fix(withinString): include balanced parens - closes #247

CHANGELOG.md

@@ -2,6 +2,10 @@
 
 The release notes tracked in this document are also made available on the [releases page](https://github.com/medialize/URI.js/releases)
 
+### master ###
+
+* fixing [`URI.withinString()`](http://medialize.github.io/URI.js/docs.html#static-withinString) to capture balanced parentheses - [Issue #247](https://github.com/medialize/URI.js/issues/247)
+
 ### 1.18.3 (November 17th 2016) ###
 
 * fixing UMD wrappers to properly detect CommonJS - [Issue #318](https://github.com/medialize/URI.js/issues/318), [PR #319](https://github.com/medialize/URI.js/pull/319)

src/URI.js

@@ -220,7 +220,9 @@
     // everything up to the next whitespace
     end: /[\s\r\n]|$/,
     // trim trailing punctuation captured by end RegExp
-    trim: /[`!()\[\]{};:'".,<>?«»“”„‘’]+$/
+    trim: /[`!()\[\]{};:'".,<>?«»“”„‘’]+$/,
+    // balanced parens inclusion (), [], {}, <>
+    parens: /(\([^\)]*\)|\[[^\]]*\]|\{[^}]*\}|<[^>]*>)/g,
   };
   // http://www.iana.org/assignments/uri-schemes.html
   // http://en.wikipedia.org/wiki/List_of_TCP_and_UDP_port_numbers#Well-known_ports
@@ -942,6 +944,7 @@
     var _start = options.start || URI.findUri.start;
     var _end = options.end || URI.findUri.end;
     var _trim = options.trim || URI.findUri.trim;
+    var _parens = options.parens || URI.findUri.parens;
     var _attributeOpen = /[a-z0-9-]=["']?$/i;
 
     _start.lastIndex = 0;
@@ -961,7 +964,25 @@
       }
 
       var end = start + string.slice(start).search(_end);
-      var slice = string.slice(start, end).replace(_trim, '');
+      var slice = string.slice(start, end);
+      // make sure we include well balanced parens
+      var parensEnd = -1;
+      while (true) {
+        var parensMatch = _parens.exec(slice);
+        if (!parensMatch) {
+          break;
+        }
+
+        var parensMatchEnd = parensMatch.index + parensMatch[0].length;
+        parensEnd = Math.max(parensEnd, parensMatchEnd);
+      }
+
+      if (parensEnd > -1) {
+        slice = slice.slice(0, parensEnd) + slice.slice(parensEnd + 1).replace(_trim, '');
+      } else {
+        slice = slice.replace(_trim, '');
+      }
+
       if (options.ignore && options.ignore.test(slice)) {
         continue;
       }

test/test.js

@@ -1579,12 +1579,16 @@
       + 'http://google.com is a search engine, like http://www.bing.com\n'
       + 'http://exämple.org/foo.html?baz=la#bumm is an IDN URL,\n'
       + 'http://123.123.123.123/foo.html is IPv4 and http://fe80:0000:0000:0000:0204:61ff:fe9d:f156/foobar.html is IPv6.\n'
-      + 'links can also be in parens (http://example.org) or quotes »http://example.org«.';
+      + 'links can also be in parens (http://example.org) or quotes »http://example.org«, '
+      + 'yet https://example.com/with_(balanced_parentheses) contains the closing parens, but '
+      + 'https://example.com/with_unbalanced_parentheses) does not.';
     var expected = 'Hello <a>www.example.com</a>,\n'
       + '<a>http://google.com</a> is a search engine, like <a>http://www.bing.com</a>\n'
       + '<a>http://exämple.org/foo.html?baz=la#bumm</a> is an IDN URL,\n'
       + '<a>http://123.123.123.123/foo.html</a> is IPv4 and <a>http://fe80:0000:0000:0000:0204:61ff:fe9d:f156/foobar.html</a> is IPv6.\n'
-      + 'links can also be in parens (<a>http://example.org</a>) or quotes »<a>http://example.org</a>«.';
+      + 'links can also be in parens (<a>http://example.org</a>) or quotes »<a>http://example.org</a>«, '
+      + 'yet <a>https://example.com/with_(balanced_parentheses)</a> contains the closing parens, but '
+      + '<a>https://example.com/with_unbalanced_parentheses</a>) does not.';
     /*jshint laxbreak: false */
     var result = URI.withinString(source, function(url) {
       return '<a>' + url + '</a>';
@@ -1685,7 +1689,7 @@
   });
   test('joinPaths', function() {
     var result;
-    
+
     result = URI.joinPaths('/a/b', '/c', 'd', '/e').toString();
     equal(result, '/a/b/c/d/e', 'absolute paths');