Win32: Unicode file name support (dirent)

Changes opendir/readdir to use Windows Unicode APIs and convert between UTF-8/UTF-16. Removes parameter checks that are already covered by xutftowcs_path. This changes detection of ENAMETOOLONG from MAX_PATH - 2 to MAX_PATH (matching is_dir_empty in mingw.c). If name + "/*" or the resulting absolute path is too long, FindFirstFile fails and errno is set through err_win_to_posix. Increases the size of dirent.d_name to accommodate the full WIN32_FIND_DATA.cFileName converted to UTF-8 (UTF-16 to UTF-8 conversion may grow by factor three in the worst case). Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Stepan Kasal <kasal@ucw.cz> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Karsten Blees committed Jan 14, 2012 at 22:01 UTC 0217569bb2db23b8686f67b0f4dda7e517dec6fd
2 files changed +11 -21
compat/win32/dirent.c
+10 -20
@@ -6,10 +6,10 @@ struct DIR {
6 int dd_stat; /* 0-based index */
7 };
8
9 -static inline void finddata2dirent(struct dirent *ent, WIN32_FIND_DATAA *fdata)
9 +static inline void finddata2dirent(struct dirent *ent, WIN32_FIND_DATAW *fdata)
10 {
11 - /* copy file name from WIN32_FIND_DATA to dirent */
12 - memcpy(ent->d_name, fdata->cFileName, sizeof(ent->d_name));
11 + /* convert UTF-16 name to UTF-8 */
12 + xwcstoutf(ent->d_name, fdata->cFileName, sizeof(ent->d_name));
13
14 /* Set file type, based on WIN32_FIND_DATA */
15 if (fdata->dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY)
@@ -20,25 +20,15 @@ static inline void finddata2dirent(struct dirent *ent, WIN32_FIND_DATAA *fdata)
20
21 DIR *opendir(const char *name)
22 {
23 - char pattern[MAX_PATH];
24 - WIN32_FIND_DATAA fdata;
23 + wchar_t pattern[MAX_PATH + 2]; /* + 2 for '/' '*' */
24 + WIN32_FIND_DATAW fdata;
25 HANDLE h;
26 int len;
27 DIR *dir;
28
29 - /* check that name is not NULL */
30 - if (!name) {
31 - errno = EINVAL;
29 + /* convert name to UTF-16 and check length < MAX_PATH */
30 + if ((len = xutftowcs_path(pattern, name)) < 0)
31 return NULL;
33 - }
34 - /* check that the pattern won't be too long for FindFirstFileA */
35 - len = strlen(name);
36 - if (len + 2 >= MAX_PATH) {
37 - errno = ENAMETOOLONG;
38 - return NULL;
39 - }
40 - /* copy name to temp buffer */
41 - memcpy(pattern, name, len + 1);
32
33 /* append optional '/' and wildcard '*' */
34 if (len && !is_dir_sep(pattern[len - 1]))
@@ -47,7 +37,7 @@ DIR *opendir(const char *name)
37 pattern[len] = 0;
38
39 /* open find handle */
50 - h = FindFirstFileA(pattern, &fdata);
40 + h = FindFirstFileW(pattern, &fdata);
41 if (h == INVALID_HANDLE_VALUE) {
42 DWORD err = GetLastError();
43 errno = (err == ERROR_DIRECTORY) ? ENOTDIR : err_win_to_posix(err);
@@ -72,8 +62,8 @@ struct dirent *readdir(DIR *dir)
62 /* if first entry, dirent has already been set up by opendir */
63 if (dir->dd_stat) {
64 /* get next entry and convert from WIN32_FIND_DATA to dirent */
75 - WIN32_FIND_DATAA fdata;
76 - if (FindNextFileA(dir->dd_handle, &fdata)) {
65 + WIN32_FIND_DATAW fdata;
66 + if (FindNextFileW(dir->dd_handle, &fdata)) {
67 finddata2dirent(&dir->dd_dir, &fdata);
68 } else {
69 DWORD lasterr = GetLastError();
compat/win32/dirent.h
+1 -1
@@ -10,7 +10,7 @@ typedef struct DIR DIR;
10
11 struct dirent {
12 unsigned char d_type; /* file type to prevent lstat after readdir */
13 - char d_name[MAX_PATH]; /* file name */
13 + char d_name[MAX_PATH * 3]; /* file name (* 3 for UTF-8 conversion) */
14 };
15
16 DIR *opendir(const char *dirname);