2
* libcucul Canvas for ultrafast compositing of Unicode letters
3
* Copyright (c) 2002-2006 Sam Hocevar <sam@zoy.org>
6
* $Id: charset.c 1014 2006-11-11 09:22:10Z sam $
8
* This library is free software; you can redistribute it and/or
9
* modify it under the terms of the Do What The Fuck You Want To
10
* Public License, Version 2, as published by Sam Hocevar. See
11
* http://sam.zoy.org/wtfpl/COPYING for more details.
15
* This file contains functions for converting characters between
16
* various character sets.
22
#if !defined(__KERNEL__)
27
#include "cucul_internals.h"
33
static char const trailing[256] =
35
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
36
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
37
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
38
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
39
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
40
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
41
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,
42
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
45
static uint32_t const offsets[6] =
47
0x00000000UL, 0x00003080UL, 0x000E2080UL,
48
0x03C82080UL, 0xFA082080UL, 0x82082080UL
55
static uint32_t const cp437_lookup1[] =
57
/* 0x01 - 0x0f: ☺ ☻ ♥ ♦ ♣ ♠ • ◘ ○ ◙ ♂ ♀ ♪ ♫ ☼ */
58
0x263a, 0x263b, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022,
59
0x25d8, 0x25cb, 0x25d9, 0x2642, 0x2640, 0x266a, 0x266b, 0x263c,
60
/* 0x10 - 0x1f: ► ◄ ↕ ‼ ¶ § ▬ ↨ ↑ ↓ → ← ∟ ↔ ▲ ▼ */
61
0x25ba, 0x25c4, 0x2195, 0x203c, 0xb6, 0xa7, 0x25ac, 0x21a8,
62
0x2191, 0x2193, 0x2192, 0x2190, 0x221f, 0x2194, 0x25b2, 0x25bc
65
static uint32_t const cp437_lookup2[] =
69
/* 0x80 - 0x8f: Ç ü é â ä à å ç ê ë è ï î ì Ä Å */
70
0xc7, 0xfc, 0xe9, 0xe2, 0xe4, 0xe0, 0xe5, 0xe7,
71
0xea, 0xeb, 0xe8, 0xef, 0xee, 0xec, 0xc4, 0xc5,
72
/* 0x90 - 0x9f: É æ Æ ô ö ò û ù ÿ Ö Ü ¢ £ ¥ ₧ ƒ */
73
0xc9, 0xe6, 0xc6, 0xf4, 0xf6, 0xf2, 0xfb, 0xf9,
74
0xff, 0xd6, 0xdc, 0xa2, 0xa3, 0xa5, 0x20a7, 0x192,
75
/* 0xa0 - 0xaf: á í ó ú ñ Ñ ª º ¿ ⌐ ¬ ½ ¼ ¡ « » */
76
0xe1, 0xed, 0xf3, 0xfa, 0xf1, 0xd1, 0xaa, 0xba,
77
0xbf, 0x2310, 0xac, 0xbd, 0xbc, 0xa1, 0xab, 0xbb,
78
/* 0xb0 - 0xbf: ░ ▒ ▓ │ ┤ ╡ ╢ ╖ ╕ ╣ ║ ╗ ╝ ╜ ╛ ┐ */
79
0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
80
0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510,
81
/* 0xc0 - 0xcf: └ ┴ ┬ ├ ─ ┼ ╞ ╟ ╚ ╔ ╩ ╦ ╠ ═ ╬ ╧ */
82
0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f,
83
0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567,
84
/* 0xd0 - 0xdf: ╨ ╤ ╥ ╙ ╘ ╒ ╓ ╫ ╪ ┘ ┌ █ ▄ ▌ ▐ ▀ */
85
0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b,
86
0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580,
87
/* 0xe0 - 0xef: α ß Γ π Σ σ µ τ Φ Θ Ω δ ∞ φ ε ∩ */
88
0x3b1, 0xdf, 0x393, 0x3c0, 0x3a3, 0x3c3, 0xb5, 0x3c4,
89
0x3a6, 0x398, 0x3a9, 0x3b4, 0x221e, 0x3c6, 0x3b5, 0x2229,
90
/* 0xf0 - 0xff: ≡ ± ≥ ≤ ⌠ ⌡ ÷ ≈ ° ∙ · √ ⁿ ² ■ <nbsp> */
91
0x2261, 0xb1, 0x2265, 0x2264, 0x2320, 0x2321, 0xf7, 0x2248,
92
0xb0, 0x2219, 0xb7, 0x221a, 0x207f, 0xb2, 0x25a0, 0xa0
95
/** \brief Convert a UTF-8 character to UTF-32.
97
* Convert a UTF-8 character read from a string and return its value in
98
* the UTF-32 character set. If the second argument is not null, the total
99
* number of read bytes is written in it.
101
* If a null byte was reached before the expected end of the UTF-8 sequence,
102
* this function returns zero and the number of read bytes is set to zero.
104
* This function never fails, but its behaviour with illegal UTF-8 sequences
107
* \param s A string containing the UTF-8 character.
108
* \param read A pointer to an unsigned integer to store the number of
109
* bytes in the character, or NULL.
110
* \return The corresponding UTF-32 character, or zero if the character
113
unsigned long int cucul_utf8_to_utf32(char const *s, unsigned int *read)
115
unsigned int bytes = trailing[(int)(unsigned char)*s];
128
ret += ((uint32_t)(unsigned char)*s++) << (6 * (bytes - i));
134
return ret - offsets[bytes];
139
/** \brief Convert a UTF-32 character to UTF-8.
141
* Convert a UTF-32 character read from a string and write its value in
142
* the UTF-8 character set into the given buffer.
144
* This function never fails, but its behaviour with illegal UTF-32 characters
147
* \param buf A pointer to a character buffer where the UTF-8 sequence will
149
* \param ch The UTF-32 character.
150
* \return The number of bytes written.
152
unsigned int cucul_utf32_to_utf8(char *buf, unsigned long int ch)
154
static const uint8_t mark[7] =
156
0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC
168
bytes = (ch < 0x800) ? 2 : (ch < 0x10000) ? 3 : 4;
173
case 4: *--parser = (ch | 0x80) & 0xbf; ch >>= 6;
174
case 3: *--parser = (ch | 0x80) & 0xbf; ch >>= 6;
175
case 2: *--parser = (ch | 0x80) & 0xbf; ch >>= 6;
177
*--parser = ch | mark[bytes];
182
/** \brief Convert a UTF-32 character to CP437.
184
* Convert a UTF-32 character read from a string and return its value in
185
* the CP437 character set, or "?" if the character has no equivalent.
187
* This function never fails.
189
* \param ch The UTF-32 character.
190
* \return The corresponding CP437 character, or "?" if not representable.
192
unsigned char cucul_utf32_to_cp437(unsigned long int ch)
202
for(i = 0; i < sizeof(cp437_lookup1) / sizeof(*cp437_lookup1); i++)
203
if(cp437_lookup1[i] == ch)
206
for(i = 0; i < sizeof(cp437_lookup2) / sizeof(*cp437_lookup2); i++)
207
if(cp437_lookup2[i] == ch)
213
/** \brief Convert a CP437 character to UTF-32.
215
* Convert a CP437 character read from a string and return its value in
216
* the UTF-32 character set, or zero if the character is a CP437 control
219
* This function never fails.
221
* \param ch The CP437 character.
222
* \return The corresponding UTF-32 character, or zero if not representable.
224
unsigned long int cucul_cp437_to_utf32(unsigned char ch)
227
return cp437_lookup2[ch - 0x7f];
233
return cp437_lookup1[ch - 0x01];
238
/** \brief Tell whether a UTF-32 character is fullwidth.
240
* Check whether the given UTF-32 character should be printed at twice
241
* the normal width (fullwidth characters). If the character is unknown
242
* or if its status cannot be decided, it is treated as a standard-width
245
* This function never fails.
247
* \param ch The UTF-32 character.
248
* \return 1 if the character is fullwidth, 0 otherwise.
250
int cucul_utf32_is_fullwidth(unsigned long int ch)
252
if(ch < 0x2e80) /* Standard stuff */
254
if(ch < 0xa700) /* Japanese, Korean, CJK, Yi... */
256
if(ch < 0xac00) /* Modified Tone Letters, Syloti Nagri */
258
if(ch < 0xd800) /* Hangul Syllables */
260
if(ch < 0xf900) /* Misc crap */
262
if(ch < 0xfb00) /* More CJK */
264
if(ch < 0xfe20) /* Misc crap */
266
if(ch < 0xfe70) /* More CJK */
268
if(ch < 0xff00) /* Misc crap */
270
if(ch < 0xff61) /* Fullwidth forms */
272
if(ch < 0xffe0) /* Halfwidth forms */
274
if(ch < 0xffe8) /* More fullwidth forms */
276
if(ch < 0x20000) /* Misc crap */
278
if(ch < 0xe0000) /* More CJK */