simple stopwords support

git-svn-id: http://code.phpbb.com/svn/sphinx/trunk@10 058e8d10-4797-47b5-994a-8fa6acaf3df0

sphinx_plugin/config/sphinx_stopwords.txt

@@ -0,0 +1,251 @@
+a
+about
+after
+ago
+all
+almost
+along
+alot
+also
+am
+an
+and
+answer
+any
+anybody
+anybodys
+anywhere
+are
+arent
+around
+as
+ask
+askd
+at
+bad
+be
+because
+been
+before
+being
+best
+better
+between
+big
+btw
+but
+by
+can
+cant
+come
+could
+couldnt
+day
+days
+days
+did
+didnt
+do
+does
+doesnt
+dont
+down
+each
+etc
+either
+else
+even
+ever
+every
+everybody
+everybodys
+everyone
+far
+find
+for
+found
+from
+get
+go
+going
+gone
+good
+got
+gotten
+had
+has
+have
+havent
+having
+her
+here
+hers
+him
+his
+home
+how
+hows
+href
+I
+Ive
+if
+in
+ini
+into
+is
+isnt
+it
+its
+its
+just
+know
+large
+less
+like
+liked
+little
+looking
+look
+looked
+looking
+lot
+maybe
+many
+me
+more
+most
+much
+must
+mustnt
+my
+near
+need
+never
+new
+news
+no
+none
+not
+nothing
+now
+of
+off
+often
+old
+on
+once
+only
+oops
+or
+other
+our
+ours
+out
+over
+page
+please
+put
+question
+questions
+questioned
+quote
+rather
+really
+recent
+said
+saw
+say
+says
+she
+see
+sees
+should
+sites
+small
+so
+some
+something
+sometime
+somewhere
+soon
+take
+than
+true
+thank
+that
+thatd
+thats
+the
+their
+theirs
+theres
+theirs
+them
+then
+there
+these
+they
+theyll
+theyd
+theyre
+this
+those
+though
+through
+thus
+time
+times
+to
+too
+under
+until
+untrue
+up
+upon
+use
+users
+version
+very
+via
+want
+was
+way
+we
+well
+went
+were
+werent
+what
+when
+where
+which
+who
+whom
+whose
+why
+wide
+will
+with
+within
+without
+wont
+world
+worse
+worst
+would
+wrote
+www
+yes
+yet
+you
+youd
+youll
+your
+youre
+yours
+AFAIK
+IIRC
+LOL
+ROTF
+ROTFLMAO
+YMMV

sphinx_plugin/includes/search/fulltext_sphinx.php

@@ -253,7 +253,7 @@ function config_updated()
 				array('source',						"source_phpbb_{$this->id}_main"),
 				array('docinfo',					'extern'),
 				array('morphology',					'none'),
-				array('stopwords',					(isset($config['fulltext_sphinx_stop_words_file'])) ? $config['fulltext_sphinx_stop_words_file'] : ''),
+				array('stopwords',					(file_exists($config['fulltext_sphinx_config_path'] . 'sphinx_stopwords.txt')) ? $config['fulltext_sphinx_config_path'] . 'sphinx_stopwords.txt' : ''),
 				array('min_word_len',				'2'),
 				array('charset_type',				'utf-8'),
 				array('charset_table',				'U+FF10..U+FF19->0..9, 0..9, U+FF41..U+FF5A->a..z, U+FF21..U+FF3A->a..z, A..Z->a..z, a..z, U+0149, U+017F, U+0138, U+00DF, U+00FF, U+00C0..U+00D6->U+00E0..U+00F6, U+00E0..U+00F6, U+00D8..U+00DE->U+00F8..U+00FE, U+00F8..U+00FE, U+0100->U+0101, U+0101, U+0102->U+0103, U+0103, U+0104->U+0105, U+0105, U+0106->U+0107, U+0107, U+0108->U+0109, U+0109, U+010A->U+010B, U+010B, U+010C->U+010D, U+010D, U+010E->U+010F, U+010F, U+0110->U+0111, U+0111, U+0112->U+0113, U+0113, U+0114->U+0115, U+0115, U+0116->U+0117, U+0117, U+0118->U+0119, U+0119, U+011A->U+011B, U+011B, U+011C->U+011D, U+011D, U+011E->U+011F, U+011F, U+0130->U+0131, U+0131, U+0132->U+0133, U+0133, U+0134->U+0135, U+0135, U+0136->U+0137, U+0137, U+0139->U+013A, U+013A, U+013B->U+013C, U+013C, U+013D->U+013E, U+013E, U+013F->U+0140, U+0140, U+0141->U+0142, U+0142, U+0143->U+0144, U+0144, U+0145->U+0146, U+0146, U+0147->U+0148, U+0148, U+014A->U+014B, U+014B, U+014C->U+014D, U+014D, U+014E->U+014F, U+014F, U+0150->U+0151, U+0151, U+0152->U+0153, U+0153, U+0154->U+0155, U+0155, U+0156->U+0157, U+0157, U+0158->U+0159, U+0159, U+015A->U+015B, U+015B, U+015C->U+015D, U+015D, U+015E->U+015F, U+015F, U+0160->U+0161, U+0161, U+0162->U+0163, U+0163, U+0164->U+0165, U+0165, U+0166->U+0167, U+0167, U+0168->U+0169, U+0169, U+016A->U+016B, U+016B, U+016C->U+016D, U+016D, U+016E->U+016F, U+016F, U+0170->U+0171, U+0171, U+0172->U+0173, U+0173, U+0174->U+0175, U+0175, U+0176->U+0177, U+0177, U+0178->U+00FF, U+00FF, U+0179->U+017A, U+017A, U+017B->U+017C, U+017C, U+017D->U+017E, U+017E, U+4E00..U+9FFF'),
@@ -1104,11 +1104,19 @@ function acp()
 			}
 		}
 
+		/**
+		* @todo check whether stopwords are really activated/make it an option
+		*/
+
 		$tpl = '
 		<dl>
 			<dt><label for="fulltext_sphinx_config_path">' . $user->lang['FULLTEXT_SPHINX_CONFIG_PATH'] . ':</label><br /><span>' . $user->lang['FULLTEXT_SPHINX_CONFIG_PATH_EXPLAIN'] . '</span></dt>
 			<dd><input id="fulltext_sphinx_config_path" type="text" size="40" maxlength="255" name="config[fulltext_sphinx_config_path]" value="' . $config['fulltext_sphinx_config_path'] . '" /></dd>
 		</dl>
+		<dl>
+			<dt><label for="fulltext_sphinx_data_path">' . $user->lang['FULLTEXT_SPHINX_STOPWORDS_FILE'] . ':</label><br /><span>' . $user->lang['FULLTEXT_SPHINX_STOPWORDS_FILE_EXPLAIN'] . '</span></dt>
+			<dd><strong>' . ((file_exists($config['fulltext_sphinx_config_path'] . 'sphinx_stopwords.txt')) ? $user->lang['YES'] : $user->lang['NO']) . '</strong></dd>
+		</dl>
 		<dl>
 			<dt><label for="fulltext_sphinx_data_path">' . $user->lang['FULLTEXT_SPHINX_DATA_PATH'] . ':</label><br /><span>' . $user->lang['FULLTEXT_SPHINX_DATA_PATH_EXPLAIN'] . '</span></dt>
 			<dd><input id="fulltext_sphinx_data_path" type="text" size="40" maxlength="255" name="config[fulltext_sphinx_data_path]" value="' . $config['fulltext_sphinx_data_path'] . '" /></dd>

sphinx_plugin/language/en/mods/fulltext_sphinx.php

@@ -35,19 +35,22 @@
 	'FULLTEXT_SPHINX_BIN_PATH_EXPLAIN'		=> 'If this path could not be determined automatically you have to enter the path to the directory in which the sphinx executables <samp>indexer</samp> and <samp>searchd</samp> reside.',
 	'FULLTEXT_SPHINX_CONFIG_PATH'			=> 'Path to configuration directory',
 	'FULLTEXT_SPHINX_CONFIG_PATH_EXPLAIN'	=> 'You should create this config directory outside the web accessable directories. It has to be writable by the user as which your webserver is running (often www-data or nobody).',
+	'FULLTEXT_SPHINX_CONFIGURE_FIRST'		=> 'Before you create an index you have to enable and configure sphinx under GENERAL -> SERVER CONFIGURATION -> Search settings.',
 	'FULLTEXT_SPHINX_DATA_PATH'				=> 'Path to data directory',
 	'FULLTEXT_SPHINX_DATA_PATH_EXPLAIN'	=> 'You should create this directory outside the web accessable directories. It has to be writable by the user as which your webserver is running (often www-data or nobody). It will be used to store the indexes and log files.',
+	'FULLTEXT_SPHINX_DELTA_POSTS'			=> 'Number of posts in frequently updated delta index',
 	'FULLTEXT_SPHINX_DIRECTORY_NOT_FOUND'	=> 'The directory <strong>%s</strong> does not exist. Please correct your path settings.',
 	'FULLTEXT_SPHINX_FILE_NOT_EXECUTABLE'	=> 'The file <strong>%s</strong> is not executable for the webserver.',
 	'FULLTEXT_SPHINX_FILE_NOT_FOUND'		=> 'The file <strong>%s</strong> does not exist. Please correct your path settings.',
 	'FULLTEXT_SPHINX_FILE_NOT_WRITABLE'	=> 'The file <strong>%s</strong> cannot be written by the webserver.',
+	'FULLTEXT_SPHINX_LAST_SEARCHES'		=> 'Recent search queries',
+	'FULLTEXT_SPHINX_MAIN_POSTS'			=> 'Number of posts in main index',
 	'FULLTEXT_SPHINX_PORT'					=> 'Sphinx search deamon port',
 	'FULLTEXT_SPHINX_PORT_EXPLAIN'			=> 'Port on which the sphinx search deamon on localhost listens. Leave empty to use the default 3312',
 	'FULLTEXT_SPHINX_REQUIRES_EXEC'		=> 'The sphinx plugin for phpBB requires PHP’s <code>exec</code> function which is disabled on your system.',
 	'FULLTEXT_SPHINX_WRONG_DATABASE'		=> 'The sphinx plugin for phpBB currently only supports MySQL',
-	'FULLTEXT_SPHINX_MAIN_POSTS'			=> 'Number of posts in main index',
-	'FULLTEXT_SPHINX_DELTA_POSTS'			=> 'Number of posts in frequently updated delta index',
-	'FULLTEXT_SPHINX_LAST_SEARCHES'		=> 'Recent search queries',
+	'FULLTEXT_SPHINX_STOPWORDS_FILE'		=> 'Stopwords activated',
+	'FULLTEXT_SPHINX_STOPWORDS_FILE_EXPLAIN'	=> 'You can place a file called sphinx_stopwords.txt containing one word in each line in your config directory. If this file is present these words will be excluded from the indexing process.',
 ));
 
 ?>

sphinx_plugin/scripts/create_links

@@ -13,7 +13,7 @@ if [ "$1" = "--help" -o "$1" = "-h" -o "$1" == "" ]; then
 fi
 
 if [ "$plugin_path" == "" ]; then
-	plugin_path="."
+	plugin_path="../"
 fi
 
 if [ "$phpbb_path" == "" ]; then