Separate UnicodeCache out into an own file.

src/scanner.h

 // Copyright 2011 the V8 project authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 // Features shared by parsing and pre-parsing scanners.
 
 #ifndef V8_SCANNER_H_
 #define V8_SCANNER_H_
 
 #include "src/allocation.h"
 #include "src/base/logging.h"
 #include "src/char-predicates.h"
 #include "src/globals.h"
 #include "src/hashmap.h"
 #include "src/list.h"
 #include "src/token.h"
 #include "src/unicode.h"
 #include "src/unicode-decoder.h"
 #include "src/utils.h"
 
 namespace v8 {
 namespace internal {
 
 
 class AstRawString;
 class AstValueFactory;
 class ParserRecorder;
+class UnicodeCache;
 
 
 // Returns the value (0 .. 15) of a hexadecimal character c.
 // If c is not a legal hexadecimal character, returns a value < 0.
 inline int HexValue(uc32 c) {
   c -= '0';
   if (static_cast<unsigned>(c) <= 9) return c;
   c = (c | 0x20) - ('a' - '0');  // detect 0x11..0x16 and 0x31..0x36.
   if (static_cast<unsigned>(c) <= 5) return c + 10;
   return -1;
@@ skipping 64 matching lines @@
   virtual bool ReadBlock() = 0;
   virtual size_t SlowSeekForward(size_t code_unit_count) = 0;
 
   const uint16_t* buffer_cursor_;
   const uint16_t* buffer_end_;
   size_t pos_;
 };
 
 
 // ---------------------------------------------------------------------
-// Caching predicates used by scanners.
-
-class UnicodeCache {
- public:
-  UnicodeCache() {}
-  typedef unibrow::Utf8Decoder<512> Utf8Decoder;
-
-  StaticResource<Utf8Decoder>* utf8_decoder() {
-    return &utf8_decoder_;
-  }
-
-  bool IsIdentifierStart(unibrow::uchar c) { return kIsIdentifierStart.get(c); }
-  bool IsIdentifierPart(unibrow::uchar c) { return kIsIdentifierPart.get(c); }
-  bool IsLineTerminator(unibrow::uchar c) { return kIsLineTerminator.get(c); }
-  bool IsLineTerminatorSequence(unibrow::uchar c, unibrow::uchar next) {
-    if (!IsLineTerminator(c)) return false;
-    if (c == 0x000d && next == 0x000a) return false;  // CR with following LF.
-    return true;
-  }
-
-  bool IsWhiteSpace(unibrow::uchar c) { return kIsWhiteSpace.get(c); }
-  bool IsWhiteSpaceOrLineTerminator(unibrow::uchar c) {
-    return kIsWhiteSpaceOrLineTerminator.get(c);
-  }
-
- private:
-  unibrow::Predicate<IdentifierStart, 128> kIsIdentifierStart;
-  unibrow::Predicate<IdentifierPart, 128> kIsIdentifierPart;
-  unibrow::Predicate<unibrow::LineTerminator, 128> kIsLineTerminator;
-  unibrow::Predicate<WhiteSpace, 128> kIsWhiteSpace;
-  unibrow::Predicate<WhiteSpaceOrLineTerminator, 128>
-      kIsWhiteSpaceOrLineTerminator;
-  StaticResource<Utf8Decoder> utf8_decoder_;
-
-  DISALLOW_COPY_AND_ASSIGN(UnicodeCache);
-};
-
-
-// ---------------------------------------------------------------------
 // DuplicateFinder discovers duplicate symbols.
 
 class DuplicateFinder {
  public:
   explicit DuplicateFinder(UnicodeCache* constants)
       : unicode_constants_(constants),
         backing_store_(16),
         map_(&Match) { }
 
   int AddOneByteSymbol(Vector<const uint8_t> key, int value);
@@ skipping 624 matching lines @@
   // inside multiline comments.
   bool has_line_terminator_before_next_;
   // Whether there is a multi-line comment that contains a
   // line-terminator after the current token, and before the next.
   bool has_multiline_comment_before_next_;
 };
 
 } }  // namespace v8::internal
 
 #endif  // V8_SCANNER_H_