diff options
| author | Andreas Gohr <andi@splitbrain.org> | 2011-02-06 19:07:31 +0100 |
|---|---|---|
| committer | Andreas Gohr <andi@splitbrain.org> | 2011-02-06 19:11:19 +0100 |
| commit | 4f0030dd466f56b3dc0c864656fb1bf0e76d2932 (patch) | |
| tree | 09291d0635244f84e673b8336a26f44d4d92d754 /inc/indexer.php | |
| parent | 412b5df14aaa2104af3d82e77380c5321cd94389 (diff) | |
| download | rpg-4f0030dd466f56b3dc0c864656fb1bf0e76d2932.tar.gz rpg-4f0030dd466f56b3dc0c864656fb1bf0e76d2932.tar.bz2 | |
ignore soft-hyphens for search FS#2049
This makes it possible to find words that include soft-hyphens. However,
search higlighting will not work and I have no idea how to make it work.
Diffstat (limited to 'inc/indexer.php')
| -rw-r--r-- | inc/indexer.php | 9 |
1 files changed, 8 insertions, 1 deletions
diff --git a/inc/indexer.php b/inc/indexer.php index 9cf079261..526c8db05 100644 --- a/inc/indexer.php +++ b/inc/indexer.php @@ -221,7 +221,14 @@ function idx_getPageWords($page){ list($page,$body) = $data; - $body = strtr($body, "\r\n\t", ' '); + $body = strtr($body, + array( + "\r" => ' ', + "\n" => ' ', + "\t" => ' ', + "\xC2\xAD" => '', //soft-hyphen + ) + ); $tokens = explode(' ', $body); $tokens = array_count_values($tokens); // count the frequency of each token |