Compare revisions

2b58eece · 2b58eece · 2b58eece · 2b58eece · 2b58eece · 2b58eece
--- a/tests/data/dirty.html
+++ b/tests/data/dirty.html
+<html>
+	<head>
+		<meta content="vim" name="generator"/>
+		<meta content="jvoisin" name="author"/>
+</head>
+<body>
+	<p>
+		<h1>Hello</h1>
+		I am a web page.
+		Please <b>love</b> me.
+		Here, have a pretty picture: <img src='dirty.jpg' alt='a pretty picture'/>
+	</p>
+</body>
+</html>
--- a/tests/data/dirty.mp4
+++ b/tests/data/dirty.mp4
--- a/tests/data/dirty.ppm
+++ b/tests/data/dirty.ppm
+P3
+# A metadata
+3 2 1
+1 0 1   0 1 0   0 0 1
+# And an other one
+1 1 0   1 0 1   1 0 0
+  # and a final one here
+
--- a/tests/data/dirty.svg
+++ b/tests/data/dirty.svg
--- a/tests/data/dirty.wav
+++ b/tests/data/dirty.wav
--- a/tests/data/dirty.webp
+++ b/tests/data/dirty.webp
--- a/tests/data/dirty.wmv
+++ b/tests/data/dirty.wmv
--- a/tests/data/dirty_with_nsid.docx
+++ b/tests/data/dirty_with_nsid.docx
--- a/tests/data/embedded.docx
+++ b/tests/data/embedded.docx
--- a/tests/data/embedded.odt
+++ b/tests/data/embedded.odt
--- a/tests/data/malformed_content_types.docx
+++ b/tests/data/malformed_content_types.docx
--- a/tests/data/narrated_powerpoint_presentation.pptx
+++ b/tests/data/narrated_powerpoint_presentation.pptx
--- a/tests/data/weird.svg
+++ b/tests/data/weird.svg
--- a/tests/fuzz.py
+++ b/tests/fuzz.py
+import mimetypes
+import os
+import sys
+
+sys.path.append('..')
+
+import atheris
+
+with atheris.instrument_imports(enable_loader_override=False):
+    from libmat2 import parser_factory, UNSUPPORTED_EXTENSIONS
+
+extensions = set()
+for parser in parser_factory._get_parsers():  # type: ignore
+    for mtype in parser.mimetypes:
+        if mtype.startswith('video'):
+            continue
+        if 'aif' in mtype:
+            continue
+        if 'wav' in mtype:
+            continue
+        if 'gif' in mtype:
+            continue
+        if 'aifc' in mtype:
+            continue
+        for extension in mimetypes.guess_all_extensions(mtype):
+            if extension not in UNSUPPORTED_EXTENSIONS:
+                extensions.add(extension)
+extensions = list(extensions)
+
+
+
+def TestOneInput(data):
+    fdp = atheris.FuzzedDataProvider(data)
+    extension = fdp.PickValueInList(extensions)
+    data = fdp.ConsumeBytes(sys.maxsize)
+
+    fname = '/tmp/mat2_fuzz' + extension
+
+    with open(fname, 'wb') as f:
+        f.write(data)
+    try:
+        p, _ = parser_factory.get_parser(fname)
+        if p:
+            p.sandbox = False
+            p.get_meta()
+            p.remove_all()
+            p, _ = parser_factory.get_parser(fname)
+            p.get_meta()
+    except ValueError:
+        pass
+    os.remove(fname)
+
+atheris.Setup(sys.argv, TestOneInput)
+atheris.Fuzz()
--- a/tests/test_climat2.py
+++ b/tests/test_climat2.py
--- a/tests/test_corrupted_files.py
+++ b/tests/test_corrupted_files.py
--- a/tests/test_deep_cleaning.py
+++ b/tests/test_deep_cleaning.py
@@ -36,6 +36,7 @@ class TestZipMetadata(unittest.TestCase):

        meta = p.get_meta()
        self.assertIsNotNone(meta)
+        self.assertEqual(meta['word/media/image1.png']['Comment'], 'This is a comment, be careful!')

        ret = p.remove_all()
        self.assertTrue(ret)
@@ -82,6 +83,8 @@ class TestZipOrder(unittest.TestCase):
            previous_name = ''
            for item in zin.infolist():
                if previous_name == '':
+                    if item.filename == 'mimetype':
+                        continue
                    previous_name = item.filename
                    continue
                elif item.filename < previous_name:
@@ -96,6 +99,8 @@ class TestZipOrder(unittest.TestCase):
            previous_name = ''
            for item in zin.infolist():
                if previous_name == '':
+                    if item.filename == 'mimetype':
+                        continue
                    previous_name = item.filename
                    continue
                self.assertGreaterEqual(item.filename, previous_name)
@@ -132,3 +137,34 @@ class TestRsidRemoval(unittest.TestCase):

        os.remove('./tests/data/clean.docx')
        os.remove('./tests/data/clean.cleaned.docx')
+
+
+class TestNsidRemoval(unittest.TestCase):
+    def test_office(self):
+        shutil.copy('./tests/data/dirty_with_nsid.docx', './tests/data/clean.docx')
+        p = office.MSOfficeParser('./tests/data/clean.docx')
+
+        meta = p.get_meta()
+        self.assertIsNotNone(meta)
+
+        how_many_rsid = False
+        with zipfile.ZipFile('./tests/data/clean.docx') as zin:
+            for item in zin.infolist():
+                if not item.filename.endswith('.xml'):
+                    continue
+                num = zin.read(item).decode('utf-8').lower().count('w:rsid')
+                how_many_rsid += num
+        self.assertEqual(how_many_rsid, 1190)
+
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        with zipfile.ZipFile('./tests/data/clean.cleaned.docx') as zin:
+            for item in zin.infolist():
+                if not item.filename.endswith('.xml'):
+                    continue
+                num = zin.read(item).decode('utf-8').lower().count('w:nsid')
+                self.assertEqual(num, 0)
+
+        os.remove('./tests/data/clean.docx')
+        os.remove('./tests/data/clean.cleaned.docx')
--- a/tests/test_libmat2.py
+++ b/tests/test_libmat2.py
--- a/tests/test_lightweight_cleaning.py
+++ b/tests/test_lightweight_cleaning.py
--- a/tests/test_policy.py
+++ b/tests/test_policy.py
No results found