[Python-checkins] cpython (merge 3.3 -> default): Issue #4844: ZipFile now raises BadZipFile when opens a ZIP file with an

[serhiy.storchaka]

http://hg.python.org/cpython/rev/e406b8bd7b38
changeset:   81850:e406b8bd7b38
parent:      81846:022477b09dc3
parent:      81849:46f24a18a4ab
user:        Serhiy Storchaka <storchaka at gmail.com>
date:        Thu Jan 31 15:30:36 2013 +0200
summary:
  Issue #4844: ZipFile now raises BadZipFile when opens a ZIP file with an
incomplete "End of Central Directory" record.  Original patch by Guilherme
Polo and Alan McIntyre.

files:
  Lib/test/test_zipfile.py |  14 ++++++++++++++
  Lib/zipfile.py           |  25 +++++++++++++++++++------
  Misc/NEWS                |   4 ++++
  3 files changed, 37 insertions(+), 6 deletions(-)


diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py
--- a/Lib/test/test_zipfile.py
+++ b/Lib/test/test_zipfile.py
@@ -996,6 +996,20 @@
         chk = zipfile.is_zipfile(fp)
         self.assertTrue(not chk)
 
+    def test_damaged_zipfile(self):
+        """Check that zipfiles with missing bytes at the end raise BadZipFile."""
+        # - Create a valid zip file
+        fp = io.BytesIO()
+        with zipfile.ZipFile(fp, mode="w") as zipf:
+            zipf.writestr("foo.txt", b"O, for a Muse of Fire!")
+        zipfiledata = fp.getvalue()
+
+        # - Now create copies of it missing the last N bytes and make sure
+        #   a BadZipFile exception is raised when we try to open it
+        for N in range(len(zipfiledata)):
+            fp = io.BytesIO(zipfiledata[:N])
+            self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, fp)
+
     def test_is_zip_valid_file(self):
         """Check that is_zipfile() correctly identifies zip files."""
         # - passing a filename
diff --git a/Lib/zipfile.py b/Lib/zipfile.py
--- a/Lib/zipfile.py
+++ b/Lib/zipfile.py
@@ -196,6 +196,8 @@
         return endrec
 
     data = fpin.read(sizeEndCentDir64Locator)
+    if len(data) != sizeEndCentDir64Locator:
+        return endrec
     sig, diskno, reloff, disks = struct.unpack(structEndArchive64Locator, data)
     if sig != stringEndArchive64Locator:
         return endrec
@@ -206,6 +208,8 @@
     # Assume no 'zip64 extensible data'
     fpin.seek(offset - sizeEndCentDir64Locator - sizeEndCentDir64, 2)
     data = fpin.read(sizeEndCentDir64)
+    if len(data) != sizeEndCentDir64:
+        return endrec
     sig, sz, create_version, read_version, disk_num, disk_dir, \
             dircount, dircount2, dirsize, diroffset = \
             struct.unpack(structEndArchive64, data)
@@ -241,7 +245,9 @@
     except OSError:
         return None
     data = fpin.read()
-    if data[0:4] == stringEndArchive and data[-2:] == b"\000\000":
+    if (len(data) == sizeEndCentDir and
+        data[0:4] == stringEndArchive and
+        data[-2:] == b"\000\000"):
         # the signature is correct and there's no comment, unpack structure
         endrec = struct.unpack(structEndArchive, data)
         endrec=list(endrec)
@@ -265,6 +271,9 @@
     if start >= 0:
         # found the magic number; attempt to unpack and interpret
         recData = data[start:start+sizeEndCentDir]
+        if len(recData) != sizeEndCentDir:
+            # Zip file is corrupted.
+            return None
         endrec = list(struct.unpack(structEndArchive, recData))
         commentSize = endrec[_ECD_COMMENT_SIZE] #as claimed by the zip file
         comment = data[start+sizeEndCentDir:start+sizeEndCentDir+commentSize]
@@ -276,7 +285,7 @@
                              endrec)
 
     # Unable to find a valid end of central directory structure
-    return
+    return None
 
 
 class ZipInfo (object):
@@ -978,9 +987,11 @@
         total = 0
         while total < size_cd:
             centdir = fp.read(sizeCentralDir)
-            if centdir[0:4] != stringCentralDir:
+            if len(centdir) != sizeCentralDir:
+                raise BadZipFile("Truncated central directory")
+            centdir = struct.unpack(structCentralDir, centdir)
+            if centdir[_CD_SIGNATURE] != stringCentralDir:
                 raise BadZipFile("Bad magic number for central directory")
-            centdir = struct.unpack(structCentralDir, centdir)
             if self.debug > 2:
                 print(centdir)
             filename = fp.read(centdir[_CD_FILENAME_LENGTH])
@@ -1123,10 +1134,12 @@
 
             # Skip the file header:
             fheader = zef_file.read(sizeFileHeader)
-            if fheader[0:4] != stringFileHeader:
+            if len(fheader) != sizeFileHeader:
+                raise BadZipFile("Truncated file header")
+            fheader = struct.unpack(structFileHeader, fheader)
+            if fheader[_FH_SIGNATURE] != stringFileHeader:
                 raise BadZipFile("Bad magic number for file header")
 
-            fheader = struct.unpack(structFileHeader, fheader)
             fname = zef_file.read(fheader[_FH_FILENAME_LENGTH])
             if fheader[_FH_EXTRA_FIELD_LENGTH]:
                 zef_file.read(fheader[_FH_EXTRA_FIELD_LENGTH])
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -236,6 +236,10 @@
 Library
 -------
 
+- Issue #4844: ZipFile now raises BadZipFile when opens a ZIP file with an
+  incomplete "End of Central Directory" record.  Original patch by Guilherme
+  Polo and Alan McIntyre.
+
 - Issue #17071: Signature.bind() now works when one of the keyword arguments
   is named ``self``.
 

-- 
Repository URL: http://hg.python.org/cpython