author | Jan Vrany <jan.vrany@fit.cvut.cz> |
Wed, 19 Aug 2009 17:14:36 +0100 | |
branch | jv |
changeset 17728 | bbc5fa73dfab |
parent 17711 | 39faaaf888b4 |
child 17845 | 7e0cfaac936d |
permissions | -rw-r--r-- |
8148 | 1 |
" |
2 |
COPYRIGHT (c) 2004 by eXept Software AG |
|
3 |
All Rights Reserved |
|
4 |
||
5 |
This software is furnished under a license and may be used |
|
6 |
only in accordance with the terms of that license and with the |
|
7 |
inclusion of the above copyright notice. This software may not |
|
8 |
be provided or otherwise made available to, or used by, any |
|
9 |
other person. No title to or ownership of the software is |
|
10 |
hereby transferred. |
|
11 |
" |
|
12 |
||
8081 | 13 |
"{ Package: 'stx:libbasic' }" |
14 |
||
15 |
"{ NameSpace: CharacterEncoderImplementations }" |
|
16 |
||
17 |
SingleByteEncoder subclass:#MAC_Arabic |
|
18 |
instanceVariableNames:'' |
|
19 |
classVariableNames:'' |
|
20 |
poolDictionaries:'' |
|
21 |
category:'Collections-Text-Encodings' |
|
22 |
! |
|
23 |
||
8148 | 24 |
!MAC_Arabic class methodsFor:'documentation'! |
25 |
||
26 |
copyright |
|
27 |
" |
|
28 |
COPYRIGHT (c) 2004 by eXept Software AG |
|
29 |
All Rights Reserved |
|
30 |
||
31 |
This software is furnished under a license and may be used |
|
32 |
only in accordance with the terms of that license and with the |
|
33 |
inclusion of the above copyright notice. This software may not |
|
34 |
be provided or otherwise made available to, or used by, any |
|
35 |
other person. No title to or ownership of the software is |
|
36 |
hereby transferred. |
|
37 |
" |
|
38 |
! ! |
|
8081 | 39 |
|
40 |
!MAC_Arabic class methodsFor:'mapping'! |
|
41 |
||
42 |
mapFileURL1_relativePathName |
|
43 |
^ 'VENDORS/APPLE/ARABIC.TXT' |
|
44 |
! |
|
45 |
||
46 |
mapping |
|
47 |
" |
|
48 |
# From: http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/ARABIC.TXT |
|
49 |
||
50 |
#======================================================================= |
|
51 |
# File name: ARABIC.TXT |
|
52 |
# |
|
53 |
# Contents: Map (external version) from Mac OS Arabic |
|
54 |
# character set to Unicode 2.1 through Unicode 3.2. |
|
55 |
# |
|
56 |
# Copyright: (c) 1994-2002 by Apple Computer, Inc., all rights |
|
57 |
# reserved. |
|
58 |
# |
|
59 |
# Contact: charsets@apple.com |
|
60 |
# |
|
61 |
# Changes: |
|
62 |
# |
|
63 |
# b3,c1 2002-Dec-19 Add comments about character display and |
|
64 |
# direction overrides. Update URLs, notes. |
|
65 |
# Matches internal utom<b4>. |
|
66 |
# b02 1999-Sep-22 Update contact e-mail address. Matches |
|
67 |
# internal utom<b1>, ufrm<b1>, and Text |
|
68 |
# Encoding Converter version 1.5. |
|
69 |
# n10 1998-Feb-05 Show required Unicode character |
|
70 |
# directionality in a different way. Matches |
|
71 |
# internal utom<n4>, ufrm<n21>, and Text |
|
72 |
# Encoding Converter version 1.3. Update |
|
73 |
# header comments; include information on |
|
74 |
# loose mapping of digits. |
|
75 |
# n07 1997-Jul-17 Update to match internal utom<n2>, ufrm<n17>: |
|
76 |
# Change standard mapping for 0xC0 from U+066D |
|
77 |
# to U+274A. Add direction overrides to |
|
78 |
# mappings for 0x25, 0x2C, 0x3B, 0x3F. Add |
|
79 |
# information on variants. |
|
80 |
# n03 1995-Apr-18 First version (after fixing some typos). |
|
81 |
# Matches internal ufrm<n11>. |
|
82 |
# |
|
83 |
# Standard header: |
|
84 |
# ---------------- |
|
85 |
# |
|
86 |
# Apple, the Apple logo, and Macintosh are trademarks of Apple |
|
87 |
# Computer, Inc., registered in the United States and other countries. |
|
88 |
# Unicode is a trademark of Unicode Inc. For the sake of brevity, |
|
89 |
# throughout this document, 'Macintosh' can be used to refer to |
|
90 |
# Macintosh computers and 'Unicode' can be used to refer to the |
|
91 |
# Unicode standard. |
|
92 |
# |
|
93 |
# Apple makes no warranty or representation, either express or |
|
94 |
# implied, with respect to these tables, their quality, accuracy, or |
|
95 |
# fitness for a particular purpose. In no event will Apple be liable |
|
96 |
# for direct, indirect, special, incidental, or consequential damages |
|
97 |
# resulting from any defect or inaccuracy in this document or the |
|
98 |
# accompanying tables. |
|
99 |
# |
|
100 |
# These mapping tables and character lists are subject to change. |
|
101 |
# The latest tables should be available from the following: |
|
102 |
# |
|
103 |
# <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/> |
|
104 |
# |
|
105 |
# For general information about Mac OS encodings and these mapping |
|
106 |
# tables, see the file 'README.TXT'. |
|
107 |
# |
|
108 |
# Format: |
|
109 |
# ------- |
|
110 |
# |
|
111 |
# Three tab-separated columns; |
|
112 |
# '#' begins a comment which continues to the end of the line. |
|
113 |
# Column #1 is the Mac OS Arabic code (in hex as 0xNN). |
|
114 |
# Column #2 is the corresponding Unicode (in hex as 0xNNNN), |
|
115 |
# possibly preceded by a tag indicating required directionality |
|
116 |
# (i.e. <LR>+0xNNNN or <RL>+0xNNNN). |
|
117 |
# Column #3 is a comment containing the Unicode name. |
|
118 |
# |
|
119 |
# The entries are in Mac OS Arabic code order. |
|
120 |
# |
|
121 |
# Control character mappings are not shown in this table, following |
|
122 |
# the conventions of the standard UTC mapping tables. However, the |
|
123 |
# Mac OS Roman character set uses the standard control characters at |
|
124 |
# 0x00-0x1F and 0x7F. |
|
125 |
# |
|
126 |
# Notes on Mac OS Arabic: |
|
127 |
# ----------------------- |
|
128 |
# |
|
129 |
# 1. General |
|
130 |
# |
|
131 |
# The Mac OS Arabic character set is intended to cover Arabic as |
|
132 |
# used in North Africa, the Arabian peninsula, and the Levant. It |
|
133 |
# also contains several characters needed for Urdu and/or Farsi. |
|
134 |
# |
|
135 |
# The Mac OS Arabic character set is essentially a superset of ISO |
|
136 |
# 8859-6. The 8859-6 code points that are interpreted differently |
|
137 |
# in the Mac OS Arabic set are as follows: |
|
138 |
# 0xA0 is NO-BREAK SPACE in 8859-6 and right-left SPACE in Mac OS |
|
139 |
# Arabic; NO-BREAK is 0x81 in Mac OS Arabic. |
|
140 |
# 0xA4 is CURRENCY SIGN in 8859-6 and right-left DOLLAR SIGN in |
|
141 |
# Mac OS Arabic. |
|
142 |
# 0xAD is SOFT HYPHEN in 8859-6 and right-left HYPHEN-MINUS in |
|
143 |
# Mac OS Arabic. |
|
144 |
# ISO 8859-6 specifies that codes 0x30-0x39 can be rendered either |
|
145 |
# with European digit shapes or Arabic digit shapes. This is also |
|
146 |
# true in Mac OS Arabic, which determines from context which digit |
|
147 |
# shapes to use (see below). |
|
148 |
# |
|
149 |
# The Mac OS Arabic character set uses the C1 controls area and other |
|
150 |
# code points which are undefined in ISO 8859-6 for additional |
|
151 |
# graphic characters: additional Arabic letters for Farsi and Urdu, |
|
152 |
# some accented Roman letters for European languages (such as French), |
|
153 |
# and duplicates of some of the punctuation, symbols, and digits in |
|
154 |
# the ASCII block. The duplicate punctuation, symbol, and digit |
|
155 |
# characters have right-left directionality, while the ASCII versions |
|
156 |
# have left-right directionality. See the next section for more |
|
157 |
# information on this. |
|
158 |
# |
|
159 |
# Mac OS Arabic characters 0xEB-0xF2 are non-spacing/combining marks. |
|
160 |
# |
|
161 |
# 2. Directional characters and roundtrip fidelity |
|
162 |
# |
|
163 |
# The Mac OS Arabic character set was developed in 1986-1987. At that |
|
164 |
# time the bidirectional line layout algorithm used in the Mac OS |
|
165 |
# Arabic system was fairly simple; it used only a few direction |
|
166 |
# classes (instead of the 19 now used in the Unicode bidirectional |
|
167 |
# algorithm). In order to permit users to handle some tricky layout |
|
168 |
# problems, certain punctuation and symbol characters were encoded |
|
169 |
# twice, one with a left-right direction attribute and the other with |
|
170 |
# a right-left direction attribute. |
|
171 |
# |
|
172 |
# For example, plus sign is encoded at 0x2B with a left-right |
|
173 |
# attribute, and at 0xAB with a right-left attribute. However, there |
|
174 |
# is only one PLUS SIGN character in Unicode. This leads to some |
|
175 |
# interesting problems when mapping between Mac OS Arabic and Unicode; |
|
176 |
# see below. |
|
177 |
# |
|
178 |
# A related problem is that even when a particular character is |
|
179 |
# encoded only once in Mac OS Arabic, it may have a different |
|
180 |
# direction attribute than the corresponding Unicode character. |
|
181 |
# |
|
182 |
# For example, the Mac OS Arabic character at 0x93 is HORIZONTAL |
|
183 |
# ELLIPSIS with strong right-left direction. However, the Unicode |
|
184 |
# character HORIZONTAL ELLIPSIS has direction class neutral. |
|
185 |
# |
|
186 |
# 3. Behavior of ASCII-range numbers in WorldScript |
|
187 |
# |
|
188 |
# Mac OS Arabic also has two sets of digit codes. |
|
189 |
# |
|
190 |
# The digits at 0x30-0x39 may be displayed using either European |
|
191 |
# digit forms or Arabic digit forms, depending on context. If there |
|
192 |
# is a 'strong European' character such as a Latin letter on either |
|
193 |
# side of a sequence consisting of digits 0x30-0x39 and possibly comma |
|
194 |
# 0x2C or period 0x2E, then the characters will be displayed using |
|
195 |
# European forms (This will happen even if there are neutral characters |
|
196 |
# between the digits and the strong European character). Otherwise, the |
|
197 |
# digits will be displayed using Arabic forms, the comma will be |
|
198 |
# displayed as Arabic thousands separator, and the period as Arabic |
|
199 |
# decimal separator. In any case, 0x2C, 0x2E, and 0x30-0x39 are always |
|
200 |
# left-right. |
|
201 |
# |
|
202 |
# The digits at 0xB0-0xB9 are always displayed using Arabic digit |
|
203 |
# shapes, and moreover, these digits always have strong right-left |
|
204 |
# directionality. These are mainly intended for special layout |
|
205 |
# purposes such as part numbers, etc. |
|
206 |
# |
|
207 |
# 4. Font variants |
|
208 |
# |
|
209 |
# The table in this file gives the Unicode mappings for the standard |
|
210 |
# Mac OS Arabic encoding. This encoding is supported by the Cairo font |
|
211 |
# (the system font for Arabic), and is the encoding supported by the |
|
212 |
# text processing utilities. However, the other Arabic fonts actually |
|
213 |
# implement slightly different encodings; this mainly affects the code |
|
214 |
# points 0xAA and 0xC0. For these code points the standard Mac OS |
|
215 |
# Arabic encoding has the following mappings: |
|
216 |
# 0xAA -> <RL>+0x002A ASTERISK, right-left |
|
217 |
# 0xC0 -> <RL>+0x274A EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, |
|
218 |
# right-left |
|
219 |
# This mapping of 0xAA is consistent with the normal convention for |
|
220 |
# Mac OS Arabic and Hebrew that the right-left duplicates have codes |
|
221 |
# that are equal to the ASCII code of the left-right character plus |
|
222 |
# 0x80. However, in all of the other fonts, 0xAA is MULTIPLY SIGN, and |
|
223 |
# right-left ASTERISK may be at a different code point. The other |
|
224 |
# variants are described below. |
|
225 |
# |
|
226 |
# The TrueType variant is used for most of the Arabic TrueType fonts: |
|
227 |
# Baghdad, Geeza, Kufi, Nadeem. It differs from the standard variant |
|
228 |
# in the following way: |
|
229 |
# 0xAA -> <RL>+0x00D7 MULTIPLICATION SIGN, right-left |
|
230 |
# 0xC0 -> <RL>+0x002A ASTERISK, right-left |
|
231 |
# |
|
232 |
# The Thuluth variant is used for the Arabic Postscript-only fonts: |
|
233 |
# Thuluth and Thuluth bold. It differs from the standard variant in |
|
234 |
# the following way: |
|
235 |
# 0xAA -> <RL>+0x00D7 MULTIPLICATION SIGN, right-left |
|
236 |
# 0xC0 -> 0x066D ARABIC FIVE POINTED STAR |
|
237 |
# |
|
238 |
# The AlBayan variant is used for the Arabic TrueType font Al Bayan. |
|
239 |
# It differs from the standard variant in the following way: |
|
240 |
# 0x81 -> no mapping (glyph just has authorship information, etc.) |
|
241 |
# 0xA3 -> 0xFDFA ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM |
|
242 |
# 0xA4 -> 0xFDF2 ARABIC LIGATURE ALLAH ISOLATED FORM |
|
243 |
# 0xAA -> <RL>+0x00D7 MULTIPLICATION SIGN, right-left |
|
244 |
# 0xDC -> <RL>+0x25CF BLACK CIRCLE, right-left |
|
245 |
# 0xFC -> <RL>+0x25A0 BLACK SQUARE, right-left |
|
246 |
# |
|
247 |
# Unicode mapping issues and notes: |
|
248 |
# --------------------------------- |
|
249 |
# |
|
250 |
# 1. Matching the direction of Mac OS Arabic characters |
|
251 |
# |
|
252 |
# When Mac OS Arabic encodes a character twice but with different |
|
253 |
# direction attributes for the two code points - as in the case of |
|
254 |
# plus sign mentioned above - we need a way to map both Mac OS Arabic |
|
255 |
# code points to Unicode and back again without loss of information. |
|
256 |
# With the plus sign, for example, mapping one of the Mac OS Arabic |
|
257 |
# characters to a code in the Unicode corporate use zone is |
|
258 |
# undesirable, since both of the plus sign characters are likely to |
|
259 |
# be used in text that is interchanged. |
|
260 |
# |
|
261 |
# The problem is solved with the use of direction override characters |
|
262 |
# and direction-dependent mappings. When mapping from Mac OS Arabic |
|
263 |
# to Unicode, we use direction overrides as necessary to force the |
|
264 |
# direction of the resulting Unicode characters. |
|
265 |
# |
|
266 |
# The required direction is indicated by a direction tag in the |
|
267 |
# mappings. A tag of <LR> means the corresponding Unicode character |
|
268 |
# must have a strong left-right context, and a tag of <RL> indicates |
|
269 |
# a right-left context. |
|
270 |
# |
|
271 |
# For example, the mapping of 0x2B is given as <LR>+0x002B; the |
|
272 |
# mapping of 0xAB is given as <RL>+0x002B. If we map an isolated |
|
273 |
# instance of 0x2B to Unicode, it should be mapped as follows (LRO |
|
274 |
# indicates LEFT-RIGHT OVERRIDE, PDF indicates POP DIRECTION |
|
275 |
# FORMATTING): |
|
276 |
# |
|
277 |
# 0x2B -> 0x202D (LRO) + 0x002B (PLUS SIGN) + 0x202C (PDF) |
|
278 |
# |
|
279 |
# When mapping several characters in a row that require direction |
|
280 |
# forcing, the overrides need only be used at the beginning and end. |
|
281 |
# For example: |
|
282 |
# |
|
283 |
# 0x24 0x20 0x28 0x29 -> 0x202D 0x0024 0x0020 0x0028 0x0029 0x202C |
|
284 |
# |
|
285 |
# If neutral characters that require direction forcing are already |
|
286 |
# between strong-direction characters with matching directionality, |
|
287 |
# then direction overrides need not be used. Direction overrides are |
|
288 |
# always needed to map the right-left digits at 0xB0-0xB9. |
|
289 |
# |
|
290 |
# When mapping from Unicode to Mac OS Arabic, the Unicode |
|
291 |
# bidirectional algorithm should be used to determine resolved |
|
292 |
# direction of the Unicode characters. The mapping from Unicode to |
|
293 |
# Mac OS Arabic can then be disambiguated by the use of the resolved |
|
294 |
# direction: |
|
295 |
# |
|
296 |
# Unicode 0x002B -> Mac OS Arabic 0x2B (if L) or 0xAB (if R) |
|
297 |
# |
|
298 |
# However, this also means the direction override characters should |
|
299 |
# be discarded when mapping from Unicode to Mac OS Arabic (after |
|
300 |
# they have been used to determine resolved direction), since the |
|
301 |
# direction override information is carried by the code point itself. |
|
302 |
# |
|
303 |
# Even when direction overrides are not needed for roundtrip |
|
304 |
# fidelity, they are sometimes used when mapping Mac OS Arabic |
|
305 |
# characters to Unicode in order to achieve similar text layout with |
|
306 |
# the resulting Unicode text. For example, the single Mac OS Arabic |
|
307 |
# ellipsis character has direction class right-left,and there is no |
|
308 |
# left-right version. However, the Unicode HORIZONTAL ELLIPSIS |
|
309 |
# character has direction class neutral (which means it may end up |
|
310 |
# with a resolved direction of left-right if surrounded by left-right |
|
311 |
# characters). When mapping the Mac OS Arabic ellipsis to Unicode, it |
|
312 |
# is surrounded with a direction override to help preserve proper |
|
313 |
# text layout. The resolved direction is not needed or used when |
|
314 |
# mapping the Unicode HORIZONTAL ELLIPSIS back to Mac OS Arabic. |
|
315 |
# |
|
316 |
# 2. Mapping the Mac OS Arabic digits |
|
317 |
# |
|
318 |
# The main table below contains mappings that should be used when |
|
319 |
# strict round-trip fidelity is required. However, for numeric |
|
320 |
# values, the mappings in that table will produce Unicode characters |
|
321 |
# that may appear different than the Mac OS Arabic text displayed on |
|
322 |
# a Mac OS system using WorldScript. This is because WorldScript |
|
323 |
# uses context-dependent display for the 0x30-0x39 digits. |
|
324 |
# |
|
325 |
# If roundtrip fidelity is not required, then the following |
|
326 |
# alternate mappings should be used when a sequence of 0x30-0x39 |
|
327 |
# digits - possibly including 0x2C and 0x2E - occurs in an Arabic |
|
328 |
# context (that is, when the first 'strong' character on either side |
|
329 |
# of the digit sequence is Arabic, or there is no strong character): |
|
330 |
# |
|
331 |
# 0x2C 0x066C # ARABIC THOUSANDS SEPARATOR |
|
332 |
# 0x2E 0x066B # ARABIC DECIMAL SEPARATOR |
|
333 |
# 0x30 0x0660 # ARABIC-INDIC DIGIT ZERO |
|
334 |
# 0x31 0x0661 # ARABIC-INDIC DIGIT ONE |
|
335 |
# 0x32 0x0662 # ARABIC-INDIC DIGIT TWO |
|
336 |
# 0x33 0x0663 # ARABIC-INDIC DIGIT THREE |
|
337 |
# 0x34 0x0664 # ARABIC-INDIC DIGIT FOUR |
|
338 |
# 0x35 0x0665 # ARABIC-INDIC DIGIT FIVE |
|
339 |
# 0x36 0x0666 # ARABIC-INDIC DIGIT SIX |
|
340 |
# 0x37 0x0667 # ARABIC-INDIC DIGIT SEVEN |
|
341 |
# 0x38 0x0668 # ARABIC-INDIC DIGIT EIGHT |
|
342 |
# 0x39 0x0669 # ARABIC-INDIC DIGIT NINE |
|
343 |
# |
|
344 |
# Details of mapping changes in each version: |
|
345 |
# ------------------------------------------- |
|
346 |
# |
|
347 |
# Changes from version n03 to version n07: |
|
348 |
# |
|
349 |
# - Change mapping for 0xC0 from U+066D to U+274A. |
|
350 |
# |
|
351 |
# - Add direction overrides (required directionality) to mappings |
|
352 |
# for 0x25, 0x2C, 0x3B, 0x3F. |
|
353 |
# |
|
354 |
################## |
|
355 |
||
356 |
0x20 <LR>+0x0020 # SPACE, left-right |
|
357 |
0x21 <LR>+0x0021 # EXCLAMATION MARK, left-right |
|
358 |
0x22 <LR>+0x0022 # QUOTATION MARK, left-right |
|
359 |
0x23 <LR>+0x0023 # NUMBER SIGN, left-right |
|
360 |
0x24 <LR>+0x0024 # DOLLAR SIGN, left-right |
|
361 |
0x25 <LR>+0x0025 # PERCENT SIGN, left-right |
|
362 |
0x26 <LR>+0x0026 # AMPERSAND, left-right |
|
363 |
0x27 <LR>+0x0027 # APOSTROPHE, left-right |
|
364 |
0x28 <LR>+0x0028 # LEFT PARENTHESIS, left-right |
|
365 |
0x29 <LR>+0x0029 # RIGHT PARENTHESIS, left-right |
|
366 |
0x2A <LR>+0x002A # ASTERISK, left-right |
|
367 |
0x2B <LR>+0x002B # PLUS SIGN, left-right |
|
368 |
0x2C <LR>+0x002C # COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR |
|
369 |
0x2D <LR>+0x002D # HYPHEN-MINUS, left-right |
|
370 |
0x2E <LR>+0x002E # FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR |
|
371 |
0x2F <LR>+0x002F # SOLIDUS, left-right |
|
372 |
0x30 0x0030 # DIGIT ZERO; in Arabic-script context, displayed as 0x0660 ARABIC-INDIC DIGIT ZERO |
|
373 |
0x31 0x0031 # DIGIT ONE; in Arabic-script context, displayed as 0x0661 ARABIC-INDIC DIGIT ONE |
|
374 |
0x32 0x0032 # DIGIT TWO; in Arabic-script context, displayed as 0x0662 ARABIC-INDIC DIGIT TWO |
|
375 |
0x33 0x0033 # DIGIT THREE; in Arabic-script context, displayed as 0x0663 ARABIC-INDIC DIGIT THREE |
|
376 |
0x34 0x0034 # DIGIT FOUR; in Arabic-script context, displayed as 0x0664 ARABIC-INDIC DIGIT FOUR |
|
377 |
0x35 0x0035 # DIGIT FIVE; in Arabic-script context, displayed as 0x0665 ARABIC-INDIC DIGIT FIVE |
|
378 |
0x36 0x0036 # DIGIT SIX; in Arabic-script context, displayed as 0x0666 ARABIC-INDIC DIGIT SIX |
|
379 |
0x37 0x0037 # DIGIT SEVEN; in Arabic-script context, displayed as 0x0667 ARABIC-INDIC DIGIT SEVEN |
|
380 |
0x38 0x0038 # DIGIT EIGHT; in Arabic-script context, displayed as 0x0668 ARABIC-INDIC DIGIT EIGHT |
|
381 |
0x39 0x0039 # DIGIT NINE; in Arabic-script context, displayed as 0x0669 ARABIC-INDIC DIGIT NINE |
|
382 |
0x3A <LR>+0x003A # COLON, left-right |
|
383 |
0x3B <LR>+0x003B # SEMICOLON, left-right |
|
384 |
0x3C <LR>+0x003C # LESS-THAN SIGN, left-right |
|
385 |
0x3D <LR>+0x003D # EQUALS SIGN, left-right |
|
386 |
0x3E <LR>+0x003E # GREATER-THAN SIGN, left-right |
|
387 |
0x3F <LR>+0x003F # QUESTION MARK, left-right |
|
388 |
0x40 0x0040 # COMMERCIAL AT |
|
389 |
0x41 0x0041 # LATIN CAPITAL LETTER A |
|
390 |
0x42 0x0042 # LATIN CAPITAL LETTER B |
|
391 |
0x43 0x0043 # LATIN CAPITAL LETTER C |
|
392 |
0x44 0x0044 # LATIN CAPITAL LETTER D |
|
393 |
0x45 0x0045 # LATIN CAPITAL LETTER E |
|
394 |
0x46 0x0046 # LATIN CAPITAL LETTER F |
|
395 |
0x47 0x0047 # LATIN CAPITAL LETTER G |
|
396 |
0x48 0x0048 # LATIN CAPITAL LETTER H |
|
397 |
0x49 0x0049 # LATIN CAPITAL LETTER I |
|
398 |
0x4A 0x004A # LATIN CAPITAL LETTER J |
|
399 |
0x4B 0x004B # LATIN CAPITAL LETTER K |
|
400 |
0x4C 0x004C # LATIN CAPITAL LETTER L |
|
401 |
0x4D 0x004D # LATIN CAPITAL LETTER M |
|
402 |
0x4E 0x004E # LATIN CAPITAL LETTER N |
|
403 |
0x4F 0x004F # LATIN CAPITAL LETTER O |
|
404 |
0x50 0x0050 # LATIN CAPITAL LETTER P |
|
405 |
0x51 0x0051 # LATIN CAPITAL LETTER Q |
|
406 |
0x52 0x0052 # LATIN CAPITAL LETTER R |
|
407 |
0x53 0x0053 # LATIN CAPITAL LETTER S |
|
408 |
0x54 0x0054 # LATIN CAPITAL LETTER T |
|
409 |
0x55 0x0055 # LATIN CAPITAL LETTER U |
|
410 |
0x56 0x0056 # LATIN CAPITAL LETTER V |
|
411 |
0x57 0x0057 # LATIN CAPITAL LETTER W |
|
412 |
0x58 0x0058 # LATIN CAPITAL LETTER X |
|
413 |
0x59 0x0059 # LATIN CAPITAL LETTER Y |
|
414 |
0x5A 0x005A # LATIN CAPITAL LETTER Z |
|
415 |
0x5B <LR>+0x005B # LEFT SQUARE BRACKET, left-right |
|
416 |
0x5C <LR>+0x005C # REVERSE SOLIDUS, left-right |
|
417 |
0x5D <LR>+0x005D # RIGHT SQUARE BRACKET, left-right |
|
418 |
0x5E <LR>+0x005E # CIRCUMFLEX ACCENT, left-right |
|
419 |
0x5F <LR>+0x005F # LOW LINE, left-right |
|
420 |
0x60 0x0060 # GRAVE ACCENT |
|
421 |
0x61 0x0061 # LATIN SMALL LETTER A |
|
422 |
0x62 0x0062 # LATIN SMALL LETTER B |
|
423 |
0x63 0x0063 # LATIN SMALL LETTER C |
|
424 |
0x64 0x0064 # LATIN SMALL LETTER D |
|
425 |
0x65 0x0065 # LATIN SMALL LETTER E |
|
426 |
0x66 0x0066 # LATIN SMALL LETTER F |
|
427 |
0x67 0x0067 # LATIN SMALL LETTER G |
|
428 |
0x68 0x0068 # LATIN SMALL LETTER H |
|
429 |
0x69 0x0069 # LATIN SMALL LETTER I |
|
430 |
0x6A 0x006A # LATIN SMALL LETTER J |
|
431 |
0x6B 0x006B # LATIN SMALL LETTER K |
|
432 |
0x6C 0x006C # LATIN SMALL LETTER L |
|
433 |
0x6D 0x006D # LATIN SMALL LETTER M |
|
434 |
0x6E 0x006E # LATIN SMALL LETTER N |
|
435 |
0x6F 0x006F # LATIN SMALL LETTER O |
|
436 |
0x70 0x0070 # LATIN SMALL LETTER P |
|
437 |
0x71 0x0071 # LATIN SMALL LETTER Q |
|
438 |
0x72 0x0072 # LATIN SMALL LETTER R |
|
439 |
0x73 0x0073 # LATIN SMALL LETTER S |
|
440 |
0x74 0x0074 # LATIN SMALL LETTER T |
|
441 |
0x75 0x0075 # LATIN SMALL LETTER U |
|
442 |
0x76 0x0076 # LATIN SMALL LETTER V |
|
443 |
0x77 0x0077 # LATIN SMALL LETTER W |
|
444 |
0x78 0x0078 # LATIN SMALL LETTER X |
|
445 |
0x79 0x0079 # LATIN SMALL LETTER Y |
|
446 |
0x7A 0x007A # LATIN SMALL LETTER Z |
|
447 |
0x7B <LR>+0x007B # LEFT CURLY BRACKET, left-right |
|
448 |
0x7C <LR>+0x007C # VERTICAL LINE, left-right |
|
449 |
0x7D <LR>+0x007D # RIGHT CURLY BRACKET, left-right |
|
450 |
0x7E 0x007E # TILDE |
|
451 |
# |
|
452 |
0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS |
|
453 |
0x81 <RL>+0x00A0 # NO-BREAK SPACE, right-left |
|
454 |
0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA |
|
455 |
0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE |
|
456 |
0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE |
|
457 |
0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS |
|
458 |
0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS |
|
459 |
0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE |
|
460 |
0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE |
|
461 |
0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX |
|
462 |
0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS |
|
463 |
0x8B 0x06BA # ARABIC LETTER NOON GHUNNA |
|
464 |
0x8C <RL>+0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left |
|
465 |
0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA |
|
466 |
0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE |
|
467 |
0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE |
|
468 |
0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX |
|
469 |
0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS |
|
470 |
0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE |
|
471 |
0x93 <RL>+0x2026 # HORIZONTAL ELLIPSIS, right-left |
|
472 |
0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX |
|
473 |
0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS |
|
474 |
0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE |
|
475 |
0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE |
|
476 |
0x98 <RL>+0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left |
|
477 |
0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX |
|
478 |
0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS |
|
479 |
0x9B <RL>+0x00F7 # DIVISION SIGN, right-left |
|
480 |
0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE |
|
481 |
0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE |
|
482 |
0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX |
|
483 |
0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS |
|
484 |
0xA0 <RL>+0x0020 # SPACE, right-left |
|
485 |
0xA1 <RL>+0x0021 # EXCLAMATION MARK, right-left |
|
486 |
0xA2 <RL>+0x0022 # QUOTATION MARK, right-left |
|
487 |
0xA3 <RL>+0x0023 # NUMBER SIGN, right-left |
|
488 |
0xA4 <RL>+0x0024 # DOLLAR SIGN, right-left |
|
489 |
0xA5 0x066A # ARABIC PERCENT SIGN |
|
490 |
0xA6 <RL>+0x0026 # AMPERSAND, right-left |
|
491 |
0xA7 <RL>+0x0027 # APOSTROPHE, right-left |
|
492 |
0xA8 <RL>+0x0028 # LEFT PARENTHESIS, right-left |
|
493 |
0xA9 <RL>+0x0029 # RIGHT PARENTHESIS, right-left |
|
494 |
0xAA <RL>+0x002A # ASTERISK, right-left |
|
495 |
0xAB <RL>+0x002B # PLUS SIGN, right-left |
|
496 |
0xAC 0x060C # ARABIC COMMA |
|
497 |
0xAD <RL>+0x002D # HYPHEN-MINUS, right-left |
|
498 |
0xAE <RL>+0x002E # FULL STOP, right-left |
|
499 |
0xAF <RL>+0x002F # SOLIDUS, right-left |
|
500 |
0xB0 <RL>+0x0660 # ARABIC-INDIC DIGIT ZERO, right-left (need override) |
|
501 |
0xB1 <RL>+0x0661 # ARABIC-INDIC DIGIT ONE, right-left (need override) |
|
502 |
0xB2 <RL>+0x0662 # ARABIC-INDIC DIGIT TWO, right-left (need override) |
|
503 |
0xB3 <RL>+0x0663 # ARABIC-INDIC DIGIT THREE, right-left (need override) |
|
504 |
0xB4 <RL>+0x0664 # ARABIC-INDIC DIGIT FOUR, right-left (need override) |
|
505 |
0xB5 <RL>+0x0665 # ARABIC-INDIC DIGIT FIVE, right-left (need override) |
|
506 |
0xB6 <RL>+0x0666 # ARABIC-INDIC DIGIT SIX, right-left (need override) |
|
507 |
0xB7 <RL>+0x0667 # ARABIC-INDIC DIGIT SEVEN, right-left (need override) |
|
508 |
0xB8 <RL>+0x0668 # ARABIC-INDIC DIGIT EIGHT, right-left (need override) |
|
509 |
0xB9 <RL>+0x0669 # ARABIC-INDIC DIGIT NINE, right-left (need override) |
|
510 |
0xBA <RL>+0x003A # COLON, right-left |
|
511 |
0xBB 0x061B # ARABIC SEMICOLON |
|
512 |
0xBC <RL>+0x003C # LESS-THAN SIGN, right-left |
|
513 |
0xBD <RL>+0x003D # EQUALS SIGN, right-left |
|
514 |
0xBE <RL>+0x003E # GREATER-THAN SIGN, right-left |
|
515 |
0xBF 0x061F # ARABIC QUESTION MARK |
|
516 |
0xC0 <RL>+0x274A # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left |
|
517 |
0xC1 0x0621 # ARABIC LETTER HAMZA |
|
518 |
0xC2 0x0622 # ARABIC LETTER ALEF WITH MADDA ABOVE |
|
519 |
0xC3 0x0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE |
|
520 |
0xC4 0x0624 # ARABIC LETTER WAW WITH HAMZA ABOVE |
|
521 |
0xC5 0x0625 # ARABIC LETTER ALEF WITH HAMZA BELOW |
|
522 |
0xC6 0x0626 # ARABIC LETTER YEH WITH HAMZA ABOVE |
|
523 |
0xC7 0x0627 # ARABIC LETTER ALEF |
|
524 |
0xC8 0x0628 # ARABIC LETTER BEH |
|
525 |
0xC9 0x0629 # ARABIC LETTER TEH MARBUTA |
|
526 |
0xCA 0x062A # ARABIC LETTER TEH |
|
527 |
0xCB 0x062B # ARABIC LETTER THEH |
|
528 |
0xCC 0x062C # ARABIC LETTER JEEM |
|
529 |
0xCD 0x062D # ARABIC LETTER HAH |
|
530 |
0xCE 0x062E # ARABIC LETTER KHAH |
|
531 |
0xCF 0x062F # ARABIC LETTER DAL |
|
532 |
0xD0 0x0630 # ARABIC LETTER THAL |
|
533 |
0xD1 0x0631 # ARABIC LETTER REH |
|
534 |
0xD2 0x0632 # ARABIC LETTER ZAIN |
|
535 |
0xD3 0x0633 # ARABIC LETTER SEEN |
|
536 |
0xD4 0x0634 # ARABIC LETTER SHEEN |
|
537 |
0xD5 0x0635 # ARABIC LETTER SAD |
|
538 |
0xD6 0x0636 # ARABIC LETTER DAD |
|
539 |
0xD7 0x0637 # ARABIC LETTER TAH |
|
540 |
0xD8 0x0638 # ARABIC LETTER ZAH |
|
541 |
0xD9 0x0639 # ARABIC LETTER AIN |
|
542 |
0xDA 0x063A # ARABIC LETTER GHAIN |
|
543 |
0xDB <RL>+0x005B # LEFT SQUARE BRACKET, right-left |
|
544 |
0xDC <RL>+0x005C # REVERSE SOLIDUS, right-left |
|
545 |
0xDD <RL>+0x005D # RIGHT SQUARE BRACKET, right-left |
|
546 |
0xDE <RL>+0x005E # CIRCUMFLEX ACCENT, right-left |
|
547 |
0xDF <RL>+0x005F # LOW LINE, right-left |
|
548 |
0xE0 0x0640 # ARABIC TATWEEL |
|
549 |
0xE1 0x0641 # ARABIC LETTER FEH |
|
550 |
0xE2 0x0642 # ARABIC LETTER QAF |
|
551 |
0xE3 0x0643 # ARABIC LETTER KAF |
|
552 |
0xE4 0x0644 # ARABIC LETTER LAM |
|
553 |
0xE5 0x0645 # ARABIC LETTER MEEM |
|
554 |
0xE6 0x0646 # ARABIC LETTER NOON |
|
555 |
0xE7 0x0647 # ARABIC LETTER HEH |
|
556 |
0xE8 0x0648 # ARABIC LETTER WAW |
|
557 |
0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA |
|
558 |
0xEA 0x064A # ARABIC LETTER YEH |
|
559 |
0xEB 0x064B # ARABIC FATHATAN |
|
560 |
0xEC 0x064C # ARABIC DAMMATAN |
|
561 |
0xED 0x064D # ARABIC KASRATAN |
|
562 |
0xEE 0x064E # ARABIC FATHA |
|
563 |
0xEF 0x064F # ARABIC DAMMA |
|
564 |
0xF0 0x0650 # ARABIC KASRA |
|
565 |
0xF1 0x0651 # ARABIC SHADDA |
|
566 |
0xF2 0x0652 # ARABIC SUKUN |
|
567 |
0xF3 0x067E # ARABIC LETTER PEH |
|
568 |
0xF4 0x0679 # ARABIC LETTER TTEH |
|
569 |
0xF5 0x0686 # ARABIC LETTER TCHEH |
|
570 |
0xF6 0x06D5 # ARABIC LETTER AE |
|
571 |
0xF7 0x06A4 # ARABIC LETTER VEH |
|
572 |
0xF8 0x06AF # ARABIC LETTER GAF |
|
573 |
0xF9 0x0688 # ARABIC LETTER DDAL |
|
574 |
0xFA 0x0691 # ARABIC LETTER RREH |
|
575 |
0xFB <RL>+0x007B # LEFT CURLY BRACKET, right-left |
|
576 |
0xFC <RL>+0x007C # VERTICAL LINE, right-left |
|
577 |
0xFD <RL>+0x007D # RIGHT CURLY BRACKET, right-left |
|
578 |
0xFE 0x0698 # ARABIC LETTER JEH |
|
579 |
0xFF 0x06D2 # ARABIC LETTER YEH BARREE |
|
580 |
||
581 |
" |
|
582 |
! ! |
|
583 |
||
584 |
!MAC_Arabic class methodsFor:'documentation'! |
|
585 |
||
586 |
version |
|
17728
bbc5fa73dfab
Merged with trunk r10466
Jan Vrany <jan.vrany@fit.cvut.cz>
parents:
17711
diff
changeset
|
587 |
^ '$Id: CharacterEncoderImplementations__MAC_Arabic.st 10467 2009-08-19 16:14:36Z vranyj1 $' |
8081 | 588 |
! ! |