Merge branch 'js/dirname-basename'

dirname() emulation has been added, as Msys2 lacks it.

* js/dirname-basename:
  mingw: avoid linking to the C library's isalpha()
  t0060: loosen overly strict expectations
  t0060: verify that basename() and dirname() work as expected
  compat/basename.c: provide a dirname() compatibility function
  compat/basename: make basename() conform to POSIX
  Refactor skipping DOS drive prefixes

compat/basename.c

@@ -1,15 +1,71 @@
 #include "../git-compat-util.h"
+#include "../strbuf.h"
 
 /* Adapted from libiberty's basename.c.  */
 char *gitbasename (char *path)
 {
 	const char *base;
-	/* Skip over the disk name in MSDOS pathnames. */
-	if (has_dos_drive_prefix(path))
-		path += 2;
+
+	if (path)
+		skip_dos_drive_prefix(&path);
+
+	if (!path || !*path)
+		return ".";
+
 	for (base = path; *path; path++) {
-		if (is_dir_sep(*path))
-			base = path + 1;
+		if (!is_dir_sep(*path))
+			continue;
+		do {
+			path++;
+		} while (is_dir_sep(*path));
+		if (*path)
+			base = path;
+		else
+			while (--path != base && is_dir_sep(*path))
+				*path = '\0';
 	}
 	return (char *)base;
 }
+
+char *gitdirname(char *path)
+{
+	static struct strbuf buf = STRBUF_INIT;
+	char *p = path, *slash = NULL, c;
+	int dos_drive_prefix;
+
+	if (!p)
+		return ".";
+
+	if ((dos_drive_prefix = skip_dos_drive_prefix(&p)) && !*p)
+		goto dot;
+
+	/*
+	 * POSIX.1-2001 says dirname("/") should return "/", and dirname("//")
+	 * should return "//", but dirname("///") should return "/" again.
+	 */
+	if (is_dir_sep(*p)) {
+		if (!p[1] || (is_dir_sep(p[1]) && !p[2]))
+			return path;
+		slash = ++p;
+	}
+	while ((c = *(p++)))
+		if (is_dir_sep(c)) {
+			char *tentative = p - 1;
+
+			/* POSIX.1-2001 says to ignore trailing slashes */
+			while (is_dir_sep(*p))
+				p++;
+			if (*p)
+				slash = tentative;
+		}
+
+	if (slash) {
+		*slash = '\0';
+		return path;
+	}
+
+dot:
+	strbuf_reset(&buf);
+	strbuf_addf(&buf, "%.*s.", dos_drive_prefix, path);
+	return buf.buf;
+}

compat/mingw.c

@@ -1935,28 +1935,31 @@ pid_t waitpid(pid_t pid, int *status, int options)
 	return -1;
 }
 
+int mingw_skip_dos_drive_prefix(char **path)
+{
+	int ret = has_dos_drive_prefix(*path);
+	*path += ret;
+	return ret;
+}
+
 int mingw_offset_1st_component(const char *path)
 {
-	int offset = 0;
-	if (has_dos_drive_prefix(path))
-		offset = 2;
+	char *pos = (char *)path;
 
 	/* unc paths */
-	else if (is_dir_sep(path[0]) && is_dir_sep(path[1])) {
-
+	if (!skip_dos_drive_prefix(&pos) &&
+			is_dir_sep(pos[0]) && is_dir_sep(pos[1])) {
 		/* skip server name */
-		char *pos = strpbrk(path + 2, "\\/");
+		pos = strpbrk(pos + 2, "\\/");
 		if (!pos)
 			return 0; /* Error: malformed unc path */
 
 		do {
 			pos++;
 		} while (*pos && !is_dir_sep(*pos));
-
-		offset = pos - path;
 	}
 
-	return offset + is_dir_sep(path[offset]);
+	return pos + is_dir_sep(*pos) - path;
 }
 
 int xutftowcsn(wchar_t *wcs, const char *utfs, size_t wcslen, int utflen)

compat/mingw.h

@@ -383,7 +383,10 @@ HANDLE winansi_get_osfhandle(int fd);
  * git specific compatibility
  */
 
-#define has_dos_drive_prefix(path) (isalpha(*(path)) && (path)[1] == ':')
+#define has_dos_drive_prefix(path) \
+	(isalpha(*(path)) && (path)[1] == ':' ? 2 : 0)
+int mingw_skip_dos_drive_prefix(char **path);
+#define skip_dos_drive_prefix mingw_skip_dos_drive_prefix
 #define is_dir_sep(c) ((c) == '/' || (c) == '\\')
 static inline char *mingw_find_last_dir_sep(const char *path)
 {

git-compat-util.h

@@ -253,6 +253,8 @@ struct itimerval {
 #else
 #define basename gitbasename
 extern char *gitbasename(char *);
+#define dirname gitdirname
+extern char *gitdirname(char *);
 #endif
 
 #ifndef NO_ICONV
@@ -335,6 +337,14 @@ static inline int git_has_dos_drive_prefix(const char *path)
 #define has_dos_drive_prefix git_has_dos_drive_prefix
 #endif
 
+#ifndef skip_dos_drive_prefix
+static inline int git_skip_dos_drive_prefix(char **path)
+{
+	return 0;
+}
+#define skip_dos_drive_prefix git_skip_dos_drive_prefix
+#endif
+
 #ifndef is_dir_sep
 static inline int git_is_dir_sep(int c)
 {

path.c

@@ -782,13 +782,10 @@ const char *relative_path(const char *in, const char *prefix,
 	else if (!prefix_len)
 		return in;
 
-	if (have_same_root(in, prefix)) {
+	if (have_same_root(in, prefix))
 		/* bypass dos_drive, for "c:" is identical to "C:" */
-		if (has_dos_drive_prefix(in)) {
-			i = 2;
-			j = 2;
-		}
-	} else {
+		i = j = has_dos_drive_prefix(in);
+	else {
 		return in;
 	}
 
@@ -943,11 +940,10 @@ const char *remove_leading_path(const char *in, const char *prefix)
 int normalize_path_copy_len(char *dst, const char *src, int *prefix_len)
 {
 	char *dst0;
+	int i;
 
-	if (has_dos_drive_prefix(src)) {
+	for (i = has_dos_drive_prefix(src); i > 0; i--)
 		*dst++ = *src++;
-		*dst++ = *src++;
-	}
 	dst0 = dst;
 
 	if (is_dir_sep(*src)) {

t/t0060-path-utils.sh

@@ -59,6 +59,9 @@ case $(uname -s) in
 	;;
 esac
 
+test_expect_success basename 'test-path-utils basename'
+test_expect_success dirname 'test-path-utils dirname'
+
 norm_path "" ""
 norm_path . ""
 norm_path ./ ""

test-path-utils.c

@@ -39,6 +39,130 @@ static void normalize_argv_string(const char **var, const char *input)
 		die("Bad value: %s\n", input);
 }
 
+struct test_data {
+	const char *from;  /* input:  transform from this ... */
+	const char *to;    /* output: ... to this.            */
+	const char *alternative; /* output: ... or this.      */
+};
+
+static int test_function(struct test_data *data, char *(*func)(char *input),
+	const char *funcname)
+{
+	int failed = 0, i;
+	char buffer[1024];
+	char *to;
+
+	for (i = 0; data[i].to; i++) {
+		if (!data[i].from)
+			to = func(NULL);
+		else {
+			strcpy(buffer, data[i].from);
+			to = func(buffer);
+		}
+		if (!strcmp(to, data[i].to))
+			continue;
+		if (!data[i].alternative)
+			error("FAIL: %s(%s) => '%s' != '%s'\n",
+				funcname, data[i].from, to, data[i].to);
+		else if (!strcmp(to, data[i].alternative))
+			continue;
+		else
+			error("FAIL: %s(%s) => '%s' != '%s', '%s'\n",
+				funcname, data[i].from, to, data[i].to,
+				data[i].alternative);
+		failed = 1;
+	}
+	return failed;
+}
+
+static struct test_data basename_data[] = {
+	/* --- POSIX type paths --- */
+	{ NULL,              "."    },
+	{ "",                "."    },
+	{ ".",               "."    },
+	{ "..",              ".."   },
+	{ "/",               "/"    },
+	{ "//",              "/", "//" },
+	{ "///",             "/", "//" },
+	{ "////",            "/", "//" },
+	{ "usr",             "usr"  },
+	{ "/usr",            "usr"  },
+	{ "/usr/",           "usr"  },
+	{ "/usr//",          "usr"  },
+	{ "/usr/lib",        "lib"  },
+	{ "usr/lib",         "lib"  },
+	{ "usr/lib///",      "lib"  },
+
+#if defined(__MINGW32__) || defined(_MSC_VER)
+	/* --- win32 type paths --- */
+	{ "\\usr",           "usr"  },
+	{ "\\usr\\",         "usr"  },
+	{ "\\usr\\\\",       "usr"  },
+	{ "\\usr\\lib",      "lib"  },
+	{ "usr\\lib",        "lib"  },
+	{ "usr\\lib\\\\\\",  "lib"  },
+	{ "C:/usr",          "usr"  },
+	{ "C:/usr",          "usr"  },
+	{ "C:/usr/",         "usr"  },
+	{ "C:/usr//",        "usr"  },
+	{ "C:/usr/lib",      "lib"  },
+	{ "C:usr/lib",       "lib"  },
+	{ "C:usr/lib///",    "lib"  },
+	{ "C:",              "."    },
+	{ "C:a",             "a"    },
+	{ "C:/",             "/"    },
+	{ "C:///",           "/"    },
+	{ "\\",              "\\", "/" },
+	{ "\\\\",            "\\", "/" },
+	{ "\\\\\\",          "\\", "/" },
+#endif
+	{ NULL,              NULL   }
+};
+
+static struct test_data dirname_data[] = {
+	/* --- POSIX type paths --- */
+	{ NULL,              "."      },
+	{ "",                "."      },
+	{ ".",               "."      },
+	{ "..",              "."      },
+	{ "/",               "/"      },
+	{ "//",              "/", "//" },
+	{ "///",             "/", "//" },
+	{ "////",            "/", "//" },
+	{ "usr",             "."      },
+	{ "/usr",            "/"      },
+	{ "/usr/",           "/"      },
+	{ "/usr//",          "/"      },
+	{ "/usr/lib",        "/usr"   },
+	{ "usr/lib",         "usr"    },
+	{ "usr/lib///",      "usr"    },
+
+#if defined(__MINGW32__) || defined(_MSC_VER)
+	/* --- win32 type paths --- */
+	{ "\\",              "\\"     },
+	{ "\\\\",            "\\\\"   },
+	{ "\\usr",           "\\"     },
+	{ "\\usr\\",         "\\"     },
+	{ "\\usr\\\\",       "\\"     },
+	{ "\\usr\\lib",      "\\usr"  },
+	{ "usr\\lib",        "usr"    },
+	{ "usr\\lib\\\\\\",  "usr"    },
+	{ "C:a",             "C:."    },
+	{ "C:/",             "C:/"    },
+	{ "C:///",           "C:/"    },
+	{ "C:/usr",          "C:/"    },
+	{ "C:/usr/",         "C:/"    },
+	{ "C:/usr//",        "C:/"    },
+	{ "C:/usr/lib",      "C:/usr" },
+	{ "C:usr/lib",       "C:usr"  },
+	{ "C:usr/lib///",    "C:usr"  },
+	{ "\\\\\\",          "\\"     },
+	{ "\\\\\\\\",        "\\"     },
+	{ "C:",              "C:.", "." },
+#endif
+	{ NULL,              NULL     }
+};
+
 int main(int argc, char **argv)
 {
 	if (argc == 3 && !strcmp(argv[1], "normalize_path_copy")) {
@@ -133,6 +257,12 @@ int main(int argc, char **argv)
 		return 0;
 	}
 
+	if (argc == 2 && !strcmp(argv[1], "basename"))
+		return test_function(basename_data, basename, argv[1]);
+
+	if (argc == 2 && !strcmp(argv[1], "dirname"))
+		return test_function(dirname_data, dirname, argv[1]);
+
 	fprintf(stderr, "%s: unknown function name: %s\n", argv[0],
 		argv[1] ? argv[1] : "(there was none)");
 	return 1;