diff data_reader.xml @ 1:2470f3968557 draft default tip

Uploaded

--- a/data_reader.xml	Mon May 09 02:52:47 2016 -0400
+++ b/data_reader.xml	Tue Jun 21 04:42:16 2016 -0400
@@ -9,10 +9,13 @@
                 --new_ending .${directory.fields.galaxy_extension} 
                 --decompress ${directory.fields.decompress} 
                 #if $results.start
-                    --start $results.start
+                    --start "$results.start"
                 #end if      
                 #if $results.last
-                    --last $results.last
+                    --last "$results.last"
+                #end if      
+                #if $results.regex
+                    --regex "$results.regex"
                 #end if      
             #end if      
             --path ${directory.fields.path} 
@@ -33,6 +36,11 @@
             <when value="data">
                 <param name="start" type="text" value="" label="String which must be at the start of each file name" />
                 <param name="last" type="text" value="" label="String which must be at the end of the file name (excluding the file type)" />
+                <param name="regex" type="text" value="" label="Regex pattern which must somewhere in the file name (excluding the file type)" >
+                    <sanitizer>
+                        <valid initial="string.printable"/>
+                    </sanitizer>
+                </param>
             </when>
             <when value="listing"/>
         </conditional>
@@ -76,7 +84,20 @@
             <output name="listing_fastq">
                 <assert_contents>
                     <has_line line="sample1.fastq" />
-                    <not_has_text text="other.fasta" />
+                    <not_has_text text="other.fastq" />
+                </assert_contents>
+            </output>
+            <output_collection name="data_collection" type="list">
+                <element name="sample1" ftype="fastq" file="sample1.fastq" />
+           </output_collection>
+         </test>
+        <test>
+            <param name="directory" value="fastq_files_id" />
+            <param name="results|regex" value="le.?" />
+            <output name="listing_fastq">
+                <assert_contents>
+                    <has_line line="sample1.fastq" />
+                    <not_has_text text="other.fastq" />
                 </assert_contents>
             </output>
             <output_collection name="data_collection" type="list">
@@ -107,13 +128,23 @@
 
 Files can also be filter for the last part before the file extsentions.
 
+Files can also be filtered by a regex pattern.  
+Only files that contain the regex string will be included.
+This uses the python search funtion so as long as the Regex pattern is found somewhere in file name (excluding extension).
+
+The three filter start, last and regex if supplied work indepently, so only files that pass all supplied test will be included.
+
+Note: Before applying the last and regex test the ending (includig the . just before the ending are removed)
+
 Assuming the directory has:
-C01_R1_001.fasta   C01_R2_001.fatsa   C02_R1_001.fasta   C02_R2_001.fatsa
+C01_R1_001.fasta   C01_R2_001.fatsa   C02_R1_001.fasta   C02_R2_002.fatsa
 
-Setting start C01 will return just the C01 files:   C01_R1_001.fasta   C01_R2_001.fatsa
+Setting start C01 will return just the C01 files:   C01_R1_001.fasta   C01_R2_002.fatsa
 
 Setting last R1_001 will return the read1 files:   C01_R1_001.fasta   C02_R1_001.fasta
 
+Setting regex R2_00.$ will return the R2 files:   C01_R2_001.fatsa   C02_R2_002.fatsa
+
 As Galaxy detects the file type based on the extension this tool will change the exstension as setup by the admin.
 
 This tool will unzip gz files if requested to by the admin,