1 files changed, 55 insertions, 0 deletions
diff --git a/inc/utf8.php b/inc/utf8.php
index d49b1413c..b0ffdb001 100644
--- a/inc/utf8.php
+++ b/inc/utf8.php
@@ -318,6 +318,61 @@ function utf8_strtoupper($string){
 }
 
 /**
+ * UTF-8 aware alternative to ucfirst
+ * Make a string's first character uppercase
+ *
+ * @author Harry Fuecks
+ * @param string
+ * @return string with first character as upper case (if applicable)
+ */
+function utf8_ucfirst($str){
+  switch ( utf8_strlen($str) ) {
+    case 0:
+        return '';
+    case 1:
+        return utf8_strtoupper($str);
+    default:
+        preg_match('/^(.{1})(.*)$/us', $str, $matches);
+        return utf8_strtoupper($matches[1]).$matches[2];
+  }
+}
+
+/**
+ * UTF-8 aware alternative to ucwords
+ * Uppercase the first character of each word in a string
+ *
+ * @author Harry Fuecks
+ * @param string
+ * @return string with first char of each word uppercase
+ * @see http://www.php.net/ucwords
+ */
+function utf8_ucwords($str) {
+  // Note: [\x0c\x09\x0b\x0a\x0d\x20] matches;
+  // form feeds, horizontal tabs, vertical tabs, linefeeds and carriage returns
+  // This corresponds to the definition of a "word" defined at http://www.php.net/ucwords
+  $pattern = '/(^|([\x0c\x09\x0b\x0a\x0d\x20]+))([^\x0c\x09\x0b\x0a\x0d\x20]{1})[^\x0c\x09\x0b\x0a\x0d\x20]*/u';
+
+  return preg_replace_callback($pattern, 'utf8_ucwords_callback',$str);
+}
+
+/**
+ * Callback function for preg_replace_callback call in utf8_ucwords
+ * You don't need to call this yourself
+ *
+ * @author Harry Fuecks
+ * @param array of matches corresponding to a single word
+ * @return string with first char of the word in uppercase
+ * @see utf8_ucwords
+ * @see utf8_strtoupper
+ */
+function utf8_ucwords_callback($matches) {
+  $leadingws = $matches[2];
+  $ucfirst = utf8_strtoupper($matches[3]);
+  $ucword = utf8_substr_replace(ltrim($matches[0]),$ucfirst,0,1);
+  return $leadingws . $ucword;
+}
+
+/**
  * Replace accented UTF-8 characters by unaccented ASCII-7 equivalents
  *
  * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1)