summaryrefslogtreecommitdiff
path: root/lisp/international
diff options
context:
space:
mode:
Diffstat (limited to 'lisp/international')
-rw-r--r--lisp/international/characters.el111
-rw-r--r--lisp/international/charprop.el6
-rw-r--r--lisp/international/mule-cmds.el24
-rw-r--r--lisp/international/titdic-cnv.el4
-rw-r--r--lisp/international/uni-comment.elbin2407 -> 2386 bytes
-rw-r--r--lisp/international/uni-name.elbin158786 -> 158833 bytes
-rw-r--r--lisp/international/uni-old-name.elbin19713 -> 19760 bytes
7 files changed, 118 insertions, 27 deletions
diff --git a/lisp/international/characters.el b/lisp/international/characters.el
index d7b55d56093..ba8b8955fba 100644
--- a/lisp/international/characters.el
+++ b/lisp/international/characters.el
@@ -1114,6 +1114,12 @@ Setup char-width-table appropriate for non-CJK language environment."
;; Setting char-script-table.
+;; The data is compiled from Blocks.txt and Scripts.txt in the
+;; "Unicode Character Database", simplified to lump together all the
+;; blocks belonging to the same language. E.g., "Basic Latin",
+;; "Latin-1 Supplement", "Latin Extended-A", etc. are all lumped
+;; together under "latin".
+;;
;; The Unicode blocks actually extend past some of these ranges with
;; undefined codepoints.
(let ((script-list nil))
@@ -1126,13 +1132,17 @@ Setup char-width-table appropriate for non-CJK language environment."
(#x0370 #x03E1 greek)
(#x03E2 #x03EF coptic)
(#x03F0 #x03F3 greek)
- (#x0400 #x04FF cyrillic)
+ (#x0400 #x052F cyrillic)
(#x0530 #x058F armenian)
(#x0590 #x05FF hebrew)
(#x0600 #x06FF arabic)
(#x0700 #x074F syriac)
- (#x07C0 #x07FA nko)
+ (#x0750 #x077F arabic)
(#x0780 #x07BF thaana)
+ (#x07C0 #x07FF nko)
+ (#x0800 #x083F samaritan)
+ (#x0840 #x085F mandaic)
+ (#x08A0 #x08FF arabic)
(#x0900 #x097F devanagari)
(#x0980 #x09FF bengali)
(#x0A00 #x0A7F gurmukhi)
@@ -1143,10 +1153,10 @@ Setup char-width-table appropriate for non-CJK language environment."
(#x0C80 #x0CFF kannada)
(#x0D00 #x0D7F malayalam)
(#x0D80 #x0DFF sinhala)
- (#x0E00 #x0E5F thai)
- (#x0E80 #x0EDF lao)
+ (#x0E00 #x0E7F thai)
+ (#x0E80 #x0EFF lao)
(#x0F00 #x0FFF tibetan)
- (#x1000 #x109F burmese)
+ (#x1000 #x109F burmese) ; according to Unicode 6.1, should be "myanmar"
(#x10A0 #x10FF georgian)
(#x1100 #x11FF hangul)
(#x1200 #x139F ethiopic)
@@ -1154,14 +1164,40 @@ Setup char-width-table appropriate for non-CJK language environment."
(#x1400 #x167F canadian-aboriginal)
(#x1680 #x169F ogham)
(#x16A0 #x16FF runic)
+ (#x1700 #x171F tagalog)
+ (#x1720 #x173F hanunoo)
+ (#x1740 #x175F buhid)
+ (#x1760 #x177F tagbanwa)
(#x1780 #x17FF khmer)
(#x1800 #x18AF mongolian)
- (#x1D00 #x1DFF phonetic)
- (#x1E00 #x1EFF latin)
+ (#x18B0 #x18FF canadian-aboriginal)
+ (#x1900 #x194F limbu)
+ (#x1950 #x197F tai-le)
+ (#x1980 #x19DF tai-lue)
+ (#x19E0 #x19FF khmer)
+ (#x1A00 #x1A00 buginese)
+ (#x1A20 #x1AAF tai-tham)
+ (#x1B00 #x1B7F balinese)
+ (#x1B80 #x1BBF sundanese)
+ (#x1BC0 #x1BFF batak)
+ (#x1C00 #x1C4F lepcha)
+ (#x1C50 #x1C7F ol-chiki)
+ (#x1CC0 #x1CCF sundanese)
+ (#x1CD0 #x1CFF vedic)
+ (#x1D00 #x1DBF phonetic)
+ (#x1DC0 #x1EFF latin)
(#x1F00 #x1FFF greek)
(#x2000 #x27FF symbol)
(#x2800 #x28FF braille)
+ (#x2900 #x2BFF symbol)
+ (#x2C00 #x2C5F glagolitic)
+ (#x2C60 #x2C7F latin)
+ (#x2C80 #x2CFF coptic)
+ (#x2D00 #x2D2F georgian)
+ (#x2D30 #x2D7F tifinagh)
(#x2D80 #x2DDF ethiopic)
+ (#x2DE0 #x2DFF cyrillic)
+ (#x2E00 #x2E7F symbol)
(#x2E80 #x2FDF han)
(#x2FF0 #x2FFF ideographic-description)
(#x3000 #x303F cjk-misc)
@@ -1170,47 +1206,92 @@ Setup char-width-table appropriate for non-CJK language environment."
(#x3130 #x318F hangul)
(#x3190 #x319F kanbun)
(#x31A0 #x31BF bopomofo)
- (#x3400 #x9FAF han)
+ (#x31C0 #x31EF cjk-misc)
+ (#x31F0 #x31FF kana)
+ (#x3200 #x9FAF han)
(#xA000 #xA4CF yi)
+ (#xA4D0 #xA4FF lisu)
+ (#xA500 #xA63F vai)
+ (#xA640 #xA69F cyrillic)
+ (#xA6A0 #xA6FF bamum)
+ (#xA700 #xA7FF latin)
+ (#xA800 #xA82F syloti-nagri)
+ (#xA830 #xA83F north-indic-number)
+ (#xA840 #xA87F phags-pa)
+ (#xA880 #xA8DF saurashtra)
+ (#xA8E0 #xA8FF devanagari)
+ (#xA900 #xA92F kayah-li)
+ (#xA930 #xA95F rejang)
+ (#xA960 #xA97F hangul)
+ (#xA980 #xA9DF javanese)
(#xAA00 #xAA5F cham)
- (#xAA60 #xAA7B burmese)
+ (#xAA60 #xAA7B burmese) ; Unicode 6.1: "myanmar"
(#xAA80 #xAADF tai-viet)
- (#xAC00 #xD7AF hangul)
+ (#xAAE0 #xAAFF meetei-mayek)
+ (#xAB00 #xAB2F ethiopic)
+ (#xABC0 #xABFF meetei-mayek)
+ (#xAC00 #xD7FF hangul)
(#xF900 #xFAFF han)
(#xFB1D #xFB4F hebrew)
(#xFB50 #xFDFF arabic)
- (#xFE70 #xFEFC arabic)
+ (#xFE30 #xFE4F han)
+ (#xFE70 #xFEFF arabic)
(#xFF00 #xFF5F cjk-misc)
(#xFF61 #xFF9F kana)
(#xFFE0 #xFFE6 cjk-misc)
(#x10000 #x100FF linear-b)
(#x10100 #x1013F aegean-number)
- (#x10140 #x1018A ancient-greek-number)
- (#x10190 #x1019B ancient-symbol)
+ (#x10140 #x1018F ancient-greek-number)
+ (#x10190 #x101CF ancient-symbol)
(#x101D0 #x101FF phaistos-disc)
(#x10280 #x1029F lycian)
(#x102A0 #x102DF carian)
(#x10300 #x1032F olt-italic)
+ (#x10330 #x1034F gothic)
(#x10380 #x1039F ugaritic)
(#x103A0 #x103DF old-persian)
(#x10400 #x1044F deseret)
(#x10450 #x1047F shavian)
(#x10480 #x104AF osmanya)
(#x10800 #x1083F cypriot-syllabary)
+ (#x10840 #x1085F aramaic)
(#x10900 #x1091F phoenician)
(#x10920 #x1093F lydian)
+ (#x10980 #x109FF meroitic)
(#x10A00 #x10A5F kharoshthi)
+ (#x10A60 #x10A7F old-south-arabian)
+ (#x10B00 #x10B3F avestan)
+ (#x10B40 #x10B5F inscriptional-parthian)
+ (#x10B60 #x10B7F inscriptional-pahlavi)
+ (#x10C00 #x10C4F old-turkic)
+ (#x10E60 #x10E7F rumi-number)
+ (#x11000 #x1107F brahmi)
+ (#x11080 #x110CF kaithi)
+ (#x110D0 #x110FF sora-sompeng)
+ (#x11100 #x1114F chakma)
+ (#x11180 #x111DF sharada)
+ (#x11680 #x116CF takri)
(#x12000 #x123FF cuneiform)
(#x12400 #x1247F cuneiform-numbers-and-punctuation)
+ (#x13000 #x1342F egyptian)
+ (#x16800 #x16A3F bamum)
+ (#x16F00 #x16F9F miao)
+ (#x1B000 #x1B0FF kana)
(#x1D000 #x1D0FF byzantine-musical-symbol)
(#x1D100 #x1D1FF musical-symbol)
(#x1D200 #x1D24F ancient-greek-musical-notation)
(#x1D300 #x1D35F tai-xuan-jing-symbol)
(#x1D360 #x1D37F counting-rod-numeral)
(#x1D400 #x1D7FF mathematical)
+ (#x1EE00 #x1EEFF arabic)
(#x1F000 #x1F02F mahjong-tile)
(#x1F030 #x1F09F domino-tile)
- (#x20000 #x2AFFF han)
+ (#x1F0A0 #x1F0FF playing-cards)
+ (#x1F100 #x1F1FF symbol)
+ (#x1F200 #x1F2FF han)
+ (#x1F300 #x1F64F symbol)
+ (#x1F680 #x1F77F symbol)
+ (#x20000 #x2B81F han)
(#x2F800 #x2FFFF han)))
(set-char-table-range char-script-table
(cons (car elt) (nth 1 elt)) (nth 2 elt))
@@ -1372,7 +1453,7 @@ METHOD must be one of these symbols:
`acronym': display an acronym of the character in a box. The
acronym is taken from `char-acronym-table', which see.
`hex-code': display the hexadecimal character code in a box."
-
+ :version "24.1"
:type '(alist :key-type (symbol :tag "Character Group")
:value-type (symbol :tag "Display Method"))
:options '((c0-control
diff --git a/lisp/international/charprop.el b/lisp/international/charprop.el
index 2424e87ae44..50226b1b773 100644
--- a/lisp/international/charprop.el
+++ b/lisp/international/charprop.el
@@ -2,7 +2,8 @@
;; FILE: uni-name.el
(define-char-code-property 'name "uni-name.el"
"Unicode character name.
-Property value is a string.")
+Property value is a string or nil.
+The value nil stands for the default value \"null string\").")
;; FILE: uni-category.el
(define-char-code-property 'general-category "uni-category.el"
"Unicode general category.
@@ -48,7 +49,8 @@ Property value is a symbol `Y' or `N'. See also the property `mirroring'.")
;; FILE: uni-old-name.el
(define-char-code-property 'old-name "uni-old-name.el"
"Unicode old names as published in Unicode 1.0.
-Property value is a string.")
+Property value is a string or nil.
+The value nil stands for the default value \"null string\").")
;; FILE: uni-comment.el
(define-char-code-property 'iso-10646-comment "uni-comment.el"
"Unicode ISO 10646 comment.
diff --git a/lisp/international/mule-cmds.el b/lisp/international/mule-cmds.el
index 378cbc9badd..debc328c551 100644
--- a/lisp/international/mule-cmds.el
+++ b/lisp/international/mule-cmds.el
@@ -1,6 +1,6 @@
;;; mule-cmds.el --- commands for multilingual environment -*-coding: iso-2022-7bit -*-
-;; Copyright (C) 1997-2012 Free Software Foundation, Inc.
+;; Copyright (C) 1997-2012 Free Software Foundation, Inc.
;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
;; 2005, 2006, 2007, 2008, 2009, 2010, 2011
;; National Institute of Advanced Industrial Science and Technology (AIST)
@@ -2863,13 +2863,18 @@ on encoding."
;; Backwards compatibility. These might be better with :init-value t,
;; but that breaks loadup.
(define-minor-mode unify-8859-on-encoding-mode
- "Obsolete."
+ "Exists only for backwards compatibility."
:group 'mule
:global t)
+;; Doc said "obsolete" in 23.1, this statement only added in 24.1.
+(make-obsolete 'unify-8859-on-encoding-mode "don't use it." "23.1")
+
(define-minor-mode unify-8859-on-decoding-mode
- "Obsolete."
+ "Exists only for backwards compatibility."
:group 'mule
:global t)
+;; Doc said "obsolete" in 23.1, this statement only added in 24.1.
+(make-obsolete 'unify-8859-on-decoding-mode "don't use it." "23.1")
(defvar nonascii-insert-offset 0)
(make-obsolete-variable 'nonascii-insert-offset "do not use it." "23.1")
@@ -2944,9 +2949,9 @@ point or a number in hash notation, e.g. #o21430 for octal,
'(metadata (category . unicode-name))
(complete-with-action action (ucs-names) string pred))))))
(cond
- ((string-match-p "^[0-9a-fA-F]+$" input)
+ ((string-match-p "\\`[0-9a-fA-F]+\\'" input)
(string-to-number input 16))
- ((string-match-p "^#" input)
+ ((string-match-p "\\`#" input)
(read input))
(t
(cdr (assoc-string input (ucs-names) t))))))
@@ -2962,6 +2967,10 @@ preceded by an asterisk `*' and use completion, it will show all
the characters whose names include that substring, not necessarily
at the beginning of the name.
+This function also accepts a hexadecimal number of Unicode code
+point or a number in hash notation, e.g. #o21430 for octal,
+#x2318 for hex, or #10r8984 for decimal.
+
The optional third arg INHERIT (non-nil when called interactively),
says to inherit text properties from adjoining text, if those
properties are sticky."
@@ -2970,9 +2979,12 @@ properties are sticky."
(prefix-numeric-value current-prefix-arg)
t))
(unless count (setq count 1))
- (if (stringp character)
+ (if (and (stringp character)
+ (string-match-p "\\`[0-9a-fA-F]+\\'" character))
(setq character (string-to-number character 16)))
(cond
+ ((null character)
+ (error "Not a Unicode character"))
((not (integerp character))
(error "Not a Unicode character code: %S" character))
((or (< character 0) (> character #x10FFFF))
diff --git a/lisp/international/titdic-cnv.el b/lisp/international/titdic-cnv.el
index 21b0fdec6e4..a8f23adcf6d 100644
--- a/lisp/international/titdic-cnv.el
+++ b/lisp/international/titdic-cnv.el
@@ -1204,8 +1204,4 @@ to store generated Quail packages."
(miscdic-convert filename dir))))
(kill-emacs 0))
-;; Local Variables:
-;; coding: iso-2022-7bit
-;; End:
-
;;; titdic-cnv.el ends here
diff --git a/lisp/international/uni-comment.el b/lisp/international/uni-comment.el
index 21ccfe3ffe7..c9743064bd4 100644
--- a/lisp/international/uni-comment.el
+++ b/lisp/international/uni-comment.el
Binary files differ
diff --git a/lisp/international/uni-name.el b/lisp/international/uni-name.el
index 8b681631067..c3e5f2e5907 100644
--- a/lisp/international/uni-name.el
+++ b/lisp/international/uni-name.el
Binary files differ
diff --git a/lisp/international/uni-old-name.el b/lisp/international/uni-old-name.el
index de2d67b9450..6165eba61cc 100644
--- a/lisp/international/uni-old-name.el
+++ b/lisp/international/uni-old-name.el
Binary files differ
View Lorry Controller Status