Implement lightweight cleaning for png and tiff

1 files changed, 29 insertions, 0 deletions

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):