annotate lisp/international/ucs-normalize.el @ 104343:396aecca2f45

(ucs-normalize-hfs-nfd-post-read-conversion): Remove unused var `buffer-modified-p'.
author Stefan Monnier <monnier@iro.umontreal.ca>
date Tue, 18 Aug 2009 19:17:22 +0000
parents 4d1464dfdc96
children fc0ed6b4a2b2
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
104250
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1 ;;; ucs-normalize.el --- Unicode normalization NFC/NFD/NFKD/NFKC
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
2
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
3 ;; Copyright (C) 2009
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
4 ;; Free Software Foundation, Inc.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
5
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
6 ;; Author: Taichi Kawabata <kawabata.taichi@gmail.com>
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
7 ;; Keywords: unicode, normalization
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
8
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
9 ;; This file is part of GNU Emacs.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
10
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
11 ;; GNU Emacs is free software: you can redistribute it and/or modify
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
12 ;; it under the terms of the GNU General Public License as published by
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
13 ;; the Free Software Foundation, either version 3 of the License, or
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
14 ;; (at your option) any later version.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
15
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
16 ;; GNU Emacs is distributed in the hope that it will be useful,
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
17 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
19 ;; GNU General Public License for more details.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
20
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
21 ;; You should have received a copy of the GNU General Public License
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
22 ;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
23
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
24 ;;; Commentary:
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
25 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
26 ;; This program has passed the NormalizationTest-5.1.0.txt.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
27 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
28 ;; References:
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
29 ;; http://www.unicode.org/reports/tr15/
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
30 ;; http://www.unicode.org/review/pr-29.html
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
31 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
32 ;; HFS-Normalization:
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
33 ;; Reference:
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
34 ;; http://developer.apple.com/technotes/tn/tn1150.html
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
35 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
36 ;; HFS Normalization excludes following area for decomposition.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
37 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
38 ;; U+02000 .. U+02FFF :: Punctuation, symbols, dingbats, arrows, etc.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
39 ;; (Characters in this region will be composed.)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
40 ;; U+0F900 .. U+0FAFF :: CJK compatibility Ideographs.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
41 ;; U+2F800 .. U+2FFFF :: CJK compatibility Ideographs.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
42 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
43 ;; HFS-Normalization is useful for normalizing text involving CJK Ideographs.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
44 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
45 ;;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
46 ;;; Implementation Notes on NFC/HFS-NFC.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
47 ;;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
48 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
49 ;; <Stages> Decomposition Composition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
50 ;; NFD: 'nfd nil
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
51 ;; NFC: 'nfd t
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
52 ;; NFKD: 'nfkd nil
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
53 ;; NFKC: 'nfkd t
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
54 ;; HFS-NFD: 'hfs-nfd 'hfs-nfd-comp-p
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
55 ;; HFS-NFC: 'hfs-nfd t
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
56 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
57 ;; Algorithm for Normalization
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
58 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
59 ;; Before normalization, following data will be prepared.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
60 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
61 ;; 1. quick-check-list
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
62 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
63 ;; `quick-check-list' consists of characters that will be decomposed
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
64 ;; during normalization. It includes composition-exclusions,
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
65 ;; singletons, non-starter-decompositions and decomposable
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
66 ;; characters.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
67 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
68 ;; `quick-check-regexp' will search the above characters plus
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
69 ;; combining characters.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
70 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
71 ;; 2. decomposition-translation
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
72 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
73 ;; `decomposition-translation' is a translation table that will be
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
74 ;; used to decompose the characters.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
75 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
76 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
77 ;; Normalization Process
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
78 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
79 ;; A. Searching (`ucs-normalize-region')
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
80 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
81 ;; Region is searched for `quick-check-regexp' to find possibly
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
82 ;; normalizable point.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
83 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
84 ;; B. Identification of Normalization Block
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
85 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
86 ;; (1) start of the block
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
87 ;; If the searched character is a starter and not combining
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
88 ;; with previous character, then the beginning of the block is
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
89 ;; the searched character. If searched character is combining
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
90 ;; character, then previous character will be the target
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
91 ;; character
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
92 ;; (2) end of the block
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
93 ;; Block ends at non-composable starter character.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
94 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
95 ;; C. Decomposition (`ucs-normalize-block')
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
96 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
97 ;; The entire block will be decomposed by
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
98 ;; `decomposition-translation' table.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
99 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
100 ;; D. Sorting and Composition of Smaller Blocks (`ucs-normalize-block-compose-chars')
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
101 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
102 ;; The block will be split to multiple samller blocks by starter
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
103 ;; charcters. Each block is sorted, and composed if necessary.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
104 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
105 ;; E. Composition of Entire Block (`ucs-normalize-compose-chars')
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
106 ;;
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
107 ;; Composed blocks are collected and again composed.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
108
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
109 ;;; Code:
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
110
104328
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
111 (defconst ucs-normalize-version "1.1")
104250
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
112
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
113 (eval-when-compile (require 'cl))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
114
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
115 (eval-when-compile
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
116
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
117 (defconst ucs-normalize-composition-exclusions
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
118 '(#x0958 #x0959 #x095A #x095B #x095C #x095D #x095E #x095F
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
119 #x09DC #x09DD #x09DF #x0A33 #x0A36 #x0A59 #x0A5A #x0A5B
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
120 #x0A5E #x0B5C #x0B5D #x0F43 #x0F4D #x0F52 #x0F57 #x0F5C
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
121 #x0F69 #x0F76 #x0F78 #x0F93 #x0F9D #x0FA2 #x0FA7 #x0FAC
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
122 #x0FB9 #xFB1D #xFB1F #xFB2A #xFB2B #xFB2C #xFB2D #xFB2E
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
123 #xFB2F #xFB30 #xFB31 #xFB32 #xFB33 #xFB34 #xFB35 #xFB36
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
124 #xFB38 #xFB39 #xFB3A #xFB3B #xFB3C #xFB3E #xFB40 #xFB41
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
125 #xFB43 #xFB44 #xFB46 #xFB47 #xFB48 #xFB49 #xFB4A #xFB4B
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
126 #xFB4C #xFB4D #xFB4E #x2ADC #x1D15E #x1D15F #x1D160 #x1D161
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
127 #x1D162 #x1D163 #x1D164 #x1D1BB #x1D1BC #x1D1BD #x1D1BE
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
128 #x1D1BF #x1D1C0)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
129 "Composition Exclusion List.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
130 This list is taken from
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
131 http://www.unicode.org/Public/UNIDATA/CompositionExclusions-5.1.0.txt")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
132
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
133 ;; Unicode ranges that decompositions & combinings are defined.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
134 (defvar check-range nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
135 (setq check-range '((#x00a0 . #x3400) (#xA600 . #xAC00) (#xF900 . #x10fff) (#x1d000 . #x1dfff) (#x2f800 . #x2faff)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
136
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
137 ;; Basic normalization functions
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
138 (defun nfd (char)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
139 (let ((decomposition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
140 (get-char-code-property char 'decomposition)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
141 (if (and decomposition (numberp (car decomposition)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
142 decomposition)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
143
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
144 (defun nfkd (char)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
145 (let ((decomposition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
146 (get-char-code-property char 'decomposition)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
147 (if (symbolp (car decomposition)) (cdr decomposition)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
148 decomposition)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
149
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
150 (defun hfs-nfd (char)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
151 (when (or (and (>= char 0) (< char #x2000))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
152 (and (>= char #x3000) (< char #xf900))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
153 (and (>= char #xfb00) (< char #x2f800))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
154 (>= char #x30000))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
155 (nfd char))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
156
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
157 (eval-and-compile
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
158 (defun ucs-normalize-hfs-nfd-comp-p (char)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
159 (and (>= char #x2000) (< char #x3000)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
160
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
161 (defsubst ucs-normalize-ccc (char)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
162 (get-char-code-property char 'canonical-combining-class))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
163 )
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
164
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
165 ;; Data common to all normalizations
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
166
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
167 (eval-when-compile
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
168
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
169 (defvar combining-chars nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
170 (setq combining-chars nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
171 (defvar decomposition-pair-to-composition nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
172 (setq decomposition-pair-to-composition nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
173 (defvar non-starter-decompositions nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
174 (setq non-starter-decompositions nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
175 (let ((char 0) ccc decomposition)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
176 (mapc
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
177 (lambda (start-end)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
178 (do ((char (car start-end) (+ char 1))) ((> char (cdr start-end)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
179 (setq ccc (ucs-normalize-ccc char))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
180 (setq decomposition (get-char-code-property
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
181 char 'decomposition))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
182 (if (and ccc (/= 0 ccc)) (add-to-list 'combining-chars char))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
183 (if (and (numberp (car decomposition))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
184 (/= (ucs-normalize-ccc (car decomposition))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
185 0))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
186 (add-to-list 'non-starter-decompositions char))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
187 (when (numberp (car decomposition))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
188 (if (and (= 2 (length decomposition))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
189 (null (memq char ucs-normalize-composition-exclusions))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
190 (null (memq char non-starter-decompositions)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
191 (setq decomposition-pair-to-composition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
192 (cons (cons decomposition char)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
193 decomposition-pair-to-composition)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
194 ;; If not singleton decomposition, second and later characters in
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
195 ;; decomposition will be the subject of combining characters.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
196 (if (cdr decomposition)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
197 (dolist (char (cdr decomposition))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
198 (add-to-list 'combining-chars char))))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
199 check-range))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
200
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
201 (setq combining-chars
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
202 (append combining-chars
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
203 '(?ᅡ ?ᅢ ?ᅣ ?ᅤ ?ᅥ ?ᅦ ?ᅧ ?ᅨ ?ᅩ ?ᅪ
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
204 ?ᅫ ?ᅬ ?ᅭ ?ᅮ ?ᅯ ?ᅰ ?ᅱ ?ᅲ ?ᅳ ?ᅴ ?ᅵ
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
205 ?ᆨ ?ᆩ ?ᆪ ?ᆫ ?ᆬ ?ᆭ ?ᆮ ?ᆯ ?ᆰ ?ᆱ ?ᆲ ?ᆳ ?ᆴ
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
206 ?ᆵ ?ᆶ ?ᆷ ?ᆸ ?ᆹ ?ᆺ ?ᆻ ?ᆼ ?ᆽ ?ᆾ ?ᆿ ?ᇀ ?ᇁ ?ᇂ)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
207 )
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
208
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
209 (eval-and-compile
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
210 (defun ucs-normalize-make-hash-table-from-alist (alist)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
211 (let ((table (make-hash-table :test 'equal :size 2000)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
212 (mapc (lambda (x) (puthash (car x) (cdr x) table)) alist)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
213 table))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
214
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
215 (defvar ucs-normalize-decomposition-pair-to-primary-composite nil
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
216 "Hashtable of decomposed pair to primary composite.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
217 Note that Hangul are excluded.")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
218 (setq ucs-normalize-decomposition-pair-to-primary-composite
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
219 (ucs-normalize-make-hash-table-from-alist
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
220 (eval-when-compile decomposition-pair-to-composition)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
221
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
222 (defun ucs-normalize-primary-composite (decomposition-pair composition-predicate)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
223 "Convert DECOMPOSITION-PAIR to primay composite using COMPOSITION-PREDICATE."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
224 (let ((char (or (gethash decomposition-pair
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
225 ucs-normalize-decomposition-pair-to-primary-composite)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
226 (and (<= #x1100 (car decomposition-pair))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
227 (< (car decomposition-pair) #x1113)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
228 (<= #x1161 (cadr decomposition-pair))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
229 (< (car decomposition-pair) #x1176)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
230 (let ((lindex (- (car decomposition-pair) #x1100))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
231 (vindex (- (cadr decomposition-pair) #x1161)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
232 (+ #xAC00 (* (+ (* lindex 21) vindex) 28))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
233 (and (<= #xac00 (car decomposition-pair))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
234 (< (car decomposition-pair) #xd7a4)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
235 (<= #x11a7 (cadr decomposition-pair))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
236 (< (cadr decomposition-pair) #x11c3)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
237 (= 0 (% (- (car decomposition-pair) #xac00) 28))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
238 (let ((tindex (- (cadr decomposition-pair) #x11a7)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
239 (+ (car decomposition-pair) tindex))))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
240 (if (and char
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
241 (functionp composition-predicate)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
242 (null (funcall composition-predicate char)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
243 nil char)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
244 )
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
245
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
246 (defvar ucs-normalize-combining-chars nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
247 (setq ucs-normalize-combining-chars (eval-when-compile combining-chars))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
248
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
249 (defvar ucs-normalize-combining-chars-regexp nil
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
250 "Regular expression to match sequence of combining characters.")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
251 (setq ucs-normalize-combining-chars-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
252 (eval-when-compile (concat (regexp-opt (mapcar 'char-to-string combining-chars)) "+")))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
253
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
254 (eval-when-compile
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
255
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
256 (defun decomposition-translation-alist (decomposition-function)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
257 (let (decomposition alist)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
258 (mapc
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
259 (lambda (start-end)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
260 (do ((char (car start-end) (+ char 1))) ((> char (cdr start-end)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
261 (setq decomposition (funcall decomposition-function char))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
262 (if decomposition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
263 (setq alist (cons (cons char
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
264 (apply 'append
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
265 (mapcar (lambda (x)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
266 (decomposition-char-recursively
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
267 x decomposition-function))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
268 decomposition)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
269 alist)))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
270 check-range)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
271 alist))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
272
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
273 (defun decomposition-char-recursively (char decomposition-function)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
274 (let ((decomposition (funcall decomposition-function char)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
275 (if decomposition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
276 (apply 'append
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
277 (mapcar (lambda (x)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
278 (decomposition-char-recursively x decomposition-function))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
279 decomposition))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
280 (list char))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
281
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
282 (defun alist-list-to-vector (alist)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
283 (mapcar (lambda (x) (cons (car x) (apply 'vector (cdr x)))) alist))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
284
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
285 (defvar nfd-alist nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
286 (setq nfd-alist (alist-list-to-vector (decomposition-translation-alist 'nfd)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
287 (defvar nfkd-alist nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
288 (setq nfkd-alist (alist-list-to-vector (decomposition-translation-alist 'nfkd)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
289 (defvar hfs-nfd-alist nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
290 (setq hfs-nfd-alist (alist-list-to-vector (decomposition-translation-alist 'hfs-nfd)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
291 )
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
292
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
293 (eval-and-compile
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
294 (defvar ucs-normalize-hangul-translation-alist nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
295 (setq ucs-normalize-hangul-translation-alist
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
296 (let ((i 0) entries)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
297 (while (< i 11172)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
298 (setq entries
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
299 (cons (cons (+ #xac00 i)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
300 (if (= 0 (% i 28))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
301 (vector (+ #x1100 (/ i 588))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
302 (+ #x1161 (/ (% i 588) 28)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
303 (vector (+ #x1100 (/ i 588))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
304 (+ #x1161 (/ (% i 588) 28))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
305 (+ #x11a7 (% i 28)))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
306 entries)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
307 i (1+ i))) entries))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
308
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
309 (defun ucs-normalize-make-translation-table-from-alist (alist)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
310 (make-translation-table-from-alist
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
311 (append alist ucs-normalize-hangul-translation-alist)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
312
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
313 (define-translation-table 'ucs-normalize-nfd-table
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
314 (ucs-normalize-make-translation-table-from-alist (eval-when-compile nfd-alist)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
315 (define-translation-table 'ucs-normalize-nfkd-table
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
316 (ucs-normalize-make-translation-table-from-alist (eval-when-compile nfkd-alist)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
317 (define-translation-table 'ucs-normalize-hfs-nfd-table
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
318 (ucs-normalize-make-translation-table-from-alist (eval-when-compile hfs-nfd-alist)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
319
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
320 (defun ucs-normalize-sort (chars)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
321 "Sort by canonical combining class of chars."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
322 (sort chars
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
323 (lambda (ch1 ch2)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
324 (< (ucs-normalize-ccc ch1) (ucs-normalize-ccc ch2)))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
325
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
326 (defun ucs-normalize-compose-chars (chars composition-predicate)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
327 "Compose CHARS by COMPOSITION-PREDICATE.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
328 CHARS must be sorted and normalized in starter-combining pairs."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
329 (if composition-predicate
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
330 (let* ((starter (car chars))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
331 remain result prev-ccc
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
332 (target-chars (cdr chars))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
333 target target-ccc
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
334 primary-composite)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
335 (while target-chars
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
336 (setq target (car target-chars)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
337 target-ccc (ucs-normalize-ccc target))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
338 (if (and (or (null prev-ccc)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
339 (< prev-ccc target-ccc))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
340 (setq primary-composite
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
341 (ucs-normalize-primary-composite (list starter target)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
342 composition-predicate)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
343 ;; case 1: composable
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
344 (setq starter primary-composite
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
345 prev-ccc nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
346 (if (= 0 target-ccc)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
347 ;; case 2: move starter
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
348 (setq result (nconc result (cons starter (nreverse remain)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
349 starter target
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
350 remain nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
351 ;; case 3: move target
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
352 (setq prev-ccc target-ccc
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
353 remain (cons target remain))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
354 (setq target-chars (cdr target-chars)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
355 (nconc result (cons starter (nreverse remain))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
356 chars))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
357
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
358 (defun ucs-normalize-block-compose-chars (chars composition-predicate)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
359 "Try composing CHARS by COMPOSITION-PREDICATE.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
360 If COMPOSITION-PREDICATE is not given, then do nothing."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
361 (let ((chars (ucs-normalize-sort chars)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
362 (if composition-predicate
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
363 (ucs-normalize-compose-chars chars composition-predicate)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
364 chars)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
365 )
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
366
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
367 (eval-when-compile
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
368
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
369 (defun quick-check-list (decomposition-translation
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
370 &optional composition-predicate)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
371 "Quick-Check List for DECOMPOSITION-TRANSLATION and COMPOSITION-PREDICATE.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
372 It includes Singletons, CompositionExclusions, and Non-Starter
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
373 decomposition. "
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
374 (let (entries decomposition composition)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
375 (mapc
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
376 (lambda (start-end)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
377 (do ((i (car start-end) (+ i 1))) ((> i (cdr start-end)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
378 (setq decomposition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
379 (string-to-list
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
380 (with-temp-buffer
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
381 (insert i)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
382 (translate-region 1 2 decomposition-translation)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
383 (buffer-string))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
384 (setq composition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
385 (ucs-normalize-block-compose-chars decomposition composition-predicate))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
386 (when (not (equal composition (list i)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
387 (setq entries (cons i entries)))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
388 check-range)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
389 ;;(remove-duplicates
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
390 (append entries
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
391 ucs-normalize-composition-exclusions
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
392 non-starter-decompositions)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
393 ;;)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
394
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
395 (defvar nfd-quick-check-list nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
396 (setq nfd-quick-check-list (quick-check-list 'ucs-normalize-nfd-table ))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
397 (defvar nfc-quick-check-list nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
398 (setq nfc-quick-check-list (quick-check-list 'ucs-normalize-nfd-table t ))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
399 (defvar nfkd-quick-check-list nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
400 (setq nfkd-quick-check-list (quick-check-list 'ucs-normalize-nfkd-table ))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
401 (defvar nfkc-quick-check-list nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
402 (setq nfkc-quick-check-list (quick-check-list 'ucs-normalize-nfkd-table t ))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
403 (defvar hfs-nfd-quick-check-list nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
404 (setq hfs-nfd-quick-check-list (quick-check-list 'ucs-normalize-hfs-nfd-table
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
405 'ucs-normalize-hfs-nfd-comp-p))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
406 (defvar hfs-nfc-quick-check-list nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
407 (setq hfs-nfc-quick-check-list (quick-check-list 'ucs-normalize-hfs-nfd-table t ))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
408
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
409 (defun quick-check-list-to-regexp (quick-check-list)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
410 (regexp-opt (mapcar 'char-to-string (append quick-check-list combining-chars))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
411
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
412 (defun quick-check-decomposition-list-to-regexp (quick-check-list)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
413 (concat (quick-check-list-to-regexp quick-check-list) "\\|[가-힣]"))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
414
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
415 (defun quick-check-composition-list-to-regexp (quick-check-list)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
416 (concat (quick-check-list-to-regexp quick-check-list) "\\|[ᅡ-ᅵᆨ-ᇂ]"))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
417 )
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
418
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
419
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
420 ;; NFD/NFC
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
421 (defvar ucs-normalize-nfd-quick-check-regexp nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
422 (setq ucs-normalize-nfd-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
423 (eval-when-compile (quick-check-decomposition-list-to-regexp nfd-quick-check-list)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
424 (defvar ucs-normalize-nfc-quick-check-regexp nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
425 (setq ucs-normalize-nfc-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
426 (eval-when-compile (quick-check-composition-list-to-regexp nfc-quick-check-list)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
427
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
428 ;; NFKD/NFKC
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
429 (defvar ucs-normalize-nfkd-quick-check-regexp nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
430 (setq ucs-normalize-nfkd-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
431 (eval-when-compile (quick-check-decomposition-list-to-regexp nfkd-quick-check-list)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
432 (defvar ucs-normalize-nfkc-quick-check-regexp nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
433 (setq ucs-normalize-nfkc-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
434 (eval-when-compile (quick-check-composition-list-to-regexp nfkc-quick-check-list)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
435
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
436 ;; HFS-NFD/HFS-NFC
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
437 (defvar ucs-normalize-hfs-nfd-quick-check-regexp nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
438 (setq ucs-normalize-hfs-nfd-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
439 (eval-when-compile (concat (quick-check-decomposition-list-to-regexp hfs-nfd-quick-check-list))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
440 (defvar ucs-normalize-hfs-nfc-quick-check-regexp nil)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
441 (setq ucs-normalize-hfs-nfc-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
442 (eval-when-compile (quick-check-composition-list-to-regexp hfs-nfc-quick-check-list)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
443
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
444 ;;------------------------------------------------------------------------------------------
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
445
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
446 ;; Normalize local region.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
447
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
448 (defun ucs-normalize-block
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
449 (from to &optional decomposition-translation-table composition-predicate)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
450 "Normalize region FROM TO, by sorting the region with canonical-cc.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
451 If DECOMPOSITION-TRANSLATION-TABLE is given, translate region
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
452 before sorting. If COMPOSITION-PREDICATE is given, then compose
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
453 the region by using it."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
454 (save-restriction
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
455 (narrow-to-region from to)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
456 (goto-char (point-min))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
457 (if decomposition-translation-table
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
458 (translate-region from to decomposition-translation-table))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
459 (goto-char (point-min))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
460 (let ((start (point)) chars); ccc)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
461 (while (not (eobp))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
462 (forward-char)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
463 (when (or (eobp)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
464 (= 0 (ucs-normalize-ccc (char-after (point)))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
465 (setq chars
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
466 (nconc chars
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
467 (ucs-normalize-block-compose-chars
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
468 (string-to-list (buffer-substring start (point)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
469 composition-predicate))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
470 start (point)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
471 ;;(unless ccc (error "Undefined character can not be normalized!"))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
472 )
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
473 (delete-region (point-min) (point-max))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
474 (apply 'insert
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
475 (ucs-normalize-compose-chars
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
476 chars composition-predicate)))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
477
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
478 (defun ucs-normalize-region
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
479 (from to quick-check-regexp translation-table composition-predicate)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
480 "Normalize region from FROM to TO.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
481 QUICK-CHECK-REGEXP is applied for searching the region.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
482 TRANSLATION-TABLE will be used to decompose region.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
483 COMPOSITION-PREDICATE will be used to compose region."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
484 (save-excursion
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
485 (save-restriction
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
486 (narrow-to-region from to)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
487 (goto-char (point-min))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
488 (let (start-pos starter)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
489 (while (re-search-forward quick-check-regexp nil t)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
490 (setq starter (string-to-char (match-string 0)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
491 (setq start-pos (match-beginning 0))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
492 (ucs-normalize-block
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
493 ;; from
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
494 (if (or (= start-pos (point-min))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
495 (and (= 0 (ucs-normalize-ccc starter))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
496 (not (memq starter ucs-normalize-combining-chars))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
497 start-pos (1- start-pos))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
498 ;; to
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
499 (if (looking-at ucs-normalize-combining-chars-regexp)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
500 (match-end 0) (1+ start-pos))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
501 translation-table composition-predicate))))))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
502
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
503 ;; --------------------------------------------------------------------------------
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
504
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
505 (defmacro ucs-normalize-string (ucs-normalize-region)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
506 `(with-temp-buffer
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
507 (insert str)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
508 (,ucs-normalize-region (point-min) (point-max))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
509 (buffer-string)))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
510
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
511 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
512 (defun ucs-normalize-NFD-region (from to)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
513 "Normalize the current region by the Unicode NFD."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
514 (interactive "r")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
515 (ucs-normalize-region from to
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
516 ucs-normalize-nfd-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
517 'ucs-normalize-nfd-table nil))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
518 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
519 (defun ucs-normalize-NFD-string (str)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
520 "Normalize the string STR by the Unicode NFD."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
521 (ucs-normalize-string ucs-normalize-NFD-region))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
522
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
523 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
524 (defun ucs-normalize-NFC-region (from to)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
525 "Normalize the current region by the Unicode NFC."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
526 (interactive "r")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
527 (ucs-normalize-region from to
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
528 ucs-normalize-nfc-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
529 'ucs-normalize-nfd-table t))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
530 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
531 (defun ucs-normalize-NFC-string (str)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
532 "Normalize the string STR by the Unicode NFC."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
533 (ucs-normalize-string ucs-normalize-NFC-region))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
534
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
535 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
536 (defun ucs-normalize-NFKD-region (from to)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
537 "Normalize the current region by the Unicode NFKD."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
538 (interactive "r")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
539 (ucs-normalize-region from to
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
540 ucs-normalize-nfkd-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
541 'ucs-normalize-nfkd-table nil))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
542 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
543 (defun ucs-normalize-NFKD-string (str)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
544 "Normalize the string STR by the Unicode NFKD."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
545 (ucs-normalize-string ucs-normalize-NFKD-region))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
546
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
547 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
548 (defun ucs-normalize-NFKC-region (from to)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
549 "Normalize the current region by the Unicode NFKC."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
550 (interactive "r")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
551 (ucs-normalize-region from to
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
552 ucs-normalize-nfkc-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
553 'ucs-normalize-nfkd-table t))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
554 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
555 (defun ucs-normalize-NFKC-string (str)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
556 "Normalize the string STR by the Unicode NFKC."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
557 (ucs-normalize-string ucs-normalize-NFKC-region))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
558
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
559 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
560 (defun ucs-normalize-HFS-NFD-region (from to)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
561 "Normalize the current region by the Unicode NFD and Mac OS's HFS Plus."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
562 (interactive "r")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
563 (ucs-normalize-region from to
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
564 ucs-normalize-hfs-nfd-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
565 'ucs-normalize-hfs-nfd-table
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
566 'ucs-normalize-hfs-nfd-comp-p))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
567 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
568 (defun ucs-normalize-HFS-NFD-string (str)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
569 "Normalize the string STR by the Unicode NFD and Mac OS's HFS Plus."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
570 (ucs-normalize-string ucs-normalize-HFS-NFD-region))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
571 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
572 (defun ucs-normalize-HFS-NFC-region (from to)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
573 "Normalize the current region by the Unicode NFC and Mac OS's HFS Plus."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
574 (interactive "r")
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
575 (ucs-normalize-region from to
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
576 ucs-normalize-hfs-nfc-quick-check-regexp
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
577 'ucs-normalize-hfs-nfd-table t))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
578 ;;;###autoload
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
579 (defun ucs-normalize-HFS-NFC-string (str)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
580 "Normalize the string STR by the Unicode NFC and Mac OS's HFS Plus."
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
581 (ucs-normalize-string ucs-normalize-HFS-NFC-region))
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
582
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
583 ;; Post-read-conversion function for `utf-8-hfs'.
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
584 (defun ucs-normalize-hfs-nfd-post-read-conversion (len)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
585 (save-excursion
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
586 (save-restriction
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
587 (narrow-to-region (point) (+ (point) len))
104343
396aecca2f45 (ucs-normalize-hfs-nfd-post-read-conversion):
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 104328
diff changeset
588 (ucs-normalize-HFS-NFC-region (point-min) (point-max))
396aecca2f45 (ucs-normalize-hfs-nfd-post-read-conversion):
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 104328
diff changeset
589 (- (point-max) (point-min)))))
104250
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
590
104328
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
591 ;; Pre-write conversion for `utf-8-hfs'.
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
592 (defun ucs-normalize-hfs-nfd-pre-write-conversion (from to)
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
593 (let ((old-buf (current-buffer)))
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
594 (set-buffer (generate-new-buffer " *temp*"))
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
595 (if (stringp from)
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
596 (insert from)
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
597 (insert-buffer-substring old-buf from to))
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
598 (ucs-normalize-HFS-NFD-region (point-min) (point-max))
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
599 nil))
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
600
104250
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
601 ;;; coding-system definition
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
602 (define-coding-system 'utf-8-hfs
104328
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
603 "UTF-8 based coding system for MacOS HFS file names.
104250
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
604 The singleton characters in HFS normalization exclusion will not
104328
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
605 be decomposed."
104250
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
606 :coding-type 'utf-8
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
607 :mnemonic ?U
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
608 :charset-list '(unicode)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
609 :post-read-conversion 'ucs-normalize-hfs-nfd-post-read-conversion
104328
4d1464dfdc96 (ucs-normalize-version): Changed to 1.1.
Kenichi Handa <handa@m17n.org>
parents: 104269
diff changeset
610 :pre-write-conversion 'ucs-normalize-hfs-nfd-pre-write-conversion
104250
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
611 )
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
612
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
613 (provide 'ucs-normalize)
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
614
104269
b086ab13a67a Add a `coding' file variable.
Eli Zaretskii <eliz@gnu.org>
parents: 104264
diff changeset
615 ;; Local Variables:
b086ab13a67a Add a `coding' file variable.
Eli Zaretskii <eliz@gnu.org>
parents: 104264
diff changeset
616 ;; coding: utf-8
b086ab13a67a Add a `coding' file variable.
Eli Zaretskii <eliz@gnu.org>
parents: 104264
diff changeset
617 ;; End:
b086ab13a67a Add a `coding' file variable.
Eli Zaretskii <eliz@gnu.org>
parents: 104264
diff changeset
618
104264
be5412b66c92 Add arch tagline
Miles Bader <miles@gnu.org>
parents: 104250
diff changeset
619 ;; arch-tag: cef65ae7-71ad-4e19-8da8-56ab4d42aaa4
104250
a6cdfcf4b769 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
620 ;;; ucs-normalize.el ends here