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.
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.
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.
27 int return_in_enum
; /* enumeration misses some charsets */
29 { "<UNKNOWN>", CS_NONE
, 0 },
30 { "ASCII", CS_ASCII
, 1 },
31 { "ISO-8859-1", CS_ISO8859_1
, 1 },
32 { "ISO-8859-1 with X11 line drawing", CS_ISO8859_1_X11
, 0 },
33 { "ISO-8859-2", CS_ISO8859_2
, 1 },
34 { "ISO-8859-3", CS_ISO8859_3
, 1 },
35 { "ISO-8859-4", CS_ISO8859_4
, 1 },
36 { "ISO-8859-5", CS_ISO8859_5
, 1 },
37 { "ISO-8859-6", CS_ISO8859_6
, 1 },
38 { "ISO-8859-7", CS_ISO8859_7
, 1 },
39 { "ISO-8859-8", CS_ISO8859_8
, 1 },
40 { "ISO-8859-9", CS_ISO8859_9
, 1 },
41 { "ISO-8859-10", CS_ISO8859_10
, 1 },
42 { "ISO-8859-11", CS_ISO8859_11
, 1 },
43 { "ISO-8859-13", CS_ISO8859_13
, 1 },
44 { "ISO-8859-14", CS_ISO8859_14
, 1 },
45 { "ISO-8859-15", CS_ISO8859_15
, 1 },
46 { "ISO-8859-16", CS_ISO8859_16
, 1 },
47 { "CP437", CS_CP437
, 1 },
48 { "CP850", CS_CP850
, 1 },
49 { "CP1250", CS_CP1250
, 1 },
50 { "Win1250", CS_CP1250
, 1 },
51 { "CP1251", CS_CP1251
, 1 },
52 { "Win1251", CS_CP1251
, 1 },
53 { "CP1252", CS_CP1252
, 1 },
54 { "Win1252", CS_CP1252
, 1 },
55 { "CP1253", CS_CP1253
, 1 },
56 { "Win1253", CS_CP1253
, 1 },
57 { "CP1254", CS_CP1254
, 1 },
58 { "Win1254", CS_CP1254
, 1 },
59 { "CP1255", CS_CP1255
, 1 },
60 { "Win1255", CS_CP1255
, 1 },
61 { "CP1256", CS_CP1256
, 1 },
62 { "Win1256", CS_CP1256
, 1 },
63 { "CP1257", CS_CP1257
, 1 },
64 { "Win1257", CS_CP1257
, 1 },
65 { "CP1258", CS_CP1258
, 1 },
66 { "Win1258", CS_CP1258
, 1 },
67 { "KOI8-R", CS_KOI8_R
, 1 },
68 { "KOI8-U", CS_KOI8_U
, 1 },
69 { "KOI8-RU", CS_KOI8_RU
, 1 },
70 { "JIS X 0201", CS_JISX0201
, 1 },
71 { "JIS-X-0201", CS_JISX0201
, 1 },
72 { "JIS_X_0201", CS_JISX0201
, 1 },
73 { "JISX0201", CS_JISX0201
, 1 },
74 { "Mac Roman", CS_MAC_ROMAN
, 1 },
75 { "Mac Turkish", CS_MAC_TURKISH
, 1 },
76 { "Mac Croatian", CS_MAC_CROATIAN
, 1 },
77 { "Mac Iceland", CS_MAC_ICELAND
, 1 },
78 { "Mac Romanian", CS_MAC_ROMANIAN
, 1 },
79 { "Mac Greek", CS_MAC_GREEK
, 1 },
80 { "Mac Cyrillic", CS_MAC_CYRILLIC
, 1 },
81 { "Mac Thai", CS_MAC_THAI
, 1 },
82 { "Mac Centeuro", CS_MAC_CENTEURO
, 1 },
83 { "Mac Symbol", CS_MAC_SYMBOL
, 1 },
84 { "Mac Dingbats", CS_MAC_DINGBATS
, 1 },
85 { "Mac Roman (old)", CS_MAC_ROMAN_OLD
, 0 },
86 { "Mac Croatian (old)", CS_MAC_CROATIAN_OLD
, 0 },
87 { "Mac Iceland (old)", CS_MAC_ICELAND_OLD
, 0 },
88 { "Mac Romanian (old)", CS_MAC_ROMANIAN_OLD
, 0 },
89 { "Mac Greek (old)", CS_MAC_GREEK_OLD
, 0 },
90 { "Mac Cyrillic (old)", CS_MAC_CYRILLIC_OLD
, 0 },
91 { "Mac Ukraine", CS_MAC_UKRAINE
, 1 },
92 { "Mac VT100", CS_MAC_VT100
, 1 },
93 { "Mac VT100 (old)", CS_MAC_VT100_OLD
, 0 },
94 { "VISCII", CS_VISCII
, 1 },
95 { "HP ROMAN8", CS_HP_ROMAN8
, 1 },
96 { "DEC MCS", CS_DEC_MCS
, 1 },
97 { "UTF-8", CS_UTF8
, 1 },
98 { "UTF-7", CS_UTF7
, 1 },
99 { "UTF-7-conservative", CS_UTF7_CONSERVATIVE
, 0 },
100 { "EUC-CN", CS_EUC_CN
, 1 },
101 { "EUC-KR", CS_EUC_KR
, 1 },
102 { "EUC-JP", CS_EUC_JP
, 1 },
103 { "ISO-2022-JP", CS_ISO2022_JP
, 1 },
104 { "ISO-2022-KR", CS_ISO2022_KR
, 1 },
105 { "Big5", CS_BIG5
, 1 },
106 { "Shift-JIS", CS_SHIFT_JIS
, 1 },
108 { "UTF-16BE", CS_UTF16BE
, 1 },
109 { "UTF-16LE", CS_UTF16LE
, 1 },
110 { "UTF-16", CS_UTF16
, 1 },
111 { "CP949", CS_CP949
, 1 },
112 { "PDFDocEncoding", CS_PDF
, 1 },
113 { "COMPOUND_TEXT", CS_CTEXT
, 1 },
114 { "COMPOUND-TEXT", CS_CTEXT
, 1 },
115 { "COMPOUND TEXT", CS_CTEXT
, 1 },
116 { "COMPOUNDTEXT", CS_CTEXT
, 1 },
117 { "CTEXT", CS_CTEXT
, 1 },
120 const char *charset_to_localenc(int charset
)
124 for (i
= 0; i
< (int)lenof(localencs
); i
++)
125 if (charset
== localencs
[i
].charset
)
126 return localencs
[i
].name
;
128 return NULL
; /* not found */
131 int charset_from_localenc(const char *name
)
135 if ( (i
= charset_from_mimeenc(name
)) != CS_NONE
)
137 if ( (i
= charset_from_xenc(name
)) != CS_NONE
)
140 for (i
= 0; i
< (int)lenof(localencs
); i
++) {
143 q
= localencs
[i
].name
;
145 if (tolower(*p
) != tolower(*q
))
150 return localencs
[i
].charset
;
153 return CS_NONE
; /* not found */
156 int charset_localenc_nth(int n
)
160 for (i
= 0; i
< (int)lenof(localencs
); i
++)
161 if (localencs
[i
].return_in_enum
&& !n
--)
162 return localencs
[i
].charset
;
164 return CS_NONE
; /* end of list */