diff options
Diffstat (limited to 'git/objects/fun.py')
| -rw-r--r-- | git/objects/fun.py | 26 |
1 files changed, 13 insertions, 13 deletions
diff --git a/git/objects/fun.py b/git/objects/fun.py index db2ec7c2..f92a4c06 100644 --- a/git/objects/fun.py +++ b/git/objects/fun.py @@ -1,6 +1,9 @@ """Module with functions which are supposed to be as fast as possible""" from stat import S_ISDIR from git.compat import ( + byte_ord, + force_bytes, + defenc, xrange, text_type ) @@ -17,13 +20,13 @@ def tree_to_stream(entries, write): bit_mask = 7 # 3 bits set for binsha, mode, name in entries: - mode_str = '' + mode_str = b'' for i in xrange(6): mode_str = chr(((mode >> (i * 3)) & bit_mask) + ord_zero) + mode_str # END for each 8 octal value # git slices away the first octal if its zero - if mode_str[0] == '0': + if byte_ord(mode_str[0]) == ord_zero: mode_str = mode_str[1:] # END save a byte @@ -33,16 +36,16 @@ def tree_to_stream(entries, write): # According to my tests, this is exactly what git does, that is it just # takes the input literally, which appears to be utf8 on linux. if isinstance(name, text_type): - name = name.encode("utf8") - write("%s %s\0%s" % (mode_str, name, binsha)) + name = name.encode(defenc) + write(b''.join(mode_str, b' ', name, b'\0', binsha)) # END for each item - def tree_entries_from_data(data): """Reads the binary representation of a tree and returns tuples of Tree items - :param data: data block with tree data + :param data: data block with tree data (as bytes) :return: list(tuple(binsha, mode, tree_relative_path), ...)""" ord_zero = ord('0') + space_ord = ord(' ') len_data = len(data) i = 0 out = list() @@ -52,10 +55,10 @@ def tree_entries_from_data(data): # read mode # Some git versions truncate the leading 0, some don't # The type will be extracted from the mode later - while data[i] != ' ': + while byte_ord(data[i]) != space_ord: # move existing mode integer up one level being 3 bits # and add the actual ordinal value of the character - mode = (mode << 3) + (ord(data[i]) - ord_zero) + mode = (mode << 3) + (byte_ord(data[i]) - ord_zero) i += 1 # END while reading mode @@ -65,7 +68,7 @@ def tree_entries_from_data(data): # parse name, it is NULL separated ns = i - while data[i] != '\0': + while byte_ord(data[i]) != 0: i += 1 # END while not reached NULL @@ -73,12 +76,9 @@ def tree_entries_from_data(data): # Only use the respective unicode object if the byte stream was encoded name = data[ns:i] try: - name_enc = name.decode("utf-8") + name = name.decode(defenc) except UnicodeDecodeError: pass - else: - if len(name) > len(name_enc): - name = name_enc # END handle encoding # byte is NULL, get next 20 |