def __init__(self, input_files, output_file, dependencies=()):
Node.__init__(self,
description="<Detect Input Duplication: %s>" %
(describe_files(input_files)),
input_files=input_files,
output_files=output_file,
dependencies=dependencies)
def __init__(self, config, reference, intervals, infiles, outfile, dependencies=()):
self._basename = os.path.basename(outfile)
infiles = safe_coerce_to_tuple(infiles)
jar_file = os.path.join(config.jar_root, "GenomeAnalysisTK.jar")
command = AtomicJavaCmdBuilder(jar_file, jre_options=config.jre_options)
command.set_option("-T", "IndelRealigner")
command.set_option("-R", "%(IN_REFERENCE)s")
command.set_option("-targetIntervals", "%(IN_INTERVALS)s")
command.set_option("-o", "%(OUT_BAMFILE)s")
command.set_option("--bam_compression", 0)
command.set_option("--disable_bam_indexing")
_set_input_files(command, infiles)
command.set_kwargs(
IN_REFERENCE=reference,
IN_REF_DICT=fileutils.swap_ext(reference, ".dict"),
IN_INTERVALS=intervals,
OUT_BAMFILE=outfile,
CHECK_GATK=_get_gatk_version_check(config),
)
calmd = AtomicCmd(
["samtools", "calmd", "-b", "%(TEMP_IN_BAM)s", "%(IN_REF)s"],
TEMP_IN_BAM=self._basename,
IN_REF=reference,
TEMP_OUT_STDOUT=self._basename + ".calmd",
CHECK_VERSION=SAMTOOLS_VERSION,
)
description = "<Indel Realigner (aligning): %s -> %r>" % (describe_files(infiles), outfile)
CommandNode.__init__(
self, description=description, command=ParallelCmds([command.finalize(), calmd]), dependencies=dependencies
)
def __init__(self, config, target_name, input_files, output_file, intervals_file = None, print_stats = False, max_contigs = _MAX_CONTIGS, dependencies = ()):
self._target_name = target_name
self._input_files = safe_coerce_to_tuple(input_files)
self._output_file = output_file
self._intervals = intervals_file
self._print_stats = print_stats
self._max_contigs = max_contigs
self._max_contigs_reached = False
input_files = []
input_files.extend(self._input_files)
input_files.extend(swap_ext(input_file, ".bai") for input_file in self._input_files)
if intervals_file:
input_files.append(intervals_file)
executables = ["coverageBed"] if intervals_file else ["genomeCoverageBed"]
auxiliary_files = []
for cmd in concatenate_input_bams(config, self._input_files)[0]:
executables.extend(cmd.executables)
auxiliary_files.extend(cmd.auxiliary_files)
Node.__init__(self,
description = "<DepthHistogram: %s -> '%s'>" \
% (describe_files(self._input_files),
self._output_file),
input_files = input_files,
output_files = self._output_file,
dependencies = dependencies,
executables = executables,
auxiliary_files = auxiliary_files)
def __init__(self, input_files, output_file, dependencies=()):
Node.__init__(self,
description="<Detect Input Duplication: %s>"
% (describe_files(input_files)),
input_files=input_files,
output_files=output_file,
dependencies=dependencies)
def __init__(self, config, reference, intervals, infiles, outfile,
dependencies=()):
self._basename = os.path.basename(outfile)
infiles = safe_coerce_to_tuple(infiles)
jar_file = os.path.join(config.jar_root, "GenomeAnalysisTK.jar")
command = AtomicJavaCmdBuilder(jar_file,
jre_options=config.jre_options)
command.set_option("-T", "IndelRealigner")
command.set_option("-R", "%(IN_REFERENCE)s")
command.set_option("-targetIntervals", "%(IN_INTERVALS)s")
command.set_option("-o", "%(OUT_BAMFILE)s")
command.set_option("--bam_compression", 0)
command.set_option("--disable_bam_indexing")
_set_input_files(command, infiles)
command.set_kwargs(IN_REFERENCE=reference,
IN_REF_DICT=fileutils.swap_ext(reference, ".dict"),
IN_INTERVALS=intervals,
OUT_BAMFILE=outfile,
CHECK_GATK=_get_gatk_version_check(config))
calmd = AtomicCmd(["samtools", "calmd", "-b",
"%(TEMP_IN_BAM)s", "%(IN_REF)s"],
TEMP_IN_BAM=self._basename,
IN_REF=reference,
TEMP_OUT_STDOUT=self._basename + ".calmd",
CHECK_VERSION=SAMTOOLS_VERSION)
description = "<Indel Realigner (aligning): %s -> %r>" \
% (describe_files(infiles), outfile)
CommandNode.__init__(self,
description=description,
command=ParallelCmds([command.finalize(), calmd]),
dependencies=dependencies)
def __init__(self, parameters):
description = "<MarkDuplicates: %s>" \
% (describe_files(parameters.input_bams),)
PicardNode.__init__(self,
command=parameters.command.finalize(),
description=description,
dependencies=parameters.dependencies)
def __init__(self, parameters):
description = "<MarkDuplicates: %s>" \
% (describe_files(parameters.input_bams),)
PicardNode.__init__(self,
command=parameters.command.finalize(),
description=description,
dependencies=parameters.dependencies)
def __init__(self, config, target_name, input_files, output_file,
regions_file=None, dependencies=()):
bam_input = MultiBAMInput(config, input_files)
if len(bam_input.files) > 1 and regions_file:
raise ValueError("DepthHistogram for regions require single, "
"indexed input BAM file.")
builder = factory.new("depths")
builder.add_value("%(TEMP_IN_BAM)s")
builder.add_value("%(OUT_FILE)s")
builder.set_option("--target-name", target_name)
builder.set_kwargs(OUT_FILE=output_file)
bam_input.setup(builder)
if regions_file:
builder.set_option('--regions-file', '%(IN_REGIONS)s')
builder.set_kwargs(IN_REGIONS=regions_file)
command = ParallelCmds(bam_input.commands + [builder.finalize()])
description = "<DepthHistogram: %s -> '%s'>" \
% (describe_files(bam_input.files), output_file)
MultiBAMInputNode.__init__(self,
bam_input=bam_input,
command=command,
description=description,
dependencies=dependencies)
def __init__(self, input_files, output_file, offset, dependencies=()):
self._offset = offset
Node.__init__(self,
description="<Validate FASTQ Files: %s>" %
(describe_files(input_files)),
input_files=input_files,
output_files=output_file,
dependencies=dependencies)
def __init__(self, input_files, output_file, offset, dependencies=()):
self._offset = offset
Node.__init__(self,
description="<Validate FASTQ Files: %s>"
% (describe_files(input_files)),
input_files=input_files,
output_files=output_file,
dependencies=dependencies)
def __init__(self, parameters):
self._version = parameters.version
self._basename = parameters.basename
if len(parameters.input_files_1) != len(parameters.input_files_2):
raise CmdError("Number of mate 1 files differ from mate 2 files: %i != %i" \
% (len(parameters.input_files_1),
len(parameters.input_files_2)))
zcat_pair_1 = _build_unicat_command(parameters.input_files_1,
"uncompressed_input_1")
zcat_pair_2 = _build_unicat_command(parameters.input_files_2,
"uncompressed_input_2")
zip_pair_1 = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".pair1.truncated")
zip_pair_2 = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".pair2.truncated")
zip_discarded = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".discarded")
adapterrm = parameters.command.finalize()
commands = [adapterrm, zip_pair_1, zip_pair_2]
if parameters.version == VERSION_15:
zip_aln = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".collapsed")
zip_aln_trunc = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".collapsed.truncated")
zip_unaligned = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".singleton.truncated")
commands += [zip_aln, zip_aln_trunc, zip_unaligned]
else:
zip_aln = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".singleton.aln.truncated")
zip_unaligned = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".singleton.unaln.truncated")
commands += [zip_aln, zip_unaligned]
commands += [zip_discarded, zcat_pair_1, zcat_pair_2]
# Opening of pipes block, so the order of these commands is dependent upon
# the order of file-opens in atomiccmd and the the programs themselves.
commands = ParallelCmds(commands)
description = "<PE_AdapterRM: %s -> '%s.*'>" \
% (fileutils.describe_files(parameters.input_files_1).replace("file", "pair"),
parameters.output_prefix)
CommandNode.__init__(self,
command=commands,
description=description,
dependencies=parameters.dependencies)
def __init__(self, input_files, output_file, dependencies=()):
Node.__init__(self,
description="<Validate FASTA Files: %s>" %
(describe_files(input_files)),
input_files=input_files,
output_files=output_file,
dependencies=dependencies)
assert len(self.output_files) == 1, self.output_files
def __init__(self, input_files, output_file, dependencies=()):
Node.__init__(self,
description="<Validate FASTA Files: %s>"
% (describe_files(input_files)),
input_files=input_files,
output_files=output_file,
dependencies=dependencies)
assert len(self.output_files) == 1, self.output_files
def __init__(self, input_files, output_file, dependencies=()):
self._output_file = output_file
Node.__init__(self,
description = "<MergeCoverage: '%s' -> '%s'>" \
% (describe_files(input_files), self._output_file),
input_files = input_files,
output_files = self._output_file,
dependencies = dependencies)
def __init__(self, input_files, output_file, dependencies=()):
self._output_file = output_file
Node.__init__(
self,
description="<MergeCoverage: '%s' -> '%s'>" % (describe_files(input_files), self._output_file),
input_files=input_files,
output_files=self._output_file,
dependencies=dependencies,
)
def __init__(self, config, input_bams, output_bam, dependencies = ()):
cat_cmds, cat_obj = concatenate_input_bams(config, input_bams)
filteruniq = AtomicCmd(["bam_rmdup_collapsed", "--remove-duplicates"],
IN_STDIN = cat_obj,
OUT_STDOUT = output_bam)
command = ParallelCmds(cat_cmds + [filteruniq])
description = "<FilterCollapsedBAM: %s>" % (describe_files(input_bams),)
CommandNode.__init__(self,
command = command,
description = description,
dependencies = dependencies)
def __init__(self, config, input_bams, output_bam, dependencies=()):
cat_cmds, cat_obj = concatenate_input_bams(config, input_bams)
filteruniq = AtomicCmd(["bam_rmdup_collapsed", "--remove-duplicates"],
IN_STDIN=cat_obj,
OUT_STDOUT=output_bam)
command = ParallelCmds(cat_cmds + [filteruniq])
description = "<FilterCollapsedBAM: %s>" % (
describe_files(input_bams), )
CommandNode.__init__(self,
command=command,
description=description,
dependencies=dependencies)
def __init__(self, parameters):
bam_input = MultiBAMInput(parameters.config, parameters.input_files)
bam_input.setup(parameters.command)
cmd_map = parameters.command.finalize()
description = "<mapDamage (plots): %s -> '%s'>" \
% (describe_files(parameters.input_files),
parameters.output_directory)
MultiBAMInputNode.__init__(self,
bam_input=bam_input,
command=ParallelCmds(bam_input.commands +
[cmd_map]),
description=description,
dependencies=parameters.dependencies)
def __init__(self, parameters):
bam_input = MultiBAMInput(parameters.config, parameters.input_files)
bam_input.setup(parameters.command)
cmd_map = parameters.command.finalize()
description = "<mapDamage (plots): %s -> '%s'>" \
% (describe_files(parameters.input_files),
parameters.output_directory)
MultiBAMInputNode.__init__(self,
bam_input=bam_input,
command=ParallelCmds(bam_input.commands +
[cmd_map]),
description=description,
dependencies=parameters.dependencies)
def __init__(self, config, input_files, output_file, dependencies=()):
bam_input = MultiBAMInput(config, input_files)
duphist_command = factory.new("duphist")
duphist_command.add_value("%(TEMP_IN_BAM)s")
duphist_command.set_kwargs(OUT_STDOUT=output_file)
bam_input.setup(duphist_command)
duphist_command = duphist_command.finalize()
commands = ParallelCmds(bam_input.commands + [duphist_command])
description = "<DuplicateHistogram: %s -> %r>" % (describe_files(input_files), output_file)
MultiBAMInputNode.__init__(
self, bam_input=bam_input, command=commands, description=description, dependencies=dependencies
)
def __init__(self, main_tree_files, support_tree_files, output_file, dependencies = ()):
self._output_file = output_file
self._main_tree_files = safe_coerce_to_tuple(main_tree_files)
self._support_tree_files = safe_coerce_to_tuple(support_tree_files)
input_files = self._main_tree_files + self._support_tree_files
description = "<NewickSupport: %s>" % \
(describe_files(main_tree_files),)
Node.__init__(self,
description = description,
input_files = input_files,
output_files = output_file,
dependencies = dependencies)
def __init__(self, parameters):
self._directory = parameters.directory
bam_input = MultiBAMInput(parameters.config, parameters.input_files)
bam_input.setup(parameters.command)
command = parameters.command.finalize()
description = "<mapDamage (rescale): %s -> %r>" \
% (describe_files(parameters.input_files),
parameters.output_file)
MultiBAMInputNode.__init__(self,
bam_input=bam_input,
command=ParallelCmds(bam_input.commands +
[command]),
description=description,
dependencies=parameters.dependencies)
def __init__(self, parameters):
self._directory = parameters.directory
bam_input = MultiBAMInput(parameters.config, parameters.input_files)
bam_input.setup(parameters.command)
command = parameters.command.finalize()
description = "<mapDamage (rescale): %s -> %r>" \
% (describe_files(parameters.input_files),
parameters.output_file)
MultiBAMInputNode.__init__(self,
bam_input=bam_input,
command=ParallelCmds(bam_input.commands +
[command]),
description=description,
dependencies=parameters.dependencies)
def __init__(self, parameters):
self._quality_offset = parameters.quality_offset
self._basename = parameters.basename
zcat = _build_cat_command(parameters.input_files, "uncompressed_input")
zip_truncated = _build_zip_command(parameters.output_format, parameters.output_prefix, ".truncated")
zip_discarded = _build_zip_command(parameters.output_format, parameters.output_prefix, ".discarded")
adapterrm = parameters.command.finalize()
commands = ParallelCmds([adapterrm, zip_discarded, zip_truncated, zcat])
CommandNode.__init__(self,
command = commands,
description = "<AdapterRM (SE): %s -> '%s.*'>" \
% (fileutils.describe_files(parameters.input_files),
parameters.output_prefix),
dependencies = parameters.dependencies)
def __init__(self, parameters):
self._basename = parameters.basename
zcat = _build_unicat_command(parameters.input_files, "uncompressed_input")
zip_truncated = _build_zip_command(parameters.output_format, parameters.output_prefix, ".truncated")
zip_discarded = _build_zip_command(parameters.output_format, parameters.output_prefix, ".discarded")
adapterrm = parameters.command.finalize()
# Opening of pipes block, so the order of these commands is dependent upon
# the order of file-opens in atomiccmd and the the programs themselves.
commands = ParallelCmds([adapterrm, zip_discarded, zip_truncated, zcat])
CommandNode.__init__(self,
command = commands,
description = "<SE_AdapterRM: %s -> '%s.*'>" \
% (fileutils.describe_files(parameters.input_files),
parameters.output_prefix),
dependencies = parameters.dependencies)
def __init__(self, config, input_bams, output_bam, keep_dupes=True, dependencies=()):
bam_input = MultiBAMInput(config, input_bams)
builder = factory.new("rmdup_collapsed")
builder.add_value("%(TEMP_IN_BAM)s")
builder.set_kwargs(OUT_STDOUT=output_bam)
bam_input.setup(builder)
if not keep_dupes:
builder.set_option("--remove-duplicates")
filteruniq = builder.finalize()
command = ParallelCmds(bam_input.commands + [filteruniq])
description = "<FilterCollapsedBAM: %s>" % (describe_files(bam_input.files),)
MultiBAMInputNode.__init__(
self, bam_input=bam_input, command=command, description=description, dependencies=dependencies
)
def __init__(self, tree_files, output_file, taxa = (), dependencies = ()):
self._output_file = output_file
self._tree_files = safe_coerce_to_tuple(tree_files)
self._reroot_on_taxa = safe_coerce_to_tuple(taxa)
reroot_on = "midpoint"
if self._reroot_on_taxa:
reroot_on = repr("', '".join(sorted(self._reroot_on_taxa)))
description = "<NewickReroot (on %s): %s>" % \
(reroot_on, describe_files(tree_files),)
Node.__init__(self,
description = description,
input_files = self._tree_files,
output_files = self._output_file,
dependencies = dependencies)
def __init__(self, config, input_files, output_file, dependencies=()):
bam_input = MultiBAMInput(config, input_files)
duphist_command = factory.new("duphist")
duphist_command.add_value('%(TEMP_IN_BAM)s')
duphist_command.set_kwargs(OUT_STDOUT=output_file)
bam_input.setup(duphist_command)
duphist_command = duphist_command.finalize()
commands = ParallelCmds(bam_input.commands + [duphist_command])
description = "<DuplicateHistogram: %s -> %r>" \
% (describe_files(input_files), output_file)
MultiBAMInputNode.__init__(self,
bam_input=bam_input,
command=commands,
description=description,
dependencies=dependencies)
def __init__(self, config, reference, infiles, outfile, dependencies=()):
infiles = safe_coerce_to_tuple(infiles)
jar_file = os.path.join(config.jar_root, "GenomeAnalysisTK.jar")
command = AtomicJavaCmdBuilder(jar_file, jre_options=config.jre_options)
command.set_option("-T", "RealignerTargetCreator")
command.set_option("-R", "%(IN_REFERENCE)s")
command.set_option("-o", "%(OUT_INTERVALS)s")
_set_input_files(command, infiles)
command.set_kwargs(
IN_REFERENCE=reference,
IN_REF_DICT=fileutils.swap_ext(reference, ".dict"),
OUT_INTERVALS=outfile,
CHECK_GATK=_get_gatk_version_check(config),
)
description = "<Indel Realigner (training): %s -> %r>" % (describe_files(infiles), outfile)
CommandNode.__init__(self, description=description, command=command.finalize(), dependencies=dependencies)
def __init__(self, parameters):
self._quality_offset = parameters.quality_offset
self._basename = parameters.basename
zcat = _build_cat_command(parameters.input_files, "uncompressed_input")
zip_truncated = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".truncated")
zip_discarded = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".discarded")
adapterrm = parameters.command.finalize()
commands = ParallelCmds(
[adapterrm, zip_discarded, zip_truncated, zcat])
CommandNode.__init__(self,
command = commands,
description = "<AdapterRM (SE): %s -> '%s.*'>" \
% (fileutils.describe_files(parameters.input_files),
parameters.output_prefix),
dependencies = parameters.dependencies)
def __init__(self, config, input_bams, output_bam, keep_dupes=True,
dependencies=()):
bam_input = MultiBAMInput(config, input_bams)
builder = factory.new("rmdup_collapsed")
builder.add_value("%(TEMP_IN_BAM)s")
builder.set_kwargs(OUT_STDOUT=output_bam)
bam_input.setup(builder)
if not keep_dupes:
builder.set_option("--remove-duplicates")
filteruniq = builder.finalize()
command = ParallelCmds(bam_input.commands + [filteruniq])
description = "<FilterCollapsedBAM: %s>" \
% (describe_files(bam_input.files),)
MultiBAMInputNode.__init__(self,
bam_input=bam_input,
command=command,
description=description,
dependencies=dependencies)
def __init__(self, config, reference, infiles, outfile, dependencies=()):
infiles = safe_coerce_to_tuple(infiles)
jar_file = os.path.join(config.jar_root, "GenomeAnalysisTK.jar")
command = AtomicJavaCmdBuilder(jar_file,
jre_options=config.jre_options)
command.set_option("-T", "RealignerTargetCreator")
command.set_option("-R", "%(IN_REFERENCE)s")
command.set_option("-o", "%(OUT_INTERVALS)s")
_set_input_files(command, infiles)
command.set_kwargs(IN_REFERENCE=reference,
IN_REF_DICT=fileutils.swap_ext(reference, ".dict"),
OUT_INTERVALS=outfile,
CHECK_GATK=_get_gatk_version_check(config))
description = "<Indel Realigner (training): %s -> %r>" \
% (describe_files(infiles), outfile)
CommandNode.__init__(self,
description=description,
command=command.finalize(),
dependencies=dependencies)
def __init__(self, config, target_name, input_files, output_file, regions_file=None, dependencies=()):
bam_input = MultiBAMInput(config, input_files)
if len(bam_input.files) > 1 and regions_file:
raise ValueError("DepthHistogram for regions require single, " "indexed input BAM file.")
builder = factory.new("depths")
builder.add_value("%(TEMP_IN_BAM)s")
builder.add_value("%(OUT_FILE)s")
builder.set_option("--target-name", target_name)
builder.set_kwargs(OUT_FILE=output_file)
bam_input.setup(builder)
if regions_file:
builder.set_option("--regions-file", "%(IN_REGIONS)s")
builder.set_kwargs(IN_REGIONS=regions_file)
command = ParallelCmds(bam_input.commands + [builder.finalize()])
description = "<DepthHistogram: %s -> '%s'>" % (describe_files(bam_input.files), output_file)
MultiBAMInputNode.__init__(
self, bam_input=bam_input, command=command, description=description, dependencies=dependencies
)
def __init__(self,
config,
target_name,
input_files,
output_file,
intervals_file=None,
print_stats=False,
max_contigs=_MAX_CONTIGS,
dependencies=()):
self._target_name = target_name
self._input_files = safe_coerce_to_tuple(input_files)
self._output_file = output_file
self._intervals = intervals_file
self._print_stats = print_stats
self._max_contigs = max_contigs
self._max_contigs_reached = False
input_files = []
input_files.extend(self._input_files)
input_files.extend(
swap_ext(input_file, ".bai") for input_file in self._input_files)
if intervals_file:
input_files.append(intervals_file)
executables = ["coverageBed"
] if intervals_file else ["genomeCoverageBed"]
auxiliary_files = []
for cmd in concatenate_input_bams(config, self._input_files)[0]:
executables.extend(cmd.executables)
auxiliary_files.extend(cmd.auxiliary_files)
Node.__init__(self,
description = "<DepthHistogram: %s -> '%s'>" \
% (describe_files(self._input_files),
self._output_file),
input_files = input_files,
output_files = self._output_file,
dependencies = dependencies,
executables = executables,
auxiliary_files = auxiliary_files)
def __init__(self, parameters):
self._version = parameters.version
self._basename = parameters.basename
if len(parameters.input_files_1) != len(parameters.input_files_2):
raise CmdError("Number of mate 1 files differ from mate 2 files: %i != %i" \
% (len(parameters.input_files_1),
len(parameters.input_files_2)))
zcat_pair_1 = _build_unicat_command(parameters.input_files_1, "uncompressed_input_1")
zcat_pair_2 = _build_unicat_command(parameters.input_files_2, "uncompressed_input_2")
zip_pair_1 = _build_zip_command(parameters.output_format, parameters.output_prefix, ".pair1.truncated")
zip_pair_2 = _build_zip_command(parameters.output_format, parameters.output_prefix, ".pair2.truncated")
zip_discarded = _build_zip_command(parameters.output_format, parameters.output_prefix, ".discarded")
adapterrm = parameters.command.finalize()
commands = [adapterrm, zip_pair_1, zip_pair_2]
if parameters.version == VERSION_15:
zip_aln = _build_zip_command(parameters.output_format, parameters.output_prefix, ".collapsed")
zip_aln_trunc = _build_zip_command(parameters.output_format, parameters.output_prefix, ".collapsed.truncated")
zip_unaligned = _build_zip_command(parameters.output_format, parameters.output_prefix, ".singleton.truncated")
commands += [zip_aln, zip_aln_trunc, zip_unaligned]
else:
zip_aln = _build_zip_command(parameters.output_format, parameters.output_prefix, ".singleton.aln.truncated")
zip_unaligned = _build_zip_command(parameters.output_format, parameters.output_prefix, ".singleton.unaln.truncated")
commands += [zip_aln, zip_unaligned]
commands += [zip_discarded, zcat_pair_1, zcat_pair_2]
# Opening of pipes block, so the order of these commands is dependent upon
# the order of file-opens in atomiccmd and the the programs themselves.
commands = ParallelCmds(commands)
description = "<PE_AdapterRM: %s -> '%s.*'>" \
% (fileutils.describe_files(parameters.input_files_1).replace("file", "pair"),
parameters.output_prefix)
CommandNode.__init__(self,
command = commands,
description = description,
dependencies = parameters.dependencies)
def __init__(self, parameters):
self._basename = parameters.basename
zcat = _build_unicat_command(parameters.input_files,
"uncompressed_input")
zip_truncated = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".truncated")
zip_discarded = _build_zip_command(parameters.output_format,
parameters.output_prefix,
".discarded")
adapterrm = parameters.command.finalize()
# Opening of pipes block, so the order of these commands is dependent upon
# the order of file-opens in atomiccmd and the the programs themselves.
commands = ParallelCmds(
[adapterrm, zip_discarded, zip_truncated, zcat])
CommandNode.__init__(self,
command = commands,
description = "<SE_AdapterRM: %s -> '%s.*'>" \
% (fileutils.describe_files(parameters.input_files),
parameters.output_prefix),
dependencies = parameters.dependencies)
def test_describe_files__iterable():
fpaths = iter(("/var/foo/bar", "/var/foo/foo"))
assert_equal(describe_files(fpaths), "2 files in '/var/foo'")
def test_describe_files__no_files():
assert_equal(describe_files(()), "No files")
def test_describe_files__same_path_abs__1_differences():
fpaths = ("/var/foo/faz", "/var/foo/fao")
assert_equal(describe_files(fpaths), "'/var/foo/fa?'")
def test_describe_files__same_path_rel():
fpaths = ("var/foo/bar", "var/foo/foo")
assert_equal(describe_files(fpaths), "2 files in 'var/foo'")
def test_describe_files__single_file():
fpath = "/var/foo/bar"
assert_equal(describe_files((fpath,)), repr(fpath))
def test_describe_files__same_path_abs__3_differences():
fpaths = ("/var/foo/bar", "/var/foo/foo")
assert_equal(describe_files(fpaths), "2 files in '/var/foo'")
def test_describe_files__different_paths_rel():
fpaths = ("var/foo/bar", "var/bar/foo")
assert_equal(describe_files(fpaths), "2 files")
def test_describe_files__no_files():
assert_equal(describe_files(()), "No files")
def test_describe_files__iterable():
fpaths = iter(("/var/foo/bar", "/var/foo/foo"))
assert_equal(describe_files(fpaths), "2 files in '/var/foo'")
def test_describe_files__different_paths_rel():
fpaths = ("var/foo/bar", "var/bar/foo")
assert_equal(describe_files(fpaths), "2 files")
def test_describe_files__same_path_rel():
fpaths = ("var/foo/bar", "var/foo/foo")
assert_equal(describe_files(fpaths), "2 files in 'var/foo'")
def test_describe_files__single_file():
fpath = "/var/foo/bar"
assert_equal(describe_files((fpath, )), repr(fpath))
