Add tar archive support

libmat2/epub.py

@@ -5,7 +5,7 @@ import xml.etree.ElementTree as ET  # type: ignore
 
 from . import archive, office
 
-class EPUBParser(archive.ArchiveBasedAbstractParser):
+class EPUBParser(archive.ZipParser):
     mimetypes = {'application/epub+zip', }
     metadata_namespace = '{http://purl.org/dc/elements/1.1/}'
 

libmat2/office.py

@@ -6,7 +6,7 @@ from typing import Dict, Set, Pattern, Tuple, Any
 
 import xml.etree.ElementTree as ET  # type: ignore
 
-from .archive import ArchiveBasedAbstractParser
+from .archive import ZipParser
 
 # pylint: disable=line-too-long
 
@@ -43,7 +43,7 @@ def _sort_xml_attributes(full_path: str) -> bool:
     return True
 
 
-class MSOfficeParser(ArchiveBasedAbstractParser):
+class MSOfficeParser(ZipParser):
     mimetypes = {
         'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
         'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
@@ -312,7 +312,7 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
                 return {file_path: 'harmful content', }
 
 
-class LibreOfficeParser(ArchiveBasedAbstractParser):
+class LibreOfficeParser(ZipParser):
     mimetypes = {
         'application/vnd.oasis.opendocument.text',
         'application/vnd.oasis.opendocument.spreadsheet',

tests/test_corrupted_files.py

 #!/usr/bin/env python3
 
 import unittest
+import time
 import shutil
 import os
 import logging
 import zipfile
+import tarfile
 
 from libmat2 import pdf, images, audio, office, parser_factory, torrent
-from libmat2 import harmless, video, web
+from libmat2 import harmless, video, web, archive
 
 # No need to logging messages, should something go wrong,
 # the testsuite _will_ fail.
@@ -278,7 +280,6 @@ class TestCorruptedFiles(unittest.TestCase):
             p.remove_all()
         os.remove('./tests/data/clean.html')
 
-
     def test_epub(self):
         with zipfile.ZipFile('./tests/data/clean.epub', 'w') as zout:
             zout.write('./tests/data/dirty.jpg', 'OEBPS/content.opf')
@@ -291,3 +292,27 @@ class TestCorruptedFiles(unittest.TestCase):
         self.assertFalse(p.remove_all())
         os.remove('./tests/data/clean.epub')
 
+    def test_tar(self):
+        with tarfile.TarFile('./tests/data/clean.tar', 'w') as zout:
+            zout.add('./tests/data/dirty.flac')
+            zout.add('./tests/data/dirty.docx')
+            zout.add('./tests/data/dirty.jpg')
+            zout.add('./tests/data/embedded_corrupted.docx')
+            tarinfo = tarfile.TarInfo(name='./tests/data/dirty.png')
+            tarinfo.mtime = time.time()
+            tarinfo.uid = 1337
+            tarinfo.gid = 1338
+            with open('./tests/data/dirty.png', 'rb') as f:
+                zout.addfile(tarinfo, f)
+        p, mimetype = parser_factory.get_parser('./tests/data/clean.tar')
+        self.assertEqual(mimetype, 'application/x-tar')
+        meta = p.get_meta()
+        self.assertEqual(meta['./tests/data/dirty.flac']['comments'], 'Thank you for using MAT !')
+        self.assertEqual(meta['./tests/data/dirty.docx']['word/media/image1.png']['Comment'], 'This is a comment, be careful!')
+        self.assertFalse(p.remove_all())
+        os.remove('./tests/data/clean.tar')
+
+        shutil.copy('./tests/data/dirty.png', './tests/data/clean.tar')
+        with self.assertRaises(ValueError):
+            archive.TarParser('./tests/data/clean.tar')
+        os.remove('./tests/data/clean.tar')

tests/test_libmat2.py

@@ -4,6 +4,8 @@ import unittest
 import shutil
 import os
 import re
+import tarfile
+import tempfile
 import zipfile
 
 from libmat2 import pdf, images, audio, office, parser_factory, torrent, harmless
@@ -195,6 +197,19 @@ class TestGetMeta(unittest.TestCase):
         self.assertEqual(meta['version'], '1.0')
         self.assertEqual(meta['harmful data'], 'underline is cool')
 
+    def test_tar(self):
+        with tarfile.TarFile('./tests/data/dirty.tar', 'w') as tout:
+            tout.add('./tests/data/dirty.flac')
+            tout.add('./tests/data/dirty.docx')
+            tout.add('./tests/data/dirty.jpg')
+        p, mimetype = parser_factory.get_parser('./tests/data/dirty.tar')
+        self.assertEqual(mimetype, 'application/x-tar')
+        meta = p.get_meta()
+        self.assertEqual(meta['./tests/data/dirty.flac']['comments'], 'Thank you for using MAT !')
+        self.assertEqual(meta['./tests/data/dirty.docx']['word/media/image1.png']['Comment'], 'This is a comment, be careful!')
+        os.remove('./tests/data/dirty.tar')
+
+
 class TestRemovingThumbnails(unittest.TestCase):
     def test_odt(self):
         shutil.copy('./tests/data/revision.odt', './tests/data/clean.odt')
@@ -702,3 +717,38 @@ class TestCleaning(unittest.TestCase):
         os.remove('./tests/data/clean.css')
         os.remove('./tests/data/clean.cleaned.css')
         os.remove('./tests/data/clean.cleaned.cleaned.css')
+
+    def test_tar(self):
+        with tarfile.TarFile('./tests/data/dirty.tar', 'w') as zout:
+            zout.add('./tests/data/dirty.flac')
+            zout.add('./tests/data/dirty.docx')
+            zout.add('./tests/data/dirty.jpg')
+        p = archive.TarParser('./tests/data/dirty.tar')
+        meta = p.get_meta()
+        self.assertEqual(meta['./tests/data/dirty.docx']['word/media/image1.png']['Comment'], 'This is a comment, be careful!')
+
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        p = archive.TarParser('./tests/data/dirty.cleaned.tar')
+        self.assertEqual(p.get_meta(), {})
+        self.assertTrue(p.remove_all())
+
+        tmp_dir = tempfile.mkdtemp()
+        with tarfile.open('./tests/data/dirty.cleaned.tar') as zout:
+            zout.extractall(path=tmp_dir)
+            zout.close()
+
+        number_of_files = 0
+        for root, _, fnames in os.walk(tmp_dir):
+            for f in fnames:
+                complete_path = os.path.join(root, f)
+                p, _ = parser_factory.get_parser(complete_path)
+                self.assertIsNotNone(p)
+                self.assertEqual(p.get_meta(), {})
+                number_of_files += 1
+        self.assertEqual(number_of_files, 3)
+
+        os.remove('./tests/data/dirty.tar')
+        os.remove('./tests/data/dirty.cleaned.tar')
+        os.remove('./tests/data/dirty.cleaned.cleaned.tar')