Changeset 67790 in webkit for trunk/JavaScriptCore/yarr/RegexPattern.h

Timestamp:

Sep 18, 2010, 2:04:15 PM (15 years ago)

Author:

[email protected]

Message:

2010-09-18 Michael Saboff <​[email protected]>

Reviewed by Gavin Barraclough.

Added code to unroll regular expressions containing ^{.
Alternatives that begin with} are tagged during parsing
and rolled up in containing sub expression structs.
After parsing, a regular expression flagged as containing
a ^{(a.k.a. BOL) is processed further in optimizeBOL().
A copy of the disjunction is made excluding alternatives that
are rooted with BOL. The original alternatives are flagged
to only be executed once. The copy of the other alternatives are
added to the original expression.
In the case that all original alternatives are flagged, there
won't be any looping alternatives.
The JIT generator will emit code accordingly, executing the
original alternatives once and then looping over the
alternatives that aren't anchored with a BOL (if any).
​https://bugs.webkit.org/show_bug.cgi?id=45787}

• yarr/RegexCompiler.cpp: (JSC::Yarr::RegexPatternConstructor::assertionBOL): (JSC::Yarr::RegexPatternConstructor::atomParenthesesEnd): (JSC::Yarr::RegexPatternConstructor::copyDisjunction): (JSC::Yarr::RegexPatternConstructor::copyTerm): (JSC::Yarr::RegexPatternConstructor::optimizeBOL): (JSC::Yarr::compileRegex):
• yarr/RegexJIT.cpp: (JSC::Yarr::RegexGenerator::generateDisjunction):
• yarr/RegexPattern.h: (JSC::Yarr::PatternAlternative::PatternAlternative): (JSC::Yarr::PatternAlternative::setOnceThrough): (JSC::Yarr::PatternAlternative::onceThrough): (JSC::Yarr::PatternDisjunction::PatternDisjunction): (JSC::Yarr::RegexPattern::RegexPattern): (JSC::Yarr::RegexPattern::reset):

2010-09-18 Michael Saboff <​[email protected]>

Reviewed by Gavin Barraclough.

Added new tests to check for proper handling of ^{in multiline
regular expressions. Added as part of
​https://bugs.webkit.org/show_bug.cgi?id=45787}

• fast/js/regexp-bol-with-multiline-expected.txt: Added.
• fast/js/regexp-bol-with-multiline.html: Added.
• fast/js/script-tests/regexp-bol-with-multiline.js: Added.

File:

• trunk/JavaScriptCore/yarr/RegexPattern.h (modified) (7 diffs)

trunk/JavaScriptCore/yarr/RegexPattern.h

@@ -208 +208 @@
     PatternAlternative(PatternDisjunction* disjunction)
         : m_parent(disjunction)
+        , m_onceThrough(false)
+        , m_hasFixedSize(false)
+        , m_startsWithBOL(false)
+        , m_containsBOL(false)
     {
     }
@@ -221 +225 @@
         ASSERT(m_terms.size());
         m_terms.shrink(m_terms.size() - 1);
+    }
+    
+    void setOnceThrough()
+    {
+        m_onceThrough = true;
+    }
+    
+    bool onceThrough()
+    {
+        return m_onceThrough;
     }
 
@@ -226 +240 @@
     PatternDisjunction* m_parent;
     unsigned m_minimumSize;
-    bool m_hasFixedSize;
+    bool m_onceThrough : 1;
+    bool m_hasFixedSize : 1;
+    bool m_startsWithBOL : 1;
+    bool m_containsBOL : 1;
 };
 
@@ -232 +249 @@
     PatternDisjunction(PatternAlternative* parent = 0)
         : m_parent(parent)
+        , m_hasFixedSize(false)
     {
     }
@@ -270 +288 @@
         : m_ignoreCase(ignoreCase)
         , m_multiline(multiline)
+        , m_containsBackreferences(false)
+        , m_containsBOL(false)
         , m_numSubpatterns(0)
         , m_maxBackReference(0)
-        , m_containsBackreferences(false)
         , newlineCached(0)
         , digitsCached(0)
@@ -295 +314 @@
 
         m_containsBackreferences = false;
+        m_containsBOL = false;
 
         newlineCached = 0;
@@ -358 +378 @@
     }
 
-    bool m_ignoreCase;
-    bool m_multiline;
+    bool m_ignoreCase : 1;
+    bool m_multiline : 1;
+    bool m_containsBackreferences : 1;
+    bool m_containsBOL : 1;
     unsigned m_numSubpatterns;
     unsigned m_maxBackReference;
-    bool m_containsBackreferences;
     PatternDisjunction* m_body;
     Vector<PatternDisjunction*, 4> m_disjunctions;