Merge branch 'en/fast-import-looser-date'

Some repositories in the wild have commits that record nonsense
committer timezone (e.g. rails.git); "git fast-import" learned an
option to pass these nonsense timestamps intact to allow recreating
existing repositories as-is.

* en/fast-import-looser-date:
  fast-import: add new --date-format=raw-permissive format

3 files changed, 57 insertions, 5 deletions

diff --git a/Documentation/git-fast-import.txt b/Documentation/git-fast-import.txt
index 77c6b3d001..7d9aad2a7e 100644
--- a/Documentation/git-fast-import.txt
+++ b/Documentation/git-fast-import.txt
@@ -293,7 +293,14 @@ by users who are located in the same location and time zone.  In this
 case a reasonable offset from UTC could be assumed.
 +
 Unlike the `rfc2822` format, this format is very strict.  Any
-variation in formatting will cause fast-import to reject the value.
+variation in formatting will cause fast-import to reject the value,
+and some sanity checks on the numeric values may also be performed.
+
+`raw-permissive`::
+	This is the same as `raw` except that no sanity checks on
+	the numeric epoch and local offset are performed.  This can
+	be useful when trying to filter or import an existing history
+	with e.g. bogus timezone values.
 
 `rfc2822`::
 	This is the standard email format as described by RFC 2822.
diff --git a/fast-import.c b/fast-import.c
index c98970274c..0dfa14dc8c 100644
--- a/fast-import.c
+++ b/fast-import.c
@@ -139,6 +139,7 @@ struct hash_list {
 
 typedef enum {
 	WHENSPEC_RAW = 1,
+	WHENSPEC_RAW_PERMISSIVE,
 	WHENSPEC_RFC2822,
 	WHENSPEC_NOW
 } whenspec_type;
@@ -1911,7 +1912,7 @@ static int parse_data(struct strbuf *sb, uintmax_t limit, uintmax_t *len_res)
 	return 1;
 }
 
-static int validate_raw_date(const char *src, struct strbuf *result)
+static int validate_raw_date(const char *src, struct strbuf *result, int strict)
 {
 	const char *orig_src = src;
 	char *endp;
@@ -1920,7 +1921,11 @@ static int validate_raw_date(const char *src, struct strbuf *result)
 	errno = 0;
 
 	num = strtoul(src, &endp, 10);
-	/* NEEDSWORK: perhaps check for reasonable values? */
+	/*
+	 * NEEDSWORK: perhaps check for reasonable values? For example, we
+	 *            could error on values representing times more than a
+	 *            day in the future.
+	 */
 	if (errno || endp == src || *endp != ' ')
 		return -1;
 
@@ -1929,7 +1934,13 @@ static int validate_raw_date(const char *src, struct strbuf *result)
 		return -1;
 
 	num = strtoul(src + 1, &endp, 10);
-	if (errno || endp == src + 1 || *endp || 1400 < num)
+	/*
+	 * NEEDSWORK: check for brokenness other than num > 1400, such as
+	 *            (num % 100) >= 60, or ((num % 100) % 15) != 0 ?
+	 */
+	if (errno || endp == src + 1 || *endp || /* did not parse */
+	    (strict && (1400 < num))             /* parsed a broken timezone */
+	   )
 		return -1;
 
 	strbuf_addstr(result, orig_src);
@@ -1963,7 +1974,11 @@ static char *parse_ident(const char *buf)
 
 	switch (whenspec) {
 	case WHENSPEC_RAW:
-		if (validate_raw_date(ltgt, &ident) < 0)
+		if (validate_raw_date(ltgt, &ident, 1) < 0)
+			die("Invalid raw date \"%s\" in ident: %s", ltgt, buf);
+		break;
+	case WHENSPEC_RAW_PERMISSIVE:
+		if (validate_raw_date(ltgt, &ident, 0) < 0)
 			die("Invalid raw date \"%s\" in ident: %s", ltgt, buf);
 		break;
 	case WHENSPEC_RFC2822:
@@ -3258,6 +3273,8 @@ static void option_date_format(const char *fmt)
 {
 	if (!strcmp(fmt, "raw"))
 		whenspec = WHENSPEC_RAW;
+	else if (!strcmp(fmt, "raw-permissive"))
+		whenspec = WHENSPEC_RAW_PERMISSIVE;
 	else if (!strcmp(fmt, "rfc2822"))
 		whenspec = WHENSPEC_RFC2822;
 	else if (!strcmp(fmt, "now"))
diff --git a/t/t9300-fast-import.sh b/t/t9300-fast-import.sh
index 768257b29e..e151df81c0 100755
--- a/t/t9300-fast-import.sh
+++ b/t/t9300-fast-import.sh
@@ -410,6 +410,34 @@ test_expect_success 'B: accept empty committer' '
 	test -z "$out"
 '
 
+test_expect_success 'B: reject invalid timezone' '
+	cat >input <<-INPUT_END &&
+	commit refs/heads/invalid-timezone
+	committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1234567890 +051800
+	data <<COMMIT
+	empty commit
+	COMMIT
+	INPUT_END
+
+	test_when_finished "git update-ref -d refs/heads/invalid-timezone" &&
+	test_must_fail git fast-import <input
+'
+
+test_expect_success 'B: accept invalid timezone with raw-permissive' '
+	cat >input <<-INPUT_END &&
+	commit refs/heads/invalid-timezone
+	committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1234567890 +051800
+	data <<COMMIT
+	empty commit
+	COMMIT
+	INPUT_END
+
+	git init invalid-timezone &&
+	git -C invalid-timezone fast-import --date-format=raw-permissive <input &&
+	git -C invalid-timezone cat-file -p invalid-timezone >out &&
+	grep "1234567890 [+]051800" out
+'
+
 test_expect_success 'B: accept and fixup committer with no name' '
 	cat >input <<-INPUT_END &&
 	commit refs/heads/empty-committer-2