From 8fb3ffa406887fe14b728af3cfb120a1b04f3b10 Mon Sep 17 00:00:00 2001
From: taitus <sebastia.roig@gmail.com>
Date: Mon, 8 May 2023 09:43:30 +0200
Subject: [PATCH] Remove pdf metadata

In order to remove metadata from PDF documents we will use the
exiftool_vendored gem.

The following line:
  Exiftool.new(attachment_path, "-overwrite_original -all:all=")
Overwrites the original file with another file without metadata.

So far this is the best solution we have found to perform this
metadata deletion.

When using Exiftool an exception is thrown, so we added a rescue
to handle it. Here is a task created where this problem is
discussed: https://github.com/exiftool-rb/exiftool.rb/issues/28.
We'll wait to see if this will be fixed in future versions.

Translated with www.DeepL.com/Translator (free version)
---
 Gemfile.lock           |  5 +++++
 Gemfile_custom         |  1 +
 app/models/document.rb | 12 ++++++++++++
 3 files changed, 18 insertions(+)

diff --git a/Gemfile.lock b/Gemfile.lock
index 92ff8bfc580d..5732f5f2da68 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -197,6 +197,10 @@ GEM
       multi_json (>= 1.3)
       rake
     execjs (2.8.1)
+    exiftool (1.2.4)
+      json
+    exiftool_vendored (12.60.0)
+      exiftool (>= 0.7.0)
     factory_bot (6.2.0)
       activesupport (>= 5.0.0)
     factory_bot_rails (6.2.0)
@@ -694,6 +698,7 @@ DEPENDENCIES
   devise-security (~> 0.16.0)
   email_spec (~> 2.2.0)
   erb_lint (~> 0.3.1)
+  exiftool_vendored (~> 12.60.0)
   factory_bot_rails (~> 6.2.0)
   faker (~> 2.22.0)
   file_validators (~> 3.0.0)
diff --git a/Gemfile_custom b/Gemfile_custom
index fe5bf8418274..27ce20b120f6 100644
--- a/Gemfile_custom
+++ b/Gemfile_custom
@@ -24,4 +24,5 @@
 #
 # Add your custom gem dependencies here
 
+gem "exiftool_vendored", "~> 12.60.0"
 gem "ruby-ntlm", "~> 0.0.4"
diff --git a/app/models/document.rb b/app/models/document.rb
index 9a48ed6150fd..1cf5d90d7a18 100644
--- a/app/models/document.rb
+++ b/app/models/document.rb
@@ -11,6 +11,8 @@ class Document < ApplicationRecord
 
   scope :admin, -> { where(admin: true) }
 
+  before_save :remove_metadata
+
   def self.humanized_accepted_content_types
     Setting.accepted_content_types_for("documents").join(", ")
   end
@@ -36,4 +38,14 @@ def association_name
     def documentable_class
       association_class
     end
+
+    def remove_metadata
+      return unless self.attachment.attached?
+      attachment_path = ActiveStorage::Blob.service.path_for(self.attachment.key)
+
+      Exiftool.new(attachment_path, "-overwrite_original -all:all=")
+      self.attachment.attach(io: File.open(attachment_path), filename: self.attachment.filename.to_s)
+    rescue Exiftool::ExiftoolNotInstalled
+      nil
+    end
 end