[Support] Add a Unicode conversion wrapper from UTF16 to UTF8

This is to support parsing UTF16 response files in LLVM/lib/Option for
lld and clang.

Reviewers: hans

Differential Revision: http://llvm-reviews.chandlerc.com/D1138

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186426 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Support/ConvertUTF.h

@@ -87,8 +87,8 @@
 
 ------------------------------------------------------------------------ */
 
-#ifndef CLANG_BASIC_CONVERTUTF_H
+#ifndef LLVM_SUPPORT_CONVERTUTF_H
-#define CLANG_BASIC_CONVERTUTF_H
+#define LLVM_SUPPORT_CONVERTUTF_H
 
 /* ---------------------------------------------------------------------
     The following 4 definitions are compiler-specific.
@@ -112,6 +112,9 @@ typedef unsigned char   Boolean; /* 0 or 1 */
 
 #define UNI_MAX_UTF8_BYTES_PER_CODE_POINT 4
 
+#define UNI_UTF16_BYTE_ORDER_MARK_NATIVE  0xFEFF
+#define UNI_UTF16_BYTE_ORDER_MARK_SWAPPED 0xFFFE
+
 typedef enum {
   conversionOK,           /* conversion successful */
   sourceExhausted,        /* partial character in source, but hit end */
@@ -165,6 +168,7 @@ unsigned getNumBytesForUTF8(UTF8 firstByte);
 /*************************************************************************/
 /* Below are LLVM-specific wrappers of the functions above. */
 
+#include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/StringRef.h"
 
 namespace llvm {
@@ -219,6 +223,22 @@ static inline ConversionResult convertUTF8Sequence(const UTF8 **source,
     return sourceExhausted;
   return ConvertUTF8toUTF32(source, *source + size, &target, target + 1, flags);
 }
+
+/**
+ * Returns true if a blob of text starts with a UTF-16 big or little endian byte
+ * order mark.
+ */
+bool hasUTF16ByteOrderMark(ArrayRef<char> SrcBytes);
+
+/**
+ * Converts a stream of raw bytes assumed to be UTF16 into a UTF8 std::string.
+ *
+ * \param [in] SrcBytes A buffer of what is assumed to be UTF-16 encoded text.
+ * \param [out] Out Converted UTF-8 is stored here on success.
+ * \returns true on success
+ */
+bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out);
+
 } /* end namespace llvm */
 
 #endif

lib/Support/ConvertUTFWrapper.cpp

@@ -8,6 +8,9 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Support/ConvertUTF.h"
+#include "llvm/Support/SwapByteOrder.h"
+#include <string>
+#include <vector>
 
 namespace llvm {
 
@@ -72,5 +75,57 @@ bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr) {
   return true;
 }
 
+bool hasUTF16ByteOrderMark(ArrayRef<char> S) {
+  return (S.size() >= 2 &&
+          ((S[0] == '\xff' && S[1] == '\xfe') ||
+           (S[0] == '\xfe' && S[1] == '\xff')));
+}
+
+bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out) {
+  assert(Out.empty());
+
+  // Error out on an uneven byte count.
+  if (SrcBytes.size() % 2)
+    return false;
+
+  // Avoid OOB by returning early on empty input.
+  if (SrcBytes.empty())
+    return true;
+
+  const UTF16 *Src = reinterpret_cast<const UTF16 *>(SrcBytes.begin());
+  const UTF16 *SrcEnd = reinterpret_cast<const UTF16 *>(SrcBytes.end());
+
+  // Byteswap if necessary.
+  std::vector<UTF16> ByteSwapped;
+  if (Src[0] == UNI_UTF16_BYTE_ORDER_MARK_SWAPPED) {
+    ByteSwapped.insert(ByteSwapped.end(), Src, SrcEnd);
+    for (unsigned I = 0, E = ByteSwapped.size(); I != E; ++I)
+      ByteSwapped[I] = llvm::sys::SwapByteOrder_16(ByteSwapped[I]);
+    Src = &ByteSwapped[0];
+    SrcEnd = &ByteSwapped[ByteSwapped.size() - 1] + 1;
+  }
+
+  // Skip the BOM for conversion.
+  if (Src[0] == UNI_UTF16_BYTE_ORDER_MARK_NATIVE)
+    Src++;
+
+  // Just allocate enough space up front.  We'll shrink it later.
+  Out.resize(SrcBytes.size() * UNI_MAX_UTF8_BYTES_PER_CODE_POINT);
+  UTF8 *Dst = reinterpret_cast<UTF8 *>(&Out[0]);
+  UTF8 *DstEnd = Dst + Out.size();
+
+  ConversionResult CR =
+      ConvertUTF16toUTF8(&Src, SrcEnd, &Dst, DstEnd, strictConversion);
+  assert(CR != targetExhausted);
+
+  if (CR != conversionOK) {
+    Out.clear();
+    return false;
+  }
+
+  Out.resize(reinterpret_cast<char *>(Dst) - &Out[0]);
+  return true;
+}
+
 } // end namespace llvm
 

unittests/Support/CMakeLists.txt

@@ -12,6 +12,7 @@ add_llvm_unittest(SupportTests
   CommandLineTest.cpp
   CompressionTest.cpp
   ConstantRangeTest.cpp
+  ConvertUTFTest.cpp
   DataExtractorTest.cpp
   EndianTest.cpp
   ErrorOrTest.cpp

unittests/Support/ConvertUTFTest.cpp

@@ -0,0 +1,65 @@
+//===- llvm/unittest/Support/ConvertUTFTest.cpp - ConvertUTF tests --------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/ConvertUTF.h"
+#include "gtest/gtest.h"
+#include <string>
+
+using namespace llvm;
+
+TEST(ConvertUTFTest, ConvertUTF16LittleEndianToUTF8String) {
+  // Src is the look of disapproval.
+  static const char Src[] = "\xff\xfe\xa0\x0c_\x00\xa0\x0c";
+  ArrayRef<char> Ref(Src, sizeof(Src) - 1);
+  std::string Result;
+  bool Success = convertUTF16ToUTF8String(Ref, Result);
+  EXPECT_TRUE(Success);
+  std::string Expected("\xe0\xb2\xa0_\xe0\xb2\xa0");
+  EXPECT_EQ(Expected, Result);
+}
+
+TEST(ConvertUTFTest, ConvertUTF16BigEndianToUTF8String) {
+  // Src is the look of disapproval.
+  static const char Src[] = "\xfe\xff\x0c\xa0\x00_\x0c\xa0";
+  ArrayRef<char> Ref(Src, sizeof(Src) - 1);
+  std::string Result;
+  bool Success = convertUTF16ToUTF8String(Ref, Result);
+  EXPECT_TRUE(Success);
+  std::string Expected("\xe0\xb2\xa0_\xe0\xb2\xa0");
+  EXPECT_EQ(Expected, Result);
+}
+
+TEST(ConvertUTFTest, OddLengthInput) {
+  std::string Result;
+  bool Success = convertUTF16ToUTF8String(ArrayRef<char>("xxxxx", 5), Result);
+  EXPECT_FALSE(Success);
+}
+
+TEST(ConvertUTFTest, Empty) {
+  std::string Result;
+  bool Success = convertUTF16ToUTF8String(ArrayRef<char>(), Result);
+  EXPECT_TRUE(Success);
+  EXPECT_TRUE(Result.empty());
+}
+
+TEST(ConvertUTFTest, HasUTF16BOM) {
+  bool HasBOM = hasUTF16ByteOrderMark(ArrayRef<char>("\xff\xfe", 2));
+  EXPECT_TRUE(HasBOM);
+  HasBOM = hasUTF16ByteOrderMark(ArrayRef<char>("\xfe\xff", 2));
+  EXPECT_TRUE(HasBOM);
+  HasBOM = hasUTF16ByteOrderMark(ArrayRef<char>("\xfe\xff ", 3));
+  EXPECT_TRUE(HasBOM); // Don't care about odd lengths.
+  HasBOM = hasUTF16ByteOrderMark(ArrayRef<char>("\xfe\xff\x00asdf", 6));
+  EXPECT_TRUE(HasBOM);
+
+  HasBOM = hasUTF16ByteOrderMark(ArrayRef<char>());
+  EXPECT_FALSE(HasBOM);
+  HasBOM = hasUTF16ByteOrderMark(ArrayRef<char>("\xfe", 1));
+  EXPECT_FALSE(HasBOM);
+}