[1076] | 1 | /**********************************************************************
|
---|
| 2 | *
|
---|
| 3 | * text_t.cpp -- a simple 16-bit character string class
|
---|
| 4 | * Copyright (C) 1999 The New Zealand Digital Library Project
|
---|
| 5 | *
|
---|
| 6 | * A component of the Greenstone digital library software
|
---|
| 7 | * from the New Zealand Digital Library Project at the
|
---|
| 8 | * University of Waikato, New Zealand.
|
---|
| 9 | *
|
---|
| 10 | * This program is free software; you can redistribute it and/or modify
|
---|
| 11 | * it under the terms of the GNU General Public License as published by
|
---|
| 12 | * the Free Software Foundation; either version 2 of the License, or
|
---|
| 13 | * (at your option) any later version.
|
---|
| 14 | *
|
---|
| 15 | * This program is distributed in the hope that it will be useful,
|
---|
| 16 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 17 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 18 | * GNU General Public License for more details.
|
---|
| 19 | *
|
---|
| 20 | * You should have received a copy of the GNU General Public License
|
---|
| 21 | * along with this program; if not, write to the Free Software
|
---|
| 22 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 23 | *
|
---|
[1860] | 24 | * $Id: text_t.cpp 10140 2005-06-16 22:49:44Z kjdon $
|
---|
| 25 | *
|
---|
[1076] | 26 | *********************************************************************/
|
---|
| 27 |
|
---|
[1860] | 28 | /*
|
---|
| 29 | $Log$
|
---|
[10140] | 30 | Revision 1.25 2005/06/16 22:49:44 kjdon
|
---|
| 31 | added starts_with and ends_with functions
|
---|
| 32 |
|
---|
[9593] | 33 | Revision 1.24 2005/04/07 04:27:18 kjdon
|
---|
| 34 | added some x++ -> ++x changes submitted by Emanuel Dejanu
|
---|
| 35 |
|
---|
[8727] | 36 | Revision 1.23 2004/12/02 22:21:34 kjdon
|
---|
| 37 | added some changes made by Emanuel Dejanu (Simple Words)
|
---|
| 38 |
|
---|
[7382] | 39 | Revision 1.22 2004/05/24 03:43:22 mdewsnip
|
---|
| 40 | (Human Info) Added const text_t g_EmptyText("") to use instead of plain ol' "".
|
---|
| 41 |
|
---|
[2487] | 42 | Revision 1.21 2001/06/01 02:51:28 sjboddie
|
---|
| 43 | Changes to get phind working under windows
|
---|
| 44 |
|
---|
[1860] | 45 | Revision 1.20 2001/01/25 18:26:44 cs025
|
---|
| 46 | Included CORBA branch for first time
|
---|
| 47 |
|
---|
| 48 | Revision 1.15.2.2 2000/04/05 10:19:38 syeates
|
---|
| 49 | added automatic conversion to allow text_t's to be <<'ed to ostreams
|
---|
| 50 |
|
---|
| 51 | Revision 1.15.2.1 2000/04/04 15:02:29 cs025
|
---|
| 52 | Corba first commit
|
---|
| 53 |
|
---|
| 54 | Revision 1.15 1999/10/14 22:52:39 sjboddie
|
---|
| 55 | joinchar can join using text_t string now too
|
---|
| 56 |
|
---|
| 57 | Revision 1.14 1999/09/24 02:30:03 rjmcnab
|
---|
| 58 | added function has_unicode_letdig
|
---|
| 59 |
|
---|
| 60 | Revision 1.13 1999/09/07 04:57:43 sjboddie
|
---|
| 61 | added gpl notice
|
---|
| 62 |
|
---|
| 63 | Revision 1.12 1999/08/31 08:04:41 rjmcnab
|
---|
| 64 | Fixed a small but hard to find bug in getcarr
|
---|
| 65 |
|
---|
| 66 | Revision 1.11 1999/07/01 04:05:09 rjmcnab
|
---|
| 67 | Optimised append functions slightly and added a reserve function.
|
---|
| 68 |
|
---|
| 69 | Revision 1.10 1999/04/26 03:58:03 sjboddie
|
---|
| 70 | added is_number function
|
---|
| 71 |
|
---|
| 72 | Revision 1.9 1999/04/06 22:17:24 rjmcnab
|
---|
| 73 | Added splits and joins using text_tset.
|
---|
| 74 |
|
---|
| 75 | Revision 1.8 1999/02/28 23:14:41 rjmcnab
|
---|
| 76 |
|
---|
| 77 | Added uc and lc to convert to uppercase and lowercase.
|
---|
| 78 |
|
---|
| 79 | Revision 1.7 1999/02/21 22:26:39 rjmcnab
|
---|
| 80 |
|
---|
| 81 | Made getint() a constant function.
|
---|
| 82 |
|
---|
| 83 | Revision 1.6 1999/02/03 01:13:26 sjboddie
|
---|
| 84 |
|
---|
| 85 | Got interface to handle subcollections and language subcollections -
|
---|
| 86 | committed changes made to some of the collections
|
---|
| 87 |
|
---|
| 88 | Revision 1.5 1999/01/19 01:38:14 rjmcnab
|
---|
| 89 |
|
---|
| 90 | Made the source more portable.
|
---|
| 91 |
|
---|
| 92 | Revision 1.4 1999/01/12 01:51:00 rjmcnab
|
---|
| 93 |
|
---|
| 94 | Standard header.
|
---|
| 95 |
|
---|
| 96 | Revision 1.3 1999/01/08 02:33:16 rjmcnab
|
---|
| 97 |
|
---|
| 98 | Added standard header to source files.
|
---|
| 99 |
|
---|
| 100 | */
|
---|
| 101 |
|
---|
[1076] | 102 | #include "text_t.h"
|
---|
| 103 |
|
---|
| 104 | #if defined(GSDL_USE_OBJECTSPACE)
|
---|
| 105 | # include <ospace\std\algorithm>
|
---|
| 106 | #elif defined(GSDL_USE_STL_H)
|
---|
| 107 | # if defined(GSDL_USE_ALGO_H)
|
---|
| 108 | # include <algo.h>
|
---|
| 109 | # else
|
---|
| 110 | # include <algorithm.h>
|
---|
| 111 | # endif
|
---|
| 112 | #else
|
---|
| 113 | # include <algorithm>
|
---|
| 114 | #endif
|
---|
| 115 |
|
---|
[1860] | 116 | #ifdef HAVE_CONFIG_H
|
---|
| 117 | # ifdef __WIN32__
|
---|
| 118 | # include "WIN32cfg.h"
|
---|
| 119 | # else
|
---|
| 120 | # include "config.h"
|
---|
| 121 | # endif
|
---|
| 122 | #endif
|
---|
[1076] | 123 |
|
---|
[1860] | 124 |
|
---|
[1076] | 125 | #include "unitool.h"
|
---|
| 126 |
|
---|
[7382] | 127 | const text_t g_EmptyText("");
|
---|
| 128 |
|
---|
[1076] | 129 | ////////////////////////////////////
|
---|
| 130 | // text_t methods
|
---|
| 131 | ////////////////////////////////////
|
---|
| 132 |
|
---|
[1860] | 133 | // new stream converter ...
|
---|
[8727] | 134 | ostream& operator<< (ostream &o, const text_t &text)
|
---|
[1860] | 135 | {
|
---|
| 136 | text_t::const_iterator ithere = text.begin();
|
---|
| 137 | text_t::const_iterator itend = text.end();
|
---|
| 138 |
|
---|
| 139 | while (ithere != itend)
|
---|
| 140 | {
|
---|
| 141 | if (*ithere < 256)
|
---|
| 142 | {
|
---|
| 143 | o << (unsigned char)(*ithere);
|
---|
| 144 | }
|
---|
| 145 | else
|
---|
| 146 | {
|
---|
| 147 | // put a space or a question mark depending on what
|
---|
| 148 | // the character is. Question marks tell the user that
|
---|
| 149 | // they are missing some information.
|
---|
| 150 | if (is_unicode_space (*ithere))
|
---|
| 151 | o << ' ';
|
---|
| 152 | else
|
---|
| 153 | o << '?';
|
---|
| 154 | }
|
---|
[8727] | 155 | ++ithere;
|
---|
[1860] | 156 | }
|
---|
| 157 |
|
---|
| 158 | return o;
|
---|
| 159 | }
|
---|
| 160 |
|
---|
[1076] | 161 | text_t::text_t ()
|
---|
| 162 | {
|
---|
| 163 | setencoding(0);
|
---|
| 164 | clear ();
|
---|
| 165 | }
|
---|
| 166 |
|
---|
| 167 | text_t::text_t (int i)
|
---|
| 168 | {
|
---|
| 169 | setencoding(0);
|
---|
| 170 | clear ();
|
---|
| 171 | appendint (i);
|
---|
| 172 | }
|
---|
| 173 |
|
---|
[8727] | 174 | text_t::text_t (const char *s)
|
---|
[1076] | 175 | {
|
---|
| 176 | setencoding(0);
|
---|
| 177 | clear ();
|
---|
| 178 | appendcstr (s);
|
---|
| 179 | }
|
---|
| 180 |
|
---|
[8727] | 181 | text_t::text_t (const char *s, size_type nLength)
|
---|
| 182 | {
|
---|
| 183 | setencoding(0);
|
---|
| 184 | clear ();
|
---|
| 185 | appendcarr(s, nLength);
|
---|
| 186 | }
|
---|
[1860] | 187 |
|
---|
[8727] | 188 |
|
---|
[1076] | 189 | void text_t::append (const text_t &t)
|
---|
| 190 | {
|
---|
| 191 | text.insert(text.end(), t.begin(), t.end());
|
---|
| 192 | }
|
---|
| 193 |
|
---|
| 194 | void text_t::appendrange (iterator first, iterator last)
|
---|
| 195 | {
|
---|
| 196 | text.insert(text.end(), first, last);
|
---|
| 197 | }
|
---|
| 198 |
|
---|
| 199 | void text_t::appendrange (const_iterator first, const_iterator last)
|
---|
| 200 | {
|
---|
| 201 | text.insert(text.end(), first, last);
|
---|
| 202 | }
|
---|
| 203 |
|
---|
| 204 | void text_t::appendint (int i)
|
---|
| 205 | {
|
---|
| 206 | // deal with zeros and negatives
|
---|
| 207 | if (i == 0)
|
---|
| 208 | {
|
---|
| 209 | text.push_back('0');
|
---|
| 210 | return;
|
---|
| 211 | }
|
---|
| 212 | else if (i < 0)
|
---|
| 213 | {
|
---|
| 214 | text.push_back('-');
|
---|
| 215 | i *= -1;
|
---|
| 216 | }
|
---|
| 217 |
|
---|
| 218 | // get a buffer for the conversion
|
---|
| 219 | int maxbuflen = sizeof(int)*3;
|
---|
| 220 | char *buf = new char[maxbuflen];
|
---|
| 221 | int len = 0;
|
---|
| 222 |
|
---|
| 223 | // get the number in reverse
|
---|
| 224 | while (i > 0)
|
---|
| 225 | {
|
---|
| 226 | buf[len++] = '0'+ (i%10);
|
---|
| 227 | i = i/10;
|
---|
| 228 | }
|
---|
| 229 |
|
---|
| 230 | // reverse the number
|
---|
| 231 | while (len > 0)
|
---|
| 232 | {
|
---|
| 233 | text.push_back(buf[--len]);
|
---|
| 234 | }
|
---|
| 235 |
|
---|
[8727] | 236 | delete []buf;
|
---|
[1076] | 237 | }
|
---|
| 238 |
|
---|
| 239 | int text_t::getint () const
|
---|
| 240 | {
|
---|
| 241 | int i = 0;
|
---|
| 242 | int mult = 1; // become -1 for negative numbers
|
---|
| 243 |
|
---|
| 244 | const_iterator here = text.begin();
|
---|
| 245 | const_iterator end = text.end();
|
---|
| 246 |
|
---|
| 247 | // do plus and minus signs
|
---|
| 248 | if (here != end)
|
---|
| 249 | {
|
---|
| 250 | if (*here == '-')
|
---|
| 251 | {
|
---|
| 252 | mult = -1;
|
---|
[9593] | 253 | ++here;
|
---|
[1076] | 254 | }
|
---|
| 255 | else if (*here == '+')
|
---|
| 256 | {
|
---|
| 257 | mult = 1;
|
---|
[8727] | 258 | ++here;
|
---|
[1076] | 259 | }
|
---|
| 260 | }
|
---|
| 261 |
|
---|
| 262 | // deal with the number
|
---|
| 263 | while ((here != end) && (*here >= '0') && (*here <= '9'))
|
---|
| 264 | {
|
---|
| 265 | i = 10*i + (*here - '0');
|
---|
[8727] | 266 | ++here;
|
---|
[1076] | 267 | }
|
---|
| 268 |
|
---|
| 269 | i *= mult;
|
---|
| 270 | return i;
|
---|
| 271 | }
|
---|
| 272 |
|
---|
[2487] | 273 | unsigned long text_t::getulong () const
|
---|
| 274 | {
|
---|
| 275 | unsigned long i = 0;
|
---|
[1076] | 276 |
|
---|
[2487] | 277 | const_iterator here = text.begin();
|
---|
| 278 | const_iterator end = text.end();
|
---|
[1076] | 279 |
|
---|
[2487] | 280 | while ((here != end) && (*here >= '0') && (*here <= '9'))
|
---|
| 281 | {
|
---|
| 282 | i = 10*i + (*here - '0');
|
---|
[8727] | 283 | ++here;
|
---|
[2487] | 284 | }
|
---|
| 285 |
|
---|
| 286 | return i;
|
---|
| 287 | }
|
---|
| 288 |
|
---|
[8727] | 289 | void text_t::appendcarr (const char *s, size_type len)
|
---|
[1076] | 290 | {
|
---|
| 291 | unsigned char *us = (unsigned char *)s;
|
---|
[8727] | 292 | if (text.capacity() < (text.size() + len + 2)) {
|
---|
| 293 | text.reserve(text.size() + len + 2);
|
---|
| 294 | }
|
---|
| 295 |
|
---|
[1076] | 296 | while (len > 0)
|
---|
| 297 | {
|
---|
| 298 | text.push_back (*us); // append this character
|
---|
[8727] | 299 | ++us;
|
---|
| 300 | --len;
|
---|
[1076] | 301 | }
|
---|
| 302 | }
|
---|
| 303 |
|
---|
[8727] | 304 | void text_t::appendcstr (const char *s)
|
---|
[1076] | 305 | {
|
---|
[8727] | 306 | size_t len = strlen(s);
|
---|
| 307 | if (text.capacity() < (text.size() + len + 2)) {
|
---|
| 308 | text.reserve(text.size() + len + 2);
|
---|
| 309 | }
|
---|
| 310 |
|
---|
[1076] | 311 | unsigned char *us = (unsigned char *)s;
|
---|
| 312 | while (*us != '\0')
|
---|
| 313 | {
|
---|
| 314 | text.push_back (*us); // append this character
|
---|
[8727] | 315 | ++us;
|
---|
[1076] | 316 | }
|
---|
| 317 | }
|
---|
| 318 |
|
---|
| 319 |
|
---|
| 320 | // strings returned from getcarr and getcstr become the callers
|
---|
[8727] | 321 | // responsibility and should be deallocated with "delete []"
|
---|
[1076] | 322 |
|
---|
| 323 | char *text_t::getcarr(size_type &len) const
|
---|
| 324 | {
|
---|
| 325 | unsigned char *cstr = new unsigned char[size()];
|
---|
| 326 | len = 0;
|
---|
| 327 |
|
---|
| 328 | const_iterator ithere = begin();
|
---|
| 329 | const_iterator itend = end();
|
---|
| 330 | while (ithere != itend)
|
---|
| 331 | {
|
---|
| 332 | if (*ithere < 256) cstr[len] = (unsigned char)(*ithere);
|
---|
| 333 | else {
|
---|
| 334 | // put a space or a question mark depending on what
|
---|
| 335 | // the character is. Question marks tell the user that
|
---|
| 336 | // they are missing some information.
|
---|
| 337 | if (is_unicode_space (*ithere)) cstr[len] = ' ';
|
---|
| 338 | else cstr[len] = '?';
|
---|
| 339 | }
|
---|
[8727] | 340 | ++len;
|
---|
| 341 | ++ithere;
|
---|
[1076] | 342 | }
|
---|
| 343 |
|
---|
| 344 | return (char *)cstr;
|
---|
| 345 | }
|
---|
| 346 |
|
---|
| 347 | char *text_t::getcstr() const
|
---|
| 348 | {
|
---|
| 349 | unsigned char *cstr = new unsigned char[size() + 1];
|
---|
| 350 | const_iterator ithere = begin();
|
---|
| 351 | const_iterator itend = end();
|
---|
| 352 | int len = 0;
|
---|
| 353 |
|
---|
| 354 | while (ithere != itend)
|
---|
| 355 | {
|
---|
| 356 | if (*ithere < 256) cstr[len] = (unsigned char)(*ithere);
|
---|
| 357 | else {
|
---|
| 358 | // put a space or a question mark depending on what
|
---|
| 359 | // the character is. Question marks tell the user that
|
---|
| 360 | // they are missing some information.
|
---|
| 361 | if (is_unicode_space (*ithere)) cstr[len] = ' ';
|
---|
| 362 | else cstr[len] = '?';
|
---|
| 363 | }
|
---|
[8727] | 364 | ++len;
|
---|
| 365 | ++ithere;
|
---|
[1076] | 366 | }
|
---|
| 367 |
|
---|
| 368 | cstr[len] = '\0';
|
---|
| 369 |
|
---|
| 370 | return (char *)cstr;
|
---|
| 371 | }
|
---|
| 372 |
|
---|
| 373 |
|
---|
| 374 | // general functions which work on text_ts
|
---|
| 375 |
|
---|
| 376 | // find a character within a range
|
---|
| 377 | text_t::const_iterator findchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 378 | unsigned short c)
|
---|
| 379 | {
|
---|
| 380 | while (first != last)
|
---|
| 381 | {
|
---|
| 382 | if (*first == c) break;
|
---|
[8727] | 383 | ++first;
|
---|
[1076] | 384 | }
|
---|
| 385 | return first;
|
---|
| 386 | }
|
---|
| 387 |
|
---|
| 388 | text_t::iterator findchar (text_t::iterator first, text_t::iterator last,
|
---|
| 389 | unsigned short c)
|
---|
| 390 | {
|
---|
| 391 | while (first != last)
|
---|
| 392 | {
|
---|
| 393 | if (*first == c) break;
|
---|
[8727] | 394 | ++first;
|
---|
[1076] | 395 | }
|
---|
| 396 | return first;
|
---|
| 397 | }
|
---|
| 398 |
|
---|
[8727] | 399 | text_t::iterator findword (text_t::iterator first,
|
---|
| 400 | text_t::iterator last,
|
---|
[1860] | 401 | const text_t& word)
|
---|
| 402 | {
|
---|
| 403 | text_t::const_iterator word_begin = word.begin();
|
---|
| 404 | text_t::const_iterator word_end = word.end();
|
---|
| 405 |
|
---|
| 406 | while (first != last)
|
---|
| 407 | {
|
---|
| 408 | text_t::iterator char_match = first;
|
---|
| 409 | text_t::const_iterator word_here = word_begin;
|
---|
| 410 | while (word_here!=word_end)
|
---|
| 411 | {
|
---|
| 412 | if (*char_match != *word_here)
|
---|
| 413 | {
|
---|
| 414 | break;
|
---|
| 415 | }
|
---|
[8727] | 416 | ++char_match;
|
---|
| 417 | ++word_here;
|
---|
[1860] | 418 | }
|
---|
| 419 | if (word_here==word_end)
|
---|
| 420 | {
|
---|
| 421 | return first;
|
---|
| 422 | }
|
---|
[8727] | 423 | ++first;
|
---|
[1860] | 424 | }
|
---|
| 425 | return last; // get to here only if there is no match
|
---|
| 426 | }
|
---|
| 427 |
|
---|
[1076] | 428 | // get a string up to the next delimiter (which is skipped)
|
---|
| 429 | text_t::const_iterator getdelimitstr (text_t::const_iterator first,
|
---|
| 430 | text_t::const_iterator last,
|
---|
| 431 | unsigned short c, text_t &outstr)
|
---|
| 432 | {
|
---|
| 433 | text_t::const_iterator here = first;
|
---|
| 434 | here = findchar (first, last, c);
|
---|
| 435 | outstr.clear();
|
---|
| 436 | outstr.appendrange (first, here);
|
---|
[8727] | 437 | if (here != last) ++here; // skip c
|
---|
[1076] | 438 | return here;
|
---|
| 439 | }
|
---|
| 440 |
|
---|
| 441 | text_t::iterator getdelimitstr (text_t::iterator first, text_t::iterator last,
|
---|
| 442 | unsigned short c, text_t &outstr)
|
---|
| 443 | {
|
---|
| 444 | text_t::iterator here = first;
|
---|
| 445 | here = findchar (first, last, c);
|
---|
| 446 | outstr.clear();
|
---|
| 447 | outstr.appendrange (first, here);
|
---|
[8727] | 448 | if (here != last) ++here; // skip c
|
---|
[1076] | 449 | return here;
|
---|
| 450 | }
|
---|
| 451 |
|
---|
| 452 | // split a string with a character
|
---|
| 453 | void splitchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 454 | unsigned short c, text_tset &outlist)
|
---|
| 455 | {
|
---|
| 456 | outlist.erase(outlist.begin(), outlist.end());
|
---|
| 457 |
|
---|
| 458 | text_t t;
|
---|
| 459 |
|
---|
| 460 | while (first != last)
|
---|
| 461 | {
|
---|
| 462 | first = getdelimitstr (first, last, c, t);
|
---|
| 463 | outlist.insert (t);
|
---|
| 464 | }
|
---|
| 465 | }
|
---|
| 466 |
|
---|
| 467 | void splitchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 468 | unsigned short c, text_tlist &outlist)
|
---|
| 469 | {
|
---|
| 470 | outlist.erase(outlist.begin(), outlist.end());
|
---|
| 471 |
|
---|
| 472 | text_t t;
|
---|
| 473 |
|
---|
| 474 | while (first != last)
|
---|
| 475 | {
|
---|
| 476 | first = getdelimitstr (first, last, c, t);
|
---|
| 477 | outlist.push_back (t);
|
---|
| 478 | }
|
---|
| 479 | }
|
---|
| 480 |
|
---|
| 481 | void splitchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 482 | unsigned short c, text_tarray &outlist)
|
---|
| 483 | {
|
---|
| 484 | outlist.erase(outlist.begin(), outlist.end());
|
---|
| 485 |
|
---|
| 486 | text_t t;
|
---|
| 487 |
|
---|
| 488 | while (first != last)
|
---|
| 489 | {
|
---|
| 490 | first = getdelimitstr (first, last, c, t);
|
---|
| 491 | outlist.push_back (t);
|
---|
| 492 | }
|
---|
| 493 | }
|
---|
| 494 |
|
---|
| 495 | // join a string using a character
|
---|
| 496 | void joinchar (const text_tset &inlist, unsigned short c, text_t &outtext)
|
---|
| 497 | {
|
---|
| 498 | outtext.clear ();
|
---|
| 499 |
|
---|
| 500 | text_tset::const_iterator here = inlist.begin ();
|
---|
| 501 | text_tset::const_iterator end = inlist.end ();
|
---|
[8727] | 502 |
|
---|
| 503 | if (here != end) {
|
---|
| 504 | outtext += *here; ++here;
|
---|
| 505 | while (here != end) {
|
---|
| 506 | outtext.push_back (c);
|
---|
[1076] | 507 | outtext += *here;
|
---|
[8727] | 508 | ++here;
|
---|
[1076] | 509 | }
|
---|
[8727] | 510 | }
|
---|
[1076] | 511 | }
|
---|
| 512 |
|
---|
| 513 | void joinchar (const text_tlist &inlist, unsigned short c, text_t &outtext)
|
---|
| 514 | {
|
---|
| 515 | outtext.clear ();
|
---|
| 516 |
|
---|
| 517 | text_tlist::const_iterator here = inlist.begin ();
|
---|
| 518 | text_tlist::const_iterator end = inlist.end ();
|
---|
[8727] | 519 | if (here != end) {
|
---|
| 520 | outtext += *here; ++here;
|
---|
| 521 | while (here != end) {
|
---|
| 522 | outtext.push_back (c);
|
---|
[1076] | 523 | outtext += *here;
|
---|
[8727] | 524 | ++here;
|
---|
[1076] | 525 | }
|
---|
[8727] | 526 | }
|
---|
[1076] | 527 | }
|
---|
| 528 |
|
---|
| 529 | void joinchar (const text_tarray &inlist, unsigned short c, text_t &outtext)
|
---|
| 530 | {
|
---|
| 531 | outtext.clear ();
|
---|
| 532 |
|
---|
| 533 | text_tarray::const_iterator here = inlist.begin ();
|
---|
| 534 | text_tarray::const_iterator end = inlist.end ();
|
---|
[8727] | 535 | if (here != end) {
|
---|
| 536 | outtext += *here; ++here;
|
---|
| 537 | while (here != end) {
|
---|
| 538 | outtext.push_back (c);
|
---|
[1076] | 539 | outtext += *here;
|
---|
[8727] | 540 | ++here;
|
---|
[1076] | 541 | }
|
---|
[8727] | 542 | }
|
---|
[1076] | 543 | }
|
---|
| 544 |
|
---|
[8727] | 545 | void joinchar (const text_tlist &inlist, const text_t &c, text_t &outtext)
|
---|
[1088] | 546 | {
|
---|
| 547 | outtext.clear ();
|
---|
| 548 |
|
---|
| 549 | text_tlist::const_iterator here = inlist.begin ();
|
---|
| 550 | text_tlist::const_iterator end = inlist.end ();
|
---|
[8727] | 551 | if (here != end) {
|
---|
| 552 | outtext += *here; ++here;
|
---|
| 553 | while (here != end) {
|
---|
| 554 | outtext += c;
|
---|
[1088] | 555 | outtext += *here;
|
---|
[8727] | 556 | ++here;
|
---|
[1088] | 557 | }
|
---|
[8727] | 558 | }
|
---|
[1088] | 559 | }
|
---|
| 560 |
|
---|
[8727] | 561 | void joinchar (const text_tset &inlist, const text_t &c, text_t &outtext)
|
---|
[1088] | 562 | {
|
---|
| 563 | outtext.clear ();
|
---|
| 564 |
|
---|
| 565 | text_tset::const_iterator here = inlist.begin ();
|
---|
| 566 | text_tset::const_iterator end = inlist.end ();
|
---|
[8727] | 567 | if (here != end) {
|
---|
| 568 | outtext += *here; ++here;
|
---|
| 569 | while (here != end) {
|
---|
| 570 | outtext += c;
|
---|
[1088] | 571 | outtext += *here;
|
---|
[8727] | 572 | ++here;
|
---|
[1088] | 573 | }
|
---|
[8727] | 574 | }
|
---|
[1088] | 575 | }
|
---|
| 576 |
|
---|
[8727] | 577 | void joinchar (const text_tarray &inlist, const text_t &c, text_t &outtext)
|
---|
[1076] | 578 | {
|
---|
| 579 | outtext.clear ();
|
---|
| 580 |
|
---|
| 581 | text_tarray::const_iterator here = inlist.begin ();
|
---|
| 582 | text_tarray::const_iterator end = inlist.end ();
|
---|
[8727] | 583 | if (here != end) {
|
---|
| 584 | outtext += *here; ++here;
|
---|
| 585 | while (here != end) {
|
---|
| 586 | outtext += c;
|
---|
[1076] | 587 | outtext += *here;
|
---|
[8727] | 588 | ++here;
|
---|
[1076] | 589 | }
|
---|
[8727] | 590 | }
|
---|
[1076] | 591 | }
|
---|
| 592 |
|
---|
| 593 | // count the occurances of a character within a range
|
---|
| 594 | int countchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 595 | unsigned short c)
|
---|
| 596 | {
|
---|
| 597 | int count = 0;
|
---|
| 598 | while (first != last) {
|
---|
[9593] | 599 | if (*first == c) ++count;
|
---|
| 600 | ++first;
|
---|
[1076] | 601 | }
|
---|
| 602 | return count;
|
---|
| 603 | }
|
---|
| 604 |
|
---|
| 605 | // return a substring of string from first up to but not including last
|
---|
| 606 | text_t substr (text_t::const_iterator first, text_t::const_iterator last) {
|
---|
| 607 |
|
---|
[8727] | 608 | text_t substr; substr.reserve(last - first + 2);
|
---|
[1076] | 609 | while (first != last) {
|
---|
| 610 | substr.push_back(*first);
|
---|
[8727] | 611 | ++first;
|
---|
[1076] | 612 | }
|
---|
| 613 | return substr;
|
---|
| 614 | }
|
---|
| 615 |
|
---|
| 616 |
|
---|
| 617 | // convert to lowercase
|
---|
| 618 | void lc (text_t::iterator first, text_t::iterator last) {
|
---|
| 619 | while (first != last) {
|
---|
| 620 | *first = unicode_tolower(*first);
|
---|
[8727] | 621 | ++first;
|
---|
[1076] | 622 | }
|
---|
| 623 | }
|
---|
| 624 |
|
---|
| 625 | // convert to uppercase
|
---|
| 626 | void uc (text_t::iterator first, text_t::iterator last) {
|
---|
| 627 | while (first != last) {
|
---|
| 628 | *first = unicode_toupper(*first);
|
---|
[8727] | 629 | ++first;
|
---|
[1076] | 630 | }
|
---|
| 631 | }
|
---|
| 632 |
|
---|
| 633 |
|
---|
| 634 | // checks to see if it is a number (i.e. contains only 0-9)
|
---|
| 635 | bool is_number (const text_t &text) {
|
---|
| 636 |
|
---|
| 637 | text_t::const_iterator here = text.begin();
|
---|
| 638 | text_t::const_iterator end = text.end();
|
---|
| 639 |
|
---|
| 640 | while (here != end) {
|
---|
| 641 | if ((*here!='0') && (*here!='1') && (*here!='2') &&
|
---|
| 642 | (*here!='3') && (*here!='4') && (*here!='5') &&
|
---|
| 643 | (*here!='6') && (*here!='7') && (*here!='8') &&
|
---|
| 644 | (*here!='9')) return false;
|
---|
[8727] | 645 | ++here;
|
---|
[1076] | 646 | }
|
---|
| 647 | return true;
|
---|
| 648 | }
|
---|
| 649 |
|
---|
| 650 |
|
---|
| 651 | // checks to see if the text has any letters or digits
|
---|
| 652 | bool has_unicode_letdig (const text_t &text) {
|
---|
| 653 | if (text.empty()) return false;
|
---|
| 654 |
|
---|
| 655 | text_t::const_iterator here = text.begin();
|
---|
| 656 | text_t::const_iterator end = text.end();
|
---|
| 657 | while (here != end) {
|
---|
| 658 | if (is_unicode_letdig (*here)) return true;
|
---|
[8727] | 659 | ++here;
|
---|
[1076] | 660 | }
|
---|
| 661 |
|
---|
| 662 | return false;
|
---|
| 663 | }
|
---|
| 664 |
|
---|
[10140] | 665 | // checks to see if a text_t starts with the specified prefix
|
---|
| 666 | bool starts_with(const text_t& text, const text_t& prefix) {
|
---|
| 667 | if (prefix.empty()) return true;
|
---|
| 668 | if (text.empty() || text.size()<prefix.size()) return false;
|
---|
| 669 | text_t substring = substr(text.begin(), text.begin()+prefix.size());
|
---|
| 670 | return substring == prefix;
|
---|
| 671 | }
|
---|
| 672 | // checks to see if a text_t ends with the specified suffix
|
---|
| 673 | bool ends_with(const text_t& text, const text_t& suffix) {
|
---|
| 674 | if (suffix.empty()) return true;
|
---|
| 675 | if (text.empty() || text.size() < suffix.size()) return false;
|
---|
| 676 | text_t substring = substr(text.end()-suffix.size(),text.end());
|
---|
| 677 | return substring == suffix;
|
---|
[1076] | 678 |
|
---|
[10140] | 679 | }
|
---|
[1076] | 680 |
|
---|
[10140] | 681 |
|
---|
[1076] | 682 | ////////////////////////////////////
|
---|
| 683 | // convertclass methods
|
---|
| 684 | ////////////////////////////////////
|
---|
| 685 |
|
---|
| 686 | // conversion classes used for getting information in to and out of
|
---|
| 687 | // the text_t class.
|
---|
| 688 |
|
---|
| 689 | convertclass::convertclass ()
|
---|
| 690 | {
|
---|
| 691 | // nothing to do
|
---|
| 692 | }
|
---|
| 693 |
|
---|
| 694 | void convertclass::reset ()
|
---|
| 695 | {
|
---|
| 696 | // nothing to do
|
---|
| 697 | }
|
---|
| 698 |
|
---|
| 699 |
|
---|
| 700 | ////////////////////////////////////
|
---|
| 701 | // inconvertclass methods
|
---|
| 702 | ////////////////////////////////////
|
---|
| 703 |
|
---|
| 704 | // convert from a char stream to the text_t class
|
---|
| 705 | // the default version assumes the input is a ascii
|
---|
| 706 | // character array
|
---|
| 707 |
|
---|
| 708 | inconvertclass::inconvertclass ()
|
---|
| 709 | {
|
---|
| 710 | start = NULL;
|
---|
| 711 | len = 0;
|
---|
| 712 | }
|
---|
| 713 |
|
---|
| 714 |
|
---|
| 715 | void inconvertclass::reset ()
|
---|
| 716 | {
|
---|
| 717 | start = NULL;
|
---|
| 718 | len = 0;
|
---|
| 719 | }
|
---|
| 720 |
|
---|
| 721 | void inconvertclass::setinput (char *thestart, size_t thelen)
|
---|
| 722 | {
|
---|
| 723 | start = thestart;
|
---|
| 724 | len = thelen;
|
---|
| 725 | }
|
---|
| 726 |
|
---|
| 727 | void inconvertclass::convert (text_t &output, status_t &status)
|
---|
| 728 | {
|
---|
| 729 | output.clear();
|
---|
| 730 |
|
---|
| 731 | if (start == NULL || len == 0)
|
---|
| 732 | {
|
---|
| 733 | status = finished;
|
---|
| 734 | return;
|
---|
| 735 | }
|
---|
| 736 |
|
---|
[8727] | 737 | if (output.capacity() < len + 2)
|
---|
| 738 | output.reserve(len + 2);
|
---|
| 739 |
|
---|
[1076] | 740 | // don't want any funny sign conversions happening
|
---|
| 741 | unsigned char *here = (unsigned char *)start;
|
---|
| 742 | while (len > 0)
|
---|
| 743 | {
|
---|
| 744 | output.push_back (*here); // append this character
|
---|
| 745 | ++here;
|
---|
| 746 | --len;
|
---|
| 747 | }
|
---|
| 748 |
|
---|
| 749 | start = (char *)here; // save current position
|
---|
| 750 | status = finished;
|
---|
| 751 | }
|
---|
| 752 |
|
---|
| 753 | // will treat the text_t as a 8-bit string and convert
|
---|
| 754 | // it to a 16-bit string using the about convert method.
|
---|
| 755 | text_t inconvertclass::convert (const text_t &t) {
|
---|
| 756 | text_t out;
|
---|
| 757 | text_t tmpout;
|
---|
| 758 | status_t status;
|
---|
| 759 | text_t::const_iterator here = t.begin();
|
---|
| 760 | text_t::const_iterator end = t.end();
|
---|
| 761 | unsigned char cbuf[256];
|
---|
| 762 | size_t cbuflen = 0;
|
---|
| 763 |
|
---|
[8727] | 764 | out.clear();
|
---|
| 765 | if (out.capacity() < t.size() + 2)
|
---|
| 766 | out.reserve(t.size() + 2);
|
---|
[1076] | 767 | while (here != end) {
|
---|
| 768 | while (here != end && cbuflen < 256) {
|
---|
| 769 | cbuf[cbuflen++] = (unsigned char)(*here & 0xff);
|
---|
[8727] | 770 | ++here;
|
---|
[1076] | 771 | }
|
---|
| 772 |
|
---|
| 773 | if (cbuflen > 0) {
|
---|
| 774 | setinput ((char *)cbuf, cbuflen);
|
---|
| 775 | status = unfinished;
|
---|
| 776 | while (status == unfinished) {
|
---|
| 777 | convert (tmpout, status);
|
---|
| 778 | out += tmpout;
|
---|
| 779 | }
|
---|
| 780 | cbuflen = 0;
|
---|
| 781 | }
|
---|
| 782 | }
|
---|
| 783 |
|
---|
| 784 | out.setencoding (0); // unicode
|
---|
| 785 |
|
---|
| 786 | return out;
|
---|
| 787 | }
|
---|
| 788 |
|
---|
| 789 | // an instance of the default inconvertclass to do simple
|
---|
| 790 | // conversions. Note that any functions that use this are
|
---|
| 791 | // not reentrant. If a function needs to be reentrant it
|
---|
| 792 | // should declare its own instance.
|
---|
| 793 | inconvertclass ascii2text_t;
|
---|
| 794 |
|
---|
| 795 |
|
---|
| 796 | ////////////////////////////////////
|
---|
| 797 | // outconvertclass methods
|
---|
| 798 | ////////////////////////////////////
|
---|
| 799 |
|
---|
| 800 | // Convert from a text_t class to a char stream
|
---|
| 801 | // This default version assumes the output is a ascii
|
---|
| 802 | // character array. If you set the output stream you
|
---|
| 803 | // can use this class to output to a stream using the
|
---|
| 804 | // << operator. The << operator can also be conveniently
|
---|
| 805 | // used to set the output stream by doing something like
|
---|
| 806 | //
|
---|
| 807 | // cout << text_t2ascii << text_tstr << anothertext_tstr;
|
---|
| 808 | //
|
---|
| 809 | outconvertclass::outconvertclass ()
|
---|
| 810 | {
|
---|
| 811 | input = NULL;
|
---|
| 812 | outs = NULL;
|
---|
| 813 | }
|
---|
| 814 |
|
---|
| 815 | void outconvertclass::reset ()
|
---|
| 816 | {
|
---|
| 817 | input = NULL;
|
---|
| 818 | outs = NULL;
|
---|
| 819 | }
|
---|
| 820 |
|
---|
| 821 | void outconvertclass::setinput (text_t *theinput)
|
---|
| 822 | {
|
---|
| 823 | input = theinput;
|
---|
| 824 | if (input != NULL) texthere = input->begin();
|
---|
| 825 | }
|
---|
| 826 |
|
---|
[8727] | 827 | void outconvertclass::setdata(text_t *theinput, text_t::iterator thetexthere)
|
---|
| 828 | {
|
---|
| 829 | input = theinput;
|
---|
| 830 | texthere = thetexthere;
|
---|
| 831 | }
|
---|
| 832 |
|
---|
[1076] | 833 | void outconvertclass::convert (char *output, size_t maxlen,
|
---|
| 834 | size_t &len, status_t &status)
|
---|
| 835 | {
|
---|
| 836 | if (input == NULL || output == NULL)
|
---|
| 837 | {
|
---|
| 838 | status = finished;
|
---|
| 839 | return;
|
---|
| 840 | }
|
---|
| 841 |
|
---|
| 842 | // don't want any funny sign conversions happening
|
---|
| 843 | unsigned char *uoutput = (unsigned char *)output;
|
---|
| 844 | text_t::iterator textend = input->end();
|
---|
| 845 | len = 0;
|
---|
| 846 | while ((len < maxlen) && (texthere != textend))
|
---|
| 847 | {
|
---|
| 848 | if (*texthere < 256) *uoutput = (unsigned char)(*texthere);
|
---|
| 849 | else {
|
---|
| 850 | // put a space or a question mark depending on what
|
---|
| 851 | // the character is. Question marks tell the user that
|
---|
| 852 | // they are missing some information.
|
---|
| 853 | if (is_unicode_space (*texthere)) *uoutput = ' ';
|
---|
| 854 | else *uoutput = '?';
|
---|
| 855 | }
|
---|
| 856 | ++uoutput;
|
---|
| 857 | ++len;
|
---|
| 858 | ++texthere;
|
---|
| 859 | }
|
---|
| 860 |
|
---|
| 861 | if (texthere == textend) status = finished;
|
---|
| 862 | else status = unfinished;
|
---|
| 863 | }
|
---|
| 864 |
|
---|
| 865 | // will convert the 16-bit string to a 8-bit stream
|
---|
| 866 | // and place the result in a text_t. This method uses
|
---|
| 867 | // the above convert function.
|
---|
| 868 | text_t outconvertclass::convert (const text_t &t) {
|
---|
| 869 | text_t out;
|
---|
| 870 | unsigned char cbuf[256];
|
---|
| 871 | size_t cbuflen = 0;
|
---|
| 872 | status_t status = unfinished;
|
---|
[8727] | 873 |
|
---|
| 874 | out.clear();
|
---|
| 875 | if (out.capacity() < t.size() + 2)
|
---|
| 876 | out.reserve(t.size() + 2);
|
---|
[1076] | 877 | setinput ((text_t *)&t); // discard constant
|
---|
| 878 | while (status == unfinished) {
|
---|
| 879 | convert ((char *)cbuf, 256, cbuflen, status);
|
---|
| 880 | out.appendcarr ((char *)cbuf, cbuflen);
|
---|
| 881 | }
|
---|
| 882 |
|
---|
| 883 | out.setencoding (1); // other encoding
|
---|
| 884 |
|
---|
| 885 | return out;
|
---|
| 886 | }
|
---|
| 887 |
|
---|
| 888 |
|
---|
| 889 | void outconvertclass::setostream (ostream *theouts)
|
---|
| 890 | {
|
---|
| 891 | outs = theouts;
|
---|
| 892 | }
|
---|
| 893 |
|
---|
| 894 | ostream *outconvertclass::getostream ()
|
---|
| 895 | {
|
---|
| 896 | return outs;
|
---|
| 897 | }
|
---|
| 898 |
|
---|
| 899 |
|
---|
| 900 |
|
---|
| 901 |
|
---|
| 902 | // an instance of the default outconvertclass to do simple
|
---|
| 903 | // conversions
|
---|
| 904 | outconvertclass text_t2ascii;
|
---|
| 905 |
|
---|
| 906 |
|
---|
| 907 |
|
---|
| 908 | // stream operators for the output class
|
---|
| 909 |
|
---|
| 910 | outconvertclass &operator<< (ostream &theouts, outconvertclass &outconverter)
|
---|
| 911 | {
|
---|
| 912 | outconverter.setostream(&theouts);
|
---|
| 913 | return outconverter;
|
---|
| 914 | }
|
---|
| 915 |
|
---|
| 916 |
|
---|
| 917 | #define STREAMBUFSIZE 256
|
---|
| 918 | outconvertclass &operator<< (outconvertclass &outconverter, const text_t &t)
|
---|
| 919 | {
|
---|
| 920 | ostream *outstream = outconverter.getostream();
|
---|
| 921 |
|
---|
| 922 | if (outstream == NULL) return outconverter;
|
---|
| 923 |
|
---|
| 924 | char outbuf[STREAMBUFSIZE];
|
---|
| 925 | size_t len;
|
---|
| 926 | outconvertclass::status_t status = outconvertclass::unfinished;
|
---|
| 927 |
|
---|
| 928 | // assume that there is no data needing converting
|
---|
| 929 | // left in the converter
|
---|
| 930 | outconverter.setinput ((text_t *)(&t)); // note the const -> nonconst conversion
|
---|
| 931 |
|
---|
| 932 | while (status == outconvertclass::unfinished)
|
---|
| 933 | {
|
---|
| 934 | outconverter.convert (outbuf, STREAMBUFSIZE, len, status);
|
---|
| 935 | if (len > 0) outstream->write(outbuf, len);
|
---|
| 936 | }
|
---|
| 937 |
|
---|
| 938 | return outconverter;
|
---|
| 939 | }
|
---|