Integrated internal changes from Google

This includes all internal changes from around May 20 to now.

4 files changed, 122 insertions, 42 deletions

diff --git a/src/google/protobuf/io/coded_stream.cc b/src/google/protobuf/io/coded_stream.cc
index d8354c1f..148eee0e 100644
--- a/src/google/protobuf/io/coded_stream.cc
+++ b/src/google/protobuf/io/coded_stream.cc
@@ -376,6 +376,49 @@ inline ::std::pair<bool, const uint8*> ReadVarint32FromArray(
   return std::make_pair(true, ptr);
 }
 
+GOOGLE_ATTRIBUTE_ALWAYS_INLINE::std::pair<bool, const uint8*> ReadVarint64FromArray(
+    const uint8* buffer, uint64* value);
+inline ::std::pair<bool, const uint8*> ReadVarint64FromArray(
+    const uint8* buffer, uint64* value) {
+  const uint8* ptr = buffer;
+  uint32 b;
+
+  // Splitting into 32-bit pieces gives better performance on 32-bit
+  // processors.
+  uint32 part0 = 0, part1 = 0, part2 = 0;
+
+  b = *(ptr++); part0  = b      ; if (!(b & 0x80)) goto done;
+  part0 -= 0x80;
+  b = *(ptr++); part0 += b <<  7; if (!(b & 0x80)) goto done;
+  part0 -= 0x80 << 7;
+  b = *(ptr++); part0 += b << 14; if (!(b & 0x80)) goto done;
+  part0 -= 0x80 << 14;
+  b = *(ptr++); part0 += b << 21; if (!(b & 0x80)) goto done;
+  part0 -= 0x80 << 21;
+  b = *(ptr++); part1  = b      ; if (!(b & 0x80)) goto done;
+  part1 -= 0x80;
+  b = *(ptr++); part1 += b <<  7; if (!(b & 0x80)) goto done;
+  part1 -= 0x80 << 7;
+  b = *(ptr++); part1 += b << 14; if (!(b & 0x80)) goto done;
+  part1 -= 0x80 << 14;
+  b = *(ptr++); part1 += b << 21; if (!(b & 0x80)) goto done;
+  part1 -= 0x80 << 21;
+  b = *(ptr++); part2  = b      ; if (!(b & 0x80)) goto done;
+  part2 -= 0x80;
+  b = *(ptr++); part2 += b <<  7; if (!(b & 0x80)) goto done;
+  // "part2 -= 0x80 << 7" is irrelevant because (0x80 << 7) << 56 is 0.
+
+  // We have overrun the maximum size of a varint (10 bytes).  Assume
+  // the data is corrupt.
+  return std::make_pair(false, ptr);
+
+ done:
+  *value = (static_cast<uint64>(part0)) |
+           (static_cast<uint64>(part1) << 28) |
+           (static_cast<uint64>(part2) << 56);
+  return std::make_pair(true, ptr);
+}
+
 }  // namespace
 
 bool CodedInputStream::ReadVarint32Slow(uint32* value) {
@@ -408,6 +451,32 @@ int64 CodedInputStream::ReadVarint32Fallback(uint32 first_byte_or_zero) {
   }
 }
 
+int CodedInputStream::ReadVarintSizeAsIntSlow() {
+  // Directly invoke ReadVarint64Fallback, since we already tried to optimize
+  // for one-byte varints.
+  std::pair<uint64, bool> p = ReadVarint64Fallback();
+  if (!p.second || p.first > static_cast<uint64>(INT_MAX)) return -1;
+  return p.first;
+}
+
+int CodedInputStream::ReadVarintSizeAsIntFallback() {
+  if (BufferSize() >= kMaxVarintBytes ||
+      // Optimization:  We're also safe if the buffer is non-empty and it ends
+      // with a byte that would terminate a varint.
+      (buffer_end_ > buffer_ && !(buffer_end_[-1] & 0x80))) {
+    uint64 temp;
+    ::std::pair<bool, const uint8*> p = ReadVarint64FromArray(buffer_, &temp);
+    if (!p.first || temp > static_cast<uint64>(INT_MAX)) return -1;
+    buffer_ = p.second;
+    return temp;
+  } else {
+    // Really slow case: we will incur the cost of an extra function call here,
+    // but moving this out of line reduces the size of this function, which
+    // improves the common case. In micro benchmarks, this is worth about 10-15%
+    return ReadVarintSizeAsIntSlow();
+  }
+}
+
 uint32 CodedInputStream::ReadTagSlow() {
   if (buffer_ == buffer_end_) {
     // Call refresh.
@@ -499,47 +568,13 @@ std::pair<uint64, bool> CodedInputStream::ReadVarint64Fallback() {
       // Optimization:  We're also safe if the buffer is non-empty and it ends
       // with a byte that would terminate a varint.
       (buffer_end_ > buffer_ && !(buffer_end_[-1] & 0x80))) {
-    // Fast path:  We have enough bytes left in the buffer to guarantee that
-    // this read won't cross the end, so we can skip the checks.
-
-    const uint8* ptr = buffer_;
-    uint32 b;
-
-    // Splitting into 32-bit pieces gives better performance on 32-bit
-    // processors.
-    uint32 part0 = 0, part1 = 0, part2 = 0;
-
-    b = *(ptr++); part0  = b      ; if (!(b & 0x80)) goto done;
-    part0 -= 0x80;
-    b = *(ptr++); part0 += b <<  7; if (!(b & 0x80)) goto done;
-    part0 -= 0x80 << 7;
-    b = *(ptr++); part0 += b << 14; if (!(b & 0x80)) goto done;
-    part0 -= 0x80 << 14;
-    b = *(ptr++); part0 += b << 21; if (!(b & 0x80)) goto done;
-    part0 -= 0x80 << 21;
-    b = *(ptr++); part1  = b      ; if (!(b & 0x80)) goto done;
-    part1 -= 0x80;
-    b = *(ptr++); part1 += b <<  7; if (!(b & 0x80)) goto done;
-    part1 -= 0x80 << 7;
-    b = *(ptr++); part1 += b << 14; if (!(b & 0x80)) goto done;
-    part1 -= 0x80 << 14;
-    b = *(ptr++); part1 += b << 21; if (!(b & 0x80)) goto done;
-    part1 -= 0x80 << 21;
-    b = *(ptr++); part2  = b      ; if (!(b & 0x80)) goto done;
-    part2 -= 0x80;
-    b = *(ptr++); part2 += b <<  7; if (!(b & 0x80)) goto done;
-    // "part2 -= 0x80 << 7" is irrelevant because (0x80 << 7) << 56 is 0.
-
-    // We have overrun the maximum size of a varint (10 bytes).  The data
-    // must be corrupt.
-    return std::make_pair(0, false);
-
-   done:
-    Advance(ptr - buffer_);
-    return std::make_pair((static_cast<uint64>(part0)) |
-                              (static_cast<uint64>(part1) << 28) |
-                              (static_cast<uint64>(part2) << 56),
-                          true);
+    uint64 temp;
+    ::std::pair<bool, const uint8*> p = ReadVarint64FromArray(buffer_, &temp);
+    if (!p.first) {
+      return std::make_pair(0, false);
+    }
+    buffer_ = p.second;
+    return std::make_pair(temp, true);
   } else {
     uint64 temp;
     bool success = ReadVarint64Slow(&temp);
diff --git a/src/google/protobuf/io/coded_stream.h b/src/google/protobuf/io/coded_stream.h
index c81a33ac..eb320745 100644
--- a/src/google/protobuf/io/coded_stream.h
+++ b/src/google/protobuf/io/coded_stream.h
@@ -237,6 +237,17 @@ class LIBPROTOBUF_EXPORT CodedInputStream {
   // Read an unsigned integer with Varint encoding.
   bool ReadVarint64(uint64* value);
 
+  // Reads a varint off the wire into an "int". This should be used for reading
+  // sizes off the wire (sizes of strings, submessages, bytes fields, etc).
+  //
+  // The value from the wire is interpreted as unsigned.  If its value exceeds
+  // the representable value of an integer on this platform, instead of
+  // truncating we return false. Truncating (as performed by ReadVarint32()
+  // above) is an acceptable approach for fields representing an integer, but
+  // when we are parsing a size from the wire, truncating the value would result
+  // in us misparsing the payload.
+  bool ReadVarintSizeAsInt(int* value);
+
   // Read a tag.  This calls ReadVarint32() and returns the result, or returns
   // zero (which is not a valid tag) if ReadVarint32() fails.  Also, it updates
   // the last tag value, which can be checked with LastTagWas().
@@ -594,9 +605,11 @@ class LIBPROTOBUF_EXPORT CodedInputStream {
   // if it fails and the uint32 it read otherwise.  The latter has a bool
   // indicating success or failure as part of its return type.
   int64 ReadVarint32Fallback(uint32 first_byte_or_zero);
+  int ReadVarintSizeAsIntFallback();
   std::pair<uint64, bool> ReadVarint64Fallback();
   bool ReadVarint32Slow(uint32* value);
   bool ReadVarint64Slow(uint64* value);
+  int ReadVarintSizeAsIntSlow();
   bool ReadLittleEndian32Fallback(uint32* value);
   bool ReadLittleEndian64Fallback(uint64* value);
   // Fallback/slow methods for reading tags. These do not update last_tag_,
@@ -868,6 +881,19 @@ inline bool CodedInputStream::ReadVarint64(uint64* value) {
   return p.second;
 }
 
+inline bool CodedInputStream::ReadVarintSizeAsInt(int* value) {
+  if (GOOGLE_PREDICT_TRUE(buffer_ < buffer_end_)) {
+    int v = *buffer_;
+    if (v < 0x80) {
+      *value = v;
+      Advance(1);
+      return true;
+    }
+  }
+  *value = ReadVarintSizeAsIntFallback();
+  return *value >= 0;
+}
+
 // static
 inline const uint8* CodedInputStream::ReadLittleEndian32FromArray(
     const uint8* buffer,
diff --git a/src/google/protobuf/io/printer.h b/src/google/protobuf/io/printer.h
index 2ba84559..e78e2efd 100644
--- a/src/google/protobuf/io/printer.h
+++ b/src/google/protobuf/io/printer.h
@@ -200,6 +200,26 @@ class LIBPROTOBUF_EXPORT Printer {
     Annotate(begin_varname, end_varname, descriptor->file()->name(), path);
   }
 
+  // Link a subsitution variable emitted by the last call to Print to the file
+  // with path file_name.
+  void Annotate(const char* varname, const string& file_name) {
+    Annotate(varname, varname, file_name);
+  }
+
+  // Link the output range defined by the substitution variables as emitted by
+  // the last call to Print to the file with path file_name. The range begins
+  // at begin_varname's value and ends after the last character of the value
+  // substituted for end_varname.
+  void Annotate(const char* begin_varname, const char* end_varname,
+                const string& file_name) {
+    if (annotation_collector_ == NULL) {
+      // Annotations aren't turned on for this Printer.
+      return;
+    }
+    vector<int> empty_path;
+    Annotate(begin_varname, end_varname, file_name, empty_path);
+  }
+
   // Print some text after applying variable substitutions.  If a particular
   // variable in the text is not defined, this will crash.  Variables to be
   // substituted are identified by their names surrounded by delimiter
diff --git a/src/google/protobuf/io/zero_copy_stream_impl_lite.h b/src/google/protobuf/io/zero_copy_stream_impl_lite.h
index 9d81ccfb..e4d6a024 100644
--- a/src/google/protobuf/io/zero_copy_stream_impl_lite.h
+++ b/src/google/protobuf/io/zero_copy_stream_impl_lite.h
@@ -53,7 +53,6 @@
 #include <google/protobuf/io/zero_copy_stream.h>
 #include <google/protobuf/stubs/callback.h>
 #include <google/protobuf/stubs/common.h>
-#include <google/protobuf/stubs/scoped_ptr.h>
 #include <google/protobuf/stubs/stl_util.h>