Revision f514ef9787f320287d7ba71f2965127b9d8b3832 authored by Jeff King on 19 August 2015, 18:12:37 UTC, committed by Junio C Hamano on 04 September 2015, 15:50:50 UTC
When unpack-trees wants to know whether a path will
overwrite anything in the working tree, we use lstat() to
see if there is anything there. But if we are going to write
"foo/bar", we can't just lstat("foo/bar"); we need to look
for leading prefixes (e.g., "foo"). So we use the lstat cache
to find the length of the leading prefix, and copy the
filename up to that length into a temporary buffer (since
the original name is const, we cannot just stick a NUL in
it).

The copy we make goes into a PATH_MAX-sized buffer, which
will overflow if the prefix is longer than PATH_MAX. How
this happens is a little tricky, since in theory PATH_MAX is
the biggest path we will have read from the filesystem. But
this can happen if:

  - the compiled-in PATH_MAX does not accurately reflect
    what the filesystem is capable of

  - the leading prefix is not _quite_ what is on disk; it
    contains the next element from the name we are checking.
    So if we want to write "aaa/bbb/ccc/ddd" and "aaa/bbb"
    exists, the prefix of interest is "aaa/bbb/ccc". If
    "aaa/bbb" approaches PATH_MAX, then "ccc" can overflow
    it.

So this can be triggered, but it's hard to do. In
particular, you cannot just "git clone" a bogus repo. The
verify_absent checks happen before unpack-trees writes
anything to the filesystem, so there are never any leading
prefixes during the initial checkout, and the bug doesn't
trigger. And by definition, these files are larger than
PATH_MAX, so writing them will fail, and clone will
complain (though it may write a partial path, which will
cause a subsequent "git checkout" to hit the bug).

We can fix it by creating the temporary path on the heap.
The extra malloc overhead is not important, as we are
already making at least one stat() call (and probably more
for the prefix discovery).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
1 parent fdf96a2
Raw File
help.c
#include "cache.h"
#include "builtin.h"
#include "exec_cmd.h"
#include "levenshtein.h"
#include "help.h"
#include "common-cmds.h"
#include "string-list.h"
#include "column.h"
#include "version.h"
#include "refs.h"

void add_cmdname(struct cmdnames *cmds, const char *name, int len)
{
	struct cmdname *ent = xmalloc(sizeof(*ent) + len + 1);

	ent->len = len;
	memcpy(ent->name, name, len);
	ent->name[len] = 0;

	ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc);
	cmds->names[cmds->cnt++] = ent;
}

static void clean_cmdnames(struct cmdnames *cmds)
{
	int i;
	for (i = 0; i < cmds->cnt; ++i)
		free(cmds->names[i]);
	free(cmds->names);
	cmds->cnt = 0;
	cmds->alloc = 0;
}

static int cmdname_compare(const void *a_, const void *b_)
{
	struct cmdname *a = *(struct cmdname **)a_;
	struct cmdname *b = *(struct cmdname **)b_;
	return strcmp(a->name, b->name);
}

static void uniq(struct cmdnames *cmds)
{
	int i, j;

	if (!cmds->cnt)
		return;

	for (i = j = 1; i < cmds->cnt; i++) {
		if (!strcmp(cmds->names[i]->name, cmds->names[j-1]->name))
			free(cmds->names[i]);
		else
			cmds->names[j++] = cmds->names[i];
	}

	cmds->cnt = j;
}

void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
{
	int ci, cj, ei;
	int cmp;

	ci = cj = ei = 0;
	while (ci < cmds->cnt && ei < excludes->cnt) {
		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
		if (cmp < 0)
			cmds->names[cj++] = cmds->names[ci++];
		else if (cmp == 0) {
			ei++;
			free(cmds->names[ci++]);
		} else if (cmp > 0)
			ei++;
	}

	while (ci < cmds->cnt)
		cmds->names[cj++] = cmds->names[ci++];

	cmds->cnt = cj;
}

static void pretty_print_cmdnames(struct cmdnames *cmds, unsigned int colopts)
{
	struct string_list list = STRING_LIST_INIT_NODUP;
	struct column_options copts;
	int i;

	for (i = 0; i < cmds->cnt; i++)
		string_list_append(&list, cmds->names[i]->name);
	/*
	 * always enable column display, we only consult column.*
	 * about layout strategy and stuff
	 */
	colopts = (colopts & ~COL_ENABLE_MASK) | COL_ENABLED;
	memset(&copts, 0, sizeof(copts));
	copts.indent = "  ";
	copts.padding = 2;
	print_columns(&list, colopts, &copts);
	string_list_clear(&list, 0);
}

static int is_executable(const char *name)
{
	struct stat st;

	if (stat(name, &st) || /* stat, not lstat */
	    !S_ISREG(st.st_mode))
		return 0;

#if defined(GIT_WINDOWS_NATIVE)
{	/* cannot trust the executable bit, peek into the file instead */
	char buf[3] = { 0 };
	int n;
	int fd = open(name, O_RDONLY);
	st.st_mode &= ~S_IXUSR;
	if (fd >= 0) {
		n = read(fd, buf, 2);
		if (n == 2)
			/* DOS executables start with "MZ" */
			if (!strcmp(buf, "#!") || !strcmp(buf, "MZ"))
				st.st_mode |= S_IXUSR;
		close(fd);
	}
}
#endif
	return st.st_mode & S_IXUSR;
}

static void list_commands_in_dir(struct cmdnames *cmds,
					 const char *path,
					 const char *prefix)
{
	DIR *dir = opendir(path);
	struct dirent *de;
	struct strbuf buf = STRBUF_INIT;
	int len;

	if (!dir)
		return;
	if (!prefix)
		prefix = "git-";

	strbuf_addf(&buf, "%s/", path);
	len = buf.len;

	while ((de = readdir(dir)) != NULL) {
		const char *ent;
		size_t entlen;

		if (!skip_prefix(de->d_name, prefix, &ent))
			continue;

		strbuf_setlen(&buf, len);
		strbuf_addstr(&buf, de->d_name);
		if (!is_executable(buf.buf))
			continue;

		entlen = strlen(ent);
		strip_suffix(ent, ".exe", &entlen);

		add_cmdname(cmds, ent, entlen);
	}
	closedir(dir);
	strbuf_release(&buf);
}

void load_command_list(const char *prefix,
		struct cmdnames *main_cmds,
		struct cmdnames *other_cmds)
{
	const char *env_path = getenv("PATH");
	const char *exec_path = git_exec_path();

	if (exec_path) {
		list_commands_in_dir(main_cmds, exec_path, prefix);
		qsort(main_cmds->names, main_cmds->cnt,
		      sizeof(*main_cmds->names), cmdname_compare);
		uniq(main_cmds);
	}

	if (env_path) {
		char *paths, *path, *colon;
		path = paths = xstrdup(env_path);
		while (1) {
			if ((colon = strchr(path, PATH_SEP)))
				*colon = 0;
			if (!exec_path || strcmp(path, exec_path))
				list_commands_in_dir(other_cmds, path, prefix);

			if (!colon)
				break;
			path = colon + 1;
		}
		free(paths);

		qsort(other_cmds->names, other_cmds->cnt,
		      sizeof(*other_cmds->names), cmdname_compare);
		uniq(other_cmds);
	}
	exclude_cmds(other_cmds, main_cmds);
}

void list_commands(unsigned int colopts,
		   struct cmdnames *main_cmds, struct cmdnames *other_cmds)
{
	if (main_cmds->cnt) {
		const char *exec_path = git_exec_path();
		printf_ln(_("available git commands in '%s'"), exec_path);
		putchar('\n');
		pretty_print_cmdnames(main_cmds, colopts);
		putchar('\n');
	}

	if (other_cmds->cnt) {
		printf_ln(_("git commands available from elsewhere on your $PATH"));
		putchar('\n');
		pretty_print_cmdnames(other_cmds, colopts);
		putchar('\n');
	}
}

void list_common_cmds_help(void)
{
	int i, longest = 0;

	for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
		if (longest < strlen(common_cmds[i].name))
			longest = strlen(common_cmds[i].name);
	}

	puts(_("The most commonly used git commands are:"));
	for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
		printf("   %s   ", common_cmds[i].name);
		mput_char(' ', longest - strlen(common_cmds[i].name));
		puts(_(common_cmds[i].help));
	}
}

int is_in_cmdlist(struct cmdnames *c, const char *s)
{
	int i;
	for (i = 0; i < c->cnt; i++)
		if (!strcmp(s, c->names[i]->name))
			return 1;
	return 0;
}

static int autocorrect;
static struct cmdnames aliases;

static int git_unknown_cmd_config(const char *var, const char *value, void *cb)
{
	const char *p;

	if (!strcmp(var, "help.autocorrect"))
		autocorrect = git_config_int(var,value);
	/* Also use aliases for command lookup */
	if (skip_prefix(var, "alias.", &p))
		add_cmdname(&aliases, p, strlen(p));

	return git_default_config(var, value, cb);
}

static int levenshtein_compare(const void *p1, const void *p2)
{
	const struct cmdname *const *c1 = p1, *const *c2 = p2;
	const char *s1 = (*c1)->name, *s2 = (*c2)->name;
	int l1 = (*c1)->len;
	int l2 = (*c2)->len;
	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
}

static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
{
	int i;
	ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);

	for (i = 0; i < old->cnt; i++)
		cmds->names[cmds->cnt++] = old->names[i];
	free(old->names);
	old->cnt = 0;
	old->names = NULL;
}

/* An empirically derived magic number */
#define SIMILARITY_FLOOR 7
#define SIMILAR_ENOUGH(x) ((x) < SIMILARITY_FLOOR)

static const char bad_interpreter_advice[] =
	N_("'%s' appears to be a git command, but we were not\n"
	"able to execute it. Maybe git-%s is broken?");

const char *help_unknown_cmd(const char *cmd)
{
	int i, n, best_similarity = 0;
	struct cmdnames main_cmds, other_cmds;

	memset(&main_cmds, 0, sizeof(main_cmds));
	memset(&other_cmds, 0, sizeof(other_cmds));
	memset(&aliases, 0, sizeof(aliases));

	git_config(git_unknown_cmd_config, NULL);

	load_command_list("git-", &main_cmds, &other_cmds);

	add_cmd_list(&main_cmds, &aliases);
	add_cmd_list(&main_cmds, &other_cmds);
	qsort(main_cmds.names, main_cmds.cnt,
	      sizeof(*main_cmds.names), cmdname_compare);
	uniq(&main_cmds);

	/* This abuses cmdname->len for levenshtein distance */
	for (i = 0, n = 0; i < main_cmds.cnt; i++) {
		int cmp = 0; /* avoid compiler stupidity */
		const char *candidate = main_cmds.names[i]->name;

		/*
		 * An exact match means we have the command, but
		 * for some reason exec'ing it gave us ENOENT; probably
		 * it's a bad interpreter in the #! line.
		 */
		if (!strcmp(candidate, cmd))
			die(_(bad_interpreter_advice), cmd, cmd);

		/* Does the candidate appear in common_cmds list? */
		while (n < ARRAY_SIZE(common_cmds) &&
		       (cmp = strcmp(common_cmds[n].name, candidate)) < 0)
			n++;
		if ((n < ARRAY_SIZE(common_cmds)) && !cmp) {
			/* Yes, this is one of the common commands */
			n++; /* use the entry from common_cmds[] */
			if (starts_with(candidate, cmd)) {
				/* Give prefix match a very good score */
				main_cmds.names[i]->len = 0;
				continue;
			}
		}

		main_cmds.names[i]->len =
			levenshtein(cmd, candidate, 0, 2, 1, 3) + 1;
	}

	qsort(main_cmds.names, main_cmds.cnt,
	      sizeof(*main_cmds.names), levenshtein_compare);

	if (!main_cmds.cnt)
		die(_("Uh oh. Your system reports no Git commands at all."));

	/* skip and count prefix matches */
	for (n = 0; n < main_cmds.cnt && !main_cmds.names[n]->len; n++)
		; /* still counting */

	if (main_cmds.cnt <= n) {
		/* prefix matches with everything? that is too ambiguous */
		best_similarity = SIMILARITY_FLOOR + 1;
	} else {
		/* count all the most similar ones */
		for (best_similarity = main_cmds.names[n++]->len;
		     (n < main_cmds.cnt &&
		      best_similarity == main_cmds.names[n]->len);
		     n++)
			; /* still counting */
	}
	if (autocorrect && n == 1 && SIMILAR_ENOUGH(best_similarity)) {
		const char *assumed = main_cmds.names[0]->name;
		main_cmds.names[0] = NULL;
		clean_cmdnames(&main_cmds);
		fprintf_ln(stderr,
			   _("WARNING: You called a Git command named '%s', "
			     "which does not exist.\n"
			     "Continuing under the assumption that you meant '%s'"),
			cmd, assumed);
		if (autocorrect > 0) {
			fprintf_ln(stderr, _("in %0.1f seconds automatically..."),
				(float)autocorrect/10.0);
			poll(NULL, 0, autocorrect * 100);
		}
		return assumed;
	}

	fprintf_ln(stderr, _("git: '%s' is not a git command. See 'git --help'."), cmd);

	if (SIMILAR_ENOUGH(best_similarity)) {
		fprintf_ln(stderr,
			   Q_("\nDid you mean this?",
			      "\nDid you mean one of these?",
			   n));

		for (i = 0; i < n; i++)
			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
	}

	exit(1);
}

int cmd_version(int argc, const char **argv, const char *prefix)
{
	/*
	 * The format of this string should be kept stable for compatibility
	 * with external projects that rely on the output of "git version".
	 */
	printf("git version %s\n", git_version_string);
	return 0;
}

struct similar_ref_cb {
	const char *base_ref;
	struct string_list *similar_refs;
};

static int append_similar_ref(const char *refname, const unsigned char *sha1,
			      int flags, void *cb_data)
{
	struct similar_ref_cb *cb = (struct similar_ref_cb *)(cb_data);
	char *branch = strrchr(refname, '/') + 1;
	const char *remote;

	/* A remote branch of the same name is deemed similar */
	if (skip_prefix(refname, "refs/remotes/", &remote) &&
	    !strcmp(branch, cb->base_ref))
		string_list_append(cb->similar_refs, remote);
	return 0;
}

static struct string_list guess_refs(const char *ref)
{
	struct similar_ref_cb ref_cb;
	struct string_list similar_refs = STRING_LIST_INIT_NODUP;

	ref_cb.base_ref = ref;
	ref_cb.similar_refs = &similar_refs;
	for_each_ref(append_similar_ref, &ref_cb);
	return similar_refs;
}

void help_unknown_ref(const char *ref, const char *cmd, const char *error)
{
	int i;
	struct string_list suggested_refs = guess_refs(ref);

	fprintf_ln(stderr, _("%s: %s - %s"), cmd, ref, error);

	if (suggested_refs.nr > 0) {
		fprintf_ln(stderr,
			   Q_("\nDid you mean this?",
			      "\nDid you mean one of these?",
			      suggested_refs.nr));
		for (i = 0; i < suggested_refs.nr; i++)
			fprintf(stderr, "\t%s\n", suggested_refs.items[i].string);
	}

	string_list_clear(&suggested_refs, 0);
	exit(1);
}
back to top