From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 From: PJ Reiniger Date: Mon, 9 May 2022 00:04:30 -0400 Subject: [PATCH 20/33] ConvertUTF: use SmallVector for UTF conversion --- llvm/include/llvm/Support/ConvertUTF.h | 7 ++++--- llvm/lib/Support/ConvertUTFWrapper.cpp | 6 +++--- llvm/unittests/Support/ConvertUTFTest.cpp | 22 +++++++++++----------- 3 files changed, 18 insertions(+), 17 deletions(-) diff --git a/llvm/include/llvm/Support/ConvertUTF.h b/llvm/include/llvm/Support/ConvertUTF.h index d5f66c4525dd5b2e2cdb4ab5e4d523c19e36b25f..6d746c88be56f42a1056a26d44b4ab0ac2bd6ef8 100644 --- a/llvm/include/llvm/Support/ConvertUTF.h +++ b/llvm/include/llvm/Support/ConvertUTF.h @@ -247,7 +247,7 @@ LLVM_ABI bool ConvertUTF8toWide(const char *Source, std::wstring &Result); * \return true on success. */ LLVM_ABI bool convertWideToUTF8(const std::wstring &Source, - std::string &Result); + SmallVectorImpl &Result); /** * Convert an Unicode code point to UTF8 sequence. @@ -302,7 +302,7 @@ LLVM_ABI bool hasUTF16ByteOrderMark(span SrcBytes); * \returns true on success */ LLVM_ABI bool convertUTF16ToUTF8String(span SrcBytes, - std::string &Out); + SmallVectorImpl &Out); /** * Converts a UTF16 string into a UTF8 std::string. @@ -311,7 +311,8 @@ LLVM_ABI bool convertUTF16ToUTF8String(span SrcBytes, * \param [out] Out Converted UTF-8 is stored here on success. * \returns true on success */ -LLVM_ABI bool convertUTF16ToUTF8String(span Src, std::string &Out); +LLVM_ABI bool convertUTF16ToUTF8String(span Src, + SmallVectorImpl &Out); /** * Converts a stream of raw bytes assumed to be UTF32 into a UTF8 std::string. diff --git a/llvm/lib/Support/ConvertUTFWrapper.cpp b/llvm/lib/Support/ConvertUTFWrapper.cpp index d15c9652b0b79e5ce7a708d30844d0ece3944d2c..a14e5a6fb155c31a5f4db6b7b39a429186825651 100644 --- a/llvm/lib/Support/ConvertUTFWrapper.cpp +++ b/llvm/lib/Support/ConvertUTFWrapper.cpp @@ -82,7 +82,7 @@ bool hasUTF16ByteOrderMark(span S) { (S[0] == '\xfe' && S[1] == '\xff'))); } -bool convertUTF16ToUTF8String(span SrcBytes, std::string &Out) { +bool convertUTF16ToUTF8String(span SrcBytes, SmallVectorImpl &Out) { assert(Out.empty()); // Error out on an uneven byte count. @@ -133,7 +133,7 @@ bool convertUTF16ToUTF8String(span SrcBytes, std::string &Out) { return true; } -bool convertUTF16ToUTF8String(span Src, std::string &Out) { +bool convertUTF16ToUTF8String(span Src, SmallVectorImpl &Out) { return convertUTF16ToUTF8String( span(reinterpret_cast(Src.data()), Src.size() * sizeof(UTF16)), @@ -269,7 +269,7 @@ 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 &Result) { if (sizeof(wchar_t) == 1) { const UTF8 *Start = reinterpret_cast(Source.data()); const UTF8 *End = diff --git a/llvm/unittests/Support/ConvertUTFTest.cpp b/llvm/unittests/Support/ConvertUTFTest.cpp index 77e70a46d3621ecfaed923d87256184addfda721..eb17a06c4369c9486c57b61f519a7429d9ef3d80 100644 --- a/llvm/unittests/Support/ConvertUTFTest.cpp +++ b/llvm/unittests/Support/ConvertUTFTest.cpp @@ -19,11 +19,11 @@ TEST(ConvertUTFTest, ConvertUTF16LittleEndianToUTF8String) { // Src is the look of disapproval. alignas(UTF16) static const char Src[] = "\xff\xfe\xa0\x0c_\x00\xa0\x0c"; span 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, ConvertUTF32LittleEndianToUTF8String) { @@ -42,11 +42,11 @@ TEST(ConvertUTFTest, ConvertUTF16BigEndianToUTF8String) { // Src is the look of disapproval. alignas(UTF16) static const char Src[] = "\xfe\xff\x0c\xa0\x00_\x0c\xa0"; span 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, ConvertUTF32BigEndianToUTF8String) { @@ -75,17 +75,17 @@ TEST(ConvertUTFTest, ConvertUTF8ToUTF16String) { } TEST(ConvertUTFTest, OddLengthInput) { - std::string Result; + SmallString<20> Result; bool Success = convertUTF16ToUTF8String(span("xxxxx", 5), Result); EXPECT_FALSE(Success); } TEST(ConvertUTFTest, Empty) { - std::string Result; + SmallString<20> Result; bool Success = convertUTF16ToUTF8String(span(), Result); EXPECT_TRUE(Success); - EXPECT_TRUE(Result.empty()); + EXPECT_TRUE(std::string{Result}.empty()); } TEST(ConvertUTFTest, HasUTF16BOM) { @@ -108,11 +108,11 @@ TEST(ConvertUTFTest, UTF16WrappersForConvertUTF16ToUTF8String) { // Src is the look of disapproval. alignas(UTF16) static const char Src[] = "\xff\xfe\xa0\x0c_\x00\xa0\x0c"; span 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) { @@ -132,11 +132,11 @@ 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 {