mingw: make the dirent implementation pluggable

Emulating the POSIX `dirent` API on Windows via
`FindFirstFile()`/`FindNextFile()` is pretty staightforward, however,
most of the information provided in the `WIN32_FIND_DATA` structure is
thrown away in the process. A more sophisticated implementation may
cache this data, e.g. for later reuse in calls to `lstat()`.

Make the `dirent` implementation pluggable so that it can be switched at
runtime, e.g. based on a config option.

Define a base DIR structure with pointers to `readdir()`/`closedir()`
that match the `opendir()` implementation (similar to vtable pointers in
Object-Oriented Programming). Define `readdir()`/`closedir()` so that
they call the function pointers in the `DIR` structure. This allows to
choose the `opendir()` implementation on a call-by-call basis.

Make the fixed-size `dirent.d_name` buffer a flex array, as `d_name` may
be implementation specific (e.g. a caching implementation may allocate a
`struct dirent` with _just_ the size needed to hold the `d_name` in
question).

Signed-off-by: Karsten Blees <blees@dcon.de>
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>

Author: kblees

compat/win32/dirent.c

@@ -1,15 +1,21 @@
 #include "../../git-compat-util.h"
 
-struct DIR {
-	struct dirent dd_dir; /* includes d_type */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpedantic"
+typedef struct dirent_DIR {
+	struct DIR base_dir;  /* extend base struct DIR */
 	HANDLE dd_handle;     /* FindFirstFile handle */
 	int dd_stat;          /* 0-based index */
-};
+	struct dirent dd_dir; /* includes d_type */
+} dirent_DIR;
+#pragma GCC diagnostic pop
+
+DIR *(*opendir)(const char *dirname) = dirent_opendir;
 
 static inline void finddata2dirent(struct dirent *ent, WIN32_FIND_DATAW *fdata)
 {
-	/* convert UTF-16 name to UTF-8 */
-	xwcstoutf(ent->d_name, fdata->cFileName, sizeof(ent->d_name));
+	/* convert UTF-16 name to UTF-8 (d_name points to dirent_DIR.dd_name) */
+	xwcstoutf(ent->d_name, fdata->cFileName, MAX_PATH * 3);
 
 	/* Set file type, based on WIN32_FIND_DATA */
 	if ((fdata->dwFileAttributes & FILE_ATTRIBUTE_REPARSE_POINT)
@@ -21,7 +27,7 @@ static inline void finddata2dirent(struct dirent *ent, WIN32_FIND_DATAW *fdata)
 		ent->d_type = DT_REG;
 }
 
-struct dirent *readdir(DIR *dir)
+static struct dirent *dirent_readdir(dirent_DIR *dir)
 {
 	if (!dir) {
 		errno = EBADF; /* No set_errno for mingw */
@@ -48,7 +54,7 @@ struct dirent *readdir(DIR *dir)
 	return &dir->dd_dir;
 }
 
-int closedir(DIR *dir)
+static int dirent_closedir(dirent_DIR *dir)
 {
 	if (!dir) {
 		errno = EBADF;
@@ -60,13 +66,13 @@ int closedir(DIR *dir)
 	return 0;
 }
 
-DIR *opendir(const char *name)
+DIR *dirent_opendir(const char *name)
 {
 	wchar_t pattern[MAX_PATH + 2]; /* + 2 for '/' '*' */
 	WIN32_FIND_DATAW fdata;
 	HANDLE h;
 	int len;
-	DIR *dir;
+	dirent_DIR *dir;
 
 	/* convert name to UTF-16 and check length < MAX_PATH */
 	if ((len = xutftowcs_path(pattern, name)) < 0)
@@ -87,9 +93,11 @@ DIR *opendir(const char *name)
 	}
 
 	/* initialize DIR structure and copy first dir entry */
-	dir = xmalloc(sizeof(DIR));
+	dir = xmalloc(sizeof(dirent_DIR) + MAX_PATH);
+	dir->base_dir.preaddir = (struct dirent *(*)(DIR *dir)) dirent_readdir;
+	dir->base_dir.pclosedir = (int (*)(DIR *dir)) dirent_closedir;
 	dir->dd_handle = h;
 	dir->dd_stat = 0;
 	finddata2dirent(&dir->dd_dir, &fdata);
-	return dir;
+	return (DIR*) dir;
 }

compat/win32/dirent.h

@@ -1,20 +1,34 @@
 #ifndef DIRENT_H
 #define DIRENT_H
 
-typedef struct DIR DIR;
-
 #define DT_UNKNOWN 0
 #define DT_DIR     1
 #define DT_REG     2
 #define DT_LNK     3
 
 struct dirent {
-	unsigned char d_type;      /* file type to prevent lstat after readdir */
-	char d_name[MAX_PATH * 3]; /* file name (* 3 for UTF-8 conversion) */
+	unsigned char d_type; /* file type to prevent lstat after readdir */
+	char d_name[/* FLEX_ARRAY */]; /* file name */
 };
 
-DIR *opendir(const char *dirname);
-struct dirent *readdir(DIR *dir);
-int closedir(DIR *dir);
+/*
+ * Base DIR structure, contains pointers to readdir/closedir implementations so
+ * that opendir may choose a concrete implementation on a call-by-call basis.
+ */
+typedef struct DIR {
+	struct dirent *(*preaddir)(struct DIR *dir);
+	int (*pclosedir)(struct DIR *dir);
+} DIR;
+
+/* default dirent implementation */
+extern DIR *dirent_opendir(const char *dirname);
+
+#define opendir git_opendir
+
+/* current dirent implementation */
+extern DIR *(*opendir)(const char *dirname);
+
+#define readdir(dir) (dir->preaddir(dir))
+#define closedir(dir) (dir->pclosedir(dir))
 
 #endif /* DIRENT_H */