Add 2008 to copyright years.
[bpt/emacs.git] / lisp / nxml / nxml-uchnm.el
1 ;;; nxml-uchnm.el --- support for Unicode standard cha names in nxml-mode
2
3 ;; Copyright (C) 2003, 2007, 2008 Free Software Foundation, Inc.
4
5 ;; Author: James Clark
6 ;; Keywords: XML
7
8 ;; This file is part of GNU Emacs.
9
10 ;; GNU Emacs is free software; you can redistribute it and/or modify
11 ;; it under the terms of the GNU General Public License as published by
12 ;; the Free Software Foundation; either version 3, or (at your option)
13 ;; any later version.
14
15 ;; GNU Emacs is distributed in the hope that it will be useful,
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 ;; GNU General Public License for more details.
19
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with GNU Emacs; see the file COPYING. If not, write to the
22 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
23 ;; Boston, MA 02110-1301, USA.
24
25 ;;; Commentary:
26
27 ;; This enables the use of the character names defined in the Unicode
28 ;; Standard. The use of the names can be controlled on a per-block
29 ;; basis, so as both to reduce memory usage and loading time,
30 ;; and to make completion work better.
31 ;; The main entry point is `nxml-enable-unicode-char-name-sets'. Typically,
32 ;; this is added to `nxml-mode-hook' (rng-auto.el does this already).
33 ;; To customize the blocks for which names are used
34
35 ;;; Code:
36
37 (require 'nxml-mode)
38
39 (defconst nxml-unicode-blocks
40 '(("Basic Latin" #x0000 #x007F)
41 ("Latin-1 Supplement" #x0080 #x00FF)
42 ("Latin Extended-A" #x0100 #x017F)
43 ("Latin Extended-B" #x0180 #x024F)
44 ("IPA Extensions" #x0250 #x02AF)
45 ("Spacing Modifier Letters" #x02B0 #x02FF)
46 ("Combining Diacritical Marks" #x0300 #x036F)
47 ("Greek and Coptic" #x0370 #x03FF)
48 ("Cyrillic" #x0400 #x04FF)
49 ("Cyrillic Supplementary" #x0500 #x052F)
50 ("Armenian" #x0530 #x058F)
51 ("Hebrew" #x0590 #x05FF)
52 ("Arabic" #x0600 #x06FF)
53 ("Syriac" #x0700 #x074F)
54 ("Thaana" #x0780 #x07BF)
55 ("Devanagari" #x0900 #x097F)
56 ("Bengali" #x0980 #x09FF)
57 ("Gurmukhi" #x0A00 #x0A7F)
58 ("Gujarati" #x0A80 #x0AFF)
59 ("Oriya" #x0B00 #x0B7F)
60 ("Tamil" #x0B80 #x0BFF)
61 ("Telugu" #x0C00 #x0C7F)
62 ("Kannada" #x0C80 #x0CFF)
63 ("Malayalam" #x0D00 #x0D7F)
64 ("Sinhala" #x0D80 #x0DFF)
65 ("Thai" #x0E00 #x0E7F)
66 ("Lao" #x0E80 #x0EFF)
67 ("Tibetan" #x0F00 #x0FFF)
68 ("Myanmar" #x1000 #x109F)
69 ("Georgian" #x10A0 #x10FF)
70 ("Hangul Jamo" #x1100 #x11FF)
71 ("Ethiopic" #x1200 #x137F)
72 ("Cherokee" #x13A0 #x13FF)
73 ("Unified Canadian Aboriginal Syllabics" #x1400 #x167F)
74 ("Ogham" #x1680 #x169F)
75 ("Runic" #x16A0 #x16FF)
76 ("Tagalog" #x1700 #x171F)
77 ("Hanunoo" #x1720 #x173F)
78 ("Buhid" #x1740 #x175F)
79 ("Tagbanwa" #x1760 #x177F)
80 ("Khmer" #x1780 #x17FF)
81 ("Mongolian" #x1800 #x18AF)
82 ("Latin Extended Additional" #x1E00 #x1EFF)
83 ("Greek Extended" #x1F00 #x1FFF)
84 ("General Punctuation" #x2000 #x206F)
85 ("Superscripts and Subscripts" #x2070 #x209F)
86 ("Currency Symbols" #x20A0 #x20CF)
87 ("Combining Diacritical Marks for Symbols" #x20D0 #x20FF)
88 ("Letterlike Symbols" #x2100 #x214F)
89 ("Number Forms" #x2150 #x218F)
90 ("Arrows" #x2190 #x21FF)
91 ("Mathematical Operators" #x2200 #x22FF)
92 ("Miscellaneous Technical" #x2300 #x23FF)
93 ("Control Pictures" #x2400 #x243F)
94 ("Optical Character Recognition" #x2440 #x245F)
95 ("Enclosed Alphanumerics" #x2460 #x24FF)
96 ("Box Drawing" #x2500 #x257F)
97 ("Block Elements" #x2580 #x259F)
98 ("Geometric Shapes" #x25A0 #x25FF)
99 ("Miscellaneous Symbols" #x2600 #x26FF)
100 ("Dingbats" #x2700 #x27BF)
101 ("Miscellaneous Mathematical Symbols-A" #x27C0 #x27EF)
102 ("Supplemental Arrows-A" #x27F0 #x27FF)
103 ("Braille Patterns" #x2800 #x28FF)
104 ("Supplemental Arrows-B" #x2900 #x297F)
105 ("Miscellaneous Mathematical Symbols-B" #x2980 #x29FF)
106 ("Supplemental Mathematical Operators" #x2A00 #x2AFF)
107 ("CJK Radicals Supplement" #x2E80 #x2EFF)
108 ("Kangxi Radicals" #x2F00 #x2FDF)
109 ("Ideographic Description Characters" #x2FF0 #x2FFF)
110 ("CJK Symbols and Punctuation" #x3000 #x303F)
111 ("Hiragana" #x3040 #x309F)
112 ("Katakana" #x30A0 #x30FF)
113 ("Bopomofo" #x3100 #x312F)
114 ("Hangul Compatibility Jamo" #x3130 #x318F)
115 ("Kanbun" #x3190 #x319F)
116 ("Bopomofo Extended" #x31A0 #x31BF)
117 ("Katakana Phonetic Extensions" #x31F0 #x31FF)
118 ("Enclosed CJK Letters and Months" #x3200 #x32FF)
119 ("CJK Compatibility" #x3300 #x33FF)
120 ("CJK Unified Ideographs Extension A" #x3400 #x4DBF)
121 ;;("CJK Unified Ideographs" #x4E00 #x9FFF)
122 ("Yi Syllables" #xA000 #xA48F)
123 ("Yi Radicals" #xA490 #xA4CF)
124 ;;("Hangul Syllables" #xAC00 #xD7AF)
125 ;;("High Surrogates" #xD800 #xDB7F)
126 ;;("High Private Use Surrogates" #xDB80 #xDBFF)
127 ;;("Low Surrogates" #xDC00 #xDFFF)
128 ;;("Private Use Area" #xE000 #xF8FF)
129 ;;("CJK Compatibility Ideographs" #xF900 #xFAFF)
130 ("Alphabetic Presentation Forms" #xFB00 #xFB4F)
131 ("Arabic Presentation Forms-A" #xFB50 #xFDFF)
132 ("Variation Selectors" #xFE00 #xFE0F)
133 ("Combining Half Marks" #xFE20 #xFE2F)
134 ("CJK Compatibility Forms" #xFE30 #xFE4F)
135 ("Small Form Variants" #xFE50 #xFE6F)
136 ("Arabic Presentation Forms-B" #xFE70 #xFEFF)
137 ("Halfwidth and Fullwidth Forms" #xFF00 #xFFEF)
138 ("Specials" #xFFF0 #xFFFF)
139 ("Old Italic" #x10300 #x1032F)
140 ("Gothic" #x10330 #x1034F)
141 ("Deseret" #x10400 #x1044F)
142 ("Byzantine Musical Symbols" #x1D000 #x1D0FF)
143 ("Musical Symbols" #x1D100 #x1D1FF)
144 ("Mathematical Alphanumeric Symbols" #x1D400 #x1D7FF)
145 ;;("CJK Unified Ideographs Extension B" #x20000 #x2A6DF)
146 ;;("CJK Compatibility Ideographs Supplement" #x2F800 #x2FA1F)
147 ("Tags" #xE0000 #xE007F)
148 ;;("Supplementary Private Use Area-A" #xF0000 #xFFFFF)
149 ;;("Supplementary Private Use Area-B" #x100000 #x10FFFF)
150 )
151 "List of Unicode blocks.
152 For each block there is a list (NAME FIRST LAST), where
153 NAME is a string giving the offical name of the block,
154 FIRST is the first code-point and LAST is the last code-point.
155 Blocks containing only characters with algorithmic names or no names
156 are omitted.")
157
158 (defun nxml-unicode-block-char-name-set (name)
159 "Return a symbol for a block whose offical Unicode name is NAME.
160 The symbol is generated by downcasing and replacing each space
161 by a hyphen."
162 (intern (replace-regexp-in-string " " "-" (downcase name))))
163
164 ;; This is intended to be a superset of the coverage
165 ;; of existing standard entity sets.
166 (defvar nxml-enabled-unicode-blocks-default
167 '(basic-latin
168 latin-1-supplement
169 latin-extended-a
170 latin-extended-b
171 ipa-extensions
172 spacing-modifier-letters
173 combining-diacritical-marks
174 greek-and-coptic
175 cyrillic
176 general-punctuation
177 superscripts-and-subscripts
178 currency-symbols
179 combining-diacritical-marks-for-symbols
180 letterlike-symbols
181 number-forms
182 arrows
183 mathematical-operators
184 miscellaneous-technical
185 control-pictures
186 optical-character-recognition
187 enclosed-alphanumerics
188 box-drawing
189 block-elements
190 geometric-shapes
191 miscellaneous-symbols
192 dingbats
193 miscellaneous-mathematical-symbols-a
194 supplemental-arrows-a
195 supplemental-arrows-b
196 miscellaneous-mathematical-symbols-b
197 supplemental-mathematical-operators
198 cjk-symbols-and-punctuation
199 alphabetic-presentation-forms
200 variation-selectors
201 small-form-variants
202 specials
203 mathematical-alphanumeric-symbols)
204 "Default value for `nxml-enabled-unicode-blocks'.")
205
206 (mapc (lambda (block)
207 (nxml-autoload-char-name-set
208 (nxml-unicode-block-char-name-set (car block))
209 (expand-file-name
210 (format "nxml/%05X-%05X"
211 (nth 1 block)
212 (nth 2 block))
213 data-directory)))
214 nxml-unicode-blocks)
215
216 (defvar nxml-enable-unicode-char-name-sets-flag nil)
217
218 (defcustom nxml-enabled-unicode-blocks nxml-enabled-unicode-blocks-default
219 "List of Unicode blocks for which Unicode character names are enabled.
220 Each block is identified by a symbol derived from the name
221 of the block by downcasing and replacing each space by a hyphen."
222 :group 'nxml
223 :set (lambda (sym value)
224 (set-default 'nxml-enabled-unicode-blocks value)
225 (when nxml-enable-unicode-char-name-sets-flag
226 (nxml-enable-unicode-char-name-sets-1)))
227 :type (cons 'set
228 (mapcar (lambda (block)
229 `(const :tag ,(format "%s (%04X-%04X)"
230 (nth 0 block)
231 (nth 1 block)
232 (nth 2 block))
233 ,(nxml-unicode-block-char-name-set
234 (nth 0 block))))
235 nxml-unicode-blocks)))
236
237 ;;;###autoload
238 (defun nxml-enable-unicode-char-name-sets ()
239 "Enable the use of Unicode standard names for characters.
240 The Unicode blocks for which names are enabled is controlled by
241 the variable `nxml-enabled-unicode-blocks'."
242 (interactive)
243 (setq nxml-char-name-ignore-case t)
244 (setq nxml-enable-unicode-char-name-sets-flag t)
245 (nxml-enable-unicode-char-name-sets-1))
246
247 (defun nxml-enable-unicode-char-name-sets-1 ()
248 (mapc (lambda (block)
249 (nxml-disable-char-name-set
250 (nxml-unicode-block-char-name-set (car block))))
251 nxml-unicode-blocks)
252 (mapc (lambda (nameset)
253 (nxml-enable-char-name-set nameset))
254 nxml-enabled-unicode-blocks))
255
256 (provide 'nxml-uchnm)
257
258 ;; arch-tag: 440248c3-b604-467c-8b50-e83662c659a3
259 ;;; nxml-uchnm.el ends here