# HG changeset patch
# User peterjc
# Date 1417094454 18000
# Node ID ba3ec1b3e6350350603e6ea91788e8586bbef3df
# Parent  61cec46f6be595505f649c62ba5d988ce85d3476
Uploaded v0.0.6, handle white space in identifier columns, embed citation, simpler XML

diff -r 61cec46f6be5 -r ba3ec1b3e635 test-data/four_human_proteins.rename.tabular
--- a/test-data/four_human_proteins.rename.tabular	Wed Nov 20 12:11:32 2013 -0500
+++ b/test-data/four_human_proteins.rename.tabular	Thu Nov 27 08:20:54 2014 -0500
@@ -1,5 +1,5 @@
 #FASTA	ID
-sp|Q9BS26|ERP44_HUMAN	Q9BS26
+sp|Q9BS26|ERP44_HUMAN	Q9BS26 and ignore this description
 sp|Q9NSY1|BMP2K_HUMAN	Q9NSY1
-sp|P06213|INSR_HUMAN	P06213
+sp|P06213|INSR_HUMAN and ignore this description	P06213
 sp|P08100|OPSD_HUMAN	P08100
diff -r 61cec46f6be5 -r ba3ec1b3e635 tools/seq_rename/README.rst
--- a/tools/seq_rename/README.rst	Wed Nov 20 12:11:32 2013 -0500
+++ b/tools/seq_rename/README.rst	Thu Nov 27 08:20:54 2014 -0500
@@ -1,7 +1,7 @@
 Galaxy tool to rename FASTA, QUAL, FASTQ or SFF sequences
 =========================================================
 
-This tool is copyright 2011-2013 by Peter Cock, The James Hutton Institute
+This tool is copyright 2011-2014 by Peter Cock, The James Hutton Institute
 (formerly SCRI, Scottish Crop Research Institute), UK. All rights reserved.
 See the licence text below.
 
@@ -35,20 +35,20 @@
 
 There are just two files to install to use this tool from within Galaxy:
 
-* seq_rename.py (the Python script)
-* seq_rename.xml (the Galaxy tool definition)
+* ``seq_rename.py`` (the Python script)
+* ``seq_rename.xml`` (the Galaxy tool definition)
 
-The suggested location is in a dedicated tools/seq_rename folder.
+The suggested location is in a dedicated ``tools/seq_rename`` folder.
 
-You will also need to modify the tools_conf.xml file to tell Galaxy to offer the
+You will also need to modify the ``tools_conf.xml`` file to tell Galaxy to offer the
 tool. One suggested location is in the filters section. Simply add the line::
 
     <tool file="seq_rename/seq_rename.xml" />
 
-If you wish to run the unit tests, also add this to tools_conf.xml.sample
-and move/copy the test-data files under Galaxy's test-data folder. Then::
+If you wish to run the unit tests, also move/copy the ``test-data/`` files
+under Galaxy's ``test-data/`` folder. Then::
 
-    $ ./run_functional_tests.sh -id seq_rename
+    $ ./run_tests.sh -id seq_rename
 
 You will also need to install Biopython 1.54 or later. That's it.
 
@@ -70,7 +70,11 @@
         - Updated citation information (Cock et al. 2013).
         - Development moved to GitHub, https://github.com/peterjc/pico_galaxy
         - Renamed folder and adopted README.rst naming.
-v0.0.5  - Correct automated dependency definition
+v0.0.5  - Correct automated dependency definition.
+v0.0.6  - Simplified XML to apply input format to output data.
+        - Tool definition now embeds citation information.
+        - If white space is found in the requested tabular field then only
+          the first word is used as the identifier (with a warning to stderr).
 ======= ======================================================================
 
 
diff -r 61cec46f6be5 -r ba3ec1b3e635 tools/seq_rename/seq_rename.py
--- a/tools/seq_rename/seq_rename.py	Wed Nov 20 12:11:32 2013 -0500
+++ b/tools/seq_rename/seq_rename.py	Thu Nov 27 08:20:54 2014 -0500
@@ -20,13 +20,11 @@
 This script is copyright 2011-2013 by Peter Cock, The James Hutton Institute UK.
 All rights reserved. See accompanying text file for licence details (MIT
 license).
-
-This is version 0.0.4 of the script.
 """
 import sys
 
 if "-v" in sys.argv or "--version" in sys.argv:
-    print "v0.0.4"
+    print "v0.0.6"
     sys.exit(0)
 
 def stop_err(msg, err=1):
@@ -57,13 +55,38 @@
     stop_err("Old and new column arguments are the same!")
 
 def parse_ids(tabular_file, old_col, new_col):
-    """Read tabular file and record all specified ID mappings."""
+    """Read tabular file and record all specified ID mappings.
+
+    Will print a single warning to stderr if any of the old/new column
+    entries have non-trailing white space (only the first word will
+    be used as the identifier).
+
+    Internal white space in the new column is taken as desired output.
+    """
     handle = open(tabular_file, "rU")
+    old_warn = False
+    new_warn = False
     for line in handle:
+        if not line.strip():
+            # Ignore blank lines
+            continue
         if not line.startswith("#"):
             parts = line.rstrip("\n").split("\t")
-            yield parts[old_col].strip(), parts[new_col].strip()
+            old = parts[old_col].strip().split(None, 1)
+            new = parts[new_col].strip().split(None, 1)
+            if not old_warn and len(old) > 1:
+                old_warn = "WARNING: Some of your old identifiers had white space in them, " + \
+                           "using first word only. e.g.:\n%s\n" % parts[old_col].strip()
+            if not new_warn and len(new) > 1:
+                new_warn = "WARNING: Some of your new identifiers had white space in them, " + \
+                           "using first word only. e.g.:\n%s\n" % parts[new_col].strip()
+            yield old[0], new[0]
     handle.close()
+    if old_warn:
+        sys.stderr.write(old_warn)
+    if new_warn:
+        sys.stderr.write(new_warn)
+
 
 #Load the rename mappings
 rename = dict(parse_ids(tabular_file, old_column, new_column))
diff -r 61cec46f6be5 -r ba3ec1b3e635 tools/seq_rename/seq_rename.xml
--- a/tools/seq_rename/seq_rename.xml	Wed Nov 20 12:11:32 2013 -0500
+++ b/tools/seq_rename/seq_rename.xml	Thu Nov 27 08:20:54 2014 -0500
@@ -1,4 +1,4 @@
-<tool id="seq_rename" name="Rename sequences" version="0.0.4">
+<tool id="seq_rename" name="Rename sequences" version="0.0.6">
     <description>with ID mapping from a tabular file</description>
     <requirements>
         <requirement type="package" version="1.62">biopython</requirement>
@@ -20,17 +20,7 @@
         <param name="new_column" type="data_column" data_ref="input_tabular" multiple="False" numerical="False" label="Column containing new sequence identifiers"/>
     </inputs>
     <outputs>
-        <data name="output_file" format="fasta" label="Renamed ${on_string}">
-            <!-- TODO - Replace this with format="input:input_fastq" if/when that works -->
-            <change_format>
-                <when input_dataset="input_file" attribute="extension" value="sff" format="sff" />
-		<when input_dataset="input_file" attribute="extension" value="fastq" format="fastq" />
-		<when input_dataset="input_file" attribute="extension" value="fastqsanger" format="fastqsanger" />
-		<when input_dataset="input_file" attribute="extension" value="fastqsolexa" format="fastqsolexa" />
-		<when input_dataset="input_file" attribute="extension" value="fastqillumina" format="fastqillumina" />
-		<when input_dataset="input_file" attribute="extension" value="fastqcssanger" format="fastqcssanger" />
-            </change_format>
-        </data>
+        <data name="output_file" format="input" metadata_source="input_file" label="Renamed ${on_string}"/>
     </outputs>
     <tests>
         <test>
@@ -55,12 +45,17 @@
 new sequence file (of the same format) where the sequence identifiers have been
 renamed according to the specified columns in your tabular file.
 
+Any original description is preserved (N/A for the SFF file format).
+
 WARNING: If you have any duplicates in the input sequence file, you will still
 have duplicate sequences in the output.
 
 WARNING: If the tabular file has more than one new name for any old ID, the
 last one is used.
 
+WARNING: The old and new names in your tabular file should not contain white space.
+If they do, only the first word is used as the identifier.
+
 **References**
 
 If you use this Galaxy tool in work leading to a scientific publication please
@@ -81,4 +76,8 @@
 This tool is available to install into other Galaxy Instances via the Galaxy
 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/seq_rename
     </help>
+    <citations>
+        <citation type="doi">10.7717/peerj.167</citation>
+        <citation type="doi">10.1093/bioinformatics/btp163</citation>
+    </citations>
 </tool>
diff -r 61cec46f6be5 -r ba3ec1b3e635 tools/seq_rename/tool_dependencies.xml
--- a/tools/seq_rename/tool_dependencies.xml	Wed Nov 20 12:11:32 2013 -0500
+++ b/tools/seq_rename/tool_dependencies.xml	Thu Nov 27 08:20:54 2014 -0500
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <tool_dependency>
     <package name="biopython" version="1.62">
-        <repository changeset_revision="ac9cc2992b69" name="package_biopython_1_62" owner="biopython" toolshed="http://testtoolshed.g2.bx.psu.edu" />
+        <repository changeset_revision="ac9cc2992b69" name="package_biopython_1_62" owner="biopython" toolshed="https://testtoolshed.g2.bx.psu.edu" />
     </package>
 </tool_dependency>