Add support for .odt

src/libreoffice.py

+import re
+import subprocess
+import json
+import zipfile
+import tempfile
+import shutil
+import os
+
+from . import abstract, parser_factory
+
+class LibreOfficeParser(abstract.AbstractParser):
+    mimetypes = {
+            'application/vnd.oasis.opendocument.text',
+    }
+
+    def get_meta(self):
+        """
+        Yes, I know that parsing xml with regexp ain't pretty,
+        be my guest and fix it if you want.
+        """
+        metadata = {}
+        zipin = zipfile.ZipFile(self.filename)
+        for item in zipin.namelist():
+            if item == 'meta.xml':
+                content = zipin.read(item).decode('utf-8')
+                for (key, value) in re.findall(r"<((?:meta|dc).+?)>(.+)</\1>", content, re.I):
+                    metadata[key] = value
+                if not metadata:  # better safe than sorry
+                    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.filename[-1] == '/':
+                continue  # `is_dir` is added in Python3.6
+            elif item.filename == 'meta.xml':
+                    continue  # don't keep metadata files
+
+            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

tests/test_libmat2.py

@@ -4,7 +4,7 @@ import unittest
 import shutil
 import os
 
-from src import pdf, png, jpg, audio, office
+from src import pdf, png, jpg, audio, office, libreoffice
 
 class TestGetMeta(unittest.TestCase):
     def test_pdf(self):
@@ -46,6 +46,14 @@ class TestGetMeta(unittest.TestCase):
         self.assertEqual(meta['dc:creator'], 'julien voisin')
         self.assertEqual(meta['Application'], 'LibreOffice/5.4.5.1$Linux_X86_64 LibreOffice_project/40m0$Build-1')
 
+    def test_libreoffice(self):
+        p = libreoffice.LibreOfficeParser('./tests/data/dirty.odt')
+        meta = p.get_meta()
+        self.assertEqual(meta['meta:initial-creator'], 'jvoisin ')
+        self.assertEqual(meta['meta:creation-date'], '2011-07-26T03:27:48')
+        self.assertEqual(meta['meta:generator'], 'LibreOffice/3.3$Unix LibreOffice_project/330m19$Build-202')
+
+
 
 class TestCleaning(unittest.TestCase):
     def test_pdf(self):
@@ -153,3 +161,19 @@ class TestCleaning(unittest.TestCase):
         self.assertEqual(p.get_meta(), {})
 
         os.remove('./tests/data/clean.docx')
+
+
+    def test_libreoffice(self):
+        shutil.copy('./tests/data/dirty.odt', './tests/data/clean.odt')
+        p = libreoffice.LibreOfficeParser('./tests/data/clean.odt')
+
+        meta = p.get_meta()
+        self.assertIsNotNone(meta)
+
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        p = libreoffice.LibreOfficeParser('./tests/data/clean.odt.cleaned')
+        self.assertEqual(p.get_meta(), {})
+
+        os.remove('./tests/data/clean.odt')