def get_parser():
p = get_pbparser(tool_id=Constants.TOOL_ID,
version=__version__,
name="Coverage",
description=__doc__,
driver_exe=Constants.DRIVER_EXE,
is_distributed=True)
ap = p.arg_parser.parser
p.add_input_file_type(FileTypes.DS_REF,
"reference",
name="Reference DataSet",
description="Reference DataSet XML or FASTA file")
p.add_input_file_type(FileTypes.GFF,
"gff",
name="Alignment Summary GFF",
description="Alignment Summary GFF")
p.add_output_file_type(FileTypes.REPORT,
"report_json",
name=meta_rpt.title,
description="Path to write report JSON output",
default_name=meta_rpt.id)
p.add_int(
option_id=Constants.MAX_CONTIGS_ID,
option_str="maxContigs",
default=Constants.MAX_CONTIGS_DEFAULT,
name="Maximum number of contigs to plot",
description="Maximum number of contigs to plot in coverage report")
return p
def _get_parser():
parser = get_pbparser(TOOL_ID, __version__, "CCS Mapping Statistics", __doc__, DRIVER_EXE)
parser.add_input_file_type(FileTypes.DS_ALIGN_CCS, "alignment_file", "ConsensusAlignment XML DataSet", "BAM, SAM or ConsensusAlignment DataSet")
parser.add_output_file_type(FileTypes.REPORT, "report_json", "PacBio Json Report", "Output report JSON file.", "mapping_stats_report.json")
return parser
def get_contract_parser():
"""
Central point of programmatically defining a Parser.
:rtype: PbParser
:return: PbParser
"""
# Commandline exe to call "{exe}" /path/to/resolved-tool-contract.json
driver_exe = "python -m pbcommand.cli.example.dev_app --resolved-tool-contract "
desc = "Dev app for Testing that supports emitting tool contracts"
subcomponents = [("my_subcomponent", "1.2.3")]
resource_types = (ResourceTypes.TMP_FILE, ResourceTypes.TMP_FILE, ResourceTypes.TMP_DIR)
p = get_pbparser(
TOOL_ID,
__version__,
"Example Dev App",
desc,
driver_exe,
is_distributed=False,
resource_types=resource_types,
subcomponents=subcomponents,
)
add_args_and_options(p)
return p
def test_misc_parser_types(self):
p = get_pbparser("pbcommand.tasks.test_parsers", "0.1.0", "Tool Name",
"Tool Descripion", "pbcommand-driver-exe ")
p.add_int("pbcommand.task_options.n",
"n",
default=0,
name="N",
description="Integer option")
p.add_float("pbcommand.task_options.f",
"f",
default=0,
name="F",
description="Float option")
# XXX note that the 'default' value is not actually what the option is
# set to by default - it simply signals that action=store_true
p.add_boolean("pbcommand.task_options.loud",
"loud",
default=False,
name="Verbose",
description="Boolean option")
pa = p.arg_parser.parser.parse_args
opts = pa(["--n", "250", "--f", "1.2345", "--loud"])
self.assertEqual(opts.n, 250)
self.assertEqual(opts.f, 1.2345)
self.assertTrue(opts.loud)
opts2 = pa([])
self.assertFalse(opts2.loud)
def get_parser():
driver_exe = "python -m pbcommand.cli.examples.dev_app --resolved-tool-contract "
desc = "Dev app for Testing that supports emitting tool contracts"
# Can specify libs or other dependencies that
subcomponents = [("pbcommand", VERSION), ("my_component", "0.1.0"), ("my_component_id", "1.2.3")]
# ResourceTypes.*
resource_types = (ResourceTypes.TMP_FILE, ResourceTypes.TMP_FILE, ResourceTypes.TMP_DIR)
# Create an instance of a Pacbio Parser
p = get_pbparser(
TOOL_ID,
VERSION,
"Txt App",
desc,
driver_exe,
is_distributed=False,
resource_types=resource_types,
subcomponents=subcomponents,
)
# Add Input Files types
p.add_input_file_type(FileTypes.TXT, "txt_in", "Txt file", "Generic Text File")
# Add output files types
p.add_output_file_type(FileTypes.TXT, "txt_out", "Txt outfile", "Generic Output Txt file", "output.txt")
p.add_int("pbcommand.task_options.dev_max_nlines", "max_nlines", 10, "Max Lines", "Max Number of lines to Copy")
return p
def _get_parser():
driver_exe = ("python -m "
"pbreports.report.polished_assembly "
"--resolved-tool-contract ")
p = get_pbparser(Constants.TOOL_ID, __version__, spec.title, __doc__,
driver_exe)
return _add_options_to_parser(p)
def test_misc_parser_types(self):
p = get_pbparser(
"pbcommand.tasks.test_parsers",
"0.1.0",
"Tool Name",
"Tool Descripion",
"pbcommand-driver-exe ")
p.add_int("pbcommand.task_options.n", "n", default=0, name="N",
description="Integer option")
p.add_float("pbcommand.task_options.f", "f", default=0, name="F",
description="Float option")
# XXX note that the 'default' value is not actually what the option is
# set to by default - it simply signals that action=store_true
p.add_boolean("pbcommand.task_options.loud", "loud", default=False,
name="Verbose", description="Boolean option")
pa = p.arg_parser.parser.parse_args
opts = pa(["--n", "250", "--f", "1.2345", "--loud"])
self.assertEqual(opts.n, 250)
self.assertEqual(opts.f, 1.2345)
self.assertTrue(opts.loud)
opts2 = pa([])
self.assertFalse(opts2.loud)
def get_parser():
p = get_pbparser(tool_id=Constants.TOOL_ID,
version=__version__,
name=Constants.TOOL_NAME,
description=__doc__,
driver_exe=Constants.DRIVER_EXE)
p.add_input_file_type(FileTypes.DS_SUBREADS,
"subreads",
name="BarcodedSubreadSet",
description="Barcoded Subread DataSet XML")
p.add_input_file_type(FileTypes.DS_BARCODE,
"barcodes",
name="BarcodeSet",
description="Barcode DataSet XML")
p.add_output_file_type(FileTypes.REPORT,
"report_json",
name="Barcode Report",
description="Summary of barcoding results",
default_name="barcode_report")
# TODO(nechols)(2016-03-15) not yet supported in SA 3.x
# this is necessary for BasH5Reader to handle the differences between the
# .ccs.h5 files and .bas.h5 files.
ap = p.arg_parser.parser
ap.add_argument('--ccs',
action='store_true',
help='Use consensus reads instead of subreads.')
return p
def get_contract_parser():
"""
Central point of programmatically defining a Parser.
:rtype: PbParser
:return: PbParser
"""
# Commandline exe to call "{exe}" /path/to/resolved-tool-contract.json
driver_exe = "python -m pbcommand.cli.example.dev_app --resolved-tool-contract "
desc = "Dev app for Testing that supports emitting tool contracts"
subcomponents = [("my_subcomponent", "1.2.3")]
resource_types = (ResourceTypes.TMP_FILE,
ResourceTypes.TMP_FILE,
ResourceTypes.TMP_DIR)
p = get_pbparser(TOOL_ID,
__version__,
"Example Dev App",
desc,
driver_exe,
is_distributed=False,
resource_types=resource_types,
subcomponents=subcomponents)
add_args_and_options(p)
return p
def get_parser():
p = get_pbparser(
tool_id=Constants.TOOL_ID,
version=__version__,
name=Constants.TOOL_NAME,
description=__doc__,
driver_exe=Constants.DRIVER_EXE,
)
p.add_input_file_type(
FileTypes.DS_SUBREADS, "subreads", name="BarcodedSubreadSet", description="Barcoded Subread DataSet XML"
)
p.add_input_file_type(FileTypes.DS_BARCODE, "barcodes", name="BarcodeSet", description="Barcode DataSet XML")
p.add_output_file_type(
FileTypes.REPORT,
"report_json",
name="Barcode report",
description="Path to write Report json output.",
default_name="barcode_report",
)
# TODO(nechols)(2016-03-15) not yet supported in SA 3.x
# this is necessary for BasH5Reader to handle the differences between the
# .ccs.h5 files and .bas.h5 files.
ap = p.arg_parser.parser
ap.add_argument("--ccs", action="store_true", help="Use consensus reads instead of subreads.")
return p
def get_contract_parser():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
spec.title,
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
add_base_options_pbcommand(p, "Top Variants Report")
p.add_input_file_type(FileTypes.GFF,
file_id="gff",
name="GFF file",
description="variants.gff (can be gzip'ed)")
p.add_input_file_type(FileTypes.DS_REF,
file_id="reference",
name="Reference dataset",
description="ReferenceSet or FASTA")
# p.add_output_file_type(FileTypes.REPORT, "report",
# "JSON report", "JSON report", "report.json")
p.add_int(Constants.HOW_MANY_ID, "how_many",
default=Constants.HOW_MANY_DEFAULT,
name="Number of variants",
description="number of top variants to show (default=100)")
p.add_int(Constants.BATCH_SORT_SIZE_ID, "batch_sort_size",
default=Constants.BATCH_SORT_SIZE_DEFAULT,
name="Batch sort size",
description="Intermediate sort size parameter (default=10000)")
# XXX do we need a flag for minor variants?
return p
def get_parser():
p = get_pbparser(tool_id=Constants.TOOL_ID,
version=__version__,
name=Constants.TOOL_NAME,
description=__doc__,
driver_exe=Constants.DRIVER_EXE)
p.add_input_file_type(
FileTypes.DATASTORE,
"ds_bc",
name="JSON Datastore or SubreadSet or ConsensusReadSet",
description="Datastore of barcoded SubreadSet/ConsensusReadSet files")
p.add_input_file_type(FileTypes.DS_SUBREADS,
"subreads_in",
name="Input SubreadSet",
description="Input SubreadSet (without barcodes)")
p.add_input_file_type(FileTypes.DS_BARCODE,
"barcodes",
name="BarcodeSet",
description="Barcode DataSet XML")
p.add_output_file_type(FileTypes.REPORT,
"report_json",
name="Barcode Report",
description="Summary of barcoding results",
default_name="barcode_report")
p.tool_contract_parser.add_output_file_type(
FileTypes.CSV,
"report_csv",
name="Barcode Report Details",
description="Barcode Details Table as CSV",
default_name="barcodes_report")
p.add_boolean(Constants.ISOSEQ_MODE, "isoseq_mode", False, "Iso-Seq mode",
"Iso-Seq mode")
return p
def get_parser():
"""
Construct a hybrid PbParser with most tool contract parameters defined
separately from argparser parameters.
"""
p = get_pbparser(
tool_id=Constants.TOOL_ID,
version=__VERSION__,
name="variantCaller",
description="Compute genomic consensus and call variants relative to the reference.",
driver_exe=Constants.DRIVER_EXE,
nproc=SymbolTypes.MAX_NPROC,
resource_types=(),
default_level="WARN")
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.DS_ALIGN, "infile",
"Alignment DataSet", "BAM or Alignment DataSet")
tcp.add_input_file_type(FileTypes.DS_REF, "reference",
"Reference DataSet", "Fasta or Reference DataSet")
tcp.add_output_file_type(FileTypes.GFF, "variants",
name="Consensus GFF",
description="Consensus GFF",
default_name="variants")
tcp.add_output_file_type(FileTypes.DS_CONTIG, "consensus",
name="Consensus ContigSet",
description="Consensus sequence in Fasta format",
default_name="consensus")
tcp.add_output_file_type(FileTypes.FASTQ, "consensus_fastq",
name="Consensus fastq",
description="Consensus fastq",
default_name="consensus")
tcp.add_str(
option_id=Constants.ALGORITHM_ID,
option_str="algorithm",
default=Constants.DEFAULT_ALGORITHM,
name="Algorithm",
description="Variant calling algorithm")
tcp.add_int(
option_id=Constants.MIN_CONFIDENCE_ID,
option_str="minConfidence",
default=Constants.DEFAULT_MIN_CONFIDENCE,
name="Minimum confidence",
description="The minimum confidence for a variant call to be output "+\
"to variants.gff")
tcp.add_int(
option_id=Constants.MIN_COVERAGE_ID,
option_str="minCoverage",
default=Constants.DEFAULT_MIN_COVERAGE,
name="Minimum coverage",
description="The minimum site coverage that must be achieved for " +\
"variant calls and consensus to be calculated for a site.")
tcp.add_boolean(
option_id=Constants.DIPLOID_MODE_ID,
option_str="diploid",
default=False,
name="Diploid mode (experimental)",
description="Enable detection of heterozygous variants (experimental)")
add_options_to_argument_parser(p.arg_parser.parser)
return p
def get_parser():
p = get_pbparser(Constants.TOOL_ID,
Constants.VERSION,
"AlignmentSet consolidate",
__doc__,
Constants.DRIVER,
is_distributed=True,
resource_types=(ResourceTypes.TMP_DIR,))
p.add_input_file_type(FileTypes.DS_ALIGN, "align_in", "Input AlignmentSet",
"Gathered AlignmentSet to consolidate")
p.add_output_file_type(FileTypes.DS_ALIGN,
"ds_out",
"Alignments",
description="Alignment results dataset",
default_name="combined")
p.add_boolean(Constants.CONSOLIDATE_ID, "consolidate",
default=False,
name="Consolidate .bam",
description="Merge chunked/gathered .bam files")
p.add_int(Constants.N_FILES_ID, "consolidate_n_files",
default=1,
name="Number of .bam files",
description="Number of .bam files to create in consolidate mode")
return p
def get_parser():
p = get_pbparser(
tool_id=Constants.TOOL_ID,
version=__version__,
name="Coverage",
description=__doc__,
driver_exe=Constants.DRIVER_EXE,
is_distributed=True)
ap = p.arg_parser.parser
p.add_input_file_type(FileTypes.DS_REF, "reference",
name="Reference DataSet",
description="Reference DataSet XML or FASTA file")
p.add_input_file_type(FileTypes.GFF, "gff",
name="Alignment Summary GFF",
description="Alignment Summary GFF")
p.add_output_file_type(FileTypes.REPORT, "report_json",
name="JSON report",
description="Path to write report JSON output",
default_name="coverage_report")
p.add_int(
option_id=Constants.MAX_CONTIGS_ID,
option_str="maxContigs",
default=Constants.MAX_CONTIGS_DEFAULT,
name="Maximum number of contigs to plot",
description="Maximum number of contigs to plot in coverage report")
return p
def get_parser():
driver_exe = "python -m pbcommand.cli.examples.dev_app --resolved-tool-contract "
desc = "Dev app for Testing that supports emitting tool contracts"
# Can specify libs or other dependencies that
subcomponents = [("pbcommand", VERSION), ("my_component", "0.1.0"),
("my_component_id", "1.2.3")]
# ResourceTypes.*
resource_types = (ResourceTypes.TMP_FILE, ResourceTypes.TMP_FILE,
ResourceTypes.TMP_DIR)
# Create an instance of a Pacbio Parser
p = get_pbparser(TOOL_ID,
VERSION,
"Txt App",
desc,
driver_exe,
is_distributed=False,
resource_types=resource_types,
subcomponents=subcomponents)
# Add Input Files types
p.add_input_file_type(FileTypes.TXT, "txt_in", "Txt file",
"Generic Text File")
# Add output files types
p.add_output_file_type(FileTypes.TXT, "txt_out", "Txt outfile",
"Generic Output Txt file", "output")
p.add_int("pbcommand.task_options.dev_max_nlines", "max_nlines", 10,
"Max Lines", "Max Number of lines to Copy")
return p
def get_contract_parser():
p = get_pbparser(Constants.TOOL_ID,
__version__,
meta_rpt.title,
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
add_base_options_pbcommand(p, "Top Variants Report")
p.add_input_file_type(FileTypes.GFF,
file_id="gff",
name="GFF file",
description="variants.gff (can be gzip'ed)")
p.add_input_file_type(FileTypes.DS_REF,
file_id="reference",
name="Reference dataset",
description="ReferenceSet or FASTA")
# p.add_output_file_type(FileTypes.REPORT, "report",
# "JSON report", "JSON report", "report.json")
p.add_int(Constants.HOW_MANY_ID,
"how_many",
default=Constants.HOW_MANY_DEFAULT,
name="Number of variants",
description="number of top variants to show (default=100)")
p.add_int(Constants.BATCH_SORT_SIZE_ID,
"batch_sort_size",
default=Constants.BATCH_SORT_SIZE_DEFAULT,
name="Batch sort size",
description="Intermediate sort size parameter (default=10000)")
# XXX do we need a flag for minor variants?
return p
def get_contract_parser():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Iso-Seq Cluster Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
p.add_input_file_type(FileTypes.DS_CONTIG, "inReadsFN", "Fasta reads",
description="Reads in FASTA format, usually are consensus, " +
"isoforms produced by Iso-Seq Cluster.")
p.add_input_file_type(FileTypes.DS_CONTIG, "hq_isoforms_fq", "HQ isoforms in Fastq",
description="HQ isoforms in FASTQ format produced by Iso-Seq Cluster.")
p.add_input_file_type(FileTypes.DS_CONTIG, "lq_isoforms_fq", "LQ isoforms in Fastq",
description="LQ isoforms in FASTQ format produced by Iso-Seq Cluster.")
p.add_input_file_type(FileTypes.JSON, "inSummaryFN", "Summary text",
description="A summary produced by Iso-Seq Cluster, e.g. " +
"cluster_summary.txt")
p.add_output_file_type(FileTypes.REPORT, "outJson", "Transcript Clustering Report",
description="Summary of results from pbtranscript",
default_name="isoseq_cluster_report")
return p
def _get_parser():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Iso-Seq Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
p.add_input_file_type(
FileTypes.DS_TRANSCRIPT,
"hq_transcripts",
"Clustered high-quality transcripts",
description="Clustered transcripts from 'sierra' in BAM dataset format")
p.add_input_file_type(
FileTypes.DS_TRANSCRIPT,
"lq_transcripts",
"Clustered low-quality transcripts",
description="Clustered transcripts from 'sierra' in BAM dataset format")
p.add_output_file_type(
FileTypes.REPORT,
"outJson",
"Transcript Clustering Report",
description="Summary of results from pbtranscript",
default_name="isoseq3_report")
return p
def get_parser():
"""
Construct a hybrid PbParser with most tool contract parameters defined
separately from argparser parameters.
"""
p = get_pbparser(
tool_id=Constants.TOOL_ID,
version=__VERSION__,
name="variantCaller",
description="Compute genomic consensus and call variants relative to the reference.",
driver_exe=Constants.DRIVER_EXE,
nproc=SymbolTypes.MAX_NPROC,
resource_types=(),
default_level="WARN")
tcp = p.tool_contract_parser
tcp.add_input_file_type(FileTypes.DS_ALIGN, "infile",
"Alignment DataSet", "BAM or Alignment DataSet")
tcp.add_input_file_type(FileTypes.DS_REF, "reference",
"Reference DataSet", "Fasta or Reference DataSet")
tcp.add_output_file_type(FileTypes.GFF, "variants",
name="Variant Calls",
description="List of variants from the reference",
default_name="variants")
tcp.add_output_file_type(FileTypes.DS_CONTIG, "consensus",
name="Consensus Contigs",
description="Consensus contigs dataset",
default_name="consensus")
tcp.add_output_file_type(FileTypes.FASTQ, "consensus_fastq",
name="Consensus Contigs",
description="Consensus contigs in FASTQ format",
default_name="consensus")
tcp.add_str(
option_id=Constants.ALGORITHM_ID,
option_str="algorithm",
default=Constants.DEFAULT_ALGORITHM,
name="Algorithm",
description="Variant calling algorithm")
tcp.add_int(
option_id=Constants.MIN_CONFIDENCE_ID,
option_str="minConfidence",
default=Constants.DEFAULT_MIN_CONFIDENCE,
name="Minimum confidence",
description="The minimum confidence for a variant call to be output "+\
"to variants.gff")
tcp.add_int(
option_id=Constants.MIN_COVERAGE_ID,
option_str="minCoverage",
default=Constants.DEFAULT_MIN_COVERAGE,
name="Minimum coverage",
description="The minimum site coverage that must be achieved for " +\
"variant calls and consensus to be calculated for a site.")
tcp.add_boolean(
option_id=Constants.DIPLOID_MODE_ID,
option_str="diploid",
default=False,
name="Diploid mode (experimental)",
description="Enable detection of heterozygous variants (experimental)")
add_options_to_argument_parser(p.arg_parser.parser)
return p
def _get_parser():
driver_exe = ("python -m "
"pbreports.report.summarize_coverage.summarize_coverage "
"--resolved-tool-contract ")
p = get_pbparser(Constants.TOOL_ID, __version__, "Summarize Coverage",
__doc__, driver_exe)
return add_options_to_parser(p)
def _get_parser_core():
driver_exe = ("python -m "
"pbreports.report.amplicon_analysis_timing "
"--resolved-tool-contract ")
p = get_pbparser(Constants.TOOL_ID, __version__, spec.title, __doc__,
driver_exe)
return p
def _get_parser():
p = get_pbparser(Constants.TOOL_ID,
__version__,
"Minor Variants Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
return _add_options_to_parser(p)
def _get_parser_core():
p = get_pbparser(Constants.TOOL_ID,
__version__,
meta_rpt.title,
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
return p
def _get_parser():
p = get_pbparser(Constants.TOOL_ID,
__version__,
spec.title,
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
return _add_options_to_parser(p)
def get_parser():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Summarize Coverage (CCS)",
__doc__,
Constants.DRIVER_EXE)
return p
def _get_parser_core():
p = get_pbparser(Constants.TOOL_ID,
__version__,
"Loading XML Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
return p
def _get_parser_core():
p = get_pbparser(Constants.TOOL_ID,
__version__,
"Raw Dataset Statistics XML Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
return p
def get_parser():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Summarize Coverage (CCS)",
__doc__,
Constants.DRIVER_EXE)
return p
def _get_parser():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Amplicon Analysis Input",
__doc__,
Constants.DRIVER_EXE)
return _add_options_to_parser(p)
def _get_parser_core():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Amplicon Analysis Input",
__doc__,
Constants.DRIVER_EXE)
return p
def _get_parser_core():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Loading XML Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
return p
def _get_parser_core():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
spec.title,
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
return p
def _get_parser_core():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Raw Dataset Statistics XML Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
return p
def _get_parser():
desc = "Create a Mapping Report from a Aligned BAM or Alignment DataSet"
driver_exe = "python -m pbreports.report.mapping_stats --resolved-tool-contract "
parser = get_pbparser(TOOL_ID, __version__, "Mapping Statistics", desc, driver_exe)
parser.add_input_file_type(FileTypes.DS_ALIGN, "alignment_file", "Alignment XML DataSet", "BAM, SAM or Alignment DataSet")
parser.add_output_file_type(FileTypes.REPORT, "report_json", "PacBio Json Report", "Output report JSON file.", "mapping_stats_report.json")
return parser
def test_catch_output_file_extension(self):
p = get_pbparser("pbcommand.tasks.test_parsers", "0.1.0", "Tool Name",
"Tool Descripion", "pbcommand-driver-exe ")
p.add_output_file_type(file_type=FileTypes.GFF,
file_id="gff",
name="GFF file",
description="GFF file description",
default_name="annotations.gff")
tc = p.to_contract()
self.assertRaises(ValueError, tc.to_dict)
def get_base_contract_parser(Constants=BaseConstants, default_level="WARN"):
p = get_pbparser(tool_id=Constants.TOOL_ID,
version=get_version(),
name=Constants.TOOL_ID,
description=Constants.PARSER_DESC,
driver_exe=Constants.DRIVER_EXE,
nproc=SymbolTypes.MAX_NPROC,
resource_types=(ResourceTypes.TMP_DIR, ),
default_level=default_level)
return p
def _get_parser_core():
driver_exe = "python -m pbreports.report.sat --resolved-tool-contract "
p = get_pbparser(
TOOL_ID,
__version__,
"SAT Report",
__doc__,
driver_exe,
is_distributed=True)
return p
def test_input_output_files(self):
p = get_pbparser(
"pbcommand.tasks.test_parsers",
"0.1",
"Display Name",
"Tool Description ",
"pbcommand-driver-cmd",
is_distributed=False,
nproc=1,
resource_types=())
p.add_input_file_type(
file_type=FileTypes.FASTA,
file_id="fasta",
name="Fasta file",
description="Fasta file description")
p.add_input_file_type(FileTypes.JSON,
"json",
"JSON file",
"JSON file description")
p.add_output_file_type(
file_type=FileTypes.GFF,
file_id="gff",
name="GFF file",
description="GFF file description",
default_name="annotations")
tc_contract = p.to_contract()
d = tc_contract.to_dict()
inputs = d['tool_contract']['input_types']
self.assertEqual(inputs, [
{
'description': 'Fasta file description',
'title': 'Fasta file',
'id': 'fasta',
'file_type_id': 'PacBio.FileTypes.Fasta'
},
{
'description': 'JSON file description',
'title': 'JSON file',
'id': 'json',
'file_type_id': 'PacBio.FileTypes.json'
}
])
outputs = d['tool_contract']['output_types']
self.assertEqual(outputs, [
{
'title': 'GFF file',
'description': 'GFF file description',
'default_name': 'annotations',
'id': 'gff',
'file_type_id': 'PacBio.FileTypes.gff'
}
])
def _get_parser_core():
driver_exe = ("python -m "
"pbreports.report.preassembly "
"--resolved-tool-contract ")
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Preassembly",
__doc__,
driver_exe)
return p
def _get_parser_core():
driver_exe = ("python -m "
"pbreports.report.amplicon_analysis_timing "
"--resolved-tool-contract ")
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Amplicon Analysis Timing",
__doc__,
driver_exe)
return p
def _get_parser_core():
driver_exe = ("python -m "
"pbreports.report.polished_assembly "
"--resolved-tool-contract ")
p = get_pbparser(
Constants.TOOL_ID,
__version__,
meta_rpt.title,
__doc__,
driver_exe)
return p
def _get_parser_core():
driver_exe = ("python -m "
"pbreports.report.summarize_coverage.summarize_coverage "
"--resolved-tool-contract ")
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Summarize Coverage",
__doc__,
driver_exe)
return p
def _get_parser_core():
driver_exe = ("python -m "
"pbreports.report.amplicon_analysis_consensus "
"--resolved-tool-contract ")
p = get_pbparser(
Constants.TOOL_ID,
__version__,
spec.title,
__doc__,
driver_exe)
return p
def get_base_contract_parser(Constants=BaseConstants, default_level="WARN"):
p = get_pbparser(
tool_id=Constants.TOOL_ID,
version=get_version(),
name=Constants.TOOL_ID,
description=Constants.PARSER_DESC,
driver_exe=Constants.DRIVER_EXE,
nproc=SymbolTypes.MAX_NPROC,
resource_types=(ResourceTypes.TMP_DIR,),
default_level=default_level)
return p
def _get_parser():
parser = get_pbparser(Constants.TOOL_ID, __version__,
ccs_spec.title, __doc__,
Constants.DRIVER_EXE)
parser.add_input_file_type(FileTypes.DS_ALIGN_CCS, "alignment_file",
"ConsensusAlignment XML DataSet",
"BAM, SAM or ConsensusAlignment DataSet")
parser.add_output_file_type(FileTypes.REPORT, "report_json",
"Mapping Statistics Report",
"Summary of alignment results",
default_name=Constants.R_ID)
return parser
def _get_parser():
parser = get_pbparser(Constants.TOOL_ID, __version__,
spec.title, __doc__,
Constants.DRIVER_EXE)
parser.add_input_file_type(FileTypes.DS_ALIGN_CCS, "alignment_file",
"ConsensusAlignment XML DataSet",
"BAM, SAM or ConsensusAlignment DataSet")
parser.add_output_file_type(FileTypes.REPORT, "report_json",
"Mapping Statistics Report",
"Summary of alignment results",
default_name=Constants.R_ID)
return parser
def _get_parser():
parser = get_pbparser(Constants.TOOL_ID, __version__,
meta_rpt.title, __doc__,
Constants.DRIVER_EXE)
parser.add_input_file_type(FileTypes.DS_ALIGN_CCS, "alignment_file",
"ConsensusAlignment XML DataSet",
"BAM, SAM or ConsensusAlignment DataSet")
parser.add_output_file_type(FileTypes.REPORT, "report_json",
"CCS Mapping Statistics Report",
"Output report JSON file.",
default_name=meta_rpt.id)
return parser
def get_parser():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Modifications Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
p.add_input_file_type(FileTypes.H5, "basemods_h5", "HDF5 file",
"HDF5 file of base modifications from ipdSummary")
add_base_options_pbcommand(p, "Basemods report")
return p
def _get_parser():
desc = "Create a Mapping Report from a Aligned BAM or Alignment DataSet"
driver_exe = "python -m pbreports.report.mapping_stats --resolved-tool-contract "
parser = get_pbparser(Constants.TOOL_ID, __version__,
"Mapping Statistics", desc, driver_exe,
nproc=1)
parser.add_input_file_type(FileTypes.DS_ALIGN, "alignment_file",
"Alignment XML DataSet", "BAM, SAM or Alignment DataSet")
parser.add_output_file_type(FileTypes.REPORT, "report_json", "Mapping Statistics Report",
"Output report JSON file.", meta_rpt.id)
return parser
def _get_parser():
desc = "Create a Mapping Report from a Aligned BAM or Alignment DataSet"
driver_exe = "python -m pbreports.report.mapping_stats --resolved-tool-contract "
parser = get_pbparser(Constants.TOOL_ID, __version__,
"Mapping Statistics", desc, driver_exe,
nproc=1)
parser.add_input_file_type(FileTypes.DS_ALIGN, "alignment_file",
"Alignment XML DataSet", "BAM, SAM or Alignment DataSet")
parser.add_output_file_type(FileTypes.REPORT, "report_json",
"Mapping Statistics Report",
"Summary of alignment results", Constants.R_ID)
return parser
def get_parser():
p = get_pbparser(Constants.TOOL_ID, __version__, meta_rpt.title, __doc__,
Constants.DRIVER_EXE)
p.add_input_file_type(FileTypes.GFF, 'gff_file', "GFF file",
"Path to motifs.gff.gz")
p.add_input_file_type(FileTypes.CSV, 'motif_summary_csv', "CSV file",
'Path to Motif summary CSV')
p.add_output_file_type(FileTypes.REPORT,
'report_json',
name="Motifs report",
description="Path of output JSON report",
default_name="motifs_report")
return p
def get_subreads_report_parser(tool_id, version, title, desc, driver_exe):
p = get_pbparser(tool_id, version, title, desc, driver_exe,
is_distributed=True)
p.add_input_file_type(
FileTypes.DS_SUBREADS,
file_id="subread_set",
name="SubreadSet",
description="SubreadSet")
p.add_output_file_type(FileTypes.REPORT, "report", title,
description=("Filename of JSON output report. "
"Should be name only, and will be "
"written to output dir"),
default_name="report")
return p
def get_parser():
p = get_pbparser(
Constants.TOOL_ID,
__version__,
"Modifications Report",
__doc__,
Constants.DRIVER_EXE,
is_distributed=True)
p.add_input_file_type(FileTypes.H5, "basemods_h5", "HDF5 file",
"HDF5 file of base modifications from ipdSummary")
p.add_output_file_type(FileTypes.REPORT, "report", "Basemods report",
description="Summary of basemod results",
default_name="report")
return p
def _get_contract_parser():
"""
Central point of programmatically defining a Parser.
:rtype: PbParser
:return: PbParser
"""
# Number of processors to use
nproc = 2
# Commandline exe to call "{exe}" /path/to/resolved-tool-contract.json
driver_exe = "python -m pbcommand.cli.example.dev_app --resolved-tool-contract "
desc = "Dev app for Testing that supports emitting tool contracts"
p = get_pbparser(TOOL_ID, __version__, "DevApp", desc, driver_exe,
is_distributed=False, nproc=nproc)
return p
def test_catch_output_file_extension(self):
p = get_pbparser(
"pbcommand.tasks.test_parsers",
"0.1.0",
"Tool Name",
"Tool Descripion",
"pbcommand-driver-exe ")
p.add_output_file_type(
file_type=FileTypes.GFF,
file_id="gff",
name="GFF file",
description="GFF file description",
default_name="annotations.gff")
tc = p.to_contract()
self.assertRaises(ValueError, tc.to_dict)
def _get_parser():
parser = get_pbparser(Constants.TOOL_ID, __version__, spec.title, __doc__,
Constants.DRIVER_EXE)
parser.add_input_file_type(FileTypes.DS_ALIGN, "alignment_file",
"Alignment XML DataSet",
"BAM, SAM or Alignment DataSet")
parser.add_input_file_type(FileTypes.DS_SUBREADS, "subreads_file",
"Subreads XML DataSet",
"Unmapped BAM or Subreads DataSet")
parser.add_output_file_type(FileTypes.REPORT,
"report_json",
"Mapping Statistics Report",
"Summary of alignment results",
default_name=Constants.R_ID)
return parser