mirror of
https://github.com/osm-search/Nominatim.git
synced 2026-02-16 15:47:58 +00:00
remove special status of partial tokens
Full-word tokens are no longer marked by a space at the beginning of the token. Use the new Partial token category instead. This removes a couple of special casing, we don't really need. The word table still has the space for compatibility reasons, so the tokenizer code needs to get rid of it when loading the tokens.
This commit is contained in:
@@ -137,14 +137,14 @@ class Tokenizer
|
||||
|
||||
// Try more interpretations for Tokens that could not be matched.
|
||||
foreach ($aTokens as $sToken) {
|
||||
if ($sToken[0] == ' ' && !$oValidTokens->contains($sToken)) {
|
||||
if (preg_match('/^ ([0-9]{5}) [0-9]{4}$/', $sToken, $aData)) {
|
||||
if ($sToken[0] != ' ' && !$oValidTokens->contains($sToken)) {
|
||||
if (preg_match('/^([0-9]{5}) [0-9]{4}$/', $sToken, $aData)) {
|
||||
// US ZIP+4 codes - merge in the 5-digit ZIP code
|
||||
$oValidTokens->addToken(
|
||||
$sToken,
|
||||
new Token\Postcode(null, $aData[1], 'us')
|
||||
);
|
||||
} elseif (preg_match('/^ [0-9]+$/', $sToken)) {
|
||||
} elseif (preg_match('/^[0-9]+$/', $sToken)) {
|
||||
// Unknown single word token with a number.
|
||||
// Assume it is a house number.
|
||||
$oValidTokens->addToken(
|
||||
|
||||
Reference in New Issue
Block a user