Mercurial > emacs
diff lisp/language/european.el @ 89483:2f877ed80fa6
*** empty log message ***
| author | Kenichi Handa <handa@m17n.org> |
|---|---|
| date | Mon, 08 Sep 2003 12:53:41 +0000 |
| parents | 375f2633d815 5f226da850bf |
| children | 3a4e30359ac0 |
line wrap: on
line diff
--- a/lisp/language/european.el Mon Sep 08 11:56:09 2003 +0000 +++ b/lisp/language/european.el Mon Sep 08 12:53:41 2003 +0000 @@ -1,8 +1,11 @@ ;;; european.el --- support for European languages -*- coding: iso-2022-7bit; -*- ;; Copyright (C) 1995, 1997, 2001 Electrotechnical Laboratory, JAPAN. -;; Licensed to the Free Software Foundation. +;; Licensed to the Free Software Foundation. ;; Copyright (C) 2001, 2002, 2003 Free Software Foundation, Inc. +;; Copyright (C) 2003 +;; National Institute of Advanced Industrial Science and Technology (AIST) +;; Registration Number H13PRO009 ;; Keywords: multilingual, European @@ -25,19 +28,19 @@ ;;; Commentary: -;; For European scripts, character sets ISO8859-1,2,3,4,9,14,15 are -;; supported. +;; For European scripts, character sets ISO8859-1,2,3,4,9,10,13,14,15, +;; windows-1250,2,4,7, mac-roman, adobe-standard-encoding, cp850 and +;; next are supported. ;;; Code: ;; Latin-1 (ISO-8859-1) (set-language-info-alist - "Latin-1" '((charset ascii latin-iso8859-1) - (coding-system iso-latin-1) + "Latin-1" '((charset iso-8859-1) + (coding-system iso-latin-1 iso-latin-9 windows-1252) (coding-priority iso-latin-1) - (nonascii-translation . latin-iso8859-1) - (unibyte-syntax . "latin-1") + (nonascii-translation . iso-8859-1) (unibyte-display . iso-latin-1) (input-method . "latin-1-prefix") (sample-text @@ -65,23 +68,21 @@ ;; Latin-2 (ISO-8859-2) -(make-coding-system - 'iso-latin-2 2 ?2 - "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)." - '(ascii latin-iso8859-2 nil nil - nil nil nil nil nil nil nil nil nil nil nil t) - '((safe-charsets ascii latin-iso8859-2) - (mime-charset . iso-8859-2))) +(define-coding-system 'iso-latin-2 + "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)." + :coding-type 'charset + :mnemonic ?2 + :charset-list '(iso-8859-2) + :mime-charset 'iso-8859-2) (define-coding-system-alias 'iso-8859-2 'iso-latin-2) (define-coding-system-alias 'latin-2 'iso-latin-2) (set-language-info-alist - "Latin-2" '((charset ascii latin-iso8859-2) - (coding-system iso-latin-2) + "Latin-2" '((charset iso-8859-2) + (coding-system iso-latin-2 windows-1250) (coding-priority iso-latin-2) - (nonascii-translation . latin-iso8859-2) - (unibyte-syntax . "latin-2") + (nonascii-translation . iso-8859-2) (unibyte-display . iso-latin-2) (input-method . "latin-2-prefix") (documentation . "\ @@ -93,6 +94,7 @@ We also have specific language environments for the following languages: For Czech, \"Czech\". For Croatian, \"Croatian\". + For Polish, \"Polish\". For Romanian, \"Romanian\". For Slovak, \"Slovak\".")) '("European")) @@ -100,23 +102,21 @@ ;; Latin-3 (ISO-8859-3) -(make-coding-system - 'iso-latin-3 2 ?3 - "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)." - '(ascii latin-iso8859-3 nil nil - nil nil nil nil nil nil nil nil nil nil nil t) - '((safe-charsets ascii latin-iso8859-3) - (mime-charset . iso-8859-3))) +(define-coding-system 'iso-latin-3 + "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)." + :coding-type 'charset + :mnemonic ?3 + :charset-list '(iso-8859-3) + :mime-charset 'iso-8859-3) (define-coding-system-alias 'iso-8859-3 'iso-latin-3) (define-coding-system-alias 'latin-3 'iso-latin-3) (set-language-info-alist - "Latin-3" '((charset ascii latin-iso8859-3) + "Latin-3" '((charset iso-8859-3) (coding-system iso-latin-3) (coding-priority iso-latin-3) - (nonascii-translation . latin-iso8859-3) - (unibyte-syntax . "latin-3") + (nonascii-translation . iso-8859-3) (unibyte-display . iso-latin-3) (input-method . "latin-3-prefix") (documentation . "\ @@ -128,23 +128,21 @@ ;; Latin-4 (ISO-8859-4) -(make-coding-system - 'iso-latin-4 2 ?4 - "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)." - '(ascii latin-iso8859-4 nil nil - nil nil nil nil nil nil nil nil nil nil nil t) - '((safe-charsets ascii latin-iso8859-4) - (mime-charset . iso-8859-4))) +(define-coding-system 'iso-latin-4 + "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)." + :coding-type 'charset + :mnemonic ?4 + :charset-list '(iso-8859-4) + :mime-charset 'iso-8859-4) (define-coding-system-alias 'iso-8859-4 'iso-latin-4) (define-coding-system-alias 'latin-4 'iso-latin-4) (set-language-info-alist - "Latin-4" '((charset ascii latin-iso8859-4) + "Latin-4" '((charset iso-8859-4) (coding-system iso-8859-4) (coding-priority iso-8859-4) - (nonascii-translation . latin-iso8859-4) - (unibyte-syntax . "latin-4") + (nonascii-translation . iso-8859-4) (unibyte-display . iso-8859-4) (input-method . "latin-4-postfix") (documentation . "\ @@ -156,49 +154,91 @@ ;; Latin-5 (ISO-8859-9) -(make-coding-system - 'iso-latin-5 2 ?9 - "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)." - '(ascii latin-iso8859-9 nil nil - nil nil nil nil nil nil nil nil nil nil nil t) - '((safe-charsets ascii latin-iso8859-9) - (mime-charset . iso-8859-9))) +(define-coding-system 'iso-latin-5 + "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)." + :coding-type 'charset + :mnemonic ?9 + :charset-list '(iso-8859-9) + :mime-charset 'iso-8859-9) (define-coding-system-alias 'iso-8859-9 'iso-latin-5) (define-coding-system-alias 'latin-5 'iso-latin-5) (set-language-info-alist - "Latin-5" '((charset ascii latin-iso8859-9) + "Latin-5" '((charset iso-8859-9) (coding-system iso-latin-5) (coding-priority iso-latin-5) - (nonascii-translation . latin-iso8859-9) - (unibyte-syntax . "latin-5") + (nonascii-translation . iso-8859-9) (unibyte-display . iso-latin-5) (input-method . "latin-5-postfix") - (documentation . "Support for Turkish language.")) + (documentation . "Support for Latin-5.\ +See also the Turkish environment.")) '("European")) +;; Latin-6 (ISO-8859-10) + +(define-coding-system 'iso-latin-6 + "ISO 2022 based 8-bit encoding for Latin-6 (MIME:ISO-8859-10)." + :coding-type 'charset + :mnemonic ?9 + :charset-list '(iso-8859-10) + :mime-charset 'iso-8859-10) + +(define-coding-system-alias 'iso-8859-10 'iso-latin-6) +(define-coding-system-alias 'latin-6 'iso-latin-6) + +(set-language-info-alist + "Latin-6" '((charset iso-8859-10) + (coding-system iso-latin-6) + (coding-priority iso-latin-6) + (nonascii-translation . iso-8859-10) + (unibyte-display . iso-latin-6) + ;; Fixme: input method. + (documentation . "Support for generic Latin-6 (Northern European).")) + '("European")) + + +;; Latin-7 (ISO-8859-13) + +(define-coding-system 'iso-latin-7 + "ISO 2022 based 8-bit encoding for Latin-7 (MIME:ISO-8859-13)." + :coding-type 'charset + :mnemonic ?9 + :charset-list '(iso-8859-13) + :mime-charset 'iso-8859-13) + +(define-coding-system-alias 'iso-8859-13 'iso-latin-7) +(define-coding-system-alias 'latin-7 'iso-latin-7) + +(set-language-info-alist + "Latin-7" '((charset iso-8859-13) + (coding-system iso-latin-7) + (coding-priority iso-latin-7) + (nonascii-translation . iso-8859-13) + (unibyte-display . iso-latin-7) + ;; Fixme: input method. + (documentation . "Support for generic Latin-7 (Baltic Rim).")) + '("European")) + ;; Latin-8 (ISO-8859-14) -(make-coding-system - 'iso-latin-8 2 ?W ; `W' for `Welsh', since `C' - ; for `Celtic' is taken. - "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)." - '(ascii latin-iso8859-14 nil nil - nil nil nil nil nil nil nil nil nil nil nil t t) - '((safe-charsets ascii latin-iso8859-14) - (mime-charset . iso-8859-14))) +(define-coding-system 'iso-latin-8 + "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)." + :coding-type 'charset + ;; `W' for `Welsh', since `C' for `Celtic' is taken. + :mnemonic ?W + :charset-list '(iso-8859-14) + :mime-charset 'iso-8859-14) (define-coding-system-alias 'iso-8859-14 'iso-latin-8) (define-coding-system-alias 'latin-8 'iso-latin-8) (set-language-info-alist - "Latin-8" '((charset ascii latin-iso8859-14) + "Latin-8" '((charset iso-8859-14) (coding-system iso-latin-8) (coding-priority iso-latin-8) - (nonascii-translation . latin-iso8859-14) - (unibyte-syntax . "latin-8") + (nonascii-translation . iso-8859-14) (unibyte-display . iso-latin-8) (input-method . "latin-8-prefix") ;; Fixme: Welsh/Ga{e}lic greetings @@ -212,24 +252,23 @@ ;; Latin-9 (ISO-8859-15) -(make-coding-system - 'iso-latin-9 2 ?0 ; `0' for `Latin-0' - "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)." - '(ascii latin-iso8859-15 nil nil - nil nil nil nil nil nil nil nil nil nil nil t t) - '((safe-charsets ascii latin-iso8859-15) - (mime-charset . iso-8859-15))) +(define-coding-system 'iso-latin-9 + "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)." + :coding-type 'charset + ;; `0' for `Latin-0' + :mnemonic ?0 + :charset-list '(iso-8859-15) + :mime-charset 'iso-8859-15) (define-coding-system-alias 'iso-8859-15 'iso-latin-9) (define-coding-system-alias 'latin-9 'iso-latin-9) (define-coding-system-alias 'latin-0 'iso-latin-9) (set-language-info-alist - "Latin-9" '((charset ascii latin-iso8859-15) + "Latin-9" '((charset iso-8859-15) (coding-system iso-latin-9) (coding-priority iso-latin-9) - (nonascii-translation . latin-iso8859-15) - (unibyte-syntax . "latin-9") + (nonascii-translation . iso-8859-15) (unibyte-display . iso-latin-9) (input-method . "latin-9-prefix") (sample-text @@ -241,13 +280,115 @@ Latin-9 is sometimes nicknamed `Latin-0'.")) '("European")) +(define-coding-system 'windows-1250 + "windows-1250 (Central European) encoding (MIME: WINDOWS-1250)" + :coding-type 'charset + :mnemonic ?* + :charset-list '(windows-1250) + :mime-charset 'windows-1250) +(define-coding-system-alias 'cp1250 'windows-1250) + +(define-coding-system 'windows-1252 + "windows-1252 (Western European) encoding (MIME: WINDOWS-1252)" + :coding-type 'charset + :mnemonic ?* + :charset-list '(windows-1252) + :mime-charset 'windows-1252) +(define-coding-system-alias 'cp1252 'windows-1252) + +(define-coding-system 'windows-1254 + "windows-1254 (Turkish) encoding (MIME: WINDOWS-1254)" + :coding-type 'charset + :mnemonic ?* + :charset-list '(windows-1254) + :mime-charset 'windows-1254) +(define-coding-system-alias 'cp1254 'windows-1254) + +(define-coding-system 'windows-1257 + "windows-1257 (Baltic) encoding (MIME: WINDOWS-1257)" + :coding-type 'charset + :mnemonic ?* + :charset-list '(windows-1257) + :mime-charset 'windows-1257) +(define-coding-system-alias 'cp1257 'windows-1257) + +(define-coding-system 'cp850 + "DOS codepage 850 (Western European)" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp850) + :mime-charset 'cp850) +(define-coding-system-alias 'ibm850 'cp850) + +(define-coding-system 'cp852 + "DOS codepage 852 (Slavic)" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp852) + :mime-charset 'cp852) +(define-coding-system-alias 'ibm852 'cp852) + +(define-coding-system 'cp857 + "DOS codepage 857 (Turkish)" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp857) + :mime-charset 'cp857) +(define-coding-system-alias 'ibm857 'cp857) + +(define-coding-system 'cp858 + "Codepage 858 (Multilingual Latin I + Euro)" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp858) + :mime-charset 'cp858) + +(define-coding-system 'cp860 + "DOS codepage 860 (Portuguese)" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp860) + :mime-charset 'cp860) +(define-coding-system-alias 'ibm860 'cp860) + +(define-coding-system 'cp861 + "DOS codepage 861 (Icelandic)" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp861) + :mime-charset 'cp861) +(define-coding-system-alias 'ibm861 'cp861) + +(define-coding-system 'cp863 + "DOS codepage 863 (French Canadian)" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp863) + :mime-charset 'cp863) +(define-coding-system-alias 'ibm863 'cp863) + +(define-coding-system 'cp865 + "DOS codepage 865 (Norwegian/Danish)" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp865) + :mime-charset 'cp865) +(define-coding-system-alias 'ibm865 'cp865) + +(define-coding-system 'cp437 + "DOS codepage 437" + :coding-type 'charset + :mnemonic ?D + :charset-list '(cp437) + :mime-charset 'cp437) +(define-coding-system-alias 'ibm437 'cp437) + (set-language-info-alist "Dutch" '((tutorial . "TUTORIAL.nl") - (charset ascii latin-iso8859-1) + (charset iso-8859-1) (coding-system iso-latin-1 iso-latin-9) (coding-priority iso-latin-1) - (nonascii-translation . latin-iso8859-1) - (unibyte-syntax . "latin-1") + (nonascii-translation . iso-8859-1) (unibyte-display . iso-latin-1) (input-method . "dutch") (sample-text . "Er is een aantal manieren waarop je dit kan doen") @@ -258,12 +399,11 @@ (set-language-info-alist "German" '((tutorial . "TUTORIAL.de") - (charset ascii latin-iso8859-1) + (charset iso-8859-1) (coding-system iso-latin-1 iso-latin-9) (coding-priority iso-latin-1) + (nonascii-translation . iso-8859-1) (input-method . "german-postfix") - (nonascii-translation . latin-iso8859-1) - (unibyte-syntax . "latin-1") (unibyte-display . iso-latin-1) (sample-text . "\ German (Deutsch Nord) Guten Tag @@ -276,11 +416,10 @@ (set-language-info-alist "French" '((tutorial . "TUTORIAL.fr") - (charset ascii latin-iso8859-1) + (charset iso-8859-1) (coding-system iso-latin-1 iso-latin-9) (coding-priority iso-latin-1) - (nonascii-translation . latin-iso8859-1) - (unibyte-syntax . "latin-1") + (nonascii-translation . iso-8859-1) (unibyte-display . iso-latin-1) (input-method . "latin-1-prefix") (sample-text . "French (Fran,Ag(Bais) Bonjour, Salut") @@ -291,11 +430,10 @@ (set-language-info-alist "Italian" '((tutorial . "TUTORIAL.it") - (charset ascii latin-iso8859-1) + (charset iso-8859-1) (coding-system iso-latin-1 iso-latin-9) (coding-priority iso-latin-1) - (nonascii-translation . latin-iso8859-1) - (unibyte-syntax . "latin-1") + (nonascii-translation . iso-8859-1) (unibyte-display . iso-latin-1) (input-method . "italian-postfix") (sample-text . "Salve, ciao!") @@ -306,12 +444,11 @@ '("European")) (set-language-info-alist - "Slovenian" '((charset . (ascii latin-iso8859-2)) - (coding-system . (iso-8859-2)) + "Slovenian" '((charset iso-8859-2) + (coding-system . (iso-8859-2 windows-1250)) (coding-priority . (iso-8859-2)) - (nonascii-translation . latin-iso8859-2) + (nonascii-translation . iso-8859-2) (input-method . "slovenian") - (unibyte-syntax . "latin-2") (unibyte-display . iso-8859-2) (tutorial . "TUTORIAL.sl") (sample-text . ",B.(Belimo vam uspe,B9(Ben dan!") @@ -322,12 +459,11 @@ (set-language-info-alist "Spanish" '((tutorial . "TUTORIAL.es") - (charset ascii latin-iso8859-1) + (charset iso-8859-1) (coding-system iso-latin-1 iso-latin-9) (coding-priority iso-latin-1) (input-method . "spanish-postfix") - (nonascii-translation . latin-iso8859-1) - (unibyte-syntax . "latin-1") + (nonascii-translation . iso-8859-1) (unibyte-display . iso-latin-1) (sample-text . "Spanish (Espa,Aq(Bol) ,A!(BHola!") (documentation . "\ @@ -342,27 +478,36 @@ ;; "Latin-3" language environment. (set-language-info-alist - "Turkish" '((charset ascii latin-iso8859-9) - (coding-system iso-latin-5 iso-latin-3) + "Turkish" '((charset iso-8859-9) + (coding-system iso-latin-5 windows-1254 iso-latin-3) (coding-priority iso-latin-5) - (nonascii-translation . latin-iso8859-9) - (unibyte-syntax . "latin-5") + (nonascii-translation . iso-8859-9) (unibyte-display . iso-latin-5) (input-method . "turkish-postfix") (sample-text . "Turkish (T,M|(Brk,Mg(Be) Merhaba") - (documentation . t))) + (setup-function + . (lambda () + (set-case-syntax-pair ?I ?,C9(B (standard-case-table)) + (set-case-syntax-pair ?,C)(B ?i (standard-case-table)))) + (exit-function + . (lambda () + (set-case-syntax-pair ?I ?i (standard-case-table)) + (set-case-syntax ?,C9(B "w" (standard-case-table)) + (set-case-syntax ?,C)(B "w" (standard-case-table)))) + (documentation . "Support for Turkish. +Differs from the Latin-5 environment in using the `turkish-postfix' input +method and applying Turkish case rules for the characters i, I, ,C9(B, ,C)(B."))) ;; Polish ISO 8859-2 environment. ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl> ;; Keywords: multilingual, Polish (set-language-info-alist - "Polish" '((charset . (ascii latin-iso8859-2)) - (coding-system . (iso-8859-2)) - (coding-priority . (iso-8859-2)) + "Polish" '((charset iso-8859-2) + (coding-system iso-8859-2 windows-1250) + (coding-priority iso-8859-2) (input-method . "polish-slash") - (nonascii-translation . latin-iso8859-2) - (unibyte-syntax . "latin-2") + (nonascii-translation . iso-8859-2) (unibyte-display . iso-8859-2) (tutorial . "TUTORIAL.pl") (sample-text . "P,Bs(Bjd,B<(B, ki,Bq(B-,B?(Be t,Bj(B chmurno,B6f(B w g,B31(Bb flaszy") @@ -372,7 +517,7 @@ (set-language-info-alist "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based (coding-priority utf-8 latin-8) - (nonascii-translation . latin-iso8859-14) + (nonascii-translation . iso-8859-14) (input-method . "welsh") (documentation . "Support for Welsh, using Unicode.")) '("European")) @@ -389,244 +534,118 @@ (set-language-info-alist "Latin-7" `((coding-system latin-7) (coding-priority latin-7) - (nonascii-translation . ,(get 'decode-iso-latin-7 - 'translation-table)) + (nonascii-translation . iso-8859-13) (input-method . "latin-prefix") - (features code-pages) (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian.")) '("European")) (set-language-info-alist - "Lithuanian" `((coding-system latin-7) + "Lithuanian" `((coding-system latin-7 windows-1257) (coding-priority latin-7) + (nonascii-translation . iso-8859-13) (input-method . "lithuanian-keyboard") - (nonascii-translation . ,(get 'decode-iso-latin-7 - 'translation-table)) - (features code-pages) (documentation . "Support for Lithuanian.")) '("European")) (set-language-info-alist - "Latvian" `((coding-system latin-7) + "Latvian" `((coding-system latin-7 windows-1257) (coding-priority latin-7) + (nonascii-translation . iso-8859-13) (input-method . "latvian-keyboard") - (nonascii-translation . ,(get 'decode-iso-latin-7 - 'translation-table)) - (features code-pages) (documentation . "Support for Latvian.")) '("European")) (set-language-info-alist "Swedish" '((tutorial . "TUTORIAL.sv") - (charset ascii latin-iso8859-1) + (charset iso-8859-1) (coding-system iso-latin-1) (coding-priority iso-latin-1) - (nonascii-translation . latin-iso8859-1) - (unibyte-syntax . "latin-1") + (nonascii-translation . iso-8859-1) (unibyte-display . iso-latin-1) (sample-text . "Goddag Hej") (documentation . "Support for Swedish")) '("European")) (set-language-info-alist - "Croatian" '((charset . (ascii latin-iso8859-2)) - (coding-system . (iso-8859-2)) - (coding-priority . (iso-8859-2)) + "Croatian" '((charset iso-8859-2) + (coding-system iso-8859-2) + (coding-priority iso-8859-2) (input-method . "croatian") - (nonascii-translation . latin-iso8859-2) - (unibyte-syntax . "latin-2") + (nonascii-translation . iso-8859-2) (unibyte-display . iso-8859-2) (documentation . "Support for Croatian with Latin-2 encoding.")) '("European")) + -;; Definitions for the Mac Roman character sets and coding system. -;; The Mac Roman encoding uses all 128 code points in the range 128 to -;; 255 for actual characters. Emacs decodes them to one of the -;; following character sets. -;; ascii, latin-iso8859-1, mule-unicode-0100-24ff, -;; mule-unicode-2500-33ff, mule-unicode-e000-ffff +(define-coding-system 'mac-roman + "Mac Roman Encoding (MIME:MACINTOSH)." + :coding-type 'charset + :mnemonic ?M + :charset-list '(mac-roman) + :mime-charset 'macintosh) + +(define-coding-system 'next + "NeXTstep encoding" + :coding-type 'charset + :mnemonic ?* + :charset-list '(next) + :mime-charset 'next) + +(define-coding-system 'hp-roman8 + "Hewlet-Packard roman-8 encoding (MIME:ROMAN-8)" + :coding-type 'charset + :mnemonic ?* + :charset-list '(hp-roman8) + :mime-charset 'hp-roman8) +(define-coding-system-alias 'roman8 'hp-roman8) + +(define-coding-system 'adobe-standard-encoding + "Adobe `standard' encoding for PostScript" + :coding-type 'charset + :mnemonic ?* + :charset-list '(adobe-standard-encoding) + :mime-charset 'adobe-standard-encoding) -(let - ((encoding-vector (make-vector 256 nil)) - (i 0) - (vec ;; mac-roman (128..255) -> UCS mapping - [ #x00C4 ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS - #x00C5 ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE - #x00C7 ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA - #x00C9 ;; 131:LATIN CAPITAL LETTER E WITH ACUTE - #x00D1 ;; 132:LATIN CAPITAL LETTER N WITH TILDE - #x00D6 ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS - #x00DC ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS - #x00E1 ;; 135:LATIN SMALL LETTER A WITH ACUTE - #x00E0 ;; 136:LATIN SMALL LETTER A WITH GRAVE - #x00E2 ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX - #x00E4 ;; 138:LATIN SMALL LETTER A WITH DIAERESIS - #x00E3 ;; 139:LATIN SMALL LETTER A WITH TILDE - #x00E5 ;; 140:LATIN SMALL LETTER A WITH RING ABOVE - #x00E7 ;; 141:LATIN SMALL LETTER C WITH CEDILLA - #x00E9 ;; 142:LATIN SMALL LETTER E WITH ACUTE - #x00E8 ;; 143:LATIN SMALL LETTER E WITH GRAVE - #x00EA ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX - #x00EB ;; 145:LATIN SMALL LETTER E WITH DIAERESIS - #x00ED ;; 146:LATIN SMALL LETTER I WITH ACUTE - #x00EC ;; 147:LATIN SMALL LETTER I WITH GRAVE - #x00EE ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX - #x00EF ;; 149:LATIN SMALL LETTER I WITH DIAERESIS - #x00F1 ;; 150:LATIN SMALL LETTER N WITH TILDE - #x00F3 ;; 151:LATIN SMALL LETTER O WITH ACUTE - #x00F2 ;; 152:LATIN SMALL LETTER O WITH GRAVE - #x00F4 ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX - #x00F6 ;; 154:LATIN SMALL LETTER O WITH DIAERESIS - #x00F5 ;; 155:LATIN SMALL LETTER O WITH TILDE - #x00FA ;; 156:LATIN SMALL LETTER U WITH ACUTE - #x00F9 ;; 157:LATIN SMALL LETTER U WITH GRAVE - #x00FB ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX - #x00FC ;; 159:LATIN SMALL LETTER U WITH DIAERESIS - #x2020 ;; 160:DAGGER - #x00B0 ;; 161:DEGREE SIGN - #x00A2 ;; 162:CENT SIGN - #x00A3 ;; 163:POUND SIGN - #x00A7 ;; 164:SECTION SIGN - #x2022 ;; 165:BULLET - #x00B6 ;; 166:PILCROW SIGN - #x00DF ;; 167:LATIN SMALL LETTER SHARP S - #x00AE ;; 168:REGISTERED SIGN - #x00A9 ;; 169:COPYRIGHT SIGN - #x2122 ;; 170:TRADE MARK SIGN - #x00B4 ;; 171:ACUTE ACCENT - #x00A8 ;; 172:DIAERESIS - #x2260 ;; 173:NOT EQUAL TO - #x00C6 ;; 174:LATIN CAPITAL LETTER AE - #x00D8 ;; 175:LATIN CAPITAL LETTER O WITH STROKE - #x221E ;; 176:INFINITY - #x00B1 ;; 177:PLUS-MINUS SIGN - #x2264 ;; 178:LESS-THAN OR EQUAL TO - #x2265 ;; 179:GREATER-THAN OR EQUAL TO - #x00A5 ;; 180:YEN SIGN - #x00B5 ;; 181:MICRO SIGN - #x2202 ;; 182:PARTIAL DIFFERENTIAL - #x2211 ;; 183:N-ARY SUMMATION - #x220F ;; 184:N-ARY PRODUCT - #x03C0 ;; 185:GREEK SMALL LETTER PI - #x222B ;; 186:INTEGRAL - #x00AA ;; 187:FEMININE ORDINAL INDICATOR - #x00BA ;; 188:MASCULINE ORDINAL INDICATOR - #x03A9 ;; 189:GREEK CAPITAL LETTER OMEGA - #x00E6 ;; 190:LATIN SMALL LETTER AE - #x00F8 ;; 191:LATIN SMALL LETTER O WITH STROKE - #x00BF ;; 192:INVERTED QUESTION MARK - #x00A1 ;; 193:INVERTED EXCLAMATION MARK - #x00AC ;; 194:NOT SIGN - #x221A ;; 195:SQUARE ROOT - #x0192 ;; 196:LATIN SMALL LETTER F WITH HOOK - #x2248 ;; 197:ALMOST EQUAL TO - #x2206 ;; 198:INCREMENT - #x00AB ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - #x00BB ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - #x2026 ;; 201:HORIZONTAL ELLIPSIS - #x00A0 ;; 202:NO-BREAK SPACE - #x00C0 ;; 203:LATIN CAPITAL LETTER A WITH GRAVE - #x00C3 ;; 204:LATIN CAPITAL LETTER A WITH TILDE - #x00D5 ;; 205:LATIN CAPITAL LETTER O WITH TILDE - #x0152 ;; 206:LATIN CAPITAL LIGATURE OE - #x0153 ;; 207:LATIN SMALL LIGATURE OE - #x2013 ;; 208:EN DASH - #x2014 ;; 209:EM DASH - #x201C ;; 210:LEFT DOUBLE QUOTATION MARK - #x201D ;; 211:RIGHT DOUBLE QUOTATION MARK - #x2018 ;; 212:LEFT SINGLE QUOTATION MARK - #x2019 ;; 213:RIGHT SINGLE QUOTATION MARK - #x00F7 ;; 214:DIVISION SIGN - #x25CA ;; 215:LOZENGE - #x00FF ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS - #x0178 ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS - #x2044 ;; 218:FRACTION SLASH - #x20AC ;; 219:EURO SIGN - #x2039 ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK - #x203A ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - #xFB01 ;; 222:LATIN SMALL LIGATURE FI - #xFB02 ;; 223:LATIN SMALL LIGATURE FL - #x2021 ;; 224:DOUBLE DAGGER - #x00B7 ;; 225:MIDDLE DOT - #x201A ;; 226:SINGLE LOW-9 QUOTATION MARK - #x201E ;; 227:DOUBLE LOW-9 QUOTATION MARK - #x2030 ;; 228:PER MILLE SIGN - #x00C2 ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX - #x00CA ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX - #x00C1 ;; 231:LATIN CAPITAL LETTER A WITH ACUTE - #x00CB ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS - #x00C8 ;; 233:LATIN CAPITAL LETTER E WITH GRAVE - #x00CD ;; 234:LATIN CAPITAL LETTER I WITH ACUTE - #x00CE ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX - #x00CF ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS - #x00CC ;; 237:LATIN CAPITAL LETTER I WITH GRAVE - #x00D3 ;; 238:LATIN CAPITAL LETTER O WITH ACUTE - #x00D4 ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX - #xF8FF ;; 240:Apple logo - #x00D2 ;; 241:LATIN CAPITAL LETTER O WITH GRAVE - #x00DA ;; 242:LATIN CAPITAL LETTER U WITH ACUTE - #x00DB ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX - #x00D9 ;; 244:LATIN CAPITAL LETTER U WITH GRAVE - #x0131 ;; 245:LATIN SMALL LETTER DOTLESS I - #x02C6 ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT - #x02DC ;; 247:SMALL TILDE - #x00AF ;; 248:MACRON - #x02D8 ;; 249:BREVE - #x02D9 ;; 250:DOT ABOVE - #x02DA ;; 251:RING ABOVE - #x00B8 ;; 252:CEDILLA - #x02DD ;; 253:DOUBLE ACUTE ACCENT - #x02DB ;; 254:OGONEK - #x02C7 ;; 255:CARON - ]) - translation-table) - (while (< i 128) - (aset encoding-vector i i) - (setq i (1+ i))) - (while (< i 256) - (aset encoding-vector i - (decode-char 'ucs (aref vec (- i 128)))) - (setq i (1+ i))) - (setq translation-table - (make-translation-table-from-vector encoding-vector)) - (define-translation-table 'mac-roman-decoder translation-table) - (define-translation-table 'mac-roman-encoder - (char-table-extra-slot translation-table 0))) - -(define-ccl-program decode-mac-roman - `(4 - ((loop - (read r1) - (if (r1 < 128) ;; ASCII - (r0 = ,(charset-id 'ascii)) - (if (r1 < 160) - (r0 = ,(charset-id 'eight-bit-control)) - (r0 = ,(charset-id 'eight-bit-graphic)))) - (translate-character mac-roman-decoder r0 r1) - (write-multibyte-character r0 r1) - (repeat)))) - "CCL program to decode Mac Roman") - -(define-ccl-program encode-mac-roman - `(1 - ((loop - (read-multibyte-character r0 r1) - (translate-character ucs-mule-to-mule-unicode r0 r1) - (translate-character mac-roman-encoder r0 r1) - (if (r0 != ,(charset-id 'ascii)) - (if (r0 != ,(charset-id 'eight-bit-graphic)) - (if (r0 != ,(charset-id 'eight-bit-control)) - (r1 = ??)))) - (write-repeat r1)))) - "CCL program to encode Mac Roman") - -(make-coding-system - 'mac-roman 4 ?M - "Mac Roman Encoding (MIME:MACINTOSH)." - '(decode-mac-roman . encode-mac-roman) - (list (cons 'safe-chars (get 'mac-roman-encoder 'translation-table)) - '(valid-codes (0 . 255)) - '(mime-charset . macintosh))) ; per IANA, rfc1345 + +;; For automatic composing of diacritics and combining marks. +(dolist (range '( ;; combining diacritical marks + (#x0300 #x0314 (tc . bc)) + (#x0315 (tr . bl)) + (#x0316 #x0319 (bc . tc)) + (#x031A (tr . cl)) + (#x031B #x0320 (bc . tc)) + (#x0321 (Br . tr)) + (#x0322 (Br . tl)) + (#x0323 #x0333 (bc . tc)) + (#x0334 #x0338 (Bc . Bc)) + (#x0339 #x033C (bc . tc)) + (#x033D #x033F (tc . bc)) + (#x0340 (tl . bc)) + (#x0341 (tr . bc)) + (#x0342 #x0344 (tc . bc)) + (#x0345 (bc . tc)) + (#x0346 (tc . bc)) + (#x0347 #x0349 (bc . tc)) + (#x034A #x034C (tc . bc)) + (#x034D #x034E (bc . tc)) + ;; combining diacritical marks for symbols + (#x20D0 #x20D1 (tc . bc)) + (#x20D2 #x20D3 (Bc . Bc)) + (#x20D4 #x20D7 (tc . bc)) + (#x20D8 #x20DA (Bc . Bc)) + (#x20DB #x20DC (tc . bc)) + (#x20DD #x20E0 (Bc . Bc)) + (#x20E1 (tc . bc)) + (#x20E2 #x20E3 (Bc . Bc)))) + (let* ((from (car range)) + (to (if (= (length range) 3) + (nth 1 range) + from)) + (composition (car (last range)))) + (while (<= from to) + (put-char-code-property from 'diacritic-composition composition) + (aset composition-function-table from 'diacritic-composition-function) + (setq from (1+ from))))) (defconst diacritic-composition-pattern "\\C^\\c^+") @@ -658,29 +677,52 @@ (diacritic-compose-region (point) (+ (point) len)) len) -(defun diacritic-composition-function (from to pattern &optional string) - "Compose diacritic text in the region FROM and TO. -The text matches the regular expression PATTERN. -Optional 4th argument STRING, if non-nil, is a string containing text +(defun diacritic-composition-function (pos &optional string) + "Compose diacritic text around POS. +Optional 2nd argument STRING, if non-nil, is a string containing text to compose. -The return value is the number of composed characters." - (when (< (1+ from) to) - (if string - (compose-string string from to) - (compose-region from to)) - (- to from))) - -;; Register a function to compose Unicode diacrtics and marks. -(let ((patterns '(("\\C^\\c^+" . diacritic-composition-function)))) - (let ((c #x300)) - (while (<= c #x362) - (aset composition-function-table (decode-char 'ucs c) patterns) - (setq c (1+ c))) - (setq c #x20d0) - (while (<= c #x20e3) - (aset composition-function-table (decode-char 'ucs c) patterns) - (setq c (1+ c))))) +The return value is the end position of composed characters, +or nil if no characters are composed." + (setq pos (1- pos)) + (if string + (let ((ch (aref string pos)) + start end components ch composition) + (when (and (>= pos 0) + ;; Previous character is latin. + (aref (char-category-set ch) ?l) + (/= ch 32)) + (setq start pos + end (length string) + components (list ch) + pos (1+ pos)) + (while (and + (< pos end) + (setq ch (aref string pos) + composition + (get-char-code-property ch 'diacritic-composition))) + (setq components (cons ch (cons composition components)) + pos (1+ pos))) + (compose-string string start pos (nreverse components)) + pos)) + (let ((ch (char-after pos)) + start end components composition) + (when (and (>= pos (point-min)) + (aref (char-category-set ch) ?l) + (/= ch 32)) + (setq start pos + end (point-max) + components (list ch) + pos (1+ pos)) + (while (and + (< pos end) + (setq ch (char-after pos) + composition + (get-char-code-property ch 'diacritic-composition))) + (setq components (cons ch (cons composition components)) + pos (1+ pos))) + (compose-region start pos (nreverse components)) + pos)))) (provide 'european)