From 5e78c0e036375a1db3da88a1546abe968db33dad Mon Sep 17 00:00:00 2001
From: jvoisin <julien.voisin@dustri.org>
Date: Tue, 9 Oct 2018 17:08:57 +0200
Subject: [PATCH] Implement lightweight mode of msoffice files
---
libmat2/abstract.py | 10 ++--------
libmat2/office.py | 5 +++--
libmat2/pdf.py | 7 ++++++-
mat2 | 3 +--
tests/test_libmat2.py | 25 +++++++++++++++++++++++--
5 files changed, 35 insertions(+), 15 deletions(-)
diff --git a/libmat2/abstract.py b/libmat2/abstract.py
index cd72f2c..889c6c8 100644
--- a/libmat2/abstract.py
+++ b/libmat2/abstract.py
@@ -12,13 +12,14 @@ class AbstractParser(abc.ABC):
meta_list = set() # type: Set[str]
mimetypes = set() # type: Set[str]
- def __init__(self, filename: str) -> None:
+ def __init__(self, filename: str, lightweight_cleaning: bool=False) -> None:
"""
:raises ValueError: Raised upon an invalid file
"""
self.filename = filename
fname, extension = os.path.splitext(filename)
self.output_filename = fname + '.cleaned' + extension
+ self.lightweight_cleaning = lightweight_cleaning
@abc.abstractmethod
def get_meta(self) -> Dict[str, str]:
@@ -27,10 +28,3 @@ class AbstractParser(abc.ABC):
@abc.abstractmethod
def remove_all(self) -> bool:
pass # pragma: no cover
-
- def remove_all_lightweight(self) -> bool:
- """ This method removes _SOME_ metadata.
- It might be useful to implement it for fileformats that do
- not support non-destructive cleaning.
- """
- return self.remove_all()
diff --git a/libmat2/office.py b/libmat2/office.py
index 32e7b75..afb5e33 100644
--- a/libmat2/office.py
+++ b/libmat2/office.py
@@ -267,8 +267,9 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
f.write(b'</cp:coreProperties>')
- if self.__remove_rsid(full_path) is False:
- return False
+ if self.lightweight_cleaning is False:
+ if self.__remove_rsid(full_path) is False:
+ return False
try:
_sort_xml_attributes(full_path)
diff --git a/libmat2/pdf.py b/libmat2/pdf.py
index c8769aa..b6b782e 100644
--- a/libmat2/pdf.py
+++ b/libmat2/pdf.py
@@ -37,7 +37,7 @@ class PDFParser(abstract.AbstractParser):
except GLib.GError: # Invalid PDF
raise ValueError
- def remove_all_lightweight(self):
+ def __remove_all_ligthweight(self) -> bool:
"""
Load the document into Poppler, render pages on a new PDFSurface.
"""
@@ -65,6 +65,11 @@ class PDFParser(abstract.AbstractParser):
return True
def remove_all(self):
+ if self.lightweight_cleaning is True:
+ return self.__remove_all_ligthweight()
+ return self.__remove_all_complete()
+
+ def __remove_all_complete(self) -> bool:
"""
Load the document into Poppler, render pages on PNG,
and shove those PNG into a new PDF.
diff --git a/mat2 b/mat2
index 987e439..722b3f7 100755
--- a/mat2
+++ b/mat2
@@ -87,8 +87,7 @@ def clean_meta(filename: str, is_lightweight: bool, policy: UnknownMemberPolicy)
print("[-] %s's format (%s) is not supported" % (filename, mtype))
return False
p.unknown_member_policy = policy
- if is_lightweight:
- return p.remove_all_lightweight()
+ p.lightwith_cleaning = is_lightweight
return p.remove_all()
diff --git a/tests/test_libmat2.py b/tests/test_libmat2.py
index 957503d..e6f238e 100644
--- a/tests/test_libmat2.py
+++ b/tests/test_libmat2.py
@@ -182,6 +182,25 @@ class TestRevisionsCleaning(unittest.TestCase):
os.remove('./tests/data/revision_clean.cleaned.docx')
class TestLightWeightCleaning(unittest.TestCase):
+ def test_msoffice(self):
+ shutil.copy('./tests/data/dirty.docx', './tests/data/clean.docx')
+ p = office.MSOfficeParser('./tests/data/clean.docx')
+
+ meta = p.get_meta()
+ self.assertEqual(meta['cp:lastModifiedBy'], 'Julien Voisin')
+
+ p.lightweight_cleaning = True
+ ret = p.remove_all()
+ self.assertTrue(ret)
+
+ # FIXME blocked by https://0xacab.org/jvoisin/mat2/issues/73
+ #p = office.MSOfficeParser('./tests/data/clean.cleaned.docx')
+ #expected_meta = {'creation-date': -1, 'format': 'docx-1.5', 'mod-date': -1}
+ #self.assertEqual(p.get_meta(), expected_meta)
+
+ os.remove('./tests/data/clean.docx')
+ os.remove('./tests/data/clean.cleaned.docx')
+
def test_pdf(self):
shutil.copy('./tests/data/dirty.pdf', './tests/data/clean.pdf')
p = pdf.PDFParser('./tests/data/clean.pdf')
@@ -189,7 +208,8 @@ class TestLightWeightCleaning(unittest.TestCase):
meta = p.get_meta()
self.assertEqual(meta['producer'], 'pdfTeX-1.40.14')
- ret = p.remove_all_lightweight()
+ p.lightweight_cleaning = True
+ ret = p.remove_all()
self.assertTrue(ret)
p = pdf.PDFParser('./tests/data/clean.cleaned.pdf')
@@ -206,7 +226,8 @@ class TestLightWeightCleaning(unittest.TestCase):
meta = p.get_meta()
self.assertEqual(meta['Comment'], 'This is a comment, be careful!')
- ret = p.remove_all_lightweight()
+ p.lightweight_cleaning = True
+ ret = p.remove_all()
self.assertTrue(ret)
p = images.PNGParser('./tests/data/clean.cleaned.png')
--
GitLab