Adds _wopen support on Windows so that files with UTF-8 names

can be opened.

Fixes: HDFFV-2714, HDFFV-3914, HDFFV-3895, HDFFV-8237, HDFFV-10413, HDFFV-10691

4 files changed, 148 insertions, 6 deletions

diff --git a/release_docs/RELEASE.txt b/release_docs/RELEASE.txt
index aed539b..b5cc20c 100644
--- a/release_docs/RELEASE.txt
+++ b/release_docs/RELEASE.txt
@@ -135,6 +135,14 @@ New Features
 
       (DER - 2018/12/08, HDFFV-10252)
 
+    - Added the ability to open files with UTF-8 file names on Windows.
+
+      The POSIX open(2) API call on Windows is limited to ASCII
+      file names. The library has been updated to convert incoming file
+      names to UTF-16 (via MultiByteToWideChar(CP_UTF8, ...) and use
+      _wopen() instead.
+
+     (DER - 2019/03/15, HDFFV-2714, HDFFV-3914, HDFFV-3895, HDFFV-8237, HDFFV-10413, HDFFV-10691)
 
     Parallel Library:
     -----------------
diff --git a/src/H5system.c b/src/H5system.c
index f47d057..2ddc29a 100644
--- a/src/H5system.c
+++ b/src/H5system.c
@@ -985,6 +985,132 @@ Wroundf(float arg)
     return (float)(arg < 0.0F ? HDceil(arg - 0.5F) : HDfloor(arg + 0.5F));
 }
 
+/*-------------------------------------------------------------------------
+* Function:     H5_get_utf16_str
+*
+* Purpose:      Gets a UTF-16 string from an UTF-8 (or ASCII) string.
+*
+* Return:       Success:    A pointer to a UTF-16 string
+*                           This must be freed by the caller using H5MM_xfree()
+*               Failure:    NULL
+*
+* Programmer:  Dana Robinson
+*              Spring 2019
+*
+*-------------------------------------------------------------------------
+*/
+const wchar_t *
+H5_get_utf16_str(const char *s)
+{
+    int     nwchars = -1;       /* Length of the UTF-16 buffer */
+    wchar_t *ret_s  = NULL;     /* UTF-16 version of the string */
+
+    /* Get the number of UTF-16 characters needed */
+    if(0 == (nwchars = MultiByteToWideChar(CP_UTF8, 0, s, -1, NULL, 0)))
+        goto error;
+
+    /* Allocate a buffer for the UTF-16 string */
+    if(NULL == (ret_s = (wchar_t *)H5MM_calloc(sizeof(wchar_t) * (size_t)nwchars)))
+        goto error;
+
+    /* Convert the input UTF-8 string to UTF-16 */
+    if(0 == MultiByteToWideChar(CP_UTF8, 0, s, -1, ret_s, nwchars))
+        goto error;
+
+    return ret_s;
+
+error:
+    if(ret_s)
+        H5MM_xfree((void *)ret_s);
+    return NULL;
+}   /* end H5_get_utf16_str() */
+
+/*-------------------------------------------------------------------------
+ * Function:     Wopen_utf8
+ *
+ * Purpose:      UTF-8 equivalent of open(2) for use on Windows.
+ *               Converts a UTF-8 input path to UTF-16 and then opens the
+ *               file via _wopen() under the hood
+ *
+ * Return:       Success:    A POSIX file descriptor
+ *               Failure:    -1
+ *
+ * Programmer:  Dana Robinson
+ *              Spring 2019
+ *
+ *-------------------------------------------------------------------------
+ */
+int
+Wopen_utf8(const char *path, int oflag, ...)
+{
+    int fd          = -1;       /* POSIX file descriptor to be returned */
+    wchar_t *wpath  = NULL;     /* UTF-16 version of the path */
+    int pmode       = 0;        /* mode (optionally set via variable args) */
+
+    /* Convert the input UTF-8 path to UTF-16 */
+    if(NULL == (wpath = H5_get_utf16_str(path)))
+        goto done;
+
+    /* _O_BINARY must be set in Windows to avoid CR-LF <-> LF EOL
+    * transformations when performing I/O. Note that this will
+    * produce Unix-style text files, though.
+    */
+    oflag |= _O_BINARY;
+
+    /* Get the mode, if O_CREAT was specified */
+    if(oflag & O_CREAT) {
+        va_list vl;
+
+        HDva_start(vl, oflag);
+        pmode = HDva_arg(vl, int);
+        HDva_end(vl);
+    }
+
+    /* Open the file */
+    fd = _wopen(wpath, oflag, pmode);
+
+done:
+    if(wpath)
+        H5MM_xfree((void *)wpath);
+
+    return fd;
+}   /* end Wopen_utf8() */
+
+/*-------------------------------------------------------------------------
+ * Function:     Wremove_utf8
+ *
+ * Purpose:      UTF-8 equivalent of remove(3) for use on Windows.
+ *               Converts a UTF-8 input path to UTF-16 and then opens the
+ *               file via _wremove() under the hood
+ *
+ * Return:       Success:    0
+ *               Failure:    -1
+ *
+ * Programmer:  Dana Robinson
+ *              Spring 2019
+ *
+ *-------------------------------------------------------------------------
+ */
+int
+Wremove_utf8(const char *path)
+{
+    wchar_t *wpath = NULL;     /* UTF-16 version of the path */
+    int ret;
+
+    /* Convert the input UTF-8 path to UTF-16 */
+    if(NULL == (wpath = H5_get_utf16_str(path)))
+        goto done;
+
+    /* Open the file */
+    ret = _wremove(wpath);
+
+done:
+    if(wpath)
+        H5MM_xfree((void *)wpath);
+
+    return ret;
+}   /* end Wremove_utf8() */
+
 #endif /* H5_HAVE_WIN32_API */
 
 
diff --git a/src/H5win32defs.h b/src/H5win32defs.h
index 140afc3..2ae2575 100644
--- a/src/H5win32defs.h
+++ b/src/H5win32defs.h
@@ -34,6 +34,7 @@ typedef __int64             h5_stat_size_t;
 #define HDaccess(F,M)       _access(F,M)
 #define HDchdir(S)          _chdir(S)
 #define HDclose(F)          _close(F)
+#define HDcreat(S,M)        Wopen_utf8(S,O_CREAT|O_TRUNC|O_RDWR,M)
 #define HDdup(F)            _dup(F)
 #define HDfdopen(N,S)       _fdopen(N,S)
 #define HDfileno(F)         _fileno(F)
@@ -47,15 +48,13 @@ typedef __int64             h5_stat_size_t;
 #define HDmkdir(S,M)        _mkdir(S)
 #define HDnanosleep(N, O)   Wnanosleep(N, O)
 #define HDoff_t             __int64
-/* _O_BINARY must be set in Windows to avoid CR-LF <-> LF EOL
- * transformations when performing I/O. Note that this will
- * produce Unix-style text files, though.
- *
- * Also note that the variadic macro is using a VC++ extension
+
+/* Note that the variadic HDopen macro is using a VC++ extension
  * where the comma is dropped if nothing is passed to the ellipsis.
  */
-#define HDopen(S,F,...)       _open(S, F | _O_BINARY, __VA_ARGS__)
+#define HDopen(S,F,...)     Wopen_utf8(S,F,__VA_ARGS__)
 #define HDread(F,M,Z)       _read(F,M,Z)
+#define HDremove(S)         Wremove_utf8(S)
 #define HDrmdir(S)          _rmdir(S)
 #define HDsetvbuf(F,S,M,Z)  setvbuf(F,S,M,(Z>1?Z:2))
 #define HDsleep(S)          Sleep(S*1000)
@@ -128,6 +127,9 @@ extern "C" {
     H5_DLL int c99_vsnprintf(char* str, size_t size, const char* format, va_list ap);
     H5_DLL int Wnanosleep(const struct timespec *req, struct timespec *rem);
     H5_DLL herr_t H5_expand_windows_env_vars(char **env_var);
+    H5_DLL const wchar_t *H5_get_utf16_str(const char *s);
+	H5_DLL int Wopen_utf8(const char *path, int oflag, ...);
+    H5_DLL int Wremove_utf8(const char *path);
 
     /* Round functions only needed for VS2012 and earlier.
      * They are always built to ensure they don't go stale and
diff --git a/tools/test/perform/sio_engine.c b/tools/test/perform/sio_engine.c
index 4fead3f..11de229 100644
--- a/tools/test/perform/sio_engine.c
+++ b/tools/test/perform/sio_engine.c
@@ -54,6 +54,12 @@
 } while(0)
 
 /* POSIX I/O macros */
+#ifdef H5_HAVE_WIN32_API
+/* Can't link against the library, so this test will use the older, non-Unicode
+ * _open() call on Windows.
+ */
+#define HDopen(S,F,...)           _open(S, F | _O_BINARY, __VA_ARGS__)
+#endif /* H5_HAVE_WIN32_API */
 #define POSIXCREATE(fn)           HDopen(fn, O_CREAT|O_TRUNC|O_RDWR, 0600)
 #define POSIXOPEN(fn, F)          HDopen(fn, F, 0600)
 #define POSIXCLOSE(F)             HDclose(F)