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
|
/*
* Copyright (C) 2010-2012 Regents of the University of Michigan,
* Hyun Min Kang, Matthew Flickenger, Matthew Snyder,
* and Goncalo Abecasis
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include "VcfRecord.h"
VcfRecord::VcfRecord()
{
reset();
}
VcfRecord::~VcfRecord()
{
}
bool VcfRecord::read(IFILE filePtr, bool siteOnly,
VcfRecordDiscardRules& discardRules,
VcfSubsetSamples* sampleSubset)
{
// Clear out any previously set values.
reset();
if(filePtr == NULL)
{
myStatus.setStatus(StatGenStatus::FAIL_ORDER,
"Error reading VCF record before opening the file.");
return(false);
}
if(ifeof(filePtr))
{
// End of file, just return false.
return(false);
}
// Read the chromosome.
if(!readTilTab(filePtr, myChrom))
{
if(myChrom.empty())
{
// EOF.
return(false);
}
// Not an empty line.
myStatus.setStatus(StatGenStatus::FAIL_PARSE,
"Error reading VCF Record CHROM.");
return(false);
}
// Read the 1-based Position
std::string strPos;
if(!readTilTab(filePtr, strPos))
{
myStatus.setStatus(StatGenStatus::FAIL_PARSE,
"Error reading VCF Record POS.");
return(false);
}
else
{
// Read the position, so convert to an integer.
my1BasedPosNum = atoi(strPos.c_str());
}
// Read the ID.
if(!readTilTab(filePtr, myID))
{
myStatus.setStatus(StatGenStatus::FAIL_PARSE,
"Error reading VCF Record ID.");
return(false);
}
if(discardRules.discardForID(myID))
{
// Do not keep this id, so consume the rest of the record and
// return the next record.
filePtr->discardLine();
return(read(filePtr, siteOnly, discardRules, sampleSubset));
}
// Read the Ref.
if(!readTilTab(filePtr, myRef))
{
myStatus.setStatus(StatGenStatus::FAIL_PARSE,
"Error reading VCF Record REF.");
return(false);
}
// Read the Alt.
myAltArray.clear();
if(!readTilTab(filePtr, myAlt))
{
myStatus.setStatus(StatGenStatus::FAIL_PARSE,
"Error reading VCF Record ALT.");
return(false);
}
// Read the Qual.
if(!readTilTab(filePtr, myQual))
{
myStatus.setStatus(StatGenStatus::FAIL_PARSE,
"Error reading VCF Record QUAL.");
return(false);
}
else
{
if(myQual != ".")
{
// Read the quality, so convert to an integer.
myQualNum = atof(myQual.c_str());
}
else
{
myQualNum = -1;
}
}
// Read the Filter.
if(!myFilter.read(filePtr))
{
myStatus.setStatus(StatGenStatus::FAIL_PARSE,
"Error reading VCF Record FILTER.");
return(false);
}
// Read the Info (could be the last word in the line or file).
if(!myInfo.read(filePtr))
{
// Found the end of the line after the info field, so return true,
// successfully read the record.
return(true);
}
if(siteOnly)
{
// Do not store genotypes, so just consume the rest of the line.
filePtr->readTilChar("\n");
}
else
{
// Not yet at the end of the line, so read the genotype fields
// (format & samples)
try
{
myGenotype.read(filePtr, sampleSubset);
}
catch(std::exception& e)
{
myDummyString = "Failed parsing the Genotype Fields of " + myChrom + ":" +
std::to_string((long long int)my1BasedPosNum) + " (chr:pos) - " + e.what();
myStatus.setStatus(StatGenStatus::FAIL_PARSE, myDummyString.c_str());
return(false);
}
}
// Found the end of the line, return true since all required fields
// were read.
return(true);
}
bool VcfRecord::write(IFILE filePtr, bool siteOnly)
{
if(filePtr == NULL)
{
myStatus.setStatus(StatGenStatus::FAIL_ORDER,
"Error writing VCF record before opening the file.");
return(false);
}
int numWritten = 0;
int numExpected = 0;
if(myChrom.length() == 0)
{
numWritten += ifprintf(filePtr, ".\t");
numExpected += 2;
}
else
{
numWritten += ifprintf(filePtr, "%s\t", myChrom.c_str());
numExpected += myChrom.length() + 1;
}
if(false) //my1BasedPos.length() == 0)
{
numWritten += ifprintf(filePtr, ".\t");
numExpected += 2;
}
else
{
std::string strPos = std::to_string((long long int)my1BasedPosNum);
numWritten += ifprintf(filePtr, "%s\t", strPos.c_str());
numExpected += strPos.length() + 1;
}
if(myID.length() == 0)
{
numWritten += ifprintf(filePtr, ".\t");
numExpected += 2;
}
else
{
numWritten += ifprintf(filePtr, "%s\t", myID.c_str());
numExpected += myID.length() + 1;
}
if(myRef.length() == 0)
{
numWritten += ifprintf(filePtr, ".\t");
numExpected += 2;
}
else
{
numWritten += ifprintf(filePtr, "%s\t", myRef.c_str());
numExpected += myRef.length() + 1;
}
if(myAlt.length() == 0)
{
numWritten += ifprintf(filePtr, ".\t");
numExpected += 2;
}
else
{
numWritten += ifprintf(filePtr, "%s\t", myAlt.c_str());
numExpected += myAlt.length() + 1;
}
if(myQual.length() == 0)
{
numWritten += ifprintf(filePtr, ".\t");
numExpected += 2;
}
else
{
numWritten += ifprintf(filePtr, "%s\t", myQual.c_str());
numExpected += myQual.length() + 1;
}
const std::string& filterString = myFilter.getString();
if(filterString.length() == 0)
{
numWritten += ifprintf(filePtr, ".\t");
numExpected += 2;
}
else
{
numWritten += ifprintf(filePtr, "%s\t", filterString.c_str());
numExpected += filterString.length() + 1;
}
// Write the info.
bool writeSuccess = myInfo.write(filePtr);
// Only write the format & genotype if we are not just writing siteOnly
// data and there is at least one sample
if((!siteOnly) && (myGenotype.getNumSamples() != 0))
{
writeSuccess &= myGenotype.write(filePtr);
}
// Write the new line.
numWritten += ifprintf(filePtr, "\n");
numExpected += 1;
return((numWritten == numExpected) && writeSuccess);
}
void VcfRecord::reset()
{
myChrom.clear();
my1BasedPosNum = 0;
//my1BasedPos.clear();
myID.clear();
myRef.clear();
myAlt.clear();
myAltArray.clear();
myQualNum = 0;;
myQual.clear();
myFilter.clear();
myInfo.clear();
myGenotype.clear();
myAlleleCount.clear();
myStatus = StatGenStatus::SUCCESS;
}
// Return the error after a failed call.
const StatGenStatus& VcfRecord::getStatus()
{
return(myStatus);
}
const char* VcfRecord::getAlleles(unsigned int index)
{
if(index == 0)
{
return(myRef.c_str());
}
if(index > getNumAlts())
{
// Index out of range.
// Throw an exception.
throw(std::runtime_error("VcfRecord::getAlleles called with an index that is greater than the number of alternates."));
return(NULL);
}
// Alternate allele, so return the alternate.
return(myAltArray.get(index-1).c_str());
}
int VcfRecord::getIntAllele(unsigned int index)
{
const char* alleles = getAlleles(index);
switch(alleles[0])
{
case 'A':
return(1);
break;
case 'C':
return(2);
break;
case 'G':
return(3);
break;
case 'T':
return(4);
break;
default:
std::cerr << "VcfRecord::getIntAllele, unknown allele, "
<< alleles[0] << std::endl;
}
return(0);
}
unsigned int VcfRecord::getNumAlts()
{
int numAlts = myAltArray.size();
if(numAlts != 0)
{
// Already parsed so just return the number of alternates.
return(numAlts);
}
// Check if it is just '.'.
if((myAlt.length() == 1) && (myAlt == "."))
{
// No alternates.
return(0);
}
// Parse the alternates by looping looking for commas.
std::string* altStr = &(myAltArray.getNextEmpty());
for(std::string::iterator iter = myAlt.begin(); iter != myAlt.end(); iter++)
{
if(*iter == ',')
{
altStr = &(myAltArray.getNextEmpty());
}
else
{
altStr->push_back(*iter);
}
}
return(myAltArray.size());
}
int VcfRecord::getAlleleCount(unsigned int index,
VcfSubsetSamples* sampleSubset)
{
unsigned int numAlts = getNumAlts();
if(index > numAlts)
{
// Index out of range.
// Throw an exception.
throw(std::runtime_error("VcfRecord::getAlleles called with an index that is greater than the number of alternates."));
return(-1);
}
if(myAlleleCount.size() == 0)
{
unsigned int gt = 0;
myAlleleCount.resize(numAlts+1, 0);
// Loop through the samples, counting the number of each allele.
for(int sampleNum = 0; sampleNum < getNumSamples();
sampleNum++)
{
if((sampleSubset != NULL) &&
!(sampleSubset->keep(sampleNum)))
{
// Skip this sample.
continue;
}
for(int gtNum = 0; gtNum < getNumGTs(sampleNum); gtNum++)
{
gt = getGT(sampleNum, gtNum);
if((gt < 0) || (gt > numAlts))
{
// Out of range GT, so continue to the next gt
continue;
}
// Increment the minor allele count
++myAlleleCount[gt];
}
}
}
// Alternate allele, so return the alternate.
return(myAlleleCount[index]);
}
bool VcfRecord::readTilTab(IFILE filePtr, std::string& stringRef)
{
int charRead = 0;
while(1)
{
charRead = ifgetc(filePtr);
if((charRead == '\n') || (charRead == EOF))
{
// Didn't find a tab, found a '\n' or eof
// It still populated the string with values up
// until the tab.
return(false);
}
if(charRead == '\t')
{
// hit the tab character, so exit the loop.
break;
}
stringRef += charRead;
}
return(true);
}
|