Initial commit

21 files changed, 15992 insertions, 0 deletions

diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_casefolding.h b/contrib/SDL-3.2.8/src/stdlib/SDL_casefolding.h
new file mode 100644
index 0000000..6fbe0a7
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_casefolding.h
@@ -0,0 +1,2769 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+
+/*
+ * This data was generated by SDL/build-scripts/makecasefoldhashtable.pl
+ *
+ * Do not manually edit this file!
+ */
+
+#ifndef SDL_casefolding_h_
+#define SDL_casefolding_h_
+
+/* We build three simple hashmaps here: one that maps Unicode codepoints to
+a one, two, or three lowercase codepoints. To retrieve this info: look at
+case_fold_hashX, where X is 1, 2, or 3. Most foldable codepoints fold to one,
+a few dozen fold to two, and a handful fold to three. If the codepoint isn't
+in any of these hashes, it doesn't fold (no separate upper and lowercase).
+
+Almost all these codepoints fit into 16 bits, so we hash them as such to save
+memory. If a codepoint is > 0xFFFF, we have separate hashes for them,
+since there are (currently) only about 120 of them and (currently) all of them
+map to a single lowercase codepoint. */
+
+typedef struct CaseFoldMapping1_32
+{
+    Uint32 from;
+    Uint32 to0;
+} CaseFoldMapping1_32;
+
+typedef struct CaseFoldMapping1_16
+{
+    Uint16 from;
+    Uint16 to0;
+} CaseFoldMapping1_16;
+
+typedef struct CaseFoldMapping2_16
+{
+    Uint16 from;
+    Uint16 to0;
+    Uint16 to1;
+} CaseFoldMapping2_16;
+
+typedef struct CaseFoldMapping3_16
+{
+    Uint16 from;
+    Uint16 to0;
+    Uint16 to1;
+    Uint16 to2;
+} CaseFoldMapping3_16;
+
+typedef struct CaseFoldHashBucket1_16
+{
+    const CaseFoldMapping1_16 *list;
+    const Uint8 count;
+} CaseFoldHashBucket1_16;
+
+typedef struct CaseFoldHashBucket1_32
+{
+    const CaseFoldMapping1_32 *list;
+    const Uint8 count;
+} CaseFoldHashBucket1_32;
+
+typedef struct CaseFoldHashBucket2_16
+{
+    const CaseFoldMapping2_16 *list;
+    const Uint8 count;
+} CaseFoldHashBucket2_16;
+
+typedef struct CaseFoldHashBucket3_16
+{
+    const CaseFoldMapping3_16 *list;
+    const Uint8 count;
+} CaseFoldHashBucket3_16;
+
+static const CaseFoldMapping1_16 case_fold1_16_000[] = {
+    { 0x0202, 0x0203 },
+    { 0x0404, 0x0454 },
+    { 0x1E1E, 0x1E1F },
+    { 0x2C2C, 0x2C5C },
+    { 0xABAB, 0x13DB }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_001[] = {
+    { 0x0100, 0x0101 },
+    { 0x0405, 0x0455 },
+    { 0x0504, 0x0505 },
+    { 0x2C2D, 0x2C5D },
+    { 0xA7A6, 0xA7A7 },
+    { 0xABAA, 0x13DA }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_002[] = {
+    { 0x0200, 0x0201 },
+    { 0x0406, 0x0456 },
+    { 0x1E1C, 0x1E1D },
+    { 0x1F1D, 0x1F15 },
+    { 0x2C2E, 0x2C5E },
+    { 0xABA9, 0x13D9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_003[] = {
+    { 0x0102, 0x0103 },
+    { 0x0407, 0x0457 },
+    { 0x0506, 0x0507 },
+    { 0x1F1C, 0x1F14 },
+    { 0x2C2F, 0x2C5F },
+    { 0xA7A4, 0xA7A5 },
+    { 0xABA8, 0x13D8 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_004[] = {
+    { 0x0206, 0x0207 },
+    { 0x0400, 0x0450 },
+    { 0x1E1A, 0x1E1B },
+    { 0x1F1B, 0x1F13 },
+    { 0x2C28, 0x2C58 },
+    { 0xABAF, 0x13DF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_005[] = {
+    { 0x0104, 0x0105 },
+    { 0x0401, 0x0451 },
+    { 0x0500, 0x0501 },
+    { 0x1F1A, 0x1F12 },
+    { 0x2C29, 0x2C59 },
+    { 0xA7A2, 0xA7A3 },
+    { 0xABAE, 0x13DE }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_006[] = {
+    { 0x0204, 0x0205 },
+    { 0x0402, 0x0452 },
+    { 0x1E18, 0x1E19 },
+    { 0x1F19, 0x1F11 },
+    { 0x2C2A, 0x2C5A },
+    { 0xABAD, 0x13DD }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_007[] = {
+    { 0x0106, 0x0107 },
+    { 0x0403, 0x0453 },
+    { 0x0502, 0x0503 },
+    { 0x1F18, 0x1F10 },
+    { 0x2126, 0x03C9 },
+    { 0x2C2B, 0x2C5B },
+    { 0xA7A0, 0xA7A1 },
+    { 0xABAC, 0x13DC }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_008[] = {
+    { 0x020A, 0x020B },
+    { 0x040C, 0x045C },
+    { 0x1E16, 0x1E17 },
+    { 0x2C24, 0x2C54 },
+    { 0xABA3, 0x13D3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_009[] = {
+    { 0x0108, 0x0109 },
+    { 0x040D, 0x045D },
+    { 0x050C, 0x050D },
+    { 0x2C25, 0x2C55 },
+    { 0xA7AE, 0x026A },
+    { 0xABA2, 0x13D2 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_010[] = {
+    { 0x0208, 0x0209 },
+    { 0x040E, 0x045E },
+    { 0x1E14, 0x1E15 },
+    { 0x212B, 0x00E5 },
+    { 0x2C26, 0x2C56 },
+    { 0xA7AD, 0x026C },
+    { 0xABA1, 0x13D1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_011[] = {
+    { 0x010A, 0x010B },
+    { 0x040F, 0x045F },
+    { 0x050E, 0x050F },
+    { 0x212A, 0x006B },
+    { 0x2C27, 0x2C57 },
+    { 0xA7AC, 0x0261 },
+    { 0xABA0, 0x13D0 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_012[] = {
+    { 0x020E, 0x020F },
+    { 0x0408, 0x0458 },
+    { 0x1E12, 0x1E13 },
+    { 0x2C20, 0x2C50 },
+    { 0xA7AB, 0x025C },
+    { 0xABA7, 0x13D7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_013[] = {
+    { 0x010C, 0x010D },
+    { 0x0409, 0x0459 },
+    { 0x0508, 0x0509 },
+    { 0x2C21, 0x2C51 },
+    { 0xA7AA, 0x0266 },
+    { 0xABA6, 0x13D6 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_014[] = {
+    { 0x020C, 0x020D },
+    { 0x040A, 0x045A },
+    { 0x1E10, 0x1E11 },
+    { 0x2C22, 0x2C52 },
+    { 0xABA5, 0x13D5 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_015[] = {
+    { 0x010E, 0x010F },
+    { 0x040B, 0x045B },
+    { 0x050A, 0x050B },
+    { 0x2C23, 0x2C53 },
+    { 0xA7A8, 0xA7A9 },
+    { 0xABA4, 0x13D4 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_016[] = {
+    { 0x0212, 0x0213 },
+    { 0x0414, 0x0434 },
+    { 0x1E0E, 0x1E0F },
+    { 0x1F0F, 0x1F07 },
+    { 0xABBB, 0x13EB }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_017[] = {
+    { 0x0110, 0x0111 },
+    { 0x0415, 0x0435 },
+    { 0x0514, 0x0515 },
+    { 0x1F0E, 0x1F06 },
+    { 0xA7B6, 0xA7B7 },
+    { 0xABBA, 0x13EA }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_018[] = {
+    { 0x0210, 0x0211 },
+    { 0x0416, 0x0436 },
+    { 0x1E0C, 0x1E0D },
+    { 0x1F0D, 0x1F05 },
+    { 0xABB9, 0x13E9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_019[] = {
+    { 0x0112, 0x0113 },
+    { 0x0417, 0x0437 },
+    { 0x0516, 0x0517 },
+    { 0x1F0C, 0x1F04 },
+    { 0x2132, 0x214E },
+    { 0xA7B4, 0xA7B5 },
+    { 0xABB8, 0x13E8 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_020[] = {
+    { 0x0216, 0x0217 },
+    { 0x0410, 0x0430 },
+    { 0x1E0A, 0x1E0B },
+    { 0x1F0B, 0x1F03 },
+    { 0xA7B3, 0xAB53 },
+    { 0xABBF, 0x13EF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_021[] = {
+    { 0x0114, 0x0115 },
+    { 0x0411, 0x0431 },
+    { 0x0510, 0x0511 },
+    { 0x1F0A, 0x1F02 },
+    { 0xA7B2, 0x029D },
+    { 0xABBE, 0x13EE }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_022[] = {
+    { 0x0214, 0x0215 },
+    { 0x0412, 0x0432 },
+    { 0x1E08, 0x1E09 },
+    { 0x1F09, 0x1F01 },
+    { 0xA7B1, 0x0287 },
+    { 0xABBD, 0x13ED }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_023[] = {
+    { 0x0116, 0x0117 },
+    { 0x0413, 0x0433 },
+    { 0x0512, 0x0513 },
+    { 0x1F08, 0x1F00 },
+    { 0xA7B0, 0x029E },
+    { 0xABBC, 0x13EC }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_024[] = {
+    { 0x021A, 0x021B },
+    { 0x041C, 0x043C },
+    { 0x1E06, 0x1E07 },
+    { 0xABB3, 0x13E3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_025[] = {
+    { 0x0118, 0x0119 },
+    { 0x041D, 0x043D },
+    { 0x051C, 0x051D },
+    { 0xA7BE, 0xA7BF },
+    { 0xABB2, 0x13E2 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_026[] = {
+    { 0x0218, 0x0219 },
+    { 0x041E, 0x043E },
+    { 0x1E04, 0x1E05 },
+    { 0xABB1, 0x13E1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_027[] = {
+    { 0x011A, 0x011B },
+    { 0x041F, 0x043F },
+    { 0x051E, 0x051F },
+    { 0xA7BC, 0xA7BD },
+    { 0xABB0, 0x13E0 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_028[] = {
+    { 0x021E, 0x021F },
+    { 0x0418, 0x0438 },
+    { 0x1E02, 0x1E03 },
+    { 0xABB7, 0x13E7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_029[] = {
+    { 0x011C, 0x011D },
+    { 0x0419, 0x0439 },
+    { 0x0518, 0x0519 },
+    { 0xA7BA, 0xA7BB },
+    { 0xABB6, 0x13E6 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_030[] = {
+    { 0x021C, 0x021D },
+    { 0x041A, 0x043A },
+    { 0x1E00, 0x1E01 },
+    { 0xABB5, 0x13E5 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_031[] = {
+    { 0x011E, 0x011F },
+    { 0x041B, 0x043B },
+    { 0x051A, 0x051B },
+    { 0xA7B8, 0xA7B9 },
+    { 0xABB4, 0x13E4 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_032[] = {
+    { 0x0222, 0x0223 },
+    { 0x0424, 0x0444 },
+    { 0x1E3E, 0x1E3F },
+    { 0x1F3F, 0x1F37 },
+    { 0x2C0C, 0x2C3C },
+    { 0xA686, 0xA687 },
+    { 0xAB8B, 0x13BB }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_033[] = {
+    { 0x0120, 0x0121 },
+    { 0x0425, 0x0445 },
+    { 0x0524, 0x0525 },
+    { 0x1F3E, 0x1F36 },
+    { 0x2C0D, 0x2C3D },
+    { 0xA786, 0xA787 },
+    { 0xAB8A, 0x13BA }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_034[] = {
+    { 0x0220, 0x019E },
+    { 0x0426, 0x0446 },
+    { 0x1E3C, 0x1E3D },
+    { 0x1F3D, 0x1F35 },
+    { 0x2C0E, 0x2C3E },
+    { 0xA684, 0xA685 },
+    { 0xAB89, 0x13B9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_035[] = {
+    { 0x0122, 0x0123 },
+    { 0x0427, 0x0447 },
+    { 0x0526, 0x0527 },
+    { 0x1F3C, 0x1F34 },
+    { 0x2C0F, 0x2C3F },
+    { 0xA784, 0xA785 },
+    { 0xAB88, 0x13B8 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_036[] = {
+    { 0x0226, 0x0227 },
+    { 0x0420, 0x0440 },
+    { 0x1E3A, 0x1E3B },
+    { 0x1F3B, 0x1F33 },
+    { 0x2C08, 0x2C38 },
+    { 0xA682, 0xA683 },
+    { 0xAB8F, 0x13BF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_037[] = {
+    { 0x0124, 0x0125 },
+    { 0x0421, 0x0441 },
+    { 0x0520, 0x0521 },
+    { 0x1F3A, 0x1F32 },
+    { 0x2C09, 0x2C39 },
+    { 0xA782, 0xA783 },
+    { 0xAB8E, 0x13BE }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_038[] = {
+    { 0x0224, 0x0225 },
+    { 0x0422, 0x0442 },
+    { 0x1E38, 0x1E39 },
+    { 0x1F39, 0x1F31 },
+    { 0x2C0A, 0x2C3A },
+    { 0xA680, 0xA681 },
+    { 0xAB8D, 0x13BD }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_039[] = {
+    { 0x0126, 0x0127 },
+    { 0x0423, 0x0443 },
+    { 0x0522, 0x0523 },
+    { 0x1F38, 0x1F30 },
+    { 0x2C0B, 0x2C3B },
+    { 0xA780, 0xA781 },
+    { 0xAB8C, 0x13BC }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_040[] = {
+    { 0x022A, 0x022B },
+    { 0x042C, 0x044C },
+    { 0x1E36, 0x1E37 },
+    { 0x2C04, 0x2C34 },
+    { 0xA68E, 0xA68F },
+    { 0xAB83, 0x13B3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_041[] = {
+    { 0x0128, 0x0129 },
+    { 0x042D, 0x044D },
+    { 0x052C, 0x052D },
+    { 0x2C05, 0x2C35 },
+    { 0xAB82, 0x13B2 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_042[] = {
+    { 0x0228, 0x0229 },
+    { 0x042E, 0x044E },
+    { 0x1E34, 0x1E35 },
+    { 0x2C06, 0x2C36 },
+    { 0xA68C, 0xA68D },
+    { 0xA78D, 0x0265 },
+    { 0xAB81, 0x13B1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_043[] = {
+    { 0x012A, 0x012B },
+    { 0x042F, 0x044F },
+    { 0x052E, 0x052F },
+    { 0x2C07, 0x2C37 },
+    { 0xAB80, 0x13B0 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_044[] = {
+    { 0x022E, 0x022F },
+    { 0x0428, 0x0448 },
+    { 0x1E32, 0x1E33 },
+    { 0x2C00, 0x2C30 },
+    { 0xA68A, 0xA68B },
+    { 0xA78B, 0xA78C },
+    { 0xAB87, 0x13B7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_045[] = {
+    { 0x012C, 0x012D },
+    { 0x0429, 0x0449 },
+    { 0x0528, 0x0529 },
+    { 0x2C01, 0x2C31 },
+    { 0xAB86, 0x13B6 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_046[] = {
+    { 0x022C, 0x022D },
+    { 0x042A, 0x044A },
+    { 0x1E30, 0x1E31 },
+    { 0x2C02, 0x2C32 },
+    { 0xA688, 0xA689 },
+    { 0xAB85, 0x13B5 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_047[] = {
+    { 0x012E, 0x012F },
+    { 0x042B, 0x044B },
+    { 0x052A, 0x052B },
+    { 0x2C03, 0x2C33 },
+    { 0xAB84, 0x13B4 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_048[] = {
+    { 0x0232, 0x0233 },
+    { 0x0535, 0x0565 },
+    { 0x1E2E, 0x1E2F },
+    { 0x1F2F, 0x1F27 },
+    { 0x2C1C, 0x2C4C },
+    { 0xA696, 0xA697 },
+    { 0xAB9B, 0x13CB }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_049[] = {
+    { 0x0534, 0x0564 },
+    { 0x1F2E, 0x1F26 },
+    { 0x2C1D, 0x2C4D },
+    { 0xA796, 0xA797 },
+    { 0xAB9A, 0x13CA }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_050[] = {
+    { 0x0230, 0x0231 },
+    { 0x0537, 0x0567 },
+    { 0x1E2C, 0x1E2D },
+    { 0x1F2D, 0x1F25 },
+    { 0x2C1E, 0x2C4E },
+    { 0xA694, 0xA695 },
+    { 0xAB99, 0x13C9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_051[] = {
+    { 0x0132, 0x0133 },
+    { 0x0536, 0x0566 },
+    { 0x1F2C, 0x1F24 },
+    { 0x2C1F, 0x2C4F },
+    { 0xAB98, 0x13C8 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_052[] = {
+    { 0x0531, 0x0561 },
+    { 0x1E2A, 0x1E2B },
+    { 0x1F2B, 0x1F23 },
+    { 0x2C18, 0x2C48 },
+    { 0xA692, 0xA693 },
+    { 0xAB9F, 0x13CF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_053[] = {
+    { 0x0134, 0x0135 },
+    { 0x1F2A, 0x1F22 },
+    { 0x2C19, 0x2C49 },
+    { 0xA792, 0xA793 },
+    { 0xAB9E, 0x13CE }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_054[] = {
+    { 0x0533, 0x0563 },
+    { 0x1E28, 0x1E29 },
+    { 0x1F29, 0x1F21 },
+    { 0x2C1A, 0x2C4A },
+    { 0xA690, 0xA691 },
+    { 0xAB9D, 0x13CD }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_055[] = {
+    { 0x0136, 0x0137 },
+    { 0x0532, 0x0562 },
+    { 0x1F28, 0x1F20 },
+    { 0x2C1B, 0x2C4B },
+    { 0xA790, 0xA791 },
+    { 0xAB9C, 0x13CC }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_056[] = {
+    { 0x0139, 0x013A },
+    { 0x023A, 0x2C65 },
+    { 0x053D, 0x056D },
+    { 0x1E26, 0x1E27 },
+    { 0x2C14, 0x2C44 },
+    { 0xAB93, 0x13C3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_057[] = {
+    { 0x023B, 0x023C },
+    { 0x053C, 0x056C },
+    { 0x2C15, 0x2C45 },
+    { 0xA79E, 0xA79F },
+    { 0xAB92, 0x13C2 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_058[] = {
+    { 0x013B, 0x013C },
+    { 0x053F, 0x056F },
+    { 0x1E24, 0x1E25 },
+    { 0x2C16, 0x2C46 },
+    { 0xAB91, 0x13C1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_059[] = {
+    { 0x053E, 0x056E },
+    { 0x2C17, 0x2C47 },
+    { 0xA79C, 0xA79D },
+    { 0xAB90, 0x13C0 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_060[] = {
+    { 0x013D, 0x013E },
+    { 0x023E, 0x2C66 },
+    { 0x0539, 0x0569 },
+    { 0x1E22, 0x1E23 },
+    { 0x2C10, 0x2C40 },
+    { 0xA69A, 0xA69B },
+    { 0xAB97, 0x13C7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_061[] = {
+    { 0x0538, 0x0568 },
+    { 0x2C11, 0x2C41 },
+    { 0xA79A, 0xA79B },
+    { 0xAB96, 0x13C6 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_062[] = {
+    { 0x013F, 0x0140 },
+    { 0x053B, 0x056B },
+    { 0x1E20, 0x1E21 },
+    { 0x2C12, 0x2C42 },
+    { 0xA698, 0xA699 },
+    { 0xAB95, 0x13C5 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_063[] = {
+    { 0x023D, 0x019A },
+    { 0x053A, 0x056A },
+    { 0x2C13, 0x2C43 },
+    { 0xA798, 0xA799 },
+    { 0xAB94, 0x13C4 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_064[] = {
+    { 0x0141, 0x0142 },
+    { 0x0545, 0x0575 },
+    { 0x1E5E, 0x1E5F },
+    { 0x1F5F, 0x1F57 },
+    { 0x2161, 0x2171 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_065[] = {
+    { 0x0243, 0x0180 },
+    { 0x0544, 0x0574 },
+    { 0x2160, 0x2170 },
+    { 0x2C6D, 0x0251 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_066[] = {
+    { 0x0143, 0x0144 },
+    { 0x0547, 0x0577 },
+    { 0x1E5C, 0x1E5D },
+    { 0x1F5D, 0x1F55 },
+    { 0x2163, 0x2173 },
+    { 0x2C6E, 0x0271 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_067[] = {
+    { 0x0241, 0x0242 },
+    { 0x0546, 0x0576 },
+    { 0x2162, 0x2172 },
+    { 0x2C6F, 0x0250 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_068[] = {
+    { 0x0145, 0x0146 },
+    { 0x0246, 0x0247 },
+    { 0x0541, 0x0571 },
+    { 0x1E5A, 0x1E5B },
+    { 0x1F5B, 0x1F53 },
+    { 0x2165, 0x2175 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_069[] = {
+    { 0x0540, 0x0570 },
+    { 0x2164, 0x2174 },
+    { 0x2C69, 0x2C6A }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_070[] = {
+    { 0x0147, 0x0148 },
+    { 0x0244, 0x0289 },
+    { 0x0345, 0x03B9 },
+    { 0x0543, 0x0573 },
+    { 0x1E58, 0x1E59 },
+    { 0x1F59, 0x1F51 },
+    { 0x2167, 0x2177 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_071[] = {
+    { 0x0245, 0x028C },
+    { 0x0542, 0x0572 },
+    { 0x2166, 0x2176 },
+    { 0x2C6B, 0x2C6C }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_072[] = {
+    { 0x024A, 0x024B },
+    { 0x054D, 0x057D },
+    { 0x1E56, 0x1E57 },
+    { 0x2169, 0x2179 },
+    { 0x2C64, 0x027D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_073[] = {
+    { 0x054C, 0x057C },
+    { 0x2168, 0x2178 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_074[] = {
+    { 0x0248, 0x0249 },
+    { 0x054F, 0x057F },
+    { 0x1E54, 0x1E55 },
+    { 0x216B, 0x217B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_075[] = {
+    { 0x014A, 0x014B },
+    { 0x054E, 0x057E },
+    { 0x216A, 0x217A },
+    { 0x2C67, 0x2C68 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_076[] = {
+    { 0x024E, 0x024F },
+    { 0x0549, 0x0579 },
+    { 0x1E52, 0x1E53 },
+    { 0x216D, 0x217D },
+    { 0x2C60, 0x2C61 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_077[] = {
+    { 0x014C, 0x014D },
+    { 0x0548, 0x0578 },
+    { 0x216C, 0x217C }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_078[] = {
+    { 0x024C, 0x024D },
+    { 0x054B, 0x057B },
+    { 0x1E50, 0x1E51 },
+    { 0x216F, 0x217F },
+    { 0x2C62, 0x026B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_079[] = {
+    { 0x014E, 0x014F },
+    { 0x054A, 0x057A },
+    { 0x216E, 0x217E },
+    { 0x2C63, 0x1D7D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_080[] = {
+    { 0x0555, 0x0585 },
+    { 0x1E4E, 0x1E4F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_081[] = {
+    { 0x0150, 0x0151 },
+    { 0x0554, 0x0584 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_082[] = {
+    { 0x1E4C, 0x1E4D },
+    { 0x1F4D, 0x1F45 },
+    { 0x2C7E, 0x023F },
+    { 0xA7F5, 0xA7F6 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_083[] = {
+    { 0x0152, 0x0153 },
+    { 0x0556, 0x0586 },
+    { 0x1F4C, 0x1F44 },
+    { 0x2C7F, 0x0240 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_084[] = {
+    { 0x0551, 0x0581 },
+    { 0x1E4A, 0x1E4B },
+    { 0x1F4B, 0x1F43 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_085[] = {
+    { 0x0154, 0x0155 },
+    { 0x0550, 0x0580 },
+    { 0x1F4A, 0x1F42 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_086[] = {
+    { 0x0553, 0x0583 },
+    { 0x1E48, 0x1E49 },
+    { 0x1F49, 0x1F41 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_087[] = {
+    { 0x0156, 0x0157 },
+    { 0x0552, 0x0582 },
+    { 0x1F48, 0x1F40 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_088[] = {
+    { 0x1E46, 0x1E47 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_089[] = {
+    { 0x0158, 0x0159 },
+    { 0x2C75, 0x2C76 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_090[] = {
+    { 0x1E44, 0x1E45 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_091[] = {
+    { 0x015A, 0x015B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_092[] = {
+    { 0x1E42, 0x1E43 },
+    { 0x2C70, 0x0252 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_093[] = {
+    { 0x015C, 0x015D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_094[] = {
+    { 0x1E40, 0x1E41 },
+    { 0x2C72, 0x2C73 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_095[] = {
+    { 0x015E, 0x015F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_096[] = {
+    { 0x0464, 0x0465 },
+    { 0x1E7E, 0x1E7F },
+    { 0xA7C7, 0xA7C8 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_097[] = {
+    { 0x0160, 0x0161 },
+    { 0xA7C6, 0x1D8E }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_098[] = {
+    { 0x0466, 0x0467 },
+    { 0x1E7C, 0x1E7D },
+    { 0xA7C5, 0x0282 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_099[] = {
+    { 0x0162, 0x0163 },
+    { 0xA7C4, 0xA794 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_100[] = {
+    { 0x0460, 0x0461 },
+    { 0x1E7A, 0x1E7B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_101[] = {
+    { 0x0164, 0x0165 },
+    { 0xA7C2, 0xA7C3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_102[] = {
+    { 0x0462, 0x0463 },
+    { 0x1E78, 0x1E79 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_103[] = {
+    { 0x0166, 0x0167 },
+    { 0xA7C0, 0xA7C1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_104[] = {
+    { 0x046C, 0x046D },
+    { 0x1E76, 0x1E77 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_105[] = {
+    { 0x0168, 0x0169 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_106[] = {
+    { 0x046E, 0x046F },
+    { 0x1E74, 0x1E75 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_107[] = {
+    { 0x016A, 0x016B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_108[] = {
+    { 0x0468, 0x0469 },
+    { 0x1E72, 0x1E73 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_109[] = {
+    { 0x016C, 0x016D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_110[] = {
+    { 0x046A, 0x046B },
+    { 0x1E70, 0x1E71 },
+    { 0xA7C9, 0xA7CA }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_111[] = {
+    { 0x016E, 0x016F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_112[] = {
+    { 0x0474, 0x0475 },
+    { 0x1E6E, 0x1E6F },
+    { 0x1F6F, 0x1F67 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_113[] = {
+    { 0x0170, 0x0171 },
+    { 0x0372, 0x0373 },
+    { 0x1F6E, 0x1F66 },
+    { 0xA7D6, 0xA7D7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_114[] = {
+    { 0x0476, 0x0477 },
+    { 0x1E6C, 0x1E6D },
+    { 0x1F6D, 0x1F65 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_115[] = {
+    { 0x0172, 0x0173 },
+    { 0x0370, 0x0371 },
+    { 0x1F6C, 0x1F64 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_116[] = {
+    { 0x0470, 0x0471 },
+    { 0x1E6A, 0x1E6B },
+    { 0x1F6B, 0x1F63 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_117[] = {
+    { 0x0174, 0x0175 },
+    { 0x0376, 0x0377 },
+    { 0x1F6A, 0x1F62 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_118[] = {
+    { 0x0472, 0x0473 },
+    { 0x1E68, 0x1E69 },
+    { 0x1F69, 0x1F61 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_119[] = {
+    { 0x0176, 0x0177 },
+    { 0x1F68, 0x1F60 },
+    { 0xA7D0, 0xA7D1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_120[] = {
+    { 0x0179, 0x017A },
+    { 0x047C, 0x047D },
+    { 0x1E66, 0x1E67 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_121[] = {
+    { 0x0178, 0x00FF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_122[] = {
+    { 0x017B, 0x017C },
+    { 0x047E, 0x047F },
+    { 0x1E64, 0x1E65 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_124[] = {
+    { 0x017D, 0x017E },
+    { 0x037F, 0x03F3 },
+    { 0x0478, 0x0479 },
+    { 0x1E62, 0x1E63 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_126[] = {
+    { 0x017F, 0x0073 },
+    { 0x047A, 0x047B },
+    { 0x1E60, 0x1E61 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_127[] = {
+    { 0xA7D8, 0xA7D9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_128[] = {
+    { 0x0181, 0x0253 },
+    { 0x1C9C, 0x10DC },
+    { 0x2CAC, 0x2CAD }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_129[] = {
+    { 0x1C9D, 0x10DD },
+    { 0xA726, 0xA727 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_130[] = {
+    { 0x1C9E, 0x10DE },
+    { 0x2CAE, 0x2CAF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_131[] = {
+    { 0x0182, 0x0183 },
+    { 0x1C9F, 0x10DF },
+    { 0xA724, 0xA725 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_132[] = {
+    { 0x0480, 0x0481 },
+    { 0x1C98, 0x10D8 },
+    { 0x2CA8, 0x2CA9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_133[] = {
+    { 0x0184, 0x0185 },
+    { 0x0386, 0x03AC },
+    { 0x1C99, 0x10D9 },
+    { 0x1E9B, 0x1E61 },
+    { 0xA722, 0xA723 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_134[] = {
+    { 0x0187, 0x0188 },
+    { 0x1C9A, 0x10DA },
+    { 0x2CAA, 0x2CAB }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_135[] = {
+    { 0x0186, 0x0254 },
+    { 0x1C9B, 0x10DB }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_136[] = {
+    { 0x0189, 0x0256 },
+    { 0x048C, 0x048D },
+    { 0x1C94, 0x10D4 },
+    { 0x2CA4, 0x2CA5 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_137[] = {
+    { 0x038A, 0x03AF },
+    { 0x1C95, 0x10D5 },
+    { 0xA72E, 0xA72F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_138[] = {
+    { 0x018B, 0x018C },
+    { 0x0389, 0x03AE },
+    { 0x048E, 0x048F },
+    { 0x1C96, 0x10D6 },
+    { 0x1E94, 0x1E95 },
+    { 0x2CA6, 0x2CA7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_139[] = {
+    { 0x018A, 0x0257 },
+    { 0x0388, 0x03AD },
+    { 0x1C97, 0x10D7 },
+    { 0xA72C, 0xA72D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_140[] = {
+    { 0x038F, 0x03CE },
+    { 0x1C90, 0x10D0 },
+    { 0x1E92, 0x1E93 },
+    { 0x2CA0, 0x2CA1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_141[] = {
+    { 0x038E, 0x03CD },
+    { 0x1C91, 0x10D1 },
+    { 0xA72A, 0xA72B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_142[] = {
+    { 0x018F, 0x0259 },
+    { 0x048A, 0x048B },
+    { 0x1C92, 0x10D2 },
+    { 0x1E90, 0x1E91 },
+    { 0x2CA2, 0x2CA3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_143[] = {
+    { 0x018E, 0x01DD },
+    { 0x038C, 0x03CC },
+    { 0x1C93, 0x10D3 },
+    { 0xA728, 0xA729 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_144[] = {
+    { 0x0191, 0x0192 },
+    { 0x0393, 0x03B3 },
+    { 0x0494, 0x0495 },
+    { 0x1E8E, 0x1E8F },
+    { 0x2CBC, 0x2CBD }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_145[] = {
+    { 0x0190, 0x025B },
+    { 0x0392, 0x03B2 },
+    { 0xA736, 0xA737 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_146[] = {
+    { 0x0193, 0x0260 },
+    { 0x0391, 0x03B1 },
+    { 0x0496, 0x0497 },
+    { 0x1E8C, 0x1E8D },
+    { 0x24B6, 0x24D0 },
+    { 0x2CBE, 0x2CBF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_147[] = {
+    { 0x24B7, 0x24D1 },
+    { 0xA734, 0xA735 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_148[] = {
+    { 0x0397, 0x03B7 },
+    { 0x0490, 0x0491 },
+    { 0x1C88, 0xA64B },
+    { 0x1E8A, 0x1E8B },
+    { 0x2CB8, 0x2CB9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_149[] = {
+    { 0x0194, 0x0263 },
+    { 0x0396, 0x03B6 },
+    { 0xA732, 0xA733 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_150[] = {
+    { 0x0197, 0x0268 },
+    { 0x0395, 0x03B5 },
+    { 0x0492, 0x0493 },
+    { 0x1E88, 0x1E89 },
+    { 0x2CBA, 0x2CBB }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_151[] = {
+    { 0x0196, 0x0269 },
+    { 0x0394, 0x03B4 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_152[] = {
+    { 0x039B, 0x03BB },
+    { 0x049C, 0x049D },
+    { 0x1C84, 0x0442 },
+    { 0x1E86, 0x1E87 },
+    { 0x24BC, 0x24D6 },
+    { 0x2CB4, 0x2CB5 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_153[] = {
+    { 0x0198, 0x0199 },
+    { 0x039A, 0x03BA },
+    { 0x1C85, 0x0442 },
+    { 0x24BD, 0x24D7 },
+    { 0xA73E, 0xA73F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_154[] = {
+    { 0x0399, 0x03B9 },
+    { 0x049E, 0x049F },
+    { 0x1C86, 0x044A },
+    { 0x1E84, 0x1E85 },
+    { 0x24BE, 0x24D8 },
+    { 0x2CB6, 0x2CB7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_155[] = {
+    { 0x0398, 0x03B8 },
+    { 0x1C87, 0x0463 },
+    { 0x24BF, 0x24D9 },
+    { 0xA73C, 0xA73D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_156[] = {
+    { 0x019D, 0x0272 },
+    { 0x039F, 0x03BF },
+    { 0x0498, 0x0499 },
+    { 0x1C80, 0x0432 },
+    { 0x1E82, 0x1E83 },
+    { 0x24B8, 0x24D2 },
+    { 0x2CB0, 0x2CB1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_157[] = {
+    { 0x019C, 0x026F },
+    { 0x039E, 0x03BE },
+    { 0x1C81, 0x0434 },
+    { 0x24B9, 0x24D3 },
+    { 0xA73A, 0xA73B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_158[] = {
+    { 0x019F, 0x0275 },
+    { 0x039D, 0x03BD },
+    { 0x049A, 0x049B },
+    { 0x1C82, 0x043E },
+    { 0x1E80, 0x1E81 },
+    { 0x24BA, 0x24D4 },
+    { 0x2CB2, 0x2CB3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_159[] = {
+    { 0x039C, 0x03BC },
+    { 0x1C83, 0x0441 },
+    { 0x24BB, 0x24D5 },
+    { 0xA738, 0xA739 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_160[] = {
+    { 0x03A3, 0x03C3 },
+    { 0x04A4, 0x04A5 },
+    { 0x10B0, 0x2D10 },
+    { 0x1EBE, 0x1EBF },
+    { 0x2C8C, 0x2C8D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_161[] = {
+    { 0x01A0, 0x01A1 },
+    { 0x10B1, 0x2D11 },
+    { 0x1CBD, 0x10FD },
+    { 0x1FBE, 0x03B9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_162[] = {
+    { 0x03A1, 0x03C1 },
+    { 0x04A6, 0x04A7 },
+    { 0x10B2, 0x2D12 },
+    { 0x1CBE, 0x10FE },
+    { 0x1EBC, 0x1EBD },
+    { 0x2183, 0x2184 },
+    { 0x2C8E, 0x2C8F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_163[] = {
+    { 0x01A2, 0x01A3 },
+    { 0x03A0, 0x03C0 },
+    { 0x10B3, 0x2D13 },
+    { 0x1CBF, 0x10FF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_164[] = {
+    { 0x03A7, 0x03C7 },
+    { 0x04A0, 0x04A1 },
+    { 0x10B4, 0x2D14 },
+    { 0x1CB8, 0x10F8 },
+    { 0x1EBA, 0x1EBB },
+    { 0x1FBB, 0x1F71 },
+    { 0x2C88, 0x2C89 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_165[] = {
+    { 0x01A4, 0x01A5 },
+    { 0x03A6, 0x03C6 },
+    { 0x10B5, 0x2D15 },
+    { 0x1CB9, 0x10F9 },
+    { 0x1FBA, 0x1F70 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_166[] = {
+    { 0x01A7, 0x01A8 },
+    { 0x03A5, 0x03C5 },
+    { 0x04A2, 0x04A3 },
+    { 0x10B6, 0x2D16 },
+    { 0x1CBA, 0x10FA },
+    { 0x1EB8, 0x1EB9 },
+    { 0x1FB9, 0x1FB1 },
+    { 0x2C8A, 0x2C8B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_167[] = {
+    { 0x01A6, 0x0280 },
+    { 0x03A4, 0x03C4 },
+    { 0x10B7, 0x2D17 },
+    { 0x1FB8, 0x1FB0 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_168[] = {
+    { 0x01A9, 0x0283 },
+    { 0x03AB, 0x03CB },
+    { 0x04AC, 0x04AD },
+    { 0x10B8, 0x2D18 },
+    { 0x1CB4, 0x10F4 },
+    { 0x1EB6, 0x1EB7 },
+    { 0x2C84, 0x2C85 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_169[] = {
+    { 0x03AA, 0x03CA },
+    { 0x10B9, 0x2D19 },
+    { 0x1CB5, 0x10F5 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_170[] = {
+    { 0x03A9, 0x03C9 },
+    { 0x04AE, 0x04AF },
+    { 0x10BA, 0x2D1A },
+    { 0x1CB6, 0x10F6 },
+    { 0x1EB4, 0x1EB5 },
+    { 0x2C86, 0x2C87 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_171[] = {
+    { 0x03A8, 0x03C8 },
+    { 0x10BB, 0x2D1B },
+    { 0x1CB7, 0x10F7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_172[] = {
+    { 0x04A8, 0x04A9 },
+    { 0x10BC, 0x2D1C },
+    { 0x1CB0, 0x10F0 },
+    { 0x1EB2, 0x1EB3 },
+    { 0x2C80, 0x2C81 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_173[] = {
+    { 0x01AC, 0x01AD },
+    { 0x10BD, 0x2D1D },
+    { 0x1CB1, 0x10F1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_174[] = {
+    { 0x01AF, 0x01B0 },
+    { 0x04AA, 0x04AB },
+    { 0x10BE, 0x2D1E },
+    { 0x1CB2, 0x10F2 },
+    { 0x1EB0, 0x1EB1 },
+    { 0x2C82, 0x2C83 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_175[] = {
+    { 0x01AE, 0x0288 },
+    { 0x10BF, 0x2D1F },
+    { 0x1CB3, 0x10F3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_176[] = {
+    { 0x01B1, 0x028A },
+    { 0x04B4, 0x04B5 },
+    { 0x10A0, 0x2D00 },
+    { 0x1CAC, 0x10EC },
+    { 0x1EAE, 0x1EAF },
+    { 0x2C9C, 0x2C9D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_177[] = {
+    { 0x10A1, 0x2D01 },
+    { 0x1CAD, 0x10ED }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_178[] = {
+    { 0x01B3, 0x01B4 },
+    { 0x04B6, 0x04B7 },
+    { 0x10A2, 0x2D02 },
+    { 0x1CAE, 0x10EE },
+    { 0x1EAC, 0x1EAD },
+    { 0x2C9E, 0x2C9F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_179[] = {
+    { 0x01B2, 0x028B },
+    { 0x10A3, 0x2D03 },
+    { 0x1CAF, 0x10EF }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_180[] = {
+    { 0x01B5, 0x01B6 },
+    { 0x04B0, 0x04B1 },
+    { 0x10A4, 0x2D04 },
+    { 0x1CA8, 0x10E8 },
+    { 0x1EAA, 0x1EAB },
+    { 0x2C98, 0x2C99 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_181[] = {
+    { 0x00B5, 0x03BC },
+    { 0x10A5, 0x2D05 },
+    { 0x1CA9, 0x10E9 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_182[] = {
+    { 0x01B7, 0x0292 },
+    { 0x04B2, 0x04B3 },
+    { 0x10A6, 0x2D06 },
+    { 0x1CAA, 0x10EA },
+    { 0x1EA8, 0x1EA9 },
+    { 0x2C9A, 0x2C9B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_183[] = {
+    { 0x10A7, 0x2D07 },
+    { 0x1CAB, 0x10EB }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_184[] = {
+    { 0x04BC, 0x04BD },
+    { 0x10A8, 0x2D08 },
+    { 0x1CA4, 0x10E4 },
+    { 0x1EA6, 0x1EA7 },
+    { 0x2C94, 0x2C95 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_185[] = {
+    { 0x01B8, 0x01B9 },
+    { 0x10A9, 0x2D09 },
+    { 0x1CA5, 0x10E5 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_186[] = {
+    { 0x04BE, 0x04BF },
+    { 0x10AA, 0x2D0A },
+    { 0x1CA6, 0x10E6 },
+    { 0x1EA4, 0x1EA5 },
+    { 0x2C96, 0x2C97 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_187[] = {
+    { 0x10AB, 0x2D0B },
+    { 0x1CA7, 0x10E7 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_188[] = {
+    { 0x04B8, 0x04B9 },
+    { 0x10AC, 0x2D0C },
+    { 0x1CA0, 0x10E0 },
+    { 0x1EA2, 0x1EA3 },
+    { 0x2C90, 0x2C91 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_189[] = {
+    { 0x01BC, 0x01BD },
+    { 0x10AD, 0x2D0D },
+    { 0x1CA1, 0x10E1 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_190[] = {
+    { 0x04BA, 0x04BB },
+    { 0x10AE, 0x2D0E },
+    { 0x1CA2, 0x10E2 },
+    { 0x1EA0, 0x1EA1 },
+    { 0x2C92, 0x2C93 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_191[] = {
+    { 0x10AF, 0x2D0F },
+    { 0x1CA3, 0x10E3 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_192[] = {
+    { 0x00C0, 0x00E0 },
+    { 0x1EDE, 0x1EDF },
+    { 0xA666, 0xA667 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_193[] = {
+    { 0x00C1, 0x00E1 },
+    { 0x03C2, 0x03C3 },
+    { 0x04C5, 0x04C6 },
+    { 0x2CED, 0x2CEE },
+    { 0xA766, 0xA767 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_194[] = {
+    { 0x00C2, 0x00E2 },
+    { 0x1EDC, 0x1EDD },
+    { 0xA664, 0xA665 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_195[] = {
+    { 0x00C3, 0x00E3 },
+    { 0x04C7, 0x04C8 },
+    { 0xA764, 0xA765 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_196[] = {
+    { 0x00C4, 0x00E4 },
+    { 0x01C5, 0x01C6 },
+    { 0x04C0, 0x04CF },
+    { 0x1EDA, 0x1EDB },
+    { 0x1FDB, 0x1F77 },
+    { 0xA662, 0xA663 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_197[] = {
+    { 0x00C5, 0x00E5 },
+    { 0x01C4, 0x01C6 },
+    { 0x04C1, 0x04C2 },
+    { 0x1FDA, 0x1F76 },
+    { 0xA762, 0xA763 },
+    { 0xFF3A, 0xFF5A }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_198[] = {
+    { 0x00C6, 0x00E6 },
+    { 0x01C7, 0x01C9 },
+    { 0x1ED8, 0x1ED9 },
+    { 0x1FD9, 0x1FD1 },
+    { 0xA660, 0xA661 },
+    { 0xFF39, 0xFF59 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_199[] = {
+    { 0x00C7, 0x00E7 },
+    { 0x04C3, 0x04C4 },
+    { 0x1FD8, 0x1FD0 },
+    { 0x2CEB, 0x2CEC },
+    { 0xA760, 0xA761 },
+    { 0xFF38, 0xFF58 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_200[] = {
+    { 0x00C8, 0x00E8 },
+    { 0x1ED6, 0x1ED7 },
+    { 0xFF37, 0xFF57 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_201[] = {
+    { 0x00C9, 0x00E9 },
+    { 0x01C8, 0x01C9 },
+    { 0x04CD, 0x04CE },
+    { 0xA76E, 0xA76F },
+    { 0xFF36, 0xFF56 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_202[] = {
+    { 0x00CA, 0x00EA },
+    { 0x01CB, 0x01CC },
+    { 0x1ED4, 0x1ED5 },
+    { 0xA66C, 0xA66D },
+    { 0xFF35, 0xFF55 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_203[] = {
+    { 0x00CB, 0x00EB },
+    { 0x01CA, 0x01CC },
+    { 0xA76C, 0xA76D },
+    { 0xFF34, 0xFF54 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_204[] = {
+    { 0x00CC, 0x00EC },
+    { 0x01CD, 0x01CE },
+    { 0x03CF, 0x03D7 },
+    { 0x1ED2, 0x1ED3 },
+    { 0x2CE0, 0x2CE1 },
+    { 0xA66A, 0xA66B },
+    { 0xFF33, 0xFF53 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_205[] = {
+    { 0x00CD, 0x00ED },
+    { 0x04C9, 0x04CA },
+    { 0xA76A, 0xA76B },
+    { 0xFF32, 0xFF52 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_206[] = {
+    { 0x00CE, 0x00EE },
+    { 0x01CF, 0x01D0 },
+    { 0x1ED0, 0x1ED1 },
+    { 0x2CE2, 0x2CE3 },
+    { 0xA668, 0xA669 },
+    { 0xFF31, 0xFF51 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_207[] = {
+    { 0x00CF, 0x00EF },
+    { 0x04CB, 0x04CC },
+    { 0xA768, 0xA769 },
+    { 0xFF30, 0xFF50 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_208[] = {
+    { 0x00D0, 0x00F0 },
+    { 0x01D1, 0x01D2 },
+    { 0x04D4, 0x04D5 },
+    { 0x10C0, 0x2D20 },
+    { 0x1ECE, 0x1ECF },
+    { 0xAB7B, 0x13AB },
+    { 0xFF2F, 0xFF4F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_209[] = {
+    { 0x00D1, 0x00F1 },
+    { 0x10C1, 0x2D21 },
+    { 0xAB7A, 0x13AA },
+    { 0xFF2E, 0xFF4E }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_210[] = {
+    { 0x00D2, 0x00F2 },
+    { 0x01D3, 0x01D4 },
+    { 0x03D1, 0x03B8 },
+    { 0x04D6, 0x04D7 },
+    { 0x10C2, 0x2D22 },
+    { 0x1ECC, 0x1ECD },
+    { 0xAB79, 0x13A9 },
+    { 0xFF2D, 0xFF4D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_211[] = {
+    { 0x00D3, 0x00F3 },
+    { 0x03D0, 0x03B2 },
+    { 0x10C3, 0x2D23 },
+    { 0xAB78, 0x13A8 },
+    { 0xFF2C, 0xFF4C }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_212[] = {
+    { 0x00D4, 0x00F4 },
+    { 0x01D5, 0x01D6 },
+    { 0x04D0, 0x04D1 },
+    { 0x10C4, 0x2D24 },
+    { 0x1ECA, 0x1ECB },
+    { 0x1FCB, 0x1F75 },
+    { 0xAB7F, 0x13AF },
+    { 0xFF2B, 0xFF4B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_213[] = {
+    { 0x00D5, 0x00F5 },
+    { 0x03D6, 0x03C0 },
+    { 0x10C5, 0x2D25 },
+    { 0x1FCA, 0x1F74 },
+    { 0xAB7E, 0x13AE },
+    { 0xFF2A, 0xFF4A }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_214[] = {
+    { 0x00D6, 0x00F6 },
+    { 0x01D7, 0x01D8 },
+    { 0x03D5, 0x03C6 },
+    { 0x04D2, 0x04D3 },
+    { 0x1EC8, 0x1EC9 },
+    { 0x1FC9, 0x1F73 },
+    { 0xAB7D, 0x13AD },
+    { 0xFF29, 0xFF49 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_215[] = {
+    { 0x10C7, 0x2D27 },
+    { 0x1FC8, 0x1F72 },
+    { 0xAB7C, 0x13AC },
+    { 0xFF28, 0xFF48 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_216[] = {
+    { 0x00D8, 0x00F8 },
+    { 0x01D9, 0x01DA },
+    { 0x04DC, 0x04DD },
+    { 0x1EC6, 0x1EC7 },
+    { 0xAB73, 0x13A3 },
+    { 0xFF27, 0xFF47 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_217[] = {
+    { 0x00D9, 0x00F9 },
+    { 0x03DA, 0x03DB },
+    { 0xA77E, 0xA77F },
+    { 0xAB72, 0x13A2 },
+    { 0xFF26, 0xFF46 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_218[] = {
+    { 0x00DA, 0x00FA },
+    { 0x01DB, 0x01DC },
+    { 0x04DE, 0x04DF },
+    { 0x1EC4, 0x1EC5 },
+    { 0xA77D, 0x1D79 },
+    { 0xAB71, 0x13A1 },
+    { 0xFF25, 0xFF45 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_219[] = {
+    { 0x00DB, 0x00FB },
+    { 0x03D8, 0x03D9 },
+    { 0xAB70, 0x13A0 },
+    { 0xFF24, 0xFF44 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_220[] = {
+    { 0x00DC, 0x00FC },
+    { 0x04D8, 0x04D9 },
+    { 0x1EC2, 0x1EC3 },
+    { 0xA77B, 0xA77C },
+    { 0xAB77, 0x13A7 },
+    { 0xFF23, 0xFF43 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_221[] = {
+    { 0x00DD, 0x00FD },
+    { 0x03DE, 0x03DF },
+    { 0x10CD, 0x2D2D },
+    { 0xAB76, 0x13A6 },
+    { 0xFF22, 0xFF42 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_222[] = {
+    { 0x00DE, 0x00FE },
+    { 0x04DA, 0x04DB },
+    { 0x1EC0, 0x1EC1 },
+    { 0x2CF2, 0x2CF3 },
+    { 0xA779, 0xA77A },
+    { 0xAB75, 0x13A5 },
+    { 0xFF21, 0xFF41 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_223[] = {
+    { 0x01DE, 0x01DF },
+    { 0x03DC, 0x03DD },
+    { 0xAB74, 0x13A4 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_224[] = {
+    { 0x04E4, 0x04E5 },
+    { 0x1EFE, 0x1EFF },
+    { 0x24C4, 0x24DE },
+    { 0x2CCC, 0x2CCD },
+    { 0xA646, 0xA647 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_225[] = {
+    { 0x01E0, 0x01E1 },
+    { 0x03E2, 0x03E3 },
+    { 0x24C5, 0x24DF },
+    { 0xA746, 0xA747 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_226[] = {
+    { 0x04E6, 0x04E7 },
+    { 0x1EFC, 0x1EFD },
+    { 0x24C6, 0x24E0 },
+    { 0x2CCE, 0x2CCF },
+    { 0xA644, 0xA645 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_227[] = {
+    { 0x01E2, 0x01E3 },
+    { 0x03E0, 0x03E1 },
+    { 0x24C7, 0x24E1 },
+    { 0xA744, 0xA745 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_228[] = {
+    { 0x04E0, 0x04E1 },
+    { 0x1EFA, 0x1EFB },
+    { 0x1FFB, 0x1F7D },
+    { 0x24C0, 0x24DA },
+    { 0x2CC8, 0x2CC9 },
+    { 0xA642, 0xA643 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_229[] = {
+    { 0x01E4, 0x01E5 },
+    { 0x03E6, 0x03E7 },
+    { 0x1FFA, 0x1F7C },
+    { 0x24C1, 0x24DB },
+    { 0xA742, 0xA743 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_230[] = {
+    { 0x04E2, 0x04E3 },
+    { 0x1EF8, 0x1EF9 },
+    { 0x1FF9, 0x1F79 },
+    { 0x24C2, 0x24DC },
+    { 0x2CCA, 0x2CCB },
+    { 0xA640, 0xA641 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_231[] = {
+    { 0x01E6, 0x01E7 },
+    { 0x03E4, 0x03E5 },
+    { 0x1FF8, 0x1F78 },
+    { 0x24C3, 0x24DD },
+    { 0xA740, 0xA741 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_232[] = {
+    { 0x04EC, 0x04ED },
+    { 0x13FB, 0x13F3 },
+    { 0x1EF6, 0x1EF7 },
+    { 0x24CC, 0x24E6 },
+    { 0x2CC4, 0x2CC5 },
+    { 0xA64E, 0xA64F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_233[] = {
+    { 0x01E8, 0x01E9 },
+    { 0x03EA, 0x03EB },
+    { 0x13FA, 0x13F2 },
+    { 0x24CD, 0x24E7 },
+    { 0xA74E, 0xA74F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_234[] = {
+    { 0x04EE, 0x04EF },
+    { 0x13F9, 0x13F1 },
+    { 0x1EF4, 0x1EF5 },
+    { 0x24CE, 0x24E8 },
+    { 0x2CC6, 0x2CC7 },
+    { 0xA64C, 0xA64D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_235[] = {
+    { 0x01EA, 0x01EB },
+    { 0x03E8, 0x03E9 },
+    { 0x13F8, 0x13F0 },
+    { 0x24CF, 0x24E9 },
+    { 0xA74C, 0xA74D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_236[] = {
+    { 0x04E8, 0x04E9 },
+    { 0x1EF2, 0x1EF3 },
+    { 0x24C8, 0x24E2 },
+    { 0x2CC0, 0x2CC1 },
+    { 0xA64A, 0xA64B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_237[] = {
+    { 0x01EC, 0x01ED },
+    { 0x03EE, 0x03EF },
+    { 0x24C9, 0x24E3 },
+    { 0xA74A, 0xA74B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_238[] = {
+    { 0x04EA, 0x04EB },
+    { 0x13FD, 0x13F5 },
+    { 0x1EF0, 0x1EF1 },
+    { 0x24CA, 0x24E4 },
+    { 0x2CC2, 0x2CC3 },
+    { 0xA648, 0xA649 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_239[] = {
+    { 0x01EE, 0x01EF },
+    { 0x03EC, 0x03ED },
+    { 0x13FC, 0x13F4 },
+    { 0x24CB, 0x24E5 },
+    { 0xA748, 0xA749 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_240[] = {
+    { 0x01F1, 0x01F3 },
+    { 0x04F4, 0x04F5 },
+    { 0x1EEE, 0x1EEF },
+    { 0x2CDC, 0x2CDD },
+    { 0xA656, 0xA657 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_241[] = {
+    { 0xA756, 0xA757 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_242[] = {
+    { 0x03F1, 0x03C1 },
+    { 0x04F6, 0x04F7 },
+    { 0x1EEC, 0x1EED },
+    { 0x2CDE, 0x2CDF },
+    { 0xA654, 0xA655 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_243[] = {
+    { 0x01F2, 0x01F3 },
+    { 0x03F0, 0x03BA },
+    { 0x1FEC, 0x1FE5 },
+    { 0xA754, 0xA755 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_244[] = {
+    { 0x03F7, 0x03F8 },
+    { 0x04F0, 0x04F1 },
+    { 0x1EEA, 0x1EEB },
+    { 0x1FEB, 0x1F7B },
+    { 0x2CD8, 0x2CD9 },
+    { 0xA652, 0xA653 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_245[] = {
+    { 0x01F4, 0x01F5 },
+    { 0x1FEA, 0x1F7A },
+    { 0xA752, 0xA753 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_246[] = {
+    { 0x01F7, 0x01BF },
+    { 0x03F5, 0x03B5 },
+    { 0x04F2, 0x04F3 },
+    { 0x1EE8, 0x1EE9 },
+    { 0x1FE9, 0x1FE1 },
+    { 0x2CDA, 0x2CDB },
+    { 0xA650, 0xA651 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_247[] = {
+    { 0x01F6, 0x0195 },
+    { 0x03F4, 0x03B8 },
+    { 0x1FE8, 0x1FE0 },
+    { 0xA750, 0xA751 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_248[] = {
+    { 0x04FC, 0x04FD },
+    { 0x1EE6, 0x1EE7 },
+    { 0x2CD4, 0x2CD5 },
+    { 0xA65E, 0xA65F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_249[] = {
+    { 0x01F8, 0x01F9 },
+    { 0x03FA, 0x03FB },
+    { 0xA75E, 0xA75F }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_250[] = {
+    { 0x03F9, 0x03F2 },
+    { 0x04FE, 0x04FF },
+    { 0x1EE4, 0x1EE5 },
+    { 0x2CD6, 0x2CD7 },
+    { 0xA65C, 0xA65D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_251[] = {
+    { 0x01FA, 0x01FB },
+    { 0xA75C, 0xA75D }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_252[] = {
+    { 0x03FF, 0x037D },
+    { 0x04F8, 0x04F9 },
+    { 0x1EE2, 0x1EE3 },
+    { 0x2CD0, 0x2CD1 },
+    { 0xA65A, 0xA65B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_253[] = {
+    { 0x01FC, 0x01FD },
+    { 0x03FE, 0x037C },
+    { 0xA75A, 0xA75B }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_254[] = {
+    { 0x03FD, 0x037B },
+    { 0x04FA, 0x04FB },
+    { 0x1EE0, 0x1EE1 },
+    { 0x2CD2, 0x2CD3 },
+    { 0xA658, 0xA659 }
+};
+
+static const CaseFoldMapping1_16 case_fold1_16_255[] = {
+    { 0x01FE, 0x01FF },
+    { 0xA758, 0xA759 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_000[] = {
+    { 0x10404, 0x1042C },
+    { 0x10414, 0x1043C },
+    { 0x10424, 0x1044C },
+    { 0x104B4, 0x104DC },
+    { 0x104C4, 0x104EC },
+    { 0x10575, 0x1059C },
+    { 0x10585, 0x105AC },
+    { 0x10595, 0x105BC },
+    { 0x10C8C, 0x10CCC },
+    { 0x10C9C, 0x10CDC },
+    { 0x10CAC, 0x10CEC },
+    { 0x118A8, 0x118C8 },
+    { 0x118B8, 0x118D8 },
+    { 0x16E4E, 0x16E6E },
+    { 0x16E5E, 0x16E7E },
+    { 0x1E909, 0x1E92B },
+    { 0x1E919, 0x1E93B }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_001[] = {
+    { 0x10405, 0x1042D },
+    { 0x10415, 0x1043D },
+    { 0x10425, 0x1044D },
+    { 0x104B5, 0x104DD },
+    { 0x104C5, 0x104ED },
+    { 0x10574, 0x1059B },
+    { 0x10584, 0x105AB },
+    { 0x10594, 0x105BB },
+    { 0x10C8D, 0x10CCD },
+    { 0x10C9D, 0x10CDD },
+    { 0x10CAD, 0x10CED },
+    { 0x118A9, 0x118C9 },
+    { 0x118B9, 0x118D9 },
+    { 0x16E4F, 0x16E6F },
+    { 0x16E5F, 0x16E7F },
+    { 0x1E908, 0x1E92A },
+    { 0x1E918, 0x1E93A }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_002[] = {
+    { 0x10406, 0x1042E },
+    { 0x10416, 0x1043E },
+    { 0x10426, 0x1044E },
+    { 0x104B6, 0x104DE },
+    { 0x104C6, 0x104EE },
+    { 0x10577, 0x1059E },
+    { 0x10587, 0x105AE },
+    { 0x10C8E, 0x10CCE },
+    { 0x10C9E, 0x10CDE },
+    { 0x10CAE, 0x10CEE },
+    { 0x118AA, 0x118CA },
+    { 0x118BA, 0x118DA },
+    { 0x16E4C, 0x16E6C },
+    { 0x16E5C, 0x16E7C },
+    { 0x1E90B, 0x1E92D },
+    { 0x1E91B, 0x1E93D }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_003[] = {
+    { 0x10407, 0x1042F },
+    { 0x10417, 0x1043F },
+    { 0x10427, 0x1044F },
+    { 0x104B7, 0x104DF },
+    { 0x104C7, 0x104EF },
+    { 0x10576, 0x1059D },
+    { 0x10586, 0x105AD },
+    { 0x10C8F, 0x10CCF },
+    { 0x10C9F, 0x10CDF },
+    { 0x10CAF, 0x10CEF },
+    { 0x118AB, 0x118CB },
+    { 0x118BB, 0x118DB },
+    { 0x16E4D, 0x16E6D },
+    { 0x16E5D, 0x16E7D },
+    { 0x1E90A, 0x1E92C },
+    { 0x1E91A, 0x1E93C }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_004[] = {
+    { 0x10400, 0x10428 },
+    { 0x10410, 0x10438 },
+    { 0x10420, 0x10448 },
+    { 0x104B0, 0x104D8 },
+    { 0x104C0, 0x104E8 },
+    { 0x104D0, 0x104F8 },
+    { 0x10571, 0x10598 },
+    { 0x10581, 0x105A8 },
+    { 0x10591, 0x105B8 },
+    { 0x10C88, 0x10CC8 },
+    { 0x10C98, 0x10CD8 },
+    { 0x10CA8, 0x10CE8 },
+    { 0x118AC, 0x118CC },
+    { 0x118BC, 0x118DC },
+    { 0x16E4A, 0x16E6A },
+    { 0x16E5A, 0x16E7A },
+    { 0x1E90D, 0x1E92F },
+    { 0x1E91D, 0x1E93F }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_005[] = {
+    { 0x10401, 0x10429 },
+    { 0x10411, 0x10439 },
+    { 0x10421, 0x10449 },
+    { 0x104B1, 0x104D9 },
+    { 0x104C1, 0x104E9 },
+    { 0x104D1, 0x104F9 },
+    { 0x10570, 0x10597 },
+    { 0x10580, 0x105A7 },
+    { 0x10590, 0x105B7 },
+    { 0x10C89, 0x10CC9 },
+    { 0x10C99, 0x10CD9 },
+    { 0x10CA9, 0x10CE9 },
+    { 0x118AD, 0x118CD },
+    { 0x118BD, 0x118DD },
+    { 0x16E4B, 0x16E6B },
+    { 0x16E5B, 0x16E7B },
+    { 0x1E90C, 0x1E92E },
+    { 0x1E91C, 0x1E93E }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_006[] = {
+    { 0x10402, 0x1042A },
+    { 0x10412, 0x1043A },
+    { 0x10422, 0x1044A },
+    { 0x104B2, 0x104DA },
+    { 0x104C2, 0x104EA },
+    { 0x104D2, 0x104FA },
+    { 0x10573, 0x1059A },
+    { 0x10583, 0x105AA },
+    { 0x10C8A, 0x10CCA },
+    { 0x10C9A, 0x10CDA },
+    { 0x10CAA, 0x10CEA },
+    { 0x118AE, 0x118CE },
+    { 0x118BE, 0x118DE },
+    { 0x16E48, 0x16E68 },
+    { 0x16E58, 0x16E78 },
+    { 0x1E90F, 0x1E931 },
+    { 0x1E91F, 0x1E941 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_007[] = {
+    { 0x10403, 0x1042B },
+    { 0x10413, 0x1043B },
+    { 0x10423, 0x1044B },
+    { 0x104B3, 0x104DB },
+    { 0x104C3, 0x104EB },
+    { 0x104D3, 0x104FB },
+    { 0x10572, 0x10599 },
+    { 0x10582, 0x105A9 },
+    { 0x10592, 0x105B9 },
+    { 0x10C8B, 0x10CCB },
+    { 0x10C9B, 0x10CDB },
+    { 0x10CAB, 0x10CEB },
+    { 0x118AF, 0x118CF },
+    { 0x118BF, 0x118DF },
+    { 0x16E49, 0x16E69 },
+    { 0x16E59, 0x16E79 },
+    { 0x1E90E, 0x1E930 },
+    { 0x1E91E, 0x1E940 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_008[] = {
+    { 0x1040C, 0x10434 },
+    { 0x1041C, 0x10444 },
+    { 0x104BC, 0x104E4 },
+    { 0x104CC, 0x104F4 },
+    { 0x1057D, 0x105A4 },
+    { 0x1058D, 0x105B4 },
+    { 0x10C84, 0x10CC4 },
+    { 0x10C94, 0x10CD4 },
+    { 0x10CA4, 0x10CE4 },
+    { 0x118A0, 0x118C0 },
+    { 0x118B0, 0x118D0 },
+    { 0x16E46, 0x16E66 },
+    { 0x16E56, 0x16E76 },
+    { 0x1E901, 0x1E923 },
+    { 0x1E911, 0x1E933 },
+    { 0x1E921, 0x1E943 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_009[] = {
+    { 0x1040D, 0x10435 },
+    { 0x1041D, 0x10445 },
+    { 0x104BD, 0x104E5 },
+    { 0x104CD, 0x104F5 },
+    { 0x1057C, 0x105A3 },
+    { 0x1058C, 0x105B3 },
+    { 0x10C85, 0x10CC5 },
+    { 0x10C95, 0x10CD5 },
+    { 0x10CA5, 0x10CE5 },
+    { 0x118A1, 0x118C1 },
+    { 0x118B1, 0x118D1 },
+    { 0x16E47, 0x16E67 },
+    { 0x16E57, 0x16E77 },
+    { 0x1E900, 0x1E922 },
+    { 0x1E910, 0x1E932 },
+    { 0x1E920, 0x1E942 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_010[] = {
+    { 0x1040E, 0x10436 },
+    { 0x1041E, 0x10446 },
+    { 0x104BE, 0x104E6 },
+    { 0x104CE, 0x104F6 },
+    { 0x1057F, 0x105A6 },
+    { 0x1058F, 0x105B6 },
+    { 0x10C86, 0x10CC6 },
+    { 0x10C96, 0x10CD6 },
+    { 0x10CA6, 0x10CE6 },
+    { 0x118A2, 0x118C2 },
+    { 0x118B2, 0x118D2 },
+    { 0x16E44, 0x16E64 },
+    { 0x16E54, 0x16E74 },
+    { 0x1E903, 0x1E925 },
+    { 0x1E913, 0x1E935 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_011[] = {
+    { 0x1040F, 0x10437 },
+    { 0x1041F, 0x10447 },
+    { 0x104BF, 0x104E7 },
+    { 0x104CF, 0x104F7 },
+    { 0x1057E, 0x105A5 },
+    { 0x1058E, 0x105B5 },
+    { 0x10C87, 0x10CC7 },
+    { 0x10C97, 0x10CD7 },
+    { 0x10CA7, 0x10CE7 },
+    { 0x118A3, 0x118C3 },
+    { 0x118B3, 0x118D3 },
+    { 0x16E45, 0x16E65 },
+    { 0x16E55, 0x16E75 },
+    { 0x1E902, 0x1E924 },
+    { 0x1E912, 0x1E934 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_012[] = {
+    { 0x10408, 0x10430 },
+    { 0x10418, 0x10440 },
+    { 0x104B8, 0x104E0 },
+    { 0x104C8, 0x104F0 },
+    { 0x10579, 0x105A0 },
+    { 0x10589, 0x105B0 },
+    { 0x10C80, 0x10CC0 },
+    { 0x10C90, 0x10CD0 },
+    { 0x10CA0, 0x10CE0 },
+    { 0x10CB0, 0x10CF0 },
+    { 0x118A4, 0x118C4 },
+    { 0x118B4, 0x118D4 },
+    { 0x16E42, 0x16E62 },
+    { 0x16E52, 0x16E72 },
+    { 0x1E905, 0x1E927 },
+    { 0x1E915, 0x1E937 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_013[] = {
+    { 0x10409, 0x10431 },
+    { 0x10419, 0x10441 },
+    { 0x104B9, 0x104E1 },
+    { 0x104C9, 0x104F1 },
+    { 0x10578, 0x1059F },
+    { 0x10588, 0x105AF },
+    { 0x10C81, 0x10CC1 },
+    { 0x10C91, 0x10CD1 },
+    { 0x10CA1, 0x10CE1 },
+    { 0x10CB1, 0x10CF1 },
+    { 0x118A5, 0x118C5 },
+    { 0x118B5, 0x118D5 },
+    { 0x16E43, 0x16E63 },
+    { 0x16E53, 0x16E73 },
+    { 0x1E904, 0x1E926 },
+    { 0x1E914, 0x1E936 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_014[] = {
+    { 0x1040A, 0x10432 },
+    { 0x1041A, 0x10442 },
+    { 0x104BA, 0x104E2 },
+    { 0x104CA, 0x104F2 },
+    { 0x10C82, 0x10CC2 },
+    { 0x10C92, 0x10CD2 },
+    { 0x10CA2, 0x10CE2 },
+    { 0x10CB2, 0x10CF2 },
+    { 0x118A6, 0x118C6 },
+    { 0x118B6, 0x118D6 },
+    { 0x16E40, 0x16E60 },
+    { 0x16E50, 0x16E70 },
+    { 0x1E907, 0x1E929 },
+    { 0x1E917, 0x1E939 }
+};
+
+static const CaseFoldMapping1_32 case_fold1_32_015[] = {
+    { 0x1040B, 0x10433 },
+    { 0x1041B, 0x10443 },
+    { 0x104BB, 0x104E3 },
+    { 0x104CB, 0x104F3 },
+    { 0x1057A, 0x105A1 },
+    { 0x1058A, 0x105B1 },
+    { 0x10C83, 0x10CC3 },
+    { 0x10C93, 0x10CD3 },
+    { 0x10CA3, 0x10CE3 },
+    { 0x118A7, 0x118C7 },
+    { 0x118B7, 0x118D7 },
+    { 0x16E41, 0x16E61 },
+    { 0x16E51, 0x16E71 },
+    { 0x1E906, 0x1E928 },
+    { 0x1E916, 0x1E938 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_000[] = {
+    { 0x1E9E, 0x0073, 0x0073 },
+    { 0x1F8F, 0x1F07, 0x03B9 },
+    { 0x1F9F, 0x1F27, 0x03B9 },
+    { 0x1FAF, 0x1F67, 0x03B9 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_001[] = {
+    { 0x0130, 0x0069, 0x0307 },
+    { 0x01F0, 0x006A, 0x030C },
+    { 0x1F8E, 0x1F06, 0x03B9 },
+    { 0x1F9E, 0x1F26, 0x03B9 },
+    { 0x1FAE, 0x1F66, 0x03B9 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_002[] = {
+    { 0x0587, 0x0565, 0x0582 },
+    { 0x1F8D, 0x1F05, 0x03B9 },
+    { 0x1F9D, 0x1F25, 0x03B9 },
+    { 0x1FAD, 0x1F65, 0x03B9 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_003[] = {
+    { 0x1F8C, 0x1F04, 0x03B9 },
+    { 0x1F9C, 0x1F24, 0x03B9 },
+    { 0x1FAC, 0x1F64, 0x03B9 },
+    { 0x1FBC, 0x03B1, 0x03B9 },
+    { 0x1FCC, 0x03B7, 0x03B9 },
+    { 0x1FFC, 0x03C9, 0x03B9 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_004[] = {
+    { 0x1E9A, 0x0061, 0x02BE },
+    { 0x1F8B, 0x1F03, 0x03B9 },
+    { 0x1F9B, 0x1F23, 0x03B9 },
+    { 0x1FAB, 0x1F63, 0x03B9 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_005[] = {
+    { 0x1F8A, 0x1F02, 0x03B9 },
+    { 0x1F9A, 0x1F22, 0x03B9 },
+    { 0x1FAA, 0x1F62, 0x03B9 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_006[] = {
+    { 0x1E98, 0x0077, 0x030A },
+    { 0x1F89, 0x1F01, 0x03B9 },
+    { 0x1F99, 0x1F21, 0x03B9 },
+    { 0x1FA9, 0x1F61, 0x03B9 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_007[] = {
+    { 0x1E99, 0x0079, 0x030A },
+    { 0x1F88, 0x1F00, 0x03B9 },
+    { 0x1F98, 0x1F20, 0x03B9 },
+    { 0x1FA8, 0x1F60, 0x03B9 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_008[] = {
+    { 0x0149, 0x02BC, 0x006E },
+    { 0x1E96, 0x0068, 0x0331 },
+    { 0x1F87, 0x1F07, 0x03B9 },
+    { 0x1F97, 0x1F27, 0x03B9 },
+    { 0x1FA7, 0x1F67, 0x03B9 },
+    { 0xFB13, 0x0574, 0x0576 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_009[] = {
+    { 0x1E97, 0x0074, 0x0308 },
+    { 0x1F86, 0x1F06, 0x03B9 },
+    { 0x1F96, 0x1F26, 0x03B9 },
+    { 0x1FA6, 0x1F66, 0x03B9 },
+    { 0x1FB6, 0x03B1, 0x0342 },
+    { 0x1FC6, 0x03B7, 0x0342 },
+    { 0x1FD6, 0x03B9, 0x0342 },
+    { 0x1FE6, 0x03C5, 0x0342 },
+    { 0x1FF6, 0x03C9, 0x0342 },
+    { 0xFB02, 0x0066, 0x006C }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_010[] = {
+    { 0x1F85, 0x1F05, 0x03B9 },
+    { 0x1F95, 0x1F25, 0x03B9 },
+    { 0x1FA5, 0x1F65, 0x03B9 },
+    { 0xFB01, 0x0066, 0x0069 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_011[] = {
+    { 0x1F84, 0x1F04, 0x03B9 },
+    { 0x1F94, 0x1F24, 0x03B9 },
+    { 0x1FA4, 0x1F64, 0x03B9 },
+    { 0x1FB4, 0x03AC, 0x03B9 },
+    { 0x1FC4, 0x03AE, 0x03B9 },
+    { 0x1FE4, 0x03C1, 0x0313 },
+    { 0x1FF4, 0x03CE, 0x03B9 },
+    { 0xFB00, 0x0066, 0x0066 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_012[] = {
+    { 0x1F83, 0x1F03, 0x03B9 },
+    { 0x1F93, 0x1F23, 0x03B9 },
+    { 0x1FA3, 0x1F63, 0x03B9 },
+    { 0x1FB3, 0x03B1, 0x03B9 },
+    { 0x1FC3, 0x03B7, 0x03B9 },
+    { 0x1FF3, 0x03C9, 0x03B9 },
+    { 0xFB17, 0x0574, 0x056D }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_013[] = {
+    { 0x1F82, 0x1F02, 0x03B9 },
+    { 0x1F92, 0x1F22, 0x03B9 },
+    { 0x1FA2, 0x1F62, 0x03B9 },
+    { 0x1FB2, 0x1F70, 0x03B9 },
+    { 0x1FC2, 0x1F74, 0x03B9 },
+    { 0x1FF2, 0x1F7C, 0x03B9 },
+    { 0xFB06, 0x0073, 0x0074 },
+    { 0xFB16, 0x057E, 0x0576 }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_014[] = {
+    { 0x1F81, 0x1F01, 0x03B9 },
+    { 0x1F91, 0x1F21, 0x03B9 },
+    { 0x1FA1, 0x1F61, 0x03B9 },
+    { 0xFB05, 0x0073, 0x0074 },
+    { 0xFB15, 0x0574, 0x056B }
+};
+
+static const CaseFoldMapping2_16 case_fold2_16_015[] = {
+    { 0x00DF, 0x0073, 0x0073 },
+    { 0x1F50, 0x03C5, 0x0313 },
+    { 0x1F80, 0x1F00, 0x03B9 },
+    { 0x1F90, 0x1F20, 0x03B9 },
+    { 0x1FA0, 0x1F60, 0x03B9 },
+    { 0xFB14, 0x0574, 0x0565 }
+};
+
+static const CaseFoldMapping3_16 case_fold3_16_000[] = {
+    { 0x1FB7, 0x03B1, 0x0342, 0x03B9 },
+    { 0x1FC7, 0x03B7, 0x0342, 0x03B9 },
+    { 0x1FD3, 0x03B9, 0x0308, 0x0301 },
+    { 0x1FD7, 0x03B9, 0x0308, 0x0342 },
+    { 0x1FE3, 0x03C5, 0x0308, 0x0301 },
+    { 0x1FE7, 0x03C5, 0x0308, 0x0342 },
+    { 0x1FF7, 0x03C9, 0x0342, 0x03B9 },
+    { 0xFB03, 0x0066, 0x0066, 0x0069 }
+};
+
+static const CaseFoldMapping3_16 case_fold3_16_001[] = {
+    { 0x1F52, 0x03C5, 0x0313, 0x0300 },
+    { 0x1F56, 0x03C5, 0x0313, 0x0342 },
+    { 0x1FD2, 0x03B9, 0x0308, 0x0300 },
+    { 0x1FE2, 0x03C5, 0x0308, 0x0300 }
+};
+
+static const CaseFoldMapping3_16 case_fold3_16_003[] = {
+    { 0x0390, 0x03B9, 0x0308, 0x0301 },
+    { 0x03B0, 0x03C5, 0x0308, 0x0301 },
+    { 0x1F54, 0x03C5, 0x0313, 0x0301 },
+    { 0xFB04, 0x0066, 0x0066, 0x006C }
+};
+
+static const CaseFoldHashBucket1_16 case_fold_hash1_16[] = {
+    { case_fold1_16_000, SDL_arraysize(case_fold1_16_000) },
+    { case_fold1_16_001, SDL_arraysize(case_fold1_16_001) },
+    { case_fold1_16_002, SDL_arraysize(case_fold1_16_002) },
+    { case_fold1_16_003, SDL_arraysize(case_fold1_16_003) },
+    { case_fold1_16_004, SDL_arraysize(case_fold1_16_004) },
+    { case_fold1_16_005, SDL_arraysize(case_fold1_16_005) },
+    { case_fold1_16_006, SDL_arraysize(case_fold1_16_006) },
+    { case_fold1_16_007, SDL_arraysize(case_fold1_16_007) },
+    { case_fold1_16_008, SDL_arraysize(case_fold1_16_008) },
+    { case_fold1_16_009, SDL_arraysize(case_fold1_16_009) },
+    { case_fold1_16_010, SDL_arraysize(case_fold1_16_010) },
+    { case_fold1_16_011, SDL_arraysize(case_fold1_16_011) },
+    { case_fold1_16_012, SDL_arraysize(case_fold1_16_012) },
+    { case_fold1_16_013, SDL_arraysize(case_fold1_16_013) },
+    { case_fold1_16_014, SDL_arraysize(case_fold1_16_014) },
+    { case_fold1_16_015, SDL_arraysize(case_fold1_16_015) },
+    { case_fold1_16_016, SDL_arraysize(case_fold1_16_016) },
+    { case_fold1_16_017, SDL_arraysize(case_fold1_16_017) },
+    { case_fold1_16_018, SDL_arraysize(case_fold1_16_018) },
+    { case_fold1_16_019, SDL_arraysize(case_fold1_16_019) },
+    { case_fold1_16_020, SDL_arraysize(case_fold1_16_020) },
+    { case_fold1_16_021, SDL_arraysize(case_fold1_16_021) },
+    { case_fold1_16_022, SDL_arraysize(case_fold1_16_022) },
+    { case_fold1_16_023, SDL_arraysize(case_fold1_16_023) },
+    { case_fold1_16_024, SDL_arraysize(case_fold1_16_024) },
+    { case_fold1_16_025, SDL_arraysize(case_fold1_16_025) },
+    { case_fold1_16_026, SDL_arraysize(case_fold1_16_026) },
+    { case_fold1_16_027, SDL_arraysize(case_fold1_16_027) },
+    { case_fold1_16_028, SDL_arraysize(case_fold1_16_028) },
+    { case_fold1_16_029, SDL_arraysize(case_fold1_16_029) },
+    { case_fold1_16_030, SDL_arraysize(case_fold1_16_030) },
+    { case_fold1_16_031, SDL_arraysize(case_fold1_16_031) },
+    { case_fold1_16_032, SDL_arraysize(case_fold1_16_032) },
+    { case_fold1_16_033, SDL_arraysize(case_fold1_16_033) },
+    { case_fold1_16_034, SDL_arraysize(case_fold1_16_034) },
+    { case_fold1_16_035, SDL_arraysize(case_fold1_16_035) },
+    { case_fold1_16_036, SDL_arraysize(case_fold1_16_036) },
+    { case_fold1_16_037, SDL_arraysize(case_fold1_16_037) },
+    { case_fold1_16_038, SDL_arraysize(case_fold1_16_038) },
+    { case_fold1_16_039, SDL_arraysize(case_fold1_16_039) },
+    { case_fold1_16_040, SDL_arraysize(case_fold1_16_040) },
+    { case_fold1_16_041, SDL_arraysize(case_fold1_16_041) },
+    { case_fold1_16_042, SDL_arraysize(case_fold1_16_042) },
+    { case_fold1_16_043, SDL_arraysize(case_fold1_16_043) },
+    { case_fold1_16_044, SDL_arraysize(case_fold1_16_044) },
+    { case_fold1_16_045, SDL_arraysize(case_fold1_16_045) },
+    { case_fold1_16_046, SDL_arraysize(case_fold1_16_046) },
+    { case_fold1_16_047, SDL_arraysize(case_fold1_16_047) },
+    { case_fold1_16_048, SDL_arraysize(case_fold1_16_048) },
+    { case_fold1_16_049, SDL_arraysize(case_fold1_16_049) },
+    { case_fold1_16_050, SDL_arraysize(case_fold1_16_050) },
+    { case_fold1_16_051, SDL_arraysize(case_fold1_16_051) },
+    { case_fold1_16_052, SDL_arraysize(case_fold1_16_052) },
+    { case_fold1_16_053, SDL_arraysize(case_fold1_16_053) },
+    { case_fold1_16_054, SDL_arraysize(case_fold1_16_054) },
+    { case_fold1_16_055, SDL_arraysize(case_fold1_16_055) },
+    { case_fold1_16_056, SDL_arraysize(case_fold1_16_056) },
+    { case_fold1_16_057, SDL_arraysize(case_fold1_16_057) },
+    { case_fold1_16_058, SDL_arraysize(case_fold1_16_058) },
+    { case_fold1_16_059, SDL_arraysize(case_fold1_16_059) },
+    { case_fold1_16_060, SDL_arraysize(case_fold1_16_060) },
+    { case_fold1_16_061, SDL_arraysize(case_fold1_16_061) },
+    { case_fold1_16_062, SDL_arraysize(case_fold1_16_062) },
+    { case_fold1_16_063, SDL_arraysize(case_fold1_16_063) },
+    { case_fold1_16_064, SDL_arraysize(case_fold1_16_064) },
+    { case_fold1_16_065, SDL_arraysize(case_fold1_16_065) },
+    { case_fold1_16_066, SDL_arraysize(case_fold1_16_066) },
+    { case_fold1_16_067, SDL_arraysize(case_fold1_16_067) },
+    { case_fold1_16_068, SDL_arraysize(case_fold1_16_068) },
+    { case_fold1_16_069, SDL_arraysize(case_fold1_16_069) },
+    { case_fold1_16_070, SDL_arraysize(case_fold1_16_070) },
+    { case_fold1_16_071, SDL_arraysize(case_fold1_16_071) },
+    { case_fold1_16_072, SDL_arraysize(case_fold1_16_072) },
+    { case_fold1_16_073, SDL_arraysize(case_fold1_16_073) },
+    { case_fold1_16_074, SDL_arraysize(case_fold1_16_074) },
+    { case_fold1_16_075, SDL_arraysize(case_fold1_16_075) },
+    { case_fold1_16_076, SDL_arraysize(case_fold1_16_076) },
+    { case_fold1_16_077, SDL_arraysize(case_fold1_16_077) },
+    { case_fold1_16_078, SDL_arraysize(case_fold1_16_078) },
+    { case_fold1_16_079, SDL_arraysize(case_fold1_16_079) },
+    { case_fold1_16_080, SDL_arraysize(case_fold1_16_080) },
+    { case_fold1_16_081, SDL_arraysize(case_fold1_16_081) },
+    { case_fold1_16_082, SDL_arraysize(case_fold1_16_082) },
+    { case_fold1_16_083, SDL_arraysize(case_fold1_16_083) },
+    { case_fold1_16_084, SDL_arraysize(case_fold1_16_084) },
+    { case_fold1_16_085, SDL_arraysize(case_fold1_16_085) },
+    { case_fold1_16_086, SDL_arraysize(case_fold1_16_086) },
+    { case_fold1_16_087, SDL_arraysize(case_fold1_16_087) },
+    { case_fold1_16_088, SDL_arraysize(case_fold1_16_088) },
+    { case_fold1_16_089, SDL_arraysize(case_fold1_16_089) },
+    { case_fold1_16_090, SDL_arraysize(case_fold1_16_090) },
+    { case_fold1_16_091, SDL_arraysize(case_fold1_16_091) },
+    { case_fold1_16_092, SDL_arraysize(case_fold1_16_092) },
+    { case_fold1_16_093, SDL_arraysize(case_fold1_16_093) },
+    { case_fold1_16_094, SDL_arraysize(case_fold1_16_094) },
+    { case_fold1_16_095, SDL_arraysize(case_fold1_16_095) },
+    { case_fold1_16_096, SDL_arraysize(case_fold1_16_096) },
+    { case_fold1_16_097, SDL_arraysize(case_fold1_16_097) },
+    { case_fold1_16_098, SDL_arraysize(case_fold1_16_098) },
+    { case_fold1_16_099, SDL_arraysize(case_fold1_16_099) },
+    { case_fold1_16_100, SDL_arraysize(case_fold1_16_100) },
+    { case_fold1_16_101, SDL_arraysize(case_fold1_16_101) },
+    { case_fold1_16_102, SDL_arraysize(case_fold1_16_102) },
+    { case_fold1_16_103, SDL_arraysize(case_fold1_16_103) },
+    { case_fold1_16_104, SDL_arraysize(case_fold1_16_104) },
+    { case_fold1_16_105, SDL_arraysize(case_fold1_16_105) },
+    { case_fold1_16_106, SDL_arraysize(case_fold1_16_106) },
+    { case_fold1_16_107, SDL_arraysize(case_fold1_16_107) },
+    { case_fold1_16_108, SDL_arraysize(case_fold1_16_108) },
+    { case_fold1_16_109, SDL_arraysize(case_fold1_16_109) },
+    { case_fold1_16_110, SDL_arraysize(case_fold1_16_110) },
+    { case_fold1_16_111, SDL_arraysize(case_fold1_16_111) },
+    { case_fold1_16_112, SDL_arraysize(case_fold1_16_112) },
+    { case_fold1_16_113, SDL_arraysize(case_fold1_16_113) },
+    { case_fold1_16_114, SDL_arraysize(case_fold1_16_114) },
+    { case_fold1_16_115, SDL_arraysize(case_fold1_16_115) },
+    { case_fold1_16_116, SDL_arraysize(case_fold1_16_116) },
+    { case_fold1_16_117, SDL_arraysize(case_fold1_16_117) },
+    { case_fold1_16_118, SDL_arraysize(case_fold1_16_118) },
+    { case_fold1_16_119, SDL_arraysize(case_fold1_16_119) },
+    { case_fold1_16_120, SDL_arraysize(case_fold1_16_120) },
+    { case_fold1_16_121, SDL_arraysize(case_fold1_16_121) },
+    { case_fold1_16_122, SDL_arraysize(case_fold1_16_122) },
+    { NULL, 0 },
+    { case_fold1_16_124, SDL_arraysize(case_fold1_16_124) },
+    { NULL, 0 },
+    { case_fold1_16_126, SDL_arraysize(case_fold1_16_126) },
+    { case_fold1_16_127, SDL_arraysize(case_fold1_16_127) },
+    { case_fold1_16_128, SDL_arraysize(case_fold1_16_128) },
+    { case_fold1_16_129, SDL_arraysize(case_fold1_16_129) },
+    { case_fold1_16_130, SDL_arraysize(case_fold1_16_130) },
+    { case_fold1_16_131, SDL_arraysize(case_fold1_16_131) },
+    { case_fold1_16_132, SDL_arraysize(case_fold1_16_132) },
+    { case_fold1_16_133, SDL_arraysize(case_fold1_16_133) },
+    { case_fold1_16_134, SDL_arraysize(case_fold1_16_134) },
+    { case_fold1_16_135, SDL_arraysize(case_fold1_16_135) },
+    { case_fold1_16_136, SDL_arraysize(case_fold1_16_136) },
+    { case_fold1_16_137, SDL_arraysize(case_fold1_16_137) },
+    { case_fold1_16_138, SDL_arraysize(case_fold1_16_138) },
+    { case_fold1_16_139, SDL_arraysize(case_fold1_16_139) },
+    { case_fold1_16_140, SDL_arraysize(case_fold1_16_140) },
+    { case_fold1_16_141, SDL_arraysize(case_fold1_16_141) },
+    { case_fold1_16_142, SDL_arraysize(case_fold1_16_142) },
+    { case_fold1_16_143, SDL_arraysize(case_fold1_16_143) },
+    { case_fold1_16_144, SDL_arraysize(case_fold1_16_144) },
+    { case_fold1_16_145, SDL_arraysize(case_fold1_16_145) },
+    { case_fold1_16_146, SDL_arraysize(case_fold1_16_146) },
+    { case_fold1_16_147, SDL_arraysize(case_fold1_16_147) },
+    { case_fold1_16_148, SDL_arraysize(case_fold1_16_148) },
+    { case_fold1_16_149, SDL_arraysize(case_fold1_16_149) },
+    { case_fold1_16_150, SDL_arraysize(case_fold1_16_150) },
+    { case_fold1_16_151, SDL_arraysize(case_fold1_16_151) },
+    { case_fold1_16_152, SDL_arraysize(case_fold1_16_152) },
+    { case_fold1_16_153, SDL_arraysize(case_fold1_16_153) },
+    { case_fold1_16_154, SDL_arraysize(case_fold1_16_154) },
+    { case_fold1_16_155, SDL_arraysize(case_fold1_16_155) },
+    { case_fold1_16_156, SDL_arraysize(case_fold1_16_156) },
+    { case_fold1_16_157, SDL_arraysize(case_fold1_16_157) },
+    { case_fold1_16_158, SDL_arraysize(case_fold1_16_158) },
+    { case_fold1_16_159, SDL_arraysize(case_fold1_16_159) },
+    { case_fold1_16_160, SDL_arraysize(case_fold1_16_160) },
+    { case_fold1_16_161, SDL_arraysize(case_fold1_16_161) },
+    { case_fold1_16_162, SDL_arraysize(case_fold1_16_162) },
+    { case_fold1_16_163, SDL_arraysize(case_fold1_16_163) },
+    { case_fold1_16_164, SDL_arraysize(case_fold1_16_164) },
+    { case_fold1_16_165, SDL_arraysize(case_fold1_16_165) },
+    { case_fold1_16_166, SDL_arraysize(case_fold1_16_166) },
+    { case_fold1_16_167, SDL_arraysize(case_fold1_16_167) },
+    { case_fold1_16_168, SDL_arraysize(case_fold1_16_168) },
+    { case_fold1_16_169, SDL_arraysize(case_fold1_16_169) },
+    { case_fold1_16_170, SDL_arraysize(case_fold1_16_170) },
+    { case_fold1_16_171, SDL_arraysize(case_fold1_16_171) },
+    { case_fold1_16_172, SDL_arraysize(case_fold1_16_172) },
+    { case_fold1_16_173, SDL_arraysize(case_fold1_16_173) },
+    { case_fold1_16_174, SDL_arraysize(case_fold1_16_174) },
+    { case_fold1_16_175, SDL_arraysize(case_fold1_16_175) },
+    { case_fold1_16_176, SDL_arraysize(case_fold1_16_176) },
+    { case_fold1_16_177, SDL_arraysize(case_fold1_16_177) },
+    { case_fold1_16_178, SDL_arraysize(case_fold1_16_178) },
+    { case_fold1_16_179, SDL_arraysize(case_fold1_16_179) },
+    { case_fold1_16_180, SDL_arraysize(case_fold1_16_180) },
+    { case_fold1_16_181, SDL_arraysize(case_fold1_16_181) },
+    { case_fold1_16_182, SDL_arraysize(case_fold1_16_182) },
+    { case_fold1_16_183, SDL_arraysize(case_fold1_16_183) },
+    { case_fold1_16_184, SDL_arraysize(case_fold1_16_184) },
+    { case_fold1_16_185, SDL_arraysize(case_fold1_16_185) },
+    { case_fold1_16_186, SDL_arraysize(case_fold1_16_186) },
+    { case_fold1_16_187, SDL_arraysize(case_fold1_16_187) },
+    { case_fold1_16_188, SDL_arraysize(case_fold1_16_188) },
+    { case_fold1_16_189, SDL_arraysize(case_fold1_16_189) },
+    { case_fold1_16_190, SDL_arraysize(case_fold1_16_190) },
+    { case_fold1_16_191, SDL_arraysize(case_fold1_16_191) },
+    { case_fold1_16_192, SDL_arraysize(case_fold1_16_192) },
+    { case_fold1_16_193, SDL_arraysize(case_fold1_16_193) },
+    { case_fold1_16_194, SDL_arraysize(case_fold1_16_194) },
+    { case_fold1_16_195, SDL_arraysize(case_fold1_16_195) },
+    { case_fold1_16_196, SDL_arraysize(case_fold1_16_196) },
+    { case_fold1_16_197, SDL_arraysize(case_fold1_16_197) },
+    { case_fold1_16_198, SDL_arraysize(case_fold1_16_198) },
+    { case_fold1_16_199, SDL_arraysize(case_fold1_16_199) },
+    { case_fold1_16_200, SDL_arraysize(case_fold1_16_200) },
+    { case_fold1_16_201, SDL_arraysize(case_fold1_16_201) },
+    { case_fold1_16_202, SDL_arraysize(case_fold1_16_202) },
+    { case_fold1_16_203, SDL_arraysize(case_fold1_16_203) },
+    { case_fold1_16_204, SDL_arraysize(case_fold1_16_204) },
+    { case_fold1_16_205, SDL_arraysize(case_fold1_16_205) },
+    { case_fold1_16_206, SDL_arraysize(case_fold1_16_206) },
+    { case_fold1_16_207, SDL_arraysize(case_fold1_16_207) },
+    { case_fold1_16_208, SDL_arraysize(case_fold1_16_208) },
+    { case_fold1_16_209, SDL_arraysize(case_fold1_16_209) },
+    { case_fold1_16_210, SDL_arraysize(case_fold1_16_210) },
+    { case_fold1_16_211, SDL_arraysize(case_fold1_16_211) },
+    { case_fold1_16_212, SDL_arraysize(case_fold1_16_212) },
+    { case_fold1_16_213, SDL_arraysize(case_fold1_16_213) },
+    { case_fold1_16_214, SDL_arraysize(case_fold1_16_214) },
+    { case_fold1_16_215, SDL_arraysize(case_fold1_16_215) },
+    { case_fold1_16_216, SDL_arraysize(case_fold1_16_216) },
+    { case_fold1_16_217, SDL_arraysize(case_fold1_16_217) },
+    { case_fold1_16_218, SDL_arraysize(case_fold1_16_218) },
+    { case_fold1_16_219, SDL_arraysize(case_fold1_16_219) },
+    { case_fold1_16_220, SDL_arraysize(case_fold1_16_220) },
+    { case_fold1_16_221, SDL_arraysize(case_fold1_16_221) },
+    { case_fold1_16_222, SDL_arraysize(case_fold1_16_222) },
+    { case_fold1_16_223, SDL_arraysize(case_fold1_16_223) },
+    { case_fold1_16_224, SDL_arraysize(case_fold1_16_224) },
+    { case_fold1_16_225, SDL_arraysize(case_fold1_16_225) },
+    { case_fold1_16_226, SDL_arraysize(case_fold1_16_226) },
+    { case_fold1_16_227, SDL_arraysize(case_fold1_16_227) },
+    { case_fold1_16_228, SDL_arraysize(case_fold1_16_228) },
+    { case_fold1_16_229, SDL_arraysize(case_fold1_16_229) },
+    { case_fold1_16_230, SDL_arraysize(case_fold1_16_230) },
+    { case_fold1_16_231, SDL_arraysize(case_fold1_16_231) },
+    { case_fold1_16_232, SDL_arraysize(case_fold1_16_232) },
+    { case_fold1_16_233, SDL_arraysize(case_fold1_16_233) },
+    { case_fold1_16_234, SDL_arraysize(case_fold1_16_234) },
+    { case_fold1_16_235, SDL_arraysize(case_fold1_16_235) },
+    { case_fold1_16_236, SDL_arraysize(case_fold1_16_236) },
+    { case_fold1_16_237, SDL_arraysize(case_fold1_16_237) },
+    { case_fold1_16_238, SDL_arraysize(case_fold1_16_238) },
+    { case_fold1_16_239, SDL_arraysize(case_fold1_16_239) },
+    { case_fold1_16_240, SDL_arraysize(case_fold1_16_240) },
+    { case_fold1_16_241, SDL_arraysize(case_fold1_16_241) },
+    { case_fold1_16_242, SDL_arraysize(case_fold1_16_242) },
+    { case_fold1_16_243, SDL_arraysize(case_fold1_16_243) },
+    { case_fold1_16_244, SDL_arraysize(case_fold1_16_244) },
+    { case_fold1_16_245, SDL_arraysize(case_fold1_16_245) },
+    { case_fold1_16_246, SDL_arraysize(case_fold1_16_246) },
+    { case_fold1_16_247, SDL_arraysize(case_fold1_16_247) },
+    { case_fold1_16_248, SDL_arraysize(case_fold1_16_248) },
+    { case_fold1_16_249, SDL_arraysize(case_fold1_16_249) },
+    { case_fold1_16_250, SDL_arraysize(case_fold1_16_250) },
+    { case_fold1_16_251, SDL_arraysize(case_fold1_16_251) },
+    { case_fold1_16_252, SDL_arraysize(case_fold1_16_252) },
+    { case_fold1_16_253, SDL_arraysize(case_fold1_16_253) },
+    { case_fold1_16_254, SDL_arraysize(case_fold1_16_254) },
+    { case_fold1_16_255, SDL_arraysize(case_fold1_16_255) },
+};
+
+static const CaseFoldHashBucket1_32 case_fold_hash1_32[] = {
+    { case_fold1_32_000, SDL_arraysize(case_fold1_32_000) },
+    { case_fold1_32_001, SDL_arraysize(case_fold1_32_001) },
+    { case_fold1_32_002, SDL_arraysize(case_fold1_32_002) },
+    { case_fold1_32_003, SDL_arraysize(case_fold1_32_003) },
+    { case_fold1_32_004, SDL_arraysize(case_fold1_32_004) },
+    { case_fold1_32_005, SDL_arraysize(case_fold1_32_005) },
+    { case_fold1_32_006, SDL_arraysize(case_fold1_32_006) },
+    { case_fold1_32_007, SDL_arraysize(case_fold1_32_007) },
+    { case_fold1_32_008, SDL_arraysize(case_fold1_32_008) },
+    { case_fold1_32_009, SDL_arraysize(case_fold1_32_009) },
+    { case_fold1_32_010, SDL_arraysize(case_fold1_32_010) },
+    { case_fold1_32_011, SDL_arraysize(case_fold1_32_011) },
+    { case_fold1_32_012, SDL_arraysize(case_fold1_32_012) },
+    { case_fold1_32_013, SDL_arraysize(case_fold1_32_013) },
+    { case_fold1_32_014, SDL_arraysize(case_fold1_32_014) },
+    { case_fold1_32_015, SDL_arraysize(case_fold1_32_015) },
+};
+
+static const CaseFoldHashBucket2_16 case_fold_hash2_16[] = {
+    { case_fold2_16_000, SDL_arraysize(case_fold2_16_000) },
+    { case_fold2_16_001, SDL_arraysize(case_fold2_16_001) },
+    { case_fold2_16_002, SDL_arraysize(case_fold2_16_002) },
+    { case_fold2_16_003, SDL_arraysize(case_fold2_16_003) },
+    { case_fold2_16_004, SDL_arraysize(case_fold2_16_004) },
+    { case_fold2_16_005, SDL_arraysize(case_fold2_16_005) },
+    { case_fold2_16_006, SDL_arraysize(case_fold2_16_006) },
+    { case_fold2_16_007, SDL_arraysize(case_fold2_16_007) },
+    { case_fold2_16_008, SDL_arraysize(case_fold2_16_008) },
+    { case_fold2_16_009, SDL_arraysize(case_fold2_16_009) },
+    { case_fold2_16_010, SDL_arraysize(case_fold2_16_010) },
+    { case_fold2_16_011, SDL_arraysize(case_fold2_16_011) },
+    { case_fold2_16_012, SDL_arraysize(case_fold2_16_012) },
+    { case_fold2_16_013, SDL_arraysize(case_fold2_16_013) },
+    { case_fold2_16_014, SDL_arraysize(case_fold2_16_014) },
+    { case_fold2_16_015, SDL_arraysize(case_fold2_16_015) },
+};
+
+static const CaseFoldHashBucket3_16 case_fold_hash3_16[] = {
+    { case_fold3_16_000, SDL_arraysize(case_fold3_16_000) },
+    { case_fold3_16_001, SDL_arraysize(case_fold3_16_001) },
+    { NULL, 0 },
+    { case_fold3_16_003, SDL_arraysize(case_fold3_16_003) },
+};
+
+#endif // SDL_casefolding_h_
+
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_crc16.c b/contrib/SDL-3.2.8/src/stdlib/SDL_crc16.c
new file mode 100644
index 0000000..828ce94
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_crc16.c
@@ -0,0 +1,52 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+/* Public domain CRC implementation adapted from:
+   http://home.thep.lu.se/~bjorn/crc/crc32_simple.c
+
+   This algorithm is compatible with the 16-bit CRC described here:
+   https://www.lammertbies.nl/comm/info/crc-calculation
+*/
+/* NOTE: DO NOT CHANGE THIS ALGORITHM
+   There is code that relies on this in the joystick code
+*/
+
+static Uint16 crc16_for_byte(Uint8 r)
+{
+    Uint16 crc = 0;
+    int i;
+    for (i = 0; i < 8; ++i) {
+        crc = ((crc ^ r) & 1 ? 0xA001 : 0) ^ crc >> 1;
+        r >>= 1;
+    }
+    return crc;
+}
+
+Uint16 SDL_crc16(Uint16 crc, const void *data, size_t len)
+{
+    // As an optimization we can precalculate a 256 entry table for each byte
+    size_t i;
+    for (i = 0; i < len; ++i) {
+        crc = crc16_for_byte((Uint8)crc ^ ((const Uint8 *)data)[i]) ^ crc >> 8;
+    }
+    return crc;
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_crc32.c b/contrib/SDL-3.2.8/src/stdlib/SDL_crc32.c
new file mode 100644
index 0000000..9c2d097
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_crc32.c
@@ -0,0 +1,50 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+/* Public domain CRC implementation adapted from:
+   http://home.thep.lu.se/~bjorn/crc/crc32_simple.c
+
+   This algorithm is compatible with the 32-bit CRC described here:
+   https://www.lammertbies.nl/comm/info/crc-calculation
+*/
+/* NOTE: DO NOT CHANGE THIS ALGORITHM
+   There is code that relies on this in the joystick code
+*/
+
+static Uint32 crc32_for_byte(Uint32 r)
+{
+    int i;
+    for (i = 0; i < 8; ++i) {
+        r = (r & 1 ? 0 : (Uint32)0xEDB88320L) ^ r >> 1;
+    }
+    return r ^ (Uint32)0xFF000000L;
+}
+
+Uint32 SDL_crc32(Uint32 crc, const void *data, size_t len)
+{
+    // As an optimization we can precalculate a 256 entry table for each byte
+    size_t i;
+    for (i = 0; i < len; ++i) {
+        crc = crc32_for_byte((Uint8)crc ^ ((const Uint8 *)data)[i]) ^ crc >> 8;
+    }
+    return crc;
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_getenv.c b/contrib/SDL-3.2.8/src/stdlib/SDL_getenv.c
new file mode 100644
index 0000000..b4a1922
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_getenv.c
@@ -0,0 +1,601 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+#include "SDL_getenv_c.h"
+
+#if defined(SDL_PLATFORM_WINDOWS)
+#include "../core/windows/SDL_windows.h"
+#endif
+
+#ifdef SDL_PLATFORM_ANDROID
+#include "../core/android/SDL_android.h"
+#endif
+
+#if defined(SDL_PLATFORM_WINDOWS)
+#define HAVE_WIN32_ENVIRONMENT
+#elif defined(HAVE_GETENV) && \
+      (defined(HAVE_SETENV) || defined(HAVE_PUTENV)) && \
+      (defined(HAVE_UNSETENV) || defined(HAVE_PUTENV))
+#define HAVE_LIBC_ENVIRONMENT
+#if defined(SDL_PLATFORM_MACOS)
+#include <crt_externs.h>
+#define environ (*_NSGetEnviron())
+#elif defined(SDL_PLATFORM_FREEBSD)
+#include <dlfcn.h>
+#define environ ((char **)dlsym(RTLD_DEFAULT, "environ"))
+#else
+extern char **environ;
+#endif
+#else
+#define HAVE_LOCAL_ENVIRONMENT
+static char **environ;
+#endif
+
+
+struct SDL_Environment
+{
+    SDL_Mutex *lock;   // !!! FIXME: reuse SDL_HashTable's lock.
+    SDL_HashTable *strings;
+};
+static SDL_Environment *SDL_environment;
+
+SDL_Environment *SDL_GetEnvironment(void)
+{
+    if (!SDL_environment) {
+        SDL_environment = SDL_CreateEnvironment(true);
+    }
+    return SDL_environment;
+}
+
+bool SDL_InitEnvironment(void)
+{
+    return (SDL_GetEnvironment() != NULL);
+}
+
+void SDL_QuitEnvironment(void)
+{
+    SDL_Environment *env = SDL_environment;
+
+    if (env) {
+        SDL_environment = NULL;
+        SDL_DestroyEnvironment(env);
+    }
+}
+
+SDL_Environment *SDL_CreateEnvironment(bool populated)
+{
+    SDL_Environment *env = SDL_calloc(1, sizeof(*env));
+    if (!env) {
+        return NULL;
+    }
+
+    env->strings = SDL_CreateHashTable(0, false, SDL_HashString, SDL_KeyMatchString, SDL_DestroyHashKey, NULL);
+    if (!env->strings) {
+        SDL_free(env);
+        return NULL;
+    }
+
+    // Don't fail if we can't create a mutex (e.g. on a single-thread environment)  // !!! FIXME: single-threaded environments should still return a non-NULL, do-nothing object here. Check for failure!
+    env->lock = SDL_CreateMutex();
+
+    if (populated) {
+#ifdef SDL_PLATFORM_WINDOWS
+        LPWCH strings = GetEnvironmentStringsW();
+        if (strings) {
+            for (LPWCH string = strings; *string; string += SDL_wcslen(string) + 1) {
+                char *variable = WIN_StringToUTF8W(string);
+                if (!variable) {
+                    continue;
+                }
+
+                char *value = SDL_strchr(variable, '=');
+                if (!value || value == variable) {
+                    SDL_free(variable);
+                    continue;
+                }
+                *value++ = '\0';
+
+                SDL_InsertIntoHashTable(env->strings, variable, value, true);
+            }
+            FreeEnvironmentStringsW(strings);
+        }
+#else
+#ifdef SDL_PLATFORM_ANDROID
+        // Make sure variables from the application manifest are available
+        Android_JNI_GetManifestEnvironmentVariables();
+#endif
+        char **strings = environ;
+        if (strings) {
+            for (int i = 0; strings[i]; ++i) {
+                char *variable = SDL_strdup(strings[i]);
+                if (!variable) {
+                    continue;
+                }
+
+                char *value = SDL_strchr(variable, '=');
+                if (!value || value == variable) {
+                    SDL_free(variable);
+                    continue;
+                }
+                *value++ = '\0';
+
+                SDL_InsertIntoHashTable(env->strings, variable, value, true);
+            }
+        }
+#endif // SDL_PLATFORM_WINDOWS
+    }
+
+    return env;
+}
+
+const char *SDL_GetEnvironmentVariable(SDL_Environment *env, const char *name)
+{
+    const char *result = NULL;
+
+    if (!env) {
+        return NULL;
+    } else if (!name || *name == '\0') {
+        return NULL;
+    }
+
+    SDL_LockMutex(env->lock);
+    {
+        const char *value;
+
+        if (SDL_FindInHashTable(env->strings, name, (const void **)&value)) {
+            result = SDL_GetPersistentString(value);
+        }
+    }
+    SDL_UnlockMutex(env->lock);
+
+    return result;
+}
+
+typedef struct CountEnvStringsData
+{
+    size_t count;
+    size_t length;
+} CountEnvStringsData;
+
+static bool SDLCALL CountEnvStrings(void *userdata, const SDL_HashTable *table, const void *key, const void *value)
+{
+    CountEnvStringsData *data = (CountEnvStringsData *) userdata;
+    data->length += SDL_strlen((const char *) key) + 1 + SDL_strlen((const char *) value) + 1;
+    data->count++;
+    return true;  // keep iterating.
+}
+
+typedef struct CopyEnvStringsData
+{
+    char **result;
+    char *string;
+    size_t count;
+} CopyEnvStringsData;
+
+static bool SDLCALL CopyEnvStrings(void *userdata, const SDL_HashTable *table, const void *vkey, const void *vvalue)
+{
+    CopyEnvStringsData *data = (CopyEnvStringsData *) userdata;
+    const char *key = (const char *) vkey;
+    const char *value = (const char *) vvalue;
+    size_t len;
+
+    len = SDL_strlen(key);
+    data->result[data->count] = data->string;
+    SDL_memcpy(data->string, key, len);
+    data->string += len;
+    *(data->string++) = '=';
+
+    len = SDL_strlen(value);
+    SDL_memcpy(data->string, value, len);
+    data->string += len;
+    *(data->string++) = '\0';
+    data->count++;
+
+    return true;  // keep iterating.
+}
+
+char **SDL_GetEnvironmentVariables(SDL_Environment *env)
+{
+    char **result = NULL;
+
+    if (!env) {
+        SDL_InvalidParamError("env");
+        return NULL;
+    }
+
+    SDL_LockMutex(env->lock);
+    {
+        // First pass, get the size we need for all the strings
+        CountEnvStringsData countdata = { 0, 0 };
+        SDL_IterateHashTable(env->strings, CountEnvStrings, &countdata);
+
+        // Allocate memory for the strings
+        result = (char **)SDL_malloc((countdata.count + 1) * sizeof(*result) + countdata.length);
+        if (result) {
+            // Second pass, copy the strings
+            char *string = (char *)(result + countdata.count + 1);
+            CopyEnvStringsData cpydata = { result, string, 0 };
+            SDL_IterateHashTable(env->strings, CopyEnvStrings, &cpydata);
+            SDL_assert(countdata.count == cpydata.count);
+            result[cpydata.count] = NULL;
+        }
+    }
+    SDL_UnlockMutex(env->lock);
+
+    return result;
+}
+
+bool SDL_SetEnvironmentVariable(SDL_Environment *env, const char *name, const char *value, bool overwrite)
+{
+    bool result = false;
+
+    if (!env) {
+        return SDL_InvalidParamError("env");
+    } else if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL) {
+        return SDL_InvalidParamError("name");
+    } else if (!value) {
+        return SDL_InvalidParamError("value");
+    }
+
+    SDL_LockMutex(env->lock);
+    {
+        char *string = NULL;
+        if (SDL_asprintf(&string, "%s=%s", name, value) > 0) {
+            const size_t len = SDL_strlen(name);
+            string[len] = '\0';
+            const char *origname = name;
+            name = string;
+            value = string + len + 1;
+            result = SDL_InsertIntoHashTable(env->strings, name, value, overwrite);
+            if (!result) {
+                SDL_free(string);
+                if (!overwrite) {
+                    const void *existing_value = NULL;
+                    // !!! FIXME: InsertIntoHashTable does this lookup too, maybe we should have a means to report that, to avoid duplicate work?
+                    if (SDL_FindInHashTable(env->strings, origname, &existing_value)) {
+                        result = true;  // it already existed, and we refused to overwrite it. Call it success.
+                    }
+                }
+            }
+        }
+    }
+    SDL_UnlockMutex(env->lock);
+
+    return result;
+}
+
+bool SDL_UnsetEnvironmentVariable(SDL_Environment *env, const char *name)
+{
+    bool result = false;
+
+    if (!env) {
+        return SDL_InvalidParamError("env");
+    } else if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL) {
+        return SDL_InvalidParamError("name");
+    }
+
+    SDL_LockMutex(env->lock);
+    {
+        const void *value;
+        if (SDL_FindInHashTable(env->strings, name, &value)) {
+            result = SDL_RemoveFromHashTable(env->strings, name);
+        } else {
+            result = true;
+        }
+    }
+    SDL_UnlockMutex(env->lock);
+
+    return result;
+}
+
+void SDL_DestroyEnvironment(SDL_Environment *env)
+{
+    if (!env || env == SDL_environment) {
+        return;
+    }
+
+    SDL_DestroyMutex(env->lock);
+    SDL_DestroyHashTable(env->strings);
+    SDL_free(env);
+}
+
+// Put a variable into the environment
+// Note: Name may not contain a '=' character. (Reference: http://www.unix.com/man-page/Linux/3/setenv/)
+#ifdef HAVE_LIBC_ENVIRONMENT
+#if defined(HAVE_SETENV)
+int SDL_setenv_unsafe(const char *name, const char *value, int overwrite)
+{
+    // Input validation
+    if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL || !value) {
+        return -1;
+    }
+
+    SDL_SetEnvironmentVariable(SDL_GetEnvironment(), name, value, (overwrite != 0));
+
+    return setenv(name, value, overwrite);
+}
+// We have a real environment table, but no real setenv? Fake it w/ putenv.
+#else
+int SDL_setenv_unsafe(const char *name, const char *value, int overwrite)
+{
+    char *new_variable;
+
+    // Input validation
+    if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL || !value) {
+        return -1;
+    }
+
+    SDL_SetEnvironmentVariable(SDL_GetEnvironment(), name, value, (overwrite != 0));
+
+    if (getenv(name) != NULL) {
+        if (!overwrite) {
+            return 0; // leave the existing one there.
+        }
+    }
+
+    // This leaks. Sorry. Get a better OS so we don't have to do this.
+    SDL_asprintf(&new_variable, "%s=%s", name, value);
+    if (!new_variable) {
+        return -1;
+    }
+    return putenv(new_variable);
+}
+#endif
+#elif defined(HAVE_WIN32_ENVIRONMENT)
+int SDL_setenv_unsafe(const char *name, const char *value, int overwrite)
+{
+    // Input validation
+    if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL || !value) {
+        return -1;
+    }
+
+    SDL_SetEnvironmentVariable(SDL_GetEnvironment(), name, value, (overwrite != 0));
+
+    if (!overwrite) {
+        if (GetEnvironmentVariableA(name, NULL, 0) > 0) {
+            return 0; // asked not to overwrite existing value.
+        }
+    }
+    if (!SetEnvironmentVariableA(name, value)) {
+        return -1;
+    }
+    return 0;
+}
+#else // roll our own
+
+int SDL_setenv_unsafe(const char *name, const char *value, int overwrite)
+{
+    int added;
+    size_t len, i;
+    char **new_env;
+    char *new_variable;
+
+    // Input validation
+    if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL || !value) {
+        return -1;
+    }
+
+    // See if it already exists
+    if (!overwrite && SDL_getenv_unsafe(name)) {
+        return 0;
+    }
+
+    SDL_SetEnvironmentVariable(SDL_GetEnvironment(), name, value, (overwrite != 0));
+
+    // Allocate memory for the variable
+    len = SDL_strlen(name) + SDL_strlen(value) + 2;
+    new_variable = (char *)SDL_malloc(len);
+    if (!new_variable) {
+        return -1;
+    }
+
+    SDL_snprintf(new_variable, len, "%s=%s", name, value);
+    value = new_variable + SDL_strlen(name) + 1;
+    name = new_variable;
+
+    // Actually put it into the environment
+    added = 0;
+    i = 0;
+    if (environ) {
+        // Check to see if it's already there...
+        len = (value - name);
+        for (; environ[i]; ++i) {
+            if (SDL_strncmp(environ[i], name, len) == 0) {
+                // If we found it, just replace the entry
+                SDL_free(environ[i]);
+                environ[i] = new_variable;
+                added = 1;
+                break;
+            }
+        }
+    }
+
+    // Didn't find it in the environment, expand and add
+    if (!added) {
+        new_env = SDL_realloc(environ, (i + 2) * sizeof(char *));
+        if (new_env) {
+            environ = new_env;
+            environ[i++] = new_variable;
+            environ[i++] = (char *)0;
+            added = 1;
+        } else {
+            SDL_free(new_variable);
+        }
+    }
+    return added ? 0 : -1;
+}
+#endif // HAVE_LIBC_ENVIRONMENT
+
+#ifdef HAVE_LIBC_ENVIRONMENT
+#if defined(HAVE_UNSETENV)
+int SDL_unsetenv_unsafe(const char *name)
+{
+    // Input validation
+    if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL) {
+        return -1;
+    }
+
+    SDL_UnsetEnvironmentVariable(SDL_GetEnvironment(), name);
+
+    return unsetenv(name);
+}
+// We have a real environment table, but no unsetenv? Fake it w/ putenv.
+#else
+int SDL_unsetenv_unsafe(const char *name)
+{
+    // Input validation
+    if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL) {
+        return -1;
+    }
+
+    SDL_UnsetEnvironmentVariable(SDL_GetEnvironment(), name);
+
+    // Hope this environment uses the non-standard extension of removing the environment variable if it has no '='
+    return putenv(name);
+}
+#endif
+#elif defined(HAVE_WIN32_ENVIRONMENT)
+int SDL_unsetenv_unsafe(const char *name)
+{
+    // Input validation
+    if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL) {
+        return -1;
+    }
+
+    SDL_UnsetEnvironmentVariable(SDL_GetEnvironment(), name);
+
+    if (!SetEnvironmentVariableA(name, NULL)) {
+        return -1;
+    }
+    return 0;
+}
+#else
+int SDL_unsetenv_unsafe(const char *name)
+{
+    size_t len, i;
+
+    // Input validation
+    if (!name || *name == '\0' || SDL_strchr(name, '=') != NULL) {
+        return -1;
+    }
+
+    SDL_UnsetEnvironmentVariable(SDL_GetEnvironment(), name);
+
+    if (environ) {
+        len = SDL_strlen(name);
+        for (i = 0; environ[i]; ++i) {
+            if ((SDL_strncmp(environ[i], name, len) == 0) &&
+                (environ[i][len] == '=')) {
+                // Just clear out this entry for now
+                *environ[i] = '\0';
+                break;
+            }
+        }
+    }
+    return 0;
+}
+#endif // HAVE_LIBC_ENVIRONMENT
+
+// Retrieve a variable named "name" from the environment
+#ifdef HAVE_LIBC_ENVIRONMENT
+const char *SDL_getenv_unsafe(const char *name)
+{
+#ifdef SDL_PLATFORM_ANDROID
+    // Make sure variables from the application manifest are available
+    Android_JNI_GetManifestEnvironmentVariables();
+#endif
+
+    // Input validation
+    if (!name || *name == '\0') {
+        return NULL;
+    }
+
+    return getenv(name);
+}
+#elif defined(HAVE_WIN32_ENVIRONMENT)
+const char *SDL_getenv_unsafe(const char *name)
+{
+    DWORD length, maxlen = 0;
+    char *string = NULL;
+    const char *result = NULL;
+
+    // Input validation
+    if (!name || *name == '\0') {
+        return NULL;
+    }
+
+    for ( ; ; ) {
+        SetLastError(ERROR_SUCCESS);
+        length = GetEnvironmentVariableA(name, string, maxlen);
+
+        if (length > maxlen) {
+            char *temp = (char *)SDL_realloc(string, length);
+            if (!temp)  {
+                return NULL;
+            }
+            string = temp;
+            maxlen = length;
+        } else {
+            if (GetLastError() != ERROR_SUCCESS) {
+                if (string) {
+                    SDL_free(string);
+                }
+                return NULL;
+            }
+            break;
+        }
+    }
+    if (string) {
+        result = SDL_GetPersistentString(string);
+        SDL_free(string);
+    }
+    return result;
+}
+#else
+const char *SDL_getenv_unsafe(const char *name)
+{
+    size_t len, i;
+    const char *value = NULL;
+
+    // Input validation
+    if (!name || *name == '\0') {
+        return NULL;
+    }
+
+    if (environ) {
+        len = SDL_strlen(name);
+        for (i = 0; environ[i]; ++i) {
+            if ((SDL_strncmp(environ[i], name, len) == 0) &&
+                (environ[i][len] == '=')) {
+                value = &environ[i][len + 1];
+                break;
+            }
+        }
+    }
+    return value;
+}
+#endif // HAVE_LIBC_ENVIRONMENT
+
+const char *SDL_getenv(const char *name)
+{
+    return SDL_GetEnvironmentVariable(SDL_GetEnvironment(), name);
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_getenv_c.h b/contrib/SDL-3.2.8/src/stdlib/SDL_getenv_c.h
new file mode 100644
index 0000000..9cf997d
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_getenv_c.h
@@ -0,0 +1,24 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+extern bool SDL_InitEnvironment(void);
+extern void SDL_QuitEnvironment(void);
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_iconv.c b/contrib/SDL-3.2.8/src/stdlib/SDL_iconv.c
new file mode 100644
index 0000000..fbea033
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_iconv.c
@@ -0,0 +1,860 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+// This file contains portable iconv functions for SDL
+
+#if defined(HAVE_ICONV) && defined(HAVE_ICONV_H)
+#ifndef SDL_USE_LIBICONV
+// Define LIBICONV_PLUG to use iconv from the base instead of ports and avoid linker errors.
+#define LIBICONV_PLUG 1
+#endif
+#include <iconv.h>
+#include <errno.h>
+
+SDL_COMPILE_TIME_ASSERT(iconv_t, sizeof(iconv_t) <= sizeof(SDL_iconv_t));
+
+SDL_iconv_t SDL_iconv_open(const char *tocode, const char *fromcode)
+{
+    return (SDL_iconv_t)((uintptr_t)iconv_open(tocode, fromcode));
+}
+
+int SDL_iconv_close(SDL_iconv_t cd)
+{
+    if ((size_t)cd == SDL_ICONV_ERROR) {
+        return -1;
+    }
+    return iconv_close((iconv_t)((uintptr_t)cd));
+}
+
+size_t SDL_iconv(SDL_iconv_t cd,
+          const char **inbuf, size_t *inbytesleft,
+          char **outbuf, size_t *outbytesleft)
+{
+    if ((size_t)cd == SDL_ICONV_ERROR) {
+        return SDL_ICONV_ERROR;
+    }
+    /* iconv's second parameter may or may not be `const char const *` depending on the
+       C runtime's whims. Casting to void * seems to make everyone happy, though. */
+    const size_t retCode = iconv((iconv_t)((uintptr_t)cd), (void *)inbuf, inbytesleft, outbuf, outbytesleft);
+    if (retCode == (size_t)-1) {
+        switch (errno) {
+        case E2BIG:
+            return SDL_ICONV_E2BIG;
+        case EILSEQ:
+            return SDL_ICONV_EILSEQ;
+        case EINVAL:
+            return SDL_ICONV_EINVAL;
+        default:
+            return SDL_ICONV_ERROR;
+        }
+    }
+    return retCode;
+}
+
+#else
+
+/* Lots of useful information on Unicode at:
+    http://www.cl.cam.ac.uk/~mgk25/unicode.html
+*/
+
+#define UNICODE_BOM 0xFEFF
+
+#define UNKNOWN_ASCII   '?'
+#define UNKNOWN_UNICODE 0xFFFD
+
+enum
+{
+    ENCODING_UNKNOWN,
+    ENCODING_ASCII,
+    ENCODING_LATIN1,
+    ENCODING_UTF8,
+    ENCODING_UTF16, // Needs byte order marker
+    ENCODING_UTF16BE,
+    ENCODING_UTF16LE,
+    ENCODING_UTF32, // Needs byte order marker
+    ENCODING_UTF32BE,
+    ENCODING_UTF32LE,
+    ENCODING_UCS2BE,
+    ENCODING_UCS2LE,
+    ENCODING_UCS4BE,
+    ENCODING_UCS4LE,
+};
+#if SDL_BYTEORDER == SDL_BIG_ENDIAN
+#define ENCODING_UTF16NATIVE ENCODING_UTF16BE
+#define ENCODING_UTF32NATIVE ENCODING_UTF32BE
+#define ENCODING_UCS2NATIVE  ENCODING_UCS2BE
+#define ENCODING_UCS4NATIVE  ENCODING_UCS4BE
+#else
+#define ENCODING_UTF16NATIVE ENCODING_UTF16LE
+#define ENCODING_UTF32NATIVE ENCODING_UTF32LE
+#define ENCODING_UCS2NATIVE  ENCODING_UCS2LE
+#define ENCODING_UCS4NATIVE  ENCODING_UCS4LE
+#endif
+
+struct SDL_iconv_data_t
+{
+    int src_fmt;
+    int dst_fmt;
+};
+
+static struct
+{
+    const char *name;
+    int format;
+} encodings[] = {
+    /* *INDENT-OFF* */ // clang-format off
+    { "ASCII", ENCODING_ASCII },
+    { "US-ASCII", ENCODING_ASCII },
+    { "8859-1", ENCODING_LATIN1 },
+    { "ISO-8859-1", ENCODING_LATIN1 },
+#if defined(SDL_PLATFORM_WINDOWS) || defined(SDL_PLATFORM_OS2)
+    { "WCHAR_T", ENCODING_UTF16LE },
+#else
+    { "WCHAR_T", ENCODING_UCS4NATIVE },
+#endif
+    { "UTF8", ENCODING_UTF8 },
+    { "UTF-8", ENCODING_UTF8 },
+    { "UTF16", ENCODING_UTF16 },
+    { "UTF-16", ENCODING_UTF16 },
+    { "UTF16BE", ENCODING_UTF16BE },
+    { "UTF-16BE", ENCODING_UTF16BE },
+    { "UTF16LE", ENCODING_UTF16LE },
+    { "UTF-16LE", ENCODING_UTF16LE },
+    { "UTF32", ENCODING_UTF32 },
+    { "UTF-32", ENCODING_UTF32 },
+    { "UTF32BE", ENCODING_UTF32BE },
+    { "UTF-32BE", ENCODING_UTF32BE },
+    { "UTF32LE", ENCODING_UTF32LE },
+    { "UTF-32LE", ENCODING_UTF32LE },
+    { "UCS2", ENCODING_UCS2BE },
+    { "UCS-2", ENCODING_UCS2BE },
+    { "UCS-2LE", ENCODING_UCS2LE },
+    { "UCS-2BE", ENCODING_UCS2BE },
+    { "UCS-2-INTERNAL", ENCODING_UCS2NATIVE },
+    { "UCS4", ENCODING_UCS4BE },
+    { "UCS-4", ENCODING_UCS4BE },
+    { "UCS-4LE", ENCODING_UCS4LE },
+    { "UCS-4BE", ENCODING_UCS4BE },
+    { "UCS-4-INTERNAL", ENCODING_UCS4NATIVE },
+/* *INDENT-ON* */ // clang-format on
+};
+
+static const char *getlocale(char *buffer, size_t bufsize)
+{
+    const char *lang;
+    char *ptr;
+
+    lang = SDL_getenv("LC_ALL");
+    if (!lang) {
+        lang = SDL_getenv("LC_CTYPE");
+    }
+    if (!lang) {
+        lang = SDL_getenv("LC_MESSAGES");
+    }
+    if (!lang) {
+        lang = SDL_getenv("LANG");
+    }
+    if (!lang || !*lang || SDL_strcmp(lang, "C") == 0) {
+        lang = "ASCII";
+    }
+
+    // We need to trim down strings like "en_US.UTF-8@blah" to "UTF-8"
+    ptr = SDL_strchr(lang, '.');
+    if (ptr) {
+        lang = ptr + 1;
+    }
+
+    SDL_strlcpy(buffer, lang, bufsize);
+    ptr = SDL_strchr(buffer, '@');
+    if (ptr) {
+        *ptr = '\0'; // chop end of string.
+    }
+
+    return buffer;
+}
+
+SDL_iconv_t SDL_iconv_open(const char *tocode, const char *fromcode)
+{
+    int src_fmt = ENCODING_UNKNOWN;
+    int dst_fmt = ENCODING_UNKNOWN;
+    int i;
+    char fromcode_buffer[64];
+    char tocode_buffer[64];
+
+    if (!fromcode || !*fromcode) {
+        fromcode = getlocale(fromcode_buffer, sizeof(fromcode_buffer));
+    }
+    if (!tocode || !*tocode) {
+        tocode = getlocale(tocode_buffer, sizeof(tocode_buffer));
+    }
+    for (i = 0; i < SDL_arraysize(encodings); ++i) {
+        if (SDL_strcasecmp(fromcode, encodings[i].name) == 0) {
+            src_fmt = encodings[i].format;
+            if (dst_fmt != ENCODING_UNKNOWN) {
+                break;
+            }
+        }
+        if (SDL_strcasecmp(tocode, encodings[i].name) == 0) {
+            dst_fmt = encodings[i].format;
+            if (src_fmt != ENCODING_UNKNOWN) {
+                break;
+            }
+        }
+    }
+    if (src_fmt != ENCODING_UNKNOWN && dst_fmt != ENCODING_UNKNOWN) {
+        SDL_iconv_t cd = (SDL_iconv_t)SDL_malloc(sizeof(*cd));
+        if (cd) {
+            cd->src_fmt = src_fmt;
+            cd->dst_fmt = dst_fmt;
+            return cd;
+        }
+    }
+    return (SDL_iconv_t)-1;
+}
+
+size_t SDL_iconv(SDL_iconv_t cd,
+          const char **inbuf, size_t *inbytesleft,
+          char **outbuf, size_t *outbytesleft)
+{
+    // For simplicity, we'll convert everything to and from UCS-4
+    const char *src;
+    char *dst;
+    size_t srclen, dstlen;
+    Uint32 ch = 0;
+    size_t total;
+
+    if ((size_t)cd == SDL_ICONV_ERROR) {
+        return SDL_ICONV_ERROR;
+    }
+    if (!inbuf || !*inbuf) {
+        // Reset the context
+        return 0;
+    }
+    if (!outbuf || !*outbuf || !outbytesleft || !*outbytesleft) {
+        return SDL_ICONV_E2BIG;
+    }
+    src = *inbuf;
+    srclen = (inbytesleft ? *inbytesleft : 0);
+    dst = *outbuf;
+    dstlen = *outbytesleft;
+
+    switch (cd->src_fmt) {
+    case ENCODING_UTF16:
+        // Scan for a byte order marker
+        {
+            Uint8 *p = (Uint8 *)src;
+            size_t n = srclen / 2;
+            while (n) {
+                if (p[0] == 0xFF && p[1] == 0xFE) {
+                    cd->src_fmt = ENCODING_UTF16BE;
+                    break;
+                } else if (p[0] == 0xFE && p[1] == 0xFF) {
+                    cd->src_fmt = ENCODING_UTF16LE;
+                    break;
+                }
+                p += 2;
+                --n;
+            }
+            if (n == 0) {
+                // We can't tell, default to host order
+                cd->src_fmt = ENCODING_UTF16NATIVE;
+            }
+        }
+        break;
+    case ENCODING_UTF32:
+        // Scan for a byte order marker
+        {
+            Uint8 *p = (Uint8 *)src;
+            size_t n = srclen / 4;
+            while (n) {
+                if (p[0] == 0xFF && p[1] == 0xFE &&
+                    p[2] == 0x00 && p[3] == 0x00) {
+                    cd->src_fmt = ENCODING_UTF32BE;
+                    break;
+                } else if (p[0] == 0x00 && p[1] == 0x00 &&
+                           p[2] == 0xFE && p[3] == 0xFF) {
+                    cd->src_fmt = ENCODING_UTF32LE;
+                    break;
+                }
+                p += 4;
+                --n;
+            }
+            if (n == 0) {
+                // We can't tell, default to host order
+                cd->src_fmt = ENCODING_UTF32NATIVE;
+            }
+        }
+        break;
+    }
+
+    switch (cd->dst_fmt) {
+    case ENCODING_UTF16:
+        // Default to host order, need to add byte order marker
+        if (dstlen < 2) {
+            return SDL_ICONV_E2BIG;
+        }
+        *(Uint16 *)dst = UNICODE_BOM;
+        dst += 2;
+        dstlen -= 2;
+        cd->dst_fmt = ENCODING_UTF16NATIVE;
+        break;
+    case ENCODING_UTF32:
+        // Default to host order, need to add byte order marker
+        if (dstlen < 4) {
+            return SDL_ICONV_E2BIG;
+        }
+        *(Uint32 *)dst = UNICODE_BOM;
+        dst += 4;
+        dstlen -= 4;
+        cd->dst_fmt = ENCODING_UTF32NATIVE;
+        break;
+    }
+
+    total = 0;
+    while (srclen > 0) {
+        // Decode a character
+        switch (cd->src_fmt) {
+        case ENCODING_ASCII:
+        {
+            Uint8 *p = (Uint8 *)src;
+            ch = (Uint32)(p[0] & 0x7F);
+            ++src;
+            --srclen;
+        } break;
+        case ENCODING_LATIN1:
+        {
+            Uint8 *p = (Uint8 *)src;
+            ch = (Uint32)p[0];
+            ++src;
+            --srclen;
+        } break;
+        case ENCODING_UTF8: // RFC 3629
+        {
+            Uint8 *p = (Uint8 *)src;
+            size_t left = 0;
+            bool overlong = false;
+            if (p[0] >= 0xF0) {
+                if ((p[0] & 0xF8) != 0xF0) {
+                    /* Skip illegal sequences
+                       return SDL_ICONV_EILSEQ;
+                     */
+                    ch = UNKNOWN_UNICODE;
+                } else {
+                    if (p[0] == 0xF0 && srclen > 1 && (p[1] & 0xF0) == 0x80) {
+                        overlong = true;
+                    }
+                    ch = (Uint32)(p[0] & 0x07);
+                    left = 3;
+                }
+            } else if (p[0] >= 0xE0) {
+                if ((p[0] & 0xF0) != 0xE0) {
+                    /* Skip illegal sequences
+                       return SDL_ICONV_EILSEQ;
+                     */
+                    ch = UNKNOWN_UNICODE;
+                } else {
+                    if (p[0] == 0xE0 && srclen > 1 && (p[1] & 0xE0) == 0x80) {
+                        overlong = true;
+                    }
+                    ch = (Uint32)(p[0] & 0x0F);
+                    left = 2;
+                }
+            } else if (p[0] >= 0xC0) {
+                if ((p[0] & 0xE0) != 0xC0) {
+                    /* Skip illegal sequences
+                       return SDL_ICONV_EILSEQ;
+                     */
+                    ch = UNKNOWN_UNICODE;
+                } else {
+                    if ((p[0] & 0xDE) == 0xC0) {
+                        overlong = true;
+                    }
+                    ch = (Uint32)(p[0] & 0x1F);
+                    left = 1;
+                }
+            } else {
+                if (p[0] & 0x80) {
+                    /* Skip illegal sequences
+                       return SDL_ICONV_EILSEQ;
+                     */
+                    ch = UNKNOWN_UNICODE;
+                } else {
+                    ch = (Uint32)p[0];
+                }
+            }
+            ++src;
+            --srclen;
+            if (srclen < left) {
+                return SDL_ICONV_EINVAL;
+            }
+            while (left--) {
+                ++p;
+                if ((p[0] & 0xC0) != 0x80) {
+                    /* Skip illegal sequences
+                       return SDL_ICONV_EILSEQ;
+                     */
+                    ch = UNKNOWN_UNICODE;
+                    break;
+                }
+                ch <<= 6;
+                ch |= (p[0] & 0x3F);
+                ++src;
+                --srclen;
+            }
+            if (overlong) {
+                /* Potential security risk
+                   return SDL_ICONV_EILSEQ;
+                 */
+                ch = UNKNOWN_UNICODE;
+            }
+            if ((ch >= 0xD800 && ch <= 0xDFFF) ||
+                (ch == 0xFFFE || ch == 0xFFFF) || ch > 0x10FFFF) {
+                /* Skip illegal sequences
+                   return SDL_ICONV_EILSEQ;
+                 */
+                ch = UNKNOWN_UNICODE;
+            }
+        } break;
+        case ENCODING_UTF16BE: // RFC 2781
+        {
+            Uint8 *p = (Uint8 *)src;
+            Uint16 W1, W2;
+            if (srclen < 2) {
+                return SDL_ICONV_EINVAL;
+            }
+            W1 = ((Uint16)p[0] << 8) | (Uint16)p[1];
+            src += 2;
+            srclen -= 2;
+            if (W1 < 0xD800 || W1 > 0xDFFF) {
+                ch = (Uint32)W1;
+                break;
+            }
+            if (W1 > 0xDBFF) {
+                /* Skip illegal sequences
+                   return SDL_ICONV_EILSEQ;
+                 */
+                ch = UNKNOWN_UNICODE;
+                break;
+            }
+            if (srclen < 2) {
+                return SDL_ICONV_EINVAL;
+            }
+            p = (Uint8 *)src;
+            W2 = ((Uint16)p[0] << 8) | (Uint16)p[1];
+            src += 2;
+            srclen -= 2;
+            if (W2 < 0xDC00 || W2 > 0xDFFF) {
+                /* Skip illegal sequences
+                   return SDL_ICONV_EILSEQ;
+                 */
+                ch = UNKNOWN_UNICODE;
+                break;
+            }
+            ch = (((Uint32)(W1 & 0x3FF) << 10) |
+                  (Uint32)(W2 & 0x3FF)) +
+                 0x10000;
+        } break;
+        case ENCODING_UTF16LE: // RFC 2781
+        {
+            Uint8 *p = (Uint8 *)src;
+            Uint16 W1, W2;
+            if (srclen < 2) {
+                return SDL_ICONV_EINVAL;
+            }
+            W1 = ((Uint16)p[1] << 8) | (Uint16)p[0];
+            src += 2;
+            srclen -= 2;
+            if (W1 < 0xD800 || W1 > 0xDFFF) {
+                ch = (Uint32)W1;
+                break;
+            }
+            if (W1 > 0xDBFF) {
+                /* Skip illegal sequences
+                   return SDL_ICONV_EILSEQ;
+                 */
+                ch = UNKNOWN_UNICODE;
+                break;
+            }
+            if (srclen < 2) {
+                return SDL_ICONV_EINVAL;
+            }
+            p = (Uint8 *)src;
+            W2 = ((Uint16)p[1] << 8) | (Uint16)p[0];
+            src += 2;
+            srclen -= 2;
+            if (W2 < 0xDC00 || W2 > 0xDFFF) {
+                /* Skip illegal sequences
+                   return SDL_ICONV_EILSEQ;
+                 */
+                ch = UNKNOWN_UNICODE;
+                break;
+            }
+            ch = (((Uint32)(W1 & 0x3FF) << 10) |
+                  (Uint32)(W2 & 0x3FF)) +
+                 0x10000;
+        } break;
+        case ENCODING_UCS2LE:
+        {
+            Uint8 *p = (Uint8 *)src;
+            if (srclen < 2) {
+                return SDL_ICONV_EINVAL;
+            }
+            ch = ((Uint32)p[1] << 8) | (Uint32)p[0];
+            src += 2;
+            srclen -= 2;
+        } break;
+        case ENCODING_UCS2BE:
+        {
+            Uint8 *p = (Uint8 *)src;
+            if (srclen < 2) {
+                return SDL_ICONV_EINVAL;
+            }
+            ch = ((Uint32)p[0] << 8) | (Uint32)p[1];
+            src += 2;
+            srclen -= 2;
+        } break;
+        case ENCODING_UCS4BE:
+        case ENCODING_UTF32BE:
+        {
+            Uint8 *p = (Uint8 *)src;
+            if (srclen < 4) {
+                return SDL_ICONV_EINVAL;
+            }
+            ch = ((Uint32)p[0] << 24) |
+                 ((Uint32)p[1] << 16) |
+                 ((Uint32)p[2] << 8) | (Uint32)p[3];
+            src += 4;
+            srclen -= 4;
+        } break;
+        case ENCODING_UCS4LE:
+        case ENCODING_UTF32LE:
+        {
+            Uint8 *p = (Uint8 *)src;
+            if (srclen < 4) {
+                return SDL_ICONV_EINVAL;
+            }
+            ch = ((Uint32)p[3] << 24) |
+                 ((Uint32)p[2] << 16) |
+                 ((Uint32)p[1] << 8) | (Uint32)p[0];
+            src += 4;
+            srclen -= 4;
+        } break;
+        }
+
+        // Encode a character
+        switch (cd->dst_fmt) {
+        case ENCODING_ASCII:
+        {
+            Uint8 *p = (Uint8 *)dst;
+            if (dstlen < 1) {
+                return SDL_ICONV_E2BIG;
+            }
+            if (ch > 0x7F) {
+                *p = UNKNOWN_ASCII;
+            } else {
+                *p = (Uint8)ch;
+            }
+            ++dst;
+            --dstlen;
+        } break;
+        case ENCODING_LATIN1:
+        {
+            Uint8 *p = (Uint8 *)dst;
+            if (dstlen < 1) {
+                return SDL_ICONV_E2BIG;
+            }
+            if (ch > 0xFF) {
+                *p = UNKNOWN_ASCII;
+            } else {
+                *p = (Uint8)ch;
+            }
+            ++dst;
+            --dstlen;
+        } break;
+        case ENCODING_UTF8: // RFC 3629
+        {
+            Uint8 *p = (Uint8 *)dst;
+            if (ch > 0x10FFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            if (ch <= 0x7F) {
+                if (dstlen < 1) {
+                    return SDL_ICONV_E2BIG;
+                }
+                *p = (Uint8)ch;
+                ++dst;
+                --dstlen;
+            } else if (ch <= 0x7FF) {
+                if (dstlen < 2) {
+                    return SDL_ICONV_E2BIG;
+                }
+                p[0] = 0xC0 | (Uint8)((ch >> 6) & 0x1F);
+                p[1] = 0x80 | (Uint8)(ch & 0x3F);
+                dst += 2;
+                dstlen -= 2;
+            } else if (ch <= 0xFFFF) {
+                if (dstlen < 3) {
+                    return SDL_ICONV_E2BIG;
+                }
+                p[0] = 0xE0 | (Uint8)((ch >> 12) & 0x0F);
+                p[1] = 0x80 | (Uint8)((ch >> 6) & 0x3F);
+                p[2] = 0x80 | (Uint8)(ch & 0x3F);
+                dst += 3;
+                dstlen -= 3;
+            } else {
+                if (dstlen < 4) {
+                    return SDL_ICONV_E2BIG;
+                }
+                p[0] = 0xF0 | (Uint8)((ch >> 18) & 0x07);
+                p[1] = 0x80 | (Uint8)((ch >> 12) & 0x3F);
+                p[2] = 0x80 | (Uint8)((ch >> 6) & 0x3F);
+                p[3] = 0x80 | (Uint8)(ch & 0x3F);
+                dst += 4;
+                dstlen -= 4;
+            }
+        } break;
+        case ENCODING_UTF16BE: // RFC 2781
+        {
+            Uint8 *p = (Uint8 *)dst;
+            if (ch > 0x10FFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            if (ch < 0x10000) {
+                if (dstlen < 2) {
+                    return SDL_ICONV_E2BIG;
+                }
+                p[0] = (Uint8)(ch >> 8);
+                p[1] = (Uint8)ch;
+                dst += 2;
+                dstlen -= 2;
+            } else {
+                Uint16 W1, W2;
+                if (dstlen < 4) {
+                    return SDL_ICONV_E2BIG;
+                }
+                ch = ch - 0x10000;
+                W1 = 0xD800 | (Uint16)((ch >> 10) & 0x3FF);
+                W2 = 0xDC00 | (Uint16)(ch & 0x3FF);
+                p[0] = (Uint8)(W1 >> 8);
+                p[1] = (Uint8)W1;
+                p[2] = (Uint8)(W2 >> 8);
+                p[3] = (Uint8)W2;
+                dst += 4;
+                dstlen -= 4;
+            }
+        } break;
+        case ENCODING_UTF16LE: // RFC 2781
+        {
+            Uint8 *p = (Uint8 *)dst;
+            if (ch > 0x10FFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            if (ch < 0x10000) {
+                if (dstlen < 2) {
+                    return SDL_ICONV_E2BIG;
+                }
+                p[1] = (Uint8)(ch >> 8);
+                p[0] = (Uint8)ch;
+                dst += 2;
+                dstlen -= 2;
+            } else {
+                Uint16 W1, W2;
+                if (dstlen < 4) {
+                    return SDL_ICONV_E2BIG;
+                }
+                ch = ch - 0x10000;
+                W1 = 0xD800 | (Uint16)((ch >> 10) & 0x3FF);
+                W2 = 0xDC00 | (Uint16)(ch & 0x3FF);
+                p[1] = (Uint8)(W1 >> 8);
+                p[0] = (Uint8)W1;
+                p[3] = (Uint8)(W2 >> 8);
+                p[2] = (Uint8)W2;
+                dst += 4;
+                dstlen -= 4;
+            }
+        } break;
+        case ENCODING_UCS2BE:
+        {
+            Uint8 *p = (Uint8 *)dst;
+            if (ch > 0xFFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            if (dstlen < 2) {
+                return SDL_ICONV_E2BIG;
+            }
+            p[0] = (Uint8)(ch >> 8);
+            p[1] = (Uint8)ch;
+            dst += 2;
+            dstlen -= 2;
+        } break;
+        case ENCODING_UCS2LE:
+        {
+            Uint8 *p = (Uint8 *)dst;
+            if (ch > 0xFFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            if (dstlen < 2) {
+                return SDL_ICONV_E2BIG;
+            }
+            p[1] = (Uint8)(ch >> 8);
+            p[0] = (Uint8)ch;
+            dst += 2;
+            dstlen -= 2;
+        } break;
+        case ENCODING_UTF32BE:
+            if (ch > 0x10FFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            SDL_FALLTHROUGH;
+        case ENCODING_UCS4BE:
+            if (ch > 0x7FFFFFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            {
+                Uint8 *p = (Uint8 *)dst;
+                if (dstlen < 4) {
+                    return SDL_ICONV_E2BIG;
+                }
+                p[0] = (Uint8)(ch >> 24);
+                p[1] = (Uint8)(ch >> 16);
+                p[2] = (Uint8)(ch >> 8);
+                p[3] = (Uint8)ch;
+                dst += 4;
+                dstlen -= 4;
+            }
+            break;
+        case ENCODING_UTF32LE:
+            if (ch > 0x10FFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            SDL_FALLTHROUGH;
+        case ENCODING_UCS4LE:
+            if (ch > 0x7FFFFFFF) {
+                ch = UNKNOWN_UNICODE;
+            }
+            {
+                Uint8 *p = (Uint8 *)dst;
+                if (dstlen < 4) {
+                    return SDL_ICONV_E2BIG;
+                }
+                p[3] = (Uint8)(ch >> 24);
+                p[2] = (Uint8)(ch >> 16);
+                p[1] = (Uint8)(ch >> 8);
+                p[0] = (Uint8)ch;
+                dst += 4;
+                dstlen -= 4;
+            }
+            break;
+        }
+
+        // Update state
+        *inbuf = src;
+        *inbytesleft = srclen;
+        *outbuf = dst;
+        *outbytesleft = dstlen;
+        ++total;
+    }
+    return total;
+}
+
+int SDL_iconv_close(SDL_iconv_t cd)
+{
+    if (cd == (SDL_iconv_t)-1) {
+        return -1;
+    }
+    SDL_free(cd);
+    return 0;
+}
+
+#endif // !HAVE_ICONV
+
+char *SDL_iconv_string(const char *tocode, const char *fromcode, const char *inbuf, size_t inbytesleft)
+{
+    SDL_iconv_t cd;
+    char *string;
+    size_t stringsize;
+    char *outbuf;
+    size_t outbytesleft;
+    size_t retCode = 0;
+
+    if (!tocode || !*tocode) {
+        tocode = "UTF-8";
+    }
+    if (!fromcode || !*fromcode) {
+        fromcode = "UTF-8";
+    }
+    cd = SDL_iconv_open(tocode, fromcode);
+    if (cd == (SDL_iconv_t)-1) {
+        return NULL;
+    }
+
+    stringsize = inbytesleft;
+    string = (char *)SDL_malloc(stringsize + sizeof(Uint32));
+    if (!string) {
+        SDL_iconv_close(cd);
+        return NULL;
+    }
+    outbuf = string;
+    outbytesleft = stringsize;
+    SDL_memset(outbuf, 0, sizeof(Uint32));
+
+    while (inbytesleft > 0) {
+        const size_t oldinbytesleft = inbytesleft;
+        retCode = SDL_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+        switch (retCode) {
+        case SDL_ICONV_E2BIG:
+        {
+            const ptrdiff_t diff = (ptrdiff_t) (outbuf - string);
+            char *oldstring = string;
+            stringsize *= 2;
+            string = (char *)SDL_realloc(string, stringsize + sizeof(Uint32));
+            if (!string) {
+                SDL_free(oldstring);
+                SDL_iconv_close(cd);
+                return NULL;
+            }
+            outbuf = string + diff;
+            outbytesleft = stringsize - diff;
+            SDL_memset(outbuf, 0, sizeof(Uint32));
+            continue;
+        }
+        case SDL_ICONV_EILSEQ:
+            // Try skipping some input data - not perfect, but...
+            ++inbuf;
+            --inbytesleft;
+            break;
+        case SDL_ICONV_EINVAL:
+        case SDL_ICONV_ERROR:
+            // We can't continue...
+            inbytesleft = 0;
+            break;
+        }
+        // Avoid infinite loops when nothing gets converted
+        if (oldinbytesleft == inbytesleft) {
+            break;
+        }
+    }
+    SDL_memset(outbuf, 0, sizeof(Uint32));
+    SDL_iconv_close(cd);
+
+    return string;
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_malloc.c b/contrib/SDL-3.2.8/src/stdlib/SDL_malloc.c
new file mode 100644
index 0000000..008675f
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_malloc.c
@@ -0,0 +1,6507 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+/* This file contains portable memory management functions for SDL */
+
+#ifndef HAVE_MALLOC
+#define LACKS_SYS_TYPES_H
+#define LACKS_STDIO_H
+#define LACKS_STRINGS_H
+#define LACKS_STRING_H
+#define LACKS_STDLIB_H
+#define ABORT
+#define NO_MALLOC_STATS 1
+#define USE_LOCKS 1
+#define USE_DL_PREFIX
+
+/*
+  This is a version (aka dlmalloc) of malloc/free/realloc written by
+  Doug Lea and released to the public domain, as explained at
+  http://creativecommons.org/publicdomain/zero/1.0/ Send questions,
+  comments, complaints, performance data, etc to dl@cs.oswego.edu
+
+* Version 2.8.6 Wed Aug 29 06:57:58 2012  Doug Lea
+   Note: There may be an updated version of this malloc obtainable at
+           ftp://gee.cs.oswego.edu/pub/misc/malloc.c
+         Check before installing!
+
+* Quickstart
+
+  This library is all in one file to simplify the most common usage:
+  ftp it, compile it (-O3), and link it into another program. All of
+  the compile-time options default to reasonable values for use on
+  most platforms.  You might later want to step through various
+  compile-time and dynamic tuning options.
+
+  For convenience, an include file for code using this malloc is at:
+     ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.6.h
+  You don't really need this .h file unless you call functions not
+  defined in your system include files.  The .h file contains only the
+  excerpts from this file needed for using this malloc on ANSI C/C++
+  systems, so long as you haven't changed compile-time options about
+  naming and tuning parameters.  If you do, then you can create your
+  own malloc.h that does include all settings by cutting at the point
+  indicated below. Note that you may already by default be using a C
+  library containing a malloc that is based on some version of this
+  malloc (for example in linux). You might still want to use the one
+  in this file to customize settings or to avoid overheads associated
+  with library versions.
+
+* Vital statistics:
+
+  Supported pointer/size_t representation:       4 or 8 bytes
+       size_t MUST be an unsigned type of the same width as
+       pointers. (If you are using an ancient system that declares
+       size_t as a signed type, or need it to be a different width
+       than pointers, you can use a previous release of this malloc
+       (e.g. 2.7.2) supporting these.)
+
+  Alignment:                                     8 bytes (minimum)
+       This suffices for nearly all current machines and C compilers.
+       However, you can define MALLOC_ALIGNMENT to be wider than this
+       if necessary (up to 128bytes), at the expense of using more space.
+
+  Minimum overhead per allocated chunk:   4 or  8 bytes (if 4byte sizes)
+                                          8 or 16 bytes (if 8byte sizes)
+       Each malloced chunk has a hidden word of overhead holding size
+       and status information, and additional cross-check word
+       if FOOTERS is defined.
+
+  Minimum allocated size: 4-byte ptrs:  16 bytes    (including overhead)
+                          8-byte ptrs:  32 bytes    (including overhead)
+
+       Even a request for zero bytes (i.e., malloc(0)) returns a
+       pointer to something of the minimum allocatable size.
+       The maximum overhead wastage (i.e., number of extra bytes
+       allocated than were requested in malloc) is less than or equal
+       to the minimum size, except for requests >= mmap_threshold that
+       are serviced via mmap(), where the worst case wastage is about
+       32 bytes plus the remainder from a system page (the minimal
+       mmap unit); typically 4096 or 8192 bytes.
+
+  Security: static-safe; optionally more or less
+       The "security" of malloc refers to the ability of malicious
+       code to accentuate the effects of errors (for example, freeing
+       space that is not currently malloc'ed or overwriting past the
+       ends of chunks) in code that calls malloc.  This malloc
+       guarantees not to modify any memory locations below the base of
+       heap, i.e., static variables, even in the presence of usage
+       errors.  The routines additionally detect most improper frees
+       and reallocs.  All this holds as long as the static bookkeeping
+       for malloc itself is not corrupted by some other means.  This
+       is only one aspect of security -- these checks do not, and
+       cannot, detect all possible programming errors.
+
+       If FOOTERS is defined nonzero, then each allocated chunk
+       carries an additional check word to verify that it was malloced
+       from its space.  These check words are the same within each
+       execution of a program using malloc, but differ across
+       executions, so externally crafted fake chunks cannot be
+       freed. This improves security by rejecting frees/reallocs that
+       could corrupt heap memory, in addition to the checks preventing
+       writes to statics that are always on.  This may further improve
+       security at the expense of time and space overhead.  (Note that
+       FOOTERS may also be worth using with MSPACES.)
+
+       By default detected errors cause the program to abort (calling
+       "abort()"). You can override this to instead proceed past
+       errors by defining PROCEED_ON_ERROR.  In this case, a bad free
+       has no effect, and a malloc that encounters a bad address
+       caused by user overwrites will ignore the bad address by
+       dropping pointers and indices to all known memory. This may
+       be appropriate for programs that should continue if at all
+       possible in the face of programming errors, although they may
+       run out of memory because dropped memory is never reclaimed.
+
+       If you don't like either of these options, you can define
+       CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything
+       else. And if if you are sure that your program using malloc has
+       no errors or vulnerabilities, you can define INSECURE to 1,
+       which might (or might not) provide a small performance improvement.
+
+       It is also possible to limit the maximum total allocatable
+       space, using malloc_set_footprint_limit. This is not
+       designed as a security feature in itself (calls to set limits
+       are not screened or privileged), but may be useful as one
+       aspect of a secure implementation.
+
+  Thread-safety: NOT thread-safe unless USE_LOCKS defined non-zero
+       When USE_LOCKS is defined, each public call to malloc, free,
+       etc is surrounded with a lock. By default, this uses a plain
+       pthread mutex, win32 critical section, or a spin-lock if if
+       available for the platform and not disabled by setting
+       USE_SPIN_LOCKS=0.  However, if USE_RECURSIVE_LOCKS is defined,
+       recursive versions are used instead (which are not required for
+       base functionality but may be needed in layered extensions).
+       Using a global lock is not especially fast, and can be a major
+       bottleneck.  It is designed only to provide minimal protection
+       in concurrent environments, and to provide a basis for
+       extensions.  If you are using malloc in a concurrent program,
+       consider instead using nedmalloc
+       (http://www.nedprod.com/programs/portable/nedmalloc/) or
+       ptmalloc (See http://www.malloc.de), which are derived from
+       versions of this malloc.
+
+  System requirements: Any combination of MORECORE and/or MMAP/MUNMAP
+       This malloc can use unix sbrk or any emulation (invoked using
+       the CALL_MORECORE macro) and/or mmap/munmap or any emulation
+       (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system
+       memory.  On most unix systems, it tends to work best if both
+       MORECORE and MMAP are enabled.  On Win32, it uses emulations
+       based on VirtualAlloc. It also uses common C library functions
+       like memset.
+
+  Compliance: I believe it is compliant with the Single Unix Specification
+       (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably
+       others as well.
+
+* Overview of algorithms
+
+  This is not the fastest, most space-conserving, most portable, or
+  most tunable malloc ever written. However it is among the fastest
+  while also being among the most space-conserving, portable and
+  tunable.  Consistent balance across these factors results in a good
+  general-purpose allocator for malloc-intensive programs.
+
+  In most ways, this malloc is a best-fit allocator. Generally, it
+  chooses the best-fitting existing chunk for a request, with ties
+  broken in approximately least-recently-used order. (This strategy
+  normally maintains low fragmentation.) However, for requests less
+  than 256bytes, it deviates from best-fit when there is not an
+  exactly fitting available chunk by preferring to use space adjacent
+  to that used for the previous small request, as well as by breaking
+  ties in approximately most-recently-used order. (These enhance
+  locality of series of small allocations.)  And for very large requests
+  (>= 256Kb by default), it relies on system memory mapping
+  facilities, if supported.  (This helps avoid carrying around and
+  possibly fragmenting memory used only for large chunks.)
+
+  All operations (except malloc_stats and mallinfo) have execution
+  times that are bounded by a constant factor of the number of bits in
+  a size_t, not counting any clearing in calloc or copying in realloc,
+  or actions surrounding MORECORE and MMAP that have times
+  proportional to the number of non-contiguous regions returned by
+  system allocation routines, which is often just 1. In real-time
+  applications, you can optionally suppress segment traversals using
+  NO_SEGMENT_TRAVERSAL, which assures bounded execution even when
+  system allocators return non-contiguous spaces, at the typical
+  expense of carrying around more memory and increased fragmentation.
+
+  The implementation is not very modular and seriously overuses
+  macros. Perhaps someday all C compilers will do as good a job
+  inlining modular code as can now be done by brute-force expansion,
+  but now, enough of them seem not to.
+
+  Some compilers issue a lot of warnings about code that is
+  dead/unreachable only on some platforms, and also about intentional
+  uses of negation on unsigned types. All known cases of each can be
+  ignored.
+
+  For a longer but out of date high-level description, see
+     http://gee.cs.oswego.edu/dl/html/malloc.html
+
+* MSPACES
+  If MSPACES is defined, then in addition to malloc, free, etc.,
+  this file also defines mspace_malloc, mspace_free, etc. These
+  are versions of malloc routines that take an "mspace" argument
+  obtained using create_mspace, to control all internal bookkeeping.
+  If ONLY_MSPACES is defined, only these versions are compiled.
+  So if you would like to use this allocator for only some allocations,
+  and your system malloc for others, you can compile with
+  ONLY_MSPACES and then do something like...
+    static mspace mymspace = create_mspace(0,0); // for example
+    #define mymalloc(bytes)  mspace_malloc(mymspace, bytes)
+
+  (Note: If you only need one instance of an mspace, you can instead
+  use "USE_DL_PREFIX" to relabel the global malloc.)
+
+  You can similarly create thread-local allocators by storing
+  mspaces as thread-locals. For example:
+    static __thread mspace tlms = 0;
+    void*  tlmalloc(size_t bytes) {
+      if (tlms == 0) tlms = create_mspace(0, 0);
+      return mspace_malloc(tlms, bytes);
+    }
+    void  tlfree(void* mem) { mspace_free(tlms, mem); }
+
+  Unless FOOTERS is defined, each mspace is completely independent.
+  You cannot allocate from one and free to another (although
+  conformance is only weakly checked, so usage errors are not always
+  caught). If FOOTERS is defined, then each chunk carries around a tag
+  indicating its originating mspace, and frees are directed to their
+  originating spaces. Normally, this requires use of locks.
+
+ -------------------------  Compile-time options ---------------------------
+
+Be careful in setting #define values for numerical constants of type
+size_t. On some systems, literal values are not automatically extended
+to size_t precision unless they are explicitly casted. You can also
+use the symbolic values MAX_SIZE_T, SIZE_T_ONE, etc below.
+
+WIN32                    default: defined if _WIN32 defined
+  Defining WIN32 sets up defaults for MS environment and compilers.
+  Otherwise defaults are for unix. Beware that there seem to be some
+  cases where this malloc might not be a pure drop-in replacement for
+  Win32 malloc: Random-looking failures from Win32 GDI API's (eg;
+  SetDIBits()) may be due to bugs in some video driver implementations
+  when pixel buffers are malloc()ed, and the region spans more than
+  one VirtualAlloc()ed region. Because dlmalloc uses a small (64Kb)
+  default granularity, pixel buffers may straddle virtual allocation
+  regions more often than when using the Microsoft allocator.  You can
+  avoid this by using VirtualAlloc() and VirtualFree() for all pixel
+  buffers rather than using malloc().  If this is not possible,
+  recompile this malloc with a larger DEFAULT_GRANULARITY. Note:
+  in cases where MSC and gcc (cygwin) are known to differ on WIN32,
+  conditions use _MSC_VER to distinguish them.
+
+DLMALLOC_EXPORT       default: extern
+  Defines how public APIs are declared. If you want to export via a
+  Windows DLL, you might define this as
+    #define DLMALLOC_EXPORT extern  __declspec(dllexport)
+  If you want a POSIX ELF shared object, you might use
+    #define DLMALLOC_EXPORT extern __attribute__((visibility("default")))
+
+MALLOC_ALIGNMENT         default: (size_t)(2 * sizeof(void *))
+  Controls the minimum alignment for malloc'ed chunks.  It must be a
+  power of two and at least 8, even on machines for which smaller
+  alignments would suffice. It may be defined as larger than this
+  though. Note however that code and data structures are optimized for
+  the case of 8-byte alignment.
+
+MSPACES                  default: 0 (false)
+  If true, compile in support for independent allocation spaces.
+  This is only supported if HAVE_MMAP is true.
+
+ONLY_MSPACES             default: 0 (false)
+  If true, only compile in mspace versions, not regular versions.
+
+USE_LOCKS                default: 0 (false)
+  Causes each call to each public routine to be surrounded with
+  pthread or WIN32 mutex lock/unlock. (If set true, this can be
+  overridden on a per-mspace basis for mspace versions.) If set to a
+  non-zero value other than 1, locks are used, but their
+  implementation is left out, so lock functions must be supplied manually,
+  as described below.
+
+USE_SPIN_LOCKS           default: 1 iff USE_LOCKS and spin locks available
+  If true, uses custom spin locks for locking. This is currently
+  supported only gcc >= 4.1, older gccs on x86 platforms, and recent
+  MS compilers.  Otherwise, posix locks or win32 critical sections are
+  used.
+
+USE_RECURSIVE_LOCKS      default: not defined
+  If defined nonzero, uses recursive (aka reentrant) locks, otherwise
+  uses plain mutexes. This is not required for malloc proper, but may
+  be needed for layered allocators such as nedmalloc.
+
+LOCK_AT_FORK            default: not defined
+  If defined nonzero, performs pthread_atfork upon initialization
+  to initialize child lock while holding parent lock. The implementation
+  assumes that pthread locks (not custom locks) are being used. In other
+  cases, you may need to customize the implementation.
+
+FOOTERS                  default: 0
+  If true, provide extra checking and dispatching by placing
+  information in the footers of allocated chunks. This adds
+  space and time overhead.
+
+INSECURE                 default: 0
+  If true, omit checks for usage errors and heap space overwrites.
+
+USE_DL_PREFIX            default: NOT defined
+  Causes compiler to prefix all public routines with the string 'dl'.
+  This can be useful when you only want to use this malloc in one part
+  of a program, using your regular system malloc elsewhere.
+
+MALLOC_INSPECT_ALL       default: NOT defined
+  If defined, compiles malloc_inspect_all and mspace_inspect_all, that
+  perform traversal of all heap space.  Unless access to these
+  functions is otherwise restricted, you probably do not want to
+  include them in secure implementations.
+
+ABORT                    default: defined as abort()
+  Defines how to abort on failed checks.  On most systems, a failed
+  check cannot die with an "assert" or even print an informative
+  message, because the underlying print routines in turn call malloc,
+  which will fail again.  Generally, the best policy is to simply call
+  abort(). It's not very useful to do more than this because many
+  errors due to overwriting will show up as address faults (null, odd
+  addresses etc) rather than malloc-triggered checks, so will also
+  abort.  Also, most compilers know that abort() does not return, so
+  can better optimize code conditionally calling it.
+
+PROCEED_ON_ERROR           default: defined as 0 (false)
+  Controls whether detected bad addresses cause them to bypassed
+  rather than aborting. If set, detected bad arguments to free and
+  realloc are ignored. And all bookkeeping information is zeroed out
+  upon a detected overwrite of freed heap space, thus losing the
+  ability to ever return it from malloc again, but enabling the
+  application to proceed. If PROCEED_ON_ERROR is defined, the
+  static variable malloc_corruption_error_count is compiled in
+  and can be examined to see if errors have occurred. This option
+  generates slower code than the default abort policy.
+
+DEBUG                    default: NOT defined
+  The DEBUG setting is mainly intended for people trying to modify
+  this code or diagnose problems when porting to new platforms.
+  However, it may also be able to better isolate user errors than just
+  using runtime checks.  The assertions in the check routines spell
+  out in more detail the assumptions and invariants underlying the
+  algorithms.  The checking is fairly extensive, and will slow down
+  execution noticeably. Calling malloc_stats or mallinfo with DEBUG
+  set will attempt to check every non-mmapped allocated and free chunk
+  in the course of computing the summaries.
+
+ABORT_ON_ASSERT_FAILURE   default: defined as 1 (true)
+  Debugging assertion failures can be nearly impossible if your
+  version of the assert macro causes malloc to be called, which will
+  lead to a cascade of further failures, blowing the runtime stack.
+  ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(),
+  which will usually make debugging easier.
+
+MALLOC_FAILURE_ACTION     default: sets errno to ENOMEM, or no-op on win32
+  The action to take before "return 0" when malloc fails to be able to
+  return memory because there is none available.
+
+HAVE_MORECORE             default: 1 (true) unless win32 or ONLY_MSPACES
+  True if this system supports sbrk or an emulation of it.
+
+MORECORE                  default: sbrk
+  The name of the sbrk-style system routine to call to obtain more
+  memory.  See below for guidance on writing custom MORECORE
+  functions. The type of the argument to sbrk/MORECORE varies across
+  systems.  It cannot be size_t, because it supports negative
+  arguments, so it is normally the signed type of the same width as
+  size_t (sometimes declared as "intptr_t").  It doesn't much matter
+  though. Internally, we only call it with arguments less than half
+  the max value of a size_t, which should work across all reasonable
+  possibilities, although sometimes generating compiler warnings.
+
+MORECORE_CONTIGUOUS       default: 1 (true) if HAVE_MORECORE
+  If true, take advantage of fact that consecutive calls to MORECORE
+  with positive arguments always return contiguous increasing
+  addresses.  This is true of unix sbrk. It does not hurt too much to
+  set it true anyway, since malloc copes with non-contiguities.
+  Setting it false when definitely non-contiguous saves time
+  and possibly wasted space it would take to discover this though.
+
+MORECORE_CANNOT_TRIM      default: NOT defined
+  True if MORECORE cannot release space back to the system when given
+  negative arguments. This is generally necessary only if you are
+  using a hand-crafted MORECORE function that cannot handle negative
+  arguments.
+
+NO_SEGMENT_TRAVERSAL       default: 0
+  If non-zero, suppresses traversals of memory segments
+  returned by either MORECORE or CALL_MMAP. This disables
+  merging of segments that are contiguous, and selectively
+  releasing them to the OS if unused, but bounds execution times.
+
+HAVE_MMAP                 default: 1 (true)
+  True if this system supports mmap or an emulation of it.  If so, and
+  HAVE_MORECORE is not true, MMAP is used for all system
+  allocation. If set and HAVE_MORECORE is true as well, MMAP is
+  primarily used to directly allocate very large blocks. It is also
+  used as a backup strategy in cases where MORECORE fails to provide
+  space from system. Note: A single call to MUNMAP is assumed to be
+  able to unmap memory that may have be allocated using multiple calls
+  to MMAP, so long as they are adjacent.
+
+HAVE_MREMAP               default: 1 on linux, else 0
+  If true realloc() uses mremap() to re-allocate large blocks and
+  extend or shrink allocation spaces.
+
+MMAP_CLEARS               default: 1 except on WINCE.
+  True if mmap clears memory so calloc doesn't need to. This is true
+  for standard unix mmap using /dev/zero and on WIN32 except for WINCE.
+
+USE_BUILTIN_FFS            default: 0 (i.e., not used)
+  Causes malloc to use the builtin ffs() function to compute indices.
+  Some compilers may recognize and intrinsify ffs to be faster than the
+  supplied C version. Also, the case of x86 using gcc is special-cased
+  to an asm instruction, so is already as fast as it can be, and so
+  this setting has no effect. Similarly for Win32 under recent MS compilers.
+  (On most x86s, the asm version is only slightly faster than the C version.)
+
+malloc_getpagesize         default: derive from system includes, or 4096.
+  The system page size. To the extent possible, this malloc manages
+  memory from the system in page-size units.  This may be (and
+  usually is) a function rather than a constant. This is ignored
+  if WIN32, where page size is determined using getSystemInfo during
+  initialization.
+
+USE_DEV_RANDOM             default: 0 (i.e., not used)
+  Causes malloc to use /dev/random to initialize secure magic seed for
+  stamping footers. Otherwise, the current time is used.
+
+NO_MALLINFO                default: 0
+  If defined, don't compile "mallinfo". This can be a simple way
+  of dealing with mismatches between system declarations and
+  those in this file.
+
+MALLINFO_FIELD_TYPE        default: size_t
+  The type of the fields in the mallinfo struct. This was originally
+  defined as "int" in SVID etc, but is more usefully defined as
+  size_t. The value is used only if  HAVE_USR_INCLUDE_MALLOC_H is not set
+
+NO_MALLOC_STATS            default: 0
+  If defined, don't compile "malloc_stats". This avoids calls to
+  fprintf and bringing in stdio dependencies you might not want.
+
+REALLOC_ZERO_BYTES_FREES    default: not defined
+  This should be set if a call to realloc with zero bytes should
+  be the same as a call to free. Some people think it should. Otherwise,
+  since this malloc returns a unique pointer for malloc(0), so does
+  realloc(p, 0).
+
+LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H
+LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H,  LACKS_ERRNO_H
+LACKS_STDLIB_H LACKS_SCHED_H LACKS_TIME_H  default: NOT defined unless on WIN32
+  Define these if your system does not have these header files.
+  You might need to manually insert some of the declarations they provide.
+
+DEFAULT_GRANULARITY        default: page size if MORECORE_CONTIGUOUS,
+                                system_info.dwAllocationGranularity in WIN32,
+                                otherwise 64K.
+      Also settable using mallopt(M_GRANULARITY, x)
+  The unit for allocating and deallocating memory from the system.  On
+  most systems with contiguous MORECORE, there is no reason to
+  make this more than a page. However, systems with MMAP tend to
+  either require or encourage larger granularities.  You can increase
+  this value to prevent system allocation functions to be called so
+  often, especially if they are slow.  The value must be at least one
+  page and must be a power of two.  Setting to 0 causes initialization
+  to either page size or win32 region size.  (Note: In previous
+  versions of malloc, the equivalent of this option was called
+  "TOP_PAD")
+
+DEFAULT_TRIM_THRESHOLD    default: 2MB
+      Also settable using mallopt(M_TRIM_THRESHOLD, x)
+  The maximum amount of unused top-most memory to keep before
+  releasing via malloc_trim in free().  Automatic trimming is mainly
+  useful in long-lived programs using contiguous MORECORE.  Because
+  trimming via sbrk can be slow on some systems, and can sometimes be
+  wasteful (in cases where programs immediately afterward allocate
+  more large chunks) the value should be high enough so that your
+  overall system performance would improve by releasing this much
+  memory.  As a rough guide, you might set to a value close to the
+  average size of a process (program) running on your system.
+  Releasing this much memory would allow such a process to run in
+  memory.  Generally, it is worth tuning trim thresholds when a
+  program undergoes phases where several large chunks are allocated
+  and released in ways that can reuse each other's storage, perhaps
+  mixed with phases where there are no such chunks at all. The trim
+  value must be greater than page size to have any useful effect.  To
+  disable trimming completely, you can set to MAX_SIZE_T. Note that the trick
+  some people use of mallocing a huge space and then freeing it at
+  program startup, in an attempt to reserve system memory, doesn't
+  have the intended effect under automatic trimming, since that memory
+  will immediately be returned to the system.
+
+DEFAULT_MMAP_THRESHOLD       default: 256K
+      Also settable using mallopt(M_MMAP_THRESHOLD, x)
+  The request size threshold for using MMAP to directly service a
+  request. Requests of at least this size that cannot be allocated
+  using already-existing space will be serviced via mmap.  (If enough
+  normal freed space already exists it is used instead.)  Using mmap
+  segregates relatively large chunks of memory so that they can be
+  individually obtained and released from the host system. A request
+  serviced through mmap is never reused by any other request (at least
+  not directly; the system may just so happen to remap successive
+  requests to the same locations).  Segregating space in this way has
+  the benefits that: Mmapped space can always be individually released
+  back to the system, which helps keep the system level memory demands
+  of a long-lived program low.  Also, mapped memory doesn't become
+  `locked' between other chunks, as can happen with normally allocated
+  chunks, which means that even trimming via malloc_trim would not
+  release them.  However, it has the disadvantage that the space
+  cannot be reclaimed, consolidated, and then used to service later
+  requests, as happens with normal chunks.  The advantages of mmap
+  nearly always outweigh disadvantages for "large" chunks, but the
+  value of "large" may vary across systems.  The default is an
+  empirically derived value that works well in most systems. You can
+  disable mmap by setting to MAX_SIZE_T.
+
+MAX_RELEASE_CHECK_RATE   default: 4095 unless not HAVE_MMAP
+  The number of consolidated frees between checks to release
+  unused segments when freeing. When using non-contiguous segments,
+  especially with multiple mspaces, checking only for topmost space
+  doesn't always suffice to trigger trimming. To compensate for this,
+  free() will, with a period of MAX_RELEASE_CHECK_RATE (or the
+  current number of segments, if greater) try to release unused
+  segments to the OS when freeing chunks that result in
+  consolidation. The best value for this parameter is a compromise
+  between slowing down frees with relatively costly checks that
+  rarely trigger versus holding on to unused memory. To effectively
+  disable, set to MAX_SIZE_T. This may lead to a very slight speed
+  improvement at the expense of carrying around more memory.
+*/
+
+/* Version identifier to allow people to support multiple versions */
+#ifndef DLMALLOC_VERSION
+#define DLMALLOC_VERSION 20806
+#endif /* DLMALLOC_VERSION */
+
+#ifndef DLMALLOC_EXPORT
+#define DLMALLOC_EXPORT extern
+#endif
+
+#ifndef WIN32
+#ifdef _WIN32
+#define WIN32 1
+#endif  /* _WIN32 */
+#ifdef _WIN32_WCE
+#define LACKS_FCNTL_H
+#define WIN32 1
+#endif /* _WIN32_WCE */
+#endif  /* WIN32 */
+#ifdef WIN32
+#define WIN32_LEAN_AND_MEAN
+#include <windows.h>
+#include <tchar.h>
+#define HAVE_MMAP 1
+#define HAVE_MORECORE 0
+#define LACKS_UNISTD_H
+#define LACKS_SYS_PARAM_H
+#define LACKS_SYS_MMAN_H
+#define LACKS_STRING_H
+#define LACKS_STRINGS_H
+#define LACKS_SYS_TYPES_H
+#define LACKS_ERRNO_H
+#define LACKS_SCHED_H
+#ifndef MALLOC_FAILURE_ACTION
+#define MALLOC_FAILURE_ACTION
+#endif /* MALLOC_FAILURE_ACTION */
+#ifndef MMAP_CLEARS
+#ifdef _WIN32_WCE /* WINCE reportedly does not clear */
+#define MMAP_CLEARS 0
+#else
+#define MMAP_CLEARS 1
+#endif /* _WIN32_WCE */
+#endif /*MMAP_CLEARS */
+#endif  /* WIN32 */
+
+#if defined(DARWIN) || defined(_DARWIN)
+/* Mac OSX docs advise not to use sbrk; it seems better to use mmap */
+#ifndef HAVE_MORECORE
+#define HAVE_MORECORE 0
+#define HAVE_MMAP 1
+/* OSX allocators provide 16 byte alignment */
+#ifndef MALLOC_ALIGNMENT
+#define MALLOC_ALIGNMENT ((size_t)16U)
+#endif
+#endif  /* HAVE_MORECORE */
+#endif  /* DARWIN */
+
+#ifndef LACKS_SYS_TYPES_H
+#include <sys/types.h>  /* For size_t */
+#endif  /* LACKS_SYS_TYPES_H */
+
+/* The maximum possible size_t value has all bits set */
+#define MAX_SIZE_T           (~(size_t)0)
+
+#ifndef USE_LOCKS /* ensure true if spin or recursive locks set */
+#define USE_LOCKS  ((defined(USE_SPIN_LOCKS) && USE_SPIN_LOCKS != 0) || \
+                    (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0))
+#endif /* USE_LOCKS */
+
+#if USE_LOCKS /* Spin locks for gcc >= 4.1, older gcc on x86, MSC >= 1310 */
+#if ((defined(__GNUC__) &&                                              \
+      ((__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1)) ||      \
+       defined(__i386__) || defined(__x86_64__))) ||                    \
+     (defined(_MSC_VER) && _MSC_VER>=1310))
+#ifndef USE_SPIN_LOCKS
+#define USE_SPIN_LOCKS 1
+#endif /* USE_SPIN_LOCKS */
+#elif USE_SPIN_LOCKS
+#error "USE_SPIN_LOCKS defined without implementation"
+#endif /* ... locks available... */
+#elif !defined(USE_SPIN_LOCKS)
+#define USE_SPIN_LOCKS 0
+#endif /* USE_LOCKS */
+
+#ifndef ONLY_MSPACES
+#define ONLY_MSPACES 0
+#endif  /* ONLY_MSPACES */
+#ifndef MSPACES
+#if ONLY_MSPACES
+#define MSPACES 1
+#else   /* ONLY_MSPACES */
+#define MSPACES 0
+#endif  /* ONLY_MSPACES */
+#endif  /* MSPACES */
+#ifndef MALLOC_ALIGNMENT
+#define MALLOC_ALIGNMENT ((size_t)(2 * sizeof(void *)))
+#endif  /* MALLOC_ALIGNMENT */
+#ifndef FOOTERS
+#define FOOTERS 0
+#endif  /* FOOTERS */
+#ifndef ABORT
+#define ABORT  abort()
+#endif  /* ABORT */
+#ifndef ABORT_ON_ASSERT_FAILURE
+#define ABORT_ON_ASSERT_FAILURE 1
+#endif  /* ABORT_ON_ASSERT_FAILURE */
+#ifndef PROCEED_ON_ERROR
+#define PROCEED_ON_ERROR 0
+#endif  /* PROCEED_ON_ERROR */
+
+#ifndef INSECURE
+#define INSECURE 0
+#endif  /* INSECURE */
+#ifndef MALLOC_INSPECT_ALL
+#define MALLOC_INSPECT_ALL 0
+#endif  /* MALLOC_INSPECT_ALL */
+#ifndef HAVE_MMAP
+#define HAVE_MMAP 1
+#endif  /* HAVE_MMAP */
+#ifndef MMAP_CLEARS
+#define MMAP_CLEARS 1
+#endif  /* MMAP_CLEARS */
+#ifndef HAVE_MREMAP
+#ifdef linux
+#define HAVE_MREMAP 1
+#define _GNU_SOURCE /* Turns on mremap() definition */
+#else   /* linux */
+#define HAVE_MREMAP 0
+#endif  /* linux */
+#endif  /* HAVE_MREMAP */
+#ifndef MALLOC_FAILURE_ACTION
+#define MALLOC_FAILURE_ACTION  errno = ENOMEM;
+#endif  /* MALLOC_FAILURE_ACTION */
+#ifndef HAVE_MORECORE
+#if ONLY_MSPACES
+#define HAVE_MORECORE 0
+#else   /* ONLY_MSPACES */
+#define HAVE_MORECORE 1
+#endif  /* ONLY_MSPACES */
+#endif  /* HAVE_MORECORE */
+#if !HAVE_MORECORE
+#define MORECORE_CONTIGUOUS 0
+#else   /* !HAVE_MORECORE */
+#define MORECORE_DEFAULT sbrk
+#ifndef MORECORE_CONTIGUOUS
+#define MORECORE_CONTIGUOUS 1
+#endif  /* MORECORE_CONTIGUOUS */
+#endif  /* HAVE_MORECORE */
+#ifndef DEFAULT_GRANULARITY
+#if (MORECORE_CONTIGUOUS || defined(WIN32))
+#define DEFAULT_GRANULARITY (0)  /* 0 means to compute in init_mparams */
+#else   /* MORECORE_CONTIGUOUS */
+#define DEFAULT_GRANULARITY ((size_t)64U * (size_t)1024U)
+#endif  /* MORECORE_CONTIGUOUS */
+#endif  /* DEFAULT_GRANULARITY */
+#ifndef DEFAULT_TRIM_THRESHOLD
+#ifndef MORECORE_CANNOT_TRIM
+#define DEFAULT_TRIM_THRESHOLD ((size_t)2U * (size_t)1024U * (size_t)1024U)
+#else   /* MORECORE_CANNOT_TRIM */
+#define DEFAULT_TRIM_THRESHOLD MAX_SIZE_T
+#endif  /* MORECORE_CANNOT_TRIM */
+#endif  /* DEFAULT_TRIM_THRESHOLD */
+#ifndef DEFAULT_MMAP_THRESHOLD
+#if HAVE_MMAP
+#define DEFAULT_MMAP_THRESHOLD ((size_t)256U * (size_t)1024U)
+#else   /* HAVE_MMAP */
+#define DEFAULT_MMAP_THRESHOLD MAX_SIZE_T
+#endif  /* HAVE_MMAP */
+#endif  /* DEFAULT_MMAP_THRESHOLD */
+#ifndef MAX_RELEASE_CHECK_RATE
+#if HAVE_MMAP
+#define MAX_RELEASE_CHECK_RATE 4095
+#else
+#define MAX_RELEASE_CHECK_RATE MAX_SIZE_T
+#endif /* HAVE_MMAP */
+#endif /* MAX_RELEASE_CHECK_RATE */
+#ifndef USE_BUILTIN_FFS
+#define USE_BUILTIN_FFS 0
+#endif  /* USE_BUILTIN_FFS */
+#ifndef USE_DEV_RANDOM
+#define USE_DEV_RANDOM 0
+#endif  /* USE_DEV_RANDOM */
+#ifndef NO_MALLINFO
+#define NO_MALLINFO 0
+#endif  /* NO_MALLINFO */
+#ifndef MALLINFO_FIELD_TYPE
+#define MALLINFO_FIELD_TYPE size_t
+#endif  /* MALLINFO_FIELD_TYPE */
+#ifndef NO_MALLOC_STATS
+#define NO_MALLOC_STATS 0
+#endif  /* NO_MALLOC_STATS */
+#ifndef NO_SEGMENT_TRAVERSAL
+#define NO_SEGMENT_TRAVERSAL 0
+#endif /* NO_SEGMENT_TRAVERSAL */
+
+/*
+  mallopt tuning options.  SVID/XPG defines four standard parameter
+  numbers for mallopt, normally defined in malloc.h.  None of these
+  are used in this malloc, so setting them has no effect. But this
+  malloc does support the following options.
+*/
+
+#define M_TRIM_THRESHOLD     (-1)
+#define M_GRANULARITY        (-2)
+#define M_MMAP_THRESHOLD     (-3)
+
+/* ------------------------ Mallinfo declarations ------------------------ */
+
+#if !NO_MALLINFO
+/*
+  This version of malloc supports the standard SVID/XPG mallinfo
+  routine that returns a struct containing usage properties and
+  statistics. It should work on any system that has a
+  /usr/include/malloc.h defining struct mallinfo.  The main
+  declaration needed is the mallinfo struct that is returned (by-copy)
+  by mallinfo().  The malloinfo struct contains a bunch of fields that
+  are not even meaningful in this version of malloc.  These fields are
+  are instead filled by mallinfo() with other numbers that might be of
+  interest.
+
+  HAVE_USR_INCLUDE_MALLOC_H should be set if you have a
+  /usr/include/malloc.h file that includes a declaration of struct
+  mallinfo.  If so, it is included; else a compliant version is
+  declared below.  These must be precisely the same for mallinfo() to
+  work.  The original SVID version of this struct, defined on most
+  systems with mallinfo, declares all fields as ints. But some others
+  define as unsigned long. If your system defines the fields using a
+  type of different width than listed here, you MUST #include your
+  system version and #define HAVE_USR_INCLUDE_MALLOC_H.
+*/
+
+/* #define HAVE_USR_INCLUDE_MALLOC_H */
+
+#ifdef HAVE_USR_INCLUDE_MALLOC_H
+#include "/usr/include/malloc.h"
+#else /* HAVE_USR_INCLUDE_MALLOC_H */
+#ifndef STRUCT_MALLINFO_DECLARED
+/* HP-UX (and others?) redefines mallinfo unless _STRUCT_MALLINFO is defined */
+#define _STRUCT_MALLINFO
+#define STRUCT_MALLINFO_DECLARED 1
+struct mallinfo {
+  MALLINFO_FIELD_TYPE arena;    /* non-mmapped space allocated from system */
+  MALLINFO_FIELD_TYPE ordblks;  /* number of free chunks */
+  MALLINFO_FIELD_TYPE smblks;   /* always 0 */
+  MALLINFO_FIELD_TYPE hblks;    /* always 0 */
+  MALLINFO_FIELD_TYPE hblkhd;   /* space in mmapped regions */
+  MALLINFO_FIELD_TYPE usmblks;  /* maximum total allocated space */
+  MALLINFO_FIELD_TYPE fsmblks;  /* always 0 */
+  MALLINFO_FIELD_TYPE uordblks; /* total allocated space */
+  MALLINFO_FIELD_TYPE fordblks; /* total free space */
+  MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */
+};
+#endif /* STRUCT_MALLINFO_DECLARED */
+#endif /* HAVE_USR_INCLUDE_MALLOC_H */
+#endif /* NO_MALLINFO */
+
+/*
+  Try to persuade compilers to inline. The most critical functions for
+  inlining are defined as macros, so these aren't used for them.
+*/
+
+#if 0 /* SDL */
+#ifndef FORCEINLINE
+  #if defined(__GNUC__)
+#define FORCEINLINE __inline __attribute__ ((always_inline))
+  #elif defined(_MSC_VER)
+    #define FORCEINLINE __forceinline
+  #endif
+#endif
+#endif /* SDL */
+#ifndef NOINLINE
+  #if defined(__GNUC__)
+    #define NOINLINE __attribute__ ((noinline))
+  #elif defined(_MSC_VER)
+    #define NOINLINE __declspec(noinline)
+  #else
+    #define NOINLINE
+  #endif
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#if 0 /* SDL */
+#ifndef FORCEINLINE
+ #define FORCEINLINE inline
+#endif
+#endif /* SDL */
+#endif /* __cplusplus */
+#if 0 /* SDL */
+#ifndef FORCEINLINE
+ #define FORCEINLINE
+#endif
+#endif /* SDL_FORCE_INLINE */
+
+#if !ONLY_MSPACES
+
+/* ------------------- Declarations of public routines ------------------- */
+
+#ifndef USE_DL_PREFIX
+#define dlcalloc               calloc
+#define dlfree                 free
+#define dlmalloc               malloc
+#define dlmemalign             memalign
+#define dlposix_memalign       posix_memalign
+#define dlrealloc              realloc
+#define dlrealloc_in_place     realloc_in_place
+#define dlvalloc               valloc
+#define dlpvalloc              pvalloc
+#define dlmallinfo             mallinfo
+#define dlmallopt              mallopt
+#define dlmalloc_trim          malloc_trim
+#define dlmalloc_stats         malloc_stats
+#define dlmalloc_usable_size   malloc_usable_size
+#define dlmalloc_footprint     malloc_footprint
+#define dlmalloc_max_footprint malloc_max_footprint
+#define dlmalloc_footprint_limit malloc_footprint_limit
+#define dlmalloc_set_footprint_limit malloc_set_footprint_limit
+#define dlmalloc_inspect_all   malloc_inspect_all
+#define dlindependent_calloc   independent_calloc
+#define dlindependent_comalloc independent_comalloc
+#define dlbulk_free            bulk_free
+#endif /* USE_DL_PREFIX */
+
+/*
+  malloc(size_t n)
+  Returns a pointer to a newly allocated chunk of at least n bytes, or
+  null if no space is available, in which case errno is set to ENOMEM
+  on ANSI C systems.
+
+  If n is zero, malloc returns a minimum-sized chunk. (The minimum
+  size is 16 bytes on most 32bit systems, and 32 bytes on 64bit
+  systems.)  Note that size_t is an unsigned type, so calls with
+  arguments that would be negative if signed are interpreted as
+  requests for huge amounts of space, which will often fail. The
+  maximum supported value of n differs across systems, but is in all
+  cases less than the maximum representable value of a size_t.
+*/
+DLMALLOC_EXPORT void* dlmalloc(size_t);
+
+/*
+  free(void* p)
+  Releases the chunk of memory pointed to by p, that had been previously
+  allocated using malloc or a related routine such as realloc.
+  It has no effect if p is null. If p was not malloced or already
+  freed, free(p) will by default cause the current program to abort.
+*/
+DLMALLOC_EXPORT void  dlfree(void*);
+
+/*
+  calloc(size_t n_elements, size_t element_size);
+  Returns a pointer to n_elements * element_size bytes, with all locations
+  set to zero.
+*/
+DLMALLOC_EXPORT void* dlcalloc(size_t, size_t);
+
+/*
+  realloc(void* p, size_t n)
+  Returns a pointer to a chunk of size n that contains the same data
+  as does chunk p up to the minimum of (n, p's size) bytes, or null
+  if no space is available.
+
+  The returned pointer may or may not be the same as p. The algorithm
+  prefers extending p in most cases when possible, otherwise it
+  employs the equivalent of a malloc-copy-free sequence.
+
+  If p is null, realloc is equivalent to malloc.
+
+  If space is not available, realloc returns null, errno is set (if on
+  ANSI) and p is NOT freed.
+
+  if n is for fewer bytes than already held by p, the newly unused
+  space is lopped off and freed if possible.  realloc with a size
+  argument of zero (re)allocates a minimum-sized chunk.
+
+  The old unix realloc convention of allowing the last-free'd chunk
+  to be used as an argument to realloc is not supported.
+*/
+DLMALLOC_EXPORT void* dlrealloc(void*, size_t);
+
+/*
+  realloc_in_place(void* p, size_t n)
+  Resizes the space allocated for p to size n, only if this can be
+  done without moving p (i.e., only if there is adjacent space
+  available if n is greater than p's current allocated size, or n is
+  less than or equal to p's size). This may be used instead of plain
+  realloc if an alternative allocation strategy is needed upon failure
+  to expand space; for example, reallocation of a buffer that must be
+  memory-aligned or cleared. You can use realloc_in_place to trigger
+  these alternatives only when needed.
+
+  Returns p if successful; otherwise null.
+*/
+DLMALLOC_EXPORT void* dlrealloc_in_place(void*, size_t);
+
+/*
+  memalign(size_t alignment, size_t n);
+  Returns a pointer to a newly allocated chunk of n bytes, aligned
+  in accord with the alignment argument.
+
+  The alignment argument should be a power of two. If the argument is
+  not a power of two, the nearest greater power is used.
+  8-byte alignment is guaranteed by normal malloc calls, so don't
+  bother calling memalign with an argument of 8 or less.
+
+  Overreliance on memalign is a sure way to fragment space.
+*/
+DLMALLOC_EXPORT void* dlmemalign(size_t, size_t);
+
+/*
+  int posix_memalign(void** pp, size_t alignment, size_t n);
+  Allocates a chunk of n bytes, aligned in accord with the alignment
+  argument. Differs from memalign only in that it (1) assigns the
+  allocated memory to *pp rather than returning it, (2) fails and
+  returns EINVAL if the alignment is not a power of two (3) fails and
+  returns ENOMEM if memory cannot be allocated.
+*/
+DLMALLOC_EXPORT int dlposix_memalign(void**, size_t, size_t);
+
+/*
+  valloc(size_t n);
+  Equivalent to memalign(pagesize, n), where pagesize is the page
+  size of the system. If the pagesize is unknown, 4096 is used.
+*/
+DLMALLOC_EXPORT void* dlvalloc(size_t);
+
+/*
+  mallopt(int parameter_number, int parameter_value)
+  Sets tunable parameters The format is to provide a
+  (parameter-number, parameter-value) pair.  mallopt then sets the
+  corresponding parameter to the argument value if it can (i.e., so
+  long as the value is meaningful), and returns 1 if successful else
+  0.  To workaround the fact that mallopt is specified to use int,
+  not size_t parameters, the value -1 is specially treated as the
+  maximum unsigned size_t value.
+
+  SVID/XPG/ANSI defines four standard param numbers for mallopt,
+  normally defined in malloc.h.  None of these are use in this malloc,
+  so setting them has no effect. But this malloc also supports other
+  options in mallopt. See below for details.  Briefly, supported
+  parameters are as follows (listed defaults are for "typical"
+  configurations).
+
+  Symbol            param #  default    allowed param values
+  M_TRIM_THRESHOLD     -1   2*1024*1024   any   (-1 disables)
+  M_GRANULARITY        -2     page size   any power of 2 >= page size
+  M_MMAP_THRESHOLD     -3      256*1024   any   (or 0 if no MMAP support)
+*/
+DLMALLOC_EXPORT int dlmallopt(int, int);
+
+/*
+  malloc_footprint();
+  Returns the number of bytes obtained from the system.  The total
+  number of bytes allocated by malloc, realloc etc., is less than this
+  value. Unlike mallinfo, this function returns only a precomputed
+  result, so can be called frequently to monitor memory consumption.
+  Even if locks are otherwise defined, this function does not use them,
+  so results might not be up to date.
+*/
+DLMALLOC_EXPORT size_t dlmalloc_footprint(void);
+
+/*
+  malloc_max_footprint();
+  Returns the maximum number of bytes obtained from the system. This
+  value will be greater than current footprint if deallocated space
+  has been reclaimed by the system. The peak number of bytes allocated
+  by malloc, realloc etc., is less than this value. Unlike mallinfo,
+  this function returns only a precomputed result, so can be called
+  frequently to monitor memory consumption.  Even if locks are
+  otherwise defined, this function does not use them, so results might
+  not be up to date.
+*/
+DLMALLOC_EXPORT size_t dlmalloc_max_footprint(void);
+
+/*
+  malloc_footprint_limit();
+  Returns the number of bytes that the heap is allowed to obtain from
+  the system, returning the last value returned by
+  malloc_set_footprint_limit, or the maximum size_t value if
+  never set. The returned value reflects a permission. There is no
+  guarantee that this number of bytes can actually be obtained from
+  the system.
+*/
+DLMALLOC_EXPORT size_t dlmalloc_footprint_limit();
+
+/*
+  malloc_set_footprint_limit();
+  Sets the maximum number of bytes to obtain from the system, causing
+  failure returns from malloc and related functions upon attempts to
+  exceed this value. The argument value may be subject to page
+  rounding to an enforceable limit; this actual value is returned.
+  Using an argument of the maximum possible size_t effectively
+  disables checks. If the argument is less than or equal to the
+  current malloc_footprint, then all future allocations that require
+  additional system memory will fail. However, invocation cannot
+  retroactively deallocate existing used memory.
+*/
+DLMALLOC_EXPORT size_t dlmalloc_set_footprint_limit(size_t bytes);
+
+#if MALLOC_INSPECT_ALL
+/*
+  malloc_inspect_all(void(*handler)(void *start,
+                                    void *end,
+                                    size_t used_bytes,
+                                    void* callback_arg),
+                      void* arg);
+  Traverses the heap and calls the given handler for each managed
+  region, skipping all bytes that are (or may be) used for bookkeeping
+  purposes.  Traversal does not include include chunks that have been
+  directly memory mapped. Each reported region begins at the start
+  address, and continues up to but not including the end address.  The
+  first used_bytes of the region contain allocated data. If
+  used_bytes is zero, the region is unallocated. The handler is
+  invoked with the given callback argument. If locks are defined, they
+  are held during the entire traversal. It is a bad idea to invoke
+  other malloc functions from within the handler.
+
+  For example, to count the number of in-use chunks with size greater
+  than 1000, you could write:
+  static int count = 0;
+  void count_chunks(void* start, void* end, size_t used, void* arg) {
+    if (used >= 1000) ++count;
+  }
+  then:
+    malloc_inspect_all(count_chunks, NULL);
+
+  malloc_inspect_all is compiled only if MALLOC_INSPECT_ALL is defined.
+*/
+DLMALLOC_EXPORT void dlmalloc_inspect_all(void(*handler)(void*, void *, size_t, void*),
+                           void* arg);
+
+#endif /* MALLOC_INSPECT_ALL */
+
+#if !NO_MALLINFO
+/*
+  mallinfo()
+  Returns (by copy) a struct containing various summary statistics:
+
+  arena:     current total non-mmapped bytes allocated from system
+  ordblks:   the number of free chunks
+  smblks:    always zero.
+  hblks:     current number of mmapped regions
+  hblkhd:    total bytes held in mmapped regions
+  usmblks:   the maximum total allocated space. This will be greater
+                than current total if trimming has occurred.
+  fsmblks:   always zero
+  uordblks:  current total allocated space (normal or mmapped)
+  fordblks:  total free space
+  keepcost:  the maximum number of bytes that could ideally be released
+               back to system via malloc_trim. ("ideally" means that
+               it ignores page restrictions etc.)
+
+  Because these fields are ints, but internal bookkeeping may
+  be kept as longs, the reported values may wrap around zero and
+  thus be inaccurate.
+*/
+DLMALLOC_EXPORT struct mallinfo dlmallinfo(void);
+#endif /* NO_MALLINFO */
+
+/*
+  independent_calloc(size_t n_elements, size_t element_size, void* chunks[]);
+
+  independent_calloc is similar to calloc, but instead of returning a
+  single cleared space, it returns an array of pointers to n_elements
+  independent elements that can hold contents of size elem_size, each
+  of which starts out cleared, and can be independently freed,
+  realloc'ed etc. The elements are guaranteed to be adjacently
+  allocated (this is not guaranteed to occur with multiple callocs or
+  mallocs), which may also improve cache locality in some
+  applications.
+
+  The "chunks" argument is optional (i.e., may be null, which is
+  probably the most typical usage). If it is null, the returned array
+  is itself dynamically allocated and should also be freed when it is
+  no longer needed. Otherwise, the chunks array must be of at least
+  n_elements in length. It is filled in with the pointers to the
+  chunks.
+
+  In either case, independent_calloc returns this pointer array, or
+  null if the allocation failed.  If n_elements is zero and "chunks"
+  is null, it returns a chunk representing an array with zero elements
+  (which should be freed if not wanted).
+
+  Each element must be freed when it is no longer needed. This can be
+  done all at once using bulk_free.
+
+  independent_calloc simplifies and speeds up implementations of many
+  kinds of pools.  It may also be useful when constructing large data
+  structures that initially have a fixed number of fixed-sized nodes,
+  but the number is not known at compile time, and some of the nodes
+  may later need to be freed. For example:
+
+  struct Node { int item; struct Node* next; };
+
+  struct Node* build_list() {
+    struct Node** pool;
+    int n = read_number_of_nodes_needed();
+    if (n <= 0) return 0;
+    pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0);
+    if (pool == 0) die();
+    // organize into a linked list...
+    struct Node* first = pool[0];
+    for (i = 0; i < n-1; ++i)
+      pool[i]->next = pool[i+1];
+    free(pool);     // Can now free the array (or not, if it is needed later)
+    return first;
+  }
+*/
+DLMALLOC_EXPORT void** dlindependent_calloc(size_t, size_t, void**);
+
+/*
+  independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]);
+
+  independent_comalloc allocates, all at once, a set of n_elements
+  chunks with sizes indicated in the "sizes" array.    It returns
+  an array of pointers to these elements, each of which can be
+  independently freed, realloc'ed etc. The elements are guaranteed to
+  be adjacently allocated (this is not guaranteed to occur with
+  multiple callocs or mallocs), which may also improve cache locality
+  in some applications.
+
+  The "chunks" argument is optional (i.e., may be null). If it is null
+  the returned array is itself dynamically allocated and should also
+  be freed when it is no longer needed. Otherwise, the chunks array
+  must be of at least n_elements in length. It is filled in with the
+  pointers to the chunks.
+
+  In either case, independent_comalloc returns this pointer array, or
+  null if the allocation failed.  If n_elements is zero and chunks is
+  null, it returns a chunk representing an array with zero elements
+  (which should be freed if not wanted).
+
+  Each element must be freed when it is no longer needed. This can be
+  done all at once using bulk_free.
+
+  independent_comallac differs from independent_calloc in that each
+  element may have a different size, and also that it does not
+  automatically clear elements.
+
+  independent_comalloc can be used to speed up allocation in cases
+  where several structs or objects must always be allocated at the
+  same time.  For example:
+
+  struct Head { ... }
+  struct Foot { ... }
+
+  void send_message(char* msg) {
+    int msglen = strlen(msg);
+    size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) };
+    void* chunks[3];
+    if (independent_comalloc(3, sizes, chunks) == 0)
+      die();
+    struct Head* head = (struct Head*)(chunks[0]);
+    char*        body = (char*)(chunks[1]);
+    struct Foot* foot = (struct Foot*)(chunks[2]);
+    // ...
+  }
+
+  In general though, independent_comalloc is worth using only for
+  larger values of n_elements. For small values, you probably won't
+  detect enough difference from series of malloc calls to bother.
+
+  Overuse of independent_comalloc can increase overall memory usage,
+  since it cannot reuse existing noncontiguous small chunks that
+  might be available for some of the elements.
+*/
+DLMALLOC_EXPORT void** dlindependent_comalloc(size_t, size_t*, void**);
+
+/*
+  bulk_free(void* array[], size_t n_elements)
+  Frees and clears (sets to null) each non-null pointer in the given
+  array.  This is likely to be faster than freeing them one-by-one.
+  If footers are used, pointers that have been allocated in different
+  mspaces are not freed or cleared, and the count of all such pointers
+  is returned.  For large arrays of pointers with poor locality, it
+  may be worthwhile to sort this array before calling bulk_free.
+*/
+DLMALLOC_EXPORT size_t  dlbulk_free(void**, size_t n_elements);
+
+/*
+  pvalloc(size_t n);
+  Equivalent to valloc(minimum-page-that-holds(n)), that is,
+  round up n to nearest pagesize.
+ */
+DLMALLOC_EXPORT void*  dlpvalloc(size_t);
+
+/*
+  malloc_trim(size_t pad);
+
+  If possible, gives memory back to the system (via negative arguments
+  to sbrk) if there is unused memory at the `high' end of the malloc
+  pool or in unused MMAP segments. You can call this after freeing
+  large blocks of memory to potentially reduce the system-level memory
+  requirements of a program. However, it cannot guarantee to reduce
+  memory. Under some allocation patterns, some large free blocks of
+  memory will be locked between two used chunks, so they cannot be
+  given back to the system.
+
+  The `pad' argument to malloc_trim represents the amount of free
+  trailing space to leave untrimmed. If this argument is zero, only
+  the minimum amount of memory to maintain internal data structures
+  will be left. Non-zero arguments can be supplied to maintain enough
+  trailing space to service future expected allocations without having
+  to re-obtain memory from the system.
+
+  Malloc_trim returns 1 if it actually released any memory, else 0.
+*/
+DLMALLOC_EXPORT int  dlmalloc_trim(size_t);
+
+/*
+  malloc_stats();
+  Prints on stderr the amount of space obtained from the system (both
+  via sbrk and mmap), the maximum amount (which may be more than
+  current if malloc_trim and/or munmap got called), and the current
+  number of bytes allocated via malloc (or realloc, etc) but not yet
+  freed. Note that this is the number of bytes allocated, not the
+  number requested. It will be larger than the number requested
+  because of alignment and bookkeeping overhead. Because it includes
+  alignment wastage as being in use, this figure may be greater than
+  zero even when no user-level chunks are allocated.
+
+  The reported current and maximum system memory can be inaccurate if
+  a program makes other calls to system memory allocation functions
+  (normally sbrk) outside of malloc.
+
+  malloc_stats prints only the most commonly interesting statistics.
+  More information can be obtained by calling mallinfo.
+*/
+DLMALLOC_EXPORT void  dlmalloc_stats(void);
+
+/*
+  malloc_usable_size(void* p);
+
+  Returns the number of bytes you can actually use in
+  an allocated chunk, which may be more than you requested (although
+  often not) due to alignment and minimum size constraints.
+  You can use this many bytes without worrying about
+  overwriting other allocated objects. This is not a particularly great
+  programming practice. malloc_usable_size can be more useful in
+  debugging and assertions, for example:
+
+  p = malloc(n);
+  assert(malloc_usable_size(p) >= 256);
+*/
+size_t dlmalloc_usable_size(void*);
+
+#endif /* ONLY_MSPACES */
+
+#if MSPACES
+
+/*
+  mspace is an opaque type representing an independent
+  region of space that supports mspace_malloc, etc.
+*/
+typedef void* mspace;
+
+/*
+  create_mspace creates and returns a new independent space with the
+  given initial capacity, or, if 0, the default granularity size.  It
+  returns null if there is no system memory available to create the
+  space.  If argument locked is non-zero, the space uses a separate
+  lock to control access. The capacity of the space will grow
+  dynamically as needed to service mspace_malloc requests.  You can
+  control the sizes of incremental increases of this space by
+  compiling with a different DEFAULT_GRANULARITY or dynamically
+  setting with mallopt(M_GRANULARITY, value).
+*/
+DLMALLOC_EXPORT mspace create_mspace(size_t capacity, int locked);
+
+/*
+  destroy_mspace destroys the given space, and attempts to return all
+  of its memory back to the system, returning the total number of
+  bytes freed. After destruction, the results of access to all memory
+  used by the space become undefined.
+*/
+DLMALLOC_EXPORT size_t destroy_mspace(mspace msp);
+
+/*
+  create_mspace_with_base uses the memory supplied as the initial base
+  of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this
+  space is used for bookkeeping, so the capacity must be at least this
+  large. (Otherwise 0 is returned.) When this initial space is
+  exhausted, additional memory will be obtained from the system.
+  Destroying this space will deallocate all additionally allocated
+  space (if possible) but not the initial base.
+*/
+DLMALLOC_EXPORT mspace create_mspace_with_base(void* base, size_t capacity, int locked);
+
+/*
+  mspace_track_large_chunks controls whether requests for large chunks
+  are allocated in their own untracked mmapped regions, separate from
+  others in this mspace. By default large chunks are not tracked,
+  which reduces fragmentation. However, such chunks are not
+  necessarily released to the system upon destroy_mspace.  Enabling
+  tracking by setting to true may increase fragmentation, but avoids
+  leakage when relying on destroy_mspace to release all memory
+  allocated using this space.  The function returns the previous
+  setting.
+*/
+DLMALLOC_EXPORT int mspace_track_large_chunks(mspace msp, int enable);
+
+
+/*
+  mspace_malloc behaves as malloc, but operates within
+  the given space.
+*/
+DLMALLOC_EXPORT void* mspace_malloc(mspace msp, size_t bytes);
+
+/*
+  mspace_free behaves as free, but operates within
+  the given space.
+
+  If compiled with FOOTERS==1, mspace_free is not actually needed.
+  free may be called instead of mspace_free because freed chunks from
+  any space are handled by their originating spaces.
+*/
+DLMALLOC_EXPORT void mspace_free(mspace msp, void* mem);
+
+/*
+  mspace_realloc behaves as realloc, but operates within
+  the given space.
+
+  If compiled with FOOTERS==1, mspace_realloc is not actually
+  needed.  realloc may be called instead of mspace_realloc because
+  realloced chunks from any space are handled by their originating
+  spaces.
+*/
+DLMALLOC_EXPORT void* mspace_realloc(mspace msp, void* mem, size_t newsize);
+
+/*
+  mspace_calloc behaves as calloc, but operates within
+  the given space.
+*/
+DLMALLOC_EXPORT void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size);
+
+/*
+  mspace_memalign behaves as memalign, but operates within
+  the given space.
+*/
+DLMALLOC_EXPORT void* mspace_memalign(mspace msp, size_t alignment, size_t bytes);
+
+/*
+  mspace_independent_calloc behaves as independent_calloc, but
+  operates within the given space.
+*/
+DLMALLOC_EXPORT void** mspace_independent_calloc(mspace msp, size_t n_elements,
+                                 size_t elem_size, void* chunks[]);
+
+/*
+  mspace_independent_comalloc behaves as independent_comalloc, but
+  operates within the given space.
+*/
+DLMALLOC_EXPORT void** mspace_independent_comalloc(mspace msp, size_t n_elements,
+                                   size_t sizes[], void* chunks[]);
+
+/*
+  mspace_footprint() returns the number of bytes obtained from the
+  system for this space.
+*/
+DLMALLOC_EXPORT size_t mspace_footprint(mspace msp);
+
+/*
+  mspace_max_footprint() returns the peak number of bytes obtained from the
+  system for this space.
+*/
+DLMALLOC_EXPORT size_t mspace_max_footprint(mspace msp);
+
+
+#if !NO_MALLINFO
+/*
+  mspace_mallinfo behaves as mallinfo, but reports properties of
+  the given space.
+*/
+DLMALLOC_EXPORT struct mallinfo mspace_mallinfo(mspace msp);
+#endif /* NO_MALLINFO */
+
+/*
+  malloc_usable_size(void* p) behaves the same as malloc_usable_size;
+*/
+DLMALLOC_EXPORT size_t mspace_usable_size(const void* mem);
+
+/*
+  mspace_malloc_stats behaves as malloc_stats, but reports
+  properties of the given space.
+*/
+DLMALLOC_EXPORT void mspace_malloc_stats(mspace msp);
+
+/*
+  mspace_trim behaves as malloc_trim, but
+  operates within the given space.
+*/
+DLMALLOC_EXPORT int mspace_trim(mspace msp, size_t pad);
+
+/*
+  An alias for mallopt.
+*/
+DLMALLOC_EXPORT int mspace_mallopt(int, int);
+
+#endif /* MSPACES */
+
+#ifdef __cplusplus
+}  /* end of extern "C" */
+#endif /* __cplusplus */
+
+/*
+  ========================================================================
+  To make a fully customizable malloc.h header file, cut everything
+  above this line, put into file malloc.h, edit to suit, and #include it
+  on the next line, as well as in programs that use this malloc.
+  ========================================================================
+*/
+
+/* #include "malloc.h" */
+
+/*------------------------------ internal #includes ---------------------- */
+
+#ifdef _MSC_VER
+#pragma warning( disable : 4146 ) /* no "unsigned" warnings */
+#endif /* _MSC_VER */
+#if !NO_MALLOC_STATS
+#include <stdio.h>       /* for printing in malloc_stats */
+#endif /* NO_MALLOC_STATS */
+#ifndef LACKS_ERRNO_H
+#include <errno.h>       /* for MALLOC_FAILURE_ACTION */
+#endif /* LACKS_ERRNO_H */
+#ifdef DEBUG
+#if ABORT_ON_ASSERT_FAILURE
+#undef assert
+#define assert(x) if(!(x)) ABORT
+#else /* ABORT_ON_ASSERT_FAILURE */
+#include <assert.h>
+#endif /* ABORT_ON_ASSERT_FAILURE */
+#else  /* DEBUG */
+#ifndef assert
+#define assert(x)
+#endif
+#define DEBUG 0
+#endif /* DEBUG */
+#if !defined(WIN32) && !defined(LACKS_TIME_H)
+#include <time.h>        /* for magic initialization */
+#endif /* WIN32 */
+#ifndef LACKS_STDLIB_H
+#include <stdlib.h>      /* for abort() */
+#endif /* LACKS_STDLIB_H */
+#ifndef LACKS_STRING_H
+#include <string.h>      /* for memset etc */
+#endif  /* LACKS_STRING_H */
+#if USE_BUILTIN_FFS
+#ifndef LACKS_STRINGS_H
+#include <strings.h>     /* for ffs */
+#endif /* LACKS_STRINGS_H */
+#endif /* USE_BUILTIN_FFS */
+#if HAVE_MMAP
+#ifndef LACKS_SYS_MMAN_H
+/* On some versions of linux, mremap decl in mman.h needs __USE_GNU set */
+#if (defined(linux) && !defined(__USE_GNU))
+#define __USE_GNU 1
+#include <sys/mman.h>    /* for mmap */
+#undef __USE_GNU
+#else
+#include <sys/mman.h>    /* for mmap */
+#endif /* linux */
+#endif /* LACKS_SYS_MMAN_H */
+#ifndef LACKS_FCNTL_H
+#include <fcntl.h>
+#endif /* LACKS_FCNTL_H */
+#endif /* HAVE_MMAP */
+#ifndef LACKS_UNISTD_H
+#include <unistd.h>     /* for sbrk, sysconf */
+#else /* LACKS_UNISTD_H */
+#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
+extern void*     sbrk(ptrdiff_t);
+#endif /* FreeBSD etc */
+#endif /* LACKS_UNISTD_H */
+
+/* Declarations for locking */
+#if USE_LOCKS
+#ifndef WIN32
+#if defined (__SVR4) && defined (__sun)  /* solaris */
+#include <thread.h>
+#elif !defined(LACKS_SCHED_H)
+#include <sched.h>
+#endif /* solaris or LACKS_SCHED_H */
+#if (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0) || !USE_SPIN_LOCKS
+#include <pthread.h>
+#endif /* USE_RECURSIVE_LOCKS ... */
+#elif defined(_MSC_VER)
+#ifndef _M_AMD64
+/* These are already defined on AMD64 builds */
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+LONG __cdecl _InterlockedCompareExchange(LONG volatile *Dest, LONG Exchange, LONG Comp);
+LONG __cdecl _InterlockedExchange(LONG volatile *Target, LONG Value);
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+#endif /* _M_AMD64 */
+#pragma intrinsic (_InterlockedCompareExchange)
+#pragma intrinsic (_InterlockedExchange)
+#define interlockedcompareexchange _InterlockedCompareExchange
+#define interlockedexchange _InterlockedExchange
+#elif defined(WIN32) && defined(__GNUC__)
+#define interlockedcompareexchange(a, b, c) __sync_val_compare_and_swap(a, c, b)
+#define interlockedexchange __sync_lock_test_and_set
+#endif /* Win32 */
+#else /* USE_LOCKS */
+#endif /* USE_LOCKS */
+
+#ifndef LOCK_AT_FORK
+#define LOCK_AT_FORK 0
+#endif
+
+/* Declarations for bit scanning on win32 */
+#if defined(_MSC_VER) && _MSC_VER>=1300
+#ifndef BitScanForward /* Try to avoid pulling in WinNT.h */
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+unsigned char _BitScanForward(unsigned long *index, unsigned long mask);
+unsigned char _BitScanReverse(unsigned long *index, unsigned long mask);
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#define BitScanForward _BitScanForward
+#define BitScanReverse _BitScanReverse
+#pragma intrinsic(_BitScanForward)
+#pragma intrinsic(_BitScanReverse)
+#endif /* BitScanForward */
+#endif /* defined(_MSC_VER) && _MSC_VER>=1300 */
+
+#ifndef WIN32
+#ifndef malloc_getpagesize
+#  ifdef _SC_PAGESIZE         /* some SVR4 systems omit an underscore */
+#    ifndef _SC_PAGE_SIZE
+#      define _SC_PAGE_SIZE _SC_PAGESIZE
+#    endif
+#  endif
+#  ifdef _SC_PAGE_SIZE
+#    define malloc_getpagesize sysconf(_SC_PAGE_SIZE)
+#  else
+#    if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE)
+       extern int getpagesize();
+#      define malloc_getpagesize getpagesize()
+#    else
+#      ifdef WIN32 /* use supplied emulation of getpagesize */
+#        define malloc_getpagesize getpagesize()
+#      else
+#        ifndef LACKS_SYS_PARAM_H
+#          include <sys/param.h>
+#        endif
+#        ifdef EXEC_PAGESIZE
+#          define malloc_getpagesize EXEC_PAGESIZE
+#        else
+#          ifdef NBPG
+#            ifndef CLSIZE
+#              define malloc_getpagesize NBPG
+#            else
+#              define malloc_getpagesize (NBPG * CLSIZE)
+#            endif
+#          else
+#            ifdef NBPC
+#              define malloc_getpagesize NBPC
+#            else
+#              ifdef PAGESIZE
+#                define malloc_getpagesize PAGESIZE
+#              else /* just guess */
+#                define malloc_getpagesize ((size_t)4096U)
+#              endif
+#            endif
+#          endif
+#        endif
+#      endif
+#    endif
+#  endif
+#endif
+#endif
+
+/* ------------------- size_t and alignment properties -------------------- */
+
+/* The byte and bit size of a size_t */
+#define SIZE_T_SIZE         (sizeof(size_t))
+#define SIZE_T_BITSIZE      (sizeof(size_t) << 3)
+
+/* Some constants coerced to size_t */
+/* Annoying but necessary to avoid errors on some platforms */
+#define SIZE_T_ZERO         ((size_t)0)
+#define SIZE_T_ONE          ((size_t)1)
+#define SIZE_T_TWO          ((size_t)2)
+#define SIZE_T_FOUR         ((size_t)4)
+#define TWO_SIZE_T_SIZES    (SIZE_T_SIZE<<1)
+#define FOUR_SIZE_T_SIZES   (SIZE_T_SIZE<<2)
+#define SIX_SIZE_T_SIZES    (FOUR_SIZE_T_SIZES+TWO_SIZE_T_SIZES)
+#define HALF_MAX_SIZE_T     (MAX_SIZE_T / 2U)
+
+/* The bit mask value corresponding to MALLOC_ALIGNMENT */
+#define CHUNK_ALIGN_MASK    (MALLOC_ALIGNMENT - SIZE_T_ONE)
+
+/* True if address a has acceptable alignment */
+#define is_aligned(A)       (((size_t)((A)) & (CHUNK_ALIGN_MASK)) == 0)
+
+/* the number of bytes to offset an address to align it */
+#define align_offset(A)\
+ ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\
+  ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK))
+
+/* -------------------------- MMAP preliminaries ------------------------- */
+
+/*
+   If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and
+   checks to fail so compiler optimizer can delete code rather than
+   using so many "#if"s.
+*/
+
+
+/* MORECORE and MMAP must return MFAIL on failure */
+#define MFAIL                ((void*)(MAX_SIZE_T))
+#define CMFAIL               ((char*)(MFAIL)) /* defined for convenience */
+
+#if HAVE_MMAP
+
+#ifndef WIN32
+#define MUNMAP_DEFAULT(a, s)  munmap((a), (s))
+#define MMAP_PROT            (PROT_READ|PROT_WRITE)
+#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON)
+#define MAP_ANONYMOUS        MAP_ANON
+#endif /* MAP_ANON */
+#ifdef MAP_ANONYMOUS
+#define MMAP_FLAGS           (MAP_PRIVATE|MAP_ANONYMOUS)
+#define MMAP_DEFAULT(s)       mmap(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0)
+#else /* MAP_ANONYMOUS */
+/*
+   Nearly all versions of mmap support MAP_ANONYMOUS, so the following
+   is unlikely to be needed, but is supplied just in case.
+*/
+#define MMAP_FLAGS           (MAP_PRIVATE)
+static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */
+#define MMAP_DEFAULT(s) ((dev_zero_fd < 0) ? \
+           (dev_zero_fd = open("/dev/zero", O_RDWR), \
+            mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \
+            mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0))
+#endif /* MAP_ANONYMOUS */
+
+#define DIRECT_MMAP_DEFAULT(s) MMAP_DEFAULT(s)
+
+#else /* WIN32 */
+
+/* Win32 MMAP via VirtualAlloc */
+SDL_FORCE_INLINE void* win32mmap(size_t size) {
+  void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE);
+  return (ptr != 0)? ptr: MFAIL;
+}
+
+/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */
+SDL_FORCE_INLINE void* win32direct_mmap(size_t size) {
+  void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN,
+                           PAGE_READWRITE);
+  return (ptr != 0)? ptr: MFAIL;
+}
+
+/* This function supports releasing coalesed segments */
+SDL_FORCE_INLINE int win32munmap(void* ptr, size_t size) {
+  MEMORY_BASIC_INFORMATION minfo;
+  char* cptr = (char*)ptr;
+  while (size) {
+    if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0)
+      return -1;
+    if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr ||
+        minfo.State != MEM_COMMIT || minfo.RegionSize > size)
+      return -1;
+    if (VirtualFree(cptr, 0, MEM_RELEASE) == 0)
+      return -1;
+    cptr += minfo.RegionSize;
+    size -= minfo.RegionSize;
+  }
+  return 0;
+}
+
+#define MMAP_DEFAULT(s)             win32mmap(s)
+#define MUNMAP_DEFAULT(a, s)        win32munmap((a), (s))
+#define DIRECT_MMAP_DEFAULT(s)      win32direct_mmap(s)
+#endif /* WIN32 */
+#endif /* HAVE_MMAP */
+
+#if HAVE_MREMAP
+#ifndef WIN32
+#define MREMAP_DEFAULT(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv))
+#endif /* WIN32 */
+#endif /* HAVE_MREMAP */
+
+/**
+ * Define CALL_MORECORE
+ */
+#if HAVE_MORECORE
+    #ifdef MORECORE
+        #define CALL_MORECORE(S)    MORECORE(S)
+    #else  /* MORECORE */
+        #define CALL_MORECORE(S)    MORECORE_DEFAULT(S)
+    #endif /* MORECORE */
+#else  /* HAVE_MORECORE */
+    #define CALL_MORECORE(S)        MFAIL
+#endif /* HAVE_MORECORE */
+
+/**
+ * Define CALL_MMAP/CALL_MUNMAP/CALL_DIRECT_MMAP
+ */
+#if HAVE_MMAP
+    #define USE_MMAP_BIT            (SIZE_T_ONE)
+
+    #ifdef MMAP
+        #define CALL_MMAP(s)        MMAP(s)
+    #else /* MMAP */
+        #define CALL_MMAP(s)        MMAP_DEFAULT(s)
+    #endif /* MMAP */
+    #ifdef MUNMAP
+        #define CALL_MUNMAP(a, s)   MUNMAP((a), (s))
+    #else /* MUNMAP */
+        #define CALL_MUNMAP(a, s)   MUNMAP_DEFAULT((a), (s))
+    #endif /* MUNMAP */
+    #ifdef DIRECT_MMAP
+        #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s)
+    #else /* DIRECT_MMAP */
+        #define CALL_DIRECT_MMAP(s) DIRECT_MMAP_DEFAULT(s)
+    #endif /* DIRECT_MMAP */
+#else  /* HAVE_MMAP */
+    #define USE_MMAP_BIT            (SIZE_T_ZERO)
+
+    #define MMAP(s)                 MFAIL
+    #define MUNMAP(a, s)            (-1)
+    #define DIRECT_MMAP(s)          MFAIL
+    #define CALL_DIRECT_MMAP(s)     DIRECT_MMAP(s)
+    #define CALL_MMAP(s)            MMAP(s)
+    #define CALL_MUNMAP(a, s)       MUNMAP((a), (s))
+#endif /* HAVE_MMAP */
+
+/**
+ * Define CALL_MREMAP
+ */
+#if HAVE_MMAP && HAVE_MREMAP
+    #ifdef MREMAP
+        #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP((addr), (osz), (nsz), (mv))
+    #else /* MREMAP */
+        #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP_DEFAULT((addr), (osz), (nsz), (mv))
+    #endif /* MREMAP */
+#else  /* HAVE_MMAP && HAVE_MREMAP */
+    #define CALL_MREMAP(addr, osz, nsz, mv)     MFAIL
+#endif /* HAVE_MMAP && HAVE_MREMAP */
+
+/* mstate bit set if continguous morecore disabled or failed */
+#define USE_NONCONTIGUOUS_BIT (4U)
+
+/* segment bit set in create_mspace_with_base */
+#define EXTERN_BIT            (8U)
+
+
+/* --------------------------- Lock preliminaries ------------------------ */
+
+/*
+  When locks are defined, there is one global lock, plus
+  one per-mspace lock.
+
+  The global lock_ensures that mparams.magic and other unique
+  mparams values are initialized only once. It also protects
+  sequences of calls to MORECORE.  In many cases sys_alloc requires
+  two calls, that should not be interleaved with calls by other
+  threads.  This does not protect against direct calls to MORECORE
+  by other threads not using this lock, so there is still code to
+  cope the best we can on interference.
+
+  Per-mspace locks surround calls to malloc, free, etc.
+  By default, locks are simple non-reentrant mutexes.
+
+  Because lock-protected regions generally have bounded times, it is
+  OK to use the supplied simple spinlocks. Spinlocks are likely to
+  improve performance for lightly contended applications, but worsen
+  performance under heavy contention.
+
+  If USE_LOCKS is > 1, the definitions of lock routines here are
+  bypassed, in which case you will need to define the type MLOCK_T,
+  and at least INITIAL_LOCK, DESTROY_LOCK, ACQUIRE_LOCK, RELEASE_LOCK
+  and TRY_LOCK.  You must also declare a
+    static MLOCK_T malloc_global_mutex = { initialization values };.
+
+*/
+
+#if !USE_LOCKS
+#define USE_LOCK_BIT               (0U)
+#define INITIAL_LOCK(l)            (0)
+#define DESTROY_LOCK(l)            (0)
+#define ACQUIRE_MALLOC_GLOBAL_LOCK()
+#define RELEASE_MALLOC_GLOBAL_LOCK()
+
+#else
+#if USE_LOCKS > 1
+/* -----------------------  User-defined locks ------------------------ */
+/* Define your own lock implementation here */
+/* #define INITIAL_LOCK(lk)  ... */
+/* #define DESTROY_LOCK(lk)  ... */
+/* #define ACQUIRE_LOCK(lk)  ... */
+/* #define RELEASE_LOCK(lk)  ... */
+/* #define TRY_LOCK(lk) ... */
+/* static MLOCK_T malloc_global_mutex = ... */
+
+#elif USE_SPIN_LOCKS
+
+/* First, define CAS_LOCK and CLEAR_LOCK on ints */
+/* Note CAS_LOCK defined to return 0 on success */
+
+#if defined(__GNUC__)&& (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1))
+#define CAS_LOCK(sl)     __sync_lock_test_and_set(sl, 1)
+#define CLEAR_LOCK(sl)   __sync_lock_release(sl)
+
+#elif (defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)))
+/* Custom spin locks for older gcc on x86 */
+SDL_FORCE_INLINE int x86_cas_lock(int *sl) {
+  int ret;
+  int val = 1;
+  int cmp = 0;
+  __asm__ __volatile__  ("lock; cmpxchgl %1, %2"
+                         : "=a" (ret)
+                         : "r" (val), "m" (*(sl)), "0"(cmp)
+                         : "memory", "cc");
+  return ret;
+}
+
+SDL_FORCE_INLINE void x86_clear_lock(int* sl) {
+  assert(*sl != 0);
+  int prev = 0;
+  int ret;
+  __asm__ __volatile__ ("lock; xchgl %0, %1"
+                        : "=r" (ret)
+                        : "m" (*(sl)), "0"(prev)
+                        : "memory");
+}
+
+#define CAS_LOCK(sl)     x86_cas_lock(sl)
+#define CLEAR_LOCK(sl)   x86_clear_lock(sl)
+
+#else /* Win32 MSC */
+#define CAS_LOCK(sl)     interlockedexchange(sl, (LONG)1)
+#define CLEAR_LOCK(sl)   interlockedexchange (sl, (LONG)0)
+
+#endif /* ... gcc spins locks ... */
+
+/* How to yield for a spin lock */
+#define SPINS_PER_YIELD       63
+#if defined(_MSC_VER)
+#define SLEEP_EX_DURATION     50 /* delay for yield/sleep */
+#define SPIN_LOCK_YIELD  SleepEx(SLEEP_EX_DURATION, FALSE)
+#elif defined (__SVR4) && defined (__sun) /* solaris */
+#define SPIN_LOCK_YIELD   thr_yield();
+#elif !defined(LACKS_SCHED_H)
+#define SPIN_LOCK_YIELD   sched_yield();
+#else
+#define SPIN_LOCK_YIELD
+#endif /* ... yield ... */
+
+#if !defined(USE_RECURSIVE_LOCKS) || USE_RECURSIVE_LOCKS == 0
+/* Plain spin locks use single word (embedded in malloc_states) */
+static int spin_acquire_lock(volatile long *sl) {
+  int spins = 0;
+  while (*sl != 0 || CAS_LOCK(sl)) {
+    if ((++spins & SPINS_PER_YIELD) == 0) {
+      SPIN_LOCK_YIELD;
+    }
+  }
+  return 0;
+}
+
+#define MLOCK_T               volatile long
+#define TRY_LOCK(sl)          !CAS_LOCK(sl)
+#define RELEASE_LOCK(sl)      CLEAR_LOCK(sl)
+#define ACQUIRE_LOCK(sl)      (CAS_LOCK(sl)? spin_acquire_lock(sl) : 0)
+#define INITIAL_LOCK(sl)      (*sl = 0)
+#define DESTROY_LOCK(sl)      (0)
+static MLOCK_T malloc_global_mutex = 0;
+
+#else /* USE_RECURSIVE_LOCKS */
+/* types for lock owners */
+#ifdef WIN32
+#define THREAD_ID_T           DWORD
+#define CURRENT_THREAD        GetCurrentThreadId()
+#define EQ_OWNER(X,Y)         ((X) == (Y))
+#else
+/*
+  Note: the following assume that pthread_t is a type that can be
+  initialized to (casted) zero. If this is not the case, you will need to
+  somehow redefine these or not use spin locks.
+*/
+#define THREAD_ID_T           pthread_t
+#define CURRENT_THREAD        pthread_self()
+#define EQ_OWNER(X,Y)         pthread_equal(X, Y)
+#endif
+
+struct malloc_recursive_lock {
+  int sl;
+  unsigned int c;
+  THREAD_ID_T threadid;
+};
+
+#define MLOCK_T  struct malloc_recursive_lock
+static MLOCK_T malloc_global_mutex = { 0, 0, (THREAD_ID_T)0};
+
+SDL_FORCE_INLINE void recursive_release_lock(MLOCK_T *lk) {
+  assert(lk->sl != 0);
+  if (--lk->c == 0) {
+    CLEAR_LOCK(&lk->sl);
+  }
+}
+
+SDL_FORCE_INLINE int recursive_acquire_lock(MLOCK_T *lk) {
+  THREAD_ID_T mythreadid = CURRENT_THREAD;
+  int spins = 0;
+  for (;;) {
+    if (*((volatile int *)(&lk->sl)) == 0) {
+      if (!CAS_LOCK(&lk->sl)) {
+        lk->threadid = mythreadid;
+        lk->c = 1;
+        return 0;
+      }
+    }
+    else if (EQ_OWNER(lk->threadid, mythreadid)) {
+      ++lk->c;
+      return 0;
+    }
+    if ((++spins & SPINS_PER_YIELD) == 0) {
+      SPIN_LOCK_YIELD;
+    }
+  }
+}
+
+SDL_FORCE_INLINE int recursive_try_lock(MLOCK_T *lk) {
+  THREAD_ID_T mythreadid = CURRENT_THREAD;
+  if (*((volatile int *)(&lk->sl)) == 0) {
+    if (!CAS_LOCK(&lk->sl)) {
+      lk->threadid = mythreadid;
+      lk->c = 1;
+      return 1;
+    }
+  }
+  else if (EQ_OWNER(lk->threadid, mythreadid)) {
+    ++lk->c;
+    return 1;
+  }
+  return 0;
+}
+
+#define RELEASE_LOCK(lk)      recursive_release_lock(lk)
+#define TRY_LOCK(lk)          recursive_try_lock(lk)
+#define ACQUIRE_LOCK(lk)      recursive_acquire_lock(lk)
+#define INITIAL_LOCK(lk)      ((lk)->threadid = (THREAD_ID_T)0, (lk)->sl = 0, (lk)->c = 0)
+#define DESTROY_LOCK(lk)      (0)
+#endif /* USE_RECURSIVE_LOCKS */
+
+#elif defined(WIN32) /* Win32 critical sections */
+#define MLOCK_T               CRITICAL_SECTION
+#define ACQUIRE_LOCK(lk)      (EnterCriticalSection(lk), 0)
+#define RELEASE_LOCK(lk)      LeaveCriticalSection(lk)
+#define TRY_LOCK(lk)          TryEnterCriticalSection(lk)
+#define INITIAL_LOCK(lk)      (!InitializeCriticalSectionAndSpinCount((lk), 0x80000000|4000))
+#define DESTROY_LOCK(lk)      (DeleteCriticalSection(lk), 0)
+#define NEED_GLOBAL_LOCK_INIT
+
+static MLOCK_T malloc_global_mutex;
+static volatile LONG malloc_global_mutex_status;
+
+/* Use spin loop to initialize global lock */
+static void init_malloc_global_mutex() {
+  for (;;) {
+    long stat = malloc_global_mutex_status;
+    if (stat > 0)
+      return;
+    /* transition to < 0 while initializing, then to > 0) */
+    if (stat == 0 &&
+        interlockedcompareexchange(&malloc_global_mutex_status, (LONG)-1, (LONG)0) == 0) {
+      InitializeCriticalSection(&malloc_global_mutex);
+      interlockedexchange(&malloc_global_mutex_status, (LONG)1);
+      return;
+    }
+    SleepEx(0, FALSE);
+  }
+}
+
+#else /* pthreads-based locks */
+#define MLOCK_T               pthread_mutex_t
+#define ACQUIRE_LOCK(lk)      pthread_mutex_lock(lk)
+#define RELEASE_LOCK(lk)      pthread_mutex_unlock(lk)
+#define TRY_LOCK(lk)          (!pthread_mutex_trylock(lk))
+#define INITIAL_LOCK(lk)      pthread_init_lock(lk)
+#define DESTROY_LOCK(lk)      pthread_mutex_destroy(lk)
+
+#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0 && defined(linux) && !defined(PTHREAD_MUTEX_RECURSIVE)
+/* Cope with old-style linux recursive lock initialization by adding */
+/* skipped internal declaration from pthread.h */
+extern int pthread_mutexattr_setkind_np __P ((pthread_mutexattr_t *__attr,
+                                              int __kind));
+#define PTHREAD_MUTEX_RECURSIVE PTHREAD_MUTEX_RECURSIVE_NP
+#define pthread_mutexattr_settype(x,y) pthread_mutexattr_setkind_np(x,y)
+#endif /* USE_RECURSIVE_LOCKS ... */
+
+static MLOCK_T malloc_global_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+static int pthread_init_lock (MLOCK_T *lk) {
+  pthread_mutexattr_t attr;
+  if (pthread_mutexattr_init(&attr)) return 1;
+#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0
+  if (pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)) return 1;
+#endif
+  if (pthread_mutex_init(lk, &attr)) return 1;
+  if (pthread_mutexattr_destroy(&attr)) return 1;
+  return 0;
+}
+
+#endif /* ... lock types ... */
+
+/* Common code for all lock types */
+#define USE_LOCK_BIT               (2U)
+
+#ifndef ACQUIRE_MALLOC_GLOBAL_LOCK
+#define ACQUIRE_MALLOC_GLOBAL_LOCK()  ACQUIRE_LOCK(&malloc_global_mutex);
+#endif
+
+#ifndef RELEASE_MALLOC_GLOBAL_LOCK
+#define RELEASE_MALLOC_GLOBAL_LOCK()  RELEASE_LOCK(&malloc_global_mutex);
+#endif
+
+#endif /* USE_LOCKS */
+
+/* -----------------------  Chunk representations ------------------------ */
+
+/*
+  (The following includes lightly edited explanations by Colin Plumb.)
+
+  The malloc_chunk declaration below is misleading (but accurate and
+  necessary).  It declares a "view" into memory allowing access to
+  necessary fields at known offsets from a given base.
+
+  Chunks of memory are maintained using a `boundary tag' method as
+  originally described by Knuth.  (See the paper by Paul Wilson
+  ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such
+  techniques.)  Sizes of free chunks are stored both in the front of
+  each chunk and at the end.  This makes consolidating fragmented
+  chunks into bigger chunks fast.  The head fields also hold bits
+  representing whether chunks are free or in use.
+
+  Here are some pictures to make it clearer.  They are "exploded" to
+  show that the state of a chunk can be thought of as extending from
+  the high 31 bits of the head field of its header through the
+  prev_foot and PINUSE_BIT bit of the following chunk header.
+
+  A chunk that's in use looks like:
+
+   chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+           | Size of previous chunk (if P = 0)                             |
+           +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P|
+         | Size of this chunk                                         1| +-+
+   mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         |                                                               |
+         +-                                                             -+
+         |                                                               |
+         +-                                                             -+
+         |                                                               :
+         +-      size - sizeof(size_t) available payload bytes          -+
+         :                                                               |
+ chunk-> +-                                                             -+
+         |                                                               |
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1|
+       | Size of next chunk (may or may not be in use)               | +-+
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+    And if it's free, it looks like this:
+
+   chunk-> +-                                                             -+
+           | User payload (must be in use, or we would have merged!)       |
+           +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P|
+         | Size of this chunk                                         0| +-+
+   mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         | Next pointer                                                  |
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         | Prev pointer                                                  |
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         |                                                               :
+         +-      size - sizeof(struct chunk) unused bytes               -+
+         :                                                               |
+ chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         | Size of this chunk                                            |
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0|
+       | Size of next chunk (must be in use, or we would have merged)| +-+
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+       |                                                               :
+       +- User payload                                                -+
+       :                                                               |
+       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+                                                                     |0|
+                                                                     +-+
+  Note that since we always merge adjacent free chunks, the chunks
+  adjacent to a free chunk must be in use.
+
+  Given a pointer to a chunk (which can be derived trivially from the
+  payload pointer) we can, in O(1) time, find out whether the adjacent
+  chunks are free, and if so, unlink them from the lists that they
+  are on and merge them with the current chunk.
+
+  Chunks always begin on even word boundaries, so the mem portion
+  (which is returned to the user) is also on an even word boundary, and
+  thus at least double-word aligned.
+
+  The P (PINUSE_BIT) bit, stored in the unused low-order bit of the
+  chunk size (which is always a multiple of two words), is an in-use
+  bit for the *previous* chunk.  If that bit is *clear*, then the
+  word before the current chunk size contains the previous chunk
+  size, and can be used to find the front of the previous chunk.
+  The very first chunk allocated always has this bit set, preventing
+  access to non-existent (or non-owned) memory. If pinuse is set for
+  any given chunk, then you CANNOT determine the size of the
+  previous chunk, and might even get a memory addressing fault when
+  trying to do so.
+
+  The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of
+  the chunk size redundantly records whether the current chunk is
+  inuse (unless the chunk is mmapped). This redundancy enables usage
+  checks within free and realloc, and reduces indirection when freeing
+  and consolidating chunks.
+
+  Each freshly allocated chunk must have both cinuse and pinuse set.
+  That is, each allocated chunk borders either a previously allocated
+  and still in-use chunk, or the base of its memory arena. This is
+  ensured by making all allocations from the `lowest' part of any
+  found chunk.  Further, no free chunk physically borders another one,
+  so each free chunk is known to be preceded and followed by either
+  inuse chunks or the ends of memory.
+
+  Note that the `foot' of the current chunk is actually represented
+  as the prev_foot of the NEXT chunk. This makes it easier to
+  deal with alignments etc but can be very confusing when trying
+  to extend or adapt this code.
+
+  The exceptions to all this are
+
+     1. The special chunk `top' is the top-most available chunk (i.e.,
+        the one bordering the end of available memory). It is treated
+        specially.  Top is never included in any bin, is used only if
+        no other chunk is available, and is released back to the
+        system if it is very large (see M_TRIM_THRESHOLD).  In effect,
+        the top chunk is treated as larger (and thus less well
+        fitting) than any other available chunk.  The top chunk
+        doesn't update its trailing size field since there is no next
+        contiguous chunk that would have to index off it. However,
+        space is still allocated for it (TOP_FOOT_SIZE) to enable
+        separation or merging when space is extended.
+
+     3. Chunks allocated via mmap, have both cinuse and pinuse bits
+        cleared in their head fields.  Because they are allocated
+        one-by-one, each must carry its own prev_foot field, which is
+        also used to hold the offset this chunk has within its mmapped
+        region, which is needed to preserve alignment. Each mmapped
+        chunk is trailed by the first two fields of a fake next-chunk
+        for sake of usage checks.
+
+*/
+
+struct malloc_chunk {
+  size_t               prev_foot;  /* Size of previous chunk (if free).  */
+  size_t               head;       /* Size and inuse bits. */
+  struct malloc_chunk* fd;         /* double links -- used only if free. */
+  struct malloc_chunk* bk;
+};
+
+typedef struct malloc_chunk  mchunk;
+typedef struct malloc_chunk* mchunkptr;
+typedef struct malloc_chunk* sbinptr;  /* The type of bins of chunks */
+typedef unsigned int bindex_t;         /* Described below */
+typedef unsigned int binmap_t;         /* Described below */
+typedef unsigned int flag_t;           /* The type of various bit flag sets */
+
+/* ------------------- Chunks sizes and alignments ----------------------- */
+
+#define MCHUNK_SIZE         (sizeof(mchunk))
+
+#if FOOTERS
+#define CHUNK_OVERHEAD      (TWO_SIZE_T_SIZES)
+#else /* FOOTERS */
+#define CHUNK_OVERHEAD      (SIZE_T_SIZE)
+#endif /* FOOTERS */
+
+/* MMapped chunks need a second word of overhead ... */
+#define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES)
+/* ... and additional padding for fake next-chunk at foot */
+#define MMAP_FOOT_PAD       (FOUR_SIZE_T_SIZES)
+
+/* The smallest size we can malloc is an aligned minimal chunk */
+#define MIN_CHUNK_SIZE\
+  ((MCHUNK_SIZE + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK)
+
+/* conversion from malloc headers to user pointers, and back */
+#define chunk2mem(p)        ((void*)((char*)(p)       + TWO_SIZE_T_SIZES))
+#define mem2chunk(mem)      ((mchunkptr)((char*)(mem) - TWO_SIZE_T_SIZES))
+/* chunk associated with aligned address A */
+#define align_as_chunk(A)   (mchunkptr)((A) + align_offset(chunk2mem(A)))
+
+/* Bounds on request (not chunk) sizes. */
+#define MAX_REQUEST         ((-MIN_CHUNK_SIZE) << 2)
+#define MIN_REQUEST         (MIN_CHUNK_SIZE - CHUNK_OVERHEAD - SIZE_T_ONE)
+
+/* pad request bytes into a usable size */
+#define pad_request(req) \
+   (((req) + CHUNK_OVERHEAD + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK)
+
+/* pad request, checking for minimum (but not maximum) */
+#define request2size(req) \
+  (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req))
+
+
+/* ------------------ Operations on head and foot fields ----------------- */
+
+/*
+  The head field of a chunk is or'ed with PINUSE_BIT when previous
+  adjacent chunk in use, and or'ed with CINUSE_BIT if this chunk is in
+  use, unless mmapped, in which case both bits are cleared.
+
+  FLAG4_BIT is not used by this malloc, but might be useful in extensions.
+*/
+
+#define PINUSE_BIT          (SIZE_T_ONE)
+#define CINUSE_BIT          (SIZE_T_TWO)
+#define FLAG4_BIT           (SIZE_T_FOUR)
+#define INUSE_BITS          (PINUSE_BIT|CINUSE_BIT)
+#define FLAG_BITS           (PINUSE_BIT|CINUSE_BIT|FLAG4_BIT)
+
+/* Head value for fenceposts */
+#define FENCEPOST_HEAD      (INUSE_BITS|SIZE_T_SIZE)
+
+/* extraction of fields from head words */
+#define cinuse(p)           ((p)->head & CINUSE_BIT)
+#define pinuse(p)           ((p)->head & PINUSE_BIT)
+#define flag4inuse(p)       ((p)->head & FLAG4_BIT)
+#define is_inuse(p)         (((p)->head & INUSE_BITS) != PINUSE_BIT)
+#define is_mmapped(p)       (((p)->head & INUSE_BITS) == 0)
+
+#define chunksize(p)        ((p)->head & ~(FLAG_BITS))
+
+#define clear_pinuse(p)     ((p)->head &= ~PINUSE_BIT)
+#define set_flag4(p)        ((p)->head |= FLAG4_BIT)
+#define clear_flag4(p)      ((p)->head &= ~FLAG4_BIT)
+
+/* Treat space at ptr +/- offset as a chunk */
+#define chunk_plus_offset(p, s)  ((mchunkptr)(((char*)(p)) + (s)))
+#define chunk_minus_offset(p, s) ((mchunkptr)(((char*)(p)) - (s)))
+
+/* Ptr to next or previous physical malloc_chunk. */
+#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->head & ~FLAG_BITS)))
+#define prev_chunk(p) ((mchunkptr)( ((char*)(p)) - ((p)->prev_foot) ))
+
+/* extract next chunk's pinuse bit */
+#define next_pinuse(p)  ((next_chunk(p)->head) & PINUSE_BIT)
+
+/* Get/set size at footer */
+#define get_foot(p, s)  (((mchunkptr)((char*)(p) + (s)))->prev_foot)
+#define set_foot(p, s)  (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s))
+
+/* Set size, pinuse bit, and foot */
+#define set_size_and_pinuse_of_free_chunk(p, s)\
+  ((p)->head = (s|PINUSE_BIT), set_foot(p, s))
+
+/* Set size, pinuse bit, foot, and clear next pinuse */
+#define set_free_with_pinuse(p, s, n)\
+  (clear_pinuse(n), set_size_and_pinuse_of_free_chunk(p, s))
+
+/* Get the internal overhead associated with chunk p */
+#define overhead_for(p)\
+ (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD)
+
+/* Return true if malloced space is not necessarily cleared */
+#if MMAP_CLEARS
+#define calloc_must_clear(p) (!is_mmapped(p))
+#else /* MMAP_CLEARS */
+#define calloc_must_clear(p) (1)
+#endif /* MMAP_CLEARS */
+
+/* ---------------------- Overlaid data structures ----------------------- */
+
+/*
+  When chunks are not in use, they are treated as nodes of either
+  lists or trees.
+
+  "Small"  chunks are stored in circular doubly-linked lists, and look
+  like this:
+
+    chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Size of previous chunk                            |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+    `head:' |             Size of chunk, in bytes                         |P|
+      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Forward pointer to next chunk in list             |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Back pointer to previous chunk in list            |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Unused space (may be 0 bytes long)                .
+            .                                                               .
+            .                                                               |
+nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+    `foot:' |             Size of chunk, in bytes                           |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+  Larger chunks are kept in a form of bitwise digital trees (aka
+  tries) keyed on chunksizes.  Because malloc_tree_chunks are only for
+  free chunks greater than 256 bytes, their size doesn't impose any
+  constraints on user chunk sizes.  Each node looks like:
+
+    chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Size of previous chunk                            |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+    `head:' |             Size of chunk, in bytes                         |P|
+      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Forward pointer to next chunk of same size        |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Back pointer to previous chunk of same size       |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Pointer to left child (child[0])                  |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Pointer to right child (child[1])                 |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Pointer to parent                                 |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             bin index of this chunk                           |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Unused space                                      .
+            .                                                               |
+nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+    `foot:' |             Size of chunk, in bytes                           |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+  Each tree holding treenodes is a tree of unique chunk sizes.  Chunks
+  of the same size are arranged in a circularly-linked list, with only
+  the oldest chunk (the next to be used, in our FIFO ordering)
+  actually in the tree.  (Tree members are distinguished by a non-null
+  parent pointer.)  If a chunk with the same size an an existing node
+  is inserted, it is linked off the existing node using pointers that
+  work in the same way as fd/bk pointers of small chunks.
+
+  Each tree contains a power of 2 sized range of chunk sizes (the
+  smallest is 0x100 <= x < 0x180), which is is divided in half at each
+  tree level, with the chunks in the smaller half of the range (0x100
+  <= x < 0x140 for the top nose) in the left subtree and the larger
+  half (0x140 <= x < 0x180) in the right subtree.  This is, of course,
+  done by inspecting individual bits.
+
+  Using these rules, each node's left subtree contains all smaller
+  sizes than its right subtree.  However, the node at the root of each
+  subtree has no particular ordering relationship to either.  (The
+  dividing line between the subtree sizes is based on trie relation.)
+  If we remove the last chunk of a given size from the interior of the
+  tree, we need to replace it with a leaf node.  The tree ordering
+  rules permit a node to be replaced by any leaf below it.
+
+  The smallest chunk in a tree (a common operation in a best-fit
+  allocator) can be found by walking a path to the leftmost leaf in
+  the tree.  Unlike a usual binary tree, where we follow left child
+  pointers until we reach a null, here we follow the right child
+  pointer any time the left one is null, until we reach a leaf with
+  both child pointers null. The smallest chunk in the tree will be
+  somewhere along that path.
+
+  The worst case number of steps to add, find, or remove a node is
+  bounded by the number of bits differentiating chunks within
+  bins. Under current bin calculations, this ranges from 6 up to 21
+  (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case
+  is of course much better.
+*/
+
+struct malloc_tree_chunk {
+  /* The first four fields must be compatible with malloc_chunk */
+  size_t                    prev_foot;
+  size_t                    head;
+  struct malloc_tree_chunk* fd;
+  struct malloc_tree_chunk* bk;
+
+  struct malloc_tree_chunk* child[2];
+  struct malloc_tree_chunk* parent;
+  bindex_t                  index;
+};
+
+typedef struct malloc_tree_chunk  tchunk;
+typedef struct malloc_tree_chunk* tchunkptr;
+typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */
+
+/* A little helper macro for trees */
+#define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1])
+
+/* ----------------------------- Segments -------------------------------- */
+
+/*
+  Each malloc space may include non-contiguous segments, held in a
+  list headed by an embedded malloc_segment record representing the
+  top-most space. Segments also include flags holding properties of
+  the space. Large chunks that are directly allocated by mmap are not
+  included in this list. They are instead independently created and
+  destroyed without otherwise keeping track of them.
+
+  Segment management mainly comes into play for spaces allocated by
+  MMAP.  Any call to MMAP might or might not return memory that is
+  adjacent to an existing segment.  MORECORE normally contiguously
+  extends the current space, so this space is almost always adjacent,
+  which is simpler and faster to deal with. (This is why MORECORE is
+  used preferentially to MMAP when both are available -- see
+  sys_alloc.)  When allocating using MMAP, we don't use any of the
+  hinting mechanisms (inconsistently) supported in various
+  implementations of unix mmap, or distinguish reserving from
+  committing memory. Instead, we just ask for space, and exploit
+  contiguity when we get it.  It is probably possible to do
+  better than this on some systems, but no general scheme seems
+  to be significantly better.
+
+  Management entails a simpler variant of the consolidation scheme
+  used for chunks to reduce fragmentation -- new adjacent memory is
+  normally prepended or appended to an existing segment. However,
+  there are limitations compared to chunk consolidation that mostly
+  reflect the fact that segment processing is relatively infrequent
+  (occurring only when getting memory from system) and that we
+  don't expect to have huge numbers of segments:
+
+  * Segments are not indexed, so traversal requires linear scans.  (It
+    would be possible to index these, but is not worth the extra
+    overhead and complexity for most programs on most platforms.)
+  * New segments are only appended to old ones when holding top-most
+    memory; if they cannot be prepended to others, they are held in
+    different segments.
+
+  Except for the top-most segment of an mstate, each segment record
+  is kept at the tail of its segment. Segments are added by pushing
+  segment records onto the list headed by &mstate.seg for the
+  containing mstate.
+
+  Segment flags control allocation/merge/deallocation policies:
+  * If EXTERN_BIT set, then we did not allocate this segment,
+    and so should not try to deallocate or merge with others.
+    (This currently holds only for the initial segment passed
+    into create_mspace_with_base.)
+  * If USE_MMAP_BIT set, the segment may be merged with
+    other surrounding mmapped segments and trimmed/de-allocated
+    using munmap.
+  * If neither bit is set, then the segment was obtained using
+    MORECORE so can be merged with surrounding MORECORE'd segments
+    and deallocated/trimmed using MORECORE with negative arguments.
+*/
+
+struct malloc_segment {
+  char*        base;             /* base address */
+  size_t       size;             /* allocated size */
+  struct malloc_segment* next;   /* ptr to next segment */
+  flag_t       sflags;           /* mmap and extern flag */
+};
+
+#define is_mmapped_segment(S)  ((S)->sflags & USE_MMAP_BIT)
+#define is_extern_segment(S)   ((S)->sflags & EXTERN_BIT)
+
+typedef struct malloc_segment  msegment;
+typedef struct malloc_segment* msegmentptr;
+
+/* ---------------------------- malloc_state ----------------------------- */
+
+/*
+   A malloc_state holds all of the bookkeeping for a space.
+   The main fields are:
+
+  Top
+    The topmost chunk of the currently active segment. Its size is
+    cached in topsize.  The actual size of topmost space is
+    topsize+TOP_FOOT_SIZE, which includes space reserved for adding
+    fenceposts and segment records if necessary when getting more
+    space from the system.  The size at which to autotrim top is
+    cached from mparams in trim_check, except that it is disabled if
+    an autotrim fails.
+
+  Designated victim (dv)
+    This is the preferred chunk for servicing small requests that
+    don't have exact fits.  It is normally the chunk split off most
+    recently to service another small request.  Its size is cached in
+    dvsize. The link fields of this chunk are not maintained since it
+    is not kept in a bin.
+
+  SmallBins
+    An array of bin headers for free chunks.  These bins hold chunks
+    with sizes less than MIN_LARGE_SIZE bytes. Each bin contains
+    chunks of all the same size, spaced 8 bytes apart.  To simplify
+    use in double-linked lists, each bin header acts as a malloc_chunk
+    pointing to the real first node, if it exists (else pointing to
+    itself).  This avoids special-casing for headers.  But to avoid
+    waste, we allocate only the fd/bk pointers of bins, and then use
+    repositioning tricks to treat these as the fields of a chunk.
+
+  TreeBins
+    Treebins are pointers to the roots of trees holding a range of
+    sizes. There are 2 equally spaced treebins for each power of two
+    from TREE_SHIFT to TREE_SHIFT+16. The last bin holds anything
+    larger.
+
+  Bin maps
+    There is one bit map for small bins ("smallmap") and one for
+    treebins ("treemap).  Each bin sets its bit when non-empty, and
+    clears the bit when empty.  Bit operations are then used to avoid
+    bin-by-bin searching -- nearly all "search" is done without ever
+    looking at bins that won't be selected.  The bit maps
+    conservatively use 32 bits per map word, even if on 64bit system.
+    For a good description of some of the bit-based techniques used
+    here, see Henry S. Warren Jr's book "Hacker's Delight" (and
+    supplement at http://hackersdelight.org/). Many of these are
+    intended to reduce the branchiness of paths through malloc etc, as
+    well as to reduce the number of memory locations read or written.
+
+  Segments
+    A list of segments headed by an embedded malloc_segment record
+    representing the initial space.
+
+  Address check support
+    The least_addr field is the least address ever obtained from
+    MORECORE or MMAP. Attempted frees and reallocs of any address less
+    than this are trapped (unless INSECURE is defined).
+
+  Magic tag
+    A cross-check field that should always hold same value as mparams.magic.
+
+  Max allowed footprint
+    The maximum allowed bytes to allocate from system (zero means no limit)
+
+  Flags
+    Bits recording whether to use MMAP, locks, or contiguous MORECORE
+
+  Statistics
+    Each space keeps track of current and maximum system memory
+    obtained via MORECORE or MMAP.
+
+  Trim support
+    Fields holding the amount of unused topmost memory that should trigger
+    trimming, and a counter to force periodic scanning to release unused
+    non-topmost segments.
+
+  Locking
+    If USE_LOCKS is defined, the "mutex" lock is acquired and released
+    around every public call using this mspace.
+
+  Extension support
+    A void* pointer and a size_t field that can be used to help implement
+    extensions to this malloc.
+*/
+
+/* Bin types, widths and sizes */
+#define NSMALLBINS        (32U)
+#define NTREEBINS         (32U)
+#define SMALLBIN_SHIFT    (3U)
+#define SMALLBIN_WIDTH    (SIZE_T_ONE << SMALLBIN_SHIFT)
+#define TREEBIN_SHIFT     (8U)
+#define MIN_LARGE_SIZE    (SIZE_T_ONE << TREEBIN_SHIFT)
+#define MAX_SMALL_SIZE    (MIN_LARGE_SIZE - SIZE_T_ONE)
+#define MAX_SMALL_REQUEST (MAX_SMALL_SIZE - CHUNK_ALIGN_MASK - CHUNK_OVERHEAD)
+
+struct malloc_state {
+  binmap_t   smallmap;
+  binmap_t   treemap;
+  size_t     dvsize;
+  size_t     topsize;
+  char*      least_addr;
+  mchunkptr  dv;
+  mchunkptr  top;
+  size_t     trim_check;
+  size_t     release_checks;
+  size_t     magic;
+  mchunkptr  smallbins[(NSMALLBINS+1)*2];
+  tbinptr    treebins[NTREEBINS];
+  size_t     footprint;
+  size_t     max_footprint;
+  size_t     footprint_limit; /* zero means no limit */
+  flag_t     mflags;
+#if USE_LOCKS
+  MLOCK_T    mutex;     /* locate lock among fields that rarely change */
+#endif /* USE_LOCKS */
+  msegment   seg;
+  void*      extp;      /* Unused but available for extensions */
+  size_t     exts;
+};
+
+typedef struct malloc_state*    mstate;
+
+/* ------------- Global malloc_state and malloc_params ------------------- */
+
+/*
+  malloc_params holds global properties, including those that can be
+  dynamically set using mallopt. There is a single instance, mparams,
+  initialized in init_mparams. Note that the non-zeroness of "magic"
+  also serves as an initialization flag.
+*/
+
+struct malloc_params {
+  size_t magic;
+  size_t page_size;
+  size_t granularity;
+  size_t mmap_threshold;
+  size_t trim_threshold;
+  flag_t default_mflags;
+};
+
+static struct malloc_params mparams;
+
+/* Ensure mparams initialized */
+#define ensure_initialization() (void)(mparams.magic != 0 || init_mparams())
+
+#if !ONLY_MSPACES
+
+/* The global malloc_state used for all non-"mspace" calls */
+static struct malloc_state _gm_;
+#define gm                 (&_gm_)
+#define is_global(M)       ((M) == &_gm_)
+
+#endif /* !ONLY_MSPACES */
+
+#define is_initialized(M)  ((M)->top != 0)
+
+/* -------------------------- system alloc setup ------------------------- */
+
+/* Operations on mflags */
+
+#define use_lock(M)           ((M)->mflags &   USE_LOCK_BIT)
+#define enable_lock(M)        ((M)->mflags |=  USE_LOCK_BIT)
+#if USE_LOCKS
+#define disable_lock(M)       ((M)->mflags &= ~USE_LOCK_BIT)
+#else
+#define disable_lock(M)
+#endif
+
+#define use_mmap(M)           ((M)->mflags &   USE_MMAP_BIT)
+#define enable_mmap(M)        ((M)->mflags |=  USE_MMAP_BIT)
+#if HAVE_MMAP
+#define disable_mmap(M)       ((M)->mflags &= ~USE_MMAP_BIT)
+#else
+#define disable_mmap(M)
+#endif
+
+#define use_noncontiguous(M)  ((M)->mflags &   USE_NONCONTIGUOUS_BIT)
+#define disable_contiguous(M) ((M)->mflags |=  USE_NONCONTIGUOUS_BIT)
+
+#define set_lock(M,L)\
+ ((M)->mflags = (L)?\
+  ((M)->mflags | USE_LOCK_BIT) :\
+  ((M)->mflags & ~USE_LOCK_BIT))
+
+/* page-align a size */
+#define page_align(S)\
+ (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE))
+
+/* granularity-align a size */
+#define granularity_align(S)\
+  (((S) + (mparams.granularity - SIZE_T_ONE))\
+   & ~(mparams.granularity - SIZE_T_ONE))
+
+
+/* For mmap, use granularity alignment on windows, else page-align */
+#ifdef WIN32
+#define mmap_align(S) granularity_align(S)
+#else
+#define mmap_align(S) page_align(S)
+#endif
+
+/* For sys_alloc, enough padding to ensure can malloc request on success */
+#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT)
+
+#define is_page_aligned(S)\
+   (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0)
+#define is_granularity_aligned(S)\
+   (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0)
+
+/*  True if segment S holds address A */
+#define segment_holds(S, A)\
+  ((char*)(A) >= S->base && (char*)(A) < S->base + S->size)
+
+/* Return segment holding given address */
+static msegmentptr segment_holding(mstate m, char* addr) {
+  msegmentptr sp = &m->seg;
+  for (;;) {
+    if (addr >= sp->base && addr < sp->base + sp->size)
+      return sp;
+    if ((sp = sp->next) == 0)
+      return 0;
+  }
+}
+
+/* Return true if segment contains a segment link */
+static int has_segment_link(mstate m, msegmentptr ss) {
+  msegmentptr sp = &m->seg;
+  for (;;) {
+    if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size)
+      return 1;
+    if ((sp = sp->next) == 0)
+      return 0;
+  }
+}
+
+#ifndef MORECORE_CANNOT_TRIM
+#define should_trim(M,s)  ((s) > (M)->trim_check)
+#else  /* MORECORE_CANNOT_TRIM */
+#define should_trim(M,s)  (0)
+#endif /* MORECORE_CANNOT_TRIM */
+
+/*
+  TOP_FOOT_SIZE is padding at the end of a segment, including space
+  that may be needed to place segment records and fenceposts when new
+  noncontiguous segments are added.
+*/
+#define TOP_FOOT_SIZE\
+  (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE)
+
+
+/* -------------------------------  Hooks -------------------------------- */
+
+/*
+  PREACTION should be defined to return 0 on success, and nonzero on
+  failure. If you are not using locking, you can redefine these to do
+  anything you like.
+*/
+
+#if USE_LOCKS
+#define PREACTION(M)  ((use_lock(M))? ACQUIRE_LOCK(&(M)->mutex) : 0)
+#define POSTACTION(M) { if (use_lock(M)) RELEASE_LOCK(&(M)->mutex); }
+#else /* USE_LOCKS */
+
+#ifndef PREACTION
+#define PREACTION(M) (0)
+#endif  /* PREACTION */
+
+#ifndef POSTACTION
+#define POSTACTION(M)
+#endif  /* POSTACTION */
+
+#endif /* USE_LOCKS */
+
+/*
+  CORRUPTION_ERROR_ACTION is triggered upon detected bad addresses.
+  USAGE_ERROR_ACTION is triggered on detected bad frees and
+  reallocs. The argument p is an address that might have triggered the
+  fault. It is ignored by the two predefined actions, but might be
+  useful in custom actions that try to help diagnose errors.
+*/
+
+#if PROCEED_ON_ERROR
+
+/* A count of the number of corruption errors causing resets */
+int malloc_corruption_error_count;
+
+/* default corruption action */
+static void reset_on_error(mstate m);
+
+#define CORRUPTION_ERROR_ACTION(m)  reset_on_error(m)
+#define USAGE_ERROR_ACTION(m, p)
+
+#else /* PROCEED_ON_ERROR */
+
+#ifndef CORRUPTION_ERROR_ACTION
+#define CORRUPTION_ERROR_ACTION(m) ABORT
+#endif /* CORRUPTION_ERROR_ACTION */
+
+#ifndef USAGE_ERROR_ACTION
+#define USAGE_ERROR_ACTION(m,p) ABORT
+#endif /* USAGE_ERROR_ACTION */
+
+#endif /* PROCEED_ON_ERROR */
+
+
+/* -------------------------- Debugging setup ---------------------------- */
+
+#if ! DEBUG
+
+#define check_free_chunk(M,P)
+#define check_inuse_chunk(M,P)
+#define check_malloced_chunk(M,P,N)
+#define check_mmapped_chunk(M,P)
+#define check_malloc_state(M)
+#define check_top_chunk(M,P)
+
+#else /* DEBUG */
+#define check_free_chunk(M,P)       do_check_free_chunk(M,P)
+#define check_inuse_chunk(M,P)      do_check_inuse_chunk(M,P)
+#define check_top_chunk(M,P)        do_check_top_chunk(M,P)
+#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N)
+#define check_mmapped_chunk(M,P)    do_check_mmapped_chunk(M,P)
+#define check_malloc_state(M)       do_check_malloc_state(M)
+
+static void   do_check_any_chunk(mstate m, mchunkptr p);
+static void   do_check_top_chunk(mstate m, mchunkptr p);
+static void   do_check_mmapped_chunk(mstate m, mchunkptr p);
+static void   do_check_inuse_chunk(mstate m, mchunkptr p);
+static void   do_check_free_chunk(mstate m, mchunkptr p);
+static void   do_check_malloced_chunk(mstate m, void* mem, size_t s);
+static void   do_check_tree(mstate m, tchunkptr t);
+static void   do_check_treebin(mstate m, bindex_t i);
+static void   do_check_smallbin(mstate m, bindex_t i);
+static void   do_check_malloc_state(mstate m);
+static int    bin_find(mstate m, mchunkptr x);
+static size_t traverse_and_check(mstate m);
+#endif /* DEBUG */
+
+/* ---------------------------- Indexing Bins ---------------------------- */
+
+#define is_small(s)         (((s) >> SMALLBIN_SHIFT) < NSMALLBINS)
+#define small_index(s)      (bindex_t)((s)  >> SMALLBIN_SHIFT)
+#define small_index2size(i) ((i)  << SMALLBIN_SHIFT)
+#define MIN_SMALL_INDEX     (small_index(MIN_CHUNK_SIZE))
+
+/* addressing by index. See above about smallbin repositioning */
+#define smallbin_at(M, i)   ((sbinptr)((char*)&((M)->smallbins[(i)<<1])))
+#define treebin_at(M,i)     (&((M)->treebins[i]))
+
+/* assign tree index for size S to variable I. Use x86 asm if possible  */
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+#define compute_tree_index(S, I)\
+{\
+  unsigned int X = S >> TREEBIN_SHIFT;\
+  if (X == 0)\
+    I = 0;\
+  else if (X > 0xFFFF)\
+    I = NTREEBINS-1;\
+  else {\
+    unsigned int K = (unsigned) sizeof(X)*__CHAR_BIT__ - 1 - (unsigned) __builtin_clz(X); \
+    I =  (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+  }\
+}
+
+#elif defined (__INTEL_COMPILER)
+#define compute_tree_index(S, I)\
+{\
+  size_t X = S >> TREEBIN_SHIFT;\
+  if (X == 0)\
+    I = 0;\
+  else if (X > 0xFFFF)\
+    I = NTREEBINS-1;\
+  else {\
+    unsigned int K = _bit_scan_reverse (X); \
+    I =  (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+  }\
+}
+
+#elif defined(_MSC_VER) && _MSC_VER>=1300
+#define compute_tree_index(S, I)\
+{\
+  size_t X = S >> TREEBIN_SHIFT;\
+  if (X == 0)\
+    I = 0;\
+  else if (X > 0xFFFF)\
+    I = NTREEBINS-1;\
+  else {\
+    unsigned int K;\
+    _BitScanReverse((DWORD *) &K, (DWORD) X);\
+    I =  (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+  }\
+}
+
+#else /* GNUC */
+#define compute_tree_index(S, I)\
+{\
+  size_t X = S >> TREEBIN_SHIFT;\
+  if (X == 0)\
+    I = 0;\
+  else if (X > 0xFFFF)\
+    I = NTREEBINS-1;\
+  else {\
+    unsigned int Y = (unsigned int)X;\
+    unsigned int N = ((Y - 0x100) >> 16) & 8;\
+    unsigned int K = (((Y <<= N) - 0x1000) >> 16) & 4;\
+    N += K;\
+    N += K = (((Y <<= K) - 0x4000) >> 16) & 2;\
+    K = 14 - N + ((Y <<= K) >> 15);\
+    I = (K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1));\
+  }\
+}
+#endif /* GNUC */
+
+/* Bit representing maximum resolved size in a treebin at i */
+#define bit_for_tree_index(i) \
+   (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2)
+
+/* Shift placing maximum resolved bit in a treebin at i as sign bit */
+#define leftshift_for_tree_index(i) \
+   ((i == NTREEBINS-1)? 0 : \
+    ((SIZE_T_BITSIZE-SIZE_T_ONE) - (((i) >> 1) + TREEBIN_SHIFT - 2)))
+
+/* The size of the smallest chunk held in bin with index i */
+#define minsize_for_tree_index(i) \
+   ((SIZE_T_ONE << (((i) >> 1) + TREEBIN_SHIFT)) |  \
+   (((size_t)((i) & SIZE_T_ONE)) << (((i) >> 1) + TREEBIN_SHIFT - 1)))
+
+
+/* ------------------------ Operations on bin maps ----------------------- */
+
+/* bit corresponding to given index */
+#define idx2bit(i)              ((binmap_t)(1) << (i))
+
+/* Mark/Clear bits with given index */
+#define mark_smallmap(M,i)      ((M)->smallmap |=  idx2bit(i))
+#define clear_smallmap(M,i)     ((M)->smallmap &= ~idx2bit(i))
+#define smallmap_is_marked(M,i) ((M)->smallmap &   idx2bit(i))
+
+#define mark_treemap(M,i)       ((M)->treemap  |=  idx2bit(i))
+#define clear_treemap(M,i)      ((M)->treemap  &= ~idx2bit(i))
+#define treemap_is_marked(M,i)  ((M)->treemap  &   idx2bit(i))
+
+/* isolate the least set bit of a bitmap */
+#define least_bit(x)         ((x) & -(x))
+
+/* mask with all bits to left of least bit of x on */
+#define left_bits(x)         ((x<<1) | -(x<<1))
+
+/* mask with all bits to left of or equal to least bit of x on */
+#define same_or_left_bits(x) ((x) | -(x))
+
+/* index corresponding to given bit. Use x86 asm if possible */
+
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+#define compute_bit2idx(X, I)\
+{\
+  unsigned int J;\
+  J = __builtin_ctz(X); \
+  I = (bindex_t)J;\
+}
+
+#elif defined (__INTEL_COMPILER)
+#define compute_bit2idx(X, I)\
+{\
+  unsigned int J;\
+  J = _bit_scan_forward (X); \
+  I = (bindex_t)J;\
+}
+
+#elif defined(_MSC_VER) && _MSC_VER>=1300
+#define compute_bit2idx(X, I)\
+{\
+  unsigned int J;\
+  _BitScanForward((DWORD *) &J, X);\
+  I = (bindex_t)J;\
+}
+
+#elif USE_BUILTIN_FFS
+#define compute_bit2idx(X, I) I = ffs(X)-1
+
+#else
+#define compute_bit2idx(X, I)\
+{\
+  unsigned int Y = X - 1;\
+  unsigned int K = Y >> (16-4) & 16;\
+  unsigned int N = K;        Y >>= K;\
+  N += K = Y >> (8-3) &  8;  Y >>= K;\
+  N += K = Y >> (4-2) &  4;  Y >>= K;\
+  N += K = Y >> (2-1) &  2;  Y >>= K;\
+  N += K = Y >> (1-0) &  1;  Y >>= K;\
+  I = (bindex_t)(N + Y);\
+}
+#endif /* GNUC */
+
+
+/* ----------------------- Runtime Check Support ------------------------- */
+
+/*
+  For security, the main invariant is that malloc/free/etc never
+  writes to a static address other than malloc_state, unless static
+  malloc_state itself has been corrupted, which cannot occur via
+  malloc (because of these checks). In essence this means that we
+  believe all pointers, sizes, maps etc held in malloc_state, but
+  check all of those linked or offsetted from other embedded data
+  structures.  These checks are interspersed with main code in a way
+  that tends to minimize their run-time cost.
+
+  When FOOTERS is defined, in addition to range checking, we also
+  verify footer fields of inuse chunks, which can be used guarantee
+  that the mstate controlling malloc/free is intact.  This is a
+  streamlined version of the approach described by William Robertson
+  et al in "Run-time Detection of Heap-based Overflows" LISA'03
+  http://www.usenix.org/events/lisa03/tech/robertson.html The footer
+  of an inuse chunk holds the xor of its mstate and a random seed,
+  that is checked upon calls to free() and realloc().  This is
+  (probabalistically) unguessable from outside the program, but can be
+  computed by any code successfully malloc'ing any chunk, so does not
+  itself provide protection against code that has already broken
+  security through some other means.  Unlike Robertson et al, we
+  always dynamically check addresses of all offset chunks (previous,
+  next, etc). This turns out to be cheaper than relying on hashes.
+*/
+
+#if !INSECURE
+/* Check if address a is at least as high as any from MORECORE or MMAP */
+#define ok_address(M, a) ((char*)(a) >= (M)->least_addr)
+/* Check if address of next chunk n is higher than base chunk p */
+#define ok_next(p, n)    ((char*)(p) < (char*)(n))
+/* Check if p has inuse status */
+#define ok_inuse(p)     is_inuse(p)
+/* Check if p has its pinuse bit on */
+#define ok_pinuse(p)     pinuse(p)
+
+#else /* !INSECURE */
+#define ok_address(M, a) (1)
+#define ok_next(b, n)    (1)
+#define ok_inuse(p)      (1)
+#define ok_pinuse(p)     (1)
+#endif /* !INSECURE */
+
+#if (FOOTERS && !INSECURE)
+/* Check if (alleged) mstate m has expected magic field */
+#define ok_magic(M)      ((M)->magic == mparams.magic)
+#else  /* (FOOTERS && !INSECURE) */
+#define ok_magic(M)      (1)
+#endif /* (FOOTERS && !INSECURE) */
+
+/* In gcc, use __builtin_expect to minimize impact of checks */
+#if !INSECURE
+#if defined(__GNUC__) && __GNUC__ >= 3
+#define RTCHECK(e)  __builtin_expect(e, 1)
+#else /* GNUC */
+#define RTCHECK(e)  (e)
+#endif /* GNUC */
+#else /* !INSECURE */
+#define RTCHECK(e)  (1)
+#endif /* !INSECURE */
+
+/* macros to set up inuse chunks with or without footers */
+
+#if !FOOTERS
+
+#define mark_inuse_foot(M,p,s)
+
+/* Macros for setting head/foot of non-mmapped chunks */
+
+/* Set cinuse bit and pinuse bit of next chunk */
+#define set_inuse(M,p,s)\
+  ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\
+  ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT)
+
+/* Set cinuse and pinuse of this chunk and pinuse of next chunk */
+#define set_inuse_and_pinuse(M,p,s)\
+  ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+  ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT)
+
+/* Set size, cinuse and pinuse bit of this chunk */
+#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\
+  ((p)->head = (s|PINUSE_BIT|CINUSE_BIT))
+
+#else /* FOOTERS */
+
+/* Set foot of inuse chunk to be xor of mstate and seed */
+#define mark_inuse_foot(M,p,s)\
+  (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic))
+
+#define get_mstate_for(p)\
+  ((mstate)(((mchunkptr)((char*)(p) +\
+    (chunksize(p))))->prev_foot ^ mparams.magic))
+
+#define set_inuse(M,p,s)\
+  ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\
+  (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \
+  mark_inuse_foot(M,p,s))
+
+#define set_inuse_and_pinuse(M,p,s)\
+  ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+  (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\
+ mark_inuse_foot(M,p,s))
+
+#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\
+  ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+  mark_inuse_foot(M, p, s))
+
+#endif /* !FOOTERS */
+
+/* ---------------------------- setting mparams -------------------------- */
+
+#if LOCK_AT_FORK
+static void pre_fork(void)         { ACQUIRE_LOCK(&(gm)->mutex); }
+static void post_fork_parent(void) { RELEASE_LOCK(&(gm)->mutex); }
+static void post_fork_child(void)  { INITIAL_LOCK(&(gm)->mutex); }
+#endif /* LOCK_AT_FORK */
+
+/* Initialize mparams */
+static int init_mparams(void) {
+#ifdef NEED_GLOBAL_LOCK_INIT
+  if (malloc_global_mutex_status <= 0)
+    init_malloc_global_mutex();
+#endif
+
+  ACQUIRE_MALLOC_GLOBAL_LOCK();
+  if (mparams.magic == 0) {
+    size_t magic;
+    size_t psize;
+    size_t gsize;
+
+#ifndef WIN32
+    psize = malloc_getpagesize;
+    gsize = ((DEFAULT_GRANULARITY != 0)? DEFAULT_GRANULARITY : psize);
+#else /* WIN32 */
+    {
+      SYSTEM_INFO system_info;
+      GetSystemInfo(&system_info);
+      psize = system_info.dwPageSize;
+      gsize = ((DEFAULT_GRANULARITY != 0)?
+               DEFAULT_GRANULARITY : system_info.dwAllocationGranularity);
+    }
+#endif /* WIN32 */
+
+    /* Sanity-check configuration:
+       size_t must be unsigned and as wide as pointer type.
+       ints must be at least 4 bytes.
+       alignment must be at least 8.
+       Alignment, min chunk size, and page size must all be powers of 2.
+    */
+    if ((sizeof(size_t) != sizeof(char*)) ||
+        (MAX_SIZE_T < MIN_CHUNK_SIZE)  ||
+        (sizeof(int) < 4)  ||
+        (MALLOC_ALIGNMENT < (size_t)8U) ||
+        ((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-SIZE_T_ONE)) != 0) ||
+        ((MCHUNK_SIZE      & (MCHUNK_SIZE-SIZE_T_ONE))      != 0) ||
+        ((gsize            & (gsize-SIZE_T_ONE))            != 0) ||
+        ((psize            & (psize-SIZE_T_ONE))            != 0))
+      ABORT;
+    mparams.granularity = gsize;
+    mparams.page_size = psize;
+    mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD;
+    mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD;
+#if MORECORE_CONTIGUOUS
+    mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT;
+#else  /* MORECORE_CONTIGUOUS */
+    mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT;
+#endif /* MORECORE_CONTIGUOUS */
+
+#if !ONLY_MSPACES
+    /* Set up lock for main malloc area */
+    gm->mflags = mparams.default_mflags;
+    (void)INITIAL_LOCK(&gm->mutex);
+#endif
+#if LOCK_AT_FORK
+    pthread_atfork(&pre_fork, &post_fork_parent, &post_fork_child);
+#endif
+
+    {
+#if USE_DEV_RANDOM
+      int fd;
+      unsigned char buf[sizeof(size_t)];
+      /* Try to use /dev/urandom, else fall back on using time */
+      if ((fd = open("/dev/urandom", O_RDONLY)) >= 0 &&
+          read(fd, buf, sizeof(buf)) == sizeof(buf)) {
+        magic = *((size_t *) buf);
+        close(fd);
+      }
+      else
+#endif /* USE_DEV_RANDOM */
+#ifdef WIN32
+      magic = (size_t)(GetTickCount() ^ (size_t)0x55555555U);
+#elif defined(LACKS_TIME_H)
+      magic = (size_t)&magic ^ (size_t)0x55555555U;
+#else
+      magic = (size_t)(time(0) ^ (size_t)0x55555555U);
+#endif
+      magic |= (size_t)8U;    /* ensure nonzero */
+      magic &= ~(size_t)7U;   /* improve chances of fault for bad values */
+      /* Until memory modes commonly available, use volatile-write */
+      (*(volatile size_t *)(&(mparams.magic))) = magic;
+    }
+  }
+
+  RELEASE_MALLOC_GLOBAL_LOCK();
+  return 1;
+}
+
+/* support for mallopt */
+static int change_mparam(int param_number, int value) {
+  size_t val;
+  ensure_initialization();
+  val = (value == -1)? MAX_SIZE_T : (size_t)value;
+  switch(param_number) {
+  case M_TRIM_THRESHOLD:
+    mparams.trim_threshold = val;
+    return 1;
+  case M_GRANULARITY:
+    if (val >= mparams.page_size && ((val & (val-1)) == 0)) {
+      mparams.granularity = val;
+      return 1;
+    }
+    else
+      return 0;
+  case M_MMAP_THRESHOLD:
+    mparams.mmap_threshold = val;
+    return 1;
+  default:
+    return 0;
+  }
+}
+
+#if DEBUG
+/* ------------------------- Debugging Support --------------------------- */
+
+/* Check properties of any chunk, whether free, inuse, mmapped etc  */
+static void do_check_any_chunk(mstate m, mchunkptr p) {
+  assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+  assert(ok_address(m, p));
+}
+
+/* Check properties of top chunk */
+static void do_check_top_chunk(mstate m, mchunkptr p) {
+  msegmentptr sp = segment_holding(m, (char*)p);
+  size_t  sz = p->head & ~INUSE_BITS; /* third-lowest bit can be set! */
+  assert(sp != 0);
+  assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+  assert(ok_address(m, p));
+  assert(sz == m->topsize);
+  assert(sz > 0);
+  assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE);
+  assert(pinuse(p));
+  assert(!pinuse(chunk_plus_offset(p, sz)));
+}
+
+/* Check properties of (inuse) mmapped chunks */
+static void do_check_mmapped_chunk(mstate m, mchunkptr p) {
+  size_t  sz = chunksize(p);
+  size_t len = (sz + (p->prev_foot) + MMAP_FOOT_PAD);
+  assert(is_mmapped(p));
+  assert(use_mmap(m));
+  assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+  assert(ok_address(m, p));
+  assert(!is_small(sz));
+  assert((len & (mparams.page_size-SIZE_T_ONE)) == 0);
+  assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD);
+  assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0);
+}
+
+/* Check properties of inuse chunks */
+static void do_check_inuse_chunk(mstate m, mchunkptr p) {
+  do_check_any_chunk(m, p);
+  assert(is_inuse(p));
+  assert(next_pinuse(p));
+  /* If not pinuse and not mmapped, previous chunk has OK offset */
+  assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p);
+  if (is_mmapped(p))
+    do_check_mmapped_chunk(m, p);
+}
+
+/* Check properties of free chunks */
+static void do_check_free_chunk(mstate m, mchunkptr p) {
+  size_t sz = chunksize(p);
+  mchunkptr next = chunk_plus_offset(p, sz);
+  do_check_any_chunk(m, p);
+  assert(!is_inuse(p));
+  assert(!next_pinuse(p));
+  assert (!is_mmapped(p));
+  if (p != m->dv && p != m->top) {
+    if (sz >= MIN_CHUNK_SIZE) {
+      assert((sz & CHUNK_ALIGN_MASK) == 0);
+      assert(is_aligned(chunk2mem(p)));
+      assert(next->prev_foot == sz);
+      assert(pinuse(p));
+      assert (next == m->top || is_inuse(next));
+      assert(p->fd->bk == p);
+      assert(p->bk->fd == p);
+    }
+    else  /* markers are always of size SIZE_T_SIZE */
+      assert(sz == SIZE_T_SIZE);
+  }
+}
+
+/* Check properties of malloced chunks at the point they are malloced */
+static void do_check_malloced_chunk(mstate m, void* mem, size_t s) {
+  if (mem != 0) {
+    mchunkptr p = mem2chunk(mem);
+    size_t sz = p->head & ~INUSE_BITS;
+    do_check_inuse_chunk(m, p);
+    assert((sz & CHUNK_ALIGN_MASK) == 0);
+    assert(sz >= MIN_CHUNK_SIZE);
+    assert(sz >= s);
+    /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */
+    assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE));
+  }
+}
+
+/* Check a tree and its subtrees.  */
+static void do_check_tree(mstate m, tchunkptr t) {
+  tchunkptr head = 0;
+  tchunkptr u = t;
+  bindex_t tindex = t->index;
+  size_t tsize = chunksize(t);
+  bindex_t idx;
+  compute_tree_index(tsize, idx);
+  assert(tindex == idx);
+  assert(tsize >= MIN_LARGE_SIZE);
+  assert(tsize >= minsize_for_tree_index(idx));
+  assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1))));
+
+  do { /* traverse through chain of same-sized nodes */
+    do_check_any_chunk(m, ((mchunkptr)u));
+    assert(u->index == tindex);
+    assert(chunksize(u) == tsize);
+    assert(!is_inuse(u));
+    assert(!next_pinuse(u));
+    assert(u->fd->bk == u);
+    assert(u->bk->fd == u);
+    if (u->parent == 0) {
+      assert(u->child[0] == 0);
+      assert(u->child[1] == 0);
+    }
+    else {
+      assert(head == 0); /* only one node on chain has parent */
+      head = u;
+      assert(u->parent != u);
+      assert (u->parent->child[0] == u ||
+              u->parent->child[1] == u ||
+              *((tbinptr*)(u->parent)) == u);
+      if (u->child[0] != 0) {
+        assert(u->child[0]->parent == u);
+        assert(u->child[0] != u);
+        do_check_tree(m, u->child[0]);
+      }
+      if (u->child[1] != 0) {
+        assert(u->child[1]->parent == u);
+        assert(u->child[1] != u);
+        do_check_tree(m, u->child[1]);
+      }
+      if (u->child[0] != 0 && u->child[1] != 0) {
+        assert(chunksize(u->child[0]) < chunksize(u->child[1]));
+      }
+    }
+    u = u->fd;
+  } while (u != t);
+  assert(head != 0);
+}
+
+/*  Check all the chunks in a treebin.  */
+static void do_check_treebin(mstate m, bindex_t i) {
+  tbinptr* tb = treebin_at(m, i);
+  tchunkptr t = *tb;
+  int empty = (m->treemap & (1U << i)) == 0;
+  if (t == 0)
+    assert(empty);
+  if (!empty)
+    do_check_tree(m, t);
+}
+
+/*  Check all the chunks in a smallbin.  */
+static void do_check_smallbin(mstate m, bindex_t i) {
+  sbinptr b = smallbin_at(m, i);
+  mchunkptr p = b->bk;
+  unsigned int empty = (m->smallmap & (1U << i)) == 0;
+  if (p == b)
+    assert(empty);
+  if (!empty) {
+    for (; p != b; p = p->bk) {
+      size_t size = chunksize(p);
+      mchunkptr q;
+      /* each chunk claims to be free */
+      do_check_free_chunk(m, p);
+      /* chunk belongs in bin */
+      assert(small_index(size) == i);
+      assert(p->bk == b || chunksize(p->bk) == chunksize(p));
+      /* chunk is followed by an inuse chunk */
+      q = next_chunk(p);
+      if (q->head != FENCEPOST_HEAD)
+        do_check_inuse_chunk(m, q);
+    }
+  }
+}
+
+/* Find x in a bin. Used in other check functions. */
+static int bin_find(mstate m, mchunkptr x) {
+  size_t size = chunksize(x);
+  if (is_small(size)) {
+    bindex_t sidx = small_index(size);
+    sbinptr b = smallbin_at(m, sidx);
+    if (smallmap_is_marked(m, sidx)) {
+      mchunkptr p = b;
+      do {
+        if (p == x)
+          return 1;
+      } while ((p = p->fd) != b);
+    }
+  }
+  else {
+    bindex_t tidx;
+    compute_tree_index(size, tidx);
+    if (treemap_is_marked(m, tidx)) {
+      tchunkptr t = *treebin_at(m, tidx);
+      size_t sizebits = size << leftshift_for_tree_index(tidx);
+      while (t != 0 && chunksize(t) != size) {
+        t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1];
+        sizebits <<= 1;
+      }
+      if (t != 0) {
+        tchunkptr u = t;
+        do {
+          if (u == (tchunkptr)x)
+            return 1;
+        } while ((u = u->fd) != t);
+      }
+    }
+  }
+  return 0;
+}
+
+/* Traverse each chunk and check it; return total */
+static size_t traverse_and_check(mstate m) {
+  size_t sum = 0;
+  if (is_initialized(m)) {
+    msegmentptr s = &m->seg;
+    sum += m->topsize + TOP_FOOT_SIZE;
+    while (s != 0) {
+      mchunkptr q = align_as_chunk(s->base);
+      mchunkptr lastq = 0;
+      assert(pinuse(q));
+      while (segment_holds(s, q) &&
+             q != m->top && q->head != FENCEPOST_HEAD) {
+        sum += chunksize(q);
+        if (is_inuse(q)) {
+          assert(!bin_find(m, q));
+          do_check_inuse_chunk(m, q);
+        }
+        else {
+          assert(q == m->dv || bin_find(m, q));
+          assert(lastq == 0 || is_inuse(lastq)); /* Not 2 consecutive free */
+          do_check_free_chunk(m, q);
+        }
+        lastq = q;
+        q = next_chunk(q);
+      }
+      s = s->next;
+    }
+  }
+  return sum;
+}
+
+
+/* Check all properties of malloc_state. */
+static void do_check_malloc_state(mstate m) {
+  bindex_t i;
+  size_t total;
+  /* check bins */
+  for (i = 0; i < NSMALLBINS; ++i)
+    do_check_smallbin(m, i);
+  for (i = 0; i < NTREEBINS; ++i)
+    do_check_treebin(m, i);
+
+  if (m->dvsize != 0) { /* check dv chunk */
+    do_check_any_chunk(m, m->dv);
+    assert(m->dvsize == chunksize(m->dv));
+    assert(m->dvsize >= MIN_CHUNK_SIZE);
+    assert(bin_find(m, m->dv) == 0);
+  }
+
+  if (m->top != 0) {   /* check top chunk */
+    do_check_top_chunk(m, m->top);
+    /*assert(m->topsize == chunksize(m->top)); redundant */
+    assert(m->topsize > 0);
+    assert(bin_find(m, m->top) == 0);
+  }
+
+  total = traverse_and_check(m);
+  assert(total <= m->footprint);
+  assert(m->footprint <= m->max_footprint);
+}
+#endif /* DEBUG */
+
+/* ----------------------------- statistics ------------------------------ */
+
+#if !NO_MALLINFO
+static struct mallinfo internal_mallinfo(mstate m) {
+  struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
+  ensure_initialization();
+  if (!PREACTION(m)) {
+    check_malloc_state(m);
+    if (is_initialized(m)) {
+      size_t nfree = SIZE_T_ONE; /* top always free */
+      size_t mfree = m->topsize + TOP_FOOT_SIZE;
+      size_t sum = mfree;
+      msegmentptr s = &m->seg;
+      while (s != 0) {
+        mchunkptr q = align_as_chunk(s->base);
+        while (segment_holds(s, q) &&
+               q != m->top && q->head != FENCEPOST_HEAD) {
+          size_t sz = chunksize(q);
+          sum += sz;
+          if (!is_inuse(q)) {
+            mfree += sz;
+            ++nfree;
+          }
+          q = next_chunk(q);
+        }
+        s = s->next;
+      }
+
+      nm.arena    = sum;
+      nm.ordblks  = nfree;
+      nm.hblkhd   = m->footprint - sum;
+      nm.usmblks  = m->max_footprint;
+      nm.uordblks = m->footprint - mfree;
+      nm.fordblks = mfree;
+      nm.keepcost = m->topsize;
+    }
+
+    POSTACTION(m);
+  }
+  return nm;
+}
+#endif /* !NO_MALLINFO */
+
+#if !NO_MALLOC_STATS
+static void internal_malloc_stats(mstate m) {
+  ensure_initialization();
+  if (!PREACTION(m)) {
+    size_t maxfp = 0;
+    size_t fp = 0;
+    size_t used = 0;
+    check_malloc_state(m);
+    if (is_initialized(m)) {
+      msegmentptr s = &m->seg;
+      maxfp = m->max_footprint;
+      fp = m->footprint;
+      used = fp - (m->topsize + TOP_FOOT_SIZE);
+
+      while (s != 0) {
+        mchunkptr q = align_as_chunk(s->base);
+        while (segment_holds(s, q) &&
+               q != m->top && q->head != FENCEPOST_HEAD) {
+          if (!is_inuse(q))
+            used -= chunksize(q);
+          q = next_chunk(q);
+        }
+        s = s->next;
+      }
+    }
+    POSTACTION(m); /* drop lock */
+    fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp));
+    fprintf(stderr, "system bytes     = %10lu\n", (unsigned long)(fp));
+    fprintf(stderr, "in use bytes     = %10lu\n", (unsigned long)(used));
+  }
+}
+#endif /* NO_MALLOC_STATS */
+
+/* ----------------------- Operations on smallbins ----------------------- */
+
+/*
+  Various forms of linking and unlinking are defined as macros.  Even
+  the ones for trees, which are very long but have very short typical
+  paths.  This is ugly but reduces reliance on inlining support of
+  compilers.
+*/
+
+/* Link a free chunk into a smallbin  */
+#define insert_small_chunk(M, P, S) {\
+  bindex_t I  = small_index(S);\
+  mchunkptr B = smallbin_at(M, I);\
+  mchunkptr F = B;\
+  assert(S >= MIN_CHUNK_SIZE);\
+  if (!smallmap_is_marked(M, I))\
+    mark_smallmap(M, I);\
+  else if (RTCHECK(ok_address(M, B->fd)))\
+    F = B->fd;\
+  else {\
+    CORRUPTION_ERROR_ACTION(M);\
+  }\
+  B->fd = P;\
+  F->bk = P;\
+  P->fd = F;\
+  P->bk = B;\
+}
+
+/* Unlink a chunk from a smallbin  */
+#define unlink_small_chunk(M, P, S) {\
+  mchunkptr F = P->fd;\
+  mchunkptr B = P->bk;\
+  bindex_t I = small_index(S);\
+  assert(P != B);\
+  assert(P != F);\
+  assert(chunksize(P) == small_index2size(I));\
+  if (RTCHECK(F == smallbin_at(M,I) || (ok_address(M, F) && F->bk == P))) { \
+    if (B == F) {\
+      clear_smallmap(M, I);\
+    }\
+    else if (RTCHECK(B == smallbin_at(M,I) ||\
+                     (ok_address(M, B) && B->fd == P))) {\
+      F->bk = B;\
+      B->fd = F;\
+    }\
+    else {\
+      CORRUPTION_ERROR_ACTION(M);\
+    }\
+  }\
+  else {\
+    CORRUPTION_ERROR_ACTION(M);\
+  }\
+}
+
+/* Unlink the first chunk from a smallbin */
+#define unlink_first_small_chunk(M, B, P, I) {\
+  mchunkptr F = P->fd;\
+  assert(P != B);\
+  assert(P != F);\
+  assert(chunksize(P) == small_index2size(I));\
+  if (B == F) {\
+    clear_smallmap(M, I);\
+  }\
+  else if (RTCHECK(ok_address(M, F) && F->bk == P)) {\
+    F->bk = B;\
+    B->fd = F;\
+  }\
+  else {\
+    CORRUPTION_ERROR_ACTION(M);\
+  }\
+}
+
+/* Replace dv node, binning the old one */
+/* Used only when dvsize known to be small */
+#define replace_dv(M, P, S) {\
+  size_t DVS = M->dvsize;\
+  assert(is_small(DVS));\
+  if (DVS != 0) {\
+    mchunkptr DV = M->dv;\
+    insert_small_chunk(M, DV, DVS);\
+  }\
+  M->dvsize = S;\
+  M->dv = P;\
+}
+
+/* ------------------------- Operations on trees ------------------------- */
+
+/* Insert chunk into tree */
+#define insert_large_chunk(M, X, S) {\
+  tbinptr* H;\
+  bindex_t I;\
+  compute_tree_index(S, I);\
+  H = treebin_at(M, I);\
+  X->index = I;\
+  X->child[0] = X->child[1] = 0;\
+  if (!treemap_is_marked(M, I)) {\
+    mark_treemap(M, I);\
+    *H = X;\
+    X->parent = (tchunkptr)H;\
+    X->fd = X->bk = X;\
+  }\
+  else {\
+    tchunkptr T = *H;\
+    size_t K = S << leftshift_for_tree_index(I);\
+    for (;;) {\
+      if (chunksize(T) != S) {\
+        tchunkptr* C = &(T->child[(K >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]);\
+        K <<= 1;\
+        if (*C != 0)\
+          T = *C;\
+        else if (RTCHECK(ok_address(M, C))) {\
+          *C = X;\
+          X->parent = T;\
+          X->fd = X->bk = X;\
+          break;\
+        }\
+        else {\
+          CORRUPTION_ERROR_ACTION(M);\
+          break;\
+        }\
+      }\
+      else {\
+        tchunkptr F = T->fd;\
+        if (RTCHECK(ok_address(M, T) && ok_address(M, F))) {\
+          T->fd = F->bk = X;\
+          X->fd = F;\
+          X->bk = T;\
+          X->parent = 0;\
+          break;\
+        }\
+        else {\
+          CORRUPTION_ERROR_ACTION(M);\
+          break;\
+        }\
+      }\
+    }\
+  }\
+}
+
+/*
+  Unlink steps:
+
+  1. If x is a chained node, unlink it from its same-sized fd/bk links
+     and choose its bk node as its replacement.
+  2. If x was the last node of its size, but not a leaf node, it must
+     be replaced with a leaf node (not merely one with an open left or
+     right), to make sure that lefts and rights of descendents
+     correspond properly to bit masks.  We use the rightmost descendent
+     of x.  We could use any other leaf, but this is easy to locate and
+     tends to counteract removal of leftmosts elsewhere, and so keeps
+     paths shorter than minimally guaranteed.  This doesn't loop much
+     because on average a node in a tree is near the bottom.
+  3. If x is the base of a chain (i.e., has parent links) relink
+     x's parent and children to x's replacement (or null if none).
+*/
+
+#define unlink_large_chunk(M, X) {\
+  tchunkptr XP = X->parent;\
+  tchunkptr R;\
+  if (X->bk != X) {\
+    tchunkptr F = X->fd;\
+    R = X->bk;\
+    if (RTCHECK(ok_address(M, F) && F->bk == X && R->fd == X)) {\
+      F->bk = R;\
+      R->fd = F;\
+    }\
+    else {\
+      CORRUPTION_ERROR_ACTION(M);\
+    }\
+  }\
+  else {\
+    tchunkptr* RP;\
+    if (((R = *(RP = &(X->child[1]))) != 0) ||\
+        ((R = *(RP = &(X->child[0]))) != 0)) {\
+      tchunkptr* CP;\
+      while ((*(CP = &(R->child[1])) != 0) ||\
+             (*(CP = &(R->child[0])) != 0)) {\
+        R = *(RP = CP);\
+      }\
+      if (RTCHECK(ok_address(M, RP)))\
+        *RP = 0;\
+      else {\
+        CORRUPTION_ERROR_ACTION(M);\
+      }\
+    }\
+  }\
+  if (XP != 0) {\
+    tbinptr* H = treebin_at(M, X->index);\
+    if (X == *H) {\
+      if ((*H = R) == 0) \
+        clear_treemap(M, X->index);\
+    }\
+    else if (RTCHECK(ok_address(M, XP))) {\
+      if (XP->child[0] == X) \
+        XP->child[0] = R;\
+      else \
+        XP->child[1] = R;\
+    }\
+    else\
+      CORRUPTION_ERROR_ACTION(M);\
+    if (R != 0) {\
+      if (RTCHECK(ok_address(M, R))) {\
+        tchunkptr C0, C1;\
+        R->parent = XP;\
+        if ((C0 = X->child[0]) != 0) {\
+          if (RTCHECK(ok_address(M, C0))) {\
+            R->child[0] = C0;\
+            C0->parent = R;\
+          }\
+          else\
+            CORRUPTION_ERROR_ACTION(M);\
+        }\
+        if ((C1 = X->child[1]) != 0) {\
+          if (RTCHECK(ok_address(M, C1))) {\
+            R->child[1] = C1;\
+            C1->parent = R;\
+          }\
+          else\
+            CORRUPTION_ERROR_ACTION(M);\
+        }\
+      }\
+      else\
+        CORRUPTION_ERROR_ACTION(M);\
+    }\
+  }\
+}
+
+/* Relays to large vs small bin operations */
+
+#define insert_chunk(M, P, S)\
+  if (is_small(S)) insert_small_chunk(M, P, S)\
+  else { tchunkptr TP = (tchunkptr)(P); insert_large_chunk(M, TP, S); }
+
+#define unlink_chunk(M, P, S)\
+  if (is_small(S)) unlink_small_chunk(M, P, S)\
+  else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); }
+
+
+/* Relays to internal calls to malloc/free from realloc, memalign etc */
+
+#if ONLY_MSPACES
+#define internal_malloc(m, b) mspace_malloc(m, b)
+#define internal_free(m, mem) mspace_free(m,mem);
+#else /* ONLY_MSPACES */
+#if MSPACES
+#define internal_malloc(m, b)\
+  ((m == gm)? dlmalloc(b) : mspace_malloc(m, b))
+#define internal_free(m, mem)\
+   if (m == gm) dlfree(mem); else mspace_free(m,mem);
+#else /* MSPACES */
+#define internal_malloc(m, b) dlmalloc(b)
+#define internal_free(m, mem) dlfree(mem)
+#endif /* MSPACES */
+#endif /* ONLY_MSPACES */
+
+/* -----------------------  Direct-mmapping chunks ----------------------- */
+
+/*
+  Directly mmapped chunks are set up with an offset to the start of
+  the mmapped region stored in the prev_foot field of the chunk. This
+  allows reconstruction of the required argument to MUNMAP when freed,
+  and also allows adjustment of the returned chunk to meet alignment
+  requirements (especially in memalign).
+*/
+
+/* Malloc using mmap */
+static void* mmap_alloc(mstate m, size_t nb) {
+  size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+  if (m->footprint_limit != 0) {
+    size_t fp = m->footprint + mmsize;
+    if (fp <= m->footprint || fp > m->footprint_limit)
+      return 0;
+  }
+  if (mmsize > nb) {     /* Check for wrap around 0 */
+    char* mm = (char*)(CALL_DIRECT_MMAP(mmsize));
+    if (mm != CMFAIL) {
+      size_t offset = align_offset(chunk2mem(mm));
+      size_t psize = mmsize - offset - MMAP_FOOT_PAD;
+      mchunkptr p = (mchunkptr)(mm + offset);
+      p->prev_foot = offset;
+      p->head = psize;
+      mark_inuse_foot(m, p, psize);
+      chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD;
+      chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0;
+
+      if (m->least_addr == 0 || mm < m->least_addr)
+        m->least_addr = mm;
+      if ((m->footprint += mmsize) > m->max_footprint)
+        m->max_footprint = m->footprint;
+      assert(is_aligned(chunk2mem(p)));
+      check_mmapped_chunk(m, p);
+      return chunk2mem(p);
+    }
+  }
+  return 0;
+}
+
+/* Realloc using mmap */
+static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb, int flags) {
+  size_t oldsize = chunksize(oldp);
+  (void)flags; /* placate people compiling -Wunused */
+  if (is_small(nb)) /* Can't shrink mmap regions below small size */
+    return 0;
+  /* Keep old chunk if big enough but not too big */
+  if (oldsize >= nb + SIZE_T_SIZE &&
+      (oldsize - nb) <= (mparams.granularity << 1))
+    return oldp;
+  else {
+    size_t offset = oldp->prev_foot;
+    size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD;
+    size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+    char* cp = (char*)CALL_MREMAP((char*)oldp - offset,
+                                  oldmmsize, newmmsize, flags);
+    if (cp != CMFAIL) {
+      mchunkptr newp = (mchunkptr)(cp + offset);
+      size_t psize = newmmsize - offset - MMAP_FOOT_PAD;
+      newp->head = psize;
+      mark_inuse_foot(m, newp, psize);
+      chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD;
+      chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0;
+
+      if (cp < m->least_addr)
+        m->least_addr = cp;
+      if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint)
+        m->max_footprint = m->footprint;
+      check_mmapped_chunk(m, newp);
+      return newp;
+    }
+  }
+  return 0;
+}
+
+
+/* -------------------------- mspace management -------------------------- */
+
+/* Initialize top chunk and its size */
+static void init_top(mstate m, mchunkptr p, size_t psize) {
+  /* Ensure alignment */
+  size_t offset = align_offset(chunk2mem(p));
+  p = (mchunkptr)((char*)p + offset);
+  psize -= offset;
+
+  m->top = p;
+  m->topsize = psize;
+  p->head = psize | PINUSE_BIT;
+  /* set size of fake trailing chunk holding overhead space only once */
+  chunk_plus_offset(p, psize)->head = TOP_FOOT_SIZE;
+  m->trim_check = mparams.trim_threshold; /* reset on each update */
+}
+
+/* Initialize bins for a new mstate that is otherwise zeroed out */
+static void init_bins(mstate m) {
+  /* Establish circular links for smallbins */
+  bindex_t i;
+  for (i = 0; i < NSMALLBINS; ++i) {
+    sbinptr bin = smallbin_at(m,i);
+    bin->fd = bin->bk = bin;
+  }
+}
+
+#if PROCEED_ON_ERROR
+
+/* default corruption action */
+static void reset_on_error(mstate m) {
+  int i;
+  ++malloc_corruption_error_count;
+  /* Reinitialize fields to forget about all memory */
+  m->smallmap = m->treemap = 0;
+  m->dvsize = m->topsize = 0;
+  m->seg.base = 0;
+  m->seg.size = 0;
+  m->seg.next = 0;
+  m->top = m->dv = 0;
+  for (i = 0; i < NTREEBINS; ++i)
+    *treebin_at(m, i) = 0;
+  init_bins(m);
+}
+#endif /* PROCEED_ON_ERROR */
+
+/* Allocate chunk and prepend remainder with chunk in successor base. */
+static void* prepend_alloc(mstate m, char* newbase, char* oldbase,
+                           size_t nb) {
+  mchunkptr p = align_as_chunk(newbase);
+  mchunkptr oldfirst = align_as_chunk(oldbase);
+  size_t psize = (char*)oldfirst - (char*)p;
+  mchunkptr q = chunk_plus_offset(p, nb);
+  size_t qsize = psize - nb;
+  set_size_and_pinuse_of_inuse_chunk(m, p, nb);
+
+  assert((char*)oldfirst > (char*)q);
+  assert(pinuse(oldfirst));
+  assert(qsize >= MIN_CHUNK_SIZE);
+
+  /* consolidate remainder with first chunk of old base */
+  if (oldfirst == m->top) {
+    size_t tsize = m->topsize += qsize;
+    m->top = q;
+    q->head = tsize | PINUSE_BIT;
+    check_top_chunk(m, q);
+  }
+  else if (oldfirst == m->dv) {
+    size_t dsize = m->dvsize += qsize;
+    m->dv = q;
+    set_size_and_pinuse_of_free_chunk(q, dsize);
+  }
+  else {
+    if (!is_inuse(oldfirst)) {
+      size_t nsize = chunksize(oldfirst);
+      unlink_chunk(m, oldfirst, nsize);
+      oldfirst = chunk_plus_offset(oldfirst, nsize);
+      qsize += nsize;
+    }
+    set_free_with_pinuse(q, qsize, oldfirst);
+    insert_chunk(m, q, qsize);
+    check_free_chunk(m, q);
+  }
+
+  check_malloced_chunk(m, chunk2mem(p), nb);
+  return chunk2mem(p);
+}
+
+/* Add a segment to hold a new noncontiguous region */
+static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) {
+  /* Determine locations and sizes of segment, fenceposts, old top */
+  char* old_top = (char*)m->top;
+  msegmentptr oldsp = segment_holding(m, old_top);
+  char* old_end = oldsp->base + oldsp->size;
+  size_t ssize = pad_request(sizeof(struct malloc_segment));
+  char* rawsp = old_end - (ssize + FOUR_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+  size_t offset = align_offset(chunk2mem(rawsp));
+  char* asp = rawsp + offset;
+  char* csp = (asp < (old_top + MIN_CHUNK_SIZE))? old_top : asp;
+  mchunkptr sp = (mchunkptr)csp;
+  msegmentptr ss = (msegmentptr)(chunk2mem(sp));
+  mchunkptr tnext = chunk_plus_offset(sp, ssize);
+  mchunkptr p = tnext;
+  int nfences = 0;
+
+  /* reset top to new space */
+  init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE);
+
+  /* Set up segment record */
+  assert(is_aligned(ss));
+  set_size_and_pinuse_of_inuse_chunk(m, sp, ssize);
+  *ss = m->seg; /* Push current record */
+  m->seg.base = tbase;
+  m->seg.size = tsize;
+  m->seg.sflags = mmapped;
+  m->seg.next = ss;
+
+  /* Insert trailing fenceposts */
+  for (;;) {
+    mchunkptr nextp = chunk_plus_offset(p, SIZE_T_SIZE);
+    p->head = FENCEPOST_HEAD;
+    ++nfences;
+    if ((char*)(&(nextp->head)) < old_end)
+      p = nextp;
+    else
+      break;
+  }
+  (void)nfences;
+  assert(nfences >= 2);
+
+  /* Insert the rest of old top into a bin as an ordinary free chunk */
+  if (csp != old_top) {
+    mchunkptr q = (mchunkptr)old_top;
+    size_t psize = csp - old_top;
+    mchunkptr tn = chunk_plus_offset(q, psize);
+    set_free_with_pinuse(q, psize, tn);
+    insert_chunk(m, q, psize);
+  }
+
+  check_top_chunk(m, m->top);
+}
+
+/* -------------------------- System allocation -------------------------- */
+
+/* Get memory from system using MORECORE or MMAP */
+static void* sys_alloc(mstate m, size_t nb) {
+  char* tbase = CMFAIL;
+  size_t tsize = 0;
+  flag_t mmap_flag = 0;
+  size_t asize; /* allocation size */
+
+  ensure_initialization();
+
+  /* Directly map large chunks, but only if already initialized */
+  if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) {
+    void* mem = mmap_alloc(m, nb);
+    if (mem != 0)
+      return mem;
+  }
+
+  asize = granularity_align(nb + SYS_ALLOC_PADDING);
+  if (asize <= nb)
+    return 0; /* wraparound */
+  if (m->footprint_limit != 0) {
+    size_t fp = m->footprint + asize;
+    if (fp <= m->footprint || fp > m->footprint_limit)
+      return 0;
+  }
+
+  /*
+    Try getting memory in any of three ways (in most-preferred to
+    least-preferred order):
+    1. A call to MORECORE that can normally contiguously extend memory.
+       (disabled if not MORECORE_CONTIGUOUS or not HAVE_MORECORE or
+       or main space is mmapped or a previous contiguous call failed)
+    2. A call to MMAP new space (disabled if not HAVE_MMAP).
+       Note that under the default settings, if MORECORE is unable to
+       fulfill a request, and HAVE_MMAP is true, then mmap is
+       used as a noncontiguous system allocator. This is a useful backup
+       strategy for systems with holes in address spaces -- in this case
+       sbrk cannot contiguously expand the heap, but mmap may be able to
+       find space.
+    3. A call to MORECORE that cannot usually contiguously extend memory.
+       (disabled if not HAVE_MORECORE)
+
+   In all cases, we need to request enough bytes from system to ensure
+   we can malloc nb bytes upon success, so pad with enough space for
+   top_foot, plus alignment-pad to make sure we don't lose bytes if
+   not on boundary, and round this up to a granularity unit.
+  */
+
+  if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) {
+    char* br = CMFAIL;
+    size_t ssize = asize; /* sbrk call size */
+    msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top);
+    ACQUIRE_MALLOC_GLOBAL_LOCK();
+
+    if (ss == 0) {  /* First time through or recovery */
+      char* base = (char*)CALL_MORECORE(0);
+      if (base != CMFAIL) {
+        size_t fp;
+        /* Adjust to end on a page boundary */
+        if (!is_page_aligned(base))
+          ssize += (page_align((size_t)base) - (size_t)base);
+        fp = m->footprint + ssize; /* recheck limits */
+        if (ssize > nb && ssize < HALF_MAX_SIZE_T &&
+            (m->footprint_limit == 0 ||
+             (fp > m->footprint && fp <= m->footprint_limit)) &&
+            (br = (char*)(CALL_MORECORE(ssize))) == base) {
+          tbase = base;
+          tsize = ssize;
+        }
+      }
+    }
+    else {
+      /* Subtract out existing available top space from MORECORE request. */
+      ssize = granularity_align(nb - m->topsize + SYS_ALLOC_PADDING);
+      /* Use mem here only if it did continuously extend old space */
+      if (ssize < HALF_MAX_SIZE_T &&
+          (br = (char*)(CALL_MORECORE(ssize))) == ss->base+ss->size) {
+        tbase = br;
+        tsize = ssize;
+      }
+    }
+
+    if (tbase == CMFAIL) {    /* Cope with partial failure */
+      if (br != CMFAIL) {    /* Try to use/extend the space we did get */
+        if (ssize < HALF_MAX_SIZE_T &&
+            ssize < nb + SYS_ALLOC_PADDING) {
+          size_t esize = granularity_align(nb + SYS_ALLOC_PADDING - ssize);
+          if (esize < HALF_MAX_SIZE_T) {
+            char* end = (char*)CALL_MORECORE(esize);
+            if (end != CMFAIL)
+              ssize += esize;
+            else {            /* Can't use; try to release */
+              (void) CALL_MORECORE(-ssize);
+              br = CMFAIL;
+            }
+          }
+        }
+      }
+      if (br != CMFAIL) {    /* Use the space we did get */
+        tbase = br;
+        tsize = ssize;
+      }
+      else
+        disable_contiguous(m); /* Don't try contiguous path in the future */
+    }
+
+    RELEASE_MALLOC_GLOBAL_LOCK();
+  }
+
+  if (HAVE_MMAP && tbase == CMFAIL) {  /* Try MMAP */
+    char* mp = (char*)(CALL_MMAP(asize));
+    if (mp != CMFAIL) {
+      tbase = mp;
+      tsize = asize;
+      mmap_flag = USE_MMAP_BIT;
+    }
+  }
+
+  if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */
+    if (asize < HALF_MAX_SIZE_T) {
+      char* br = CMFAIL;
+      char* end = CMFAIL;
+      ACQUIRE_MALLOC_GLOBAL_LOCK();
+      br = (char*)(CALL_MORECORE(asize));
+      end = (char*)(CALL_MORECORE(0));
+      RELEASE_MALLOC_GLOBAL_LOCK();
+      if (br != CMFAIL && end != CMFAIL && br < end) {
+        size_t ssize = end - br;
+        if (ssize > nb + TOP_FOOT_SIZE) {
+          tbase = br;
+          tsize = ssize;
+        }
+      }
+    }
+  }
+
+  if (tbase != CMFAIL) {
+
+    if ((m->footprint += tsize) > m->max_footprint)
+      m->max_footprint = m->footprint;
+
+    if (!is_initialized(m)) { /* first-time initialization */
+      if (m->least_addr == 0 || tbase < m->least_addr)
+        m->least_addr = tbase;
+      m->seg.base = tbase;
+      m->seg.size = tsize;
+      m->seg.sflags = mmap_flag;
+      m->magic = mparams.magic;
+      m->release_checks = MAX_RELEASE_CHECK_RATE;
+      init_bins(m);
+#if !ONLY_MSPACES
+      if (is_global(m))
+        init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE);
+      else
+#endif
+      {
+        /* Offset top by embedded malloc_state */
+        mchunkptr mn = next_chunk(mem2chunk(m));
+        init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE);
+      }
+    }
+
+    else {
+      /* Try to merge with an existing segment */
+      msegmentptr sp = &m->seg;
+      /* Only consider most recent segment if traversal suppressed */
+      while (sp != 0 && tbase != sp->base + sp->size)
+        sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next;
+      if (sp != 0 &&
+          !is_extern_segment(sp) &&
+          (sp->sflags & USE_MMAP_BIT) == mmap_flag &&
+          segment_holds(sp, m->top)) { /* append */
+        sp->size += tsize;
+        init_top(m, m->top, m->topsize + tsize);
+      }
+      else {
+        if (tbase < m->least_addr)
+          m->least_addr = tbase;
+        sp = &m->seg;
+        while (sp != 0 && sp->base != tbase + tsize)
+          sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next;
+        if (sp != 0 &&
+            !is_extern_segment(sp) &&
+            (sp->sflags & USE_MMAP_BIT) == mmap_flag) {
+          char* oldbase = sp->base;
+          sp->base = tbase;
+          sp->size += tsize;
+          return prepend_alloc(m, tbase, oldbase, nb);
+        }
+        else
+          add_segment(m, tbase, tsize, mmap_flag);
+      }
+    }
+
+    if (nb < m->topsize) { /* Allocate from new or extended top space */
+      size_t rsize = m->topsize -= nb;
+      mchunkptr p = m->top;
+      mchunkptr r = m->top = chunk_plus_offset(p, nb);
+      r->head = rsize | PINUSE_BIT;
+      set_size_and_pinuse_of_inuse_chunk(m, p, nb);
+      check_top_chunk(m, m->top);
+      check_malloced_chunk(m, chunk2mem(p), nb);
+      return chunk2mem(p);
+    }
+  }
+
+  MALLOC_FAILURE_ACTION;
+  return 0;
+}
+
+/* -----------------------  system deallocation -------------------------- */
+
+/* Unmap and unlink any mmapped segments that don't contain used chunks */
+static size_t release_unused_segments(mstate m) {
+  size_t released = 0;
+  int nsegs = 0;
+  msegmentptr pred = &m->seg;
+  msegmentptr sp = pred->next;
+  while (sp != 0) {
+    char* base = sp->base;
+    size_t size = sp->size;
+    msegmentptr next = sp->next;
+    ++nsegs;
+    if (is_mmapped_segment(sp) && !is_extern_segment(sp)) {
+      mchunkptr p = align_as_chunk(base);
+      size_t psize = chunksize(p);
+      /* Can unmap if first chunk holds entire segment and not pinned */
+      if (!is_inuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) {
+        tchunkptr tp = (tchunkptr)p;
+        assert(segment_holds(sp, (char*)sp));
+        if (p == m->dv) {
+          m->dv = 0;
+          m->dvsize = 0;
+        }
+        else {
+          unlink_large_chunk(m, tp);
+        }
+        if (CALL_MUNMAP(base, size) == 0) {
+          released += size;
+          m->footprint -= size;
+          /* unlink obsoleted record */
+          sp = pred;
+          sp->next = next;
+        }
+        else { /* back out if cannot unmap */
+          insert_large_chunk(m, tp, psize);
+        }
+      }
+    }
+    if (NO_SEGMENT_TRAVERSAL) /* scan only first segment */
+      break;
+    pred = sp;
+    sp = next;
+  }
+  /* Reset check counter */
+  m->release_checks = (((size_t) nsegs > (size_t) MAX_RELEASE_CHECK_RATE)?
+                       (size_t) nsegs : (size_t) MAX_RELEASE_CHECK_RATE);
+  return released;
+}
+
+static int sys_trim(mstate m, size_t pad) {
+  size_t released = 0;
+  ensure_initialization();
+  if (pad < MAX_REQUEST && is_initialized(m)) {
+    pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */
+
+    if (m->topsize > pad) {
+      /* Shrink top space in granularity-size units, keeping at least one */
+      size_t unit = mparams.granularity;
+      size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit -
+                      SIZE_T_ONE) * unit;
+      msegmentptr sp = segment_holding(m, (char*)m->top);
+
+      if (!is_extern_segment(sp)) {
+        if (is_mmapped_segment(sp)) {
+          if (HAVE_MMAP &&
+              sp->size >= extra &&
+              !has_segment_link(m, sp)) { /* can't shrink if pinned */
+            size_t newsize = sp->size - extra;
+            (void)newsize; /* placate people compiling -Wunused-variable */
+            /* Prefer mremap, fall back to munmap */
+            if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) ||
+                (CALL_MUNMAP(sp->base + newsize, extra) == 0)) {
+              released = extra;
+            }
+          }
+        }
+        else if (HAVE_MORECORE) {
+          if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */
+            extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit;
+          ACQUIRE_MALLOC_GLOBAL_LOCK();
+          {
+            /* Make sure end of memory is where we last set it. */
+            char* old_br = (char*)(CALL_MORECORE(0));
+            if (old_br == sp->base + sp->size) {
+              char* rel_br = (char*)(CALL_MORECORE(-extra));
+              char* new_br = (char*)(CALL_MORECORE(0));
+              if (rel_br != CMFAIL && new_br < old_br)
+                released = old_br - new_br;
+            }
+          }
+          RELEASE_MALLOC_GLOBAL_LOCK();
+        }
+      }
+
+      if (released != 0) {
+        sp->size -= released;
+        m->footprint -= released;
+        init_top(m, m->top, m->topsize - released);
+        check_top_chunk(m, m->top);
+      }
+    }
+
+    /* Unmap any unused mmapped segments */
+    if (HAVE_MMAP)
+      released += release_unused_segments(m);
+
+    /* On failure, disable autotrim to avoid repeated failed future calls */
+    if (released == 0 && m->topsize > m->trim_check)
+      m->trim_check = MAX_SIZE_T;
+  }
+
+  return (released != 0)? 1 : 0;
+}
+
+/* Consolidate and bin a chunk. Differs from exported versions
+   of free mainly in that the chunk need not be marked as inuse.
+*/
+static void dispose_chunk(mstate m, mchunkptr p, size_t psize) {
+  mchunkptr next = chunk_plus_offset(p, psize);
+  if (!pinuse(p)) {
+    mchunkptr prev;
+    size_t prevsize = p->prev_foot;
+    if (is_mmapped(p)) {
+      psize += prevsize + MMAP_FOOT_PAD;
+      if (CALL_MUNMAP((char*)p - prevsize, psize) == 0)
+        m->footprint -= psize;
+      return;
+    }
+    prev = chunk_minus_offset(p, prevsize);
+    psize += prevsize;
+    p = prev;
+    if (RTCHECK(ok_address(m, prev))) { /* consolidate backward */
+      if (p != m->dv) {
+        unlink_chunk(m, p, prevsize);
+      }
+      else if ((next->head & INUSE_BITS) == INUSE_BITS) {
+        m->dvsize = psize;
+        set_free_with_pinuse(p, psize, next);
+        return;
+      }
+    }
+    else {
+      CORRUPTION_ERROR_ACTION(m);
+      return;
+    }
+  }
+  if (RTCHECK(ok_address(m, next))) {
+    if (!cinuse(next)) {  /* consolidate forward */
+      if (next == m->top) {
+        size_t tsize = m->topsize += psize;
+        m->top = p;
+        p->head = tsize | PINUSE_BIT;
+        if (p == m->dv) {
+          m->dv = 0;
+          m->dvsize = 0;
+        }
+        return;
+      }
+      else if (next == m->dv) {
+        size_t dsize = m->dvsize += psize;
+        m->dv = p;
+        set_size_and_pinuse_of_free_chunk(p, dsize);
+        return;
+      }
+      else {
+        size_t nsize = chunksize(next);
+        psize += nsize;
+        unlink_chunk(m, next, nsize);
+        set_size_and_pinuse_of_free_chunk(p, psize);
+        if (p == m->dv) {
+          m->dvsize = psize;
+          return;
+        }
+      }
+    }
+    else {
+      set_free_with_pinuse(p, psize, next);
+    }
+    insert_chunk(m, p, psize);
+  }
+  else {
+    CORRUPTION_ERROR_ACTION(m);
+  }
+}
+
+/* ---------------------------- malloc --------------------------- */
+
+/* allocate a large request from the best fitting chunk in a treebin */
+static void* tmalloc_large(mstate m, size_t nb) {
+  tchunkptr v = 0;
+  size_t rsize = -nb; /* Unsigned negation */
+  tchunkptr t;
+  bindex_t idx;
+  compute_tree_index(nb, idx);
+  if ((t = *treebin_at(m, idx)) != 0) {
+    /* Traverse tree for this bin looking for node with size == nb */
+    size_t sizebits = nb << leftshift_for_tree_index(idx);
+    tchunkptr rst = 0;  /* The deepest untaken right subtree */
+    for (;;) {
+      tchunkptr rt;
+      size_t trem = chunksize(t) - nb;
+      if (trem < rsize) {
+        v = t;
+        if ((rsize = trem) == 0)
+          break;
+      }
+      rt = t->child[1];
+      t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1];
+      if (rt != 0 && rt != t)
+        rst = rt;
+      if (t == 0) {
+        t = rst; /* set t to least subtree holding sizes > nb */
+        break;
+      }
+      sizebits <<= 1;
+    }
+  }
+  if (t == 0 && v == 0) { /* set t to root of next non-empty treebin */
+    binmap_t leftbits = left_bits(idx2bit(idx)) & m->treemap;
+    if (leftbits != 0) {
+      bindex_t i;
+      binmap_t leastbit = least_bit(leftbits);
+      compute_bit2idx(leastbit, i);
+      t = *treebin_at(m, i);
+    }
+  }
+
+  while (t != 0) { /* find smallest of tree or subtree */
+    size_t trem = chunksize(t) - nb;
+    if (trem < rsize) {
+      rsize = trem;
+      v = t;
+    }
+    t = leftmost_child(t);
+  }
+
+  /*  If dv is a better fit, return 0 so malloc will use it */
+  if (v != 0 && rsize < (size_t)(m->dvsize - nb)) {
+    if (RTCHECK(ok_address(m, v))) { /* split */
+      mchunkptr r = chunk_plus_offset(v, nb);
+      assert(chunksize(v) == rsize + nb);
+      if (RTCHECK(ok_next(v, r))) {
+        unlink_large_chunk(m, v);
+        if (rsize < MIN_CHUNK_SIZE)
+          set_inuse_and_pinuse(m, v, (rsize + nb));
+        else {
+          set_size_and_pinuse_of_inuse_chunk(m, v, nb);
+          set_size_and_pinuse_of_free_chunk(r, rsize);
+          insert_chunk(m, r, rsize);
+        }
+        return chunk2mem(v);
+      }
+    }
+    CORRUPTION_ERROR_ACTION(m);
+  }
+  return 0;
+}
+
+/* allocate a small request from the best fitting chunk in a treebin */
+static void* tmalloc_small(mstate m, size_t nb) {
+  tchunkptr t, v;
+  size_t rsize;
+  bindex_t i;
+  binmap_t leastbit = least_bit(m->treemap);
+  compute_bit2idx(leastbit, i);
+  v = t = *treebin_at(m, i);
+  rsize = chunksize(t) - nb;
+
+  while ((t = leftmost_child(t)) != 0) {
+    size_t trem = chunksize(t) - nb;
+    if (trem < rsize) {
+      rsize = trem;
+      v = t;
+    }
+  }
+
+  if (RTCHECK(ok_address(m, v))) {
+    mchunkptr r = chunk_plus_offset(v, nb);
+    assert(chunksize(v) == rsize + nb);
+    if (RTCHECK(ok_next(v, r))) {
+      unlink_large_chunk(m, v);
+      if (rsize < MIN_CHUNK_SIZE)
+        set_inuse_and_pinuse(m, v, (rsize + nb));
+      else {
+        set_size_and_pinuse_of_inuse_chunk(m, v, nb);
+        set_size_and_pinuse_of_free_chunk(r, rsize);
+        replace_dv(m, r, rsize);
+      }
+      return chunk2mem(v);
+    }
+  }
+
+  CORRUPTION_ERROR_ACTION(m);
+  return 0;
+}
+
+#if !ONLY_MSPACES
+
+void* dlmalloc(size_t bytes) {
+  /*
+     Basic algorithm:
+     If a small request (< 256 bytes minus per-chunk overhead):
+       1. If one exists, use a remainderless chunk in associated smallbin.
+          (Remainderless means that there are too few excess bytes to
+          represent as a chunk.)
+       2. If it is big enough, use the dv chunk, which is normally the
+          chunk adjacent to the one used for the most recent small request.
+       3. If one exists, split the smallest available chunk in a bin,
+          saving remainder in dv.
+       4. If it is big enough, use the top chunk.
+       5. If available, get memory from system and use it
+     Otherwise, for a large request:
+       1. Find the smallest available binned chunk that fits, and use it
+          if it is better fitting than dv chunk, splitting if necessary.
+       2. If better fitting than any binned chunk, use the dv chunk.
+       3. If it is big enough, use the top chunk.
+       4. If request size >= mmap threshold, try to directly mmap this chunk.
+       5. If available, get memory from system and use it
+
+     The ugly goto's here ensure that postaction occurs along all paths.
+  */
+
+#if USE_LOCKS
+  ensure_initialization(); /* initialize in sys_alloc if not using locks */
+#endif
+
+  if (!PREACTION(gm)) {
+    void* mem;
+    size_t nb;
+    if (bytes <= MAX_SMALL_REQUEST) {
+      bindex_t idx;
+      binmap_t smallbits;
+      nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes);
+      idx = small_index(nb);
+      smallbits = gm->smallmap >> idx;
+
+      if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */
+        mchunkptr b, p;
+        idx += ~smallbits & 1;       /* Uses next bin if idx empty */
+        b = smallbin_at(gm, idx);
+        p = b->fd;
+        assert(chunksize(p) == small_index2size(idx));
+        unlink_first_small_chunk(gm, b, p, idx);
+        set_inuse_and_pinuse(gm, p, small_index2size(idx));
+        mem = chunk2mem(p);
+        check_malloced_chunk(gm, mem, nb);
+        goto postaction;
+      }
+
+      else if (nb > gm->dvsize) {
+        if (smallbits != 0) { /* Use chunk in next nonempty smallbin */
+          mchunkptr b, p, r;
+          size_t rsize;
+          bindex_t i;
+          binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx));
+          binmap_t leastbit = least_bit(leftbits);
+          compute_bit2idx(leastbit, i);
+          b = smallbin_at(gm, i);
+          p = b->fd;
+          assert(chunksize(p) == small_index2size(i));
+          unlink_first_small_chunk(gm, b, p, i);
+          rsize = small_index2size(i) - nb;
+          /* Fit here cannot be remainderless if 4byte sizes */
+          if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE)
+            set_inuse_and_pinuse(gm, p, small_index2size(i));
+          else {
+            set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+            r = chunk_plus_offset(p, nb);
+            set_size_and_pinuse_of_free_chunk(r, rsize);
+            replace_dv(gm, r, rsize);
+          }
+          mem = chunk2mem(p);
+          check_malloced_chunk(gm, mem, nb);
+          goto postaction;
+        }
+
+        else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) {
+          check_malloced_chunk(gm, mem, nb);
+          goto postaction;
+        }
+      }
+    }
+    else if (bytes >= MAX_REQUEST)
+      nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */
+    else {
+      nb = pad_request(bytes);
+      if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) {
+        check_malloced_chunk(gm, mem, nb);
+        goto postaction;
+      }
+    }
+
+    if (nb <= gm->dvsize) {
+      size_t rsize = gm->dvsize - nb;
+      mchunkptr p = gm->dv;
+      if (rsize >= MIN_CHUNK_SIZE) { /* split dv */
+        mchunkptr r = gm->dv = chunk_plus_offset(p, nb);
+        gm->dvsize = rsize;
+        set_size_and_pinuse_of_free_chunk(r, rsize);
+        set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+      }
+      else { /* exhaust dv */
+        size_t dvs = gm->dvsize;
+        gm->dvsize = 0;
+        gm->dv = 0;
+        set_inuse_and_pinuse(gm, p, dvs);
+      }
+      mem = chunk2mem(p);
+      check_malloced_chunk(gm, mem, nb);
+      goto postaction;
+    }
+
+    else if (nb < gm->topsize) { /* Split top */
+      size_t rsize = gm->topsize -= nb;
+      mchunkptr p = gm->top;
+      mchunkptr r = gm->top = chunk_plus_offset(p, nb);
+      r->head = rsize | PINUSE_BIT;
+      set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+      mem = chunk2mem(p);
+      check_top_chunk(gm, gm->top);
+      check_malloced_chunk(gm, mem, nb);
+      goto postaction;
+    }
+
+    mem = sys_alloc(gm, nb);
+
+  postaction:
+    POSTACTION(gm);
+    return mem;
+  }
+
+  return 0;
+}
+
+/* ---------------------------- free --------------------------- */
+
+void dlfree(void* mem) {
+  /*
+     Consolidate freed chunks with preceeding or succeeding bordering
+     free chunks, if they exist, and then place in a bin.  Intermixed
+     with special cases for top, dv, mmapped chunks, and usage errors.
+  */
+
+  if (mem != 0) {
+    mchunkptr p  = mem2chunk(mem);
+#if FOOTERS
+    mstate fm = get_mstate_for(p);
+    if (!ok_magic(fm)) {
+      USAGE_ERROR_ACTION(fm, p);
+      return;
+    }
+#else /* FOOTERS */
+#define fm gm
+#endif /* FOOTERS */
+    if (!PREACTION(fm)) {
+      check_inuse_chunk(fm, p);
+      if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) {
+        size_t psize = chunksize(p);
+        mchunkptr next = chunk_plus_offset(p, psize);
+        if (!pinuse(p)) {
+          size_t prevsize = p->prev_foot;
+          if (is_mmapped(p)) {
+            psize += prevsize + MMAP_FOOT_PAD;
+            if (CALL_MUNMAP((char*)p - prevsize, psize) == 0)
+              fm->footprint -= psize;
+            goto postaction;
+          }
+          else {
+            mchunkptr prev = chunk_minus_offset(p, prevsize);
+            psize += prevsize;
+            p = prev;
+            if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */
+              if (p != fm->dv) {
+                unlink_chunk(fm, p, prevsize);
+              }
+              else if ((next->head & INUSE_BITS) == INUSE_BITS) {
+                fm->dvsize = psize;
+                set_free_with_pinuse(p, psize, next);
+                goto postaction;
+              }
+            }
+            else
+              goto erroraction;
+          }
+        }
+
+        if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) {
+          if (!cinuse(next)) {  /* consolidate forward */
+            if (next == fm->top) {
+              size_t tsize = fm->topsize += psize;
+              fm->top = p;
+              p->head = tsize | PINUSE_BIT;
+              if (p == fm->dv) {
+                fm->dv = 0;
+                fm->dvsize = 0;
+              }
+              if (should_trim(fm, tsize))
+                sys_trim(fm, 0);
+              goto postaction;
+            }
+            else if (next == fm->dv) {
+              size_t dsize = fm->dvsize += psize;
+              fm->dv = p;
+              set_size_and_pinuse_of_free_chunk(p, dsize);
+              goto postaction;
+            }
+            else {
+              size_t nsize = chunksize(next);
+              psize += nsize;
+              unlink_chunk(fm, next, nsize);
+              set_size_and_pinuse_of_free_chunk(p, psize);
+              if (p == fm->dv) {
+                fm->dvsize = psize;
+                goto postaction;
+              }
+            }
+          }
+          else
+            set_free_with_pinuse(p, psize, next);
+
+          if (is_small(psize)) {
+            insert_small_chunk(fm, p, psize);
+            check_free_chunk(fm, p);
+          }
+          else {
+            tchunkptr tp = (tchunkptr)p;
+            insert_large_chunk(fm, tp, psize);
+            check_free_chunk(fm, p);
+            if (--fm->release_checks == 0)
+              release_unused_segments(fm);
+          }
+          goto postaction;
+        }
+      }
+    erroraction:
+      USAGE_ERROR_ACTION(fm, p);
+    postaction:
+      POSTACTION(fm);
+    }
+  }
+#if !FOOTERS
+#undef fm
+#endif /* FOOTERS */
+}
+
+void* dlcalloc(size_t n_elements, size_t elem_size) {
+  void* mem;
+  size_t req = 0;
+  if (n_elements != 0) {
+    req = n_elements * elem_size;
+    if (((n_elements | elem_size) & ~(size_t)0xffff) &&
+        (req / n_elements != elem_size))
+      req = MAX_SIZE_T; /* force downstream failure on overflow */
+  }
+  mem = dlmalloc(req);
+  if (mem != 0 && calloc_must_clear(mem2chunk(mem)))
+    memset(mem, 0, req);
+  return mem;
+}
+
+#endif /* !ONLY_MSPACES */
+
+/* ------------ Internal support for realloc, memalign, etc -------------- */
+
+/* Try to realloc; only in-place unless can_move true */
+static mchunkptr try_realloc_chunk(mstate m, mchunkptr p, size_t nb,
+                                   int can_move) {
+  mchunkptr newp = 0;
+  size_t oldsize = chunksize(p);
+  mchunkptr next = chunk_plus_offset(p, oldsize);
+  if (RTCHECK(ok_address(m, p) && ok_inuse(p) &&
+              ok_next(p, next) && ok_pinuse(next))) {
+    if (is_mmapped(p)) {
+      newp = mmap_resize(m, p, nb, can_move);
+    }
+    else if (oldsize >= nb) {             /* already big enough */
+      size_t rsize = oldsize - nb;
+      if (rsize >= MIN_CHUNK_SIZE) {      /* split off remainder */
+        mchunkptr r = chunk_plus_offset(p, nb);
+        set_inuse(m, p, nb);
+        set_inuse(m, r, rsize);
+        dispose_chunk(m, r, rsize);
+      }
+      newp = p;
+    }
+    else if (next == m->top) {  /* extend into top */
+      if (oldsize + m->topsize > nb) {
+        size_t newsize = oldsize + m->topsize;
+        size_t newtopsize = newsize - nb;
+        mchunkptr newtop = chunk_plus_offset(p, nb);
+        set_inuse(m, p, nb);
+        newtop->head = newtopsize |PINUSE_BIT;
+        m->top = newtop;
+        m->topsize = newtopsize;
+        newp = p;
+      }
+    }
+    else if (next == m->dv) { /* extend into dv */
+      size_t dvs = m->dvsize;
+      if (oldsize + dvs >= nb) {
+        size_t dsize = oldsize + dvs - nb;
+        if (dsize >= MIN_CHUNK_SIZE) {
+          mchunkptr r = chunk_plus_offset(p, nb);
+          mchunkptr n = chunk_plus_offset(r, dsize);
+          set_inuse(m, p, nb);
+          set_size_and_pinuse_of_free_chunk(r, dsize);
+          clear_pinuse(n);
+          m->dvsize = dsize;
+          m->dv = r;
+        }
+        else { /* exhaust dv */
+          size_t newsize = oldsize + dvs;
+          set_inuse(m, p, newsize);
+          m->dvsize = 0;
+          m->dv = 0;
+        }
+        newp = p;
+      }
+    }
+    else if (!cinuse(next)) { /* extend into next free chunk */
+      size_t nextsize = chunksize(next);
+      if (oldsize + nextsize >= nb) {
+        size_t rsize = oldsize + nextsize - nb;
+        unlink_chunk(m, next, nextsize);
+        if (rsize < MIN_CHUNK_SIZE) {
+          size_t newsize = oldsize + nextsize;
+          set_inuse(m, p, newsize);
+        }
+        else {
+          mchunkptr r = chunk_plus_offset(p, nb);
+          set_inuse(m, p, nb);
+          set_inuse(m, r, rsize);
+          dispose_chunk(m, r, rsize);
+        }
+        newp = p;
+      }
+    }
+  }
+  else {
+    USAGE_ERROR_ACTION(m, chunk2mem(p));
+  }
+  return newp;
+}
+
+static void* internal_memalign(mstate m, size_t alignment, size_t bytes) {
+  void* mem = 0;
+  if (alignment <  MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */
+    alignment = MIN_CHUNK_SIZE;
+  if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */
+    size_t a = MALLOC_ALIGNMENT << 1;
+    while (a < alignment) a <<= 1;
+    alignment = a;
+  }
+  if (bytes >= MAX_REQUEST - alignment) {
+    if (m != 0)  { /* Test isn't needed but avoids compiler warning */
+      MALLOC_FAILURE_ACTION;
+    }
+  }
+  else {
+    size_t nb = request2size(bytes);
+    size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD;
+    mem = internal_malloc(m, req);
+    if (mem != 0) {
+      mchunkptr p = mem2chunk(mem);
+      if (PREACTION(m))
+        return 0;
+      if ((((size_t)(mem)) & (alignment - 1)) != 0) { /* misaligned */
+        /*
+          Find an aligned spot inside chunk.  Since we need to give
+          back leading space in a chunk of at least MIN_CHUNK_SIZE, if
+          the first calculation places us at a spot with less than
+          MIN_CHUNK_SIZE leader, we can move to the next aligned spot.
+          We've allocated enough total room so that this is always
+          possible.
+        */
+        char* br = (char*)mem2chunk((size_t)(((size_t)((char*)mem + alignment -
+                                                       SIZE_T_ONE)) &
+                                             -alignment));
+        char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)?
+          br : br+alignment;
+        mchunkptr newp = (mchunkptr)pos;
+        size_t leadsize = pos - (char*)(p);
+        size_t newsize = chunksize(p) - leadsize;
+
+        if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */
+          newp->prev_foot = p->prev_foot + leadsize;
+          newp->head = newsize;
+        }
+        else { /* Otherwise, give back leader, use the rest */
+          set_inuse(m, newp, newsize);
+          set_inuse(m, p, leadsize);
+          dispose_chunk(m, p, leadsize);
+        }
+        p = newp;
+      }
+
+      /* Give back spare room at the end */
+      if (!is_mmapped(p)) {
+        size_t size = chunksize(p);
+        if (size > nb + MIN_CHUNK_SIZE) {
+          size_t remainder_size = size - nb;
+          mchunkptr remainder = chunk_plus_offset(p, nb);
+          set_inuse(m, p, nb);
+          set_inuse(m, remainder, remainder_size);
+          dispose_chunk(m, remainder, remainder_size);
+        }
+      }
+
+      mem = chunk2mem(p);
+      assert (chunksize(p) >= nb);
+      assert(((size_t)mem & (alignment - 1)) == 0);
+      check_inuse_chunk(m, p);
+      POSTACTION(m);
+    }
+  }
+  return mem;
+}
+
+/*
+  Common support for independent_X routines, handling
+    all of the combinations that can result.
+  The opts arg has:
+    bit 0 set if all elements are same size (using sizes[0])
+    bit 1 set if elements should be zeroed
+*/
+static void** ialloc(mstate m,
+                     size_t n_elements,
+                     size_t* sizes,
+                     int opts,
+                     void* chunks[]) {
+
+  size_t    element_size;   /* chunksize of each element, if all same */
+  size_t    contents_size;  /* total size of elements */
+  size_t    array_size;     /* request size of pointer array */
+  void*     mem;            /* malloced aggregate space */
+  mchunkptr p;              /* corresponding chunk */
+  size_t    remainder_size; /* remaining bytes while splitting */
+  void**    marray;         /* either "chunks" or malloced ptr array */
+  mchunkptr array_chunk;    /* chunk for malloced ptr array */
+  flag_t    was_enabled;    /* to disable mmap */
+  size_t    size;
+  size_t    i;
+
+  ensure_initialization();
+  /* compute array length, if needed */
+  if (chunks != 0) {
+    if (n_elements == 0)
+      return chunks; /* nothing to do */
+    marray = chunks;
+    array_size = 0;
+  }
+  else {
+    /* if empty req, must still return chunk representing empty array */
+    if (n_elements == 0)
+      return (void**)internal_malloc(m, 0);
+    marray = 0;
+    array_size = request2size(n_elements * (sizeof(void*)));
+  }
+
+  /* compute total element size */
+  if (opts & 0x1) { /* all-same-size */
+    element_size = request2size(*sizes);
+    contents_size = n_elements * element_size;
+  }
+  else { /* add up all the sizes */
+    element_size = 0;
+    contents_size = 0;
+    for (i = 0; i != n_elements; ++i)
+      contents_size += request2size(sizes[i]);
+  }
+
+  size = contents_size + array_size;
+
+  /*
+     Allocate the aggregate chunk.  First disable direct-mmapping so
+     malloc won't use it, since we would not be able to later
+     free/realloc space internal to a segregated mmap region.
+  */
+  was_enabled = use_mmap(m);
+  disable_mmap(m);
+  mem = internal_malloc(m, size - CHUNK_OVERHEAD);
+  if (was_enabled)
+    enable_mmap(m);
+  if (mem == 0)
+    return 0;
+
+  if (PREACTION(m)) return 0;
+  p = mem2chunk(mem);
+  remainder_size = chunksize(p);
+
+  assert(!is_mmapped(p));
+
+  if (opts & 0x2) {       /* optionally clear the elements */
+    memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size);
+  }
+
+  /* If not provided, allocate the pointer array as final part of chunk */
+  if (marray == 0) {
+    size_t  array_chunk_size;
+    array_chunk = chunk_plus_offset(p, contents_size);
+    array_chunk_size = remainder_size - contents_size;
+    marray = (void**) (chunk2mem(array_chunk));
+    set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size);
+    remainder_size = contents_size;
+  }
+
+  /* split out elements */
+  for (i = 0; ; ++i) {
+    marray[i] = chunk2mem(p);
+    if (i != n_elements-1) {
+      if (element_size != 0)
+        size = element_size;
+      else
+        size = request2size(sizes[i]);
+      remainder_size -= size;
+      set_size_and_pinuse_of_inuse_chunk(m, p, size);
+      p = chunk_plus_offset(p, size);
+    }
+    else { /* the final element absorbs any overallocation slop */
+      set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size);
+      break;
+    }
+  }
+
+#if DEBUG
+  if (marray != chunks) {
+    /* final element must have exactly exhausted chunk */
+    if (element_size != 0) {
+      assert(remainder_size == element_size);
+    }
+    else {
+      assert(remainder_size == request2size(sizes[i]));
+    }
+    check_inuse_chunk(m, mem2chunk(marray));
+  }
+  for (i = 0; i != n_elements; ++i)
+    check_inuse_chunk(m, mem2chunk(marray[i]));
+
+#endif /* DEBUG */
+
+  POSTACTION(m);
+  return marray;
+}
+
+/* Try to free all pointers in the given array.
+   Note: this could be made faster, by delaying consolidation,
+   at the price of disabling some user integrity checks, We
+   still optimize some consolidations by combining adjacent
+   chunks before freeing, which will occur often if allocated
+   with ialloc or the array is sorted.
+*/
+static size_t internal_bulk_free(mstate m, void* array[], size_t nelem) {
+  size_t unfreed = 0;
+  if (!PREACTION(m)) {
+    void** a;
+    void** fence = &(array[nelem]);
+    for (a = array; a != fence; ++a) {
+      void* mem = *a;
+      if (mem != 0) {
+        mchunkptr p = mem2chunk(mem);
+        size_t psize = chunksize(p);
+#if FOOTERS
+        if (get_mstate_for(p) != m) {
+          ++unfreed;
+          continue;
+        }
+#endif
+        check_inuse_chunk(m, p);
+        *a = 0;
+        if (RTCHECK(ok_address(m, p) && ok_inuse(p))) {
+          void ** b = a + 1; /* try to merge with next chunk */
+          mchunkptr next = next_chunk(p);
+          if (b != fence && *b == chunk2mem(next)) {
+            size_t newsize = chunksize(next) + psize;
+            set_inuse(m, p, newsize);
+            *b = chunk2mem(p);
+          }
+          else
+            dispose_chunk(m, p, psize);
+        }
+        else {
+          CORRUPTION_ERROR_ACTION(m);
+          break;
+        }
+      }
+    }
+    if (should_trim(m, m->topsize))
+      sys_trim(m, 0);
+    POSTACTION(m);
+  }
+  return unfreed;
+}
+
+/* Traversal */
+#if MALLOC_INSPECT_ALL
+static void internal_inspect_all(mstate m,
+                                 void(*handler)(void *start,
+                                                void *end,
+                                                size_t used_bytes,
+                                                void* callback_arg),
+                                 void* arg) {
+  if (is_initialized(m)) {
+    mchunkptr top = m->top;
+    msegmentptr s;
+    for (s = &m->seg; s != 0; s = s->next) {
+      mchunkptr q = align_as_chunk(s->base);
+      while (segment_holds(s, q) && q->head != FENCEPOST_HEAD) {
+        mchunkptr next = next_chunk(q);
+        size_t sz = chunksize(q);
+        size_t used;
+        void* start;
+        if (is_inuse(q)) {
+          used = sz - CHUNK_OVERHEAD; /* must not be mmapped */
+          start = chunk2mem(q);
+        }
+        else {
+          used = 0;
+          if (is_small(sz)) {     /* offset by possible bookkeeping */
+            start = (void*)((char*)q + sizeof(struct malloc_chunk));
+          }
+          else {
+            start = (void*)((char*)q + sizeof(struct malloc_tree_chunk));
+          }
+        }
+        if (start < (void*)next)  /* skip if all space is bookkeeping */
+          handler(start, next, used, arg);
+        if (q == top)
+          break;
+        q = next;
+      }
+    }
+  }
+}
+#endif /* MALLOC_INSPECT_ALL */
+
+/* ------------------ Exported realloc, memalign, etc -------------------- */
+
+#if !ONLY_MSPACES
+
+void* dlrealloc(void* oldmem, size_t bytes) {
+  void* mem = 0;
+  if (oldmem == 0) {
+    mem = dlmalloc(bytes);
+  }
+  else if (bytes >= MAX_REQUEST) {
+    MALLOC_FAILURE_ACTION;
+  }
+#ifdef REALLOC_ZERO_BYTES_FREES
+  else if (bytes == 0) {
+    dlfree(oldmem);
+  }
+#endif /* REALLOC_ZERO_BYTES_FREES */
+  else {
+    size_t nb = request2size(bytes);
+    mchunkptr oldp = mem2chunk(oldmem);
+#if ! FOOTERS
+    mstate m = gm;
+#else /* FOOTERS */
+    mstate m = get_mstate_for(oldp);
+    if (!ok_magic(m)) {
+      USAGE_ERROR_ACTION(m, oldmem);
+      return 0;
+    }
+#endif /* FOOTERS */
+    if (!PREACTION(m)) {
+      mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1);
+      POSTACTION(m);
+      if (newp != 0) {
+        check_inuse_chunk(m, newp);
+        mem = chunk2mem(newp);
+      }
+      else {
+        mem = internal_malloc(m, bytes);
+        if (mem != 0) {
+          size_t oc = chunksize(oldp) - overhead_for(oldp);
+          memcpy(mem, oldmem, (oc < bytes)? oc : bytes);
+          internal_free(m, oldmem);
+        }
+      }
+    }
+  }
+  return mem;
+}
+
+void* dlrealloc_in_place(void* oldmem, size_t bytes) {
+  void* mem = 0;
+  if (oldmem != 0) {
+    if (bytes >= MAX_REQUEST) {
+      MALLOC_FAILURE_ACTION;
+    }
+    else {
+      size_t nb = request2size(bytes);
+      mchunkptr oldp = mem2chunk(oldmem);
+#if ! FOOTERS
+      mstate m = gm;
+#else /* FOOTERS */
+      mstate m = get_mstate_for(oldp);
+      if (!ok_magic(m)) {
+        USAGE_ERROR_ACTION(m, oldmem);
+        return 0;
+      }
+#endif /* FOOTERS */
+      if (!PREACTION(m)) {
+        mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0);
+        POSTACTION(m);
+        if (newp == oldp) {
+          check_inuse_chunk(m, newp);
+          mem = oldmem;
+        }
+      }
+    }
+  }
+  return mem;
+}
+
+void* dlmemalign(size_t alignment, size_t bytes) {
+  if (alignment <= MALLOC_ALIGNMENT) {
+    return dlmalloc(bytes);
+  }
+  return internal_memalign(gm, alignment, bytes);
+}
+
+int dlposix_memalign(void** pp, size_t alignment, size_t bytes) {
+  void* mem = 0;
+  if (alignment == MALLOC_ALIGNMENT)
+    mem = dlmalloc(bytes);
+  else {
+    size_t d = alignment / sizeof(void*);
+    size_t r = alignment % sizeof(void*);
+    if (r != 0 || d == 0 || (d & (d-SIZE_T_ONE)) != 0)
+      return EINVAL;
+    else if (bytes <= MAX_REQUEST - alignment) {
+      if (alignment <  MIN_CHUNK_SIZE)
+        alignment = MIN_CHUNK_SIZE;
+      mem = internal_memalign(gm, alignment, bytes);
+    }
+  }
+  if (mem == 0)
+    return ENOMEM;
+  else {
+    *pp = mem;
+    return 0;
+  }
+}
+
+void* dlvalloc(size_t bytes) {
+  size_t pagesz;
+  ensure_initialization();
+  pagesz = mparams.page_size;
+  return dlmemalign(pagesz, bytes);
+}
+
+void* dlpvalloc(size_t bytes) {
+  size_t pagesz;
+  ensure_initialization();
+  pagesz = mparams.page_size;
+  return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE));
+}
+
+void** dlindependent_calloc(size_t n_elements, size_t elem_size,
+                            void* chunks[]) {
+  size_t sz = elem_size; /* serves as 1-element array */
+  return ialloc(gm, n_elements, &sz, 3, chunks);
+}
+
+void** dlindependent_comalloc(size_t n_elements, size_t sizes[],
+                              void* chunks[]) {
+  return ialloc(gm, n_elements, sizes, 0, chunks);
+}
+
+size_t dlbulk_free(void* array[], size_t nelem) {
+  return internal_bulk_free(gm, array, nelem);
+}
+
+#if MALLOC_INSPECT_ALL
+void dlmalloc_inspect_all(void(*handler)(void *start,
+                                         void *end,
+                                         size_t used_bytes,
+                                         void* callback_arg),
+                          void* arg) {
+  ensure_initialization();
+  if (!PREACTION(gm)) {
+    internal_inspect_all(gm, handler, arg);
+    POSTACTION(gm);
+  }
+}
+#endif /* MALLOC_INSPECT_ALL */
+
+int dlmalloc_trim(size_t pad) {
+  int result = 0;
+  ensure_initialization();
+  if (!PREACTION(gm)) {
+    result = sys_trim(gm, pad);
+    POSTACTION(gm);
+  }
+  return result;
+}
+
+size_t dlmalloc_footprint(void) {
+  return gm->footprint;
+}
+
+size_t dlmalloc_max_footprint(void) {
+  return gm->max_footprint;
+}
+
+size_t dlmalloc_footprint_limit(void) {
+  size_t maf = gm->footprint_limit;
+  return maf == 0 ? MAX_SIZE_T : maf;
+}
+
+size_t dlmalloc_set_footprint_limit(size_t bytes) {
+  size_t result;  /* invert sense of 0 */
+  if (bytes == 0)
+    result = granularity_align(1); /* Use minimal size */
+  if (bytes == MAX_SIZE_T)
+    result = 0;                    /* disable */
+  else
+    result = granularity_align(bytes);
+  return gm->footprint_limit = result;
+}
+
+#if !NO_MALLINFO
+struct mallinfo dlmallinfo(void) {
+  return internal_mallinfo(gm);
+}
+#endif /* NO_MALLINFO */
+
+#if !NO_MALLOC_STATS
+void dlmalloc_stats() {
+  internal_malloc_stats(gm);
+}
+#endif /* NO_MALLOC_STATS */
+
+int dlmallopt(int param_number, int value) {
+  return change_mparam(param_number, value);
+}
+
+size_t dlmalloc_usable_size(void* mem) {
+  if (mem != 0) {
+    mchunkptr p = mem2chunk(mem);
+    if (is_inuse(p))
+      return chunksize(p) - overhead_for(p);
+  }
+  return 0;
+}
+
+#endif /* !ONLY_MSPACES */
+
+/* ----------------------------- user mspaces ---------------------------- */
+
+#if MSPACES
+
+static mstate init_user_mstate(char* tbase, size_t tsize) {
+  size_t msize = pad_request(sizeof(struct malloc_state));
+  mchunkptr mn;
+  mchunkptr msp = align_as_chunk(tbase);
+  mstate m = (mstate)(chunk2mem(msp));
+  memset(m, 0, msize);
+  (void)INITIAL_LOCK(&m->mutex);
+  msp->head = (msize|INUSE_BITS);
+  m->seg.base = m->least_addr = tbase;
+  m->seg.size = m->footprint = m->max_footprint = tsize;
+  m->magic = mparams.magic;
+  m->release_checks = MAX_RELEASE_CHECK_RATE;
+  m->mflags = mparams.default_mflags;
+  m->extp = 0;
+  m->exts = 0;
+  disable_contiguous(m);
+  init_bins(m);
+  mn = next_chunk(mem2chunk(m));
+  init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) - TOP_FOOT_SIZE);
+  check_top_chunk(m, m->top);
+  return m;
+}
+
+mspace create_mspace(size_t capacity, int locked) {
+  mstate m = 0;
+  size_t msize;
+  ensure_initialization();
+  msize = pad_request(sizeof(struct malloc_state));
+  if (capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) {
+    size_t rs = ((capacity == 0)? mparams.granularity :
+                 (capacity + TOP_FOOT_SIZE + msize));
+    size_t tsize = granularity_align(rs);
+    char* tbase = (char*)(CALL_MMAP(tsize));
+    if (tbase != CMFAIL) {
+      m = init_user_mstate(tbase, tsize);
+      m->seg.sflags = USE_MMAP_BIT;
+      set_lock(m, locked);
+    }
+  }
+  return (mspace)m;
+}
+
+mspace create_mspace_with_base(void* base, size_t capacity, int locked) {
+  mstate m = 0;
+  size_t msize;
+  ensure_initialization();
+  msize = pad_request(sizeof(struct malloc_state));
+  if (capacity > msize + TOP_FOOT_SIZE &&
+      capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) {
+    m = init_user_mstate((char*)base, capacity);
+    m->seg.sflags = EXTERN_BIT;
+    set_lock(m, locked);
+  }
+  return (mspace)m;
+}
+
+int mspace_track_large_chunks(mspace msp, int enable) {
+  int ret = 0;
+  mstate ms = (mstate)msp;
+  if (!PREACTION(ms)) {
+    if (!use_mmap(ms)) {
+      ret = 1;
+    }
+    if (!enable) {
+      enable_mmap(ms);
+    } else {
+      disable_mmap(ms);
+    }
+    POSTACTION(ms);
+  }
+  return ret;
+}
+
+size_t destroy_mspace(mspace msp) {
+  size_t freed = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    msegmentptr sp = &ms->seg;
+    (void)DESTROY_LOCK(&ms->mutex); /* destroy before unmapped */
+    while (sp != 0) {
+      char* base = sp->base;
+      size_t size = sp->size;
+      flag_t flag = sp->sflags;
+      (void)base; /* placate people compiling -Wunused-variable */
+      sp = sp->next;
+      if ((flag & USE_MMAP_BIT) && !(flag & EXTERN_BIT) &&
+          CALL_MUNMAP(base, size) == 0)
+        freed += size;
+    }
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return freed;
+}
+
+/*
+  mspace versions of routines are near-clones of the global
+  versions. This is not so nice but better than the alternatives.
+*/
+
+void* mspace_malloc(mspace msp, size_t bytes) {
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  if (!PREACTION(ms)) {
+    void* mem;
+    size_t nb;
+    if (bytes <= MAX_SMALL_REQUEST) {
+      bindex_t idx;
+      binmap_t smallbits;
+      nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes);
+      idx = small_index(nb);
+      smallbits = ms->smallmap >> idx;
+
+      if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */
+        mchunkptr b, p;
+        idx += ~smallbits & 1;       /* Uses next bin if idx empty */
+        b = smallbin_at(ms, idx);
+        p = b->fd;
+        assert(chunksize(p) == small_index2size(idx));
+        unlink_first_small_chunk(ms, b, p, idx);
+        set_inuse_and_pinuse(ms, p, small_index2size(idx));
+        mem = chunk2mem(p);
+        check_malloced_chunk(ms, mem, nb);
+        goto postaction;
+      }
+
+      else if (nb > ms->dvsize) {
+        if (smallbits != 0) { /* Use chunk in next nonempty smallbin */
+          mchunkptr b, p, r;
+          size_t rsize;
+          bindex_t i;
+          binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx));
+          binmap_t leastbit = least_bit(leftbits);
+          compute_bit2idx(leastbit, i);
+          b = smallbin_at(ms, i);
+          p = b->fd;
+          assert(chunksize(p) == small_index2size(i));
+          unlink_first_small_chunk(ms, b, p, i);
+          rsize = small_index2size(i) - nb;
+          /* Fit here cannot be remainderless if 4byte sizes */
+          if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE)
+            set_inuse_and_pinuse(ms, p, small_index2size(i));
+          else {
+            set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+            r = chunk_plus_offset(p, nb);
+            set_size_and_pinuse_of_free_chunk(r, rsize);
+            replace_dv(ms, r, rsize);
+          }
+          mem = chunk2mem(p);
+          check_malloced_chunk(ms, mem, nb);
+          goto postaction;
+        }
+
+        else if (ms->treemap != 0 && (mem = tmalloc_small(ms, nb)) != 0) {
+          check_malloced_chunk(ms, mem, nb);
+          goto postaction;
+        }
+      }
+    }
+    else if (bytes >= MAX_REQUEST)
+      nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */
+    else {
+      nb = pad_request(bytes);
+      if (ms->treemap != 0 && (mem = tmalloc_large(ms, nb)) != 0) {
+        check_malloced_chunk(ms, mem, nb);
+        goto postaction;
+      }
+    }
+
+    if (nb <= ms->dvsize) {
+      size_t rsize = ms->dvsize - nb;
+      mchunkptr p = ms->dv;
+      if (rsize >= MIN_CHUNK_SIZE) { /* split dv */
+        mchunkptr r = ms->dv = chunk_plus_offset(p, nb);
+        ms->dvsize = rsize;
+        set_size_and_pinuse_of_free_chunk(r, rsize);
+        set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+      }
+      else { /* exhaust dv */
+        size_t dvs = ms->dvsize;
+        ms->dvsize = 0;
+        ms->dv = 0;
+        set_inuse_and_pinuse(ms, p, dvs);
+      }
+      mem = chunk2mem(p);
+      check_malloced_chunk(ms, mem, nb);
+      goto postaction;
+    }
+
+    else if (nb < ms->topsize) { /* Split top */
+      size_t rsize = ms->topsize -= nb;
+      mchunkptr p = ms->top;
+      mchunkptr r = ms->top = chunk_plus_offset(p, nb);
+      r->head = rsize | PINUSE_BIT;
+      set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+      mem = chunk2mem(p);
+      check_top_chunk(ms, ms->top);
+      check_malloced_chunk(ms, mem, nb);
+      goto postaction;
+    }
+
+    mem = sys_alloc(ms, nb);
+
+  postaction:
+    POSTACTION(ms);
+    return mem;
+  }
+
+  return 0;
+}
+
+void mspace_free(mspace msp, void* mem) {
+  if (mem != 0) {
+    mchunkptr p  = mem2chunk(mem);
+#if FOOTERS
+    mstate fm = get_mstate_for(p);
+    (void)msp; /* placate people compiling -Wunused */
+#else /* FOOTERS */
+    mstate fm = (mstate)msp;
+#endif /* FOOTERS */
+    if (!ok_magic(fm)) {
+      USAGE_ERROR_ACTION(fm, p);
+      return;
+    }
+    if (!PREACTION(fm)) {
+      check_inuse_chunk(fm, p);
+      if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) {
+        size_t psize = chunksize(p);
+        mchunkptr next = chunk_plus_offset(p, psize);
+        if (!pinuse(p)) {
+          size_t prevsize = p->prev_foot;
+          if (is_mmapped(p)) {
+            psize += prevsize + MMAP_FOOT_PAD;
+            if (CALL_MUNMAP((char*)p - prevsize, psize) == 0)
+              fm->footprint -= psize;
+            goto postaction;
+          }
+          else {
+            mchunkptr prev = chunk_minus_offset(p, prevsize);
+            psize += prevsize;
+            p = prev;
+            if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */
+              if (p != fm->dv) {
+                unlink_chunk(fm, p, prevsize);
+              }
+              else if ((next->head & INUSE_BITS) == INUSE_BITS) {
+                fm->dvsize = psize;
+                set_free_with_pinuse(p, psize, next);
+                goto postaction;
+              }
+            }
+            else
+              goto erroraction;
+          }
+        }
+
+        if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) {
+          if (!cinuse(next)) {  /* consolidate forward */
+            if (next == fm->top) {
+              size_t tsize = fm->topsize += psize;
+              fm->top = p;
+              p->head = tsize | PINUSE_BIT;
+              if (p == fm->dv) {
+                fm->dv = 0;
+                fm->dvsize = 0;
+              }
+              if (should_trim(fm, tsize))
+                sys_trim(fm, 0);
+              goto postaction;
+            }
+            else if (next == fm->dv) {
+              size_t dsize = fm->dvsize += psize;
+              fm->dv = p;
+              set_size_and_pinuse_of_free_chunk(p, dsize);
+              goto postaction;
+            }
+            else {
+              size_t nsize = chunksize(next);
+              psize += nsize;
+              unlink_chunk(fm, next, nsize);
+              set_size_and_pinuse_of_free_chunk(p, psize);
+              if (p == fm->dv) {
+                fm->dvsize = psize;
+                goto postaction;
+              }
+            }
+          }
+          else
+            set_free_with_pinuse(p, psize, next);
+
+          if (is_small(psize)) {
+            insert_small_chunk(fm, p, psize);
+            check_free_chunk(fm, p);
+          }
+          else {
+            tchunkptr tp = (tchunkptr)p;
+            insert_large_chunk(fm, tp, psize);
+            check_free_chunk(fm, p);
+            if (--fm->release_checks == 0)
+              release_unused_segments(fm);
+          }
+          goto postaction;
+        }
+      }
+    erroraction:
+      USAGE_ERROR_ACTION(fm, p);
+    postaction:
+      POSTACTION(fm);
+    }
+  }
+}
+
+void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) {
+  void* mem;
+  size_t req = 0;
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  if (n_elements != 0) {
+    req = n_elements * elem_size;
+    if (((n_elements | elem_size) & ~(size_t)0xffff) &&
+        (req / n_elements != elem_size))
+      req = MAX_SIZE_T; /* force downstream failure on overflow */
+  }
+  mem = internal_malloc(ms, req);
+  if (mem != 0 && calloc_must_clear(mem2chunk(mem)))
+    memset(mem, 0, req);
+  return mem;
+}
+
+void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) {
+  void* mem = 0;
+  if (oldmem == 0) {
+    mem = mspace_malloc(msp, bytes);
+  }
+  else if (bytes >= MAX_REQUEST) {
+    MALLOC_FAILURE_ACTION;
+  }
+#ifdef REALLOC_ZERO_BYTES_FREES
+  else if (bytes == 0) {
+    mspace_free(msp, oldmem);
+  }
+#endif /* REALLOC_ZERO_BYTES_FREES */
+  else {
+    size_t nb = request2size(bytes);
+    mchunkptr oldp = mem2chunk(oldmem);
+#if ! FOOTERS
+    mstate m = (mstate)msp;
+#else /* FOOTERS */
+    mstate m = get_mstate_for(oldp);
+    if (!ok_magic(m)) {
+      USAGE_ERROR_ACTION(m, oldmem);
+      return 0;
+    }
+#endif /* FOOTERS */
+    if (!PREACTION(m)) {
+      mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1);
+      POSTACTION(m);
+      if (newp != 0) {
+        check_inuse_chunk(m, newp);
+        mem = chunk2mem(newp);
+      }
+      else {
+        mem = mspace_malloc(m, bytes);
+        if (mem != 0) {
+          size_t oc = chunksize(oldp) - overhead_for(oldp);
+          memcpy(mem, oldmem, (oc < bytes)? oc : bytes);
+          mspace_free(m, oldmem);
+        }
+      }
+    }
+  }
+  return mem;
+}
+
+void* mspace_realloc_in_place(mspace msp, void* oldmem, size_t bytes) {
+  void* mem = 0;
+  if (oldmem != 0) {
+    if (bytes >= MAX_REQUEST) {
+      MALLOC_FAILURE_ACTION;
+    }
+    else {
+      size_t nb = request2size(bytes);
+      mchunkptr oldp = mem2chunk(oldmem);
+#if ! FOOTERS
+      mstate m = (mstate)msp;
+#else /* FOOTERS */
+      mstate m = get_mstate_for(oldp);
+      (void)msp; /* placate people compiling -Wunused */
+      if (!ok_magic(m)) {
+        USAGE_ERROR_ACTION(m, oldmem);
+        return 0;
+      }
+#endif /* FOOTERS */
+      if (!PREACTION(m)) {
+        mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0);
+        POSTACTION(m);
+        if (newp == oldp) {
+          check_inuse_chunk(m, newp);
+          mem = oldmem;
+        }
+      }
+    }
+  }
+  return mem;
+}
+
+void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) {
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  if (alignment <= MALLOC_ALIGNMENT)
+    return mspace_malloc(msp, bytes);
+  return internal_memalign(ms, alignment, bytes);
+}
+
+void** mspace_independent_calloc(mspace msp, size_t n_elements,
+                                 size_t elem_size, void* chunks[]) {
+  size_t sz = elem_size; /* serves as 1-element array */
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  return ialloc(ms, n_elements, &sz, 3, chunks);
+}
+
+void** mspace_independent_comalloc(mspace msp, size_t n_elements,
+                                   size_t sizes[], void* chunks[]) {
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  return ialloc(ms, n_elements, sizes, 0, chunks);
+}
+
+size_t mspace_bulk_free(mspace msp, void* array[], size_t nelem) {
+  return internal_bulk_free((mstate)msp, array, nelem);
+}
+
+#if MALLOC_INSPECT_ALL
+void mspace_inspect_all(mspace msp,
+                        void(*handler)(void *start,
+                                       void *end,
+                                       size_t used_bytes,
+                                       void* callback_arg),
+                        void* arg) {
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    if (!PREACTION(ms)) {
+      internal_inspect_all(ms, handler, arg);
+      POSTACTION(ms);
+    }
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+}
+#endif /* MALLOC_INSPECT_ALL */
+
+int mspace_trim(mspace msp, size_t pad) {
+  int result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    if (!PREACTION(ms)) {
+      result = sys_trim(ms, pad);
+      POSTACTION(ms);
+    }
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+#if !NO_MALLOC_STATS
+void mspace_malloc_stats(mspace msp) {
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    internal_malloc_stats(ms);
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+}
+#endif /* NO_MALLOC_STATS */
+
+size_t mspace_footprint(mspace msp) {
+  size_t result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    result = ms->footprint;
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+size_t mspace_max_footprint(mspace msp) {
+  size_t result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    result = ms->max_footprint;
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+size_t mspace_footprint_limit(mspace msp) {
+  size_t result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    size_t maf = ms->footprint_limit;
+    result = (maf == 0) ? MAX_SIZE_T : maf;
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+size_t mspace_set_footprint_limit(mspace msp, size_t bytes) {
+  size_t result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    if (bytes == 0)
+      result = granularity_align(1); /* Use minimal size */
+    if (bytes == MAX_SIZE_T)
+      result = 0;                    /* disable */
+    else
+      result = granularity_align(bytes);
+    ms->footprint_limit = result;
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+#if !NO_MALLINFO
+struct mallinfo mspace_mallinfo(mspace msp) {
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return internal_mallinfo(ms);
+}
+#endif /* NO_MALLINFO */
+
+size_t mspace_usable_size(const void* mem) {
+  if (mem != 0) {
+    mchunkptr p = mem2chunk(mem);
+    if (is_inuse(p))
+      return chunksize(p) - overhead_for(p);
+  }
+  return 0;
+}
+
+int mspace_mallopt(int param_number, int value) {
+  return change_mparam(param_number, value);
+}
+
+#endif /* MSPACES */
+
+
+/* -------------------- Alternative MORECORE functions ------------------- */
+
+/*
+  Guidelines for creating a custom version of MORECORE:
+
+  * For best performance, MORECORE should allocate in multiples of pagesize.
+  * MORECORE may allocate more memory than requested. (Or even less,
+      but this will usually result in a malloc failure.)
+  * MORECORE must not allocate memory when given argument zero, but
+      instead return one past the end address of memory from previous
+      nonzero call.
+  * For best performance, consecutive calls to MORECORE with positive
+      arguments should return increasing addresses, indicating that
+      space has been contiguously extended.
+  * Even though consecutive calls to MORECORE need not return contiguous
+      addresses, it must be OK for malloc'ed chunks to span multiple
+      regions in those cases where they do happen to be contiguous.
+  * MORECORE need not handle negative arguments -- it may instead
+      just return MFAIL when given negative arguments.
+      Negative arguments are always multiples of pagesize. MORECORE
+      must not misinterpret negative args as large positive unsigned
+      args. You can suppress all such calls from even occurring by defining
+      MORECORE_CANNOT_TRIM,
+
+  As an example alternative MORECORE, here is a custom allocator
+  kindly contributed for pre-OSX macOS.  It uses virtually but not
+  necessarily physically contiguous non-paged memory (locked in,
+  present and won't get swapped out).  You can use it by uncommenting
+  this section, adding some #includes, and setting up the appropriate
+  defines above:
+
+      #define MORECORE osMoreCore
+
+  There is also a shutdown routine that should somehow be called for
+  cleanup upon program exit.
+
+  #define MAX_POOL_ENTRIES 100
+  #define MINIMUM_MORECORE_SIZE  (64 * 1024U)
+  static int next_os_pool;
+  void *our_os_pools[MAX_POOL_ENTRIES];
+
+  void *osMoreCore(int size)
+  {
+    void *ptr = 0;
+    static void *sbrk_top = 0;
+
+    if (size > 0)
+    {
+      if (size < MINIMUM_MORECORE_SIZE)
+         size = MINIMUM_MORECORE_SIZE;
+      if (CurrentExecutionLevel() == kTaskLevel)
+         ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0);
+      if (ptr == 0)
+      {
+        return (void *) MFAIL;
+      }
+      // save ptrs so they can be freed during cleanup
+      our_os_pools[next_os_pool] = ptr;
+      next_os_pool++;
+      ptr = (void *) ((((size_t) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK);
+      sbrk_top = (char *) ptr + size;
+      return ptr;
+    }
+    else if (size < 0)
+    {
+      // we don't currently support shrink behavior
+      return (void *) MFAIL;
+    }
+    else
+    {
+      return sbrk_top;
+    }
+  }
+
+  // cleanup any allocated memory pools
+  // called as last thing before shutting down driver
+
+  void osCleanupMem(void)
+  {
+    void **ptr;
+
+    for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++)
+      if (*ptr)
+      {
+         PoolDeallocate(*ptr);
+         *ptr = 0;
+      }
+  }
+
+*/
+
+
+/* -----------------------------------------------------------------------
+History:
+    v2.8.6 Wed Aug 29 06:57:58 2012  Doug Lea
+      * fix bad comparison in dlposix_memalign
+      * don't reuse adjusted asize in sys_alloc
+      * add LOCK_AT_FORK -- thanks to Kirill Artamonov for the suggestion
+      * reduce compiler warnings -- thanks to all who reported/suggested these
+
+    v2.8.5 Sun May 22 10:26:02 2011  Doug Lea  (dl at gee)
+      * Always perform unlink checks unless INSECURE
+      * Add posix_memalign.
+      * Improve realloc to expand in more cases; expose realloc_in_place.
+        Thanks to Peter Buhr for the suggestion.
+      * Add footprint_limit, inspect_all, bulk_free. Thanks
+        to Barry Hayes and others for the suggestions.
+      * Internal refactorings to avoid calls while holding locks
+      * Use non-reentrant locks by default. Thanks to Roland McGrath
+        for the suggestion.
+      * Small fixes to mspace_destroy, reset_on_error.
+      * Various configuration extensions/changes. Thanks
+         to all who contributed these.
+
+    V2.8.4a Thu Apr 28 14:39:43 2011 (dl at gee.cs.oswego.edu)
+      * Update Creative Commons URL
+
+    V2.8.4 Wed May 27 09:56:23 2009  Doug Lea  (dl at gee)
+      * Use zeros instead of prev foot for is_mmapped
+      * Add mspace_track_large_chunks; thanks to Jean Brouwers
+      * Fix set_inuse in internal_realloc; thanks to Jean Brouwers
+      * Fix insufficient sys_alloc padding when using 16byte alignment
+      * Fix bad error check in mspace_footprint
+      * Adaptations for ptmalloc; thanks to Wolfram Gloger.
+      * Reentrant spin locks; thanks to Earl Chew and others
+      * Win32 improvements; thanks to Niall Douglas and Earl Chew
+      * Add NO_SEGMENT_TRAVERSAL and MAX_RELEASE_CHECK_RATE options
+      * Extension hook in malloc_state
+      * Various small adjustments to reduce warnings on some compilers
+      * Various configuration extensions/changes for more platforms. Thanks
+         to all who contributed these.
+
+    V2.8.3 Thu Sep 22 11:16:32 2005  Doug Lea  (dl at gee)
+      * Add max_footprint functions
+      * Ensure all appropriate literals are size_t
+      * Fix conditional compilation problem for some #define settings
+      * Avoid concatenating segments with the one provided
+        in create_mspace_with_base
+      * Rename some variables to avoid compiler shadowing warnings
+      * Use explicit lock initialization.
+      * Better handling of sbrk interference.
+      * Simplify and fix segment insertion, trimming and mspace_destroy
+      * Reinstate REALLOC_ZERO_BYTES_FREES option from 2.7.x
+      * Thanks especially to Dennis Flanagan for help on these.
+
+    V2.8.2 Sun Jun 12 16:01:10 2005  Doug Lea  (dl at gee)
+      * Fix memalign brace error.
+
+    V2.8.1 Wed Jun  8 16:11:46 2005  Doug Lea  (dl at gee)
+      * Fix improper #endif nesting in C++
+      * Add explicit casts needed for C++
+
+    V2.8.0 Mon May 30 14:09:02 2005  Doug Lea  (dl at gee)
+      * Use trees for large bins
+      * Support mspaces
+      * Use segments to unify sbrk-based and mmap-based system allocation,
+        removing need for emulation on most platforms without sbrk.
+      * Default safety checks
+      * Optional footer checks. Thanks to William Robertson for the idea.
+      * Internal code refactoring
+      * Incorporate suggestions and platform-specific changes.
+        Thanks to Dennis Flanagan, Colin Plumb, Niall Douglas,
+        Aaron Bachmann,  Emery Berger, and others.
+      * Speed up non-fastbin processing enough to remove fastbins.
+      * Remove useless cfree() to avoid conflicts with other apps.
+      * Remove internal memcpy, memset. Compilers handle builtins better.
+      * Remove some options that no one ever used and rename others.
+
+    V2.7.2 Sat Aug 17 09:07:30 2002  Doug Lea  (dl at gee)
+      * Fix malloc_state bitmap array misdeclaration
+
+    V2.7.1 Thu Jul 25 10:58:03 2002  Doug Lea  (dl at gee)
+      * Allow tuning of FIRST_SORTED_BIN_SIZE
+      * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte.
+      * Better detection and support for non-contiguousness of MORECORE.
+        Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger
+      * Bypass most of malloc if no frees. Thanks To Emery Berger.
+      * Fix freeing of old top non-contiguous chunk im sysmalloc.
+      * Raised default trim and map thresholds to 256K.
+      * Fix mmap-related #defines. Thanks to Lubos Lunak.
+      * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield.
+      * Branch-free bin calculation
+      * Default trim and mmap thresholds now 256K.
+
+    V2.7.0 Sun Mar 11 14:14:06 2001  Doug Lea  (dl at gee)
+      * Introduce independent_comalloc and independent_calloc.
+        Thanks to Michael Pachos for motivation and help.
+      * Make optional .h file available
+      * Allow > 2GB requests on 32bit systems.
+      * new WIN32 sbrk, mmap, munmap, lock code from <Walter@GeNeSys-e.de>.
+        Thanks also to Andreas Mueller <a.mueller at paradatec.de>,
+        and Anonymous.
+      * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for
+        helping test this.)
+      * memalign: check alignment arg
+      * realloc: don't try to shift chunks backwards, since this
+        leads to  more fragmentation in some programs and doesn't
+        seem to help in any others.
+      * Collect all cases in malloc requiring system memory into sysmalloc
+      * Use mmap as backup to sbrk
+      * Place all internal state in malloc_state
+      * Introduce fastbins (although similar to 2.5.1)
+      * Many minor tunings and cosmetic improvements
+      * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK
+      * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS
+        Thanks to Tony E. Bennett <tbennett@nvidia.com> and others.
+      * Include errno.h to support default failure action.
+
+    V2.6.6 Sun Dec  5 07:42:19 1999  Doug Lea  (dl at gee)
+      * return null for negative arguments
+      * Added Several WIN32 cleanups from Martin C. Fong <mcfong at yahoo.com>
+         * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h'
+          (e.g. WIN32 platforms)
+         * Cleanup header file inclusion for WIN32 platforms
+         * Cleanup code to avoid Microsoft Visual C++ compiler complaints
+         * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing
+           memory allocation routines
+         * Set 'malloc_getpagesize' for WIN32 platforms (needs more work)
+         * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to
+           usage of 'assert' in non-WIN32 code
+         * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to
+           avoid infinite loop
+      * Always call 'fREe()' rather than 'free()'
+
+    V2.6.5 Wed Jun 17 15:57:31 1998  Doug Lea  (dl at gee)
+      * Fixed ordering problem with boundary-stamping
+
+    V2.6.3 Sun May 19 08:17:58 1996  Doug Lea  (dl at gee)
+      * Added pvalloc, as recommended by H.J. Liu
+      * Added 64bit pointer support mainly from Wolfram Gloger
+      * Added anonymously donated WIN32 sbrk emulation
+      * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen
+      * malloc_extend_top: fix mask error that caused wastage after
+        foreign sbrks
+      * Add linux mremap support code from HJ Liu
+
+    V2.6.2 Tue Dec  5 06:52:55 1995  Doug Lea  (dl at gee)
+      * Integrated most documentation with the code.
+      * Add support for mmap, with help from
+        Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
+      * Use last_remainder in more cases.
+      * Pack bins using idea from  colin@nyx10.cs.du.edu
+      * Use ordered bins instead of best-fit threshhold
+      * Eliminate block-local decls to simplify tracing and debugging.
+      * Support another case of realloc via move into top
+      * Fix error occuring when initial sbrk_base not word-aligned.
+      * Rely on page size for units instead of SBRK_UNIT to
+        avoid surprises about sbrk alignment conventions.
+      * Add mallinfo, mallopt. Thanks to Raymond Nijssen
+        (raymond@es.ele.tue.nl) for the suggestion.
+      * Add `pad' argument to malloc_trim and top_pad mallopt parameter.
+      * More precautions for cases where other routines call sbrk,
+        courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
+      * Added macros etc., allowing use in linux libc from
+        H.J. Lu (hjl@gnu.ai.mit.edu)
+      * Inverted this history list
+
+    V2.6.1 Sat Dec  2 14:10:57 1995  Doug Lea  (dl at gee)
+      * Re-tuned and fixed to behave more nicely with V2.6.0 changes.
+      * Removed all preallocation code since under current scheme
+        the work required to undo bad preallocations exceeds
+        the work saved in good cases for most test programs.
+      * No longer use return list or unconsolidated bins since
+        no scheme using them consistently outperforms those that don't
+        given above changes.
+      * Use best fit for very large chunks to prevent some worst-cases.
+      * Added some support for debugging
+
+    V2.6.0 Sat Nov  4 07:05:23 1995  Doug Lea  (dl at gee)
+      * Removed footers when chunks are in use. Thanks to
+        Paul Wilson (wilson@cs.texas.edu) for the suggestion.
+
+    V2.5.4 Wed Nov  1 07:54:51 1995  Doug Lea  (dl at gee)
+      * Added malloc_trim, with help from Wolfram Gloger
+        (wmglo@Dent.MED.Uni-Muenchen.DE).
+
+    V2.5.3 Tue Apr 26 10:16:01 1994  Doug Lea  (dl at g)
+
+    V2.5.2 Tue Apr  5 16:20:40 1994  Doug Lea  (dl at g)
+      * realloc: try to expand in both directions
+      * malloc: swap order of clean-bin strategy;
+      * realloc: only conditionally expand backwards
+      * Try not to scavenge used bins
+      * Use bin counts as a guide to preallocation
+      * Occasionally bin return list chunks in first scan
+      * Add a few optimizations from colin@nyx10.cs.du.edu
+
+    V2.5.1 Sat Aug 14 15:40:43 1993  Doug Lea  (dl at g)
+      * faster bin computation & slightly different binning
+      * merged all consolidations to one part of malloc proper
+         (eliminating old malloc_find_space & malloc_clean_bin)
+      * Scan 2 returns chunks (not just 1)
+      * Propagate failure in realloc if malloc returns 0
+      * Add stuff to allow compilation on non-ANSI compilers
+          from kpv@research.att.com
+
+    V2.5 Sat Aug  7 07:41:59 1993  Doug Lea  (dl at g.oswego.edu)
+      * removed potential for odd address access in prev_chunk
+      * removed dependency on getpagesize.h
+      * misc cosmetics and a bit more internal documentation
+      * anticosmetics: mangled names in macros to evade debugger strangeness
+      * tested on sparc, hp-700, dec-mips, rs6000
+          with gcc & native cc (hp, dec only) allowing
+          Detlefs & Zorn comparison study (in SIGPLAN Notices.)
+
+    Trial version Fri Aug 28 13:14:29 1992  Doug Lea  (dl at g.oswego.edu)
+      * Based loosely on libg++-1.2X malloc. (It retains some of the overall
+         structure of old version,  but most details differ.)
+
+*/
+
+#endif /* !HAVE_MALLOC */
+
+#ifdef HAVE_MALLOC
+static void * SDLCALL real_malloc(size_t s) { return malloc(s); }
+static void * SDLCALL real_calloc(size_t n, size_t s) { return calloc(n, s); }
+static void * SDLCALL real_realloc(void *p, size_t s) { return realloc(p,s); }
+static void   SDLCALL real_free(void *p) { free(p); }
+#else
+#define real_malloc dlmalloc
+#define real_calloc dlcalloc
+#define real_realloc dlrealloc
+#define real_free dlfree
+#endif
+
+// mark the allocator entry points as KEEPALIVE so we can call these from JavaScript.
+// otherwise they could could get so aggressively inlined that their symbols
+// don't exist at all in the final binary!
+#ifdef SDL_PLATFORM_EMSCRIPTEN
+#include <emscripten/emscripten.h>
+extern SDL_DECLSPEC SDL_MALLOC EMSCRIPTEN_KEEPALIVE void * SDLCALL SDL_malloc(size_t size);
+extern SDL_DECLSPEC SDL_MALLOC SDL_ALLOC_SIZE2(1, 2) EMSCRIPTEN_KEEPALIVE void * SDLCALL SDL_calloc(size_t nmemb, size_t size);
+extern SDL_DECLSPEC SDL_ALLOC_SIZE(2) EMSCRIPTEN_KEEPALIVE void * SDLCALL SDL_realloc(void *mem, size_t size);
+extern SDL_DECLSPEC EMSCRIPTEN_KEEPALIVE void SDLCALL SDL_free(void *mem);
+#endif
+
+/* Memory functions used by SDL that can be replaced by the application */
+static struct
+{
+    SDL_malloc_func malloc_func;
+    SDL_calloc_func calloc_func;
+    SDL_realloc_func realloc_func;
+    SDL_free_func free_func;
+    SDL_AtomicInt num_allocations;
+} s_mem = {
+    real_malloc, real_calloc, real_realloc, real_free, { 0 }
+};
+
+// Define this if you want to track the number of allocations active
+// #define SDL_TRACK_ALLOCATION_COUNT
+#ifdef SDL_TRACK_ALLOCATION_COUNT
+#define INCREMENT_ALLOCATION_COUNT()    (void)SDL_AtomicIncRef(&s_mem.num_allocations)
+#define DECREMENT_ALLOCATION_COUNT()    (void)SDL_AtomicDecRef(&s_mem.num_allocations)
+#else
+#define INCREMENT_ALLOCATION_COUNT()
+#define DECREMENT_ALLOCATION_COUNT()
+#endif
+
+
+void SDL_GetOriginalMemoryFunctions(SDL_malloc_func *malloc_func,
+                                    SDL_calloc_func *calloc_func,
+                                    SDL_realloc_func *realloc_func,
+                                    SDL_free_func *free_func)
+{
+    if (malloc_func) {
+        *malloc_func = real_malloc;
+    }
+    if (calloc_func) {
+        *calloc_func = real_calloc;
+    }
+    if (realloc_func) {
+        *realloc_func = real_realloc;
+    }
+    if (free_func) {
+        *free_func = real_free;
+    }
+}
+
+void SDL_GetMemoryFunctions(SDL_malloc_func *malloc_func,
+                            SDL_calloc_func *calloc_func,
+                            SDL_realloc_func *realloc_func,
+                            SDL_free_func *free_func)
+{
+    if (malloc_func) {
+        *malloc_func = s_mem.malloc_func;
+    }
+    if (calloc_func) {
+        *calloc_func = s_mem.calloc_func;
+    }
+    if (realloc_func) {
+        *realloc_func = s_mem.realloc_func;
+    }
+    if (free_func) {
+        *free_func = s_mem.free_func;
+    }
+}
+
+bool SDL_SetMemoryFunctions(SDL_malloc_func malloc_func,
+                                SDL_calloc_func calloc_func,
+                                SDL_realloc_func realloc_func,
+                                SDL_free_func free_func)
+{
+    if (!malloc_func) {
+        return SDL_InvalidParamError("malloc_func");
+    }
+    if (!calloc_func) {
+        return SDL_InvalidParamError("calloc_func");
+    }
+    if (!realloc_func) {
+        return SDL_InvalidParamError("realloc_func");
+    }
+    if (!free_func) {
+        return SDL_InvalidParamError("free_func");
+    }
+
+    s_mem.malloc_func = malloc_func;
+    s_mem.calloc_func = calloc_func;
+    s_mem.realloc_func = realloc_func;
+    s_mem.free_func = free_func;
+    return true;
+}
+
+int SDL_GetNumAllocations(void)
+{
+#ifdef SDL_TRACK_ALLOCATION_COUNT
+    return SDL_GetAtomicInt(&s_mem.num_allocations);
+#else
+    return -1;
+#endif
+}
+
+void *SDL_malloc(size_t size)
+{
+    void *mem;
+
+    if (!size) {
+        size = 1;
+    }
+
+    mem = s_mem.malloc_func(size);
+    if (mem) {
+        INCREMENT_ALLOCATION_COUNT();
+    } else {
+        SDL_OutOfMemory();
+    }
+
+    return mem;
+}
+
+void *SDL_calloc(size_t nmemb, size_t size)
+{
+    void *mem;
+
+    if (!nmemb || !size) {
+        nmemb = 1;
+        size = 1;
+    }
+
+    mem = s_mem.calloc_func(nmemb, size);
+    if (mem) {
+        INCREMENT_ALLOCATION_COUNT();
+    } else {
+        SDL_OutOfMemory();
+    }
+
+    return mem;
+}
+
+void *SDL_realloc(void *ptr, size_t size)
+{
+    void *mem;
+
+    if (!size) {
+        size = 1;
+    }
+
+    mem = s_mem.realloc_func(ptr, size);
+    if (mem && !ptr) {
+        INCREMENT_ALLOCATION_COUNT();
+    } else if (!mem) {
+        SDL_OutOfMemory();
+    }
+
+    return mem;
+}
+
+void SDL_free(void *ptr)
+{
+    if (!ptr) {
+        return;
+    }
+
+    s_mem.free_func(ptr);
+    DECREMENT_ALLOCATION_COUNT();
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_memcpy.c b/contrib/SDL-3.2.8/src/stdlib/SDL_memcpy.c
new file mode 100644
index 0000000..315edf0
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_memcpy.c
@@ -0,0 +1,101 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+
+#ifdef SDL_memcpy
+#undef SDL_memcpy
+#endif
+#if SDL_DYNAMIC_API
+#define SDL_memcpy SDL_memcpy_REAL
+#endif
+void *SDL_memcpy(SDL_OUT_BYTECAP(len) void *dst, SDL_IN_BYTECAP(len) const void *src, size_t len)
+{
+#if defined(__GNUC__) && (defined(HAVE_LIBC) && HAVE_LIBC)
+    /* Presumably this is well tuned for speed.
+       On my machine this is twice as fast as the C code below.
+     */
+    return __builtin_memcpy(dst, src, len);
+#elif defined(HAVE_MEMCPY)
+    return memcpy(dst, src, len);
+#elif defined(HAVE_BCOPY)
+    bcopy(src, dst, len);
+    return dst;
+#else
+    /* GCC 4.9.0 with -O3 will generate movaps instructions with the loop
+       using Uint32* pointers, so we need to make sure the pointers are
+       aligned before we loop using them.
+     */
+    if (((uintptr_t)src & 0x3) || ((uintptr_t)dst & 0x3)) {
+        // Do an unaligned byte copy
+        Uint8 *srcp1 = (Uint8 *)src;
+        Uint8 *dstp1 = (Uint8 *)dst;
+
+        while (len--) {
+            *dstp1++ = *srcp1++;
+        }
+    } else {
+        size_t left = (len % 4);
+        Uint32 *srcp4, *dstp4;
+        Uint8 *srcp1, *dstp1;
+
+        srcp4 = (Uint32 *)src;
+        dstp4 = (Uint32 *)dst;
+        len /= 4;
+        while (len--) {
+            *dstp4++ = *srcp4++;
+        }
+
+        srcp1 = (Uint8 *)srcp4;
+        dstp1 = (Uint8 *)dstp4;
+        switch (left) {
+        case 3:
+            *dstp1++ = *srcp1++;
+            SDL_FALLTHROUGH;
+        case 2:
+            *dstp1++ = *srcp1++;
+            SDL_FALLTHROUGH;
+        case 1:
+            *dstp1++ = *srcp1++;
+        }
+    }
+    return dst;
+#endif // HAVE_MEMCPY
+}
+
+/* The optimizer on Visual Studio 2005 and later generates memcpy() and memset() calls.
+   We will provide our own implementation if we're not building with a C runtime. */
+#ifndef HAVE_LIBC
+// NOLINTNEXTLINE(readability-redundant-declaration)
+extern void *memcpy(void *dst, const void *src, size_t len);
+#if defined(_MSC_VER) && !defined(__INTEL_LLVM_COMPILER)
+#pragma intrinsic(memcpy)
+#endif
+
+#if defined(_MSC_VER) && !defined(__clang__)
+#pragma function(memcpy)
+#endif
+// NOLINTNEXTLINE(readability-inconsistent-declaration-parameter-name)
+void *memcpy(void *dst, const void *src, size_t len)
+{
+    return SDL_memcpy(dst, src, len);
+}
+#endif // !HAVE_LIBC
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_memmove.c b/contrib/SDL-3.2.8/src/stdlib/SDL_memmove.c
new file mode 100644
index 0000000..4e0d26c
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_memmove.c
@@ -0,0 +1,73 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+
+#ifdef SDL_memmove
+#undef SDL_memmove
+#endif
+#if SDL_DYNAMIC_API
+#define SDL_memmove SDL_memmove_REAL
+#endif
+void *SDL_memmove(SDL_OUT_BYTECAP(len) void *dst, SDL_IN_BYTECAP(len) const void *src, size_t len)
+{
+#if defined(__GNUC__) && (defined(HAVE_LIBC) && HAVE_LIBC)
+    // Presumably this is well tuned for speed.
+    return __builtin_memmove(dst, src, len);
+#elif defined(HAVE_MEMMOVE)
+    return memmove(dst, src, len);
+#else
+    char *srcp = (char *)src;
+    char *dstp = (char *)dst;
+
+    if (src < dst) {
+        srcp += len - 1;
+        dstp += len - 1;
+        while (len--) {
+            *dstp-- = *srcp--;
+        }
+    } else {
+        while (len--) {
+            *dstp++ = *srcp++;
+        }
+    }
+    return dst;
+#endif // HAVE_MEMMOVE
+}
+
+
+#ifndef HAVE_LIBC
+// NOLINTNEXTLINE(readability-redundant-declaration)
+extern void *memmove(void *dst, const void *src, size_t len);
+#if defined(_MSC_VER) && !defined(__INTEL_LLVM_COMPILER)
+#pragma intrinsic(memmove)
+#endif
+
+#if defined(_MSC_VER) && !defined(__clang__)
+#pragma function(memmove)
+#endif
+// NOLINTNEXTLINE(readability-inconsistent-declaration-parameter-name)
+void *memmove(void *dst, const void *src, size_t len)
+{
+    return SDL_memmove(dst, src, len);
+}
+#endif // !HAVE_LIBC
+
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_memset.c b/contrib/SDL-3.2.8/src/stdlib/SDL_memset.c
new file mode 100644
index 0000000..324f917
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_memset.c
@@ -0,0 +1,139 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+
+#ifdef SDL_memset
+#undef SDL_memset
+#endif
+#if SDL_DYNAMIC_API
+#define SDL_memset SDL_memset_REAL
+#endif
+void *SDL_memset(SDL_OUT_BYTECAP(len) void *dst, int c, size_t len)
+{
+#if defined(__GNUC__) && (defined(HAVE_LIBC) && HAVE_LIBC)
+    return __builtin_memset(dst, c, len);
+#elif defined(HAVE_MEMSET)
+    return memset(dst, c, len);
+#else
+    size_t left;
+    Uint32 *dstp4;
+    Uint8 *dstp1 = (Uint8 *)dst;
+    Uint8 value1;
+    Uint32 value4;
+
+    // The value used in memset() is a byte, passed as an int
+    c &= 0xff;
+
+    /* The destination pointer needs to be aligned on a 4-byte boundary to
+     * execute a 32-bit set. Set first bytes manually if needed until it is
+     * aligned. */
+    value1 = (Uint8)c;
+    while ((uintptr_t)dstp1 & 0x3) {
+        if (len--) {
+            *dstp1++ = value1;
+        } else {
+            return dst;
+        }
+    }
+
+    value4 = ((Uint32)c | ((Uint32)c << 8) | ((Uint32)c << 16) | ((Uint32)c << 24));
+    dstp4 = (Uint32 *)dstp1;
+    left = (len % 4);
+    len /= 4;
+    while (len--) {
+        *dstp4++ = value4;
+    }
+
+    dstp1 = (Uint8 *)dstp4;
+    switch (left) {
+    case 3:
+        *dstp1++ = value1;
+        SDL_FALLTHROUGH;
+    case 2:
+        *dstp1++ = value1;
+        SDL_FALLTHROUGH;
+    case 1:
+        *dstp1++ = value1;
+    }
+
+    return dst;
+#endif // HAVE_MEMSET
+}
+
+// Note that memset() is a byte assignment and this is a 32-bit assignment, so they're not directly equivalent.
+void *SDL_memset4(void *dst, Uint32 val, size_t dwords)
+{
+#if defined(__APPLE__) && defined(HAVE_STRING_H)
+    memset_pattern4(dst, &val, dwords * 4);
+#elif defined(__GNUC__) && defined(__i386__)
+    int u0, u1, u2;
+    __asm__ __volatile__(
+        "cld \n\t"
+        "rep ; stosl \n\t"
+        : "=&D"(u0), "=&a"(u1), "=&c"(u2)
+        : "0"(dst), "1"(val), "2"(SDL_static_cast(Uint32, dwords))
+        : "memory");
+#else
+    size_t _n = (dwords + 3) / 4;
+    Uint32 *_p = SDL_static_cast(Uint32 *, dst);
+    Uint32 _val = (val);
+    if (dwords == 0) {
+        return dst;
+    }
+    switch (dwords % 4) {
+    case 0:
+        do {
+            *_p++ = _val;
+            SDL_FALLTHROUGH;
+        case 3:
+            *_p++ = _val;
+            SDL_FALLTHROUGH;
+        case 2:
+            *_p++ = _val;
+            SDL_FALLTHROUGH;
+        case 1:
+            *_p++ = _val;
+        } while (--_n);
+    }
+#endif
+    return dst;
+}
+
+/* The optimizer on Visual Studio 2005 and later generates memcpy() and memset() calls.
+   We will provide our own implementation if we're not building with a C runtime. */
+#ifndef HAVE_LIBC
+// NOLINTNEXTLINE(readability-redundant-declaration)
+extern void *memset(void *dst, int c, size_t len);
+#if defined(_MSC_VER) && !defined(__INTEL_LLVM_COMPILER)
+#pragma intrinsic(memset)
+#endif
+
+#if defined(_MSC_VER) && !defined(__clang__)
+#pragma function(memset)
+#endif
+// NOLINTNEXTLINE(readability-inconsistent-declaration-parameter-name)
+void *memset(void *dst, int c, size_t len)
+{
+    return SDL_memset(dst, c, len);
+}
+#endif // !HAVE_LIBC
+
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc.c b/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc.c
new file mode 100644
index 0000000..6698403
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc.c
@@ -0,0 +1,746 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+// This file contains SDL replacements for functions in the C library
+
+#if !defined(HAVE_LIBC) && !defined(SDL_STATIC_LIB)
+
+// These are some C runtime intrinsics that need to be defined
+
+#ifdef _MSC_VER
+
+#ifndef __FLTUSED__
+#define __FLTUSED__
+__declspec(selectany) int _fltused = 1;
+#endif
+
+#ifdef _M_IX86
+
+// Float to long
+void __declspec(naked) _ftol()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        ebp
+        mov         ebp,esp
+        sub         esp,20h
+        and         esp,0FFFFFFF0h
+        fld         st(0)
+        fst         dword ptr [esp+18h]
+        fistp       qword ptr [esp+10h]
+        fild        qword ptr [esp+10h]
+        mov         edx,dword ptr [esp+18h]
+        mov         eax,dword ptr [esp+10h]
+        test        eax,eax
+        je          integer_QnaN_or_zero
+arg_is_not_integer_QnaN:
+        fsubp       st(1),st
+        test        edx,edx
+        jns         positive
+        fstp        dword ptr [esp]
+        mov         ecx,dword ptr [esp]
+        xor         ecx,80000000h
+        add         ecx,7FFFFFFFh
+        adc         eax,0
+        mov         edx,dword ptr [esp+14h]
+        adc         edx,0
+        jmp         localexit
+positive:
+        fstp        dword ptr [esp]
+        mov         ecx,dword ptr [esp]
+        add         ecx,7FFFFFFFh
+        sbb         eax,0
+        mov         edx,dword ptr [esp+14h]
+        sbb         edx,0
+        jmp         localexit
+integer_QnaN_or_zero:
+        mov         edx,dword ptr [esp+14h]
+        test        edx,7FFFFFFFh
+        jne         arg_is_not_integer_QnaN
+        fstp        dword ptr [esp+18h]
+        fstp        dword ptr [esp+18h]
+localexit:
+        leave
+        ret
+    }
+    /* *INDENT-ON* */
+}
+
+void _ftol2_sse()
+{
+    _ftol();
+}
+
+void _ftol2()
+{
+    _ftol();
+}
+
+// 64-bit math operators for 32-bit systems
+void __declspec(naked) _allmul()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        mov         eax, dword ptr[esp+8]
+        mov         ecx, dword ptr[esp+10h]
+        or          ecx, eax
+        mov         ecx, dword ptr[esp+0Ch]
+        jne         hard
+        mov         eax, dword ptr[esp+4]
+        mul         ecx
+        ret         10h
+hard:
+        push        ebx
+        mul         ecx
+        mov         ebx, eax
+        mov         eax, dword ptr[esp+8]
+        mul         dword ptr[esp+14h]
+        add         ebx, eax
+        mov         eax, dword ptr[esp+8]
+        mul         ecx
+        add         edx, ebx
+        pop         ebx
+        ret         10h
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _alldiv()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        edi
+        push        esi
+        push        ebx
+        xor         edi,edi
+        mov         eax,dword ptr [esp+14h]
+        or          eax,eax
+        jge         L1
+        inc         edi
+        mov         edx,dword ptr [esp+10h]
+        neg         eax
+        neg         edx
+        sbb         eax,0
+        mov         dword ptr [esp+14h],eax
+        mov         dword ptr [esp+10h],edx
+L1:
+        mov         eax,dword ptr [esp+1Ch]
+        or          eax,eax
+        jge         L2
+        inc         edi
+        mov         edx,dword ptr [esp+18h]
+        neg         eax
+        neg         edx
+        sbb         eax,0
+        mov         dword ptr [esp+1Ch],eax
+        mov         dword ptr [esp+18h],edx
+L2:
+        or          eax,eax
+        jne         L3
+        mov         ecx,dword ptr [esp+18h]
+        mov         eax,dword ptr [esp+14h]
+        xor         edx,edx
+        div         ecx
+        mov         ebx,eax
+        mov         eax,dword ptr [esp+10h]
+        div         ecx
+        mov         edx,ebx
+        jmp         L4
+L3:
+        mov         ebx,eax
+        mov         ecx,dword ptr [esp+18h]
+        mov         edx,dword ptr [esp+14h]
+        mov         eax,dword ptr [esp+10h]
+L5:
+        shr         ebx,1
+        rcr         ecx,1
+        shr         edx,1
+        rcr         eax,1
+        or          ebx,ebx
+        jne         L5
+        div         ecx
+        mov         esi,eax
+        mul         dword ptr [esp+1Ch]
+        mov         ecx,eax
+        mov         eax,dword ptr [esp+18h]
+        mul         esi
+        add         edx,ecx
+        jb          L6
+        cmp         edx,dword ptr [esp+14h]
+        ja          L6
+        jb          L7
+        cmp         eax,dword ptr [esp+10h]
+        jbe         L7
+L6:
+        dec         esi
+L7:
+        xor         edx,edx
+        mov         eax,esi
+L4:
+        dec         edi
+        jne         L8
+        neg         edx
+        neg         eax
+        sbb         edx,0
+L8:
+        pop         ebx
+        pop         esi
+        pop         edi
+        ret         10h
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _aulldiv()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        ebx
+        push        esi
+        mov         eax,dword ptr [esp+18h]
+        or          eax,eax
+        jne         L1
+        mov         ecx,dword ptr [esp+14h]
+        mov         eax,dword ptr [esp+10h]
+        xor         edx,edx
+        div         ecx
+        mov         ebx,eax
+        mov         eax,dword ptr [esp+0Ch]
+        div         ecx
+        mov         edx,ebx
+        jmp         L2
+L1:
+        mov         ecx,eax
+        mov         ebx,dword ptr [esp+14h]
+        mov         edx,dword ptr [esp+10h]
+        mov         eax,dword ptr [esp+0Ch]
+L3:
+        shr         ecx,1
+        rcr         ebx,1
+        shr         edx,1
+        rcr         eax,1
+        or          ecx,ecx
+        jne         L3
+        div         ebx
+        mov         esi,eax
+        mul         dword ptr [esp+18h]
+        mov         ecx,eax
+        mov         eax,dword ptr [esp+14h]
+        mul         esi
+        add         edx,ecx
+        jb          L4
+        cmp         edx,dword ptr [esp+10h]
+        ja          L4
+        jb          L5
+        cmp         eax,dword ptr [esp+0Ch]
+        jbe         L5
+L4:
+        dec         esi
+L5:
+        xor         edx,edx
+        mov         eax,esi
+L2:
+        pop         esi
+        pop         ebx
+        ret         10h
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _allrem()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        ebx
+        push        edi
+        xor         edi,edi
+        mov         eax,dword ptr [esp+10h]
+        or          eax,eax
+        jge         L1
+        inc         edi
+        mov         edx,dword ptr [esp+0Ch]
+        neg         eax
+        neg         edx
+        sbb         eax,0
+        mov         dword ptr [esp+10h],eax
+        mov         dword ptr [esp+0Ch],edx
+L1:
+        mov         eax,dword ptr [esp+18h]
+        or          eax,eax
+        jge         L2
+        mov         edx,dword ptr [esp+14h]
+        neg         eax
+        neg         edx
+        sbb         eax,0
+        mov         dword ptr [esp+18h],eax
+        mov         dword ptr [esp+14h],edx
+L2:
+        or          eax,eax
+        jne         L3
+        mov         ecx,dword ptr [esp+14h]
+        mov         eax,dword ptr [esp+10h]
+        xor         edx,edx
+        div         ecx
+        mov         eax,dword ptr [esp+0Ch]
+        div         ecx
+        mov         eax,edx
+        xor         edx,edx
+        dec         edi
+        jns         L4
+        jmp         L8
+L3:
+        mov         ebx,eax
+        mov         ecx,dword ptr [esp+14h]
+        mov         edx,dword ptr [esp+10h]
+        mov         eax,dword ptr [esp+0Ch]
+L5:
+        shr         ebx,1
+        rcr         ecx,1
+        shr         edx,1
+        rcr         eax,1
+        or          ebx,ebx
+        jne         L5
+        div         ecx
+        mov         ecx,eax
+        mul         dword ptr [esp+18h]
+        xchg        eax,ecx
+        mul         dword ptr [esp+14h]
+        add         edx,ecx
+        jb          L6
+        cmp         edx,dword ptr [esp+10h]
+        ja          L6
+        jb          L7
+        cmp         eax,dword ptr [esp+0Ch]
+        jbe         L7
+L6:
+        sub         eax,dword ptr [esp+14h]
+        sbb         edx,dword ptr [esp+18h]
+L7:
+        sub         eax,dword ptr [esp+0Ch]
+        sbb         edx,dword ptr [esp+10h]
+        dec         edi
+        jns         L8
+L4:
+        neg         edx
+        neg         eax
+        sbb         edx,0
+L8:
+        pop         edi
+        pop         ebx
+        ret         10h
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _aullrem()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        ebx
+        mov         eax,dword ptr [esp+14h]
+        or          eax,eax
+        jne         L1
+        mov         ecx,dword ptr [esp+10h]
+        mov         eax,dword ptr [esp+0Ch]
+        xor         edx,edx
+        div         ecx
+        mov         eax,dword ptr [esp+8]
+        div         ecx
+        mov         eax,edx
+        xor         edx,edx
+        jmp         L2
+L1:
+        mov         ecx,eax
+        mov         ebx,dword ptr [esp+10h]
+        mov         edx,dword ptr [esp+0Ch]
+        mov         eax,dword ptr [esp+8]
+L3:
+        shr         ecx,1
+        rcr         ebx,1
+        shr         edx,1
+        rcr         eax,1
+        or          ecx,ecx
+        jne         L3
+        div         ebx
+        mov         ecx,eax
+        mul         dword ptr [esp+14h]
+        xchg        eax,ecx
+        mul         dword ptr [esp+10h]
+        add         edx,ecx
+        jb          L4
+        cmp         edx,dword ptr [esp+0Ch]
+        ja          L4
+        jb          L5
+        cmp         eax,dword ptr [esp+8]
+        jbe         L5
+L4:
+        sub         eax,dword ptr [esp+10h]
+        sbb         edx,dword ptr [esp+14h]
+L5:
+        sub         eax,dword ptr [esp+8]
+        sbb         edx,dword ptr [esp+0Ch]
+        neg         edx
+        neg         eax
+        sbb         edx,0
+L2:
+        pop         ebx
+        ret         10h
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _alldvrm()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        edi
+        push        esi
+        push        ebp
+        xor         edi,edi
+        xor         ebp,ebp
+        mov         eax,dword ptr [esp+14h]
+        or          eax,eax
+        jge         L1
+        inc         edi
+        inc         ebp
+        mov         edx,dword ptr [esp+10h]
+        neg         eax
+        neg         edx
+        sbb         eax,0
+        mov         dword ptr [esp+14h],eax
+        mov         dword ptr [esp+10h],edx
+L1:
+        mov         eax,dword ptr [esp+1Ch]
+        or          eax,eax
+        jge         L2
+        inc         edi
+        mov         edx,dword ptr [esp+18h]
+        neg         eax
+        neg         edx
+        sbb         eax,0
+        mov         dword ptr [esp+1Ch],eax
+        mov         dword ptr [esp+18h],edx
+L2:
+        or          eax,eax
+        jne         L3
+        mov         ecx,dword ptr [esp+18h]
+        mov         eax,dword ptr [esp+14h]
+        xor         edx,edx
+        div         ecx
+        mov         ebx,eax
+        mov         eax,dword ptr [esp+10h]
+        div         ecx
+        mov         esi,eax
+        mov         eax,ebx
+        mul         dword ptr [esp+18h]
+        mov         ecx,eax
+        mov         eax,esi
+        mul         dword ptr [esp+18h]
+        add         edx,ecx
+        jmp         L4
+L3:
+        mov         ebx,eax
+        mov         ecx,dword ptr [esp+18h]
+        mov         edx,dword ptr [esp+14h]
+        mov         eax,dword ptr [esp+10h]
+L5:
+        shr         ebx,1
+        rcr         ecx,1
+        shr         edx,1
+        rcr         eax,1
+        or          ebx,ebx
+        jne         L5
+        div         ecx
+        mov         esi,eax
+        mul         dword ptr [esp+1Ch]
+        mov         ecx,eax
+        mov         eax,dword ptr [esp+18h]
+        mul         esi
+        add         edx,ecx
+        jb          L6
+        cmp         edx,dword ptr [esp+14h]
+        ja          L6
+        jb          L7
+        cmp         eax,dword ptr [esp+10h]
+        jbe         L7
+L6:
+        dec         esi
+        sub         eax,dword ptr [esp+18h]
+        sbb         edx,dword ptr [esp+1Ch]
+L7:
+        xor         ebx,ebx
+L4:
+        sub         eax,dword ptr [esp+10h]
+        sbb         edx,dword ptr [esp+14h]
+        dec         ebp
+        jns         L9
+        neg         edx
+        neg         eax
+        sbb         edx,0
+L9:
+        mov         ecx,edx
+        mov         edx,ebx
+        mov         ebx,ecx
+        mov         ecx,eax
+        mov         eax,esi
+        dec         edi
+        jne         L8
+        neg         edx
+        neg         eax
+        sbb         edx,0
+L8:
+        pop         ebp
+        pop         esi
+        pop         edi
+        ret         10h
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _aulldvrm()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        esi
+        mov         eax,dword ptr [esp+14h]
+        or          eax,eax
+        jne         L1
+        mov         ecx,dword ptr [esp+10h]
+        mov         eax,dword ptr [esp+0Ch]
+        xor         edx,edx
+        div         ecx
+        mov         ebx,eax
+        mov         eax,dword ptr [esp+8]
+        div         ecx
+        mov         esi,eax
+        mov         eax,ebx
+        mul         dword ptr [esp+10h]
+        mov         ecx,eax
+        mov         eax,esi
+        mul         dword ptr [esp+10h]
+        add         edx,ecx
+        jmp         L2
+L1:
+        mov         ecx,eax
+        mov         ebx,dword ptr [esp+10h]
+        mov         edx,dword ptr [esp+0Ch]
+        mov         eax,dword ptr [esp+8]
+L3:
+        shr         ecx,1
+        rcr         ebx,1
+        shr         edx,1
+        rcr         eax,1
+        or          ecx,ecx
+        jne         L3
+        div         ebx
+        mov         esi,eax
+        mul         dword ptr [esp+14h]
+        mov         ecx,eax
+        mov         eax,dword ptr [esp+10h]
+        mul         esi
+        add         edx,ecx
+        jb          L4
+        cmp         edx,dword ptr [esp+0Ch]
+        ja          L4
+        jb          L5
+        cmp         eax,dword ptr [esp+8]
+        jbe         L5
+L4:
+        dec         esi
+        sub         eax,dword ptr [esp+10h]
+        sbb         edx,dword ptr [esp+14h]
+L5:
+        xor         ebx,ebx
+L2:
+        sub         eax,dword ptr [esp+8]
+        sbb         edx,dword ptr [esp+0Ch]
+        neg         edx
+        neg         eax
+        sbb         edx,0
+        mov         ecx,edx
+        mov         edx,ebx
+        mov         ebx,ecx
+        mov         ecx,eax
+        mov         eax,esi
+        pop         esi
+        ret         10h
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _allshl()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        cmp         cl,40h
+        jae         RETZERO
+        cmp         cl,20h
+        jae         MORE32
+        shld        edx,eax,cl
+        shl         eax,cl
+        ret
+MORE32:
+        mov         edx,eax
+        xor         eax,eax
+        and         cl,1Fh
+        shl         edx,cl
+        ret
+RETZERO:
+        xor         eax,eax
+        xor         edx,edx
+        ret
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _allshr()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        cmp         cl,3Fh
+        jae         RETSIGN
+        cmp         cl,20h
+        jae         MORE32
+        shrd        eax,edx,cl
+        sar         edx,cl
+        ret
+MORE32:
+        mov         eax,edx
+        sar         edx,1Fh
+        and         cl,1Fh
+        sar         eax,cl
+        ret
+RETSIGN:
+        sar         edx,1Fh
+        mov         eax,edx
+        ret
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _aullshr()
+{
+    /* *INDENT-OFF* */
+    __asm {
+        cmp         cl,40h
+        jae         RETZERO
+        cmp         cl,20h
+        jae         MORE32
+        shrd        eax,edx,cl
+        shr         edx,cl
+        ret
+MORE32:
+        mov         eax,edx
+        xor         edx,edx
+        and         cl,1Fh
+        shr         eax,cl
+        ret
+RETZERO:
+        xor         eax,eax
+        xor         edx,edx
+        ret
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _chkstk(void)
+{
+    __asm {
+        push        ecx
+        mov         ecx,esp     ; lea         ecx,dword ptr [esp]+4
+        add         ecx,4
+        sub         ecx,eax
+        sbb         eax,eax
+        not         eax
+        and         ecx,eax
+        mov         eax,esp
+        and         eax,0xfffff000
+L1:
+        cmp         ecx,eax
+        jb          short L2
+        mov         eax,ecx
+        pop         ecx
+        xchg        esp,eax
+        mov         eax,dword ptr [eax]
+        mov         dword ptr [esp],eax
+        ret
+L2:
+        sub         eax,0x1000
+        test        dword ptr [eax],eax
+        jmp         short L1
+    }
+}
+
+void __declspec(naked) _alloca_probe_8(void)
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        ecx
+        mov         ecx,esp     ; lea         ecx,dword ptr [esp]+8
+        add         ecx,8
+        sub         ecx,eax
+        and         ecx,0x7
+        add         eax,ecx
+        sbb         ecx,ecx
+        or          eax,ecx
+        pop         ecx
+        jmp         _chkstk
+    }
+    /* *INDENT-ON* */
+}
+
+void __declspec(naked) _alloca_probe_16(void)
+{
+    /* *INDENT-OFF* */
+    __asm {
+        push        ecx
+        mov         ecx,esp     ; lea         ecx,dword ptr [esp]+8
+        add         ecx,8
+        sub         ecx,eax
+        and         ecx,0xf
+        add         eax,ecx
+        sbb         ecx,ecx
+        or          eax,ecx
+        pop         ecx
+        jmp         _chkstk
+    }
+    /* *INDENT-ON* */
+}
+
+#endif // _M_IX86
+
+#endif // MSC_VER
+
+#ifdef __ICL
+/* The classic Intel compiler generates calls to _intel_fast_memcpy
+ * and _intel_fast_memset when building an optimized SDL library */
+void *_intel_fast_memcpy(void *dst, const void *src, size_t len)
+{
+    return SDL_memcpy(dst, src, len);
+}
+void *_intel_fast_memset(void *dst, int c, size_t len)
+{
+    return SDL_memset(dst, c, len);
+}
+#endif
+
+#endif // !HAVE_LIBC && !SDL_STATIC_LIB
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc_arm64.masm b/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc_arm64.masm
new file mode 100644
index 0000000..a769cc1
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc_arm64.masm
@@ -0,0 +1,26 @@
+TeStackLimit EQU 0x00010

+PAGE_SIZE equ 0x1000

+

+    AREA CODE, READONLY

+

+    EXPORT __chkstk

+

+__chkstk PROC

+    ldr                          x17,[x18, #TeStackLimit]

+    subs                         x16,sp,x15, LSL  #0x4

+    csel                         x16,xzr,x16,cc

+    cmp                          x16,x17

+    b.cc                         chkstk_start_loop

+    ret

+chkstk_start_loop

+    and                          x16,x16,#-PAGE_SIZE

+chkstk_loop

+    sub                          x17,x17,#0x1, LSL #12

+    ldr                          xzr,[x17]

+    cmp                          x17,x16

+    b.ne                         chkstk_loop

+    ret

+

+    ENDP

+

+    END

diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc_x64.masm b/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc_x64.masm
new file mode 100644
index 0000000..1590d88
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_mslibc_x64.masm
@@ -0,0 +1,29 @@
+include ksamd64.inc

+

+text        SEGMENT EXECUTE

+

+public      __chkstk

+

+__chkstk:

+    sub         rsp,010h

+    mov         QWORD PTR [rsp],r10

+    mov         QWORD PTR [rsp+08h],r11

+    xor         r11,r11

+    lea         r10,[rsp+018h]

+    sub         r10,rax

+    cmovb       r10,r11

+    mov         r11,QWORD PTR gs:[TeStackLimit]

+    cmp         r10,r11

+    jae         chkstk_finish

+    and         r10w,0f000h

+chkstk_loop:

+    lea         r11,[r11-PAGE_SIZE]

+    mov         BYTE PTR [r11],0h

+    cmp         r10,r11

+    jne         chkstk_loop

+chkstk_finish:

+    mov         r10,QWORD PTR [rsp]

+    mov         r11,QWORD PTR [rsp+08h]

+    add         rsp,010h

+    ret

+end

diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_murmur3.c b/contrib/SDL-3.2.8/src/stdlib/SDL_murmur3.c
new file mode 100644
index 0000000..6b030bd
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_murmur3.c
@@ -0,0 +1,87 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+// Public domain murmur3 32-bit hash algorithm
+//
+// Adapted from: https://en.wikipedia.org/wiki/MurmurHash
+
+static SDL_INLINE Uint32 murmur_32_scramble(Uint32 k)
+{
+    k *= 0xcc9e2d51;
+    k = (k << 15) | (k >> 17);
+    k *= 0x1b873593;
+    return k;
+}
+
+Uint32 SDLCALL SDL_murmur3_32(const void *data, size_t len, Uint32 seed)
+{
+    const Uint8 *bytes = (const Uint8 *)data;
+    Uint32 hash = seed;
+    Uint32 k;
+
+    // Read in groups of 4.
+    if ((((uintptr_t)bytes) & 3) == 0) {
+        // We can do aligned 32-bit reads
+        for (size_t i = len >> 2; i--; ) {
+            k = *(const Uint32 *)bytes;
+            k = SDL_Swap32LE(k);
+            bytes += sizeof(Uint32);
+            hash ^= murmur_32_scramble(k);
+            hash = (hash << 13) | (hash >> 19);
+            hash = hash * 5 + 0xe6546b64;
+        }
+    } else {
+        for (size_t i = len >> 2; i--; ) {
+            SDL_memcpy(&k, bytes, sizeof(Uint32));
+            k = SDL_Swap32LE(k);
+            bytes += sizeof(Uint32);
+            hash ^= murmur_32_scramble(k);
+            hash = (hash << 13) | (hash >> 19);
+            hash = hash * 5 + 0xe6546b64;
+        }
+    }
+
+    // Read the rest.
+    size_t left = (len & 3);
+    if (left) {
+        k = 0;
+        for (size_t i = left; i--; ) {
+            k <<= 8;
+            k |= bytes[i];
+        }
+
+        // A swap is *not* necessary here because the preceding loop already
+        // places the low bytes in the low places according to whatever endianness
+        // we use. Swaps only apply when the memory is copied in a chunk.
+        hash ^= murmur_32_scramble(k);
+    }
+
+    /* Finalize. */
+    hash ^= len;
+    hash ^= hash >> 16;
+    hash *= 0x85ebca6b;
+    hash ^= hash >> 13;
+    hash *= 0xc2b2ae35;
+    hash ^= hash >> 16;
+
+    return hash;
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_qsort.c b/contrib/SDL-3.2.8/src/stdlib/SDL_qsort.c
new file mode 100644
index 0000000..4ed2863
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_qsort.c
@@ -0,0 +1,574 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+// SDL3 always uses its own internal qsort implementation, below, so
+// it can guarantee stable sorts across platforms and not have to
+// tapdance to support the various qsort_r interfaces, or bridge from
+// the C runtime's non-SDLCALL compare functions.
+
+#ifdef assert
+#undef assert
+#endif
+#define assert SDL_assert
+#ifdef malloc
+#undef malloc
+#endif
+#define malloc SDL_malloc
+#ifdef free
+#undef free
+#endif
+#define free SDL_free
+#ifdef memcpy
+#undef memcpy
+#endif
+#define memcpy SDL_memcpy
+#ifdef memmove
+#undef memmove
+#endif
+#define memmove SDL_memmove
+
+/*
+This code came from Gareth McCaughan, under the zlib license.
+Specifically this: https://www.mccaughan.org.uk/software/qsort.c-1.16
+
+Everything below this comment until the HAVE_QSORT #endif was from Gareth
+(any minor changes will be noted inline).
+
+Thank you to Gareth for relicensing this code under the zlib license for our
+benefit!
+
+Update for SDL3: we have modified this from a qsort function to qsort_r.
+
+--ryan.
+*/
+
+/* This is a drop-in replacement for the C library's |qsort()| routine.
+ *
+ * It is intended for use where you know or suspect that your
+ * platform's qsort is bad. If that isn't the case, then you
+ * should probably use the qsort your system gives you in preference
+ * to mine -- it will likely have been tested and tuned better.
+ *
+ * Features:
+ *   - Median-of-three pivoting (and more)
+ *   - Truncation and final polishing by a single insertion sort
+ *   - Early truncation when no swaps needed in pivoting step
+ *   - Explicit recursion, guaranteed not to overflow
+ *   - A few little wrinkles stolen from the GNU |qsort()|.
+ *     (For the avoidance of doubt, no code was stolen, only
+ *     broad ideas.)
+ *   - separate code for non-aligned / aligned / word-size objects
+ *
+ * Earlier releases of this code used an idiosyncratic licence
+ * I wrote myself, because I'm an idiot. The code is now released
+ * under the "zlib/libpng licence"; you will find the actual
+ * terms in the next comment. I request (but do not require)
+ * that if you make any changes beyond the name of the exported
+ * routine and reasonable tweaks to the TRUNC_* and
+ * PIVOT_THRESHOLD values, you modify the _ID string so as
+ * to make it clear that you have changed the code.
+ *
+ * If you find problems with this code, or find ways of
+ * making it significantly faster, please let me know!
+ * My e-mail address, valid as of early 2016 and for the
+ * foreseeable future, is
+ *    gareth.mccaughan@pobox.com
+ * Thanks!
+ *
+ * Gareth McCaughan
+ */
+
+/* Copyright (c) 1998-2021 Gareth McCaughan
+ *
+ * This software is provided 'as-is', without any express or implied
+ * warranty. In no event will the authors be held liable for any
+ * damages arising from the use of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute it
+ * freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented;
+ *    you must not claim that you wrote the original software.
+ *    If you use this software in a product, an acknowledgment
+ *    in the product documentation would be appreciated but
+ *    is not required.
+ *
+ * 2. Altered source versions must be plainly marked as such,
+ *    and must not be misrepresented as being the original software.
+ *
+ * 3. This notice may not be removed or altered from any source
+ *    distribution.
+ */
+
+/* Revision history since release:
+ *   1998-03-19 v1.12 First release I have any records of.
+ *   2007-09-02 v1.13 Fix bug kindly reported by Dan Bodoh
+ *                    (premature termination of recursion).
+ *                    Add a few clarifying comments.
+ *                    Minor improvements to debug output.
+ *   2016-02-21 v1.14 Replace licence with 2-clause BSD,
+ *                    and clarify a couple of things in
+ *                    comments. No code changes.
+ *   2016-03-10 v1.15 Fix bug kindly reported by Ryan Gordon
+ *                    (pre-insertion-sort messed up).
+ *                    Disable DEBUG_QSORT by default.
+ *                    Tweak comments very slightly.
+ *   2021-02-20 v1.16 Fix bug kindly reported by Ray Gardner
+ *                    (error in recursion leading to possible
+ *                    stack overflow).
+ *                    When checking alignment, avoid casting
+ *                    pointer to possibly-smaller integer.
+ */
+
+/* BEGIN SDL CHANGE ... commented this out with an #if 0 block. --ryan. */
+#if 0
+#include <assert.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+#undef DEBUG_QSORT
+
+static char _ID[]="<qsort.c gjm WITH CHANGES FOR SDL3 1.16 2021-02-20>";
+#endif
+/* END SDL CHANGE ... commented this out with an #if 0 block. --ryan. */
+
+/* How many bytes are there per word? (Must be a power of 2,
+ * and must in fact equal sizeof(int).)
+ */
+#define WORD_BYTES sizeof(int)
+
+/* How big does our stack need to be? Answer: one entry per
+ * bit in a |size_t|. (Actually, a bit less because we don't
+ * recurse all the way down to size-1 subarrays.)
+ */
+#define STACK_SIZE (8*sizeof(size_t))
+
+/* Different situations have slightly different requirements,
+ * and we make life epsilon easier by using different truncation
+ * points for the three different cases.
+ * So far, I have tuned TRUNC_words and guessed that the same
+ * value might work well for the other two cases. Of course
+ * what works well on my machine might work badly on yours.
+ */
+#define TRUNC_nonaligned        12
+#define TRUNC_aligned           12
+#define TRUNC_words             12*WORD_BYTES   /* nb different meaning */
+
+/* We use a simple pivoting algorithm for shortish sub-arrays
+ * and a more complicated one for larger ones. The threshold
+ * is PIVOT_THRESHOLD.
+ */
+#define PIVOT_THRESHOLD 40
+
+typedef struct { char * first; char * last; } stack_entry;
+#define pushLeft {stack[stacktop].first=ffirst;stack[stacktop++].last=last;}
+#define pushRight {stack[stacktop].first=first;stack[stacktop++].last=llast;}
+#define doLeft {first=ffirst;llast=last;continue;}
+#define doRight {ffirst=first;last=llast;continue;}
+#define pop {if (--stacktop<0) break;\
+  first=ffirst=stack[stacktop].first;\
+  last=llast=stack[stacktop].last;\
+  continue;}
+
+/* Some comments on the implementation.
+ * 1. When we finish partitioning the array into "low"
+ *    and "high", we forget entirely about short subarrays,
+ *    because they'll be done later by insertion sort.
+ *    Doing lots of little insertion sorts might be a win
+ *    on large datasets for locality-of-reference reasons,
+ *    but it makes the code much nastier and increases
+ *    bookkeeping overhead.
+ * 2. We always save the longer and get to work on the
+ *    shorter. This guarantees that whenever we push
+ *    a k'th entry onto the stack we are about to get
+ *    working on something of size <= N/2^k where N is
+ *    the original array size; so the stack can't need
+ *    more than log_2(max-array-size) entries.
+ * 3. We choose a pivot by looking at the first, last
+ *    and middle elements. We arrange them into order
+ *    because it's easy to do that in conjunction with
+ *    choosing the pivot, and it makes things a little
+ *    easier in the partitioning step. Anyway, the pivot
+ *    is the middle of these three. It's still possible
+ *    to construct datasets where the algorithm takes
+ *    time of order n^2, but it simply never happens in
+ *    practice.
+ * 3' Newsflash: On further investigation I find that
+ *    it's easy to construct datasets where median-of-3
+ *    simply isn't good enough. So on large-ish subarrays
+ *    we do a more sophisticated pivoting: we take three
+ *    sets of 3 elements, find their medians, and then
+ *    take the median of those.
+ * 4. We copy the pivot element to a separate place
+ *    because that way we can always do our comparisons
+ *    directly against a pointer to that separate place,
+ *    and don't have to wonder "did we move the pivot
+ *    element?". This makes the inner loop better.
+ * 5. It's possible to make the pivoting even more
+ *    reliable by looking at more candidates when n
+ *    is larger. (Taking this to its logical conclusion
+ *    results in a variant of quicksort that doesn't
+ *    have that n^2 worst case.) However, the overhead
+ *    from the extra bookkeeping means that it's just
+ *    not worth while.
+ * 6. This is pretty clean and portable code. Here are
+ *    all the potential portability pitfalls and problems
+ *    I know of:
+ *      - In one place (the insertion sort) I construct
+ *        a pointer that points just past the end of the
+ *        supplied array, and assume that (a) it won't
+ *        compare equal to any pointer within the array,
+ *        and (b) it will compare equal to a pointer
+ *        obtained by stepping off the end of the array.
+ *        These might fail on some segmented architectures.
+ *      - I assume that there are 8 bits in a |char| when
+ *        computing the size of stack needed. This would
+ *        fail on machines with 9-bit or 16-bit bytes.
+ *      - I assume that if |((int)base&(sizeof(int)-1))==0|
+ *        and |(size&(sizeof(int)-1))==0| then it's safe to
+ *        get at array elements via |int*|s, and that if
+ *        actually |size==sizeof(int)| as well then it's
+ *        safe to treat the elements as |int|s. This might
+ *        fail on systems that convert pointers to integers
+ *        in non-standard ways.
+ *      - I assume that |8*sizeof(size_t)<=INT_MAX|. This
+ *        would be false on a machine with 8-bit |char|s,
+ *        16-bit |int|s and 4096-bit |size_t|s. :-)
+ */
+
+/* The recursion logic is the same in each case.
+ * We keep chopping up until we reach subarrays of size
+ * strictly less than Trunc; we leave these unsorted. */
+#define Recurse(Trunc)                          \
+      { size_t l=last-ffirst,r=llast-first;     \
+        if (l<Trunc) {                          \
+          if (r>=Trunc) doRight                 \
+          else pop                              \
+        }                                       \
+        else if (l<=r) { pushRight; doLeft }    \
+        else if (r>=Trunc) { pushLeft; doRight }\
+        else doLeft                             \
+      }
+
+/* and so is the pivoting logic (note: last is inclusive): */
+#define Pivot(swapper,sz)                       \
+  if ((size_t)(last-first)>PIVOT_THRESHOLD*sz) mid=pivot_big(first,mid,last,sz,compare,userdata);\
+  else {        \
+    if (compare(userdata,first,mid)<0) {                        \
+      if (compare(userdata,mid,last)>0) {               \
+        swapper(mid,last);                      \
+        if (compare(userdata,first,mid)>0) swapper(first,mid);\
+      }                                         \
+    }                                           \
+    else {                                      \
+      if (compare(userdata,mid,last)>0) swapper(first,last)\
+      else {                                    \
+        swapper(first,mid);                     \
+        if (compare(userdata,mid,last)>0) swapper(mid,last);\
+      }                                         \
+    }                                           \
+    first+=sz; last-=sz;                        \
+  }
+
+#ifdef DEBUG_QSORT
+#include <stdio.h>
+#endif
+
+/* and so is the partitioning logic: */
+#define Partition(swapper,sz) {                 \
+  do {                                          \
+    while (compare(userdata,first,pivot)<0) first+=sz;  \
+    while (compare(userdata,pivot,last)<0) last-=sz;    \
+    if (first<last) {                           \
+      swapper(first,last);                      \
+      first+=sz; last-=sz; }                    \
+    else if (first==last) { first+=sz; last-=sz; break; }\
+  } while (first<=last);                        \
+}
+
+/* and so is the pre-insertion-sort operation of putting
+ * the smallest element into place as a sentinel.
+ * Doing this makes the inner loop nicer. I got this
+ * idea from the GNU implementation of qsort().
+ * We find the smallest element from the first |nmemb|,
+ * or the first |limit|, whichever is smaller;
+ * therefore we must have ensured that the globally smallest
+ * element is in the first |limit| (because our
+ * quicksort recursion bottoms out only once we
+ * reach subarrays smaller than |limit|).
+ */
+#define PreInsertion(swapper,limit,sz)          \
+  first=base;                                   \
+  last=first + ((nmemb>limit ? limit : nmemb)-1)*sz;\
+  while (last!=base) {                          \
+    if (compare(userdata,first,last)>0) first=last;     \
+    last-=sz; }                                 \
+  if (first!=base) swapper(first,(char*)base);
+
+/* and so is the insertion sort, in the first two cases: */
+#define Insertion(swapper)                      \
+  last=((char*)base)+nmemb*size;                \
+  for (first=((char*)base)+size;first!=last;first+=size) {      \
+    char *test;                                 \
+    /* Find the right place for |first|.        \
+     * My apologies for var reuse. */           \
+    for (test=first-size;compare(userdata,test,first)>0;test-=size) ;   \
+    test+=size;                                 \
+    if (test!=first) {                          \
+      /* Shift everything in [test,first)       \
+       * up by one, and place |first|           \
+       * where |test| is. */                    \
+      memcpy(pivot,first,size);                 \
+      memmove(test+size,test,first-test);       \
+      memcpy(test,pivot,size);                  \
+    }                                           \
+  }
+
+#define SWAP_nonaligned(a,b) { \
+  register char *aa=(a),*bb=(b); \
+  register size_t sz=size; \
+  do { register char t=*aa; *aa++=*bb; *bb++=t; } while (--sz); }
+
+#define SWAP_aligned(a,b) { \
+  register int *aa=(int*)(a),*bb=(int*)(b); \
+  register size_t sz=size; \
+  do { register int t=*aa;*aa++=*bb; *bb++=t; } while (sz-=WORD_BYTES); }
+
+#define SWAP_words(a,b) { \
+  register int t=*((int*)a); *((int*)a)=*((int*)b); *((int*)b)=t; }
+
+/* ---------------------------------------------------------------------- */
+
+static char * pivot_big(char *first, char *mid, char *last, size_t size,
+                        int (SDLCALL *compare)(void *, const void *, const void *), void *userdata) {
+  size_t d=(((last-first)/size)>>3)*size;
+#ifdef DEBUG_QSORT
+fprintf(stderr, "pivot_big: first=%p last=%p size=%lu n=%lu\n", first, (unsigned long)last, size, (unsigned long)((last-first+1)/size));
+#endif
+  char *m1,*m2,*m3;
+  { char *a=first, *b=first+d, *c=first+2*d;
+#ifdef DEBUG_QSORT
+fprintf(stderr,"< %d %d %d @ %p %p %p\n",*(int*)a,*(int*)b,*(int*)c, a,b,c);
+#endif
+    m1 = compare(userdata,a,b)<0 ?
+           (compare(userdata,b,c)<0 ? b : (compare(userdata,a,c)<0 ? c : a))
+         : (compare(userdata,a,c)<0 ? a : (compare(userdata,b,c)<0 ? c : b));
+  }
+  { char *a=mid-d, *b=mid, *c=mid+d;
+#ifdef DEBUG_QSORT
+fprintf(stderr,". %d %d %d @ %p %p %p\n",*(int*)a,*(int*)b,*(int*)c, a,b,c);
+#endif
+    m2 = compare(userdata,a,b)<0 ?
+           (compare(userdata,b,c)<0 ? b : (compare(userdata,a,c)<0 ? c : a))
+         : (compare(userdata,a,c)<0 ? a : (compare(userdata,b,c)<0 ? c : b));
+  }
+  { char *a=last-2*d, *b=last-d, *c=last;
+#ifdef DEBUG_QSORT
+fprintf(stderr,"> %d %d %d @ %p %p %p\n",*(int*)a,*(int*)b,*(int*)c, a,b,c);
+#endif
+    m3 = compare(userdata,a,b)<0 ?
+           (compare(userdata,b,c)<0 ? b : (compare(userdata,a,c)<0 ? c : a))
+         : (compare(userdata,a,c)<0 ? a : (compare(userdata,b,c)<0 ? c : b));
+  }
+#ifdef DEBUG_QSORT
+fprintf(stderr,"-> %d %d %d @ %p %p %p\n",*(int*)m1,*(int*)m2,*(int*)m3, m1,m2,m3);
+#endif
+  return compare(userdata,m1,m2)<0 ?
+           (compare(userdata,m2,m3)<0 ? m2 : (compare(userdata,m1,m3)<0 ? m3 : m1))
+         : (compare(userdata,m1,m3)<0 ? m1 : (compare(userdata,m2,m3)<0 ? m3 : m2));
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void qsort_r_nonaligned(void *base, size_t nmemb, size_t size,
+           int (SDLCALL *compare)(void *, const void *, const void *), void *userdata) {
+
+  stack_entry stack[STACK_SIZE];
+  int stacktop=0;
+  char *first,*last;
+  char *pivot=malloc(size);
+  size_t trunc=TRUNC_nonaligned*size;
+  assert(pivot != NULL);
+
+  first=(char*)base; last=first+(nmemb-1)*size;
+
+  if ((size_t)(last-first)>=trunc) {
+    char *ffirst=first, *llast=last;
+    while (1) {
+      /* Select pivot */
+      { char * mid=first+size*((last-first)/size >> 1);
+        Pivot(SWAP_nonaligned,size);
+        memcpy(pivot,mid,size);
+      }
+      /* Partition. */
+      Partition(SWAP_nonaligned,size);
+      /* Prepare to recurse/iterate. */
+      Recurse(trunc)
+    }
+  }
+  PreInsertion(SWAP_nonaligned,TRUNC_nonaligned,size);
+  Insertion(SWAP_nonaligned);
+  free(pivot);
+}
+
+static void qsort_r_aligned(void *base, size_t nmemb, size_t size,
+           int (SDLCALL *compare)(void *,const void *, const void *), void *userdata) {
+
+  stack_entry stack[STACK_SIZE];
+  int stacktop=0;
+  char *first,*last;
+  char *pivot=malloc(size);
+  size_t trunc=TRUNC_aligned*size;
+  assert(pivot != NULL);
+
+  first=(char*)base; last=first+(nmemb-1)*size;
+
+  if ((size_t)(last-first)>=trunc) {
+    char *ffirst=first,*llast=last;
+    while (1) {
+      /* Select pivot */
+      { char * mid=first+size*((last-first)/size >> 1);
+        Pivot(SWAP_aligned,size);
+        memcpy(pivot,mid,size);
+      }
+      /* Partition. */
+      Partition(SWAP_aligned,size);
+      /* Prepare to recurse/iterate. */
+      Recurse(trunc)
+    }
+  }
+  PreInsertion(SWAP_aligned,TRUNC_aligned,size);
+  Insertion(SWAP_aligned);
+  free(pivot);
+}
+
+static void qsort_r_words(void *base, size_t nmemb,
+           int (SDLCALL *compare)(void *,const void *, const void *), void *userdata) {
+
+  stack_entry stack[STACK_SIZE];
+  int stacktop=0;
+  char *first,*last;
+  char *pivot=malloc(WORD_BYTES);
+  assert(pivot != NULL);
+
+  first=(char*)base; last=first+(nmemb-1)*WORD_BYTES;
+
+  if (last-first>=TRUNC_words) {
+    char *ffirst=first, *llast=last;
+    while (1) {
+#ifdef DEBUG_QSORT
+fprintf(stderr,"Doing %d:%d: ",
+        (first-(char*)base)/WORD_BYTES,
+        (last-(char*)base)/WORD_BYTES);
+#endif
+      /* Select pivot */
+      { char * mid=first+WORD_BYTES*((last-first) / (2*WORD_BYTES));
+        Pivot(SWAP_words,WORD_BYTES);
+        *(int*)pivot=*(int*)mid;
+#ifdef DEBUG_QSORT
+fprintf(stderr,"pivot = %p = #%lu = %d\n", mid, (unsigned long)(((int*)mid)-((int*)base)), *(int*)mid);
+#endif
+      }
+      /* Partition. */
+      Partition(SWAP_words,WORD_BYTES);
+#ifdef DEBUG_QSORT
+fprintf(stderr, "after partitioning first=#%lu last=#%lu\n", (first-(char*)base)/4lu, (last-(char*)base)/4lu);
+#endif
+      /* Prepare to recurse/iterate. */
+      Recurse(TRUNC_words)
+    }
+  }
+  PreInsertion(SWAP_words,TRUNC_words/WORD_BYTES,WORD_BYTES);
+  /* Now do insertion sort. */
+  last=((char*)base)+nmemb*WORD_BYTES;
+  for (first=((char*)base)+WORD_BYTES;first!=last;first+=WORD_BYTES) {
+    /* Find the right place for |first|. My apologies for var reuse */
+    int *pl=(int*)(first-WORD_BYTES),*pr=(int*)first;
+    *(int*)pivot=*(int*)first;
+    for (;compare(userdata,pl,pivot)>0;pr=pl,--pl) {
+      *pr=*pl; }
+    if (pr!=(int*)first) *pr=*(int*)pivot;
+  }
+  free(pivot);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void SDL_qsort_r(void *base, size_t nmemb, size_t size,
+           SDL_CompareCallback_r compare, void *userdata) {
+
+  if (nmemb<=1) return;
+  if (((uintptr_t)base|size)&(WORD_BYTES-1))
+    qsort_r_nonaligned(base,nmemb,size,compare,userdata);
+  else if (size!=WORD_BYTES)
+    qsort_r_aligned(base,nmemb,size,compare,userdata);
+  else
+    qsort_r_words(base,nmemb,compare,userdata);
+}
+
+static int SDLCALL qsort_non_r_bridge(void *userdata, const void *a, const void *b)
+{
+    int (SDLCALL *compare)(const void *, const void *) = (int (SDLCALL *)(const void *, const void *)) userdata;
+    return compare(a, b);
+}
+
+void SDL_qsort(void *base, size_t nmemb, size_t size, SDL_CompareCallback compare)
+{
+    SDL_qsort_r(base, nmemb, size, qsort_non_r_bridge, compare);
+}
+
+// Don't use the C runtime for such a simple function, since we want to allow SDLCALL callbacks and userdata.
+// SDL's replacement: Taken from the Public Domain C Library (PDCLib):
+// Permission is granted to use, modify, and / or redistribute at will.
+void *SDL_bsearch_r(const void *key, const void *base, size_t nmemb, size_t size, SDL_CompareCallback_r compare, void *userdata)
+{
+    const void *pivot;
+    size_t corr;
+    int rc;
+
+    while (nmemb) {
+        /* algorithm needs -1 correction if remaining elements are an even number. */
+        corr = nmemb % 2;
+        nmemb /= 2;
+        pivot = (const char *)base + (nmemb * size);
+        rc = compare(userdata, key, pivot);
+
+        if (rc > 0) {
+            base = (const char *)pivot + size;
+            /* applying correction */
+            nmemb -= (1 - corr);
+        } else if (rc == 0) {
+            return (void *)pivot;
+        }
+    }
+
+    return NULL;
+}
+
+void *SDL_bsearch(const void *key, const void *base, size_t nmemb, size_t size, SDL_CompareCallback compare)
+{
+    // qsort_non_r_bridge just happens to match calling conventions, so reuse it.
+    return SDL_bsearch_r(key, base, nmemb, size, qsort_non_r_bridge, compare);
+}
+
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_random.c b/contrib/SDL-3.2.8/src/stdlib/SDL_random.c
new file mode 100644
index 0000000..a774d30
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_random.c
@@ -0,0 +1,115 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+// This file contains portable random functions for SDL
+
+static Uint64 SDL_rand_state;
+static bool SDL_rand_initialized = false;
+
+void SDL_srand(Uint64 seed)
+{
+    if (!seed) {
+        seed = SDL_GetPerformanceCounter();
+    }
+    SDL_rand_state = seed;
+    SDL_rand_initialized = true;
+}
+
+Sint32 SDL_rand(Sint32 n)
+{
+    if (!SDL_rand_initialized) {
+        SDL_srand(0);
+    }
+
+    return SDL_rand_r(&SDL_rand_state, n);
+}
+
+float SDL_randf(void)
+{
+    if (!SDL_rand_initialized) {
+        SDL_srand(0);
+    }
+
+    return SDL_randf_r(&SDL_rand_state);
+}
+
+Uint32 SDL_rand_bits(void)
+{
+    if (!SDL_rand_initialized) {
+        SDL_srand(0);
+    }
+
+    return SDL_rand_bits_r(&SDL_rand_state);
+}
+
+Uint32 SDL_rand_bits_r(Uint64 *state)
+{
+    if (!state) {
+        return 0;
+    }
+
+    // The C and A parameters of this LCG have been chosen based on hundreds
+    // of core-hours of testing with PractRand and TestU01's Crush.
+    // Using a 32-bit A improves performance on 32-bit architectures.
+    // C can be any odd number, but < 256 generates smaller code on ARM32
+    // These values perform as well as a full 64-bit implementation against
+    // Crush and PractRand. Plus, their worst-case performance is better
+    // than common 64-bit constants when tested against PractRand using seeds
+    // with only a single bit set.
+
+    // We tested all 32-bit and 33-bit A with all C < 256 from a v2 of:
+    // Steele GL, Vigna S. Computationally easy, spectrally good multipliers
+    // for congruential pseudorandom number generators.
+    // Softw Pract Exper. 2022;52(2):443-458. doi: 10.1002/spe.3030
+    // https://arxiv.org/abs/2001.05304v2
+
+    *state = *state * 0xff1cd035ul + 0x05;
+
+    // Only return top 32 bits because they have a longer period
+    return (Uint32)(*state >> 32);
+}
+
+Sint32 SDL_rand_r(Uint64 *state, Sint32 n)
+{
+    // Algorithm: get 32 bits from SDL_rand_bits() and treat it as a 0.32 bit
+    // fixed point number. Multiply by the 31.0 bit n to get a 31.32 bit
+    // result. Shift right by 32 to get the 31 bit integer that we want.
+
+    if (n < 0) {
+        // The algorithm looks like it works for numbers < 0 but it has an
+        // infinitesimal chance of returning a value out of range.
+        // Returning -SDL_rand(abs(n)) blows up at INT_MIN instead.
+        // It's easier to just say no.
+        return 0;
+    }
+
+    // On 32-bit arch, the compiler will optimize to a single 32-bit multiply
+    Uint64 val = (Uint64)SDL_rand_bits_r(state) * n;
+    return (Sint32)(val >> 32);
+}
+
+float SDL_randf_r(Uint64 *state)
+{
+    // Note: its using 24 bits because float has 23 bits significand + 1 implicit bit
+    return (SDL_rand_bits_r(state) >> (32 - 24)) * 0x1p-24f;
+}
+
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_stdlib.c b/contrib/SDL-3.2.8/src/stdlib/SDL_stdlib.c
new file mode 100644
index 0000000..98faab9
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_stdlib.c
@@ -0,0 +1,567 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+// This file contains portable stdlib functions for SDL
+
+#include "../libm/math_libm.h"
+
+double SDL_atan(double x)
+{
+#ifdef HAVE_ATAN
+    return atan(x);
+#else
+    return SDL_uclibc_atan(x);
+#endif
+}
+
+float SDL_atanf(float x)
+{
+#ifdef HAVE_ATANF
+    return atanf(x);
+#else
+    return (float)SDL_atan((double)x);
+#endif
+}
+
+double SDL_atan2(double y, double x)
+{
+#ifdef HAVE_ATAN2
+    return atan2(y, x);
+#else
+    return SDL_uclibc_atan2(y, x);
+#endif
+}
+
+float SDL_atan2f(float y, float x)
+{
+#ifdef HAVE_ATAN2F
+    return atan2f(y, x);
+#else
+    return (float)SDL_atan2((double)y, (double)x);
+#endif
+}
+
+double SDL_acos(double val)
+{
+#ifdef HAVE_ACOS
+    return acos(val);
+#else
+    double result;
+    if (val == -1.0) {
+        result = SDL_PI_D;
+    } else {
+        result = SDL_atan(SDL_sqrt(1.0 - val * val) / val);
+        if (result < 0.0) {
+            result += SDL_PI_D;
+        }
+    }
+    return result;
+#endif
+}
+
+float SDL_acosf(float val)
+{
+#ifdef HAVE_ACOSF
+    return acosf(val);
+#else
+    return (float)SDL_acos((double)val);
+#endif
+}
+
+double SDL_asin(double val)
+{
+#ifdef HAVE_ASIN
+    return asin(val);
+#else
+    double result;
+    if (val == -1.0) {
+        result = -(SDL_PI_D / 2.0);
+    } else {
+        result = (SDL_PI_D / 2.0) - SDL_acos(val);
+    }
+    return result;
+#endif
+}
+
+float SDL_asinf(float val)
+{
+#ifdef HAVE_ASINF
+    return asinf(val);
+#else
+    return (float)SDL_asin((double)val);
+#endif
+}
+
+double SDL_ceil(double x)
+{
+#ifdef HAVE_CEIL
+    return ceil(x);
+#else
+    double integer = SDL_floor(x);
+    double fraction = x - integer;
+    if (fraction > 0.0) {
+        integer += 1.0;
+    }
+    return integer;
+#endif // HAVE_CEIL
+}
+
+float SDL_ceilf(float x)
+{
+#ifdef HAVE_CEILF
+    return ceilf(x);
+#else
+    return (float)SDL_ceil((double)x);
+#endif
+}
+
+double SDL_copysign(double x, double y)
+{
+#ifdef HAVE_COPYSIGN
+    return copysign(x, y);
+#elif defined(HAVE__COPYSIGN)
+    return _copysign(x, y);
+#elif defined(__WATCOMC__) && defined(__386__)
+    // this is nasty as hell, but it works..
+    unsigned int *xi = (unsigned int *)&x,
+                 *yi = (unsigned int *)&y;
+    xi[1] = (yi[1] & 0x80000000) | (xi[1] & 0x7fffffff);
+    return x;
+#else
+    return SDL_uclibc_copysign(x, y);
+#endif // HAVE_COPYSIGN
+}
+
+float SDL_copysignf(float x, float y)
+{
+#ifdef HAVE_COPYSIGNF
+    return copysignf(x, y);
+#else
+    return (float)SDL_copysign((double)x, (double)y);
+#endif
+}
+
+double SDL_cos(double x)
+{
+#ifdef HAVE_COS
+    return cos(x);
+#else
+    return SDL_uclibc_cos(x);
+#endif
+}
+
+float SDL_cosf(float x)
+{
+#ifdef HAVE_COSF
+    return cosf(x);
+#else
+    return (float)SDL_cos((double)x);
+#endif
+}
+
+double SDL_exp(double x)
+{
+#ifdef HAVE_EXP
+    return exp(x);
+#else
+    return SDL_uclibc_exp(x);
+#endif
+}
+
+float SDL_expf(float x)
+{
+#ifdef HAVE_EXPF
+    return expf(x);
+#else
+    return (float)SDL_exp((double)x);
+#endif
+}
+
+double SDL_fabs(double x)
+{
+#ifdef HAVE_FABS
+    return fabs(x);
+#else
+    return SDL_uclibc_fabs(x);
+#endif
+}
+
+float SDL_fabsf(float x)
+{
+#ifdef HAVE_FABSF
+    return fabsf(x);
+#else
+    return (float)SDL_fabs((double)x);
+#endif
+}
+
+double SDL_floor(double x)
+{
+#ifdef HAVE_FLOOR
+    return floor(x);
+#else
+    return SDL_uclibc_floor(x);
+#endif
+}
+
+float SDL_floorf(float x)
+{
+#ifdef HAVE_FLOORF
+    return floorf(x);
+#else
+    return (float)SDL_floor((double)x);
+#endif
+}
+
+double SDL_trunc(double x)
+{
+#ifdef HAVE_TRUNC
+    return trunc(x);
+#else
+    if (x >= 0.0f) {
+        return SDL_floor(x);
+    } else {
+        return SDL_ceil(x);
+    }
+#endif
+}
+
+float SDL_truncf(float x)
+{
+#ifdef HAVE_TRUNCF
+    return truncf(x);
+#else
+    return (float)SDL_trunc((double)x);
+#endif
+}
+
+double SDL_fmod(double x, double y)
+{
+#ifdef HAVE_FMOD
+    return fmod(x, y);
+#else
+    return SDL_uclibc_fmod(x, y);
+#endif
+}
+
+float SDL_fmodf(float x, float y)
+{
+#ifdef HAVE_FMODF
+    return fmodf(x, y);
+#else
+    return (float)SDL_fmod((double)x, (double)y);
+#endif
+}
+
+int SDL_isinf(double x)
+{
+#ifdef HAVE_ISINF
+    return isinf(x);
+#else
+    return SDL_uclibc_isinf(x);
+#endif
+}
+
+int SDL_isinff(float x)
+{
+#ifdef HAVE_ISINF_FLOAT_MACRO
+    return isinf(x);
+#elif defined(HAVE_ISINFF)
+    return isinff(x);
+#else
+    return SDL_uclibc_isinff(x);
+#endif
+}
+
+int SDL_isnan(double x)
+{
+#ifdef HAVE_ISNAN
+    return isnan(x);
+#else
+    return SDL_uclibc_isnan(x);
+#endif
+}
+
+int SDL_isnanf(float x)
+{
+#ifdef HAVE_ISNAN_FLOAT_MACRO
+    return isnan(x);
+#elif defined(HAVE_ISNANF)
+    return isnanf(x);
+#else
+    return SDL_uclibc_isnanf(x);
+#endif
+}
+
+double SDL_log(double x)
+{
+#ifdef HAVE_LOG
+    return log(x);
+#else
+    return SDL_uclibc_log(x);
+#endif
+}
+
+float SDL_logf(float x)
+{
+#ifdef HAVE_LOGF
+    return logf(x);
+#else
+    return (float)SDL_log((double)x);
+#endif
+}
+
+double SDL_log10(double x)
+{
+#ifdef HAVE_LOG10
+    return log10(x);
+#else
+    return SDL_uclibc_log10(x);
+#endif
+}
+
+float SDL_log10f(float x)
+{
+#ifdef HAVE_LOG10F
+    return log10f(x);
+#else
+    return (float)SDL_log10((double)x);
+#endif
+}
+
+double SDL_modf(double x, double *y)
+{
+#ifdef HAVE_MODF
+    return modf(x, y);
+#else
+    return SDL_uclibc_modf(x, y);
+#endif
+}
+
+float SDL_modff(float x, float *y)
+{
+#ifdef HAVE_MODFF
+    return modff(x, y);
+#else
+    double double_result, double_y;
+    double_result = SDL_modf((double)x, &double_y);
+    *y = (float)double_y;
+    return (float)double_result;
+#endif
+}
+
+double SDL_pow(double x, double y)
+{
+#ifdef HAVE_POW
+    return pow(x, y);
+#else
+    return SDL_uclibc_pow(x, y);
+#endif
+}
+
+float SDL_powf(float x, float y)
+{
+#ifdef HAVE_POWF
+    return powf(x, y);
+#else
+    return (float)SDL_pow((double)x, (double)y);
+#endif
+}
+
+double SDL_round(double arg)
+{
+#if defined HAVE_ROUND
+    return round(arg);
+#else
+    if (arg >= 0.0) {
+        return SDL_floor(arg + 0.5);
+    } else {
+        return SDL_ceil(arg - 0.5);
+    }
+#endif
+}
+
+float SDL_roundf(float arg)
+{
+#if defined HAVE_ROUNDF
+    return roundf(arg);
+#else
+    return (float)SDL_round((double)arg);
+#endif
+}
+
+long SDL_lround(double arg)
+{
+#if defined HAVE_LROUND
+    return lround(arg);
+#else
+    return (long)SDL_round(arg);
+#endif
+}
+
+long SDL_lroundf(float arg)
+{
+#if defined HAVE_LROUNDF
+    return lroundf(arg);
+#else
+    return (long)SDL_round((double)arg);
+#endif
+}
+
+double SDL_scalbn(double x, int n)
+{
+#ifdef HAVE_SCALBN
+    return scalbn(x, n);
+#elif defined(HAVE__SCALB)
+    return _scalb(x, n);
+#elif defined(HAVE_LIBC) && defined(HAVE_FLOAT_H) && (FLT_RADIX == 2)
+    /* from scalbn(3): If FLT_RADIX equals 2 (which is
+     * usual), then scalbn() is equivalent to ldexp(3). */
+    return ldexp(x, n);
+#else
+    return SDL_uclibc_scalbn(x, n);
+#endif
+}
+
+float SDL_scalbnf(float x, int n)
+{
+#ifdef HAVE_SCALBNF
+    return scalbnf(x, n);
+#else
+    return (float)SDL_scalbn((double)x, n);
+#endif
+}
+
+double SDL_sin(double x)
+{
+#ifdef HAVE_SIN
+    return sin(x);
+#else
+    return SDL_uclibc_sin(x);
+#endif
+}
+
+float SDL_sinf(float x)
+{
+#ifdef HAVE_SINF
+    return sinf(x);
+#else
+    return (float)SDL_sin((double)x);
+#endif
+}
+
+double SDL_sqrt(double x)
+{
+#ifdef HAVE_SQRT
+    return sqrt(x);
+#else
+    return SDL_uclibc_sqrt(x);
+#endif
+}
+
+float SDL_sqrtf(float x)
+{
+#ifdef HAVE_SQRTF
+    return sqrtf(x);
+#else
+    return (float)SDL_sqrt((double)x);
+#endif
+}
+
+double SDL_tan(double x)
+{
+#ifdef HAVE_TAN
+    return tan(x);
+#else
+    return SDL_uclibc_tan(x);
+#endif
+}
+
+float SDL_tanf(float x)
+{
+#ifdef HAVE_TANF
+    return tanf(x);
+#else
+    return (float)SDL_tan((double)x);
+#endif
+}
+
+int SDL_abs(int x)
+{
+#ifdef HAVE_ABS
+    return abs(x);
+#else
+    return (x < 0) ? -x : x;
+#endif
+}
+
+int SDL_isalpha(int x) { return (SDL_isupper(x)) || (SDL_islower(x)); }
+int SDL_isalnum(int x) { return (SDL_isalpha(x)) || (SDL_isdigit(x)); }
+int SDL_isdigit(int x) { return ((x) >= '0') && ((x) <= '9'); }
+int SDL_isxdigit(int x) { return (((x) >= 'A') && ((x) <= 'F')) || (((x) >= 'a') && ((x) <= 'f')) || (SDL_isdigit(x)); }
+int SDL_ispunct(int x) { return (SDL_isgraph(x)) && (!SDL_isalnum(x)); }
+int SDL_isspace(int x) { return ((x) == ' ') || ((x) == '\t') || ((x) == '\r') || ((x) == '\n') || ((x) == '\f') || ((x) == '\v'); }
+int SDL_isupper(int x) { return ((x) >= 'A') && ((x) <= 'Z'); }
+int SDL_islower(int x) { return ((x) >= 'a') && ((x) <= 'z'); }
+int SDL_isprint(int x) { return ((x) >= ' ') && ((x) < '\x7f'); }
+int SDL_isgraph(int x) { return (SDL_isprint(x)) && ((x) != ' '); }
+int SDL_iscntrl(int x) { return (((x) >= '\0') && ((x) <= '\x1f')) || ((x) == '\x7f'); }
+int SDL_toupper(int x) { return ((x) >= 'a') && ((x) <= 'z') ? ('A' + ((x) - 'a')) : (x); }
+int SDL_tolower(int x) { return ((x) >= 'A') && ((x) <= 'Z') ? ('a' + ((x) - 'A')) : (x); }
+int SDL_isblank(int x) { return ((x) == ' ') || ((x) == '\t'); }
+
+void *SDL_aligned_alloc(size_t alignment, size_t size)
+{
+    size_t padding;
+    Uint8 *result = NULL;
+
+    if (alignment < sizeof(void*)) {
+        alignment = sizeof(void*);
+    }
+    padding = (alignment - (size % alignment));
+
+    if (SDL_size_add_check_overflow(size, alignment, &size) &&
+        SDL_size_add_check_overflow(size, sizeof(void *), &size) &&
+        SDL_size_add_check_overflow(size, padding, &size)) {
+        void *original = SDL_malloc(size);
+        if (original) {
+            // Make sure we have enough space to store the original pointer
+            result = (Uint8 *)original + sizeof(original);
+
+            // Align the pointer we're going to return
+            result += alignment - (((size_t)result) % alignment);
+
+            // Store the original pointer right before the returned value
+            SDL_memcpy(result - sizeof(original), &original, sizeof(original));
+        }
+    }
+    return result;
+}
+
+void SDL_aligned_free(void *mem)
+{
+    if (mem) {
+        void *original;
+        SDL_memcpy(&original, ((Uint8 *)mem - sizeof(original)), sizeof(original));
+        SDL_free(original);
+    }
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_string.c b/contrib/SDL-3.2.8/src/stdlib/SDL_string.c
new file mode 100644
index 0000000..007719e
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_string.c
@@ -0,0 +1,2515 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+// This file contains portable string manipulation functions for SDL
+
+#include "SDL_vacopy.h"
+
+#ifdef SDL_PLATFORM_VITA
+#include <psp2/kernel/clib.h>
+#endif
+
+#include "SDL_sysstdlib.h"
+
+#include "SDL_casefolding.h"
+
+#if defined(__SIZEOF_WCHAR_T__)
+#define SDL_SIZEOF_WCHAR_T __SIZEOF_WCHAR_T__
+#elif defined(SDL_PLATFORM_WINDOWS)
+#define SDL_SIZEOF_WCHAR_T 2
+#else  // assume everything else is UTF-32 (add more tests if compiler-assert fails below!)
+#define SDL_SIZEOF_WCHAR_T 4
+#endif
+SDL_COMPILE_TIME_ASSERT(sizeof_wchar_t, sizeof(wchar_t) == SDL_SIZEOF_WCHAR_T);
+
+
+char *SDL_UCS4ToUTF8(Uint32 codepoint, char *dst)
+{
+    if (!dst) {
+        return NULL;  // I guess...?
+    } else if (codepoint > 0x10FFFF) {  // Outside the range of Unicode codepoints (also, larger than can be encoded in 4 bytes of UTF-8!).
+        codepoint = SDL_INVALID_UNICODE_CODEPOINT;
+    } else if ((codepoint >= 0xD800) && (codepoint <= 0xDFFF)) {  // UTF-16 surrogate values are illegal in UTF-8.
+        codepoint = SDL_INVALID_UNICODE_CODEPOINT;
+    }
+
+    Uint8 *p = (Uint8 *)dst;
+    if (codepoint <= 0x7F) {
+        *p = (Uint8)codepoint;
+        ++dst;
+    } else if (codepoint <= 0x7FF) {
+        p[0] = 0xC0 | (Uint8)((codepoint >> 6) & 0x1F);
+        p[1] = 0x80 | (Uint8)(codepoint & 0x3F);
+        dst += 2;
+    } else if (codepoint <= 0xFFFF) {
+        p[0] = 0xE0 | (Uint8)((codepoint >> 12) & 0x0F);
+        p[1] = 0x80 | (Uint8)((codepoint >> 6) & 0x3F);
+        p[2] = 0x80 | (Uint8)(codepoint & 0x3F);
+        dst += 3;
+    } else {
+        SDL_assert(codepoint <= 0x10FFFF);
+        p[0] = 0xF0 | (Uint8)((codepoint >> 18) & 0x07);
+        p[1] = 0x80 | (Uint8)((codepoint >> 12) & 0x3F);
+        p[2] = 0x80 | (Uint8)((codepoint >> 6) & 0x3F);
+        p[3] = 0x80 | (Uint8)(codepoint & 0x3F);
+        dst += 4;
+    }
+
+    return dst;
+}
+
+
+// this expects `from` and `to` to be UTF-32 encoding!
+int SDL_CaseFoldUnicode(Uint32 from, Uint32 *to)
+{
+    // !!! FIXME: since the hashtable is static, maybe we should binary
+    // !!! FIXME: search it instead of walking the whole bucket.
+
+    if (from < 128) {   // low-ASCII, easy!
+        if ((from >= 'A') && (from <= 'Z')) {
+            *to = 'a' + (from - 'A');
+            return 1;
+        }
+    } else if (from <= 0xFFFF) {  // the Basic Multilingual Plane.
+        const Uint8 hash = ((from ^ (from >> 8)) & 0xFF);
+        const Uint16 from16 = (Uint16) from;
+
+        // see if it maps to a single char (most common)...
+        {
+            const CaseFoldHashBucket1_16 *bucket = &case_fold_hash1_16[hash];
+            const int count = (int) bucket->count;
+            for (int i = 0; i < count; i++) {
+                const CaseFoldMapping1_16 *mapping = &bucket->list[i];
+                if (mapping->from == from16) {
+                    *to = mapping->to0;
+                    return 1;
+                }
+            }
+        }
+
+        // see if it folds down to two chars...
+        {
+            const CaseFoldHashBucket2_16 *bucket = &case_fold_hash2_16[hash & 15];
+            const int count = (int) bucket->count;
+            for (int i = 0; i < count; i++) {
+                const CaseFoldMapping2_16 *mapping = &bucket->list[i];
+                if (mapping->from == from16) {
+                    to[0] = mapping->to0;
+                    to[1] = mapping->to1;
+                    return 2;
+                }
+            }
+        }
+
+        // okay, maybe it's _three_ characters!
+        {
+            const CaseFoldHashBucket3_16 *bucket = &case_fold_hash3_16[hash & 3];
+            const int count = (int) bucket->count;
+            for (int i = 0; i < count; i++) {
+                const CaseFoldMapping3_16 *mapping = &bucket->list[i];
+                if (mapping->from == from16) {
+                    to[0] = mapping->to0;
+                    to[1] = mapping->to1;
+                    to[2] = mapping->to2;
+                    return 3;
+                }
+            }
+        }
+
+    } else {  // codepoint that doesn't fit in 16 bits.
+        const Uint8 hash = ((from ^ (from >> 8)) & 0xFF);
+        const CaseFoldHashBucket1_32 *bucket = &case_fold_hash1_32[hash & 15];
+        const int count = (int) bucket->count;
+        for (int i = 0; i < count; i++) {
+            const CaseFoldMapping1_32 *mapping = &bucket->list[i];
+            if (mapping->from == from) {
+                *to = mapping->to0;
+                return 1;
+            }
+        }
+    }
+
+    // Not found...there's no folding needed for this codepoint.
+    *to = from;
+    return 1;
+}
+
+#define UNICODE_STRCASECMP(bits, slen1, slen2, update_slen1, update_slen2) \
+    Uint32 folded1[3], folded2[3]; \
+    int head1 = 0, tail1 = 0, head2 = 0, tail2 = 0; \
+    while (true) { \
+        Uint32 cp1, cp2; \
+        if (head1 != tail1) { \
+            cp1 = folded1[tail1++]; \
+        } else { \
+            const Uint##bits *str1start = (const Uint##bits *) str1; \
+            head1 = SDL_CaseFoldUnicode(StepUTF##bits(&str1, slen1), folded1); \
+            update_slen1; \
+            cp1 = folded1[0]; \
+            tail1 = 1; \
+        } \
+        if (head2 != tail2) { \
+            cp2 = folded2[tail2++]; \
+        } else { \
+            const Uint##bits *str2start = (const Uint##bits *) str2; \
+            head2 = SDL_CaseFoldUnicode(StepUTF##bits(&str2, slen2), folded2); \
+            update_slen2; \
+            cp2 = folded2[0]; \
+            tail2 = 1; \
+        } \
+        if (cp1 < cp2) { \
+            return -1; \
+        } else if (cp1 > cp2) { \
+            return 1; \
+        } else if (cp1 == 0) { \
+            break;  /* complete match. */ \
+        } \
+    } \
+    return 0
+
+
+static Uint32 StepUTF8(const char **_str, const size_t slen)
+{
+    /*
+     * From rfc3629, the UTF-8 spec:
+     *  https://www.ietf.org/rfc/rfc3629.txt
+     *
+     *   Char. number range  |        UTF-8 octet sequence
+     *      (hexadecimal)    |              (binary)
+     *   --------------------+---------------------------------------------
+     *   0000 0000-0000 007F | 0xxxxxxx
+     *   0000 0080-0000 07FF | 110xxxxx 10xxxxxx
+     *   0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx
+     *   0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
+     */
+
+    const Uint8 *str = (const Uint8 *) *_str;
+    const Uint32 octet = (Uint32) (slen ? *str : 0);
+
+    if (octet == 0) {  // null terminator, end of string.
+        return 0;  // don't advance `*_str`.
+    } else if ((octet & 0x80) == 0) {  // 0xxxxxxx: one byte codepoint.
+        (*_str)++;
+        return octet;
+    } else if (((octet & 0xE0) == 0xC0) && (slen >= 2)) {  // 110xxxxx 10xxxxxx: two byte codepoint.
+        const Uint8 str1 = str[1];
+        if ((str1 & 0xC0) == 0x80) {  // If trailing bytes aren't 10xxxxxx, sequence is bogus.
+            const Uint32 result = ((octet & 0x1F) << 6) | (str1 & 0x3F);
+            if (result >= 0x0080) {  // rfc3629 says you can't use overlong sequences for smaller values.
+                *_str += 2;
+                return result;
+            }
+        }
+    } else if (((octet & 0xF0) == 0xE0) && (slen >= 3)) {  // 1110xxxx 10xxxxxx 10xxxxxx: three byte codepoint.
+        const Uint8 str1 = str[1];
+        const Uint8 str2 = str[2];
+        if (((str1 & 0xC0) == 0x80) && ((str2 & 0xC0) == 0x80)) {  // If trailing bytes aren't 10xxxxxx, sequence is bogus.
+            const Uint32 octet2 = ((Uint32) (str1 & 0x3F)) << 6;
+            const Uint32 octet3 = ((Uint32) (str2 & 0x3F));
+            const Uint32 result = ((octet & 0x0F) << 12) | octet2 | octet3;
+            if (result >= 0x800) {  // rfc3629 says you can't use overlong sequences for smaller values.
+                if ((result < 0xD800) || (result > 0xDFFF)) {  // UTF-16 surrogate values are illegal in UTF-8.
+                    *_str += 3;
+                    return result;
+                }
+            }
+        }
+    } else if (((octet & 0xF8) == 0xF0) && (slen >= 4)) {  // 11110xxxx 10xxxxxx 10xxxxxx 10xxxxxx: four byte codepoint.
+        const Uint8 str1 = str[1];
+        const Uint8 str2 = str[2];
+        const Uint8 str3 = str[3];
+        if (((str1 & 0xC0) == 0x80) && ((str2 & 0xC0) == 0x80) && ((str3 & 0xC0) == 0x80)) {  // If trailing bytes aren't 10xxxxxx, sequence is bogus.
+            const Uint32 octet2 = ((Uint32) (str1 & 0x1F)) << 12;
+            const Uint32 octet3 = ((Uint32) (str2 & 0x3F)) << 6;
+            const Uint32 octet4 = ((Uint32) (str3 & 0x3F));
+            const Uint32 result = ((octet & 0x07) << 18) | octet2 | octet3 | octet4;
+            if (result >= 0x10000) {  // rfc3629 says you can't use overlong sequences for smaller values.
+                *_str += 4;
+                return result;
+            }
+        }
+    }
+
+    // bogus byte, skip ahead, return a REPLACEMENT CHARACTER.
+    (*_str)++;
+    return SDL_INVALID_UNICODE_CODEPOINT;
+}
+
+Uint32 SDL_StepUTF8(const char **pstr, size_t *pslen)
+{
+    if (!pslen) {
+        return StepUTF8(pstr, 4);  // 4 == max codepoint size.
+    }
+    const char *origstr = *pstr;
+    const Uint32 result = StepUTF8(pstr, *pslen);
+    *pslen -= (size_t) (*pstr - origstr);
+    return result;
+}
+
+Uint32 SDL_StepBackUTF8(const char *start, const char **pstr)
+{
+    if (!pstr || *pstr <= start) {
+        return 0;
+    }
+
+    // Step back over the previous UTF-8 character
+    const char *str = *pstr;
+    do {
+        if (str == start) {
+            break;
+        }
+        --str;
+    } while ((*str & 0xC0) == 0x80);
+
+    size_t length = (*pstr - str);
+    *pstr = str;
+    return StepUTF8(&str, length);
+}
+
+#if (SDL_SIZEOF_WCHAR_T == 2)
+static Uint32 StepUTF16(const Uint16 **_str, const size_t slen)
+{
+    const Uint16 *str = *_str;
+    Uint32 cp = (Uint32) *(str++);
+    if (cp == 0) {
+        return 0;  // don't advance string pointer.
+    } else if ((cp >= 0xDC00) && (cp <= 0xDFFF)) {
+        cp = SDL_INVALID_UNICODE_CODEPOINT;  // Orphaned second half of surrogate pair
+    } else if ((cp >= 0xD800) && (cp <= 0xDBFF)) {  // start of surrogate pair!
+        const Uint32 pair = (Uint32) *str;
+        if ((pair == 0) || ((pair < 0xDC00) || (pair > 0xDFFF))) {
+            cp = SDL_INVALID_UNICODE_CODEPOINT;
+        } else {
+            str++;  // eat the other surrogate.
+            cp = 0x10000 + (((cp - 0xD800) << 10) | (pair - 0xDC00));
+        }
+    }
+
+    *_str = str;
+    return (cp > 0x10FFFF) ? SDL_INVALID_UNICODE_CODEPOINT : cp;
+}
+#elif (SDL_SIZEOF_WCHAR_T == 4)
+static Uint32 StepUTF32(const Uint32 **_str, const size_t slen)
+{
+    if (!slen) {
+        return 0;
+    }
+
+    const Uint32 *str = *_str;
+    const Uint32 cp = *str;
+    if (cp == 0) {
+        return 0;  // don't advance string pointer.
+    }
+
+    (*_str)++;
+    return (cp > 0x10FFFF) ? SDL_INVALID_UNICODE_CODEPOINT : cp;
+}
+#endif
+
+#define UTF8_IsLeadByte(c)     ((c) >= 0xC0 && (c) <= 0xF4)
+#define UTF8_IsTrailingByte(c) ((c) >= 0x80 && (c) <= 0xBF)
+
+static size_t UTF8_GetTrailingBytes(unsigned char c)
+{
+    if (c >= 0xC0 && c <= 0xDF) {
+        return 1;
+    } else if (c >= 0xE0 && c <= 0xEF) {
+        return 2;
+    } else if (c >= 0xF0 && c <= 0xF4) {
+        return 3;
+    }
+
+    return 0;
+}
+
+#if !defined(HAVE_VSSCANF) || !defined(HAVE_STRTOL) || !defined(HAVE_STRTOUL) || !defined(HAVE_STRTOLL) || !defined(HAVE_STRTOULL) || !defined(HAVE_STRTOD)
+/**
+ * Parses an unsigned long long and returns the unsigned value and sign bit.
+ *
+ * Positive values are clamped to ULLONG_MAX.
+ * The result `value == 0 && negative` indicates negative overflow
+ * and might need to be handled differently depending on whether a
+ * signed or unsigned integer is being parsed.
+ */
+static size_t SDL_ScanUnsignedLongLongInternal(const char *text, int count, int radix, unsigned long long *valuep, bool *negativep)
+{
+    const unsigned long long ullong_max = ~0ULL;
+
+    const char *text_start = text;
+    const char *number_start = text_start;
+    unsigned long long value = 0;
+    bool negative = false;
+    bool overflow = false;
+
+    if (radix == 0 || (radix >= 2 && radix <= 36)) {
+        while (SDL_isspace(*text)) {
+            ++text;
+        }
+        if (*text == '-' || *text == '+') {
+            negative = *text == '-';
+            ++text;
+        }
+        if ((radix == 0 || radix == 16) && *text == '0' && text[1] != '\0') {
+            ++text;
+            if (*text == 'x' || *text == 'X') {
+                radix = 16;
+                ++text;
+            } else if (radix == 0) {
+                radix = 8;
+            }
+        } else if (radix == 0) {
+            radix = 10;
+        }
+        number_start = text;
+        do {
+            unsigned long long digit;
+            if (*text >= '0' && *text <= '9') {
+                digit = *text - '0';
+            } else if (radix > 10) {
+                if (*text >= 'A' && *text < 'A' + (radix - 10)) {
+                    digit = 10 + (*text - 'A');
+                } else if (*text >= 'a' && *text < 'a' + (radix - 10)) {
+                    digit = 10 + (*text - 'a');
+                } else {
+                    break;
+                }
+            } else {
+                break;
+            }
+            if (value != 0 && radix > ullong_max / value) {
+                overflow = true;
+            } else {
+                value *= radix;
+                if (digit > ullong_max - value) {
+                    overflow = true;
+                } else {
+                    value += digit;
+                }
+            }
+            ++text;
+        } while (count == 0 || (text - text_start) != count);
+    }
+    if (text == number_start) {
+        if (radix == 16 && text > text_start && (*(text - 1) == 'x' || *(text - 1) == 'X')) {
+            // the string was "0x"; consume the '0' but not the 'x'
+            --text;
+        } else {
+            // no number was parsed, and thus no characters were consumed
+            text = text_start;
+        }
+    }
+    if (overflow) {
+        if (negative) {
+            value = 0;
+        } else {
+            value = ullong_max;
+        }
+    } else if (value == 0) {
+        negative = false;
+    }
+    *valuep = value;
+    *negativep = negative;
+    return text - text_start;
+}
+#endif
+
+#ifndef HAVE_WCSTOL
+// SDL_ScanUnsignedLongLongInternalW assumes that wchar_t can be converted to int without truncating bits
+SDL_COMPILE_TIME_ASSERT(wchar_t_int, sizeof(wchar_t) <= sizeof(int));
+
+/**
+ * Parses an unsigned long long and returns the unsigned value and sign bit.
+ *
+ * Positive values are clamped to ULLONG_MAX.
+ * The result `value == 0 && negative` indicates negative overflow
+ * and might need to be handled differently depending on whether a
+ * signed or unsigned integer is being parsed.
+ */
+static size_t SDL_ScanUnsignedLongLongInternalW(const wchar_t *text, int count, int radix, unsigned long long *valuep, bool *negativep)
+{
+    const unsigned long long ullong_max = ~0ULL;
+
+    const wchar_t *text_start = text;
+    const wchar_t *number_start = text_start;
+    unsigned long long value = 0;
+    bool negative = false;
+    bool overflow = false;
+
+    if (radix == 0 || (radix >= 2 && radix <= 36)) {
+        while (SDL_isspace(*text)) {
+            ++text;
+        }
+        if (*text == '-' || *text == '+') {
+            negative = *text == '-';
+            ++text;
+        }
+        if ((radix == 0 || radix == 16) && *text == '0') {
+            ++text;
+            if (*text == 'x' || *text == 'X') {
+                radix = 16;
+                ++text;
+            } else if (radix == 0) {
+                radix = 8;
+            }
+        } else if (radix == 0) {
+            radix = 10;
+        }
+        number_start = text;
+        do {
+            unsigned long long digit;
+            if (*text >= '0' && *text <= '9') {
+                digit = *text - '0';
+            } else if (radix > 10) {
+                if (*text >= 'A' && *text < 'A' + (radix - 10)) {
+                    digit = 10 + (*text - 'A');
+                } else if (*text >= 'a' && *text < 'a' + (radix - 10)) {
+                    digit = 10 + (*text - 'a');
+                } else {
+                    break;
+                }
+            } else {
+                break;
+            }
+            if (value != 0 && radix > ullong_max / value) {
+                overflow = true;
+            } else {
+                value *= radix;
+                if (digit > ullong_max - value) {
+                    overflow = true;
+                } else {
+                    value += digit;
+                }
+            }
+            ++text;
+        } while (count == 0 || (text - text_start) != count);
+    }
+    if (text == number_start) {
+        if (radix == 16 && text > text_start && (*(text - 1) == 'x' || *(text - 1) == 'X')) {
+            // the string was "0x"; consume the '0' but not the 'x'
+            --text;
+        } else {
+            // no number was parsed, and thus no characters were consumed
+            text = text_start;
+        }
+    }
+    if (overflow) {
+        if (negative) {
+            value = 0;
+        } else {
+            value = ullong_max;
+        }
+    } else if (value == 0) {
+        negative = false;
+    }
+    *valuep = value;
+    *negativep = negative;
+    return text - text_start;
+}
+#endif
+
+#if !defined(HAVE_VSSCANF) || !defined(HAVE_STRTOL)
+static size_t SDL_ScanLong(const char *text, int count, int radix, long *valuep)
+{
+    const unsigned long long_max = (~0UL) >> 1;
+    unsigned long long value;
+    bool negative;
+    size_t len = SDL_ScanUnsignedLongLongInternal(text, count, radix, &value, &negative);
+    if (negative) {
+        const unsigned long abs_long_min = long_max + 1;
+        if (value == 0 || value > abs_long_min) {
+            value = 0ULL - abs_long_min;
+        } else {
+            value = 0ULL - value;
+        }
+    } else if (value > long_max) {
+        value = long_max;
+    }
+    *valuep = (long)value;
+    return len;
+}
+#endif
+
+#ifndef HAVE_WCSTOL
+static size_t SDL_ScanLongW(const wchar_t *text, int count, int radix, long *valuep)
+{
+    const unsigned long long_max = (~0UL) >> 1;
+    unsigned long long value;
+    bool negative;
+    size_t len = SDL_ScanUnsignedLongLongInternalW(text, count, radix, &value, &negative);
+    if (negative) {
+        const unsigned long abs_long_min = long_max + 1;
+        if (value == 0 || value > abs_long_min) {
+            value = 0ULL - abs_long_min;
+        } else {
+            value = 0ULL - value;
+        }
+    } else if (value > long_max) {
+        value = long_max;
+    }
+    *valuep = (long)value;
+    return len;
+}
+#endif
+
+#if !defined(HAVE_VSSCANF) || !defined(HAVE_STRTOUL)
+static size_t SDL_ScanUnsignedLong(const char *text, int count, int radix, unsigned long *valuep)
+{
+    const unsigned long ulong_max = ~0UL;
+    unsigned long long value;
+    bool negative;
+    size_t len = SDL_ScanUnsignedLongLongInternal(text, count, radix, &value, &negative);
+    if (negative) {
+        if (value == 0 || value > ulong_max) {
+            value = ulong_max;
+        } else if (value == ulong_max) {
+            value = 1;
+        } else {
+            value = 0ULL - value;
+        }
+    } else if (value > ulong_max) {
+        value = ulong_max;
+    }
+    *valuep = (unsigned long)value;
+    return len;
+}
+#endif
+
+#ifndef HAVE_VSSCANF
+static size_t SDL_ScanUintPtrT(const char *text, uintptr_t *valuep)
+{
+    const uintptr_t uintptr_max = ~(uintptr_t)0;
+    unsigned long long value;
+    bool negative;
+    size_t len = SDL_ScanUnsignedLongLongInternal(text, 0, 16, &value, &negative);
+    if (negative) {
+        if (value == 0 || value > uintptr_max) {
+            value = uintptr_max;
+        } else if (value == uintptr_max) {
+            value = 1;
+        } else {
+            value = 0ULL - value;
+        }
+    } else if (value > uintptr_max) {
+        value = uintptr_max;
+    }
+    *valuep = (uintptr_t)value;
+    return len;
+}
+#endif
+
+#if !defined(HAVE_VSSCANF) || !defined(HAVE_STRTOLL)
+static size_t SDL_ScanLongLong(const char *text, int count, int radix, long long *valuep)
+{
+    const unsigned long long llong_max = (~0ULL) >> 1;
+    unsigned long long value;
+    bool negative;
+    size_t len = SDL_ScanUnsignedLongLongInternal(text, count, radix, &value, &negative);
+    if (negative) {
+        const unsigned long long abs_llong_min = llong_max + 1;
+        if (value == 0 || value > abs_llong_min) {
+            value = 0ULL - abs_llong_min;
+        } else {
+            value = 0ULL - value;
+        }
+    } else if (value > llong_max) {
+        value = llong_max;
+    }
+    *valuep = value;
+    return len;
+}
+#endif
+
+#if !defined(HAVE_VSSCANF) || !defined(HAVE_STRTOULL) || !defined(HAVE_STRTOD)
+static size_t SDL_ScanUnsignedLongLong(const char *text, int count, int radix, unsigned long long *valuep)
+{
+    const unsigned long long ullong_max = ~0ULL;
+    bool negative;
+    size_t len = SDL_ScanUnsignedLongLongInternal(text, count, radix, valuep, &negative);
+    if (negative) {
+        if (*valuep == 0) {
+            *valuep = ullong_max;
+        } else {
+            *valuep = 0ULL - *valuep;
+        }
+    }
+    return len;
+}
+#endif
+
+#if !defined(HAVE_VSSCANF) || !defined(HAVE_STRTOD)
+static size_t SDL_ScanFloat(const char *text, double *valuep)
+{
+    const char *text_start = text;
+    const char *number_start = text_start;
+    double value = 0.0;
+    bool negative = false;
+
+    while (SDL_isspace(*text)) {
+        ++text;
+    }
+    if (*text == '-' || *text == '+') {
+        negative = *text == '-';
+        ++text;
+    }
+    number_start = text;
+    if (SDL_isdigit(*text)) {
+        value += SDL_strtoull(text, (char **)(&text), 10);
+        if (*text == '.') {
+            double denom = 10;
+            ++text;
+            while (SDL_isdigit(*text)) {
+                value += (double)(*text - '0') / denom;
+                denom *= 10;
+                ++text;
+            }
+        }
+    }
+    if (text == number_start) {
+        // no number was parsed, and thus no characters were consumed
+        text = text_start;
+    } else if (negative) {
+        value = -value;
+    }
+    *valuep = value;
+    return text - text_start;
+}
+#endif
+
+int SDL_memcmp(const void *s1, const void *s2, size_t len)
+{
+#ifdef SDL_PLATFORM_VITA
+    /*
+      Using memcmp on NULL is UB per POSIX / C99 7.21.1/2.
+      But, both linux and bsd allow that, with an exception:
+      zero length strings are always identical, so NULLs are never dereferenced.
+      sceClibMemcmp on PSVita doesn't allow that, so we check ourselves.
+    */
+    if (len == 0) {
+        return 0;
+    }
+    return sceClibMemcmp(s1, s2, len);
+#elif defined(HAVE_MEMCMP)
+    return memcmp(s1, s2, len);
+#else
+    char *s1p = (char *)s1;
+    char *s2p = (char *)s2;
+    while (len--) {
+        if (*s1p != *s2p) {
+            return *s1p - *s2p;
+        }
+        ++s1p;
+        ++s2p;
+    }
+    return 0;
+#endif // HAVE_MEMCMP
+}
+
+size_t SDL_strlen(const char *string)
+{
+#ifdef HAVE_STRLEN
+    return strlen(string);
+#else
+    size_t len = 0;
+    while (*string++) {
+        ++len;
+    }
+    return len;
+#endif // HAVE_STRLEN
+}
+
+size_t SDL_strnlen(const char *string, size_t maxlen)
+{
+#ifdef HAVE_STRNLEN
+    return strnlen(string, maxlen);
+#else
+    size_t len = 0;
+    while (len < maxlen && *string++) {
+        ++len;
+    }
+    return len;
+#endif // HAVE_STRNLEN
+}
+
+size_t SDL_wcslen(const wchar_t *string)
+{
+#ifdef HAVE_WCSLEN
+    return wcslen(string);
+#else
+    size_t len = 0;
+    while (*string++) {
+        ++len;
+    }
+    return len;
+#endif // HAVE_WCSLEN
+}
+
+size_t SDL_wcsnlen(const wchar_t *string, size_t maxlen)
+{
+#ifdef HAVE_WCSNLEN
+    return wcsnlen(string, maxlen);
+#else
+    size_t len = 0;
+    while (len < maxlen && *string++) {
+        ++len;
+    }
+    return len;
+#endif // HAVE_WCSNLEN
+}
+
+size_t SDL_wcslcpy(SDL_OUT_Z_CAP(maxlen) wchar_t *dst, const wchar_t *src, size_t maxlen)
+{
+#ifdef HAVE_WCSLCPY
+    return wcslcpy(dst, src, maxlen);
+#else
+    size_t srclen = SDL_wcslen(src);
+    if (maxlen > 0) {
+        size_t len = SDL_min(srclen, maxlen - 1);
+        SDL_memcpy(dst, src, len * sizeof(wchar_t));
+        dst[len] = '\0';
+    }
+    return srclen;
+#endif // HAVE_WCSLCPY
+}
+
+size_t SDL_wcslcat(SDL_INOUT_Z_CAP(maxlen) wchar_t *dst, const wchar_t *src, size_t maxlen)
+{
+#ifdef HAVE_WCSLCAT
+    return wcslcat(dst, src, maxlen);
+#else
+    size_t dstlen = SDL_wcslen(dst);
+    size_t srclen = SDL_wcslen(src);
+    if (dstlen < maxlen) {
+        SDL_wcslcpy(dst + dstlen, src, maxlen - dstlen);
+    }
+    return dstlen + srclen;
+#endif // HAVE_WCSLCAT
+}
+
+wchar_t *SDL_wcsdup(const wchar_t *string)
+{
+    size_t len = ((SDL_wcslen(string) + 1) * sizeof(wchar_t));
+    wchar_t *newstr = (wchar_t *)SDL_malloc(len);
+    if (newstr) {
+        SDL_memcpy(newstr, string, len);
+    }
+    return newstr;
+}
+
+wchar_t *SDL_wcsnstr(const wchar_t *haystack, const wchar_t *needle, size_t maxlen)
+{
+    size_t length = SDL_wcslen(needle);
+    if (length == 0) {
+        return (wchar_t *)haystack;
+    }
+    while (maxlen >= length && *haystack) {
+        if (maxlen >= length && SDL_wcsncmp(haystack, needle, length) == 0) {
+            return (wchar_t *)haystack;
+        }
+        ++haystack;
+        --maxlen;
+    }
+    return NULL;
+}
+
+wchar_t *SDL_wcsstr(const wchar_t *haystack, const wchar_t *needle)
+{
+#ifdef HAVE_WCSSTR
+    return SDL_const_cast(wchar_t *, wcsstr(haystack, needle));
+#else
+    return SDL_wcsnstr(haystack, needle, SDL_wcslen(haystack));
+#endif // HAVE_WCSSTR
+}
+
+int SDL_wcscmp(const wchar_t *str1, const wchar_t *str2)
+{
+#ifdef HAVE_WCSCMP
+    return wcscmp(str1, str2);
+#else
+    while (*str1 && *str2) {
+        if (*str1 != *str2) {
+            break;
+        }
+        ++str1;
+        ++str2;
+    }
+    return *str1 - *str2;
+#endif // HAVE_WCSCMP
+}
+
+int SDL_wcsncmp(const wchar_t *str1, const wchar_t *str2, size_t maxlen)
+{
+#ifdef HAVE_WCSNCMP
+    return wcsncmp(str1, str2, maxlen);
+#else
+    while (*str1 && *str2 && maxlen) {
+        if (*str1 != *str2) {
+            break;
+        }
+        ++str1;
+        ++str2;
+        --maxlen;
+    }
+    if (!maxlen) {
+        return 0;
+    }
+    return *str1 - *str2;
+
+#endif // HAVE_WCSNCMP
+}
+
+int SDL_wcscasecmp(const wchar_t *wstr1, const wchar_t *wstr2)
+{
+#if (SDL_SIZEOF_WCHAR_T == 2)
+    const Uint16 *str1 = (const Uint16 *) wstr1;
+    const Uint16 *str2 = (const Uint16 *) wstr2;
+    UNICODE_STRCASECMP(16, 2, 2, (void) str1start, (void) str2start);  // always NULL-terminated, no need to adjust lengths.
+#elif (SDL_SIZEOF_WCHAR_T == 4)
+    const Uint32 *str1 = (const Uint32 *) wstr1;
+    const Uint32 *str2 = (const Uint32 *) wstr2;
+    UNICODE_STRCASECMP(32, 1, 1, (void) str1start, (void) str2start);  // always NULL-terminated, no need to adjust lengths.
+#else
+    #error Unexpected wchar_t size
+    return -1;
+#endif
+}
+
+int SDL_wcsncasecmp(const wchar_t *wstr1, const wchar_t *wstr2, size_t maxlen)
+{
+    size_t slen1 = maxlen;
+    size_t slen2 = maxlen;
+
+#if (SDL_SIZEOF_WCHAR_T == 2)
+    const Uint16 *str1 = (const Uint16 *) wstr1;
+    const Uint16 *str2 = (const Uint16 *) wstr2;
+    UNICODE_STRCASECMP(16, slen1, slen2, slen1 -= (size_t) (str1 - str1start), slen2 -= (size_t) (str2 - str2start));
+#elif (SDL_SIZEOF_WCHAR_T == 4)
+    const Uint32 *str1 = (const Uint32 *) wstr1;
+    const Uint32 *str2 = (const Uint32 *) wstr2;
+    UNICODE_STRCASECMP(32, slen1, slen2, slen1 -= (size_t) (str1 - str1start), slen2 -= (size_t) (str2 - str2start));
+#else
+    #error Unexpected wchar_t size
+    return -1;
+#endif
+}
+
+long SDL_wcstol(const wchar_t *string, wchar_t **endp, int base)
+{
+#ifdef HAVE_WCSTOL
+    return wcstol(string, endp, base);
+#else
+    long value = 0;
+    size_t len = SDL_ScanLongW(string, 0, base, &value);
+    if (endp) {
+        *endp = (wchar_t *)string + len;
+    }
+    return value;
+#endif // HAVE_WCSTOL
+}
+
+size_t SDL_strlcpy(SDL_OUT_Z_CAP(maxlen) char *dst, const char *src, size_t maxlen)
+{
+#ifdef HAVE_STRLCPY
+    return strlcpy(dst, src, maxlen);
+#else
+    size_t srclen = SDL_strlen(src);
+    if (maxlen > 0) {
+        size_t len = SDL_min(srclen, maxlen - 1);
+        SDL_memcpy(dst, src, len);
+        dst[len] = '\0';
+    }
+    return srclen;
+#endif // HAVE_STRLCPY
+}
+
+size_t SDL_utf8strlcpy(SDL_OUT_Z_CAP(dst_bytes) char *dst, const char *src, size_t dst_bytes)
+{
+    size_t bytes = 0;
+
+        if (dst_bytes > 0) {
+                size_t src_bytes = SDL_strlen(src);
+                size_t i = 0;
+                size_t trailing_bytes = 0;
+
+                bytes = SDL_min(src_bytes, dst_bytes - 1);
+                if (bytes) {
+                        unsigned char c = (unsigned char)src[bytes - 1];
+                        if (UTF8_IsLeadByte(c)) {
+                                --bytes;
+                        } else if (UTF8_IsTrailingByte(c)) {
+                                for (i = bytes - 1; i != 0; --i) {
+                                        c = (unsigned char)src[i];
+                                        trailing_bytes = UTF8_GetTrailingBytes(c);
+                                        if (trailing_bytes) {
+                                                if ((bytes - i) != (trailing_bytes + 1)) {
+                                                        bytes = i;
+                                                }
+
+                                                break;
+                                        }
+                                }
+                        }
+                        SDL_memcpy(dst, src, bytes);
+                }
+                dst[bytes] = '\0';
+        }
+
+    return bytes;
+}
+
+size_t SDL_utf8strlen(const char *str)
+{
+    size_t result = 0;
+    while (SDL_StepUTF8(&str, NULL)) {
+        result++;
+    }
+    return result;
+}
+
+size_t SDL_utf8strnlen(const char *str, size_t bytes)
+{
+    size_t result = 0;
+    while (SDL_StepUTF8(&str, &bytes)) {
+        result++;
+    }
+    return result;
+}
+
+size_t SDL_strlcat(SDL_INOUT_Z_CAP(maxlen) char *dst, const char *src, size_t maxlen)
+{
+#ifdef HAVE_STRLCAT
+    return strlcat(dst, src, maxlen);
+#else
+    size_t dstlen = SDL_strlen(dst);
+    size_t srclen = SDL_strlen(src);
+    if (dstlen < maxlen) {
+        SDL_strlcpy(dst + dstlen, src, maxlen - dstlen);
+    }
+    return dstlen + srclen;
+#endif // HAVE_STRLCAT
+}
+
+char *SDL_strdup(const char *string)
+{
+    size_t len = SDL_strlen(string) + 1;
+    char *newstr = (char *)SDL_malloc(len);
+    if (newstr) {
+        SDL_memcpy(newstr, string, len);
+    }
+    return newstr;
+}
+
+char *SDL_strndup(const char *string, size_t maxlen)
+{
+    size_t len = SDL_strnlen(string, maxlen);
+    char *newstr = (char *)SDL_malloc(len + 1);
+    if (newstr) {
+        SDL_memcpy(newstr, string, len);
+        newstr[len] = '\0';
+    }
+    return newstr;
+}
+
+char *SDL_strrev(char *string)
+{
+#ifdef HAVE__STRREV
+    return _strrev(string);
+#else
+    size_t len = SDL_strlen(string);
+    char *a = &string[0];
+    char *b = &string[len - 1];
+    len /= 2;
+    while (len--) {
+        const char c = *a; // NOLINT(clang-analyzer-core.uninitialized.Assign)
+        *a++ = *b;
+        *b-- = c;
+    }
+    return string;
+#endif // HAVE__STRREV
+}
+
+char *SDL_strupr(char *string)
+{
+    char *bufp = string;
+    while (*bufp) {
+        *bufp = (char)SDL_toupper((unsigned char)*bufp);
+        ++bufp;
+    }
+    return string;
+}
+
+char *SDL_strlwr(char *string)
+{
+    char *bufp = string;
+    while (*bufp) {
+        *bufp = (char)SDL_tolower((unsigned char)*bufp);
+        ++bufp;
+    }
+    return string;
+}
+
+char *SDL_strchr(const char *string, int c)
+{
+#ifdef HAVE_STRCHR
+    return SDL_const_cast(char *, strchr(string, c));
+#elif defined(HAVE_INDEX)
+    return SDL_const_cast(char *, index(string, c));
+#else
+    while (*string) {
+        if (*string == c) {
+            return (char *)string;
+        }
+        ++string;
+    }
+    if (c == '\0') {
+        return (char *)string;
+    }
+    return NULL;
+#endif // HAVE_STRCHR
+}
+
+char *SDL_strrchr(const char *string, int c)
+{
+#ifdef HAVE_STRRCHR
+    return SDL_const_cast(char *, strrchr(string, c));
+#elif defined(HAVE_RINDEX)
+    return SDL_const_cast(char *, rindex(string, c));
+#else
+    const char *bufp = string + SDL_strlen(string);
+    while (bufp >= string) {
+        if (*bufp == c) {
+            return (char *)bufp;
+        }
+        --bufp;
+    }
+    return NULL;
+#endif // HAVE_STRRCHR
+}
+
+char *SDL_strnstr(const char *haystack, const char *needle, size_t maxlen)
+{
+#ifdef HAVE_STRNSTR
+    return SDL_const_cast(char *, strnstr(haystack, needle, maxlen));
+#else
+    size_t length = SDL_strlen(needle);
+    if (length == 0) {
+        return (char *)haystack;
+    }
+    while (maxlen >= length && *haystack) {
+        if (SDL_strncmp(haystack, needle, length) == 0) {
+            return (char *)haystack;
+        }
+        ++haystack;
+        --maxlen;
+    }
+    return NULL;
+#endif // HAVE_STRSTR
+}
+
+char *SDL_strstr(const char *haystack, const char *needle)
+{
+#ifdef HAVE_STRSTR
+    return SDL_const_cast(char *, strstr(haystack, needle));
+#else
+    return SDL_strnstr(haystack, needle, SDL_strlen(haystack));
+#endif // HAVE_STRSTR
+}
+
+char *SDL_strcasestr(const char *haystack, const char *needle)
+{
+    const size_t length = SDL_strlen(needle);
+    do {
+        if (SDL_strncasecmp(haystack, needle, length) == 0) {
+            return (char *)haystack;
+        }
+    } while (SDL_StepUTF8(&haystack, NULL));  // move ahead by a full codepoint at a time, regardless of bytes.
+
+    return NULL;
+}
+
+#if !defined(HAVE__LTOA) || !defined(HAVE__I64TOA) || \
+    !defined(HAVE__ULTOA) || !defined(HAVE__UI64TOA)
+static const char ntoa_table[] = {
+    '0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
+    'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J',
+    'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T',
+    'U', 'V', 'W', 'X', 'Y', 'Z'
+};
+#endif // ntoa() conversion table
+
+char *SDL_itoa(int value, char *string, int radix)
+{
+#ifdef HAVE_ITOA
+    return itoa(value, string, radix);
+#else
+    return SDL_ltoa((long)value, string, radix);
+#endif // HAVE_ITOA
+}
+
+char *SDL_uitoa(unsigned int value, char *string, int radix)
+{
+#ifdef HAVE__UITOA
+    return _uitoa(value, string, radix);
+#else
+    return SDL_ultoa((unsigned long)value, string, radix);
+#endif // HAVE__UITOA
+}
+
+char *SDL_ltoa(long value, char *string, int radix)
+{
+#ifdef HAVE__LTOA
+    return _ltoa(value, string, radix);
+#else
+    char *bufp = string;
+
+    if (value < 0) {
+        *bufp++ = '-';
+        SDL_ultoa(-value, bufp, radix);
+    } else {
+        SDL_ultoa(value, bufp, radix);
+    }
+
+    return string;
+#endif // HAVE__LTOA
+}
+
+char *SDL_ultoa(unsigned long value, char *string, int radix)
+{
+#ifdef HAVE__ULTOA
+    return _ultoa(value, string, radix);
+#else
+    char *bufp = string;
+
+    if (value) {
+        while (value > 0) {
+            *bufp++ = ntoa_table[value % radix];
+            value /= radix;
+        }
+    } else {
+        *bufp++ = '0';
+    }
+    *bufp = '\0';
+
+    // The numbers went into the string backwards. :)
+    SDL_strrev(string);
+
+    return string;
+#endif // HAVE__ULTOA
+}
+
+char *SDL_lltoa(long long value, char *string, int radix)
+{
+#ifdef HAVE__I64TOA
+    return _i64toa(value, string, radix);
+#else
+    char *bufp = string;
+
+    if (value < 0) {
+        *bufp++ = '-';
+        SDL_ulltoa(-value, bufp, radix);
+    } else {
+        SDL_ulltoa(value, bufp, radix);
+    }
+
+    return string;
+#endif // HAVE__I64TOA
+}
+
+char *SDL_ulltoa(unsigned long long value, char *string, int radix)
+{
+#ifdef HAVE__UI64TOA
+    return _ui64toa(value, string, radix);
+#else
+    char *bufp = string;
+
+    if (value) {
+        while (value > 0) {
+            *bufp++ = ntoa_table[value % radix];
+            value /= radix;
+        }
+    } else {
+        *bufp++ = '0';
+    }
+    *bufp = '\0';
+
+    // The numbers went into the string backwards. :)
+    SDL_strrev(string);
+
+    return string;
+#endif // HAVE__UI64TOA
+}
+
+int SDL_atoi(const char *string)
+{
+#ifdef HAVE_ATOI
+    return atoi(string);
+#else
+    return SDL_strtol(string, NULL, 10);
+#endif // HAVE_ATOI
+}
+
+double SDL_atof(const char *string)
+{
+#ifdef HAVE_ATOF
+    return atof(string);
+#else
+    return SDL_strtod(string, NULL);
+#endif // HAVE_ATOF
+}
+
+long SDL_strtol(const char *string, char **endp, int base)
+{
+#ifdef HAVE_STRTOL
+    return strtol(string, endp, base);
+#else
+    long value = 0;
+    size_t len = SDL_ScanLong(string, 0, base, &value);
+    if (endp) {
+        *endp = (char *)string + len;
+    }
+    return value;
+#endif // HAVE_STRTOL
+}
+
+unsigned long SDL_strtoul(const char *string, char **endp, int base)
+{
+#ifdef HAVE_STRTOUL
+    return strtoul(string, endp, base);
+#else
+    unsigned long value = 0;
+    size_t len = SDL_ScanUnsignedLong(string, 0, base, &value);
+    if (endp) {
+        *endp = (char *)string + len;
+    }
+    return value;
+#endif // HAVE_STRTOUL
+}
+
+long long SDL_strtoll(const char *string, char **endp, int base)
+{
+#ifdef HAVE_STRTOLL
+    return strtoll(string, endp, base);
+#else
+    long long value = 0;
+    size_t len = SDL_ScanLongLong(string, 0, base, &value);
+    if (endp) {
+        *endp = (char *)string + len;
+    }
+    return value;
+#endif // HAVE_STRTOLL
+}
+
+unsigned long long SDL_strtoull(const char *string, char **endp, int base)
+{
+#ifdef HAVE_STRTOULL
+    return strtoull(string, endp, base);
+#else
+    unsigned long long value = 0;
+    size_t len = SDL_ScanUnsignedLongLong(string, 0, base, &value);
+    if (endp) {
+        *endp = (char *)string + len;
+    }
+    return value;
+#endif // HAVE_STRTOULL
+}
+
+double SDL_strtod(const char *string, char **endp)
+{
+#ifdef HAVE_STRTOD
+    return strtod(string, endp);
+#else
+    double value;
+    size_t len = SDL_ScanFloat(string, &value);
+    if (endp) {
+        *endp = (char *)string + len;
+    }
+    return value;
+#endif // HAVE_STRTOD
+}
+
+int SDL_strcmp(const char *str1, const char *str2)
+{
+#ifdef HAVE_STRCMP
+    return strcmp(str1, str2);
+#else
+    int result;
+
+    while (1) {
+        result = ((unsigned char)*str1 - (unsigned char)*str2);
+        if (result != 0 || (*str1 == '\0' /* && *str2 == '\0'*/)) {
+            break;
+        }
+        ++str1;
+        ++str2;
+    }
+    return result;
+#endif // HAVE_STRCMP
+}
+
+int SDL_strncmp(const char *str1, const char *str2, size_t maxlen)
+{
+#ifdef HAVE_STRNCMP
+    return strncmp(str1, str2, maxlen);
+#else
+    int result = 0;
+
+    while (maxlen) {
+        result = (int)(unsigned char)*str1 - (unsigned char)*str2;
+        if (result != 0 || *str1 == '\0' /* && *str2 == '\0'*/) {
+            break;
+        }
+        ++str1;
+        ++str2;
+        --maxlen;
+    }
+    return result;
+#endif // HAVE_STRNCMP
+}
+
+int SDL_strcasecmp(const char *str1, const char *str2)
+{
+    UNICODE_STRCASECMP(8, 4, 4, (void) str1start, (void) str2start);  // always NULL-terminated, no need to adjust lengths.
+}
+
+int SDL_strncasecmp(const char *str1, const char *str2, size_t maxlen)
+{
+    size_t slen1 = maxlen;
+    size_t slen2 = maxlen;
+    UNICODE_STRCASECMP(8, slen1, slen2, slen1 -= (size_t) (str1 - ((const char *) str1start)), slen2 -= (size_t) (str2 - ((const char *) str2start)));
+}
+
+int SDL_sscanf(const char *text, SDL_SCANF_FORMAT_STRING const char *fmt, ...)
+{
+    int rc;
+    va_list ap;
+    va_start(ap, fmt);
+    rc = SDL_vsscanf(text, fmt, ap);
+    va_end(ap);
+    return rc;
+}
+
+#ifdef HAVE_VSSCANF
+int SDL_vsscanf(const char *text, const char *fmt, va_list ap)
+{
+    return vsscanf(text, fmt, ap);
+}
+#else
+static bool CharacterMatchesSet(char c, const char *set, size_t set_len)
+{
+    bool invert = false;
+    bool result = false;
+
+    if (*set == '^') {
+        invert = true;
+        ++set;
+        --set_len;
+    }
+    while (set_len > 0 && !result) {
+        if (set_len >= 3 && set[1] == '-') {
+            char low_char = SDL_min(set[0], set[2]);
+            char high_char = SDL_max(set[0], set[2]);
+            if (c >= low_char && c <= high_char) {
+                result = true;
+            }
+            set += 3;
+            set_len -= 3;
+        } else {
+            if (c == *set) {
+                result = true;
+            }
+            ++set;
+            --set_len;
+        }
+    }
+    if (invert) {
+        result = !result;
+    }
+    return result;
+}
+
+// NOLINTNEXTLINE(readability-non-const-parameter)
+int SDL_vsscanf(const char *text, SDL_SCANF_FORMAT_STRING const char *fmt, va_list ap)
+{
+    const char *start = text;
+    int result = 0;
+
+    if (!text || !*text) {
+        return -1;
+    }
+
+    while (*fmt) {
+        if (*fmt == ' ') {
+            while (SDL_isspace((unsigned char)*text)) {
+                ++text;
+            }
+            ++fmt;
+            continue;
+        }
+        if (*fmt == '%') {
+            bool done = false;
+            long count = 0;
+            int radix = 10;
+            enum
+            {
+                DO_SHORT,
+                DO_INT,
+                DO_LONG,
+                DO_LONGLONG,
+                DO_SIZE_T
+            } inttype = DO_INT;
+            size_t advance;
+            bool suppress = false;
+
+            ++fmt;
+            if (*fmt == '%') {
+                if (*text == '%') {
+                    ++text;
+                    ++fmt;
+                    continue;
+                }
+                break;
+            }
+            if (*fmt == '*') {
+                suppress = true;
+                ++fmt;
+            }
+            fmt += SDL_ScanLong(fmt, 0, 10, &count);
+
+            if (*fmt == 'c') {
+                if (!count) {
+                    count = 1;
+                }
+                if (suppress) {
+                    while (count--) {
+                        ++text;
+                    }
+                } else {
+                    char *valuep = va_arg(ap, char *);
+                    while (count--) {
+                        *valuep++ = *text++;
+                    }
+                    ++result;
+                }
+                continue;
+            }
+
+            while (SDL_isspace((unsigned char)*text)) {
+                ++text;
+            }
+
+            // FIXME: implement more of the format specifiers
+            while (!done) {
+                switch (*fmt) {
+                case '*':
+                    suppress = true;
+                    break;
+                case 'h':
+                    if (inttype == DO_INT) {
+                        inttype = DO_SHORT;
+                    } else if (inttype > DO_SHORT) {
+                        ++inttype;
+                    }
+                    break;
+                case 'l':
+                    if (inttype < DO_LONGLONG) {
+                        ++inttype;
+                    }
+                    break;
+                case 'I':
+                    if (SDL_strncmp(fmt, "I64", 3) == 0) {
+                        fmt += 2;
+                        inttype = DO_LONGLONG;
+                    }
+                    break;
+                case 'z':
+                    inttype = DO_SIZE_T;
+                    break;
+                case 'i':
+                {
+                    int index = 0;
+                    if (text[index] == '-') {
+                        ++index;
+                    }
+                    if (text[index] == '0') {
+                        if (SDL_tolower((unsigned char)text[index + 1]) == 'x') {
+                            radix = 16;
+                        } else {
+                            radix = 8;
+                        }
+                    }
+                }
+                    SDL_FALLTHROUGH;
+                case 'd':
+                    if (inttype == DO_LONGLONG) {
+                        long long value = 0;
+                        advance = SDL_ScanLongLong(text, count, radix, &value);
+                        text += advance;
+                        if (advance && !suppress) {
+                            Sint64 *valuep = va_arg(ap, Sint64 *);
+                            *valuep = value;
+                            ++result;
+                        }
+                    } else if (inttype == DO_SIZE_T) {
+                        long long value = 0;
+                        advance = SDL_ScanLongLong(text, count, radix, &value);
+                        text += advance;
+                        if (advance && !suppress) {
+                            size_t *valuep = va_arg(ap, size_t *);
+                            *valuep = (size_t)value;
+                            ++result;
+                        }
+                    } else {
+                        long value = 0;
+                        advance = SDL_ScanLong(text, count, radix, &value);
+                        text += advance;
+                        if (advance && !suppress) {
+                            switch (inttype) {
+                            case DO_SHORT:
+                            {
+                                short *valuep = va_arg(ap, short *);
+                                *valuep = (short)value;
+                            } break;
+                            case DO_INT:
+                            {
+                                int *valuep = va_arg(ap, int *);
+                                *valuep = (int)value;
+                            } break;
+                            case DO_LONG:
+                            {
+                                long *valuep = va_arg(ap, long *);
+                                *valuep = value;
+                            } break;
+                            case DO_LONGLONG:
+                            case DO_SIZE_T:
+                                // Handled above
+                                break;
+                            }
+                            ++result;
+                        }
+                    }
+                    done = true;
+                    break;
+                case 'o':
+                    if (radix == 10) {
+                        radix = 8;
+                    }
+                    SDL_FALLTHROUGH;
+                case 'x':
+                case 'X':
+                    if (radix == 10) {
+                        radix = 16;
+                    }
+                    SDL_FALLTHROUGH;
+                case 'u':
+                    if (inttype == DO_LONGLONG) {
+                        unsigned long long value = 0;
+                        advance = SDL_ScanUnsignedLongLong(text, count, radix, &value);
+                        text += advance;
+                        if (advance && !suppress) {
+                            Uint64 *valuep = va_arg(ap, Uint64 *);
+                            *valuep = value;
+                            ++result;
+                        }
+                    } else if (inttype == DO_SIZE_T) {
+                        unsigned long long value = 0;
+                        advance = SDL_ScanUnsignedLongLong(text, count, radix, &value);
+                        text += advance;
+                        if (advance && !suppress) {
+                            size_t *valuep = va_arg(ap, size_t *);
+                            *valuep = (size_t)value;
+                            ++result;
+                        }
+                    } else {
+                        unsigned long value = 0;
+                        advance = SDL_ScanUnsignedLong(text, count, radix, &value);
+                        text += advance;
+                        if (advance && !suppress) {
+                            switch (inttype) {
+                            case DO_SHORT:
+                            {
+                                short *valuep = va_arg(ap, short *);
+                                *valuep = (short)value;
+                            } break;
+                            case DO_INT:
+                            {
+                                int *valuep = va_arg(ap, int *);
+                                *valuep = (int)value;
+                            } break;
+                            case DO_LONG:
+                            {
+                                long *valuep = va_arg(ap, long *);
+                                *valuep = value;
+                            } break;
+                            case DO_LONGLONG:
+                            case DO_SIZE_T:
+                                // Handled above
+                                break;
+                            }
+                            ++result;
+                        }
+                    }
+                    done = true;
+                    break;
+                case 'p':
+                {
+                    uintptr_t value = 0;
+                    advance = SDL_ScanUintPtrT(text, &value);
+                    text += advance;
+                    if (advance && !suppress) {
+                        void **valuep = va_arg(ap, void **);
+                        *valuep = (void *)value;
+                        ++result;
+                    }
+                }
+                    done = true;
+                    break;
+                case 'f':
+                {
+                    double value = 0.0;
+                    advance = SDL_ScanFloat(text, &value);
+                    text += advance;
+                    if (advance && !suppress) {
+                        float *valuep = va_arg(ap, float *);
+                        *valuep = (float)value;
+                        ++result;
+                    }
+                }
+                    done = true;
+                    break;
+                case 's':
+                    if (suppress) {
+                        while (!SDL_isspace((unsigned char)*text)) {
+                            ++text;
+                            if (count) {
+                                if (--count == 0) {
+                                    break;
+                                }
+                            }
+                        }
+                    } else {
+                        char *valuep = va_arg(ap, char *);
+                        while (!SDL_isspace((unsigned char)*text)) {
+                            *valuep++ = *text++;
+                            if (count) {
+                                if (--count == 0) {
+                                    break;
+                                }
+                            }
+                        }
+                        *valuep = '\0';
+                        ++result;
+                    }
+                    done = true;
+                    break;
+                case 'n':
+                    switch (inttype) {
+                    case DO_SHORT:
+                    {
+                        short *valuep = va_arg(ap, short *);
+                        *valuep = (short)(text - start);
+                    } break;
+                    case DO_INT:
+                    {
+                        int *valuep = va_arg(ap, int *);
+                        *valuep = (int)(text - start);
+                    } break;
+                    case DO_LONG:
+                    {
+                        long *valuep = va_arg(ap, long *);
+                        *valuep = (long)(text - start);
+                    } break;
+                    case DO_LONGLONG:
+                    {
+                        long long *valuep = va_arg(ap, long long *);
+                        *valuep = (long long)(text - start);
+                    } break;
+                    case DO_SIZE_T:
+                    {
+                        size_t *valuep = va_arg(ap, size_t *);
+                        *valuep = (size_t)(text - start);
+                    } break;
+                    }
+                    done = true;
+                    break;
+                case '[':
+                {
+                    const char *set = fmt + 1;
+                    while (*fmt && *fmt != ']') {
+                        ++fmt;
+                    }
+                    if (*fmt) {
+                        size_t set_len = (fmt - set);
+                        if (suppress) {
+                            while (CharacterMatchesSet(*text, set, set_len)) {
+                                ++text;
+                                if (count) {
+                                    if (--count == 0) {
+                                        break;
+                                    }
+                                }
+                            }
+                        } else {
+                            bool had_match = false;
+                            char *valuep = va_arg(ap, char *);
+                            while (CharacterMatchesSet(*text, set, set_len)) {
+                                had_match = true;
+                                *valuep++ = *text++;
+                                if (count) {
+                                    if (--count == 0) {
+                                        break;
+                                    }
+                                }
+                            }
+                            *valuep = '\0';
+                            if (had_match) {
+                                ++result;
+                            }
+                        }
+                    }
+                }
+                    done = true;
+                    break;
+                default:
+                    done = true;
+                    break;
+                }
+                ++fmt;
+            }
+            continue;
+        }
+        if (*text == *fmt) {
+            ++text;
+            ++fmt;
+            continue;
+        }
+        // Text didn't match format specifier
+        break;
+    }
+
+    return result;
+}
+#endif // HAVE_VSSCANF
+
+int SDL_snprintf(SDL_OUT_Z_CAP(maxlen) char *text, size_t maxlen, SDL_PRINTF_FORMAT_STRING const char *fmt, ...)
+{
+    va_list ap;
+    int result;
+
+    va_start(ap, fmt);
+    result = SDL_vsnprintf(text, maxlen, fmt, ap);
+    va_end(ap);
+
+    return result;
+}
+
+int SDL_swprintf(SDL_OUT_Z_CAP(maxlen) wchar_t *text, size_t maxlen, SDL_PRINTF_FORMAT_STRING const wchar_t *fmt, ...)
+{
+    va_list ap;
+    int result;
+
+    va_start(ap, fmt);
+    result = SDL_vswprintf(text, maxlen, fmt, ap);
+    va_end(ap);
+
+    return result;
+}
+
+#if defined(HAVE_LIBC) && defined(__WATCOMC__)
+// _vsnprintf() doesn't ensure nul termination
+int SDL_vsnprintf(SDL_OUT_Z_CAP(maxlen) char *text, size_t maxlen, const char *fmt, va_list ap)
+{
+    int result;
+    if (!fmt) {
+        fmt = "";
+    }
+    result = _vsnprintf(text, maxlen, fmt, ap);
+    if (maxlen > 0) {
+        text[maxlen - 1] = '\0';
+    }
+    if (result < 0) {
+        result = (int)maxlen;
+    }
+    return result;
+}
+#elif defined(HAVE_VSNPRINTF)
+int SDL_vsnprintf(SDL_OUT_Z_CAP(maxlen) char *text, size_t maxlen, const char *fmt, va_list ap)
+{
+    if (!fmt) {
+        fmt = "";
+    }
+    return vsnprintf(text, maxlen, fmt, ap);
+}
+#else
+#define TEXT_AND_LEN_ARGS (length < maxlen) ? &text[length] : NULL, (length < maxlen) ? (maxlen - length) : 0
+
+// FIXME: implement more of the format specifiers
+typedef enum
+{
+    SDL_CASE_NOCHANGE,
+    SDL_CASE_LOWER,
+    SDL_CASE_UPPER
+} SDL_letter_case;
+
+typedef struct
+{
+    bool left_justify;
+    bool force_sign;
+    bool force_type; // for now: used only by float printer, ignored otherwise.
+    bool pad_zeroes;
+    SDL_letter_case force_case;
+    int width;
+    int radix;
+    int precision;
+} SDL_FormatInfo;
+
+static size_t SDL_PrintString(char *text, size_t maxlen, SDL_FormatInfo *info, const char *string)
+{
+    const char fill = (info && info->pad_zeroes) ? '0' : ' ';
+    size_t width = 0;
+    size_t filllen = 0;
+    size_t length = 0;
+    size_t slen, sz;
+
+    if (!string) {
+        string = "(null)";
+    }
+
+    sz = SDL_strlen(string);
+    if (info && info->width > 0 && (size_t)info->width > sz) {
+        width = info->width - sz;
+        if (info->precision >= 0 && (size_t)info->precision < sz) {
+            width += sz - (size_t)info->precision;
+        }
+
+        filllen = SDL_min(width, maxlen);
+        if (!info->left_justify) {
+            SDL_memset(text, fill, filllen);
+            text += filllen;
+            maxlen -= filllen;
+            length += width;
+            filllen = 0;
+        }
+    }
+
+    SDL_strlcpy(text, string, maxlen);
+    length += sz;
+
+    if (filllen > 0) {
+        SDL_memset(text + sz, fill, filllen);
+        length += width;
+    }
+
+    if (info) {
+        if (info->precision >= 0 && (size_t)info->precision < sz) {
+            slen = (size_t)info->precision;
+            if (slen < maxlen) {
+                text[slen] = '\0';
+            }
+            length -= (sz - slen);
+        }
+        if (maxlen > 1) {
+            if (info->force_case == SDL_CASE_LOWER) {
+                SDL_strlwr(text);
+            } else if (info->force_case == SDL_CASE_UPPER) {
+                SDL_strupr(text);
+            }
+        }
+    }
+    return length;
+}
+
+static size_t SDL_PrintStringW(char *text, size_t maxlen, SDL_FormatInfo *info, const wchar_t *wide_string)
+{
+    size_t length = 0;
+    if (wide_string) {
+        char *string = SDL_iconv_string("UTF-8", "WCHAR_T", (char *)(wide_string), (SDL_wcslen(wide_string) + 1) * sizeof(*wide_string));
+        length = SDL_PrintString(TEXT_AND_LEN_ARGS, info, string);
+        SDL_free(string);
+    } else {
+        length = SDL_PrintString(TEXT_AND_LEN_ARGS, info, NULL);
+    }
+    return length;
+}
+
+static void SDL_IntPrecisionAdjust(char *num, size_t maxlen, SDL_FormatInfo *info)
+{ // left-pad num with zeroes.
+    size_t sz, pad, have_sign;
+
+    if (!info) {
+        return;
+    }
+
+    have_sign = 0;
+    if (*num == '-' || *num == '+') {
+        have_sign = 1;
+        ++num;
+        --maxlen;
+    }
+    sz = SDL_strlen(num);
+    if (info->precision > 0 && sz < (size_t)info->precision) {
+        pad = (size_t)info->precision - sz;
+        if (pad + sz + 1 <= maxlen) { // otherwise ignore the precision
+            SDL_memmove(num + pad, num, sz + 1);
+            SDL_memset(num, '0', pad);
+        }
+    }
+    info->precision = -1; // so that SDL_PrintString() doesn't make a mess.
+
+    if (info->pad_zeroes && info->width > 0 && (size_t)info->width > sz + have_sign) {
+        /* handle here: spaces are added before the sign
+           but zeroes must be placed _after_ the sign. */
+        // sz hasn't changed: we ignore pad_zeroes if a precision is given.
+        pad = (size_t)info->width - sz - have_sign;
+        if (pad + sz + 1 <= maxlen) {
+            SDL_memmove(num + pad, num, sz + 1);
+            SDL_memset(num, '0', pad);
+        }
+        info->width = 0; // so that SDL_PrintString() doesn't make a mess.
+    }
+}
+
+static size_t SDL_PrintLong(char *text, size_t maxlen, SDL_FormatInfo *info, long value)
+{
+    char num[130], *p = num;
+
+    if (info->force_sign && value >= 0L) {
+        *p++ = '+';
+    }
+
+    SDL_ltoa(value, p, info ? info->radix : 10);
+    SDL_IntPrecisionAdjust(num, sizeof(num), info);
+    return SDL_PrintString(text, maxlen, info, num);
+}
+
+static size_t SDL_PrintUnsignedLong(char *text, size_t maxlen, SDL_FormatInfo *info, unsigned long value)
+{
+    char num[130];
+
+    SDL_ultoa(value, num, info ? info->radix : 10);
+    SDL_IntPrecisionAdjust(num, sizeof(num), info);
+    return SDL_PrintString(text, maxlen, info, num);
+}
+
+static size_t SDL_PrintLongLong(char *text, size_t maxlen, SDL_FormatInfo *info, long long value)
+{
+    char num[130], *p = num;
+
+    if (info->force_sign && value >= (Sint64)0) {
+        *p++ = '+';
+    }
+
+    SDL_lltoa(value, p, info ? info->radix : 10);
+    SDL_IntPrecisionAdjust(num, sizeof(num), info);
+    return SDL_PrintString(text, maxlen, info, num);
+}
+
+static size_t SDL_PrintUnsignedLongLong(char *text, size_t maxlen, SDL_FormatInfo *info, unsigned long long value)
+{
+    char num[130];
+
+    SDL_ulltoa(value, num, info ? info->radix : 10);
+    SDL_IntPrecisionAdjust(num, sizeof(num), info);
+    return SDL_PrintString(text, maxlen, info, num);
+}
+
+static size_t SDL_PrintFloat(char *text, size_t maxlen, SDL_FormatInfo *info, double arg, bool g)
+{
+    char num[327];
+    size_t length = 0;
+    size_t integer_length;
+    int precision = info->precision;
+
+    // This isn't especially accurate, but hey, it's easy. :)
+    unsigned long long value;
+
+    if (arg < 0.0 || (arg == 0.0 && 1.0 / arg < 0.0)) { // additional check for signed zero
+        num[length++] = '-';
+        arg = -arg;
+    } else if (info->force_sign) {
+        num[length++] = '+';
+    }
+    value = (unsigned long long)arg;
+    integer_length = SDL_PrintUnsignedLongLong(&num[length], sizeof(num) - length, NULL, value);
+    length += integer_length;
+    arg -= value;
+    if (precision < 0) {
+        precision = 6;
+    }
+    if (g) {
+        // The precision includes the integer portion
+        precision -= SDL_min((int)integer_length, precision);
+    }
+    if (info->force_type || precision > 0) {
+        const char decimal_separator = '.';
+        double integer_value;
+
+        SDL_assert(length < sizeof(num));
+        num[length++] = decimal_separator;
+        while (precision > 1) {
+            arg *= 10.0;
+            arg = SDL_modf(arg, &integer_value);
+            SDL_assert(length < sizeof(num));
+            num[length++] = '0' + (char)integer_value;
+            --precision;
+        }
+        if (precision == 1) {
+            arg *= 10.0;
+            integer_value = SDL_round(arg);
+            if (integer_value == 10.0) {
+                // Carry the one...
+                size_t i;
+
+                for (i = length; i--; ) {
+                    if (num[i] == decimal_separator) {
+                        continue;
+                    }
+                    if (num[i] == '9') {
+                        num[i] = '0';
+                        if (i == 0 || num[i - 1] == '-' || num[i - 1] == '+') {
+                            SDL_memmove(&num[i+1], &num[i], length - i);
+                            num[i] = '1';
+                            ++length;
+                            break;
+                        }
+                    } else {
+                        ++num[i];
+                        break;
+                    }
+                }
+                SDL_assert(length < sizeof(num));
+                num[length++] = '0';
+            } else {
+                SDL_assert(length < sizeof(num));
+                num[length++] = '0' + (char)integer_value;
+            }
+        }
+
+        if (g) {
+            // Trim trailing zeroes and decimal separator
+            size_t i;
+
+            for (i = length - 1; num[i] != decimal_separator; --i) {
+                if (num[i] == '0') {
+                    --length;
+                } else {
+                    break;
+                }
+            }
+            if (num[i] == decimal_separator) {
+                --length;
+            }
+        }
+    }
+    num[length] = '\0';
+
+    info->precision = -1;
+    length = SDL_PrintString(text, maxlen, info, num);
+
+    if (info->width > 0 && (size_t)info->width > length) {
+        const char fill = info->pad_zeroes ? '0' : ' ';
+        size_t width = info->width - length;
+        size_t filllen, movelen;
+
+        filllen = SDL_min(width, maxlen);
+        movelen = SDL_min(length, (maxlen - filllen));
+        SDL_memmove(&text[filllen], text, movelen);
+        SDL_memset(text, fill, filllen);
+        length += width;
+    }
+    return length;
+}
+
+static size_t SDL_PrintPointer(char *text, size_t maxlen, SDL_FormatInfo *info, const void *value)
+{
+    char num[130];
+    size_t length;
+
+    if (!value) {
+        return SDL_PrintString(text, maxlen, info, NULL);
+    }
+
+    SDL_ulltoa((unsigned long long)(uintptr_t)value, num, 16);
+    length = SDL_PrintString(text, maxlen, info, "0x");
+    return length + SDL_PrintString(TEXT_AND_LEN_ARGS, info, num);
+}
+
+// NOLINTNEXTLINE(readability-non-const-parameter)
+int SDL_vsnprintf(SDL_OUT_Z_CAP(maxlen) char *text, size_t maxlen, SDL_PRINTF_FORMAT_STRING const char *fmt, va_list ap)
+{
+    size_t length = 0;
+
+    if (!text) {
+        maxlen = 0;
+    }
+    if (!fmt) {
+        fmt = "";
+    }
+    while (*fmt) {
+        if (*fmt == '%') {
+            bool done = false;
+            bool check_flag;
+            SDL_FormatInfo info;
+            enum
+            {
+                DO_INT,
+                DO_LONG,
+                DO_LONGLONG,
+                DO_SIZE_T
+            } inttype = DO_INT;
+
+            SDL_zero(info);
+            info.radix = 10;
+            info.precision = -1;
+
+            check_flag = true;
+            while (check_flag) {
+                ++fmt;
+                switch (*fmt) {
+                case '-':
+                    info.left_justify = true;
+                    break;
+                case '+':
+                    info.force_sign = true;
+                    break;
+                case '#':
+                    info.force_type = true;
+                    break;
+                case '0':
+                    info.pad_zeroes = true;
+                    break;
+                default:
+                    check_flag = false;
+                    break;
+                }
+            }
+
+            if (*fmt >= '0' && *fmt <= '9') {
+                info.width = SDL_strtol(fmt, (char **)&fmt, 0);
+            } else if (*fmt == '*') {
+                ++fmt;
+                info.width = va_arg(ap, int);
+            }
+
+            if (*fmt == '.') {
+                ++fmt;
+                if (*fmt >= '0' && *fmt <= '9') {
+                    info.precision = SDL_strtol(fmt, (char **)&fmt, 0);
+                } else if (*fmt == '*') {
+                    ++fmt;
+                    info.precision = va_arg(ap, int);
+                } else {
+                    info.precision = 0;
+                }
+                if (info.precision < 0) {
+                    info.precision = 0;
+                }
+            }
+
+            while (!done) {
+                switch (*fmt) {
+                case '%':
+                    if (length < maxlen) {
+                        text[length] = '%';
+                    }
+                    ++length;
+                    done = true;
+                    break;
+                case 'c':
+                    // char is promoted to int when passed through (...)
+                    if (length < maxlen) {
+                        text[length] = (char)va_arg(ap, int);
+                    }
+                    ++length;
+                    done = true;
+                    break;
+                case 'h':
+                    // short is promoted to int when passed through (...)
+                    break;
+                case 'l':
+                    if (inttype < DO_LONGLONG) {
+                        ++inttype;
+                    }
+                    break;
+                case 'I':
+                    if (SDL_strncmp(fmt, "I64", 3) == 0) {
+                        fmt += 2;
+                        inttype = DO_LONGLONG;
+                    }
+                    break;
+                case 'z':
+                    inttype = DO_SIZE_T;
+                    break;
+                case 'i':
+                case 'd':
+                    if (info.precision >= 0) {
+                        info.pad_zeroes = false;
+                    }
+                    switch (inttype) {
+                    case DO_INT:
+                        length += SDL_PrintLong(TEXT_AND_LEN_ARGS, &info,
+                                                (long)va_arg(ap, int));
+                        break;
+                    case DO_LONG:
+                        length += SDL_PrintLong(TEXT_AND_LEN_ARGS, &info,
+                                                va_arg(ap, long));
+                        break;
+                    case DO_LONGLONG:
+                        length += SDL_PrintLongLong(TEXT_AND_LEN_ARGS, &info,
+                                                    va_arg(ap, long long));
+                        break;
+                    case DO_SIZE_T:
+                        length += SDL_PrintLongLong(TEXT_AND_LEN_ARGS, &info,
+                                                    va_arg(ap, size_t));
+                        break;
+                    }
+                    done = true;
+                    break;
+                case 'p':
+                    info.force_case = SDL_CASE_LOWER;
+                    length += SDL_PrintPointer(TEXT_AND_LEN_ARGS, &info, va_arg(ap, void *));
+                    done = true;
+                    break;
+                case 'x':
+                    info.force_case = SDL_CASE_LOWER;
+                    SDL_FALLTHROUGH;
+                case 'X':
+                    if (info.force_case == SDL_CASE_NOCHANGE) {
+                        info.force_case = SDL_CASE_UPPER;
+                    }
+                    if (info.radix == 10) {
+                        info.radix = 16;
+                    }
+                    SDL_FALLTHROUGH;
+                case 'o':
+                    if (info.radix == 10) {
+                        info.radix = 8;
+                    }
+                    SDL_FALLTHROUGH;
+                case 'u':
+                    info.force_sign = false;
+                    if (info.precision >= 0) {
+                        info.pad_zeroes = false;
+                    }
+                    switch (inttype) {
+                    case DO_INT:
+                        length += SDL_PrintUnsignedLong(TEXT_AND_LEN_ARGS, &info,
+                                                        va_arg(ap, unsigned int));
+                        break;
+                    case DO_LONG:
+                        length += SDL_PrintUnsignedLong(TEXT_AND_LEN_ARGS, &info,
+                                                        va_arg(ap, unsigned long));
+                        break;
+                    case DO_LONGLONG:
+                        length += SDL_PrintUnsignedLongLong(TEXT_AND_LEN_ARGS, &info,
+                                                            va_arg(ap, unsigned long long));
+                        break;
+                    case DO_SIZE_T:
+                        length += SDL_PrintUnsignedLongLong(TEXT_AND_LEN_ARGS, &info,
+                                                            va_arg(ap, size_t));
+                        break;
+                    }
+                    done = true;
+                    break;
+                case 'f':
+                    length += SDL_PrintFloat(TEXT_AND_LEN_ARGS, &info, va_arg(ap, double), false);
+                    done = true;
+                    break;
+                case 'g':
+                    length += SDL_PrintFloat(TEXT_AND_LEN_ARGS, &info, va_arg(ap, double), true);
+                    done = true;
+                    break;
+                case 'S':
+                    info.pad_zeroes = false;
+                    length += SDL_PrintStringW(TEXT_AND_LEN_ARGS, &info, va_arg(ap, wchar_t *));
+                    done = true;
+                    break;
+                case 's':
+                    info.pad_zeroes = false;
+                    if (inttype > DO_INT) {
+                        length += SDL_PrintStringW(TEXT_AND_LEN_ARGS, &info, va_arg(ap, wchar_t *));
+                    } else {
+                        length += SDL_PrintString(TEXT_AND_LEN_ARGS, &info, va_arg(ap, char *));
+                    }
+                    done = true;
+                    break;
+                default:
+                    done = true;
+                    break;
+                }
+                ++fmt;
+            }
+        } else {
+            if (length < maxlen) {
+                text[length] = *fmt;
+            }
+            ++fmt;
+            ++length;
+        }
+    }
+    if (length < maxlen) {
+        text[length] = '\0';
+    } else if (maxlen > 0) {
+        text[maxlen - 1] = '\0';
+    }
+    return (int)length;
+}
+
+#undef TEXT_AND_LEN_ARGS
+#endif // HAVE_VSNPRINTF
+
+int SDL_vswprintf(SDL_OUT_Z_CAP(maxlen) wchar_t *text, size_t maxlen, const wchar_t *fmt, va_list ap)
+{
+    char *fmt_utf8 = NULL;
+    if (fmt) {
+        fmt_utf8 = SDL_iconv_string("UTF-8", "WCHAR_T", (const char *)fmt, (SDL_wcslen(fmt) + 1) * sizeof(wchar_t));
+        if (!fmt_utf8) {
+            return -1;
+        }
+    }
+
+    char tinybuf[64];  // for really small strings, calculate it once.
+
+    // generate the text to find the final text length
+    va_list aq;
+    va_copy(aq, ap);
+    const int utf8len = SDL_vsnprintf(tinybuf, sizeof (tinybuf), fmt_utf8, aq);
+    va_end(aq);
+
+    if (utf8len < 0) {
+        SDL_free(fmt_utf8);
+        return -1;
+    }
+
+    bool isstack = false;
+    char *smallbuf = NULL;
+    char *utf8buf;
+    int result;
+
+    if (utf8len < sizeof (tinybuf)) {   // whole thing fit in the stack buffer, just use that copy.
+        utf8buf = tinybuf;
+    } else {  // didn't fit in the stack buffer, allocate the needed space and run it again.
+        utf8buf = smallbuf = SDL_small_alloc(char, utf8len + 1, &isstack);
+        if (!smallbuf) {
+            SDL_free(fmt_utf8);
+            return -1;  // oh well.
+        }
+        const int utf8len2 = SDL_vsnprintf(smallbuf, utf8len + 1, fmt_utf8, ap);
+        if (utf8len2 > utf8len) {
+            SDL_free(fmt_utf8);
+            return SDL_SetError("Formatted output changed between two runs");  // race condition on the parameters, and we no longer have room...yikes.
+        }
+    }
+
+    SDL_free(fmt_utf8);
+
+    wchar_t *wbuf = (wchar_t *)SDL_iconv_string("WCHAR_T", "UTF-8", utf8buf, utf8len + 1);
+    if (wbuf) {
+        if (text) {
+            SDL_wcslcpy(text, wbuf, maxlen);
+        }
+        result = (int)SDL_wcslen(wbuf);
+        SDL_free(wbuf);
+    } else {
+        result = -1;
+    }
+
+    if (smallbuf != NULL) {
+        SDL_small_free(smallbuf, isstack);
+    }
+
+    return result;
+}
+
+int SDL_asprintf(char **strp, SDL_PRINTF_FORMAT_STRING const char *fmt, ...)
+{
+    va_list ap;
+    int result;
+
+    va_start(ap, fmt);
+    result = SDL_vasprintf(strp, fmt, ap);
+    va_end(ap);
+
+    return result;
+}
+
+int SDL_vasprintf(char **strp, SDL_PRINTF_FORMAT_STRING const char *fmt, va_list ap)
+{
+    int result;
+    int size = 100; // Guess we need no more than 100 bytes
+    char *p, *np;
+    va_list aq;
+
+    *strp = NULL;
+
+    p = (char *)SDL_malloc(size);
+    if (!p) {
+        return -1;
+    }
+
+    while (1) {
+        // Try to print in the allocated space
+        va_copy(aq, ap);
+        result = SDL_vsnprintf(p, size, fmt, aq);
+        va_end(aq);
+
+        // Check error code
+        if (result < 0) {
+            SDL_free(p);
+            return result;
+        }
+
+        // If that worked, return the string
+        if (result < size) {
+            *strp = p;
+            return result;
+        }
+
+        // Else try again with more space
+        size = result + 1; // Precisely what is needed
+
+        np = (char *)SDL_realloc(p, size);
+        if (!np) {
+            SDL_free(p);
+            return -1;
+        } else {
+            p = np;
+        }
+    }
+}
+
+char * SDL_strpbrk(const char *str, const char *breakset)
+{
+#ifdef HAVE_STRPBRK
+    return strpbrk(str, breakset);
+#else
+
+    for (; *str; str++) {
+        const char *b;
+
+        for (b = breakset; *b; b++) {
+            if (*str == *b) {
+                return (char *) str;
+            }
+        }
+    }
+    return NULL;
+#endif
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_strtokr.c b/contrib/SDL-3.2.8/src/stdlib/SDL_strtokr.c
new file mode 100644
index 0000000..e600808
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_strtokr.c
@@ -0,0 +1,95 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "SDL_internal.h"
+
+
+char *SDL_strtok_r(char *s1, const char *s2, char **ptr)
+{
+#ifdef HAVE_STRTOK_R
+    return strtok_r(s1, s2, ptr);
+
+#else /* SDL implementation */
+/*
+ * Adapted from _PDCLIB_strtok() of PDClib library at
+ * https://github.com/DevSolar/pdclib.git
+ *
+ * The code was under CC0 license:
+ * https://creativecommons.org/publicdomain/zero/1.0/legalcode :
+ *
+ *                        No Copyright
+ *
+ * The person who associated a work with this deed has dedicated the
+ * work to the public domain by waiving all of his or her rights to
+ * the work worldwide under copyright law, including all related and
+ * neighboring rights, to the extent allowed by law.
+ *
+ * You can copy, modify, distribute and perform the work, even for
+ * commercial purposes, all without asking permission. See Other
+ * Information below.
+ */
+    const char *p = s2;
+
+    if (!s2 || !ptr || (!s1 && !*ptr)) return NULL;
+
+    if (s1 != NULL) {  /* new string */
+        *ptr = s1;
+    } else { /* old string continued */
+        if (*ptr == NULL) {
+        /* No old string, no new string, nothing to do */
+            return NULL;
+        }
+        s1 = *ptr;
+    }
+
+    /* skip leading s2 characters */
+    while (*p && *s1) {
+        if (*s1 == *p) {
+        /* found separator; skip and start over */
+            ++s1;
+            p = s2;
+            continue;
+        }
+        ++p;
+    }
+
+    if (! *s1) { /* no more to parse */
+        *ptr = s1;
+        return NULL;
+    }
+
+    /* skipping non-s2 characters */
+    *ptr = s1;
+    while (**ptr) {
+        p = s2;
+        while (*p) {
+            if (**ptr == *p++) {
+            /* found separator; overwrite with '\0', position *ptr, return */
+                *((*ptr)++) = '\0';
+                return s1;
+            }
+        }
+        ++(*ptr);
+    }
+
+    /* parsed to end of string */
+    return s1;
+#endif
+}
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_sysstdlib.h b/contrib/SDL-3.2.8/src/stdlib/SDL_sysstdlib.h
new file mode 100644
index 0000000..7d43ab0
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_sysstdlib.h
@@ -0,0 +1,32 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+
+#ifndef SDL_sysstdlib_h_
+#define SDL_sysstdlib_h_
+
+// most things you might need internally in here are public APIs, this is
+// just a few special pieces right now.
+
+// this expects `from` to be a Unicode codepoint, and `to` to point to AT LEAST THREE Uint32s.
+int SDL_CaseFoldUnicode(Uint32 from, Uint32 *to);
+
+#endif
+
diff --git a/contrib/SDL-3.2.8/src/stdlib/SDL_vacopy.h b/contrib/SDL-3.2.8/src/stdlib/SDL_vacopy.h
new file mode 100644
index 0000000..fee560e
--- /dev/null
+++ b/contrib/SDL-3.2.8/src/stdlib/SDL_vacopy.h
@@ -0,0 +1,30 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2025 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+
+// Do our best to make sure va_copy is working
+#if defined(_MSC_VER) && _MSC_VER <= 1800
+// Visual Studio 2013 tries to link with _vacopy in the C runtime. Newer versions do an inline assignment
+#undef va_copy
+#define va_copy(dst, src) dst = src
+
+#elif defined(__GNUC__) && (__GNUC__ < 3)
+#define va_copy(dst, src) __va_copy(dst, src)
+#endif