Enable slices of external strings (in the tentative implementation).

TEST=cctest test-strings/SliceFromExternal, mjsunit/string-slices.js

Review URL: http://codereview.chromium.org/7832002

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9295 ce2b1a6d-e550-0410-aec6-3dcde31c8c00

src/heap.cc

@@ -2737,25 +2737,23 @@ MaybeObject* Heap::AllocateSubString(String* buffer,
   // Make an attempt to flatten the buffer to reduce access time.
   buffer = buffer->TryFlattenGetString();
 
-  // TODO(1626): For now slicing external strings is not supported.  However,
-  // a flat cons string can have an external string as first part in some cases.
-  // Therefore we have to single out this case as well.
   if (!FLAG_string_slices ||
-      (buffer->IsConsString() &&
-        (!buffer->IsFlat() ||
-         !ConsString::cast(buffer)->first()->IsSeqString())) ||
-      buffer->IsExternalString() ||
+      !buffer->IsFlat() ||
       length < SlicedString::kMinLength ||
       pretenure == TENURED) {
     Object* result;
-    { MaybeObject* maybe_result = buffer->IsAsciiRepresentation()
-                     ? AllocateRawAsciiString(length, pretenure)
-                     : AllocateRawTwoByteString(length, pretenure);
+    // WriteToFlat takes care of the case when an indirect string has a
+    // different encoding from its underlying string.  These encodings may
+    // differ because of externalization.
+    bool is_ascii = buffer->IsAsciiRepresentation();
+    { MaybeObject* maybe_result = is_ascii
+                                  ? AllocateRawAsciiString(length, pretenure)
+                                  : AllocateRawTwoByteString(length, pretenure);
       if (!maybe_result->ToObject(&result)) return maybe_result;
     }
     String* string_result = String::cast(result);
     // Copy the characters into the new object.
-    if (buffer->IsAsciiRepresentation()) {
+    if (is_ascii) {
       ASSERT(string_result->IsAsciiRepresentation());
       char* dest = SeqAsciiString::cast(string_result)->GetChars();
       String::WriteToFlat(buffer, dest, start, end);
@@ -2768,12 +2766,17 @@ MaybeObject* Heap::AllocateSubString(String* buffer,
   }
 
   ASSERT(buffer->IsFlat());
-  ASSERT(!buffer->IsExternalString());
 #if DEBUG
   buffer->StringVerify();
 #endif
 
   Object* result;
+  // When slicing an indirect string we use its encoding for a newly created
+  // slice and don't check the encoding of the underlying string.  This is safe
+  // even if the encodings are different because of externalization.  If an
+  // indirect ASCII string is pointing to a two-byte string, the two-byte char
+  // codes of the underlying string must still fit into ASCII (because
+  // externalization must not change char codes).
   { Map* map = buffer->IsAsciiRepresentation()
                  ? sliced_ascii_string_map()
                  : sliced_string_map();
@@ -2799,7 +2802,8 @@ MaybeObject* Heap::AllocateSubString(String* buffer,
     sliced_string->set_parent(buffer);
     sliced_string->set_offset(start);
   }
-  ASSERT(sliced_string->parent()->IsSeqString());
+  ASSERT(sliced_string->parent()->IsSeqString() ||
+         sliced_string->parent()->IsExternalString());
   return result;
 }
 

src/runtime.cc

@@ -2893,7 +2893,7 @@ void FindStringIndicesDispatch(Isolate* isolate,
       }
     } else {
       Vector<const uc16> subject_vector = subject_content.ToUC16Vector();
-      if (pattern->IsAsciiRepresentation()) {
+      if (pattern_content.IsAscii()) {
         FindStringIndices(isolate,
                           subject_vector,
                           pattern_content.ToAsciiVector(),

test/cctest/test-strings.cc

@@ -502,6 +502,35 @@ TEST(SliceFromCons) {
 }
 
 
+class AsciiVectorResource : public v8::String::ExternalAsciiStringResource {
+ public:
+  explicit AsciiVectorResource(i::Vector<const char> vector)
+      : data_(vector) {}
+  virtual ~AsciiVectorResource() {}
+  virtual size_t length() const { return data_.length(); }
+  virtual const char* data() const { return data_.start(); }
+ private:
+  i::Vector<const char> data_;
+};
+
+
+TEST(SliceFromExternal) {
+  FLAG_string_slices = true;
+  InitializeVM();
+  v8::HandleScope scope;
+  AsciiVectorResource resource(
+      i::Vector<const char>("abcdefghijklmnopqrstuvwxyz", 26));
+  Handle<String> string = FACTORY->NewExternalStringFromAscii(&resource);
+  CHECK(string->IsExternalString());
+  Handle<String> slice = FACTORY->NewSubString(string, 1, 25);
+  CHECK(slice->IsSlicedString());
+  CHECK(string->IsExternalString());
+  CHECK_EQ(SlicedString::cast(*slice)->parent(), *string);
+  CHECK(SlicedString::cast(*slice)->parent()->IsExternalString());
+  CHECK(slice->IsFlat());
+}
+
+
 TEST(TrivialSlice) {
   // This tests whether a slice that contains the entire parent string
   // actually creates a new string (it should not).

test/mjsunit/string-slices.js

@@ -189,11 +189,16 @@ assertEquals("\u03B4\u03B5\u03B6\u03B7\u03B8\u03B9abcdefghijklmnop",
 assertEquals("\u03B2\u03B3\u03B4\u03B5\u03B4\u03B5\u03B6\u03B7",
     utf.substring(5,1) + utf.substring(3,7));
 
-/*
 // Externalizing strings.
-var a = "123456789qwertyuiopasdfghjklzxcvbnm";
-var b = a.slice(1,-1);
+var a = "123456789" + "qwertyuiopasdfghjklzxcvbnm";
+var b = "23456789qwertyuiopasdfghjklzxcvbn"
 assertEquals(a.slice(1,-1), b);
-externalizeString(a);
+
+assertTrue(isAsciiString(a));
+externalizeString(a, true);
+assertFalse(isAsciiString(a));
+
 assertEquals(a.slice(1,-1), b);
-*/
+assertTrue(/3456789qwe/.test(a));
+assertEquals(5, a.indexOf("678"));
+assertEquals("12345", a.split("6")[0]);