parse_date(): allow ancient git-timestamp

The date-time parser parses out a human-readble datestring piece by
piece, so that it could even parse a string in a rather strange
notation like 'noon november 11, 2005', but restricts itself from
parsing strings in "<seconds since epoch> <timezone>" format only
for reasonably new timestamps (like 1974 or newer) with 10 or more
digits. This is to prevent a string like "20100917" from getting
interpreted as seconds since epoch (we want to treat it as September
17, 2010 instead) while doing so.

The same codepath is used to read back the timestamp that we have
already recorded in the headers of commit and tag objects; because
of this, such a commit with timestamp "0 +0000" cannot be rebased or
amended very easily.

Teach parse_date() codepath to special case a string of the form
"<digits> +<4-digits>" to work this issue around, but require that
there is no other cruft around the string when parsing a timestamp
of this format for safety.

Note that this has a slight backward incompatibility implications.

If somebody writes "git commit --date='20100917 +0900'" and wants it
to mean a timestamp in September 2010 in Japan, this change will
break such a use case.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/date.c b/date.c
index 896fbb48060c673b8dc2f2aa6ea3de3c1042fbd2..099ddbe7fc9ea1595be8797fb4bca230fa143a32 100644 (file)
--- a/date.c
+++ b/date.c
@@ -585,6 +585,33 @@ static int date_string(unsigned long date, int offset, char *buf, int len)
        return snprintf(buf, len, "%lu %c%02d%02d", date, sign, offset / 60, offset % 60);
 }
 
+/*
+ * Parse a string like "0 +0000" as ancient timestamp near epoch, but
+ * only when it appears not as part of any other string.
+ */
+static int match_object_header_date(const char *date, unsigned long *timestamp, int *offset)
+{
+       char *end;
+       unsigned long stamp;
+       int ofs;
+
+       if (*date < '0' || '9' <= *date)
+               return -1;
+       stamp = strtoul(date, &end, 10);
+       if (*end != ' ' || stamp == ULONG_MAX || (end[1] != '+' && end[1] != '-'))
+               return -1;
+       date = end + 2;
+       ofs = strtol(date, &end, 10);
+       if ((*end != '\0' && (*end != '\n')) || end != date + 4)
+               return -1;
+       ofs = (ofs / 100) * 60 + (ofs % 100);
+       if (date[-1] == '-')
+               ofs = -ofs;
+       *timestamp = stamp;
+       *offset = ofs;
+       return 0;
+}
+
 /* Gr. strptime is crap for this; it doesn't have a way to require RFC2822
    (i.e. English) day/month names, and it doesn't work correctly with %z. */
 int parse_date_basic(const char *date, unsigned long *timestamp, int *offset)
@@ -610,6 +637,8 @@ int parse_date_basic(const char *date, unsigned long *timestamp, int *offset)
        *offset = -1;
        tm_gmt = 0;
 
+       if (!match_object_header_date(date, timestamp, offset))
+               return 0; /* success */
        for (;;) {
                int match = 0;
                unsigned char c = *date;