From b851ded09a300033849b60ab47a468087ce557a1 Mon Sep 17 00:00:00 2001 From: Yasuhiro Matsumoto Date: Wed, 24 Aug 2016 10:34:16 +0900 Subject: [PATCH] os: use GetConsoleCP() instead of GetACP() It is possible (and common) for Windows systems to use a different codepage for console applications from that used on normal windowed application (called ANSI codepage); for instance, most of the western Europe uses CP850 for console (for backward compatibility with MS-DOS), while windowed applications use a different codepage depending on the country (eg: CP1252 aka Latin-1). The usage being changed with this commit is specifically related to decoding input coming from the console, so the previous usage of the ANSI codepage was wrong. Also fixes an issue that previous did convert bytes as NFD. Go is designed to handle single Unicode code point. This fix change behaivor to NFC. Fixes #16857. Change-Id: I4f41ae83ece47321b6e9a79a2087ecbb8ac066dd Reviewed-on: https://go-review.googlesource.com/27575 Reviewed-by: Hiroshi Ioka Reviewed-by: Alex Brainman --- src/internal/syscall/windows/syscall_windows.go | 1 + src/internal/syscall/windows/zsyscall_windows.go | 7 +++++++ src/os/file_windows.go | 8 +++++--- 3 files changed, 13 insertions(+), 3 deletions(-) diff --git a/src/internal/syscall/windows/syscall_windows.go b/src/internal/syscall/windows/syscall_windows.go index 47ca602ae1..015862d713 100644 --- a/src/internal/syscall/windows/syscall_windows.go +++ b/src/internal/syscall/windows/syscall_windows.go @@ -138,4 +138,5 @@ func Rename(oldpath, newpath string) error { } //sys GetACP() (acp uint32) = kernel32.GetACP +//sys GetConsoleCP() (ccp uint32) = kernel32.GetConsoleCP //sys MultiByteToWideChar(codePage uint32, dwFlags uint32, str *byte, nstr int32, wchar *uint16, nwchar int32) (nwrite int32, err error) = kernel32.MultiByteToWideChar diff --git a/src/internal/syscall/windows/zsyscall_windows.go b/src/internal/syscall/windows/zsyscall_windows.go index 21fe12fe1b..0b814e9b4a 100644 --- a/src/internal/syscall/windows/zsyscall_windows.go +++ b/src/internal/syscall/windows/zsyscall_windows.go @@ -43,6 +43,7 @@ var ( procGetComputerNameExW = modkernel32.NewProc("GetComputerNameExW") procMoveFileExW = modkernel32.NewProc("MoveFileExW") procGetACP = modkernel32.NewProc("GetACP") + procGetConsoleCP = modkernel32.NewProc("GetConsoleCP") procMultiByteToWideChar = modkernel32.NewProc("MultiByteToWideChar") ) @@ -84,6 +85,12 @@ func GetACP() (acp uint32) { return } +func GetConsoleCP() (ccp uint32) { + r0, _, _ := syscall.Syscall(procGetConsoleCP.Addr(), 0, 0, 0, 0) + ccp = uint32(r0) + return +} + func MultiByteToWideChar(codePage uint32, dwFlags uint32, str *byte, nstr int32, wchar *uint16, nwchar int32) (nwrite int32, err error) { r0, _, e1 := syscall.Syscall6(procMultiByteToWideChar.Addr(), 6, uintptr(codePage), uintptr(dwFlags), uintptr(unsafe.Pointer(str)), uintptr(nstr), uintptr(unsafe.Pointer(wchar)), uintptr(nwchar)) nwrite = int32(r0) diff --git a/src/os/file_windows.go b/src/os/file_windows.go index e1f9f1c33d..efbf0e85fb 100644 --- a/src/os/file_windows.go +++ b/src/os/file_windows.go @@ -217,14 +217,16 @@ func (f *File) readConsole(b []byte) (n int, err error) { if len(b) > 0 { pmb = &mbytes[0] } - acp := windows.GetACP() - nwc, err := windows.MultiByteToWideChar(acp, 2, pmb, int32(nmb), nil, 0) + ccp := windows.GetConsoleCP() + // Convert from 8-bit console encoding to UTF16. + // MultiByteToWideChar defaults to Unicode NFC form, which is the expected one. + nwc, err := windows.MultiByteToWideChar(ccp, 0, pmb, int32(nmb), nil, 0) if err != nil { return 0, err } wchars := make([]uint16, nwc) pwc := &wchars[0] - nwc, err = windows.MultiByteToWideChar(acp, 2, pmb, int32(nmb), pwc, nwc) + nwc, err = windows.MultiByteToWideChar(ccp, 0, pmb, int32(nmb), pwc, nwc) if err != nil { return 0, err }