# HG changeset patch
# User davidvanzessen
# Date 1441110867 14400
# Node ID 1f1640608245adc0ef6b31460122480b3b712a71
# Parent  a3c4e3e62e1054e38e2e7b68f050022527f1da8b
Uploaded

diff -r a3c4e3e62e10 -r 1f1640608245 extract_duplicates.r
--- a/extract_duplicates.r	Tue Sep 01 07:49:47 2015 -0400
+++ b/extract_duplicates.r	Tue Sep 01 08:34:27 2015 -0400
@@ -3,14 +3,21 @@
 input=args[1]
 column=as.numeric(args[2])
 header=(args[3] == "yes")
-out_file=args[4]
+regex_filter=args[4]
+out_file=args[5]
+
+print(regex_filter)
 
 dat = read.table(input, header=header, sep="\t", fill=T, stringsAsFactors=F, quote="")
 
-duplicates = dat[duplicated(dat[,column]),column]
+dat.names = names(dat)
 
-dat = dat[dat[,column] %in% duplicates,]
+dat$filtered = gsub("\\(.*", "", dat[,column])
+
+duplicates = dat[duplicated(dat$filtered),"filtered"]
 
-dat = dat[order(dat[,column]),]
+dat = dat[dat[,"filtered"] %in% duplicates,]
 
-write.table(dat, out_file, sep="\t", row.names=F, col.names=header, quote=F)
+dat = dat[order(dat[,"filtered"]),]
+
+write.table(dat[,dat.names], out_file, sep="\t", row.names=F, col.names=header, quote=F)
diff -r a3c4e3e62e10 -r 1f1640608245 extract_duplicates.sh
--- a/extract_duplicates.sh	Tue Sep 01 07:49:47 2015 -0400
+++ b/extract_duplicates.sh	Tue Sep 01 08:34:27 2015 -0400
@@ -1,7 +1,8 @@
 input=$1
 column=$2
 header=$3
-out_file=$4
+regex_filter=$4
+out_file=$5
 
 dir="$(cd "$(dirname "$0")" && pwd)"
-Rscript --verbose $dir/extract_duplicates.r ${input} ${column} ${header} ${out_file} 2>&1
+Rscript --verbose $dir/extract_duplicates.r ${input} ${column} ${header} "${regex_filter}" ${out_file} 2>&1
diff -r a3c4e3e62e10 -r 1f1640608245 extract_duplicates.xml
--- a/extract_duplicates.xml	Tue Sep 01 07:49:47 2015 -0400
+++ b/extract_duplicates.xml	Tue Sep 01 08:34:27 2015 -0400
@@ -1,11 +1,12 @@
 <tool id="extract_duplicates" name="Extract Duplicates" version="1.1.0">
   <description>to a new dataset</description>
   <command interpreter="bash">
-    extract_duplicates.sh $input $column $header $out_file
+    extract_duplicates.sh $input $column $header "$regex_filter" $out_file
   </command>
   <inputs>
     <param format="tabular" name="input" type="data" label="Input"/>
 		<param name="column" label="on column" type="data_column" data_ref="input" accept_default="true" />
+		<param name="regex_filter" type="text" label="Filter to sanitize the column" value="\\(.*" size='70'/>
 		<param name="header" type="boolean" checked="False" truevalue="yes" falsevalue="no" label="Input file has a header?" help="if checked, the first line of the input will be treated as a header"/>
   </inputs>
   <outputs>