Example #1
0
/*
 * We anonymize each component of a path individually,
 * so that paths a/b and a/c will share a common root.
 * The paths are cached via anonymize_mem so that repeated
 * lookups for "a" will yield the same value.
 */
static void anonymize_path(struct strbuf *out, const char *path,
			   struct hashmap *map,
			   void *(*generate)(const void *, size_t *))
{
	while (*path) {
		const char *end_of_component = strchrnul(path, '/');
		size_t len = end_of_component - path;
		const char *c = anonymize_mem(map, generate, path, &len);
		strbuf_add(out, c, len);
		path = end_of_component;
		if (*path)
			strbuf_addch(out, *path++);
	}
}
Example #2
0
/*
 * Our strategy here is to anonymize the names and email addresses,
 * but keep timestamps intact, as they influence things like traversal
 * order (and by themselves should not be too revealing).
 */
static void anonymize_ident_line(const char **beg, const char **end)
{
	static struct strbuf buffers[] = { STRBUF_INIT, STRBUF_INIT };
	static unsigned which_buffer;

	struct strbuf *out;
	struct ident_split split;
	const char *end_of_header;

	out = &buffers[which_buffer++];
	which_buffer %= ARRAY_SIZE(buffers);
	strbuf_reset(out);

	/* skip "committer", "author", "tagger", etc */
	end_of_header = strchr(*beg, ' ');
	if (!end_of_header)
		die("BUG: malformed line fed to anonymize_ident_line: %.*s",
		    (int)(*end - *beg), *beg);
	end_of_header++;
	strbuf_add(out, *beg, end_of_header - *beg);

	if (!split_ident_line(&split, end_of_header, *end - end_of_header) &&
	    split.date_begin) {
		const char *ident;
		size_t len;

		len = split.mail_end - split.name_begin;
		ident = anonymize_mem(&idents, anonymize_ident,
				      split.name_begin, &len);
		strbuf_add(out, ident, len);
		strbuf_addch(out, ' ');
		strbuf_add(out, split.date_begin, split.tz_end - split.date_begin);
	} else {
		strbuf_addstr(out, "Malformed Ident <*****@*****.**> 0 -0000");
	}

	*beg = out->buf;
	*end = out->buf + out->len;
}
Example #3
0
static void handle_tag(const char *name, struct tag *tag)
{
	unsigned long size;
	enum object_type type;
	char *buf;
	const char *tagger, *tagger_end, *message;
	size_t message_size = 0;
	struct object *tagged;
	int tagged_mark;
	struct commit *p;

	/* Trees have no identifier in fast-export output, thus we have no way
	 * to output tags of trees, tags of tags of trees, etc.  Simply omit
	 * such tags.
	 */
	tagged = tag->tagged;
	while (tagged->type == OBJ_TAG) {
		tagged = ((struct tag *)tagged)->tagged;
	}
	if (tagged->type == OBJ_TREE) {
		warning("Omitting tag %s,\nsince tags of trees (or tags of tags of trees, etc.) are not supported.",
			sha1_to_hex(tag->object.sha1));
		return;
	}

	buf = read_sha1_file(tag->object.sha1, &type, &size);
	if (!buf)
		die ("Could not read tag %s", sha1_to_hex(tag->object.sha1));
	message = memmem(buf, size, "\n\n", 2);
	if (message) {
		message += 2;
		message_size = strlen(message);
	}
	tagger = memmem(buf, message ? message - buf : size, "\ntagger ", 8);
	if (!tagger) {
		if (fake_missing_tagger)
			tagger = "tagger Unspecified Tagger "
				"<unspecified-tagger> 0 +0000";
		else
			tagger = "";
		tagger_end = tagger + strlen(tagger);
	} else {
		tagger++;
		tagger_end = strchrnul(tagger, '\n');
		if (anonymize)
			anonymize_ident_line(&tagger, &tagger_end);
	}

	if (anonymize) {
		name = anonymize_refname(name);
		if (message) {
			static struct hashmap tags;
			message = anonymize_mem(&tags, anonymize_tag,
						message, &message_size);
		}
	}

	/* handle signed tags */
	if (message) {
		const char *signature = strstr(message,
					       "\n-----BEGIN PGP SIGNATURE-----\n");
		if (signature)
			switch(signed_tag_mode) {
			case ABORT:
				die ("Encountered signed tag %s; use "
				     "--signed-tags=<mode> to handle it.",
				     sha1_to_hex(tag->object.sha1));
			case WARN:
				warning ("Exporting signed tag %s",
					 sha1_to_hex(tag->object.sha1));
				/* fallthru */
			case VERBATIM:
				break;
			case WARN_STRIP:
				warning ("Stripping signature from tag %s",
					 sha1_to_hex(tag->object.sha1));
				/* fallthru */
			case STRIP:
				message_size = signature + 1 - message;
				break;
			}
	}

	/* handle tag->tagged having been filtered out due to paths specified */
	tagged = tag->tagged;
	tagged_mark = get_object_mark(tagged);
	if (!tagged_mark) {
		switch(tag_of_filtered_mode) {
		case ABORT:
			die ("Tag %s tags unexported object; use "
			     "--tag-of-filtered-object=<mode> to handle it.",
			     sha1_to_hex(tag->object.sha1));
		case DROP:
			/* Ignore this tag altogether */
			return;
		case REWRITE:
			if (tagged->type != OBJ_COMMIT) {
				die ("Tag %s tags unexported %s!",
				     sha1_to_hex(tag->object.sha1),
				     typename(tagged->type));
			}
			p = (struct commit *)tagged;
			for (;;) {
				if (p->parents && p->parents->next)
					break;
				if (p->object.flags & UNINTERESTING)
					break;
				if (!(p->object.flags & TREESAME))
					break;
				if (!p->parents)
					die ("Can't find replacement commit for tag %s\n",
					     sha1_to_hex(tag->object.sha1));
				p = p->parents->item;
			}
			tagged_mark = get_object_mark(&p->object);
		}
	}
Example #4
0
static const unsigned char *anonymize_sha1(const unsigned char *sha1)
{
	static struct hashmap sha1s;
	size_t len = 20;
	return anonymize_mem(&sha1s, generate_fake_sha1, sha1, &len);
}
Example #5
0
static const unsigned char *anonymize_sha1(const struct object_id *oid)
{
	static struct hashmap sha1s;
	size_t len = GIT_SHA1_RAWSZ;
	return anonymize_mem(&sha1s, generate_fake_oid, oid, &len);
}