1 |
wakaba |
1.1 |
#!/usr/local/bin/perl
|
2 |
|
|
use utf8; ## This file is written in UTF-8
|
3 |
|
|
use strict;
|
4 |
|
|
require 'mkpm.pl';
|
5 |
|
|
use vars qw(%PROP %SET %SET_ALIAS);
|
6 |
|
|
$PROP{module_name} = 'UCS';
|
7 |
|
|
$PROP{version} = do{my @r=(q$Revision: 1.1 $=~/\d+/g);sprintf "%d."."%02d" x $#r,@r};
|
8 |
|
|
$PROP{author_name} = 'Wakaba';
|
9 |
|
|
$PROP{author_mail} = 'w@suika.fam.cx';
|
10 |
|
|
|
11 |
|
|
my $l = <<EOH;
|
12 |
|
|
1 BASIC LATIN 0020 - 007E
|
13 |
|
|
2 LATIN-1 SUPPLEMENT 00A0 - 00FF
|
14 |
|
|
3 LATIN EXTENDED-A 0100 - 017F
|
15 |
|
|
4 LATIN EXTENDED-B 0180 - 024F
|
16 |
|
|
6 SPACING MODIFIER LETTERS 02B0 - 02FF
|
17 |
|
|
7 COMBINING DIACRITICAL MARKS 0300 - 036F
|
18 |
|
|
8 BASIC GREEK 0370 - 03CF
|
19 |
|
|
9 GREEK SYMBOLS AND COPTIC 03D0 - 03FF
|
20 |
|
|
10 CYRILLIC 0400 - 04FF
|
21 |
|
|
11 ARMENIAN 0530 - 058F
|
22 |
|
|
12 BASIC HEBREW 05D0 - 05EA
|
23 |
|
|
13 HEBREW EXTENDED 0590 - 05CF, 05EB - 05FF
|
24 |
|
|
14 BASIC ARABIC 0600 - 065F
|
25 |
|
|
15 ARABIC EXTENDED 0660 - 06FF
|
26 |
|
|
16 DEVANAGARI 0900 - 097F, 200C, 200D
|
27 |
|
|
17 BENGALI 0980 - 09FF,200C, 200D
|
28 |
|
|
18 GURMUKHI 0A00 - 0A7F,200C, 200D
|
29 |
|
|
19 GUJARATI 0A80 - 0AFF,200C, 200D
|
30 |
|
|
20 ORIYA 0B00 - 0B7F,200C, 200D
|
31 |
|
|
21 TAMIL 0B80 - 0BFF,200C, 200D
|
32 |
|
|
22 TELUGU 0C00 - 0C7F,200C, 200D
|
33 |
|
|
23 KANNADA 0C80 - 0CFF,200C, 200D
|
34 |
|
|
24 MALAYALAM 0D00 - 0D7F,200C, 200D
|
35 |
|
|
25 THAI 0E00 - 0E7F
|
36 |
|
|
26 LAO 0E80 - 0EFF
|
37 |
|
|
27 BASIC GEORGIAN 10D0 - 10FF
|
38 |
|
|
28 GEORGIAN EXTENDED 10A0 - 10CF
|
39 |
|
|
29 HANGUL JAMO 1100 - 11FF
|
40 |
|
|
30 LATIN EXTENDED ADDITIONAL 1E00 - 1EFF
|
41 |
|
|
31 GREEK EXTENDED 1F00 - 1FFF
|
42 |
|
|
32 GENERAL PUNCTUATION 2000 - 206F
|
43 |
|
|
33 SUPERSCRIPTS AND SUBSCRIPTS 2070 - 209F
|
44 |
|
|
34 CURRENCY SYMBOLS 20A0 - 20CF
|
45 |
|
|
35 COMBINING DIACRITICAL MARKS FOR SYMBOLS 20D0 - 20FF
|
46 |
|
|
36 LETTERLIKE SYMBOLS 2100 - 214F
|
47 |
|
|
37 NUMBER FORMS 2150 - 218F
|
48 |
|
|
38 ARROWS 2190 - 21FF
|
49 |
|
|
39 MATHEMATICAL OPERATORS 2200 - 22FF
|
50 |
|
|
40 MISCELLANEOUS TECHNICAL 2300 - 23FF
|
51 |
|
|
41 CONTROL PICTURES 2400 - 243F
|
52 |
|
|
42 OPTICAL CHARACTER RECOGNITION 2440 - 245F
|
53 |
|
|
43 ENCLOSED ALPHANUMERICS 2460 - 24FF
|
54 |
|
|
44 BOX DRAWING 2500 - 257F
|
55 |
|
|
45 BLOCK ELEMENTS 2580 - 259F
|
56 |
|
|
46 GEOMETRIC SHAPES 25A0 - 25FF
|
57 |
|
|
47 MISCELLANEOUS SYMBOLS 2600 - 26FF
|
58 |
|
|
48 DINGBATS 2700 - 27BF
|
59 |
|
|
49 CJK SYMBOLS AND PUNCTUATION 3000 - 303F
|
60 |
|
|
50 HIRAGANA 3040 - 309F
|
61 |
|
|
51 KATAKANA 30A0 - 30FF
|
62 |
|
|
52 BOPOMOFO 3100 - 312F,31A0 - 31BF
|
63 |
|
|
53 HANGUL COMPATIBILITY JAMO 3130 - 318F
|
64 |
|
|
54 CJK MISCELLANEOUS 3190 - 319F
|
65 |
|
|
55 ENCLOSED CJK LETTERS AND MONTHS 3200 - 32FF
|
66 |
|
|
56 CJK COMPATIBILITY 3300 - 33FF
|
67 |
|
|
## 57-59 were deleted at ISO/IEC 10646-1:1993 Amd.5 (so-called Korean mess)
|
68 |
|
|
57 Basic Hangul 3400-3D3D
|
69 |
|
|
58 Supplemental Hangul A 3D2E-44B7
|
70 |
|
|
58 Supplemental Hangul B 44BE-4DFF
|
71 |
|
|
60 CJK UNIFIED IDEOGRAPHS 4E00 - 9FFF
|
72 |
|
|
61 PRIVATE USE AREA E000 - F8FF
|
73 |
|
|
62 CJK COMPATIBILITY IDEOGRAPHS F900 - FAFF
|
74 |
|
|
63 ALPHABETIC PRESENTATION FORMS FB00 - FB4F
|
75 |
|
|
64 ARABIC PRESENTATION FORMS-A FB50 - FDFF
|
76 |
|
|
65 COMBINING HALF MARKS FE20 - FE2F
|
77 |
|
|
66 CJK COMPATIBILITY FORMS FE30 - FE4F
|
78 |
|
|
67 SMALL FORM VARIANTS FE50 - FE6F
|
79 |
|
|
68 ARABIC PRESENTATION FORMS-B FE70 - FEFE
|
80 |
|
|
69 HALFWIDTH AND FULLWIDTH FORMS FF00 - FFEF
|
81 |
|
|
70 SPECIALS FFF0 - FFFD
|
82 |
|
|
71 HANGUL SYLLABLES AC00 - D7A3
|
83 |
|
|
72 BASIC TIBETAN 0F00 - 0FBF
|
84 |
|
|
73 ETHIOPIC 1200 - 137F
|
85 |
|
|
74 UNIFIED CANADIAN ABORIGINAL SYLLABICS 1400 - 167F
|
86 |
|
|
75 CHEROKEE 13A0 - 13FF
|
87 |
|
|
76 YI SYLLABLES A000 - A48F
|
88 |
|
|
77 YI RADICALS A490 - A4CF
|
89 |
|
|
78 KANGXI RADICALS 2F00 - 2FDF
|
90 |
|
|
79 CJK RADICALS SUPPLEMENT 2E80 - 2EFF
|
91 |
|
|
80 BRAILLE PATTERNS 2800 - 28FF
|
92 |
|
|
81 CJK UNIFIED IDEOGRAPHS EXTENSION A 3400 - 4DBF
|
93 |
|
|
82 OGHAM 1680 - 169F
|
94 |
|
|
83 RUNIC 16A0 - 16FF
|
95 |
|
|
84 SINHALA 0D80 - 0DFF
|
96 |
|
|
85 SYRIAC 0700 - 074F
|
97 |
|
|
86 THAANA 0780 - 07BF
|
98 |
|
|
87 BASIC MYANMAR 1000 - 104F,200C, 200D
|
99 |
|
|
88 KHMER 1780 - 17FF,200C, 200D
|
100 |
|
|
89 MONGOLIAN 1800 - 18AF
|
101 |
|
|
90 EXTENDED MYANMAR 1050 - 109F
|
102 |
|
|
91 TIBETAN 0F00 - 0FFF
|
103 |
|
|
200 ZERO-WIDTH BOUNDARY INDICATORS 200B - 200D,FEFF
|
104 |
|
|
201 FORMAT SEPARATORS 2028 - 2029
|
105 |
|
|
202 BI-DIRECTIONAL FORMAT MARKS 200E - 200F
|
106 |
|
|
203 BI-DIRECTIONAL FORMAT EMBEDDINGS 202A - 202E
|
107 |
|
|
204 HANGUL FILL CHARACTERS 3164, FFA0
|
108 |
|
|
205 CHARACTER SHAPING SELECTORS 206A - 206D
|
109 |
|
|
206 NUMERIC SHAPE SELECTORS 206E - 206F
|
110 |
|
|
207 IDEOGRAPHIC DESCRIPTION CHARACTERS 2FF0 - 2FFF
|
111 |
|
|
#270 COMBINING CHARACTERS
|
112 |
|
|
#271 COMBINING CHARACTERS B-2
|
113 |
|
|
## 92-101,180,10646 ISO/IEC 10646-1:2000 Amd.1
|
114 |
|
|
180 CJK UNIFIED IDEOGRAPHS ALL 3400-4DBF,4E00-9FFF,FA0E-FA0F,FA11,FA14-FA14,FA1F,FA21,FA23-FA24,FA27-FA29,20000-2A6DF
|
115 |
|
|
10646 UNICODE 0000-FDCF,FDF0-FFFD,10000-1FFFD,20000-2FFFD,E0000-EFFFD,F0000-FFFFD,100000-10FFFD
|
116 |
|
|
92 CYRILLIC SUPPLEMENTARY 0500-052F
|
117 |
|
|
93 TAGALOG 1700-171F
|
118 |
|
|
94 HANUNOO 1720-173F
|
119 |
|
|
95 BUHID 1740-175F
|
120 |
|
|
96 TAGBANWA 1760-177F
|
121 |
|
|
97 SUPPLEMENTAL ARROWS 2900-297F
|
122 |
|
|
98 MISCLLANEOUS MATHMATICAL SYMBOLS 2980-29FF
|
123 |
|
|
99 SUPPLEMENTAL MATHMATICAL OPERATORS 2A00-2AFF
|
124 |
|
|
100 KATAKANA PHONETIC EXTENSIONS 31F0-31FF
|
125 |
|
|
101 VARIATION SELECTORS FE00-FE0F
|
126 |
|
|
## 104-108 ISO/IEC 10646-1:2000 Amd.2
|
127 |
|
|
104 LIMBU 1900-194F
|
128 |
|
|
105 TAI LE 1950-197F
|
129 |
|
|
106 SUPPLEMENTAL ARROWS-C 2B00-2B2F
|
130 |
|
|
107 SUPPLEMENTAL CJK COMPATIBILITY 31C0-31EF
|
131 |
|
|
108 YIJING HEXAGRAM SYMBOLS 4DC0-4DFF
|
132 |
|
|
## 1001-4000 ISO/IEC 10646-2:2001
|
133 |
|
|
1001 ETRUSCAN 010300-01032F
|
134 |
|
|
1002 GOTHIC 010330-01034F
|
135 |
|
|
1003 DESERET 010400-01044F
|
136 |
|
|
1004 BYZANTINE MUSICAL SYMBOLS 01D000-01D0FF
|
137 |
|
|
1005 WESTERN MUSICAL SYMBOLS 01D100-01D1FF
|
138 |
|
|
2001 CJK UNIFIED IDEOGRAPHS EXTENSION B 020000-02A71F
|
139 |
|
|
## Note: ISO/IEC 10646-2:2000 incorrectly gave collection No. 2001 to
|
140 |
|
|
## CJK COMP. ID. SUPPLEMENT. This was fixed by its Amd.1.
|
141 |
|
|
2002 CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT 02F800-02FA1F
|
142 |
|
|
3001 TAGS 0E0000-0E007F
|
143 |
|
|
3002 ALTERNATE FORMAT CHARACTERS EXTENDED 0E0000-0E0FFF
|
144 |
|
|
1000 SMP 010000-01FFFD
|
145 |
|
|
#1900 SMP COMBINING CHARACTERS
|
146 |
|
|
2000 SIP 020000-02FFFD
|
147 |
|
|
3000 SPP 0E0000-0EFFFD
|
148 |
|
|
4000 PART 2 010000-01FFFD,020000-02FFFD,0E0000-0EFFFD
|
149 |
|
|
## 1007-3002 ISO/IEC 10646-2:2001 Amd.1
|
150 |
|
|
1007 LINEAR B SYLLABARY 10000-1007F
|
151 |
|
|
1008 LINEAR B IDEOGRAMS 10080-100FF
|
152 |
|
|
1009 AEGAN NUMBERS 10100-1013F
|
153 |
|
|
1010 UGARITIC 10380-1039F
|
154 |
|
|
1011 SHAVIAN 10450-1047F
|
155 |
|
|
1012 OSMANYA 10480-104AF
|
156 |
|
|
1013 CYPRIOT SYLLABARY 10800-1083F
|
157 |
|
|
3002 VARIATION SELECTORS SUPPLEMENT E0110-E01FF
|
158 |
|
|
EOH
|
159 |
|
|
|
160 |
|
|
for (split /\n/, $l) {
|
161 |
|
|
if (/^(\d+)\s([^\t]+)\t(.+)/) {
|
162 |
|
|
my ($num, $name, $range) = ($1, lc $2, $3);
|
163 |
|
|
$name =~ s/\bcjk\b/CJK/;
|
164 |
|
|
$name =~ s/[\x20-](\w)/uc $1/ge; $name =~ s/^(\w)/uc $1/e;
|
165 |
|
|
$name =~ s/^([A-Z][A-Z])/_$1/;
|
166 |
|
|
$range =~ tr/\x20//d;
|
167 |
|
|
my @range;
|
168 |
|
|
for (split /,/, $range) {
|
169 |
|
|
if (/([0-9A-F]+)-([0-9A-F]+)/) {
|
170 |
|
|
push @range, sprintf '!%s %s '."\n", $1, $2;
|
171 |
|
|
} else {
|
172 |
|
|
push @range, '!'.$_."\n";
|
173 |
|
|
}
|
174 |
|
|
}
|
175 |
|
|
$SET{$name} = join '', @range;
|
176 |
|
|
$SET_ALIAS{$num} = $name;
|
177 |
|
|
}
|
178 |
|
|
}
|
179 |
|
|
|
180 |
|
|
$SET{IPAExtensions} = <<EOH;
|
181 |
|
|
!0250 02AF
|
182 |
|
|
EOH
|
183 |
|
|
$SET_ALIAS{5} = 'IPAExtensions';
|
184 |
|
|
|
185 |
|
|
$SET{_BMP} = <<EOH;
|
186 |
|
|
!0000 D7FF
|
187 |
|
|
!E000 FFFD
|
188 |
|
|
EOH
|
189 |
|
|
$SET_ALIAS{300} = '_BMP';
|
190 |
|
|
|
191 |
|
|
## 299 BMP FIRST EDITION (ISO/IEC 10646-1:2000 A.3.2)
|
192 |
|
|
$SET_ALIAS{299} = '_BMPFirstEdition';
|
193 |
|
|
$SET{_BMPFirstEdition} = col2list (<<EOH) . <<EOH;
|
194 |
|
|
00 20-7E A0-FF
|
195 |
|
|
01 00-F5 FA-FF
|
196 |
|
|
02 00-17 50-A8 B0-DE E0-E9
|
197 |
|
|
03 00-45 60-61 74-75 7A 7E 84-8A 8C 8E-A1
|
198 |
|
|
03 A3-CE D0-D6 DA DC DE E0 E2-F3
|
199 |
|
|
04 01-0C 0E-4F 51-5C 5E-86 90-C4 C7-C8 CB-CC D0-EB EE-F5 F8-F9
|
200 |
|
|
05 31-56 59-5F 61-87 89 B0-B9 BB-C3 D0-EA F0-F4
|
201 |
|
|
06 0C 1B 1F 21-3A 40-52 60-6D 70-B7 BA-BE C0-CE D0-ED F0-F9
|
202 |
|
|
09 01-03 05-39 3C-4D 50-54 58-70 81-83 85-8C
|
203 |
|
|
09 8F-90 93-A8 AA-B0 B2 B6-B9 BC BE-C4
|
204 |
|
|
09 C7-C8 CB-CD D7 DC-DD DF-E3 E6-FA
|
205 |
|
|
0A 02 05-0A 0F-10 13-28 2A-30 32-33 35-36
|
206 |
|
|
0A 38-39 3C 3E-42 47-48 4B-4D 59-5C 5E 66-74
|
207 |
|
|
0A 81-83 85-8B 8D 8F-91 93-A8 AA-B0 B2-B3
|
208 |
|
|
0A B5-B9 BC-C5 C7-C9 CB-CD D0 E0 E6-EF
|
209 |
|
|
0B 01-03 05-0C 0F-10 13-28 2A-30 32-33 36-39
|
210 |
|
|
0B 3C-43 47-48 4B-4D 56-57 5C-5D 5F-61 66-70
|
211 |
|
|
0B 82-83 85-8A 8E-90 92-25 99-9A 9C 9E-9F
|
212 |
|
|
0B A3-A4 A8-AA AE-B5 B7-B9 BE-C2 C6-C8 CA-CD D7 E7-F2
|
213 |
|
|
0C 01-03 05-0C 0E-10 12-28 2A-33 35-39 3E-44
|
214 |
|
|
0C 46-48 4A-4D 55-56 60-61 66-6F 82-83 85-8C
|
215 |
|
|
0C 8E-90 92-A8 AA-B3 B5-B9 BE-C4 C6-C8 CA-CD D5-D6 DE E0-E1 E6-EF
|
216 |
|
|
0D 02-03 05-0C 0E-10 12-28 2A-39 3E-43 46-48 4A-4D 57 60-61 66-6F
|
217 |
|
|
0E 01-3A 3F-5B 81-82 84 87-88 8A 8D 94-97
|
218 |
|
|
0E 99-9F A1-A3 A5 A7 AA-AB AD-B9 BB-BD C0-C4 C6 C8-CD D0-D9 DC-DD
|
219 |
|
|
10 A0-C5 D0-F6 FB
|
220 |
|
|
11 00-59 5F-A2 A8-F9
|
221 |
|
|
1E 00-9A A0-F9
|
222 |
|
|
1F 00-15 18-1D 20-45 48-4D 50-57 59 5B 5D
|
223 |
|
|
1F 5F-7D 80-B4 B6-C4 C6-D3 D6-DB DD-EF F2-F4 F6-FE
|
224 |
|
|
20 00-2E 30-46 6A-70 74-8E A0-AA D0-E1
|
225 |
|
|
21 00-38 53-82 90-EA
|
226 |
|
|
22 00-F1
|
227 |
|
|
23 00 02-7A
|
228 |
|
|
24 00-24 40-4A 60-EA
|
229 |
|
|
25 00-95 A0-EF
|
230 |
|
|
26 00-13 1A-6F
|
231 |
|
|
27 01-04 06-09 0C-27 29-4B 4D 4F-52 56 58-5E 61-67 76-94 98-AF B1-BE
|
232 |
|
|
30 00-37 3F 41-94 99-9E A1-FE
|
233 |
|
|
31 05-2C 31-8E 90-9F
|
234 |
|
|
32 00-1C 20-43 60-7B 7F-B0 C0-CB D0-FE
|
235 |
|
|
33 00-76 7B-DD E0-FE
|
236 |
|
|
FB 00-06 13-17 1E-36 38-3C 3E 40-41 43-44 46-B1 D3-FF
|
237 |
|
|
FC 00-FF
|
238 |
|
|
FD 00-3F 50-8F 92-C7 F0-FB
|
239 |
|
|
FE 20-23 30-44 49-52 54-66 68-6B 70-72 74 76-FC FF
|
240 |
|
|
FF 01-5E 61-BE C2-C7 CA-CF D2-D7 DA-DC E0-E6 E8-EE FD
|
241 |
|
|
EOH
|
242 |
|
|
!3400 4DFF
|
243 |
|
|
!4E00 9FA5
|
244 |
|
|
!E000 F8FF
|
245 |
|
|
!F900 FA2D
|
246 |
|
|
EOH
|
247 |
|
|
|
248 |
|
|
## 301 BMP-AMD.7 (ISO/IEC 10646-1:2000 A.3.1)
|
249 |
|
|
$SET_ALIAS{301} = '_BMP_AMD7';
|
250 |
|
|
$SET{_BMP_AMD7} = col2list (<<EOH) . <<EOH;
|
251 |
|
|
00 20-7E A0-FF
|
252 |
|
|
01 00-F5 FA-FF
|
253 |
|
|
02 00-17 50-A8 B0-DE E0-E9
|
254 |
|
|
03 00-45 60-61 74-75 7A 7E 84-8A 8C 8E-A1
|
255 |
|
|
03 A3-CE D0-D6 DA DC DE E0 E2-F3
|
256 |
|
|
04 01-0C 0E-4F 51-5C 5E-86 90-C4 C7-C8 CB-CC D0-EB EE-F5 F8-F9
|
257 |
|
|
05 31-56 59-5F 61-87 89 91-A1 A3-B9 BB-C4 D0-EA F0-F4
|
258 |
|
|
06 0C 1B 1F 21-3A 40-52 60-6D 70-B7 BA-BE C0-CE D0-ED F0-F9
|
259 |
|
|
09 01-03 05-39 3C-4D 50-54 58-70 81-83 85-8C
|
260 |
|
|
09 8F-90 93-A8 AA-B0 B2 B6-B9 BC BE-C4
|
261 |
|
|
09 C7-C8 CB-CD D7 DC-DD DF-E3 E6-FA
|
262 |
|
|
0A 02 05-0A 0F-10 13-28 2A-30 32-33 35-36
|
263 |
|
|
0A 38-39 3C 3E-42 47-48 4B-4D 59-5C 5E 66-74
|
264 |
|
|
0A 81-83 85-8B 8D 8F-91 93-A8 AA-B0 B2-B3
|
265 |
|
|
0A B5-B9 BC-C5 C7-C9 CB-CD D0 E0 E6-EF
|
266 |
|
|
0B 01-03 05-0C 0F-10 13-28 2A-30 32-33 36-39
|
267 |
|
|
0B 3C-43 47-48 4B-4D 56-57 5C-5D 5F-61 66-70
|
268 |
|
|
0B 82-83 85-8A 8E-90 92-25 99-9A 9C 9E-9F
|
269 |
|
|
0B A3-A4 A8-AA AE-B5 B7-B9 BE-C2 C6-C8 CA-CD D7 E7-F2
|
270 |
|
|
0C 01-03 05-0C 0E-10 12-28 2A-33 35-39 3E-44
|
271 |
|
|
0C 46-48 4A-4D 55-56 60-61 66-6F 82-83 85-8C
|
272 |
|
|
0C 8E-90 92-A8 AA-B3 B5-B9 BE-C4 C6-C8 CA-CD D5-D6 DE E0-E1 E6-EF
|
273 |
|
|
0D 02-03 05-0C 0E-10 12-28 2A-39 3E-43 46-48 4A-4D 57 60-61 66-6F
|
274 |
|
|
0E 01-3A 3F-5B 81-82 84 87-88 8A 8D 94-97
|
275 |
|
|
0E 99-9F A1-A3 A5 A7 AA-AB AD-B9 BB-BD C0-C4 C6 C8-CD D0-D9 DC-DD
|
276 |
|
|
0F 00-47 49-69 71-8B 90-95 97 99-AD B1-B7 B9
|
277 |
|
|
10 A0-C5 D0-F6 FB
|
278 |
|
|
11 00-59 5F-A2 A8-F9
|
279 |
|
|
1E 00-9B A0-F9
|
280 |
|
|
1F 00-15 18-1D 20-45 48-4D 50-57 59 5B 5D
|
281 |
|
|
1F 5F-7D 80-B4 B6-C4 C6-D3 D6-DB DD-EF F2-F4 F6-FE
|
282 |
|
|
20 00-2E 30-46 6A-70 74-8E A0-AB D0-E1
|
283 |
|
|
21 00-38 53-82 90-EA
|
284 |
|
|
22 00-F1
|
285 |
|
|
23 00 02-7A
|
286 |
|
|
24 00-24 40-4A 60-EA
|
287 |
|
|
25 00-95 A0-EF
|
288 |
|
|
26 00-13 1A-6F
|
289 |
|
|
27 01-04 06-09 0C-27 29-4B 4D 4F-52 56 58-5E 61-67 76-94 98-AF B1-BE
|
290 |
|
|
30 00-37 3F 41-94 99-9E A1-FE
|
291 |
|
|
31 05-2C 31-8E 90-9F
|
292 |
|
|
32 00-1C 20-43 60-7B 7F-B0 C0-CB D0-FE
|
293 |
|
|
33 00-76 7B-DD E0-FE
|
294 |
|
|
FB 00-06 13-17 1E-36 38-3C 3E 40-41 43-44 46-B1 D3-FF
|
295 |
|
|
FC 00-FF
|
296 |
|
|
FD 00-3F 50-8F 92-C7 F0-FB
|
297 |
|
|
FE 20-23 30-44 49-52 54-66 68-6B 70-72 74 76-FC FF
|
298 |
|
|
FF 01-5E 61-BE C2-C7 CA-CF D2-D7 DA-DC E0-E6 E8-EE FD
|
299 |
|
|
EOH
|
300 |
|
|
!4E00 9FA5
|
301 |
|
|
!AC00 D7A3
|
302 |
|
|
!E000 F8FF
|
303 |
|
|
!F900 FA2D
|
304 |
|
|
EOH
|
305 |
|
|
|
306 |
|
|
## 302 BMP SECOND EDITION (ISO/IEC 10646-1:2000 A.3.3)
|
307 |
|
|
## Warning: This list is taken from draft of 10646, so it can be incorrect.
|
308 |
|
|
$SET_ALIAS{302} = '_BMPSecondEdition';
|
309 |
|
|
$SET{_BMPSecondEdition} = col2list (<<EOH) . <<EOH;
|
310 |
|
|
00 20-7E A0-FF
|
311 |
|
|
01 00-FF
|
312 |
|
|
02 00-33 50-AD B0-EE
|
313 |
|
|
03 00-4E 60-62 74-75 7A 7E 84-8A 8C 8E-A1 A3-CE D0-D7 DA-F3
|
314 |
|
|
04 00-86 88-89 8C-CE D0-F5 F8-F9
|
315 |
|
|
05 31-56 59-5F 61-87 89-8A 91-A1 A3-B9 BB-C4 D0-EA F0-F4
|
316 |
|
|
06 0C 1B 1F 21-3A 40-55 60-6D 70-ED..F0-FE
|
317 |
|
|
07 00-0D 0F-2C 30-4A 80-BF
|
318 |
|
|
09 01-03 05-39 3C-4D 50-54 58-70 81-83 85-8C 8F-90 93-A8 AA-B0
|
319 |
|
|
09 B2 B6-B9 BC BE-C4 C7-C8 CB-CD D7 DC-DD DF-E3 E6-FA
|
320 |
|
|
0A 02 05-0A 0F-10 13-28 2A-30 32-33 35-36
|
321 |
|
|
0A 38-39 3C 3E-42 47-48 4B-4D 59-5C 5E 66-74 81-83 85-8B
|
322 |
|
|
0A 8D 8F-91 93-A8 AA-B0 B2-B3 B5-B9 BC-C5 C7-C9 CB-CD D0 E0 E6-EF
|
323 |
|
|
0B 01-03 05-0C 0F-10 13-28 2A-30 32-33 36-39
|
324 |
|
|
0B 3C-43 47-48 4B-4D 56-57 5C-5D 5F-61 66-70
|
325 |
|
|
0B 82-83 85-8A 8E-90 92-25 99-9A 9C 9E-9F
|
326 |
|
|
0B A3-A4 A8-AA AE-B5 B7-B9 BE-C2 C6-C8 CA-CD D7 E7-F2
|
327 |
|
|
0C 01-03 05-0C 0E-10 12-28 2A-33 35-39 3E-44
|
328 |
|
|
0C 46-48 4A-4D 55-56 60-61 66-6F 82-83 85-8C
|
329 |
|
|
0C 8E-90 92-A8 AA-B3 B5-B9 BE-C4 C6-C8 CA-CD D5-D6 DE E0-E1 E6-EF
|
330 |
|
|
0D 02-03 05-0C 0E-10 12-28 2A-39 3E-43 46-48
|
331 |
|
|
0D 4A-4D 57 60-61 66-6F 82-83 85-96 9A-B1
|
332 |
|
|
0D B3-BB BD C0-C6 CA CF-D4 D6 D8-DF F2-F4
|
333 |
|
|
0E 01-3A 3F-5B 81-82 84 87-88 8A 8D 94-97
|
334 |
|
|
0E 99-9F A1-A3 A5 A7 AA-AB AD-B9 BB-BD C0-C4 C6 C8-CD D0-D9 DC-DD
|
335 |
|
|
0F 00-47 49-6A 71-8B 90-97 99-BC BE-CC CF
|
336 |
|
|
10 00-21 23-27 29-2A 2C-32 36-39 40-59 A0-C5 D0-F6 FB
|
337 |
|
|
11 00-59 5F-A2 A8-F9
|
338 |
|
|
12 20-26 28-46 48 4A-4D 50-56 58 5A-5D 60-86 88 8A-8D
|
339 |
|
|
12 90-AE B0 B2-B5 B8-BE C0 C2-C5 C8-CE D0-D6 D8-EE F0-FF
|
340 |
|
|
13 00-0E 10 12-15 18-1E 20-46 48-5A 61-7C A0-F4
|
341 |
|
|
16 00-76 80-9C A0-F0
|
342 |
|
|
17 80-DC E0-E9
|
343 |
|
|
18 00-0E 10-19 20-77 80-A9
|
344 |
|
|
1E 00-9B A0-F9
|
345 |
|
|
1F 00-15 18-1D 20-45 48-4D 50-57 59 5B 5D
|
346 |
|
|
1F 5F-7D 80-B4 B6-C4 C6-D3 D6-DB DD-EF F2-F4 F6-FE
|
347 |
|
|
20 00-46 48-4D 4F 6A-70 74-8E A0-AF D0-E3
|
348 |
|
|
21 00-3A 53-83 90-F3
|
349 |
|
|
22 00-F1
|
350 |
|
|
23 00-7B 7D-9A
|
351 |
|
|
24 00-26 40-4A 60-EA
|
352 |
|
|
25 00-95 A0-F7
|
353 |
|
|
26 00-13 19-71
|
354 |
|
|
27 01-04 06-09 0C-27 29-4B 4D 4F-52 56 58-5E 61-67 76-94 98-AF B1-BE
|
355 |
|
|
28 00-FF
|
356 |
|
|
2E 80-99 9B-F3
|
357 |
|
|
2F 00-D5 F0-FB
|
358 |
|
|
30 00-3A 3E-3F 41-94 99-9E A1-FE
|
359 |
|
|
31 05-2C 31-8E 90-B7
|
360 |
|
|
32 00-1C 20-43 60-7B 7F-B0 C0-CB D0-FE
|
361 |
|
|
33 00-76 7B-DD E0-FE
|
362 |
|
|
A4 00-8C 90-A1 A4-B3 B5-C0 C2-C4 C6
|
363 |
|
|
FB 00-06 13-17 1D-36 38-3C 3E 40-41 43-44 46-B1 D3-FF
|
364 |
|
|
FC 00-FF
|
365 |
|
|
FD 00-3F 50-8F 92-C7 F0-FB
|
366 |
|
|
FE 20-23 30-44 49-52 54-66 68-6B 70-72 74 76-FC FF
|
367 |
|
|
FF 01-5E 61-BE C2-C7 CA-CF D2-D7 DA-DC E0-E6 E8-EE F9-FD
|
368 |
|
|
EOH
|
369 |
|
|
!1401 15FF
|
370 |
|
|
!4E00 9FA5
|
371 |
|
|
!AC00 D7A3
|
372 |
|
|
!E000 F8FF
|
373 |
|
|
!F900 FA2D
|
374 |
|
|
EOH
|
375 |
|
|
|
376 |
|
|
$SET{GeneralFormatCharacters} = $SET{ $SET_ALIAS{200} }.$SET{ $SET_ALIAS{201} }
|
377 |
|
|
.$SET{ $SET_ALIAS{202} }.$SET{ $SET_ALIAS{203} };
|
378 |
|
|
$SET{ScriptSpecificFormatCharacters} = $SET{ $SET_ALIAS{204} }
|
379 |
|
|
.$SET{ $SET_ALIAS{205} }.$SET{ $SET_ALIAS{206} }.$SET{ $SET_ALIAS{207} };
|
380 |
|
|
$SET_ALIAS{250} = 'GeneralFormatCharacters';
|
381 |
|
|
$SET_ALIAS{251} = 'ScriptSpecificFormatCharacters';
|
382 |
|
|
|
383 |
|
|
## 281-284 ISO/IEC 10646-1:2000 Amd.1
|
384 |
|
|
$SET_ALIAS{281} = '_MES1';
|
385 |
|
|
$SET{_MES1} = col2list (<<EOH);
|
386 |
|
|
00 20-7E A0-FF
|
387 |
|
|
01 00-13 16-2B 2E-4D 50-7E
|
388 |
|
|
02 C7 D8-DB DD
|
389 |
|
|
20 15 18-19 1C-1D AC
|
390 |
|
|
21 22 26 5B-5E 90-93
|
391 |
|
|
26 6A
|
392 |
|
|
EOH
|
393 |
|
|
|
394 |
|
|
$SET_ALIAS{282} = '_MES2';
|
395 |
|
|
$SET{_MES2} = col2list (<<EOH);
|
396 |
|
|
00 20-7E A0-FF
|
397 |
|
|
01 00-7F 8F 92 B7 DE-EF FA-FF
|
398 |
|
|
02 18-1B 1E-1F 59 7C 92 BB-BD C6-C7 C9 D8-DD EE
|
399 |
|
|
03 74-75 7A 7E 84-8A 8C 8E-A1 A3-CE D7 DA-E1
|
400 |
|
|
04 00-5F 90-C4 C7-C8 CB-CC D0-EB EE-F5 F8-F9
|
401 |
|
|
1E 02-03 0A-0B 1E-1F 40-41 56-57 60-61 6A-6B 80-85 9B F2-F3
|
402 |
|
|
1F 00-15 18-1D 20-45 48-4D 50-57 59 5B 5D 5F-7D 80-B4 B6-C4 C6-D3 D6-DB DD-EF
|
403 |
|
|
1F F2-F4 F6-FE
|
404 |
|
|
20 13-15 17-1E 20-22 26 30 32-33 39-3A 3C 3E 44 4A 7F 82 A3-A4 A7 AC AF
|
405 |
|
|
21 05 16 22 26 5B-5E 90-95 A8
|
406 |
|
|
22 00 02-03 06 08-09 0F 11-12 19-1A 1E-1F 27-2B 48 59 60-61 64-65 82-83 95 97
|
407 |
|
|
23 02 10 20-21 29-2A
|
408 |
|
|
25 00 02 0C 10 14 18 1C 24 2C 34 3C 50-6C 80 84 88 8C 90-93 A0 AC B2 BA BC C4
|
409 |
|
|
25 CA-CB D8-D9
|
410 |
|
|
26 3A-3C 40 42 60 63 65-66 6A-6B
|
411 |
|
|
FB 01-02
|
412 |
|
|
FF FD
|
413 |
|
|
EOH
|
414 |
|
|
|
415 |
|
|
$SET_ALIAS{283} = '_MES3A';
|
416 |
|
|
$SET{_MES3A} = '';
|
417 |
|
|
for (1..11, 27, 30..40, 42, 44..47, 63, 65, 70) {
|
418 |
|
|
$SET{_MES3A} .= $SET{ $SET_ALIAS{$_} };
|
419 |
|
|
}
|
420 |
|
|
|
421 |
|
|
$SET_ALIAS{284} = '_MES3B';
|
422 |
|
|
$SET{_MES3B} = col2list (<<EOH);
|
423 |
|
|
00 20-7E A0-FF
|
424 |
|
|
01 00-FF
|
425 |
|
|
02 00-1F 22-33 50-AD B0-EE
|
426 |
|
|
03 00-4E 60-62 74-75 7A 7E 84-8A 8C 8E-A1 A3-CE D0-D7 DA-F3
|
427 |
|
|
04 00-86 88-89 8C-C4 C7-C8 CB-CC D0-F5 F8-F9
|
428 |
|
|
05 31-56 59-5F 61-87 89-8A
|
429 |
|
|
10 D0-F6 FB
|
430 |
|
|
1E 00-9B A0-F9
|
431 |
|
|
1F 00-15 18-1D 20-45 48-4D 50-57 59 5B 5D 5F-7D 80-B4 B6-C4 C6-D3 D6-DB DD-EF
|
432 |
|
|
1F F2-F4 F6-FE
|
433 |
|
|
20 00-46 48-4D 6A-70 74-8E A0-AF D0-E3
|
434 |
|
|
21 00-3A 53-83 90-F3
|
435 |
|
|
22 00-F1
|
436 |
|
|
23 00-7B 7D-9A
|
437 |
|
|
24 40-4A
|
438 |
|
|
25 00-95 A0-F7
|
439 |
|
|
26 00-13 19-71
|
440 |
|
|
FB 00-06 13-17
|
441 |
|
|
FE 20-23
|
442 |
|
|
FF F9-FD
|
443 |
|
|
EOH
|
444 |
|
|
|
445 |
|
|
## 500-501 Removed by ISO/IEC 10646-1:2000 Amd.1
|
446 |
|
|
$SET{PrivateUsePlanes} = <<EOH;
|
447 |
|
|
0F0000 10FFFF
|
448 |
|
|
E00000 FFFFFF
|
449 |
|
|
EOH
|
450 |
|
|
$SET_ALIAS{500} = 'PrivateUsePlanes';
|
451 |
|
|
$SET{PrivateUseGroups} = <<EOH;
|
452 |
|
|
60000000 7FFFFFFF
|
453 |
|
|
EOH
|
454 |
|
|
$SET_ALIAS{500} = 'PrivateUseGroups';
|
455 |
|
|
|
456 |
|
|
&print_module;
|
457 |
|
|
|
458 |
|
|
## $Date: 2002/08/23 23:16:32 $
|
459 |
|
|
### UCS-src.upl ends here
|