[1505] | 1 | /* |
---|
| 2 | * ORXONOX - the hottest 3D action shooter ever to exist |
---|
| 3 | * > www.orxonox.net < |
---|
| 4 | * |
---|
| 5 | * |
---|
| 6 | * License notice: |
---|
| 7 | * |
---|
| 8 | * This program is free software; you can redistribute it and/or |
---|
| 9 | * modify it under the terms of the GNU General Public License |
---|
| 10 | * as published by the Free Software Foundation; either version 2 |
---|
| 11 | * of the License, or (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, write to the Free Software |
---|
| 20 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
---|
| 21 | * |
---|
| 22 | * Author: |
---|
| 23 | * Fabian 'x3n' Landau |
---|
| 24 | * Co-authors: |
---|
| 25 | * Benjamin Grauer |
---|
| 26 | * |
---|
| 27 | */ |
---|
| 28 | |
---|
[1791] | 29 | /** |
---|
[2171] | 30 | @file |
---|
[1791] | 31 | @brief Implementation of several string manipulation functions. |
---|
| 32 | */ |
---|
| 33 | |
---|
[3250] | 34 | #include "StringUtils.h" |
---|
[1505] | 35 | |
---|
| 36 | #include <cctype> |
---|
[7284] | 37 | #include <boost/scoped_array.hpp> |
---|
[2087] | 38 | #include "Convert.h" |
---|
| 39 | #include "Math.h" |
---|
[1625] | 40 | |
---|
[2171] | 41 | namespace orxonox |
---|
[2087] | 42 | { |
---|
[6417] | 43 | std::string BLANKSTRING; |
---|
[2087] | 44 | |
---|
[2171] | 45 | std::string getUniqueNumberString() |
---|
| 46 | { |
---|
[3280] | 47 | return multi_cast<std::string>(getUniqueNumber()); |
---|
[2171] | 48 | } |
---|
[1505] | 49 | |
---|
[2171] | 50 | /** |
---|
| 51 | @brief Removes all whitespaces from a string. |
---|
| 52 | @param str The string to strip |
---|
| 53 | */ |
---|
| 54 | void strip(std::string* str) |
---|
| 55 | { |
---|
| 56 | size_t pos; |
---|
[6417] | 57 | while ((pos = str->find(' ')) < str->length()) |
---|
| 58 | str->erase(pos, 1); |
---|
| 59 | while ((pos = str->find('\t')) < str->length()) |
---|
| 60 | str->erase(pos, 1); |
---|
| 61 | while ((pos = str->find('\n')) < str->length()) |
---|
| 62 | str->erase(pos, 1); |
---|
[2171] | 63 | } |
---|
[1505] | 64 | |
---|
[2171] | 65 | /** |
---|
| 66 | @brief Returns a copy of a string without whitespaces. |
---|
| 67 | @param str The string to strip |
---|
| 68 | @return The stripped line |
---|
| 69 | */ |
---|
| 70 | std::string getStripped(const std::string& str) |
---|
| 71 | { |
---|
[6417] | 72 | std::string output(str); |
---|
[2171] | 73 | strip(&output); |
---|
| 74 | return output; |
---|
| 75 | } |
---|
[1505] | 76 | |
---|
[2171] | 77 | /** |
---|
| 78 | @brief Returns a copy of a string without trailing whitespaces. |
---|
| 79 | @param str The string |
---|
| 80 | @return The modified copy |
---|
| 81 | */ |
---|
| 82 | std::string removeTrailingWhitespaces(const std::string& str) |
---|
| 83 | { |
---|
| 84 | size_t pos1 = 0; |
---|
[3300] | 85 | int pos2 = static_cast<int>(str.size() - 1); |
---|
[2171] | 86 | for (; pos1 < str.size() && (str[pos1] == ' ' || str[pos1] == '\t' || str[pos1] == '\n'); pos1++); |
---|
| 87 | for (; pos2 > 0 && (str[pos2] == ' ' || str[pos2] == '\t' || str[pos2] == '\n'); pos2--); |
---|
| 88 | return str.substr(pos1, pos2 - pos1 + 1); |
---|
| 89 | } |
---|
[1505] | 90 | |
---|
[2171] | 91 | /** |
---|
| 92 | @brief Returns the position of the next quote in the string, starting with start. |
---|
| 93 | @param str The string |
---|
| 94 | @param start The startposition |
---|
| 95 | @return The position of the next quote (std::string::npos if there is no next quote) |
---|
| 96 | */ |
---|
| 97 | size_t getNextQuote(const std::string& str, size_t start) |
---|
[1505] | 98 | { |
---|
[2171] | 99 | size_t quote = start - 1; |
---|
| 100 | |
---|
[6417] | 101 | while ((quote = str.find('"', quote + 1)) != std::string::npos) |
---|
[2171] | 102 | { |
---|
| 103 | size_t backslash = quote; |
---|
| 104 | size_t numbackslashes = 0; |
---|
| 105 | for (; backslash > 0; backslash--, numbackslashes++) |
---|
| 106 | if (str[backslash - 1] != '\\') |
---|
| 107 | break; |
---|
| 108 | |
---|
| 109 | if (numbackslashes % 2 == 0) |
---|
[1505] | 110 | break; |
---|
[2171] | 111 | } |
---|
[1505] | 112 | |
---|
[2171] | 113 | return quote; |
---|
[1505] | 114 | } |
---|
| 115 | |
---|
[2171] | 116 | /** |
---|
| 117 | @brief Returns true if pos is between two quotes. |
---|
| 118 | @param str The string |
---|
| 119 | @param pos The position to check |
---|
| 120 | @return True if pos is between two quotes |
---|
| 121 | */ |
---|
| 122 | bool isBetweenQuotes(const std::string& str, size_t pos) |
---|
[1505] | 123 | { |
---|
[2171] | 124 | if (pos == std::string::npos) |
---|
[1830] | 125 | return false; |
---|
[1505] | 126 | |
---|
[2171] | 127 | size_t quotecount = 0; |
---|
[3301] | 128 | size_t quote = static_cast<size_t>(-1); |
---|
[2171] | 129 | while ((quote = getNextQuote(str, quote + 1)) < pos) |
---|
| 130 | { |
---|
| 131 | if (quote == pos) |
---|
| 132 | return false; |
---|
| 133 | quotecount++; |
---|
| 134 | } |
---|
[1505] | 135 | |
---|
[2171] | 136 | if (quote == std::string::npos) |
---|
| 137 | return false; |
---|
[1505] | 138 | |
---|
[2171] | 139 | return ((quotecount % 2) == 1); |
---|
| 140 | } |
---|
[1505] | 141 | |
---|
[2171] | 142 | /** |
---|
| 143 | @brief Returns true if the string contains something like '..."between quotes"...'. |
---|
| 144 | @param The string |
---|
| 145 | @return True if there is something between quotes |
---|
| 146 | */ |
---|
| 147 | bool hasStringBetweenQuotes(const std::string& str) |
---|
| 148 | { |
---|
| 149 | size_t pos1 = getNextQuote(str, 0); |
---|
| 150 | size_t pos2 = getNextQuote(str, pos1 + 1); |
---|
| 151 | return (pos1 != std::string::npos && pos2 != std::string::npos && pos2 > pos1 + 1); |
---|
| 152 | } |
---|
[1505] | 153 | |
---|
[2171] | 154 | /** |
---|
| 155 | @brief If the string contains something like '..."between quotes"...' then 'between quotes' gets returned (without quotes). |
---|
| 156 | @param The string |
---|
| 157 | @param The string between the quotes |
---|
| 158 | */ |
---|
| 159 | std::string getStringBetweenQuotes(const std::string& str) |
---|
| 160 | { |
---|
| 161 | size_t pos1 = getNextQuote(str, 0); |
---|
| 162 | size_t pos2 = getNextQuote(str, pos1 + 1); |
---|
| 163 | if (pos1 != std::string::npos && pos2 != std::string::npos) |
---|
| 164 | return str.substr(pos1, pos2 - pos1 + 1); |
---|
| 165 | else |
---|
| 166 | return ""; |
---|
| 167 | } |
---|
[1505] | 168 | |
---|
[2171] | 169 | /** |
---|
| 170 | @brief Removes enclosing quotes if available (including whitespaces at the outside of the quotes). |
---|
| 171 | @brief str The string to strip |
---|
| 172 | @return The string with removed quotes |
---|
| 173 | */ |
---|
| 174 | std::string stripEnclosingQuotes(const std::string& str) |
---|
[1505] | 175 | { |
---|
[2171] | 176 | size_t start = std::string::npos; |
---|
| 177 | size_t end = 0; |
---|
| 178 | |
---|
| 179 | for (size_t pos = 0; (pos < str.size()) && (pos < std::string::npos); pos++) |
---|
[1505] | 180 | { |
---|
[2171] | 181 | if (str[pos] == '"') |
---|
| 182 | { |
---|
| 183 | start = pos; |
---|
| 184 | break; |
---|
| 185 | } |
---|
| 186 | |
---|
| 187 | if ((str[pos] != ' ') && (str[pos] != '\t') && (str[pos] != '\n')) |
---|
| 188 | return str; |
---|
[1505] | 189 | } |
---|
| 190 | |
---|
[2171] | 191 | for (size_t pos = str.size() - 1; pos < std::string::npos; pos--) |
---|
| 192 | { |
---|
| 193 | if (str[pos] == '"') |
---|
| 194 | { |
---|
| 195 | end = pos; |
---|
| 196 | break; |
---|
| 197 | } |
---|
[1505] | 198 | |
---|
[2171] | 199 | if ((str[pos] != ' ') && (str[pos] != '\t') && (str[pos] != '\n')) |
---|
| 200 | return str; |
---|
[1505] | 201 | } |
---|
| 202 | |
---|
[2171] | 203 | if ((start != std::string::npos) && (end != 0)) |
---|
| 204 | return str.substr(start + 1, end - start - 1); |
---|
| 205 | else |
---|
[1505] | 206 | return str; |
---|
| 207 | } |
---|
| 208 | |
---|
[2171] | 209 | /** |
---|
| 210 | @brief Removes enclosing {braces} (braces must be exactly on the beginning and the end of the string). |
---|
| 211 | @param str The string to strip |
---|
| 212 | @return The striped string |
---|
| 213 | */ |
---|
| 214 | std::string stripEnclosingBraces(const std::string& str) |
---|
| 215 | { |
---|
| 216 | std::string output = str; |
---|
[1505] | 217 | |
---|
[2171] | 218 | while (output.size() >= 2 && output[0] == '{' && output[output.size() - 1] == '}') |
---|
| 219 | output = output.substr(1, output.size() - 2); |
---|
[1505] | 220 | |
---|
[2171] | 221 | return output; |
---|
| 222 | } |
---|
[1505] | 223 | |
---|
[2171] | 224 | /** |
---|
| 225 | @brief Determines if a string is a comment (starts with a comment-symbol). |
---|
| 226 | @param str The string to check |
---|
| 227 | @return True = it's a comment |
---|
[1505] | 228 | |
---|
[2171] | 229 | A comment is defined by a leading '#', '%', ';' or '//'. |
---|
| 230 | */ |
---|
| 231 | bool isComment(const std::string& str) |
---|
| 232 | { |
---|
| 233 | // Strip the line, whitespaces are disturbing |
---|
[6417] | 234 | const std::string& teststring = getStripped(str); |
---|
[1505] | 235 | |
---|
[2171] | 236 | // There are four possible comment-symbols: |
---|
| 237 | // 1) #comment in script-language style |
---|
| 238 | // 2) %comment in matlab style |
---|
| 239 | // 3) ;comment in unreal tournament config-file style |
---|
| 240 | // 4) //comment in code style |
---|
| 241 | if (teststring.size() >= 2) |
---|
| 242 | { |
---|
| 243 | if (teststring[0] == '#' || teststring[0] == '%' || teststring[0] == ';' || (teststring[0] == '/' && teststring[1] == '/')) |
---|
| 244 | return true; |
---|
| 245 | } |
---|
| 246 | else if (teststring.size() == 1) |
---|
| 247 | { |
---|
| 248 | if (teststring[0] == '#' || teststring[0] == '%' || teststring[0] == ';') |
---|
| 249 | return true; |
---|
| 250 | } |
---|
[1505] | 251 | |
---|
[2171] | 252 | return false; |
---|
[1505] | 253 | } |
---|
[2171] | 254 | |
---|
| 255 | /** |
---|
| 256 | @brief Determines if a string is empty (contains only whitespaces). |
---|
| 257 | @param str The string to check |
---|
| 258 | @return True = it's empty |
---|
| 259 | */ |
---|
| 260 | bool isEmpty(const std::string& str) |
---|
[1505] | 261 | { |
---|
[6417] | 262 | return getStripped(str).empty(); |
---|
[1505] | 263 | } |
---|
| 264 | |
---|
[2171] | 265 | /** |
---|
| 266 | @brief Determines if a string contains only numbers and maximal one '.'. |
---|
| 267 | @param str The string to check |
---|
| 268 | @return True = it's a number |
---|
| 269 | */ |
---|
| 270 | bool isNumeric(const std::string& str) |
---|
| 271 | { |
---|
| 272 | bool foundPoint = false; |
---|
[1505] | 273 | |
---|
[2171] | 274 | for (std::string::const_iterator it = str.begin(); it != str.end(); ++it) |
---|
[1505] | 275 | { |
---|
[2171] | 276 | if (((*it) < '0' || (*it) > '9')) |
---|
| 277 | { |
---|
| 278 | if ((*it) != '.' && !foundPoint) |
---|
| 279 | foundPoint = true; |
---|
| 280 | else |
---|
| 281 | return false; |
---|
| 282 | } |
---|
[1505] | 283 | } |
---|
[2171] | 284 | |
---|
| 285 | return true; |
---|
[1505] | 286 | } |
---|
| 287 | |
---|
[2171] | 288 | /** |
---|
| 289 | @brief Adds backslashes to the given string which makes special chars visible. Existing slashes will be doubled. |
---|
| 290 | @param str The string to manipulate |
---|
| 291 | @return The string with added slashes |
---|
| 292 | */ |
---|
| 293 | std::string addSlashes(const std::string& str) |
---|
| 294 | { |
---|
[6424] | 295 | std::string output(str.size() * 2, ' '); |
---|
| 296 | size_t i = 0; |
---|
| 297 | for (size_t pos = 0; pos < str.size(); ++pos) |
---|
| 298 | { |
---|
| 299 | switch (str[pos]) |
---|
| 300 | { |
---|
| 301 | case '\\': output[i] = '\\'; output[i + 1] = '\\'; break; |
---|
| 302 | case '\n': output[i] = '\\'; output[i + 1] = 'n'; break; |
---|
| 303 | case '\t': output[i] = '\\'; output[i + 1] = 't'; break; |
---|
| 304 | case '\v': output[i] = '\\'; output[i + 1] = 'v'; break; |
---|
| 305 | case '\b': output[i] = '\\'; output[i + 1] = 'b'; break; |
---|
| 306 | case '\r': output[i] = '\\'; output[i + 1] = 'r'; break; |
---|
| 307 | case '\f': output[i] = '\\'; output[i + 1] = 'f'; break; |
---|
| 308 | case '\a': output[i] = '\\'; output[i + 1] = 'a'; break; |
---|
| 309 | case '"': output[i] = '\\'; output[i + 1] = '"'; break; |
---|
| 310 | case '\0': output[i] = '\\'; output[i + 1] = '0'; break; |
---|
| 311 | default : output[i] = str[pos]; ++i; continue; |
---|
| 312 | } |
---|
| 313 | i += 2; |
---|
| 314 | } |
---|
| 315 | output.resize(i); |
---|
[1505] | 316 | |
---|
[2171] | 317 | return output; |
---|
| 318 | } |
---|
[1505] | 319 | |
---|
[2171] | 320 | /** |
---|
| 321 | @brief Removes backslashes from the given string. Double backslashes are interpreted as one backslash. |
---|
| 322 | @param str The string to manipulate |
---|
| 323 | @return The string with removed slashes |
---|
| 324 | */ |
---|
| 325 | std::string removeSlashes(const std::string& str) |
---|
| 326 | { |
---|
| 327 | if (str.size() <= 1) |
---|
| 328 | return str; |
---|
[1505] | 329 | |
---|
[6424] | 330 | std::string output(str.size(), ' '); |
---|
| 331 | size_t i = 0; |
---|
| 332 | size_t pos = 0; |
---|
| 333 | while (pos < str.size() - 1) |
---|
[2171] | 334 | { |
---|
| 335 | if (str[pos] == '\\') |
---|
| 336 | { |
---|
[6424] | 337 | switch (str[pos + 1]) |
---|
| 338 | { |
---|
| 339 | case '\\': output[i] = '\\'; break; |
---|
| 340 | case 'n': output[i] = '\n'; break; |
---|
| 341 | case 't': output[i] = '\t'; break; |
---|
| 342 | case 'v': output[i] = '\v'; break; |
---|
| 343 | case 'b': output[i] = '\b'; break; |
---|
| 344 | case 'r': output[i] = '\r'; break; |
---|
| 345 | case 'f': output[i] = '\f'; break; |
---|
| 346 | case 'a': output[i] = '\a'; break; |
---|
| 347 | case '"': output[i] = '"'; break; |
---|
| 348 | case '0': output[i] = '\0'; break; |
---|
| 349 | default: ++pos; continue; |
---|
| 350 | } |
---|
| 351 | pos += 2; ++i; |
---|
[2171] | 352 | } |
---|
[6424] | 353 | else |
---|
| 354 | output[i++] = str[pos++]; |
---|
[2171] | 355 | } |
---|
[6424] | 356 | if (pos < str.size()) |
---|
| 357 | output[i++] = str[pos]; |
---|
| 358 | output.resize(i); |
---|
[1505] | 359 | |
---|
[2171] | 360 | return output; |
---|
| 361 | } |
---|
| 362 | |
---|
| 363 | /** |
---|
| 364 | @brief Replaces each char between A and Z with its lowercase equivalent. |
---|
| 365 | @param str The string to convert |
---|
| 366 | */ |
---|
| 367 | void lowercase(std::string* str) |
---|
[1505] | 368 | { |
---|
[2171] | 369 | for (size_t i = 0; i < str->size(); ++i) |
---|
[1505] | 370 | { |
---|
[3300] | 371 | (*str)[i] = static_cast<char>(tolower((*str)[i])); |
---|
[1505] | 372 | } |
---|
| 373 | } |
---|
| 374 | |
---|
[2171] | 375 | /** |
---|
| 376 | @brief Returns a copy of the given string without uppercase chars. |
---|
| 377 | @param str The string |
---|
| 378 | @return The copy |
---|
| 379 | */ |
---|
| 380 | std::string getLowercase(const std::string& str) |
---|
| 381 | { |
---|
[6417] | 382 | std::string output(str); |
---|
[2171] | 383 | lowercase(&output); |
---|
| 384 | return output; |
---|
| 385 | } |
---|
[1505] | 386 | |
---|
[2171] | 387 | /** |
---|
| 388 | @brief Replaces each char between a and z with its uppercase equivalent. |
---|
| 389 | @param str The string to convert |
---|
| 390 | */ |
---|
| 391 | void uppercase(std::string* str) |
---|
[1505] | 392 | { |
---|
[2171] | 393 | for (size_t i = 0; i < str->size(); ++i) |
---|
| 394 | { |
---|
[3300] | 395 | (*str)[i] = static_cast<char>(toupper((*str)[i])); |
---|
[2171] | 396 | } |
---|
[1505] | 397 | } |
---|
| 398 | |
---|
[2171] | 399 | /** |
---|
| 400 | @brief Returns a copy of the given string without lowercase chars. |
---|
| 401 | @param str The string |
---|
| 402 | @return The copy |
---|
| 403 | */ |
---|
| 404 | std::string getUppercase(const std::string& str) |
---|
| 405 | { |
---|
[6417] | 406 | std::string output(str); |
---|
[2171] | 407 | uppercase(&output); |
---|
| 408 | return output; |
---|
| 409 | } |
---|
[1505] | 410 | |
---|
[2171] | 411 | /** |
---|
| 412 | @brief Compares two strings ignoring different casing. |
---|
| 413 | @param s1 First string |
---|
| 414 | @param s2 Second string |
---|
| 415 | */ |
---|
| 416 | int nocaseCmp(const std::string& s1, const std::string& s2) |
---|
[1505] | 417 | { |
---|
[2171] | 418 | std::string::const_iterator it1=s1.begin(); |
---|
| 419 | std::string::const_iterator it2=s2.begin(); |
---|
| 420 | |
---|
| 421 | //stop when either string's end has been reached |
---|
| 422 | while ( (it1!=s1.end()) && (it2!=s2.end()) ) |
---|
| 423 | { |
---|
| 424 | if(::toupper(*it1) != ::toupper(*it2)) //letters differ? |
---|
| 425 | // return -1 to indicate smaller than, 1 otherwise |
---|
| 426 | return (::toupper(*it1) < ::toupper(*it2)) ? -1 : 1; |
---|
| 427 | //proceed to the next character in each string |
---|
| 428 | ++it1; |
---|
| 429 | ++it2; |
---|
| 430 | } |
---|
| 431 | size_t size1=s1.size(), size2=s2.size();// cache lengths |
---|
| 432 | //return -1,0 or 1 according to strings' lengths |
---|
| 433 | if (size1==size2) |
---|
| 434 | return 0; |
---|
| 435 | return (size1<size2) ? -1 : 1; |
---|
[1505] | 436 | } |
---|
| 437 | |
---|
| 438 | |
---|
[2171] | 439 | /** |
---|
| 440 | @brief Compares the first 'len' chars of two strings ignoring different casing. |
---|
| 441 | @param s1 First string |
---|
| 442 | @param s2 Second string |
---|
| 443 | @param len Maximal number of chars to compare |
---|
| 444 | */ |
---|
| 445 | int nocaseCmp(const std::string& s1, const std::string& s2, size_t len) |
---|
[1505] | 446 | { |
---|
[2171] | 447 | if (len == 0) |
---|
| 448 | return 0; |
---|
| 449 | std::string::const_iterator it1=s1.begin(); |
---|
| 450 | std::string::const_iterator it2=s2.begin(); |
---|
[1505] | 451 | |
---|
[2171] | 452 | //stop when either string's end has been reached |
---|
| 453 | while ( (it1!=s1.end()) && (it2!=s2.end()) && len-- > 0) |
---|
| 454 | { |
---|
| 455 | if(::toupper(*it1) != ::toupper(*it2)) //letters differ? |
---|
| 456 | // return -1 to indicate smaller than, 1 otherwise |
---|
| 457 | return (::toupper(*it1) < ::toupper(*it2)) ? -1 : 1; |
---|
| 458 | //proceed to the next character in each string |
---|
| 459 | ++it1; |
---|
| 460 | ++it2; |
---|
| 461 | } |
---|
[1505] | 462 | return 0; |
---|
[2171] | 463 | } |
---|
[1505] | 464 | |
---|
[2171] | 465 | /** |
---|
| 466 | @brief Returns true if the string contains a comment, introduced by #, %, ; or //. |
---|
| 467 | @param str The string |
---|
| 468 | @return True if the string contains a comment |
---|
| 469 | */ |
---|
| 470 | bool hasComment(const std::string& str) |
---|
[1505] | 471 | { |
---|
[2171] | 472 | return (getCommentPosition(str) != std::string::npos); |
---|
[1505] | 473 | } |
---|
| 474 | |
---|
[2171] | 475 | /** |
---|
| 476 | @brief If the string contains a comment, the comment gets returned (including the comment symbol), an empty string otherwise. |
---|
| 477 | @param str The string |
---|
| 478 | @return The comment |
---|
| 479 | */ |
---|
| 480 | std::string getComment(const std::string& str) |
---|
| 481 | { |
---|
| 482 | return str.substr(getCommentPosition(str)); |
---|
| 483 | } |
---|
[1505] | 484 | |
---|
[2171] | 485 | /** |
---|
| 486 | @brief If the string contains a comment, the position of the comment-symbol gets returned, std::string::npos otherwise. |
---|
| 487 | @param str The string |
---|
| 488 | @return The position |
---|
| 489 | */ |
---|
| 490 | size_t getCommentPosition(const std::string& str) |
---|
| 491 | { |
---|
| 492 | return getNextCommentPosition(str, 0); |
---|
| 493 | } |
---|
[1505] | 494 | |
---|
[2171] | 495 | /** |
---|
| 496 | @brief Returns the position of the next comment-symbol, starting with start. |
---|
| 497 | @param str The string |
---|
| 498 | @param start The startposition |
---|
| 499 | @return The position |
---|
| 500 | */ |
---|
| 501 | size_t getNextCommentPosition(const std::string& str, size_t start) |
---|
| 502 | { |
---|
| 503 | for (size_t i = start; i < str.size(); i++) |
---|
| 504 | if (isComment(str.substr(i))) |
---|
| 505 | return i; |
---|
[1505] | 506 | |
---|
[2171] | 507 | return std::string::npos; |
---|
| 508 | } |
---|
[3327] | 509 | |
---|
| 510 | /** |
---|
| 511 | @brief Replaces individual charaters |
---|
| 512 | @param str String to be manipulated |
---|
| 513 | @param target Character to be replaced |
---|
| 514 | @param replacement Replacement character |
---|
| 515 | @return Number of replacements |
---|
| 516 | */ |
---|
[7284] | 517 | size_t replaceCharacters(std::string& str, char target, char replacement) |
---|
[3327] | 518 | { |
---|
| 519 | size_t j = 0; |
---|
| 520 | for (size_t i = 0; i < str.size(); ++i) |
---|
| 521 | { |
---|
| 522 | if (str[i] == target) |
---|
| 523 | { |
---|
| 524 | str[i] = replacement; |
---|
| 525 | ++j; |
---|
| 526 | } |
---|
| 527 | } |
---|
| 528 | return j; |
---|
| 529 | } |
---|
[7284] | 530 | |
---|
| 531 | /** |
---|
| 532 | @brief Calculates the Levenshtein distance between two strings. |
---|
| 533 | |
---|
| 534 | The Levenshtein distance is defined by the number of transformations needed to convert str1 |
---|
| 535 | into str2. Possible transformations are substituted, added, or removed characters. |
---|
| 536 | */ |
---|
| 537 | unsigned int getLevenshteinDistance(const std::string& str1, const std::string& str2) |
---|
| 538 | { |
---|
| 539 | size_t cols = str1.size() + 1; |
---|
| 540 | size_t rows = str2.size() + 1; |
---|
| 541 | boost::scoped_array<int> matrix(new int[rows * cols]); |
---|
| 542 | |
---|
| 543 | for (size_t r = 0; r < rows; ++r) |
---|
| 544 | for (size_t c = 0; c < cols; ++c) |
---|
| 545 | matrix[r*cols + c] = 0; |
---|
| 546 | |
---|
| 547 | for (size_t i = 1; i < cols; ++i) |
---|
| 548 | matrix[0*cols + i] = i; |
---|
| 549 | for (size_t i = 1; i < rows; ++i) |
---|
| 550 | matrix[i*cols + 0] = i; |
---|
| 551 | |
---|
| 552 | for (size_t r = 1; r < rows; ++r) |
---|
| 553 | for (size_t c = 1; c < cols; ++c) |
---|
| 554 | matrix[r*cols + c] = (str1[c-1] != str2[r-1]); |
---|
| 555 | |
---|
| 556 | for (size_t r = 1; r < rows; ++r) |
---|
| 557 | for (size_t c = 1; c < cols; ++c) |
---|
| 558 | matrix[r*cols + c] = std::min(std::min(matrix[(r-1)*cols + c] + 1, |
---|
| 559 | matrix[r*cols + c-1] + 1), |
---|
| 560 | matrix[(r-1)*cols + c-1] + (str1[c-1] != str2[r-1])); |
---|
| 561 | |
---|
| 562 | return matrix[(rows-1)*cols + cols-1]; |
---|
| 563 | } |
---|
[1505] | 564 | } |
---|