Python khmer.ReadParser类代码示例

def test_read_pair_iterator_in_error_mode():
    assert 0

    rparser = \
        ReadParser(utils.get_test_data("test-abund-read-paired.fa"))

    # If walks like an iterator and quacks like an iterator...
    rpi = rparser.iter_read_pairs()
    assert "__iter__" in dir(rpi)
    assert "next" in dir(rpi)

    # Are the alleged pairs actually pairs?
    read_pairs_1 = []
    for read_1, read_2 in rpi:
        read_pairs_1.append([read_1, read_2])
        assert read_1.name[: 19] == read_2.name[: 19]

    # Reload parser.
    # Note: No 'rewind' or 'reset' capability at the time of this writing.
    rparser = \
        ReadParser(utils.get_test_data("test-abund-read-paired.fa"))

    # Ensure that error mode is the default mode.
    read_pairs_2 = []
    for read_1, read_2 \
            in rparser.iter_read_pairs(ReadParser.PAIR_MODE_ERROR_ON_UNPAIRED):
        read_pairs_2.append([read_1, read_2])
    matches = \
        map(
            lambda rp1, rp2: rp1[0].name == rp2[0].name,
            read_pairs_1, read_pairs_2
        )
    assert all(matches)  # Assert ALL the matches. :-]

def test_bzip2_decompression_truncated_pairiter():

    rparser = ReadParser(utils.get_test_data("100-reads.fq.truncated.bz2"))
    try:
        for read in rparser.iter_read_pairs():
            pass
        assert 0, "this should fail"
    except IOError as err:
        print str(err)

def test_iternext():
    rparser = ReadParser(utils.get_test_data("fakelump.fa.stoptags.txt"))
    read_pairs = []
    try:
        for read_1, read_2 in rparser.iter_read_pairs():
            read_pairs.append(read_1, read_2)
        assert 0, "Shouldn't be able to iterate over non FASTA file"
    except IOError, err:
        print str(err)

def test_read_pair_iterator_in_error_mode_xfail( ):

    rparser = \
    ReadParser( utils.get_test_data( "test-abund-read-impaired.fa" ) )

    failed = True
    try:
        for rpair in rparser.iter_read_pairs( ): pass
        failed = False
    except IOError as exc: pass
    assert failed

def test_gzip_decompression_truncated_pairiter():

    rparser = ReadParser(utils.get_test_data("100-reads.fq.truncated.gz"))
    try:
        for _ in rparser.iter_read_pairs():
            pass
        assert 0, "this should fail"
    except OSError as err:
        print(str(err))
    except ValueError as err:
        print(str(err))

def test_read_pair_iterator_in_ignore_mode():
    assert 0

    rparser = \
        ReadParser(utils.get_test_data("test-abund-read-impaired.fa"))

    read_pairs = []
    for read_1, read_2 \
            in rparser.iter_read_pairs(ReadParser.PAIR_MODE_IGNORE_UNPAIRED):
        read_pairs.append([read_1, read_2])
        assert read_1.name[: 19] == read_2.name[: 19]
    assert 2 == len(read_pairs)

def test_read_pair_iterator_in_error_mode_xfail():

    rparser = \
        ReadParser(utils.get_test_data("test-abund-read-impaired.fa"))

    failed = True
    try:
        for _ in rparser.iter_read_pairs():
            pass
        failed = False
    except ValueError as exc:
        assert "Invalid read pair" in str(exc), str(exc)
    assert failed

def test_iterator_identities():

    rparser = \
        ReadParser(utils.get_test_data("test-abund-read-paired.fa"))
    assert rparser is rparser.__iter__()
    assert rparser is rparser.iter_reads()

def main():
    parser = sanitize_help(get_parser())
    args = parser.parse_args()

    configure_logging(args.quiet)

    ###

    if len(set(args.input_filenames)) != len(args.input_filenames):
        log_error("Error: Cannot input the same filename multiple times.")
        sys.exit(1)

    if args.trim_at_coverage != DEFAULT_TRIM_AT_COVERAGE and \
       not args.variable_coverage:
        log_error("Error: --trim-at-coverage/-Z given, but "
                  "--variable-coverage/-V not specified.")
        sys.exit(1)

    if args.diginorm_coverage != DEFAULT_DIGINORM_COVERAGE and \
       not args.diginorm:
        log_error("Error: --diginorm-coverage given, but "
                  "--diginorm not specified.")
        sys.exit(1)

    if args.diginorm and args.single_pass:
        log_error("Error: --diginorm and --single-pass are incompatible!\n"
                  "You probably want to use normalize-by-median.py instead.")
        sys.exit(1)

    ###

    graphtype = 'countgraph' if not args.small_count else 'smallcountgraph'
    report_on_config(args, graphtype=graphtype)
    check_valid_file_exists(args.input_filenames)
    check_space(args.input_filenames, args.force)
    if args.savegraph:
        graphsize = calculate_graphsize(args, graphtype)
        check_space_for_graph(args.savegraph, graphsize, args.force)

    if ('-' in args.input_filenames or '/dev/stdin' in args.input_filenames) \
       and not args.output:
        log_error("Accepting input from stdin; output filename must "
                  "be provided with -o.")
        sys.exit(1)

    if args.loadgraph:
        log_info('loading countgraph from {graph}', graph=args.loadgraph)
        if args.small_count:
            ct = SmallCountgraph.load(args.loadgraph)
        else:
            ct = Countgraph.load(args.loadgraph)
    else:
        log_info('making countgraph')
        ct = khmer_args.create_countgraph(args)

    K = ct.ksize()
    tempdir = tempfile.mkdtemp('khmer', 'tmp', args.tempdir)
    log_info('created temporary directory {temp};\n'
             'use -T to change location', temp=tempdir)

    trimmer = Trimmer(ct, not args.variable_coverage, args.cutoff,
                      args.trim_at_coverage)
    if args.diginorm:
        trimmer.set_diginorm(args.diginorm_coverage)

    # ### FIRST PASS ###

    save_pass2_total = 0

    written_bp = 0
    written_reads = 0

    # only create the file writer once if outfp is specified; otherwise,
    # create it for each file.
    if args.output:
        trimfp = get_file_writer(args.output, args.gzip, args.bzip)

    pass2list = []
    for filename in args.input_filenames:
        # figure out temporary filename for 2nd pass
        pass2filename = os.path.basename(filename) + '.pass2'
        pass2filename = os.path.join(tempdir, pass2filename)
        pass2fp = open(pass2filename, 'w')

        # construct output filenames
        if args.output is None:
            # note: this will be saved in trimfp.
            outfp = open(os.path.basename(filename) + '.abundtrim', 'wb')

            # get file handle w/gzip, bzip
            trimfp = get_file_writer(outfp, args.gzip, args.bzip)

        # record all this info
        pass2list.append((filename, pass2filename, trimfp))

        # input file stuff: get a broken_paired reader.
        paired_iter = broken_paired_reader(ReadParser(filename), min_length=K,
                                           force_single=args.ignore_pairs)

        # main loop through the file.
#.........这里部分代码省略.........

def reads():
    infile = utils.get_test_data('valid-read-testing.fq')
    reads = ReadParser(infile)
    yield reads
    reads.close()