| 1 |
/* BaitFisher (version 1.2.7) a program for designing DNA target enrichment baits |
| 2 |
* Copyright 2013-2016 by Christoph Mayer |
| 3 |
* |
| 4 |
* This source file is part of the BaitFisher-package. |
| 5 |
* |
| 6 |
* This program is free software: you can redistribute it and/or modify |
| 7 |
* it under the terms of the GNU General Public License as published by |
| 8 |
* the Free Software Foundation, either version 3 of the License, or |
| 9 |
* (at your option) any later version. |
| 10 |
* |
| 11 |
* This program is distributed in the hope that it will be useful, |
| 12 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 13 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 14 |
* GNU General Public License for more details. |
| 15 |
* |
| 16 |
* You should have received a copy of the GNU General Public License |
| 17 |
* along with BaitFisher. If not, see <http://www.gnu.org/licenses/>. |
| 18 |
* |
| 19 |
* |
| 20 |
* For any enquiries send an Email to Christoph Mayer |
| 21 |
* [email protected] |
| 22 |
* |
| 23 |
* When publishing work that is based on the results please cite: |
| 24 |
* Mayer et al. 2016: BaitFisher: A software package for multi-species target DNA enrichment probe design |
| 25 |
* |
| 26 |
*/ |
| 27 |
|
| 28 |
#ifndef EASYSTRING_H |
| 29 |
#define EASYSTRING_H |
| 30 |
|
| 31 |
#include <iostream> |
| 32 |
#include <string> |
| 33 |
#include <cstring> // for strchr |
| 34 |
#include <cstdlib> |
| 35 |
#include <fstream> |
| 36 |
|
| 37 |
// A usefull global function split: |
| 38 |
//(Code copied from the stringtok.h file on the gnu libstdc++ page. |
| 39 |
|
| 40 |
|
| 41 |
|
| 42 |
namespace { |
| 43 |
inline bool |
| 44 |
isws(char c, const char* wstr="\r\n\t\v\f ") |
| 45 |
{ |
| 46 |
return (strchr(wstr,c) != NULL); |
| 47 |
} |
| 48 |
} |
| 49 |
|
| 50 |
namespace { |
| 51 |
// |
| 52 |
// Reads through a string. If braces are encountered we do not tokenize inside but try to read them. |
| 53 |
// |
| 54 |
inline void |
| 55 |
skip_until_ws_respect(const std::string &s, std::string::size_type &pos, char const * const ws = "\r\n\t\v\f ") |
| 56 |
{ |
| 57 |
char c; |
| 58 |
|
| 59 |
unsigned count_parent = 0; |
| 60 |
unsigned count_brace = 0; |
| 61 |
unsigned count_curly = 0; |
| 62 |
unsigned count_sq = 0; |
| 63 |
unsigned count_dq = 0; |
| 64 |
|
| 65 |
std::string::size_type size = s.size(); |
| 66 |
|
| 67 |
while (pos < size) |
| 68 |
{ |
| 69 |
c = s[pos]; |
| 70 |
if (c == '(') { ++count_parent; } |
| 71 |
else if (c == ')') { --count_parent; } |
| 72 |
else if (c == '[') { ++count_brace; } |
| 73 |
else if (c == ']') { --count_brace; } |
| 74 |
else if (c == '{') { ++count_curly; } |
| 75 |
else if (c == '}') { --count_curly; } |
| 76 |
else if (c == '\'') { count_sq = (count_sq+1)%2; } |
| 77 |
else if (c == '\"') { count_dq = (count_dq+1)%2; } |
| 78 |
|
| 79 |
if (isws(c, ws) && count_parent==0 && count_brace==0 && count_curly==0 && count_sq==0 && count_dq==0) |
| 80 |
return; |
| 81 |
|
| 82 |
++pos; |
| 83 |
} |
| 84 |
} |
| 85 |
} |
| 86 |
|
| 87 |
namespace std |
| 88 |
{ |
| 89 |
|
| 90 |
/***************************************************************** |
| 91 |
* Simplistic and quite Standard, but a bit slow. This should be |
| 92 |
* templatized on basic_string instead, or on a more generic StringT |
| 93 |
* that just happens to support ::size_type, .substr(), and so on. |
| 94 |
* I had hoped that "whitespace" would be a trait, but it isn't, so |
| 95 |
* the user must supply it. Enh, this lets them break up strings on |
| 96 |
* different things easier than traits would anyhow. |
| 97 |
*/ |
| 98 |
template <typename Container> |
| 99 |
int |
| 100 |
split (Container &l, string const &s, char const * const ws = "\r\n\t\v\f ") |
| 101 |
{ |
| 102 |
l.clear(); |
| 103 |
const string::size_type S = s.size(); |
| 104 |
string::size_type i = 0; |
| 105 |
|
| 106 |
while (i < S) { |
| 107 |
// eat leading whitespace |
| 108 |
while ((i < S) && (isws(s[i],ws))) ++i; |
| 109 |
if (i == S) return l.size(); // nothing left but WS |
| 110 |
|
| 111 |
// find end of word |
| 112 |
string::size_type j = i+1; |
| 113 |
while ((j < S) && (!isws(s[j],ws))) ++j; |
| 114 |
|
| 115 |
// add word |
| 116 |
l.push_back(s.substr(i,j-i)); |
| 117 |
|
| 118 |
// set up for next loop |
| 119 |
i = j+1; |
| 120 |
} |
| 121 |
return l.size(); |
| 122 |
} |
| 123 |
|
| 124 |
// |
| 125 |
// Tokenizer which does not split braces. |
| 126 |
// |
| 127 |
template <typename Container> |
| 128 |
int |
| 129 |
split_respect (Container &l, string const &s, char const * const ws = "\r\n\t\v\f ") |
| 130 |
{ |
| 131 |
l.clear(); |
| 132 |
const string::size_type S = s.size(); |
| 133 |
string::size_type i = 0; |
| 134 |
|
| 135 |
while (i < S) { |
| 136 |
// eat leading whitespace |
| 137 |
while ((i < S) && (isws(s[i],ws))) ++i; |
| 138 |
if (i == S) return l.size(); // nothing left but WS |
| 139 |
|
| 140 |
// find end of word |
| 141 |
string::size_type j = i; // We can't skip the first char which can be a brace. |
| 142 |
skip_until_ws_respect(s, j, ws); |
| 143 |
|
| 144 |
// add word |
| 145 |
l.push_back(s.substr(i,j-i)); |
| 146 |
|
| 147 |
// set up for next loop |
| 148 |
i = j+1; |
| 149 |
} |
| 150 |
return l.size(); |
| 151 |
} |
| 152 |
|
| 153 |
// Multiple successive deliminators result in multiple hits. |
| 154 |
template <typename Container> |
| 155 |
int |
| 156 |
split_strict (Container &l, string const &s, char const * const ws = " \t\n") |
| 157 |
{ |
| 158 |
l.clear(); |
| 159 |
const string::size_type S = s.size(); |
| 160 |
string::size_type i = 0; |
| 161 |
|
| 162 |
while (i < S) { |
| 163 |
// find end of word |
| 164 |
string::size_type j = i; |
| 165 |
while ((j < S) && (!isws(s[j],ws))) ++j; |
| 166 |
|
| 167 |
// add word |
| 168 |
l.push_back(s.substr(i,j-i)); |
| 169 |
|
| 170 |
// set up for next loop |
| 171 |
i = j+1; |
| 172 |
|
| 173 |
if (i==S) // Only true of last string is empty since otherwise i==S+1 |
| 174 |
{ |
| 175 |
l.push_back(""); |
| 176 |
} |
| 177 |
} |
| 178 |
return l.size(); |
| 179 |
} |
| 180 |
|
| 181 |
|
| 182 |
|
| 183 |
class easystring: public string |
| 184 |
{ |
| 185 |
public: |
| 186 |
// Default constructor: |
| 187 |
easystring():string(){}; |
| 188 |
|
| 189 |
// Copy constructor: |
| 190 |
easystring(const string& s):string(s){} |
| 191 |
easystring(const string& s, size_type pos, size_type n):string(s,pos,n){} |
| 192 |
|
| 193 |
// Other constructors: |
| 194 |
easystring(const char* s, size_type n):string(s,n){} |
| 195 |
easystring(size_type n, char c):string(n,c){} |
| 196 |
template <class InputIterator> |
| 197 |
easystring(InputIterator first, InputIterator last):string(first, last){} |
| 198 |
|
| 199 |
// Type conversion constructors: |
| 200 |
easystring(const char* s):string(s){} |
| 201 |
easystring(const char c):string(1,c){} |
| 202 |
easystring(const int i):string() |
| 203 |
{ |
| 204 |
// std::cout << "Hallo" << std::endl; |
| 205 |
char tmp[21]; // Sufficient for 64 bit numbers + sign |
| 206 |
sprintf(tmp, "%d", i); |
| 207 |
append(tmp); |
| 208 |
} |
| 209 |
easystring(const long i):string() |
| 210 |
{ |
| 211 |
// std::cout << "Hallo" << std::endl; |
| 212 |
char tmp[21]; // Sufficient for 64 bit numbers + sign |
| 213 |
sprintf(tmp, "%ld", i); |
| 214 |
append(tmp); |
| 215 |
} |
| 216 |
easystring(const unsigned i):string() |
| 217 |
{ |
| 218 |
// std::cout << "Hallo" << std::endl; |
| 219 |
char tmp[21]; // Sufficient for 64 bit numbers |
| 220 |
sprintf(tmp, "%u", i); |
| 221 |
append(tmp); |
| 222 |
} |
| 223 |
easystring(const unsigned long i):string() |
| 224 |
{ |
| 225 |
// std::cout << "Hallo" << std::endl; |
| 226 |
char tmp[21]; // Sufficient for 64 bit numbers |
| 227 |
sprintf(tmp, "%lu", i); |
| 228 |
append(tmp); |
| 229 |
} |
| 230 |
easystring(const double x, int pres):string() |
| 231 |
{ |
| 232 |
// std::cout << "Hallo" << std::endl; |
| 233 |
char tmp[25]; // Sufficient for 64 bit numbers |
| 234 |
sprintf(tmp, "%.*f", pres, x); |
| 235 |
append(tmp); |
| 236 |
} |
| 237 |
|
| 238 |
|
| 239 |
void removeSpacesFront(const char* delims="\r\n\t\v\f ") |
| 240 |
{ |
| 241 |
string::size_type i; |
| 242 |
const string::size_type n = size(); |
| 243 |
|
| 244 |
for (i=0; i < n && isws((*this)[i], delims); ++i); |
| 245 |
erase(0,i); |
| 246 |
} |
| 247 |
|
| 248 |
|
| 249 |
void removeSpacesBack(const char* delims="\r\n\t\v\f ") |
| 250 |
{ |
| 251 |
unsigned i; |
| 252 |
unsigned n = size(); |
| 253 |
|
| 254 |
if (n > 0) |
| 255 |
{ |
| 256 |
for (i=n-1; i != 0 && isws((*this)[i], delims); --i); |
| 257 |
|
| 258 |
if (i == 0 && isws((*this)[0], delims)) |
| 259 |
erase(); |
| 260 |
else |
| 261 |
erase(i+1); |
| 262 |
} |
| 263 |
} |
| 264 |
|
| 265 |
|
| 266 |
void ToUpper() |
| 267 |
{ |
| 268 |
iterator it, it_end; |
| 269 |
|
| 270 |
it = begin(); |
| 271 |
it_end = end(); |
| 272 |
|
| 273 |
while (it != it_end) |
| 274 |
{ |
| 275 |
*it = toupper(*it); |
| 276 |
++it; |
| 277 |
} |
| 278 |
} |
| 279 |
|
| 280 |
void ToLower() |
| 281 |
{ |
| 282 |
string::iterator it, it_end; |
| 283 |
|
| 284 |
it = begin(); |
| 285 |
it_end = end(); |
| 286 |
|
| 287 |
while (it != it_end) |
| 288 |
{ |
| 289 |
*it = tolower(*it); |
| 290 |
++it; |
| 291 |
} |
| 292 |
} |
| 293 |
|
| 294 |
// Convert to unsigned long |
| 295 |
unsigned ToUnsigned() const |
| 296 |
{ |
| 297 |
char *end; |
| 298 |
return strtoul(c_str(), &end, 0); |
| 299 |
} |
| 300 |
|
| 301 |
// Convert to unsigned long |
| 302 |
unsigned long ToUnsignedLong() const |
| 303 |
{ |
| 304 |
char *end; |
| 305 |
return strtoul(c_str(), &end, 0); |
| 306 |
} |
| 307 |
|
| 308 |
// Convert to int |
| 309 |
int ToInt() const |
| 310 |
{ |
| 311 |
char *end; |
| 312 |
return strtol(c_str(), &end, 0); |
| 313 |
|
| 314 |
} |
| 315 |
|
| 316 |
|
| 317 |
// Convert to long |
| 318 |
long ToLong() const |
| 319 |
{ |
| 320 |
char *end; |
| 321 |
return strtol(c_str(), &end, 0); |
| 322 |
} |
| 323 |
|
| 324 |
long ToLong(string::size_type beg_pos, |
| 325 |
string::size_type& end_pos) const |
| 326 |
{ |
| 327 |
const char *beg = c_str()+beg_pos; |
| 328 |
char *end; |
| 329 |
long result; |
| 330 |
|
| 331 |
result = strtol(beg, &end, 0); |
| 332 |
end_pos = end-c_str(); |
| 333 |
return result; |
| 334 |
} |
| 335 |
|
| 336 |
unsigned ToUnsigned(string::size_type beg_pos, |
| 337 |
string::size_type& end_pos) const |
| 338 |
{ |
| 339 |
const char *beg = c_str()+beg_pos; |
| 340 |
char *end; |
| 341 |
long result; |
| 342 |
|
| 343 |
result = strtoul(beg, &end, 0); |
| 344 |
end_pos = end-c_str(); |
| 345 |
return result; |
| 346 |
} |
| 347 |
|
| 348 |
|
| 349 |
// Convert to double |
| 350 |
double ToDouble() const |
| 351 |
{ |
| 352 |
char *end; |
| 353 |
return strtod(c_str(), &end); |
| 354 |
} |
| 355 |
|
| 356 |
double ToDouble(string::size_type beg_pos, |
| 357 |
string::size_type& end_pos) const |
| 358 |
{ |
| 359 |
const char *beg = c_str()+beg_pos; |
| 360 |
char *end; |
| 361 |
double result; |
| 362 |
|
| 363 |
result = strtod(beg, &end); |
| 364 |
end_pos = end-c_str(); |
| 365 |
return result; |
| 366 |
} |
| 367 |
|
| 368 |
// not tested |
| 369 |
unsigned countChar(char c) |
| 370 |
{ |
| 371 |
unsigned n = 0; |
| 372 |
string::iterator b = begin(); |
| 373 |
string::iterator e = end(); |
| 374 |
|
| 375 |
while (b<e) |
| 376 |
{ |
| 377 |
if (*b == c) |
| 378 |
++n; |
| 379 |
++b; |
| 380 |
} |
| 381 |
return n; |
| 382 |
} |
| 383 |
|
| 384 |
// not tested |
| 385 |
void unquote() |
| 386 |
{ |
| 387 |
removeSpacesBack(); |
| 388 |
removeSpacesFront(); |
| 389 |
if (*begin() == '"' && *(end()-1) == '"' ) |
| 390 |
{ |
| 391 |
this->erase(begin()); |
| 392 |
this->erase(end()-1); |
| 393 |
} |
| 394 |
else if (*begin() == '\'' && *(end()-1) == '\'' ) |
| 395 |
{ |
| 396 |
this->erase(begin()); |
| 397 |
this->erase(end()-1); |
| 398 |
} |
| 399 |
} |
| 400 |
|
| 401 |
// not tested |
| 402 |
void unquote(char s, char e) |
| 403 |
{ |
| 404 |
removeSpacesBack(); |
| 405 |
removeSpacesFront(); |
| 406 |
if (*begin() == s && *(end()-1) == e ) |
| 407 |
{ |
| 408 |
this->erase(begin()); |
| 409 |
this->erase(end()-1); |
| 410 |
} |
| 411 |
} |
| 412 |
|
| 413 |
// get the next token and remove it from the called object. |
| 414 |
easystring& get_next_token(easystring &str, const char * ws = "\r\n\t\v\f ") |
| 415 |
{ |
| 416 |
const string::size_type n = size(); |
| 417 |
string::size_type i = 0; |
| 418 |
|
| 419 |
str.clear(); |
| 420 |
|
| 421 |
// eat leading whitespace/deliminators -- this sould be more efficient than |
| 422 |
// calling removeSpacesFront since we only need to erase in the front of the string once. |
| 423 |
while ( (i < n) && ( isws( (*this)[i], ws)) ) ++i; |
| 424 |
|
| 425 |
if (i == n) // nothing left so re remove alle spaces and the string will be empty |
| 426 |
{ |
| 427 |
erase(); |
| 428 |
} |
| 429 |
else |
| 430 |
{ |
| 431 |
// find end of word |
| 432 |
string::size_type j = i+1; |
| 433 |
while ( (j < n) && (!isws( (*this)[j], ws)) ) ++j; |
| 434 |
|
| 435 |
str = string(*this, i, j); // the next token |
| 436 |
erase(0, j); // remove token from called object |
| 437 |
} |
| 438 |
|
| 439 |
return *this; |
| 440 |
} |
| 441 |
|
| 442 |
|
| 443 |
// xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx |
| 444 |
// Be careful with keywords containing punctuations since they do not |
| 445 |
// count as upper case chars. The upper case loop stops there. |
| 446 |
|
| 447 |
// Possible bug: I think "I" abbreviates "INPUT" which is not OK. |
| 448 |
|
| 449 |
// Use !isalpha() to as equivalent to "isupper() so we prolong the upper region. |
| 450 |
|
| 451 |
bool is_CAPITALIZED_abbreviation_of(const easystring &keyword) |
| 452 |
{ |
| 453 |
unsigned i = 0; |
| 454 |
unsigned max = size(); |
| 455 |
|
| 456 |
// max cannot be greater than keyword.size() |
| 457 |
if ( max > keyword.size() ) |
| 458 |
return false; |
| 459 |
|
| 460 |
// We start comparrison in upper case region. Lets see how far we can go. |
| 461 |
while (i < max && toupper( (*this)[i] ) == keyword[i] ) |
| 462 |
{ |
| 463 |
++i; |
| 464 |
} |
| 465 |
|
| 466 |
// First we check whether both strings have the same length and we matched all chars. |
| 467 |
// This means that we matched exactly the upper case region of keyword, which is the |
| 468 |
// complete keyword. |
| 469 |
if ( i == max && max == keyword.size() ) |
| 470 |
return true; |
| 471 |
|
| 472 |
// If we get here, i must be smaller than keyword.size() since we can only have |
| 473 |
// * i == max and i == keyword.size(): Not possible after previous if |
| 474 |
// * i < max and i == keyword.size(): Not possible since max <= keyword.size() |
| 475 |
// * i == max and i < keyword.size(): |
| 476 |
// * i < max and i < keyword.size(): |
| 477 |
|
| 478 |
// Thus, keyword[i] is valid and we use it to check whether we are in the upper case region |
| 479 |
// (were all !alpha() should also be considered as upper case chars in this context!!). |
| 480 |
// We simply check whether we are in the !islower() region. |
| 481 |
|
| 482 |
if ( !islower( keyword[i]) ) // We are still in non-lower case region |
| 483 |
return false; |
| 484 |
|
| 485 |
// If we get here, we are in the in the lower-case region |
| 486 |
// There are two possibilities: |
| 487 |
// - i == max, |
| 488 |
if (i==max) |
| 489 |
return true; |
| 490 |
// - our string is longer than the upper case region, so we have to continue |
| 491 |
// our comparison. |
| 492 |
|
| 493 |
// Let us move through lower case region |
| 494 |
while (i < max && ((*this)[i] == keyword[i] || tolower((*this)[i]) == keyword[i]) ) |
| 495 |
++i; |
| 496 |
|
| 497 |
// Could we match all letters in str? |
| 498 |
if (i==max) |
| 499 |
return true; |
| 500 |
else |
| 501 |
return false; |
| 502 |
} |
| 503 |
|
| 504 |
|
| 505 |
}; |
| 506 |
|
| 507 |
|
| 508 |
} |
| 509 |
|
| 510 |
|
| 511 |
#endif |