… | |
… | |
8 | const struct n2cs { |
8 | const struct n2cs { |
9 | const char *name; |
9 | const char *name; |
10 | codeset cs; |
10 | codeset cs; |
11 | } n2cs[] = { |
11 | } n2cs[] = { |
12 | /* first one found is the normalized one */ |
12 | /* first one found is the normalized one */ |
13 | { "ISO88591", CS_ISO8859_1 }, |
13 | { "ISO88591", CS_ISO8859_1 }, |
14 | { "ISO8859PRIMARY", CS_ISO8859_1 }, // some stupid fonts use this (hi tigert) |
14 | { "ISO8859PRIMARY", CS_ISO8859_1 }, // some stupid fonts use this (hi tigert) |
15 | { "ISO88592", CS_ISO8859_2 }, |
15 | { "ISO88592", CS_ISO8859_2 }, |
16 | { "ISO88593", CS_ISO8859_3 }, |
16 | { "ISO88593", CS_ISO8859_3 }, |
17 | { "ISO88594", CS_ISO8859_4 }, |
17 | { "ISO88594", CS_ISO8859_4 }, |
18 | { "ISO88595", CS_ISO8859_5 }, |
18 | { "ISO88595", CS_ISO8859_5 }, |
19 | { "ISO88596", CS_ISO8859_6 }, |
19 | { "ISO88596", CS_ISO8859_6 }, |
20 | { "ISO88597", CS_ISO8859_7 }, |
20 | { "ISO88597", CS_ISO8859_7 }, |
21 | { "ISO88598", CS_ISO8859_8 }, |
21 | { "ISO88598", CS_ISO8859_8 }, |
22 | { "ISO88599", CS_ISO8859_9 }, |
22 | { "ISO88599", CS_ISO8859_9 }, |
23 | { "ISO885910", CS_ISO8859_10 }, |
23 | { "ISO885910", CS_ISO8859_10 }, |
24 | { "ISO885911", CS_ISO8859_11 }, |
24 | { "ISO885911", CS_ISO8859_11 }, |
25 | { "ISO885913", CS_ISO8859_13 }, |
25 | { "ISO885913", CS_ISO8859_13 }, |
26 | { "ISO885914", CS_ISO8859_14 }, |
26 | { "ISO885914", CS_ISO8859_14 }, |
27 | { "ISO885915", CS_ISO8859_15 }, |
27 | { "ISO885915", CS_ISO8859_15 }, |
28 | { "FCD885915", CS_ISO8859_15 }, |
28 | { "FCD885915", CS_ISO8859_15 }, |
29 | { "ISO885916", CS_ISO8859_16 }, |
29 | { "ISO885916", CS_ISO8859_16 }, |
|
|
30 | |
|
|
31 | { "TIS620*", CS_ISO8859_11 }, // close enough |
30 | |
32 | |
31 | { "ISO106461", CS_UNICODE }, |
33 | { "ISO10646*", CS_UNICODE }, |
32 | { "UNICODE", CS_UNICODE }, |
34 | { "UNICODE", CS_UNICODE }, |
33 | { "UTF8", CS_UNICODE }, |
35 | { "UTF8", CS_UNICODE }, |
34 | |
36 | |
35 | { "ASCII", CS_US_ASCII }, |
37 | { "ASCII", CS_US_ASCII }, |
36 | { "USASCII", CS_US_ASCII }, |
38 | { "USASCII", CS_US_ASCII }, |
37 | { "ANSIX341968", CS_US_ASCII }, |
39 | { "ANSIX341968", CS_US_ASCII }, |
38 | |
40 | |
39 | { "KOI8R", CS_KOI8_R }, |
41 | { "KOI8R", CS_KOI8_R }, |
40 | { "GOST19768741", CS_KOI8_R }, |
42 | { "GOST1976874*", CS_KOI8_R }, |
|
|
43 | { "KOI8RU", CS_KOI8_U }, |
41 | { "KOI8U", CS_KOI8_U }, |
44 | { "KOI8U", CS_KOI8_U }, |
42 | |
45 | |
43 | { "KSC560119870", CS_KSC5601_1987_0 }, |
|
|
44 | { "KSX100119970", CS_KSC5601_1987_0 }, |
|
|
45 | { "KSX100119980", CS_KSC5601_1987_0 }, // adds johab |
|
|
46 | |
|
|
47 | { "GB231219800", CS_GB2312_1980_0 }, |
|
|
48 | |
|
|
49 | { "VISCII", CS_VISCII }, |
46 | { "VISCII*", CS_VISCII }, |
50 | { "VISCII111", CS_VISCII }, |
47 | |
51 | { "TIS62025291", CS_VISCII }, /* close enough */ |
|
|
52 | |
|
|
53 | { "JISX020119760", CS_JIS0201_1976_0 }, |
48 | { "JISX0201*", CS_JIS0201_1976_0 }, |
54 | { "JISX020819830", CS_JIS0208_1983_0 }, |
49 | { "JISX0208*", CS_JIS0208_1983_0 }, // also wrongly matches -1990-0 (check Encode::JP) |
55 | { "JISX020819900", CS_JIS0208_1983_0 }, /* ehrm. */ |
|
|
56 | { "JISX021219900", CS_JIS0212_1990_0 }, |
50 | { "JISX0212*", CS_JIS0212_1990_0 }, |
|
|
51 | { "JISX0221*", CS_UNICODE }, |
|
|
52 | |
|
|
53 | { "KSC5601*", CS_KSC5601_1987_0 }, |
|
|
54 | { "KSX1001*", CS_KSC5601_1987_0 }, |
|
|
55 | { "KSC5700*", CS_UNICODE }, // unicode plus extensions |
|
|
56 | |
|
|
57 | { "BIG5P*", CS_BIG5_PLUS }, |
|
|
58 | { "BIG5ETEN*", CS_BIG5_EXT }, |
|
|
59 | { "BIG5*", CS_BIG5 }, |
|
|
60 | { "GB2312*", CS_GB2312_1980_0 }, |
|
|
61 | { "GB6345*", CS_GB2312_1980_0 }, // slightly different to gb2312?? |
|
|
62 | { "GB8565*", CS_GB2312_1980_0 }, // a superset of gb2312?? |
|
|
63 | { "GB13000*", CS_UNICODE }, |
|
|
64 | { "CNS1164319921", CS_CNS11643_1992_1 }, |
|
|
65 | { "CNS1164319922", CS_CNS11643_1992_2 }, |
|
|
66 | { "CNS1164319923", CS_CNS11643_1992_3 }, |
|
|
67 | { "CNS1164319924", CS_CNS11643_1992_4 }, |
|
|
68 | { "CNS1164319925", CS_CNS11643_1992_5 }, |
|
|
69 | { "CNS1164319926", CS_CNS11643_1992_6 }, |
|
|
70 | { "CNS1164319927", CS_CNS11643_1992_7 }, |
|
|
71 | { "CNS116431992F", CS_CNS11643_1992_F }, |
57 | |
72 | |
58 | { 0, CS_UNKNOWN } |
73 | { 0, CS_UNKNOWN } |
59 | }; |
74 | }; |
60 | |
75 | |
61 | static const char * |
76 | static const char * |
… | |
… | |
85 | name = normalize_name (name); |
100 | name = normalize_name (name); |
86 | |
101 | |
87 | const struct n2cs *i = n2cs; |
102 | const struct n2cs *i = n2cs; |
88 | |
103 | |
89 | do { |
104 | do { |
|
|
105 | int len = strlen (i->name); |
|
|
106 | |
|
|
107 | if ((i->name[len - 1] == '*' |
|
|
108 | && !strncmp (name, i->name, len - 1)) |
90 | if (!strcmp (name, i->name)) |
109 | || !strcmp (name, i->name)) |
91 | return i->cs; |
110 | return i->cs; |
|
|
111 | |
92 | } while ((++i)->name); |
112 | } while ((++i)->name); |
93 | |
113 | |
94 | return CS_UNKNOWN; |
114 | return CS_UNKNOWN; |
95 | } |
115 | } |
96 | |
116 | |
… | |
… | |
109 | |
129 | |
110 | struct rxvt_codeset_conv_unicode_16 : rxvt_codeset_conv { |
130 | struct rxvt_codeset_conv_unicode_16 : rxvt_codeset_conv { |
111 | uint32_t to_unicode (uint32_t enc) const { return enc; } |
131 | uint32_t to_unicode (uint32_t enc) const { return enc; } |
112 | uint32_t from_unicode (uint32_t unicode) const { return unicode <= 65535 ? unicode : NOCHAR; } |
132 | uint32_t from_unicode (uint32_t unicode) const { return unicode <= 65535 ? unicode : NOCHAR; } |
113 | } rxvt_codeset_conv_unicode_16; |
133 | } rxvt_codeset_conv_unicode_16; |
114 | |
|
|
115 | /* block character set, must conform to the dec special pseudofont in defaultfont.C */ |
|
|
116 | struct rxvt_codeset_conv_special : rxvt_codeset_conv { |
|
|
117 | uint32_t to_unicode (uint32_t enc) const { |
|
|
118 | return enc; |
|
|
119 | } |
|
|
120 | |
|
|
121 | uint32_t from_unicode (uint32_t unicode) const { |
|
|
122 | return unicode; |
|
|
123 | } |
|
|
124 | } rxvt_codeset_conv_special; |
|
|
125 | |
134 | |
126 | #define ENCODING_DEFAULT |
135 | #define ENCODING_DEFAULT |
127 | |
136 | |
128 | #include "table/iso8859_1.h" |
137 | #include "table/iso8859_1.h" |
129 | #include "table/iso8859_15.h" |
138 | #include "table/iso8859_15.h" |
… | |
… | |
152 | #include "table/ksc5601_1987_0.h" |
161 | #include "table/ksc5601_1987_0.h" |
153 | |
162 | |
154 | //#define ENCODING_CN |
163 | //#define ENCODING_CN |
155 | |
164 | |
156 | #include "table/gb2312_1980_0.h" |
165 | #include "table/gb2312_1980_0.h" |
|
|
166 | #include "table/big5.h" |
157 | |
167 | |
158 | //#define ENCODING_CN_EXT |
168 | //#define ENCODING_CN_EXT |
159 | |
169 | |
160 | #include "table/cns11643_1992_1.h" |
170 | #include "table/cns11643_1992_1.h" |
161 | #include "table/cns11643_1992_2.h" |
171 | #include "table/cns11643_1992_2.h" |
… | |
… | |
181 | //#define ENCODING_JP_EXT |
191 | //#define ENCODING_JP_EXT |
182 | |
192 | |
183 | #include "table/jis0213_1.h" |
193 | #include "table/jis0213_1.h" |
184 | #include "table/jis0213_2.h" |
194 | #include "table/jis0213_2.h" |
185 | |
195 | |
|
|
196 | // order must match table in encoding.h(!) |
186 | const rxvt_codeset_conv *rxvt_codeset[NUM_CODESETS] = { |
197 | const rxvt_codeset_conv *rxvt_codeset[NUM_CODESETS] = { |
187 | &rxvt_codeset_conv_unknown, |
198 | &rxvt_codeset_conv_unknown, |
188 | &rxvt_codeset_conv_special, |
|
|
189 | |
199 | |
190 | &rxvt_codeset_conv_us_ascii, |
200 | &rxvt_codeset_conv_us_ascii, |
191 | |
201 | |
192 | &rxvt_codeset_conv_iso8859_1, |
202 | &rxvt_codeset_conv_iso8859_1, |
193 | &rxvt_codeset_conv_iso8859_2, |
203 | &rxvt_codeset_conv_iso8859_2, |
… | |
… | |
225 | &rxvt_codeset_conv_cns11643_1992_4, |
235 | &rxvt_codeset_conv_cns11643_1992_4, |
226 | &rxvt_codeset_conv_cns11643_1992_5, |
236 | &rxvt_codeset_conv_cns11643_1992_5, |
227 | &rxvt_codeset_conv_cns11643_1992_6, |
237 | &rxvt_codeset_conv_cns11643_1992_6, |
228 | &rxvt_codeset_conv_cns11643_1992_7, |
238 | &rxvt_codeset_conv_cns11643_1992_7, |
229 | &rxvt_codeset_conv_cns11643_1992_f, |
239 | &rxvt_codeset_conv_cns11643_1992_f, |
|
|
240 | &rxvt_codeset_conv_big5, |
230 | &rxvt_codeset_conv_big5_ext, |
241 | &rxvt_codeset_conv_big5_ext, |
231 | &rxvt_codeset_conv_big5_plus, |
242 | &rxvt_codeset_conv_big5_plus, |
232 | |
243 | |
233 | &rxvt_codeset_conv_viscii, |
244 | &rxvt_codeset_conv_viscii, |
234 | |
245 | |
235 | &rxvt_codeset_conv_unicode_16, |
246 | &rxvt_codeset_conv_unicode_16, |
236 | &rxvt_codeset_conv_unicode |
247 | &rxvt_codeset_conv_unicode |
237 | }; |
248 | }; |
238 | |
249 | |
|
|
250 | //#define ENCODING_COMPOSE |
|
|
251 | |
|
|
252 | #include "table/compose.h" |
|
|
253 | |
|
|
254 | uint32_t |
|
|
255 | rxvt_compose (uint32_t c1, uint32_t c2) |
|
|
256 | { |
|
|
257 | int l = 0; |
|
|
258 | int r = sizeof (rxvt_compose_table) / sizeof (rxvt_compose_entry) - 1; |
|
|
259 | int m; |
|
|
260 | |
|
|
261 | while (r > l) |
|
|
262 | { |
|
|
263 | m = (l + r) / 2; |
|
|
264 | rxvt_compose_entry &c = rxvt_compose_table[m]; |
|
|
265 | |
|
|
266 | if (c.c1 < c1 || (c.c1 == c1 && c.c2 < c2)) |
|
|
267 | l = m + 1; |
|
|
268 | else if (c.c1 > c1 || (c.c1 == c1 && c.c2 > c2)) |
|
|
269 | r = m - 1; |
|
|
270 | else |
|
|
271 | return c.r; |
|
|
272 | } |
|
|
273 | |
|
|
274 | return NOCHAR; |
|
|
275 | } |