From 27162a79266d88cce087a8ba881a6bcc6c78c276 Mon Sep 17 00:00:00 2001
From: Uwe Steinmann <steinm@debian.org>
Date: Thu, 8 Aug 2019 07:47:12 +0200
Subject: [PATCH] add converters for fulltext search

---
 doc/README.Converters | 46 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 41 insertions(+), 5 deletions(-)

diff --git a/doc/README.Converters b/doc/README.Converters
index 5256f0f89..784922b4c 100644
--- a/doc/README.Converters
+++ b/doc/README.Converters
@@ -1,5 +1,33 @@
-Conversion to pdf
-=================
+Conversion to text for fulltext search
+=======================================
+
+text/plain
+text/csv
+  cat '%s'
+
+application/pdf
+  pdftotext -nopgbrk %s - | sed -e 's/ [a-zA-Z0-9.]\{1\} / /g' -e 's/[0-9.]//g'
+
+application/vnd.openxmlformats-officedocument.wordprocessingml.document
+  docx2txt '%s' -
+
+application/msword
+  catdoc %s
+
+application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
+  xlsx2csv %s
+
+application/vnd.ms-excel
+  xls2csv %s
+
+text/html
+  html2text %s
+
+Many office formats
+  unoconv -d document -f txt --stdout '%s'
+
+Conversion to pdf for pdf preview
+==================================
 
 text/plain
 text/csv
@@ -22,8 +50,16 @@ application/vnd.ms-excel
 application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
   unoconv -d spreadsheet -f pdf --stdout -v '%f' > '%o'
 
-Preview
-========
+Conversion to png for preview images
+=====================================
+
+If you have problems running convert on PDF documents then read this page
+https://askubuntu.com/questions/1081895/trouble-with-batch-conversion-of-png-to-pdf-using-convert
+It basically instructs you to comment out the line
+
+<policy domain="coder" rights="none" pattern="PDF" />
+
+in /etc/ImageMagick-6/policy.xml
 
 image/jpg
 image/jpeg
@@ -46,5 +82,5 @@ application/rtf
 application/vnd.ms-powerpoint
 text/csv
 application/vnd.wordperfect
-  /usr/bin/unoconv -d document -e PageRange=1 -f pdf --stdout -v '%f' | gs -dBATCH -dNOPAUSE -sDEVICE=pngalpha -dPDFFitPage -r72x72 -sOutputFile=- -dFirstPage=1 -dLastPage=1 -q - | convert -resize %wx png:- '%o'
+  unoconv -d document -e PageRange=1 -f pdf --stdout -v '%f' | gs -dBATCH -dNOPAUSE -sDEVICE=pngalpha -dPDFFitPage -r72x72 -sOutputFile=- -dFirstPage=1 -dLastPage=1 -q - | convert -resize %wx png:- '%o'