Spin out base-utf8 sub-module

Before:
8224 gen/lib/c/clang-5.0-dynamic/wuffs-base-core.lo
8200 gen/lib/c/clang-5.0-static/wuffs-base-core.o
8704 gen/lib/c/gcc-dynamic/wuffs-base-core.lo
8920 gen/lib/c/gcc-static/wuffs-base-core.o

After:
6216 gen/lib/c/clang-5.0-dynamic/wuffs-base-core.lo
2736 gen/lib/c/clang-5.0-dynamic/wuffs-base-utf8.lo
6216 gen/lib/c/clang-5.0-static/wuffs-base-core.o
2712 gen/lib/c/clang-5.0-static/wuffs-base-utf8.o
6728 gen/lib/c/gcc-dynamic/wuffs-base-core.lo
3008 gen/lib/c/gcc-dynamic/wuffs-base-utf8.lo
6728 gen/lib/c/gcc-static/wuffs-base-core.o
3224 gen/lib/c/gcc-static/wuffs-base-utf8.o
This commit is contained in:
Nigel Tao committed 2020-06-22 13:40:03 +10:00
1 parent 22a09b4133
commit 668e92cb81
6 files changed
+216 -201

No files matched your search

+9 -2
View File
@@ -120,8 +120,6 @@ const uint32_t wuffs_base__pixel_format__bits_per_channel[16] = {
// !! INSERT vtable names.
// !! INSERT base/strconv-impl.c.
#endif // !defined(WUFFS_CONFIG__MODULES) ||
// defined(WUFFS_CONFIG__MODULE__BASE) ||
// defined(WUFFS_CONFIG__MODULE__BASE__CORE)
@@ -162,6 +160,15 @@ const uint32_t wuffs_base__pixel_format__bits_per_channel[16] = {
// defined(WUFFS_CONFIG__MODULE__BASE) ||
// defined(WUFFS_CONFIG__MODULE__BASE__PIXCONV)
#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \
defined(WUFFS_CONFIG__MODULE__BASE__UTF8)
// !! INSERT base/utf8-submodule.c.
#endif // !defined(WUFFS_CONFIG__MODULES) ||
// defined(WUFFS_CONFIG__MODULE__BASE) ||
// defined(WUFFS_CONFIG__MODULE__BASE__UTF8)
#ifdef __cplusplus
} // extern "C"
#endif
File renamed without changes.
+4 -3
View File
@@ -100,6 +100,7 @@ var BaseSubModules = []string{
"i64conv",
"interfaces",
"pixconv",
"utf8",
}
// Do transpiles a Wuffs program to a C program.
@@ -128,7 +129,7 @@ func Do(args []string) error {
"// !! INSERT base/f64conv-submodule.c.\n": insertBaseF64ConvSubmoduleC,
"// !! INSERT base/i64conv-submodule.c.\n": insertBaseI64ConvSubmoduleC,
"// !! INSERT base/pixconv-submodule.c.\n": insertBasePixConvSubmoduleC,
"// !! INSERT base/strconv-impl.c.\n": insertBaseStrConvImplC,
"// !! INSERT base/utf8-submodule.c.\n": insertBaseUTF8SubmoduleC,
"// !! INSERT vtable names.\n": func(b *buffer) error {
for _, n := range builtin.Interfaces {
buf.printf("const char* wuffs_base__%s__vtable_name = "+
@@ -355,8 +356,8 @@ func insertBasePixConvSubmoduleC(buf *buffer) error {
return nil
}
func insertBaseStrConvImplC(buf *buffer) error {
buf.writes(data.BaseStrConvImplC)
func insertBaseUTF8SubmoduleC(buf *buffer) error {
buf.writes(data.BaseUTF8SubmoduleC)
return nil
}
+13 -13
View File
@@ -23,19 +23,9 @@ const BaseAllImplC = "" +
"" +
"// ----------------\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__CORE)\n\nconst uint8_t wuffs_base__low_bits_mask__u8[9] = {\n 0x00, 0x01, 0x03, 0x07, 0x0F, 0x1F, 0x3F, 0x7F, 0xFF,\n};\n\nconst uint16_t wuffs_base__low_bits_mask__u16[17] = {\n 0x0000, 0x0001, 0x0003, 0x0007, 0x000F, 0x001F, 0x003F, 0x007F, 0x00FF,\n 0x01FF, 0x03FF, 0x07FF, 0x0FFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF,\n};\n\nconst uint32_t wuffs_base__low_bits_mask__u32[33] = {\n 0x00000000, 0x00000001, 0x00000003, 0x00000007, 0x0000000F, 0x0000001F,\n 0x0000003F, 0x0000007F, 0x000000FF, 0x000001FF, 0x000003FF, 0x000007FF,\n 0x00000FFF, 0x00001FFF, 0x00003FFF, 0x00007FFF, 0x0000FFFF, 0x0001FFFF,\n 0x0003FFFF, 0x0007FFFF, 0x000FFFFF, 0x001FFFFF, 0x003FFFFF, 0x007FFFFF,\n 0x00FFFFFF, 0x01FFFFFF, 0x03FFFFFF, 0x07FFFFFF, 0x0FFFFFFF, 0x1FFFFFFF,\n 0x3FFFFFFF, 0x7FFFFFFF, 0xFFFFFFFF,\n};\n\nconst uint64_t wuffs_base__low_bits_mask__u64[65] = {\n 0x0000000000000000, 0x000" +
"0000000000001, 0x0000000000000003,\n 0x0000000000000007, 0x000000000000000F, 0x000000000000001F,\n 0x000000000000003F, 0x000000000000007F, 0x00000000000000FF,\n 0x00000000000001FF, 0x00000000000003FF, 0x00000000000007FF,\n 0x0000000000000FFF, 0x0000000000001FFF, 0x0000000000003FFF,\n 0x0000000000007FFF, 0x000000000000FFFF, 0x000000000001FFFF,\n 0x000000000003FFFF, 0x000000000007FFFF, 0x00000000000FFFFF,\n 0x00000000001FFFFF, 0x00000000003FFFFF, 0x00000000007FFFFF,\n 0x0000000000FFFFFF, 0x0000000001FFFFFF, 0x0000000003FFFFFF,\n 0x0000000007FFFFFF, 0x000000000FFFFFFF, 0x000000001FFFFFFF,\n 0x000000003FFFFFFF, 0x000000007FFFFFFF, 0x00000000FFFFFFFF,\n 0x00000001FFFFFFFF, 0x00000003FFFFFFFF, 0x00000007FFFFFFFF,\n 0x0000000FFFFFFFFF, 0x0000001FFFFFFFFF, 0x0000003FFFFFFFFF,\n 0x0000007FFFFFFFFF, 0x000000FFFFFFFFFF, 0x000001FFFFFFFFFF,\n 0x000003FFFFFFFFFF, 0x000007FFFFFFFFFF, 0x00000FFFFFFFFFFF,\n 0x00001FFFFFFFFFFF, 0x00003FFFFFFFFFFF, 0x00007FFFFFFFFFFF,\n 0x0000FFFFFFFFFFFF, 0x000" +
"1FFFFFFFFFFFF, 0x0003FFFFFFFFFFFF,\n 0x0007FFFFFFFFFFFF, 0x000FFFFFFFFFFFFF, 0x001FFFFFFFFFFFFF,\n 0x003FFFFFFFFFFFFF, 0x007FFFFFFFFFFFFF, 0x00FFFFFFFFFFFFFF,\n 0x01FFFFFFFFFFFFFF, 0x03FFFFFFFFFFFFFF, 0x07FFFFFFFFFFFFFF,\n 0x0FFFFFFFFFFFFFFF, 0x1FFFFFFFFFFFFFFF, 0x3FFFFFFFFFFFFFFF,\n 0x7FFFFFFFFFFFFFFF, 0xFFFFFFFFFFFFFFFF,\n};\n\nconst uint32_t wuffs_base__pixel_format__bits_per_channel[16] = {\n 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,\n 0x08, 0x0A, 0x0C, 0x10, 0x18, 0x20, 0x30, 0x40,\n};\n\n// !! INSERT wuffs_base__status strings.\n\n// !! INSERT vtable names.\n\n// !! INSERT base/strconv-impl.c.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__CORE)\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__INTERFACES)\n\n// !! INSERT InterfaceDefinitions.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE_" +
"_BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__INTERFACES)\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__F64CONV)\n\n// !! INSERT base/f64conv-submodule.c.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__F64CONV)\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__I64CONV)\n\n// !! INSERT base/i64conv-submodule.c.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__I64CONV)\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__PIXCONV)\n\n// !! INSERT base/pixconv-submodule.c.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__B" +
"ASE__PIXCONV)\n\n#ifdef __cplusplus\n} // extern \"C\"\n#endif\n\n#endif // WUFFS_IMPLEMENTATION\n\n// !! WUFFS MONOLITHIC RELEASE DISCARDS EVERYTHING BELOW.\n\n#endif // WUFFS_INCLUDE_GUARD__BASE\n" +
""
const BaseStrConvImplC = "" +
"// ---------------- Unicode and UTF-8\n\nWUFFS_BASE__MAYBE_STATIC size_t //\nwuffs_base__utf_8__encode(wuffs_base__slice_u8 dst, uint32_t code_point) {\n if (code_point <= 0x7F) {\n if (dst.len >= 1) {\n dst.ptr[0] = (uint8_t)(code_point);\n return 1;\n }\n\n } else if (code_point <= 0x07FF) {\n if (dst.len >= 2) {\n dst.ptr[0] = (uint8_t)(0xC0 | ((code_point >> 6)));\n dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));\n return 2;\n }\n\n } else if (code_point <= 0xFFFF) {\n if ((dst.len >= 3) && ((code_point < 0xD800) || (0xDFFF < code_point))) {\n dst.ptr[0] = (uint8_t)(0xE0 | ((code_point >> 12)));\n dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 6) & 0x3F));\n dst.ptr[2] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));\n return 3;\n }\n\n } else if (code_point <= 0x10FFFF) {\n if (dst.len >= 4) {\n dst.ptr[0] = (uint8_t)(0xF0 | ((code_point >> 18)));\n dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 12) & 0x3F));\n dst.ptr[2] = (uint8_t)(0x80 |" +
" ((code_point >> 6) & 0x3F));\n dst.ptr[3] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));\n return 4;\n }\n }\n\n return 0;\n}\n\n// wuffs_base__utf_8__byte_length_minus_1 is the byte length (minus 1) of a\n// UTF-8 encoded code point, based on the encoding's initial byte.\n// - 0x00 is 1-byte UTF-8 (ASCII).\n// - 0x01 is the start of 2-byte UTF-8.\n// - 0x02 is the start of 3-byte UTF-8.\n// - 0x03 is the start of 4-byte UTF-8.\n// - 0x40 is a UTF-8 tail byte.\n// - 0x80 is invalid UTF-8.\n//\n// RFC 3629 (UTF-8) gives this grammar for valid UTF-8:\n// UTF8-1 = %x00-7F\n// UTF8-2 = %xC2-DF UTF8-tail\n// UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /\n// %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )\n// UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /\n// %xF4 %x80-8F 2( UTF8-tail )\n// UTF8-tail = %x80-BF\nstatic const uint8_t wuffs_base__utf_8__byte_length_minus_1[256] = {\n // 0 1 2 3 4 5 " +
" 6 7\n // 8 9 A B C D E F\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x00 ..= 0x07.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x08 ..= 0x0F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x10 ..= 0x17.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x18 ..= 0x1F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x20 ..= 0x27.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x28 ..= 0x2F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x30 ..= 0x37.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x38 ..= 0x3F.\n\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x40 ..= 0x47.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x48 ..= 0x4F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x50 ..= 0x57.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x58 ..= 0x5F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x60 ..= 0x67.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00" +
", 0x00, 0x00, // 0x68 ..= 0x6F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x70 ..= 0x77.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x78 ..= 0x7F.\n\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x80 ..= 0x87.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x88 ..= 0x8F.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x90 ..= 0x97.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x98 ..= 0x9F.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xA0 ..= 0xA7.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xA8 ..= 0xAF.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xB0 ..= 0xB7.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xB8 ..= 0xBF.\n\n 0x80, 0x80, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xC0 ..= 0xC7.\n 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xC8 ..= 0xCF.\n 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xD0 ..= 0xD7.\n 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xD8 ..= 0" +
"xDF.\n 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, // 0xE0 ..= 0xE7.\n 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, // 0xE8 ..= 0xEF.\n 0x03, 0x03, 0x03, 0x03, 0x03, 0x80, 0x80, 0x80, // 0xF0 ..= 0xF7.\n 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, // 0xF8 ..= 0xFF.\n // 0 1 2 3 4 5 6 7\n // 8 9 A B C D E F\n};\n\nWUFFS_BASE__MAYBE_STATIC wuffs_base__utf_8__next__output //\nwuffs_base__utf_8__next(wuffs_base__slice_u8 s) {\n if (s.len == 0) {\n return wuffs_base__make_utf_8__next__output(0, 0);\n }\n uint32_t c = s.ptr[0];\n switch (wuffs_base__utf_8__byte_length_minus_1[c & 0xFF]) {\n case 0:\n return wuffs_base__make_utf_8__next__output(c, 1);\n\n case 1:\n if (s.len < 2) {\n break;\n }\n c = wuffs_base__load_u16le__no_bounds_check(s.ptr);\n if ((c & 0xC000) != 0x8000) {\n break;\n }\n c = (0x0007C0 & (c << 6)) | (0x00003F & (c >> 8));\n return wuffs_base__make_utf_8__next__output(" +
"c, 2);\n\n case 2:\n if (s.len < 3) {\n break;\n }\n c = wuffs_base__load_u24le__no_bounds_check(s.ptr);\n if ((c & 0xC0C000) != 0x808000) {\n break;\n }\n c = (0x00F000 & (c << 12)) | (0x000FC0 & (c >> 2)) |\n (0x00003F & (c >> 16));\n if ((c <= 0x07FF) || ((0xD800 <= c) && (c <= 0xDFFF))) {\n break;\n }\n return wuffs_base__make_utf_8__next__output(c, 3);\n\n case 3:\n if (s.len < 4) {\n break;\n }\n c = wuffs_base__load_u32le__no_bounds_check(s.ptr);\n if ((c & 0xC0C0C000) != 0x80808000) {\n break;\n }\n c = (0x1C0000 & (c << 18)) | (0x03F000 & (c << 4)) |\n (0x000FC0 & (c >> 10)) | (0x00003F & (c >> 24));\n if ((c <= 0xFFFF) || (0x110000 <= c)) {\n break;\n }\n return wuffs_base__make_utf_8__next__output(c, 4);\n }\n\n return wuffs_base__make_utf_8__next__output(\n WUFFS_BASE__UNICODE_REPLACEMENT_CHARACTER, 1);\n}\n\nWUFFS_BASE__MAYBE_STATIC size_t //\nwuffs_base__utf_8__longest_va" +
"lid_prefix(wuffs_base__slice_u8 s) {\n // TODO: possibly optimize the all-ASCII case (4 or 8 bytes at a time).\n //\n // TODO: possibly optimize this by manually inlining the\n // wuffs_base__utf_8__next calls.\n size_t original_len = s.len;\n while (s.len > 0) {\n wuffs_base__utf_8__next__output o = wuffs_base__utf_8__next(s);\n if ((o.code_point > 0x7F) && (o.byte_length == 1)) {\n break;\n }\n s.ptr += o.byte_length;\n s.len -= o.byte_length;\n }\n return original_len - s.len;\n}\n\nWUFFS_BASE__MAYBE_STATIC size_t //\nwuffs_base__ascii__longest_valid_prefix(wuffs_base__slice_u8 s) {\n // TODO: possibly optimize this by checking 4 or 8 bytes at a time.\n uint8_t* original_ptr = s.ptr;\n uint8_t* p = s.ptr;\n uint8_t* q = s.ptr + s.len;\n for (; (p != q) && ((*p & 0x80) == 0); p++) {\n }\n return (size_t)(p - original_ptr);\n}\n" +
"1FFFFFFFFFFFF, 0x0003FFFFFFFFFFFF,\n 0x0007FFFFFFFFFFFF, 0x000FFFFFFFFFFFFF, 0x001FFFFFFFFFFFFF,\n 0x003FFFFFFFFFFFFF, 0x007FFFFFFFFFFFFF, 0x00FFFFFFFFFFFFFF,\n 0x01FFFFFFFFFFFFFF, 0x03FFFFFFFFFFFFFF, 0x07FFFFFFFFFFFFFF,\n 0x0FFFFFFFFFFFFFFF, 0x1FFFFFFFFFFFFFFF, 0x3FFFFFFFFFFFFFFF,\n 0x7FFFFFFFFFFFFFFF, 0xFFFFFFFFFFFFFFFF,\n};\n\nconst uint32_t wuffs_base__pixel_format__bits_per_channel[16] = {\n 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,\n 0x08, 0x0A, 0x0C, 0x10, 0x18, 0x20, 0x30, 0x40,\n};\n\n// !! INSERT wuffs_base__status strings.\n\n// !! INSERT vtable names.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__CORE)\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__INTERFACES)\n\n// !! INSERT InterfaceDefinitions.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_" +
"CONFIG__MODULE__BASE__INTERFACES)\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__F64CONV)\n\n// !! INSERT base/f64conv-submodule.c.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__F64CONV)\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__I64CONV)\n\n// !! INSERT base/i64conv-submodule.c.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__I64CONV)\n\n#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__PIXCONV)\n\n// !! INSERT base/pixconv-submodule.c.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__PIXCONV)\n\n#if !defined(WUFFS_C" +
"ONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \\\n defined(WUFFS_CONFIG__MODULE__BASE__UTF8)\n\n// !! INSERT base/utf8-submodule.c.\n\n#endif // !defined(WUFFS_CONFIG__MODULES) ||\n // defined(WUFFS_CONFIG__MODULE__BASE) ||\n // defined(WUFFS_CONFIG__MODULE__BASE__UTF8)\n\n#ifdef __cplusplus\n} // extern \"C\"\n#endif\n\n#endif // WUFFS_IMPLEMENTATION\n\n// !! WUFFS MONOLITHIC RELEASE DISCARDS EVERYTHING BELOW.\n\n#endif // WUFFS_INCLUDE_GUARD__BASE\n" +
""
const BaseF64ConvSubmoduleC = "" +
@@ -191,6 +181,16 @@ const BasePixConvSubmoduleC = "" +
" dst_palette.len, src.ptr, src.len);\n }\n return 0;\n}\n" +
""
const BaseUTF8SubmoduleC = "" +
"// ---------------- Unicode and UTF-8\n\nWUFFS_BASE__MAYBE_STATIC size_t //\nwuffs_base__utf_8__encode(wuffs_base__slice_u8 dst, uint32_t code_point) {\n if (code_point <= 0x7F) {\n if (dst.len >= 1) {\n dst.ptr[0] = (uint8_t)(code_point);\n return 1;\n }\n\n } else if (code_point <= 0x07FF) {\n if (dst.len >= 2) {\n dst.ptr[0] = (uint8_t)(0xC0 | ((code_point >> 6)));\n dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));\n return 2;\n }\n\n } else if (code_point <= 0xFFFF) {\n if ((dst.len >= 3) && ((code_point < 0xD800) || (0xDFFF < code_point))) {\n dst.ptr[0] = (uint8_t)(0xE0 | ((code_point >> 12)));\n dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 6) & 0x3F));\n dst.ptr[2] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));\n return 3;\n }\n\n } else if (code_point <= 0x10FFFF) {\n if (dst.len >= 4) {\n dst.ptr[0] = (uint8_t)(0xF0 | ((code_point >> 18)));\n dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 12) & 0x3F));\n dst.ptr[2] = (uint8_t)(0x80 |" +
" ((code_point >> 6) & 0x3F));\n dst.ptr[3] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));\n return 4;\n }\n }\n\n return 0;\n}\n\n// wuffs_base__utf_8__byte_length_minus_1 is the byte length (minus 1) of a\n// UTF-8 encoded code point, based on the encoding's initial byte.\n// - 0x00 is 1-byte UTF-8 (ASCII).\n// - 0x01 is the start of 2-byte UTF-8.\n// - 0x02 is the start of 3-byte UTF-8.\n// - 0x03 is the start of 4-byte UTF-8.\n// - 0x40 is a UTF-8 tail byte.\n// - 0x80 is invalid UTF-8.\n//\n// RFC 3629 (UTF-8) gives this grammar for valid UTF-8:\n// UTF8-1 = %x00-7F\n// UTF8-2 = %xC2-DF UTF8-tail\n// UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /\n// %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )\n// UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /\n// %xF4 %x80-8F 2( UTF8-tail )\n// UTF8-tail = %x80-BF\nstatic const uint8_t wuffs_base__utf_8__byte_length_minus_1[256] = {\n // 0 1 2 3 4 5 " +
" 6 7\n // 8 9 A B C D E F\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x00 ..= 0x07.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x08 ..= 0x0F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x10 ..= 0x17.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x18 ..= 0x1F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x20 ..= 0x27.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x28 ..= 0x2F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x30 ..= 0x37.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x38 ..= 0x3F.\n\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x40 ..= 0x47.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x48 ..= 0x4F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x50 ..= 0x57.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x58 ..= 0x5F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x60 ..= 0x67.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00" +
", 0x00, 0x00, // 0x68 ..= 0x6F.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x70 ..= 0x77.\n 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x78 ..= 0x7F.\n\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x80 ..= 0x87.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x88 ..= 0x8F.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x90 ..= 0x97.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x98 ..= 0x9F.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xA0 ..= 0xA7.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xA8 ..= 0xAF.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xB0 ..= 0xB7.\n 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xB8 ..= 0xBF.\n\n 0x80, 0x80, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xC0 ..= 0xC7.\n 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xC8 ..= 0xCF.\n 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xD0 ..= 0xD7.\n 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xD8 ..= 0" +
"xDF.\n 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, // 0xE0 ..= 0xE7.\n 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, // 0xE8 ..= 0xEF.\n 0x03, 0x03, 0x03, 0x03, 0x03, 0x80, 0x80, 0x80, // 0xF0 ..= 0xF7.\n 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, // 0xF8 ..= 0xFF.\n // 0 1 2 3 4 5 6 7\n // 8 9 A B C D E F\n};\n\nWUFFS_BASE__MAYBE_STATIC wuffs_base__utf_8__next__output //\nwuffs_base__utf_8__next(wuffs_base__slice_u8 s) {\n if (s.len == 0) {\n return wuffs_base__make_utf_8__next__output(0, 0);\n }\n uint32_t c = s.ptr[0];\n switch (wuffs_base__utf_8__byte_length_minus_1[c & 0xFF]) {\n case 0:\n return wuffs_base__make_utf_8__next__output(c, 1);\n\n case 1:\n if (s.len < 2) {\n break;\n }\n c = wuffs_base__load_u16le__no_bounds_check(s.ptr);\n if ((c & 0xC000) != 0x8000) {\n break;\n }\n c = (0x0007C0 & (c << 6)) | (0x00003F & (c >> 8));\n return wuffs_base__make_utf_8__next__output(" +
"c, 2);\n\n case 2:\n if (s.len < 3) {\n break;\n }\n c = wuffs_base__load_u24le__no_bounds_check(s.ptr);\n if ((c & 0xC0C000) != 0x808000) {\n break;\n }\n c = (0x00F000 & (c << 12)) | (0x000FC0 & (c >> 2)) |\n (0x00003F & (c >> 16));\n if ((c <= 0x07FF) || ((0xD800 <= c) && (c <= 0xDFFF))) {\n break;\n }\n return wuffs_base__make_utf_8__next__output(c, 3);\n\n case 3:\n if (s.len < 4) {\n break;\n }\n c = wuffs_base__load_u32le__no_bounds_check(s.ptr);\n if ((c & 0xC0C0C000) != 0x80808000) {\n break;\n }\n c = (0x1C0000 & (c << 18)) | (0x03F000 & (c << 4)) |\n (0x000FC0 & (c >> 10)) | (0x00003F & (c >> 24));\n if ((c <= 0xFFFF) || (0x110000 <= c)) {\n break;\n }\n return wuffs_base__make_utf_8__next__output(c, 4);\n }\n\n return wuffs_base__make_utf_8__next__output(\n WUFFS_BASE__UNICODE_REPLACEMENT_CHARACTER, 1);\n}\n\nWUFFS_BASE__MAYBE_STATIC size_t //\nwuffs_base__utf_8__longest_va" +
"lid_prefix(wuffs_base__slice_u8 s) {\n // TODO: possibly optimize the all-ASCII case (4 or 8 bytes at a time).\n //\n // TODO: possibly optimize this by manually inlining the\n // wuffs_base__utf_8__next calls.\n size_t original_len = s.len;\n while (s.len > 0) {\n wuffs_base__utf_8__next__output o = wuffs_base__utf_8__next(s);\n if ((o.code_point > 0x7F) && (o.byte_length == 1)) {\n break;\n }\n s.ptr += o.byte_length;\n s.len -= o.byte_length;\n }\n return original_len - s.len;\n}\n\nWUFFS_BASE__MAYBE_STATIC size_t //\nwuffs_base__ascii__longest_valid_prefix(wuffs_base__slice_u8 s) {\n // TODO: possibly optimize this by checking 4 or 8 bytes at a time.\n uint8_t* original_ptr = s.ptr;\n uint8_t* p = s.ptr;\n uint8_t* q = s.ptr + s.len;\n for (; (p != q) && ((*p & 0x80) == 0); p++) {\n }\n return (size_t)(p - original_ptr);\n}\n" +
""
const BaseFundamentalPrivateH = "" +
"// ---------------- Fundamentals\n\n// WUFFS_BASE__MAGIC is a magic number to check that initializers are called.\n// It's not foolproof, given C doesn't automatically zero memory before use,\n// but it should catch 99.99% of cases.\n//\n// Its (non-zero) value is arbitrary, based on md5sum(\"wuffs\").\n#define WUFFS_BASE__MAGIC ((uint32_t)0x3CCB6C71)\n\n// WUFFS_BASE__DISABLED is a magic number to indicate that a non-recoverable\n// error was previously encountered.\n//\n// Its (non-zero) value is arbitrary, based on md5sum(\"disabled\").\n#define WUFFS_BASE__DISABLED ((uint32_t)0x075AE3D2)\n\n// Denote intentional fallthroughs for -Wimplicit-fallthrough.\n//\n// The order matters here. Clang also defines \"__GNUC__\".\n#if defined(__clang__) && defined(__cplusplus) && (__cplusplus >= 201103L)\n#define WUFFS_BASE__FALLTHROUGH [[clang::fallthrough]]\n#elif !defined(__clang__) && defined(__GNUC__) && (__GNUC__ >= 7)\n#define WUFFS_BASE__FALLTHROUGH __attribute__((fallthrough))\n#else\n#define WUFFS_BASE__FALLTHROUGH\n#endif\n\n// Use switch " +
"cases for coroutine suspension points, similar to the technique\n// in https://www.chiark.greenend.org.uk/~sgtatham/coroutines.html\n//\n// We use trivial macros instead of an explicit assignment and case statement\n// so that clang-format doesn't get confused by the unusual \"case\"s.\n#define WUFFS_BASE__COROUTINE_SUSPENSION_POINT_0 case 0:;\n#define WUFFS_BASE__COROUTINE_SUSPENSION_POINT(n) \\\n coro_susp_point = n; \\\n WUFFS_BASE__FALLTHROUGH; \\\n case n:;\n\n#define WUFFS_BASE__COROUTINE_SUSPENSION_POINT_MAYBE_SUSPEND(n) \\\n if (!status.repr) { \\\n goto ok; \\\n } else if (*status.repr != '$') { \\\n goto exit; \\\n } \\\n coro_susp_point = n; \\\n goto suspend; " +
+1 -1
View File
@@ -74,11 +74,11 @@ func genBase(out *bytes.Buffer) error {
filename, varname string
}{
{"../base/all-impl.c", "BaseAllImplC"},
{"../base/strconv-impl.c", "BaseStrConvImplC"},
{"../base/f64conv-submodule.c", "BaseF64ConvSubmoduleC"},
{"../base/i64conv-submodule.c", "BaseI64ConvSubmoduleC"},
{"../base/pixconv-submodule.c", "BasePixConvSubmoduleC"},
{"../base/utf8-submodule.c", "BaseUTF8SubmoduleC"},
{"../base/fundamental-private.h", "BaseFundamentalPrivateH"},
{"../base/fundamental-public.h", "BaseFundamentalPublicH"},
+189 -182
View File
@@ -8237,188 +8237,6 @@ const char* wuffs_base__image_decoder__vtable_name = "{vtable}wuffs_base__image_
const char* wuffs_base__io_transformer__vtable_name = "{vtable}wuffs_base__io_transformer";
const char* wuffs_base__token_decoder__vtable_name = "{vtable}wuffs_base__token_decoder";
// ---------------- Unicode and UTF-8
WUFFS_BASE__MAYBE_STATIC size_t //
wuffs_base__utf_8__encode(wuffs_base__slice_u8 dst, uint32_t code_point) {
if (code_point <= 0x7F) {
if (dst.len >= 1) {
dst.ptr[0] = (uint8_t)(code_point);
return 1;
}
} else if (code_point <= 0x07FF) {
if (dst.len >= 2) {
dst.ptr[0] = (uint8_t)(0xC0 | ((code_point >> 6)));
dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));
return 2;
}
} else if (code_point <= 0xFFFF) {
if ((dst.len >= 3) && ((code_point < 0xD800) || (0xDFFF < code_point))) {
dst.ptr[0] = (uint8_t)(0xE0 | ((code_point >> 12)));
dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 6) & 0x3F));
dst.ptr[2] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));
return 3;
}
} else if (code_point <= 0x10FFFF) {
if (dst.len >= 4) {
dst.ptr[0] = (uint8_t)(0xF0 | ((code_point >> 18)));
dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 12) & 0x3F));
dst.ptr[2] = (uint8_t)(0x80 | ((code_point >> 6) & 0x3F));
dst.ptr[3] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));
return 4;
}
}
return 0;
}
// wuffs_base__utf_8__byte_length_minus_1 is the byte length (minus 1) of a
// UTF-8 encoded code point, based on the encoding's initial byte.
// - 0x00 is 1-byte UTF-8 (ASCII).
// - 0x01 is the start of 2-byte UTF-8.
// - 0x02 is the start of 3-byte UTF-8.
// - 0x03 is the start of 4-byte UTF-8.
// - 0x40 is a UTF-8 tail byte.
// - 0x80 is invalid UTF-8.
//
// RFC 3629 (UTF-8) gives this grammar for valid UTF-8:
// UTF8-1 = %x00-7F
// UTF8-2 = %xC2-DF UTF8-tail
// UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
// %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
// UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
// %xF4 %x80-8F 2( UTF8-tail )
// UTF8-tail = %x80-BF
static const uint8_t wuffs_base__utf_8__byte_length_minus_1[256] = {
// 0 1 2 3 4 5 6 7
// 8 9 A B C D E F
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x00 ..= 0x07.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x08 ..= 0x0F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x10 ..= 0x17.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x18 ..= 0x1F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x20 ..= 0x27.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x28 ..= 0x2F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x30 ..= 0x37.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x38 ..= 0x3F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x40 ..= 0x47.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x48 ..= 0x4F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x50 ..= 0x57.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x58 ..= 0x5F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x60 ..= 0x67.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x68 ..= 0x6F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x70 ..= 0x77.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x78 ..= 0x7F.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x80 ..= 0x87.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x88 ..= 0x8F.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x90 ..= 0x97.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x98 ..= 0x9F.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xA0 ..= 0xA7.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xA8 ..= 0xAF.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xB0 ..= 0xB7.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xB8 ..= 0xBF.
0x80, 0x80, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xC0 ..= 0xC7.
0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xC8 ..= 0xCF.
0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xD0 ..= 0xD7.
0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xD8 ..= 0xDF.
0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, // 0xE0 ..= 0xE7.
0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, // 0xE8 ..= 0xEF.
0x03, 0x03, 0x03, 0x03, 0x03, 0x80, 0x80, 0x80, // 0xF0 ..= 0xF7.
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, // 0xF8 ..= 0xFF.
// 0 1 2 3 4 5 6 7
// 8 9 A B C D E F
};
WUFFS_BASE__MAYBE_STATIC wuffs_base__utf_8__next__output //
wuffs_base__utf_8__next(wuffs_base__slice_u8 s) {
if (s.len == 0) {
return wuffs_base__make_utf_8__next__output(0, 0);
}
uint32_t c = s.ptr[0];
switch (wuffs_base__utf_8__byte_length_minus_1[c & 0xFF]) {
case 0:
return wuffs_base__make_utf_8__next__output(c, 1);
case 1:
if (s.len < 2) {
break;
}
c = wuffs_base__load_u16le__no_bounds_check(s.ptr);
if ((c & 0xC000) != 0x8000) {
break;
}
c = (0x0007C0 & (c << 6)) | (0x00003F & (c >> 8));
return wuffs_base__make_utf_8__next__output(c, 2);
case 2:
if (s.len < 3) {
break;
}
c = wuffs_base__load_u24le__no_bounds_check(s.ptr);
if ((c & 0xC0C000) != 0x808000) {
break;
}
c = (0x00F000 & (c << 12)) | (0x000FC0 & (c >> 2)) |
(0x00003F & (c >> 16));
if ((c <= 0x07FF) || ((0xD800 <= c) && (c <= 0xDFFF))) {
break;
}
return wuffs_base__make_utf_8__next__output(c, 3);
case 3:
if (s.len < 4) {
break;
}
c = wuffs_base__load_u32le__no_bounds_check(s.ptr);
if ((c & 0xC0C0C000) != 0x80808000) {
break;
}
c = (0x1C0000 & (c << 18)) | (0x03F000 & (c << 4)) |
(0x000FC0 & (c >> 10)) | (0x00003F & (c >> 24));
if ((c <= 0xFFFF) || (0x110000 <= c)) {
break;
}
return wuffs_base__make_utf_8__next__output(c, 4);
}
return wuffs_base__make_utf_8__next__output(
WUFFS_BASE__UNICODE_REPLACEMENT_CHARACTER, 1);
}
WUFFS_BASE__MAYBE_STATIC size_t //
wuffs_base__utf_8__longest_valid_prefix(wuffs_base__slice_u8 s) {
// TODO: possibly optimize the all-ASCII case (4 or 8 bytes at a time).
//
// TODO: possibly optimize this by manually inlining the
// wuffs_base__utf_8__next calls.
size_t original_len = s.len;
while (s.len > 0) {
wuffs_base__utf_8__next__output o = wuffs_base__utf_8__next(s);
if ((o.code_point > 0x7F) && (o.byte_length == 1)) {
break;
}
s.ptr += o.byte_length;
s.len -= o.byte_length;
}
return original_len - s.len;
}
WUFFS_BASE__MAYBE_STATIC size_t //
wuffs_base__ascii__longest_valid_prefix(wuffs_base__slice_u8 s) {
// TODO: possibly optimize this by checking 4 or 8 bytes at a time.
uint8_t* original_ptr = s.ptr;
uint8_t* p = s.ptr;
uint8_t* q = s.ptr + s.len;
for (; (p != q) && ((*p & 0x80) == 0); p++) {
}
return (size_t)(p - original_ptr);
}
#endif // !defined(WUFFS_CONFIG__MODULES) ||
// defined(WUFFS_CONFIG__MODULE__BASE) ||
// defined(WUFFS_CONFIG__MODULE__BASE__CORE)
@@ -12214,6 +12032,195 @@ wuffs_base__pixel_swizzler__swizzle_interleaved_from_slice(
// defined(WUFFS_CONFIG__MODULE__BASE) ||
// defined(WUFFS_CONFIG__MODULE__BASE__PIXCONV)
#if !defined(WUFFS_CONFIG__MODULES) || defined(WUFFS_CONFIG__MODULE__BASE) || \
defined(WUFFS_CONFIG__MODULE__BASE__UTF8)
// ---------------- Unicode and UTF-8
WUFFS_BASE__MAYBE_STATIC size_t //
wuffs_base__utf_8__encode(wuffs_base__slice_u8 dst, uint32_t code_point) {
if (code_point <= 0x7F) {
if (dst.len >= 1) {
dst.ptr[0] = (uint8_t)(code_point);
return 1;
}
} else if (code_point <= 0x07FF) {
if (dst.len >= 2) {
dst.ptr[0] = (uint8_t)(0xC0 | ((code_point >> 6)));
dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));
return 2;
}
} else if (code_point <= 0xFFFF) {
if ((dst.len >= 3) && ((code_point < 0xD800) || (0xDFFF < code_point))) {
dst.ptr[0] = (uint8_t)(0xE0 | ((code_point >> 12)));
dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 6) & 0x3F));
dst.ptr[2] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));
return 3;
}
} else if (code_point <= 0x10FFFF) {
if (dst.len >= 4) {
dst.ptr[0] = (uint8_t)(0xF0 | ((code_point >> 18)));
dst.ptr[1] = (uint8_t)(0x80 | ((code_point >> 12) & 0x3F));
dst.ptr[2] = (uint8_t)(0x80 | ((code_point >> 6) & 0x3F));
dst.ptr[3] = (uint8_t)(0x80 | ((code_point >> 0) & 0x3F));
return 4;
}
}
return 0;
}
// wuffs_base__utf_8__byte_length_minus_1 is the byte length (minus 1) of a
// UTF-8 encoded code point, based on the encoding's initial byte.
// - 0x00 is 1-byte UTF-8 (ASCII).
// - 0x01 is the start of 2-byte UTF-8.
// - 0x02 is the start of 3-byte UTF-8.
// - 0x03 is the start of 4-byte UTF-8.
// - 0x40 is a UTF-8 tail byte.
// - 0x80 is invalid UTF-8.
//
// RFC 3629 (UTF-8) gives this grammar for valid UTF-8:
// UTF8-1 = %x00-7F
// UTF8-2 = %xC2-DF UTF8-tail
// UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
// %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
// UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
// %xF4 %x80-8F 2( UTF8-tail )
// UTF8-tail = %x80-BF
static const uint8_t wuffs_base__utf_8__byte_length_minus_1[256] = {
// 0 1 2 3 4 5 6 7
// 8 9 A B C D E F
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x00 ..= 0x07.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x08 ..= 0x0F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x10 ..= 0x17.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x18 ..= 0x1F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x20 ..= 0x27.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x28 ..= 0x2F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x30 ..= 0x37.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x38 ..= 0x3F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x40 ..= 0x47.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x48 ..= 0x4F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x50 ..= 0x57.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x58 ..= 0x5F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x60 ..= 0x67.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x68 ..= 0x6F.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x70 ..= 0x77.
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // 0x78 ..= 0x7F.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x80 ..= 0x87.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x88 ..= 0x8F.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x90 ..= 0x97.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x98 ..= 0x9F.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xA0 ..= 0xA7.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xA8 ..= 0xAF.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xB0 ..= 0xB7.
0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0xB8 ..= 0xBF.
0x80, 0x80, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xC0 ..= 0xC7.
0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xC8 ..= 0xCF.
0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xD0 ..= 0xD7.
0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, // 0xD8 ..= 0xDF.
0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, // 0xE0 ..= 0xE7.
0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, // 0xE8 ..= 0xEF.
0x03, 0x03, 0x03, 0x03, 0x03, 0x80, 0x80, 0x80, // 0xF0 ..= 0xF7.
0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, // 0xF8 ..= 0xFF.
// 0 1 2 3 4 5 6 7
// 8 9 A B C D E F
};
WUFFS_BASE__MAYBE_STATIC wuffs_base__utf_8__next__output //
wuffs_base__utf_8__next(wuffs_base__slice_u8 s) {
if (s.len == 0) {
return wuffs_base__make_utf_8__next__output(0, 0);
}
uint32_t c = s.ptr[0];
switch (wuffs_base__utf_8__byte_length_minus_1[c & 0xFF]) {
case 0:
return wuffs_base__make_utf_8__next__output(c, 1);
case 1:
if (s.len < 2) {
break;
}
c = wuffs_base__load_u16le__no_bounds_check(s.ptr);
if ((c & 0xC000) != 0x8000) {
break;
}
c = (0x0007C0 & (c << 6)) | (0x00003F & (c >> 8));
return wuffs_base__make_utf_8__next__output(c, 2);
case 2:
if (s.len < 3) {
break;
}
c = wuffs_base__load_u24le__no_bounds_check(s.ptr);
if ((c & 0xC0C000) != 0x808000) {
break;
}
c = (0x00F000 & (c << 12)) | (0x000FC0 & (c >> 2)) |
(0x00003F & (c >> 16));
if ((c <= 0x07FF) || ((0xD800 <= c) && (c <= 0xDFFF))) {
break;
}
return wuffs_base__make_utf_8__next__output(c, 3);
case 3:
if (s.len < 4) {
break;
}
c = wuffs_base__load_u32le__no_bounds_check(s.ptr);
if ((c & 0xC0C0C000) != 0x80808000) {
break;
}
c = (0x1C0000 & (c << 18)) | (0x03F000 & (c << 4)) |
(0x000FC0 & (c >> 10)) | (0x00003F & (c >> 24));
if ((c <= 0xFFFF) || (0x110000 <= c)) {
break;
}
return wuffs_base__make_utf_8__next__output(c, 4);
}
return wuffs_base__make_utf_8__next__output(
WUFFS_BASE__UNICODE_REPLACEMENT_CHARACTER, 1);
}
WUFFS_BASE__MAYBE_STATIC size_t //
wuffs_base__utf_8__longest_valid_prefix(wuffs_base__slice_u8 s) {
// TODO: possibly optimize the all-ASCII case (4 or 8 bytes at a time).
//
// TODO: possibly optimize this by manually inlining the
// wuffs_base__utf_8__next calls.
size_t original_len = s.len;
while (s.len > 0) {
wuffs_base__utf_8__next__output o = wuffs_base__utf_8__next(s);
if ((o.code_point > 0x7F) && (o.byte_length == 1)) {
break;
}
s.ptr += o.byte_length;
s.len -= o.byte_length;
}
return original_len - s.len;
}
WUFFS_BASE__MAYBE_STATIC size_t //
wuffs_base__ascii__longest_valid_prefix(wuffs_base__slice_u8 s) {
// TODO: possibly optimize this by checking 4 or 8 bytes at a time.
uint8_t* original_ptr = s.ptr;
uint8_t* p = s.ptr;
uint8_t* q = s.ptr + s.len;
for (; (p != q) && ((*p & 0x80) == 0); p++) {
}
return (size_t)(p - original_ptr);
}
#endif // !defined(WUFFS_CONFIG__MODULES) ||
// defined(WUFFS_CONFIG__MODULE__BASE) ||
// defined(WUFFS_CONFIG__MODULE__BASE__UTF8)
#ifdef __cplusplus
} // extern "C"
#endif