1//========================================================================= 2// FILENAME : textutils.c 3// DESCRIPTION : Misc. text utilities 4//========================================================================= 5// Copyright (c) 2008- NETGEAR, Inc. All Rights Reserved. 6//========================================================================= 7 8/* This program is free software; you can redistribute it and/or modify 9 * it under the terms of the GNU General Public License as published by 10 * the Free Software Foundation; either version 2 of the License, or 11 * (at your option) any later version. 12 * 13 * This program is distributed in the hope that it will be useful, 14 * but WITHOUT ANY WARRANTY; without even the implied warranty of 15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 16 * GNU General Public License for more details. 17 * 18 * You should have received a copy of the GNU General Public License 19 * along with this program. If not, see <http://www.gnu.org/licenses/>. 20 */ 21 22 23#include <stdlib.h> 24#include <stdio.h> 25#include <string.h> 26#include <ctype.h> 27 28#include "misc.h" 29#include "textutils.h" 30#include "../log.h" 31 32static unsigned int 33_char_htoi(char h) 34{ 35 if (h<'0') 36 return 0; 37 if (h<='9') 38 return h-'0'; 39 if (h<'A') 40 return 0; 41 if (h<='F') 42 return h-'A'+10; 43 if (h<'a') 44 return 0; 45 if (h<='f') 46 return h-'a'+10; 47 return 0; 48} 49 50void 51urldecode(char *src) 52{ 53 char c, *s, *d; 54 55 for (d=s=src; *s; s++, d++) { 56 c = *s; 57 if (c=='%') { 58 c = *++s; 59 if (c=='%') 60 c = '%'; 61 else { 62 c = _char_htoi(c)<<4 | _char_htoi(*++s); 63 } 64 *d = c; 65 } 66 else { 67 *d = c; 68 } 69 } 70 *d = '\0'; 71} 72 73#if 0 74static int 75is_ignoredword(const char *str) 76{ 77 int i; 78 79 if (!prefs.ignoredwords) 80 return 0; 81 82 for (i=0; prefs.ignoredwords[i].n; i++) { 83 if (!(strncasecmp(prefs.ignoredwords[i].word, str, prefs.ignoredwords[i].n))) { 84 char next_char = str[prefs.ignoredwords[i].n]; 85 if (isalnum(next_char)) 86 continue; 87 return prefs.ignoredwords[i].n; 88 } 89 } 90 return 0; 91} 92#endif 93 94char * 95skipspaces(const char *str) 96{ 97 while (isspace(*str)) str++; 98 return (char*) str; 99} 100 101/* 102U+0040 (40): @ A B C D E F G H I J K L M N O 103U+0050 (50): P Q R S T U V W X Y Z [ \ ] ^ _ 104U+0060 (60): ` a b c d e f g h i j k l m n o 105U+0070 (70): p q r s t u v w x y z { | } ~ 106 107U+00c0 (c3 80): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 108U+00d0 (c3 90): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 109U+00e0 (c3 a0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 110U+00f0 (c3 b0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 111U+0100 (c4 80): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 112U+0110 (c4 90): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 113U+0120 (c4 a0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 114U+0130 (c4 b0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 115U+0140 (c5 80): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 116U+0150 (c5 90): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 117U+0160 (c5 a0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 118U+0170 (c5 b0): �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� 119 */ 120 121// conversion table for latin diacritical char to ascii one char or two chars. 122unsigned short UtoAscii[] = { 123 // U+00c0 124 0x0041,0x0041,0x0041,0x0041, 0x0041,0x0041,0x4145,0x0043, 0x0045,0x0045,0x0045,0x0045, 0x0049,0x0049,0x0049,0x0049, 125 0x0044,0x004e,0x004f,0x004f, 0x004f,0x004f,0x004f,0xc397, 0xc398,0x0055,0x0055,0x0055, 0x0055,0x0059,0x0050,0x5353, 126 // U+00e0 127 0x0041,0x0041,0x0041,0x0041, 0x0041,0x0041,0x4145,0x0043, 0x0045,0x0045,0x0045,0x0045, 0x0049,0x0049,0x0049,0x0049, 128 0x0044,0x004e,0x004f,0x004f, 0x004f,0x004f,0x004f,0xc397, 0xc398,0x0055,0x0055,0x0055, 0x0055,0x0059,0x0050,0x5353, 129 // U+0100 130 0x0041,0x0041,0x0041,0x0041, 0x0041,0x0041,0x0043,0x0043, 0x0043,0x0043,0x0043,0x0043, 0x0043,0x0043,0x0044,0x0044, 131 0x0044,0x0044,0x0045,0x0045, 0x0045,0x0045,0x0045,0x0045, 0x0045,0x0045,0x0045,0x0045, 0x0047,0x0047,0x0047,0x0047, 132 // U+0120 133 0x0047,0x0047,0x0047,0x0047, 0x0048,0x0048,0x0048,0x0048, 0x0049,0x0049,0x0049,0x0049, 0x0049,0x0049,0x0049,0x0049, 134 0x0049,0x0049,0x494a,0x494a, 0x004a,0x004a,0x004b,0x004b, 0x004b,0x004c,0x004c,0x004c, 0x004c,0x004c,0x004c,0x004c, 135 // U+0140 136 0x004c,0x004c,0x004c,0x004e, 0x004e,0x004e,0x004e,0x004e, 0x004e,0x004e,0x004e,0x004e, 0x004f,0x004f,0x004f,0x004f, 137 0x004f,0x004f,0x4f45,0x4f45, 0x0052,0x0052,0x0052,0x0052, 0x0052,0x0052,0x0053,0x0053, 0x0053,0x0053,0x0053,0x0053, 138 // U+0160 139 0x0053,0x0053,0x0054,0x0054, 0x0054,0x0054,0x0054,0x0054, 0x0055,0x0055,0x0055,0x0055, 0x0055,0x0055,0x0055,0x0055, 140 0x0055,0x0055,0x0055,0x0055, 0x0057,0x0057,0x0059,0x0059, 0x0059,0x005a,0x005a,0x005a, 0x005a,0x005a,0x005a,0xc5bf 141}; 142 143// conversion table for toupper() function for latin diacritical char 144unsigned short UtoUpper[] = { 145 // U+00c0 146 0xc380,0xc381,0xc382,0xc383, 0xc384,0xc385,0xc386,0xc387, 0xc388,0xc389,0xc38a,0xc38b, 0xc38c,0xc38d,0xc38e,0xc38f, 147 0xc390,0xc391,0xc392,0xc393, 0xc394,0xc395,0xc396,0xc397, 0xc398,0xc399,0xc39a,0xc39b, 0xc39c,0xc39d,0xc39e,0x5353, 148 // U+00e0 149 0xc380,0xc381,0xc382,0xc383, 0xc384,0xc385,0xc386,0xc387, 0xc388,0xc389,0xc38a,0xc38b, 0xc38c,0xc38d,0xc38e,0xc38f, 150 0xc390,0xc391,0xc392,0xc393, 0xc394,0xc395,0xc396,0xc397, 0xc398,0xc399,0xc39a,0xc39b, 0xc39c,0xc39d,0xc39e,0xc39f, 151 // U+0100 152 0xc480,0xc480,0xc482,0xc482, 0xc484,0xc484,0xc486,0xc486, 0xc488,0xc488,0xc48a,0xc48a, 0xc48c,0xc48c,0xc48e,0xc48e, 153 0xc490,0xc490,0xc492,0xc492, 0xc494,0xc494,0xc496,0xc496, 0xc498,0xc498,0xc49a,0xc49a, 0xc49c,0xc49c,0xc49e,0xc49e, 154 // U+0120 155 0xc4a0,0xc4a0,0xc4a2,0xc4a2, 0xc4a4,0xc4a4,0xc4a6,0xc4a6, 0xc4a8,0xc4a8,0xc4aa,0xc4aa, 0xc4ac,0xc4ac,0xc4ae,0xc4ae, 156 0xc4b0,0xc4b0,0xc4b2,0xc4b2, 0xc4b4,0xc4b4,0xc4b6,0xc4b6, 0xc4b8,0xc4b9,0xc4b9,0xc4bb, 0xc4bb,0xc4bd,0xc4bd,0xc4bf, 157 // U+0140 158 0xc4bf,0xc581,0xc581,0xc583, 0xc583,0xc585,0xc585,0xc587, 0xc587,0xc589,0xc58a,0xc58a, 0xc58c,0xc58c,0xc58e,0xc58e, 159 0xc590,0xc591,0xc592,0xc593, 0xc594,0xc595,0xc596,0xc597, 0xc598,0xc599,0xc59a,0xc59b, 0xc59c,0xc59d,0xc59e,0xc59f, 160 // U+0160 161 0xc5a0,0xc5a0,0xc5a2,0xc5a2, 0xc5a4,0xc5a4,0xc5a6,0xc5a6, 0xc5a8,0xc5a8,0xc5aa,0xc5aa, 0xc5ac,0xc5ac,0xc5ae,0xc5ae, 162 0xc5b0,0xc5b1,0xc5b2,0xc5b3, 0xc5b4,0xc5b5,0xc5b6,0xc5b7, 0xc5b8,0xc5b9,0xc5b9,0xc5bb, 0xc5bc,0xc5bd,0xc5bd,0xc5bf, 163}; 164 165 166int 167safe_atoi(char *s) 168{ 169 if (!s) 170 return 0; 171 if ((s[0]>='0' && s[0]<='9') || s[0]=='-' || s[0]=='+') 172 return atoi(s); 173 return 0; 174} 175 176// NOTE: support U+0000 ~ U+FFFF only. 177int 178utf16le_to_utf8(char *dst, int n, __u16 utf16le) 179{ 180 __u16 wc = le16_to_cpu(utf16le); 181 if (wc < 0x80) { 182 if (n<1) return 0; 183 *dst++ = wc & 0xff; 184 return 1; 185 } 186 else if (wc < 0x800) { 187 if (n<2) return 0; 188 *dst++ = 0xc0 | (wc>>6); 189 *dst++ = 0x80 | (wc & 0x3f); 190 return 2; 191 } 192 else { 193 if (n<3) return 0; 194 *dst++ = 0xe0 | (wc>>12); 195 *dst++ = 0x80 | ((wc>>6) & 0x3f); 196 *dst++ = 0x80 | (wc & 0x3f); 197 return 3; 198 } 199} 200 201void 202fetch_string_txt(char *fname, char *lang, int n, ...) 203{ 204 va_list args; 205 char **keys; 206 char ***strs; 207 char **defstr; 208 int i; 209 FILE *fp; 210 char buf[4096]; 211 int state; 212 char *p; 213 char *langid; 214 const char *lang_en = "EN"; 215 216 if (!(keys = malloc(sizeof(keys) * n))) { 217 DPRINTF(E_FATAL, L_SCANNER, "Out of memory\n"); 218 } 219 if (!(strs = malloc(sizeof(strs) * n))) { 220 DPRINTF(E_FATAL, L_SCANNER, "Out of memory\n"); 221 } 222 if (!(defstr = malloc(sizeof(defstr) * n))) { 223 DPRINTF(E_FATAL, L_SCANNER, "Out of memory\n"); 224 } 225 226 va_start(args, n); 227 for (i=0; i<n; i++) { 228 keys[i] = va_arg(args, char *); 229 strs[i] = va_arg(args, char **); 230 defstr[i] = va_arg(args, char *); 231 } 232 va_end(args); 233 234 if (!(fp = fopen(fname, "rb"))) { 235 DPRINTF(E_ERROR, L_SCANNER, "Cannot open <%s>\n", fname); 236 goto _exit; 237 } 238 239 state = -1; 240 while (fgets(buf, sizeof(buf), fp)) { 241 int len = strlen(buf); 242 243 if (buf[len-1]=='\n') buf[len-1] = '\0'; 244 245 if (state<0) { 246 if (isalpha(buf[0])) { 247 for (i=0; i<n; i++) { 248 if (!(strcmp(keys[i], buf))) { 249 state = i; 250 break; 251 } 252 } 253 } 254 } 255 else { 256 int found = 0; 257 258 if (isalpha(buf[0]) || buf[0]=='\0') { 259 state = -1; 260 continue; 261 } 262 263 p = buf; 264 while (isspace(*p)) p++; 265 if (*p == '\0') { 266 state = -1; 267 continue; 268 } 269 langid = p; 270 while (!isspace(*p)) p++; 271 *p++ = '\0'; 272 273 if (!strcmp(lang, langid)) 274 found = 1; 275 else if (strcmp(lang_en, langid)) 276 continue; 277 278 while (isspace(*p)) p++; 279 if (*strs[state]) 280 free(*strs[state]); 281 *strs[state] = strdup(p); 282 283 if (found) 284 state = -1; 285 } 286 } 287 288 for (i=0; i<n; i++) { 289 if (!*strs[i]) 290 *strs[i] = defstr[i]; 291 } 292 fclose(fp); 293 294 _exit: 295 free(keys); 296 free(strs); 297 free(defstr); 298} 299