Changeset 27571 in webkit for trunk/JavaScriptCore/kjs/regexp.cpp

Timestamp:

Nov 7, 2007, 9:18:39 AM (18 years ago)

Author:

[email protected]

Message:

JavaScriptCore:

Reviewed by Darin Adler.

Fixed part of ​http://bugs.webkit.org/show_bug.cgi?id=15861
15% of string-validate-input.js is spent compiling the same regular expression.

Put RegExpImp properties into a static hashtable to avoid a slew of
PropertyMap churn when creating a RegExpImp.

Factored important bits of regular expression implementation out of
RegExpImp (the JS object) and into RegExp (the PCRE wrapper class),
making RegExp a ref-counted class. (This will help later.)

Removed PCRE_POSIX support because I didn't quite know how to test it
and keep it working with these changes.

1.1% SunSpider speedup. 5.8% speedup on string-validate-input.js.

• kjs/regexp.h: A few interface changes:

1. Renamed "subpatterns()" => "numSubpatterns()"
2. Made flag enumeration private and replaced it with public getters for specific flags.
3. Made RegExp ref-counted so RegExps can be shared by RegExpImps.
4. Made RegExp take a string of flags instead of an int, eliminating duplicated flag parsing code elsewhere.

• kjs/regexp_object.cpp: (KJS::RegExpProtoFunc::callAsFunction): For RegExp.compile:
• Fixed a bug where compile(undefined) would throw an exception.
• Removed some now-redundant code.
• Used RegExp sharing to eliminate an allocation and a bunch of PropertyMap thrash. (Not a big win since compile is a deprecated function. I mainly did this to test the plubming.)

LayoutTests:

Reviewed by Darin Adler.

Beefed up the RegExp.compile testcase to cover a mistake in the
original check-in and a mistake I made while developing my new patch.

• fast/js/resources/regexp-compile.js:

File:

• trunk/JavaScriptCore/kjs/regexp.cpp (modified) (4 diffs)

trunk/JavaScriptCore/kjs/regexp.cpp

@@ -31 +31 @@
 namespace KJS {
 
-RegExp::RegExp(const UString &p, int flags)
-  : m_flags(flags), m_constructionError(0), m_numSubPatterns(0)
+RegExp::RegExp(const UString& pattern)
+  : m_refCount(0)
+  , m_pattern(pattern)
+  , m_flags(0)
+  , m_constructionError(0)
+  , m_numSubpatterns(0)
 {
-#if !USE(POSIX_REGEX)
+    const char* errorMessage;
+    m_regExp = jsRegExpCompile(reinterpret_cast<const JSRegExpChar*>(m_pattern.data()), m_pattern.size(), 0, &m_numSubpatterns, &errorMessage);
+    if (!m_regExp)
+        m_constructionError = strdup(errorMessage);
+}
 
-  int options = 0;
-  if (flags & IgnoreCase)
-    options |= JS_REGEXP_CASELESS;
-  if (flags & Multiline)
-    options |= JS_REGEXP_MULTILINE;
+RegExp::RegExp(const UString& pattern, const UString& flags)
+  : m_refCount(0)
+  , m_pattern(pattern)
+  , m_flags(0)
+  , m_constructionError(0)
+  , m_numSubpatterns(0)
+{
+    // NOTE: The global flag is handled on a case-by-case basis by functions like
+    // String::match and RegExpImp::match.
+    if (flags.find('g') != -1)
+        m_flags |= Global;
 
-  const char* errorMessage;
-  m_regex = jsRegExpCompile(reinterpret_cast<const JSRegExpChar*>(p.data()), p.size(), options,
-    &m_numSubPatterns, &errorMessage);
-  if (!m_regex) {
-    m_constructionError = strdup(errorMessage);
-    return;
-  }
+    // FIXME: Eliminate duplication by adding a way ask a JSRegExp what its flags are.
+    int options = 0;
+    if (flags.find('i') != -1) {
+        m_flags |= IgnoreCase;
+        options |= JS_REGEXP_CASELESS;
+    }
 
-#else /* USE(POSIX_REGEX) */
-
-  int regflags = 0;
-#ifdef REG_EXTENDED
-  regflags |= REG_EXTENDED;
-#endif
-#ifdef REG_ICASE
-  if (flags & IgnoreCase)
-    regflags |= REG_ICASE;
-#endif
-
-  //NOTE: Multiline is not feasible with POSIX regex.
-  //if ( f & Multiline )
-  //    ;
-  // Note: the Global flag is already handled by RegExpProtoFunc::execute
-
-  // FIXME: support \u Unicode escapes.
-
-  int errorCode = regcomp(&m_regex, p.ascii(), regflags);
-  if (errorCode != 0) {
-    char errorMessage[80];
-    regerror(errorCode, &m_regex, errorMessage, sizeof errorMessage);
-    m_constructionError = strdup(errorMessage);
-  }
-
-#endif
+    if (flags.find('m') != -1) {
+        m_flags |= Multiline;
+        options |= JS_REGEXP_MULTILINE;
+    }
+    
+    const char* errorMessage;
+    m_regExp = jsRegExpCompile(reinterpret_cast<const JSRegExpChar*>(m_pattern.data()), m_pattern.size(), options, &m_numSubpatterns, &errorMessage);
+    if (!m_regExp)
+        m_constructionError = strdup(errorMessage);
 }
 
 RegExp::~RegExp()
 {
-#if !USE(POSIX_REGEX)
-  jsRegExpFree(m_regex);
-#else
-  /* TODO: is this really okay after an error ? */
-  regfree(&m_regex);
-#endif
+  jsRegExpFree(m_regExp);
   free(m_constructionError);
 }
@@ -99 +90 @@
     return -1;
 
-#if !USE(POSIX_REGEX)
-
-  if (!m_regex)
+  if (!m_regExp)
     return -1;
 
@@ -113 +102 @@
     offsetVector = fixedSizeOffsetVector;
   } else {
-    offsetVectorSize = (m_numSubPatterns + 1) * 3;
+    offsetVectorSize = (m_numSubpatterns + 1) * 3;
     offsetVector = new int [offsetVectorSize];
     ovector->set(offsetVector);
   }
 
-  int numMatches = jsRegExpExecute(m_regex, reinterpret_cast<const JSRegExpChar*>(s.data()), s.size(), i, offsetVector, offsetVectorSize);
+  int numMatches = jsRegExpExecute(m_regExp, reinterpret_cast<const JSRegExpChar*>(s.data()), s.size(), i, offsetVector, offsetVectorSize);
 
   if (numMatches < 0) {
@@ -131 +120 @@
 
   return offsetVector[0];
-
-#else
-
-  const unsigned maxMatch = 10;
-  regmatch_t rmatch[maxMatch];
-
-  char *str = strdup(s.ascii()); // TODO: why ???
-  if (regexec(&m_regex, str + i, maxMatch, rmatch, 0)) {
-    free(str);
-    return UString::null();
-  }
-  free(str);
-
-  if (!ovector) {
-    *pos = rmatch[0].rm_so + i;
-    return s.substr(rmatch[0].rm_so + i, rmatch[0].rm_eo - rmatch[0].rm_so);
-  }
-
-  // map rmatch array to ovector used in PCRE case
-  m_numSubPatterns = 0;
-  for(unsigned j = 1; j < maxMatch && rmatch[j].rm_so >= 0 ; j++)
-      m_numSubPatterns++;
-  int ovecsize = (m_numSubPatterns+1)*3; // see above
-  *ovector = new int[ovecsize];
-  for (unsigned j = 0; j < m_numSubPatterns + 1; j++) {
-    if (j>maxMatch)
-      break;
-    (*ovector)[2*j] = rmatch[j].rm_so + i;
-    (*ovector)[2*j+1] = rmatch[j].rm_eo + i;
-  }
-
-  *pos = (*ovector)[0];
-  return s.substr((*ovector)[0], (*ovector)[1] - (*ovector)[0]);
-
-#endif
 }