comparison lisp/international/codepage.el @ 24454:fe0089dd2d2f

(cp1250-decode-table, cp1251-decode-table, cp1253-decode-table, cp1257-decode-table): New translation tables for MS Windows codepages. (cp-make-coding-systems-for-codepage): Accept 4 digit codepages.

24453:3b8991c22dcd

   nil 236 147 233 nil 228 148 nil 155 214 nil nil 129 nil 215 nil]
  "Table for converting ISO-8859-4 characters into codepage 775 glyphs.")
(setplist 'cp775-decode-table
	  '(charset latin-iso8859-4 language "Latin-4" offset 160))

;;;###autoload
(defun cp-make-coding-systems-for-codepage (codepage iso-name offset)
  "Create a coding system to convert IBM CODEPAGE into charset ISO-NAME
whose first character is at offset OFFSET from the beginning of 8-bit
ASCII table.

    (let (alist chset sname)
      (mapatoms
       (function
	(lambda (sym)
	  (if (and (boundp sym)
		   (string-match "\\`cp\\([1-9][0-9][0-9]\\)-decode-table\\'"
				 (setq sname (symbol-name sym)))
		   (vectorp (symbol-value sym))
		   (setq chset (get sym 'charset)))
	      (setq alist
		    (cons (cons (match-string 1 sname) chset) alist))))))

24454:fe0089dd2d2f

   nil 236 147 233 nil 228 148 nil 155 214 nil nil 129 nil 215 nil]
  "Table for converting ISO-8859-4 characters into codepage 775 glyphs.")
(setplist 'cp775-decode-table
	  '(charset latin-iso8859-4 language "Latin-4" offset 160))

;; Support for the Windows 12xx series of codepages that MS has
;; butchered from the ISO-8859 specs. This does not add support for
;; the extended characters that MS has added in the 128 - 159 coding
;; range, only translates those characters that can be expressed in
;; the corresponding iso-8859 codepage.

;; Codepage Mapping:
;;
;; Windows-1250: ISO-8859-2 (Central Europe) - differs in some positions
;; Windows-1251: ISO-8859-5 (Cyrillic)       - differs wildly
;; Windows-1252: ISO-8859-1 (West Europe)    - exact match
;; Windows-1253: ISO-8859-7 (Greek)          - differs in some positions
;; Windows-1254: ISO-8859-9 (Turkish)        - exact match
;; Windows-1255: ISO-8859-8 (Hebrew)         - exact match
;; Windows-1256: ISO-8859-6 (Arabic)         - half match
;; Windows-1257: ISO-8859-4 (Baltic)         - differs, future Latin-7
;; Windows-1258: VISCII (Vietnamese)         - Completely different

(defvar cp1250-decode-table
  [
    160 165 162 163 164 188 140 167 168 138 170 141 143 173 142 175
    176 185 178 179 180 190 156 161 184 154 186 157 159 189 158 191
    192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
    208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
    224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
    240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 ]
  "ISO-8859-2 to Windows-1250 (Central Europe) codepage decoding table")
(setplist 'cp1250-decode-table
          '(charset latin-iso8859-2 language "Latin-2" offset 160))

(defvar cp1251-decode-table
  [
    160 168 128 129 170 189 178 175 163 138 140 142 141 173 161 143
    192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
    208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
    224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
    240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
    185 184 144 131 186 190 179 191 188 154 156 158 157 167 162 159 ]
  "ISO-8859-5 to Windows-1251 (Cyrillic) codepage decoding table")
(setplist 'cp1251-decode-table
          '(charset cyrillic-iso8859-5 language "Cyrillic-ISO" offset 160))

;; cp1253 is missing nbsp so we cannot quite translate perfectly. It
;; also has two micro/mu characters which would require more complex
;; processing to accomodate.
(defvar cp1253-decode-table
  [
    nil 145 146 163 nil nil 166 167 168 169 nil 171 172 173 nil 151
    176 177 178 179 180 161 162 183 184 185 186 187 188 189 190 191
    192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
    208 209 nil 211 212 213 214 215 216 217 218 219 220 221 222 223
    224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
    240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 nil ]
  "ISO-8859-7 to Windows-1253 (Greek) codepage decoding table")
(setplist 'cp1253-decode-table
          '(charset greek-iso8859-7 language "Greek" offset 160))

;; Since Latin-7 is not yet official, and Emacs does not support it,
;; provide translation between Windows-1257 and Latin-4 the best we
;; can.
(defvar cp1257-decode-table
  [
    160 192 nil 170 164 nil 207 167 nil 208 199 204 nil 173 222 nil
    176 224 nil 186 nil nil 239 nil nil 240 231 236 nil nil 254 nil
    194 nil nil nil 196 197 175 193 200 201 198 nil 203 nil nil 206
    nil 210 212 205 nil 213 214 215 168 216 nil nil 220 nil 219 223
    226 nil nil nil 228 229 191 225 232 233 230 nil 235 nil nil 238
    nil 242 244 237 nil 245 246 247 184 248 nil nil 252 nil 251 nil ]
  "ISO-8859-4 to Windows-1257 (Baltic) codepage decoding table")
(setplist 'cp1257-decode-table
          '(charset latin-iso8859-4 language "Latin-4" offset 160))

;;;###autoload
(defun cp-make-coding-systems-for-codepage (codepage iso-name offset)
  "Create a coding system to convert IBM CODEPAGE into charset ISO-NAME
whose first character is at offset OFFSET from the beginning of 8-bit
ASCII table.

    (let (alist chset sname)
      (mapatoms
       (function
	(lambda (sym)
	  (if (and (boundp sym)
		   (string-match "\\`cp\\([1-9][0-9][0-9][0-9]?\\)-decode-table\\'"
				 (setq sname (symbol-name sym)))
		   (vectorp (symbol-value sym))
		   (setq chset (get sym 'charset)))
	      (setq alist
		    (cons (cons (match-string 1 sname) chset) alist))))))