Merge branch 'lt/approxidate'

* lt/approxidate:
  fix approxidate parsing of relative months and years
  tests: add date printing and parsing tests
  refactor test-date interface
  Add date formatting and parsing functions relative to a given time
  Further 'approxidate' improvements
  Improve on 'approxidate'

Conflicts:
	date.c

4 files changed, 316 insertions, 107 deletions

diff --git a/cache.h b/cache.h
index 808dabacd..5fad24ce2 100644
--- a/cache.h
+++ b/cache.h
@@ -731,9 +731,14 @@ enum date_mode {
 };
 
 const char *show_date(unsigned long time, int timezone, enum date_mode mode);
+const char *show_date_relative(unsigned long time, int tz,
+			       const struct timeval *now,
+			       char *timebuf,
+			       size_t timebuf_size);
 int parse_date(const char *date, char *buf, int bufsize);
 void datestamp(char *buf, int bufsize);
 unsigned long approxidate(const char *);
+unsigned long approxidate_relative(const char *date, const struct timeval *now);
 enum date_mode parse_date_format(const char *format);
 
 #define IDENT_WARN_ON_NO_NAME  1
diff --git a/date.c b/date.c
index f011692c2..e9ee4aa74 100644
--- a/date.c
+++ b/date.c
@@ -24,6 +24,8 @@ time_t tm_to_time_t(const struct tm *tm)
 		return -1;
 	if (month < 2 || (year + 2) % 4)
 		day--;
+	if (tm->tm_hour < 0 || tm->tm_min < 0 || tm->tm_sec < 0)
+		return -1;
 	return (year * 365 + (year + 1) / 4 + mdays[month] + day) * 24*60*60UL +
 		tm->tm_hour * 60*60 + tm->tm_min * 60 + tm->tm_sec;
 }
@@ -84,6 +86,67 @@ static int local_tzoffset(unsigned long time)
 	return offset * eastwest;
 }
 
+const char *show_date_relative(unsigned long time, int tz,
+			       const struct timeval *now,
+			       char *timebuf,
+			       size_t timebuf_size)
+{
+	unsigned long diff;
+	if (now->tv_sec < time)
+		return "in the future";
+	diff = now->tv_sec - time;
+	if (diff < 90) {
+		snprintf(timebuf, timebuf_size, "%lu seconds ago", diff);
+		return timebuf;
+	}
+	/* Turn it into minutes */
+	diff = (diff + 30) / 60;
+	if (diff < 90) {
+		snprintf(timebuf, timebuf_size, "%lu minutes ago", diff);
+		return timebuf;
+	}
+	/* Turn it into hours */
+	diff = (diff + 30) / 60;
+	if (diff < 36) {
+		snprintf(timebuf, timebuf_size, "%lu hours ago", diff);
+		return timebuf;
+	}
+	/* We deal with number of days from here on */
+	diff = (diff + 12) / 24;
+	if (diff < 14) {
+		snprintf(timebuf, timebuf_size, "%lu days ago", diff);
+		return timebuf;
+	}
+	/* Say weeks for the past 10 weeks or so */
+	if (diff < 70) {
+		snprintf(timebuf, timebuf_size, "%lu weeks ago", (diff + 3) / 7);
+		return timebuf;
+	}
+	/* Say months for the past 12 months or so */
+	if (diff < 360) {
+		snprintf(timebuf, timebuf_size, "%lu months ago", (diff + 15) / 30);
+		return timebuf;
+	}
+	/* Give years and months for 5 years or so */
+	if (diff < 1825) {
+		unsigned long years = diff / 365;
+		unsigned long months = (diff % 365 + 15) / 30;
+		int n;
+		n = snprintf(timebuf, timebuf_size, "%lu year%s",
+				years, (years > 1 ? "s" : ""));
+		if (months)
+			snprintf(timebuf + n, timebuf_size - n,
+					", %lu month%s ago",
+					months, (months > 1 ? "s" : ""));
+		else
+			snprintf(timebuf + n, timebuf_size - n, " ago");
+		return timebuf;
+	}
+	/* Otherwise, just years. Centuries is probably overkill. */
+	snprintf(timebuf, timebuf_size, "%lu years ago", (diff + 183) / 365);
+	return timebuf;
+}
+
 const char *show_date(unsigned long time, int tz, enum date_mode mode)
 {
 	struct tm *tm;
@@ -95,63 +158,10 @@ const char *show_date(unsigned long time, int tz, enum date_mode mode)
 	}
 
 	if (mode == DATE_RELATIVE) {
-		unsigned long diff;
 		struct timeval now;
 		gettimeofday(&now, NULL);
-		if (now.tv_sec < time)
-			return "in the future";
-		diff = now.tv_sec - time;
-		if (diff < 90) {
-			snprintf(timebuf, sizeof(timebuf), "%lu seconds ago", diff);
-			return timebuf;
-		}
-		/* Turn it into minutes */
-		diff = (diff + 30) / 60;
-		if (diff < 90) {
-			snprintf(timebuf, sizeof(timebuf), "%lu minutes ago", diff);
-			return timebuf;
-		}
-		/* Turn it into hours */
-		diff = (diff + 30) / 60;
-		if (diff < 36) {
-			snprintf(timebuf, sizeof(timebuf), "%lu hours ago", diff);
-			return timebuf;
-		}
-		/* We deal with number of days from here on */
-		diff = (diff + 12) / 24;
-		if (diff < 14) {
-			snprintf(timebuf, sizeof(timebuf), "%lu days ago", diff);
-			return timebuf;
-		}
-		/* Say weeks for the past 10 weeks or so */
-		if (diff < 70) {
-			snprintf(timebuf, sizeof(timebuf), "%lu weeks ago", (diff + 3) / 7);
-			return timebuf;
-		}
-		/* Say months for the past 12 months or so */
-		if (diff < 360) {
-			snprintf(timebuf, sizeof(timebuf), "%lu months ago", (diff + 15) / 30);
-			return timebuf;
-		}
-		/* Give years and months for 5 years or so */
-		if (diff < 1825) {
-			unsigned long years = diff / 365;
-			unsigned long months = (diff % 365 + 15) / 30;
-			int n;
-			n = snprintf(timebuf, sizeof(timebuf), "%lu year%s",
-					years, (years > 1 ? "s" : ""));
-			if (months)
-				snprintf(timebuf + n, sizeof(timebuf) - n,
-					", %lu month%s ago",
-					months, (months > 1 ? "s" : ""));
-			else
-				snprintf(timebuf + n, sizeof(timebuf) - n,
-					" ago");
-			return timebuf;
-		}
-		/* Otherwise, just years. Centuries is probably overkill. */
-		snprintf(timebuf, sizeof(timebuf), "%lu years ago", (diff + 183) / 365);
-		return timebuf;
+		return show_date_relative(time, tz, &now,
+					  timebuf, sizeof(timebuf));
 	}
 
 	if (mode == DATE_LOCAL)
@@ -425,13 +435,19 @@ static int match_multi_number(unsigned long num, char c, const char *date, char
 	return end - date;
 }
 
-/* Have we filled in any part of the time/date yet? */
+/*
+ * Have we filled in any part of the time/date yet?
+ * We just do a binary 'and' to see if the sign bit
+ * is set in all the values.
+ */
 static inline int nodate(struct tm *tm)
 {
-	return tm->tm_year < 0 &&
-		tm->tm_mon < 0 &&
-		tm->tm_mday < 0 &&
-		!(tm->tm_hour | tm->tm_min | tm->tm_sec);
+	return (tm->tm_year &
+		tm->tm_mon &
+		tm->tm_mday &
+		tm->tm_hour &
+		tm->tm_min &
+		tm->tm_sec) < 0;
 }
 
 /*
@@ -525,11 +541,8 @@ static int match_digit(const char *date, struct tm *tm, int *offset, int *tm_gmt
 		}
 	}
 
-	if (num > 0 && num < 32) {
-		tm->tm_mday = num;
-	} else if (num > 0 && num < 13) {
+	if (num > 0 && num < 13 && tm->tm_mon < 0)
 		tm->tm_mon = num-1;
-	}
 
 	return n;
 }
@@ -583,6 +596,9 @@ int parse_date(const char *date, char *result, int maxlen)
 	tm.tm_mon = -1;
 	tm.tm_mday = -1;
 	tm.tm_isdst = -1;
+	tm.tm_hour = -1;
+	tm.tm_min = -1;
+	tm.tm_sec = -1;
 	offset = -1;
 	tm_gmt = 0;
 
@@ -657,42 +673,59 @@ void datestamp(char *buf, int bufsize)
 	date_string(now, offset, buf, bufsize);
 }
 
-static void update_tm(struct tm *tm, unsigned long sec)
+/*
+ * Relative time update (eg "2 days ago").  If we haven't set the time
+ * yet, we need to set it from current time.
+ */
+static unsigned long update_tm(struct tm *tm, struct tm *now, unsigned long sec)
 {
-	time_t n = mktime(tm) - sec;
+	time_t n;
+
+	if (tm->tm_mday < 0)
+		tm->tm_mday = now->tm_mday;
+	if (tm->tm_mon < 0)
+		tm->tm_mon = now->tm_mon;
+	if (tm->tm_year < 0) {
+		tm->tm_year = now->tm_year;
+		if (tm->tm_mon > now->tm_mon)
+			tm->tm_year--;
+	}
+
+	n = mktime(tm) - sec;
 	localtime_r(&n, tm);
+	return n;
 }
 
-static void date_yesterday(struct tm *tm, int *num)
+static void date_yesterday(struct tm *tm, struct tm *now, int *num)
 {
-	update_tm(tm, 24*60*60);
+	update_tm(tm, now, 24*60*60);
 }
 
-static void date_time(struct tm *tm, int hour)
+static void date_time(struct tm *tm, struct tm *now, int hour)
 {
 	if (tm->tm_hour < hour)
-		date_yesterday(tm, NULL);
+		date_yesterday(tm, now, NULL);
 	tm->tm_hour = hour;
 	tm->tm_min = 0;
 	tm->tm_sec = 0;
 }
 
-static void date_midnight(struct tm *tm, int *num)
+static void date_midnight(struct tm *tm, struct tm *now, int *num)
 {
-	date_time(tm, 0);
+	date_time(tm, now, 0);
 }
 
-static void date_noon(struct tm *tm, int *num)
+static void date_noon(struct tm *tm, struct tm *now, int *num)
 {
-	date_time(tm, 12);
+	date_time(tm, now, 12);
 }
 
-static void date_tea(struct tm *tm, int *num)
+static void date_tea(struct tm *tm, struct tm *now, int *num)
 {
-	date_time(tm, 17);
+	date_time(tm, now, 17);
 }
 
-static void date_pm(struct tm *tm, int *num)
+static void date_pm(struct tm *tm, struct tm *now, int *num)
 {
 	int hour, n = *num;
 	*num = 0;
@@ -706,7 +739,7 @@ static void date_pm(struct tm *tm, int *num)
 	tm->tm_hour = (hour % 12) + 12;
 }
 
-static void date_am(struct tm *tm, int *num)
+static void date_am(struct tm *tm, struct tm *now, int *num)
 {
 	int hour, n = *num;
 	*num = 0;
@@ -720,7 +753,7 @@ static void date_am(struct tm *tm, int *num)
 	tm->tm_hour = (hour % 12);
 }
 
-static void date_never(struct tm *tm, int *num)
+static void date_never(struct tm *tm, struct tm *now, int *num)
 {
 	time_t n = 0;
 	localtime_r(&n, tm);
@@ -728,7 +761,7 @@ static void date_never(struct tm *tm, int *num)
 
 static const struct special {
 	const char *name;
-	void (*fn)(struct tm *, int *);
+	void (*fn)(struct tm *, struct tm *, int *);
 } special[] = {
 	{ "yesterday", date_yesterday },
 	{ "noon", date_noon },
@@ -757,7 +790,7 @@ static const struct typelen {
 	{ NULL }
 };
 
-static const char *approxidate_alpha(const char *date, struct tm *tm, int *num)
+static const char *approxidate_alpha(const char *date, struct tm *tm, struct tm *now, int *num)
 {
 	const struct typelen *tl;
 	const struct special *s;
@@ -778,7 +811,7 @@ static const char *approxidate_alpha(const char *date, struct tm *tm, int *num)
 	for (s = special; s->name; s++) {
 		int len = strlen(s->name);
 		if (match_string(date, s->name) == len) {
-			s->fn(tm, num);
+			s->fn(tm, now, num);
 			return end;
 		}
 	}
@@ -800,7 +833,7 @@ static const char *approxidate_alpha(const char *date, struct tm *tm, int *num)
 	while (tl->type) {
 		int len = strlen(tl->type);
 		if (match_string(date, tl->type) >= len-1) {
-			update_tm(tm, tl->length * *num);
+			update_tm(tm, now, tl->length * *num);
 			*num = 0;
 			return end;
 		}
@@ -818,13 +851,15 @@ static const char *approxidate_alpha(const char *date, struct tm *tm, int *num)
 				n++;
 			diff += 7*n;
 
-			update_tm(tm, diff * 24 * 60 * 60);
+			update_tm(tm, now, diff * 24 * 60 * 60);
 			return end;
 		}
 	}
 
 	if (match_string(date, "months") >= 5) {
-		int n = tm->tm_mon - *num;
+		int n;
+		update_tm(tm, now, 0); /* fill in date fields if needed */
+		n = tm->tm_mon - *num;
 		*num = 0;
 		while (n < 0) {
 			n += 12;
@@ -835,6 +870,7 @@ static const char *approxidate_alpha(const char *date, struct tm *tm, int *num)
 	}
 
 	if (match_string(date, "years") >= 4) {
+		update_tm(tm, now, 0); /* fill in date fields if needed */
 		tm->tm_year -= *num;
 		*num = 0;
 		return end;
@@ -866,36 +902,82 @@ static const char *approxidate_digit(const char *date, struct tm *tm, int *num)
 	return end;
 }
 
-unsigned long approxidate(const char *date)
+/*
+ * Do we have a pending number at the end, or when
+ * we see a new one? Let's assume it's a month day,
+ * as in "Dec 6, 1992"
+ */
+static void pending_number(struct tm *tm, int *num)
+{
+	int number = *num;
+
+	if (number) {
+		*num = 0;
+		if (tm->tm_mday < 0 && number < 32)
+			tm->tm_mday = number;
+		else if (tm->tm_mon < 0 && number < 13)
+			tm->tm_mon = number-1;
+		else if (tm->tm_year < 0) {
+			if (number > 1969 && number < 2100)
+				tm->tm_year = number - 1900;
+			else if (number > 69 && number < 100)
+				tm->tm_year = number;
+			else if (number < 38)
+				tm->tm_year = 100 + number;
+			/* We screw up for number = 00 ? */
+		}
+	}
+}
+
+static unsigned long approxidate_str(const char *date, const struct timeval *tv)
 {
 	int number = 0;
 	struct tm tm, now;
-	struct timeval tv;
 	time_t time_sec;
-	char buffer[50];
-
-	if (parse_date(date, buffer, sizeof(buffer)) > 0)
-		return strtoul(buffer, NULL, 10);
 
-	gettimeofday(&tv, NULL);
-	time_sec = tv.tv_sec;
+	time_sec = tv->tv_sec;
 	localtime_r(&time_sec, &tm);
 	now = tm;
+
+	tm.tm_year = -1;
+	tm.tm_mon = -1;
+	tm.tm_mday = -1;
+
 	for (;;) {
 		unsigned char c = *date;
 		if (!c)
 			break;
 		date++;
 		if (isdigit(c)) {
+			pending_number(&tm, &number);
 			date = approxidate_digit(date-1, &tm, &number);
 			continue;
 		}
 		if (isalpha(c))
-			date = approxidate_alpha(date-1, &tm, &number);
+			date = approxidate_alpha(date-1, &tm, &now, &number);
 	}
-	if (number > 0 && number < 32)
-		tm.tm_mday = number;
-	if (tm.tm_mon > now.tm_mon && tm.tm_year == now.tm_year)
-		tm.tm_year--;
-	return mktime(&tm);
+	pending_number(&tm, &number);
+	return update_tm(&tm, &now, 0);
+}
+
+unsigned long approxidate_relative(const char *date, const struct timeval *tv)
+{
+	char buffer[50];
+
+	if (parse_date(date, buffer, sizeof(buffer)) > 0)
+		return strtoul(buffer, NULL, 0);
+
+	return approxidate_str(date, tv);
+}
+
+unsigned long approxidate(const char *date)
+{
+	struct timeval tv;
+	char buffer[50];
+
+	if (parse_date(date, buffer, sizeof(buffer)) > 0)
+		return strtoul(buffer, NULL, 0);
+
+	gettimeofday(&tv, NULL);
+	return approxidate_str(date, &tv);
 }
diff --git a/t/t0006-date.sh b/t/t0006-date.sh
new file mode 100755
index 000000000..a4d8fa8fa
--- /dev/null
+++ b/t/t0006-date.sh
@@ -0,0 +1,75 @@
+#!/bin/sh
+
+test_description='test date parsing and printing'
+. ./test-lib.sh
+
+# arbitrary reference time: 2009-08-30 19:20:00
+TEST_DATE_NOW=1251660000; export TEST_DATE_NOW
+
+check_show() {
+	t=$(($TEST_DATE_NOW - $1))
+	echo "$t -> $2" >expect
+	test_expect_${3:-success} "relative date ($2)" "
+	test-date show $t >actual &&
+	test_cmp expect actual
+	"
+}
+
+check_show 5 '5 seconds ago'
+check_show 300 '5 minutes ago'
+check_show 18000 '5 hours ago'
+check_show 432000 '5 days ago'
+check_show 1728000 '3 weeks ago'
+check_show 13000000 '5 months ago'
+check_show 37500000 '1 year, 2 months ago'
+check_show 55188000 '1 year, 9 months ago'
+check_show 630000000 '20 years ago'
+
+check_parse() {
+	echo "$1 -> $2" >expect
+	test_expect_${3:-success} "parse date ($1)" "
+	test-date parse '$1' >actual &&
+	test_cmp expect actual
+	"
+}
+
+check_parse 2008 bad
+check_parse 2008-02 bad
+check_parse 2008-02-14 bad
+check_parse '2008-02-14 20:30:45' '2008-02-14 20:30:45 +0000'
+
+check_approxidate() {
+	echo "$1 -> $2 +0000" >expect
+	test_expect_${3:-success} "parse approxidate ($1)" "
+	test-date approxidate '$1' >actual &&
+	test_cmp expect actual
+	"
+}
+
+check_approxidate now '2009-08-30 19:20:00'
+check_approxidate '5 seconds ago' '2009-08-30 19:19:55'
+check_approxidate 5.seconds.ago '2009-08-30 19:19:55'
+check_approxidate 10.minutes.ago '2009-08-30 19:10:00'
+check_approxidate yesterday '2009-08-29 19:20:00'
+check_approxidate 3.days.ago '2009-08-27 19:20:00'
+check_approxidate 3.weeks.ago '2009-08-09 19:20:00'
+check_approxidate 3.months.ago '2009-05-30 19:20:00'
+check_approxidate 2.years.3.months.ago '2007-05-30 19:20:00'
+
+check_approxidate '6am yesterday' '2009-08-29 06:00:00'
+check_approxidate '6pm yesterday' '2009-08-29 18:00:00'
+check_approxidate '3:00' '2009-08-30 03:00:00'
+check_approxidate '15:00' '2009-08-30 15:00:00'
+check_approxidate 'noon today' '2009-08-30 12:00:00'
+check_approxidate 'noon yesterday' '2009-08-29 12:00:00'
+
+check_approxidate 'last tuesday' '2009-08-25 19:20:00'
+check_approxidate 'July 5th' '2009-07-05 19:20:00'
+check_approxidate '06/05/2009' '2009-06-05 19:20:00'
+check_approxidate '06.05.2009' '2009-05-06 19:20:00'
+
+check_approxidate 'Jun 6, 5AM' '2009-06-06 05:00:00'
+check_approxidate '5AM Jun 6' '2009-06-06 05:00:00'
+check_approxidate '6AM, June 7, 2009' '2009-06-07 06:00:00'
+
+test_done
diff --git a/test-date.c b/test-date.c
index 62e8f2387..a9e705f79 100644
--- a/test-date.c
+++ b/test-date.c
@@ -1,20 +1,67 @@
 #include "cache.h"
 
-int main(int argc, char **argv)
+static const char *usage_msg = "\n"
+"  test-date show [time_t]...\n"
+"  test-date parse [date]...\n"
+"  test-date approxidate [date]...\n";
+
+static void show_dates(char **argv, struct timeval *now)
 {
-	int i;
+	char buf[128];
+
+	for (; *argv; argv++) {
+		time_t t = atoi(*argv);
+		show_date_relative(t, 0, now, buf, sizeof(buf));
+		printf("%s -> %s\n", *argv, buf);
+	}
+}
 
-	for (i = 1; i < argc; i++) {
+static void parse_dates(char **argv, struct timeval *now)
+{
+	for (; *argv; argv++) {
 		char result[100];
 		time_t t;
 
-		memcpy(result, "bad", 4);
-		parse_date(argv[i], result, sizeof(result));
+		result[0] = 0;
+		parse_date(*argv, result, sizeof(result));
 		t = strtoul(result, NULL, 0);
-		printf("%s -> %s -> %s", argv[i], result, ctime(&t));
+		printf("%s -> %s\n", *argv,
+			t ? show_date(t, 0, DATE_ISO8601) : "bad");
+	}
+}
 
-		t = approxidate(argv[i]);
-		printf("%s -> %s\n", argv[i], ctime(&t));
+static void parse_approxidate(char **argv, struct timeval *now)
+{
+	for (; *argv; argv++) {
+		time_t t;
+		t = approxidate_relative(*argv, now);
+		printf("%s -> %s\n", *argv, show_date(t, 0, DATE_ISO8601));
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct timeval now;
+	const char *x;
+
+	x = getenv("TEST_DATE_NOW");
+	if (x) {
+		now.tv_sec = atoi(x);
+		now.tv_usec = 0;
 	}
+	else
+		gettimeofday(&now, NULL);
+
+	argv++;
+	if (!*argv)
+		usage(usage_msg);
+	if (!strcmp(*argv, "show"))
+		show_dates(argv+1, &now);
+	else if (!strcmp(*argv, "parse"))
+		parse_dates(argv+1, &now);
+	else if (!strcmp(*argv, "approxidate"))
+		parse_approxidate(argv+1, &now);
+	else
+		usage(usage_msg);
 	return 0;
 }