Merge branch 'ab/mktag'

"git mktag" validates its input using its own rules before writing
a tag object---it has been updated to share the logic with "git
fsck".

* ab/mktag: (23 commits)
  mktag: add a --[no-]strict option
  mktag: mark strings for translation
  mktag: convert to parse-options
  mktag: allow omitting the header/body \n separator
  mktag: allow turning off fsck.extraHeaderEntry
  fsck: make fsck_config() re-usable
  mktag: use fsck instead of custom verify_tag()
  mktag: use puts(str) instead of printf("%s\n", str)
  mktag: remove redundant braces in one-line body "if"
  mktag: use default strbuf_read() hint
  mktag tests: test verify_object() with replaced objects
  mktag tests: improve verify_object() test coverage
  mktag tests: test "hash-object" compatibility
  mktag tests: stress test whitespace handling
  mktag tests: run "fsck" after creating "mytag"
  mktag tests: don't create "mytag" twice
  mktag tests: don't redirect stderr to a file needlessly
  mktag tests: remove needless SHA-1 hardcoding
  mktag tests: use "test_commit" helper
  mktag tests: don't needlessly use a subshell
  ...

2 files changed, 84 insertions, 171 deletions

diff --git a/builtin/fsck.c b/builtin/fsck.c
index fbf26cafcf..821e7798c7 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -73,25 +73,7 @@ static const char *printable_type(const struct object_id *oid,
 
 static int fsck_config(const char *var, const char *value, void *cb)
 {
-	if (strcmp(var, "fsck.skiplist") == 0) {
-		const char *path;
-		struct strbuf sb = STRBUF_INIT;
-
-		if (git_config_pathname(&path, var, value))
-			return 1;
-		strbuf_addf(&sb, "skiplist=%s", path);
-		free((char *)path);
-		fsck_set_msg_types(&fsck_obj_options, sb.buf);
-		strbuf_release(&sb);
-		return 0;
-	}
-
-	if (skip_prefix(var, "fsck.", &var)) {
-		fsck_set_msg_type(&fsck_obj_options, var, value);
-		return 0;
-	}
-
-	return git_default_config(var, value, cb);
+	return fsck_config_internal(var, value, cb, &fsck_obj_options);
 }
 
 static int objerror(struct object *obj, const char *err)
diff --git a/builtin/mktag.c b/builtin/mktag.c
index 4982d3a93e..41a399a69e 100644
--- a/builtin/mktag.c
+++ b/builtin/mktag.c
@@ -1,179 +1,110 @@
 #include "builtin.h"
+#include "parse-options.h"
 #include "tag.h"
 #include "replace-object.h"
 #include "object-store.h"
+#include "fsck.h"
+#include "config.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 char const * const builtin_mktag_usage[] = {
+	N_("git mktag"),
+	NULL
+};
+static int option_strict = 1;
+
+static struct fsck_options fsck_options = FSCK_OPTIONS_STRICT;
+
+static int mktag_config(const char *var, const char *value, void *cb)
 {
-	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);
+	return fsck_config_internal(var, value, cb, &fsck_options);
+}
+
+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)
+{
+	switch (msg_type) {
+	case FSCK_WARN:
+		if (!option_strict) {
+			fprintf_ln(stderr, _("warning: tag input does not pass fsck: %s"), message);
+			return 0;
+
 		}
-		free(buffer);
+		/* fallthrough */
+	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));
-	}
+	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);
 
-	/* 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));
-
-	/* The actual stuff afterwards we don't care about.. */
-	return 0;
+	return ret;
 }
 
 int cmd_mktag(int argc, const char **argv, const char *prefix)
 {
+	static struct option builtin_mktag_options[] = {
+		OPT_BOOL(0, "strict", &option_strict,
+			 N_("enable more strict checking")),
+		OPT_END(),
+	};
 	struct strbuf buf = STRBUF_INIT;
+	struct object_id tagged_oid;
+	int tagged_type;
 	struct object_id result;
 
-	if (argc != 1)
-		usage("git mktag");
+	argc = parse_options(argc, argv, NULL,
+			     builtin_mktag_options,
+			     builtin_mktag_usage, 0);
 
-	if (strbuf_read(&buf, 0, 4096) < 0) {
-		die_errno("could not read from stdin");
-	}
+	if (strbuf_read(&buf, 0, 0) < 0)
+		die_errno(_("could not read from stdin"));
+
+	fsck_options.error_func = mktag_fsck_error_func;
+	fsck_set_msg_type(&fsck_options, "extraheaderentry", "warn");
+	/* config might set fsck.extraHeaderEntry=* again */
+	git_config(mktag_config, NULL);
+	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"));
 
-	/* 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");
+	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");
+		die(_("unable to write tag file"));
 
 	strbuf_release(&buf);
-	printf("%s\n", oid_to_hex(&result));
+	puts(oid_to_hex(&result));
 	return 0;
 }