(set-language-info-alist
"Latin-1" '((charset ascii latin-iso8859-1)
(coding-system iso-latin-1)
(coding-priority iso-latin-1 windows-1252)
(nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(unibyte-display . iso-latin-1)
(input-method . "latin-1-prefix")
(sample-text
. "Hello, Hej, Tere, Hei, Bonjour, Gr,A|_(B Gott, Ciao, ,A!(BHola!")
(documentation . "\
This language environment is a generic one for the Latin-1 (ISO-8859-1)
character set which supports the following European languages:
Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
Scottish Gaelic, Spanish, and Swedish.
We also have specific language environments for the following languages:
For Dutch, \"Dutch\".
For German, \"German\".
For French, \"French\".
For Italian, \"Italian\".
For Slovenian, \"Slovenian\".
For Spanish, \"Spanish\".
Latin-1 also covers several written languages outside Europe, including
Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
'("European"))
(eval-and-compile
(setq
non-iso-charset-alist
(cp-make-coding-system
windows-1252
[?\$,1tL(B nil ?\$,1rz(B ?\$,1!R(B ?\$,1r~(B ?\$,1s&(B ?\$,1s (B ?\$,1s!(B ?\$,1$f(B ?\$,1s0(B ?\$,1! (B ?\$,1s9(B ?\$,1 r(B nil ?\$,1!=(B nil nil
?\$,1rx(B ?\$,1ry(B ?\$,1r|(B ?\$,1r}(B ?\$,1s"(B ?\$,1rs(B ?\$,1rt(B ?\$,1$|(B ?\$,1ub(B ?\$,1!!(B ?\$,1s:(B ?\$,1 s(B nil ?\$,1!>(B ?\$,1!8(B ?\,A (B ?\,A!(B
?\,A"(B ?\,A#(B ?\,A$(B ?\,A%(B ?\,A&(B ?\,A'(B ?\,A((B ?\,A)(B ?\,A*(B ?\,A+(B ?\,A,(B ?\,A-(B ?\,A.(B ?\,A/(B ?\,A0(B ?\,A1(B ?\,A2(B
?\,A3(B ?\,A4(B ?\,A5(B ?\,A6(B ?\,A7(B ?\,A8(B ?\,A9(B ?\,A:(B ?\,A ?\,AD(B ?\,AE(B ?\,AF(B ?\,AG(B ?\,AH(B ?\,AI(B ?\,AJ(B ?\,AK(B ?\,AL(B ?\,AM(B ?\,AN(B ?\,AO(B ?\,AP(B ?\,AQ(B ?\,AR(B ?\,AS(B ?\,AT(B
?\,AU(B ?\,AV(B ?\,AW(B ?\,AX(B ?\,AY(B ?\,AZ(B ?\,A[(B ?\,A\(B ?\,A](B ?\,A^(B ?\,A_(B ?\,A`(B ?\,Aa(B ?\,Ab(B ?\,Ac(B ?\,Ad(B ?\,Ae(B
?\,Af(B ?\,Ag(B ?\,Ah(B ?\,Ai(B ?\,Aj(B ?\,Ak(B ?\,Al(B ?\,Am(B ?\,An(B ?\,Ao(B ?\,Ap(B ?\,Aq(B ?\,Ar(B ?\,As(B ?\,At(B ?\,Au(B ?\,Av(B
?\,Aw(B ?\,Ax(B ?\,Ay(B ?\,Az(B ?\,A{(B ?\,A|(B ?\,A}(B ?\,A~(B ?\,A(B])))
(define-coding-system-alias 'cp1252 'windows-1252)
(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-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)
(coding-priority iso-latin-2)
(nonascii-translation . latin-iso8859-2)
(unibyte-syntax . "latin-2")
(unibyte-display . iso-latin-2)
(input-method . "latin-2-prefix")
(documentation . "\
This language environment is a generic one for the Latin-2 (ISO-8859-2)
character set which supports the following languages:
Albanian, Czech, English, German, Hungarian, Polish, Romanian,
Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
and Swedish.
We also have specific language environments for the following languages:
For Czech, \"Czech\".
For Croatian, \"Croatian\".
For Romanian, \"Romanian\".
For Slovak, \"Slovak\"."))
'("European"))
(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-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)
(coding-system iso-latin-3)
(coding-priority iso-latin-3)
(nonascii-translation . latin-iso8859-3)
(unibyte-syntax . "latin-3")
(unibyte-display . iso-latin-3)
(input-method . "latin-3-prefix")
(documentation . "\
These languages are supported with the Latin-3 (ISO-8859-3) character set:
Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
German, Italian, Maltese, Spanish, and Turkish."))
'("European"))
(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-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)
(coding-system iso-8859-4)
(coding-priority iso-8859-4)
(nonascii-translation . latin-iso8859-4)
(unibyte-syntax . "latin-4")
(unibyte-display . iso-8859-4)
(input-method . "latin-4-postfix")
(documentation . "\
These languages are supported with the Latin-4 (ISO-8859-4) character set:
Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
Latvian, Lithuanian, and Norwegian."))
'("European"))
(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-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)
(coding-system iso-latin-5)
(coding-priority iso-latin-5)
(nonascii-translation . latin-iso8859-9)
(unibyte-syntax . "latin-5")
(unibyte-display . iso-latin-5)
(input-method . "latin-5-postfix")
(documentation . "Support for Turkish language."))
'("European"))
(make-coding-system
'iso-latin-8 2 ?W "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-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)
(coding-system iso-latin-8)
(coding-priority iso-latin-8)
(nonascii-translation . latin-iso8859-14)
(unibyte-syntax . "latin-8")
(unibyte-display . iso-latin-8)
(input-method . "latin-8-prefix")
(sample-text . ",_"(B ,_p(B ,_^(B")
(documentation . "\
This language environment is a generic one for the Latin-8 (ISO-8859-14)
character set which supports the Celtic languages, including those not
covered by other ISO-8859 character sets:
Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
'("European"))
;; 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-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)
(coding-system iso-latin-9)
(coding-priority iso-latin-9)
(nonascii-translation . latin-iso8859-15)
(unibyte-syntax . "latin-9")
(unibyte-display . iso-latin-9)
(input-method . "latin-9-prefix")
(sample-text
. "AVE. ,b&(48<=>(B ,b$(B")
(documentation . "\
This language environment is a generic one for the Latin-9 (ISO-8859-15)
character set which supports the same languages as Latin-1 with the
addition of the Euro sign and some additional French and Finnish letters.
Latin-9 is sometimes nicknamed `Latin-0'."))
'("European"))
(set-language-info-alist
"Dutch" '((tutorial . "TUTORIAL.nl")
(charset ascii latin-iso8859-1)
(coding-system iso-latin-1 iso-latin-9)
(coding-priority iso-latin-1)
(nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(unibyte-display . iso-latin-1)
(input-method . "dutch")
(sample-text . "Er is een aantal manieren waarop je dit kan doen")
(documentation . "\
This language environment is almost the same as Latin-1,
but it selects the Dutch tutorial and input method."))
'("European"))
(set-language-info-alist
"German" '((tutorial . "TUTORIAL.de")
(charset ascii latin-iso8859-1)
(coding-system iso-latin-1 iso-latin-9)
(coding-priority iso-latin-1 windows-1252)
(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
German (Deutsch S,A|(Bd) Gr,A|_(B Gott")
(documentation . "\
This language environment is almost the same as Latin-1,
but sets the default input method to \"german-postfix\".
Additionally, it selects the German tutorial."))
'("European"))
(set-language-info-alist
"French" '((tutorial . "TUTORIAL.fr")
(charset ascii latin-iso8859-1)
(coding-system iso-latin-1 iso-latin-9)
(coding-priority iso-latin-1)
(nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(unibyte-display . iso-latin-1)
(input-method . "latin-1-prefix")
(sample-text . "French (Fran,Ag(Bais) Bonjour, Salut")
(documentation . "\
This language environment is almost the same as Latin-1,
but it selects the French tutorial and input method."))
'("European"))
(set-language-info-alist
"Italian" '((tutorial . "TUTORIAL.it")
(charset ascii latin-iso8859-1)
(coding-system iso-latin-1 iso-latin-9)
(coding-priority iso-latin-1)
(nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(unibyte-display . iso-latin-1)
(input-method . "italian-postfix")
(sample-text . "Salve, ciao!")
(documentation . "\
This language environment is almost the same as Latin-1,
but sets the default input method to \"italian-postfix\".
Additionally, it selects the Italian tutorial."))
'("European"))
(set-language-info-alist
"Slovenian" '((charset . (ascii latin-iso8859-2))
(coding-system . (iso-8859-2))
(coding-priority . (iso-8859-2))
(nonascii-translation . latin-iso8859-2)
(input-method . "slovenian")
(unibyte-syntax . "latin-2")
(unibyte-display . iso-8859-2)
(tutorial . "TUTORIAL.sl")
(sample-text . ",B.(Belimo vam uspe,B9(Ben dan!")
(documentation . "\
This language environment is almost the same as Latin-2,
but it selects the Slovenian tutorial and input method."))
'("European"))
(set-language-info-alist
"Spanish" '((tutorial . "TUTORIAL.es")
(charset ascii latin-iso8859-1)
(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")
(unibyte-display . iso-latin-1)
(sample-text . "Spanish (Espa,Aq(Bol) ,A!(BHola!")
(documentation . "\
This language environment is almost the same as Latin-1,
but it sets the default input method to \"spanish-postfix\",
and it selects the Spanish tutorial."))
'("European"))
(set-language-info-alist
"Turkish" '((charset ascii latin-iso8859-9)
(coding-system iso-latin-5 iso-latin-3)
(coding-priority iso-latin-5)
(nonascii-translation . latin-iso8859-9)
(unibyte-syntax . "latin-5")
(unibyte-display . iso-latin-5)
(input-method . "turkish-postfix")
(sample-text . "Turkish (T,M|(Brk,Mg(Be) Merhaba")
(documentation . t)
(setup-function . turkish-case-conversion-enable)
(exit-function . turkish-case-conversion-disable)))
(defun turkish-case-conversion-enable ()
"Set up Turkish case conversion of `i' and `I' into `$,1 P(B' and `$,1 Q(B'."
(let ((table (standard-case-table)))
(set-case-syntax-pair ?$,1 P(B ?i table)
(set-case-syntax-pair ?I ?$,1 Q(B table)))
(defun turkish-case-conversion-disable ()
"Set up normal (non-Turkish) case conversion of `i' into `I'."
(let ((table (standard-case-table)))
(set-case-syntax-pair ?I ?i table)
(set-case-syntax ?$,1 P(B "w" table)
(set-case-syntax ?$,1 Q(B "w" table)))
(set-language-info-alist
"Polish" '((charset . (ascii latin-iso8859-2))
(coding-system . (iso-8859-2))
(coding-priority . (iso-8859-2))
(input-method . "polish-slash")
(nonascii-translation . latin-iso8859-2)
(unibyte-syntax . "latin-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")
(documentation . t))
'("European"))
(set-language-info-alist
"Welsh" `((coding-system utf-8 latin-8) (coding-priority utf-8 latin-8)
(nonascii-translation . latin-iso8859-14)
(input-method . "welsh")
(documentation . "Support for Welsh, using Unicode."))
'("European"))
(set-language-info-alist
"Latin-6" `((coding-system latin-6)
(coding-priority latin-6)
(nonascii-translation . ,(get 'decode-iso-latin-6 'translation-table))
(input-method . "latin-prefix")
(features code-pages)
(documentation . "Support for Latin-6."))
'("European"))
(set-language-info-alist
"Latin-7" `((coding-system latin-7)
(coding-priority latin-7)
(nonascii-translation . ,(get 'decode-iso-latin-7
'translation-table))
(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)
(coding-priority latin-7)
(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)
(coding-priority latin-7)
(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)
(coding-system iso-latin-1)
(coding-priority iso-latin-1)
(nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-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))
(input-method . "croatian")
(nonascii-translation . latin-iso8859-2)
(unibyte-syntax . "latin-2")
(unibyte-display . iso-8859-2)
(documentation . "Support for Croatian with Latin-2 encoding."))
'("European"))
(set-language-info-alist
"Brazilian Portuguese" '((tutorial . "TUTORIAL.pt_BR")
(charset ascii latin-iso8859-1)
(coding-system iso-latin-1 iso-latin-9)
(coding-priority iso-latin-1)
(nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(unibyte-display . iso-latin-1)
(input-method . "latin-1-prefix")
(sample-text . "Oi")
(documentation . "Support for Brazilian Portuguese."))
'("European"))
(set-language-info-alist
"Esperanto" '((tutorial . "TUTORIAL.eo")
(charset ascii latin-iso8859-3)
(coding-system iso-latin-3)
(coding-priority iso-latin-3)
(nonascii-translation . latin-iso8859-3)
(unibyte-syntax . "latin-3")
(unibyte-display . iso-latin-3)
(input-method . "latin-3-prefix")
(documentation . "Support for Esperanto with ISO-8859-3 character set."))
'("European"))
(let
((encoding-vector (make-vector 256 nil))
(i 0)
(vec [ #x00C4 #x00C5 #x00C7 #x00C9 #x00D1 #x00D6 #x00DC #x00E1 #x00E0 #x00E2 #x00E4 #x00E3 #x00E5 #x00E7 #x00E9 #x00E8 #x00EA #x00EB #x00ED #x00EC #x00EE #x00EF #x00F1 #x00F3 #x00F2 #x00F4 #x00F6 #x00F5 #x00FA #x00F9 #x00FB #x00FC #x2020 #x00B0 #x00A2 #x00A3 #x00A7 #x2022 #x00B6 #x00DF #x00AE #x00A9 #x2122 #x00B4 #x00A8 #x2260 #x00C6 #x00D8 #x221E #x00B1 #x2264 #x2265 #x00A5 #x00B5 #x2202 #x2211 #x220F #x03C0 #x222B #x00AA #x00BA #x03A9 #x00E6 #x00F8 #x00BF #x00A1 #x00AC #x221A #x0192 #x2248 #x2206 #x00AB #x00BB #x2026 #x00A0 #x00C0 #x00C3 #x00D5 #x0152 #x0153 #x2013 #x2014 #x201C #x201D #x2018 #x2019 #x00F7 #x25CA #x00FF #x0178 #x2044 #x20AC #x2039 #x203A #xFB01 #xFB02 #x2021 #x00B7 #x201A #x201E #x2030 #x00C2 #x00CA #x00C1 #x00CB #x00C8 #x00CD #x00CE #x00CF #x00CC #x00D3 #x00D4 #xF8FF #x00D2 #x00DA #x00DB #x00D9 #x0131 #x02C6 #x02DC #x00AF #x02D8 #x02D9 #x02DA #x00B8 #x02DD #x02DB #x02C7 ])
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) (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)))
(defconst diacritic-composition-pattern "\\C^\\c^+")
(defun diacritic-compose-region (beg end)
"Compose diacritic characters in the region.
When called from a program, expects two arguments,
positions (integers or markers) specifying the region."
(interactive "r")
(save-restriction
(narrow-to-region beg end)
(goto-char (point-min))
(while (re-search-forward diacritic-composition-pattern nil t)
(compose-region (match-beginning 0) (match-end 0)))))
(defun diacritic-compose-string (string)
"Compose diacritic characters in STRING and return the resulting string."
(let ((idx 0))
(while (setq idx (string-match diacritic-composition-pattern string idx))
(compose-string string idx (match-end 0))
(setq idx (match-end 0))))
string)
(defun diacritic-compose-buffer ()
"Compose diacritic characters in the current buffer."
(interactive)
(diacritic-compose-region (point-min) (point-max)))
(defun diacritic-post-read-conversion (len)
(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
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)))
(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)))))
(provide 'european)