Previous changeset 24:c07b61d069ac (2018-11-09) Next changeset 26:a2e7cb2e0a30 (2020-08-20) |
Commit message:
planemo upload for repository https://github.com/peterjc/galaxy_blast/tree/master/tools/blastxml_to_top_descr commit 960f4708be7cdd486e4569e7b44eb856b2cad79d-dirty |
modified:
tools/blastxml_to_top_descr/blastxml_to_top_descr.py tools/blastxml_to_top_descr/repository_dependencies.xml |
b |
diff -r c07b61d069ac -r c32600ce6c9a tools/blastxml_to_top_descr/blastxml_to_top_descr.py --- a/tools/blastxml_to_top_descr/blastxml_to_top_descr.py Fri Nov 09 11:59:43 2018 -0500 +++ b/tools/blastxml_to_top_descr/blastxml_to_top_descr.py Fri Feb 22 09:56:23 2019 -0500 |
[ |
@@ -24,6 +24,7 @@ else: from galaxy import eggs # noqa - ignore flake8 F401 import pkg_resources + pkg_resources.require("elementtree") from elementtree import ElementTree @@ -41,23 +42,54 @@ """ parser = OptionParser(usage=usage) -parser.add_option("-t", "--topN", dest="topN", default=3, - help="Number of descriptions to collect (in order from file)") -parser.add_option("-o", "--output", dest="out_file", default=None, - help="Output filename for tabular file", - metavar="FILE") -parser.add_option("-f", "--format", dest="format", default="blastxml", - help="Input format (blastxml or tabular)") -parser.add_option("-q", "--qseqid", dest="qseqid", default="1", - help="Column for query 'qseqid' (for tabular input; default 1)") -parser.add_option("-s", "--sseqid", dest="sseqid", default="2", - help="Column for subject 'sseqid' (for tabular input; default 2)") -parser.add_option("-d", "--salltitles", dest="salltitles", default="25", - help="Column for descriptions 'salltitles' (for tabular input; default 25)") +parser.add_option( + "-t", + "--topN", + dest="topN", + default=3, + help="Number of descriptions to collect (in order from file)", +) +parser.add_option( + "-o", + "--output", + dest="out_file", + default=None, + help="Output filename for tabular file", + metavar="FILE", +) +parser.add_option( + "-f", + "--format", + dest="format", + default="blastxml", + help="Input format (blastxml or tabular)", +) +parser.add_option( + "-q", + "--qseqid", + dest="qseqid", + default="1", + help="Column for query 'qseqid' (for tabular input; default 1)", +) +parser.add_option( + "-s", + "--sseqid", + dest="sseqid", + default="2", + help="Column for subject 'sseqid' (for tabular input; default 2)", +) +parser.add_option( + "-d", + "--salltitles", + dest="salltitles", + default="25", + help="Column for descriptions 'salltitles' (for tabular input; default 25)", +) (options, args) = parser.parse_args() if len(sys.argv) == 4 and len(args) == 3 and not options.out_file: - sys.exit("""The API has changed, replace this: + sys.exit( + """The API has changed, replace this: $ python blastxml_to_top_descr.py input.xml output.tab 3 @@ -66,7 +98,8 @@ $ python blastxml_to_top_descr.py -o output.tab -t 3 input.xml Sorry. -""") +""" + ) if not args: sys.exit("Input filename missing, try -h") @@ -140,7 +173,9 @@ except Exception: with open(in_file) as handle: header = handle.read(100) - sys.exit("Invalid data format in XML file %r which starts: %r" % (in_file, header)) + sys.exit( + "Invalid data format in XML file %r which starts: %r" % (in_file, header) + ) # turn it into an iterator context = iter(context) # get the root element @@ -149,7 +184,10 @@ except Exception: with open(in_file) as handle: header = handle.read(100) - sys.exit("Unable to get root element from XML file %r which starts: %r" % (in_file, header)) + sys.exit( + "Unable to get root element from XML file %r which starts: %r" + % (in_file, header) + ) re_default_query_id = re.compile(r"^Query_\d+$") assert re_default_query_id.match(r"Query_101") @@ -180,7 +218,9 @@ # <Iteration_hits>... qseqid = elem.findtext("Iteration_query-ID") if qseqid is None: - sys.exit("Missing <Iteration_query-ID> (could be really old BLAST XML data?)") + sys.exit( + "Missing <Iteration_query-ID> (could be really old BLAST XML data?)" + ) if re_default_query_id.match(qseqid): # Place holder ID, take the first word of the query definition qseqid = elem.findtext("Iteration_query-def").split(None, 1)[0] @@ -206,13 +246,16 @@ # <Hit_accession>P56514</Hit_accession> # or, # <Hit_id>Subject_1</Hit_id> - # <Hit_def>gi|57163783|ref|NP_001009242.1| rhodopsin [Felis catus]</Hit_def> + # <Hit_def>gi|57163783|ref|NP_001009242.1| + # rhodopsin [Felis catus]</Hit_def> # <Hit_accession>Subject_1</Hit_accession> # # apparently depending on the parse_deflines switch sseqid = hit.findtext("Hit_id").split(None, 1)[0] hit_def = sseqid + " " + hit.findtext("Hit_def") - if re_default_subject_id.match(sseqid) and sseqid == hit.findtext("Hit_accession"): + if re_default_subject_id.match(sseqid) and sseqid == hit.findtext( + "Hit_accession" + ): # Place holder ID, take the first word of the subject definition hit_def = hit.findtext("Hit_def") sseqid = hit_def.split(None, 1)[0] @@ -249,7 +292,7 @@ if out_file is None: outfile = sys.stdout else: - outfile = open(out_file, 'w') + outfile = open(out_file, "w") outfile.write("#Query\t%s\n" % "\t".join("BLAST hit %i" % (i + 1) for i in range(topN))) for query, descrs in hits: count += 1 |
b |
diff -r c07b61d069ac -r c32600ce6c9a tools/blastxml_to_top_descr/repository_dependencies.xml --- a/tools/blastxml_to_top_descr/repository_dependencies.xml Fri Nov 09 11:59:43 2018 -0500 +++ b/tools/blastxml_to_top_descr/repository_dependencies.xml Fri Feb 22 09:56:23 2019 -0500 |
b |
@@ -1,4 +1,4 @@ -<?xml version="1.0"?> +<?xml version="1.0" ?> <repositories description="Requires BLAST XML and database datatype definitions."> -<repository changeset_revision="3eada762af11" name="blast_datatypes" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu" /> -</repositories> + <repository changeset_revision="1250aab8b97a" name="blast_datatypes" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu"/> +</repositories> \ No newline at end of file |