Change default mode for parse_url to be more like PHP; cleaned up fun…

…ction and allowed custom ini settings to change parsing mode
marcuswestin · Mar 12, 2011 · c216260 · c216260
1 parent 32b8792
commit c216260
Showing 1 changed file with 32 additions and 69 deletions.
diff --git a/functions/url/parse_url.js b/functions/url/parse_url.js
@@ -2,87 +2,50 @@ function parse_url (str, component) {
     // http://kevin.vanzonneveld.net
     // +      original by: Steven Levithan (http://blog.stevenlevithan.com)
     // + reimplemented by: Brett Zamir (http://brett-zamir.me)
+    // + input by: Lorenzo Pisani
+    // + input by: Tony
+    // + improved by: Brett Zamir (http://brett-zamir.me)
     // %          note: Based on http://stevenlevithan.com/demo/parseuri/js/assets/parseuri.js
     // %          note: blog post at http://blog.stevenlevithan.com/archives/parseuri
     // %          note: demo at http://stevenlevithan.com/demo/parseuri/js/assets/parseuri.js
-    // %          note: Does not replace invaild characters with '_' as in PHP, nor does it return false with
+    // %          note: Does not replace invalid characters with '_' as in PHP, nor does it return false with
     // %          note: a seriously malformed URL.
-    // %          note: Besides function name, is the same as parseUri besides the commented out portion
-    // %          note: and the additional section following, as well as our allowing an extra slash after
-    // %          note: the scheme/protocol (to allow file:/// as in PHP)
+    // %          note: Besides function name, is essentially the same as parseUri as well as our allowing
+    // %          note: an extra slash after the scheme/protocol (to allow file:/// as in PHP)
     // *     example 1: parse_url('http://username:password@hostname/path?arg=value#anchor');
     // *     returns 1: {scheme: 'http', host: 'hostname', user: 'username', pass: 'password', path: '/path', query: 'arg=value', fragment: 'anchor'}
-    var o = {
-        strictMode: false,
-        key: ["source", "protocol", "authority", "userInfo", "user", "password", "host", "port", "relative", "path", "directory", "file", "query", "anchor"],
-        q: {
-            name: "queryKey",
-            parser: /(?:^|&)([^&=]*)=?([^&]*)/g
-        },
-        parser: {
+    var key = ['source', 'scheme', 'authority', 'userInfo', 'user', 'pass', 'host', 'port', 
+                        'relative', 'path', 'directory', 'file', 'query', 'fragment'],
+        ini = (this.php_js && this.php_js.ini) || {},
+        mode = (ini['phpjs.parse_url.mode'] && 
+            ini['phpjs.parse_url.mode'].local_value) || 'php',
+        parser = {
+            php: /^(?:([^:\/?#]+):)?(?:\/\/()(?:(?:()(?:([^:@]*):?([^:@]*))?@)?([^:\/?#]*)(?::(\d*))?))?()(?:(()(?:(?:[^?#\/]*\/)*)()(?:[^?#]*))(?:\?([^#]*))?(?:#(.*))?)/,
             strict: /^(?:([^:\/?#]+):)?(?:\/\/((?:(([^:@]*):?([^:@]*))?@)?([^:\/?#]*)(?::(\d*))?))?((((?:[^?#\/]*\/)*)([^?#]*))(?:\?([^#]*))?(?:#(.*))?)/,
-            loose: /^(?:(?![^:@]+:[^:@\/]*@)([^:\/?#.]+):)?(?:\/\/\/?)?((?:(([^:@]*):?([^:@]*))?@)?([^:\/?#]*)(?::(\d*))?)(((\/(?:[^?#](?![^?#\/]*\.[^?#\/.]+(?:[?#]|$)))*\/?)?([^?#\/]*))(?:\?([^#]*))?(?:#(.*))?)/ // Added one optional slash to post-protocol to catch file:/// (should restrict this)
-        }
-    };
+            loose: /^(?:(?![^:@]+:[^:@\/]*@)([^:\/?#.]+):)?(?:\/\/\/?)?((?:(([^:@]*):?([^:@]*))?@)?([^:\/?#]*)(?::(\d*))?)(((\/(?:[^?#](?![^?#\/]*\.[^?#\/.]+(?:[?#]|$)))*\/?)?([^?#\/]*))(?:\?([^#]*))?(?:#(.*))?)/ // Added one optional slash to post-scheme to catch file:/// (should restrict this)
+        };
 
-    var m = o.parser[o.strictMode ? "strict" : "loose"].exec(str),
+    var m = parser[mode].exec(str),
         uri = {},
         i = 14;
     while (i--) {
-        uri[o.key[i]] = m[i] || "";
+        if (m[i]) {
+          uri[key[i]] = m[i];  
+        }
     }
-    // Uncomment the following to use the original more detailed (non-PHP) script
-/*
-        uri[o.q.name] = {};
-        uri[o.key[12]].replace(o.q.parser, function ($0, $1, $2) {
-        if ($1) {uri[o.q.name][$1] = $2;}
-        });
-        return uri;
-    */
 
-    switch (component) {
-    case 'PHP_URL_SCHEME':
-        return uri.protocol;
-    case 'PHP_URL_HOST':
-        return uri.host;
-    case 'PHP_URL_PORT':
-        return uri.port;
-    case 'PHP_URL_USER':
-        return uri.user;
-    case 'PHP_URL_PASS':
-        return uri.password;
-    case 'PHP_URL_PATH':
-        return uri.path;
-    case 'PHP_URL_QUERY':
-        return uri.query;
-    case 'PHP_URL_FRAGMENT':
-        return uri.anchor;
-    default:
-        var retArr = {};
-        if (uri.protocol !== '') {
-            retArr.scheme = uri.protocol;
-        }
-        if (uri.host !== '') {
-            retArr.host = uri.host;
-        }
-        if (uri.port !== '') {
-            retArr.port = uri.port;
-        }
-        if (uri.user !== '') {
-            retArr.user = uri.user;
-        }
-        if (uri.password !== '') {
-            retArr.pass = uri.password;
-        }
-        if (uri.path !== '') {
-            retArr.path = uri.path;
-        }
-        if (uri.query !== '') {
-            retArr.query = uri.query;
-        }
-        if (uri.anchor !== '') {
-            retArr.fragment = uri.anchor;
-        }
-        return retArr;
+    if (component) {
+        return uri[component.replace('PHP_URL_', '').toLowerCase()];
+    }
+    if (mode !== 'php') {
+        var name = (ini['phpjs.parse_url.queryKey'] && 
+                ini['phpjs.parse_url.queryKey'].local_value) || 'queryKey';
+        parser = /(?:^|&)([^&=]*)=?([^&]*)/g;
+        uri[name] = {};
+        uri[key[12]].replace(parser, function ($0, $1, $2) {
+            if ($1) {uri[name][$1] = $2;}
+        });
     }
+    delete uri.source;
+    return uri;
 }