source: libcaca/trunk/cucul/charset.c @ 963

Last change on this file since 963 was 963, checked in by Sam Hocevar, 15 years ago
  • Documented the newly exported charset functions.
  • Property svn:keywords set to Id
File size: 7.6 KB
Line 
1/*
2 *  libcucul      Canvas for ultrafast compositing of Unicode letters
3 *  Copyright (c) 2002-2006 Sam Hocevar <sam@zoy.org>
4 *                All Rights Reserved
5 *
6 *  $Id: charset.c 963 2006-05-19 05:30:01Z sam $
7 *
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.
12 */
13
14/*
15 *  This file contains functions for converting characters between
16 *  various character sets.
17 */
18
19#include "config.h"
20#include "common.h"
21
22#if !defined(__KERNEL__)
23#   include <string.h>
24#endif
25
26#include "cucul.h"
27#include "cucul_internals.h"
28
29/*
30 * UTF-8 handling
31 */
32
33static char const trailing[256] =
34{
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
43};
44
45static uint32_t const offsets[6] =
46{
47    0x00000000UL, 0x00003080UL, 0x000E2080UL,
48    0x03C82080UL, 0xFA082080UL, 0x82082080UL
49};
50
51/*
52 * CP437 handling
53 */
54
55static uint32_t const cp437_lookup1[] =
56{
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
63};
64
65static uint32_t const cp437_lookup2[] =
66{
67    /* 0x7f: ⌂ */
68    0x2302,
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
93};
94
95/** \brief Convert a UTF-8 character to UTF-32.
96 *
97 *  This function converts a UTF-8 character read from a string and returns
98 *  its value in the UTF-32 character set.
99 *
100 *  This function never fails, but its behaviour with illegal UTF-8 sequences
101 *  is undefined.
102 *
103 *  \param s A string containing the UTF-8 character.
104 *  \return The corresponding UTF-32 character.
105 */
106unsigned long int cucul_utf8_to_utf32(char const *s)
107{
108    int bytes = trailing[(int)(unsigned char)*s];
109    uint32_t ret = 0;
110
111    switch(bytes)
112    {
113        /* FIXME: do something for invalid sequences (4 and 5) */
114        case 3: ret += (uint8_t)*s++; ret <<= 6;
115        case 2: ret += (uint8_t)*s++; ret <<= 6;
116        case 1: ret += (uint8_t)*s++; ret <<= 6;
117        case 0: ret += (uint8_t)*s++;
118    }
119
120    ret -= offsets[bytes];
121
122    return ret;
123}
124
125/** \brief Convert a UTF-32 character to UTF-8.
126 *
127 *  This function converts a UTF-32 character read from a string and writes
128 *  its value in the UTF-8 character set into the given buffer.
129 *
130 *  This function never fails, but its behaviour with illegal UTF-32 characters
131 *  is undefined.
132 *
133 *  \param buf A pointer to a character buffer where the UTF-8 sequence will
134 *  be written.
135 *  \param ch The UTF-32 character.
136 *  \return The number of bytes written.
137 */
138unsigned int cucul_utf32_to_utf8(char *buf, unsigned long int ch)
139{
140    static const uint8_t mark[7] =
141    {
142        0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC
143    };
144
145    char *parser = buf;
146    int bytes;
147
148    if(ch < 0x80)
149    {
150        *parser++ = ch;
151        return 1;
152    }
153
154    bytes = (ch < 0x800) ? 2 : (ch < 0x10000) ? 3 : 4;
155    parser += bytes;
156
157    switch(bytes)
158    {
159        case 4: *--parser = (ch | 0x80) & 0xbf; ch >>= 6;
160        case 3: *--parser = (ch | 0x80) & 0xbf; ch >>= 6;
161        case 2: *--parser = (ch | 0x80) & 0xbf; ch >>= 6;
162    }
163    *--parser = ch | mark[bytes];
164
165    return bytes;
166}
167
168/** \brief Convert a UTF-32 character to CP437.
169 *
170 *  This function converts a UTF-32 character read from a string and returns
171 *  its value in the CP437 character set, or "?" if the character has no
172 *  equivalent.
173 *
174 *  This function never fails.
175 *
176 *  \param ch The UTF-32 character.
177 *  \return The corresponding CP437 character, or "?" if not representable.
178 */
179unsigned char cucul_utf32_to_cp437(unsigned long int ch)
180{
181    unsigned int i;
182
183    if(ch < 0x00000020)
184        return '?';
185
186    if(ch < 0x00000080)
187        return ch;
188
189    for(i = 0; i < sizeof(cp437_lookup1) / sizeof(*cp437_lookup1); i++)
190        if(cp437_lookup1[i] == ch)
191            return 0x01 + i;
192
193    for(i = 0; i < sizeof(cp437_lookup2) / sizeof(*cp437_lookup2); i++)
194        if(cp437_lookup2[i] == ch)
195            return 0x7f + i;
196
197    return '?';
198}
199
200/** \brief Convert a CP437 character to UTF-32.
201 *
202 *  This function converts a CP437 character read from a string and returns
203 *  its value in the UTF-32 character set, or zero if the character is a
204 *  CP437 control character.
205 *
206 *  This function never fails.
207 *
208 *  \param ch The CP437 character.
209 *  \return The corresponding UTF-32 character, or zero if not representable.
210 */
211unsigned long int cucul_cp437_to_utf32(unsigned char ch)
212{
213    if(ch > 0x7f)
214        return cp437_lookup2[ch - 0x7f];
215
216    if(ch >= 0x20)
217        return (uint32_t)ch;
218
219    if(ch > 0)
220        return cp437_lookup1[ch - 0x01];
221
222    return 0x00000000;
223}
224
225/*
226 * XXX: The following functions are local.
227 */
228
229unsigned int _cucul_strlen_utf8(char const *s)
230{
231    int len = 0;
232    char const *parser = s;
233
234    while(*parser)
235    {
236        int i;
237        int bytes = 1 + trailing[(int)(unsigned char)*parser];
238
239        for(i = 1; i < bytes; i++)
240            if(!parser[i])
241                return len;
242        parser += bytes;
243        len++;
244    }
245
246    return len;
247}
248
249char const *_cucul_skip_utf8(char const *s, unsigned int x)
250{
251    char const *parser = s;
252
253    while(x)
254    {
255        int i;
256        int bytes = 1 + trailing[(int)(unsigned char)*parser];
257
258        for(i = 1; i < bytes; i++)
259            if(!parser[i])
260                return parser;
261        parser += bytes;
262        x--;
263    }
264
265    return parser;
266}
267
Note: See TracBrowser for help on using the repository browser.