From: Diane Trout <diane@ghic.org>
Date: Fri, 20 Mar 2015 20:47:36 +0000 (-0700)
Subject: Specify text vs binary mode for opening files.
X-Git-Url: http://woldlab.caltech.edu/gitweb/?p=htsworkflow.git;a=commitdiff_plain;h=3c442a662e3553dbb3b70da4e95bdc3c1625cf20

Specify text vs binary mode for opening files.

(And another smart_text cast sliped in)
---

diff --git a/experiments/views.py b/experiments/views.py
index e5f675d..7d30bbe 100644
--- a/experiments/views.py
+++ b/experiments/views.py
@@ -176,7 +176,7 @@ def read_result_file(self, key):
         content_type = data_file.file_type.mimetype
 
     if os.path.exists(data_file.pathname):
-        return HttpResponse(open(data_file.pathname,'r'),
+        return HttpResponse(open(data_file.pathname,'rb'),
                             content_type=content_type)
 
     raise Http404
diff --git a/htsworkflow/pipelines/eland.py b/htsworkflow/pipelines/eland.py
index b9a7ca3..3298ae4 100644
--- a/htsworkflow/pipelines/eland.py
+++ b/htsworkflow/pipelines/eland.py
@@ -150,7 +150,7 @@ class ElandLane(ResultLane):
         self._reads = 0
 
         for pathname in self.pathnames:
-            stream = autoopen(pathname, 'r')
+            stream = autoopen(pathname, 'rt')
             if self.eland_type == ELAND_SINGLE:
                 result = self._update_eland_result(stream)
             elif self.eland_type == ELAND_MULTI or \
@@ -548,7 +548,7 @@ class SequenceLane(ResultLane):
         """
         Determine if we have a scarf or fastq sequence file
         """
-        f = open(pathname,'r')
+        f = open(pathname,'rt')
         l = f.readline()
         f.close()
 
@@ -575,8 +575,8 @@ class SequenceLane(ResultLane):
 
         LOGGER.info("summarizing results for %s" % (pathname))
         lines = 0
-        f = open(pathname)
-        for l in f.xreadlines():
+        f = open(pathname, 'rt')
+        for l in f:
             lines += 1
         f.close()
 
diff --git a/htsworkflow/submission/daf.py b/htsworkflow/submission/daf.py
index 9c4b30e..b2d7419 100644
--- a/htsworkflow/submission/daf.py
+++ b/htsworkflow/submission/daf.py
@@ -270,7 +270,7 @@ class UCSCSubmission(object):
             self.daf = daf_file.read()
         else:
             # file
-            stream = open(daf_file, 'r')
+            stream = open(daf_file, 'rt')
             self.daf = stream.read()
             stream.close()
 
diff --git a/htsworkflow/util/hashfile.py b/htsworkflow/util/hashfile.py
index 9762883..c6cc0f9 100644
--- a/htsworkflow/util/hashfile.py
+++ b/htsworkflow/util/hashfile.py
@@ -14,7 +14,7 @@ def make_md5sum(filename):
     md5_cache = os.path.join(filename+".md5")
     if os.path.exists(md5_cache):
         logger.debug("Found md5sum in {0}".format(md5_cache))
-        stream = open(md5_cache,'r')
+        stream = open(md5_cache,'rt')
         lines = stream.readlines()
         md5sum = parse_md5sum_line(lines, filename)
     else:
@@ -35,13 +35,13 @@ def make_md5sum_unix(filename, md5_cache):
     md5sum = parse_md5sum_line(lines, filename)
     if md5sum is not None:
         logger.debug("Caching sum in {0}".format(md5_cache))
-        stream = open(md5_cache, "w")
-        stream.write(stdin)
+        stream = open(md5_cache, "wt")
+        stream.write(smart_text(stdin))
         stream.close()
     return md5sum
 
 def parse_md5sum_line(lines, filename):
-    md5sum, md5sum_filename = lines[0].split()
+    md5sum, md5sum_filename = smart_text(lines[0]).split()
     md5sum_filename = os.path.basename(md5sum_filename)
     filename = os.path.basename(filename)
     if md5sum_filename != filename:
diff --git a/htsworkflow/util/rdfhelp.py b/htsworkflow/util/rdfhelp.py
index 33197dd..ea1020c 100644
--- a/htsworkflow/util/rdfhelp.py
+++ b/htsworkflow/util/rdfhelp.py
@@ -344,7 +344,7 @@ def add_default_schemas(model, schema_path=None):
         for path in schema_path:
             for pathname in glob(os.path.join(path, '*.turtle')):
                 url = 'file://' + os.path.splitext(pathname)[0]
-                stream = open(pathname, 'r')
+                stream = open(pathname, 'rt')
                 add_schema(model, stream, url)
                 stream.close()