rxvt-unicode/src/encoding.C

/*--------------------------------*-C-*---------------------------------*
 * File:        encoding.C
 *----------------------------------------------------------------------*
 *
 * All portions of code are copyright by their respective author/s.
 * Copyright (c) 2003-2004 Marc Lehmann <pcg@goof.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *----------------------------------------------------------------------*/

#include "../config.h"

#include "encoding.h"

#include <cstdlib>
#include <cstring>

const struct n2cs {
  const char *name;
  codeset cs;
} n2cs[] = {
  /* first one found is the normalized one */
  { "ISO88591",         CS_ISO8859_1        },
  { "ISO8859PRIMARY",   CS_ISO8859_1        }, // some stupid fonts use this (hi tigert)
  { "ISO88592",         CS_ISO8859_2        },
  { "ISO88593",         CS_ISO8859_3        },
  { "ISO88594",         CS_ISO8859_4        },
  { "ISO88595",         CS_ISO8859_5        },
  { "ISO88596",         CS_ISO8859_6        },
  { "ISO88597",         CS_ISO8859_7        },
  { "ISO88598",         CS_ISO8859_8        },
  { "ISO88599",         CS_ISO8859_9        },
  { "ISO885910",        CS_ISO8859_10       },
  { "ISO885911",        CS_ISO8859_11       },
  { "ISO885913",        CS_ISO8859_13       },
  { "ISO885914",        CS_ISO8859_14       },
  { "ISO885915",        CS_ISO8859_15       },
  { "FCD885915",        CS_ISO8859_15       },
  { "ISO885916",        CS_ISO8859_16       },
                                            
  { "TIS620*",          CS_ISO8859_11       }, // close enough

  { "ISO10646*",        CS_UNICODE          },
  { "UNICODE",          CS_UNICODE          },
  { "UTF8",             CS_UNICODE          },
                                            
  { "ASCII",            CS_US_ASCII         },
  { "USASCII",          CS_US_ASCII         },
  { "ANSIX341968",      CS_US_ASCII         },
                                            
  { "KOI8R",            CS_KOI8_R           },
  { "GOST1976874*",     CS_KOI8_R           },
  { "KOI8RU",           CS_KOI8_U           },
  { "KOI8U",            CS_KOI8_U           },

  { "VISCII*",          CS_VISCII           },
                                            
  { "JISX0201*",        CS_JIS0201_1976_0   },
  { "JISC6226*",        CS_JIS0208_1990_0   }, // also wrongly matches -1987-0? (check Encode::JP)
  { "JISX0208*",        CS_JIS0208_1990_0   }, // also wrongly matches -1987-0? (check Encode::JP)
  { "JISX0212*",        CS_JIS0212_1990_0   },
  { "JISX021320001",    CS_JIS0213_1        },
  { "JISX021320002",    CS_JIS0213_2        },
  { "JISX0221*",        CS_UNICODE          }, // _very_ close
                                            
  { "KSC5601*",         CS_KSC5601_1987_0   },
  { "KSX1001*",         CS_KSC5601_1987_0   },
  { "KSC5700*",         CS_UNICODE          }, // unicode plus extensions
                                            
  { "BIG5P*",           CS_BIG5_PLUS        },
  { "BIG5ETEN*",        CS_BIG5_EXT         },
  { "BIG5*",            CS_BIG5             },
  { "GB2312*",          CS_GB2312_1980_0    },
  { "GB6345*",          CS_GB2312_1980_0    }, // slightly different to gb2312??
  { "GB8565*",          CS_GB2312_1980_0    }, // a superset of gb2312??
  { "GB13000*",         CS_UNICODE          },
  { "CNS1164319921",    CS_CNS11643_1992_1  },
  { "CNS1164319922",    CS_CNS11643_1992_2  },
  { "CNS1164319923",    CS_CNS11643_1992_3  },
  { "CNS1164319924",    CS_CNS11643_1992_4  },
  { "CNS1164319925",    CS_CNS11643_1992_5  },
  { "CNS1164319926",    CS_CNS11643_1992_6  },
  { "CNS1164319927",    CS_CNS11643_1992_7  },
  { "CNS116431992F",    CS_CNS11643_1992_F  },

  { 0,                  CS_UNKNOWN      }
};

static const char *
normalize_name (const char *name)
{
  static char res[16];
  char *r;

  for (r = res; *name && r < res + 15; name++)
    if ((*name >= '0' && *name <= '9')
        || (*name >= 'A' && *name <= 'Z'))
      *r++ = *name;
    else if (*name >= 'a' && *name <= 'z')
      *r++ = *name - ('a' - 'A');

  *r = 0;

  return res;
}

codeset
codeset_from_name (const char *name)
{
  if (!name)
    return CS_UNKNOWN;

  name = normalize_name (name);

  const struct n2cs *i = n2cs;

  do {
    int len = strlen (i->name);

    if ((i->name[len - 1] == '*'
         && !strncmp (name, i->name, len - 1))
        || !strcmp (name, i->name))
        return i->cs;

  } while ((++i)->name);

  return CS_UNKNOWN;
}

static unicode_t cs_unknown_to_unicode (uint32_t enc)          { return NOCHAR; }
static uint32_t cs_unknown_from_unicode (unicode_t unicode)    { return NOCHAR; }

static unicode_t cs_unicode_to_unicode (uint32_t enc)          { return enc; }
static uint32_t cs_unicode_from_unicode (unicode_t unicode)    { return unicode; }

#define cs_us_ascii_to_unicode cs_unicode_to_unicode
static uint32_t cs_us_ascii_from_unicode (unicode_t unicode)   { return unicode <= 127 ? unicode : NOCHAR; }

#define cs_us_ascii_to_unicode_16 cs_unicode_to_unicode
static uint32_t cs_unicode_16_from_unicode (unicode_t unicode) { return unicode <= 65535 ? unicode : NOCHAR; }

#define ENCODING_DEFAULT

#include "table/iso8859_1.h"
#include "table/iso8859_15.h"

//#define ENCODING_EU

#include "table/iso8859_2.h"
#include "table/iso8859_3.h"
#include "table/iso8859_4.h"
#include "table/iso8859_5.h"
#include "table/iso8859_6.h"
#include "table/iso8859_7.h"
#include "table/iso8859_8.h"
#include "table/iso8859_9.h"
#include "table/iso8859_10.h"
#include "table/iso8859_11.h"
#include "table/iso8859_13.h"
#include "table/iso8859_14.h"
#include "table/iso8859_16.h"

#include "table/koi8_r.h"
#include "table/koi8_u.h"

//#define ENCODING_KR

#include "table/ksc5601_1987_0.h"

//#define ENCODING_ZH

#include "table/gb2312_1980_0.h"
#include "table/big5.h"

//#define ENCODING_ZH_EXT

#include "table/cns11643_1992_1.h"
#include "table/cns11643_1992_2.h"
#include "table/cns11643_1992_3.h"
#include "table/cns11643_1992_4.h"
#include "table/cns11643_1992_5.h"
#include "table/cns11643_1992_6.h"
#include "table/cns11643_1992_7.h"
#include "table/cns11643_1992_f.h"
#include "table/big5_ext.h"
#include "table/big5_plus.h"

//#define ENCODING_VN

#include "table/viscii.h"

//#define ENCODING_JP

#include "table/jis0201_1976_0.h"
#include "table/jis0208_1990_0.h"
#include "table/jis0212_1990_0.h"

//#define ENCODING_JP_EXT

#include "table/jis0213_1.h"
#include "table/jis0213_2.h"

#if ENCODING_TO_UNICODE
# define ENC(base) { cs_ ## base ## _from_unicode, cs_ ## base ## _to_unicode }
#else
# define ENC(base) { cs_ ## base ## _from_unicode }
#endif
  

// order must match table in encoding.h(!)
const rxvt_codeset_conv rxvt_codeset[NUM_CODESETS] = {
  ENC (unknown),

  ENC (us_ascii),

  ENC (iso8859_1),
  ENC (iso8859_2),
  ENC (iso8859_3),
  ENC (iso8859_4),
  ENC (iso8859_5),
  ENC (iso8859_6),
  ENC (iso8859_7),
  ENC (iso8859_8),
  ENC (iso8859_9),
  ENC (iso8859_10),
  ENC (iso8859_11),
  ENC (iso8859_13),
  ENC (iso8859_14),
  ENC (iso8859_15),
  ENC (iso8859_16),

  ENC (koi8_r),
  ENC (koi8_u),

  ENC (jis0201_1976_0),
  ENC (jis0208_1990_0),
  ENC (jis0212_1990_0),

  ENC (jis0213_1),
  ENC (jis0213_2),

  ENC (ksc5601_1987_0),

  ENC (gb2312_1980_0),

  ENC (cns11643_1992_1),
  ENC (cns11643_1992_2),
  ENC (cns11643_1992_3),
  ENC (cns11643_1992_4),
  ENC (cns11643_1992_5),
  ENC (cns11643_1992_6),
  ENC (cns11643_1992_7),
  ENC (cns11643_1992_f),
  ENC (big5),
  ENC (big5_ext),
  ENC (big5_plus),

  ENC (viscii),

  ENC (unicode_16),
  ENC (unicode),
};

#if ENABLE_COMBINING
# define ENCODING_COMPOSE
#endif

#include "table/compose.h"

unicode_t
rxvt_compose (unicode_t c1, unicode_t c2)
{
  int l = 0;
  int r = sizeof (rxvt_compose_table) / sizeof (rxvt_compose_entry) - 1;
  int m;

  while (r > l)
    {
      m = (l + r) / 2;
      rxvt_compose_entry &c = rxvt_compose_table[m];

      if (c.c1 < c1 || (c.c1 == c1 && c.c2 < c2))
        l = m + 1;
      else if (c.c1 > c1 || (c.c1 == c1 && c.c2 > c2))
        r = m - 1;
      else
        return c.r;
    }

  return NOCHAR;
}

#include "table/category.h"

bool unicode::is_space (unicode_t c)
{
  return IS_SPACE (c)
         || c == 0x09; // exclude tabs, too, as we store them in the buffer
}
Revision:	1.20
Committed:	Sun Sep 5 09:32:59 2004 UTC (19 years, 8 months ago) by root
Content type:	text/plain
Branch:	MAIN
CVS Tags:	rel-4_0, rel-4_1, rel-4_2, rel-4_3
Changes since 1.19:	+2 -2 lines
Log Message:	* empty log message *
#	Content
1	/---------------------------------C----------------------------------
2	* File: encoding.C
3	----------------------------------------------------------------------
4	*
5	* All portions of code are copyright by their respective author/s.
6	* Copyright (c) 2003-2004 Marc Lehmann <pcg@goof.com>
7	*
8	* This program is free software; you can redistribute it and/or modify
9	* it under the terms of the GNU General Public License as published by
10	* the Free Software Foundation; either version 2 of the License, or
11	* (at your option) any later version.
12	*
13	* This program is distributed in the hope that it will be useful,
14	* but WITHOUT ANY WARRANTY; without even the implied warranty of
15	* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16	* GNU General Public License for more details.
17	*
18	* You should have received a copy of the GNU General Public License
19	* along with this program; if not, write to the Free Software
20	* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
21	----------------------------------------------------------------------/
22
23	#include "../config.h"
24
25	#include "encoding.h"
26
27	#include <cstdlib>
28	#include <cstring>
29
30	const struct n2cs {
31	const char *name;
32	codeset cs;
33	} n2cs[] = {
34	/* first one found is the normalized one */
35	{ "ISO88591", CS_ISO8859_1 },
36	{ "ISO8859PRIMARY", CS_ISO8859_1 }, // some stupid fonts use this (hi tigert)
37	{ "ISO88592", CS_ISO8859_2 },
38	{ "ISO88593", CS_ISO8859_3 },
39	{ "ISO88594", CS_ISO8859_4 },
40	{ "ISO88595", CS_ISO8859_5 },
41	{ "ISO88596", CS_ISO8859_6 },
42	{ "ISO88597", CS_ISO8859_7 },
43	{ "ISO88598", CS_ISO8859_8 },
44	{ "ISO88599", CS_ISO8859_9 },
45	{ "ISO885910", CS_ISO8859_10 },
46	{ "ISO885911", CS_ISO8859_11 },
47	{ "ISO885913", CS_ISO8859_13 },
48	{ "ISO885914", CS_ISO8859_14 },
49	{ "ISO885915", CS_ISO8859_15 },
50	{ "FCD885915", CS_ISO8859_15 },
51	{ "ISO885916", CS_ISO8859_16 },
52
53	{ "TIS620*", CS_ISO8859_11 }, // close enough
54
55	{ "ISO10646*", CS_UNICODE },
56	{ "UNICODE", CS_UNICODE },
57	{ "UTF8", CS_UNICODE },
58
59	{ "ASCII", CS_US_ASCII },
60	{ "USASCII", CS_US_ASCII },
61	{ "ANSIX341968", CS_US_ASCII },
62
63	{ "KOI8R", CS_KOI8_R },
64	{ "GOST1976874*", CS_KOI8_R },
65	{ "KOI8RU", CS_KOI8_U },
66	{ "KOI8U", CS_KOI8_U },
67
68	{ "VISCII*", CS_VISCII },
69
70	{ "JISX0201*", CS_JIS0201_1976_0 },
71	{ "JISC6226*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
72	{ "JISX0208*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
73	{ "JISX0212*", CS_JIS0212_1990_0 },
74	{ "JISX021320001", CS_JIS0213_1 },
75	{ "JISX021320002", CS_JIS0213_2 },
76	{ "JISX0221*", CS_UNICODE }, // _very_ close
77
78	{ "KSC5601*", CS_KSC5601_1987_0 },
79	{ "KSX1001*", CS_KSC5601_1987_0 },
80	{ "KSC5700*", CS_UNICODE }, // unicode plus extensions
81
82	{ "BIG5P*", CS_BIG5_PLUS },
83	{ "BIG5ETEN*", CS_BIG5_EXT },
84	{ "BIG5*", CS_BIG5 },
85	{ "GB2312*", CS_GB2312_1980_0 },
86	{ "GB6345*", CS_GB2312_1980_0 }, // slightly different to gb2312??
87	{ "GB8565*", CS_GB2312_1980_0 }, // a superset of gb2312??
88	{ "GB13000*", CS_UNICODE },
89	{ "CNS1164319921", CS_CNS11643_1992_1 },
90	{ "CNS1164319922", CS_CNS11643_1992_2 },
91	{ "CNS1164319923", CS_CNS11643_1992_3 },
92	{ "CNS1164319924", CS_CNS11643_1992_4 },
93	{ "CNS1164319925", CS_CNS11643_1992_5 },
94	{ "CNS1164319926", CS_CNS11643_1992_6 },
95	{ "CNS1164319927", CS_CNS11643_1992_7 },
96	{ "CNS116431992F", CS_CNS11643_1992_F },
97
98	{ 0, CS_UNKNOWN }
99	};
100
101	static const char *
102	normalize_name (const char *name)
103	{
104	static char res[16];
105	char *r;
106
107	for (r = res; *name && r < res + 15; name++)
108	if ((name >= '0' && name <= '9')
109	\|\| (name >= 'A' && name <= 'Z'))
110	r++ = name;
111	else if (name >= 'a' && name <= 'z')
112	r++ = name - ('a' - 'A');
113
114	*r = 0;
115
116	return res;
117	}
118
119	codeset
120	codeset_from_name (const char *name)
121	{
122	if (!name)
123	return CS_UNKNOWN;
124
125	name = normalize_name (name);
126
127	const struct n2cs *i = n2cs;
128
129	do {
130	int len = strlen (i->name);
131
132	if ((i->name[len - 1] == '*'
133	&& !strncmp (name, i->name, len - 1))
134	\|\| !strcmp (name, i->name))
135	return i->cs;
136
137	} while ((++i)->name);
138
139	return CS_UNKNOWN;
140	}
141
142	static unicode_t cs_unknown_to_unicode (uint32_t enc) { return NOCHAR; }
143	static uint32_t cs_unknown_from_unicode (unicode_t unicode) { return NOCHAR; }
144
145	static unicode_t cs_unicode_to_unicode (uint32_t enc) { return enc; }
146	static uint32_t cs_unicode_from_unicode (unicode_t unicode) { return unicode; }
147
148	#define cs_us_ascii_to_unicode cs_unicode_to_unicode
149	static uint32_t cs_us_ascii_from_unicode (unicode_t unicode) { return unicode <= 127 ? unicode : NOCHAR; }
150
151	#define cs_us_ascii_to_unicode_16 cs_unicode_to_unicode
152	static uint32_t cs_unicode_16_from_unicode (unicode_t unicode) { return unicode <= 65535 ? unicode : NOCHAR; }
153
154	#define ENCODING_DEFAULT
155
156	#include "table/iso8859_1.h"
157	#include "table/iso8859_15.h"
158
159	//#define ENCODING_EU
160
161	#include "table/iso8859_2.h"
162	#include "table/iso8859_3.h"
163	#include "table/iso8859_4.h"
164	#include "table/iso8859_5.h"
165	#include "table/iso8859_6.h"
166	#include "table/iso8859_7.h"
167	#include "table/iso8859_8.h"
168	#include "table/iso8859_9.h"
169	#include "table/iso8859_10.h"
170	#include "table/iso8859_11.h"
171	#include "table/iso8859_13.h"
172	#include "table/iso8859_14.h"
173	#include "table/iso8859_16.h"
174
175	#include "table/koi8_r.h"
176	#include "table/koi8_u.h"
177
178	//#define ENCODING_KR
179
180	#include "table/ksc5601_1987_0.h"
181
182	//#define ENCODING_ZH
183
184	#include "table/gb2312_1980_0.h"
185	#include "table/big5.h"
186
187	//#define ENCODING_ZH_EXT
188
189	#include "table/cns11643_1992_1.h"
190	#include "table/cns11643_1992_2.h"
191	#include "table/cns11643_1992_3.h"
192	#include "table/cns11643_1992_4.h"
193	#include "table/cns11643_1992_5.h"
194	#include "table/cns11643_1992_6.h"
195	#include "table/cns11643_1992_7.h"
196	#include "table/cns11643_1992_f.h"
197	#include "table/big5_ext.h"
198	#include "table/big5_plus.h"
199
200	//#define ENCODING_VN
201
202	#include "table/viscii.h"
203
204	//#define ENCODING_JP
205
206	#include "table/jis0201_1976_0.h"
207	#include "table/jis0208_1990_0.h"
208	#include "table/jis0212_1990_0.h"
209
210	//#define ENCODING_JP_EXT
211
212	#include "table/jis0213_1.h"
213	#include "table/jis0213_2.h"
214
215	#if ENCODING_TO_UNICODE
216	# define ENC(base) { cs_ ## base ## _from_unicode, cs_ ## base ## _to_unicode }
217	#else
218	# define ENC(base) { cs_ ## base ## _from_unicode }
219	#endif
220
221
222	// order must match table in encoding.h(!)
223	const rxvt_codeset_conv rxvt_codeset[NUM_CODESETS] = {
224	ENC (unknown),
225
226	ENC (us_ascii),
227
228	ENC (iso8859_1),
229	ENC (iso8859_2),
230	ENC (iso8859_3),
231	ENC (iso8859_4),
232	ENC (iso8859_5),
233	ENC (iso8859_6),
234	ENC (iso8859_7),
235	ENC (iso8859_8),
236	ENC (iso8859_9),
237	ENC (iso8859_10),
238	ENC (iso8859_11),
239	ENC (iso8859_13),
240	ENC (iso8859_14),
241	ENC (iso8859_15),
242	ENC (iso8859_16),
243
244	ENC (koi8_r),
245	ENC (koi8_u),
246
247	ENC (jis0201_1976_0),
248	ENC (jis0208_1990_0),
249	ENC (jis0212_1990_0),
250
251	ENC (jis0213_1),
252	ENC (jis0213_2),
253
254	ENC (ksc5601_1987_0),
255
256	ENC (gb2312_1980_0),
257
258	ENC (cns11643_1992_1),
259	ENC (cns11643_1992_2),
260	ENC (cns11643_1992_3),
261	ENC (cns11643_1992_4),
262	ENC (cns11643_1992_5),
263	ENC (cns11643_1992_6),
264	ENC (cns11643_1992_7),
265	ENC (cns11643_1992_f),
266	ENC (big5),
267	ENC (big5_ext),
268	ENC (big5_plus),
269
270	ENC (viscii),
271
272	ENC (unicode_16),
273	ENC (unicode),
274	};
275
276	#if ENABLE_COMBINING
277	# define ENCODING_COMPOSE
278	#endif
279
280	#include "table/compose.h"
281
282	unicode_t
283	rxvt_compose (unicode_t c1, unicode_t c2)
284	{
285	int l = 0;
286	int r = sizeof (rxvt_compose_table) / sizeof (rxvt_compose_entry) - 1;
287	int m;
288
289	while (r > l)
290	{
291	m = (l + r) / 2;
292	rxvt_compose_entry &c = rxvt_compose_table[m];
293
294	if (c.c1 < c1 \|\| (c.c1 == c1 && c.c2 < c2))
295	l = m + 1;
296	else if (c.c1 > c1 \|\| (c.c1 == c1 && c.c2 > c2))
297	r = m - 1;
298	else
299	return c.r;
300	}
301
302	return NOCHAR;
303	}
304
305	#include "table/category.h"
306
307	bool unicode::is_space (unicode_t c)
308	{
309	return IS_SPACE (c)
310	\|\| c == 0x09; // exclude tabs, too, as we store them in the buffer
311	}