Test unicode file name

tronkko · Sep 11, 2018 · 9dcd11b · 9dcd11b
1 parent 8d026f7
commit 9dcd11b
Show file tree

Hide file tree

Showing 3 changed files with 414 additions and 63 deletions.
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -51,4 +51,5 @@ endfunction (add_test_executable)
 add_test_executable (t-compile tests/t-compile.c)
 add_test_executable (t-dirent tests/t-dirent.c)
 add_test_executable (t-scandir tests/t-scandir.c)
+add_test_executable (t-unicode tests/t-unicode.c)
 add_test_executable (t-cplusplus tests/t-cplusplus.cpp)
diff --git a/include/dirent.h b/include/dirent.h
@@ -1026,7 +1026,6 @@ versionsort(
     return alphasort (a, b);
 }
 
-
 /* Convert multi-byte string to wide character string */
 static int
 dirent_mbstowcs_s(
@@ -1037,46 +1036,83 @@ dirent_mbstowcs_s(
     size_t count)
 {
     int error;
+    int n;
+    size_t len;
+    UINT cp;
+    DWORD flags;
+
+    /* Determine code page for multi-byte string */
+    if (AreFileApisANSI ()) {
+        /* Default ANSI code page */
+        cp = GetACP ();
+    } else {
+        /* Default OEM code page */
+        cp = GetOEMCP ();
+    }
 
-#if defined(_MSC_VER)  &&  _MSC_VER >= 1400
-
-    /* Microsoft Visual Studio 2005 or later */
-    error = mbstowcs_s (pReturnValue, wcstr, sizeInWords, mbstr, count);
-
-#else
+    /*
+     * Determine flags based on the character set.  For more information,
+     * please see https://docs.microsoft.com/fi-fi/windows/desktop/api/stringapiset/nf-stringapiset-multibytetowidechar
+     */
+    switch (cp) {
+    case 42:
+    case 50220:
+    case 50221:
+    case 50222:
+    case 50225:
+    case 50227:
+    case 50229:
+    case 57002:
+    case 57003:
+    case 57004:
+    case 57005:
+    case 57006:
+    case 57007:
+    case 57008:
+    case 57009:
+    case 57010:
+    case 57011:
+    case 65000:
+        /* MultiByteToWideChar does not support MB_ERR_INVALID_CHARS */
+        flags = 0;
+        break;
+
+    default:
+        /*
+         * Ask MultiByteToWideChar to return an error if a multi-byte
+         * character cannot be converted to a wide-character.
+         */
+        flags = MB_ERR_INVALID_CHARS;
+    }
 
-    /* Older Visual Studio or non-Microsoft compiler */
-    size_t n;
+    /* Compute the length of input string without zero-terminator */
+    len = 0;
+    while (mbstr[len] != '\0'  &&  len < count) {
+        len++;
+    }
 
-    /* Convert to wide-character string (or count characters) */
-    n = mbstowcs (wcstr, mbstr, sizeInWords);
-    if (!wcstr  ||  n < count) {
+    /* Convert to wide-character string */
+    n = MultiByteToWideChar(
+        /* Source code page */ cp,
+        /* Flags */ flags,
+        /* Pointer to string to convert */ mbstr,
+        /* Size of multi-byte string */ (int) len,
+        /* Pointer to output buffer */ wcstr,
+        /* Size of output buffer */ sizeInWords - 1
+    );
 
-        /* Zero-terminate output buffer */
-        if (wcstr  &&  sizeInWords) {
-            if (n >= sizeInWords) {
-                n = sizeInWords - 1;
-            }
-            wcstr[n] = 0;
-        }
+    /* Ensure that output buffer is zero-terminated */
+    wcstr[n] = '\0';
 
-        /* Length of resulting multi-byte string WITH zero terminator */
-        if (pReturnValue) {
-            *pReturnValue = n + 1;
-        }
+    /* Return length of wide-character string with zero-terminator */
+    *pReturnValue = (size_t) (n + 1);
 
-        /* Success */
+    /* Return zero if conversion succeeded */
+    if (n > 0) {
         error = 0;
-
     } else {
-
-        /* Could not convert string */
         error = 1;
-
     }
-
-#endif
-
     return error;
 }
 
@@ -1089,47 +1125,77 @@ dirent_wcstombs_s(
     const wchar_t *wcstr,
     size_t count)
 {
+    int n;
     int error;
+    UINT cp;
+    size_t len;
+    BOOL flag = 0;
+    LPBOOL pflag;
+
+    /* Determine code page for multi-byte string */
+    if (AreFileApisANSI ()) {
+        /* Default ANSI code page */
+        cp = GetACP ();
+    } else {
+        /* Default OEM code page */
+        cp = GetOEMCP ();
+    }
 
-#if defined(_MSC_VER)  &&  _MSC_VER >= 1400
-
-    /* Microsoft Visual Studio 2005 or later */
-    error = wcstombs_s (pReturnValue, mbstr, sizeInBytes, wcstr, count);
-
-#else
-
-    /* Older Visual Studio or non-Microsoft compiler */
-    size_t n;
-
-    /* Convert to multi-byte string (or count the number of bytes needed) */
-    n = wcstombs (mbstr, wcstr, sizeInBytes);
-    if (!mbstr  ||  n < count) {
+    /* Compute the length of input string without zero-terminator */
+    len = 0;
+    while (wcstr[len] != '\0'  &&  len < count) {
+        len++;
+    }
 
-        /* Zero-terminate output buffer */
-        if (mbstr  &&  sizeInBytes) {
-            if (n >= sizeInBytes) {
-                n = sizeInBytes - 1;
-            }
-            mbstr[n] = '\0';
-        }
+    /*
+     * Determine if we can ask WideCharToMultiByte to return information on
+     * broken characters.  For more information, please see
+     * https://docs.microsoft.com/en-us/windows/desktop/api/stringapiset/nf-stringapiset-widechartomultibyte
+     */
+    switch (cp) {
+    case CP_UTF7:
+    case CP_UTF8:
+        /*
+         * WideCharToMultiByte fails if we request information on default
+         * characters.  This is just a nuisance but doesn't affect the
+         * converion: if Windows is configured to use UTF-8, then the default
+         * character should not be needed anyway.
+         */
+        pflag = NULL;
+        break;
 
-        /* Length of resulting multi-bytes string WITH zero-terminator */
-        if (pReturnValue) {
-            *pReturnValue = n + 1;
-        }
+    default:
+        /*
+         * Request that WideCharToMultiByte sets the flag if it uses the
+         * default character.
+         */
+        pflag = &flag;
+    }
 
-        /* Success */
+    /* Convert wide-character string to multi-byte character string */
+    n = WideCharToMultiByte(
+        /* Target code page */ cp,
+        /* Flags */ 0,
+        /* Pointer to unicode string */ wcstr,
+        /* Length of unicode string */ (int) len,
+        /* Pointer to output buffer */ mbstr,
+        /* Size of output buffer */ sizeInBytes - 1,
+        /* Default character */ NULL,
+        /* Whether default character was used or not */ pflag
+    );
+
+    /* Ensure that output buffer is zero-terminated */
+    mbstr[n] = '\0';
+
+    /* Return length of multi-byte string with zero-terminator */
+    *pReturnValue = (size_t) (n + 1);
+
+    /* Return zero if conversion succeeded without using default characters */
+    if (n > 0  &&  flag == 0) {
         error = 0;
-
     } else {
-
-        /* Cannot convert string */
         error = 1;
-
     }
-
-#endif
-
     return error;
 }