[regexp] Port RegExpConstructor to C++

src/builtins/builtins-regexp.cc

Index: src/builtins/builtins-regexp.cc
diff --git a/src/builtins/builtins-regexp.cc b/src/builtins/builtins-regexp.cc
index 5f62efabfe6830f15737139f4a652a86ec3a2c9b..2ed4fd9de269351a6c7374e734127a9eb1cabb16 100644
--- a/src/builtins/builtins-regexp.cc
+++ b/src/builtins/builtins-regexp.cc
@@ -7,10 +7,152 @@
 
 #include "src/code-factory.h"
 #include "src/regexp/jsregexp.h"
+#include "src/string-builder.h"
 
 namespace v8 {
 namespace internal {
 
+// -----------------------------------------------------------------------------
+// ES6 section 21.2 RegExp Objects
+
+namespace {
+
+// ES#sec-isregexp IsRegExp ( argument )
+Maybe<bool> IsRegExp(Isolate* isolate, Handle<Object> object) {
+  if (!object->IsJSReceiver()) return Just(false);
+
+  Handle<JSReceiver> receiver = Handle<JSReceiver>::cast(object);
+
+  if (isolate->regexp_function()->initial_map() == receiver->map()) {
+    // Fast-path for unmodified JSRegExp instances.
+    return Just(true);
+  }
+
+  Handle<Object> match;
+  ASSIGN_RETURN_ON_EXCEPTION_VALUE(
+      isolate, match,
+      JSObject::GetProperty(receiver, isolate->factory()->match_symbol()),
+      Nothing<bool>());
+
+  if (!match->IsUndefined(isolate)) return Just(match->BooleanValue());
+  return Just(object->IsJSRegExp());
+}
+
+Handle<String> PatternFlags(Isolate* isolate, Handle<JSRegExp> regexp) {
+  IncrementalStringBuilder builder(isolate);

[Yang, 2016/10/05 07:40:34]

Using the IncrementalStringBuilder is a bit overkill here. We have at most 5
characters and it's definitely always a one-byte string. We could just allocate
a char[5] on the stack and pass that to Factory::NewStringFromOneByte.

The IncrementalStringBuilder would always allocate a 32-character string on the
heap, check for the length on every Append, and truncate the string at the end.
We could extend it to allocate arbitrary sizes at the start (5 in our cases) and
use the IncrementalStringBuilder::NoExtend to avoid the checks, but that seems
over-enginieering it too.

Using NewStringFromOneByte also has the benefit that we would canonicalize
single-character strings.

Then again, all of this probably does not affect performance a lot. And could be
done in a separate CL.

[jgruber, 2016/10/05 08:37:03]

Good point, done. We could improve this even more in the future by not
converting flags back and forth between the bitmap and string representation in
some cases.

+  const JSRegExp::Flags flags = regexp->GetFlags();
+
+  if ((flags & JSRegExp::kGlobal) != 0) builder.AppendCharacter('g');
+  if ((flags & JSRegExp::kIgnoreCase) != 0) builder.AppendCharacter('i');
+  if ((flags & JSRegExp::kMultiline) != 0) builder.AppendCharacter('m');
+  if ((flags & JSRegExp::kUnicode) != 0) builder.AppendCharacter('u');
+  if ((flags & JSRegExp::kSticky) != 0) builder.AppendCharacter('y');
+
+  return builder.Finish().ToHandleChecked();
+}
+
+// ES#sec-regexpinitialize
+// Runtime Semantics: RegExpInitialize ( obj, pattern, flags )
+MaybeHandle<JSRegExp> RegExpInitialize(Isolate* isolate,
+                                       Handle<JSRegExp> regexp,
+                                       Handle<Object> pattern,
+                                       Handle<Object> flags) {
+  Handle<String> pattern_string;
+  if (pattern->IsUndefined(isolate)) {
+    pattern_string = isolate->factory()->empty_string();
+  } else {
+    ASSIGN_RETURN_ON_EXCEPTION(isolate, pattern_string,
+                               Object::ToString(isolate, pattern), JSRegExp);
+  }
+
+  Handle<String> flags_string;
+  if (flags->IsUndefined(isolate)) {
+    flags_string = isolate->factory()->empty_string();
+  } else {
+    ASSIGN_RETURN_ON_EXCEPTION(isolate, flags_string,
+                               Object::ToString(isolate, flags), JSRegExp);
+  }
+
+  // TODO(jgruber): We could avoid the flags back and forth conversions.
+  RETURN_RESULT(isolate,
+                JSRegExp::Initialize(regexp, pattern_string, flags_string),
+                JSRegExp);
+}
+
+}  // namespace
+
+// ES#sec-regexp-pattern-flags
+// RegExp ( pattern, flags )
+BUILTIN(RegExpConstructor) {
+  HandleScope scope(isolate);
+
+  Handle<HeapObject> new_target = args.new_target();
+  Handle<Object> pattern = args.atOrUndefined(isolate, 1);
+  Handle<Object> flags = args.atOrUndefined(isolate, 2);
+
+  Handle<JSFunction> target = isolate->regexp_function();
+
+  bool pattern_is_regexp;
+  {
+    Maybe<bool> maybe_pattern_is_regexp = IsRegExp(isolate, pattern);
+    if (maybe_pattern_is_regexp.IsNothing()) {
+      DCHECK(isolate->has_pending_exception());
+      return isolate->heap()->exception();
+    }
+    pattern_is_regexp = maybe_pattern_is_regexp.FromJust();
+  }
+
+  if (new_target->IsUndefined(isolate)) {
+    new_target = target;
+
+    // ES6 section 21.2.3.1 step 3.b
+    if (pattern_is_regexp && flags->IsUndefined(isolate)) {
+      Handle<Object> pattern_constructor;
+      ASSIGN_RETURN_FAILURE_ON_EXCEPTION(
+          isolate, pattern_constructor,
+          Object::GetProperty(pattern,
+                              isolate->factory()->constructor_string()));
+
+      if (pattern_constructor.is_identical_to(new_target)) {
+        return *pattern;
+      }
+    }
+  }
+
+  if (pattern->IsJSRegExp()) {
+    Handle<JSRegExp> regexp_pattern = Handle<JSRegExp>::cast(pattern);
+
+    if (flags->IsUndefined(isolate)) {
+      flags = PatternFlags(isolate, regexp_pattern);
+    }
+    pattern = handle(regexp_pattern->source(), isolate);
+  } else if (pattern_is_regexp) {
+    Handle<Object> pattern_source;
+    ASSIGN_RETURN_FAILURE_ON_EXCEPTION(
+        isolate, pattern_source,
+        Object::GetProperty(pattern, isolate->factory()->source_string()));
+
+    if (flags->IsUndefined(isolate)) {
+      ASSIGN_RETURN_FAILURE_ON_EXCEPTION(
+          isolate, flags,
+          Object::GetProperty(pattern, isolate->factory()->flags_string()));
+    }
+    pattern = pattern_source;
+  }
+
+  Handle<JSReceiver> new_target_receiver = Handle<JSReceiver>::cast(new_target);
+
+  // TODO(jgruber): Fast-path for target == new_target == unmodified JSRegExp.
+
+  Handle<JSObject> object;
+  ASSIGN_RETURN_FAILURE_ON_EXCEPTION(
+      isolate, object, JSObject::New(target, new_target_receiver));
+  Handle<JSRegExp> regexp = Handle<JSRegExp>::cast(object);
+
+  RETURN_RESULT_OR_FAILURE(isolate,
+                           RegExpInitialize(isolate, regexp, pattern, flags));
+}
+
 namespace {
 
 compiler::Node* LoadLastIndex(CodeStubAssembler* a, compiler::Node* context,