def parse_help(cmd: typing.Collection[str],
text: str,
parse_positionals=True) -> Command:
"""
Parse a string of help text into a Command. Use this if you already have run the executable and extracted the
help text yourself
:param cmd: List of arguments used to generate this help text, e.g. ['bwa', 'mem']
:param text: The help text to parse
:param parse_positionals: If false, don't parse positional arguments
"""
help_command = CliParser(
parse_positionals=parse_positionals).parse_command(name=cmd, cmd=text)
usage_command = parse_usage(cmd, text)
# Combine the two commands by picking from the help_command where possible, otherwise falling back on the usage
fields = dict(
help_text=text,
# Use the help command's positionals preferentially, but fall back to usage
positional=help_command.positional or usage_command.positional,
# Combine the flags from both help and usage
named=list(_combine_flags([help_command.named, usage_command.named])),
)
for field in dataclasses.fields(Command):
fields[field.name] = (fields.get(field.name)
or getattr(help_command, field.name)
or getattr(usage_command, field.name))
return Command(**fields)
def test_pisces_usage():
text = "USAGE: dotnet Pisces.dll -bam <bam path> -g <genome path>"
command = parse_usage(["pisces"], text)
assert len(command.named) == 2
assert len(command.positional) == 0
assert command.named[0].longest_synonym == "-bam"
assert command.named[1].longest_synonym == "-g"
def test_bwt2sa():
text = """
Usage: bwa bwt2sa [-i 32] <in.bwt> <out.sa>
"""
command = parse_usage(["bwa", "bwt2sa"], text)
# in and out
assert len(command.positional) == 2
# -i
assert len(command.named) == 1
def test_samtools_merge_full(process):
text = process("""
Usage: samtools merge [-nurlf] [-h inh.sam] [-b <bamlist.fofn>] <out.bam> <in1.bam> [<in2.bam> ... <inN.bam>]
""")
command = parse_usage(cmd=["samtools", "merge"], text=text)
assert len(command.positional) == 3
assert command.positional[0].name == "out.bam"
assert command.positional[1].name == "in1.bam"
assert len(command.named) == 3
assert command.named[0].longest_synonym == "-nurlf"
assert command.named[1].longest_synonym == "-h"
assert command.named[2].longest_synonym == "-b"
def test_trailing_text(process):
"""
Tests that the usage parser will not parse text after the usage section has ended
"""
text = process("""
usage: htseq-count [options] alignment_file gff_file
This script takes one or more alignment files in SAM/BAM format and a feature
file in GFF format and calculates for each feature the number of reads mapping
to it. See http://htseq.readthedocs.io/en/master/count.html for details.
""")
command = parse_usage(["htseq-count"], text)
# We don't count either the command "htseq-count", or "[options]" as an argument, so there are only 2 positionals
assert len(command.positional) == 2
def test_bedtools_multiinter():
text = """
Summary: Identifies common intervals among multiple
BED/GFF/VCF files.
Usage: bedtools multiinter [OPTIONS] -i FILE1 FILE2 .. FILEn
Requires that each interval file is sorted by chrom/start.
Options:
-cluster Invoke Ryan Layers's clustering algorithm.
"""
command = parse_usage(["bedtools", "multiinter"], text)
assert len(command.positional) == 0
assert len(command.named) == 1
assert command.named[0].longest_synonym == "-i"
assert isinstance(command.named[0].args, RepeatFlagArg)
def test_mid_line_usage():
text = """
Can't open --usage: No such file or directory at /usr/bin/samtools.pl line 50.
"""
command = parse_usage(["samtools.pl", "showALEN"], text, debug=True)
assert command.empty
def test_samtools_dict():
text = """
Usage: samtools dict [options] <file.fa|file.fa.gz>
"""
command = parse_usage(["samtools", "dict"], text, debug=True)
assert len(command.positional) == 1