From 5b4c8d8774c18c3bd0f99059b6c0fa1c62d4295f Mon Sep 17 00:00:00 2001
From: bgertzfield <bgertzfield@gmail.com>
Date: Thu, 28 Apr 2011 13:26:24 +0000
Subject: [PATCH] Fix UnicodeText const_iterator to make it work for MacOS.

---
 cpp/CMakeLists.txt              |  1 +
 cpp/src/utf/unicodetext.cc      |  8 +++---
 cpp/src/utf/unicodetext_test.cc | 45 +++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 4 deletions(-)
 create mode 100644 cpp/src/utf/unicodetext_test.cc

diff --git a/cpp/CMakeLists.txt b/cpp/CMakeLists.txt
index 64390595f..95110bbe8 100644
--- a/cpp/CMakeLists.txt
+++ b/cpp/CMakeLists.txt
@@ -234,6 +234,7 @@ set (TEST_SOURCES
   "src/run_tests.cc"
   "src/stringutil_test.cc"
   "src/test_metadata.cc"  # Generated by build tools.
+  "src/utf/unicodetext_test.cc"
 )
 
 add_executable (libphonenumber_test ${TEST_SOURCES})
diff --git a/cpp/src/utf/unicodetext.cc b/cpp/src/utf/unicodetext.cc
index 82c1b42fa..1039f1f60 100644
--- a/cpp/src/utf/unicodetext.cc
+++ b/cpp/src/utf/unicodetext.cc
@@ -442,22 +442,22 @@ char32 UnicodeText::const_iterator::operator*() const {
   // for speed, we do the calculation ourselves.)
 
   // Convert from UTF-8
-  int byte1 = it_[0];
+  uint8 byte1 = static_cast<uint8>(it_[0]);
   if (byte1 < 0x80)
     return byte1;
 
-  int byte2 = it_[1];
+  uint8 byte2 = static_cast<uint8>(it_[1]);
   if (byte1 < 0xE0)
     return ((byte1 & 0x1F) << 6)
           | (byte2 & 0x3F);
 
-  int byte3 = it_[2];
+  uint8 byte3 = static_cast<uint8>(it_[2]);
   if (byte1 < 0xF0)
     return ((byte1 & 0x0F) << 12)
          | ((byte2 & 0x3F) << 6)
          |  (byte3 & 0x3F);
 
-  int byte4 = it_[3];
+  uint8 byte4 = static_cast<uint8>(it_[3]);
   return ((byte1 & 0x07) << 18)
        | ((byte2 & 0x3F) << 12)
        | ((byte3 & 0x3F) << 6)
diff --git a/cpp/src/utf/unicodetext_test.cc b/cpp/src/utf/unicodetext_test.cc
new file mode 100644
index 000000000..51ba094a3
--- /dev/null
+++ b/cpp/src/utf/unicodetext_test.cc
@@ -0,0 +1,45 @@
+// Copyright 2011 Facebook, Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License"); you may
+// not use this file except in compliance with the License. You may obtain
+// a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+// WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+// License for the specific language governing permissions and limitations
+// under the License.
+//
+// Author: Ben Gertzfield
+
+#include <gtest/gtest.h>
+
+#include "unicodetext.h"
+
+namespace i18n {
+namespace unicodetext {
+
+TEST(UnicodeTextTest, Iterator) {
+  struct value {
+    const char* utf8;
+    unsigned int code_point;
+  } values[] = {
+    { "\x31", 0x31 }, // U+0031 DIGIT ONE
+    { "\xC2\xBD", 0x00BD }, // U+00BD VULGAR FRACTION ONE HALF
+    { "\xEF\xBC\x91", 0xFF11 }, // U+FF11 FULLWIDTH DIGIT ONE
+    { "\xF0\x9F\x80\x80", 0x1F000 }, // U+1F000 MAHJONG TILE EAST WIND
+  };
+
+  for (size_t i = 0; i < sizeof values / sizeof values[0]; i++) {
+    string number(values[i].utf8);
+    UnicodeText number_as_unicode;
+    number_as_unicode.PointToUTF8(number.data(), number.size());
+    UnicodeText::const_iterator it = number_as_unicode.begin();
+    EXPECT_EQ(values[i].code_point, *it);
+  }
+}
+
+} // namespace unicodetext
+} // namespace i18n