sbrl-github/Pepperminty-Wiki
sbrl-github
/
Pepperminty-Wiki
mirror of https://github.com/sbrl/Pepperminty-Wiki.git
1
0
Fork 0
Code

Add $capture_offsets option to tokenize(). 

TODO: Utilise this in the indexer & update the changelog mentioning that
_all_ inverted indexes will need to be rebuilt
This commit is contained in:
Starbeamrainbowlabs 2018-06-30 00:08:57 +01:00
parent 8403ffd5c3
commit cdee30c286
Signed by: sbrl
GPG Key ID: 1BE5172E637709C2
3 changed files with 21 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
build/index.php
View File

@ -397,7 +397,7 @@ if($settings->sessionprefix == "auto")
/////////////////////////////////////////////////////////////////////////////
/** The version of Pepperminty Wiki currently running. */
$version = "v0.17-dev";
$commit = "80f2cc77a8fa474394492f08ea7f4c998d076acc";
$commit = "8403ffd5c3de9725756bcfc5929ce9239be1379b";
/// Environment ///
/** Holds information about the current request environment. */
$env = new stdClass();
@ -4194,14 +4194,16 @@ class search
{
$nterm = $term;
// Skip over stop words (see https://en.wikipedia.org/wiki/Stop_words)
if(in_array($nterm, self::$stop_words)) continue;
if(in_array($nterm, self::$stop_words)) { $i++; continue; }
if(!isset($index[$nterm]))
{
$index[$nterm] = [ "freq" => 0, "offsets" => [] ];
}
// FIXME: Here we use the index of the token in the array, when we want the number of characters into the page!
$index[$nterm]["freq"]++;
$index[$nterm]["offsets"][] = $i;
@ -4213,20 +4215,25 @@ class search
/**
* Converts a source string into a series of raw tokens.
* @param string $source The source string to process.
* @param string $source The source string to process.
* @param boolean $capture_offsets Whether to capture & return the character offsets of the tokens detected. If true, then each token returned will be an array in the form [ token, char_offset ].
* @return array An array of raw tokens extracted from the specified source string.
*/
public static function tokenize($source)
public static function tokenize($source, $capture_offsets = false)
{
/** Normalises input characters for searching & indexing */
static $literator; if($literator == null) $literator = Transliterator::createFromRules(':: Any-Latin; :: Latin-ASCII; :: NFD; :: [:Nonspacing Mark:] Remove; :: Lower(); :: NFC;', Transliterator::FORWARD);
$flags = PREG_SPLIT_NO_EMPTY; // Don't return empty items
if($capture_offsets)
$flags |= PREG_SPLIT_OFFSET_CAPTURE;
// We don't need to normalise here because the transliterator handles
// this for us. Also, we can't move the literator to a static variable
// because PHP doesn't like it very much
$source = $literator->transliterate($source);
$source = preg_replace('/[\[\]\|\{\}\/]/u', " ", $source);
return preg_split("/((^\p{P}+)|(\p{P}*\s+\p{P}*)|(\p{P}+$))|\|/u", $source, -1, PREG_SPLIT_NO_EMPTY);
return preg_split("/((^\p{P}+)|(\p{P}*\s+\p{P}*)|(\p{P}+$))|\|/u", $source, -1, $flags);
}
/**

2
module_index.json
View File

@ -104,7 +104,7 @@
"author": "Starbeamrainbowlabs",
"description": "Adds proper search functionality to Pepperminty Wiki using an inverted index to provide a full text search engine. If pages don't show up, then you might have hit a stop word. If not, try requesting the `invindex-rebuild` action to rebuild the inverted index from scratch.",
"id": "feature-search",
"lastupdate": 1530270319,
"lastupdate": 1530313680,
"optional": false
},
{

11
modules/feature-search.php
View File

@ -569,20 +569,25 @@ class search
/**
* Converts a source string into a series of raw tokens.
* @param string $source The source string to process.
* @param string $source The source string to process.
* @param boolean $capture_offsets Whether to capture & return the character offsets of the tokens detected. If true, then each token returned will be an array in the form [ token, char_offset ].
* @return array An array of raw tokens extracted from the specified source string.
*/
public static function tokenize($source)
public static function tokenize($source, $capture_offsets = false)
{
/** Normalises input characters for searching & indexing */
static $literator; if($literator == null) $literator = Transliterator::createFromRules(':: Any-Latin; :: Latin-ASCII; :: NFD; :: [:Nonspacing Mark:] Remove; :: Lower(); :: NFC;', Transliterator::FORWARD);
$flags = PREG_SPLIT_NO_EMPTY; // Don't return empty items
if($capture_offsets)
$flags |= PREG_SPLIT_OFFSET_CAPTURE;
// We don't need to normalise here because the transliterator handles
// this for us. Also, we can't move the literator to a static variable
// because PHP doesn't like it very much
$source = $literator->transliterate($source);
$source = preg_replace('/[\[\]\|\{\}\/]/u', " ", $source);
return preg_split("/((^\p{P}+)|(\p{P}*\s+\p{P}*)|(\p{P}+$))|\|/u", $source, -1, PREG_SPLIT_NO_EMPTY);
return preg_split("/((^\p{P}+)|(\p{P}*\s+\p{P}*)|(\p{P}+$))|\|/u", $source, -1, $flags);
}
/**