You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by he...@apache.org on 2021/04/14 20:16:46 UTC

svn commit: r1888778 - in /spamassassin/trunk: lib/Mail/SpamAssassin/Plugin/ExtractText.pm t/extracttext.t

Author: hege
Date: Wed Apr 14 20:16:46 2021
New Revision: 1888778

URL: http://svn.apache.org/viewvc?rev=1888778&view=rev
Log:
Better pdftotext defaults

Modified:
    spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/ExtractText.pm
    spamassassin/trunk/t/extracttext.t

Modified: spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/ExtractText.pm
URL: http://svn.apache.org/viewvc/spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/ExtractText.pm?rev=1888778&r1=1888777&r2=1888778&view=diff
==============================================================================
--- spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/ExtractText.pm (original)
+++ spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/ExtractText.pm Wed Apr 14 20:16:46 2021
@@ -30,7 +30,7 @@ ifplugin Mail::SpamAssassin::Plugin::Ext
   extracttext_external  pdftohtml  /usr/bin/pdftohtml -i -stdout -noframes -nodrm {}
   extracttext_use       pdftohtml  .pdf application/pdf
 
-  extracttext_external  pdftotext  /usr/bin/pdftotext -q -nopgbrk -enc UTF-8 {} -
+  extracttext_external  pdftotext  /usr/bin/pdftotext -nopgbrk -layout -enc UTF-8 {} -
   extracttext_use       pdftotext  .pdf application/pdf
 
   # http://docx2txt.sourceforge.net

Modified: spamassassin/trunk/t/extracttext.t
URL: http://svn.apache.org/viewvc/spamassassin/trunk/t/extracttext.t?rev=1888778&r1=1888777&r2=1888778&view=diff
==============================================================================
--- spamassassin/trunk/t/extracttext.t (original)
+++ spamassassin/trunk/t/extracttext.t Wed Apr 14 20:16:46 2021
@@ -49,7 +49,7 @@ if (HAS_PDFTOHTML) {
 
 if (HAS_PDFTOTEXT) {
    tstprefs("
-     extracttext_external  pdftotext  /usr/bin/pdftotext -q -nopgbrk -enc UTF-8 {} -
+     extracttext_external  pdftotext  /usr/bin/pdftotext -nopgbrk -layout -enc UTF-8 {} -
      extracttext_use       pdftotext  .pdf
      extracttext_timeout 30 40
    ");
@@ -61,7 +61,7 @@ if (HAS_PDFTOTEXT) {
 
    # Should fail
    tstprefs("
-     extracttext_external  pdftotext  /usr/bin/pdftotext -q -nopgbrk -enc UTF-8 {} -
+     extracttext_external  pdftotext  /usr/bin/pdftotext -nopgbrk -layout -enc UTF-8 {} -
      extracttext_use       pdftotext  .FOO
      extracttext_timeout 30 40
    ");