Merged revisions 76443 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r76443 | lars.gustaebel | 2009-11-22 19:30:53 +0100 (Sun, 22 Nov 2009) | 24 lines

  Issue #6123: Fix opening empty archives and files.

  (Note that an empty archive is not the same as an empty file. An
  empty archive contains no members and is correctly terminated with an
  EOF block full of zeros. An empty file contains no data at all.)

  The problem was that although tarfile was able to create empty
  archives, it failed to open them raising a ReadError. On the other
  hand, tarfile opened empty files without error in most read modes and
  presented them as empty archives. (However, some modes still raised
  errors: "r|gz" raised ReadError, but "r:gz" worked, "r:bz2" even
  raised EOFError.)

  In order to get a more fine-grained control over the various internal
  error conditions I now split up the HeaderError exception into a
  number of meaningful sub-exceptions. This makes it easier in the
  TarFile.next() method to react to the different conditions in the
  correct way.

  The visible change in its behaviour now is that tarfile will open
  empty archives correctly and raise ReadError consistently for empty
  files.
........

1 files changed, 60 insertions, 27 deletions

diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 6ce5fb1aad..55bb4e3f15 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -194,7 +194,7 @@ def nti(s):
         try:
             n = int(nts(s, "ascii", "strict") or "0", 8)
         except ValueError:
-            raise HeaderError("invalid header")
+            raise InvalidHeaderError("invalid header")
     else:
         n = 0
         for i in range(len(s) - 1):
@@ -325,8 +325,23 @@ class StreamError(TarError):
     """Exception for unsupported operations on stream-like TarFiles."""
     pass
 class HeaderError(TarError):
+    """Base exception for header errors."""
+    pass
+class EmptyHeaderError(HeaderError):
+    """Exception for empty headers."""
+    pass
+class TruncatedHeaderError(HeaderError):
+    """Exception for truncated headers."""
+    pass
+class EOFHeaderError(HeaderError):
+    """Exception for end of file headers."""
+    pass
+class InvalidHeaderError(HeaderError):
     """Exception for invalid headers."""
     pass
+class SubsequentHeaderError(HeaderError):
+    """Exception for missing and invalid extended headers."""
+    pass
 
 #---------------------------
 # internal stream interface
@@ -1171,14 +1186,16 @@ class TarInfo(object):
     def frombuf(cls, buf, encoding, errors):
         """Construct a TarInfo object from a 512 byte bytes object.
         """
+        if len(buf) == 0:
+            raise EmptyHeaderError("empty header")
         if len(buf) != BLOCKSIZE:
-            raise HeaderError("truncated header")
+            raise TruncatedHeaderError("truncated header")
         if buf.count(NUL) == BLOCKSIZE:
-            raise HeaderError("empty header")
+            raise EOFHeaderError("end of file header")
 
         chksum = nti(buf[148:156])
         if chksum not in calc_chksums(buf):
-            raise HeaderError("bad checksum")
+            raise InvalidHeaderError("bad checksum")
 
         obj = cls()
         obj.name = nts(buf[0:100], encoding, errors)
@@ -1234,8 +1251,6 @@ class TarInfo(object):
            tarfile.
         """
         buf = tarfile.fileobj.read(BLOCKSIZE)
-        if not buf:
-            return
         obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors)
         obj.offset = tarfile.fileobj.tell() - BLOCKSIZE
         return obj._proc_member(tarfile)
@@ -1288,9 +1303,10 @@ class TarInfo(object):
         buf = tarfile.fileobj.read(self._block(self.size))
 
         # Fetch the next header and process it.
-        next = self.fromtarfile(tarfile)
-        if next is None:
-            raise HeaderError("missing subsequent header")
+        try:
+            next = self.fromtarfile(tarfile)
+        except HeaderError:
+            raise SubsequentHeaderError("missing or bad subsequent header")
 
         # Patch the TarInfo object from the next header with
         # the longname information.
@@ -1380,12 +1396,12 @@ class TarInfo(object):
             pos += length
 
         # Fetch the next header.
-        next = self.fromtarfile(tarfile)
+        try:
+            next = self.fromtarfile(tarfile)
+        except HeaderError:
+            raise SubsequentHeaderError("missing or bad subsequent header")
 
         if self.type in (XHDTYPE, SOLARIS_XHDTYPE):
-            if next is None:
-                raise HeaderError("missing subsequent header")
-
             # Patch the TarInfo object with the extended header info.
             next._apply_pax_info(pax_headers, tarfile.encoding, tarfile.errors)
             next.offset = self.offset
@@ -1557,12 +1573,16 @@ class TarFile(object):
             if self.mode == "a":
                 # Move to the end of the archive,
                 # before the first empty block.
-                self.firstmember = None
                 while True:
-                    if self.next() is None:
-                        if self.offset > 0:
-                            self.fileobj.seek(self.fileobj.tell() - BLOCKSIZE)
+                    self.fileobj.seek(self.offset)
+                    try:
+                        tarinfo = self.tarinfo.fromtarfile(self)
+                        self.members.append(tarinfo)
+                    except EOFHeaderError:
+                        self.fileobj.seek(self.offset)
                         break
+                    except HeaderError as e:
+                        raise ReadError(str(e))
 
             if self.mode in "aw":
                 self._loaded = True
@@ -1715,7 +1735,7 @@ class TarFile(object):
 
         try:
             t = cls.taropen(name, mode, fileobj, **kwargs)
-        except IOError:
+        except (IOError, EOFError):
             raise ReadError("not a bzip2 file")
         t._extfileobj = False
         return t
@@ -2287,24 +2307,37 @@ class TarFile(object):
 
         # Read the next block.
         self.fileobj.seek(self.offset)
+        tarinfo = None
         while True:
             try:
                 tarinfo = self.tarinfo.fromtarfile(self)
-                if tarinfo is None:
-                    return
-                self.members.append(tarinfo)
-
-            except HeaderError as e:
+            except EOFHeaderError as e:
                 if self.ignore_zeros:
                     self._dbg(2, "0x%X: %s" % (self.offset, e))
                     self.offset += BLOCKSIZE
                     continue
-                else:
-                    if self.offset == 0:
-                        raise ReadError(str(e))
-                    return None
+            except InvalidHeaderError as e:
+                if self.ignore_zeros:
+                    self._dbg(2, "0x%X: %s" % (self.offset, e))
+                    self.offset += BLOCKSIZE
+                    continue
+                elif self.offset == 0:
+                    raise ReadError(str(e))
+            except EmptyHeaderError:
+                if self.offset == 0:
+                    raise ReadError("empty file")
+            except TruncatedHeaderError as e:
+                if self.offset == 0:
+                    raise ReadError(str(e))
+            except SubsequentHeaderError as e:
+                raise ReadError(str(e))
             break
 
+        if tarinfo is not None:
+            self.members.append(tarinfo)
+        else:
+            self._loaded = True
+
         return tarinfo
 
     #--------------------------------------------------------------------------