Re: [PATCH] Provide a dirname() function when NO_LIBGEN_H=YesPlease

[Ramsay Jones <ramsay@ramsayjones.plus.com>]

[-- Attachment #1: Type: text/plain, Size: 3186 bytes --]

Hi Johannes,

On 30/09/15 15:50, Johannes Schindelin wrote:
> When there is no `libgen.h` to our disposal, we miss the `dirname()`
> function.
> 
> So far, we only had one user of that function: credential-cache--daemon
> (which was only compiled when Unix sockets are available, anyway). But
> now we also have `builtin/am.c` as user, so we need it.

Yes, many moons ago (on my old 32-bit laptop) when I was still 'working'
with MinGW I noticed this same thing while looking into providing a win32
emulation of unix sockets. So, I had to look into this at the same time.
Since this didn't progress, I didn't mention the libgen issue.

Anyway, I still have a 'test-libgen.c' file (attached) from back then that
contains some tests. I don't quite recall what the final state of this
code was, but it was intended to test _existing_ libgen implementations
as well as provide a 'git' version which would work on MinGW, cygwin and
linux. Note that some of the existing implementations didn't all agree on
what the tests should report! I don't remember if I looked at the POSIX
spec or not.

So, I don't know how useful it will be - if nothing else, there are some
tests! :-D

HTH

Ramsay Jones


> 
> Since `dirname()` is a sibling of `basename()`, we simply put our very
> own `gitdirname()` implementation next to `gitbasename()` and use it
> if `NO_LIBGEN_H` has been set.
> 
> Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
> ---
> 
> 	I stumbled over the compile warning when upgrading Git for Windows
> 	to 2.6.0. There was a left-over NO_LIBGEN_H=YesPlease (which we
> 	no longer need in Git for Windows 2.x), but it did point to the
> 	fact that we use `dirname()` in builtin/am.c now, so we better
> 	have a fall-back implementation for platforms without libgen.h.
> 
> 	I tested this implementation a bit, but I still would appreciate
> 	a few eye-balls to go over it.
> 
>  compat/basename.c | 26 ++++++++++++++++++++++++++
>  git-compat-util.h |  2 ++
>  2 files changed, 28 insertions(+)
> 
> diff --git a/compat/basename.c b/compat/basename.c
> index d8f8a3c..10dba38 100644
> --- a/compat/basename.c
> +++ b/compat/basename.c
> @@ -13,3 +13,29 @@ char *gitbasename (char *path)
>  	}
>  	return (char *)base;
>  }
> +
> +char *gitdirname(char *path)
> +{
> +	char *p = path, *slash, c;
> +
> +	/* Skip over the disk name in MSDOS pathnames. */
> +	if (has_dos_drive_prefix(p))
> +		p += 2;
> +	/* POSIX.1-2001 says dirname("/") should return "/" */
> +	slash = is_dir_sep(*p) ? ++p : NULL;
> +	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)
> +		return ".";
> +	*slash = '\0';
> +	return path;
> +}
> diff --git a/git-compat-util.h b/git-compat-util.h
> index f649e81..8b01aa5 100644
> --- a/git-compat-util.h
> +++ b/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
> 

[-- Attachment #2: test-libgen.c --]
[-- Type: text/x-csrc, Size: 6506 bytes --]

#include <stdio.h>
#include <string.h>
#include <ctype.h>
#ifndef NO_LIBGEN_H
# include <libgen.h>
#endif

struct test_data {
	char *from;  /* input:  transform from this ... */
	char *to;    /* output: ... to this.            */
};

#ifdef NO_LIBGEN_H

#if defined(__MINGW32__) || defined(_MSC_VER)
#define has_dos_drive_prefix(path) (isalpha(*(path)) && (path)[1] == ':')
#define is_dir_sep(c) ((c) == '/' || (c) == '\\')
#else
#define has_dos_drive_prefix(path) 0
#define is_dir_sep(c) ((c) == '/')
#endif

#define basename gitbasename
#define dirname gitdirname

char *gitbasename (char *path)
{
	char *p;

	if (!path || !*path)
		return ".";
	/* skip drive designator, if any */
	if (has_dos_drive_prefix(path))
		path += 2;
	if (!*path)
		return ".";
	/* trim trailing directory separators */
	p = path + strlen(path) - 1;
	while (is_dir_sep(*p)) {
		if (p == path)
			return path;
		*p-- = '\0';
	}
	/* find begining of last path component */
	while (p >= path && !is_dir_sep(*p))
		p--;
	return p + 1;
}

char *gitdirname(char *path)
{
	char *p, *start;

	if (!path || !*path)
		return ".";
	start = path;
	/* skip drive designator, if any */
	if (has_dos_drive_prefix(path))
		start += 2;
	/* check for // */
	if (strcmp(start, "//") == 0)
		return path;
	/* check for \\ */
	if (is_dir_sep('\\') && strcmp(start, "\\\\") == 0)
		return path;
	/* trim trailing directory separators */
	p = path + strlen(path) - 1;
	while (is_dir_sep(*p)) {
		if (p == start)
			return path;
		*p-- = '\0';
	}
	/* find begining of last path component */
	while (p >= start && !is_dir_sep(*p))
		p--;
	/* terminate dirname */
	if (p < start) {
		p = start;
		*p++ = '.';
	} else if (p == start)
		p++;
	*p = '\0';
	return path;
}

#endif

static int test_basename(void)
{
	static struct test_data t[] = {

		/* --- POSIX type paths --- */
		{ NULL,              "."    },
		{ "",                "."    },
		{ ".",               "."    },
		{ "..",              ".."   },
		{ "/",               "/"    },
#if defined(__CYGWIN__) && !defined(NO_LIBGEN_H)
		{ "//",              "//"   },
		{ "///",             "//"   },
		{ "////",            "//"   },
#else
		{ "//",              "/"    },
		{ "///",             "/"    },
		{ "////",            "/"    },
#endif
		{ "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:///",           "/"    },
#if defined(NO_LIBGEN_H)
		{ "\\",              "\\"   },
		{ "\\\\",            "\\"   },
		{ "\\\\\\",          "\\"   },
#else

		/* win32 platform variations: */
#if defined(__MINGW32__)
		{ "\\",              "/"    },
		{ "\\\\",            "/"    },
		{ "\\\\\\",          "/"    },
#endif

#if defined(_MSC_VER)
		{ "\\",              "\\"   },
		{ "\\\\",            "\\"   },
		{ "\\\\\\",          "\\"   },
#endif

#endif
#endif
		{ NULL,              "."    }
	};
	static char input[1024];
	char *from, *to;
	int i, failed = 0;

	for (i = 0; i < sizeof(t)/sizeof(t[0]); i++) {
		from = NULL;
		if (t[i].from) {
			strcpy(input, t[i].from);
			from = input;
		}
		to = basename(from);
		if (strcmp(to, t[i].to) != 0) {
			fprintf(stderr, "FAIL: basename(%s) => '%s' != '%s'\n",
				t[i].from, to, t[i].to);
			failed++;
		}
	}
	return failed != 0;
}

static int test_dirname(void)
{
	static struct test_data t[] = {

		/* --- POSIX type paths --- */
		{ NULL,              "."      },
		{ "",                "."      },
		{ ".",               "."      },
		{ "..",              "."      },
		{ "/",               "/"      },
		{ "//",              "//"     },
#if defined(__CYGWIN__) && !defined(NO_LIBGEN_H)
		{ "///",             "//"     },
		{ "////",            "//"     },
#else
		{ "///",             "/"      },
		{ "////",            "/"      },
#endif
		{ "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"  },
		{ "\\\\\\",          "\\"     },
		{ "\\\\\\\\",        "\\"     },
#if defined(NO_LIBGEN_H)
		{ "C:",              "C:."    },
#else

		/* win32 platform variations: */
#if defined(__MINGW32__)
		/* the following is clearly wrong ... */
		{ "C:",              "."      },
#endif

#if defined(_MSC_VER)
		{ "C:",              "C:."    },
#endif

#endif
#endif
		{ NULL,              "."      }
	};
	static char input[1024];
	char *from, *to;
	int i, failed = 0;

	for (i = 0; i < sizeof(t)/sizeof(t[0]); i++) {
		from = NULL;
		if (t[i].from) {
			strcpy(input, t[i].from);
			from = input;
		}
		to = dirname(from);
		if (strcmp(to, t[i].to) != 0) {
			fprintf(stderr, "FAIL: dirname(%s) => '%s' != '%s'\n",
				t[i].from, to, t[i].to);
			failed++;
		}
	}
	return failed != 0;
}

int main(int argc, char **argv)
{
	if (argc == 2 && !strcmp(argv[1], "basename"))
		return test_basename();

	if (argc == 2 && !strcmp(argv[1], "dirname"))
		return test_dirname();

	fprintf(stderr, "%s: unknown function name: %s\n", argv[0],
		argv[1] ? argv[1] : "(there was none)");
	return 1;
}