improve Mojo::DOM::CSS to handle attribute selectors with single quot…

…es correctly (closes #777)
mojolicious · Apr 5, 2015 · 3bcced3 · 3bcced3
1 parent 74ea9ad
commit 3bcced3
Show file tree

Hide file tree

Showing 3 changed files with 18 additions and 14 deletions.
diff --git a/Changes b/Changes
@@ -1,6 +1,8 @@
 
-6.06  2015-04-02
+6.06  2015-04-05
   - Added "chat.pl" to example scripts.
+  - Improved Mojo::DOM::CSS to handle attribute selectors with single quotes
+    correctly.
 
 6.05  2015-03-24
   - Fixed circular require bug in Mojo::Base and Mojo::Util.

diff --git a/lib/Mojo/DOM/CSS.pm b/lib/Mojo/DOM/CSS.pm
@@ -6,11 +6,11 @@ has 'tree';
 my $ESCAPE_RE = qr/\\[^0-9a-fA-F]|\\[0-9a-fA-F]{1,6}/;
 my $ATTR_RE   = qr/
   \[
-  ((?:$ESCAPE_RE|[\w\-])+)           # Key
+  ((?:$ESCAPE_RE|[\w\-])+)                             # Key
   (?:
-    (\W)?=                           # Operator
-    (?:"((?:\\"|[^"])*)"|([^\]]+?))  # Value
-    (?:\s+(i))?                      # Case-sensitivity
+    (\W)?=                                             # Operator
+    (?:"((?:\\"|[^"])*)"|'((?:\\'|[^'])*)'|([^\]]+?))  # Value
+    (?:\s+(i))?                                        # Case-sensitivity
   )?
   \]
 /x;
@@ -90,7 +90,7 @@ sub _compile {
 
     # Attributes
     elsif ($css =~ /\G$ATTR_RE/gco) {
-      push @$last, ['attr', _name($1), _value($2 // '', $3 // $4, $5)];
+      push @$last, ['attr', _name($1), _value($2 // '', $3 // $4 // $5, $6)];
     }
 
     # Pseudo-class (":not" contains more selectors)

diff --git a/t/mojo/dom.t b/t/mojo/dom.t
@@ -370,14 +370,16 @@ is $dom->at('[foo=ba]'), undef, 'no result';
 is $dom->at('.tset')->text, 'works', 'right text';
 
 # Already decoded Unicode snowman and quotes in selector
-$dom = Mojo::DOM->new('<div id="snowm&quot;an">☃</div>');
-is $dom->at('[id="snowm\"an"]')->text,      '☃', 'right text';
-is $dom->at('[id="snowm\22 an"]')->text,    '☃', 'right text';
-is $dom->at('[id="snowm\000022an"]')->text, '☃', 'right text';
-is $dom->at('[id="snowm\22an"]'),      undef, 'no result';
-is $dom->at('[id="snowm\21 an"]'),     undef, 'no result';
-is $dom->at('[id="snowm\000021an"]'),  undef, 'no result';
-is $dom->at('[id="snowm\000021 an"]'), undef, 'no result';
+$dom = Mojo::DOM->new('<div id="snow&apos;m&quot;an">☃</div>');
+is $dom->at('[id="snow\'m\"an"]')->text,      '☃', 'right text';
+is $dom->at('[id="snow\'m\22 an"]')->text,    '☃', 'right text';
+is $dom->at('[id="snow\'m\000022an"]')->text, '☃', 'right text';
+is $dom->at('[id="snow\'m\22an"]'),      undef, 'no result';
+is $dom->at('[id="snow\'m\21 an"]'),     undef, 'no result';
+is $dom->at('[id="snow\'m\000021an"]'),  undef, 'no result';
+is $dom->at('[id="snow\'m\000021 an"]'), undef, 'no result';
+is $dom->at("[id='snow\\'m\"an']")->text,  '☃', 'right text';
+is $dom->at("[id='snow\\27m\"an']")->text, '☃', 'right text';
 
 # Unicode and escaped selectors
 my $html