summaryrefslogtreecommitdiff
path: root/lisp/language
diff options
context:
space:
mode:
Diffstat (limited to 'lisp/language')
-rw-r--r--lisp/language/chinese.el5
-rw-r--r--lisp/language/hebrew.el2
-rw-r--r--lisp/language/ind-util.el40
-rw-r--r--lisp/language/japanese.el10
-rw-r--r--lisp/language/korean.el12
-rw-r--r--lisp/language/lao-util.el16
-rw-r--r--lisp/language/misc-lang.el8
-rw-r--r--lisp/language/tibet-util.el14
-rw-r--r--lisp/language/tibetan.el8
9 files changed, 86 insertions, 29 deletions
diff --git a/lisp/language/chinese.el b/lisp/language/chinese.el
index bc6969c1398..4389db961d8 100644
--- a/lisp/language/chinese.el
+++ b/lisp/language/chinese.el
@@ -103,6 +103,11 @@
(define-coding-system-alias 'hz-gb-2312 'chinese-hz)
(define-coding-system-alias 'hz 'chinese-hz)
+;; FIXME: 'define-coding-system' automatically sets :ascii-compatible-p,
+;; to any encoding whose :coding-type is 'utf-8', but UTF-7 is not ASCII
+;; compatible, so we override that here (bug#40407).
+(coding-system-put 'chinese-hz :ascii-compatible-p nil)
+
(set-language-info-alist
"Chinese-GB" '((charset chinese-gb2312 chinese-sisheng)
(iso639-language . zh)
diff --git a/lisp/language/hebrew.el b/lisp/language/hebrew.el
index 573541aec16..08b70abfc29 100644
--- a/lisp/language/hebrew.el
+++ b/lisp/language/hebrew.el
@@ -240,7 +240,7 @@ Bidirectional editing is supported.")))
(let* ((base "[\u05D0-\u05F2\uFB1D\uFB1F-\uFB28\uFB2A-\uFB4F]")
(combining
- "[\u0591-\u05BD\u05BF\u05C1-\u05C2\u05C4-\u05C5\u05C7\uFB1E]+")
+ "[\u034F\u0591-\u05BD\u05BF\u05C1-\u05C2\u05C4-\u05C5\u05C7\uFB1E]+")
(pattern1 (concat base combining))
(pattern2 (concat base "\u200D" combining)))
(set-char-table-range
diff --git a/lisp/language/ind-util.el b/lisp/language/ind-util.el
index 4319e5537e7..62885227f10 100644
--- a/lisp/language/ind-util.el
+++ b/lisp/language/ind-util.el
@@ -232,8 +232,8 @@
'(
(;; VOWELS
(?അ nil) (?ആ ?ാ) (?ഇ ?ി) (?ഈ ?ീ) (?ഉ ?ു) (?ഊ ?ൂ)
- (?ഋ ?ൃ) (?ഌ nil) nil (?ഏ ?േ) (?എ ?െ) (?ഐ ?ൈ)
- nil (?ഓ ?ോ) (?ഒ ?ൊ) (?ഔ ?ൌ) nil nil)
+ (?ഋ ?ൃ) (?ഌ ?ൢ) (?ൡ ?ൣ) (?ഏ ?േ) (?എ ?െ) (?ഐ ?ൈ)
+ nil (?ഒ ?ൊ) (?ഓ ?ോ) (?ഔ ?ൗ) (?് ?്) (?ൠ ?ൄ))
(;; CONSONANTS
?ക ?ഖ ?ഗ ?ഘ ?ങ ;; GUTTRULS
?ച ?ഛ ?ജ ?ഝ ?ഞ ;; PALATALS
@@ -243,13 +243,16 @@
?യ ?ര ?റ ?ല ?ള ?ഴ ?വ ;; SEMIVOWELS
?ശ ?ഷ ?സ ?ഹ ;; SIBILANTS
nil nil nil nil nil nil nil nil ;; NUKTAS
- "ജ്ഞ" "ക്ഷ")
+ "ജ്ഞ" "ക്ഷ"
+ "റ്റ" "ന്റ" "ത്ത" "ത്ഥ" "ഞ്ഞ" "ങ്ങ" "ന്ന"
+ "ഞ്ച" "ന്ക" "ങ്ക" "ച്ച" "ച്ഛ" "ക്ക"
+ "ബ്ബ" "ക്ക" "ഗ്ഗ" "ജ്ജ" "മ്മ" "പ്പ" "വ്വ" "ക്സ" "ശ്ശ")
(;; Misc Symbols
nil ?ം ?ഃ nil ?് nil nil)
(;; Digits
?൦ ?൧ ?൨ ?൩ ?൪ ?൫ ?൬ ?൭ ?൮ ?൯)
- (;; Inscript-extra (4) (#, $, ^, *, ])
- "്ര" "ര്" "ത്ര" "ശ്ര" nil)))
+ (;; Chillus
+ "ണ്" ?ൺ "ന്" ?ൻ "ര്" ?ർ "ല്" ?ൽ "ള്" ?ൾ)))
(defvar indian-tml-base-table
'(
@@ -323,6 +326,29 @@
(;; misc -- 7
".N" (".n" "M") "H" ".a" ".h" ("AUM" "OM") "..")))
+(defvar indian-mlm-mozhi-table
+ '(;; for encode/decode
+ (;; vowels -- 18
+ "a" ("aa" "A") "i" ("ii" "I") "u" ("uu" "U")
+ "R" "Ll" "Lll" ("E" "ae") "e" "ai"
+ nil "o" "O" "au" "~" "RR")
+ (;; consonants -- 40
+ ("k" "c") "kh" "g" "gh" "ng"
+ "ch" ("Ch" "chh") "j" "jh" "nj"
+ "T" "Th" "D" "Dh" "N"
+ "th" "thh" "d" "dh" "n" nil
+ "p" ("ph" "f") "b" "bh" "m"
+ "y" "r" "rr" "l" "L" "zh" ("v" "w")
+ ("S" "z") "sh" "s" "h"
+ nil nil nil nil nil nil nil nil
+ nil "X"
+ ;; some of these are extra to Mozhi
+ ("t" "tt") "nt" "tth" "tthh" "nnj" "nng" "nn"
+ "nch" "nc" "nk" "cch" "cchh" "cc"
+ "B" ("C" "K" "q") "G" "J" "M" "P" "V" "x" "Z")
+ (;; misc -- 7
+ nil nil "H")))
+
(defvar indian-kyoto-harvard-table
'(;; for encode/decode
(;; vowel
@@ -524,6 +550,10 @@
(indian-make-hash indian-mlm-base-table
indian-itrans-v5-table))
+(defvar indian-mlm-mozhi-hash
+ (indian-make-hash indian-mlm-base-table
+ indian-mlm-mozhi-table))
+
(defvar indian-tml-itrans-v5-hash
(indian-make-hash indian-tml-base-table
indian-itrans-v5-table-for-tamil))
diff --git a/lisp/language/japanese.el b/lisp/language/japanese.el
index d77efa48c9b..9a99245dfde 100644
--- a/lisp/language/japanese.el
+++ b/lisp/language/japanese.el
@@ -82,9 +82,7 @@
(#x00A6 . #xFFE4) ; BROKEN LINE FULLWIDTH BROKEN LINE
)))
(define-translation-table 'japanese-ucs-jis-to-cp932-map map)
- (mapc #'(lambda (x) (let ((tmp (car x)))
- (setcar x (cdr x)) (setcdr x tmp)))
- map)
+ (setq map (mapcar (lambda (x) (cons (cdr x) (car x))) map))
(define-translation-table 'japanese-ucs-cp932-to-jis-map map))
;; U+2014 (EM DASH) vs U+2015 (HORIZONTAL BAR)
@@ -241,8 +239,10 @@ eucJP-ms is defined in <http://www.opengroup.or.jp/jvc/cde/appendix.html>."
(#x2b65 . [#x02E9 #x02E5])
(#x2b66 . [#x02E5 #x02E9])))
table)
- (dolist (elt map)
- (setcar elt (decode-char 'japanese-jisx0213-1 (car elt))))
+ (setq map
+ (mapcar (lambda (x) (cons (decode-char 'japanese-jisx0213-1 (car x))
+ (cdr x)))
+ map))
(setq table (make-translation-table-from-alist map))
(define-translation-table 'jisx0213-to-unicode table)
(define-translation-table 'unicode-to-jisx0213
diff --git a/lisp/language/korean.el b/lisp/language/korean.el
index 210d0fabaf7..7e758159a48 100644
--- a/lisp/language/korean.el
+++ b/lisp/language/korean.el
@@ -84,6 +84,18 @@ and the following key bindings are available within Korean input methods:
F9, Hangul_Hanja: hangul-to-hanja-conversion")
))
+;; For auto-composing conjoining jamo.
+(let* ((choseong "[\u1100-\u115F\uA960-\uA97C]")
+ (jungseong "[\u1160-\u11A7\uD7B0-\uD7C6]")
+ (jongseong "[\u11A8-\u11FF\uD7CB-\uD7FB]?")
+ (pattern (concat choseong jungseong jongseong)))
+ (set-char-table-range composition-function-table
+ '(#x1100 . #x115F)
+ (list (vector pattern 0 'font-shape-gstring)))
+ (set-char-table-range composition-function-table
+ '(#xA960 . #xA97C)
+ (list (vector pattern 0 'font-shape-gstring))))
+
(provide 'korean)
;;; korean.el ends here
diff --git a/lisp/language/lao-util.el b/lisp/language/lao-util.el
index a20aecee421..fa4c2f7f891 100644
--- a/lisp/language/lao-util.el
+++ b/lisp/language/lao-util.el
@@ -183,7 +183,9 @@
;; Semi-vowel-sign-lo and lower vowels are put under the letter.
(defconst lao-transcription-consonant-alist
- (sort '(;; single consonants
+ (sort
+ (copy-sequence
+ '(;; single consonants
("k" . "ກ")
("kh" . "ຂ")
("qh" . "ຄ")
@@ -223,14 +225,16 @@
("hy" . ["ຫຍ"])
("hn" . ["ຫນ"])
("hm" . ["ຫມ"])
- )
- (function (lambda (x y) (> (length (car x)) (length (car y)))))))
+ ))
+ (lambda (x y) (> (length (car x)) (length (car y))))))
(defconst lao-transcription-semi-vowel-alist
'(("r" . "ຼ")))
(defconst lao-transcription-vowel-alist
- (sort '(("a" . "ະ")
+ (sort
+ (copy-sequence
+ '(("a" . "ະ")
("ar" . "າ")
("i" . "ິ")
("ii" . "ີ")
@@ -257,8 +261,8 @@
("ai" . "ໄ")
("ei" . "ໃ")
("ao" . ["ເົາ"])
- ("aM" . "ຳ"))
- (function (lambda (x y) (> (length (car x)) (length (car y)))))))
+ ("aM" . "ຳ")))
+ (lambda (x y) (> (length (car x)) (length (car y))))))
;; Maa-sakod is put at the tail.
(defconst lao-transcription-maa-sakod-alist
diff --git a/lisp/language/misc-lang.el b/lisp/language/misc-lang.el
index e25e63b4c5c..e3a24c41536 100644
--- a/lisp/language/misc-lang.el
+++ b/lisp/language/misc-lang.el
@@ -136,10 +136,10 @@ thin (i.e. 1-dot width) space."
(set-char-table-range
composition-function-table
'(#x600 . #x74F)
- (list (vector "[\u0600-\u074F\u200C\u200D]+" 0
- 'arabic-shape-gstring)
- (vector "[\u200C\u200D][\u0600-\u074F\u200C\u200D]+" 1
- 'arabic-shape-gstring)))
+ (list (vector "[\u200C\u200D][\u0600-\u074F\u200C\u200D]+"
+ 1 'arabic-shape-gstring)
+ (vector "[\u0600-\u074F\u200C\u200D]+"
+ 0 'arabic-shape-gstring)))
(provide 'misc-lang)
diff --git a/lisp/language/tibet-util.el b/lisp/language/tibet-util.el
index 29fff9175b7..8684cdb1338 100644
--- a/lisp/language/tibet-util.el
+++ b/lisp/language/tibet-util.el
@@ -43,13 +43,17 @@
("་" . "་")
("༔" . "༔")
;; Yes these are dirty. But ...
- ("༎ ༎" . ,(compose-string "༎ ༎" 0 3 [?༎ (Br . Bl) ? (Br . Bl) ?༎]))
+ ("༎ ༎" . ,(compose-string (copy-sequence "༎ ༎")
+ 0 3 [?༎ (Br . Bl) ? (Br . Bl) ?༎]))
("༄༅༅" . ,(compose-string
- "࿁࿂࿂࿂" 0 4
+ (copy-sequence "࿁࿂࿂࿂") 0 4
[?࿁ (Br . Bl) ?࿂ (Br . Bl) ?࿂ (Br . Bl) ?࿂]))
- ("༄༅" . ,(compose-string "࿁࿂࿂" 0 3 [?࿁ (Br . Bl) ?࿂ (Br . Bl) ?࿂]))
- ("༆" . ,(compose-string "࿁࿂༙" 0 3 [?࿁ (Br . Bl) ?࿂ (br . tr) ?༙]))
- ("༄" . ,(compose-string "࿁࿂" 0 2 [?࿁ (Br . Bl) ?࿂]))))
+ ("༄༅" . ,(compose-string (copy-sequence "࿁࿂࿂")
+ 0 3 [?࿁ (Br . Bl) ?࿂ (Br . Bl) ?࿂]))
+ ("༆" . ,(compose-string (copy-sequence "࿁࿂༙")
+ 0 3 [?࿁ (Br . Bl) ?࿂ (br . tr) ?༙]))
+ ("༄" . ,(compose-string (copy-sequence "࿁࿂")
+ 0 2 [?࿁ (Br . Bl) ?࿂]))))
;;;###autoload
(defun tibetan-char-p (ch)
diff --git a/lisp/language/tibetan.el b/lisp/language/tibetan.el
index d31cd5cd528..bbd4729f6c5 100644
--- a/lisp/language/tibetan.el
+++ b/lisp/language/tibetan.el
@@ -326,7 +326,9 @@
(defconst tibetan-subjoined-transcription-alist
- (sort '(("+k" . "ྐ")
+ (sort
+ (copy-sequence
+ '(("+k" . "ྐ")
("+kh" . "ྑ")
("+g" . "ྒ")
("+gh" . "ྒྷ")
@@ -371,8 +373,8 @@
("+W" . "ྺ") ;; fixed form subscribed WA
("+Y" . "ྻ") ;; fixed form subscribed YA
("+R" . "ྼ") ;; fixed form subscribed RA
- )
- (lambda (x y) (> (length (car x)) (length (car y))))))
+ ))
+ (lambda (x y) (> (length (car x)) (length (car y))))))
;;;
;;; alist for Tibetan base consonant <-> subjoined consonant conversion.
generated by cgit v1.2.3 (git 2.39.1) at 2025-06-21 17:29:18 +0000