<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en-GB">
	<id>https://wiki.eprints.org/w/index.php?action=history&amp;feed=atom&amp;title=API%3AEPrints%2FIndex%2FTokenizer</id>
	<title>API:EPrints/Index/Tokenizer - Revision history</title>
	<link rel="self" type="application/atom+xml" href="https://wiki.eprints.org/w/index.php?action=history&amp;feed=atom&amp;title=API%3AEPrints%2FIndex%2FTokenizer"/>
	<link rel="alternate" type="text/html" href="https://wiki.eprints.org/w/index.php?title=API:EPrints/Index/Tokenizer&amp;action=history"/>
	<updated>2026-04-12T09:32:54Z</updated>
	<subtitle>Revision history for this page on the wiki</subtitle>
	<generator>MediaWiki 1.31.8</generator>
	<entry>
		<id>https://wiki.eprints.org/w/index.php?title=API:EPrints/Index/Tokenizer&amp;diff=14126&amp;oldid=prev</id>
		<title>Pod2wiki: Created page with &quot;&lt;!-- Pod2Wiki=_preamble_   This page has been automatically generated from the EPrints 3.4 source. Any wiki changes made between the 'Pod2Wiki=*' and 'Edit below this comment'...&quot;</title>
		<link rel="alternate" type="text/html" href="https://wiki.eprints.org/w/index.php?title=API:EPrints/Index/Tokenizer&amp;diff=14126&amp;oldid=prev"/>
		<updated>2022-01-10T01:00:05Z</updated>

		<summary type="html">&lt;p&gt;Created page with &amp;quot;&amp;lt;!-- Pod2Wiki=_preamble_   This page has been automatically generated from the EPrints 3.4 source. Any wiki changes made between the &amp;#039;Pod2Wiki=*&amp;#039; and &amp;#039;Edit below this comment&amp;#039;...&amp;quot;&lt;/p&gt;
&lt;p&gt;&lt;b&gt;New page&lt;/b&gt;&lt;/p&gt;&lt;div&gt;&amp;lt;!-- Pod2Wiki=_preamble_ &lt;br /&gt;
This page has been automatically generated from the EPrints 3.4 source. Any wiki changes made between the 'Pod2Wiki=*' and 'Edit below this comment' comments will be lost.&lt;br /&gt;
 --&amp;gt;{{API}}{{Pod2Wiki}}{{API:Source|file=EPrints/Index/Tokenizer.pm|package_name=EPrints::Index::Tokenizer}}[[Category:API|TOKENIZER]][[Category:API:EPrints/Index|TOKENIZER]]&amp;lt;div&amp;gt;&amp;lt;!-- Edit below this comment --&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&amp;lt;!-- Pod2Wiki=_private_ --&amp;gt;&amp;lt;!-- Pod2Wiki=head_name --&amp;gt;&lt;br /&gt;
==NAME==&lt;br /&gt;
'''EPrints::Index::Tokenizer''' - text indexing utility methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;div style='background-color: #e8e8f; margin: 0.5em 0em 1em 0em; border: solid 1px #cce;  padding: 0em 1em 0em 1em; font-size: 80%; '&amp;gt;&lt;br /&gt;
&amp;lt;span style='display:none'&amp;gt;User Comments&amp;lt;/span&amp;gt;&lt;br /&gt;
&amp;lt;!-- Edit below this comment --&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&amp;lt;!-- Pod2Wiki= --&amp;gt;&lt;br /&gt;
&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;lt;!-- Pod2Wiki=head_description --&amp;gt;&lt;br /&gt;
==DESCRIPTION==&lt;br /&gt;
This module provides utility methods for processing free text into  indexable things.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;div style='background-color: #e8e8f; margin: 0.5em 0em 1em 0em; border: solid 1px #cce;  padding: 0em 1em 0em 1em; font-size: 80%; '&amp;gt;&lt;br /&gt;
&amp;lt;span style='display:none'&amp;gt;User Comments&amp;lt;/span&amp;gt;&lt;br /&gt;
&amp;lt;!-- Edit below this comment --&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&amp;lt;!-- Pod2Wiki= --&amp;gt;&lt;br /&gt;
&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;lt;!-- Pod2Wiki=head_methods --&amp;gt;&lt;br /&gt;
==METHODS==&lt;br /&gt;
&amp;lt;div style='background-color: #e8e8f; margin: 0.5em 0em 1em 0em; border: solid 1px #cce;  padding: 0em 1em 0em 1em; font-size: 80%; '&amp;gt;&lt;br /&gt;
&amp;lt;span style='display:none'&amp;gt;User Comments&amp;lt;/span&amp;gt;&lt;br /&gt;
&amp;lt;!-- Edit below this comment --&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&amp;lt;!-- Pod2Wiki= --&amp;gt;&lt;br /&gt;
&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;lt;!-- Pod2Wiki=item_split_words --&amp;gt;&lt;br /&gt;
===split_words===&lt;br /&gt;
&lt;br /&gt;
 @words = EPrints::Index::Tokenizer::split_words( $session, $utext )&lt;br /&gt;
Splits a utf8 string &amp;lt;tt&amp;gt;$utext&amp;lt;/tt&amp;gt; into individual words. &lt;br /&gt;
&lt;br /&gt;
&amp;lt;div style='background-color: #e8e8f; margin: 0.5em 0em 1em 0em; border: solid 1px #cce;  padding: 0em 1em 0em 1em; font-size: 80%; '&amp;gt;&lt;br /&gt;
&amp;lt;span style='display:none'&amp;gt;User Comments&amp;lt;/span&amp;gt;&lt;br /&gt;
&amp;lt;!-- Edit below this comment --&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&amp;lt;!-- Pod2Wiki= --&amp;gt;&lt;br /&gt;
&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;lt;!-- Pod2Wiki=item_split_search_value --&amp;gt;&lt;br /&gt;
===split_search_value===&lt;br /&gt;
&lt;br /&gt;
 @terms = EPrints::Index::Tokenizer::split_search_value( $session, $value )&lt;br /&gt;
Splits and returns &amp;lt;tt&amp;gt;$value&amp;lt;/tt&amp;gt; into search terms.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;div style='background-color: #e8e8f; margin: 0.5em 0em 1em 0em; border: solid 1px #cce;  padding: 0em 1em 0em 1em; font-size: 80%; '&amp;gt;&lt;br /&gt;
&amp;lt;span style='display:none'&amp;gt;User Comments&amp;lt;/span&amp;gt;&lt;br /&gt;
&amp;lt;!-- Edit below this comment --&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&amp;lt;!-- Pod2Wiki= --&amp;gt;&lt;br /&gt;
&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;lt;!-- Pod2Wiki=item_apply_mapping --&amp;gt;&lt;br /&gt;
===apply_mapping===&lt;br /&gt;
&lt;br /&gt;
 $utext2 = EPrints::Index::Tokenizer::apply_mapping( $session, $utext )&lt;br /&gt;
Replaces certain unicode characters in &amp;lt;tt&amp;gt;$utext&amp;lt;/tt&amp;gt; with ASCII  equivalents and returns the new string.&lt;br /&gt;
&lt;br /&gt;
This is used before indexing words so that things like umlauts will be ignored when searching.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;div style='background-color: #e8e8f; margin: 0.5em 0em 1em 0em; border: solid 1px #cce;  padding: 0em 1em 0em 1em; font-size: 80%; '&amp;gt;&lt;br /&gt;
&amp;lt;span style='display:none'&amp;gt;User Comments&amp;lt;/span&amp;gt;&lt;br /&gt;
&amp;lt;!-- Edit below this comment --&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&amp;lt;!-- Pod2Wiki= --&amp;gt;&lt;br /&gt;
&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;lt;!-- Pod2Wiki=head_copyright --&amp;gt;&lt;br /&gt;
==COPYRIGHT==&lt;br /&gt;
{{API:Copyright}}&lt;br /&gt;
&amp;lt;div style='background-color: #e8e8f; margin: 0.5em 0em 1em 0em; border: solid 1px #cce;  padding: 0em 1em 0em 1em; font-size: 80%; '&amp;gt;&lt;br /&gt;
&amp;lt;span style='display:none'&amp;gt;User Comments&amp;lt;/span&amp;gt;&lt;br /&gt;
&amp;lt;!-- Edit below this comment --&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&amp;lt;!-- Pod2Wiki= --&amp;gt;&lt;br /&gt;
&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;lt;!-- Pod2Wiki=_postamble_ --&amp;gt;&amp;lt;!-- Edit below this comment --&amp;gt;&lt;/div&gt;</summary>
		<author><name>Pod2wiki</name></author>
		
	</entry>
</feed>