Be more lenient with 4 byte UTF-8 sequences.

Accept 4 byte sequences and convert them into surrogate
pairs instead of expecting 2 separate 3 byte sequences
each encoding one half of a surrogate pair.

Note that in addition to supporting 4 byte sequences in
strings from JNI, we also tolerate them in dex files. This
is mainly for consistency, and there's no need to claim any
sort of official support.

bug: 18848397
bug: https://code.google.com/p/android/issues/detail?id=81341
Change-Id: Ibc98d29e59d98803e640f2489ea4c56912a59b29

1 files changed, 4 insertions, 14 deletions

diff --git a/runtime/mirror/string-inl.h b/runtime/mirror/string-inl.h
index 14d7de2ffb..4a95519bd0 100644
--- a/runtime/mirror/string-inl.h
+++ b/runtime/mirror/string-inl.h
@@ -33,6 +33,10 @@ inline uint32_t String::ClassSize() {
   return Class::ComputeClassSize(true, vtable_entries, 0, 1, 0, 1, 2);
 }
 
+inline uint16_t String::UncheckedCharAt(int32_t index) {
+  return GetCharArray()->Get(index + GetOffset());
+}
+
 inline CharArray* String::GetCharArray() {
   return GetFieldObject<CharArray>(ValueOffset());
 }
@@ -54,20 +58,6 @@ inline String* String::Intern() {
   return Runtime::Current()->GetInternTable()->InternWeak(this);
 }
 
-inline uint16_t String::CharAt(int32_t index) {
-  // TODO: do we need this? Equals is the only caller, and could
-  // bounds check itself.
-  DCHECK_GE(count_, 0);  // ensures the unsigned comparison is safe.
-  if (UNLIKELY(static_cast<uint32_t>(index) >= static_cast<uint32_t>(count_))) {
-    Thread* self = Thread::Current();
-    ThrowLocation throw_location = self->GetCurrentLocationForThrow();
-    self->ThrowNewExceptionF(throw_location, "Ljava/lang/StringIndexOutOfBoundsException;",
-                             "length=%i; index=%i", count_, index);
-    return 0;
-  }
-  return GetCharArray()->Get(index + GetOffset());
-}
-
 inline int32_t String::GetHashCode() {
   int32_t result = GetField32(OFFSET_OF_OBJECT_MEMBER(String, hash_code_));
   if (UNLIKELY(result == 0)) {