If BadZipFile is raised we should catch it and raise a different exception instead

CHANGELOG

@@ -1,6 +1,9 @@
 
 Changelog
 =========
+* 0.3.8
+    * If zipfile fails to open the passed in file, we are now raising a
+      `MalformedDocxException` instead of a `BadZipFIle`.
 * 0.3.7
     * Some inline tags (most notably the underline tag) could have a `val` of
       `none` and that would signify that the style is disabled. A `val` of

README.rst

@@ -222,6 +222,11 @@ The base parser `Docx2Html` relies on certain css class being set for certain be
 * class `pydocx-strike` -> Strike a line through.
 * class `pydocx-hidden` -> Hide the text.
 
+Exceptions
+##########
+
+Right now there is only one custom exception (`MalformedDocxException`). It is raised if either the `xml` or `zipfile` libraries raise an exception.
+
 Optional Arguments
 ##################
 

pydocx/DocxParser.py

@@ -14,6 +14,7 @@
     find_ancestor_with_tag,
     has_descendant_with_tag,
 )
+from pydocx.exceptions import MalformedDocxException
 
 logging.basicConfig(level=logging.DEBUG)
 logger = logging.getLogger("NewParser")
@@ -37,7 +38,10 @@
 
 @contextmanager
 def ZipFile(path):  # This is not needed in python 3.2+
-    f = zipfile.ZipFile(path)
+    try:
+        f = zipfile.ZipFile(path)
+    except zipfile.BadZipfile:
+        raise MalformedDocxException('Passed in document is not a docx')
     yield f
     f.close()
 

pydocx/tests/test_docx.py

@@ -1,12 +1,14 @@
 import base64
-
 from os import path
+from tempfile import NamedTemporaryFile
 
 from nose.plugins.skip import SkipTest
+from nose.tools import raises
 
 from pydocx.tests import assert_html_equal, BASE_HTML
 from pydocx.parsers.Docx2Html import Docx2Html
 from pydocx.DocxParser import ZipFile
+from pydocx.exceptions import MalformedDocxException
 
 
 def convert(path, *args, **kwargs):
@@ -749,6 +751,12 @@ def test_missing_numbering():
     ''')
 
 
+@raises(MalformedDocxException)
+def test_malformed_docx_exception():
+    with NamedTemporaryFile(suffix='.docx') as f:
+        convert(f.name)
+
+
 def _converter(*args, **kwargs):
     # Having a converter that does nothing is the same as if abiword fails to
     # convert.