Merge 'unicode' into HEAD

Author: kasal

compat/mingw.c

@@ -118,10 +118,7 @@ static inline int fcntl(int fd, int cmd, ...)
  * simple adaptors
  */
 
-static inline int mingw_mkdir(const char *path, int mode)
-{
-	return mkdir(path);
-}
+int mingw_mkdir(const char *path, int mode);
 #define mkdir mingw_mkdir
 
 #define WNOHANG 1
@@ -192,11 +189,27 @@ FILE *mingw_freopen (const char *filename, const char *otype, FILE *stream);
 int mingw_fflush(FILE *stream);
 #define fflush mingw_fflush
 
+int mingw_access(const char *filename, int mode);
+#undef access
+#define access mingw_access
+
+int mingw_chdir(const char *dirname);
+#define chdir mingw_chdir
+
+int mingw_chmod(const char *filename, int mode);
+#define chmod mingw_chmod
+
+char *mingw_mktemp(char *template);
+#define mktemp mingw_mktemp
+
 char *mingw_getcwd(char *pointer, int len);
 #define getcwd mingw_getcwd
 
 char *mingw_getenv(const char *name);
 #define getenv mingw_getenv
+int mingw_putenv(const char *namevalue);
+#define putenv mingw_putenv
+#define unsetenv mingw_putenv
 
 int mingw_gethostname(char *host, int namelen);
 #define gethostname mingw_gethostname
@@ -317,12 +330,8 @@ int mingw_raise(int sig);
  * ANSI emulation wrappers
  */
 
-int winansi_fputs(const char *str, FILE *stream);
-int winansi_printf(const char *format, ...) __attribute__((format (printf, 1, 2)));
-int winansi_fprintf(FILE *stream, const char *format, ...) __attribute__((format (printf, 2, 3)));
-#define fputs winansi_fputs
-#define printf(...) winansi_printf(__VA_ARGS__)
-#define fprintf(...) winansi_fprintf(__VA_ARGS__)
+void winansi_init(void);
+HANDLE winansi_get_osfhandle(int fd);
 
 /*
  * git specific compatibility
@@ -348,12 +357,112 @@ int mingw_offset_1st_component(const char *path);
 void mingw_open_html(const char *path);
 #define open_html mingw_open_html
 
-/*
- * helpers
+void mingw_mark_as_git_dir(const char *dir);
+#define mark_as_git_dir mingw_mark_as_git_dir
+
+/**
+ * Converts UTF-8 encoded string to UTF-16LE.
+ *
+ * To support repositories with legacy-encoded file names, invalid UTF-8 bytes
+ * 0xa0 - 0xff are converted to corresponding printable Unicode chars \u00a0 -
+ * \u00ff, and invalid UTF-8 bytes 0x80 - 0x9f (which would make non-printable
+ * Unicode) are converted to hex-code.
+ *
+ * Lead-bytes not followed by an appropriate number of trail-bytes, over-long
+ * encodings and 4-byte encodings > \u10ffff are detected as invalid UTF-8.
+ *
+ * Maximum space requirement for the target buffer is two wide chars per UTF-8
+ * char (((strlen(utf) * 2) + 1) [* sizeof(wchar_t)]).
+ *
+ * The maximum space is needed only if the entire input string consists of
+ * invalid UTF-8 bytes in range 0x80-0x9f, as per the following table:
+ *
+ *               |                   | UTF-8 | UTF-16 |
+ *   Code point  |  UTF-8 sequence   | bytes | words  | ratio
+ * --------------+-------------------+-------+--------+-------
+ * 000000-00007f | 0-7f              |   1   |   1    |  1
+ * 000080-0007ff | c2-df + 80-bf     |   2   |   1    |  0.5
+ * 000800-00ffff | e0-ef + 2 * 80-bf |   3   |   1    |  0.33
+ * 010000-10ffff | f0-f4 + 3 * 80-bf |   4   |  2 (a) |  0.5
+ * invalid       | 80-9f             |   1   |  2 (b) |  2
+ * invalid       | a0-ff             |   1   |   1    |  1
+ *
+ * (a) encoded as UTF-16 surrogate pair
+ * (b) encoded as two hex digits
+ *
+ * Note that, while the UTF-8 encoding scheme can be extended to 5-byte, 6-byte
+ * or even indefinite-byte sequences, the largest valid code point \u10ffff
+ * encodes as only 4 UTF-8 bytes.
+ *
+ * Parameters:
+ * wcs: wide char target buffer
+ * utf: string to convert
+ * wcslen: size of target buffer (in wchar_t's)
+ * utflen: size of string to convert, or -1 if 0-terminated
+ *
+ * Returns:
+ * length of converted string (_wcslen(wcs)), or -1 on failure
+ *
+ * Errors:
+ * EINVAL: one of the input parameters is invalid (e.g. NULL)
+ * ERANGE: the output buffer is too small
+ */
+int xutftowcsn(wchar_t *wcs, const char *utf, size_t wcslen, int utflen);
+
+/**
+ * Simplified variant of xutftowcsn, assumes input string is \0-terminated.
+ */
+static inline int xutftowcs(wchar_t *wcs, const char *utf, size_t wcslen)
+{
+	return xutftowcsn(wcs, utf, wcslen, -1);
+}
+
+/**
+ * Simplified file system specific variant of xutftowcsn, assumes output
+ * buffer size is MAX_PATH wide chars and input string is \0-terminated,
+ * fails with ENAMETOOLONG if input string is too long.
  */
+static inline int xutftowcs_path(wchar_t *wcs, const char *utf)
+{
+	int result = xutftowcsn(wcs, utf, MAX_PATH, -1);
+	if (result < 0 && errno == ERANGE)
+		errno = ENAMETOOLONG;
+	return result;
+}
 
-char **make_augmented_environ(const char *const *vars);
-void free_environ(char **env);
+/**
+ * Converts UTF-16LE encoded string to UTF-8.
+ *
+ * Maximum space requirement for the target buffer is three UTF-8 chars per
+ * wide char ((_wcslen(wcs) * 3) + 1).
+ *
+ * The maximum space is needed only if the entire input string consists of
+ * UTF-16 words in range 0x0800-0xd7ff or 0xe000-0xffff (i.e. \u0800-\uffff
+ * modulo surrogate pairs), as per the following table:
+ *
+ *               |                       | UTF-16 | UTF-8 |
+ *   Code point  |  UTF-16 sequence      | words  | bytes | ratio
+ * --------------+-----------------------+--------+-------+-------
+ * 000000-00007f | 0000-007f             |   1    |   1   |  1
+ * 000080-0007ff | 0080-07ff             |   1    |   2   |  2
+ * 000800-00ffff | 0800-d7ff / e000-ffff |   1    |   3   |  3
+ * 010000-10ffff | d800-dbff + dc00-dfff |   2    |   4   |  2
+ *
+ * Note that invalid code points > 10ffff cannot be represented in UTF-16.
+ *
+ * Parameters:
+ * utf: target buffer
+ * wcs: wide string to convert
+ * utflen: size of target buffer
+ *
+ * Returns:
+ * length of converted string, or -1 on failure
+ *
+ * Errors:
+ * EINVAL: one of the input parameters is invalid (e.g. NULL)
+ * ERANGE: the output buffer is too small
+ */
+int xwcstoutf(char *utf, const wchar_t *wcs, size_t utflen);
 
 /*
  * A critical section used in the implementation of the spawn
@@ -363,22 +472,16 @@ void free_environ(char **env);
 extern CRITICAL_SECTION pinfo_cs;
 
 /*
- * A replacement of main() that ensures that argv[0] has a path
- * and that default fmode and std(in|out|err) are in binary mode
+ * A replacement of main() that adds win32 specific initialization.
  */
 
+void mingw_startup();
 #define main(c,v) dummy_decl_mingw_main(); \
 static int mingw_main(c,v); \
-int main(int argc, char **argv) \
+int main(c,v) \
 { \
-	extern CRITICAL_SECTION pinfo_cs; \
-	_fmode = _O_BINARY; \
-	_setmode(_fileno(stdin), _O_BINARY); \
-	_setmode(_fileno(stdout), _O_BINARY); \
-	_setmode(_fileno(stderr), _O_BINARY); \
-	argv[0] = xstrdup(_pgmptr); \
-	InitializeCriticalSection(&pinfo_cs); \
-	return mingw_main(argc, argv); \
+	mingw_startup(); \
+	return mingw_main(__argc, __argv); \
 } \
 static int mingw_main(c,v)
 

compat/mingw.h

@@ -1,96 +1,81 @@
-#include "../git-compat-util.h"
-#include "dirent.h"
+#include "../../git-compat-util.h"
 
 struct DIR {
 	struct dirent dd_dir; /* includes d_type */
 	HANDLE dd_handle;     /* FindFirstFile handle */
 	int dd_stat;          /* 0-based index */
-	char dd_name[1];      /* extend struct */
 };
 
+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));
+
+	/* Set file type, based on WIN32_FIND_DATA */
+	if (fdata->dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY)
+		ent->d_type = DT_DIR;
+	else
+		ent->d_type = DT_REG;
+}
+
 DIR *opendir(const char *name)
 {
-	DWORD attrs = GetFileAttributesA(name);
+	wchar_t pattern[MAX_PATH + 2]; /* + 2 for '/' '*' */
+	WIN32_FIND_DATAW fdata;
+	HANDLE h;
 	int len;
-	DIR *p;
+	DIR *dir;
 
-	/* check for valid path */
-	if (attrs == INVALID_FILE_ATTRIBUTES) {
-		errno = ENOENT;
+	/* convert name to UTF-16 and check length < MAX_PATH */
+	if ((len = xutftowcs_path(pattern, name)) < 0)
 		return NULL;
-	}
 
-	/* check if it's a directory */
-	if (!(attrs & FILE_ATTRIBUTE_DIRECTORY)) {
-		errno = ENOTDIR;
+	/* append optional '/' and wildcard '*' */
+	if (len && !is_dir_sep(pattern[len - 1]))
+		pattern[len++] = '/';
+	pattern[len++] = '*';
+	pattern[len] = 0;
+
+	/* open find handle */
+	h = FindFirstFileW(pattern, &fdata);
+	if (h == INVALID_HANDLE_VALUE) {
+		DWORD err = GetLastError();
+		errno = (err == ERROR_DIRECTORY) ? ENOTDIR : err_win_to_posix(err);
 		return NULL;
 	}
 
-	/* check that the pattern won't be too long for FindFirstFileA */
-	len = strlen(name);
-	if (is_dir_sep(name[len - 1]))
-		len--;
-	if (len + 2 >= MAX_PATH) {
-		errno = ENAMETOOLONG;
-		return NULL;
-	}
-
-	p = malloc(sizeof(DIR) + len + 2);
-	if (!p)
-		return NULL;
-
-	memset(p, 0, sizeof(DIR) + len + 2);
-	strcpy(p->dd_name, name);
-	p->dd_name[len] = '/';
-	p->dd_name[len+1] = '*';
-
-	p->dd_handle = INVALID_HANDLE_VALUE;
-	return p;
+	/* initialize DIR structure and copy first dir entry */
+	dir = xmalloc(sizeof(DIR));
+	dir->dd_handle = h;
+	dir->dd_stat = 0;
+	finddata2dirent(&dir->dd_dir, &fdata);
+	return dir;
 }
 
 struct dirent *readdir(DIR *dir)
 {
-	WIN32_FIND_DATAA buf;
-	HANDLE handle;
-
-	if (!dir || !dir->dd_handle) {
+	if (!dir) {
 		errno = EBADF; /* No set_errno for mingw */
 		return NULL;
 	}
 
-	if (dir->dd_handle == INVALID_HANDLE_VALUE && dir->dd_stat == 0) {
-		DWORD lasterr;
-		handle = FindFirstFileA(dir->dd_name, &buf);
-		lasterr = GetLastError();
-		dir->dd_handle = handle;
-		if (handle == INVALID_HANDLE_VALUE && (lasterr != ERROR_NO_MORE_FILES)) {
-			errno = err_win_to_posix(lasterr);
+	/* if first entry, dirent has already been set up by opendir */
+	if (dir->dd_stat) {
+		/* get next entry and convert from WIN32_FIND_DATA to dirent */
+		WIN32_FIND_DATAW fdata;
+		if (FindNextFileW(dir->dd_handle, &fdata)) {
+			finddata2dirent(&dir->dd_dir, &fdata);
+		} else {
+			DWORD lasterr = GetLastError();
+			/* POSIX says you shouldn't set errno when readdir can't
+			   find any more files; so, if another error we leave it set. */
+			if (lasterr != ERROR_NO_MORE_FILES)
+				errno = err_win_to_posix(lasterr);
 			return NULL;
 		}
-	} else if (dir->dd_handle == INVALID_HANDLE_VALUE) {
-		return NULL;
-	} else if (!FindNextFileA(dir->dd_handle, &buf)) {
-		DWORD lasterr = GetLastError();
-		FindClose(dir->dd_handle);
-		dir->dd_handle = INVALID_HANDLE_VALUE;
-		/* POSIX says you shouldn't set errno when readdir can't
-		   find any more files; so, if another error we leave it set. */
-		if (lasterr != ERROR_NO_MORE_FILES)
-			errno = err_win_to_posix(lasterr);
-		return NULL;
 	}
 
-	/* We get here if `buf' contains valid data.  */
-	strcpy(dir->dd_dir.d_name, buf.cFileName);
 	++dir->dd_stat;
-
-	/* Set file type, based on WIN32_FIND_DATA */
-	dir->dd_dir.d_type = 0;
-	if (buf.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY)
-		dir->dd_dir.d_type |= DT_DIR;
-	else
-		dir->dd_dir.d_type |= DT_REG;
-
 	return &dir->dd_dir;
 }
 
@@ -101,8 +86,7 @@ int closedir(DIR *dir)
 		return -1;
 	}
 
-	if (dir->dd_handle != INVALID_HANDLE_VALUE)
-		FindClose(dir->dd_handle);
+	FindClose(dir->dd_handle);
 	free(dir);
 	return 0;
 }

compat/win32/dirent.c

@@ -9,12 +9,8 @@ typedef struct DIR DIR;
 #define DT_LNK     3
 
 struct dirent {
-	long d_ino;                      /* Always zero. */
-	char d_name[FILENAME_MAX];       /* File name. */
-	union {
-		unsigned short d_reclen; /* Always zero. */
-		unsigned char  d_type;   /* Reimplementation adds this */
-	};
+	unsigned char d_type;      /* file type to prevent lstat after readdir */
+	char d_name[MAX_PATH * 3]; /* file name (* 3 for UTF-8 conversion) */
 };
 
 DIR *opendir(const char *dirname);