file open() pass: convert all read and write to ensure binary 'b' flag is set (#56)

pywb/cdx/cdxsource.py

@@ -30,7 +30,7 @@ class CDXFile(CDXSource):
     def load_cdx(self, query):
         def do_open():
             try:
-                source = open(self.filename)
+                source = open(self.filename, 'rb')
                 gen = iter_range(source, query.key, query.end_key)
                 for line in gen:
                     yield line

pywb/cdx/test/test_redis_source.py

@@ -26,7 +26,7 @@ test_cdx_dir = get_test_dir() + 'cdx/'
 
 def load_cdx_into_redis(source, filename, key=None):
     # load a cdx into mock redis
-    with open(test_cdx_dir + filename) as fh:
+    with open(test_cdx_dir + filename, 'rb') as fh:
         for line in fh:
             zadd_cdx(source, line, key)
 

pywb/cdx/zipnum.py

@@ -84,7 +84,7 @@ class ZipNumCluster(CDXSource):
         self.loc_mtime = new_mtime
 
         logging.debug('Loading loc from: ' + self.loc_filename)
-        with open(self.loc_filename) as fh:
+        with open(self.loc_filename, 'rb') as fh:
             for line in fh:
                 parts = line.rstrip().split('\t')
                 self.loc_map[parts[0]] = parts[1:]
@@ -112,7 +112,7 @@ class ZipNumCluster(CDXSource):
     def load_cdx(self, query):
         self.load_loc()
 
-        reader = open(self.summary)
+        reader = open(self.summary, 'rb')
 
         idx_iter = iter_range(reader,
                               query.key,

pywb/framework/proxy.py

@@ -334,7 +334,7 @@ class ProxyRouter(object):
                 return None
 
             buff = ''
-            with open(self.ca.ca_file) as fh:
+            with open(self.ca.ca_file, 'rb') as fh:
                 buff = fh.read()
 
             content_type = 'application/x-x509-ca-cert'

pywb/utils/test/test_binsearch.py

@@ -66,12 +66,12 @@ from pywb import get_test_dir
 test_cdx_dir = get_test_dir() + 'cdx/'
 
 def print_binsearch_results(key, iter_func):
-    with open(test_cdx_dir + 'iana.cdx') as cdx:
+    with open(test_cdx_dir + 'iana.cdx', 'rb') as cdx:
         for line in iter_func(cdx, key):
             print line
 
 def print_binsearch_results_range(key, end_key, iter_func, prev_size=0):
-    with open(test_cdx_dir + 'iana.cdx') as cdx:
+    with open(test_cdx_dir + 'iana.cdx', 'rb') as cdx:
         for line in iter_func(cdx, key, end_key, prev_size=prev_size):
             print line
 

pywb/utils/test/test_bufferedreaders.py

@@ -3,11 +3,11 @@ r"""
 #=================================================================
 
 # DecompressingBufferedReader readline()
->>> DecompressingBufferedReader(open(test_cdx_dir + 'iana.cdx', 'rU')).readline()
+>>> DecompressingBufferedReader(open(test_cdx_dir + 'iana.cdx', 'rb')).readline()
 ' CDX N b a m s k r M S V g\n'
 
 # detect not compressed
->>> DecompressingBufferedReader(open(test_cdx_dir + 'iana.cdx', 'rU'), decomp_type = 'gzip').readline()
+>>> DecompressingBufferedReader(open(test_cdx_dir + 'iana.cdx', 'rb'), decomp_type = 'gzip').readline()
 ' CDX N b a m s k r M S V g\n'
 
 # decompress with on the fly compression, default gzip compression

pywb/warc/cdxindexer.py

@@ -115,7 +115,7 @@ def write_multi_cdx_index(output, inputs, **options):
             outpath = cdx_filename(filename)
             outpath = os.path.join(output, outpath)
 
-            with open(outpath, 'w') as outfile:
+            with open(outpath, 'wb') as outfile:
                 with open(fullpath, 'rb') as infile:
                     write_cdx_index(outfile, infile, filename, **options)
 
@@ -124,7 +124,7 @@ def write_multi_cdx_index(output, inputs, **options):
         if output == '-':
             outfile = sys.stdout
         else:
-            outfile = open(output, 'w')
+            outfile = open(output, 'wb')
 
         if options.get('sort'):
             writer_cls = SortedCDXWriter

pywb/warc/pathresolvers.py

@@ -57,7 +57,7 @@ class RedisResolver:
 class PathIndexResolver:
     def __init__(self, pathindex_file):
         self.pathindex_file = pathindex_file
-        self.reader = open(pathindex_file)
+        self.reader = open(pathindex_file, 'rb')
 
     def __call__(self, filename):
         result = iter_exact(self.reader, filename, '\t')

pywb/warc/test/test_indexing.py

@@ -160,7 +160,7 @@ TEST_CDX_DIR = get_test_dir() + 'cdx/'
 TEST_WARC_DIR = get_test_dir() + 'warcs/'
 
 def read_fully(cdx):
-    with open(TEST_CDX_DIR + cdx, 'rU') as fh:
+    with open(TEST_CDX_DIR + cdx, 'rb') as fh:
         curr = BytesIO()
         while True:
             b = fh.read()
@@ -213,7 +213,7 @@ def cli_lines_with_dir(input_):
 
         print filename
 
-        with open(os.path.join(tmp_dir, filename), 'rU') as fh:
+        with open(os.path.join(tmp_dir, filename), 'rb') as fh:
             lines = fh.read(8192).rstrip().split('\n')
 
     finally: