Examples with XReadLines org.broadinstitute.hellbender.utils.text.XReadLines used on opensource projects

Example 1 with XReadLines

use of org.broadinstitute.hellbender.utils.text.XReadLines in project gatk by broadinstitute.

the class AlleleBiasedDownsamplingUtils method loadContaminationFile.

/**
     * Create sample-contamination maps from file.
     * The format is: tab-separated with no header,
     * each line is: sampleID contaminationFraction
     *
     * @param file   Filename containing two columns: SampleID and Contamination
     * @param defaultContaminationFraction default contamination fraction, used for samples that do no specify one
     * @param sampleIDs          Set of Samples of interest (no reason to include every sample in file) or null to turn off checking
     * @param logger                      for logging output
     * @return sample-contamination Map. The returned map is a {@link DefaultedMap} that defaults to the defaultContaminationFraction for unspecified samples
     * @throws UserException if there's an IO problem reading the file.
     * @throws UserException if the file is malformed
     */
public static DefaultedMap<String, Double> loadContaminationFile(final File file, final double defaultContaminationFraction, final Set<String> sampleIDs, final Logger logger) {
    final DefaultedMap<String, Double> sampleContamination = new DefaultedMap<>(defaultContaminationFraction);
    final Set<String> nonSamplesInContaminationFile = new LinkedHashSet<>(sampleContamination.keySet());
    try (final XReadLines reader = new XReadLines(file, true)) {
        for (final String line : reader) {
            if (line.isEmpty()) {
                continue;
            }
            final String[] fields = line.split("\t");
            if (fields.length != 2) {
                throw new UserException.MalformedFile("Contamination file must have exactly two, tab-delimited columns. Offending line:\n" + line);
            }
            if (fields[0].isEmpty() || fields[1].isEmpty()) {
                throw new UserException.MalformedFile("Contamination file can not have empty strings in either column. Offending line:\n" + line);
            }
            final double contamination;
            try {
                contamination = Double.parseDouble(fields[1]);
            } catch (final NumberFormatException e) {
                throw new UserException.MalformedFile("Contamination file contains unparsable double in the second field. Offending line: " + line);
            }
            final String sampleName = fields[0];
            if (sampleContamination.containsKey(sampleName)) {
                throw new UserException.MalformedFile("Contamination file contains duplicate entries for input name " + sampleName);
            }
            if (contamination < 0.0 || contamination > 1.0) {
                throw new UserException.MalformedFile("Contamination file contains unacceptable contamination value (must be 0<=x<=1): " + line);
            }
            if (sampleIDs == null || sampleIDs.contains(sampleName)) {
                sampleContamination.put(sampleName, contamination);
            } else {
                nonSamplesInContaminationFile.add(sampleName);
            }
        }
        //output to the user info lines telling which samples are in the Contamination File
        if (!sampleContamination.isEmpty()) {
            logger.info(String.format("The following samples were found in the Contamination file and will be processed at the contamination level therein: %s", sampleContamination.keySet().toString()));
            //output to the user info lines telling which samples are NOT in the Contamination File
            if (sampleIDs != null) {
                final Set<String> samplesNotInContaminationFile = Sets.difference(sampleIDs, sampleContamination.keySet());
                if (!samplesNotInContaminationFile.isEmpty()) {
                    logger.info(String.format("The following samples were NOT found in the Contamination file and will be processed at the default contamination level: %s", samplesNotInContaminationFile.toString()));
                }
            }
        }
        //output to the user Samples that do not have lines in the Contamination File
        if (!nonSamplesInContaminationFile.isEmpty()) {
            logger.info(String.format("The following entries were found in the Contamination file but were not SAMPLEIDs. They will be ignored: %s", nonSamplesInContaminationFile.toString()));
        }
        return sampleContamination;
    } catch (IOException e) {
        throw new UserException.CouldNotReadInputFile("I/O Error while reading sample-contamination file " + file.getAbsolutePath() + ": " + e.getMessage());
    }
}

Example 2 with XReadLines

use of org.broadinstitute.hellbender.utils.text.XReadLines in project gatk by broadinstitute.

the class IntervalUtils method intervalFileToList.

/**
     * Read a file of genome locations to process. The file may be in Picard
     * or GATK interval format.
     *
     * @param glParser   GenomeLocParser
     * @param fileName  interval file
     * @return List<GenomeLoc> List of Genome Locs that have been parsed from file
     */
public static List<GenomeLoc> intervalFileToList(final GenomeLocParser glParser, final String fileName) {
    Utils.nonNull(glParser, "glParser is null");
    Utils.nonNull(fileName, "file name is null");
    final File inputFile = new File(fileName);
    final List<GenomeLoc> ret = new ArrayList<>();
    /**
         * First try to read the file as a Picard interval file since that's well structured --
         * we'll fail quickly if it's not a valid file.
         */
    boolean isPicardInterval = false;
    try {
        // Note: Picard will skip over intervals with contigs not in the sequence dictionary
        final IntervalList il = IntervalList.fromFile(inputFile);
        isPicardInterval = true;
        for (final Interval interval : il.getIntervals()) {
            // https://github.com/broadinstitute/gatk/issues/2089
            if (interval.getStart() - interval.getEnd() == 1) {
                logger.warn("Ignoring possibly incorrectly converted length 1 interval : " + interval);
            } else if (glParser.isValidGenomeLoc(interval.getContig(), interval.getStart(), interval.getEnd(), true)) {
                ret.add(glParser.createGenomeLoc(interval.getContig(), interval.getStart(), interval.getEnd(), true));
            } else {
                throw new UserException(inputFile.getAbsolutePath() + " has an invalid interval : " + interval);
            }
        }
    }// if that didn't work, try parsing file as a GATK interval file
     catch (final Exception e) {
        if (// definitely a picard file, but we failed to parse
        isPicardInterval) {
            throw new UserException.CouldNotReadInputFile(inputFile, e);
        } else {
            try (XReadLines reader = new XReadLines(new File(fileName))) {
                for (final String line : reader) {
                    if (!line.trim().isEmpty()) {
                        ret.add(glParser.parseGenomeLoc(line));
                    }
                }
            } catch (final IOException e2) {
                throw new UserException.CouldNotReadInputFile(inputFile, e2);
            }
        }
    }
    if (ret.isEmpty()) {
        throw new UserException.MalformedFile(new File(fileName), "It contains no intervals.");
    }
    return ret;
}

Example 3 with XReadLines

use of org.broadinstitute.hellbender.utils.text.XReadLines in project gatk by broadinstitute.

the class ClipReadsIntegrationTest method testClipper.

@Test(dataProvider = "clipOptions")
public void testClipper(String inBam, String reference, String extension, String option, String optAbrv, boolean doStats) throws IOException {
    final String tmpBAMOutName = BaseTest.createTempFile(inBam + "." + optAbrv, extension).getAbsolutePath();
    String tmpStatOutName = null;
    if (doStats) {
        tmpStatOutName = BaseTest.createTempFile(inBam + "." + optAbrv, ".tmp").getAbsolutePath();
    }
    final List<String> args = new ArrayList<>();
    args.addAll(Arrays.<String>asList("--input", new File(localTestData, inBam + extension).getAbsolutePath(), "--output", tmpBAMOutName));
    if (doStats) {
        args.addAll(Arrays.<String>asList("-os", tmpStatOutName));
    }
    File referenceFile = null;
    if (reference != null) {
        referenceFile = new File(getTestDataDir(), reference);
        args.add("-R");
        args.add(referenceFile.getAbsolutePath());
    }
    args.addAll(Arrays.asList(option.split("\\s+")));
    final ClipReads.ClippingData res = (ClipReads.ClippingData) this.runCommandLine(args);
    System.out.println(res);
    final File outFileBam = new File(tmpBAMOutName);
    final File expectedOutBam = new File(localTestData, "expected." + inBam + "." + optAbrv + extension);
    Assert.assertTrue(expectedOutBam.exists(), "expected output read file exists " + expectedOutBam.getAbsolutePath());
    Assert.assertTrue(outFileBam.exists(), "actual output read file exists " + outFileBam.getAbsolutePath());
    SamAssertionUtils.assertSamsEqual(expectedOutBam, outFileBam, referenceFile);
    if (doStats) {
        final File outFileStat = new File(tmpStatOutName);
        final File expectedOutStat = new File(localTestData, "expected." + inBam + "." + optAbrv + ".tmp");
        Assert.assertTrue(expectedOutStat.exists(), "expected output stat file exists " + expectedOutStat.getAbsolutePath());
        Assert.assertTrue(outFileStat.exists(), "actual output stat file exists " + outFileStat.getAbsolutePath());
        List<String> actualLines = new XReadLines(new File(tmpStatOutName)).readLines();
        List<String> expectedLines = new XReadLines(expectedOutStat).readLines();
        Assert.assertEquals(actualLines.toString(), expectedLines.toString());
    }
}

Example 4 with XReadLines

use of org.broadinstitute.hellbender.utils.text.XReadLines in project gatk by broadinstitute.

the class CountReadsSparkIntegrationTest method testCountReadsWithIntervals.

@Test(dataProvider = "intervals", groups = "spark")
public void testCountReadsWithIntervals(final String interval_args, final long expectedCount) throws Exception {
    final File ORIG_BAM = new File(getTestDataDir(), "count_reads_sorted.bam");
    final File outputFile = createTempFile("count_reads_spark", "count");
    ArgumentsBuilder args = new ArgumentsBuilder();
    args.addInput(ORIG_BAM);
    args.add(interval_args);
    args.addOutput(outputFile);
    this.runCommandLine(args.getArgsArray());
    try (XReadLines output = new XReadLines(outputFile)) {
        Assert.assertEquals((long) Long.valueOf(output.next()), expectedCount);
    }
}

Example 5 with XReadLines

use of org.broadinstitute.hellbender.utils.text.XReadLines in project gatk by broadinstitute.

the class TrancheUnitTest method readData.

private ArrayList<VariantDatum> readData() throws IOException {
    ArrayList<VariantDatum> vd = new ArrayList<>();
    try (XReadLines xrl = new XReadLines(QUAL_DATA, true)) {
        for (String line : xrl) {
            String[] parts = line.split("\t");
            // QUAL,TRANSITION,ID,LOD,FILTER
            if (!parts[0].equals("QUAL")) {
                VariantDatum datum = new VariantDatum();
                datum.lod = Double.valueOf(parts[3]);
                datum.isTransition = parts[1].equals("1");
                datum.isKnown = !parts[2].equals(".");
                datum.isSNP = true;
                datum.atTruthSite = datum.isKnown;
                vd.add(datum);
            }
        }
    }
    return vd;
}