| 1 | /* utf8.h
|
|---|
| 2 | *
|
|---|
| 3 | * Copyright (C) 2000, 2001, 2002, 2005 by Larry Wall and others
|
|---|
| 4 | *
|
|---|
| 5 | * You may distribute under the terms of either the GNU General Public
|
|---|
| 6 | * License or the Artistic License, as specified in the README file.
|
|---|
| 7 | *
|
|---|
| 8 | */
|
|---|
| 9 |
|
|---|
| 10 | /* Use UTF-8 as the default script encoding?
|
|---|
| 11 | * Turning this on will break scripts having non-UTF-8 binary
|
|---|
| 12 | * data (such as Latin-1) in string literals. */
|
|---|
| 13 | #ifdef USE_UTF8_SCRIPTS
|
|---|
| 14 | # define USE_UTF8_IN_NAMES (!IN_BYTES)
|
|---|
| 15 | #else
|
|---|
| 16 | # define USE_UTF8_IN_NAMES (PL_hints & HINT_UTF8)
|
|---|
| 17 | #endif
|
|---|
| 18 |
|
|---|
| 19 | #ifdef EBCDIC
|
|---|
| 20 | /* The equivalent of these macros but implementing UTF-EBCDIC
|
|---|
| 21 | are in the following header file:
|
|---|
| 22 | */
|
|---|
| 23 |
|
|---|
| 24 | #include "utfebcdic.h"
|
|---|
| 25 | #else
|
|---|
| 26 | START_EXTERN_C
|
|---|
| 27 |
|
|---|
| 28 | #ifdef DOINIT
|
|---|
| 29 | EXTCONST unsigned char PL_utf8skip[] = {
|
|---|
| 30 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
|
|---|
| 31 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
|
|---|
| 32 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
|
|---|
| 33 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
|
|---|
| 34 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus */
|
|---|
| 35 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus */
|
|---|
| 36 | 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* scripts */
|
|---|
| 37 | 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6, /* cjk etc. */
|
|---|
| 38 | 7,13, /* Perl extended (not UTF-8). Up to 72bit allowed (64-bit + reserved). */
|
|---|
| 39 | };
|
|---|
| 40 | #else
|
|---|
| 41 | EXTCONST unsigned char PL_utf8skip[];
|
|---|
| 42 | #endif
|
|---|
| 43 |
|
|---|
| 44 | END_EXTERN_C
|
|---|
| 45 | #define UTF8SKIP(s) PL_utf8skip[*(const U8*)s]
|
|---|
| 46 |
|
|---|
| 47 | /* Native character to iso-8859-1 */
|
|---|
| 48 | #define NATIVE_TO_ASCII(ch) (ch)
|
|---|
| 49 | #define ASCII_TO_NATIVE(ch) (ch)
|
|---|
| 50 | /* Transform after encoding */
|
|---|
| 51 | #define NATIVE_TO_UTF(ch) (ch)
|
|---|
| 52 | #define UTF_TO_NATIVE(ch) (ch)
|
|---|
| 53 | /* Transforms in wide UV chars */
|
|---|
| 54 | #define UNI_TO_NATIVE(ch) (ch)
|
|---|
| 55 | #define NATIVE_TO_UNI(ch) (ch)
|
|---|
| 56 | /* Transforms in invariant space */
|
|---|
| 57 | #define NATIVE_TO_NEED(enc,ch) (ch)
|
|---|
| 58 | #define ASCII_TO_NEED(enc,ch) (ch)
|
|---|
| 59 |
|
|---|
| 60 | /* As there are no translations avoid the function wrapper */
|
|---|
| 61 | #define Perl_utf8n_to_uvchr Perl_utf8n_to_uvuni
|
|---|
| 62 | #define Perl_uvchr_to_utf8 Perl_uvuni_to_utf8
|
|---|
| 63 |
|
|---|
| 64 | /*
|
|---|
| 65 |
|
|---|
| 66 | The following table is from Unicode 3.2.
|
|---|
| 67 |
|
|---|
| 68 | Code Points 1st Byte 2nd Byte 3rd Byte 4th Byte
|
|---|
| 69 |
|
|---|
| 70 | U+0000..U+007F 00..7F
|
|---|
| 71 | U+0080..U+07FF C2..DF 80..BF
|
|---|
| 72 | U+0800..U+0FFF E0 A0..BF 80..BF
|
|---|
| 73 | U+1000..U+CFFF E1..EC 80..BF 80..BF
|
|---|
| 74 | U+D000..U+D7FF ED 80..9F 80..BF
|
|---|
| 75 | U+D800..U+DFFF ******* ill-formed *******
|
|---|
| 76 | U+E000..U+FFFF EE..EF 80..BF 80..BF
|
|---|
| 77 | U+10000..U+3FFFF F0 90..BF 80..BF 80..BF
|
|---|
| 78 | U+40000..U+FFFFF F1..F3 80..BF 80..BF 80..BF
|
|---|
| 79 | U+100000..U+10FFFF F4 80..8F 80..BF 80..BF
|
|---|
| 80 |
|
|---|
| 81 | Note the A0..BF in U+0800..U+0FFF, the 80..9F in U+D000...U+D7FF,
|
|---|
| 82 | the 90..BF in U+10000..U+3FFFF, and the 80...8F in U+100000..U+10FFFF.
|
|---|
| 83 | The "gaps" are caused by legal UTF-8 avoiding non-shortest encodings:
|
|---|
| 84 | it is technically possible to UTF-8-encode a single code point in different
|
|---|
| 85 | ways, but that is explicitly forbidden, and the shortest possible encoding
|
|---|
| 86 | should always be used (and that is what Perl does).
|
|---|
| 87 |
|
|---|
| 88 | */
|
|---|
| 89 |
|
|---|
| 90 | /*
|
|---|
| 91 | Another way to look at it, as bits:
|
|---|
| 92 |
|
|---|
| 93 | Code Points 1st Byte 2nd Byte 3rd Byte 4th Byte
|
|---|
| 94 |
|
|---|
| 95 | 0aaaaaaa 0aaaaaaa
|
|---|
| 96 | 00000bbbbbaaaaaa 110bbbbb 10aaaaaa
|
|---|
| 97 | ccccbbbbbbaaaaaa 1110cccc 10bbbbbb 10aaaaaa
|
|---|
| 98 | 00000dddccccccbbbbbbaaaaaa 11110ddd 10cccccc 10bbbbbb 10aaaaaa
|
|---|
| 99 |
|
|---|
| 100 | As you can see, the continuation bytes all begin with C<10>, and the
|
|---|
| 101 | leading bits of the start byte tell how many bytes the are in the
|
|---|
| 102 | encoded character.
|
|---|
| 103 |
|
|---|
| 104 | */
|
|---|
| 105 |
|
|---|
| 106 |
|
|---|
| 107 | #define UNI_IS_INVARIANT(c) (((UV)c) < 0x80)
|
|---|
| 108 | #define UTF8_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_UTF(c))
|
|---|
| 109 | #define NATIVE_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_ASCII(c))
|
|---|
| 110 | #define UTF8_IS_START(c) (((U8)c) >= 0xc0 && (((U8)c) <= 0xfd))
|
|---|
| 111 | #define UTF8_IS_CONTINUATION(c) (((U8)c) >= 0x80 && (((U8)c) <= 0xbf))
|
|---|
| 112 | #define UTF8_IS_CONTINUED(c) (((U8)c) & 0x80)
|
|---|
| 113 | #define UTF8_IS_DOWNGRADEABLE_START(c) (((U8)c & 0xfc) == 0xc0)
|
|---|
| 114 |
|
|---|
| 115 | #define UTF_START_MARK(len) ((len > 7) ? 0xFF : (0xFE << (7-len)))
|
|---|
| 116 | #define UTF_START_MASK(len) ((len >= 7) ? 0x00 : (0x1F >> (len-2)))
|
|---|
| 117 |
|
|---|
| 118 | #define UTF_CONTINUATION_MARK 0x80
|
|---|
| 119 | #define UTF_ACCUMULATION_SHIFT 6
|
|---|
| 120 | #define UTF_CONTINUATION_MASK ((U8)0x3f)
|
|---|
| 121 | #define UTF8_ACCUMULATE(old, new) (((old) << UTF_ACCUMULATION_SHIFT) | (((U8)new) & UTF_CONTINUATION_MASK))
|
|---|
| 122 |
|
|---|
| 123 | #define UTF8_EIGHT_BIT_HI(c) ((((U8)(c))>>UTF_ACCUMULATION_SHIFT)|UTF_START_MARK(2))
|
|---|
| 124 | #define UTF8_EIGHT_BIT_LO(c) (((((U8)(c)))&UTF_CONTINUATION_MASK)|UTF_CONTINUATION_MARK)
|
|---|
| 125 |
|
|---|
| 126 | #ifdef HAS_QUAD
|
|---|
| 127 | #define UNISKIP(uv) ( (uv) < 0x80 ? 1 : \
|
|---|
| 128 | (uv) < 0x800 ? 2 : \
|
|---|
| 129 | (uv) < 0x10000 ? 3 : \
|
|---|
|
|---|
