Mercurial > hg > xemacs-beta

changeset 2765:4ee3cf8de81d

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
[xemacs-hg @ 2005-05-10 17:02:52 by aidan] Add full syntax info for 8859-14, -15, -16
author aidan
date Tue, 10 May 2005 17:03:00 +0000
parents 5ea65b8a540f
children 4b800e9aaadd
files lisp/ChangeLog lisp/mule/european.el lisp/mule/latin.el
diffstat 3 files changed, 208 insertions(+), 22 deletions(-) [+]
line wrap: on
line diff
--- a/lisp/ChangeLog	Mon May 09 21:51:20 2005 +0000
+++ b/lisp/ChangeLog	Tue May 10 17:03:00 2005 +0000
@@ -1,3 +1,10 @@
+2005-05-10  Aidan Kehoe  <kehoea@parhasard.net>
+
+	* mule/european.el:
+	* mule/latin.el:
+	Add full syntax table and case mapping information for
+	iso-8859-14, iso-8859-15, iso-8859-16. 
+	
 2005-05-05  Aidan Kehoe  <kehoea@parhasard.net>
 
 	* mule/mule-ccl.el (define-ccl-program): Spelling and grammar fix
--- a/lisp/mule/european.el	Mon May 09 21:51:20 2005 +0000
+++ b/lisp/mule/european.el	Tue May 10 17:03:00 2005 +0000
@@ -145,34 +145,79 @@
 		long-name "RHP of Latin-10 (ISO 8859-16)"
 		))
 
-(loop for c from 64 to 127
+;; Latin-1 is dealt with in iso8859-1.el, which see. 
+
+;; ISO 8859-14. 
+;; 
+;; Initialise all characters to word syntax.
+(loop for c from #xa0 to #xff
+  do (modify-syntax-entry (make-char 'latin-iso8859-14 c) "w"))
+
+;; Now, the exceptions. There's just punctuation in this character set. 
+(dolist (code '(#xa0	;; NO BREAK SPACE
+		#xa3	;; POUND SIGN
+		#xa7	;; SECTION SIGN
+		#xa9	;; COPYRIGHT
+		#xad	;; SOFT HYPHEN
+		#xae	;; REGISTERED
+		#xb6))	;; PILCROW SIGN
+  (modify-syntax-entry (make-char 'latin-iso8859-14 code) "_"))
+;; end of ISO 8859-14.
+
+;; ISO 8859-16.
+;;
+;; Initialise all of iso-8859-16 to word syntax. 
+(loop for c from #xa0 to #xff
   do (modify-syntax-entry (make-char 'latin-iso8859-16 c) "w"))
-(mapc (lambda (c)
-	(modify-syntax-entry (make-char 'latin-iso8859-16 c) "w"))
-      '(#xA1 #xA2 #xA3 #xA6 #xA8 #xAA #xAC #xAE #xAF
-	#xB3 #xB4 #xB5 #xB8 #xB9 #xBA #xBC #xBD #xBE #xBF))
-
 
-;; For syntax of Latin-1 characters.
-(loop for c from 64 to 127              ; from ',A@(B' to ',A(B'
-      do (modify-syntax-entry (make-char 'latin-iso8859-1 c) "w"))
+;; And then do the exceptions. First, the punctuation (following the model
+;; of Latin-1):
+(dolist (code '(#xa0	;; NO BREAK SPACE
+		#xa4	;; EURO SIGN
+		#xa7	;; SECTION SIGN
+		#xa9	;; COPYRIGHT
+		#xad	;; SOFT HYPHEN
+		#xb0	;; DEGREE
+		#xb1	;; PLUS-MINUS SIGN
+		#xb6	;; PILCROW SIGN
+		#xb7)) ;; MIDDLE DOT 
+  (modify-syntax-entry (make-char 'latin-iso8859-16 code) "_"))
+
+;; Mark the DOUBLE LOW-9 QUOTATION MARK and its closing character as
+;; quotation marks.
+(modify-syntax-entry (make-char 'latin-iso8859-16 #xa5) "\"")
+(modify-syntax-entry (make-char 'latin-iso8859-16 #xb5) "\"")
 
-(modify-syntax-entry (make-char 'latin-iso8859-1 32) "w") ; no-break space
-(modify-syntax-entry ?,AW(B "_")
-(modify-syntax-entry ?,Aw(B "_")
+;; For some crazy reason--well, in truth, probably because Jamie never used
+;; them in anger--the guillemets have open- and close-parenthesis syntax in
+;; Latin 1. We will probably change that in the future; for the moment, I'm
+;; preserving it.
+(modify-syntax-entry (make-char 'latin-iso8859-16 #xab) 
+		     (format "(%c" (make-char 'latin-iso8859-16 #xbb)))
+(modify-syntax-entry (make-char 'latin-iso8859-16 #xbb) 
+		     (format ")%c" (make-char 'latin-iso8859-16 #xab)))
+
+;; end of ISO 8859-16. 
 
-;; For syntax of Latin-9 characters.
-;; Based on Latin-1 and differences from Jukka Korpela
-;; http://www.cs.tut.fi/~jkorpela/latin9.html
+;; ISO 8859-15. 
+;; 
+;; Based on Latin-1 and differences therefrom.
+;; 
+;; First, initialise the syntax from the corresponding Latin-1 characters. 
+(loop for c from #xa0 to #xff
+      do (modify-syntax-entry 
+	  (make-char 'latin-iso8859-15 c)
+	  (string (char-syntax (make-char 'latin-iso8859-1 c)))))
+;; Now, the exceptions
 (loop for c in '(?,b&(B ?,b((B ?,b4(B ?,b8(B ?,b<(B ?,b=(B ?,b>(B)
       do (modify-syntax-entry c "w"))
 
-(loop for c from 64 to 127              ; from ',b@(B' to ',b(B'
-      do (modify-syntax-entry (make-char 'latin-iso8859-1 c) "w"))
-
-(modify-syntax-entry (make-char 'latin-iso8859-15 32) "w") ; no-break space
-(modify-syntax-entry ?,bW(B "_")
-(modify-syntax-entry ?,bw(B "_")
+;; Again, perpetuating insanity with the guillemets.
+(modify-syntax-entry (make-char 'latin-iso8859-16 #xab) 
+		     (format "(%c" (make-char 'latin-iso8859-16 #xbb)))
+(modify-syntax-entry (make-char 'latin-iso8859-16 #xbb) 
+		     (format ")%c" (make-char 'latin-iso8859-16 #xab)))
+;; end of ISO 8859-15. 
 
 ;; For syntax of Latin-2
 (loop for c in '(?,B!(B ?,B#(B ?,B%(B ?,B&(B ?,B)(B ?,B*(B ?,B+(B ?,B,(B ?,B.(B ?,B/(B ?,B1(B ?,B3(B ?,B5(B ?,B6(B ?,B9(B ?,B:(B ?,B;(B ?,B<(B)
--- a/lisp/mule/latin.el	Mon May 09 21:51:20 2005 +0000
+++ b/lisp/mule/latin.el	Tue May 10 17:03:00 2005 +0000
@@ -1,6 +1,6 @@
 ;;; latin.el --- Support for Latin charsets. -*- coding: iso-2022-7bit; -*-
 
-;; Copyright (C) 2001 Free Software Foundation, Inc.
+;; Copyright (C) 2001, 2005 Free Software Foundation, Inc.
 
 ;; Author: Hrvoje Niksic <hniksic@xemacs.org>
 ;; Maintainer: XEmacs Development Team
@@ -242,6 +242,140 @@
 ;   (220 252)				;latin letter u with diaeresis
 ;   (222 254)				;latin letter s with cedilla
 ;   ))
+
+;; Latin 9. 
+(setup-case-pairs
+ 'latin-iso8859-15
+ '((166 168)				;latin letter s with caron *
+   (180 184)				;latin letter z with caron *
+   (188 189)				;latin ligature oe *
+   (190 255)				;latin letter y with diaeresis *
+   (192 224)				;latin letter a with grave
+   (193 225)				;latin letter a with acute
+   (194 226)				;latin letter a with circumflex
+   (195 227)				;latin letter a with tilde
+   (196 228)				;latin letter a with diaeresis
+   (197 229)				;latin letter a with ring above
+   (198 230)				;latin letter ae
+   (199 231)				;latin letter c with cedilla
+   (200 232)				;latin letter e with grave
+   (201 233)				;latin letter e with acute
+   (202 234)				;latin letter e with circumflex
+   (203 235)				;latin letter e with diaeresis
+   (204 236)				;latin letter i with grave
+   (205 237)				;latin letter i with acute
+   (206 238)				;latin letter i with circumflex
+   (207 239)				;latin letter i with diaeresis
+   (208 240)				;latin letter eth
+   (209 241)				;latin letter n with tilde
+   (210 242)				;latin letter o with grave
+   (211 243)				;latin letter o with acute
+   (212 244)				;latin letter o with circumflex
+   (213 245)				;latin letter o with tilde
+   (214 246)				;latin letter o with diaeresis
+   (216 248)				;latin letter o with stroke
+   (217 249)				;latin letter u with grave
+   (218 250)				;latin letter u with acute
+   (219 251)				;latin letter u with circumflex
+   (220 252)				;latin letter u with diaeresis
+   (221 253)				;latin letter y with acute
+   (222 254)				;latin letter thorn
+   ))
+
+;; ISO 8859-14, not in FSF, our mapping.
+(setup-case-pairs
+ 'latin-iso8859-14
+ '((161 162)				;latin letter b with dot above
+   (164 165)				;latin letter c with dot above
+   (166 171)				;latin letter d with dot above
+   (168 184)				;latin letter w with grave
+   (170 186)				;latin letter w with acute
+   (172 188)				;latin letter y with grave
+   (175 255)				;latin letter y with diaeresis
+   (176 177)				;latin letter f with dot above
+   (178 179)				;latin letter g with dot above
+   (180 181)				;latin letter m with dot above
+   (183 185)				;latin letter p with dot above
+   (187 191)				;latin letter s with dot above
+   (189 190)				;latin letter w with diaeresis
+   (192 224)				;latin letter a with grave
+   (193 225)				;latin letter a with acute
+   (194 226)				;latin letter a with circumflex
+   (195 227)				;latin letter a with tilde
+   (196 228)				;latin letter a with diaeresis
+   (197 229)				;latin letter a with ring above
+   (198 230)				;latin letter ae
+   (199 231)				;latin letter c with cedilla
+   (200 232)				;latin letter e with grave
+   (201 233)				;latin letter e with acute
+   (202 234)				;latin letter e with circumflex
+   (203 235)				;latin letter e with diaeresis
+   (204 236)				;latin letter i with grave
+   (205 237)				;latin letter i with acute
+   (206 238)				;latin letter i with circumflex
+   (207 239)				;latin letter i with diaeresis
+   (208 240)				;latin letter w with circumflex
+   (209 241)				;latin letter n with tilde
+   (210 242)				;latin letter o with grave
+   (211 243)				;latin letter o with acute
+   (212 244)				;latin letter o with circumflex
+   (213 245)				;latin letter o with tilde
+   (214 246)				;latin letter o with diaeresis
+   (215 247)				;latin letter t with dot above
+   (216 248)				;latin letter o with stroke
+   (217 249)				;latin letter u with grave
+   (218 250)				;latin letter u with acute
+   (219 251)				;latin letter u with circumflex
+   (220 252)				;latin letter u with diaeresis
+   (221 253)				;latin letter y with acute
+   (222 254)				;latin letter y with circumflex
+   ))
+
+;; ISO 8859-16, not in FSF, our mapping. 
+(setup-case-pairs
+ 'latin-iso8859-16
+ '((161 162)				;latin letter a with ogonek
+   (163 179)				;latin letter l with stroke
+   (166 168)				;latin letter s with caron
+   (170 186)				;latin letter s with comma below
+   (172 174)				;latin letter z with acute
+   (175 191)				;latin letter z with dot above
+   (178 185)				;latin letter c with caron
+   (180 184)				;latin letter z with caron
+   (190 255)				;latin letter y with diaeresis
+   (192 224)				;latin letter a with grave
+   (193 225)				;latin letter a with acute
+   (194 226)				;latin letter a with circumflex
+   (195 227)				;latin letter a with breve
+   (196 228)				;latin letter a with diaeresis
+   (197 229)				;latin letter c with acute
+   (198 230)				;latin letter ae
+   (199 231)				;latin letter c with cedilla
+   (200 232)				;latin letter e with grave
+   (201 233)				;latin letter e with acute
+   (202 234)				;latin letter e with circumflex
+   (203 235)				;latin letter e with diaeresis
+   (204 236)				;latin letter i with grave
+   (205 237)				;latin letter i with acute
+   (206 238)				;latin letter i with circumflex
+   (207 239)				;latin letter i with diaeresis
+   (208 240)				;latin letter d with stroke
+   (209 241)				;latin letter n with acute
+   (210 242)				;latin letter o with grave
+   (211 243)				;latin letter o with acute
+   (212 244)				;latin letter o with circumflex
+   (213 245)				;latin letter o with double acute
+   (214 246)				;latin letter o with diaeresis
+   (215 247)				;latin letter s with acute
+   (216 248)				;latin letter u with double acute
+   (217 249)				;latin letter u with grave
+   (218 250)				;latin letter u with acute
+   (219 251)				;latin letter u with circumflex
+   (220 252)				;latin letter u with diaeresis
+   (221 253)				;latin letter e with ogonek
+   (222 254)				;latin letter t with comma below
+   ))
+
 
 ;; This is our utility function; we don't want it in the dumped XEmacs.