Making a bit of progress...

This changes the internals to use BytesIO over StringIO, which
fixed a few of the failing tests in Python 3.  We are only
importing from `io` now, instead of the entire chain, as this is
available in Python 2.6+.

Author: kevin-brown

gitdb/db/mem.py

@@ -24,13 +24,7 @@
     DecompressMemMapReader,
 )
 
-try:
-    from cStringIO import StringIO
-except ImportError:
-    try:
-        from StringIO import StringIO
-    except ImportError:
-        from io import StringIO
+from io import StringIO
 
 __all__ = ("MemoryDB", )
 

gitdb/fun.py

@@ -21,13 +21,7 @@
 except ImportError:
     izip = zip
 
-try:
-    from cStringIO import StringIO
-except ImportError:
-    try:
-        from StringIO import StringIO
-    except ImportError:
-        from io import StringIO
+from io import StringIO
 
 # INVARIANTS
 OFS_DELTA = 6
@@ -453,7 +447,7 @@ def msb_size(data, offset=0):
     l = len(data)
     hit_msb = False
     while i < l:
-        c = ord(data[i+offset])
+        c = byte_ord(data[i+offset])
         size |= (c & 0x7f) << i*7
         i += 1
         if not c & 0x80:

gitdb/stream.py

@@ -3,13 +3,7 @@
 # This module is part of GitDB and is released under
 # the New BSD License: http://www.opensource.org/licenses/bsd-license.php
 
-try:
-    from cStringIO import StringIO
-except ImportError:
-    try:
-        from StringIO import StringIO
-    except ImportError:
-        from io import StringIO
+from io import BytesIO, StringIO
 
 import errno
 import mmap
@@ -106,20 +100,20 @@ def _parse_header_info(self):
         self._s = maxb
         hdr = self.read(maxb)
         hdrend = hdr.find("\0".encode("ascii"))
-        type, size = hdr[:hdrend].split(" ".encode("ascii"))
+        typ, size = hdr[:hdrend].split(" ".encode("ascii"))
         size = int(size)
         self._s = size
 
         # adjust internal state to match actual header length that we ignore
         # The buffer will be depleted first on future reads
         self._br = 0
-        hdrend += 1                                 # count terminating \0
-        self._buf = StringIO(hdr[hdrend:])
+        hdrend += 1
+        self._buf = BytesIO(hdr[hdrend:])
         self._buflen = len(hdr) - hdrend
 
         self._phi = True
 
-        return type, size
+        return typ.decode("ascii"), size
 
     #{ Interface
 
@@ -133,8 +127,8 @@ def new(self, m, close_on_deletion=False):
         :param close_on_deletion: if True, the memory map will be closed once we are
             being deleted"""
         inst = DecompressMemMapReader(m, close_on_deletion, 0)
-        type, size = inst._parse_header_info()
-        return type, size, inst
+        typ, size = inst._parse_header_info()
+        return typ, size, inst
 
     def data(self):
         """:return: random access compatible data we are working on"""
@@ -211,14 +205,14 @@ def read(self, size=-1):
         # END clamp size
 
         if size == 0:
-            return str()
+            return bytes()
         # END handle depletion
 
 
         # deplete the buffer, then just continue using the decompress object
         # which has an own buffer. We just need this to transparently parse the
         # header from the zlib stream
-        dat = str()
+        dat = bytes()
         if self._buf:
             if self._buflen >= size:
                 # have enough data
@@ -588,7 +582,7 @@ class ZippedStoreShaWriter(Sha1Writer):
     __slots__ = ('buf', 'zip')
     def __init__(self):
         Sha1Writer.__init__(self)
-        self.buf = StringIO()
+        self.buf = BytesIO()
         self.zip = zlib.compressobj(zlib.Z_BEST_SPEED)
 
     def __getattr__(self, attr):

gitdb/test/db/lib.py

@@ -24,13 +24,7 @@
 
 from async import IteratorReader
 
-try:
-    from cStringIO import StringIO
-except ImportError:
-    try:
-        from StringIO import StringIO
-    except ImportError:
-        from io import StringIO
+from io import StringIO
 
 from struct import pack
 
@@ -41,7 +35,7 @@ class TestDBBase(TestBase):
     """Base class providing testing routines on databases"""
 
     # data
-    two_lines = "1234\nhello world"
+    two_lines = "1234\nhello world".encode("ascii")
     all_data = (two_lines, )
 
     def _assert_object_writing_simple(self, db):

gitdb/test/lib.py

@@ -17,13 +17,7 @@
 import random
 from array import array
 
-try:
-    from cStringIO import StringIO
-except ImportError:
-    try:
-        from StringIO import StringIO
-    except ImportError:
-        from io import StringIO
+from io import StringIO
 
 import glob
 import unittest

gitdb/test/test_example.py

@@ -8,13 +8,7 @@
 from gitdb.db import LooseObjectDB
 from gitdb.util import pool
 
-try:
-    from cStringIO import StringIO
-except ImportError:
-    try:
-        from StringIO import StringIO
-    except ImportError:
-        from io import StringIO
+from io import StringIO
 
 from async import IteratorReader
 

gitdb/test/test_stream.py

@@ -82,9 +82,9 @@ def test_decompress_reader(self):
                     if with_size:
                         # need object data
                         zdata = zlib.compress(make_object(str_blob_type, cdata))
-                        type, size, reader = DecompressMemMapReader.new(zdata, close_on_deletion)
+                        typ, size, reader = DecompressMemMapReader.new(zdata, close_on_deletion)
                         assert size == len(cdata)
-                        assert type == str_blob_type
+                        assert typ == str_blob_type
 
                         # even if we don't set the size, it will be set automatically on first read
                         test_reader = DecompressMemMapReader(zdata, close_on_deletion=False)

gitdb/util.py

@@ -8,13 +8,7 @@
 import sys
 import errno
 
-try:
-    from cStringIO import StringIO
-except ImportError:
-    try:
-        from StringIO import StringIO
-    except ImportError:
-        from io import StringIO
+from io import StringIO
 
 try:
     import async.mod.zlib as zlib