| Previous changeset 9:baabc30154cd (2023-11-23) |
|
Commit message:
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/split_file_to_collection commit 5d21f3d6a3a84b4737a2091ae0d772471eb389dd |
|
modified:
split_file_to_collection.py split_file_to_collection.xml |
|
added:
test-data/split_file_0.tabular test-data/split_file_1.tabular test-data/split_file_2.tabular test-data/split_file_3.tabular |
| b |
| diff -r baabc30154cd -r 2dae863c8f42 split_file_to_collection.py --- a/split_file_to_collection.py Thu Nov 23 20:02:01 2023 +0000 +++ b/split_file_to_collection.py Thu May 23 15:03:47 2024 +0000 |
| b |
| @@ -329,6 +329,8 @@ else: record += line # after loop, write final record to file + if new_file_counter in fresh_files: + new_file.write(header) new_file.write(record) new_file.close() |
| b |
| diff -r baabc30154cd -r 2dae863c8f42 split_file_to_collection.xml --- a/split_file_to_collection.xml Thu Nov 23 20:02:01 2023 +0000 +++ b/split_file_to_collection.xml Thu May 23 15:03:47 2024 +0000 |
| [ |
| b'@@ -1,4 +1,4 @@\n-<tool id="split_file_to_collection" name="Split file" version="0.5.1">\n+<tool id="split_file_to_collection" name="Split file" version="0.5.2">\n <description>to dataset collection</description>\n <macros>\n <xml name="regex_sanitizer">\n@@ -190,38 +190,38 @@\n </conditional>\n </inputs>\n <outputs>\n- <collection name="list_output_tab" type="list" label="${tool.name} on ${on_string}">\n+ <collection name="list_output_tab" type="list" label="${tool.name} on ${on_string}: tabular">\n <discover_datasets pattern="__name__" directory="out" visible="false" format="tabular"/>\n <filter>split_parms[\'select_ftype\'] == "tabular"</filter>\n </collection>\n- <collection name="list_output_mgf" type="list" label="${tool.name} on ${on_string}">\n+ <collection name="list_output_mgf" type="list" label="${tool.name} on ${on_string}: mgf">\n <discover_datasets pattern="__name__" directory="out" visible="false" format="mgf"/>\n <filter>split_parms[\'select_ftype\'] == "mgf"</filter>\n </collection>\n- <collection name="list_output_fasta" type="list" label="${tool.name} on ${on_string}">\n+ <collection name="list_output_fasta" type="list" label="${tool.name} on ${on_string}: fasta">\n <discover_datasets pattern="__name__" directory="out" visible="false" format="fasta"/>\n <filter>split_parms[\'select_ftype\'] == "fasta"</filter>\n </collection>\n- <collection name="list_output_fastq" type="list" label="${tool.name} on ${on_string}">\n+ <collection name="list_output_fastq" type="list" label="${tool.name} on ${on_string}: fastq">\n <discover_datasets pattern="__name__" directory="out" visible="false" format="fastq"/>\n <filter>split_parms[\'select_ftype\'] == "fastq"</filter>\n </collection>\n- <collection name="list_output_sdf" type="list" label="${tool.name} on ${on_string}">\n+ <collection name="list_output_sdf" type="list" label="${tool.name} on ${on_string}: sdf">\n <discover_datasets pattern="__name__" directory="out" visible="false" format="sdf"/>\n <filter>split_parms[\'select_ftype\'] == "sdf"</filter>\n </collection>\n- <collection name="list_output_txt" type="list" label="${tool.name} on ${on_string}">\n+ <collection name="list_output_txt" type="list" label="${tool.name} on ${on_string}: txt">\n <discover_datasets pattern="__name__" directory="out" visible="false" format="txt"/>\n <filter>split_parms[\'select_ftype\'] == "txt"</filter>\n </collection>\n- <collection name="list_output_generic" type="list" label="${tool.name} on ${on_string}">\n+ <collection name="list_output_generic" type="list" label="${tool.name} on ${on_string}: generic">\n <discover_datasets pattern="__name_and_ext__" directory="out" visible="false"/>\n <filter>split_parms[\'select_ftype\'] == "generic"</filter>\n </collection>\n </outputs>\n <tests>\n <!-- 1 -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="test.tabular" ftype="tabular"/>\n <param name="select_ftype" value="tabular"/>\n <param name="select_split_by" value="col"/>\n@@ -236,7 +236,7 @@\n </output_collection>\n </test>\n <!-- 2 -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="test.tabular" ftype="tabular"/>\n <param name="select_ftype" value="tabular"/>\n <param name="select_split_by" value="row"/>\n@@ -250,7 +250,7 @@\n </output_collection>\n </test>\n <!-- 3 -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="test.tabular" ftype="tabular"/>\n <param name="select_ftype" value="tabular"/>\n <param name="select_split_by" valu'..b'="test.fasta" ftype="fasta"/>\n <param name="select_ftype" value="fasta"/>\n <param name="mode" value="numnew"/>\n@@ -411,7 +411,7 @@\n </output_collection>\n </test>\n <!-- splitting of fasta w batch assignment and specific filename prefix -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="test.fasta" ftype="fasta"/>\n <param name="select_ftype" value="fasta"/>\n <param name="mode" value="numnew"/>\n@@ -424,7 +424,7 @@\n </output_collection>\n </test>\n <!-- splitting of txt w default (alternating assignment) -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="test.tabular" ftype="txt"/>\n <param name="select_ftype" value="txt"/>\n <param name="mode" value="numnew"/>\n@@ -436,7 +436,7 @@\n </output_collection>\n </test>\n <!-- generic-regex splitting (of txt) w default assignement (alternating) -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="test.tabular" ftype="txt"/>\n <param name="select_ftype" value="generic"/>\n <param name="select_split_method" value="regex"/>\n@@ -450,7 +450,7 @@\n </output_collection>\n </test>\n <!-- generic-regex splitting (of a fasta) w random assignment -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="test.fasta" ftype="fasta"/>\n <param name="select_ftype" value="generic"/>\n <param name="select_split_method" value="regex"/>\n@@ -466,7 +466,7 @@\n </output_collection>\n </test>\n <!-- sdf + specify desired number of files -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="3_molecules.sdf" ftype="sdf"/>\n <param name="select_ftype" value="sdf"/>\n <param name="mode" value="numnew"/>\n@@ -480,7 +480,7 @@\n </output_collection>\n </test>\n <!-- sdf + specify desired number of records per file (chunksize) -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="3_molecules.sdf" ftype="sdf"/>\n <param name="select_ftype" value="sdf"/>\n <param name="mode" value="chunk"/>\n@@ -494,7 +494,7 @@\n </output_collection>\n </test>\n <!-- test split_after (by splitting fasta files after non-header lines) -->\n- <test>\n+ <test expect_num_outputs="1">\n <param name="input" value="test.fasta" ftype="fasta"/>\n <param name="select_ftype" value="generic"/>\n <param name="select_split_method" value="regex"/>\n@@ -510,6 +510,21 @@\n <element name="rand_000001" file="rand_1.fasta" ftype="fasta"/>\n </output_collection>\n </test>\n+ <test expect_num_outputs="1">\n+ <param name="input" value="test.tabular" ftype="tabular"/>\n+ <param name="select_ftype" value="tabular"/>\n+ <param name="select_split_by" value="row"/>\n+ <param name="top" value="2"/>\n+ <param name="mode" value="chunk"/>\n+ <param name="chunksize" value="1"/>\n+ <param name="allocate" value="batch"/>\n+ <output_collection name="list_output_tab" type="list">\n+ <element name="split_file_000000.tabular" file="split_file_0.tabular" ftype="tabular"/>\n+ <element name="split_file_000001.tabular" file="split_file_1.tabular" ftype="tabular"/>\n+ <element name="split_file_000002.tabular" file="split_file_2.tabular" ftype="tabular"/>\n+ <element name="split_file_000003.tabular" file="split_file_3.tabular" ftype="tabular"/>\n+ </output_collection>\n+ </test>\n </tests>\n <help><![CDATA[\n **Split file into a dataset collection**\n' |
| b |
| diff -r baabc30154cd -r 2dae863c8f42 test-data/split_file_0.tabular --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/split_file_0.tabular Thu May 23 15:03:47 2024 +0000 |
| b |
| @@ -0,0 +1,3 @@ +#This is a file +#file data +foo.mgf bar |
| b |
| diff -r baabc30154cd -r 2dae863c8f42 test-data/split_file_1.tabular --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/split_file_1.tabular Thu May 23 15:03:47 2024 +0000 |
| b |
| @@ -0,0 +1,3 @@ +#This is a file +#file data +foo2.mgf bar2 |
| b |
| diff -r baabc30154cd -r 2dae863c8f42 test-data/split_file_2.tabular --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/split_file_2.tabular Thu May 23 15:03:47 2024 +0000 |
| b |
| @@ -0,0 +1,3 @@ +#This is a file +#file data +foo3.mgf bar3 |
| b |
| diff -r baabc30154cd -r 2dae863c8f42 test-data/split_file_3.tabular --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/split_file_3.tabular Thu May 23 15:03:47 2024 +0000 |
| b |
| @@ -0,0 +1,3 @@ +#This is a file +#file data +foo.mgf bar4 |