Mercurial > repos > earlhaminst > hcluster_sg_parser
changeset 4:02d73e6ca869 draft
planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/hcluster_sg_parser commit e35f2ea026b79daaced9a2a50da02b4881d6154b
| author | earlhaminst |
|---|---|
| date | Fri, 19 Jul 2019 11:44:07 -0400 |
| parents | f9e418125021 |
| children | 07f5b2c5ac10 |
| files | hcluster_sg_parser.py hcluster_sg_parser.xml test-data/hcluster_sg1.tabular test-data/hcluster_sg1.txt |
| diffstat | 4 files changed, 38 insertions(+), 30 deletions(-) [+] |
line wrap: on
line diff
--- a/hcluster_sg_parser.py Fri Apr 28 12:51:35 2017 -0400 +++ b/hcluster_sg_parser.py Fri Jul 19 11:44:07 2019 -0400 @@ -17,20 +17,23 @@ parser.add_option('-M', '--max', type='int', default=sys.maxsize, help='Maximum number of cluster elements') options, args = parser.parse_args() - with open(args[1], 'w') as discarded_out: - with open(args[0]) as fh: - for line in fh: - line = line.rstrip() - line_cols = line.split('\t') - cluster_id = line_cols[0] - n_ids = int(line_cols[-2]) - id_list = line_cols[-1].replace(',', '\n') - if n_ids >= options.min and n_ids <= options.max: - outfile = cluster_id + '_output.txt' - with open(outfile, 'w') as f: - f.write(id_list) - else: - discarded_out.write(id_list) + with open(args[2], 'w') as discarded_max_out: + with open(args[1], 'w') as discarded_min_out: + with open(args[0]) as fh: + for line in fh: + line = line.rstrip() + line_cols = line.split('\t') + cluster_id = line_cols[0] + n_ids = int(line_cols[-2]) + id_list = line_cols[-1].replace(',', '\n') + if n_ids < options.min: + discarded_min_out.write(id_list) + elif n_ids > options.max: + discarded_max_out.write(id_list) + else: + outfile = cluster_id + '_output.txt' + with open(outfile, 'w') as f: + f.write(id_list) if __name__ == "__main__":
--- a/hcluster_sg_parser.xml Fri Apr 28 12:51:35 2017 -0400 +++ b/hcluster_sg_parser.xml Fri Jul 19 11:44:07 2019 -0400 @@ -1,4 +1,4 @@ -<tool id="hcluster_sg_parser" name="hcluster_sg parser" version="0.2.0"> +<tool id="hcluster_sg_parser" name="hcluster_sg parser" version="0.2.1"> <description>converts hcluster_sg 3-column output into lists of IDs</description> <command detect_errors="exit_code"> <![CDATA[ @@ -9,7 +9,8 @@ #if str($max_elems) -M $max_elems #end if -'$discarded' +'$discarded_min' +'$discarded_max' ]]> </command> <inputs> @@ -21,7 +22,8 @@ <collection name="ids_lists" type="list" label="${tool.name} on ${on_string}"> <discover_datasets pattern="(?P<designation>.+)_output\.txt" ext="txt" /> </collection> - <data name="discarded" format="txt" label="${tool.name} on ${on_string}: discarded IDs" /> + <data name="discarded_min" format="txt" label="${tool.name} on ${on_string}: discarded IDs less than specified" /> + <data name="discarded_max" format="txt" label="${tool.name} on ${on_string}: discarded IDs more than specified" /> </outputs> <tests> <test> @@ -32,7 +34,8 @@ <element name="2" file="2_output.txt" ftype="txt" /> <element name="3" file="3_output.txt" ftype="txt" /> </output_collection> - <output name="discarded" file="empty.txt" /> + <output name="discarded_min" file="empty.txt" /> + <output name="discarded_max" file="empty.txt" /> </test> <test> <param name="inputFile" ftype="tabular" value="hcluster_sg.tabular" /> @@ -41,10 +44,11 @@ <element name="0" file="0_output.txt" ftype="txt" /> <element name="1" file="1_output.txt" ftype="txt" /> </output_collection> - <output name="discarded" file="discarded.txt" /> + <output name="discarded_min" file="discarded.txt" /> + <output name="discarded_max" file="empty.txt" /> </test> <test> - <param name="inputFile" ftype="tabular" value="hcluster_sg1.txt" /> + <param name="inputFile" ftype="tabular" value="hcluster_sg1.tabular" /> <output_collection name="ids_lists" type="list"> <element name="0" file="hcluster_sg1_0_output.txt" ftype="txt" /> <element name="1" file="hcluster_sg1_1_output.txt" ftype="txt" /> @@ -56,7 +60,8 @@ <element name="7" file="hcluster_sg1_7_output.txt" ftype="txt" /> <element name="8" file="hcluster_sg1_8_output.txt" ftype="txt" /> </output_collection> - <output name="discarded" file="empty.txt" /> + <output name="discarded_min" file="empty.txt" /> + <output name="discarded_max" file="empty.txt" /> </test> </tests> <help>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1.tabular Fri Jul 19 11:44:07 2019 -0400 @@ -0,0 +1,9 @@ +0 0 57 1.000 0 13 11,0,4,3,5,12,7,10,13,2,1,6,9, +1 0 23 0.671 0 46 45,39,71,83,49,61,64,38,25,72,44,29,90,35,30,28,62,65,63,88,89,34,82,73,52,74,17,55,41,56,59,51,32,33,87,31,85,27,48,66,50,37,60,77,26,54, +2 0 0 1.000 0 1 84, +3 0 33 1.000 0 8 101,96,92,98,94,100,91,99, +4 0 28 1.000 0 4 40,43,76,42, +5 0 0 1.000 0 1 8, +6 0 54 1.000 0 8 18,23,21,15,22,20,14,16, +7 0 15 0.596 0 17 24,95,58,69,78,36,68,70,57,67,97,79,53,47,75,86,46, +8 0 0 1.000 0 1 102,
--- a/test-data/hcluster_sg1.txt Fri Apr 28 12:51:35 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,9 +0,0 @@ -0 0 57 1.000 0 13 11,0,4,3,5,12,7,10,13,2,1,6,9, -1 0 23 0.671 0 46 45,39,71,83,49,61,64,38,25,72,44,29,90,35,30,28,62,65,63,88,89,34,82,73,52,74,17,55,41,56,59,51,32,33,87,31,85,27,48,66,50,37,60,77,26,54, -2 0 0 1.000 0 1 84, -3 0 33 1.000 0 8 101,96,92,98,94,100,91,99, -4 0 28 1.000 0 4 40,43,76,42, -5 0 0 1.000 0 1 8, -6 0 54 1.000 0 8 18,23,21,15,22,20,14,16, -7 0 15 0.596 0 17 24,95,58,69,78,36,68,70,57,67,97,79,53,47,75,86,46, -8 0 0 1.000 0 1 102,