changeset 6:31f5701cd2e9 draft

v0.2.4 Depends on Biopython 1.67 via legacy Tool Shed package or bioconda.
author peterjc
date Thu, 11 May 2017 07:24:38 -0400
parents 6b71ad5d43fb
children 86710edcec02
files tools/sample_seqs/README.rst tools/sample_seqs/sample_seqs.py tools/sample_seqs/sample_seqs.xml tools/sample_seqs/tool_dependencies.xml
diffstat 4 files changed, 18 insertions(+), 14 deletions(-) [+]
line wrap: on
line diff
--- a/tools/sample_seqs/README.rst	Wed Feb 01 09:39:36 2017 -0500
+++ b/tools/sample_seqs/README.rst	Thu May 11 07:24:38 2017 -0400
@@ -1,7 +1,7 @@
 Galaxy tool to sub-sample sequence files
 ========================================
 
-This tool is copyright 2014-2015 by Peter Cock, The James Hutton Institute
+This tool is copyright 2014-2017 by Peter Cock, The James Hutton Institute
 (formerly SCRI, Scottish Crop Research Institute), UK. All rights reserved.
 See the licence text below (MIT licence).
 
@@ -71,6 +71,8 @@
         - Planemo for Tool Shed upload (``.shed.yml``, internal change only).
 v0.2.3  - Do the Biopython imports at the script start (internal change only).
         - Clarify paired read example in help text.
+v0.2.4  - Depends on Biopython 1.67 via legacy Tool Shed package or bioconda.
+        - Style changes to Python code (internal change only).
 ======= ======================================================================
 
 
@@ -84,17 +86,17 @@
 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/sample_seqs/
+    $ planemo shed_update -t testtoolshed --check_diff tools/sample_seqs/
     ...
 
 or::
 
-    $ planemo shed_update -t toolshed --check_diff ~/repositories/pico_galaxy/tools/sample_seqs/
+    $ planemo shed_update -t toolshed --check_diff tools/sample_seqs/
     ...
 
 To just build and check the tar ball, use::
 
-    $ planemo shed_upload --tar_only  ~/repositories/pico_galaxy/tools/sample_seqs/
+    $ planemo shed_upload --tar_only tools/sample_seqs/
     ...
     $ tar -tzf shed_upload.tar.gz 
     test-data/MID4_GLZRM4E04_rnd30_frclip.pair_sample_N5.sff
--- a/tools/sample_seqs/sample_seqs.py	Wed Feb 01 09:39:36 2017 -0500
+++ b/tools/sample_seqs/sample_seqs.py	Thu May 11 07:24:38 2017 -0400
@@ -63,7 +63,7 @@
 options, args = parser.parse_args()
 
 if options.version:
-    print("v0.2.3")
+    print("v0.2.4")
     sys.exit(0)
 
 try:
@@ -146,6 +146,7 @@
         sys.stderr.write("Sampling every %ith sequence\n" % N)
 
     def sampler(iterator):
+        """Sample every Nth sequence."""
         global N
         count = 0
         for record in iterator:
@@ -157,11 +158,12 @@
         percent = float(options.percent) / 100.0
     except ValueError:
         sys.exit("Bad -p percent argument %r" % options.percent)
-    if percent <= 0.0 or 1.0 <= percent:
+    if not(0.0 <= percent <= 1.0):
         sys.exit("Bad -p percent argument %r" % options.percent)
     sys.stderr.write("Sampling %0.3f%% of sequences\n" % (100.0 * percent))
 
     def sampler(iterator):
+        """Sample given percentage of sequences."""
         global percent
         count = 0
         taken = 0
@@ -215,6 +217,7 @@
             assert taken == N, "Picked %i, wanted %i" % (taken, N)
     else:
         def sampler(iterator):
+            """Sample given number of sequences."""
             # Mimic the percentage sampler, with double check on final count
             global N, total
             # Do we need a floating point fudge factor epsilon?
@@ -268,12 +271,11 @@
             raise ValueError(
                 "Records in Fasta files should start with '>' character")
         try:
-            id = line[1:].split(None, 1)[0]
+            line[1:].split(None, 1)[0]
         except IndexError:
             if not no_id_warned:
                 sys.stderr.write("WARNING - Malformed FASTA entry with no identifier\n")
-        no_id_warned = True
-        id = None
+                no_id_warned = True
         lines = [line]
         line = handle.readline()
         while True:
@@ -346,6 +348,7 @@
                 count = writer.write_file(iterator_filter(SffIterator(in_handle)))
     return count
 
+
 if seq_format == "sff":
     count = sff_filter(in_file, out_file, sampler, interleaved)
 elif seq_format == "fasta":
--- a/tools/sample_seqs/sample_seqs.xml	Wed Feb 01 09:39:36 2017 -0500
+++ b/tools/sample_seqs/sample_seqs.xml	Thu May 11 07:24:38 2017 -0400
@@ -1,8 +1,7 @@
-<tool id="sample_seqs" name="Sub-sample sequences files" version="0.2.3">
+<tool id="sample_seqs" name="Sub-sample sequences files" version="0.2.4">
     <description>e.g. to reduce coverage</description>
     <requirements>
-        <requirement type="package" version="1.65">biopython</requirement>
-        <requirement type="python-module">Bio</requirement>
+        <requirement type="package" version="1.67">biopython</requirement>
     </requirements>
     <stdio>
         <!-- Anything other than zero is an error -->
--- a/tools/sample_seqs/tool_dependencies.xml	Wed Feb 01 09:39:36 2017 -0500
+++ b/tools/sample_seqs/tool_dependencies.xml	Thu May 11 07:24:38 2017 -0400
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <tool_dependency>
-    <package name="biopython" version="1.65">
-        <repository changeset_revision="d8185f5631ed" name="package_biopython_1_65" owner="biopython" toolshed="https://toolshed.g2.bx.psu.edu" />
+    <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>
 </tool_dependency>