minor #15852 [CssSelector] Optimize regexs matching simple selectors (stof)

fabpot · fabpot · commit 6bc51c114f8d · 2015-09-21T08:00:16.000+02:00
This PR was merged into the 2.3 branch.

Discussion
----------

[CssSelector] Optimize regexs matching simple selectors

| Q             | A
| ------------- | ---
| Bug fix?      | no
| New feature?  | no
| BC breaks?    | no
| Deprecations? | no
| Tests pass?   | yes
| Fixed tickets | n/a
| License       | MIT
| Doc PR        | n/a

These shortcut parsers are applied first when converting a CSS selector to XPath, to be faster for simple selectors (tag matching, class matching with an optional tag, id matching with an optional tag).
None of the regexes defined here could have more chances to match more element when backtracking identifiers. So the backtracking is only slowing down the regex engine when the regex does not match (i.e. for any more complex selector for instance, or even for simple selectors without namespace of without tag name). Making quantifiers possessive solves this issue.

I also turned some capturing groups (around the namespace and the namespace delimiter) into non-capturing groups as we don't care about them in the output (they are just here to be optional).

Commits
-------

d5abe0b [CssSelector] Optimize regexs matching simple selectors
diff --git a/Parser/Shortcut/ClassParser.php b/Parser/Shortcut/ClassParser.php
@@ -33,15 +33,14 @@ public function parse($source)
     {
         // Matches an optional namespace, optional element, and required class
         // $source = 'test|input.ab6bd_field';
-        // $matches = array (size=5)
-        //     0 => string 'test:input.ab6bd_field' (length=22)
-        //     1 => string 'test:' (length=5)
-        //     2 => string 'test' (length=4)
-        //     3 => string 'input' (length=5)
-        //     4 => string 'ab6bd_field' (length=11)
-        if (preg_match('/^(([a-z]+)\|)?([\w-]+|\*)?\.([\w-]+)$/i', trim($source), $matches)) {
+        // $matches = array (size=4)
+        //     0 => string 'test|input.ab6bd_field' (length=22)
+        //     1 => string 'test' (length=4)
+        //     2 => string 'input' (length=5)
+        //     3 => string 'ab6bd_field' (length=11)
+        if (preg_match('/^(?:([a-z]++)\|)?+([\w-]++|\*)?+\.([\w-]++)$/i', trim($source), $matches)) {
             return array(
-                new SelectorNode(new ClassNode(new ElementNode($matches[2] ?: null, $matches[3] ?: null), $matches[4])),
+                new SelectorNode(new ClassNode(new ElementNode($matches[1] ?: null, $matches[2] ?: null), $matches[3])),
             );
         }
 
diff --git a/Parser/Shortcut/ElementParser.php b/Parser/Shortcut/ElementParser.php
@@ -32,13 +32,12 @@ public function parse($source)
     {
         // Matches an optional namespace, required element or `*`
         // $source = 'testns|testel';
-        // $matches = array (size=4)
-        //     0 => string 'testns:testel' (length=13)
-        //     1 => string 'testns:' (length=7)
-        //     2 => string 'testns' (length=6)
-        //     3 => string 'testel' (length=6)
-        if (preg_match('/^(([a-z]+)\|)?([\w-]+|\*)$/i', trim($source), $matches)) {
-            return array(new SelectorNode(new ElementNode($matches[2] ?: null, $matches[3])));
+        // $matches = array (size=3)
+        //     0 => string 'testns|testel' (length=13)
+        //     1 => string 'testns' (length=6)
+        //     2 => string 'testel' (length=6)
+        if (preg_match('/^(?:([a-z]++)\|)?([\w-]++|\*)$/i', trim($source), $matches)) {
+            return array(new SelectorNode(new ElementNode($matches[1] ?: null, $matches[2])));
         }
 
         return array();
diff --git a/Parser/Shortcut/HashParser.php b/Parser/Shortcut/HashParser.php
@@ -33,15 +33,14 @@ public function parse($source)
     {
         // Matches an optional namespace, optional element, and required id
         // $source = 'test|input#ab6bd_field';
-        // $matches = array (size=5)
-        //     0 => string 'test:input#ab6bd_field' (length=22)
-        //     1 => string 'test:' (length=5)
-        //     2 => string 'test' (length=4)
-        //     3 => string 'input' (length=5)
-        //     4 => string 'ab6bd_field' (length=11)
-        if (preg_match('/^(([a-z]+)\|)?([\w-]+|\*)?#([\w-]+)$/i', trim($source), $matches)) {
+        // $matches = array (size=4)
+        //     0 => string 'test|input#ab6bd_field' (length=22)
+        //     1 => string 'test' (length=4)
+        //     2 => string 'input' (length=5)
+        //     3 => string 'ab6bd_field' (length=11)
+        if (preg_match('/^(?:([a-z]++)\|)?+([\w-]++|\*)?+#([\w-]++)$/i', trim($source), $matches)) {
             return array(
-                new SelectorNode(new HashNode(new ElementNode($matches[2] ?: null, $matches[3] ?: null), $matches[4])),
+                new SelectorNode(new HashNode(new ElementNode($matches[1] ?: null, $matches[2] ?: null), $matches[3])),
             );
         }
 
