Changeset 62416 in webkit for trunk/JavaScriptCore/parser

Timestamp:

Jul 2, 2010, 4:49:07 PM (15 years ago)

Author:

[email protected]

Message:

2010-07-02 Sheriff Bot <​[email protected]>

Unreviewed, rolling out r62410.
​http://trac.webkit.org/changeset/62410
​https://bugs.webkit.org/show_bug.cgi?id=41549

accursed last minute changes (Requested by olliej on #webkit).

• parser/Lexer.cpp: (JSC::Lexer::setCode): (JSC::Lexer::copyCodeWithoutBOMs): (JSC::Lexer::sourceCode):
• parser/SourceProvider.h: (JSC::): (JSC::SourceProvider::SourceProvider): (JSC::SourceProvider::hasBOMs): (JSC::UStringSourceProvider::create): (JSC::UStringSourceProvider::getRange): (JSC::UStringSourceProvider::UStringSourceProvider):
• wtf/text/StringImpl.h:

2010-07-02 Sheriff Bot <​[email protected]>

Unreviewed, rolling out r62410.
​http://trac.webkit.org/changeset/62410
​https://bugs.webkit.org/show_bug.cgi?id=41549

accursed last minute changes (Requested by olliej on #webkit).

• bindings/js/ScriptSourceProvider.h: (WebCore::ScriptSourceProvider::ScriptSourceProvider):
• bindings/js/StringSourceProvider.h: (WebCore::StringSourceProvider::StringSourceProvider):
• loader/CachedScript.cpp: (WebCore::CachedScript::CachedScript): (WebCore::CachedScript::script):
• loader/CachedScript.h:

Location:

trunk/JavaScriptCore/parser

Files:

• Lexer.cpp (modified) (4 diffs)
• SourceProvider.h (modified) (2 diffs)

trunk/JavaScriptCore/parser/Lexer.cpp

@@ -46 +46 @@
 namespace JSC {
 
+static const UChar byteOrderMark = 0xFEFF;
 
 enum CharacterTypes {
@@ -256 +257 @@
     m_buffer16.reserveInitialCapacity((m_codeEnd - m_code) / 2);
 
+    // ECMA-262 calls for stripping all Cf characters, but we only strip BOM characters.
+    // See <https://bugs.webkit.org/show_bug.cgi?id=4931> for details.
+    if (source.provider()->hasBOMs()) {
+        for (const UChar* p = m_codeStart; p < m_codeEnd; ++p) {
+            if (UNLIKELY(*p == byteOrderMark)) {
+                copyCodeWithoutBOMs();
+                break;
+            }
+        }
+    }
+
     if (LIKELY(m_code < m_codeEnd))
         m_current = *m_code;
@@ -261 +273 @@
         m_current = -1;
     ASSERT(currentOffset() == source.startOffset());
+}
+
+void Lexer::copyCodeWithoutBOMs()
+{
+    // Note: In this case, the character offset data for debugging will be incorrect.
+    // If it's important to correctly debug code with extraneous BOMs, then the caller
+    // should strip the BOMs when creating the SourceProvider object and do its own
+    // mapping of offsets within the stripped text to original text offset.
+
+    m_codeWithoutBOMs.reserveCapacity(m_codeEnd - m_code);
+    for (const UChar* p = m_code; p < m_codeEnd; ++p) {
+        UChar c = *p;
+        if (c != byteOrderMark)
+            m_codeWithoutBOMs.append(c);
+    }
+    ptrdiff_t startDelta = m_codeStart - m_code;
+    m_code = m_codeWithoutBOMs.data();
+    m_codeStart = m_code + startDelta;
+    m_codeEnd = m_codeWithoutBOMs.data() + m_codeWithoutBOMs.size();
 }
 
@@ -1150 +1181 @@
 SourceCode Lexer::sourceCode(int openBrace, int closeBrace, int firstLine)
 {
+    if (m_codeWithoutBOMs.isEmpty())
+        return SourceCode(m_source->provider(), openBrace, closeBrace + 1, firstLine);
+
+    const UChar* data = m_source->provider()->data();
+    
+    ASSERT(openBrace < closeBrace);
+    int i;
+    for (i = m_source->startOffset(); i < openBrace; ++i) {
+        if (data[i] == byteOrderMark) {
+            openBrace++;
+            closeBrace++;
+        }
+    }
+    for (; i < closeBrace; ++i) {
+        if (data[i] == byteOrderMark)
+            closeBrace++;
+    }
+
+    ASSERT(openBrace < closeBrace);
+
     return SourceCode(m_source->provider(), openBrace, closeBrace + 1, firstLine);
 }

trunk/JavaScriptCore/parser/SourceProvider.h

@@ -35 +35 @@
 namespace JSC {
 
+    enum SourceBOMPresence { SourceHasNoBOMs, SourceCouldHaveBOMs };
+
     class SourceProvider : public RefCounted<SourceProvider> {
     public:
-        SourceProvider(const UString& url)
+        SourceProvider(const UString& url, SourceBOMPresence hasBOMs = SourceCouldHaveBOMs)
             : m_url(url)
+            , m_hasBOMs(hasBOMs)
         {
         }
@@ -50 +53 @@
         intptr_t asID() { return reinterpret_cast<intptr_t>(this); }
 
+        SourceBOMPresence hasBOMs() const { return m_hasBOMs; }
+
     private:
         UString m_url;
+        SourceBOMPresence m_hasBOMs;
     };
 
     class UStringSourceProvider : public SourceProvider {
     public:
-        static PassRefPtr<UStringSourceProvider> create(const UString& source, const UString& url, bool hasBOMs = true)
+        static PassRefPtr<UStringSourceProvider> create(const UString& source, const UString& url)
         {
-            return adoptRef(new UStringSourceProvider(source, url, hasBOMs));
+            return adoptRef(new UStringSourceProvider(source, url));
         }
 
-        UString getRange(int start, int end) const
-        {
-            return m_source.substr(start, end - start);
-        }
+        UString getRange(int start, int end) const { return m_source.substr(start, end - start); }
         const UChar* data() const { return m_source.data(); }
         int length() const { return m_source.size(); }
 
     private:
-        UStringSourceProvider(const UString& source, const UString& url, bool hasBOMs)
+        UStringSourceProvider(const UString& source, const UString& url)
             : SourceProvider(url)
             , m_source(source)
         {
-            if (hasBOMs && m_source.size()) {
-                bool scratch = false;
-                m_source = UString(m_source.rep()->copyStringWithoutBOMs(false, scratch));
-            }
         }