From 3323c1dbfade004d89c5492c84adc829095fe9fa Mon Sep 17 00:00:00 2001
From: jvoisin <julien.voisin@dustri.org>
Date: Sat, 8 Feb 2020 16:08:32 +0100
Subject: [PATCH] Remove a couple of residual metadata in pdf
This commit takes care of removing residual metadata
added by mat2 during the cleaning of pdf.
---
libmat2/pdf.py | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/libmat2/pdf.py b/libmat2/pdf.py
index 547e071..cc83812 100644
--- a/libmat2/pdf.py
+++ b/libmat2/pdf.py
@@ -122,6 +122,17 @@ class PDFParser(abstract.AbstractParser):
document.set_creator('')
document.set_creation_date(-1)
document.save('file://' + os.path.abspath(out_file))
+
+ # Cairo adds "/Producer" and "/CreationDate", and Poppler sometimes
+ # fails to remove them, we have to use this terrible regex.
+ # It should(tm) be alright though, because cairo's output format
+ # for metadata is fixed.
+ with open(out_file, 'rb') as f:
+ out = re.sub(b'<<[\s\n]*/Producer.*?>>', b' << >>', f.read(), 0,
+ re.DOTALL | re.IGNORECASE)
+ with open(out_file, 'wb') as f:
+ f.write(out)
+
return True
@staticmethod
--
GitLab