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