summaryrefslogtreecommitdiffstats
path: root/llvm/lib
diff options
context:
space:
mode:
authorReid Kleckner <rnk@google.com>2018-09-05 00:08:56 +0000
committerReid Kleckner <rnk@google.com>2018-09-05 00:08:56 +0000
commit2b8c69204b1d37d91cc775d51af50df7f478cecd (patch)
tree67a7bb12b6c40ec503027e5a4f735a53be435b7f /llvm/lib
parent2768b52117cb6a1eb0d6a0c4bb01cf52d436adbb (diff)
downloadbcm5719-llvm-2b8c69204b1d37d91cc775d51af50df7f478cecd.tar.gz
bcm5719-llvm-2b8c69204b1d37d91cc775d51af50df7f478cecd.zip
[Windows] Convert from UTF-8 to UTF-16 when writing to a Windows console
Summary: Calling WriteConsoleW is the most reliable way to print Unicode characters to a Windows console. If binary data gets printed to the console, attempting to re-encode it shouldn't be a problem, since garbage in can produce garbage out. This breaks printing strings in the local codepage, which WriteConsoleA knows how to handle. For example, this can happen when user source code is encoded with the local codepage, and an LLVM tool quotes it while emitting a caret diagnostic. This is unfortunate, but well-behaved tools should validate that their input is UTF-8 and escape non-UTF-8 characters before sending them to raw_fd_ostream. Clang already does this, but not all LLVM tools do this. One drawback to the current implementation is printing a string a byte at a time doesn't work. Consider this LLVM code: for (char C : MyStr) outs() << C; Because outs() is now unbuffered, we wil try to convert each byte to UTF-16, which will fail. However, this already didn't work, so I think we may as well update callers that do that as we find them to print complete portions of strings. You can see a real example of this in my patch to SourceMgr.cpp Fixes PR38669 and PR36267. Reviewers: zturner, efriedma Subscribers: llvm-commits, hiraditya Differential Revision: https://reviews.llvm.org/D51558 llvm-svn: 341433
Diffstat (limited to 'llvm/lib')
-rw-r--r--llvm/lib/Support/Locale.cpp13
-rw-r--r--llvm/lib/Support/SourceMgr.cpp14
-rw-r--r--llvm/lib/Support/raw_ostream.cpp84
3 files changed, 86 insertions, 25 deletions
diff --git a/llvm/lib/Support/Locale.cpp b/llvm/lib/Support/Locale.cpp
index c4cfc5e8de0..1b3300b90f2 100644
--- a/llvm/lib/Support/Locale.cpp
+++ b/llvm/lib/Support/Locale.cpp
@@ -7,24 +7,11 @@ namespace sys {
namespace locale {
int columnWidth(StringRef Text) {
-#ifdef _WIN32
- return Text.size();
-#else
return llvm::sys::unicode::columnWidthUTF8(Text);
-#endif
}
bool isPrint(int UCS) {
-#ifdef _WIN32
- // Restrict characters that we'll try to print to the lower part of ASCII
- // except for the control characters (0x20 - 0x7E). In general one can not
- // reliably output code points U+0080 and higher using narrow character C/C++
- // output functions in Windows, because the meaning of the upper 128 codes is
- // determined by the active code page in the console.
- return ' ' <= UCS && UCS <= '~';
-#else
return llvm::sys::unicode::isPrintable(UCS);
-#endif
}
} // namespace locale
diff --git a/llvm/lib/Support/SourceMgr.cpp b/llvm/lib/Support/SourceMgr.cpp
index d8fde7fa899..e17e5ab0141 100644
--- a/llvm/lib/Support/SourceMgr.cpp
+++ b/llvm/lib/Support/SourceMgr.cpp
@@ -345,12 +345,18 @@ static void buildFixItLine(std::string &CaretLine, std::string &FixItLine,
static void printSourceLine(raw_ostream &S, StringRef LineContents) {
// Print out the source line one character at a time, so we can expand tabs.
for (unsigned i = 0, e = LineContents.size(), OutCol = 0; i != e; ++i) {
- if (LineContents[i] != '\t') {
- S << LineContents[i];
- ++OutCol;
- continue;
+ size_t NextTab = LineContents.find('\t', i);
+ // If there were no tabs left, print the rest, we are done.
+ if (NextTab == StringRef::npos) {
+ S << LineContents.drop_front(i);
+ break;
}
+ // Otherwise, print from i to NextTab.
+ S << LineContents.slice(i, NextTab);
+ OutCol += NextTab - i;
+ i = NextTab;
+
// If we have a tab, emit at least one space, then round up to 8 columns.
do {
S << ' ';
diff --git a/llvm/lib/Support/raw_ostream.cpp b/llvm/lib/Support/raw_ostream.cpp
index 1dae469958f..81df38f341c 100644
--- a/llvm/lib/Support/raw_ostream.cpp
+++ b/llvm/lib/Support/raw_ostream.cpp
@@ -60,6 +60,7 @@
#endif
#ifdef _WIN32
+#include "llvm/Support/ConvertUTF.h"
#include "Windows/WindowsSupport.h"
#endif
@@ -567,6 +568,12 @@ raw_fd_ostream::raw_fd_ostream(int fd, bool shouldClose, bool unbuffered)
if (FD <= STDERR_FILENO)
ShouldClose = false;
+#ifdef _WIN32
+ // Check if this is a console device. This is not equivalent to isatty.
+ IsWindowsConsole =
+ ::GetFileType((HANDLE)::_get_osfhandle(fd)) == FILE_TYPE_CHAR;
+#endif
+
// Get the starting position.
off_t loc = ::lseek(FD, 0, SEEK_CUR);
#ifdef _WIN32
@@ -609,10 +616,68 @@ raw_fd_ostream::~raw_fd_ostream() {
/*GenCrashDiag=*/false);
}
+#if defined(_WIN32)
+// The most reliable way to print unicode in a Windows console is with
+// WriteConsoleW. To use that, first transcode from UTF-8 to UTF-16. This
+// assumes that LLVM programs always print valid UTF-8 to the console. The data
+// might not be UTF-8 for two major reasons:
+// 1. The program is printing binary (-filetype=obj -o -), in which case it
+// would have been gibberish anyway.
+// 2. The program is printing text in a semi-ascii compatible codepage like
+// shift-jis or cp1252.
+//
+// Most LLVM programs don't produce non-ascii text unless they are quoting
+// user source input. A well-behaved LLVM program should either validate that
+// the input is UTF-8 or transcode from the local codepage to UTF-8 before
+// quoting it. If they don't, this may mess up the encoding, but this is still
+// probably the best compromise we can make.
+static bool write_console_impl(int FD, StringRef Data) {
+ SmallVector<wchar_t, 256> WideText;
+
+ // Fall back to ::write if it wasn't valid UTF-8.
+ if (auto EC = sys::windows::UTF8ToUTF16(Data, WideText))
+ return false;
+
+ // On Windows 7 and earlier, WriteConsoleW has a low maximum amount of data
+ // that can be written to the console at a time.
+ size_t MaxWriteSize = WideText.size();
+ if (!RunningWindows8OrGreater())
+ MaxWriteSize = 32767;
+
+ size_t WCharsWritten = 0;
+ do {
+ size_t WCharsToWrite =
+ std::min(MaxWriteSize, WideText.size() - WCharsWritten);
+ DWORD ActuallyWritten;
+ bool Success =
+ ::WriteConsoleW((HANDLE)::_get_osfhandle(FD), &WideText[WCharsWritten],
+ WCharsToWrite, &ActuallyWritten,
+ /*Reserved=*/nullptr);
+
+ // The most likely reason for WriteConsoleW to fail is that FD no longer
+ // points to a console. Fall back to ::write. If this isn't the first loop
+ // iteration, something is truly wrong.
+ if (!Success)
+ return false;
+
+ WCharsWritten += ActuallyWritten;
+ } while (WCharsWritten != WideText.size());
+ return true;
+}
+#endif
+
void raw_fd_ostream::write_impl(const char *Ptr, size_t Size) {
assert(FD >= 0 && "File already closed.");
pos += Size;
+#if defined(_WIN32)
+ // If this is a Windows console device, try re-encoding from UTF-8 to UTF-16
+ // and using WriteConsoleW. If that fails, fall back to plain write().
+ if (IsWindowsConsole)
+ if (write_console_impl(FD, StringRef(Ptr, Size)))
+ return;
+#endif
+
// The maximum write size is limited to INT32_MAX. A write
// greater than SSIZE_MAX is implementation-defined in POSIX,
// and Windows _write requires 32 bit input.
@@ -622,12 +687,6 @@ void raw_fd_ostream::write_impl(const char *Ptr, size_t Size) {
// It is observed that Linux returns EINVAL for a very large write (>2G).
// Make it a reasonably small value.
MaxWriteSize = 1024 * 1024 * 1024;
-#elif defined(_WIN32)
- // Writing a large size of output to Windows console returns ENOMEM. It seems
- // that, prior to Windows 8, WriteFile() is redirecting to WriteConsole(), and
- // the latter has a size limit (66000 bytes or less, depending on heap usage).
- if (::_isatty(FD) && !RunningWindows8OrGreater())
- MaxWriteSize = 32767;
#endif
do {
@@ -696,8 +755,17 @@ void raw_fd_ostream::pwrite_impl(const char *Ptr, size_t Size,
}
size_t raw_fd_ostream::preferred_buffer_size() const {
-#if !defined(_MSC_VER) && !defined(__MINGW32__) && !defined(__minix)
- // Windows and Minix have no st_blksize.
+#if defined(_WIN32)
+ // Disable buffering for console devices. Console output is re-encoded from
+ // UTF-8 to UTF-16 on Windows, and buffering it would require us to split the
+ // buffer on a valid UTF-8 codepoint boundary. Terminal buffering is disabled
+ // below on most other OSs, so do the same thing on Windows and avoid that
+ // complexity.
+ if (IsWindowsConsole)
+ return 0;
+ return raw_ostream::preferred_buffer_size();
+#elif !defined(__minix)
+ // Minix has no st_blksize.
assert(FD >= 0 && "File not yet open!");
struct stat statbuf;
if (fstat(FD, &statbuf) != 0)
OpenPOWER on IntegriCloud