--- /dev/null
+commit 88ae39c72f464ce81b8eeea55bffc585807197be
+Author: bar <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"
+
--- /dev/null
+diff -r -u mnogosearch-3.3.11.orig/etc/indexer.conf-dist mnogosearch-3.3.11/etc/indexer.conf-dist
+--- mnogosearch-3.3.11.orig/etc/indexer.conf-dist 2011-01-31 11:06:27.000000000 +0100
++++ mnogosearch-3.3.11/etc/indexer.conf-dist 2011-01-31 11:15:30.000000000 +0100
+@@ -1,4 +1,4 @@
+-#!/usr/local/mnogosearch/sbin/indexer -d
++#!/usr/bin/indexer -d
+
+ ###########################################################################
+ # This is a sample indexer config file.
+@@ -49,7 +49,7 @@
+ # then PostgreSQL will not work via TCP, but will use Unix socket.
+ #
+
+-DBAddr mysql://root@localhost/test/?dbmode=blob
++DBAddr sqlite3://localhost/var/lib/mnogosearch/default.db/?dbmode=blob
+
+
+
+@@ -139,7 +139,7 @@
+ #LocalCharset Shift-JIS
+
+ # Full UNICODE
+-#LocalCharset UTF-8
++LocalCharset UTF-8
+
+ #######################################################################
+ #ForceIISCharset1251 yes/no
+@@ -169,7 +169,7 @@
+ #
+ #StopwordFile stopwords/en.sl
+
+-#Include stopwords.conf
++Include stopwords.conf
+
+
+ ###########################################################################
+@@ -180,7 +180,7 @@
+ #
+ #LangMapFile langmap/en.ascii.lm
+
+-#Include langmap.conf
++Include langmap.conf
+
+
+ #######################################################################
+@@ -310,11 +310,11 @@
+
+ # 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
++#Disallow *.rtf
++#Disallow *.doc
++#Disallow *.xls
++#Disallow *.ppt
++#Disallow *.pdf
+
+ # Exclude some known extensions using fast "String" match:
+ Disallow *.b *.sh *.md5 *.rpm
+@@ -531,16 +531,16 @@
+ # from_mime to_mime[charset] [command line [$1]]
+ #
+ #Mime application/msword "text/plain; charset=utf-8" "catdoc -a -dutf-8 $1"
+-#Mime application/msword "text/html; charset=utf-8" "wvHtml --charset=utf-8 $1 -"
++Mime application/msword "text/html; charset=utf-8" "wvHtml --charset=utf-8 $1 -"
+ #Mime application/x-troff-man text/plain "deroff"
+ #Mime text/x-postscript text/plain "ps2ascii"
+-#Mime application/pdf text/plain "pdftotext $1 -"
++Mime application/pdf "text/plain; charset=utf-8" "pdftotext $1 -"
+ #Mime application/vnd.ms-excel text/plain "xls2csv $1"
+-#Mime application/vnd.ms-excel text/html "xlhtml $1"
++Mime application/vnd.ms-excel "text/html; charset=utf-8" "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 "text/rtf*" "text/html; charset=utf-8" "unrtf --html $1"
++Mime application/vnd.ms-powerpoint "text/html; charset=utf-8" "ppthtml $1"
+ #Mime application/vnd.ms-powerpoint text/html "ppthtml $1"
+
+
+@@ -975,7 +975,7 @@
+ # Default value is "path".
+ #
+ # To index whole server "localhost":
+-#Server http://localhost/
++Server http://localhost/
+ #
+ # You can also specify some path to index subdirectory only:
+ #Server http://localhost/subdir/
+diff -r -u mnogosearch-3.3.11.orig/etc/search.htm-dist mnogosearch-3.3.11/etc/search.htm-dist
+--- mnogosearch-3.3.11.orig/etc/search.htm-dist 2011-01-27 16:10:07.000000000 +0100
++++ mnogosearch-3.3.11/etc/search.htm-dist 2011-01-31 11:17:04.000000000 +0100
+@@ -13,7 +13,7 @@
+ <!--variables
+ # Database parameters
+ # Format: <DBType>:[//[DBUser[:DBPass]@]DBHost[:DBPort]]/DBName/[?dbmode=mode]
+-DBAddr mysql://root@localhost/test/?dbmode=blob
++DBAddr sqlite3://localhost/var/lib/mnogosearch/default.db/?dbmode=blob
+
+ # Uncomment this line to enable search result cache
+ #Cache yes
+@@ -25,8 +25,8 @@
+ # Default charset is iso-8859-1 (latin1)
+ # which is suitable for the most Western European languages
+
+-LocalCharset iso-8859-1
+-BrowserCharset iso-8859-1
++LocalCharset utf-8
++BrowserCharset utf-8
+
+ # Load stopwords file. File name is either absolute
+ # or relative to /etc directory of mnoGoSearch installation.
Summary: Web indexing and search system for a small domain or intranet
Name: mnogosearch
Version: 3.3.11
-Release: 2
+Release: 3
License: GPLv2+
Group: Applications/Internet
URL: http://www.mnogosearch.org/
Source2: mnogosearch.crond
Source3: httpd.conf
+# makes adapting the configuration more easy, taken from upstream cvs
+Patch0: mnogosearch-3.3.11-prepare-config.patch
+
+# modify the default configuration suitable for our distribution
+# distribution-specific, not upstream
+Patch1: mnogosearch-distconfig.patch
+
BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-root-%(%{__id_u} -n)
Requires: %{name}-libs = %{version}-%{release}
Requires: /usr/bin/xlhtml
Requires: /usr/bin/ppthtml
Requires: /usr/bin/pdftotext
+Requires: /usr/bin/unrtf
Requires(pre): shadow-utils
# user "apache" is added to mnogosearch group so we need the user to be present
%prep
%setup -q -n mnogosearch-%{version}
+%patch0 -p1
+%patch1 -p1
+
%build
autoreconf -fi
done
)
-# fix header of config file
-sed -i 's|/usr/local/mnogosearch/sbin/indexer|%{_bindir}/indexer|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-# change default configuration
-sed -i 's|DBAddr.mysql://root@localhost/test/?dbmode=blob|DBAddr sqlite3://localhost/%{_localstatedir}/lib/mnogosearch/default.db/?dbmode=blob|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf \
- %{buildroot}%{_sysconfdir}/mnogosearch/search.htm \
-
-sed -i 's|#LocalCharset UTF-8|LocalCharset UTF-8|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-sed -i 's|#Server http://localhost/|Server http://localhost/|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-# enable common external document helpers by default
-# we require them so they will be installed
-
-sed -i 's|#Mime application/msword "text/html; charset=utf-8" "wvHtml --charset=utf-8 $1 -"|Mime application/msword "text/html; charset=utf-8" "wvHtml --charset=utf-8 $1 -"|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-sed -i 's|#Mime application/pdf text/plain "pdftotext $1 -"|Mime application/pdf text/plain "pdftotext $1 -"|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-sed -i 's|#Mime application/vnd.ms-excel text/html "xlhtml $1"|Mime application/vnd.ms-excel text/html "xlhtml $1"|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-sed -i 's|#Mime application/vnd.ms-powerpoint text/html "ppthtml $1"|Mime application/vnd.ms-powerpoint text/html "ppthtml $1"|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-sed -i 's|Disallow \*.tex \*.texi \*.xls \*.doc \*.texinfo|Disallow *.tex *.texi *.texinfo|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-sed -i 's|Disallow \*.rtf \*.pdf \*.cdf \*.ps|Disallow *.rtf *.cdf *.ps|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
-sed -i 's|Disallow \*.ai \*.eps \*.ppt \*.hqx|Disallow *.ai *.eps *.hqx|g' \
- %{buildroot}%{_sysconfdir}/mnogosearch/indexer.conf
-
# the cgi is no regular binary, move it to libexec
install -d %{buildroot}%{_libexecdir}/mnogosearch
mv -f %{buildroot}%{_bindir}/*.cgi %{buildroot}%{_libexecdir}/mnogosearch/
%{php_extdir}
%changelog
+* Mon Jan 31 2011 Gerd v. Egidy <gerd@egidy.de> 3.3.11-3
+- include upstream-patch to make adapting the config more easy
+- add unrtf to default config and requires
+- modifying the default configuration now done with a patch
+
* Thu Jan 27 2011 Gerd v. Egidy <gerd@egidy.de> 3.3.11-2
- last minute-changes in the 3.3.11 release
- enable some external document helpers by default:
git://developer.intra2net.com / mnogosearch-rpm / commitdiff