commit 88ae39c72f464ce81b8eeea55bffc585807197be Author: bar Date: Fri Jan 28 17:39:36 2011 +0000 - Moving Disallow commands for doc, pdf, ppt, xls, rtf on separate lines, to uncomment easier. - Adding unrtf diff --git a/etc/indexer.conf-dist b/etc/indexer.conf-dist index 798f0f7..a8eb757 100644 --- a/etc/indexer.conf-dist +++ b/etc/indexer.conf-dist @@ -308,6 +308,13 @@ DBAddr mysql://root@localhost/test/?dbmode=blob # special meaning in "string" match, so we have to use "regex" match here: #Disallow Regex \? +# Disallow document extensions that are not understood by default. +# Comment these lines if you have corresponding external parsers. +Disallow *.rtf +Disallow *.doc +Disallow *.xls +Disallow *.ppt +Disallow *.pdf # Exclude some known extensions using fast "String" match: Disallow *.b *.sh *.md5 *.rpm @@ -318,9 +325,9 @@ Disallow *.vdo *.mpeg *.mpe *.mpg *.avi *.movie *.mov *.wmv Disallow *.mid *.mp3 *.rm *.ram *.wav *.aiff *.ra Disallow *.vrml *.wrl *.png *.ico *.psd *.dat Disallow *.exe *.com *.cab *.dll *.bin *.class *.ex_ -Disallow *.tex *.texi *.xls *.doc *.texinfo -Disallow *.rtf *.pdf *.cdf *.ps -Disallow *.ai *.eps *.ppt *.hqx +Disallow *.tex *.texi *.texinfo +Disallow *.cdf *.ps +Disallow *.ai *.eps *.hqx Disallow *.cpt *.bms *.oda *.tcl Disallow *.o *.a *.la *.so Disallow *.pat *.pm *.m4 *.am *.css @@ -484,6 +491,7 @@ AddType text/rtf *.rtf AddType application/pdf *.pdf AddType application/msword *.doc AddType application/vnd.ms-excel *.xls +AddType application/vnd.ms-powerpoint *.ppt AddType text/x-postscript *.ps @@ -531,6 +539,7 @@ AddType application/unknown *.* #Mime application/vnd.ms-excel text/html "xlhtml $1" #Mime "text/rtf*" text/html "rthc --use-stdout $1 2>/dev/null" #Mime "text/rtf*" text/xml "rtfx -w $1 2>/dev/null" +#Mime "text/rtf*" text/html "unrtf --html $1" #Mime application/vnd.ms-powerpoint "text/html; charset=utf-8" "pptohtml $1" #Mime application/vnd.ms-powerpoint text/html "ppthtml $1"