Mercurial > repos > bgruening > split_file_on_column

changeset 0:f30aca50efbb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/split_file_on_column commit 36d05738e78c68091b45779624734e6a47829856-dirty
author bgruening
date Wed, 26 Aug 2015 07:31:55 -0400
parents
children b1914e537f3e
files split_file_on_column.tar.gz split_file_on_column.xml test-data/5cols.tabular tool_dependencies.xml
diffstat 4 files changed, 85 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
Binary file split_file_on_column.tar.gz has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/split_file_on_column.xml	Wed Aug 26 07:31:55 2015 -0400
@@ -0,0 +1,74 @@
+<tool id="tp_split_on_column" name="Split file" version="0.2">
+    <description>according to the values of a column</description>
+    <requirements>
+        <requirement type="package" version="4.1.0">gnu_awk</requirement>
+    </requirements>
+    <command>
+<![CDATA[
+        awk -F'\t' '{print > \$$column ".$infile.ext" }' $infile
+]]>
+    </command>
+    <inputs>
+        <param format="tabular" name="infile" type="data" label="File to select" />
+        <param name="column" label="on column" type="data_column" data_ref="infile" accept_default="true" />
+    </inputs>
+    <outputs>
+        <collection name="split_output" type="list" label="Table split on first column">
+            <discover_datasets pattern="__name_and_ext__" directory="." />
+        </collection>
+    </outputs>
+    <!--outputs>
+        <data format="input" name="outfile" metadata_source="infile" label="${tool.name} on ${on_string}"/>
+    </outputs-->
+    <tests>
+        <test>
+            <param name="infile" value="5cols.tabular" ftype="tabular"/>
+            <param name="column" value="5" />
+            <output_collection name="split_output" type="list">
+                <element name="1">
+                    <assert_contents>
+                        <has_text_matching expression="chr7\t56632\t56652\tcluster\t1" />
+                    </assert_contents>
+                </element>
+                <element name="2">
+                    <assert_contents>
+                        <has_text_matching expression="chr7\t56761\t56781\tcluster\t2" />
+                    </assert_contents>
+                </element>
+            </output_collection>
+        </test>
+    </tests>
+    <help>
+<![CDATA[
+
+**What it does**
+
+This tool splits a file into different smaller files using a specific column.
+It will work like the group tool, but every group is saved to its own file.
+
+-----
+
+**Example**
+
+Splitting on column 5 from this::
+
+    chr7  56632  56652  cluster 1
+    chr7  56736  56756  cluster 1
+    chr7  56761  56781  cluster 2
+    chr7  56772  56792  cluster 2
+    chr7  56775  56795  cluster 2
+
+will produce 2 files with different clusters::
+
+    chr7  56632  56652  cluster 1
+    chr7  56736  56756  cluster 1
+
+
+    chr7  56761  56781  cluster 2
+    chr7  56772  56792  cluster 2
+    chr7  56775  56795  cluster 2
+
+
+]]>
+    </help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/5cols.tabular	Wed Aug 26 07:31:55 2015 -0400
@@ -0,0 +1,5 @@
+chr7	56632	56652	cluster	1
+chr7	56736	56756	cluster	1
+chr7	56761	56781	cluster	2
+chr7	56772	56792	cluster	2
+chr7	56775	56795	cluster	2
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed Aug 26 07:31:55 2015 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="gnu_awk" version="4.1.0">
+        <repository changeset_revision="440a5170003f" name="package_gnu_awk_4_1_0" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>