[pmg-devel] [PATCH pmg-api 5/7] config: add spam option for extract_text

[Stoiko Ivanov]

toggling the configuration options for the ExtractText SA plugin (see
[0]).

The config is copied from the module itself, the informational headers
were not added, as I don't see too much gain, apart from verifying
that the plugin is working.

the external dependencies for the plugin to work are added as
Recommends, as it is a possible config to not have them installed and
simply disable the option

[0] https://metacpan.org/pod/Mail::SpamAssassin::Plugin::ExtractText
Signed-off-by: Stoiko Ivanov <s.ivanov at proxmox.com>
---
 debian/control            |  9 ++++++++-
 src/PMG/Config.pm         |  6 ++++++
 src/templates/v400.pre.in | 34 ++++++++++++++++++++++++++++++----
 3 files changed, 44 insertions(+), 5 deletions(-)

diff --git a/debian/control b/debian/control
index 93ad72c..d2ed7da 100644
--- a/debian/control
+++ b/debian/control
@@ -98,7 +98,14 @@ Depends: apt (>= 2~),
          ucf,
          ${misc:Depends},
          ${perl:Depends},
-Recommends: ifupdown2, proxmox-offline-mirror-helper
+Recommends: antiword,
+            docx2txt,
+            ifupdown2,
+            odt2txt,
+            poppler-utils,
+            proxmox-offline-mirror-helper,
+            tesseract-ocr,
+            unrtf
 Suggests: zfsutils-linux
 Description: Proxmox Mailgateway API Server Implementation
  This implements a REST API to configure Proxmox Mailgateway.
diff --git a/src/PMG/Config.pm b/src/PMG/Config.pm
index 5dcffb7..699a622 100755
--- a/src/PMG/Config.pm
+++ b/src/PMG/Config.pm
@@ -211,6 +211,11 @@ sub properties {
 	    minimum => 64,
 	    default => 256*1024,
 	},
+	extract_text => {
+	    description => "Extract text from attachments (doc, pdf, rtf, images) and scan for spam.",
+	    type => 'boolean',
+	    default => 0,
+	},
     };
 }
 
@@ -225,6 +230,7 @@ sub options {
 	bounce_score => { optional => 1 },
 	rbl_checks => { optional => 1 },
 	maxspamsize => { optional => 1 },
+	extract_text => { optional => 1 },
     };
 }
 
diff --git a/src/templates/v400.pre.in b/src/templates/v400.pre.in
index 052e73e..4d68d6c 100644
--- a/src/templates/v400.pre.in
+++ b/src/templates/v400.pre.in
@@ -16,11 +16,37 @@
 # added to new files, named according to the release they're added in.
 ###########################################################################
 
+
+[% IF pmg.spam.extract_text %]
 # ExtractText - Extract text from documents or images for matching
-#
-# Requires manual configuration, see plugin documentation.
-#
-# loadplugin Mail::SpamAssassin::Plugin::ExtractText
+# informational headers and hits not configured
+loadplugin Mail::SpamAssassin::Plugin::ExtractText
+
+ifplugin Mail::SpamAssassin::Plugin::ExtractText
+
+  extracttext_external  pdftotext  /usr/bin/pdftotext -nopgbrk -layout -enc UTF-8 {} -
+  extracttext_use       pdftotext  .pdf application/pdf
+
+  # http://docx2txt.sourceforge.net
+  extracttext_external  docx2txt   /usr/bin/docx2txt {} -
+  extracttext_use       docx2txt   .docx application/docx
+
+  extracttext_external  antiword   /usr/bin/antiword -t -w 0 -m UTF-8.txt {}
+  extracttext_use       antiword   .doc application/(?:vnd\.?)?ms-?word.*
+
+  extracttext_external  unrtf      /usr/bin/unrtf --nopict {}
+  extracttext_use       unrtf      .doc .rtf application/rtf text/rtf
+
+  extracttext_external  odt2txt    /usr/bin/odt2txt --encoding=UTF-8 {}
+  extracttext_use       odt2txt    .odt .ott application/.*?opendocument.*text
+  extracttext_use       odt2txt    .sdw .stw application/(?:x-)?soffice application/(?:x-)?starwriter
+
+  extracttext_external  tesseract  {OMP_THREAD_LIMIT=1} /usr/bin/tesseract -c page_separator= {} -
+  extracttext_use       tesseract  .jpg .png .bmp .tif .tiff image/(?:jpeg|png|x-ms-bmp|tiff)
+
+endif
+
+[% END %]
 
 # DecodeShortUrl - Check for shortened URLs
 #
-- 
2.30.2