safety-screen/Nominatim
1
0
Fork 0
forked from hans/Nominatim
Code Pull Requests Activity

ignore Unicode format characters for normalization

Browse Source 
Also adds tests.

Fixes #1007.
This commit is contained in:
Sarah Hoffmann
2018-04-10 22:48:17 +02:00
parent 28ee59dd64
commit ae83ceab5e
5 changed files with 22 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
settings/defaults.php
View File

@@ -20,7 +20,7 @@ if (isset($_GET['debug']) && $_GET['debug']) @define('CONST_Debug', true);
// Rules for normalizing terms for comparison before doing comparisons.
// The default is to remove accents and punctuation and to lower-case the
// term. Spaces are kept but collapsed to one standard space.
@define('CONST_Term_Normalization_Rules', ":: NFD (); [:Nonspacing Mark:] >; :: lower (); [[:Punctuation:][:Space:]]+ > ' '; :: NFC ();");
@define('CONST_Term_Normalization_Rules', ":: NFD (); [[:Nonspacing Mark:] [:Cf:]] >; :: lower (); [[:Punctuation:][:Space:]]+ > ' '; :: NFC ();");
// Set to false to avoid importing extra postcodes for the US.
@define('CONST_Use_Extra_US_Postcodes', true);