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 613 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;
@@ skipping 22 matching lines @@
   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_;
+  int16_t regexp_cid_;

[Ivan Posva, 2014/10/10 06:35:54]

Would an int8_t do? Or a uint8_t?

Generally it is a bad idea to add fields to RawFunction, as every field added
causes significant memory consumption.

It does not appear that this field is ever being properly preserved into or
initialized from a snapshot.

Also these fields should be sorted by size, so that we do not end up with
internal alignment. Not your CL's issue though.

[Vyacheslav Egorov (Google), 2014/10/10 08:08:08]

We were indeed concerned about the size of the Function (if you go back through
comments you will see that I was against adding any fields to it).

However here I counted the fields and saw that we have 16bits ununused - so this
field does not really increase any memory consumption.

I have a backup plan on how to *not* add this field  - which we will apply if
somebody else needs 16bits in Function. The only reason we did not apply it
right away was that it makes current CL even bigger.
Great catch with a snapshot. Really easy to forget with the current setup, and
it's not caught statically.

[jgruber1, 2014/10/10 09:29:44]

Added snapshotting of regexp_cid_.

   uint32_t kind_tag_;  // See Function::KindTagBits.
   uint16_t optimized_instruction_count_;
   uint16_t optimized_call_site_count_;
 };
 
 
 class RawClosureData : public RawObject {
  private:
   RAW_HEAP_OBJECT_IMPLEMENTATION(ClosureData);
 
@@ skipping 1075 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_;
   RawObject** to() {
-    return reinterpret_cast<RawObject**>(&ptr()->pattern_);
+    return reinterpret_cast<RawObject**>(&ptr()->external_two_byte_function_);
   }
 
   // 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_