Mercurial > repos > devteam > join

changeset 4:a10f49d9218a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/gops/join commit cae3e05d02e60f595bb8b6d77a84f030e9bd1689
author devteam
date Thu, 22 Jun 2017 18:52:36 -0400
parents ffbd1de29c28
children 718d04143c31
files gops_join.py join.xml macros.xml operation_filter.py tool_dependencies.xml
diffstat 5 files changed, 111 insertions(+), 106 deletions(-) [+]
line wrap: on
line diff
--- a/gops_join.py	Wed Nov 11 12:48:58 2015 -0500
+++ b/gops_join.py	Thu Jun 22 18:52:36 2017 -0400
@@ -8,11 +8,14 @@
     -m, --mincols=N: Require this much overlap (default 1bp)
     -f, --fill=N: none, right, left, both
 """
+from __future__ import print_function
+
 import fileinput
 import sys
+
+from bx.cookbook import doc_optparse
 from bx.intervals.io import NiceReaderWrapper
 from bx.intervals.operations.join import join
-from bx.cookbook import doc_optparse
 from bx.tabular.io import ParseError
 from galaxy.tools.util.galaxyops import fail, parse_cols_arg, skipped
 
@@ -61,7 +64,7 @@
                 out_file.write( "%s\n" % "\t".join( outfields ) )
             else:
                 out_file.write( "%s\n" % outfields )
-    except ParseError, exc:
+    except ParseError as exc:
         out_file.close()
         fail( "Invalid file format: %s" % str( exc ) )
     except MemoryError:
@@ -71,9 +74,10 @@
     out_file.close()
 
     if g1.skipped > 0:
-        print skipped( g1, filedesc=" of 1st dataset" )
+        print(skipped( g1, filedesc=" of 1st dataset" ))
     if g2.skipped > 0:
-        print skipped( g2, filedesc=" of 2nd dataset" )
+        print(skipped( g2, filedesc=" of 2nd dataset" ))
+
 
 if __name__ == "__main__":
     main()
--- a/join.xml	Wed Nov 11 12:48:58 2015 -0500
+++ b/join.xml	Thu Jun 22 18:52:36 2017 -0400
@@ -1,98 +1,92 @@
 <tool id="gops_join_1" name="Join" version="1.0.0">
-  <description>the intervals of two datasets side-by-side</description>
-  <requirements>
-    <requirement type="package" version="0.7.1">bx-python</requirement>
-    <requirement type="package" version="1.0.0">galaxy-ops</requirement>
-  </requirements>
-  <command interpreter="python">gops_join.py $input1 $input2 $output -1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol} -2 ${input2.metadata.chromCol},${input2.metadata.startCol},${input2.metadata.endCol},${input2.metadata.strandCol} -m $min -f $fill</command>
-  <inputs>
-    <param format="interval" name="input1" type="data" help="First dataset">
-      <label>Join</label>
-    </param>
-    <param format="interval" name="input2" type="data" help="Second dataset">
-      <label>with</label>
-    </param>
-    <param name="min" type="integer" value="1" help="(bp)">
-      <label>with min overlap</label>
-    </param>
-  <param name="fill" type="select" label="Return">
-    <option value="none">Only records that are joined (INNER JOIN)</option>
-    <option value="right">All records of first dataset (fill null with ".")</option>
-    <option value="left">All records of second dataset (fill null with ".")</option>
-    <option value="both">All records of both datasets (fill nulls with ".")</option>
-  </param>
-   </inputs>
-  <outputs>
-    <data format="interval" name="output" metadata_source="input1" />
-  </outputs>
-  <code file="operation_filter.py"/>
-  <tests>
-    <test>
-      <param name="input1" value="1.bed" />
-      <param name="input2" value="2.bed" />
-      <param name="min" value="1" />
-      <param name="fill" value="none" />
-      <output name="output" file="gops-join-none.dat" />
-    </test>
-    <test>
-      <param name="input1" value="1.bed" />
-      <param name="input2" value="2.bed" />
-      <param name="min" value="1" />
-      <param name="fill" value="right" />
-      <output name="output" file="gops-join-right.dat" />
-    </test>
-    <test>
-      <param name="input1" value="1.bed" />
-      <param name="input2" value="2.bed" />
-      <param name="min" value="1" />
-      <param name="fill" value="left" />
-      <output name="output" file="gops-join-left.dat" />
-    </test>
-    <test>
-      <param name="input1" value="1.bed" />
-      <param name="input2" value="2.bed" />
-      <param name="min" value="1" />
-      <param name="fill" value="both" />
-      <output name="output" file="gops-join-both.dat" />
-    </test>
-    <test>
-      <param name="input1" value="1.bed" />
-      <param name="input2" value="2.bed" />
-      <param name="min" value="500" />
-      <param name="fill" value="none" />
-      <output name="output" file="gops-join-none-500.dat" />
-    </test>
-    <test>
-      <param name="input1" value="1.bed" />
-      <param name="input2" value="2.bed" />
-      <param name="min" value="100" />
-      <param name="fill" value="both" />
-      <output name="output" file="gops-join-both-100.dat" />
-    </test>
-  </tests>
-  <help>
-
+    <description>the intervals of two datasets side-by-side</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <code file="operation_filter.py"/>
+    <command><![CDATA[
+python '$__tool_directory__/gops_join.py'
+'$input1'
+'$input2'
+'$output'
+-1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol}
+-2 ${input2.metadata.chromCol},${input2.metadata.startCol},${input2.metadata.endCol},${input2.metadata.strandCol}
+-m $min
+-f $fill
+    ]]></command>
+    <inputs>
+        <param name="input1" type="data" format="interval" label="Join" help="First dataset" />
+        <param name="input2" type="data" format="interval" label="With" help="Second dataset" />
+        <param name="min" type="integer" value="1" label="With min overlap" help="(bp)" />
+        <param name="fill" type="select" label="Return">
+            <option value="none">Only records that are joined (INNER JOIN)</option>
+            <option value="right">All records of first dataset (fill null with ".")</option>
+            <option value="left">All records of second dataset (fill null with ".")</option>
+            <option value="both">All records of both datasets (fill nulls with ".")</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="output" format_source="input1" metadata_source="input1" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="input1" value="1.bed" />
+            <param name="input2" value="2.bed" />
+            <param name="min" value="1" />
+            <param name="fill" value="none" />
+            <output name="output" file="gops-join-none.dat" />
+        </test>
+        <test>
+            <param name="input1" value="1.bed" />
+            <param name="input2" value="2.bed" />
+            <param name="min" value="1" />
+            <param name="fill" value="right" />
+            <output name="output" file="gops-join-right.dat" />
+        </test>
+        <test>
+            <param name="input1" value="1.bed" />
+            <param name="input2" value="2.bed" />
+            <param name="min" value="1" />
+            <param name="fill" value="left" />
+            <output name="output" file="gops-join-left.dat" />
+        </test>
+        <test>
+            <param name="input1" value="1.bed" />
+            <param name="input2" value="2.bed" />
+            <param name="min" value="1" />
+            <param name="fill" value="both" />
+            <output name="output" file="gops-join-both.dat" />
+        </test>
+        <test>
+            <param name="input1" value="1.bed" />
+            <param name="input2" value="2.bed" />
+            <param name="min" value="500" />
+            <param name="fill" value="none" />
+            <output name="output" file="gops-join-none-500.dat" />
+        </test>
+        <test>
+            <param name="input1" value="1.bed" />
+            <param name="input2" value="2.bed" />
+            <param name="min" value="100" />
+            <param name="fill" value="both" />
+            <output name="output" file="gops-join-both-100.dat" />
+        </test>
+    </tests>
+    <help><![CDATA[
 .. class:: infomark
 
 **TIP:** If your dataset does not appear in the pulldown menu, it means that it is not in interval format. Use "edit attributes" to set chromosome, start, end, and strand columns.
 
------
-
-**Screencasts!**
-
-See Galaxy Interval Operation Screencasts_ (right click to open this link in another window).
-
-.. _Screencasts: http://wiki.g2.bx.psu.edu/Learn/Interval%20Operations
-
------
+@SCREENCASTS@
 
 **Syntax**
 
 - **Where overlap** specifies the minimum overlap between intervals that allows them to be joined.
-- **Return only records that are joined** returns only the records of the first dataset that join to a record in the second dataset.  This is analogous to an INNER JOIN.
-- **Return all records of first dataset (fill null with &quot;.&quot;)** returns all intervals of the first dataset, and any intervals that do not join an interval from the second dataset are filled in with a period(.).  This is analogous to a LEFT JOIN.
-- **Return all records of second dataset (fill null with &quot;.&quot;)** returns all intervals of the second dataset, and any intervals that do not join an interval from the first dataset are filled in with a period(.).  **Note that this may produce an invalid interval file, since a period(.) is not a valid chrom, start, end or strand.**
-- **Return all records of both datasets (fill nulls with &quot;.&quot;)** returns all records from both datasets, and fills on either the right or left with periods.  **Note that this may produce an invalid interval file, since a period(.) is not a valid chrom, start, end or strand.**
+- **Return only records that are joined** returns only the records of the first dataset that join to a record in the second dataset. This is analogous to an INNER JOIN.
+- **Return all records of first dataset (fill null with &quot;.&quot;)** returns all intervals of the first dataset, and any intervals that do not join an interval from the second dataset are filled in with a period(.). This is analogous to a LEFT JOIN.
+- **Return all records of second dataset (fill null with &quot;.&quot;)** returns all intervals of the second dataset, and any intervals that do not join an interval from the first dataset are filled in with a period(.). **Note that this may produce an invalid interval file, since a period(.) is not a valid chrom, start, end or strand.**
+- **Return all records of both datasets (fill nulls with &quot;.&quot;)** returns all records from both datasets, and fills on either the right or left with periods. **Note that this may produce an invalid interval file, since a period(.) is not a valid chrom, start, end or strand.**
 
 -----
 
@@ -115,7 +109,5 @@
 All records of both datasets:
 
 .. image:: gops_joinFullOuter.gif
-
-
-</help>
+    ]]></help>
 </tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Thu Jun 22 18:52:36 2017 -0400
@@ -0,0 +1,20 @@
+<?xml version="1.0"?>
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="0.7.1">bx-python</requirement>
+            <requirement type="package" version="1.0.0">galaxy-ops</requirement>
+        </requirements>
+    </xml>
+    <token name="@SCREENCASTS@">
+-----
+
+**Screencasts!**
+
+See Galaxy Interval Operation Screencasts_ (right click to open this link in another window).
+
+.. _Screencasts: https://galaxyproject.org/learn/interval-operations/
+
+-----
+    </token>
+</macros>
--- a/operation_filter.py	Wed Nov 11 12:48:58 2015 -0500
+++ b/operation_filter.py	Thu Jun 22 18:52:36 2017 -0400
@@ -1,8 +1,7 @@
 # runs after the job (and after the default post-filter)
+from galaxy.jobs.handler import JOB_ERROR
 from galaxy.tools.parameters import DataToolParameter
 
-from galaxy.jobs.handler import JOB_ERROR
-
 # Older py compatibility
 try:
     set()
@@ -14,7 +13,7 @@
     dbkeys = set()
     data_param_names = set()
     data_params = 0
-    for name, param in page_param_map.iteritems():
+    for name, param in page_param_map.items():
         if isinstance( param, DataToolParameter ):
             # for each dataset parameter
             if param_values.get(name, None) is not None:
@@ -53,7 +52,6 @@
         try:
             if stderr and len( stderr ) > 0:
                 raise Exception( stderr )
-
         except Exception:
             data.blurb = JOB_ERROR
             data.state = JOB_ERROR
--- a/tool_dependencies.xml	Wed Nov 11 12:48:58 2015 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,9 +0,0 @@
-<?xml version="1.0"?>
-<tool_dependency>
-  <package name="bx-python" version="0.7.1">
-      <repository changeset_revision="2d0c08728bca" name="package_bx_python_0_7" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-    <package name="galaxy-ops" version="1.0.0">
-      <repository changeset_revision="9cbb20b85c01" name="package_galaxy_ops_1_0_0" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-</tool_dependency>