# HG changeset patch
# User peterjc
# Date 1486054143 18000
# Node ID e1398f2ba9fe7dc2de4ca0b36213503f5535148f
# Parent  7c0642fc57ad33b45f168baf926e789b0711405a
v0.0.8 galaxy_sequence_utils dependency etc

diff -r 7c0642fc57ad -r e1398f2ba9fe test-data/four_human_proteins.rename.tabular
--- a/test-data/four_human_proteins.rename.tabular	Fri Oct 11 04:39:16 2013 -0400
+++ b/test-data/four_human_proteins.rename.tabular	Thu Feb 02 11:49:03 2017 -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 7c0642fc57ad -r e1398f2ba9fe tools/seq_rename/README.rst
--- a/tools/seq_rename/README.rst	Fri Oct 11 04:39:16 2013 -0400
+++ b/tools/seq_rename/README.rst	Thu Feb 02 11:49:03 2017 -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 2011-2017 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.
 
@@ -70,6 +70,18 @@
         - 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.
+v0.0.6  - 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).
+v0.0.7  - Use the ``format_source=...`` tag.
+        - Reorder XML elements (internal change only).
+        - Planemo for Tool Shed upload (``.shed.yml``, internal change only).
+        - Capture the tool version via Galaxy (bug fix).
+v0.0.8  - Updated to point at Biopython 1.67 (latest version in Tool Shed).
+        - Explicit dependency on ``galaxy_sequence_utils``.
+        - Python style updates (internal change only).
 ======= ======================================================================
 
 
@@ -82,21 +94,30 @@
 Development has now moved to a dedicated GitHub repository:
 https://github.com/peterjc/pico_galaxy/tree/master/tools
 
-For making the "Galaxy Tool Shed" http://toolshed.g2.bx.psu.edu/ tarball use
-the following command from the Galaxy root folder::
+For pushing a release to the test or main "Galaxy Tool Shed", use the following
+Planemo commands (which requires you have set your Tool Shed access details in
+``~/.planemo.yml`` and that you have access rights on the Tool Shed)::
+
+    $ planemo shed_update -t testtoolshed --check_diff ~/repositories/pico_galaxy/tools/seq_rename/
+    ...
+
+or::
 
-    $ tar -czf seq_rename.tar.gz tools/seq_rename/README.rst tools/seq_rename/seq_rename.* tools/seq_rename/repository_dependencies.xml test-data/four_human_proteins.fasta test-data/four_human_proteins.rename.tabular test-data/four_human_proteins.rename.fasta
+    $ planemo shed_update -t toolshed --check_diff ~/repositories/pico_galaxy/tools/seq_rename/
+    ...
+
+To just build and check the tar ball, use::
 
-Check this worked::
-
-    $ tar -tzf seq_rename.tar.gz
+    $ planemo shed_upload --tar_only  ~/repositories/pico_galaxy/tools/seq_rename/
+    ...
+    $ tar -tzf shed_upload.tar.gz 
+    test-data/four_human_proteins.fasta
+    test-data/four_human_proteins.rename.fasta
+    test-data/four_human_proteins.rename.tabular
     tools/seq_rename/README.rst
     tools/seq_rename/seq_rename.py
     tools/seq_rename/seq_rename.xml
-    tools/seq_rename/repository_dependencies.xml
-    test-data/four_human_proteins.fasta
-    test-data/four_human_proteins.rename.tabular
-    test-data/four_human_proteins.rename.fasta
+    tools/seq_rename/tool_dependencies.xml
 
 
 Licence (MIT)
diff -r 7c0642fc57ad -r e1398f2ba9fe tools/seq_rename/repository_dependencies.xml
--- a/tools/seq_rename/repository_dependencies.xml	Fri Oct 11 04:39:16 2013 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,6 +0,0 @@
-<?xml version="1.0"?>
-<repositories description="This requires Biopython as a dependency.">
-<!-- Leave out the tool shed and revision to get the current
-     tool shed and latest revision at the time of upload -->
-<repository changeset_revision="3e82cbc44886" name="package_biopython_1_62" owner="biopython" toolshed="http://toolshed.g2.bx.psu.edu" />
-</repositories>
diff -r 7c0642fc57ad -r e1398f2ba9fe tools/seq_rename/seq_rename.py
--- a/tools/seq_rename/seq_rename.py	Fri Oct 11 04:39:16 2013 -0400
+++ b/tools/seq_rename/seq_rename.py	Thu Feb 02 11:49:03 2017 -0500
@@ -17,64 +17,85 @@
 molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
 http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878.
 
-This script is copyright 2011-2013 by Peter Cock, The James Hutton Institute UK.
+This script is copyright 2011-2017 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 "v0.0.8"
     sys.exit(0)
 
-def stop_err(msg, err=1):
-    sys.stderr.write(msg.rstrip() + "\n")
-    sys.exit(err)
-
-#Parse Command Line
+# Parse Command Line
 try:
     tabular_file, old_col_arg, new_col_arg, in_file, seq_format, out_file = sys.argv[1:]
 except ValueError:
-    stop_err("Expected six arguments (tabular file, old col, new col, input file, format, output file), got %i:\n%s" % (len(sys.argv)-1, " ".join(sys.argv)))
+    sys.exit("Expected six arguments (tabular file, old col, new col, input file, format, output file), got %i:\n%s" % (len(sys.argv) - 1, " ".join(sys.argv)))
 
 try:
     if old_col_arg.startswith("c"):
-        old_column = int(old_col_arg[1:])-1
+        old_column = int(old_col_arg[1:]) - 1
     else:
-        old_column = int(old_col_arg)-1
+        old_column = int(old_col_arg) - 1
 except ValueError:
-    stop_err("Expected column number, got %s" % old_col_arg)
+    sys.exit("Expected column number, got %s" % old_col_arg)
 try:
     if old_col_arg.startswith("c"):
-        new_column = int(new_col_arg[1:])-1
+        new_column = int(new_col_arg[1:]) - 1
     else:
-        new_column = int(new_col_arg)-1
+        new_column = int(new_col_arg) - 1
 except ValueError:
-    stop_err("Expected column number, got %s" % new_col_arg)
+    sys.exit("Expected column number, got %s" % new_col_arg)
 if old_column == new_column:
-    stop_err("Old and new column arguments are the same!")
+    sys.exit("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
+
+# Load the rename mappings
 rename = dict(parse_ids(tabular_file, old_column, new_column))
 print "Loaded %i ID mappings" % len(rename)
-              
-#Rewrite the sequence file
-if seq_format.lower()=="sff":
-    #Use Biopython for this format
+
+# Rewrite the sequence file
+if seq_format.lower() == "sff":
+    # Use Biopython for this format
     renamed = 0
+
     def rename_seqrecords(records, mapping):
-        global renamed #nasty, but practical!
+        global renamed  # nasty, but practical!
         for record in records:
             try:
                 record.id = mapping[record.id]
@@ -82,33 +103,33 @@
             except KeyError:
                 pass
             yield record
-                                                                
+
     try:
         from Bio.SeqIO.SffIO import SffIterator, SffWriter
     except ImportError:
-        stop_err("Requires Biopython 1.54 or later")
+        sys.exit("Requires Biopython 1.54 or later")
 
     try:
         from Bio.SeqIO.SffIO import ReadRocheXmlManifest
     except ImportError:
-        #Prior to Biopython 1.56 this was a private function
+        # Prior to Biopython 1.56 this was a private function
         from Bio.SeqIO.SffIO import _sff_read_roche_index_xml as ReadRocheXmlManifest
 
-    in_handle = open(in_file, "rb") #must be binary mode!
+    in_handle = open(in_file, "rb")  # must be binary mode!
     try:
         manifest = ReadRocheXmlManifest(in_handle)
     except ValueError:
         manifest = None
     out_handle = open(out_file, "wb")
     writer = SffWriter(out_handle, xml=manifest)
-    in_handle.seek(0) #start again after getting manifest
+    in_handle.seek(0)  # start again after getting manifest
     count = writer.write_file(rename_seqrecords(SffIterator(in_handle), rename))
     out_handle.close()
     in_handle.close()
 else:
-    #Use Galaxy for FASTA, QUAL or FASTQ
+    # Use Galaxy for FASTA, QUAL or FASTQ
     if seq_format.lower() in ["fasta", "csfasta"] \
-    or seq_format.lower().startswith("qual"):
+        or seq_format.lower().startswith("qual"):
         from galaxy_utils.sequence.fasta import fastaReader, fastaWriter
         reader = fastaReader(open(in_file, "rU"))
         writer = fastaWriter(open(out_file, "w"))
@@ -119,13 +140,13 @@
         writer = fastqWriter(open(out_file, "w"))
         marker = "@"
     else:
-        stop_err("Unsupported file type %r" % seq_format)
-    #Now do the renaming
+        sys.exit("Unsupported file type %r" % seq_format)
+    # Now do the renaming
     count = 0
     renamed = 0
     for record in reader:
-        #The [1:] is because the fastaReader leaves the > on the identifier,
-        #likewise the fastqReader leaves the @ on the identifier
+        # The [1:] is because the fastaReader leaves the > on the identifier,
+        # likewise the fastqReader leaves the @ on the identifier
         try:
             idn, descr = record.identifier[1:].split(None, 1)
         except ValueError:
diff -r 7c0642fc57ad -r e1398f2ba9fe tools/seq_rename/seq_rename.xml
--- a/tools/seq_rename/seq_rename.xml	Fri Oct 11 04:39:16 2013 -0400
+++ b/tools/seq_rename/seq_rename.xml	Thu Feb 02 11:49:03 2017 -0500
@@ -1,18 +1,19 @@
-<tool id="seq_rename" name="Rename sequences" version="0.0.4">
+<tool id="seq_rename" name="Rename sequences" version="0.0.8">
     <description>with ID mapping from a tabular file</description>
     <requirements>
-        <requirement type="package" version="1.62">biopython</requirement>
+        <requirement type="package" version="1.0.1">galaxy_sequence_utils</requirement>
+        <requirement type="package" version="1.67">biopython</requirement>
         <requirement type="python-module">Bio</requirement>
     </requirements>
-    <version_commmand interpreter="python">seq_rename.py --version</version_commmand>
-    <command interpreter="python">
-seq_rename.py $input_tabular $old_column $new_column $input_file $input_file.ext $output_file
-    </command>
     <stdio>
         <!-- Anything other than zero is an error -->
         <exit_code range="1:" />
         <exit_code range=":-1" />
     </stdio>
+    <version_command interpreter="python">seq_rename.py --version</version_command>
+    <command interpreter="python">
+seq_rename.py $input_tabular $old_column $new_column $input_file $input_file.ext $output_file
+    </command>
     <inputs>
         <param name="input_file" type="data" format="fasta,qual,fastq,sff" label="Sequence file" help="FASTA, QUAL, FASTQ, or SFF format." />
         <param name="input_tabular" type="data" format="tabular" label="Tabular file containing sequence identifiers"/>
@@ -20,17 +21,7 @@
         <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_source="input_file" metadata_source="input_file" label="Renamed ${on_string}"/>
     </outputs>
     <tests>
         <test>
@@ -55,12 +46,17 @@
 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 +77,8 @@
 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 7c0642fc57ad -r e1398f2ba9fe tools/seq_rename/tool_dependencies.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/seq_rename/tool_dependencies.xml	Thu Feb 02 11:49:03 2017 -0500
@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="biopython" version="1.67">
+        <repository changeset_revision="a42f244cce44" name="package_biopython_1_67" owner="biopython" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+    <package name="galaxy_sequence_utils" version="1.0.1">
+        <repository changeset_revision="c1ab450748ba" name="package_galaxy_sequence_utils_1_0_1" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>