From c2f8ee5fc0f13e66d006f15f584efb2f52e13b9c Mon Sep 17 00:00:00 2001
From: Jeremy Goecks <jeremy.goecks@emory.edu>
Date: Thu, 7 Feb 2013 14:46:49 -0500
Subject: [PATCH] Subtract query tool: make ignoring empty end columns and
 whitespace optional.

---
 tools/new_operations/subtract_query.py  | 18 +++++++++++-------
 tools/new_operations/subtract_query.xml | 20 ++++++++++++++++++--
 2 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/tools/new_operations/subtract_query.py b/tools/new_operations/subtract_query.py
index 65ccf04867e..b06440dd0ea 100644
--- a/tools/new_operations/subtract_query.py
+++ b/tools/new_operations/subtract_query.py
@@ -3,7 +3,8 @@
 
 """
 Subtract an entire query from another query
-usage: %prog in_file_1 in_file_2 begin_col end_col output 
+usage: %prog in_file_1 in_file_2 begin_col end_col output
+    --ignore-empty-end-cols: ignore empty end columns when subtracting
 """
 import sys, re
 from galaxy import eggs
@@ -18,7 +19,7 @@ except:
 
 assert sys.version_info[:2] >= ( 2, 4 )
 
-def get_lines(fname, begin_col='', end_col=''):
+def get_lines(fname, begin_col='', end_col='', ignore_empty_end_cols=False):
     lines = set([])
     i = 0
     for i, line in enumerate(file(fname)):
@@ -29,12 +30,15 @@ def get_lines(fname, begin_col='', end_col=''):
                 try:
                     line = line.split('\t')
                     line = '\t'.join([line[j] for j in range(begin_col-1, end_col)])
-                    # removing empty fields, we do not compare empty fields at the end of a line.
-                    line = line.rstrip()
+                    if ignore_empty_end_cols:
+                        # removing empty fields, we do not compare empty fields at the end of a line.
+                        line = line.rstrip()
                     lines.add( line )
                 except: pass
             else:
-                line = line.rstrip()
+                if ignore_empty_end_cols:
+                    # removing empty fields, we do not compare empty fields at the end of a line.
+                    line = line.rstrip()
                 lines.add( line )
     if i: return (i+1, lines)
     else: return (i, lines)
@@ -83,9 +87,9 @@ def main():
     lines1 is the set of unique lines in inp1_file
     diff1 is the number of duplicate lines removed from inp1_file
     """
-    len1, lines1 = get_lines(inp1_file, begin_col, end_col)
+    len1, lines1 = get_lines(inp1_file, begin_col, end_col, options.ignore_empty_end_cols)
     diff1 = len1 - len(lines1)
-    len2, lines2 = get_lines(inp2_file, begin_col, end_col)
+    len2, lines2 = get_lines(inp2_file, begin_col, end_col, options.ignore_empty_end_cols)
     
     lines1.difference_update(lines2)
     """lines1 is now the set of unique lines in inp1_file - the set of unique lines in inp2_file"""
diff --git a/tools/new_operations/subtract_query.xml b/tools/new_operations/subtract_query.xml
index b751fce3fc6..a603ce144be 100644
--- a/tools/new_operations/subtract_query.xml
+++ b/tools/new_operations/subtract_query.xml
@@ -1,11 +1,18 @@
-<tool id="subtract_query1" name="Subtract Whole Dataset">
+<tool id="subtract_query1" name="Subtract Whole Dataset" version="0.1">
   <description>from another dataset</description>
-  <command interpreter="python">subtract_query.py $input1 $input2 $begin_col $end_col $output</command>
+  <command interpreter="python">
+    subtract_query.py $input1 $input2 $begin_col $end_col $output
+    #if str($ignore_empty_end_cols) == 'true':
+      --ignore-empty-end-cols
+    #end if
+
+  </command>
   <inputs>
     <param format="txt" name="input2" type="data" label="Subtract" help="Second dataset" />
     <param format="txt" name="input1" type="data" label="from" help="First dataset" />
     <param name="begin_col" type="data_column" data_ref="input1" force_select="False" label="Restrict subtraction between 'begin column'" />
     <param name="end_col" type="data_column" data_ref="input1" force_select="False" label="and 'end column'" help="Specifying columns for restricting subtraction is available only for tabular formatted datasets" />
+    <param name="ignore_empty_end_cols" type="boolean" label="Ignore empty columns and whitespace at end of line when subtracting"/>
   </inputs>
   <outputs>
     <data format="input" name="output" metadata_source="input1" />
@@ -45,6 +52,15 @@
       <param name="end_col" value="None" />
       <output name="output" file="subtract-query-4.dat" />
     </test>
+    <!-- Subtract  2 tabular files with no column restrictions, ignoring empty end columns. -->
+    <test>
+      <param name="input1" value="eq-showbeginning_e.dat" />
+      <param name="input2" value="eq-showtail.dat" />
+      <param name="begin_col" value="None" />
+      <param name="end_col" value="None" />
+      <param name="ignore_empty_end_cols" value="true" />
+      <output name="output" file="subtract-query-2.dat" />
+    </test>
   </tests>
   <help>