Merge branch 'ph/parse-date-reduced-precision'

Loosen date parsing heuristics.

* ph/parse-date-reduced-precision:
  date.c: allow ISO 8601 reduced precision times
maint
Junio C Hamano 2023-01-21 17:22:00 -08:00
commit d2917b9099
2 changed files with 45 additions and 0 deletions

37
date.c
View File

@ -493,6 +493,12 @@ static int match_alpha(const char *date, struct tm *tm, int *offset)
return 2;
}

/* ISO-8601 allows yyyymmDD'T'HHMMSS, with less precision */
if (*date == 'T' && isdigit(date[1]) && tm->tm_hour == -1) {
tm->tm_min = tm->tm_sec = 0;
return 1;
}

/* BAD CRAP */
return skip_alpha(date);
}
@ -638,6 +644,18 @@ static inline int nodate(struct tm *tm)
tm->tm_sec) < 0;
}

/*
* Have we seen an ISO-8601-alike date, i.e. 20220101T0,
* In which, hour is still unset,
* and minutes and second has been set to 0.
*/
static inline int maybeiso8601(struct tm *tm)
{
return tm->tm_hour == -1 &&
tm->tm_min == 0 &&
tm->tm_sec == 0;
}

/*
* We've seen a digit. Time? Year? Date?
*/
@ -701,6 +719,25 @@ static int match_digit(const char *date, struct tm *tm, int *offset, int *tm_gmt
return end - date;
}

/* reduced precision of ISO-8601's time: HHMM or HH */
if (maybeiso8601(tm)) {
unsigned int num1 = num;
unsigned int num2 = 0;
if (n == 4) {
num1 = num / 100;
num2 = num % 100;
}
if ((n == 4 || n == 2) && !nodate(tm) &&
set_time(num1, num2, 0, tm) == 0)
return n;
/*
* We thought this is an ISO-8601 time string,
* we set minutes and seconds to 0,
* turn out it isn't, rollback the change.
*/
tm->tm_min = tm->tm_sec = -1;
}

/* Four-digit year or a timezone? */
if (n == 4) {
if (num <= 1400 && *offset == -1) {

View File

@ -88,6 +88,13 @@ check_parse 2008-02-14 bad
check_parse '2008-02-14 20:30:45' '2008-02-14 20:30:45 +0000'
check_parse '2008-02-14 20:30:45 -0500' '2008-02-14 20:30:45 -0500'
check_parse '2008.02.14 20:30:45 -0500' '2008-02-14 20:30:45 -0500'
check_parse '20080214T20:30:45' '2008-02-14 20:30:45 +0000'
check_parse '20080214T20:30' '2008-02-14 20:30:00 +0000'
check_parse '20080214T20' '2008-02-14 20:00:00 +0000'
check_parse '20080214T203045' '2008-02-14 20:30:45 +0000'
check_parse '20080214T2030' '2008-02-14 20:30:00 +0000'
check_parse '20080214T000000.20' '2008-02-14 00:00:00 +0000'
check_parse '20080214T00:00:00.20' '2008-02-14 00:00:00 +0000'
check_parse '20080214T203045-04:00' '2008-02-14 20:30:45 -0400'
check_parse '20080214T203045 -04:00' '2008-02-14 20:30:45 -0400'
check_parse '20080214T203045.019-04:00' '2008-02-14 20:30:45 -0400'
@ -99,6 +106,7 @@ check_parse '2008-02-14 20:30:45 -05' '2008-02-14 20:30:45 -0500'
check_parse '2008-02-14 20:30:45 -:30' '2008-02-14 20:30:45 +0000'
check_parse '2008-02-14 20:30:45 -05:00' '2008-02-14 20:30:45 -0500'
check_parse '2008-02-14 20:30:45' '2008-02-14 20:30:45 -0500' EST5
check_parse 'Thu, 7 Apr 2005 15:14:13 -0700' '2005-04-07 15:14:13 -0700'

check_approxidate() {
echo "$1 -> $2 +0000" >expect