forked from HIT-SCIR/ltp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
strutils.hpp
490 lines (428 loc) · 11.9 KB
/
strutils.hpp
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
#ifndef __LTP_UTILS_STRUTILS_HPP__
#define __LTP_UTILS_STRUTILS_HPP__
#include <iostream>
#include <cstdio>
#include <cstdlib>
#include <sstream>
#include <vector>
#include <string>
#include <algorithm>
namespace ltp {
namespace strutils {
inline void trim(std::string& str) {
size_t len = str.size();
if (len == 0) { return; }
while (len >= 1 && (str[len-1] == ' '
|| str[len-1]=='\t'
|| str[len-1] == '\r'
|| str[len-1] == '\n')) {
-- len;
}
str = str.substr(0, len);
size_t i = 0;
while (i < len && (str[i] == ' ' ||
str[i] == '\t' ||
str[i] == '\r' ||
str[i] == '\n')) { i ++; }
str = str.substr(i);
}
/**
* chomp a string
*
* @param str std::string
* @return std::string
*/
inline std::string trim_copy(const std::string& source) {
std::string str(source);
trim(str);
return str;
}
/**
* Cut off the following string after mark
*
* @param str std::string the string
* @param mark std::string the cut out mark
* @return std::string the cut string
*/
inline std::string cutoff(std::string str, std::string mark) {
size_t pos = str.find(mark);
if (pos == std::string::npos) {
return str;
} else {
return str.substr(0, pos);
}
}
inline void split(const std::string& source, std::vector<std::string>& ret,
int maxsplit=-1) {
std::string str(source);
int numsplit = 0;
int len = str.size();
size_t pos;
for (pos = 0; pos < str.size() && (str[pos] == ' ' || str[pos] == '\t'
|| str[pos] == '\n' || str[pos] == '\r'); ++ pos);
str = str.substr(pos);
ret.clear();
while (str.size() > 0) {
pos = std::string::npos;
for (pos = 0; pos < str.size() && (str[pos] != ' '
&& str[pos] != '\t'
&& str[pos] != '\r'
&& str[pos] != '\n'); ++ pos);
if (pos == str.size()) {
pos = std::string::npos;
}
if (maxsplit >= 0 && numsplit < maxsplit) {
ret.push_back(str.substr(0, pos));
++ numsplit;
} else if (maxsplit >= 0 && numsplit == maxsplit) {
ret.push_back(str);
++ numsplit;
} else if (maxsplit == -1) {
ret.push_back(str.substr(0, pos));
++ numsplit;
}
if (pos == std::string::npos) {
str = "";
} else {
for (; pos < str.size() && (str[pos] == ' '
|| str[pos] == '\t'
|| str[pos] == '\n'
|| str[pos] == '\r'); ++ pos);
str = str.substr(pos);
}
}
}
/**
* Return a list of words of string str, the word are separated by
* separator.
*
* @param str std::string the string
* @param maxsplit std::string the sep upperbound
* @return std::vector<std::string> the words
*/
inline std::vector<std::string> split(const std::string& source, int maxsplit = -1) {
std::vector<std::string> ret;
split(source, ret, maxsplit);
return ret;
}
/**
* Return a list of words of string str, the word are separated by
* separator.
*
* @param str std::string the string
* @param sep std::string the separator
* @param maxsplit std::string the sep upperbound
* @return std::vector<std::string> the words
*/
inline std::vector<std::string> split_by_sep(std::string str,
std::string sep = "", int maxsplit = -1) {
std::vector<std::string> ret;
int numsplit = 0;
int len = str.size();
int sep_flag = (sep != "");
if (sep == "") {
return split(str, maxsplit);
}
while (str.size() > 0) {
size_t pos = std::string::npos;
pos = str.find(sep);
if (maxsplit >= 0 && numsplit < maxsplit) {
ret.push_back(str.substr(0, pos));
++ numsplit;
} else if (maxsplit >= 0 && numsplit == maxsplit) {
ret.push_back(str);
pos = std::string::npos;
++ numsplit;
} else if (maxsplit == -1) {
ret.push_back(str.substr(0, pos));
++ numsplit;
}
if (pos == std::string::npos) {
str = "";
} else {
pos = pos + sep.size();
str = str.substr(pos);
}
}
return ret;
}
/**
* Return a list of words of string str, the word are separated by
* separator.
*
* @param str std::string the string
* @param maxsplit std::string the sep upperbound
* @return std::vector<std::string> the words
*/
inline std::vector<std::string> rsplit(std::string str, int maxsplit = -1) {
std::vector<std::string> ret;
int numsplit = 0;
int len = -1;
while ((len = str.size()) > 0) {
// warning: should not use size_t, because it's unsigned integer
int pos = 0;
for (pos = len - 1; pos >= 0 && (str[pos] != ' '
&& str[pos] != '\t'
&& str[pos] != '\r'
&& str[pos] != '\n'); -- pos);
if (maxsplit >= 0 && numsplit < maxsplit) {
ret.push_back(str.substr(pos + 1));
++ numsplit;
} else if (maxsplit >= 0 && numsplit == maxsplit) {
ret.push_back(str);
pos = -1;
++ numsplit;
} else if (maxsplit == -1) {
ret.push_back(str.substr(pos + 1));
++ numsplit;
}
if (pos == -1) {
str = "";
} else {
for (; pos >= 0 && (str[pos] == ' '
|| str[pos] == '\t'
|| str[pos] == '\n'
|| str[pos] == '\r'); -- pos);
str = str.substr(0, pos + 1);
}
}
std::reverse(ret.begin(), ret.end());
return ret;
}
/**
* Return a list of words of string str, the word are separated by
* separator.
*
* @param str std::string the string
* @param sep std::string the separator
* @param maxsplit std::string the sep upperbound
* @return std::vector<std::string> the words
*/
inline std::vector<std::string> rsplit_by_sep(std::string str, std::string sep = "", int maxsplit = -1) {
std::vector<std::string> ret;
int numsplit = 0;
int len = str.size();
int sep_flag = (sep != "");
while (str.size() > 0) {
int pos = (int) std::string::npos;
if (sep_flag) {
pos = str.rfind(sep);
} else {
for (pos = str.size() - 1; pos >= 0; -- pos) {
if (str[pos] == ' '
|| str[pos] == '\t'
|| str[pos] == '\r'
|| str[pos] == '\n') {
break;
}
}
if (pos == -1) {
pos = 0;
// pos = std::string::npos;
}
}
if (maxsplit >= 0 && numsplit < maxsplit) {
ret.push_back(str.substr(pos + sep.length(), std::string::npos));
++ numsplit;
} else if (maxsplit >= 0 && numsplit == maxsplit) {
ret.push_back(str);
pos = 0;
++ numsplit;
} else if (maxsplit == -1) {
ret.push_back(str.substr(pos, std::string::npos));
++ numsplit;
}
if (pos == 0) {
str = "";
} else {
if (sep_flag) {
// pos = pos - sep.size();
} else {
for (; pos >= 0 && (str[pos] == ' '
|| str[pos] == '\t'
|| str[pos] == '\n'
|| str[pos] == '\r'); -- pos);
}
str = str.substr(0, pos);
}
}
std::reverse(ret.begin(), ret.end());
return ret;
}
/**
* Concatenate a list of words
*
* @param sep std::vector<std::string> the words
* @return std::string the concatenated string
*/
inline std::string join(const std::vector<std::string>& sep) {
std::string ret = "";
for (unsigned int i = 0; i < sep.size(); ++ i) {
// trick, append is faster than plus operator
ret.append(sep[i]);
}
return ret;
}
/**
* Concatenate a list of words invertening the sep
*
* @param sep std::vector<std::string> the words
* @param delimiter std::string the delimiter
* @return std::string the concatenated string
*/
inline std::string join(const std::vector<std::string>& sep,
const std::string& delimiter) {
if (sep.size() == 0) {
return "";
}
std::string ret = sep[0];
for (unsigned int i = 1; i < sep.size(); ++ i) {
ret.append(delimiter);
ret.append(sep[i]);
}
return ret;
}
/**
* Return True if string starts with the prefix, otherwise return False
*
* @param str const std::string& the string
* @param head const std::string& the prefix
* @return bool true if startswith prefix, otherwise false
*/
inline bool startswith(const std::string &str, const std::string &head) {
int len = head.size();
return (str.substr(0, len) == head);
}
/**
* Return True if string ends with the suffix, otherwise return False
*
* @param str const std::string& the string
* @param suffix const std::string& the suffix
* @return bool true if endswith suffix, otherwise false
*/
inline bool endswith(const std::string &str, const std::string &suffix) {
int len = suffix.length();
int len2 = str.length();
if (len2 < len) {
return false;
}
return (str.substr(len2 - len, len) == suffix);
}
/**
* Return True if string is integer
*
* @param str const std::string& the string
* @return bool true if the string is integer,
* otherwise false
*/
inline bool is_int(const std::string &str) {
unsigned int i = 0;
if (str[0] == '-')
i = 1;
for (; i < str.size(); ++ i) {
if (false == (str[i] >= '0' && str[i] <= '9')) {
return false;
}
}
return true;
}
/**
* Return True if string is double
*
* @param str const std::string& the string
* @return bool true if the string is double,
* otherwise false
*/
inline bool is_double(const std::string &str) {
unsigned int i = 0;
int state = 0;
if (str[0] == '-')
i = 1;
for (; i < str.size(); ++ i) {
if (str[i] == '.') {
++ state;
if (state > 1) return false;
} else if (false == (str[i] >= '0' && str[i] <= '9')) {
return false;
}
}
return true;
}
/**
* Convert a string to a plain integer
*
* @param str const std::string& the string
* @return int the integer.
*/
inline int to_int(const std::string &str) {
int ret = 0;
int sign = 1;
unsigned int i = 0;
if ('-' == str[0]) {
sign = -1;
i = 1;
}
for (; i < str.size(); ++ i) {
ret *= 10;
ret += str[i] - '0';
}
return sign * ret;
}
/**
* Convert a string to a double float
*
* @param str const std::string& the string
* @return double the double float.
*/
inline double to_double(const std::string &str) {
double x = 0.0, y = 1.0;
double sign = 1.0;
unsigned int i = 0;
if ('-' == str[0]) {
sign = -1.0;
i = 1;
}
for (; i < str.size() && str[i] != '.'; ++ i) {
x *= 10.0;
x += (str[i] - '0');
}
for (++ i; i < str.size(); ++ i) {
y /= 10.0;
x += (str[i] - '0') * y;
}
return x * sign;
}
inline std::string to_str(int x) {
char buff[14];
return std::string(buff, sprintf(buff, "%d", x));
}
// remove the leading space and ending \r\n\t
inline void clean(std::string &str) {
std::string blank = " \t\r\n";
size_t pos1 = str.find_first_not_of(blank);
size_t pos2 = str.find_last_not_of(blank);
if (pos1 == std::string::npos) {
str = "";
} else {
str = str.substr(pos1, pos2 - pos1 + 1);
}
}
inline size_t count(const std::string& str, const std::string& sub) {
if (sub.length() == 0) return 0;
size_t retval = 0;
for (size_t offset = str.find(sub); offset != std::string::npos;
offset = str.find(sub, offset + sub.length())) {
++ retval;
}
return retval;
}
/**
*
*
*
*
*/
//int char_type(const std::string &str);
} //LTP_STRING_NAMESPACE_END
} //LTP_NAMESPACE_END
#endif // end for __LTP_UTILS_STRUTILS_HPP__