Port and integrate the irregexp engine from V8

runtime/vm/raw_object.h

 // Copyright (c) 2012, the Dart project authors.  Please see the AUTHORS file
 // for details. All rights reserved. Use of this source code is governed by a
 // BSD-style license that can be found in the LICENSE file.
 
 #ifndef VM_RAW_OBJECT_H_
 #define VM_RAW_OBJECT_H_
 
 #include "platform/assert.h"
 #include "vm/atomic.h"
 #include "vm/globals.h"
@@ skipping 621 matching lines @@
     kGetterFunction,     // represents getter functions e.g: get foo() { .. }.
     kSetterFunction,     // represents setter functions e.g: set foo(..) { .. }.
     kConstructor,
     kImplicitGetter,     // represents an implicit getter for fields.
     kImplicitSetter,     // represents an implicit setter for fields.
     kImplicitStaticFinalGetter,  // represents an implicit getter for static
                                  // final fields (incl. static const fields).
     kMethodExtractor,  // converts method into implicit closure on the receiver.
     kNoSuchMethodDispatcher,  // invokes noSuchMethod.
     kInvokeFieldDispatcher,  // invokes a field as a closure.
+    kIrregexpFunction,   // represents a generated irregexp matcher function.
   };
 
   enum AsyncModifier {
     kNoModifier,
     kAsync,
   };
 
  private:
   // So that the MarkingVisitor::DetachCode can null out the code fields.
   friend class MarkingVisitor;
   friend class Class;
   RAW_HEAP_OBJECT_IMPLEMENTATION(Function);
   static bool SkipCode(RawFunction* raw_fun);
 
   RawObject** from() { return reinterpret_cast<RawObject**>(&ptr()->name_); }
   RawString* name_;
   RawObject* owner_;  // Class or patch class or mixin class
                       // where this function is defined.
+  RawJSRegExp* regexp_;  // The corresponding regexp for irregexp functions.

[Florian Schneider, 2014/10/01 17:04:14]

Maybe re-use the owner field for this? It is not used otherwise, since those
functions are not member methods of a specific class.

[Vyacheslav Egorov (Google), 2014/10/01 20:13:21]

Kill this field by being more explicit about compilation instead of using lazy
compilation stub for this.

[jgruber1, 2014/10/03 18:59:52]

As discussed, the regexp object pointer is now stored in data_.

[jgruber1, 2014/10/03 18:59:53]

As discussed, the regexp object pointer is now stored in data_.

   RawAbstractType* result_type_;
   RawArray* parameter_types_;
   RawArray* parameter_names_;
   RawObject* data_;  // Additional data specific to the function kind.
   RawObject** to_snapshot() {
     return reinterpret_cast<RawObject**>(&ptr()->data_);
   }
   // Fields below are not part of the snapshot.
   RawArray* ic_data_array_;  // ICData of unoptimized code.
   RawObject** to_no_code() {
     return reinterpret_cast<RawObject**>(&ptr()->ic_data_array_);
   }
   RawInstructions* instructions_;  // Instructions of currently active code.
   RawCode* unoptimized_code_;  // Unoptimized code, keep it after optimization.
   RawObject** to() {
     return reinterpret_cast<RawObject**>(&ptr()->unoptimized_code_);
   }
 
   int32_t token_pos_;
   int32_t end_token_pos_;
   int32_t usage_counter_;  // Incremented while function is running.
   int16_t num_fixed_parameters_;
   int16_t num_optional_parameters_;  // > 0: positional; < 0: named.
   int16_t deoptimization_counter_;
   uint32_t kind_tag_;  // See Function::KindTagBits.
   uint16_t optimized_instruction_count_;
   uint16_t optimized_call_site_count_;
+  intptr_t regexp_specialization_;

[Florian Schneider, 2014/10/01 17:04:14]

As mentioned, try using the data_ field for that. It is a kind-specific field
that can be used for different purposes depending on function kind.

[Vyacheslav Egorov (Google), 2014/10/01 20:13:21]

Ditto.

[jgruber1, 2014/10/03 18:59:52]

As discussed, changed to int16_t and moved 3 lines up to avoid increasing the
size of RawFunction.

[jgruber1, 2014/10/03 18:59:53]

As discussed, changed to int16_t and moved 3 lines up to avoid increasing the
size of RawFunction.

 };
 
 
 class RawClosureData : public RawObject {
  private:
   RAW_HEAP_OBJECT_IMPLEMENTATION(ClosureData);
 
   RawObject** from() {
     return reinterpret_cast<RawObject**>(&ptr()->context_scope_);
   }
@@ skipping 1072 matching lines @@
 // VM type for capturing JS regular expressions.
 class RawJSRegExp : public RawInstance {
   RAW_HEAP_OBJECT_IMPLEMENTATION(JSRegExp);
 
   RawObject** from() {
     return reinterpret_cast<RawObject**>(&ptr()->data_length_);
   }
   RawSmi* data_length_;
   RawSmi* num_bracket_expressions_;
   RawString* pattern_;  // Pattern to be used for matching.
+  RawFunction* one_byte_function_;
+  RawFunction* two_byte_function_;
+  RawFunction* external_one_byte_function_;
+  RawFunction* external_two_byte_function_;
+  RawString* one_byte_subject_;

[Vyacheslav Egorov (Google), 2014/10/01 20:13:21]

This four subject fields smell like memory leak to me. Please kill them with
fire.

[jgruber1, 2014/10/03 18:59:53]

Done.

+  RawString* two_byte_subject_;
+  RawString* external_one_byte_subject_;
+  RawString* external_two_byte_subject_;
   RawObject** to() {
-    return reinterpret_cast<RawObject**>(&ptr()->pattern_);
+    return reinterpret_cast<RawObject**>(&ptr()->external_two_byte_subject_);
   }
 
   // A bitfield with two fields:
   // type: Uninitialized, simple or complex.
   // flags: Represents global/local, case insensitive, multiline.
   int8_t type_flags_;
 
   // Variable length data follows here.
   uint8_t* data() { OPEN_ARRAY_START(uint8_t, uint8_t); }
 };
@@ skipping 266 matching lines @@
   COMPILE_ASSERT(kExternalTypedDataInt8ArrayCid ==
                  kTypedDataInt8ArrayViewCid + 15);
   COMPILE_ASSERT(kByteBufferCid == kExternalTypedDataInt8ArrayCid + 14);
   COMPILE_ASSERT(kNullCid == kByteBufferCid + 1);
   return (kNullCid - kTypedDataInt8ArrayCid);
 }
 
 }  // namespace dart
 
 #endif  // VM_RAW_OBJECT_H_