From: Peter Krefting <peter@softwolves.pp.se>
Date: Mon, 02 Mar 2009 08:47:22 GMT
Subject: [RFC PATCH] Windows: Assume all file names to be UTF-8 encoded.
Message-ID: <alpine.DEB.2.00.0903020941120.17877@perkele.intern.softwolves.pp.se>

When opening a file through open() or fopen(), the path passed is
UTF-8 encoded. To handle this on Windows, we need to convert the
path string to UTF-16 and use the Unicode-based interface.
---
Windows does support file names using arbitrary Unicode characters, you just 
need to use its wchar_t interfaces instead of the char ones (the char ones 
just gets converted into wchar_t on the API level anyway, for the same 
reasons). This is the beginnings of support for UTF-8 file names on Git on 
Windows.

Since there is no real file system abstraction beyond using stdio (AFAIK), I 
need to hack it by replacing fopen (and open). Probably opendir/readdir as 
well (might be trickier), and possibly even hack around main() to parse the 
wchar_t command-line instead of the char copy.

This will lose all chances of Windows 9x compatibility, but I don't know if 
there are any attempts of supporting it anyway?

Please note that MultiByteToWideChar() will reject any invalid UTF-8 
strings, perhaps it should just fall back to a regular open()/fopen() in 
that case?

No Signed-Off line since this is unfinished, just presenting rough sketches 
of an idea.

  compat/mingw.c |   60 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
  compat/mingw.h |    3 ++
  2 files changed, 62 insertions(+), 1 deletions(-)

diff --git a/compat/mingw.c b/compat/mingw.c
index e25cb4f..8b19b80 100644
--- a/compat/mingw.c
+++ b/compat/mingw.c
@@ -9,13 +9,30 @@ int mingw_open (const char *filename, int oflags, ...)
  {
  	va_list args;
  	unsigned mode;
+	wchar_t *unicode_filename;
+	int unicode_filename_len;
  	va_start(args, oflags);
  	mode = va_arg(args, int);
  	va_end(args);

  	if (!strcmp(filename, "/dev/null"))
  		filename = "nul";
-	int fd = open(filename, oflags, mode);
+
+	unicode_filename_len = MultiByteToWideChar(CP_UTF8, 0, filename, -1, NULL, 0);
+	if (0 == unicode_filename_len) {
+		errno = EINVAL;
+		return -1;
+	};
+
+	unicode_filename = xmalloc(unicode_filename_len * sizeof (wchar_t));
+	if (NULL == unicode_filename) {
+		errno = ENOMEM;
+		return -1;
+	}
+	MultiByteToWideChar(CP_UTF8, 0, filename, -1, unicode_filename, unicode_filename_len);
+	int fd = _wopen(unicode_filename, oflags, mode);
+	free(unicode_filename);
+
  	if (fd < 0 && (oflags & O_CREAT) && errno == EACCES) {
  		DWORD attrs = GetFileAttributes(filename);
  		if (attrs != INVALID_FILE_ATTRIBUTES && (attrs & FILE_ATTRIBUTE_DIRECTORY))
@@ -24,6 +41,47 @@ int mingw_open (const char *filename, int oflags, ...)
  	return fd;
  }

+FILE *mingw_fopen (const char *filename, const char *mode)
+{
+	wchar_t *unicode_filename, *unicode_mode;
+	int unicode_filename_len, unicode_mode_len;
+	FILE *fh;
+
+	unicode_filename_len = MultiByteToWideChar(CP_UTF8, 0, filename, -1, NULL, 0);
+	if (0 == unicode_filename_len) {
+		errno = EINVAL;
+		return NULL;
+	};
+
+	unicode_filename = xmalloc(unicode_filename_len * sizeof (wchar_t));
+	if (NULL == unicode_filename) {
+		errno = ENOMEM;
+		return NULL;
+	}
+	MultiByteToWideChar(CP_UTF8, 0, filename, -1, unicode_filename, unicode_filename_len);
+
+	unicode_mode_len = MultiByteToWideChar(CP_UTF8, 0, mode, -1, NULL, 0);
+	if (0 == unicode_mode_len) {
+		free(unicode_filename);
+		errno = EINVAL;
+		return NULL;
+	};
+
+	unicode_mode = xmalloc(unicode_mode_len * sizeof (wchar_t));
+	if (NULL == unicode_mode) {
+		free(unicode_mode);
+		errno = ENOMEM;
+		return NULL;
+	}
+	MultiByteToWideChar(CP_UTF8, 0, mode, -1, unicode_mode, unicode_mode_len);
+
+	fh = _wfopen(unicode_filename, unicode_mode);
+	free(unicode_filename);
+	free(unicode_mode);
+
+	return fh;
+}
+
  static inline time_t filetime_to_time_t(const FILETIME *ft)
  {
  	long long winTime = ((long long)ft->dwHighDateTime << 32) + ft->dwLowDateTime;
diff --git a/compat/mingw.h b/compat/mingw.h
index 4f275cb..235df0a 100644
--- a/compat/mingw.h
+++ b/compat/mingw.h
@@ -142,6 +142,9 @@ int sigaction(int sig, struct sigaction *in, struct sigaction *out);
  int mingw_open (const char *filename, int oflags, ...);
  #define open mingw_open

+FILE *mingw_fopen (const char *filename, const char *mode);
+#define fopen mingw_fopen
+
  char *mingw_getcwd(char *pointer, int len);
  #define getcwd mingw_getcwd

-- 
1.6.0.2.1172.ga5ed0