hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-02-16 15:47:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

move special hack for US states to legacy tokenizer

Browse Source 
The hack for IL, AL and LA is only needed because these abbreviations
are removed by the legacy tokenizer as a stop word. There is no need
to keep the hack for future tokenizers. Move it therefore to the
token extraction function.
This commit is contained in:
Sarah Hoffmann
2021-08-17 14:28:55 +02:00
parent 5f2b9e317a
commit f00b8dd1c3
3 changed files with 19 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
lib-php/tokenizer/legacy_tokenizer.php
View File

@@ -87,6 +87,23 @@ class Tokenizer
$sNormQuery .= ','.$this->normalizeString($oPhrase->getPhrase());
$sSQL .= 'make_standard_name(:' .$iPhrase.') as p'.$iPhrase.',';
$aParams[':'.$iPhrase] = $oPhrase->getPhrase();
// Conflicts between US state abbreviations and various words
// for 'the' in different languages
switch (strtolower($oPhrase->getPhrase())) {
case 'il':
$aParams[':'.$iPhrase] = 'illinois';
break;
case 'al':
$aParams[':'.$iPhrase] = 'alabama';
break;
case 'la':
$aParams[':'.$iPhrase] = 'louisiana';
break;
default:
$aParams[':'.$iPhrase] = $oPhrase->getPhrase();
break;
}
}
$sSQL = substr($sSQL, 0, -1);