Add writeFileWithSystemEncoding to LibLLVMSuppor.

This patch adds to LLVMSupport the capability of writing files with
international characters encoded in the current system encoding. This
is relevant for Windows, where we can either use UTF16 or the current
code page (the legacy Windows international characters). On UNIX, the
file is always saved in UTF8.

This will be used in a patch for clang to thoroughly support response
files creation when calling other tools, addressing PR15171. On
Windows, to correctly support internationalization, we need the
ability to write response files both in UTF16 or the current code
page, depending on the tool we will call. GCC for mingw, for instance,
requires files to be encoded in the current code page. MSVC tools
requires files to be encoded in UTF16.

Patch by Rafael Auler!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217068 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Rafael Espindola
2014-09-03 20:02:00 +00:00
parent 3693c29d1c
commit 52fa0d066a
6 changed files with 167 additions and 4 deletions

View File

@ -34,6 +34,16 @@ void sleep_for(unsigned int seconds) {
#error sleep_for is not implemented on your platform.
#endif
#define ASSERT_NO_ERROR(x) \
if (std::error_code ASSERT_NO_ERROR_ec = x) { \
SmallString<128> MessageStorage; \
raw_svector_ostream Message(MessageStorage); \
Message << #x ": did not return errc::success.\n" \
<< "error number: " << ASSERT_NO_ERROR_ec.value() << "\n" \
<< "error message: " << ASSERT_NO_ERROR_ec.message() << "\n"; \
GTEST_FATAL_FAILURE_(MessageStorage.c_str()); \
} else { \
}
// From TestMain.cpp.
extern const char *TestMainArgv0;
@ -220,4 +230,44 @@ TEST(ProgramTest, TestExecuteNegative) {
}
#ifdef LLVM_ON_WIN32
const char utf16le_text[] =
"\x6c\x00\x69\x00\x6e\x00\x67\x00\xfc\x00\x69\x00\xe7\x00\x61\x00";
const char utf16be_text[] =
"\x00\x6c\x00\x69\x00\x6e\x00\x67\x00\xfc\x00\x69\x00\xe7\x00\x61";
#endif
const char utf8_text[] = "\x6c\x69\x6e\x67\xc3\xbc\x69\xc3\xa7\x61";
TEST(ProgramTest, TestWriteWithSystemEncoding) {
SmallString<128> TestDirectory;
ASSERT_NO_ERROR(fs::createUniqueDirectory("program-test", TestDirectory));
errs() << "Test Directory: " << TestDirectory << '\n';
errs().flush();
SmallString<128> file_pathname(TestDirectory);
path::append(file_pathname, "international-file.txt");
// Only on Windows we should encode in UTF16. For other systems, use UTF8
ASSERT_NO_ERROR(sys::writeFileWithEncoding(file_pathname.c_str(), utf8_text,
sys::WEM_UTF16));
int fd = 0;
ASSERT_NO_ERROR(fs::openFileForRead(file_pathname.c_str(), fd));
#if defined(LLVM_ON_WIN32)
char buf[18];
ASSERT_EQ(::read(fd, buf, 18), 18);
if (strncmp(buf, "\xfe\xff", 2) == 0) { // UTF16-BE
ASSERT_EQ(strncmp(&buf[2], utf16be_text, 16), 0);
} else if (strncmp(buf, "\xff\xfe", 2) == 0) { // UTF16-LE
ASSERT_EQ(strncmp(&buf[2], utf16le_text, 16), 0);
} else {
FAIL() << "Invalid BOM in UTF-16 file";
}
#else
char buf[10];
ASSERT_EQ(::read(fd, buf, 10), 10);
ASSERT_EQ(strncmp(buf, utf8_text, 10), 0);
#endif
::close(fd);
ASSERT_NO_ERROR(fs::remove(file_pathname.str()));
ASSERT_NO_ERROR(fs::remove(TestDirectory.str()));
}
} // end anonymous namespace