rxvt-unicode/src/encoding.C

#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   },
  { "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;
}

struct rxvt_codeset_conv_unknown : rxvt_codeset_conv {
  unicode_t to_unicode (uint32_t enc) const { return NOCHAR; }
  uint32_t from_unicode (unicode_t unicode) const { return NOCHAR; }
} rxvt_codeset_conv_unknown;

struct rxvt_codeset_conv_us_ascii : rxvt_codeset_conv {
  uint32_t from_unicode (unicode_t unicode) const { return unicode <= 127 ? unicode : NOCHAR; }
} rxvt_codeset_conv_us_ascii;

struct rxvt_codeset_conv_unicode : rxvt_codeset_conv {
  /* transparent */
} rxvt_codeset_conv_unicode;

struct rxvt_codeset_conv_unicode_16 : rxvt_codeset_conv {
  unicode_t to_unicode (uint32_t enc) const { return enc; }
  uint32_t from_unicode (unicode_t unicode) const { return unicode <= 65535 ? unicode : NOCHAR; }
} rxvt_codeset_conv_unicode_16;

#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_CN

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

//#define ENCODING_CN_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"

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

  &rxvt_codeset_conv_us_ascii,

  &rxvt_codeset_conv_iso8859_1,
  &rxvt_codeset_conv_iso8859_2,
  &rxvt_codeset_conv_iso8859_3,
  &rxvt_codeset_conv_iso8859_4,
  &rxvt_codeset_conv_iso8859_5,
  &rxvt_codeset_conv_iso8859_6,
  &rxvt_codeset_conv_iso8859_7,
  &rxvt_codeset_conv_iso8859_8,
  &rxvt_codeset_conv_iso8859_9,
  &rxvt_codeset_conv_iso8859_10,
  &rxvt_codeset_conv_iso8859_11,
  &rxvt_codeset_conv_iso8859_13,
  &rxvt_codeset_conv_iso8859_14,
  &rxvt_codeset_conv_iso8859_15,
  &rxvt_codeset_conv_iso8859_16,

  &rxvt_codeset_conv_koi8_r,
  &rxvt_codeset_conv_koi8_u,

  &rxvt_codeset_conv_jis0201_1976_0,
  &rxvt_codeset_conv_jis0208_1990_0,
  &rxvt_codeset_conv_jis0212_1990_0,

  &rxvt_codeset_conv_jis0213_1,
  &rxvt_codeset_conv_jis0213_2,

  &rxvt_codeset_conv_ksc5601_1987_0,

  &rxvt_codeset_conv_gb2312_1980_0,

  &rxvt_codeset_conv_cns11643_1992_1,
  &rxvt_codeset_conv_cns11643_1992_2,
  &rxvt_codeset_conv_cns11643_1992_3,
  &rxvt_codeset_conv_cns11643_1992_4,
  &rxvt_codeset_conv_cns11643_1992_5,
  &rxvt_codeset_conv_cns11643_1992_6,
  &rxvt_codeset_conv_cns11643_1992_7,
  &rxvt_codeset_conv_cns11643_1992_f,
  &rxvt_codeset_conv_big5,
  &rxvt_codeset_conv_big5_ext,
  &rxvt_codeset_conv_big5_plus,

  &rxvt_codeset_conv_viscii,

  &rxvt_codeset_conv_unicode_16,
  &rxvt_codeset_conv_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);
}
Revision:	1.15
Committed:	Mon Mar 15 01:27:46 2004 UTC (20 years, 2 months ago) by pcg
Content type:	text/plain
Branch:	MAIN
CVS Tags:	rel-2_7, rel-2_4, rel-2_5
Changes since 1.10:	+20 -11 lines
Log Message:	* empty log message *
#	User	Rev	Content
1	pcg	1.1	#include "../config.h"
2
3			#include "encoding.h"
4
5			#include <cstdlib>
6			#include <cstring>
7
8			const struct n2cs {
9			const char *name;
10			codeset cs;
11			} n2cs[] = {
12			/* first one found is the normalized one */
13	pcg	1.3	{ "ISO88591", CS_ISO8859_1 },
14			{ "ISO8859PRIMARY", CS_ISO8859_1 }, // some stupid fonts use this (hi tigert)
15			{ "ISO88592", CS_ISO8859_2 },
16			{ "ISO88593", CS_ISO8859_3 },
17			{ "ISO88594", CS_ISO8859_4 },
18			{ "ISO88595", CS_ISO8859_5 },
19			{ "ISO88596", CS_ISO8859_6 },
20			{ "ISO88597", CS_ISO8859_7 },
21			{ "ISO88598", CS_ISO8859_8 },
22			{ "ISO88599", CS_ISO8859_9 },
23			{ "ISO885910", CS_ISO8859_10 },
24			{ "ISO885911", CS_ISO8859_11 },
25			{ "ISO885913", CS_ISO8859_13 },
26			{ "ISO885914", CS_ISO8859_14 },
27			{ "ISO885915", CS_ISO8859_15 },
28			{ "FCD885915", CS_ISO8859_15 },
29			{ "ISO885916", CS_ISO8859_16 },
30
31	pcg	1.9	{ "TIS620*", CS_ISO8859_11 }, // close enough
32
33	pcg	1.3	{ "ISO10646*", CS_UNICODE },
34			{ "UNICODE", CS_UNICODE },
35			{ "UTF8", CS_UNICODE },
36
37			{ "ASCII", CS_US_ASCII },
38			{ "USASCII", CS_US_ASCII },
39			{ "ANSIX341968", CS_US_ASCII },
40
41			{ "KOI8R", CS_KOI8_R },
42			{ "GOST1976874*", CS_KOI8_R },
43			{ "KOI8RU", CS_KOI8_U },
44			{ "KOI8U", CS_KOI8_U },
45
46			{ "VISCII*", CS_VISCII },
47
48			{ "JISX0201*", CS_JIS0201_1976_0 },
49	pcg	1.15	{ "JISX0208*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
50	pcg	1.3	{ "JISX0212*", CS_JIS0212_1990_0 },
51	pcg	1.15	{ "JISX021320001", CS_JIS0213_1 },
52			{ "JISX021320002", CS_JIS0213_2 },
53			{ "JISX0221*", CS_UNICODE }, // _very_ close
54	pcg	1.3
55			{ "KSC5601*", CS_KSC5601_1987_0 },
56			{ "KSX1001*", CS_KSC5601_1987_0 },
57			{ "KSC5700*", CS_UNICODE }, // unicode plus extensions
58
59			{ "BIG5P*", CS_BIG5_PLUS },
60			{ "BIG5ETEN*", CS_BIG5_EXT },
61			{ "BIG5*", CS_BIG5 },
62			{ "GB2312*", CS_GB2312_1980_0 },
63			{ "GB6345*", CS_GB2312_1980_0 }, // slightly different to gb2312??
64			{ "GB8565*", CS_GB2312_1980_0 }, // a superset of gb2312??
65			{ "GB13000*", CS_UNICODE },
66			{ "CNS1164319921", CS_CNS11643_1992_1 },
67			{ "CNS1164319922", CS_CNS11643_1992_2 },
68			{ "CNS1164319923", CS_CNS11643_1992_3 },
69			{ "CNS1164319924", CS_CNS11643_1992_4 },
70			{ "CNS1164319925", CS_CNS11643_1992_5 },
71			{ "CNS1164319926", CS_CNS11643_1992_6 },
72			{ "CNS1164319927", CS_CNS11643_1992_7 },
73			{ "CNS116431992F", CS_CNS11643_1992_F },
74	pcg	1.1
75			{ 0, CS_UNKNOWN }
76			};
77
78			static const char *
79			normalize_name (const char *name)
80			{
81			static char res[16];
82			char *r;
83
84			for (r = res; *name && r < res + 15; name++)
85			if ((name >= '0' && name <= '9')
86			\|\| (name >= 'A' && name <= 'Z'))
87			r++ = name;
88			else if (name >= 'a' && name <= 'z')
89			r++ = name - ('a' - 'A');
90
91			*r = 0;
92
93			return res;
94			}
95
96			codeset
97			codeset_from_name (const char *name)
98			{
99			if (!name)
100			return CS_UNKNOWN;
101
102			name = normalize_name (name);
103
104			const struct n2cs *i = n2cs;
105
106			do {
107	pcg	1.3	int len = strlen (i->name);
108
109			if ((i->name[len - 1] == '*'
110			&& !strncmp (name, i->name, len - 1))
111			\|\| !strcmp (name, i->name))
112			return i->cs;
113
114	pcg	1.1	} while ((++i)->name);
115
116			return CS_UNKNOWN;
117			}
118
119			struct rxvt_codeset_conv_unknown : rxvt_codeset_conv {
120	pcg	1.15	unicode_t to_unicode (uint32_t enc) const { return NOCHAR; }
121			uint32_t from_unicode (unicode_t unicode) const { return NOCHAR; }
122	pcg	1.1	} rxvt_codeset_conv_unknown;
123
124			struct rxvt_codeset_conv_us_ascii : rxvt_codeset_conv {
125	pcg	1.15	uint32_t from_unicode (unicode_t unicode) const { return unicode <= 127 ? unicode : NOCHAR; }
126	pcg	1.1	} rxvt_codeset_conv_us_ascii;
127
128			struct rxvt_codeset_conv_unicode : rxvt_codeset_conv {
129			/* transparent */
130			} rxvt_codeset_conv_unicode;
131
132			struct rxvt_codeset_conv_unicode_16 : rxvt_codeset_conv {
133	pcg	1.15	unicode_t to_unicode (uint32_t enc) const { return enc; }
134			uint32_t from_unicode (unicode_t unicode) const { return unicode <= 65535 ? unicode : NOCHAR; }
135	pcg	1.1	} rxvt_codeset_conv_unicode_16;
136
137			#define ENCODING_DEFAULT
138
139			#include "table/iso8859_1.h"
140			#include "table/iso8859_15.h"
141
142			//#define ENCODING_EU
143
144			#include "table/iso8859_2.h"
145			#include "table/iso8859_3.h"
146			#include "table/iso8859_4.h"
147			#include "table/iso8859_5.h"
148			#include "table/iso8859_6.h"
149			#include "table/iso8859_7.h"
150			#include "table/iso8859_8.h"
151			#include "table/iso8859_9.h"
152			#include "table/iso8859_10.h"
153			#include "table/iso8859_11.h"
154			#include "table/iso8859_13.h"
155			#include "table/iso8859_14.h"
156			#include "table/iso8859_16.h"
157
158			#include "table/koi8_r.h"
159			#include "table/koi8_u.h"
160
161			//#define ENCODING_KR
162
163			#include "table/ksc5601_1987_0.h"
164
165			//#define ENCODING_CN
166
167			#include "table/gb2312_1980_0.h"
168	pcg	1.3	#include "table/big5.h"
169	pcg	1.1
170			//#define ENCODING_CN_EXT
171
172			#include "table/cns11643_1992_1.h"
173			#include "table/cns11643_1992_2.h"
174			#include "table/cns11643_1992_3.h"
175			#include "table/cns11643_1992_4.h"
176			#include "table/cns11643_1992_5.h"
177			#include "table/cns11643_1992_6.h"
178			#include "table/cns11643_1992_7.h"
179			#include "table/cns11643_1992_f.h"
180			#include "table/big5_ext.h"
181			#include "table/big5_plus.h"
182
183			//#define ENCODING_VN
184
185			#include "table/viscii.h"
186
187			//#define ENCODING_JP
188
189			#include "table/jis0201_1976_0.h"
190	pcg	1.15	#include "table/jis0208_1990_0.h"
191	pcg	1.1	#include "table/jis0212_1990_0.h"
192
193			//#define ENCODING_JP_EXT
194
195			#include "table/jis0213_1.h"
196			#include "table/jis0213_2.h"
197
198	pcg	1.3	// order must match table in encoding.h(!)
199	pcg	1.1	const rxvt_codeset_conv *rxvt_codeset[NUM_CODESETS] = {
200			&rxvt_codeset_conv_unknown,
201
202			&rxvt_codeset_conv_us_ascii,
203
204			&rxvt_codeset_conv_iso8859_1,
205			&rxvt_codeset_conv_iso8859_2,
206			&rxvt_codeset_conv_iso8859_3,
207			&rxvt_codeset_conv_iso8859_4,
208			&rxvt_codeset_conv_iso8859_5,
209			&rxvt_codeset_conv_iso8859_6,
210			&rxvt_codeset_conv_iso8859_7,
211			&rxvt_codeset_conv_iso8859_8,
212			&rxvt_codeset_conv_iso8859_9,
213			&rxvt_codeset_conv_iso8859_10,
214			&rxvt_codeset_conv_iso8859_11,
215			&rxvt_codeset_conv_iso8859_13,
216			&rxvt_codeset_conv_iso8859_14,
217			&rxvt_codeset_conv_iso8859_15,
218			&rxvt_codeset_conv_iso8859_16,
219
220			&rxvt_codeset_conv_koi8_r,
221			&rxvt_codeset_conv_koi8_u,
222
223			&rxvt_codeset_conv_jis0201_1976_0,
224	pcg	1.15	&rxvt_codeset_conv_jis0208_1990_0,
225	pcg	1.1	&rxvt_codeset_conv_jis0212_1990_0,
226
227			&rxvt_codeset_conv_jis0213_1,
228			&rxvt_codeset_conv_jis0213_2,
229
230			&rxvt_codeset_conv_ksc5601_1987_0,
231
232			&rxvt_codeset_conv_gb2312_1980_0,
233
234			&rxvt_codeset_conv_cns11643_1992_1,
235			&rxvt_codeset_conv_cns11643_1992_2,
236			&rxvt_codeset_conv_cns11643_1992_3,
237			&rxvt_codeset_conv_cns11643_1992_4,
238			&rxvt_codeset_conv_cns11643_1992_5,
239			&rxvt_codeset_conv_cns11643_1992_6,
240			&rxvt_codeset_conv_cns11643_1992_7,
241			&rxvt_codeset_conv_cns11643_1992_f,
242	pcg	1.3	&rxvt_codeset_conv_big5,
243	pcg	1.1	&rxvt_codeset_conv_big5_ext,
244			&rxvt_codeset_conv_big5_plus,
245
246			&rxvt_codeset_conv_viscii,
247
248			&rxvt_codeset_conv_unicode_16,
249			&rxvt_codeset_conv_unicode
250			};
251
252	pcg	1.10	#if ENABLE_COMBINING
253			# define ENCODING_COMPOSE
254			#endif
255	pcg	1.9
256			#include "table/compose.h"
257
258	pcg	1.15	unicode_t
259			rxvt_compose (unicode_t c1, unicode_t c2)
260	pcg	1.9	{
261			int l = 0;
262			int r = sizeof (rxvt_compose_table) / sizeof (rxvt_compose_entry) - 1;
263			int m;
264
265			while (r > l)
266			{
267			m = (l + r) / 2;
268			rxvt_compose_entry &c = rxvt_compose_table[m];
269
270			if (c.c1 < c1 \|\| (c.c1 == c1 && c.c2 < c2))
271			l = m + 1;
272			else if (c.c1 > c1 \|\| (c.c1 == c1 && c.c2 > c2))
273			r = m - 1;
274			else
275			return c.r;
276			}
277
278			return NOCHAR;
279			}
280	pcg	1.15
281			#include "table/category.h"
282
283			bool unicode::is_space (unicode_t c)
284			{
285			return IS_SPACE (c);
286			}