[Emacs-diffs] /srv/bzr/emacs/trunk r107323: Update char-script-table from the latest Unicode Database.

[Eli Zaretskii]

------------------------------------------------------------
revno: 107323
committer: Eli Zaretskii <address@hidden>
branch nick: trunk
timestamp: Sat 2012-02-18 13:36:54 +0200
message:
  Update char-script-table from the latest Unicode Database.
  
   lisp/international/characters.el (script-list): Sync with the latest
   Unicode Character Database.
modified:
  lisp/ChangeLog
  lisp/international/characters.el

=== modified file 'lisp/ChangeLog'
--- a/lisp/ChangeLog    2012-02-18 10:24:23 +0000
+++ b/lisp/ChangeLog    2012-02-18 11:36:54 +0000
@@ -1,3 +1,8 @@
+2012-02-18  Eli Zaretskii  <address@hidden>
+
+       * international/characters.el (script-list): Sync with the latest
+       Unicode Character Database.
+
 2012-02-18  Andreas Schwab  <address@hidden>
 
        * international/titdic-cnv.el: Remove duplicate coding tag.

=== modified file 'lisp/international/characters.el'
--- a/lisp/international/characters.el  2012-02-11 22:13:29 +0000
+++ b/lisp/international/characters.el  2012-02-18 11:36:54 +0000
@@ -1114,6 +1114,12 @@
 
 ;; 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 @@
         (#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 @@
         (#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 @@
         (#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 @@
         (#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))