Mercurial > emacs
comparison lisp/textmodes/po.el @ 43958:2479ec7d435b
(po-content-type-charset-alist): Convert the
car of each association to a string.
(po-find-file-coding-system-guts): If the charset matches a name
of a codepage, set up that codepage and return it as a coding
system to decode the file.
author | Eli Zaretskii <eliz@gnu.org> |
---|---|
date | Sat, 16 Mar 2002 17:28:49 +0000 |
parents | d97aaaffa849 |
children | 6082da91c94d |
comparison
equal
deleted
inserted
replaced
43957:1b07ba20bc15 | 43958:2479ec7d435b |
---|---|
32 | 32 |
33 ;;; Code: | 33 ;;; Code: |
34 | 34 |
35 (defconst po-content-type-charset-alist | 35 (defconst po-content-type-charset-alist |
36 '(; Note: Emacs 21 doesn't support all encodings, thus the missing entries. | 36 '(; Note: Emacs 21 doesn't support all encodings, thus the missing entries. |
37 (ASCII . undecided) | 37 ("ASCII" . undecided) |
38 (ANSI_X3.4-1968 . undecided) | 38 ("ANSI_X3.4-1968" . undecided) |
39 (US-ASCII . undecided) | 39 ("US-ASCII" . undecided) |
40 (ISO-8859-1 . iso-8859-1) | 40 ("ISO-8859-1" . iso-8859-1) |
41 (ISO_8859-1 . iso-8859-1) | 41 ("ISO_8859-1" . iso-8859-1) |
42 (ISO-8859-2 . iso-8859-2) | 42 ("ISO-8859-2" . iso-8859-2) |
43 (ISO_8859-2 . iso-8859-2) | 43 ("ISO_8859-2" . iso-8859-2) |
44 (ISO-8859-3 . iso-8859-3) | 44 ("ISO-8859-3" . iso-8859-3) |
45 (ISO_8859-3 . iso-8859-3) | 45 ("ISO_8859-3" . iso-8859-3) |
46 (ISO-8859-4 . iso-8859-4) | 46 ("ISO-8859-4" . iso-8859-4) |
47 (ISO_8859-4 . iso-8859-4) | 47 ("ISO_8859-4" . iso-8859-4) |
48 (ISO-8859-5 . iso-8859-5) | 48 ("ISO-8859-5" . iso-8859-5) |
49 (ISO_8859-5 . iso-8859-5) | 49 ("ISO_8859-5" . iso-8859-5) |
50 ;(ISO-8859-6 . ??) | 50 ;("ISO-8859-6" . ??) |
51 ;(ISO_8859-6 . ??) | 51 ;("ISO_8859-6" . ??) |
52 (ISO-8859-7 . iso-8859-7) | 52 ("ISO-8859-7" . iso-8859-7) |
53 (ISO_8859-7 . iso-8859-7) | 53 ("ISO_8859-7" . iso-8859-7) |
54 (ISO-8859-8 . iso-8859-8) | 54 ("ISO-8859-8" . iso-8859-8) |
55 (ISO_8859-8 . iso-8859-8) | 55 ("ISO_8859-8" . iso-8859-8) |
56 (ISO-8859-9 . iso-8859-9) | 56 ("ISO-8859-9" . iso-8859-9) |
57 (ISO_8859-9 . iso-8859-9) | 57 ("ISO_8859-9" . iso-8859-9) |
58 ;(ISO-8859-13 . ??) | 58 ;("ISO-8859-13" . ??) |
59 ;(ISO_8859-13 . ??) | 59 ;("ISO_8859-13" . ??) |
60 (ISO-8859-15 . iso-8859-15) ; requires Emacs 21 | 60 ("ISO-8859-15" . iso-8859-15) ; requires Emacs 21 |
61 (ISO_8859-15 . iso-8859-15) ; requires Emacs 21 | 61 ("ISO_8859-15" . iso-8859-15) ; requires Emacs 21 |
62 (KOI8-R . koi8-r) | 62 ("KOI8-R" . koi8-r) |
63 ;(KOI8-U . ??) | 63 ;("KOI8-U" . ??) |
64 (CP437 . cp437) ; requires Emacs 20 | 64 ("CP437" . cp437) ; requires Emacs 20 |
65 (CP775 . cp775) ; requires Emacs 20 | 65 ("CP775" . cp775) ; requires Emacs 20 |
66 (CP850 . cp850) ; requires Emacs 20 | 66 ("CP850" . cp850) ; requires Emacs 20 |
67 (CP852 . cp852) ; requires Emacs 20 | 67 ("CP852" . cp852) ; requires Emacs 20 |
68 (CP855 . cp855) ; requires Emacs 20 | 68 ("CP855" . cp855) ; requires Emacs 20 |
69 ;(CP856 . ??) | 69 ;("CP856" . ??) |
70 (CP857 . cp857) ; requires Emacs 20 | 70 ("CP857" . cp857) ; requires Emacs 20 |
71 (CP861 . cp861) ; requires Emacs 20 | 71 ("CP861" . cp861) ; requires Emacs 20 |
72 (CP862 . cp862) ; requires Emacs 20 | 72 ("CP862" . cp862) ; requires Emacs 20 |
73 (CP864 . cp864) ; requires Emacs 20 | 73 ("CP864" . cp864) ; requires Emacs 20 |
74 (CP865 . cp865) ; requires Emacs 20 | 74 ("CP865" . cp865) ; requires Emacs 20 |
75 (CP866 . cp866) ; requires Emacs 21 | 75 ("CP866" . cp866) ; requires Emacs 21 |
76 (CP869 . cp869) ; requires Emacs 20 | 76 ("CP869" . cp869) ; requires Emacs 20 |
77 ;(CP874 . ??) | 77 ;("CP874" . ??) |
78 ;(CP922 . ??) | 78 ;("CP922" . ??) |
79 ;(CP932 . ??) | 79 ;("CP932" . ??) |
80 ;(CP943 . ??) | 80 ;("CP943" . ??) |
81 ;(CP949 . ??) | 81 ;("CP949" . ??) |
82 ;(CP950 . ??) | 82 ;("CP950" . ??) |
83 ;(CP1046 . ??) | 83 ;("CP1046" . ??) |
84 ;(CP1124 . ??) | 84 ;("CP1124" . ??) |
85 ;(CP1129 . ??) | 85 ;("CP1129" . ??) |
86 (CP1250 . cp1250) ; requires Emacs 20 | 86 ("CP1250" . cp1250) ; requires Emacs 20 |
87 (CP1251 . cp1251) ; requires Emacs 20 | 87 ("CP1251" . cp1251) ; requires Emacs 20 |
88 (CP1252 . iso-8859-1) ; approximation | 88 ("CP1252" . iso-8859-1) ; approximation |
89 (CP1253 . cp1253) ; requires Emacs 20 | 89 ("CP1253" . cp1253) ; requires Emacs 20 |
90 (CP1254 . iso-8859-9) ; approximation | 90 ("CP1254" . iso-8859-9) ; approximation |
91 (CP1255 . iso-8859-8) ; approximation | 91 ("CP1255" . iso-8859-8) ; approximation |
92 ;(CP1256 . ??) | 92 ;("CP1256" . ??) |
93 (CP1257 . cp1257) ; requires Emacs 20 | 93 ("CP1257" . cp1257) ; requires Emacs 20 |
94 (GB2312 . cn-gb-2312) ; also named 'gb2312' in XEmacs 21 or Emacs 21 | 94 ("GB2312" . cn-gb-2312) ; also named 'gb2312' in XEmacs 21 or Emacs 21 |
95 ; also named 'euc-cn' in Emacs 20 or Emacs 21 | 95 ; also named 'euc-cn' in Emacs 20 or Emacs 21 |
96 (EUC-JP . euc-jp) | 96 ("EUC-JP" . euc-jp) |
97 (EUC-KR . euc-kr) | 97 ("EUC-KR" . euc-kr) |
98 ;(EUC-TW . ??) | 98 ;("EUC-TW" . ??) |
99 (BIG5 . big5) | 99 ("BIG5" . big5) |
100 ;(BIG5-HKSCS . ??) | 100 ;("BIG5-HKSCS" . ??) |
101 ;(GBK . ??) | 101 ;("GBK" . ??) |
102 ;(GB18030 . ??) | 102 ;("GB18030" . ??) |
103 (SHIFT_JIS . shift_jis) | 103 ("SHIFT_JIS" . shift_jis) |
104 ;(JOHAB . ??) | 104 ;("JOHAB" . ??) |
105 (TIS-620 . tis-620) ; requires Emacs 20 or Emacs 21 | 105 ("TIS-620" . tis-620) ; requires Emacs 20 or Emacs 21 |
106 (VISCII . viscii) ; requires Emacs 20 or Emacs 21 | 106 ("VISCII" . viscii) ; requires Emacs 20 or Emacs 21 |
107 (UTF-8 . utf-8) ; requires Mule-UCS in Emacs 20, or Emacs 21 | 107 ("UTF-8" . utf-8) ; requires Mule-UCS in Emacs 20, or Emacs 21 |
108 ) | 108 ) |
109 "How to convert a GNU libc/libiconv canonical charset name as seen in | 109 "How to convert a GNU libc/libiconv canonical charset name as seen in |
110 Content-Type into a Mule coding system.") | 110 Content-Type into a Mule coding system.") |
111 | 111 |
112 (defun po-find-charset (filename) | 112 (defun po-find-charset (filename) |
146 (and (eq operation 'insert-file-contents) | 146 (and (eq operation 'insert-file-contents) |
147 (file-exists-p filename) | 147 (file-exists-p filename) |
148 (with-temp-buffer | 148 (with-temp-buffer |
149 (let* ((coding-system-for-read 'no-conversion) | 149 (let* ((coding-system-for-read 'no-conversion) |
150 (charset (or (po-find-charset filename) "ascii")) | 150 (charset (or (po-find-charset filename) "ascii")) |
151 (charset-upper (intern (upcase charset))) | 151 (charset-upper (upcase charset)) |
152 (charset-lower (intern (downcase charset)))) | 152 (charset-lower (downcase charset)) |
153 (list (or (cdr (assq charset-upper po-content-type-charset-alist)) | 153 (candidate |
154 (if (memq charset-lower (coding-system-list)) | 154 (cdr (assoc charset-upper po-content-type-charset-alist))) |
155 charset-lower | 155 (try (or candidate (intern-soft charset-lower)))) |
156 'no-conversion))))))) | 156 (list (cond ((and try (coding-system-p try)) |
157 try) | |
158 ((and try | |
159 (string-match "\\`cp[1-9][0-9][0-9]?\\'" | |
160 (symbol-name try)) | |
161 (assoc (substring (symbol-name try) 2) | |
162 (cp-supported-codepages))) | |
163 (codepage-setup (substring (symbol-name try) 2)) | |
164 try) | |
165 ((and (string-match "\\`cp[1-9][0-9][0-9]?\\'" | |
166 charset-lower) | |
167 (assoc (substring charset-lower 2) | |
168 (cp-supported-codepages))) | |
169 (codepage-setup (substring charset-lower 2)) | |
170 (intern charset-lower)) | |
171 (t | |
172 'no-conversion))))))) | |
157 | 173 |
158 ;;;###autoload | 174 ;;;###autoload |
159 (defun po-find-file-coding-system (arg-list) | 175 (defun po-find-file-coding-system (arg-list) |
160 "\ | 176 "\ |
161 Return a Mule (DECODING . ENCODING) pair, according to PO file charset. | 177 Return a Mule (DECODING . ENCODING) pair, according to PO file charset. |