Integrate changes from internal code.

protoc
* Enum values may now have custom options, using syntax similar to field
  options.
* Fixed bug where .proto files which use custom options but don't actually
  define them (i.e. they import another .proto file defining the options)
  had to explicitly import descriptor.proto.
* Adjacent string literals in .proto files will now be concatenated, like in
  C.

C++
* Generated message classes now have a Swap() method which efficiently swaps
  the contents of two objects.
* All message classes now have a SpaceUsed() method which returns an estimate
  of the number of bytes of allocated memory currently owned by the object.
  This is particularly useful when you are reusing a single message object
  to improve performance but want to make sure it doesn't bloat up too large.
* New method Message::SerializeAsString() returns a string containing the
  serialized data.  May be more convenient than calling
  SerializeToString(string*).
* In debug mode, log error messages when string-type fields are found to
  contain bytes that are not valid UTF-8.
* Fixed bug where a message with multiple extension ranges couldn't parse
  extensions.
* Fixed bug where MergeFrom(const Message&) didn't do anything if invoked on
  a message that contained no fields (but possibly contained extensions).
* Fixed ShortDebugString() to not be O(n^2).  Durr.
* Fixed crash in TextFormat parsing if the first token in the input caused a
  tokenization error.

Java
* New overload of mergeFrom() which parses a slice of a byte array instead
  of the whole thing.
* New method ByteString.asReadOnlyByteBuffer() does what it sounds like.
* Improved performance of isInitialized() when optimizing for code size.

Python
* Corrected ListFields() signature in Message base class to match what
  subclasses actually implement.
* Some minor refactoring.

4 files changed, 24 insertions, 7 deletions

diff --git a/src/google/protobuf/io/tokenizer.cc b/src/google/protobuf/io/tokenizer.cc
index 8c12fac5..4823912a 100644
--- a/src/google/protobuf/io/tokenizer.cc
+++ b/src/google/protobuf/io/tokenizer.cc
@@ -623,19 +623,17 @@ double Tokenizer::ParseFloat(const string& text) {
   return result;
 }
 
-void Tokenizer::ParseString(const string& text, string* output) {
-  output->clear();
-
+void Tokenizer::ParseStringAppend(const string& text, string* output) {
   // Reminder:  text[0] is always the quote character.  (If text is
   //   empty, it's invalid, so we'll just return.)
   if (text.empty()) {
     GOOGLE_LOG(DFATAL)
-      << " ParseString::ParseString() passed text that could not have been"
-         " tokenized as a string: " << CEscape(text);
+      << " Tokenizer::ParseStringAppend() passed text that could not"
+         " have been tokenized as a string: " << CEscape(text);
     return;
   }
 
-  output->reserve(text.size());
+  output->reserve(output->size() + text.size());
 
   // Loop through the string copying characters to "output" and
   // interpreting escape sequences.  Note that any invalid escape
diff --git a/src/google/protobuf/io/tokenizer.h b/src/google/protobuf/io/tokenizer.h
index 048a588f..98386e0b 100644
--- a/src/google/protobuf/io/tokenizer.h
+++ b/src/google/protobuf/io/tokenizer.h
@@ -139,6 +139,9 @@ class LIBPROTOBUF_EXPORT Tokenizer {
   // result is undefined (possibly an assert failure).
   static void ParseString(const string& text, string* output);
 
+  // Identical to ParseString, but appends to output.
+  static void ParseStringAppend(const string& text, string* output);
+
   // Parses a TYPE_INTEGER token.  Returns false if the result would be
   // greater than max_value.  Otherwise, returns true and sets *output to the
   // result.  If the text is not from a Token of type TYPE_INTEGER originally
@@ -283,6 +286,11 @@ inline const Tokenizer::Token& Tokenizer::current() {
   return current_;
 }
 
+inline void Tokenizer::ParseString(const string& text, string* output) {
+  output->clear();
+  ParseStringAppend(text, output);
+}
+
 }  // namespace io
 }  // namespace protobuf
 
diff --git a/src/google/protobuf/io/tokenizer_unittest.cc b/src/google/protobuf/io/tokenizer_unittest.cc
index c0f5aefd..dd7ed5c8 100644
--- a/src/google/protobuf/io/tokenizer_unittest.cc
+++ b/src/google/protobuf/io/tokenizer_unittest.cc
@@ -584,6 +584,15 @@ TEST_F(TokenizerTest, ParseString) {
 #endif  // GTEST_HAS_DEATH_TEST
 }
 
+TEST_F(TokenizerTest, ParseStringAppend) {
+  // Check that ParseString and ParseStringAppend differ.
+  string output("stuff+");
+  Tokenizer::ParseStringAppend("'hello'", &output);
+  EXPECT_EQ("stuff+hello", output);
+  Tokenizer::ParseString("'hello'", &output);
+  EXPECT_EQ("hello", output);
+}
+
 // -------------------------------------------------------------------
 
 // Each case parses some input text, ignoring the tokens produced, and
diff --git a/src/google/protobuf/io/zero_copy_stream_unittest.cc b/src/google/protobuf/io/zero_copy_stream_unittest.cc
index ec92127d..2ee9e6c4 100644
--- a/src/google/protobuf/io/zero_copy_stream_unittest.cc
+++ b/src/google/protobuf/io/zero_copy_stream_unittest.cc
@@ -156,7 +156,9 @@ int IoTest::ReadFromInput(ZeroCopyInputStream* input, void* data, int size) {
 
     if (out_size <= in_size) {
       memcpy(out, in, out_size);
-      input->BackUp(in_size - out_size);
+      if (in_size > out_size) {
+        input->BackUp(in_size - out_size);
+      }
       return size;  // Copied all of it.
     }