/[jscoverage]/trunk/encoding.c
ViewVC logotype

Annotation of /trunk/encoding.c

Parent Directory Parent Directory | Revision Log Revision Log


Revision 188 - (hide annotations)
Tue Sep 23 03:48:15 2008 UTC (10 years, 10 months ago) by siliconforks
File MIME type: text/plain
File size: 13522 byte(s)
Use UTF-16 instead of UCS-2.
1 siliconforks 174 /*
2     encoding.c - character encoding
3     Copyright (C) 2008 siliconforks.com
4    
5     This program is free software; you can redistribute it and/or modify
6     it under the terms of the GNU General Public License as published by
7     the Free Software Foundation; either version 2 of the License, or
8     (at your option) any later version.
9    
10     This program is distributed in the hope that it will be useful,
11     but WITHOUT ANY WARRANTY; without even the implied warranty of
12     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13     GNU General Public License for more details.
14    
15     You should have received a copy of the GNU General Public License along
16     with this program; if not, write to the Free Software Foundation, Inc.,
17     51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
18     */
19    
20     #include <config.h>
21    
22     #include "encoding.h"
23    
24     #include <assert.h>
25     #include <string.h>
26    
27     #ifdef HAVE_ICONV_H
28     #include <iconv.h>
29     #elif defined HAVE_WINDOWS_H
30     #include <windows.h>
31     #endif
32    
33     #include "util.h"
34    
35     static void skip_bom(jschar ** characters, size_t * num_characters) {
36     jschar * c = *characters;
37     size_t nc = *num_characters;
38    
39     size_t i;
40     for (i = 0; i < nc; i++) {
41     if (c[i] != 0xfeff) {
42     break;
43     }
44     }
45    
46     if (i == 0) {
47     return;
48     }
49    
50     nc -= i;
51     jschar * old = c;
52     c = xnew(jschar, nc);
53     memcpy(c, old + i, nc * sizeof(jschar));
54     free(old);
55    
56     *characters = c;
57     *num_characters = nc;
58     }
59    
60     #ifdef HAVE_ICONV
61    
62     #ifdef WORDS_BIGENDIAN
63 siliconforks 188 #define UTF_16_INTERNAL "UTF-16BE"
64 siliconforks 174 #else
65 siliconforks 188 #define UTF_16_INTERNAL "UTF-16LE"
66 siliconforks 174 #endif
67    
68     int jscoverage_bytes_to_characters(const char * encoding, const uint8_t * bytes, size_t num_bytes, jschar ** characters, size_t * num_characters) {
69     assert(encoding != NULL);
70    
71 siliconforks 188 iconv_t state = iconv_open(UTF_16_INTERNAL, encoding);
72 siliconforks 174 if (state == (iconv_t) -1) {
73     return JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED;
74     }
75    
76     ICONV_CONST char * input = (char *) bytes;
77     size_t input_bytes_left = num_bytes;
78    
79     jschar * c = xnew(jschar, num_bytes);
80     char * output = (char *) c;
81     size_t output_bytes_left = sizeof(jschar) * num_bytes;
82    
83     size_t result = iconv(state, &input, &input_bytes_left, &output, &output_bytes_left);
84 siliconforks 178 iconv_close(state);
85 siliconforks 174 if (result == (size_t) -1) {
86     free(c);
87     return JSCOVERAGE_ERROR_INVALID_BYTE_SEQUENCE;
88     }
89    
90     assert(input_bytes_left == 0);
91    
92     size_t nc = ((jschar *) output) - c;
93    
94     skip_bom(&c, &nc);
95    
96     *characters = c;
97     *num_characters = nc;
98     return 0;
99     }
100    
101     #elif HAVE_MULTIBYTETOWIDECHAR
102    
103     /* http://msdn.microsoft.com/en-us/library/ms776446(VS.85).aspx */
104     static struct CodePage {
105     UINT value;
106     LPCSTR string;
107     } code_pages[] = {
108     {37, "IBM037"}, /* IBM EBCDIC US-Canada */
109     {437, "IBM437"}, /* OEM United States */
110     {500, "IBM500"}, /* IBM EBCDIC International */
111     {708, "ASMO-708"}, /* Arabic (ASMO 708) */
112     {720, "DOS-720"}, /* Arabic (Transparent ASMO); Arabic (DOS) */
113     {737, "ibm737"}, /* OEM Greek (formerly 437G); Greek (DOS) */
114     {775, "ibm775"}, /* OEM Baltic; Baltic (DOS) */
115     {850, "ibm850"}, /* OEM Multilingual Latin 1; Western European (DOS) */
116     {852, "ibm852"}, /* OEM Latin 2; Central European (DOS) */
117     {855, "IBM855"}, /* OEM Cyrillic (primarily Russian) */
118     {857, "ibm857"}, /* OEM Turkish; Turkish (DOS) */
119     {858, "IBM00858"}, /* OEM Multilingual Latin 1 + Euro symbol */
120     {860, "IBM860"}, /* OEM Portuguese; Portuguese (DOS) */
121     {861, "ibm861"}, /* OEM Icelandic; Icelandic (DOS) */
122     {862, "DOS-862"}, /* OEM Hebrew; Hebrew (DOS) */
123     {863, "IBM863"}, /* OEM French Canadian; French Canadian (DOS) */
124     {864, "IBM864"}, /* OEM Arabic; Arabic (864) */
125     {865, "IBM865"}, /* OEM Nordic; Nordic (DOS) */
126     {866, "cp866"}, /* OEM Russian; Cyrillic (DOS) */
127     {869, "ibm869"}, /* OEM Modern Greek; Greek, Modern (DOS) */
128     {870, "IBM870"}, /* IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2 */
129     {874, "windows-874"}, /* ANSI/OEM Thai (same as 28605, ISO 8859-15); Thai (Windows) */
130     {875, "cp875"}, /* IBM EBCDIC Greek Modern */
131     {932, "shift_jis"}, /* ANSI/OEM Japanese; Japanese (Shift-JIS) */
132     {936, "gb2312"}, /* ANSI/OEM Simplified Chinese (PRC, Singapore); Chinese Simplified (GB2312) */
133     {949, "ks_c_5601-1987"}, /* ANSI/OEM Korean (Unified Hangul Code) */
134     {950, "big5"}, /* ANSI/OEM Traditional Chinese (Taiwan; Hong Kong SAR, PRC); Chinese Traditional (Big5) */
135     {1026, "IBM1026"}, /* IBM EBCDIC Turkish (Latin 5) */
136     {1047, "IBM01047"}, /* IBM EBCDIC Latin 1/Open System */
137     {1140, "IBM01140"}, /* IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro) */
138     {1141, "IBM01141"}, /* IBM EBCDIC Germany (20273 + Euro symbol); IBM EBCDIC (Germany-Euro) */
139     {1142, "IBM01142"}, /* IBM EBCDIC Denmark-Norway (20277 + Euro symbol); IBM EBCDIC (Denmark-Norway-Euro) */
140     {1143, "IBM01143"}, /* IBM EBCDIC Finland-Sweden (20278 + Euro symbol); IBM EBCDIC (Finland-Sweden-Euro) */
141     {1144, "IBM01144"}, /* IBM EBCDIC Italy (20280 + Euro symbol); IBM EBCDIC (Italy-Euro) */
142     {1145, "IBM01145"}, /* IBM EBCDIC Latin America-Spain (20284 + Euro symbol); IBM EBCDIC (Spain-Euro) */
143     {1146, "IBM01146"}, /* IBM EBCDIC United Kingdom (20285 + Euro symbol); IBM EBCDIC (UK-Euro) */
144     {1147, "IBM01147"}, /* IBM EBCDIC France (20297 + Euro symbol); IBM EBCDIC (France-Euro) */
145     {1148, "IBM01148"}, /* IBM EBCDIC International (500 + Euro symbol); IBM EBCDIC (International-Euro) */
146     {1149, "IBM01149"}, /* IBM EBCDIC Icelandic (20871 + Euro symbol); IBM EBCDIC (Icelandic-Euro) */
147     {1200, "utf-16"}, /* Unicode UTF-16, little endian byte order (BMP of ISO 10646); available only to managed applications */
148     {1201, "unicodeFFFE"}, /* Unicode UTF-16, big endian byte order; available only to managed applications */
149     {1250, "windows-1250"}, /* ANSI Central European; Central European (Windows) */
150     {1251, "windows-1251"}, /* ANSI Cyrillic; Cyrillic (Windows) */
151     {1252, "windows-1252"}, /* ANSI Latin 1; Western European (Windows) */
152     {1253, "windows-1253"}, /* ANSI Greek; Greek (Windows) */
153     {1254, "windows-1254"}, /* ANSI Turkish; Turkish (Windows) */
154     {1255, "windows-1255"}, /* ANSI Hebrew; Hebrew (Windows) */
155     {1256, "windows-1256"}, /* ANSI Arabic; Arabic (Windows) */
156     {1257, "windows-1257"}, /* ANSI Baltic; Baltic (Windows) */
157     {1258, "windows-1258"}, /* ANSI/OEM Vietnamese; Vietnamese (Windows) */
158     {1361, "Johab"}, /* Korean (Johab) */
159     {10000, "macintosh"}, /* MAC Roman; Western European (Mac) */
160     {10001, "x-mac-japanese"}, /* Japanese (Mac) */
161     {10002, "x-mac-chinesetrad"}, /* MAC Traditional Chinese (Big5); Chinese Traditional (Mac) */
162     {10003, "x-mac-korean"}, /* Korean (Mac) */
163     {10004, "x-mac-arabic"}, /* Arabic (Mac) */
164     {10005, "x-mac-hebrew"}, /* Hebrew (Mac) */
165     {10006, "x-mac-greek"}, /* Greek (Mac) */
166     {10007, "x-mac-cyrillic"}, /* Cyrillic (Mac) */
167     {10008, "x-mac-chinesesimp"}, /* MAC Simplified Chinese (GB 2312); Chinese Simplified (Mac) */
168     {10010, "x-mac-romanian"}, /* Romanian (Mac) */
169     {10017, "x-mac-ukrainian"}, /* Ukrainian (Mac) */
170     {10021, "x-mac-thai"}, /* Thai (Mac) */
171     {10029, "x-mac-ce"}, /* MAC Latin 2; Central European (Mac) */
172     {10079, "x-mac-icelandic"}, /* Icelandic (Mac) */
173     {10081, "x-mac-turkish"}, /* Turkish (Mac) */
174     {10082, "x-mac-croatian"}, /* Croatian (Mac) */
175     {12000, "utf-32"}, /* Unicode UTF-32, little endian byte order; available only to managed applications */
176     {12001, "utf-32BE"}, /* Unicode UTF-32, big endian byte order; available only to managed applications */
177     {20000, "x-Chinese_CNS"}, /* CNS Taiwan; Chinese Traditional (CNS) */
178     {20001, "x-cp20001"}, /* TCA Taiwan */
179     {20002, "x_Chinese-Eten"}, /* Eten Taiwan; Chinese Traditional (Eten) */
180     {20003, "x-cp20003"}, /* IBM5550 Taiwan */
181     {20004, "x-cp20004"}, /* TeleText Taiwan */
182     {20005, "x-cp20005"}, /* Wang Taiwan */
183     {20105, "x-IA5"}, /* IA5 (IRV International Alphabet No. 5, 7-bit); Western European (IA5) */
184     {20106, "x-IA5-German"}, /* IA5 German (7-bit) */
185     {20107, "x-IA5-Swedish"}, /* IA5 Swedish (7-bit) */
186     {20108, "x-IA5-Norwegian"}, /* IA5 Norwegian (7-bit) */
187     {20127, "us-ascii"}, /* US-ASCII (7-bit) */
188     {20261, "x-cp20261"}, /* T.61 */
189     {20269, "x-cp20269"}, /* ISO 6937 Non-Spacing Accent */
190     {20273, "IBM273"}, /* IBM EBCDIC Germany */
191     {20277, "IBM277"}, /* IBM EBCDIC Denmark-Norway */
192     {20278, "IBM278"}, /* IBM EBCDIC Finland-Sweden */
193     {20280, "IBM280"}, /* IBM EBCDIC Italy */
194     {20284, "IBM284"}, /* IBM EBCDIC Latin America-Spain */
195     {20285, "IBM285"}, /* IBM EBCDIC United Kingdom */
196     {20290, "IBM290"}, /* IBM EBCDIC Japanese Katakana Extended */
197     {20297, "IBM297"}, /* IBM EBCDIC France */
198     {20420, "IBM420"}, /* IBM EBCDIC Arabic */
199     {20423, "IBM423"}, /* IBM EBCDIC Greek */
200     {20424, "IBM424"}, /* IBM EBCDIC Hebrew */
201     {20833, "x-EBCDIC-KoreanExtended"}, /* IBM EBCDIC Korean Extended */
202     {20838, "IBM-Thai"}, /* IBM EBCDIC Thai */
203     {20866, "koi8-r"}, /* Russian (KOI8-R); Cyrillic (KOI8-R) */
204     {20871, "IBM871"}, /* IBM EBCDIC Icelandic */
205     {20880, "IBM880"}, /* IBM EBCDIC Cyrillic Russian */
206     {20905, "IBM905"}, /* IBM EBCDIC Turkish */
207     {20924, "IBM00924"}, /* IBM EBCDIC Latin 1/Open System (1047 + Euro symbol) */
208     {20932, "EUC-JP"}, /* Japanese (JIS 0208-1990 and 0121-1990) */
209     {20936, "x-cp20936"}, /* Simplified Chinese (GB2312); Chinese Simplified (GB2312-80) */
210     {20949, "x-cp20949"}, /* Korean Wansung */
211     {21025, "cp1025"}, /* IBM EBCDIC Cyrillic Serbian-Bulgarian */
212     {21866, "koi8-u"}, /* Ukrainian (KOI8-U); Cyrillic (KOI8-U) */
213     {28591, "iso-8859-1"}, /* ISO 8859-1 Latin 1; Western European (ISO) */
214     {28592, "iso-8859-2"}, /* ISO 8859-2 Central European; Central European (ISO) */
215     {28593, "iso-8859-3"}, /* ISO 8859-3 Latin 3 */
216     {28594, "iso-8859-4"}, /* ISO 8859-4 Baltic */
217     {28595, "iso-8859-5"}, /* ISO 8859-5 Cyrillic */
218     {28596, "iso-8859-6"}, /* ISO 8859-6 Arabic */
219     {28597, "iso-8859-7"}, /* ISO 8859-7 Greek */
220     {28598, "iso-8859-8"}, /* ISO 8859-8 Hebrew; Hebrew (ISO-Visual) */
221     {28599, "iso-8859-9"}, /* ISO 8859-9 Turkish */
222     {28603, "iso-8859-13"}, /* ISO 8859-13 Estonian */
223     {28605, "iso-8859-15"}, /* ISO 8859-15 Latin 9 */
224     {29001, "x-Europa"}, /* Europa 3 */
225     {38598, "iso-8859-8-i"}, /* ISO 8859-8 Hebrew; Hebrew (ISO-Logical) */
226     {50220, "iso-2022-jp"}, /* ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS) */
227     {50221, "csISO2022JP"}, /* ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana) */
228     {50222, "iso-2022-jp"}, /* ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI) */
229     {50225, "iso-2022-kr"}, /* ISO 2022 Korean */
230     {50227, "x-cp50227"}, /* ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022) */
231     {51932, "euc-jp"}, /* EUC Japanese */
232     {51936, "EUC-CN"}, /* EUC Simplified Chinese; Chinese Simplified (EUC) */
233     {51949, "euc-kr"}, /* EUC Korean */
234     {52936, "hz-gb-2312"}, /* HZ-GB2312 Simplified Chinese; Chinese Simplified (HZ) */
235     {54936, "GB18030"}, /* Windows XP and later: GB18030 Simplified Chinese (4 byte); Chinese Simplified (GB18030) */
236     {57002, "x-iscii-de"}, /* ISCII Devanagari */
237     {57003, "x-iscii-be"}, /* ISCII Bengali */
238     {57004, "x-iscii-ta"}, /* ISCII Tamil */
239     {57005, "x-iscii-te"}, /* ISCII Telugu */
240     {57006, "x-iscii-as"}, /* ISCII Assamese */
241     {57007, "x-iscii-or"}, /* ISCII Oriya */
242     {57008, "x-iscii-ka"}, /* ISCII Kannada */
243     {57009, "x-iscii-ma"}, /* ISCII Malayalam */
244     {57010, "x-iscii-gu"}, /* ISCII Gujarati */
245     {57011, "x-iscii-pa"}, /* ISCII Punjabi */
246     {65000, "utf-7"}, /* Unicode (UTF-7) */
247     {65001, "utf-8"}, /* Unicode (UTF-8) */
248     };
249    
250     int find_code_page(const char * encoding, UINT * code_page) {
251     for (size_t i = 0; i < sizeof(code_pages) / sizeof(code_pages[0]); i++) {
252     if (strcasecmp(encoding, code_pages[i].string) == 0) {
253     *code_page = code_pages[i].value;
254     return 0;
255     }
256     }
257     return -1;
258     }
259    
260     int jscoverage_bytes_to_characters(const char * encoding, const uint8_t * bytes, size_t num_bytes, jschar ** characters, size_t * num_characters) {
261     assert(encoding != NULL);
262    
263     if (num_bytes == 0) {
264     *characters = xnew(jschar, 0);
265     *num_characters = 0;
266     return 0;
267     }
268    
269     UINT code_page;
270     if (find_code_page(encoding, &code_page) != 0) {
271     return JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED;
272     }
273    
274     if (num_bytes > INT_MAX) {
275     fatal("overflow");
276     }
277    
278     *characters = xnew(jschar, num_bytes);
279    
280     int result = MultiByteToWideChar(code_page, 0, bytes, num_bytes, *characters, num_bytes);
281     if (result == 0) {
282     free(*characters);
283     return JSCOVERAGE_ERROR_INVALID_BYTE_SEQUENCE;
284     }
285    
286     *num_characters = result;
287     skip_bom(characters, num_characters);
288     return 0;
289     }
290    
291     #else
292    
293     int jscoverage_bytes_to_characters(const char * encoding, const uint8_t * bytes, size_t num_bytes, jschar ** characters, size_t * num_characters) {
294     assert(encoding != NULL);
295    
296     if (strcasecmp(encoding, "us-ascii") != 0 && strcasecmp(encoding, "iso-8859-1") != 0 && strcasecmp(encoding, "utf-8") != 0) {
297     return JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED;
298     }
299    
300     jschar * c = xnew(jschar, num_bytes);
301     for (size_t i = 0; i < num_bytes; i++) {
302     if (bytes[i]) > 127) {
303     free(c);
304     return JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED;
305     }
306     c[i] = bytes[i];
307     }
308    
309     *characters = c;
310     *num_characters = num_bytes;
311     return 0;
312     }
313    
314     #endif

  ViewVC Help
Powered by ViewVC 1.1.24