mktag: use fsck instead of custom verify_tag()

Change the validation logic in "mktag" to use fsck's fsck_tag()
instead of its own custom parser. Curiously the logic for both dates
back to the same commit[1]. Let's unify them so we're not maintaining
two sets functions to verify that a tag is OK.

The behavior of fsck_tag() and the old "mktag" code being removed here
is different in few aspects.

I think it makes sense to remove some of those checks, namely:

 A. fsck only cares that the timezone matches [-+][0-9]{4}. The mktag
    code disallowed values larger than 1400.

    Yes there's currently no timezone with a greater offset[2], but
    since we allow any number of non-offical timezones (e.g. +1234)
    passing this through seems fine. Git also won't break in the
    future if e.g. French Polynesia decides it needs to outdo the Line
    Islands when it comes to timezone extravagance.

 B. fsck allows missing author names such as "tagger <email>", mktag
    wouldn't, but would allow e.g. "tagger [2 spaces] <email>" (but
    not "tagger [1 space] <email>"). Now we allow all of these.

 C. Like B, but "mktag" disallowed spaces in the <email> part, fsck
    allows it.

In some ways fsck_tag() is stricter than "mktag" was, namely:

 D. fsck disallows zero-padded dates, but mktag didn't care. So
    e.g. the timestamp "0000000000 +0000" produces an error now. A
    test in "t1006-cat-file.sh" relied on this, it's been changed to
    use "hash-object" (without fsck) instead.

There was one check I deemed worth keeping by porting it over to
fsck_tag():

 E. "mktag" did not allow any custom headers, and by extension (as an
    empty commit is allowed) also forbade an extra stray trailing
    newline after the headers it knew about.

    Add a new check in the "ignore" category to fsck and use it. This
    somewhat abuses the facility added in efaba7cc77f (fsck:
    optionally ignore specific fsck issues completely, 2015-06-22).

    This is somewhat of hack, but probably the least invasive change
    we can make here. The fsck command will shuffle these categories
    around, e.g. under --strict the "info" becomes a "warn" and "warn"
    becomes "error". Existing users of fsck's (and others,
    e.g. index-pack) --strict option rely on this.

    So we need to put something into a category that'll be ignored by
    all existing users of the API. Pretending that
    fsck.extraHeaderEntry=error ("ignore" by default) was set serves
    to do this for us.

1. ec4465adb38 (Add "tag" objects that can be used to sign other
   objects., 2005-04-25)

2. https://en.wikipedia.org/wiki/List_of_UTC_time_offsets

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 50 insertions, 146 deletions

diff --git a/builtin/mktag.c b/builtin/mktag.c
index d89a3c201d..4dd35bc79e 100644
--- a/builtin/mktag.c
+++ b/builtin/mktag.c
@@ -2,160 +2,60 @@
 #include "tag.h"
 #include "replace-object.h"
 #include "object-store.h"
+#include "fsck.h"
 
-/*
- * A signature file has a very simple fixed format: four lines
- * of "object <sha1>" + "type <typename>" + "tag <tagname>" +
- * "tagger <committer>", followed by a blank line, a free-form tag
- * message and a signature block that git itself doesn't care about,
- * but that can be verified with gpg or similar.
- *
- * The first four lines are guaranteed to be at least 83 bytes:
- * "object <sha1>\n" is 48 bytes, "type tag\n" at 9 bytes is the
- * shortest possible type-line, "tag .\n" at 6 bytes is the shortest
- * single-character-tag line, and "tagger . <> 0 +0000\n" at 20 bytes is
- * the shortest possible tagger-line.
- */
-
-/*
- * We refuse to tag something we can't verify. Just because.
- */
-static int verify_object(const struct object_id *oid, const char *expected_type)
+static int mktag_fsck_error_func(struct fsck_options *o,
+				 const struct object_id *oid,
+				 enum object_type object_type,
+				 int msg_type, const char *message)
 {
-	int ret = -1;
-	enum object_type type;
-	unsigned long size;
-	void *buffer = read_object_file(oid, &type, &size);
-	const struct object_id *repl = lookup_replace_object(the_repository, oid);
-
-	if (buffer) {
-		if (type == type_from_string(expected_type)) {
-			ret = check_object_signature(the_repository, repl,
-						     buffer, size,
-						     expected_type);
-		}
-		free(buffer);
+	switch (msg_type) {
+	case FSCK_WARN:
+	case FSCK_ERROR:
+		/*
+		 * We treat both warnings and errors as errors, things
+		 * like missing "tagger" lines are "only" warnings
+		 * under fsck, we've always considered them an error.
+		 */
+		fprintf_ln(stderr, "error: tag input does not pass fsck: %s", message);
+		return 1;
+	default:
+		BUG("%d (FSCK_IGNORE?) should never trigger this callback",
+		    msg_type);
 	}
-	return ret;
 }
 
-static int verify_tag(char *buffer, unsigned long size)
+static int verify_object_in_tag(struct object_id *tagged_oid, int *tagged_type)
 {
-	int typelen;
-	char type[20];
-	struct object_id oid;
-	const char *object, *type_line, *tag_line, *tagger_line, *lb, *rb, *p;
-	size_t len;
-
-	if (size < 84)
-		return error("wanna fool me ? you obviously got the size wrong !");
-
-	buffer[size] = 0;
-
-	/* Verify object line */
-	object = buffer;
-	if (memcmp(object, "object ", 7))
-		return error("char%d: does not start with \"object \"", 0);
-
-	if (parse_oid_hex(object + 7, &oid, &p))
-		return error("char%d: could not get SHA1 hash", 7);
-
-	/* Verify type line */
-	type_line = p + 1;
-	if (memcmp(type_line - 1, "\ntype ", 6))
-		return error("char%d: could not find \"\\ntype \"", 47);
-
-	/* Verify tag-line */
-	tag_line = strchr(type_line, '\n');
-	if (!tag_line)
-		return error("char%"PRIuMAX": could not find next \"\\n\"",
-				(uintmax_t) (type_line - buffer));
-	tag_line++;
-	if (memcmp(tag_line, "tag ", 4) || tag_line[4] == '\n')
-		return error("char%"PRIuMAX": no \"tag \" found",
-				(uintmax_t) (tag_line - buffer));
-
-	/* Get the actual type */
-	typelen = tag_line - type_line - strlen("type \n");
-	if (typelen >= sizeof(type))
-		return error("char%"PRIuMAX": type too long",
-				(uintmax_t) (type_line+5 - buffer));
-
-	memcpy(type, type_line+5, typelen);
-	type[typelen] = 0;
-
-	/* Verify that the object matches */
-	if (verify_object(&oid, type))
-		return error("char%d: could not verify object %s", 7, oid_to_hex(&oid));
-
-	/* Verify the tag-name: we don't allow control characters or spaces in it */
-	tag_line += 4;
-	for (;;) {
-		unsigned char c = *tag_line++;
-		if (c == '\n')
-			break;
-		if (c > ' ')
-			continue;
-		return error("char%"PRIuMAX": could not verify tag name",
-				(uintmax_t) (tag_line - buffer));
-	}
-
-	/* Verify the tagger line */
-	tagger_line = tag_line;
-
-	if (memcmp(tagger_line, "tagger ", 7))
-		return error("char%"PRIuMAX": could not find \"tagger \"",
-			(uintmax_t) (tagger_line - buffer));
-
-	/*
-	 * Check for correct form for name and email
-	 * i.e. " <" followed by "> " on _this_ line
-	 * No angle brackets within the name or email address fields.
-	 * No spaces within the email address field.
-	 */
-	tagger_line += 7;
-	if (!(lb = strstr(tagger_line, " <")) || !(rb = strstr(lb+2, "> ")) ||
-		strpbrk(tagger_line, "<>\n") != lb+1 ||
-		strpbrk(lb+2, "><\n ") != rb)
-		return error("char%"PRIuMAX": malformed tagger field",
-			(uintmax_t) (tagger_line - buffer));
-
-	/* Check for author name, at least one character, space is acceptable */
-	if (lb == tagger_line)
-		return error("char%"PRIuMAX": missing tagger name",
-			(uintmax_t) (tagger_line - buffer));
-
-	/* timestamp, 1 or more digits followed by space */
-	tagger_line = rb + 2;
-	if (!(len = strspn(tagger_line, "0123456789")))
-		return error("char%"PRIuMAX": missing tag timestamp",
-			(uintmax_t) (tagger_line - buffer));
-	tagger_line += len;
-	if (*tagger_line != ' ')
-		return error("char%"PRIuMAX": malformed tag timestamp",
-			(uintmax_t) (tagger_line - buffer));
-	tagger_line++;
-
-	/* timezone, 5 digits [+-]hhmm, max. 1400 */
-	if (!((tagger_line[0] == '+' || tagger_line[0] == '-') &&
-	      strspn(tagger_line+1, "0123456789") == 4 &&
-	      tagger_line[5] == '\n' && atoi(tagger_line+1) <= 1400))
-		return error("char%"PRIuMAX": malformed tag timezone",
-			(uintmax_t) (tagger_line - buffer));
-	tagger_line += 6;
-
-	/* Verify the blank line separating the header from the body */
-	if (*tagger_line != '\n')
-		return error("char%"PRIuMAX": trailing garbage in tag header",
-			(uintmax_t) (tagger_line - buffer));
+	int ret;
+	enum object_type type;
+	unsigned long size;
+	void *buffer;
+	const struct object_id *repl;
+
+	buffer = read_object_file(tagged_oid, &type, &size);
+	if (!buffer)
+		die("could not read tagged object '%s'",
+		    oid_to_hex(tagged_oid));
+	if (type != *tagged_type)
+		die("object '%s' tagged as '%s', but is a '%s' type",
+		    oid_to_hex(tagged_oid),
+		    type_name(*tagged_type), type_name(type));
+
+	repl = lookup_replace_object(the_repository, tagged_oid);
+	ret = check_object_signature(the_repository, repl,
+				     buffer, size, type_name(*tagged_type));
+	free(buffer);
 
-	/* The actual stuff afterwards we don't care about.. */
-	return 0;
+	return ret;
 }
 
 int cmd_mktag(int argc, const char **argv, const char *prefix)
 {
 	struct strbuf buf = STRBUF_INIT;
+	struct fsck_options fsck_options = FSCK_OPTIONS_STRICT;
+	struct object_id tagged_oid;
+	int tagged_type;
 	struct object_id result;
 
 	if (argc != 1)
@@ -164,10 +64,14 @@ int cmd_mktag(int argc, const char **argv, const char *prefix)
 	if (strbuf_read(&buf, 0, 0) < 0)
 		die_errno("could not read from stdin");
 
-	/* Verify it for some basic sanity: it needs to start with
-	   "object <sha1>\ntype\ntagger " */
-	if (verify_tag(buf.buf, buf.len) < 0)
-		die("invalid tag signature file");
+	fsck_options.error_func = mktag_fsck_error_func;
+	fsck_set_msg_type(&fsck_options, "extraheaderentry", "warn");
+	if (fsck_tag_standalone(NULL, buf.buf, buf.len, &fsck_options,
+				&tagged_oid, &tagged_type))
+		die("tag on stdin did not pass our strict fsck check");
+
+	if (verify_object_in_tag(&tagged_oid, &tagged_type))
+		die("tag on stdin did not refer to a valid object");
 
 	if (write_object_file(buf.buf, buf.len, tag_type, &result) < 0)
 		die("unable to write tag file");