[regexp] implement case-insensitive unicode regexps.

src/regexp/regexp-ast.h

 // Copyright 2016 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.
 
 #ifndef V8_REGEXP_REGEXP_AST_H_
 #define V8_REGEXP_REGEXP_AST_H_
 
 #include "src/objects.h"
 #include "src/utils.h"
 #include "src/zone.h"
@@ skipping 90 matching lines @@
     return list;
   }
   bool Contains(uc32 i) { return from_ <= i && i <= to_; }
   uc32 from() const { return from_; }
   void set_from(uc32 value) { from_ = value; }
   uc32 to() const { return to_; }
   void set_to(uc32 value) { to_ = value; }
   bool is_valid() { return from_ <= to_; }
   bool IsEverything(uc16 max) { return from_ == 0 && to_ >= max; }
   bool IsSingleton() { return (from_ == to_); }
-  void AddCaseEquivalents(Isolate* isolate, Zone* zone,
-                          ZoneList<CharacterRange>* ranges, bool is_one_byte);
+  static void AddCaseEquivalents(Isolate* isolate, Zone* zone,
+                                 ZoneList<CharacterRange>* ranges,
+                                 bool is_one_byte);
   // Whether a range list is in canonical form: Ranges ordered by from value,
   // and ranges non-overlapping and non-adjacent.
   static bool IsCanonical(ZoneList<CharacterRange>* ranges);
   // Convert range list to canonical form. The characters covered by the ranges
   // will still be the same, but no character is in more than one range, and
   // adjacent ranges are merged. The resulting list may be shorter than the
   // original, but cannot be longer.
   static void Canonicalize(ZoneList<CharacterRange>* ranges);
   // Negate the contents of a character range in canonical form.
   static void Negate(ZoneList<CharacterRange>* src,
@@ skipping 163 matching lines @@
 class RegExpCharacterClass final : public RegExpTree {
  public:
   RegExpCharacterClass(ZoneList<CharacterRange>* ranges, bool is_negated)
       : set_(ranges), is_negated_(is_negated) {}
   explicit RegExpCharacterClass(uc16 type) : set_(type), is_negated_(false) {}
   void* Accept(RegExpVisitor* visitor, void* data) override;
   RegExpNode* ToNode(RegExpCompiler* compiler, RegExpNode* on_success) override;
   RegExpCharacterClass* AsCharacterClass() override;
   bool IsCharacterClass() override;
   bool IsTextElement() override { return true; }
-  bool NeedsDesugaringForUnicode(Zone* zone);
   int min_match() override { return 1; }
   int max_match() override { return 1; }
   void AppendToText(RegExpText* text, Zone* zone) override;
   CharacterSet character_set() { return set_; }
   // TODO(lrn): Remove need for complex version if is_standard that
   // recognizes a mangled standard set and just do { return set_.is_special(); }
   bool is_standard(Zone* zone);
   // Returns a value representing the standard character set if is_standard()
   // returns true.
   // Currently used values are:
   // s : unicode whitespace
   // S : unicode non-whitespace
   // w : ASCII word character (digit, letter, underscore)
   // W : non-ASCII word character
   // d : ASCII digit
   // D : non-ASCII digit
-  // . : non-unicode non-newline
+  // . : non-newline
   // * : All characters, for advancing unanchored regexp
   uc16 standard_type() { return set_.standard_set_type(); }
   ZoneList<CharacterRange>* ranges(Zone* zone) { return set_.ranges(zone); }
   bool is_negated() { return is_negated_; }
 
  private:
   CharacterSet set_;
   bool is_negated_;
 };
 
@@ skipping 186 matching lines @@
   RegExpEmpty* AsEmpty() override;
   bool IsEmpty() override;
   int min_match() override { return 0; }
   int max_match() override { return 0; }
 };
 
 }  // namespace internal
 }  // namespace v8
 
 #endif  // V8_REGEXP_REGEXP_AST_H_