push more functionality into DebExtractor

The handle_ar_member and handle_ar_end methods now have a default
implementation adding further handlers handle_debversion,
handle_control_tar and handle_data_tar.

In that process two additional bugs were fixed:
 * decompress_tar was wrongly passing errors="surrogateescape" for
   Python 2.x even though that's only supported for Python 3.x.
 * The use of decompress actually passes the extension as unicode.

1 files changed, 5 insertions, 5 deletions

diff --git a/dedup/compression.py b/dedup/compression.py
index 5df6613..7f6dc99 100644
--- a/dedup/compression.py
+++ b/dedup/compression.py
@@ -156,10 +156,10 @@ class DecompressedStream(object):
             self.closed = True
 
 decompressors = {
-    '.gz':   GzipDecompressor,
-    '.bz2':  bz2.BZ2Decompressor,
-    '.lzma': lzma.LZMADecompressor,
-    '.xz':   lzma.LZMADecompressor,
+    u'.gz':   GzipDecompressor,
+    u'.bz2':  bz2.BZ2Decompressor,
+    u'.lzma': lzma.LZMADecompressor,
+    u'.xz':   lzma.LZMADecompressor,
 }
 
 def decompress(filelike, extension):
@@ -168,7 +168,7 @@ def decompress(filelike, extension):
                      close().
     @param extension: permitted values are "", ".gz", ".bz2", ".lzma", and
                       ".xz"
-    @type extension: str
+    @type extension: unicode
     @returns: a read-only byte-stream with the decompressed contents of the
               original filelike. It supports read(size) and close(). If the
               original supports seek(pos) and tell(), then it also supports