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 "Convert.h" |
---|
38 | #include "Math.h" |
---|
39 | |
---|
40 | namespace orxonox |
---|
41 | { |
---|
42 | std::string BLANKSTRING(""); |
---|
43 | |
---|
44 | std::string getUniqueNumberString() |
---|
45 | { |
---|
46 | return multi_cast<std::string>(getUniqueNumber()); |
---|
47 | } |
---|
48 | |
---|
49 | /** |
---|
50 | @brief Removes all whitespaces from a string. |
---|
51 | @param str The string to strip |
---|
52 | */ |
---|
53 | void strip(std::string* str) |
---|
54 | { |
---|
55 | size_t pos; |
---|
56 | while ((pos = (*str).find(" ")) < (*str).length()) |
---|
57 | (*str).erase(pos, 1); |
---|
58 | while ((pos = (*str).find("\t")) < (*str).length()) |
---|
59 | (*str).erase(pos, 1); |
---|
60 | while ((pos = (*str).find("\n")) < (*str).length()) |
---|
61 | (*str).erase(pos, 1); |
---|
62 | } |
---|
63 | |
---|
64 | /** |
---|
65 | @brief Returns a copy of a string without whitespaces. |
---|
66 | @param str The string to strip |
---|
67 | @return The stripped line |
---|
68 | */ |
---|
69 | std::string getStripped(const std::string& str) |
---|
70 | { |
---|
71 | std::string output = std::string(str); |
---|
72 | strip(&output); |
---|
73 | return output; |
---|
74 | } |
---|
75 | |
---|
76 | /** |
---|
77 | @brief Returns a copy of a string without trailing whitespaces. |
---|
78 | @param str The string |
---|
79 | @return The modified copy |
---|
80 | */ |
---|
81 | std::string removeTrailingWhitespaces(const std::string& str) |
---|
82 | { |
---|
83 | size_t pos1 = 0; |
---|
84 | int pos2 = (int)(str.size() - 1); |
---|
85 | for (; pos1 < str.size() && (str[pos1] == ' ' || str[pos1] == '\t' || str[pos1] == '\n'); pos1++); |
---|
86 | for (; pos2 > 0 && (str[pos2] == ' ' || str[pos2] == '\t' || str[pos2] == '\n'); pos2--); |
---|
87 | return str.substr(pos1, pos2 - pos1 + 1); |
---|
88 | } |
---|
89 | |
---|
90 | /** |
---|
91 | @brief Returns the position of the next quote in the string, starting with start. |
---|
92 | @param str The string |
---|
93 | @param start The startposition |
---|
94 | @return The position of the next quote (std::string::npos if there is no next quote) |
---|
95 | */ |
---|
96 | size_t getNextQuote(const std::string& str, size_t start) |
---|
97 | { |
---|
98 | size_t quote = start - 1; |
---|
99 | |
---|
100 | while ((quote = str.find('\"', quote + 1)) != std::string::npos) |
---|
101 | { |
---|
102 | size_t backslash = quote; |
---|
103 | size_t numbackslashes = 0; |
---|
104 | for (; backslash > 0; backslash--, numbackslashes++) |
---|
105 | if (str[backslash - 1] != '\\') |
---|
106 | break; |
---|
107 | |
---|
108 | if (numbackslashes % 2 == 0) |
---|
109 | break; |
---|
110 | } |
---|
111 | |
---|
112 | return quote; |
---|
113 | } |
---|
114 | |
---|
115 | /** |
---|
116 | @brief Returns true if pos is between two quotes. |
---|
117 | @param str The string |
---|
118 | @param pos The position to check |
---|
119 | @return True if pos is between two quotes |
---|
120 | */ |
---|
121 | bool isBetweenQuotes(const std::string& str, size_t pos) |
---|
122 | { |
---|
123 | if (pos == std::string::npos) |
---|
124 | return false; |
---|
125 | |
---|
126 | size_t quotecount = 0; |
---|
127 | size_t quote = (size_t)-1; |
---|
128 | while ((quote = getNextQuote(str, quote + 1)) < pos) |
---|
129 | { |
---|
130 | if (quote == pos) |
---|
131 | return false; |
---|
132 | quotecount++; |
---|
133 | } |
---|
134 | |
---|
135 | if (quote == std::string::npos) |
---|
136 | return false; |
---|
137 | |
---|
138 | return ((quotecount % 2) == 1); |
---|
139 | } |
---|
140 | |
---|
141 | /** |
---|
142 | @brief Returns true if the string contains something like '..."between quotes"...'. |
---|
143 | @param The string |
---|
144 | @return True if there is something between quotes |
---|
145 | */ |
---|
146 | bool hasStringBetweenQuotes(const std::string& str) |
---|
147 | { |
---|
148 | size_t pos1 = getNextQuote(str, 0); |
---|
149 | size_t pos2 = getNextQuote(str, pos1 + 1); |
---|
150 | return (pos1 != std::string::npos && pos2 != std::string::npos && pos2 > pos1 + 1); |
---|
151 | } |
---|
152 | |
---|
153 | /** |
---|
154 | @brief If the string contains something like '..."between quotes"...' then 'between quotes' gets returned (without quotes). |
---|
155 | @param The string |
---|
156 | @param 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 | @brief 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 | 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 | std::string temp = getStripped(str); |
---|
262 | return ((temp == "") || (temp.size() == 0)); |
---|
263 | } |
---|
264 | |
---|
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; |
---|
273 | |
---|
274 | for (std::string::const_iterator it = str.begin(); it != str.end(); ++it) |
---|
275 | { |
---|
276 | if (((*it) < '0' || (*it) > '9')) |
---|
277 | { |
---|
278 | if ((*it) != '.' && !foundPoint) |
---|
279 | foundPoint = true; |
---|
280 | else |
---|
281 | return false; |
---|
282 | } |
---|
283 | } |
---|
284 | |
---|
285 | return true; |
---|
286 | } |
---|
287 | |
---|
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 | { |
---|
295 | std::string output = str; |
---|
296 | |
---|
297 | for (size_t pos = 0; (pos = output.find('\\', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\\\"); } |
---|
298 | for (size_t pos = 0; (pos = output.find('\n', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\n"); } |
---|
299 | for (size_t pos = 0; (pos = output.find('\t', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\t"); } |
---|
300 | for (size_t pos = 0; (pos = output.find('\v', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\v"); } |
---|
301 | for (size_t pos = 0; (pos = output.find('\b', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\b"); } |
---|
302 | for (size_t pos = 0; (pos = output.find('\r', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\r"); } |
---|
303 | for (size_t pos = 0; (pos = output.find('\f', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\f"); } |
---|
304 | for (size_t pos = 0; (pos = output.find('\a', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\a"); } |
---|
305 | for (size_t pos = 0; (pos = output.find('"', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\\""); } |
---|
306 | for (size_t pos = 0; (pos = output.find('\0', pos)) < std::string::npos; pos += 2) { output.replace(pos, 1, "\\0"); } |
---|
307 | |
---|
308 | return output; |
---|
309 | } |
---|
310 | |
---|
311 | /** |
---|
312 | @brief Removes backslashes from the given string. Double backslashes are interpreted as one backslash. |
---|
313 | @param str The string to manipulate |
---|
314 | @return The string with removed slashes |
---|
315 | */ |
---|
316 | std::string removeSlashes(const std::string& str) |
---|
317 | { |
---|
318 | if (str.size() <= 1) |
---|
319 | return str; |
---|
320 | |
---|
321 | std::string output = ""; |
---|
322 | for (size_t pos = 0; pos < str.size() - 1; ) |
---|
323 | { |
---|
324 | if (str[pos] == '\\') |
---|
325 | { |
---|
326 | if (str[pos + 1] == '\\') { output += '\\'; pos += 2; continue; } |
---|
327 | else if (str[pos + 1] == 'n') { output += '\n'; pos += 2; continue; } |
---|
328 | else if (str[pos + 1] == 't') { output += '\t'; pos += 2; continue; } |
---|
329 | else if (str[pos + 1] == 'v') { output += '\v'; pos += 2; continue; } |
---|
330 | else if (str[pos + 1] == 'b') { output += '\b'; pos += 2; continue; } |
---|
331 | else if (str[pos + 1] == 'r') { output += '\r'; pos += 2; continue; } |
---|
332 | else if (str[pos + 1] == 'f') { output += '\f'; pos += 2; continue; } |
---|
333 | else if (str[pos + 1] == 'a') { output += '\a'; pos += 2; continue; } |
---|
334 | else if (str[pos + 1] == '"') { output += '"'; pos += 2; continue; } |
---|
335 | else if (str[pos + 1] == '0') { output += '\0'; pos += 2; continue; } |
---|
336 | } |
---|
337 | output += str[pos]; |
---|
338 | pos++; |
---|
339 | if (pos == str.size() - 1) |
---|
340 | output += str[pos]; |
---|
341 | } |
---|
342 | |
---|
343 | return output; |
---|
344 | } |
---|
345 | |
---|
346 | /** |
---|
347 | @brief Replaces each char between A and Z with its lowercase equivalent. |
---|
348 | @param str The string to convert |
---|
349 | */ |
---|
350 | void lowercase(std::string* str) |
---|
351 | { |
---|
352 | for (size_t i = 0; i < str->size(); ++i) |
---|
353 | { |
---|
354 | (*str)[i] = (char)tolower((*str)[i]); |
---|
355 | } |
---|
356 | } |
---|
357 | |
---|
358 | /** |
---|
359 | @brief Returns a copy of the given string without uppercase chars. |
---|
360 | @param str The string |
---|
361 | @return The copy |
---|
362 | */ |
---|
363 | std::string getLowercase(const std::string& str) |
---|
364 | { |
---|
365 | std::string output = std::string(str); |
---|
366 | lowercase(&output); |
---|
367 | return output; |
---|
368 | } |
---|
369 | |
---|
370 | /** |
---|
371 | @brief Replaces each char between a and z with its uppercase equivalent. |
---|
372 | @param str The string to convert |
---|
373 | */ |
---|
374 | void uppercase(std::string* str) |
---|
375 | { |
---|
376 | for (size_t i = 0; i < str->size(); ++i) |
---|
377 | { |
---|
378 | (*str)[i] = (char)toupper((*str)[i]); |
---|
379 | } |
---|
380 | } |
---|
381 | |
---|
382 | /** |
---|
383 | @brief Returns a copy of the given string without lowercase chars. |
---|
384 | @param str The string |
---|
385 | @return The copy |
---|
386 | */ |
---|
387 | std::string getUppercase(const std::string& str) |
---|
388 | { |
---|
389 | std::string output = std::string(str); |
---|
390 | uppercase(&output); |
---|
391 | return output; |
---|
392 | } |
---|
393 | |
---|
394 | /** |
---|
395 | @brief Compares two strings ignoring different casing. |
---|
396 | @param s1 First string |
---|
397 | @param s2 Second string |
---|
398 | */ |
---|
399 | int nocaseCmp(const std::string& s1, const std::string& s2) |
---|
400 | { |
---|
401 | std::string::const_iterator it1=s1.begin(); |
---|
402 | std::string::const_iterator it2=s2.begin(); |
---|
403 | |
---|
404 | //stop when either string's end has been reached |
---|
405 | while ( (it1!=s1.end()) && (it2!=s2.end()) ) |
---|
406 | { |
---|
407 | if(::toupper(*it1) != ::toupper(*it2)) //letters differ? |
---|
408 | // return -1 to indicate smaller than, 1 otherwise |
---|
409 | return (::toupper(*it1) < ::toupper(*it2)) ? -1 : 1; |
---|
410 | //proceed to the next character in each string |
---|
411 | ++it1; |
---|
412 | ++it2; |
---|
413 | } |
---|
414 | size_t size1=s1.size(), size2=s2.size();// cache lengths |
---|
415 | //return -1,0 or 1 according to strings' lengths |
---|
416 | if (size1==size2) |
---|
417 | return 0; |
---|
418 | return (size1<size2) ? -1 : 1; |
---|
419 | } |
---|
420 | |
---|
421 | |
---|
422 | /** |
---|
423 | @brief Compares the first 'len' chars of two strings ignoring different casing. |
---|
424 | @param s1 First string |
---|
425 | @param s2 Second string |
---|
426 | @param len Maximal number of chars to compare |
---|
427 | */ |
---|
428 | int nocaseCmp(const std::string& s1, const std::string& s2, size_t len) |
---|
429 | { |
---|
430 | if (len == 0) |
---|
431 | return 0; |
---|
432 | std::string::const_iterator it1=s1.begin(); |
---|
433 | std::string::const_iterator it2=s2.begin(); |
---|
434 | |
---|
435 | //stop when either string's end has been reached |
---|
436 | while ( (it1!=s1.end()) && (it2!=s2.end()) && len-- > 0) |
---|
437 | { |
---|
438 | if(::toupper(*it1) != ::toupper(*it2)) //letters differ? |
---|
439 | // return -1 to indicate smaller than, 1 otherwise |
---|
440 | return (::toupper(*it1) < ::toupper(*it2)) ? -1 : 1; |
---|
441 | //proceed to the next character in each string |
---|
442 | ++it1; |
---|
443 | ++it2; |
---|
444 | } |
---|
445 | return 0; |
---|
446 | } |
---|
447 | |
---|
448 | /** |
---|
449 | @brief Returns true if the string contains a comment, introduced by #, %, ; or //. |
---|
450 | @param str The string |
---|
451 | @return True if the string contains a comment |
---|
452 | */ |
---|
453 | bool hasComment(const std::string& str) |
---|
454 | { |
---|
455 | return (getCommentPosition(str) != std::string::npos); |
---|
456 | } |
---|
457 | |
---|
458 | /** |
---|
459 | @brief If the string contains a comment, the comment gets returned (including the comment symbol), an empty string otherwise. |
---|
460 | @param str The string |
---|
461 | @return The comment |
---|
462 | */ |
---|
463 | std::string getComment(const std::string& str) |
---|
464 | { |
---|
465 | return str.substr(getCommentPosition(str)); |
---|
466 | } |
---|
467 | |
---|
468 | /** |
---|
469 | @brief If the string contains a comment, the position of the comment-symbol gets returned, std::string::npos otherwise. |
---|
470 | @param str The string |
---|
471 | @return The position |
---|
472 | */ |
---|
473 | size_t getCommentPosition(const std::string& str) |
---|
474 | { |
---|
475 | return getNextCommentPosition(str, 0); |
---|
476 | } |
---|
477 | |
---|
478 | /** |
---|
479 | @brief Returns the position of the next comment-symbol, starting with start. |
---|
480 | @param str The string |
---|
481 | @param start The startposition |
---|
482 | @return The position |
---|
483 | */ |
---|
484 | size_t getNextCommentPosition(const std::string& str, size_t start) |
---|
485 | { |
---|
486 | for (size_t i = start; i < str.size(); i++) |
---|
487 | if (isComment(str.substr(i))) |
---|
488 | return i; |
---|
489 | |
---|
490 | return std::string::npos; |
---|
491 | } |
---|
492 | |
---|
493 | /** |
---|
494 | @brief Replaces individual charaters |
---|
495 | @param str String to be manipulated |
---|
496 | @param target Character to be replaced |
---|
497 | @param replacement Replacement character |
---|
498 | @return Number of replacements |
---|
499 | */ |
---|
500 | _UtilExport size_t replaceCharacters(std::string& str, char target, char replacement) |
---|
501 | { |
---|
502 | size_t j = 0; |
---|
503 | for (size_t i = 0; i < str.size(); ++i) |
---|
504 | { |
---|
505 | if (str[i] == target) |
---|
506 | { |
---|
507 | str[i] = replacement; |
---|
508 | ++j; |
---|
509 | } |
---|
510 | } |
---|
511 | return j; |
---|
512 | } |
---|
513 | } |
---|