Files
allwpilib/upstream_utils/llvm_patches/0022-Use-SmallVector-for-UTF-conversion.patch
PJ Reiniger 32cd2ddf8e [upstream_utils] Remove patch that results in building with NDEBUG causing ODR issues (#8539)
Semiwrap / meson / robotpy define `NDEBUG` when building their software
in all modes, while `allwplib` only does it when building debug. This
causes the size of `DenseMap` to differ between the shared libraries
built here, and the extension modules built in `mostrobotpy`, causing
segfaults when you try to execute code that uses `DenseMap`. This is not
a problem with the robotpy code in `allwpilib`, because bazel uses the
exact same compiler flags when building the shared libraries and
pybind11 extensions.
2026-01-03 13:32:16 -08:00

155 lines
6.3 KiB
Diff

From 0000000000000000000000000000000000000000 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 22/35] 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 72321022beb373945f7935ed72944fd68eb7d02f..5c8b966ce296699a0315d72cdfdcdb5af3d1d0b0 100644
--- a/llvm/include/llvm/Support/ConvertUTF.h
+++ b/llvm/include/llvm/Support/ConvertUTF.h
@@ -233,7 +233,7 @@ 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);
/**
@@ -288,7 +288,7 @@ 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.
@@ -297,7 +297,7 @@ 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 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 34054140489e4d536ace4650207c783d669d850e..0b62315e3461ff60a8313e73b4142b1f83e36ca7 100644
--- a/llvm/lib/Support/ConvertUTFWrapper.cpp
+++ b/llvm/lib/Support/ConvertUTFWrapper.cpp
@@ -82,7 +82,7 @@ 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.
@@ -133,7 +133,7 @@ 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()),
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<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 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<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, 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<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, ConvertUTF32BigEndianToUTF8String) {
@@ -75,17 +75,17 @@ 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) {
@@ -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<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) {
@@ -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 {