Merge pull request #12 from genomematt/issue11

fixes #11 unresolved forward read state assignment error and fixes #13 PEP479 compliance

.gitignore

@@ -5,4 +5,11 @@
 **/.DS_store
 
 #ignore egg info files
-XenoMapper.egg-info
+XenoMapper.egg-info
+\.eggs/
+
+\.pytest_cache/v/cache/
+
+\.vscode/
+
+dist/

.travis.yml

@@ -1,7 +1,6 @@
 language: python
 matrix:
   include:
-  - python: "3.3"
   - python: "3.4"
   - python: "3.5"
   - python: "3.6"

setup.py

@@ -12,7 +12,7 @@
 
 setup(
     name='XenoMapper',
-    version='1.0.1',
+    version='1.0.2',
     author='Matthew Wakefield',
     author_email='matthew.wakefield@unimelb.edu.au',
     packages=['xenomapper'],
@@ -36,6 +36,8 @@
           'Programming Language :: Python :: 3.3',
           'Programming Language :: Python :: 3.4',
           'Programming Language :: Python :: 3.5',
+          'Programming Language :: Python :: 3.6',
+          'Programming Language :: Python :: 3.7',
           'Programming Language :: Python :: Implementation :: CPython',
           'Programming Language :: Python :: Implementation :: PyPy',
           'Intended Audience :: Science/Research',

xenomapper/mappability.py

@@ -26,10 +26,10 @@
 from xenomapper.xenomapper import get_sam_header
 
 __author__ = "Matthew Wakefield"
-__copyright__ = "Copyright 2011-2016 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
+__copyright__ = "Copyright 2011-2019 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
 __credits__ = ["Matthew Wakefield",]
 __license__ = "GPLv3"
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 __maintainer__ = "Matthew Wakefield"
 __email__ = "wakefield@wehi.edu.au"
 __status__ = "Development"

xenomapper/tests/test_all.py

@@ -4,18 +4,18 @@
 test_xenomapper.py
 
 Created by Matthew Wakefield on 2012-08-16.
-Copyright (c) 2011-2016 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne. All rights reserved.
+Copyright (c) 2011-2019 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne. All rights reserved.
 """
 
 import unittest
 from xenomapper.tests.test_xenomapper import *
 from xenomapper.tests.test_mappability import *
 
 __author__ = "Matthew Wakefield"
-__copyright__ = "Copyright 2011-2016 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
+__copyright__ = "Copyright 2011-2019 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
 __credits__ = ["Matthew Wakefield",]
 __license__ = "GPLv3"
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 __maintainer__ = "Matthew Wakefield"
 __email__ = "wakefield@wehi.edu.au"
 __status__ = "Release/Stable"

xenomapper/tests/test_mappability.py

@@ -16,10 +16,10 @@
 
 
 __author__ = "Matthew Wakefield"
-__copyright__ = "Copyright 2011-2016 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
+__copyright__ = "Copyright 2011-2019 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
 __credits__ = ["Matthew Wakefield",]
 __license__ = "GPLv3"
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 __maintainer__ = "Matthew Wakefield"
 __email__ = "wakefield@wehi.edu.au"
 __status__ = "Development/Beta"

xenomapper/tests/test_xenomapper.py

@@ -14,10 +14,10 @@
 from pkg_resources import resource_stream
 
 __author__ = "Matthew Wakefield"
-__copyright__ = "Copyright 2011-2016 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
+__copyright__ = "Copyright 2011-2019 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
 __credits__ = ["Matthew Wakefield",]
 __license__ = "GPLv3"
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 __maintainer__ = "Matthew Wakefield"
 __email__ = "wakefield@wehi.edu.au"
 __status__ = "Production/Stable"
@@ -90,7 +90,7 @@ def test_consistent_output_SE(self):
                          len(test_unassigned_outfile.getvalue().split('\n'))-4) #26 lines of header in this file
         self.assertEqual(cat_counts['unassigned'],
                          len(test_unassigned_outfile.getvalue().split('\n'))-4) #26 lines of header in this file
-        self.assertEqual(hashlib.sha224(test_primary_specific_outfile.getvalue().encode('latin-1')).hexdigest(),'24107f7addcbfde7180e57965734e0e99481286f3b99e97d815613fb')
+        self.assertEqual(hashlib.sha224(test_primary_specific_outfile.getvalue().encode('latin-1')).hexdigest(),'381325b12dd9a9cd3afdd72eeb16b23cc92ddd16f675bb21bb21e08e')
         sam1.close()
         sam2.close()
         pass
@@ -122,7 +122,7 @@ def test_consistent_output_PE(self):
         self.assertEqual(sum([cat_counts[x] for x in cat_counts if 'secondary_multi' in x \
                         and not 'primary_multi' in x and not 'primary_specific' in x and not 'secondary_specific' in x])*2,
                         len(test_secondary_multi_outfile.getvalue().split('\n'))-1)
-        self.assertEqual(hashlib.sha224(test_primary_specific_outfile.getvalue().encode('latin-1')).hexdigest(),'85b2499215d91e8ef8115e81bbe745c6095772340bdd548a2bbc7d09')
+        self.assertEqual(hashlib.sha224(test_primary_specific_outfile.getvalue().encode('latin-1')).hexdigest(),'64c0e24bf141c5aa3bb0993c73b34cdfe630a504ac424843f746918d')
         sam1.close()
         sam2.close()
         pass
@@ -155,7 +155,7 @@ def test_consistent_output_conservative_PE(self):
                          len(test_secondary_specific_outfile.getvalue().split('\n'))-27)  #26 lines of header in this file
         self.assertEqual(cat_counts[('unassigned', 'unassigned')]*2, len(test_unassigned_outfile.getvalue().split('\n'))-1)
 
-        self.assertEqual(hashlib.sha224(test_primary_specific_outfile.getvalue().encode('latin-1')).hexdigest(),'5c201ba8ef87f20a11d14fbdbf091c2d7c45267707227122c77ffd26')
+        self.assertEqual(hashlib.sha224(test_primary_specific_outfile.getvalue().encode('latin-1')).hexdigest(),'c4de3de755092c8f9ff1eb2cd360a502d74ebd4c1e65ed282515ed3e')
         sam1.close()
         sam2.close()
         pass

xenomapper/xenomapper.py

@@ -25,10 +25,10 @@
 from copy import copy
 
 __author__ = "Matthew Wakefield"
-__copyright__ = "Copyright 2011-2016 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
+__copyright__ = "Copyright 2011-2019 Matthew Wakefield, The Walter and Eliza Hall Institute and The University of Melbourne"
 __credits__ = ["Matthew Wakefield",]
 __license__ = "GPL"
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 __maintainer__ = "Matthew Wakefield"
 __email__ = "wakefield@wehi.edu.au"
 __status__ = "Production/Stable"
@@ -73,22 +73,24 @@ def getBamReadPairs(bamfile1,bamfile2, skip_repeated_reads=False): #pragma: no c
     """
     bam1 = bam_lines(bamfile1)
     bam2 = bam_lines(bamfile2)
-    line1= next(bam1).strip('\n').split() #split on white space. Results in 11 fields of mandatory SAM + variable number of additional tags.
-    line2= next(bam2).strip('\n').split()
-    while line1 and line2 and line1 !=[''] and line2 !=['']:
-        assert line1[0] == line2[0]
-        yield line1,line2
-        previous_read1 = line1[0]
-        previous_read2 = line2[0]
-        if skip_repeated_reads:
-            while line1 and line2 and line1 !=[''] and line2 !=[''] and line1[0] == previous_read1:
+    try:
+        line1= next(bam1).strip('\n').split() #split on white space. Results in 11 fields of mandatory SAM + variable number of additional tags.
+        line2= next(bam2).strip('\n').split()
+        while line1 and line2 and line1 !=[''] and line2 !=['']:
+            assert line1[0] == line2[0]
+            yield line1,line2
+            previous_read1 = line1[0]
+            previous_read2 = line2[0]
+            if skip_repeated_reads:
+                while line1 and line2 and line1 !=[''] and line2 !=[''] and line1[0] == previous_read1:
+                    line1= next(bam1).strip('\n').split()
+                while line1 and line2 and line1 !=[''] and line2 !=[''] and line2[0] == previous_read2:
+                    line2= next(bam2).strip('\n').split()
+            else:
                 line1= next(bam1).strip('\n').split()
-            while line1 and line2 and line1 !=[''] and line2 !=[''] and line2[0] == previous_read2:
                 line2= next(bam2).strip('\n').split()
-        else:
-            line1= next(bam1).strip('\n').split()
-            line2= next(bam2).strip('\n').split()
-    pass
+    except StopIteration:
+        return
 
 def getReadPairs(sam1,sam2, skip_repeated_reads=False):
     """Process two sam files to yield the equivalent line from each file
@@ -434,7 +436,7 @@ def main_paired_end(readpairs,
             if secondary_multi:
                 print('\t'.join(previous_line2),file=secondary_multi) 
                 print('\t'.join(line2),file=secondary_multi)
-        elif forward_state == 'unresloved' or reverse_state == 'unresolved':
+        elif forward_state == 'unresolved' or reverse_state == 'unresolved':
             if unresolved:
                 print('\t'.join(previous_line1),file=unresolved) 
                 print('\t'.join(line1),file=unresolved)
@@ -520,7 +522,7 @@ def conservative_main_paired_end(readpairs,
             if unassigned:
                 print('\t'.join(previous_line1),file=unassigned) 
                 print('\t'.join(line1),file=unassigned)
-        elif forward_state == 'unresloved' or reverse_state == 'unresolved' \
+        elif forward_state == 'unresolved' or reverse_state == 'unresolved' \
             or (forward_state in ['primary_specific','primary_multi'] and \
                 reverse_state in ['secondary_specific','secondary_multi']) \
             or (forward_state in ['secondary_specific','secondary_multi'] and \