From 4f0030dd466f56b3dc0c864656fb1bf0e76d2932 Mon Sep 17 00:00:00 2001
From: Andreas Gohr <andi@splitbrain.org>
Date: Sun, 6 Feb 2011 19:07:31 +0100
Subject: 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.
---
 inc/indexer.php | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'inc/indexer.php')

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
 
-- 
cgit v1.2.3