From f58b9bad86f61c35cc530ff113ccbb13415261c8 Mon Sep 17 00:00:00 2001
From: PJ Reiniger <pj.reiniger@gmail.com>
Date: Mon, 9 May 2022 00:04:30 -0400
Subject: [PATCH 24/28] Use SmallVector for UTF conversion

---
 llvm/include/llvm/Support/ConvertUTF.h    |  6 +++---
 llvm/lib/Support/ConvertUTFWrapper.cpp    |  6 +++---
 llvm/unittests/Support/ConvertUTFTest.cpp | 22 +++++++++++-----------
 3 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/llvm/include/llvm/Support/ConvertUTF.h b/llvm/include/llvm/Support/ConvertUTF.h
index b085c8a17..c82947006 100644
--- a/llvm/include/llvm/Support/ConvertUTF.h
+++ b/llvm/include/llvm/Support/ConvertUTF.h
@@ -213,7 +213,7 @@ bool ConvertUTF8toWide(const char *Source, std::wstring &Result);
 * Converts a std::wstring to a UTF-8 encoded std::string.
 * \return true on success.
 */
-bool convertWideToUTF8(const std::wstring &Source, std::string &Result);
+bool convertWideToUTF8(const std::wstring &Source, SmallVectorImpl<char> &Result);
 
 
 /**
@@ -268,7 +268,7 @@ bool hasUTF16ByteOrderMark(span<const char> SrcBytes);
  * \param [out] Out Converted UTF-8 is stored here on success.
  * \returns true on success
  */
-bool convertUTF16ToUTF8String(span<const char> SrcBytes, std::string &Out);
+bool convertUTF16ToUTF8String(span<const char> SrcBytes, SmallVectorImpl<char> &Out);
 
 /**
 * Converts a UTF16 string into a UTF8 std::string.
@@ -277,7 +277,7 @@ bool convertUTF16ToUTF8String(span<const char> SrcBytes, std::string &Out);
 * \param [out] Out Converted UTF-8 is stored here on success.
 * \returns true on success
 */
-bool convertUTF16ToUTF8String(span<const UTF16> Src, std::string &Out);
+bool convertUTF16ToUTF8String(span<const UTF16> Src, SmallVectorImpl<char> &Out);
 
 /**
  * Converts a UTF-8 string into a UTF-16 string with native endianness.
diff --git a/llvm/lib/Support/ConvertUTFWrapper.cpp b/llvm/lib/Support/ConvertUTFWrapper.cpp
index cff30f16c..d3689d92a 100644
--- a/llvm/lib/Support/ConvertUTFWrapper.cpp
+++ b/llvm/lib/Support/ConvertUTFWrapper.cpp
@@ -84,7 +84,7 @@ bool hasUTF16ByteOrderMark(span<const char> S) {
            (S[0] == '\xfe' && S[1] == '\xff')));
 }
 
-bool convertUTF16ToUTF8String(span<const char> SrcBytes, std::string &Out) {
+bool convertUTF16ToUTF8String(span<const char> SrcBytes, SmallVectorImpl<char> &Out) {
   assert(Out.empty());
 
   // Error out on an uneven byte count.
@@ -135,7 +135,7 @@ bool convertUTF16ToUTF8String(span<const char> SrcBytes, std::string &Out) {
   return true;
 }
 
-bool convertUTF16ToUTF8String(span<const UTF16> Src, std::string &Out)
+bool convertUTF16ToUTF8String(span<const UTF16> Src, SmallVectorImpl<char> &Out)
 {
   return convertUTF16ToUTF8String(
       span<const char>(reinterpret_cast<const char *>(Src.data()),
@@ -213,7 +213,7 @@ bool ConvertUTF8toWide(const char *Source, std::wstring &Result) {
   return ConvertUTF8toWide(std::string_view(Source), Result);
 }
 
-bool convertWideToUTF8(const std::wstring &Source, std::string &Result) {
+bool convertWideToUTF8(const std::wstring &Source, SmallVectorImpl<char> &Result) {
   if (sizeof(wchar_t) == 1) {
     const UTF8 *Start = reinterpret_cast<const UTF8 *>(Source.data());
     const UTF8 *End =
diff --git a/llvm/unittests/Support/ConvertUTFTest.cpp b/llvm/unittests/Support/ConvertUTFTest.cpp
index 2fee8ad5c..7d7650b1c 100644
--- a/llvm/unittests/Support/ConvertUTFTest.cpp
+++ b/llvm/unittests/Support/ConvertUTFTest.cpp
@@ -19,22 +19,22 @@ TEST(ConvertUTFTest, ConvertUTF16LittleEndianToUTF8String) {
   // Src is the look of disapproval.
   alignas(UTF16) static const char Src[] = "\xff\xfe\xa0\x0c_\x00\xa0\x0c";
   span<const char> Ref(Src, sizeof(Src) - 1);
-  std::string Result;
+  SmallString<20> Result;
   bool Success = convertUTF16ToUTF8String(Ref, Result);
   EXPECT_TRUE(Success);
   std::string Expected("\xe0\xb2\xa0_\xe0\xb2\xa0");
-  EXPECT_EQ(Expected, Result);
+  EXPECT_EQ(Expected, std::string{Result});
 }
 
 TEST(ConvertUTFTest, ConvertUTF16BigEndianToUTF8String) {
   // Src is the look of disapproval.
   alignas(UTF16) static const char Src[] = "\xfe\xff\x0c\xa0\x00_\x0c\xa0";
   span<const char> Ref(Src, sizeof(Src) - 1);
-  std::string Result;
+  SmallString<20> Result;
   bool Success = convertUTF16ToUTF8String(Ref, Result);
   EXPECT_TRUE(Success);
   std::string Expected("\xe0\xb2\xa0_\xe0\xb2\xa0");
-  EXPECT_EQ(Expected, Result);
+  EXPECT_EQ(Expected, std::string{Result});
 }
 
 TEST(ConvertUTFTest, ConvertUTF8ToUTF16String) {
@@ -51,16 +51,16 @@ TEST(ConvertUTFTest, ConvertUTF8ToUTF16String) {
 }
 
 TEST(ConvertUTFTest, OddLengthInput) {
-  std::string Result;
+  SmallString<20> Result;
   bool Success = convertUTF16ToUTF8String(span<const char>("xxxxx", 5), Result);
   EXPECT_FALSE(Success);
 }
 
 TEST(ConvertUTFTest, Empty) {
-  std::string Result;
+  SmallString<20> Result;
   bool Success = convertUTF16ToUTF8String(span<const char>(), Result);
   EXPECT_TRUE(Success);
-  EXPECT_TRUE(Result.empty());
+  EXPECT_TRUE(std::string{Result}.empty());
 }
 
 TEST(ConvertUTFTest, HasUTF16BOM) {
@@ -83,11 +83,11 @@ TEST(ConvertUTFTest, UTF16WrappersForConvertUTF16ToUTF8String) {
   // Src is the look of disapproval.
   alignas(UTF16) static const char Src[] = "\xff\xfe\xa0\x0c_\x00\xa0\x0c";
   span<const UTF16> SrcRef((const UTF16 *)Src, 4);
-  std::string Result;
+  SmallString<20> Result;
   bool Success = convertUTF16ToUTF8String(SrcRef, Result);
   EXPECT_TRUE(Success);
   std::string Expected("\xe0\xb2\xa0_\xe0\xb2\xa0");
-  EXPECT_EQ(Expected, Result);
+  EXPECT_EQ(Expected, std::string{Result});
 }
 
 TEST(ConvertUTFTest, ConvertUTF8toWide) {
@@ -107,11 +107,11 @@ TEST(ConvertUTFTest, ConvertUTF8toWide) {
 TEST(ConvertUTFTest, convertWideToUTF8) {
   // Src is the look of disapproval.
   static const wchar_t Src[] = L"\x0ca0_\x0ca0";
-  std::string Result;
+  SmallString<20> Result;
   bool Success = convertWideToUTF8(Src, Result);
   EXPECT_TRUE(Success);
   std::string Expected("\xe0\xb2\xa0_\xe0\xb2\xa0");
-  EXPECT_EQ(Expected, Result);
+  EXPECT_EQ(Expected, std::string{Result});
 }
 
 struct ConvertUTFResultContainer {