1 /*
2 * local.c - translate our internal character set codes to and from
3 * our own set of plausibly legible character-set names. Also
4 * provides a canonical name for each encoding (useful for software
5 * announcing what character set it will be using), and a set of
6 * enumeration functions which return a list of supported
7 * encodings one by one.
8 *
9 * Also in this table are other ways people might plausibly refer
10 * to a charset (for example, Win1252 as well as CP1252). Where
11 * more than one string is given for a particular character set,
12 * the first one is the canonical one returned by
13 * charset_to_localenc.
14 *
15 * charset_from_localenc will attempt all other text translations
16 * as well as this table, to maximise the number of different ways
17 * you can select a supported charset.
18 */
19
20 #include <ctype.h>
21 #include "charset.h"
22 #include "internal.h"
23
24 static const struct {
25 const char *name;
26 int charset;
27 int return_in_enum; /* enumeration misses some charsets */
28 } localencs[] = {
29 { "<UNKNOWN>", CS_NONE, 0 },
30 { "ASCII", CS_ASCII, 1 },
31 { "BS 4730", CS_BS4730, 1 },
32 { "BS-4730", CS_BS4730, 0 },
33 { "BS4730", CS_BS4730, 0 },
34 { "ISO-8859-1", CS_ISO8859_1, 1 },
35 { "ISO-8859-1 with X11 line drawing", CS_ISO8859_1_X11, 0 },
36 { "ISO-8859-1-X11", CS_ISO8859_1_X11, 0 },
37 { "ISO8859-1-X11", CS_ISO8859_1_X11, 0 },
38 { "ISO-8859-2", CS_ISO8859_2, 1 },
39 { "ISO-8859-3", CS_ISO8859_3, 1 },
40 { "ISO-8859-4", CS_ISO8859_4, 1 },
41 { "ISO-8859-5", CS_ISO8859_5, 1 },
42 { "ISO-8859-6", CS_ISO8859_6, 1 },
43 { "ISO-8859-7", CS_ISO8859_7, 1 },
44 { "ISO-8859-8", CS_ISO8859_8, 1 },
45 { "ISO-8859-9", CS_ISO8859_9, 1 },
46 { "ISO-8859-10", CS_ISO8859_10, 1 },
47 { "ISO-8859-11", CS_ISO8859_11, 1 },
48 { "ISO-8859-13", CS_ISO8859_13, 1 },
49 { "ISO-8859-14", CS_ISO8859_14, 1 },
50 { "ISO-8859-15", CS_ISO8859_15, 1 },
51 { "ISO-8859-16", CS_ISO8859_16, 1 },
52 { "CP437", CS_CP437, 1 },
53 { "CP850", CS_CP850, 1 },
54 { "CP852", CS_CP852, 1 },
55 { "CP866", CS_CP866, 1 },
56 { "CP874", CS_CP874, 1 },
57 { "Win874", CS_CP874, 0 },
58 { "Win-874", CS_CP874, 0 },
59 { "CP1250", CS_CP1250, 1 },
60 { "Win1250", CS_CP1250, 0 },
61 { "CP1251", CS_CP1251, 1 },
62 { "Win1251", CS_CP1251, 0 },
63 { "CP1252", CS_CP1252, 1 },
64 { "Win1252", CS_CP1252, 0 },
65 { "CP1253", CS_CP1253, 1 },
66 { "Win1253", CS_CP1253, 0 },
67 { "CP1254", CS_CP1254, 1 },
68 { "Win1254", CS_CP1254, 0 },
69 { "CP1255", CS_CP1255, 1 },
70 { "Win1255", CS_CP1255, 0 },
71 { "CP1256", CS_CP1256, 1 },
72 { "Win1256", CS_CP1256, 0 },
73 { "CP1257", CS_CP1257, 1 },
74 { "Win1257", CS_CP1257, 0 },
75 { "CP1258", CS_CP1258, 1 },
76 { "Win1258", CS_CP1258, 0 },
77 { "KOI8-R", CS_KOI8_R, 1 },
78 { "KOI8-U", CS_KOI8_U, 1 },
79 { "KOI8-RU", CS_KOI8_RU, 1 },
80 { "JIS X 0201", CS_JISX0201, 1 },
81 { "JIS-X-0201", CS_JISX0201, 0 },
82 { "JIS_X_0201", CS_JISX0201, 0 },
83 { "JISX0201", CS_JISX0201, 0 },
84 { "Mac Roman", CS_MAC_ROMAN, 1 },
85 { "Mac-Roman", CS_MAC_ROMAN, 0 },
86 { "MacRoman", CS_MAC_ROMAN, 0 },
87 { "Mac Turkish", CS_MAC_TURKISH, 1 },
88 { "Mac-Turkish", CS_MAC_TURKISH, 0 },
89 { "MacTurkish", CS_MAC_TURKISH, 0 },
90 { "Mac Croatian", CS_MAC_CROATIAN, 1 },
91 { "Mac-Croatian", CS_MAC_CROATIAN, 0 },
92 { "MacCroatian", CS_MAC_CROATIAN, 0 },
93 { "Mac Iceland", CS_MAC_ICELAND, 1 },
94 { "Mac-Iceland", CS_MAC_ICELAND, 0 },
95 { "MacIceland", CS_MAC_ICELAND, 0 },
96 { "Mac Romanian", CS_MAC_ROMANIAN, 1 },
97 { "Mac-Romanian", CS_MAC_ROMANIAN, 0 },
98 { "MacRomanian", CS_MAC_ROMANIAN, 0 },
99 { "Mac Greek", CS_MAC_GREEK, 1 },
100 { "Mac-Greek", CS_MAC_GREEK, 0 },
101 { "MacGreek", CS_MAC_GREEK, 0 },
102 { "Mac Cyrillic", CS_MAC_CYRILLIC, 1 },
103 { "Mac-Cyrillic", CS_MAC_CYRILLIC, 0 },
104 { "MacCyrillic", CS_MAC_CYRILLIC, 0 },
105 { "Mac Thai", CS_MAC_THAI, 1 },
106 { "Mac-Thai", CS_MAC_THAI, 0 },
107 { "MacThai", CS_MAC_THAI, 0 },
108 { "Mac Centeuro", CS_MAC_CENTEURO, 1 },
109 { "Mac-Centeuro", CS_MAC_CENTEURO, 0 },
110 { "MacCenteuro", CS_MAC_CENTEURO, 0 },
111 { "Mac Symbol", CS_MAC_SYMBOL, 1 },
112 { "Mac-Symbol", CS_MAC_SYMBOL, 0 },
113 { "MacSymbol", CS_MAC_SYMBOL, 0 },
114 { "Mac Dingbats", CS_MAC_DINGBATS, 1 },
115 { "Mac-Dingbats", CS_MAC_DINGBATS, 0 },
116 { "MacDingbats", CS_MAC_DINGBATS, 0 },
117 { "Mac Roman (old)", CS_MAC_ROMAN_OLD, 0 },
118 { "Mac-Roman-old", CS_MAC_ROMAN_OLD, 0 },
119 { "MacRoman-old", CS_MAC_ROMAN_OLD, 0 },
120 { "Mac Croatian (old)", CS_MAC_CROATIAN_OLD, 0 },
121 { "Mac-Croatian-old", CS_MAC_CROATIAN_OLD, 0 },
122 { "MacCroatian-old", CS_MAC_CROATIAN_OLD, 0 },
123 { "Mac Iceland (old)", CS_MAC_ICELAND_OLD, 0 },
124 { "Mac-Iceland-old", CS_MAC_ICELAND_OLD, 0 },
125 { "MacIceland-old", CS_MAC_ICELAND_OLD, 0 },
126 { "Mac Romanian (old)", CS_MAC_ROMANIAN_OLD, 0 },
127 { "Mac-Romanian-old", CS_MAC_ROMANIAN_OLD, 0 },
128 { "MacRomanian-old", CS_MAC_ROMANIAN_OLD, 0 },
129 { "Mac Greek (old)", CS_MAC_GREEK_OLD, 0 },
130 { "Mac-Greek-old", CS_MAC_GREEK_OLD, 0 },
131 { "MacGreek-old", CS_MAC_GREEK_OLD, 0 },
132 { "Mac Cyrillic (old)", CS_MAC_CYRILLIC_OLD, 0 },
133 { "Mac-Cyrillic-old", CS_MAC_CYRILLIC_OLD, 0 },
134 { "MacCyrillic-old", CS_MAC_CYRILLIC_OLD, 0 },
135 { "Mac Ukraine", CS_MAC_UKRAINE, 1 },
136 { "Mac-Ukraine", CS_MAC_UKRAINE, 0 },
137 { "MacUkraine", CS_MAC_UKRAINE, 0 },
138 { "Mac VT100", CS_MAC_VT100, 1 },
139 { "Mac-VT100", CS_MAC_VT100, 0 },
140 { "MacVT100", CS_MAC_VT100, 0 },
141 { "Mac VT100 (old)", CS_MAC_VT100_OLD, 0 },
142 { "Mac-VT100-old", CS_MAC_VT100_OLD, 0 },
143 { "MacVT100-old", CS_MAC_VT100_OLD, 0 },
144 { "Mac Roman (Pirard encoding)", CS_MAC_PIRARD, 0 },
145 { "Mac Pirard", CS_MAC_PIRARD, 0 },
146 { "Mac-Pirard", CS_MAC_PIRARD, 0 },
147 { "MacPirard", CS_MAC_PIRARD, 0 },
148 { "VISCII", CS_VISCII, 1 },
149 { "HP ROMAN8", CS_HP_ROMAN8, 1 },
150 { "HP-ROMAN8", CS_HP_ROMAN8, 0 },
151 { "DEC MCS", CS_DEC_MCS, 1 },
152 { "DEC-MCS", CS_DEC_MCS, 1 },
153 { "DEC graphics", CS_DEC_GRAPHICS, 1 },
154 { "DEC-graphics", CS_DEC_GRAPHICS, 0 },
155 { "DECgraphics", CS_DEC_GRAPHICS, 0 },
156 { "UTF-8", CS_UTF8, 1 },
157 { "UTF-7", CS_UTF7, 1 },
158 { "UTF-7-conservative", CS_UTF7_CONSERVATIVE, 0 },
159 { "EUC-CN", CS_EUC_CN, 1 },
160 { "EUC-KR", CS_EUC_KR, 1 },
161 { "EUC-JP", CS_EUC_JP, 1 },
162 { "EUC-TW", CS_EUC_TW, 1 },
163 { "ISO-2022-JP", CS_ISO2022_JP, 1 },
164 { "ISO-2022-KR", CS_ISO2022_KR, 1 },
165 { "Big5", CS_BIG5, 1 },
166 { "Shift-JIS", CS_SHIFT_JIS, 1 },
167 { "HZ", CS_HZ, 1 },
168 { "UTF-16BE", CS_UTF16BE, 1 },
169 { "UTF-16LE", CS_UTF16LE, 1 },
170 { "UTF-16", CS_UTF16, 1 },
171 { "CP949", CS_CP949, 1 },
172 { "PDFDocEncoding", CS_PDF, 1 },
173 { "StandardEncoding", CS_PSSTD, 1 },
174 { "COMPOUND_TEXT", CS_CTEXT, 1 },
175 { "COMPOUND-TEXT", CS_CTEXT, 0 },
176 { "COMPOUND TEXT", CS_CTEXT, 0 },
177 { "COMPOUNDTEXT", CS_CTEXT, 0 },
178 { "CTEXT", CS_CTEXT, 0 },
179 { "ISO-2022", CS_ISO2022, 1 },
180 { "ISO2022", CS_ISO2022, 0 },
181 };
182
charset_to_localenc(int charset)183 const char *charset_to_localenc(int charset)
184 {
185 int i;
186
187 for (i = 0; i < (int)lenof(localencs); i++)
188 if (charset == localencs[i].charset)
189 return localencs[i].name;
190
191 return NULL; /* not found */
192 }
193
charset_from_localenc(const char * name)194 int charset_from_localenc(const char *name)
195 {
196 int i;
197
198 if ( (i = charset_from_mimeenc(name)) != CS_NONE)
199 return i;
200 if ( (i = charset_from_xenc(name)) != CS_NONE)
201 return i;
202 if ( (i = charset_from_emacsenc(name)) != CS_NONE)
203 return i;
204
205 for (i = 0; i < (int)lenof(localencs); i++) {
206 const char *p, *q;
207 p = name;
208 q = localencs[i].name;
209 while (*p || *q) {
210 if (tolower((unsigned char)*p) != tolower((unsigned char)*q))
211 break;
212 p++; q++;
213 }
214 if (!*p && !*q)
215 return localencs[i].charset;
216 }
217
218 return CS_NONE; /* not found */
219 }
220
charset_localenc_nth(int n)221 int charset_localenc_nth(int n)
222 {
223 int i;
224
225 for (i = 0; i < (int)lenof(localencs); i++)
226 if (localencs[i].return_in_enum && !n--)
227 return localencs[i].charset;
228
229 return CS_NONE; /* end of list */
230 }
231