Learn how easy it is to sync an existing GitHub or Google Code repo to a SourceForge project! See Demo

Close

[b74e2d]: tagutils / textutils.c Maximize Restore History

Download this file

textutils.c    299 lines (266 with data), 8.8 kB

  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
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
//=========================================================================
// FILENAME : textutils.c
// DESCRIPTION : Misc. text utilities
//=========================================================================
// Copyright (c) 2008- NETGEAR, Inc. All Rights Reserved.
//=========================================================================
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include "misc.h"
#include "textutils.h"
#include "../log.h"
static unsigned int
_char_htoi(char h)
{
if (h<'0')
return 0;
if (h<='9')
return h-'0';
if (h<'A')
return 0;
if (h<='F')
return h-'A'+10;
if (h<'a')
return 0;
if (h<='f')
return h-'a'+10;
return 0;
}
void
urldecode(char *src)
{
char c, *s, *d;
for (d=s=src; *s; s++, d++) {
c = *s;
if (c=='%') {
c = *++s;
if (c=='%')
c = '%';
else {
c = _char_htoi(c)<<4 | _char_htoi(*++s);
}
*d = c;
}
else {
*d = c;
}
}
*d = '\0';
}
#if 0
static int
is_ignoredword(const char *str)
{
int i;
if (!prefs.ignoredwords)
return 0;
for (i=0; prefs.ignoredwords[i].n; i++) {
if (!(strncasecmp(prefs.ignoredwords[i].word, str, prefs.ignoredwords[i].n))) {
char next_char = str[prefs.ignoredwords[i].n];
if (isalnum(next_char))
continue;
return prefs.ignoredwords[i].n;
}
}
return 0;
}
#endif
char *
skipspaces(const char *str)
{
while (isspace(*str)) str++;
return (char*) str;
}
/*
U+0040 (40): @ A B C D E F G H I J K L M N O
U+0050 (50): P Q R S T U V W X Y Z [ \ ] ^ _
U+0060 (60): ` a b c d e f g h i j k l m n o
U+0070 (70): p q r s t u v w x y z { | } ~
U+00c0 (c3 80): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+00d0 (c3 90): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+00e0 (c3 a0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+00f0 (c3 b0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+0100 (c4 80): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+0110 (c4 90): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+0120 (c4 a0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+0130 (c4 b0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+0140 (c5 80): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+0150 (c5 90): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+0160 (c5 a0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
U+0170 (c5 b0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� ��
*/
// conversion table for latin diacritical char to ascii one char or two chars.
unsigned short UtoAscii[] = {
// U+00c0
0x0041,0x0041,0x0041,0x0041, 0x0041,0x0041,0x4145,0x0043, 0x0045,0x0045,0x0045,0x0045, 0x0049,0x0049,0x0049,0x0049,
0x0044,0x004e,0x004f,0x004f, 0x004f,0x004f,0x004f,0xc397, 0xc398,0x0055,0x0055,0x0055, 0x0055,0x0059,0x0050,0x5353,
// U+00e0
0x0041,0x0041,0x0041,0x0041, 0x0041,0x0041,0x4145,0x0043, 0x0045,0x0045,0x0045,0x0045, 0x0049,0x0049,0x0049,0x0049,
0x0044,0x004e,0x004f,0x004f, 0x004f,0x004f,0x004f,0xc397, 0xc398,0x0055,0x0055,0x0055, 0x0055,0x0059,0x0050,0x5353,
// U+0100
0x0041,0x0041,0x0041,0x0041, 0x0041,0x0041,0x0043,0x0043, 0x0043,0x0043,0x0043,0x0043, 0x0043,0x0043,0x0044,0x0044,
0x0044,0x0044,0x0045,0x0045, 0x0045,0x0045,0x0045,0x0045, 0x0045,0x0045,0x0045,0x0045, 0x0047,0x0047,0x0047,0x0047,
// U+0120
0x0047,0x0047,0x0047,0x0047, 0x0048,0x0048,0x0048,0x0048, 0x0049,0x0049,0x0049,0x0049, 0x0049,0x0049,0x0049,0x0049,
0x0049,0x0049,0x494a,0x494a, 0x004a,0x004a,0x004b,0x004b, 0x004b,0x004c,0x004c,0x004c, 0x004c,0x004c,0x004c,0x004c,
// U+0140
0x004c,0x004c,0x004c,0x004e, 0x004e,0x004e,0x004e,0x004e, 0x004e,0x004e,0x004e,0x004e, 0x004f,0x004f,0x004f,0x004f,
0x004f,0x004f,0x4f45,0x4f45, 0x0052,0x0052,0x0052,0x0052, 0x0052,0x0052,0x0053,0x0053, 0x0053,0x0053,0x0053,0x0053,
// U+0160
0x0053,0x0053,0x0054,0x0054, 0x0054,0x0054,0x0054,0x0054, 0x0055,0x0055,0x0055,0x0055, 0x0055,0x0055,0x0055,0x0055,
0x0055,0x0055,0x0055,0x0055, 0x0057,0x0057,0x0059,0x0059, 0x0059,0x005a,0x005a,0x005a, 0x005a,0x005a,0x005a,0xc5bf
};
// conversion table for toupper() function for latin diacritical char
unsigned short UtoUpper[] = {
// U+00c0
0xc380,0xc381,0xc382,0xc383, 0xc384,0xc385,0xc386,0xc387, 0xc388,0xc389,0xc38a,0xc38b, 0xc38c,0xc38d,0xc38e,0xc38f,
0xc390,0xc391,0xc392,0xc393, 0xc394,0xc395,0xc396,0xc397, 0xc398,0xc399,0xc39a,0xc39b, 0xc39c,0xc39d,0xc39e,0x5353,
// U+00e0
0xc380,0xc381,0xc382,0xc383, 0xc384,0xc385,0xc386,0xc387, 0xc388,0xc389,0xc38a,0xc38b, 0xc38c,0xc38d,0xc38e,0xc38f,
0xc390,0xc391,0xc392,0xc393, 0xc394,0xc395,0xc396,0xc397, 0xc398,0xc399,0xc39a,0xc39b, 0xc39c,0xc39d,0xc39e,0xc39f,
// U+0100
0xc480,0xc480,0xc482,0xc482, 0xc484,0xc484,0xc486,0xc486, 0xc488,0xc488,0xc48a,0xc48a, 0xc48c,0xc48c,0xc48e,0xc48e,
0xc490,0xc490,0xc492,0xc492, 0xc494,0xc494,0xc496,0xc496, 0xc498,0xc498,0xc49a,0xc49a, 0xc49c,0xc49c,0xc49e,0xc49e,
// U+0120
0xc4a0,0xc4a0,0xc4a2,0xc4a2, 0xc4a4,0xc4a4,0xc4a6,0xc4a6, 0xc4a8,0xc4a8,0xc4aa,0xc4aa, 0xc4ac,0xc4ac,0xc4ae,0xc4ae,
0xc4b0,0xc4b0,0xc4b2,0xc4b2, 0xc4b4,0xc4b4,0xc4b6,0xc4b6, 0xc4b8,0xc4b9,0xc4b9,0xc4bb, 0xc4bb,0xc4bd,0xc4bd,0xc4bf,
// U+0140
0xc4bf,0xc581,0xc581,0xc583, 0xc583,0xc585,0xc585,0xc587, 0xc587,0xc589,0xc58a,0xc58a, 0xc58c,0xc58c,0xc58e,0xc58e,
0xc590,0xc591,0xc592,0xc593, 0xc594,0xc595,0xc596,0xc597, 0xc598,0xc599,0xc59a,0xc59b, 0xc59c,0xc59d,0xc59e,0xc59f,
// U+0160
0xc5a0,0xc5a0,0xc5a2,0xc5a2, 0xc5a4,0xc5a4,0xc5a6,0xc5a6, 0xc5a8,0xc5a8,0xc5aa,0xc5aa, 0xc5ac,0xc5ac,0xc5ae,0xc5ae,
0xc5b0,0xc5b1,0xc5b2,0xc5b3, 0xc5b4,0xc5b5,0xc5b6,0xc5b7, 0xc5b8,0xc5b9,0xc5b9,0xc5bb, 0xc5bc,0xc5bd,0xc5bd,0xc5bf,
};
int
safe_atoi(char *s)
{
if (!s)
return 0;
if ((s[0]>='0' && s[0]<='9') || s[0]=='-' || s[0]=='+')
return atoi(s);
return 0;
}
// NOTE: support U+0000 ~ U+FFFF only.
int
utf16le_to_utf8(char *dst, int n, __u16 utf16le)
{
__u16 wc = le16_to_cpu(utf16le);
if (wc < 0x80) {
if (n<1) return 0;
*dst++ = wc & 0xff;
return 1;
}
else if (wc < 0x800) {
if (n<2) return 0;
*dst++ = 0xc0 | (wc>>6);
*dst++ = 0x80 | (wc & 0x3f);
return 2;
}
else {
if (n<3) return 0;
*dst++ = 0xe0 | (wc>>12);
*dst++ = 0x80 | ((wc>>6) & 0x3f);
*dst++ = 0x80 | (wc & 0x3f);
return 3;
}
}
void
fetch_string_txt(char *fname, char *lang, int n, ...)
{
va_list args;
char **keys;
char ***strs;
char **defstr;
int i;
FILE *fp;
char buf[4096];
int state;
char *p;
char *langid;
const char *lang_en = "EN";
if (!(keys = malloc(sizeof(keys) * n))) {
DPRINTF(E_FATAL, L_SCANNER, "Out of memory\n");
}
if (!(strs = malloc(sizeof(strs) * n))) {
DPRINTF(E_FATAL, L_SCANNER, "Out of memory\n");
}
if (!(defstr = malloc(sizeof(defstr) * n))) {
DPRINTF(E_FATAL, L_SCANNER, "Out of memory\n");
}
va_start(args, n);
for (i=0; i<n; i++) {
keys[i] = va_arg(args, char *);
strs[i] = va_arg(args, char **);
defstr[i] = va_arg(args, char *);
}
va_end(args);
if (!(fp = fopen(fname, "rb"))) {
DPRINTF(E_ERROR, L_SCANNER, "Cannot open <%s>\n", fname);
goto _exit;
}
state = -1;
while (fgets(buf, sizeof(buf), fp)) {
int len = strlen(buf);
if (buf[len-1]=='\n') buf[len-1] = '\0';
if (state<0) {
if (isalpha(buf[0])) {
for (i=0; i<n; i++) {
if (!(strcmp(keys[i], buf))) {
state = i;
break;
}
}
}
}
else {
int found = 0;
if (isalpha(buf[0]) || buf[0]=='\0') {
state = -1;
continue;
}
p = buf;
while (isspace(*p)) p++;
if (*p == '\0') {
state = -1;
continue;
}
langid = p;
while (!isspace(*p)) p++;
*p++ = '\0';
if (!strcmp(lang, langid))
found = 1;
else if (strcmp(lang_en, langid))
continue;
while (isspace(*p)) p++;
if (*strs[state])
free(*strs[state]);
*strs[state] = strdup(p);
if (found)
state = -1;
}
}
for (i=0; i<n; i++) {
if (!*strs[i])
*strs[i] = defstr[i];
}
_exit:
free(keys);
free(strs);
free(defstr);
}