bryce/mediawiki-extensions-UniversalLanguageSelector
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improve ULS language search api

Browse Source 
* Store prefixes and infixes separately in the data
* First match language code, then prefixes, then infixes
* Try to use suggestion either in user language or autonym first
* use formatversion=2 to avoid escaping Unicode

Using Language::fetchLanguageName might can have a small
performance impact. On the other hand there is now check
to skip languages we already found, avoiding some fuzzy
matching.

This is in a preparation for a change in jquery.uls to use
the search API more, while trying to reduce the amount of
weird autocompletion suggestions we show to the user.

Bug: T73891
Change-Id: Id94c5352d9a591969bf90144d1d2d5e758d08301
This commit is contained in:
Niklas Laxström
2017-11-27 12:22:25 +01:00
parent a353c5ab65
commit e87dd20cdd
6 changed files with 51632 additions and 46567 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
data/LanguageNameIndexer.php
View File

@@ -58,11 +58,13 @@ class LanguageNameIndexer extends Maintenance {
foreach ( $words as $index => $word ) {
$bucket = LanguageNameSearch::getIndex( $word );
$type = 'prefix';
$display = $translation;
if ( $index > 0 && count( $words ) > 1 ) {
$type = 'infix';
$display = "$word <$translation>";
}
$buckets[$bucket][$display] = $targetLanguage;
$buckets[$bucket][$type][$display] = $targetLanguage;
}
}
}
@@ -87,10 +89,25 @@ class LanguageNameIndexer extends Maintenance {
foreach ( $specialLanguages as $targetLanguage => $translation ) {
$bucket = LanguageNameSearch::getIndex( $translation );
$buckets[$bucket][$translation] = $targetLanguage;
$buckets[$bucket]['prefix'][$translation] = $targetLanguage;
}
$lengths = [];
// Sorting the bucket contents gives two benefits:
// - more consistent output across environments
// - shortest matches appear first, especially exact matches
// Sort buckets by index
ksort( $buckets );
foreach ( $buckets as $index => &$bucketTypes ) {
$lengths[] = array_sum( array_map( 'count', $bucketTypes ) );
// Ensure 'prefix' is before 'infix';
krsort( $bucketTypes );
// Ensure each bucket has entries sorted
foreach ( $bucketTypes as $type => &$bucket ) {
ksort( $bucket );
}
}
$lengths = array_values( array_map( 'count', $buckets ) );
$count = count( $buckets );
$min = min( $lengths );
$max = max( $lengths );
@@ -113,7 +130,6 @@ class LanguageNameSearchData {
PHP;
ksort( $buckets );
// Format for short array format
$data = var_export( $buckets, true );
$data = str_replace( "array (", '[', $data );