1 files changed, 28 insertions, 1 deletions
diff --git a/inc/utf8.php b/inc/utf8.php
index 70b16f1a5..7d0f0a266 100644
--- a/inc/utf8.php
+++ b/inc/utf8.php
@@ -190,7 +190,7 @@ function utf8_ltrim($str,$charlist=''){
 }
 
 /**
- * Unicode aware replacement for ltrim()
+ * Unicode aware replacement for rtrim()
  *
  * @author Andreas Gohr <andi@splitbrain.org>
  * @see    rtrim()
@@ -342,6 +342,33 @@ function utf8_strpos($haystack, $needle,$offset=0) {
 }
 
 /**
+ * Encodes UTF-8 characters to HTML entities
+ *
+ * @author <vpribish at shopping dot com>
+ * @link   http://www.php.net/manual/en/function.utf8-decode.php
+ */
+function utf8_tohtml ($str) {
+  $ret = '';
+  $max = strlen($str);
+  $last = 0;  // keeps the index of the last regular character
+  for ($i=0; $i<$max; $i++) {
+    $c = $str{$i};
+    $c1 = ord($c);
+    if ($c1>>5 == 6) {  // 110x xxxx, 110 prefix for 2 bytes unicode
+      $ret .= substr($str, $last, $i-$last); // append all the regular characters we've passed
+      $c1 &= 31; // remove the 3 bit two bytes prefix
+      $c2 = ord($str{++$i}); // the next byte
+      $c2 &= 63;  // remove the 2 bit trailing byte prefix
+      $c2 |= (($c1 & 3) << 6); // last 2 bits of c1 become first 2 of c2
+      $c1 >>= 2; // c1 shifts 2 to the right
+      $ret .= '&#' . ($c1 * 100 + $c2) . ';'; // this is the fastest string concatenation
+      $last = $i+1;
+    }
+  }
+  return $ret . substr($str, $last, $i); // append the last batch of regular characters
+} 
+
+/**
  * This function returns any UTF-8 encoded text as a list of
  * Unicode values:
  *