--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/FCStxtMergeDownsample.xml	Mon Jun 22 17:42:26 2020 -0400
@@ -0,0 +1,183 @@
+<tool id="fcstxt_merge_downsample" name="Merge and downsample" version="1.1+galaxy0">
+  <description>txt-converted FCS files into one text file based on headers</description>
+  <requirements>
+    <requirement type="package" version="0.17.1">pandas</requirement>
+  </requirements>
+  <stdio>
+    <exit_code range="2" level="fatal" description="Non-numeric data. See stderr for more details." />
+    <exit_code range="3" level="warning" description="Selected columns do not exist in all files" />
+    <exit_code range="4" level="fatal" description="Run aborted - too many errors" />
+    <exit_code range="6" level="fatal" description="Please provide integers for columns you want to merge on." />
+    <exit_code range="7" level="fatal" description="Please provide a comma separated list of integers for columns you want to merge on." />
+    <exit_code range="8" level="fatal" description="Please provide a numeric value [0,1] for the downsampling factor." />
+    <exit_code range="9" level="fatal" description="There are no columns in common to all files." />
+  </stdio>
+  <command><![CDATA[
+      python '$__tool_directory__/FCStxtMergeDownsample.py' -o '${output_file}' -d '${factorDS}'
+  #if $columns
+    -c '${columns}'
+  #end if
+  #for $f in $input
+    -i '${f}'
+  #end for
+  ]]>
+  </command>
+  <inputs>
+    <param format="flowtext,txt,tabular" name="input" type="data_collection" collection_type="list" label="Text files Collection"/>
+    <param name="factorDS" type="text" label="Downsample by:" value="i.e.:0.1 or 10%" optional="true" help="1 by default (no downsampling)."/>
+    <param name="columns" type="text" label="Merge columns:" value="i.e.:1,2,5" optional="true" help="By default, will merge on the columns in common to all files.">
+    </param>
+  </inputs>
+  <outputs>
+    <data format="flowtext" name="output_file" label="Merge flowtext on ${input.name}"/>
+  </outputs>
+  <tests>
+    <test>
+      <param name="input">
+        <collection type="list">
+          <element name="input1.txt" value="test1/input1.txt"/>
+          <element name="input2.txt" value="test1/input2.txt"/>
+          <element name="input3.txt" value="test1/input3.txt"/>
+        </collection>
+      </param>
+      <param name="factorDS" value=".8"/>
+      <param name="columns" value="i.e.:1,2,5"/>
+      <output name="output_file" file="merge1.flowtext" compare="sim_size"/>
+    </test>
+    <test>
+      <param name="input">
+        <collection type="list">
+          <element name="input1.txt" value="test2/input1.txt"/>
+          <element name="input2.txt" value="test2/input2.txt"/>
+          <element name="input3.txt" value="test2/input3.txt"/>
+        </collection>
+      </param>
+      <param name="factorDS" value="i.e.:0.1 or 10%"/>
+      <param name="columns" value="1,2,3"/>
+      <output name="output_file" file="merge2.flowtext" compare="sim_size"/>
+    </test>
+  </tests>
+  <help><![CDATA[
+   This tool downsamples and merges multiple txt-converted FCS files into one text file.
+
+-----
+
+**Input files**
+
+This tool requires collections of txt, flowtext or tabular files as input.
+
+**Downsampling**
+
+By default, files are not downsampled. If a downsampling factor is provided, each file in the input dataset collection will be downsampled randomly without replacement as follows:
+
+- If n is between 0 and 1, the size of the output will be n times that of the input files.
+- If n is between 1 and 100, the size of the output will be n% that of the input files.
+
+.. class:: infomark
+
+Downsampling is implemented such that each file will contribute an equal number of event to the aggregate.
+
+.. class:: warningmark
+
+At this time, up-sampling is not supported. If the number provided is greater than 100, the tool will exit.
+
+**Output file**
+
+The output flowtext file contains is a concatenation of the input files provided all data after the header contains only numbers. By default, only columns existing in all input files (as assessed by the header) are concatenated. The user can specify columns to merge, bypassing the headers check. If a downsampling factor is provided, the corresponding proportion of each input file ONLY will be read in (and checked for errors).
+
+.. class:: warningmark
+
+Potential errors are logged to stderr. If the number of errors reaches 10, the run will be aborted. If a file contains non-numeric data, the run will be aborted.
+
+.. class:: infomark
+
+Tip: Three tools in the Flow File Tools section can help prepare files for merging and/or downsampling:
+
+- Check headers tool provides a list of headers for all files in a collection of text, flowtext or tabular files.
+- Remove, rearrange and/or rename columns tool allows manipulation of the columns of a file or a set of files.
+- Check data tool identifies the lines in a file containing non-numeric data.
+
+-----
+
+**Example**
+
+*File1*::
+
+   Marker1 Marker2 Marker3
+   34      45      12
+   33      65      10
+   87      26      76
+   24      56      32
+   95      83      53
+   74      15      87
+   ...     ...     ...
+
+*File2*::
+
+   Marker4 Marker5 Marker3
+   19      62      98
+   12      36      58
+   41      42      68
+   76      74      53
+   62      34      45
+   93      21      76
+   ...     ...     ...
+
+*Output*
+
+.. class:: infomark
+
+If run without specifying the columns::
+
+   Marker3
+   12
+   10
+   76
+   32
+   53
+   87
+   98
+   58
+   68
+   53
+   45
+   76
+   ...
+
+.. class:: infomark
+
+If run specifying columns 1,2,3::
+
+   Marker1 Marker2 Marker3
+   34      45      12
+   33      65      10
+   87      26      76
+   24      56      32
+   95      83      53
+   74      15      87
+   19      62      98
+   12      36      58
+   41      42      68
+   76      74      53
+   62      34      45
+   93      21      76
+   ...     ...     ...
+
+.. class:: infomark
+
+If run specifying columns 1,2,3 and with a downsampling factor of 0.5::
+
+   Marker1 Marker2 Marker3
+   34      45      12
+   24      56      32
+   95      83      53
+   19      62      98
+   12      36      58
+   62      34      45
+   ...     ...     ...
+ ]]>
+  </help>
+  <citations>
+    <citation type="doi">10.1038/srep02327</citation>
+  </citations>
+</tool>