author | Claus Gittinger <cg@exept.de> |
Mon, 08 Mar 2004 18:09:58 +0100 | |
changeset 8114 | 05274a80fcc4 |
parent 8081 | b468050174a9 |
child 8148 | dbf64e3142d9 |
permissions | -rw-r--r-- |
8081 | 1 |
"{ Package: 'stx:libbasic' }" |
2 |
||
3 |
"{ NameSpace: CharacterEncoderImplementations }" |
|
4 |
||
5 |
SingleByteEncoder subclass:#MS_Cyrillic |
|
6 |
instanceVariableNames:'' |
|
7 |
classVariableNames:'' |
|
8 |
poolDictionaries:'' |
|
9 |
category:'Collections-Text-Encodings' |
|
10 |
! |
|
11 |
||
12 |
||
13 |
!MS_Cyrillic class methodsFor:'mapping'! |
|
14 |
||
15 |
mapFileURL2_relativePathName |
|
16 |
^ 'CP1251' |
|
17 |
! |
|
18 |
||
19 |
mapping |
|
20 |
" |
|
21 |
# From: http://std.dkuug.dk/i18n/charmaps/CP1251 |
|
22 |
||
23 |
<code_set_name> CP1251 |
|
24 |
<comment_char> % |
|
25 |
<escape_char> / |
|
26 |
% version: 1.0 |
|
27 |
% repertoiremap: mnemonic,ds |
|
28 |
% source: UNICODE 1.0 |
|
29 |
||
30 |
% alias MS-CYRL |
|
31 |
CHARMAP |
|
32 |
<NU> /x00 <U0000> NULL (NUL) |
|
33 |
<SH> /x01 <U0001> START OF HEADING (SOH) |
|
34 |
<SX> /x02 <U0002> START OF TEXT (STX) |
|
35 |
<EX> /x03 <U0003> END OF TEXT (ETX) |
|
36 |
<ET> /x04 <U0004> END OF TRANSMISSION (EOT) |
|
37 |
<EQ> /x05 <U0005> ENQUIRY (ENQ) |
|
38 |
<AK> /x06 <U0006> ACKNOWLEDGE (ACK) |
|
39 |
<BL> /x07 <U0007> BELL (BEL) |
|
40 |
<BS> /x08 <U0008> BACKSPACE (BS) |
|
41 |
<HT> /x09 <U0009> CHARACTER TABULATION (HT) |
|
42 |
<LF> /x0A <U000A> LINE FEED (LF) |
|
43 |
<VT> /x0B <U000B> LINE TABULATION (VT) |
|
44 |
<FF> /x0C <U000C> FORM FEED (FF) |
|
45 |
<CR> /x0D <U000D> CARRIAGE RETURN (CR) |
|
46 |
<SO> /x0E <U000E> SHIFT OUT (SO) |
|
47 |
<SI> /x0F <U000F> SHIFT IN (SI) |
|
48 |
<DL> /x10 <U0010> DATALINK ESCAPE (DLE) |
|
49 |
<D1> /x11 <U0011> DEVICE CONTROL ONE (DC1) |
|
50 |
<D2> /x12 <U0012> DEVICE CONTROL TWO (DC2) |
|
51 |
<D3> /x13 <U0013> DEVICE CONTROL THREE (DC3) |
|
52 |
<D4> /x14 <U0014> DEVICE CONTROL FOUR (DC4) |
|
53 |
<NK> /x15 <U0015> NEGATIVE ACKNOWLEDGE (NAK) |
|
54 |
<SY> /x16 <U0016> SYNCHRONOUS IDLE (SYN) |
|
55 |
<EB> /x17 <U0017> END OF TRANSMISSION BLOCK (ETB) |
|
56 |
<CN> /x18 <U0018> CANCEL (CAN) |
|
57 |
<EM> /x19 <U0019> END OF MEDIUM (EM) |
|
58 |
<SB> /x1A <U001A> SUBSTITUTE (SUB) |
|
59 |
<EC> /x1B <U001B> ESCAPE (ESC) |
|
60 |
<FS> /x1C <U001C> FILE SEPARATOR (IS4) |
|
61 |
<GS> /x1D <U001D> GROUP SEPARATOR (IS3) |
|
62 |
<RS> /x1E <U001E> RECORD SEPARATOR (IS2) |
|
63 |
<US> /x1F <U001F> UNIT SEPARATOR (IS1) |
|
64 |
<SP> /x20 <U0020> SPACE |
|
65 |
<!!> /x21 <U0021> EXCLAMATION MARK |
|
66 |
<'> /x22 <U0022> QUOTATION MARK |
|
67 |
<Nb> /x23 <U0023> NUMBER SIGN |
|
68 |
<DO> /x24 <U0024> DOLLAR SIGN |
|
69 |
<%> /x25 <U0025> PERCENT SIGN |
|
70 |
<&> /x26 <U0026> AMPERSAND |
|
71 |
<'> /x27 <U0027> APOSTROPHE |
|
72 |
<(> /x28 <U0028> LEFT PARENTHESIS |
|
73 |
<)> /x29 <U0029> RIGHT PARENTHESIS |
|
74 |
<*> /x2A <U002A> ASTERISK |
|
75 |
<+> /x2B <U002B> PLUS SIGN |
|
76 |
<,> /x2C <U002C> COMMA |
|
77 |
<-> /x2D <U002D> HYPHEN-MINUS |
|
78 |
<.> /x2E <U002E> FULL STOP |
|
79 |
<//> /x2F <U002F> SOLIDUS |
|
80 |
<0> /x30 <U0030> DIGIT ZERO |
|
81 |
<1> /x31 <U0031> DIGIT ONE |
|
82 |
<2> /x32 <U0032> DIGIT TWO |
|
83 |
<3> /x33 <U0033> DIGIT THREE |
|
84 |
<4> /x34 <U0034> DIGIT FOUR |
|
85 |
<5> /x35 <U0035> DIGIT FIVE |
|
86 |
<6> /x36 <U0036> DIGIT SIX |
|
87 |
<7> /x37 <U0037> DIGIT SEVEN |
|
88 |
<8> /x38 <U0038> DIGIT EIGHT |
|
89 |
<9> /x39 <U0039> DIGIT NINE |
|
90 |
<:> /x3A <U003A> COLON |
|
91 |
<;> /x3B <U003B> SEMICOLON |
|
92 |
<<> /x3C <U003C> LESS-THAN SIGN |
|
93 |
<=> /x3D <U003D> EQUALS SIGN |
|
94 |
</>> /x3E <U003E> GREATER-THAN SIGN |
|
95 |
<?> /x3F <U003F> QUESTION MARK |
|
96 |
<At> /x40 <U0040> COMMERCIAL AT |
|
97 |
<A> /x41 <U0041> LATIN CAPITAL LETTER A |
|
98 |
<B> /x42 <U0042> LATIN CAPITAL LETTER B |
|
99 |
<C> /x43 <U0043> LATIN CAPITAL LETTER C |
|
100 |
<D> /x44 <U0044> LATIN CAPITAL LETTER D |
|
101 |
<E> /x45 <U0045> LATIN CAPITAL LETTER E |
|
102 |
<F> /x46 <U0046> LATIN CAPITAL LETTER F |
|
103 |
<G> /x47 <U0047> LATIN CAPITAL LETTER G |
|
104 |
<H> /x48 <U0048> LATIN CAPITAL LETTER H |
|
105 |
<I> /x49 <U0049> LATIN CAPITAL LETTER I |
|
106 |
<J> /x4A <U004A> LATIN CAPITAL LETTER J |
|
107 |
<K> /x4B <U004B> LATIN CAPITAL LETTER K |
|
108 |
<L> /x4C <U004C> LATIN CAPITAL LETTER L |
|
109 |
<M> /x4D <U004D> LATIN CAPITAL LETTER M |
|
110 |
<N> /x4E <U004E> LATIN CAPITAL LETTER N |
|
111 |
<O> /x4F <U004F> LATIN CAPITAL LETTER O |
|
112 |
<P> /x50 <U0050> LATIN CAPITAL LETTER P |
|
113 |
<Q> /x51 <U0051> LATIN CAPITAL LETTER Q |
|
114 |
<R> /x52 <U0052> LATIN CAPITAL LETTER R |
|
115 |
<S> /x53 <U0053> LATIN CAPITAL LETTER S |
|
116 |
<T> /x54 <U0054> LATIN CAPITAL LETTER T |
|
117 |
<U> /x55 <U0055> LATIN CAPITAL LETTER U |
|
118 |
<V> /x56 <U0056> LATIN CAPITAL LETTER V |
|
119 |
<W> /x57 <U0057> LATIN CAPITAL LETTER W |
|
120 |
<X> /x58 <U0058> LATIN CAPITAL LETTER X |
|
121 |
<Y> /x59 <U0059> LATIN CAPITAL LETTER Y |
|
122 |
<Z> /x5A <U005A> LATIN CAPITAL LETTER Z |
|
123 |
<<(> /x5B <U005B> LEFT SQUARE BRACKET |
|
124 |
<////> /x5C <U005C> REVERSE SOLIDUS |
|
125 |
<)/>> /x5D <U005D> RIGHT SQUARE BRACKET |
|
126 |
<'/>> /x5E <U005E> CIRCUMFLEX ACCENT |
|
127 |
<_> /x5F <U005F> LOW LINE |
|
128 |
<'!!> /x60 <U0060> GRAVE ACCENT |
|
129 |
<a> /x61 <U0061> LATIN SMALL LETTER A |
|
130 |
<b> /x62 <U0062> LATIN SMALL LETTER B |
|
131 |
<c> /x63 <U0063> LATIN SMALL LETTER C |
|
132 |
<d> /x64 <U0064> LATIN SMALL LETTER D |
|
133 |
<e> /x65 <U0065> LATIN SMALL LETTER E |
|
134 |
<f> /x66 <U0066> LATIN SMALL LETTER F |
|
135 |
<g> /x67 <U0067> LATIN SMALL LETTER G |
|
136 |
<h> /x68 <U0068> LATIN SMALL LETTER H |
|
137 |
<i> /x69 <U0069> LATIN SMALL LETTER I |
|
138 |
<j> /x6A <U006A> LATIN SMALL LETTER J |
|
139 |
<k> /x6B <U006B> LATIN SMALL LETTER K |
|
140 |
<l> /x6C <U006C> LATIN SMALL LETTER L |
|
141 |
<m> /x6D <U006D> LATIN SMALL LETTER M |
|
142 |
<n> /x6E <U006E> LATIN SMALL LETTER N |
|
143 |
<o> /x6F <U006F> LATIN SMALL LETTER O |
|
144 |
<p> /x70 <U0070> LATIN SMALL LETTER P |
|
145 |
<q> /x71 <U0071> LATIN SMALL LETTER Q |
|
146 |
<r> /x72 <U0072> LATIN SMALL LETTER R |
|
147 |
<s> /x73 <U0073> LATIN SMALL LETTER S |
|
148 |
<t> /x74 <U0074> LATIN SMALL LETTER T |
|
149 |
<u> /x75 <U0075> LATIN SMALL LETTER U |
|
150 |
<v> /x76 <U0076> LATIN SMALL LETTER V |
|
151 |
<w> /x77 <U0077> LATIN SMALL LETTER W |
|
152 |
<x> /x78 <U0078> LATIN SMALL LETTER X |
|
153 |
<y> /x79 <U0079> LATIN SMALL LETTER Y |
|
154 |
<z> /x7A <U007A> LATIN SMALL LETTER Z |
|
155 |
<(!!> /x7B <U007B> LEFT CURLY BRACKET |
|
156 |
<!!!!> /x7C <U007C> VERTICAL LINE |
|
157 |
<!!)> /x7D <U007D> RIGHT CURLY BRACKET |
|
158 |
<'?> /x7E <U007E> TILDE |
|
159 |
<DT> /x7F <U007F> DELETE (DEL) |
|
160 |
<D%> /x80 <U0402> CYRILLIC CAPITAL LETTER DJE (Serbocroatian) |
|
161 |
<G%> /x81 <U0403> CYRILLIC CAPITAL LETTER GJE |
|
162 |
<.9> /x82 <U201A> SINGLE LOW-9 QUOTATION MARK |
|
163 |
<g%> /x83 <U0453> CYRILLIC SMALL LETTER GJE |
|
164 |
<:9> /x84 <U201E> DOUBLE LOW-9 QUOTATION MARK |
|
165 |
<.3> /x85 <U2026> HORIZONTAL ELLIPSIS |
|
166 |
<//-> /x86 <U2020> DAGGER |
|
167 |
<//=> /x87 <U2021> DOUBLE DAGGER |
|
168 |
<%0> /x89 <U2030> PER MILLE SIGN |
|
169 |
<LJ> /x8A <U0409> CYRILLIC CAPITAL LETTER LJE |
|
170 |
<<1> /x8B <U2039> SINGLE LEFT-POINTING ANGLE QUOTATION MARK |
|
171 |
<NJ> /x8C <U040A> CYRILLIC CAPITAL LETTER NJE |
|
172 |
<KJ> /x8D <U040C> CYRILLIC CAPITAL LETTER KJE |
|
173 |
<Ts> /x8E <U040B> CYRILLIC CAPITAL LETTER TSHE (Serbocroatian) |
|
174 |
<DZ> /x8F <U040F> CYRILLIC CAPITAL LETTER DZHE |
|
175 |
<d%> /x90 <U0452> CYRILLIC SMALL LETTER DJE (Serbocroatian) |
|
176 |
<'6> /x91 <U2018> LEFT SINGLE QUOTATION MARK |
|
177 |
<'9> /x92 <U2019> RIGHT SINGLE QUOTATION MARK |
|
178 |
<'6> /x93 <U201C> LEFT DOUBLE QUOTATION MARK |
|
179 |
<'9> /x94 <U201D> RIGHT DOUBLE QUOTATION MARK |
|
180 |
<sb> /x95 <U2022> BULLET |
|
181 |
<-N> /x96 <U2013> EN DASH |
|
182 |
<-M> /x97 <U2014> EM DASH |
|
183 |
<TM> /x99 <U2122> TRADE MARK SIGN |
|
184 |
<lj> /x9A <U0459> CYRILLIC SMALL LETTER LJE |
|
185 |
</>1> /x9B <U203A> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK |
|
186 |
<nj> /x9C <U045A> CYRILLIC SMALL LETTER NJE |
|
187 |
<kj> /x9D <U045C> CYRILLIC SMALL LETTER KJE |
|
188 |
<ts> /x9E <U045B> CYRILLIC SMALL LETTER TSHE (Serbocroatian) |
|
189 |
<dz> /x9F <U045F> CYRILLIC SMALL LETTER DZHE |
|
190 |
<NS> /xA0 <U00A0> NO-BREAK SPACE |
|
191 |
<V%> /xA1 <U040E> CYRILLIC CAPITAL LETTER SHORT U (Byelorussian) |
|
192 |
<v%> /xA2 <U045E> CYRILLIC SMALL LETTER SHORT U (Byelorussian) |
|
193 |
<J%> /xA3 <U0408> CYRILLIC CAPITAL LETTER JE |
|
194 |
<Cu> /xA4 <U00A4> CURRENCY SIGN |
|
195 |
<G3> /xA5 <U0490> CYRILLIC CAPITAL LETTER GHE WITH UPTURN |
|
196 |
<BB> /xA6 <U00A6> BROKEN BAR |
|
197 |
<SE> /xA7 <U00A7> SECTION SIGN |
|
198 |
<IO> /xA8 <U0401> CYRILLIC CAPITAL LETTER IO |
|
199 |
<Co> /xA9 <U00A9> COPYRIGHT SIGN |
|
200 |
<IE> /xAA <U0404> CYRILLIC CAPITAL LETTER UKRAINIAN IE |
|
201 |
<<<> /xAB <U00AB> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK |
|
202 |
<NO> /xAC <U00AC> NOT SIGN |
|
203 |
<--> /xAD <U00AD> SOFT HYPHEN |
|
204 |
<Rg> /xAE <U00AE> REGISTERED SIGN |
|
205 |
<YI> /xAF <U0407> CYRILLIC CAPITAL LETTER YI (Ukrainian) |
|
206 |
<DG> /xB0 <U00B0> DEGREE SIGN |
|
207 |
<+-> /xB1 <U00B1> PLUS-MINUS SIGN |
|
208 |
<II> /xB2 <U0406> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I |
|
209 |
<ii> /xB3 <U0456> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I |
|
210 |
<g3> /xB4 <U0491> CYRILLIC SMALL LETTER GHE WITH UPTURN |
|
211 |
<My> /xB5 <U00B5> MICRO SIGN |
|
212 |
<PI> /xB6 <U00B6> PILCROW SIGN |
|
213 |
<.M> /xB7 <U00B7> MIDDLE DOT |
|
214 |
<io> /xB8 <U0451> CYRILLIC SMALL LETTER IO |
|
215 |
<N0> /xB9 <U2116> NUMERO SIGN |
|
216 |
<ie> /xBA <U0454> CYRILLIC SMALL LETTER UKRAINIAN IE |
|
217 |
</>/>> /xBB <U00BB> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK |
|
218 |
<j%> /xBC <U0458> CYRILLIC SMALL LETTER JE |
|
219 |
<DS> /xBD <U0405> CYRILLIC CAPITAL LETTER DZE |
|
220 |
<ds> /xBE <U0455> CYRILLIC SMALL LETTER DZE |
|
221 |
<yi> /xBF <U0457> CYRILLIC SMALL LETTER YI (Ukrainian) |
|
222 |
<A=> /xC0 <U0410> CYRILLIC CAPITAL LETTER A |
|
223 |
<B=> /xC1 <U0411> CYRILLIC CAPITAL LETTER BE |
|
224 |
<V=> /xC2 <U0412> CYRILLIC CAPITAL LETTER VE |
|
225 |
<G=> /xC3 <U0413> CYRILLIC CAPITAL LETTER GHE |
|
226 |
<D=> /xC4 <U0414> CYRILLIC CAPITAL LETTER DE |
|
227 |
<E=> /xC5 <U0415> CYRILLIC CAPITAL LETTER IE |
|
228 |
<Z%> /xC6 <U0416> CYRILLIC CAPITAL LETTER ZHE |
|
229 |
<Z=> /xC7 <U0417> CYRILLIC CAPITAL LETTER ZE |
|
230 |
<I=> /xC8 <U0418> CYRILLIC CAPITAL LETTER I |
|
231 |
<J=> /xC9 <U0419> CYRILLIC CAPITAL LETTER SHORT I |
|
232 |
<K=> /xCA <U041A> CYRILLIC CAPITAL LETTER KA |
|
233 |
<L=> /xCB <U041B> CYRILLIC CAPITAL LETTER EL |
|
234 |
<M=> /xCC <U041C> CYRILLIC CAPITAL LETTER EM |
|
235 |
<N=> /xCD <U041D> CYRILLIC CAPITAL LETTER EN |
|
236 |
<O=> /xCE <U041E> CYRILLIC CAPITAL LETTER O |
|
237 |
<P=> /xCF <U041F> CYRILLIC CAPITAL LETTER PE |
|
238 |
<R=> /xD0 <U0420> CYRILLIC CAPITAL LETTER ER |
|
239 |
<S=> /xD1 <U0421> CYRILLIC CAPITAL LETTER ES |
|
240 |
<T=> /xD2 <U0422> CYRILLIC CAPITAL LETTER TE |
|
241 |
<U=> /xD3 <U0423> CYRILLIC CAPITAL LETTER U |
|
242 |
<F=> /xD4 <U0424> CYRILLIC CAPITAL LETTER EF |
|
243 |
<H=> /xD5 <U0425> CYRILLIC CAPITAL LETTER HA |
|
244 |
<C=> /xD6 <U0426> CYRILLIC CAPITAL LETTER TSE |
|
245 |
<C%> /xD7 <U0427> CYRILLIC CAPITAL LETTER CHE |
|
246 |
<S%> /xD8 <U0428> CYRILLIC CAPITAL LETTER SHA |
|
247 |
<Sc> /xD9 <U0429> CYRILLIC CAPITAL LETTER SHCHA |
|
248 |
<='> /xDA <U042A> CYRILLIC CAPITAL LETTER HARD SIGN |
|
249 |
<Y=> /xDB <U042B> CYRILLIC CAPITAL LETTER YERU |
|
250 |
<%'> /xDC <U042C> CYRILLIC CAPITAL LETTER SOFT SIGN |
|
251 |
<JE> /xDD <U042D> CYRILLIC CAPITAL LETTER E |
|
252 |
<JU> /xDE <U042E> CYRILLIC CAPITAL LETTER YU |
|
253 |
<JA> /xDF <U042F> CYRILLIC CAPITAL LETTER YA |
|
254 |
<a=> /xE0 <U0430> CYRILLIC SMALL LETTER A |
|
255 |
<b=> /xE1 <U0431> CYRILLIC SMALL LETTER BE |
|
256 |
<v=> /xE2 <U0432> CYRILLIC SMALL LETTER VE |
|
257 |
<g=> /xE3 <U0433> CYRILLIC SMALL LETTER GHE |
|
258 |
<d=> /xE4 <U0434> CYRILLIC SMALL LETTER DE |
|
259 |
<e=> /xE5 <U0435> CYRILLIC SMALL LETTER IE |
|
260 |
<z%> /xE6 <U0436> CYRILLIC SMALL LETTER ZHE |
|
261 |
<z=> /xE7 <U0437> CYRILLIC SMALL LETTER ZE |
|
262 |
<i=> /xE8 <U0438> CYRILLIC SMALL LETTER I |
|
263 |
<j=> /xE9 <U0439> CYRILLIC SMALL LETTER SHORT I |
|
264 |
<k=> /xEA <U043A> CYRILLIC SMALL LETTER KA |
|
265 |
<l=> /xEB <U043B> CYRILLIC SMALL LETTER EL |
|
266 |
<m=> /xEC <U043C> CYRILLIC SMALL LETTER EM |
|
267 |
<n=> /xED <U043D> CYRILLIC SMALL LETTER EN |
|
268 |
<o=> /xEE <U043E> CYRILLIC SMALL LETTER O |
|
269 |
<p=> /xEF <U043F> CYRILLIC SMALL LETTER PE |
|
270 |
<r=> /xF0 <U0440> CYRILLIC SMALL LETTER ER |
|
271 |
<s=> /xF1 <U0441> CYRILLIC SMALL LETTER ES |
|
272 |
<t=> /xF2 <U0442> CYRILLIC SMALL LETTER TE |
|
273 |
<u=> /xF3 <U0443> CYRILLIC SMALL LETTER U |
|
274 |
<f=> /xF4 <U0444> CYRILLIC SMALL LETTER EF |
|
275 |
<h=> /xF5 <U0445> CYRILLIC SMALL LETTER HA |
|
276 |
<c=> /xF6 <U0446> CYRILLIC SMALL LETTER TSE |
|
277 |
<c%> /xF7 <U0447> CYRILLIC SMALL LETTER CHE |
|
278 |
<s%> /xF8 <U0448> CYRILLIC SMALL LETTER SHA |
|
279 |
<sc> /xF9 <U0449> CYRILLIC SMALL LETTER SHCHA |
|
280 |
<='> /xFA <U044A> CYRILLIC SMALL LETTER HARD SIGN |
|
281 |
<y=> /xFB <U044B> CYRILLIC SMALL LETTER YERU |
|
282 |
<%'> /xFC <U044C> CYRILLIC SMALL LETTER SOFT SIGN |
|
283 |
<je> /xFD <U044D> CYRILLIC SMALL LETTER E |
|
284 |
<ju> /xFE <U044E> CYRILLIC SMALL LETTER YU |
|
285 |
<ja> /xFF <U044F> CYRILLIC SMALL LETTER YA |
|
286 |
END CHARMAP |
|
287 |
||
288 |
" |
|
289 |
! ! |
|
290 |
||
291 |
!MS_Cyrillic class methodsFor:'documentation'! |
|
292 |
||
293 |
version |
|
8114
05274a80fcc4
separated implementation into dynamically (lazy) loaded classes
Claus Gittinger <cg@exept.de>
parents:
8081
diff
changeset
|
294 |
^ '$Header: /cvs/stx/stx/libbasic/CharacterEncoderImplementations__MS_Cyrillic.st,v 1.2 2004-03-08 17:08:37 cg Exp $' |
8081 | 295 |
! ! |