Fix for Issue #6. Bumped version

Author: evert

CHANGELOG.md

@@ -1,6 +1,14 @@
 ChangeLog
 =========
 
+1.1.0 (2016-03-07)
+------------------
+
+* #6: PHP's `parse_url()` corrupts strings if they contain certain
+  non ascii-characters such as Chinese or Hebrew. sabre/uri's `parse()`
+  function now percent-encodes these characters beforehand.
+
+
 1.0.1 (2015-04-28)
 ------------------
 

lib/Version.php

@@ -14,6 +14,6 @@ class Version {
     /**
      * Full version number
      */
-    const VERSION = '1.0.1';
+    const VERSION = '1.1.0';
 
 }

lib/functions.php

@@ -33,7 +33,7 @@ function resolve($basePath, $newPath) {
             return $base[$part];
         }
         return null;
-        
+
     };
 
     // If the new path defines a scheme, it's absolute and we can just return
@@ -172,11 +172,29 @@ function normalize($uri) {
  * return an array with all the array keys, including the ones that are not
  * set by parse_url, which makes it a bit easier to work with.
  *
+ * Unlike PHP's parse_url, it will also convert any non-ascii characters to
+ * percent-encoded strings. PHP's parse_url corrupts these characters on OS X.
+ *
  * @param string $uri
  * @return array
  */
 function parse($uri) {
 
+    // Normally a URI must be ASCII, however. However, often it's not and
+    // parse_url might corrupt these strings.
+    //
+    // For that reason we take any non-ascii characters from the uri and
+    // uriencode them first.
+    $uri = preg_replace_callback(
+        '/[^[:ascii:]]/u',
+        function($matches) {
+            return rawurlencode($matches[0]);
+        },
+        $uri
+    );
+
+    if ($uri!==$uri) die($uri . "\n");
+
     return
         parse_url($uri) + [
             'scheme'   => null,
@@ -262,5 +280,5 @@ function split($path) {
         return [$matches[1], $matches[2]];
     }
     return [null,null];
-    
+
 }

tests/ParseTest.php

@@ -38,8 +38,7 @@ function parseData() {
                 [
                     'scheme'   => 'http',
                     'host'     => 'example.org',
-                    //'path'     => '/%E6%9C%89%E8%AF%8D%E6%B3%95%E5%88%AB%E5%90%8D.zh',
-                    'path'     => '/%有词法别名.zh',
+                    'path'     => '/%E6%9C%89%E8%AF%8D%E6%B3%95%E5%88%AB%E5%90%8D.zh',
                     'port'     => null,
                     'user'     => null,
                     'query'    => null,