| 1 | ;;; nxml-uchnm.el --- support for Unicode standard cha names in nxml-mode |
| 2 | |
| 3 | ;; Copyright (C) 2003, 2007-2012 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 of the License, or |
| 13 | ;; (at your option) 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. If not, see <http://www.gnu.org/licenses/>. |
| 22 | |
| 23 | ;;; Commentary: |
| 24 | |
| 25 | ;; This enables the use of the character names defined in the Unicode |
| 26 | ;; Standard. The use of the names can be controlled on a per-block |
| 27 | ;; basis, so as both to reduce memory usage and loading time, |
| 28 | ;; and to make completion work better. |
| 29 | |
| 30 | ;;; Code: |
| 31 | |
| 32 | (require 'nxml-mode) |
| 33 | |
| 34 | (defconst nxml-unicode-blocks |
| 35 | '(("Basic Latin" #x0000 #x007F) |
| 36 | ("Latin-1 Supplement" #x0080 #x00FF) |
| 37 | ("Latin Extended-A" #x0100 #x017F) |
| 38 | ("Latin Extended-B" #x0180 #x024F) |
| 39 | ("IPA Extensions" #x0250 #x02AF) |
| 40 | ("Spacing Modifier Letters" #x02B0 #x02FF) |
| 41 | ("Combining Diacritical Marks" #x0300 #x036F) |
| 42 | ("Greek and Coptic" #x0370 #x03FF) |
| 43 | ("Cyrillic" #x0400 #x04FF) |
| 44 | ("Cyrillic Supplementary" #x0500 #x052F) |
| 45 | ("Armenian" #x0530 #x058F) |
| 46 | ("Hebrew" #x0590 #x05FF) |
| 47 | ("Arabic" #x0600 #x06FF) |
| 48 | ("Syriac" #x0700 #x074F) |
| 49 | ("Thaana" #x0780 #x07BF) |
| 50 | ("Devanagari" #x0900 #x097F) |
| 51 | ("Bengali" #x0980 #x09FF) |
| 52 | ("Gurmukhi" #x0A00 #x0A7F) |
| 53 | ("Gujarati" #x0A80 #x0AFF) |
| 54 | ("Oriya" #x0B00 #x0B7F) |
| 55 | ("Tamil" #x0B80 #x0BFF) |
| 56 | ("Telugu" #x0C00 #x0C7F) |
| 57 | ("Kannada" #x0C80 #x0CFF) |
| 58 | ("Malayalam" #x0D00 #x0D7F) |
| 59 | ("Sinhala" #x0D80 #x0DFF) |
| 60 | ("Thai" #x0E00 #x0E7F) |
| 61 | ("Lao" #x0E80 #x0EFF) |
| 62 | ("Tibetan" #x0F00 #x0FFF) |
| 63 | ("Myanmar" #x1000 #x109F) |
| 64 | ("Georgian" #x10A0 #x10FF) |
| 65 | ("Hangul Jamo" #x1100 #x11FF) |
| 66 | ("Ethiopic" #x1200 #x137F) |
| 67 | ("Cherokee" #x13A0 #x13FF) |
| 68 | ("Unified Canadian Aboriginal Syllabics" #x1400 #x167F) |
| 69 | ("Ogham" #x1680 #x169F) |
| 70 | ("Runic" #x16A0 #x16FF) |
| 71 | ("Tagalog" #x1700 #x171F) |
| 72 | ("Hanunoo" #x1720 #x173F) |
| 73 | ("Buhid" #x1740 #x175F) |
| 74 | ("Tagbanwa" #x1760 #x177F) |
| 75 | ("Khmer" #x1780 #x17FF) |
| 76 | ("Mongolian" #x1800 #x18AF) |
| 77 | ("Latin Extended Additional" #x1E00 #x1EFF) |
| 78 | ("Greek Extended" #x1F00 #x1FFF) |
| 79 | ("General Punctuation" #x2000 #x206F) |
| 80 | ("Superscripts and Subscripts" #x2070 #x209F) |
| 81 | ("Currency Symbols" #x20A0 #x20CF) |
| 82 | ("Combining Diacritical Marks for Symbols" #x20D0 #x20FF) |
| 83 | ("Letterlike Symbols" #x2100 #x214F) |
| 84 | ("Number Forms" #x2150 #x218F) |
| 85 | ("Arrows" #x2190 #x21FF) |
| 86 | ("Mathematical Operators" #x2200 #x22FF) |
| 87 | ("Miscellaneous Technical" #x2300 #x23FF) |
| 88 | ("Control Pictures" #x2400 #x243F) |
| 89 | ("Optical Character Recognition" #x2440 #x245F) |
| 90 | ("Enclosed Alphanumerics" #x2460 #x24FF) |
| 91 | ("Box Drawing" #x2500 #x257F) |
| 92 | ("Block Elements" #x2580 #x259F) |
| 93 | ("Geometric Shapes" #x25A0 #x25FF) |
| 94 | ("Miscellaneous Symbols" #x2600 #x26FF) |
| 95 | ("Dingbats" #x2700 #x27BF) |
| 96 | ("Miscellaneous Mathematical Symbols-A" #x27C0 #x27EF) |
| 97 | ("Supplemental Arrows-A" #x27F0 #x27FF) |
| 98 | ("Braille Patterns" #x2800 #x28FF) |
| 99 | ("Supplemental Arrows-B" #x2900 #x297F) |
| 100 | ("Miscellaneous Mathematical Symbols-B" #x2980 #x29FF) |
| 101 | ("Supplemental Mathematical Operators" #x2A00 #x2AFF) |
| 102 | ("CJK Radicals Supplement" #x2E80 #x2EFF) |
| 103 | ("Kangxi Radicals" #x2F00 #x2FDF) |
| 104 | ("Ideographic Description Characters" #x2FF0 #x2FFF) |
| 105 | ("CJK Symbols and Punctuation" #x3000 #x303F) |
| 106 | ("Hiragana" #x3040 #x309F) |
| 107 | ("Katakana" #x30A0 #x30FF) |
| 108 | ("Bopomofo" #x3100 #x312F) |
| 109 | ("Hangul Compatibility Jamo" #x3130 #x318F) |
| 110 | ("Kanbun" #x3190 #x319F) |
| 111 | ("Bopomofo Extended" #x31A0 #x31BF) |
| 112 | ("Katakana Phonetic Extensions" #x31F0 #x31FF) |
| 113 | ("Enclosed CJK Letters and Months" #x3200 #x32FF) |
| 114 | ("CJK Compatibility" #x3300 #x33FF) |
| 115 | ("CJK Unified Ideographs Extension A" #x3400 #x4DBF) |
| 116 | ;;("CJK Unified Ideographs" #x4E00 #x9FFF) |
| 117 | ("Yi Syllables" #xA000 #xA48F) |
| 118 | ("Yi Radicals" #xA490 #xA4CF) |
| 119 | ;;("Hangul Syllables" #xAC00 #xD7AF) |
| 120 | ;;("High Surrogates" #xD800 #xDB7F) |
| 121 | ;;("High Private Use Surrogates" #xDB80 #xDBFF) |
| 122 | ;;("Low Surrogates" #xDC00 #xDFFF) |
| 123 | ;;("Private Use Area" #xE000 #xF8FF) |
| 124 | ;;("CJK Compatibility Ideographs" #xF900 #xFAFF) |
| 125 | ("Alphabetic Presentation Forms" #xFB00 #xFB4F) |
| 126 | ("Arabic Presentation Forms-A" #xFB50 #xFDFF) |
| 127 | ("Variation Selectors" #xFE00 #xFE0F) |
| 128 | ("Combining Half Marks" #xFE20 #xFE2F) |
| 129 | ("CJK Compatibility Forms" #xFE30 #xFE4F) |
| 130 | ("Small Form Variants" #xFE50 #xFE6F) |
| 131 | ("Arabic Presentation Forms-B" #xFE70 #xFEFF) |
| 132 | ("Halfwidth and Fullwidth Forms" #xFF00 #xFFEF) |
| 133 | ("Specials" #xFFF0 #xFFFF) |
| 134 | ("Old Italic" #x10300 #x1032F) |
| 135 | ("Gothic" #x10330 #x1034F) |
| 136 | ("Deseret" #x10400 #x1044F) |
| 137 | ("Byzantine Musical Symbols" #x1D000 #x1D0FF) |
| 138 | ("Musical Symbols" #x1D100 #x1D1FF) |
| 139 | ("Mathematical Alphanumeric Symbols" #x1D400 #x1D7FF) |
| 140 | ;;("CJK Unified Ideographs Extension B" #x20000 #x2A6DF) |
| 141 | ;;("CJK Compatibility Ideographs Supplement" #x2F800 #x2FA1F) |
| 142 | ("Tags" #xE0000 #xE007F) |
| 143 | ;;("Supplementary Private Use Area-A" #xF0000 #xFFFFF) |
| 144 | ;;("Supplementary Private Use Area-B" #x100000 #x10FFFF) |
| 145 | ) |
| 146 | "List of Unicode blocks. |
| 147 | For each block there is a list (NAME FIRST LAST), where |
| 148 | NAME is a string giving the official name of the block, |
| 149 | FIRST is the first code-point and LAST is the last code-point. |
| 150 | Blocks containing only characters with algorithmic names or no names |
| 151 | are omitted.") |
| 152 | |
| 153 | (defun nxml-unicode-block-char-name-set (name) |
| 154 | "Return a symbol for a block whose official Unicode name is NAME. |
| 155 | The symbol is generated by downcasing and replacing each space |
| 156 | by a hyphen." |
| 157 | (intern (replace-regexp-in-string " " "-" (downcase name)))) |
| 158 | |
| 159 | ;; This is intended to be a superset of the coverage |
| 160 | ;; of existing standard entity sets. |
| 161 | (defvar nxml-enabled-unicode-blocks-default |
| 162 | '(basic-latin |
| 163 | latin-1-supplement |
| 164 | latin-extended-a |
| 165 | latin-extended-b |
| 166 | ipa-extensions |
| 167 | spacing-modifier-letters |
| 168 | combining-diacritical-marks |
| 169 | greek-and-coptic |
| 170 | cyrillic |
| 171 | general-punctuation |
| 172 | superscripts-and-subscripts |
| 173 | currency-symbols |
| 174 | combining-diacritical-marks-for-symbols |
| 175 | letterlike-symbols |
| 176 | number-forms |
| 177 | arrows |
| 178 | mathematical-operators |
| 179 | miscellaneous-technical |
| 180 | control-pictures |
| 181 | optical-character-recognition |
| 182 | enclosed-alphanumerics |
| 183 | box-drawing |
| 184 | block-elements |
| 185 | geometric-shapes |
| 186 | miscellaneous-symbols |
| 187 | dingbats |
| 188 | miscellaneous-mathematical-symbols-a |
| 189 | supplemental-arrows-a |
| 190 | supplemental-arrows-b |
| 191 | miscellaneous-mathematical-symbols-b |
| 192 | supplemental-mathematical-operators |
| 193 | cjk-symbols-and-punctuation |
| 194 | alphabetic-presentation-forms |
| 195 | variation-selectors |
| 196 | small-form-variants |
| 197 | specials |
| 198 | mathematical-alphanumeric-symbols) |
| 199 | "Default value for `nxml-enabled-unicode-blocks'.") |
| 200 | |
| 201 | (mapc (lambda (block) |
| 202 | (nxml-autoload-char-name-set |
| 203 | (nxml-unicode-block-char-name-set (car block)) |
| 204 | (expand-file-name |
| 205 | (format "nxml/%05X-%05X" |
| 206 | (nth 1 block) |
| 207 | (nth 2 block)) |
| 208 | data-directory))) |
| 209 | nxml-unicode-blocks) |
| 210 | |
| 211 | ;; Internal flag to control whether customize reloads the character tables. |
| 212 | ;; Should be set the first time the |
| 213 | (defvar nxml-internal-unicode-char-name-sets-enabled nil) |
| 214 | |
| 215 | (defcustom nxml-enabled-unicode-blocks nxml-enabled-unicode-blocks-default |
| 216 | "List of Unicode blocks for which Unicode character names are enabled. |
| 217 | Each block is identified by a symbol derived from the name |
| 218 | of the block by downcasing and replacing each space by a hyphen." |
| 219 | :group 'nxml |
| 220 | :set (lambda (sym value) |
| 221 | (set-default 'nxml-enabled-unicode-blocks value) |
| 222 | (when nxml-internal-unicode-char-name-sets-enabled |
| 223 | (nxml-enable-unicode-char-name-sets))) |
| 224 | :type (cons 'set |
| 225 | (mapcar (lambda (block) |
| 226 | `(const :tag ,(format "%s (%04X-%04X)" |
| 227 | (nth 0 block) |
| 228 | (nth 1 block) |
| 229 | (nth 2 block)) |
| 230 | ,(nxml-unicode-block-char-name-set |
| 231 | (nth 0 block)))) |
| 232 | nxml-unicode-blocks))) |
| 233 | |
| 234 | ;;;###autoload |
| 235 | (defun nxml-enable-unicode-char-name-sets () |
| 236 | "Enable the use of Unicode standard names for characters. |
| 237 | The Unicode blocks for which names are enabled is controlled by |
| 238 | the variable `nxml-enabled-unicode-blocks'." |
| 239 | (interactive) |
| 240 | (setq nxml-internal-unicode-char-name-sets-enabled t) |
| 241 | (mapc (lambda (block) |
| 242 | (nxml-disable-char-name-set |
| 243 | (nxml-unicode-block-char-name-set (car block)))) |
| 244 | nxml-unicode-blocks) |
| 245 | (mapc (lambda (nameset) |
| 246 | (nxml-enable-char-name-set nameset)) |
| 247 | nxml-enabled-unicode-blocks)) |
| 248 | |
| 249 | (provide 'nxml-uchnm) |
| 250 | |
| 251 | ;;; nxml-uchnm.el ends here |