Java Code Examples for htsjdk.samtools.reference.ReferenceSequenceFileFactory#getDefaultDictionaryForReferenceSequence()

/**
 * Register the reference file (and associated dictionary and index) to be downloaded to every node using Spark's
 * copying mechanism ({@code SparkContext#addFile()}).
 * @param ctx the Spark context
 * @param referencePath the reference file, can be a local file or a remote path
 * @return the reference file name; the absolute path of the file can be found by a Spark task using {@code SparkFiles#get()}
 */
protected static String addReferenceFilesForSpark(JavaSparkContext ctx, Path referencePath) {
    if (referencePath == null) {
        return null;
    }
    Path indexPath = ReferenceSequenceFileFactory.getFastaIndexFileName(referencePath);
    Path dictPath = ReferenceSequenceFileFactory.getDefaultDictionaryForReferenceSequence(referencePath);
    Path gziPath = GZIIndex.resolveIndexNameForBgzipFile(referencePath);

    ctx.addFile(referencePath.toUri().toString());
    if (Files.exists(indexPath)) {
        ctx.addFile(indexPath.toUri().toString());
    }
    if (Files.exists(dictPath)) {
        ctx.addFile(dictPath.toUri().toString());
    }
    if (Files.exists(gziPath)) {
        ctx.addFile(gziPath.toUri().toString());
    }

    return referencePath.getFileName().toString();
}
 

/**
 * Use reference filename to create URI to go into header if URI was not passed on cmd line.
 */
protected String[] customCommandLineValidation() {
    if (URI == null) {
        URI = "file:" + referenceSequence.getReferenceFile().getAbsolutePath();
    }
    if (OUTPUT == null) {
        OUTPUT = ReferenceSequenceFileFactory.getDefaultDictionaryForReferenceSequence(referenceSequence.getReferenceFile());
        logger.info("Output dictionary will be written in ", OUTPUT);
    }
    return super.customCommandLineValidation();
}
 

/**
 * Performing several preliminary checks on the file path.
 *
 * @param fastaPath Fasta file to be used as reference
 * @throws UserException If the given {@code fastaPath} is not good.
 */
private static void checkFastaPath(final Path fastaPath) {

    // does the fasta file exist? check that first...
    if (!Files.exists(fastaPath)) {
        throw new UserException.MissingReference("The specified fasta file (" + fastaPath.toUri() + ") does not exist.");
    }

    //this is the .fai index, not the .gzi
    final Path indexPath = ReferenceSequenceFileFactory.getFastaIndexFileName(fastaPath);

    // determine the name for the dict file
    final Path dictPath = ReferenceSequenceFileFactory.getDefaultDictionaryForReferenceSequence(fastaPath);

    // It's an error if either the fai or dict file does not exist. The user is now responsible
    // for creating these files.
    if (!Files.exists(indexPath)) {
        throw new UserException.MissingReferenceFaiFile(indexPath, fastaPath);
    }
    if (!Files.exists(dictPath)) {
        throw new UserException.MissingReferenceDictFile(dictPath, fastaPath);
    }

    //Block-compressed fastas additionally require a gzi index
    try {
        final Path gziPath = GZIIndex.resolveIndexNameForBgzipFile(fastaPath);
        if( IOUtil.isBlockCompressed(fastaPath, true) && !Files.exists(gziPath)){
            throw new UserException.MissingReferenceGziFile(gziPath, fastaPath);
        }
    } catch (IOException e) {
        throw new UserException.CouldNotReadInputFile("Couldn't open fasta file: " + fastaPath.toUri().toString() +  ".", e);
    }
}
 

public CreateSequenceDictionary(String FastaSequenceFileName) {
  try {
    md5 = MessageDigest.getInstance("MD5");
  } catch (NoSuchAlgorithmException e) {
    throw new RuntimeException("MD5 algorithm not found", e);
  }
  REFERENCE_SEQUENCE = new File(FastaSequenceFileName);
  URI = "file:" + REFERENCE_SEQUENCE.getAbsolutePath();
  OUTPUT = ReferenceSequenceFileFactory.getDefaultDictionaryForReferenceSequence(REFERENCE_SEQUENCE);
  logger.info("Output dictionary will be written in ", OUTPUT);
  doWork();
}