@matheusbsbs / matheus-bagliano / commits / b56be49984

date.c: allow ISO 8601 reduced precision times

ISO 8601 permits "reduced precision" time representations to omit the seconds value or both the minutes and the seconds values. The abbreviate times could look like 17:45 or 1745 to omit the seconds, or simply as 17 to omit both the minutes and the seconds. parse_date_basic accepts the 17:45 format but it rejects the other two. Change it to accept 4-digit and 2-digit time values when they follow a recognized date and a 'T'. Before this change: $ TZ=UTC test-tool date approxidate 2022-12-13T23:00 2022-12-13T2300 2022-12-13T23 2022-12-13T23:00 -> 2022-12-13 23:00:00 +0000 2022-12-13T2300 -> 2022-12-13 23:54:13 +0000 2022-12-13T23 -> 2022-12-13 23:54:13 +0000 After this change: $ TZ=UTC helper/test-tool date approxidate 2022-12-13T23:00 2022-12-13T2300 2022-12-13T23 2022-12-13T23:00 -> 2022-12-13 23:00:00 +0000 2022-12-13T2300 -> 2022-12-13 23:00:00 +0000 2022-12-13T23 -> 2022-12-13 23:00:00 +0000 Note: ISO 8601 also allows reduced precision date strings such as "2022-12" and "2022". This patch does not attempt to address these. Reported-by: Pat LaVarre <plavarre@purestorage.com> Signed-off-by: Phil Hord <phil.hord@gmail.com> Signed-off-by: Đoàn Trần Công Danh <congdanhqx@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Đoàn Trần Công Danh committed Jan 11, 2023 at 07:10 UTC b56be49984de166db6270c59e83f89d3608ddc69
2 files changed +45
date.c
+37
@@ -493,6 +493,12 @@ static int match_alpha(const char *date, struct tm *tm, int *offset)
493 return 2;
494 }
495
496 + /* ISO-8601 allows yyyymmDD'T'HHMMSS, with less precision */
497 + if (*date == 'T' && isdigit(date[1]) && tm->tm_hour == -1) {
498 + tm->tm_min = tm->tm_sec = 0;
499 + return 1;
500 + }
501 +
502 /* BAD CRAP */
503 return skip_alpha(date);
504 }
@@ -638,6 +644,18 @@ static inline int nodate(struct tm *tm)
644 tm->tm_sec) < 0;
645 }
646
647 +/*
648 + * Have we seen an ISO-8601-alike date, i.e. 20220101T0,
649 + * In which, hour is still unset,
650 + * and minutes and second has been set to 0.
651 + */
652 +static inline int maybeiso8601(struct tm *tm)
653 +{
654 + return tm->tm_hour == -1 &&
655 + tm->tm_min == 0 &&
656 + tm->tm_sec == 0;
657 +}
658 +
659 /*
660 * We've seen a digit. Time? Year? Date?
661 */
@@ -701,6 +719,25 @@ static int match_digit(const char *date, struct tm *tm, int *offset, int *tm_gmt
719 return end - date;
720 }
721
722 + /* reduced precision of ISO-8601's time: HHMM or HH */
723 + if (maybeiso8601(tm)) {
724 + unsigned int num1 = num;
725 + unsigned int num2 = 0;
726 + if (n == 4) {
727 + num1 = num / 100;
728 + num2 = num % 100;
729 + }
730 + if ((n == 4 || n == 2) && !nodate(tm) &&
731 + set_time(num1, num2, 0, tm) == 0)
732 + return n;
733 + /*
734 + * We thought this is an ISO-8601 time string,
735 + * we set minutes and seconds to 0,
736 + * turn out it isn't, rollback the change.
737 + */
738 + tm->tm_min = tm->tm_sec = -1;
739 + }
740 +
741 /* Four-digit year or a timezone? */
742 if (n == 4) {
743 if (num <= 1400 && *offset == -1) {
t/t0006-date.sh
+8
@@ -88,6 +88,13 @@ check_parse 2008-02-14 bad
88 check_parse '2008-02-14 20:30:45' '2008-02-14 20:30:45 +0000'
89 check_parse '2008-02-14 20:30:45 -0500' '2008-02-14 20:30:45 -0500'
90 check_parse '2008.02.14 20:30:45 -0500' '2008-02-14 20:30:45 -0500'
91 +check_parse '20080214T20:30:45' '2008-02-14 20:30:45 +0000'
92 +check_parse '20080214T20:30' '2008-02-14 20:30:00 +0000'
93 +check_parse '20080214T20' '2008-02-14 20:00:00 +0000'
94 +check_parse '20080214T203045' '2008-02-14 20:30:45 +0000'
95 +check_parse '20080214T2030' '2008-02-14 20:30:00 +0000'
96 +check_parse '20080214T000000.20' '2008-02-14 00:00:00 +0000'
97 +check_parse '20080214T00:00:00.20' '2008-02-14 00:00:00 +0000'
98 check_parse '20080214T203045-04:00' '2008-02-14 20:30:45 -0400'
99 check_parse '20080214T203045 -04:00' '2008-02-14 20:30:45 -0400'
100 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'
106 check_parse '2008-02-14 20:30:45 -:30' '2008-02-14 20:30:45 +0000'
107 check_parse '2008-02-14 20:30:45 -05:00' '2008-02-14 20:30:45 -0500'
108 check_parse '2008-02-14 20:30:45' '2008-02-14 20:30:45 -0500' EST5
109 +check_parse 'Thu, 7 Apr 2005 15:14:13 -0700' '2005-04-07 15:14:13 -0700'
110
111 check_approxidate() {
112 echo "$1 -> $2 +0000" >expect