1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
|
/*
* Copyright (C) 1999-2024 Free Software Foundation, Inc.
* This file is part of the GNU LIBICONV Library.
*
* The GNU LIBICONV Library is free software; you can redistribute it
* and/or modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either version 2.1
* of the License, or (at your option) any later version.
*
* The GNU LIBICONV Library is distributed in the hope that it will be
* useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with the GNU LIBICONV Library; see the file COPYING.LIB.
* If not, see <https://www.gnu.org/licenses/>.
*/
/* Part 1 of iconv_open.
Input: const char* tocode, const char* fromcode.
Output:
unsigned int from_index;
int from_wchar;
unsigned int from_surface;
unsigned int to_index;
int to_wchar;
unsigned int to_surface;
int transliterate;
unsigned int discard_ilseq;
Jumps to 'invalid' in case of error.
*/
{
char buf[MAX_WORD_LENGTH+9+9+1];
const char* cp;
char* bp;
const struct alias * ap;
unsigned int count;
from_surface = ICONV_SURFACE_NONE;
to_surface = ICONV_SURFACE_NONE;
transliterate = 0;
discard_ilseq = 0;
/* Before calling aliases_lookup, convert the input string to upper case,
* and check whether it's entirely ASCII (we call gperf with option "-7"
* to achieve a smaller table) and non-empty. If it's not entirely ASCII,
* or if it's too long, it is not a valid encoding name.
*/
for (to_wchar = 0;;) {
/* Search tocode in the table. */
for (cp = tocode, bp = buf, count = MAX_WORD_LENGTH+9+9+1; ; cp++, bp++) {
unsigned char c = (unsigned char) *cp;
if (c >= 0x80)
goto invalid;
if (c >= 'a' && c <= 'z')
c -= 'a'-'A';
*bp = c;
if (c == '\0')
break;
if (--count == 0)
goto invalid;
}
for (;;) {
char *sp = bp;
int parsed_translit = 0;
int parsed_ignore = 0;
int parsed_non_identical_discard = 0;
for (;;) {
if (sp-buf > 9 && memcmp(sp-9,"/TRANSLIT",9)==0) {
sp = sp - 9;
parsed_translit = 1;
} else if (sp-buf > 7 && memcmp(sp-7,"/IGNORE",7)==0) {
sp = sp - 7;
parsed_ignore = 1;
} else if (sp-buf > 22 && memcmp(sp-22,"/NON_IDENTICAL_DISCARD",22)==0) {
sp = sp - 22;
parsed_non_identical_discard = 1;
} else
break;
if (sp > buf && sp[-1] == '/')
sp = sp - 1;
}
if (sp > buf && sp[-1] == '/') {
bp = sp - 1;
} else if (sp-buf >= 9 && memcmp(sp-9,"/ZOS_UNIX",9)==0) {
bp = sp - 9;
to_surface = ICONV_SURFACE_EBCDIC_ZOS_UNIX;
} else
bp = sp;
*bp = '\0';
if (parsed_translit)
transliterate = 1;
if (parsed_ignore)
discard_ilseq |= DISCARD_INVALID | DISCARD_UNCONVERTIBLE;
if (parsed_non_identical_discard)
discard_ilseq |= DISCARD_UNCONVERTIBLE;
break;
}
if (buf[0] == '\0') {
tocode = locale_charset();
/* Avoid an endless loop that could occur when using an older version
of localcharset.c. */
if (tocode[0] == '\0')
goto invalid;
continue;
}
ap = aliases_lookup(buf,bp-buf);
if (ap == NULL) {
ap = aliases2_lookup(buf);
if (ap == NULL)
goto invalid;
}
if (ap->encoding_index == ei_local_char) {
tocode = locale_charset();
/* Avoid an endless loop that could occur when using an older version
of localcharset.c. */
if (tocode[0] == '\0')
goto invalid;
continue;
}
if (ap->encoding_index == ei_local_wchar_t) {
/* On systems which define __STDC_ISO_10646__, wchar_t is Unicode.
This is also the case on native Woe32 systems and Cygwin >= 1.7, where
we know that it is UTF-16. */
#if (defined _WIN32 && !defined __CYGWIN__) || (defined __CYGWIN__ && CYGWIN_VERSION_DLL_MAJOR >= 1007)
if (sizeof(wchar_t) == 4) {
to_index = ei_ucs4internal;
break;
}
if (sizeof(wchar_t) == 2) {
# if WORDS_LITTLEENDIAN
to_index = ei_utf16le;
# else
to_index = ei_utf16be;
# endif
break;
}
#elif __STDC_ISO_10646__
if (sizeof(wchar_t) == 4) {
to_index = ei_ucs4internal;
break;
}
if (sizeof(wchar_t) == 2) {
to_index = ei_ucs2internal;
break;
}
if (sizeof(wchar_t) == 1) {
to_index = ei_iso8859_1;
break;
}
#endif
#if HAVE_MBRTOWC
to_wchar = 1;
tocode = locale_charset();
continue;
#endif
goto invalid;
}
to_index = ap->encoding_index;
break;
}
for (from_wchar = 0;;) {
/* Search fromcode in the table. */
for (cp = fromcode, bp = buf, count = MAX_WORD_LENGTH+9+9+1; ; cp++, bp++) {
unsigned char c = (unsigned char) *cp;
if (c >= 0x80)
goto invalid;
if (c >= 'a' && c <= 'z')
c -= 'a'-'A';
*bp = c;
if (c == '\0')
break;
if (--count == 0)
goto invalid;
}
for (;;) {
char *sp = bp;
int parsed_translit = 0;
int parsed_ignore = 0;
int parsed_non_identical_discard = 0;
for (;;) {
if (sp-buf > 9 && memcmp(sp-9,"/TRANSLIT",9)==0) {
sp = sp - 9;
parsed_translit = 1;
} else if (sp-buf > 7 && memcmp(sp-7,"/IGNORE",7)==0) {
sp = sp - 7;
parsed_ignore = 1;
} else if (sp-buf > 22 && memcmp(sp-22,"/NON_IDENTICAL_DISCARD",22)==0) {
sp = sp - 22;
parsed_non_identical_discard = 1;
} else
break;
if (sp > buf && sp[-1] == '/')
sp = sp - 1;
}
if (sp > buf && sp[-1] == '/') {
bp = sp - 1;
} else if (sp-buf >= 9 && memcmp(sp-9,"/ZOS_UNIX",9)==0) {
bp = sp - 9;
from_surface = ICONV_SURFACE_EBCDIC_ZOS_UNIX;
} else
bp = sp;
*bp = '\0';
if (parsed_translit)
transliterate = 1;
if (parsed_ignore)
discard_ilseq |= DISCARD_INVALID | DISCARD_UNCONVERTIBLE;
if (parsed_non_identical_discard)
discard_ilseq |= DISCARD_UNCONVERTIBLE;
break;
}
if (buf[0] == '\0') {
fromcode = locale_charset();
/* Avoid an endless loop that could occur when using an older version
of localcharset.c. */
if (fromcode[0] == '\0')
goto invalid;
continue;
}
ap = aliases_lookup(buf,bp-buf);
if (ap == NULL) {
ap = aliases2_lookup(buf);
if (ap == NULL)
goto invalid;
}
if (ap->encoding_index == ei_local_char) {
fromcode = locale_charset();
/* Avoid an endless loop that could occur when using an older version
of localcharset.c. */
if (fromcode[0] == '\0')
goto invalid;
continue;
}
if (ap->encoding_index == ei_local_wchar_t) {
/* On systems which define __STDC_ISO_10646__, wchar_t is Unicode.
This is also the case on native Woe32 systems and Cygwin >= 1.7, where
we know that it is UTF-16. */
#if (defined _WIN32 && !defined __CYGWIN__) || (defined __CYGWIN__ && CYGWIN_VERSION_DLL_MAJOR >= 1007)
if (sizeof(wchar_t) == 4) {
from_index = ei_ucs4internal;
break;
}
if (sizeof(wchar_t) == 2) {
# if WORDS_LITTLEENDIAN
from_index = ei_utf16le;
# else
from_index = ei_utf16be;
# endif
break;
}
#elif __STDC_ISO_10646__
if (sizeof(wchar_t) == 4) {
from_index = ei_ucs4internal;
break;
}
if (sizeof(wchar_t) == 2) {
from_index = ei_ucs2internal;
break;
}
if (sizeof(wchar_t) == 1) {
from_index = ei_iso8859_1;
break;
}
#endif
#if HAVE_WCRTOMB
from_wchar = 1;
fromcode = locale_charset();
continue;
#endif
goto invalid;
}
from_index = ap->encoding_index;
break;
}
}
|
