Files
galaxy/tools/filters/joiner.xml
T
2020-02-19 13:13:08 -05:00

227 lines
9.2 KiB
XML

<tool id="join1" name="Join two Datasets" version="2.1.3">
<description>side by side on a specified field</description>
<requirements>
<requirement type="package" version="19.9.0">galaxy-util</requirement>
</requirements>
<command detect_errors="aggressive">
python '$__tool_directory__/join.py' '$input1' '$input2' $field1 $field2 '$out_file1' $unmatched $partial --index_depth=3 --buffer=50000000 --fill_options_file=$fill_options_file $header
</command>
<configfiles>
<configfile name="fill_options_file"><![CDATA[<%
import json
%>
#set $__fill_options = {}
#if $fill_empty_columns['fill_empty_columns_switch'] == 'fill_empty':
#set $__fill_options['fill_unjoined_only'] = $fill_empty_columns['fill_columns_by'].value == 'fill_unjoined_only'
#if $fill_empty_columns['do_fill_empty_columns']['column_fill_type'] == 'single_fill_value':
#set $__start_fill = $fill_empty_columns['do_fill_empty_columns']['fill_value'].value
#else:
#set $__start_fill = ""
#end if
#set $__fill_options['file1_columns'] = [ __start_fill for i in range( int( $input1.metadata.columns ) ) ]
#set $__fill_options['file2_columns'] = [ __start_fill for i in range( int( $input2.metadata.columns ) ) ]
#if $fill_empty_columns['do_fill_empty_columns']['column_fill_type'] == 'fill_value_by_column':
#for column_fill1 in $fill_empty_columns['do_fill_empty_columns']['column_fill1']:
#set $__fill_options['file1_columns'][ int( column_fill1['column_number1'].value ) - 1 ] = column_fill1['fill_value1'].value
#end for
#for column_fill2 in $fill_empty_columns['do_fill_empty_columns']['column_fill2']:
#set $__fill_options['file2_columns'][ int( column_fill2['column_number2'].value ) - 1 ] = column_fill2['fill_value2'].value
#end for
#end if
#end if
${json.dumps( __fill_options )}
]]></configfile>
</configfiles>
<inputs>
<param format="tabular" name="input1" type="data" label="Join"/>
<param name="field1" label="using column" type="data_column" data_ref="input1" />
<param format="tabular" name="input2" type="data" label="with" />
<param name="field2" label="and column" type="data_column" data_ref="input2" />
<param name="unmatched" type="select" label="Keep lines of first input that do not join with second input">
<option value="-u">Yes</option>
<option value="" selected="true">No</option>
</param>
<param name="partial" type="select" label="Keep lines of first input that are incomplete">
<option value="-p">Yes</option>
<option value="" selected="true">No</option>
</param>
<conditional name="fill_empty_columns">
<param name="fill_empty_columns_switch" type="select" label="Fill empty columns">
<option value="no_fill" selected="True">No</option>
<option value="fill_empty">Yes</option>
</param>
<when value="no_fill">
<!-- do nothing -->
</when>
<when value="fill_empty">
<param type="select" name="fill_columns_by" label="Only fill unjoined rows">
<option value="fill_unjoined_only" selected="True">Yes</option>
<option value="fill_all">No</option>
</param>
<conditional name="do_fill_empty_columns">
<param name="column_fill_type" type="select" label="Fill Columns by">
<option value="single_fill_value" selected="True">Single fill value</option>
<option value="fill_value_by_column">Values by column</option>
</param>
<when value="single_fill_value">
<param type="text" name="fill_value" label="Fill value" value="."/>
</when>
<when value="fill_value_by_column">
<repeat name="column_fill1" title="Fill Column for Input 1">
<param name="column_number1" label="Column" type="data_column" data_ref="input1" />
<param type="text" name="fill_value1" value="."/>
</repeat>
<repeat name="column_fill2" title="Fill Column for Input 2">
<param name="column_number2" label="Column" type="data_column" data_ref="input2" />
<param type="text" name="fill_value2" value="."/>
</repeat>
</when>
</conditional>
</when>
</conditional>
<param name="header" type="select" label="Keep the header lines">
<option value="-H">Yes</option>
<option value="" selected="true">No</option>
</param>
</inputs>
<outputs>
<data format="tabular" name="out_file1" />
</outputs>
<tests>
<test>
<param name="input1" value="1.bed"/>
<param name="input2" value="2.bed"/>
<param name="field1" value="2"/>
<param name="field2" value="2"/>
<param name="unmatched" value=""/>
<param name="partial" value=""/>
<param name="fill_empty_columns_switch" value="no_fill"/>
<output name="out_file1" file="joiner_out1.bed"/>
</test>
<test>
<param name="input1" value="1.bed"/>
<param name="input2" value="2.bed"/>
<param name="field1" value="2"/>
<param name="field2" value="2"/>
<param name="unmatched" value="Yes"/>
<param name="partial" value="Yes"/>
<param name="fill_empty_columns_switch" value="no_fill"/>
<output name="out_file1" file="joiner_out2.bed"/>
</test>
<test>
<param name="input1" value="1.bed"/>
<param name="input2" value="2.bed"/>
<param name="field1" value="2"/>
<param name="field2" value="2"/>
<param name="unmatched" value="Yes"/>
<param name="partial" value="Yes"/>
<param name="fill_empty_columns_switch" value="fill_empty"/>
<param name="fill_columns_by" value="fill_all"/>
<param name="column_fill_type" value="single_fill_value"/>
<param name="fill_value" value="~"/>
<output name="out_file1" file="joiner_out3.bed"/>
</test>
<test>
<param name="input1" value="1.bed"/>
<param name="input2" value="2.bed"/>
<param name="field1" value="2"/>
<param name="field2" value="2"/>
<param name="unmatched" value="Yes"/>
<param name="partial" value="Yes"/>
<param name="fill_empty_columns_switch" value="fill_empty"/>
<param name="fill_columns_by" value="fill_all"/>
<param name="column_fill_type" value="fill_value_by_column"/>
<param name="column_number1" value="6"/>
<param name="fill_value1" value="+"/>
<param name="column_number2" value="1"/>
<param name="fill_value2" value="NoChrom"/>
<output name="out_file1" file="joiner_out4.bed"/>
</test>
<test>
<param name="input1" value="joiner_header_in1.tab"/>
<param name="input2" value="joiner_header_in2.tab"/>
<param name="field1" value="4"/>
<param name="field2" value="1"/>
<param name="unmatched" value=""/>
<param name="partial" value=""/>
<param name="header" value="-H"/>
<param name="fill_empty_columns_switch" value="no_fill"/>
<output name="out_file1" file="joiner_out5.tab"/>
</test>
<test>
<param name="input1" value="joiner_header_in1.tab"/>
<param name="input2" value="joiner_header_in2.tab"/>
<param name="field1" value="4"/>
<param name="field2" value="1"/>
<param name="unmatched" value="Yes"/>
<param name="partial" value="Yes"/>
<param name="header" value="-H"/>
<param name="fill_empty_columns_switch" value="fill_empty"/>
<param name="fill_columns_by" value="fill_all"/>
<param name="column_fill_type" value="single_fill_value"/>
<param name="fill_value" value="."/>
<output name="out_file1" file="joiner_out6.tab"/>
</test>
<test>
<param name="input1" value="joiner_header_in1.tab"/>
<param name="input2" value="joiner_header_in2.tab"/>
<param name="field1" value="4"/>
<param name="field2" value="1"/>
<param name="unmatched" value=""/>
<param name="partial" value=""/>
<param name="header" value=""/>
<param name="fill_empty_columns_switch" value="no_fill"/>
<output name="out_file1" file="joiner_out7.tab"/>
</test>
</tests>
<help><![CDATA[
.. class:: warningmark
**This tool will force the ouput datatype to tabular.** To change metadata assignments click on the "edit attributes" link of the history item generated by this tool.
.. class:: infomark
**TIP:** If your data is not TAB delimited, use *Text Manipulation->Convert*
-----
**Syntax**
This tool joins lines of two datasets on a common field. An empty string ("") is not a valid identifier.
You may choose to include lines of your first input that do not join with your second input.
- Columns are referenced with a **number**. For example, **3** refers to the 3rd column of a tab-delimited file.
-----
**Example**
Dataset1::
chr1 10 20 geneA
chr1 50 80 geneB
chr5 10 40 geneL
Dataset2::
geneA tumor-supressor
geneB Foxp2
geneC Gnas1
geneE INK4a
Joining the 4th column of Dataset1 with the 1st column of Dataset2 will yield::
chr1 10 20 geneA geneA tumor-suppressor
chr1 50 80 geneB geneB Foxp2
Joining the 4th column of Dataset1 with the 1st column of Dataset2, while keeping all lines from Dataset1, will yield::
chr1 10 20 geneA geneA tumor-suppressor
chr1 50 80 geneB geneB Foxp2
chr5 10 40 geneL
]]></help>
<citations></citations>
</tool>