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 <algorithm> |
---|
37 | #include <cctype> |
---|
38 | #include <ctime> |
---|
39 | #include <memory> |
---|
40 | #include "Convert.h" |
---|
41 | #include "Math.h" |
---|
42 | |
---|
43 | namespace orxonox |
---|
44 | { |
---|
45 | /// A blank string (""). Used to return a blank string by reference. |
---|
46 | std::string BLANKSTRING; |
---|
47 | |
---|
48 | /// Returns a string of a unique number. This function is guaranteed to never return the same string twice. |
---|
49 | std::string getUniqueNumberString() |
---|
50 | { |
---|
51 | return multi_cast<std::string>(getUniqueNumber()); |
---|
52 | } |
---|
53 | |
---|
54 | /// Removes all whitespaces from a string. |
---|
55 | void strip(std::string* str) |
---|
56 | { |
---|
57 | str->erase(std::remove_if(str->begin(), str->end(), [](char val) { return std::isspace(val) != 0; }), str->end()); |
---|
58 | } |
---|
59 | |
---|
60 | /// Returns a copy of a string without whitespaces. |
---|
61 | std::string getStripped(const std::string& str) |
---|
62 | { |
---|
63 | std::string output(str); |
---|
64 | strip(&output); |
---|
65 | return output; |
---|
66 | } |
---|
67 | |
---|
68 | /// Returns a copy of a string without trailing whitespaces. |
---|
69 | std::string removeTrailingWhitespaces(const std::string& str) |
---|
70 | { |
---|
71 | auto pos1 = std::find_if(str.begin(), str.end(), [](char val) { return std::isspace(val) == 0; }); |
---|
72 | auto pos2 = std::find_if(str.rbegin(), str.rend(), [](char val) { return std::isspace(val) == 0; }); |
---|
73 | if (pos1 == str.end() && pos2 == str.rend()) |
---|
74 | { |
---|
75 | // String doesn't have non-whitespace characters |
---|
76 | return ""; |
---|
77 | } |
---|
78 | return std::string(pos1, pos2.base()); |
---|
79 | } |
---|
80 | |
---|
81 | /// Splits a given string by a delimiter and stores it in an output vector. See @ref SubString for a more sophisticated implementation. |
---|
82 | void vectorize(const std::string& str, char delimiter, std::vector<std::string>* output) |
---|
83 | { |
---|
84 | output->clear(); |
---|
85 | for (size_t start = 0, end = 0; end != std::string::npos; start = end + 1) |
---|
86 | { |
---|
87 | end = str.find_first_of(delimiter, start); |
---|
88 | output->push_back(str.substr(start, end - start)); |
---|
89 | } |
---|
90 | } |
---|
91 | |
---|
92 | /** |
---|
93 | @brief Returns the position of the next quotation mark in the string, starting with start. Escaped quotation marks (with \ in front) are not considered. |
---|
94 | @param str The string |
---|
95 | @param start The first position to look at |
---|
96 | @return The position of the next quotation mark (@c std::string::npos if there is none) |
---|
97 | */ |
---|
98 | size_t getNextQuote(const std::string& str, size_t start) |
---|
99 | { |
---|
100 | size_t quote = start - 1; |
---|
101 | |
---|
102 | while ((quote = str.find('"', quote + 1)) != std::string::npos) |
---|
103 | { |
---|
104 | size_t backslash = quote; |
---|
105 | size_t numbackslashes = 0; |
---|
106 | for (; backslash > 0; backslash--, numbackslashes++) |
---|
107 | if (str[backslash - 1] != '\\') |
---|
108 | break; |
---|
109 | |
---|
110 | if (numbackslashes % 2 == 0) |
---|
111 | break; |
---|
112 | } |
---|
113 | |
---|
114 | return quote; |
---|
115 | } |
---|
116 | |
---|
117 | /** |
---|
118 | @brief Returns true if pos is between two quotation marks. |
---|
119 | @param str The string |
---|
120 | @param pos The position to check |
---|
121 | @return True if pos is between two quotation marks |
---|
122 | */ |
---|
123 | bool isBetweenQuotes(const std::string& str, size_t pos) |
---|
124 | { |
---|
125 | if (pos == std::string::npos) |
---|
126 | return false; |
---|
127 | |
---|
128 | size_t quotecount = 0; |
---|
129 | size_t quote = static_cast<size_t>(-1); |
---|
130 | while ((quote = getNextQuote(str, quote + 1)) < pos) |
---|
131 | quotecount++; |
---|
132 | |
---|
133 | if (quote == pos) |
---|
134 | return false; |
---|
135 | if (quote == std::string::npos) |
---|
136 | return false; |
---|
137 | |
---|
138 | return ((quotecount % 2) == 1); |
---|
139 | } |
---|
140 | |
---|
141 | /// Returns true if the string contains something like '..."between quotaton marks"...'. |
---|
142 | bool hasStringBetweenQuotes(const std::string& str) |
---|
143 | { |
---|
144 | size_t pos1 = getNextQuote(str, 0); |
---|
145 | size_t pos2 = getNextQuote(str, pos1 + 1); |
---|
146 | return (pos1 != std::string::npos && pos2 != std::string::npos && pos2 > pos1 + 1); |
---|
147 | } |
---|
148 | |
---|
149 | /// If the string contains something like '..."between quotaton marks"...' then 'between quotaton marks' gets returned, otherwise "". |
---|
150 | std::string getStringBetweenQuotes(const std::string& str) |
---|
151 | { |
---|
152 | size_t pos1 = getNextQuote(str, 0); |
---|
153 | size_t pos2 = getNextQuote(str, pos1 + 1); |
---|
154 | if (pos1 != std::string::npos && pos2 != std::string::npos) |
---|
155 | return str.substr(pos1 + 1, pos2 - pos1 - 1); |
---|
156 | else |
---|
157 | return ""; |
---|
158 | } |
---|
159 | |
---|
160 | /** |
---|
161 | @brief Removes enclosing quotation marks if available (including whitespaces at the outside of the quotation marks). |
---|
162 | @return The stripped string without quotation marks |
---|
163 | */ |
---|
164 | std::string stripEnclosingQuotes(const std::string& str) |
---|
165 | { |
---|
166 | auto start = str.begin(); |
---|
167 | auto end = str.rbegin(); |
---|
168 | |
---|
169 | for (; start != str.end() && *start != '"'; ++start) |
---|
170 | { |
---|
171 | if (std::isspace(*start) == 0) |
---|
172 | return str; |
---|
173 | } |
---|
174 | |
---|
175 | for (; end != str.rend() && *end != '"'; ++end) |
---|
176 | { |
---|
177 | if (std::isspace(*end) == 0) |
---|
178 | return str; |
---|
179 | } |
---|
180 | |
---|
181 | if (start != str.end() && end != str.rend()) |
---|
182 | { |
---|
183 | ++start; // Skip " |
---|
184 | ++end; // Skip " |
---|
185 | return std::string(start, end.base()); |
---|
186 | } |
---|
187 | else |
---|
188 | return str; |
---|
189 | } |
---|
190 | |
---|
191 | /** |
---|
192 | @brief Removes enclosing braces '{' and '}' (the braces must be exactly on the beginning and the end of the string). |
---|
193 | @return The stripped string without braces |
---|
194 | */ |
---|
195 | std::string stripEnclosingBraces(const std::string& str) |
---|
196 | { |
---|
197 | if (str.empty()) |
---|
198 | { |
---|
199 | return ""; |
---|
200 | } |
---|
201 | |
---|
202 | auto start = str.begin(); |
---|
203 | auto end = str.rbegin(); |
---|
204 | |
---|
205 | while (*start == '{' && *end == '}') |
---|
206 | { |
---|
207 | ++start; |
---|
208 | ++end; |
---|
209 | } |
---|
210 | |
---|
211 | return std::string(start, end.base()); |
---|
212 | } |
---|
213 | |
---|
214 | /** |
---|
215 | @brief Determines if a string is a comment (starts with a comment-symbol). |
---|
216 | |
---|
217 | A comment is defined by a leading '#', '%', ';' or '//'. |
---|
218 | */ |
---|
219 | bool isComment(const std::string& str) |
---|
220 | { |
---|
221 | // Strip the line, whitespaces are disturbing |
---|
222 | const std::string& teststring = getStripped(str); |
---|
223 | |
---|
224 | // There are four possible comment-symbols: |
---|
225 | // 1) #comment in script-language style |
---|
226 | // 2) %comment in matlab style |
---|
227 | // 3) ;comment in unreal tournament config-file style |
---|
228 | // 4) //comment in code style |
---|
229 | if (teststring.size() >= 2) |
---|
230 | { |
---|
231 | if (teststring[0] == '#' || teststring[0] == '%' || teststring[0] == ';' || (teststring[0] == '/' && teststring[1] == '/')) |
---|
232 | return true; |
---|
233 | } |
---|
234 | else if (teststring.size() == 1) |
---|
235 | { |
---|
236 | if (teststring[0] == '#' || teststring[0] == '%' || teststring[0] == ';') |
---|
237 | return true; |
---|
238 | } |
---|
239 | |
---|
240 | return false; |
---|
241 | } |
---|
242 | |
---|
243 | /// Determines if a string is empty (contains only whitespaces). |
---|
244 | bool isEmpty(const std::string& str) |
---|
245 | { |
---|
246 | return std::all_of(str.begin(), str.end(), [](char val) { return std::isspace(val) != 0; }); |
---|
247 | } |
---|
248 | |
---|
249 | /** |
---|
250 | @brief Adds backslashes to the given string which makes special chars visible. Existing slashes will be doubled. |
---|
251 | |
---|
252 | This function converts all special chars like line breaks, tabs, quotation marks etc. into |
---|
253 | a human readable format by adding a backslash. So for example "\n" will be converted to |
---|
254 | "\\" + "n". |
---|
255 | |
---|
256 | This is usually used when a string is written to a file. |
---|
257 | |
---|
258 | @see removeSlashes |
---|
259 | */ |
---|
260 | std::string addSlashes(const std::string& str) |
---|
261 | { |
---|
262 | std::string output(str.size() * 2, ' '); |
---|
263 | size_t i = 0; |
---|
264 | for (const char& character : str) |
---|
265 | { |
---|
266 | switch (character) |
---|
267 | { |
---|
268 | case '\\': output[i] = '\\'; output[i + 1] = '\\'; break; |
---|
269 | case '\n': output[i] = '\\'; output[i + 1] = 'n'; break; |
---|
270 | case '\t': output[i] = '\\'; output[i + 1] = 't'; break; |
---|
271 | case '\v': output[i] = '\\'; output[i + 1] = 'v'; break; |
---|
272 | case '\b': output[i] = '\\'; output[i + 1] = 'b'; break; |
---|
273 | case '\r': output[i] = '\\'; output[i + 1] = 'r'; break; |
---|
274 | case '\f': output[i] = '\\'; output[i + 1] = 'f'; break; |
---|
275 | case '\a': output[i] = '\\'; output[i + 1] = 'a'; break; |
---|
276 | case '"': output[i] = '\\'; output[i + 1] = '"'; break; |
---|
277 | case '\0': output[i] = '\\'; output[i + 1] = '0'; break; |
---|
278 | default : output[i] = character; ++i; continue; |
---|
279 | } |
---|
280 | i += 2; |
---|
281 | } |
---|
282 | output.resize(i); |
---|
283 | |
---|
284 | return output; |
---|
285 | } |
---|
286 | |
---|
287 | /** |
---|
288 | @brief Removes backslashes from the given string. Double backslashes are interpreted as one backslash. |
---|
289 | |
---|
290 | This function removes all backslashes and converts the human readable equivalents of |
---|
291 | special chars like "\\" + "n" into their real meaning (in this case a line break or "\n"). |
---|
292 | |
---|
293 | This is usually used when reading a string from a file. |
---|
294 | |
---|
295 | @see addSlashes |
---|
296 | */ |
---|
297 | std::string removeSlashes(const std::string& str) |
---|
298 | { |
---|
299 | if (str.size() <= 1) |
---|
300 | return str; |
---|
301 | |
---|
302 | std::string output(str.size(), ' '); |
---|
303 | size_t i = 0; |
---|
304 | size_t pos = 0; |
---|
305 | while (pos < str.size() - 1) |
---|
306 | { |
---|
307 | if (str[pos] == '\\') |
---|
308 | { |
---|
309 | switch (str[pos + 1]) |
---|
310 | { |
---|
311 | case '\\': output[i] = '\\'; break; |
---|
312 | case 'n': output[i] = '\n'; break; |
---|
313 | case 't': output[i] = '\t'; break; |
---|
314 | case 'v': output[i] = '\v'; break; |
---|
315 | case 'b': output[i] = '\b'; break; |
---|
316 | case 'r': output[i] = '\r'; break; |
---|
317 | case 'f': output[i] = '\f'; break; |
---|
318 | case 'a': output[i] = '\a'; break; |
---|
319 | case '"': output[i] = '"'; break; |
---|
320 | case '0': output[i] = '\0'; break; |
---|
321 | default: ++pos; continue; |
---|
322 | } |
---|
323 | pos += 2; ++i; |
---|
324 | } |
---|
325 | else |
---|
326 | output[i++] = str[pos++]; |
---|
327 | } |
---|
328 | if (pos < str.size()) |
---|
329 | output[i++] = str[pos]; |
---|
330 | output.resize(i); |
---|
331 | |
---|
332 | return output; |
---|
333 | } |
---|
334 | |
---|
335 | /// Replaces each char between A and Z with its lowercase equivalent. |
---|
336 | void lowercase(std::string* str) |
---|
337 | { |
---|
338 | std::transform(str->begin(), str->end(), str->begin(), [](char val) { return std::tolower(val); }); |
---|
339 | } |
---|
340 | |
---|
341 | /// Returns a copy of the given string where all chars are converted to lowercase. |
---|
342 | std::string getLowercase(const std::string& str) |
---|
343 | { |
---|
344 | std::string output(str); |
---|
345 | lowercase(&output); |
---|
346 | return output; |
---|
347 | } |
---|
348 | |
---|
349 | /// Replaces each char between a and z with its uppercase equivalent. |
---|
350 | void uppercase(std::string* str) |
---|
351 | { |
---|
352 | std::transform(str->begin(), str->end(), str->begin(), [](char val) { return std::toupper(val); }); |
---|
353 | } |
---|
354 | |
---|
355 | /// Returns a copy of the given string where all chars are converted to uppercase. |
---|
356 | std::string getUppercase(const std::string& str) |
---|
357 | { |
---|
358 | std::string output(str); |
---|
359 | uppercase(&output); |
---|
360 | return output; |
---|
361 | } |
---|
362 | |
---|
363 | /** |
---|
364 | @brief Compares two strings ignoring different casing. |
---|
365 | @return s1 == s2 -> returns 0 / s1 < s2 -> returns -1 / s1 >= s2 -> returns 1 |
---|
366 | */ |
---|
367 | int nocaseCmp(const std::string& s1, const std::string& s2) |
---|
368 | { |
---|
369 | size_t size1 = s1.size(), size2 = s2.size(); // cache lengths |
---|
370 | |
---|
371 | int res = nocaseCmp(s1, s2, std::min(size1, size2)); |
---|
372 | |
---|
373 | if (res != 0) |
---|
374 | { |
---|
375 | return res; |
---|
376 | } |
---|
377 | |
---|
378 | //return -1,0 or 1 according to strings' lengths |
---|
379 | if (size1 == size2) |
---|
380 | return 0; |
---|
381 | return (size1 < size2) ? -1 : 1; |
---|
382 | |
---|
383 | } |
---|
384 | |
---|
385 | |
---|
386 | /** |
---|
387 | @brief Compares the first @a len chars of two strings ignoring different casing. |
---|
388 | @param s1 First string |
---|
389 | @param s2 Second string |
---|
390 | @param len Maximal number of chars to compare |
---|
391 | */ |
---|
392 | int nocaseCmp(const std::string& s1, const std::string& s2, size_t len) |
---|
393 | { |
---|
394 | if (len == 0) |
---|
395 | return 0; |
---|
396 | std::string::const_iterator it1 = s1.begin(); |
---|
397 | std::string::const_iterator it2 = s2.begin(); |
---|
398 | |
---|
399 | //stop when either string's end has been reached |
---|
400 | while ( (it1 != s1.end()) && (it2 != s2.end()) && len-- > 0) |
---|
401 | { |
---|
402 | if(std::toupper(*it1) != std::toupper(*it2)) //letters differ? |
---|
403 | // return -1 to indicate smaller than, 1 otherwise |
---|
404 | return (std::toupper(*it1) < std::toupper(*it2)) ? -1 : 1; |
---|
405 | //proceed to the next character in each string |
---|
406 | ++it1; |
---|
407 | ++it2; |
---|
408 | } |
---|
409 | return 0; |
---|
410 | } |
---|
411 | |
---|
412 | /// Returns true if the string contains a comment, introduced by #, %, ; or //. |
---|
413 | bool hasComment(const std::string& str) |
---|
414 | { |
---|
415 | return (getNextCommentPosition(str) != std::string::npos); |
---|
416 | } |
---|
417 | |
---|
418 | /// If the string contains a comment, the comment gets returned (including the comment symbol and white spaces in front of it), an empty string otherwise. |
---|
419 | std::string getComment(const std::string& str) |
---|
420 | { |
---|
421 | size_t pos = getNextCommentPosition(str); |
---|
422 | if (pos == std::string::npos) |
---|
423 | return ""; |
---|
424 | else |
---|
425 | return str.substr(pos); |
---|
426 | } |
---|
427 | |
---|
428 | /** |
---|
429 | @brief Returns the beginning of the next comment including whitespaces in front of the comment symbol. |
---|
430 | @param str The string |
---|
431 | @param start The first position to look at |
---|
432 | */ |
---|
433 | size_t getNextCommentPosition(const std::string& str, size_t start) |
---|
434 | { |
---|
435 | for (size_t i = start; i < str.size(); i++) |
---|
436 | if (isComment(str.substr(i))) |
---|
437 | return i; |
---|
438 | |
---|
439 | return std::string::npos; |
---|
440 | } |
---|
441 | |
---|
442 | /** |
---|
443 | @brief Replaces individual charaters |
---|
444 | @param str String to be manipulated |
---|
445 | @param target Character to be replaced |
---|
446 | @param replacement Replacement character |
---|
447 | @return Number of replacements |
---|
448 | */ |
---|
449 | size_t replaceCharacters(std::string& str, char target, char replacement) |
---|
450 | { |
---|
451 | size_t j = 0; |
---|
452 | for (char& character : str) |
---|
453 | { |
---|
454 | if (character == target) |
---|
455 | { |
---|
456 | character = replacement; |
---|
457 | ++j; |
---|
458 | } |
---|
459 | } |
---|
460 | return j; |
---|
461 | } |
---|
462 | |
---|
463 | /** |
---|
464 | @brief Calculates the Levenshtein distance between two strings. |
---|
465 | |
---|
466 | The Levenshtein distance is defined by the number of transformations needed to convert str1 |
---|
467 | into str2. Possible transformations are substituted, added, or removed characters. |
---|
468 | */ |
---|
469 | unsigned int getLevenshteinDistance(const std::string& str1, const std::string& str2) |
---|
470 | { |
---|
471 | size_t cols = str1.size() + 1; |
---|
472 | size_t rows = str2.size() + 1; |
---|
473 | const std::unique_ptr<int[]> matrix(new int[rows * cols]); |
---|
474 | |
---|
475 | for (size_t r = 0; r < rows; ++r) |
---|
476 | for (size_t c = 0; c < cols; ++c) |
---|
477 | matrix[r*cols + c] = 0; |
---|
478 | |
---|
479 | for (size_t i = 1; i < cols; ++i) |
---|
480 | matrix[0*cols + i] = i; |
---|
481 | for (size_t i = 1; i < rows; ++i) |
---|
482 | matrix[i*cols + 0] = i; |
---|
483 | |
---|
484 | for (size_t r = 1; r < rows; ++r) |
---|
485 | for (size_t c = 1; c < cols; ++c) |
---|
486 | matrix[r*cols + c] = (str1[c-1] != str2[r-1]); |
---|
487 | |
---|
488 | for (size_t r = 1; r < rows; ++r) |
---|
489 | for (size_t c = 1; c < cols; ++c) |
---|
490 | matrix[r*cols + c] = std::min(std::min(matrix[(r-1)*cols + c] + 1, |
---|
491 | matrix[r*cols + c-1] + 1), |
---|
492 | matrix[(r-1)*cols + c-1] + (str1[c-1] != str2[r-1])); |
---|
493 | |
---|
494 | return matrix[(rows-1)*cols + cols-1]; |
---|
495 | } |
---|
496 | |
---|
497 | /** |
---|
498 | @brief |
---|
499 | Get a timestamp for the current time instant. |
---|
500 | @return |
---|
501 | Returns a string with the timestamp. |
---|
502 | */ |
---|
503 | std::string getTimestamp(void) |
---|
504 | { |
---|
505 | time_t ctTime; std::time(&ctTime); |
---|
506 | tm* pTime = std::localtime(&ctTime); |
---|
507 | std::ostringstream oss; |
---|
508 | // oss << std::put_time(pTime, "%m%d%Y_%H%M%S"); // <-- std::put_time is only available in GCC 5+ |
---|
509 | oss << std::setw(2) << std::setfill('0') << (pTime->tm_mon + 1) |
---|
510 | << std::setw(2) << std::setfill('0') << pTime->tm_mday |
---|
511 | << std::setw(2) << std::setfill('0') << (pTime->tm_year + 1900) |
---|
512 | << "_" << std::setw(2) << std::setfill('0') << pTime->tm_hour |
---|
513 | << std::setw(2) << std::setfill('0') << pTime->tm_min |
---|
514 | << std::setw(2) << std::setfill('0') << pTime->tm_sec; |
---|
515 | return oss.str(); |
---|
516 | } |
---|
517 | } |
---|