Implement lightweight cleaning for png and tiff

7 files changed, 111 insertions, 43 deletions

diff --git a/.pylintrc b/.pylintrc
index 1f3dc23..31fad0e 100644
--- a/.pylintrc
+++ b/.pylintrc
@@ -6,11 +6,12 @@ max-locals=20
 disable=
     fixme,
     invalid-name,
+    duplicate-code,
     missing-docstring,
     protected-access,
-                abstract-method,
-                wrong-import-position,
-                catching-non-exception,
-                cell-var-from-loop,
-                locally-disabled,
-                invalid-sequence-index,  # pylint doesn't like things like `Tuple[int, bytes]` in type annotation
+    abstract-method,
+    wrong-import-position,
+    catching-non-exception,
+    cell-var-from-loop,
+    locally-disabled,
+    invalid-sequence-index,  # pylint doesn't like things like `Tuple[int, bytes]` in type annotation
diff --git a/libmat2/exiftool.py b/libmat2/exiftool.py
index 11dd36d..23d0d89 100644
--- a/libmat2/exiftool.py
+++ b/libmat2/exiftool.py
@@ -1,4 +1,5 @@
 import json
+import logging
 import os
 import subprocess
 from typing import Dict, Union, Set
@@ -23,6 +24,34 @@ class ExiftoolParser(abstract.AbstractParser):
             meta.pop(key, None)
         return meta
 
+    def _lightweight_cleanup(self):
+        if os.path.exists(self.output_filename):
+            try:
+                # exiftool can't force output to existing files
+                os.remove(self.output_filename)
+            except OSError as e:  # pragma: no cover
+                logging.error("The output file %s is already existing and \
+                               can't be overwritten: %s.", self.filename, e)
+                return False
+
+        # Note: '-All=' must be followed by a known exiftool option.
+        # Also, '-CommonIFD0' is needed for .tiff files
+        cmd = [_get_exiftool_path(),
+               '-all=',         # remove metadata
+               '-adobe=',       # remove adobe-specific metadata
+               '-exif:all=',    # remove all exif metadata
+               '-Time:All=',    # remove all timestamps
+               '-quiet',        # don't show useless logs
+               '-CommonIFD0=',  # remove IFD0 metadata
+               '-o', self.output_filename,
+               self.filename]
+        try:
+            subprocess.check_call(cmd)
+        except subprocess.CalledProcessError as e:  # pragma: no cover
+            logging.error("Something went wrong during the processing of %s: %s", self.filename, e)
+            return False
+        return True
+
 def _get_exiftool_path() -> str:  # pragma: no cover
     exiftool_path = '/usr/bin/exiftool'
     if os.path.isfile(exiftool_path):
diff --git a/libmat2/images.py b/libmat2/images.py
index ad80892..03cecd3 100644
--- a/libmat2/images.py
+++ b/libmat2/images.py
@@ -35,6 +35,8 @@ class PNGParser(exiftool.ExiftoolParser):
             raise ValueError
 
     def remove_all(self) -> bool:
+        if self.lightweight_cleaning:
+            return self._lightweight_cleanup()
         surface = cairo.ImageSurface.create_from_png(self.filename)
         surface.write_to_png(self.output_filename)
         return True
diff --git a/libmat2/video.py b/libmat2/video.py
index fe2a1af..b7ba0a0 100644
--- a/libmat2/video.py
+++ b/libmat2/video.py
@@ -26,7 +26,7 @@ class AVIParser(exiftool.ExiftoolParser):
 
     def remove_all(self):
         cmd = [_get_ffmpeg_path(),
-               '-i', self.filename,           # input file
+               '-i', self.filename,      # input file
                '-y',                     # overwrite existing output file
                '-loglevel', 'panic',     # Don't show log
                '-hide_banner',           # hide the banner
diff --git a/tests/test_corrupted_files.py b/tests/test_corrupted_files.py
index 82c6c3b..181d4d2 100644
--- a/tests/test_corrupted_files.py
+++ b/tests/test_corrupted_files.py
@@ -194,6 +194,13 @@ class TestCorruptedFiles(unittest.TestCase):
              images.JPGParser('./tests/data/clean.jpg')
         os.remove('./tests/data/clean.jpg')
 
+    def test_png_lightweight(self):
+        return
+        shutil.copy('./tests/data/dirty.torrent', './tests/data/clean.png')
+        p = images.PNGParser('./tests/data/clean.png')
+        self.assertTrue(p.remove_all())
+        os.remove('./tests/data/clean.png')
+
     def test_avi(self):
         try:
             video._get_ffmpeg_path()
diff --git a/tests/test_libmat2.py b/tests/test_libmat2.py
index f5fc9e8..46d6aaa 100644
--- a/tests/test_libmat2.py
+++ b/tests/test_libmat2.py
@@ -212,42 +212,6 @@ class TestRevisionsCleaning(unittest.TestCase):
         os.remove('./tests/data/revision_clean.docx')
         os.remove('./tests/data/revision_clean.cleaned.docx')
 
-class TestLightWeightCleaning(unittest.TestCase):
-    def test_pdf(self):
-        shutil.copy('./tests/data/dirty.pdf', './tests/data/clean.pdf')
-        p = pdf.PDFParser('./tests/data/clean.pdf')
-
-        meta = p.get_meta()
-        self.assertEqual(meta['producer'], 'pdfTeX-1.40.14')
-
-        p.lightweight_cleaning = True
-        ret = p.remove_all()
-        self.assertTrue(ret)
-
-        p = pdf.PDFParser('./tests/data/clean.cleaned.pdf')
-        expected_meta = {'creation-date': -1, 'format': 'PDF-1.5', 'mod-date': -1}
-        self.assertEqual(p.get_meta(), expected_meta)
-
-        os.remove('./tests/data/clean.pdf')
-        os.remove('./tests/data/clean.cleaned.pdf')
-
-    def test_png(self):
-        shutil.copy('./tests/data/dirty.png', './tests/data/clean.png')
-        p = images.PNGParser('./tests/data/clean.png')
-
-        meta = p.get_meta()
-        self.assertEqual(meta['Comment'], 'This is a comment, be careful!')
-
-        p.lightweight_cleaning = True
-        ret = p.remove_all()
-        self.assertTrue(ret)
-
-        p = images.PNGParser('./tests/data/clean.cleaned.png')
-        self.assertEqual(p.get_meta(), {})
-
-        os.remove('./tests/data/clean.png')
-        os.remove('./tests/data/clean.cleaned.png')
-
 class TestCleaning(unittest.TestCase):
     def test_pdf(self):
         shutil.copy('./tests/data/dirty.pdf', './tests/data/clean.pdf')
diff --git a/tests/test_lightweigh_cleaning.py b/tests/test_lightweigh_cleaning.py
new file mode 100644
index 0000000..7af31ad
--- /dev/null
+++ b/tests/test_lightweigh_cleaning.py
@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+
+import unittest
+import shutil
+import os
+
+from libmat2 import pdf, images
+
+class TestLightWeightCleaning(unittest.TestCase):
+    def test_pdf(self):
+        shutil.copy('./tests/data/dirty.pdf', './tests/data/clean.pdf')
+        p = pdf.PDFParser('./tests/data/clean.pdf')
+
+        meta = p.get_meta()
+        self.assertEqual(meta['producer'], 'pdfTeX-1.40.14')
+
+        p.lightweight_cleaning = True
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        p = pdf.PDFParser('./tests/data/clean.cleaned.pdf')
+        expected_meta = {'creation-date': -1, 'format': 'PDF-1.5', 'mod-date': -1}
+        self.assertEqual(p.get_meta(), expected_meta)
+
+        os.remove('./tests/data/clean.pdf')
+        os.remove('./tests/data/clean.cleaned.pdf')
+
+    def test_png(self):
+        shutil.copy('./tests/data/dirty.png', './tests/data/clean.png')
+        p = images.PNGParser('./tests/data/clean.png')
+
+        meta = p.get_meta()
+        self.assertEqual(meta['Comment'], 'This is a comment, be careful!')
+
+        p.lightweight_cleaning = True
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        p = images.PNGParser('./tests/data/clean.cleaned.png')
+        self.assertEqual(p.get_meta(), {})
+
+        p = images.PNGParser('./tests/data/clean.png')
+        p.lightweight_cleaning = True
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        os.remove('./tests/data/clean.png')
+        os.remove('./tests/data/clean.cleaned.png')
+
+    def test_jpg(self):
+        shutil.copy('./tests/data/dirty.jpg', './tests/data/clean.jpg')
+        p = images.JPGParser('./tests/data/clean.jpg')
+
+        meta = p.get_meta()
+        self.assertEqual(meta['Comment'], 'Created with GIMP')
+
+        p.lightweight_cleaning = True
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        p = images.JPGParser('./tests/data/clean.cleaned.jpg')
+        self.assertEqual(p.get_meta(), {})
+
+        os.remove('./tests/data/clean.jpg')
+        os.remove('./tests/data/clean.cleaned.jpg')