author | Claus Gittinger <cg@exept.de> |
Wed, 26 Jun 2019 22:06:12 +0200 | |
changeset 24369 | e796791ea838 |
parent 22589 | a54279da036e |
permissions | -rw-r--r-- |
17624
acb2e49fb3ab
class: CharacterEncoderImplementations::MS_Ansi
Stefan Vogel <sv@exept.de>
parents:
14560
diff
changeset
|
1 |
"{ Encoding: utf8 }" |
acb2e49fb3ab
class: CharacterEncoderImplementations::MS_Ansi
Stefan Vogel <sv@exept.de>
parents:
14560
diff
changeset
|
2 |
|
8148 | 3 |
" |
4 |
COPYRIGHT (c) 2004 by eXept Software AG |
|
5 |
All Rights Reserved |
|
6 |
||
7 |
This software is furnished under a license and may be used |
|
8 |
only in accordance with the terms of that license and with the |
|
9 |
inclusion of the above copyright notice. This software may not |
|
10 |
be provided or otherwise made available to, or used by, any |
|
11 |
other person. No title to or ownership of the software is |
|
12 |
hereby transferred. |
|
13 |
" |
|
8081 | 14 |
"{ Package: 'stx:libbasic' }" |
15 |
||
16 |
"{ NameSpace: CharacterEncoderImplementations }" |
|
17 |
||
22501 | 18 |
VariableBytesEncoder subclass:#MS_Ansi |
8081 | 19 |
instanceVariableNames:'' |
20 |
classVariableNames:'' |
|
21 |
poolDictionaries:'' |
|
22 |
category:'Collections-Text-Encodings' |
|
23 |
! |
|
24 |
||
8148 | 25 |
!MS_Ansi class methodsFor:'documentation'! |
26 |
||
27 |
copyright |
|
28 |
" |
|
29 |
COPYRIGHT (c) 2004 by eXept Software AG |
|
30 |
All Rights Reserved |
|
31 |
||
32 |
This software is furnished under a license and may be used |
|
33 |
only in accordance with the terms of that license and with the |
|
34 |
inclusion of the above copyright notice. This software may not |
|
35 |
be provided or otherwise made available to, or used by, any |
|
36 |
other person. No title to or ownership of the software is |
|
37 |
hereby transferred. |
|
38 |
" |
|
8813 | 39 |
! |
40 |
||
41 |
documentation |
|
42 |
" |
|
22585 | 43 |
Microsoft ANSI - which is what Microsoft thought what is ANSI coding in the 80s (whatever that should be). |
22501 | 44 |
It is definitely not an ANSI standard!! |
45 |
||
22585 | 46 |
In fact it is CP1252 encoding which is based on iso8859-1. |
22583 | 47 |
Codepoints 0x80–0x9F which are control characters |
22501 | 48 |
in iso8859 are mapped to special windows characters. |
49 |
||
50 |
Apparently, meanwhile Microsoft supports codepoints above 0xff as unicode. |
|
22585 | 51 |
We map unicode codepoints which are defined in CP1552 to CP1552, |
52 |
and leave others unchanged. |
|
53 |
So this encoder will return characters above 0xFF if required. |
|
54 |
(compare to MS_CP1252, which does not) |
|
8813 | 55 |
|
56 |
[see with:] |
|
57 |
CharacterEncoderImplementations::MS_Ansi showCharacterSet |
|
58 |
||
59 |
[author:] |
|
60 |
Claus Gittinger |
|
61 |
" |
|
8148 | 62 |
! ! |
8081 | 63 |
|
64 |
!MS_Ansi class methodsFor:'mapping'! |
|
65 |
||
66 |
mapFileURL2_relativePathName |
|
67 |
^ 'CP1252' |
|
8813 | 68 |
|
69 |
" |
|
70 |
self generateCode |
|
71 |
" |
|
8081 | 72 |
! |
73 |
||
74 |
mapping |
|
75 |
" |
|
76 |
# From: http://std.dkuug.dk/i18n/charmaps/CP1252 |
|
77 |
||
78 |
<code_set_name> CP1252 |
|
79 |
<comment_char> % |
|
80 |
<escape_char> / |
|
81 |
% version: 1.0 |
|
82 |
% repertoiremap: mnemonic,ds |
|
83 |
% source: UNICODE 1.0 |
|
84 |
||
85 |
% alias MS-ANSI |
|
86 |
CHARMAP |
|
87 |
<NU> /x00 <U0000> NULL (NUL) |
|
88 |
<SH> /x01 <U0001> START OF HEADING (SOH) |
|
89 |
<SX> /x02 <U0002> START OF TEXT (STX) |
|
90 |
<EX> /x03 <U0003> END OF TEXT (ETX) |
|
91 |
<ET> /x04 <U0004> END OF TRANSMISSION (EOT) |
|
92 |
<EQ> /x05 <U0005> ENQUIRY (ENQ) |
|
93 |
<AK> /x06 <U0006> ACKNOWLEDGE (ACK) |
|
94 |
<BL> /x07 <U0007> BELL (BEL) |
|
95 |
<BS> /x08 <U0008> BACKSPACE (BS) |
|
96 |
<HT> /x09 <U0009> CHARACTER TABULATION (HT) |
|
97 |
<LF> /x0A <U000A> LINE FEED (LF) |
|
98 |
<VT> /x0B <U000B> LINE TABULATION (VT) |
|
99 |
<FF> /x0C <U000C> FORM FEED (FF) |
|
100 |
<CR> /x0D <U000D> CARRIAGE RETURN (CR) |
|
101 |
<SO> /x0E <U000E> SHIFT OUT (SO) |
|
102 |
<SI> /x0F <U000F> SHIFT IN (SI) |
|
103 |
<DL> /x10 <U0010> DATALINK ESCAPE (DLE) |
|
104 |
<D1> /x11 <U0011> DEVICE CONTROL ONE (DC1) |
|
105 |
<D2> /x12 <U0012> DEVICE CONTROL TWO (DC2) |
|
106 |
<D3> /x13 <U0013> DEVICE CONTROL THREE (DC3) |
|
107 |
<D4> /x14 <U0014> DEVICE CONTROL FOUR (DC4) |
|
108 |
<NK> /x15 <U0015> NEGATIVE ACKNOWLEDGE (NAK) |
|
109 |
<SY> /x16 <U0016> SYNCHRONOUS IDLE (SYN) |
|
110 |
<EB> /x17 <U0017> END OF TRANSMISSION BLOCK (ETB) |
|
111 |
<CN> /x18 <U0018> CANCEL (CAN) |
|
112 |
<EM> /x19 <U0019> END OF MEDIUM (EM) |
|
113 |
<SB> /x1A <U001A> SUBSTITUTE (SUB) |
|
114 |
<EC> /x1B <U001B> ESCAPE (ESC) |
|
115 |
<FS> /x1C <U001C> FILE SEPARATOR (IS4) |
|
116 |
<GS> /x1D <U001D> GROUP SEPARATOR (IS3) |
|
117 |
<RS> /x1E <U001E> RECORD SEPARATOR (IS2) |
|
118 |
<US> /x1F <U001F> UNIT SEPARATOR (IS1) |
|
119 |
<SP> /x20 <U0020> SPACE |
|
120 |
<!!> /x21 <U0021> EXCLAMATION MARK |
|
121 |
<'> /x22 <U0022> QUOTATION MARK |
|
122 |
<Nb> /x23 <U0023> NUMBER SIGN |
|
123 |
<DO> /x24 <U0024> DOLLAR SIGN |
|
124 |
<%> /x25 <U0025> PERCENT SIGN |
|
125 |
<&> /x26 <U0026> AMPERSAND |
|
126 |
<'> /x27 <U0027> APOSTROPHE |
|
127 |
<(> /x28 <U0028> LEFT PARENTHESIS |
|
128 |
<)> /x29 <U0029> RIGHT PARENTHESIS |
|
129 |
<*> /x2A <U002A> ASTERISK |
|
130 |
<+> /x2B <U002B> PLUS SIGN |
|
131 |
<,> /x2C <U002C> COMMA |
|
132 |
<-> /x2D <U002D> HYPHEN-MINUS |
|
133 |
<.> /x2E <U002E> FULL STOP |
|
134 |
<//> /x2F <U002F> SOLIDUS |
|
135 |
<0> /x30 <U0030> DIGIT ZERO |
|
136 |
<1> /x31 <U0031> DIGIT ONE |
|
137 |
<2> /x32 <U0032> DIGIT TWO |
|
138 |
<3> /x33 <U0033> DIGIT THREE |
|
139 |
<4> /x34 <U0034> DIGIT FOUR |
|
140 |
<5> /x35 <U0035> DIGIT FIVE |
|
141 |
<6> /x36 <U0036> DIGIT SIX |
|
142 |
<7> /x37 <U0037> DIGIT SEVEN |
|
143 |
<8> /x38 <U0038> DIGIT EIGHT |
|
144 |
<9> /x39 <U0039> DIGIT NINE |
|
145 |
<:> /x3A <U003A> COLON |
|
146 |
<;> /x3B <U003B> SEMICOLON |
|
147 |
<<> /x3C <U003C> LESS-THAN SIGN |
|
148 |
<=> /x3D <U003D> EQUALS SIGN |
|
149 |
</>> /x3E <U003E> GREATER-THAN SIGN |
|
150 |
<?> /x3F <U003F> QUESTION MARK |
|
151 |
<At> /x40 <U0040> COMMERCIAL AT |
|
152 |
<A> /x41 <U0041> LATIN CAPITAL LETTER A |
|
153 |
<B> /x42 <U0042> LATIN CAPITAL LETTER B |
|
154 |
<C> /x43 <U0043> LATIN CAPITAL LETTER C |
|
155 |
<D> /x44 <U0044> LATIN CAPITAL LETTER D |
|
156 |
<E> /x45 <U0045> LATIN CAPITAL LETTER E |
|
157 |
<F> /x46 <U0046> LATIN CAPITAL LETTER F |
|
158 |
<G> /x47 <U0047> LATIN CAPITAL LETTER G |
|
159 |
<H> /x48 <U0048> LATIN CAPITAL LETTER H |
|
160 |
<I> /x49 <U0049> LATIN CAPITAL LETTER I |
|
161 |
<J> /x4A <U004A> LATIN CAPITAL LETTER J |
|
162 |
<K> /x4B <U004B> LATIN CAPITAL LETTER K |
|
163 |
<L> /x4C <U004C> LATIN CAPITAL LETTER L |
|
164 |
<M> /x4D <U004D> LATIN CAPITAL LETTER M |
|
165 |
<N> /x4E <U004E> LATIN CAPITAL LETTER N |
|
166 |
<O> /x4F <U004F> LATIN CAPITAL LETTER O |
|
167 |
<P> /x50 <U0050> LATIN CAPITAL LETTER P |
|
168 |
<Q> /x51 <U0051> LATIN CAPITAL LETTER Q |
|
169 |
<R> /x52 <U0052> LATIN CAPITAL LETTER R |
|
170 |
<S> /x53 <U0053> LATIN CAPITAL LETTER S |
|
171 |
<T> /x54 <U0054> LATIN CAPITAL LETTER T |
|
172 |
<U> /x55 <U0055> LATIN CAPITAL LETTER U |
|
173 |
<V> /x56 <U0056> LATIN CAPITAL LETTER V |
|
174 |
<W> /x57 <U0057> LATIN CAPITAL LETTER W |
|
175 |
<X> /x58 <U0058> LATIN CAPITAL LETTER X |
|
176 |
<Y> /x59 <U0059> LATIN CAPITAL LETTER Y |
|
177 |
<Z> /x5A <U005A> LATIN CAPITAL LETTER Z |
|
178 |
<<(> /x5B <U005B> LEFT SQUARE BRACKET |
|
179 |
<////> /x5C <U005C> REVERSE SOLIDUS |
|
180 |
<)/>> /x5D <U005D> RIGHT SQUARE BRACKET |
|
181 |
<'/>> /x5E <U005E> CIRCUMFLEX ACCENT |
|
182 |
<_> /x5F <U005F> LOW LINE |
|
183 |
<'!!> /x60 <U0060> GRAVE ACCENT |
|
184 |
<a> /x61 <U0061> LATIN SMALL LETTER A |
|
185 |
<b> /x62 <U0062> LATIN SMALL LETTER B |
|
186 |
<c> /x63 <U0063> LATIN SMALL LETTER C |
|
187 |
<d> /x64 <U0064> LATIN SMALL LETTER D |
|
188 |
<e> /x65 <U0065> LATIN SMALL LETTER E |
|
189 |
<f> /x66 <U0066> LATIN SMALL LETTER F |
|
190 |
<g> /x67 <U0067> LATIN SMALL LETTER G |
|
191 |
<h> /x68 <U0068> LATIN SMALL LETTER H |
|
192 |
<i> /x69 <U0069> LATIN SMALL LETTER I |
|
193 |
<j> /x6A <U006A> LATIN SMALL LETTER J |
|
194 |
<k> /x6B <U006B> LATIN SMALL LETTER K |
|
195 |
<l> /x6C <U006C> LATIN SMALL LETTER L |
|
196 |
<m> /x6D <U006D> LATIN SMALL LETTER M |
|
197 |
<n> /x6E <U006E> LATIN SMALL LETTER N |
|
198 |
<o> /x6F <U006F> LATIN SMALL LETTER O |
|
199 |
<p> /x70 <U0070> LATIN SMALL LETTER P |
|
200 |
<q> /x71 <U0071> LATIN SMALL LETTER Q |
|
201 |
<r> /x72 <U0072> LATIN SMALL LETTER R |
|
202 |
<s> /x73 <U0073> LATIN SMALL LETTER S |
|
203 |
<t> /x74 <U0074> LATIN SMALL LETTER T |
|
204 |
<u> /x75 <U0075> LATIN SMALL LETTER U |
|
205 |
<v> /x76 <U0076> LATIN SMALL LETTER V |
|
206 |
<w> /x77 <U0077> LATIN SMALL LETTER W |
|
207 |
<x> /x78 <U0078> LATIN SMALL LETTER X |
|
208 |
<y> /x79 <U0079> LATIN SMALL LETTER Y |
|
209 |
<z> /x7A <U007A> LATIN SMALL LETTER Z |
|
210 |
<(!!> /x7B <U007B> LEFT CURLY BRACKET |
|
211 |
<!!!!> /x7C <U007C> VERTICAL LINE |
|
212 |
<!!)> /x7D <U007D> RIGHT CURLY BRACKET |
|
213 |
<'?> /x7E <U007E> TILDE |
|
214 |
<DT> /x7F <U007F> DELETE (DEL) |
|
215 |
<.9> /x82 <U201A> SINGLE LOW-9 QUOTATION MARK |
|
216 |
<f2> /x83 <U0192> LATIN SMALL LETTER F WITH HOOK |
|
217 |
<:9> /x84 <U201E> DOUBLE LOW-9 QUOTATION MARK |
|
218 |
<.3> /x85 <U2026> HORIZONTAL ELLIPSIS |
|
219 |
<//-> /x86 <U2020> DAGGER |
|
220 |
<//=> /x87 <U2021> DOUBLE DAGGER |
|
221 |
<1/>> /x88 <U02C6> MODIFIER LETTER CIRCUMFLEX ACCENT |
|
222 |
<%0> /x89 <U2030> PER MILLE SIGN |
|
223 |
<S<> /x8A <U0160> LATIN CAPITAL LETTER S WITH CARON |
|
224 |
<<1> /x8B <U2039> SINGLE LEFT-POINTING ANGLE QUOTATION MARK |
|
225 |
<OE> /x8C <U0152> LATIN CAPITAL LIGATURE OE |
|
226 |
<'6> /x91 <U2018> LEFT SINGLE QUOTATION MARK |
|
227 |
<'9> /x92 <U2019> RIGHT SINGLE QUOTATION MARK |
|
228 |
<'6> /x93 <U201C> LEFT DOUBLE QUOTATION MARK |
|
229 |
<'9> /x94 <U201D> RIGHT DOUBLE QUOTATION MARK |
|
230 |
<sb> /x95 <U2022> BULLET |
|
231 |
<-N> /x96 <U2013> EN DASH |
|
232 |
<-M> /x97 <U2014> EM DASH |
|
233 |
<1?> /x98 <U02DC> SMALL TILDE |
|
234 |
<TM> /x99 <U2122> TRADE MARK SIGN |
|
235 |
<s<> /x9A <U0161> LATIN SMALL LETTER S WITH CARON |
|
236 |
</>1> /x9B <U203A> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK |
|
237 |
<oe> /x9C <U0153> LATIN SMALL LIGATURE OE |
|
238 |
<Y:> /x9F <U0178> LATIN CAPITAL LETTER Y WITH DIAERESIS |
|
239 |
<NS> /xA0 <U00A0> NO-BREAK SPACE |
|
240 |
<!!I> /xA1 <U00A1> INVERTED EXCLAMATION MARK |
|
241 |
<Ct> /xA2 <U00A2> CENT SIGN |
|
242 |
<Pd> /xA3 <U00A3> POUND SIGN |
|
243 |
<Cu> /xA4 <U00A4> CURRENCY SIGN |
|
244 |
<Ye> /xA5 <U00A5> YEN SIGN |
|
245 |
<BB> /xA6 <U00A6> BROKEN BAR |
|
246 |
<SE> /xA7 <U00A7> SECTION SIGN |
|
247 |
<':> /xA8 <U00A8> DIAERESIS |
|
248 |
<Co> /xA9 <U00A9> COPYRIGHT SIGN |
|
249 |
<-a> /xAA <U00AA> FEMININE ORDINAL INDICATOR |
|
250 |
<<<> /xAB <U00AB> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK |
|
251 |
<NO> /xAC <U00AC> NOT SIGN |
|
252 |
<--> /xAD <U00AD> SOFT HYPHEN |
|
253 |
<Rg> /xAE <U00AE> REGISTERED SIGN |
|
254 |
<'m> /xAF <U00AF> MACRON |
|
255 |
<DG> /xB0 <U00B0> DEGREE SIGN |
|
256 |
<+-> /xB1 <U00B1> PLUS-MINUS SIGN |
|
257 |
<2S> /xB2 <U00B2> SUPERSCRIPT TWO |
|
258 |
<3S> /xB3 <U00B3> SUPERSCRIPT THREE |
|
259 |
<''> /xB4 <U00B4> ACUTE ACCENT |
|
260 |
<My> /xB5 <U00B5> MICRO SIGN |
|
261 |
<PI> /xB6 <U00B6> PILCROW SIGN |
|
262 |
<.M> /xB7 <U00B7> MIDDLE DOT |
|
263 |
<',> /xB8 <U00B8> CEDILLA |
|
264 |
<1S> /xB9 <U00B9> SUPERSCRIPT ONE |
|
265 |
<-o> /xBA <U00BA> MASCULINE ORDINAL INDICATOR |
|
266 |
</>/>> /xBB <U00BB> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK |
|
267 |
<14> /xBC <U00BC> VULGAR FRACTION ONE QUARTER |
|
268 |
<12> /xBD <U00BD> VULGAR FRACTION ONE HALF |
|
269 |
<34> /xBE <U00BE> VULGAR FRACTION THREE QUARTERS |
|
270 |
<?I> /xBF <U00BF> INVERTED QUESTION MARK |
|
271 |
<A!!> /xC0 <U00C0> LATIN CAPITAL LETTER A WITH GRAVE |
|
272 |
<A'> /xC1 <U00C1> LATIN CAPITAL LETTER A WITH ACUTE |
|
273 |
<A/>> /xC2 <U00C2> LATIN CAPITAL LETTER A WITH CIRCUMFLEX |
|
274 |
<A?> /xC3 <U00C3> LATIN CAPITAL LETTER A WITH TILDE |
|
275 |
<A:> /xC4 <U00C4> LATIN CAPITAL LETTER A WITH DIAERESIS |
|
276 |
<AA> /xC5 <U00C5> LATIN CAPITAL LETTER A WITH RING ABOVE |
|
277 |
<AE> /xC6 <U00C6> LATIN CAPITAL LETTER AE |
|
278 |
<C,> /xC7 <U00C7> LATIN CAPITAL LETTER C WITH CEDILLA |
|
279 |
<E!!> /xC8 <U00C8> LATIN CAPITAL LETTER E WITH GRAVE |
|
280 |
<E'> /xC9 <U00C9> LATIN CAPITAL LETTER E WITH ACUTE |
|
281 |
<E/>> /xCA <U00CA> LATIN CAPITAL LETTER E WITH CIRCUMFLEX |
|
282 |
<E:> /xCB <U00CB> LATIN CAPITAL LETTER E WITH DIAERESIS |
|
283 |
<I!!> /xCC <U00CC> LATIN CAPITAL LETTER I WITH GRAVE |
|
284 |
<I'> /xCD <U00CD> LATIN CAPITAL LETTER I WITH ACUTE |
|
285 |
<I/>> /xCE <U00CE> LATIN CAPITAL LETTER I WITH CIRCUMFLEX |
|
286 |
<I:> /xCF <U00CF> LATIN CAPITAL LETTER I WITH DIAERESIS |
|
287 |
<D-> /xD0 <U00D0> LATIN CAPITAL LETTER ETH (Icelandic) |
|
288 |
<N?> /xD1 <U00D1> LATIN CAPITAL LETTER N WITH TILDE |
|
289 |
<O!!> /xD2 <U00D2> LATIN CAPITAL LETTER O WITH GRAVE |
|
290 |
<O'> /xD3 <U00D3> LATIN CAPITAL LETTER O WITH ACUTE |
|
291 |
<O/>> /xD4 <U00D4> LATIN CAPITAL LETTER O WITH CIRCUMFLEX |
|
292 |
<O?> /xD5 <U00D5> LATIN CAPITAL LETTER O WITH TILDE |
|
293 |
<O:> /xD6 <U00D6> LATIN CAPITAL LETTER O WITH DIAERESIS |
|
294 |
<*X> /xD7 <U00D7> MULTIPLICATION SIGN |
|
295 |
<O//> /xD8 <U00D8> LATIN CAPITAL LETTER O WITH STROKE |
|
296 |
<U!!> /xD9 <U00D9> LATIN CAPITAL LETTER U WITH GRAVE |
|
297 |
<U'> /xDA <U00DA> LATIN CAPITAL LETTER U WITH ACUTE |
|
298 |
<U/>> /xDB <U00DB> LATIN CAPITAL LETTER U WITH CIRCUMFLEX |
|
299 |
<U:> /xDC <U00DC> LATIN CAPITAL LETTER U WITH DIAERESIS |
|
300 |
<Y'> /xDD <U00DD> LATIN CAPITAL LETTER Y WITH ACUTE |
|
301 |
<TH> /xDE <U00DE> LATIN CAPITAL LETTER THORN (Icelandic) |
|
302 |
<ss> /xDF <U00DF> LATIN SMALL LETTER SHARP S (German) |
|
303 |
<a!!> /xE0 <U00E0> LATIN SMALL LETTER A WITH GRAVE |
|
304 |
<a'> /xE1 <U00E1> LATIN SMALL LETTER A WITH ACUTE |
|
305 |
<a/>> /xE2 <U00E2> LATIN SMALL LETTER A WITH CIRCUMFLEX |
|
306 |
<a?> /xE3 <U00E3> LATIN SMALL LETTER A WITH TILDE |
|
307 |
<a:> /xE4 <U00E4> LATIN SMALL LETTER A WITH DIAERESIS |
|
308 |
<aa> /xE5 <U00E5> LATIN SMALL LETTER A WITH RING ABOVE |
|
309 |
<ae> /xE6 <U00E6> LATIN SMALL LETTER AE |
|
310 |
<c,> /xE7 <U00E7> LATIN SMALL LETTER C WITH CEDILLA |
|
311 |
<e!!> /xE8 <U00E8> LATIN SMALL LETTER E WITH GRAVE |
|
312 |
<e'> /xE9 <U00E9> LATIN SMALL LETTER E WITH ACUTE |
|
313 |
<e/>> /xEA <U00EA> LATIN SMALL LETTER E WITH CIRCUMFLEX |
|
314 |
<e:> /xEB <U00EB> LATIN SMALL LETTER E WITH DIAERESIS |
|
315 |
<i!!> /xEC <U00EC> LATIN SMALL LETTER I WITH GRAVE |
|
316 |
<i'> /xED <U00ED> LATIN SMALL LETTER I WITH ACUTE |
|
317 |
<i/>> /xEE <U00EE> LATIN SMALL LETTER I WITH CIRCUMFLEX |
|
318 |
<i:> /xEF <U00EF> LATIN SMALL LETTER I WITH DIAERESIS |
|
319 |
<d-> /xF0 <U00F0> LATIN SMALL LETTER ETH (Icelandic) |
|
320 |
<n?> /xF1 <U00F1> LATIN SMALL LETTER N WITH TILDE |
|
321 |
<o!!> /xF2 <U00F2> LATIN SMALL LETTER O WITH GRAVE |
|
322 |
<o'> /xF3 <U00F3> LATIN SMALL LETTER O WITH ACUTE |
|
323 |
<o/>> /xF4 <U00F4> LATIN SMALL LETTER O WITH CIRCUMFLEX |
|
324 |
<o?> /xF5 <U00F5> LATIN SMALL LETTER O WITH TILDE |
|
325 |
<o:> /xF6 <U00F6> LATIN SMALL LETTER O WITH DIAERESIS |
|
326 |
<-:> /xF7 <U00F7> DIVISION SIGN |
|
327 |
<o//> /xF8 <U00F8> LATIN SMALL LETTER O WITH STROKE |
|
328 |
<u!!> /xF9 <U00F9> LATIN SMALL LETTER U WITH GRAVE |
|
329 |
<u'> /xFA <U00FA> LATIN SMALL LETTER U WITH ACUTE |
|
330 |
<u/>> /xFB <U00FB> LATIN SMALL LETTER U WITH CIRCUMFLEX |
|
331 |
<u:> /xFC <U00FC> LATIN SMALL LETTER U WITH DIAERESIS |
|
332 |
<y'> /xFD <U00FD> LATIN SMALL LETTER Y WITH ACUTE |
|
333 |
<th> /xFE <U00FE> LATIN SMALL LETTER THORN (Icelandic) |
|
334 |
<y:> /xFF <U00FF> LATIN SMALL LETTER Y WITH DIAERESIS |
|
335 |
END CHARMAP |
|
336 |
||
337 |
" |
|
338 |
! ! |
|
339 |
||
22501 | 340 |
!MS_Ansi class methodsFor:'queries'! |
341 |
||
342 |
maxCode |
|
343 |
^ 65535 |
|
344 |
! |
|
345 |
||
346 |
minCode |
|
347 |
^ 0 |
|
348 |
! ! |
|
349 |
||
8139 | 350 |
!MS_Ansi methodsFor:'encoding & decoding'! |
351 |
||
352 |
decode:codeArg |
|
22501 | 353 |
|code "{ Class: SmallInteger }" t| |
8139 | 354 |
|
14203 | 355 |
code := codeArg. |
356 |
code <= 16r7F ifTrue:[ ^ code ]. |
|
22501 | 357 |
code >= 16rA0 ifTrue:[ |
14203 | 358 |
^ codeArg. |
359 |
]. |
|
22501 | 360 |
|
22583 | 361 |
"similar to 8859-1 with different chars in the 8x..9x area" |
22501 | 362 |
"we map CP1252 chars to unicode chars" |
363 |
||
364 |
t := #( |
|
365 |
"16r0080" 16r20AC " EURO character " |
|
366 |
"16r0081" 16r0000 " invalid " |
|
367 |
"16r0082" 16r201A " SINGLE LOW-9 QUOTATION MARK " |
|
368 |
"16r0083" 16r0192 " LATIN SMALL LETTER F WITH HOOK " |
|
369 |
"16r0084" 16r201E " DOUBLE LOW-9 QUOTATION MARK " |
|
370 |
"16r0085" 16r2026 " HORIZONTAL ELLIPSIS " |
|
371 |
"16r0086" 16r2020 " DAGGER " |
|
372 |
"16r0087" 16r2021 " DOUBLE DAGGER " |
|
373 |
"16r0088" 16r02C6 " MODIFIER LETTER CIRCUMFLEX ACCENT " |
|
374 |
"16r0089" 16r2030 " PER MILLE SIGN " |
|
375 |
"16r008A" 16r0160 " LATIN CAPITAL LETTER S WITH CARON " |
|
376 |
"16r008B" 16r2039 " SINGLE LEFT-POINTING ANGLE QUOTATION MARK " |
|
377 |
"16r008C" 16r0152 " LATIN CAPITAL LIGATURE OE " |
|
378 |
"16r008D" 16r0000 " invalid " |
|
22583 | 379 |
"16r008E" 16r017D " LATIN CAPITAL Z WITH INVERSE CARON" |
22501 | 380 |
"16r008F" 16r0000 " invalid " |
381 |
"16r0090" 16r0000 " invalid " |
|
382 |
"16r0091" 16r2018 " LEFT SINGLE QUOTATION MARK " |
|
383 |
"16r0092" 16r2019 " RIGHT SINGLE QUOTATION MARK " |
|
384 |
"16r0093" 16r201C " LEFT DOUBLE QUOTATION MARK " |
|
385 |
"16r0094" 16r201D " RIGHT DOUBLE QUOTATION MARK " |
|
386 |
"16r0095" 16r2022 " BULLET " |
|
387 |
"16r0096" 16r2013 " EN DASH " |
|
388 |
"16r0097" 16r2014 " EM DASH " |
|
389 |
"16r0098" 16r02DC " SMALL TILDE " |
|
390 |
"16r0099" 16r2122 " TRADE MARK SIGN " |
|
391 |
"16r009A" 16r0161 " LATIN SMALL LETTER S WITH CARON " |
|
392 |
"16r009B" 16r203A " SINGLE RIGHT-POINTING ANGLE QUOTATION MARK " |
|
393 |
"16r009C" 16r0153 " LATIN SMALL LIGATURE OE " |
|
394 |
"16r009D" 16r0000 " invalid " |
|
22583 | 395 |
"16r009E" 16r017E " LATIN SMALL LETTER Z WITH INVERSE CARON " |
22501 | 396 |
"16r009F" 16r0178 " LATIN CAPITAL LETTER Y WITH DIAERESIS " |
397 |
) at:(code - 16r7F). |
|
398 |
t == 0 ifFalse:[^ t]. |
|
399 |
^ self decodingError. |
|
11000
2cc8e7ba3be6
ms-ansi now treated like unicode
Michael Beyl <mb@exept.de>
parents:
9269
diff
changeset
|
400 |
|
14203 | 401 |
"Modified (format): / 12-07-2012 / 14:06:56 / cg" |
8139 | 402 |
! |
403 |
||
22501 | 404 |
decodeString:anEncodedStringOrByteCollection |
405 |
"given a string in my encoding, return a unicode-string for it" |
|
406 |
||
407 |
|newString myCode code bits size "{ Class:SmallInteger }"| |
|
408 |
||
409 |
size := anEncodedStringOrByteCollection size. |
|
410 |
newString := String new:size. |
|
411 |
bits := newString bitsPerCharacter. |
|
412 |
||
413 |
1 to:size do:[:idx | |
|
414 |
code := (anEncodedStringOrByteCollection at:idx) codePoint. |
|
415 |
myCode := self decode:code. |
|
416 |
myCode > 16rFF ifTrue:[ |
|
417 |
myCode > 16rFFFF ifTrue:[ |
|
418 |
bits < 32 ifTrue:[ |
|
419 |
newString := Unicode32String fromString:newString. |
|
420 |
bits := 32. |
|
421 |
] |
|
422 |
] ifFalse:[ |
|
423 |
bits < 16 ifTrue:[ |
|
424 |
newString := Unicode16String fromString:newString. |
|
425 |
bits := 16. |
|
426 |
] |
|
427 |
] |
|
428 |
]. |
|
429 |
newString at:idx put:(Character codePoint:myCode). |
|
430 |
]. |
|
431 |
^ newString |
|
432 |
||
433 |
" |
|
434 |
CharacterEncoderImplementations::ISO8859_1 decodeString:'hello' |
|
435 |
" |
|
436 |
||
437 |
"Created: / 16-01-2018 / 19:54:02 / stefan" |
|
438 |
"Modified (format): / 17-01-2018 / 16:30:59 / stefan" |
|
439 |
! |
|
440 |
||
8139 | 441 |
encode:unicodeArg |
22501 | 442 |
|unicode "{ Class: SmallInteger }" t| |
8139 | 443 |
|
22585 | 444 |
"/ the comment in mh... is not correct. |
445 |
false ifTrue:[ |
|
446 |
"/ mh - it seems that microsoft has fixed ms-ansi to be unicode compatible |
|
447 |
"/ with XP, Vista etc. |
|
448 |
"/ as W95 is not supported anyhow, simply return identity here... |
|
449 |
^ unicodeArg. |
|
450 |
]. |
|
11000
2cc8e7ba3be6
ms-ansi now treated like unicode
Michael Beyl <mb@exept.de>
parents:
9269
diff
changeset
|
451 |
|
22501 | 452 |
"we map unicode chars to CP1252 where a mapping exists. |
453 |
If no mapping exists, we keep the unicode char" |
|
454 |
||
14205 | 455 |
unicode := unicodeArg. |
456 |
unicode > 16r2122 ifTrue:[ |
|
457 |
^ unicode. |
|
458 |
]. |
|
459 |
unicode <= 16r151 ifTrue:[ |
|
460 |
^ unicode |
|
461 |
]. |
|
462 |
unicode <= 16r2DC ifTrue:[ |
|
463 |
unicode <= 16r192 ifTrue:[ |
|
464 |
unicode <= 16r178 ifTrue:[ |
|
465 |
unicode <= 16r161 ifTrue:[ |
|
22501 | 466 |
t := #[ |
467 |
"16r0152" 16r8C " LATIN CAPITAL LIGATURE OE " |
|
468 |
"16r0153" 16r9C " LATIN SMALL LIGATURE OE " |
|
469 |
"16r0154" 16r00 " keep unicode " |
|
470 |
"16r0155" 16r00 " keep unicode " |
|
471 |
"16r0156" 16r00 " keep unicode " |
|
472 |
"16r0157" 16r00 " keep unicode " |
|
473 |
"16r0158" 16r00 " keep unicode " |
|
474 |
"16r0159" 16r00 " keep unicode " |
|
475 |
"16r015A" 16r00 " keep unicode " |
|
476 |
"16r015B" 16r00 " keep unicode " |
|
477 |
"16r015C" 16r00 " keep unicode " |
|
478 |
"16r015D" 16r00 " keep unicode " |
|
479 |
"16r015E" 16r00 " keep unicode " |
|
480 |
"16r015F" 16r00 " keep unicode " |
|
481 |
"16r0160" 16r8A " LATIN CAPITAL LETTER S WITH CARON " |
|
482 |
"16r0161" 16r9A " LATIN SMALL LETTER S WITH CARON " |
|
483 |
] at:(unicode - 16r151). |
|
484 |
t == 0 ifFalse:[^ t]. |
|
485 |
^ unicode |
|
14205 | 486 |
]. |
487 |
unicode <= 16r177 ifTrue:[ |
|
488 |
^ unicode |
|
489 |
]. |
|
490 |
^ "16r0178" 16r009F " LATIN CAPITAL LETTER Y WITH DIAERESIS " |
|
491 |
]. |
|
492 |
unicode <= 16r191 ifTrue:[ |
|
493 |
^ unicode |
|
494 |
]. |
|
495 |
^ "16r0192" 16r0083 " LATIN SMALL LETTER F WITH HOOK " |
|
496 |
]. |
|
497 |
unicode <= 16r2C5 ifTrue:[ |
|
498 |
^ unicode |
|
499 |
]. |
|
500 |
unicode == 16r2C6 ifTrue:[ |
|
501 |
^ "16r02C6" 16r0088 " MODIFIER LETTER CIRCUMFLEX ACCENT " |
|
502 |
]. |
|
503 |
unicode <= 16r2DB ifTrue:[ |
|
504 |
^ unicode |
|
505 |
]. |
|
506 |
^ "16r02DC" 16r0098 " SMALL TILDE " |
|
507 |
]. |
|
508 |
unicode <= 16r2012 ifTrue:[ |
|
509 |
^ unicode |
|
510 |
]. |
|
511 |
unicode <= 16r203A ifTrue:[ |
|
22501 | 512 |
t := #( |
513 |
"16r2013" 16r2013 "16r96" " EN DASH " |
|
514 |
"16r2014" 16r2014 "16r97" " EM DASH " |
|
515 |
"16r2015" 16r00 " keep unicode " |
|
516 |
"16r2016" 16r00 " keep unicode " |
|
517 |
"16r2017" 16r00 " keep unicode " |
|
518 |
"16r2018" 16r91 " LEFT SINGLE QUOTATION MARK " |
|
519 |
"16r2019" 16r92 " RIGHT SINGLE QUOTATION MARK " |
|
520 |
"16r201A" 16r82 " SINGLE LOW-9 QUOTATION MARK " |
|
521 |
"16r201B" 16r00 " keep unicode " |
|
522 |
"16r201C" 16r93 " LEFT DOUBLE QUOTATION MARK " |
|
523 |
"16r201D" 16r94 " RIGHT DOUBLE QUOTATION MARK " |
|
524 |
"16r201E" 16r84 " DOUBLE LOW-9 QUOTATION MARK " |
|
525 |
"16r201F" 16r00 " keep unicode " |
|
526 |
"16r2020" 16r86 " DAGGER " |
|
527 |
"16r2021" 16r87 " DOUBLE DAGGER " |
|
528 |
"16r2022" 16r95 " BULLET " |
|
529 |
"16r2023" 16r00 " keep unicode " |
|
530 |
"16r2024" 16r00 " keep unicode " |
|
531 |
"16r2025" 16r00 " keep unicode " |
|
532 |
"16r2026" 16r85 " HORIZONTAL ELLIPSIS " |
|
533 |
"16r2027" 16r00 " keep unicode " |
|
534 |
"16r2028" 16r00 " keep unicode " |
|
535 |
"16r2029" 16r00 " keep unicode " |
|
536 |
"16r202A" 16r00 " keep unicode " |
|
537 |
"16r202B" 16r00 " keep unicode " |
|
538 |
"16r202C" 16r00 " keep unicode " |
|
539 |
"16r202D" 16r00 " keep unicode " |
|
540 |
"16r202E" 16r00 " keep unicode " |
|
541 |
"16r202F" 16r00 " keep unicode " |
|
542 |
"16r2030" 16r89 " PER MILLE SIGN " |
|
543 |
"16r2031" 16r00 " keep unicode " |
|
544 |
"16r2032" 16r00 " keep unicode " |
|
545 |
"16r2033" 16r00 " keep unicode " |
|
546 |
"16r2034" 16r00 " keep unicode " |
|
547 |
"16r2035" 16r00 " keep unicode " |
|
548 |
"16r2036" 16r00 " keep unicode " |
|
549 |
"16r2037" 16r00 " keep unicode " |
|
550 |
"16r2038" 16r00 " keep unicode " |
|
551 |
"16r2039" 16r8B " SINGLE LEFT-POINTING ANGLE QUOTATION MARK " |
|
552 |
"16r203A" 16r9B " SINGLE RIGHT-POINTING ANGLE QUOTATION MARK " |
|
553 |
) at:(unicode - 16r2012). |
|
554 |
t == 0 ifFalse:[^ t]. |
|
555 |
^ unicode |
|
14205 | 556 |
]. |
557 |
"/ unicode = 16r20AC ifTrue:[ |
|
558 |
"/ ^ 16r0080 " EURO character " |
|
11000
2cc8e7ba3be6
ms-ansi now treated like unicode
Michael Beyl <mb@exept.de>
parents:
9269
diff
changeset
|
559 |
"/ ]. |
14205 | 560 |
unicode <= 16r2121 ifTrue:[ |
561 |
^ unicode |
|
562 |
]. |
|
563 |
^ "16r2122" 16r0099 " TRADE MARK SIGN " |
|
14203 | 564 |
|
14205 | 565 |
"Modified: / 12-07-2012 / 14:46:59 / cg" |
9269
f629c9eafec6
speedup encoding of long strings when no 8 bit chars are present
Claus Gittinger <cg@exept.de>
parents:
8813
diff
changeset
|
566 |
! |
f629c9eafec6
speedup encoding of long strings when no 8 bit chars are present
Claus Gittinger <cg@exept.de>
parents:
8813
diff
changeset
|
567 |
|
f629c9eafec6
speedup encoding of long strings when no 8 bit chars are present
Claus Gittinger <cg@exept.de>
parents:
8813
diff
changeset
|
568 |
encodeString:aStringOrUnicodeString |
f629c9eafec6
speedup encoding of long strings when no 8 bit chars are present
Claus Gittinger <cg@exept.de>
parents:
8813
diff
changeset
|
569 |
"redefined to speedup simple 8 bit strings" |
f629c9eafec6
speedup encoding of long strings when no 8 bit chars are present
Claus Gittinger <cg@exept.de>
parents:
8813
diff
changeset
|
570 |
|
22501 | 571 |
|newString myCode bits size "{ Class:SmallInteger }"| |
572 |
||
22585 | 573 |
"/ the comment in mh... is not correct. |
574 |
false ifTrue:[ |
|
575 |
"/ mh - it seems that microsoft has fixed ms-ansi to be unicode compatible |
|
576 |
"/ with XP, Vista etc. |
|
577 |
"/ as W95 is not supported anyhow, simply return identity here... |
|
578 |
^ aStringOrUnicodeString. |
|
579 |
]. |
|
11000
2cc8e7ba3be6
ms-ansi now treated like unicode
Michael Beyl <mb@exept.de>
parents:
9269
diff
changeset
|
580 |
|
18602
cf5b0713b748
class: CharacterEncoderImplementations::MS_Ansi
Stefan Vogel <sv@exept.de>
parents:
17624
diff
changeset
|
581 |
"/ all between 0 and 7F ? |
cf5b0713b748
class: CharacterEncoderImplementations::MS_Ansi
Stefan Vogel <sv@exept.de>
parents:
17624
diff
changeset
|
582 |
(aStringOrUnicodeString containsNon7BitAscii) ifFalse:[ |
cf5b0713b748
class: CharacterEncoderImplementations::MS_Ansi
Stefan Vogel <sv@exept.de>
parents:
17624
diff
changeset
|
583 |
^ aStringOrUnicodeString asSingleByteString. |
14205 | 584 |
]. |
22501 | 585 |
|
586 |
size := aStringOrUnicodeString size. |
|
587 |
newString := String new:size. |
|
588 |
bits := newString bitsPerCharacter. |
|
14203 | 589 |
|
22501 | 590 |
1 to:size do:[:idx | |
591 |
myCode := self encode:((aStringOrUnicodeString at:idx) codePoint). |
|
592 |
myCode > 16rFF ifTrue:[ |
|
593 |
myCode > 16rFFFF ifTrue:[ |
|
594 |
bits < 32 ifTrue:[ |
|
595 |
newString := Unicode32String fromString:newString. |
|
596 |
bits := 32. |
|
597 |
] |
|
598 |
] ifFalse:[ |
|
599 |
bits < 16 ifTrue:[ |
|
600 |
newString := Unicode16String fromString:newString. |
|
601 |
bits := 16. |
|
602 |
] |
|
603 |
] |
|
604 |
]. |
|
605 |
newString at:idx put:(Character codePoint:myCode). |
|
606 |
]. |
|
607 |
^ newString |
|
608 |
||
609 |
"Created: / 16-01-2018 / 19:53:33 / stefan" |
|
610 |
"Modified: / 17-01-2018 / 14:15:39 / stefan" |
|
8139 | 611 |
! ! |
612 |
||
22585 | 613 |
!MS_Ansi methodsFor:'queries'! |
614 |
||
615 |
characterSize:charOrCodePoint |
|
616 |
"return the number of bytes required to encode codePoint" |
|
617 |
||
618 |
|code| |
|
619 |
||
620 |
code := self encode:charOrCodePoint asInteger. |
|
621 |
code <= 16rFF ifTrue:[^ 1]. |
|
22589 | 622 |
^ 2 |
22585 | 623 |
! ! |
624 |
||
8081 | 625 |
!MS_Ansi class methodsFor:'documentation'! |
626 |
||
627 |
version |
|
18602
cf5b0713b748
class: CharacterEncoderImplementations::MS_Ansi
Stefan Vogel <sv@exept.de>
parents:
17624
diff
changeset
|
628 |
^ '$Header$' |
14205 | 629 |
! |
630 |
||
631 |
version_CVS |
|
18602
cf5b0713b748
class: CharacterEncoderImplementations::MS_Ansi
Stefan Vogel <sv@exept.de>
parents:
17624
diff
changeset
|
632 |
^ '$Header$' |
8081 | 633 |
! ! |
17624
acb2e49fb3ab
class: CharacterEncoderImplementations::MS_Ansi
Stefan Vogel <sv@exept.de>
parents:
14560
diff
changeset
|
634 |