Overview
Comment: | More efficient UTF-8 -> ISO-8859-2 conversion |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk |
Files: | files | file ages | folders |
SHA3-256: |
66c759859a60853aede12c30be67dbbc |
User & Date: | js on 2017-02-12 16:26:03 |
Other Links: | manifest | tags |
Context
2017-02-12
| ||
16:55 | More efficient UTF-8 -> ISO-8859-3 conversion check-in: 4a01b5b9f7 user: js tags: trunk | |
16:26 | More efficient UTF-8 -> ISO-8859-2 conversion check-in: 66c759859a user: js tags: trunk | |
13:33 | Save a few bytes on the encodings check-in: 8ae231f515 user: js tags: trunk | |
Changes
Modified src/encodings/iso_8859_2.m from [3c02c37635] to [b0786ce1a1].
︙ | ︙ | |||
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | 0x010D, 0x00E9, 0x0119, 0x00EB, 0x011B, 0x00ED, 0x00EE, 0x010F, 0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x00F7, 0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD, 0x0163, 0x02D9 }; const size_t of_iso_8859_2_table_offset = 256 - (sizeof(of_iso_8859_2_table) / sizeof(*of_iso_8859_2_table)); bool of_unicode_to_iso_8859_2(const of_unichar_t *input, unsigned char *output, size_t length, bool lossy) { for (size_t i = 0; i < length; i++) { of_unichar_t c = input[i]; if OF_UNLIKELY (c > 0x7F) { if OF_UNLIKELY (c > 0xFFFF) { if (lossy) { output[i] = '?'; continue; } else return false; } | > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > < < < | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | < < | | | > | < < | | < < > | | | < | < > | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | < < < < < < < < < | < < | | < < > | | | < | < > | | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | > | | > | > > > > | > | 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | 0x010D, 0x00E9, 0x0119, 0x00EB, 0x011B, 0x00ED, 0x00EE, 0x010F, 0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x00F7, 0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD, 0x0163, 0x02D9 }; const size_t of_iso_8859_2_table_offset = 256 - (sizeof(of_iso_8859_2_table) / sizeof(*of_iso_8859_2_table)); static char page0[] = { 0xA0, 0x00, 0x00, 0x00, 0xA4, 0x00, 0x00, 0xA7, 0xA8, 0x00, 0x00, 0x00, 0x00, 0xAD, 0x00, 0x00, 0xB0, 0x00, 0x00, 0x00, 0xB4, 0x00, 0x00, 0x00, 0xB8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xC1, 0xC2, 0x00, 0xC4, 0x00, 0x00, 0xC7, 0x00, 0xC9, 0x00, 0xCB, 0x00, 0xCD, 0xCE, 0x00, 0x00, 0x00, 0x00, 0xD3, 0xD4, 0x00, 0xD6, 0xD7, 0x00, 0x00, 0xDA, 0x00, 0xDC, 0xDD, 0x00, 0xDF, 0x00, 0xE1, 0xE2, 0x00, 0xE4, 0x00, 0x00, 0xE7, 0x00, 0xE9, 0x00, 0xEB, 0x00, 0xED, 0xEE, 0x00, 0x00, 0x00, 0x00, 0xF3, 0xF4, 0x00, 0xF6, 0xF7, 0x00, 0x00, 0xFA, 0x00, 0xFC, 0xFD, 0x00, 0x00 }; static uint8_t page0Start = 160; static uint16_t page0Size = sizeof(page0) / sizeof(*page0); static char page1[] = { 0xC3, 0xE3, 0xA1, 0xB1, 0xC6, 0xE6, 0x00, 0x00, 0x00, 0x00, 0xC8, 0xE8, 0xCF, 0xEF, 0xD0, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xCA, 0xEA, 0xCC, 0xEC, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xC5, 0xE5, 0x00, 0x00, 0xA5, 0xB5, 0x00, 0x00, 0xA3, 0xB3, 0xD1, 0xF1, 0x00, 0x00, 0xD2, 0xF2, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xD5, 0xF5, 0x00, 0x00, 0xC0, 0xE0, 0x00, 0x00, 0xD8, 0xF8, 0xA6, 0xB6, 0x00, 0x00, 0xAA, 0xBA, 0xA9, 0xB9, 0xDE, 0xFE, 0xAB, 0xBB, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xD9, 0xF9, 0xDB, 0xFB, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xAC, 0xBC, 0xAF, 0xBF, 0xAE, 0xBE }; static uint8_t page1Start = 2; static uint16_t page1Size = sizeof(page1) / sizeof(*page1); static char page2[] = { 0xB7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xA2, 0xFF, 0x00, 0xB2, 0x00, 0xBD }; static uint8_t page2Start = 0xC7; static uint16_t page2Size = sizeof(page2) / sizeof(*page2); bool of_unicode_to_iso_8859_2(const of_unichar_t *input, unsigned char *output, size_t length, bool lossy) { for (size_t i = 0; i < length; i++) { of_unichar_t c = input[i]; if OF_UNLIKELY (c > 0x7F) { uint8_t index; if OF_UNLIKELY (c > 0xFFFF) { if (lossy) { output[i] = '?'; continue; } else return false; } switch (c >> 8) { case 0: if OF_UNLIKELY ((c & 0xFF) < page0Start) { output[i] = (unsigned char)c; continue; } index = (c & 0xFF) - page0Start; if (index >= page0Size || page0[index] == 0) { if (lossy) { output[i] = '?'; continue; } else return false; } output[i] = page0[index]; break; case 1: index = (c & 0xFF) - page1Start; if (index >= page1Size || page1[index] == 0) { if (lossy) { output[i] = '?'; continue; } else return false; } output[i] = page1[index]; break; case 2: index = (c & 0xFF) - page2Start; if (index >= page2Size || page2[index] == 0) { if (lossy) { output[i] = '?'; continue; } else return false; } output[i] = page2[index]; break; default: if (lossy) { output[i] = '?'; continue; } else return false; } } else output[i] = (unsigned char)c; } return true; } |