Add support for docx

3 files changed, 72 insertions, 0 deletions

diff --git a/src/office.py b/src/office.py
new file mode 100644
index 0000000..d6728c8
--- /dev/null
+++ b/src/office.py
@@ -0,0 +1,52 @@
+import subprocess
+import json
+import zipfile
+import tempfile
+import shutil
+import os
+
+from . import abstract, parser_factory
+
+class OfficeParser(abstract.AbstractParser):
+    mimetypes = {
+            'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+            'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
+            'application/vnd.openxmlformats-officedocument.presentationml.presentation'
+    }
+    files_to_keep = {'_rels/.rels', 'word/_rels/document.xml.rels'}
+
+    def get_meta(self):
+        metadata = {}
+        zipin = zipfile.ZipFile(self.filename)
+        for item in zipin.namelist():
+            if item.startswith('docProps/'):
+                metadata[item] = 'harmful content'
+        zipin.close()
+        return metadata
+
+    def remove_all(self):
+        zin = zipfile.ZipFile(self.filename, 'r')
+        zout = zipfile.ZipFile(self.output_filename, 'w')
+        temp_folder = tempfile.mkdtemp()
+
+        for item in zin.infolist():
+            if item.is_dir():
+                continue
+            elif item.filename.startswith('docProps/'):
+                if not item.filename.endswith('.rels'):
+                    continue  # don't keep metadata files
+            if item.filename in self.files_to_keep:
+                zout.writestr(item, zin.read(item))
+                continue
+
+            zin.extract(member=item, path=temp_folder)
+            tmp_parser = parser_factory.get_parser(os.path.join(temp_folder, item.filename))
+            if tmp_parser is None:
+                print("%s isn't supported" % item.filename)
+                continue
+            tmp_parser.remove_all()
+            zout.write(tmp_parser.output_filename, item.filename)
+        shutil.rmtree(temp_folder)
+        zout.close()
+        zin.close()
+        return True
diff --git a/tests/data/dirty.docx b/tests/data/dirty.docx
new file mode 100644
index 0000000..97e2c21
--- /dev/null
+++ b/tests/data/dirty.docx
diff --git a/tests/test_libmat2.py b/tests/test_libmat2.py
index c21185e..02579b0 100644
--- a/tests/test_libmat2.py
+++ b/tests/test_libmat2.py
@@ -39,6 +39,11 @@ class TestGetMeta(unittest.TestCase):
         meta = p.get_meta()
         self.assertEqual(meta['TITLE'], ['I am so'])
 
+    def test_docx(self):
+        p = office.OfficeParser('./tests/data/dirty.docx')
+        meta = p.get_meta()
+        print(meta)
+
 
 class TestCleaning(unittest.TestCase):
     def test_pdf(self):
@@ -131,3 +136,18 @@ class TestCleaning(unittest.TestCase):
         self.assertEqual(p.get_meta(), {})
 
         os.remove('./tests/data/clean.flac')
+
+    def test_office(self):
+        shutil.copy('./tests/data/dirty.docx', './tests/data/clean.docx')
+        p = office.OfficeParser('./tests/data/clean.docx')
+
+        meta = p.get_meta()
+        self.assertIsNotNone(meta)
+
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        p = office.OfficeParser('./tests/data/clean.docx.cleaned')
+        self.assertEqual(p.get_meta(), {})
+
+        os.remove('./tests/data/clean.docx')