Commit e342671e authored by jvoisin's avatar jvoisin

Remove dangling references in MS Office's [Content_types].xml

parent 212d9c47
Pipeline #19218 failed with stages
in 48 seconds
......@@ -151,10 +151,44 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
return True
def __remove_content_type_members(self, full_path: str) -> bool:
""" The method will remove the dangling references
form the [Content_Types].xml file, since MS office doesn't like them
tree, namespace = _parse_xml(full_path)
except ET.ParseError: # pragma: no cover
return False
if len(namespace.items()) != 1:
return False # there should be only one namespace for Types
removed_fnames = set()
with zipfile.ZipFile(self.filename) as zin:
for fname in [item.filename for item in zin.infolist()]:
if any(map(lambda r:, self.files_to_omit)):
root = tree.getroot()
for item in root.findall('{%s}Override' % namespace['']):
name = item.attrib['PartName'][1:] # remove the leading '/'
if name in removed_fnames:
tree.write(full_path, xml_declaration=True)
return True
def _specific_cleanup(self, full_path: str) -> bool:
if os.stat(full_path).st_size == 0: # Don't process empty files
return True
if full_path.endswith('/[Content_Types].xml'):
# this file contains references to files that we might
# remove, and MS Office doesn't like dangling references
if self.__remove_content_type_members(full_path) is False:
return False
if full_path.endswith('/word/document.xml'):
# this file contains the revisions
if self.__remove_revisions(full_path) is False:
......@@ -80,6 +80,14 @@ class TestExplicitelyUnsupportedFiles(unittest.TestCase):
class TestCorruptedContentTypesOffice(unittest.TestCase):
def test_office(self):
shutil.copy('./tests/data/malformed_content_types.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
class TestCorruptedFiles(unittest.TestCase):
def test_pdf(self):
shutil.copy('./tests/data/dirty.png', './tests/data/clean.png')
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment