Mercurial > emacs
comparison lisp/international/mule-conf.el @ 88575:8a28722c246c
(iso-8859-10, symbol)
(adobe-standard-encoding, ibm850): New charsets.
(iso-8859-13): Fix IR number, final char.
(file-coding-system-alist): Add .xml.
author | Dave Love <fx@gnu.org> |
---|---|
date | Mon, 20 May 2002 15:15:05 +0000 |
parents | f8b004416777 |
children | 2516c98d56d2 |
comparison
equal
deleted
inserted
replaced
88574:8cbbc8918e1f | 88575:8a28722c246c |
---|---|
26 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330, | 26 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330, |
27 ;; Boston, MA 02111-1307, USA. | 27 ;; Boston, MA 02111-1307, USA. |
28 | 28 |
29 ;;; Commentary: | 29 ;;; Commentary: |
30 | 30 |
31 ;; Don't byte-compile this file. | 31 ;; This file defines the Emacs charsets and some basic coding systems. |
32 ;; Other coding systems are defined in the files in directory | |
33 ;; lisp/language. | |
32 | 34 |
33 ;;; Code: | 35 ;;; Code: |
36 | |
37 ;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/. | |
38 ;; Standards docs equivalent to iso-2022 and iso-8859 are at | |
39 ;; http://www.ecma.ch/. | |
34 | 40 |
35 ;;; Definitions of character sets. | 41 ;;; Definitions of character sets. |
36 | 42 |
37 ;; The charsets `ascii' and `unicode' are already defined in charset.c | 43 ;; The charsets `ascii' and `unicode' are already defined in charset.c |
38 ;; as below: | 44 ;; as below: |
152 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8") | 158 "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8") |
153 | 159 |
154 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9 | 160 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9 |
155 "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9") | 161 "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9") |
156 | 162 |
157 ;; Fixme: final char | 163 (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10 |
164 "ISO/IEC 8859/9" "Latin-6" 157 ?V nil "8859-10") | |
165 | |
166 ;; 8859-11, 12 don't (yet?) exist. | |
167 | |
158 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13 | 168 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13 |
159 "ISO/IEC 8859/13" "Latin-7" nil nil nil "8859-13") | 169 "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13") |
160 | 170 |
161 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14 | 171 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14 |
162 "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14") | 172 "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14") |
163 | 173 |
164 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15 | 174 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15 |
736 :short-name "EBCDIC-UK" | 746 :short-name "EBCDIC-UK" |
737 :long-name "EBCDIC-UK" | 747 :long-name "EBCDIC-UK" |
738 :code-space [0 255] | 748 :code-space [0 255] |
739 :mime-charset 'ebcdic-uk | 749 :mime-charset 'ebcdic-uk |
740 :map "ebcdic-uk") | 750 :map "ebcdic-uk") |
751 | |
752 (define-charset 'hp-roman8 | |
753 "Encoding used by Hewlet-Packard printer software" | |
754 :short-name "HP-ROMAN8" | |
755 :long-name "HP-ROMAN8" | |
756 :ascii-compatible-p t | |
757 :code-space [0 255] | |
758 :map "hp-roman8") | |
759 | |
760 (define-charset 'adobe-standard-encoding | |
761 "Adobe `standard encoding' used in PostScript" | |
762 :short-name "ADOBE-STANDARD-ENCODING" | |
763 :long-name "ADOBE-STANDARD-ENCODING" | |
764 :code-space [0 255] | |
765 :map "stdenc") | |
766 | |
767 (define-charset 'symbol | |
768 "Adobe symbol encoding used in PostScript" | |
769 :short-name "ADOBE-SYMBOL" | |
770 :long-name "ADOBE-SYMBOL" | |
771 :code-space [0 255] | |
772 :map "symbol") | |
773 | |
774 (define-charset 'ibm850 | |
775 "DOS codepage 850" | |
776 :short-name "IBM850" | |
777 :long-name "IBM850" | |
778 :code-space [0 255] | |
779 :map "ibm850") | |
780 (define-charset-alias 'cp850 'ibm850) | |
741 | 781 |
742 (unify-charset 'chinese-gb2312) | 782 (unify-charset 'chinese-gb2312) |
743 (unify-charset 'chinese-gbk) | 783 (unify-charset 'chinese-gbk) |
744 (unify-charset 'chinese-cns11643-1) | 784 (unify-charset 'chinese-cns11643-1) |
745 (unify-charset 'chinese-cns11643-2) | 785 (unify-charset 'chinese-cns11643-2) |
991 ;; Tar files are not decoded at all, but we treat them as raw bytes. | 1031 ;; Tar files are not decoded at all, but we treat them as raw bytes. |
992 | 1032 |
993 (setq file-coding-system-alist | 1033 (setq file-coding-system-alist |
994 '(("\\.elc\\'" . (emacs-mule . emacs-mule)) | 1034 '(("\\.elc\\'" . (emacs-mule . emacs-mule)) |
995 ("\\.utf\\(-8\\)?\\'" . utf-8) | 1035 ("\\.utf\\(-8\\)?\\'" . utf-8) |
1036 ;; This is the defined default for XML documents. It may be | |
1037 ;; overridden by a charset specification in the header. That | |
1038 ;; should be grokked by the auto-coding mechanism, but rms | |
1039 ;; vetoed that. -- fx | |
1040 ("\\.xml\\'" . utf-8) | |
996 ;; We use raw-text for reading loaddefs.el so that if it | 1041 ;; We use raw-text for reading loaddefs.el so that if it |
997 ;; happens to have DOS or Mac EOLs, they are converted to | 1042 ;; happens to have DOS or Mac EOLs, they are converted to |
998 ;; newlines. This is required to make the special treatment | 1043 ;; newlines. This is required to make the special treatment |
999 ;; of the "\ newline" combination in loaddefs.el, which marks | 1044 ;; of the "\ newline" combination in loaddefs.el, which marks |
1000 ;; the beginning of a doc string, work. | 1045 ;; the beginning of a doc string, work. |
1024 (cons (decode-char 'ucs 128) (max-char)) | 1069 (cons (decode-char 'ucs 128) (max-char)) |
1025 'self-insert-command) | 1070 'self-insert-command) |
1026 | 1071 |
1027 (aset latin-extra-code-table ?\222 t) | 1072 (aset latin-extra-code-table ?\222 t) |
1028 | 1073 |
1074 ;; Local variables: | |
1075 ;; no-byte-compile: t | |
1076 ;; End: | |
1077 | |
1029 ;;; mule-conf.el ends here | 1078 ;;; mule-conf.el ends here |