Add strptime(3) support for %U and %W (take 2)

Add support for the missing POSIX-2001 %U and %W features: the
existing FreeBSD strptime code recognizes both directives and
validates that the week number lies in the permitted range,
but then simply discards the value.

Initial support for the feature was written by Paul Green.
David Carlier added the initial handling of tm_wday/tm_yday.
Major credit goes to Andrey Chernov for detecting much of the
brokenness, and rewriting/cleaning most of the code, making it
much more robust.

Tested independently with the strptime test from the GNU C
library.

PR:		137307
MFC after:	1 month
Relnotes:	yes

1 files changed, 119 insertions, 7 deletions

diff --git a/lib/libc/stdtime/strptime.c b/lib/libc/stdtime/strptime.c
index 2333ab4..ab08017 100644
--- a/lib/libc/stdtime/strptime.c
+++ b/lib/libc/stdtime/strptime.c
@@ -55,10 +55,32 @@ __FBSDID("$FreeBSD$");
 #include "un-namespace.h"
 #include "libc_private.h"
 #include "timelocal.h"
-
+#include "tzfile.h"
+#include <stdio.h>
 static char * _strptime(const char *, const char *, struct tm *, int *, locale_t);
 
-#define	asizeof(a)	(sizeof (a) / sizeof ((a)[0]))
+#define	asizeof(a)	(sizeof(a) / sizeof((a)[0]))
+
+#define	FLAG_NONE	(1 << 0)
+#define	FLAG_YEAR	(1 << 1)
+#define	FLAG_MONTH	(1 << 2)
+#define	FLAG_YDAY	(1 << 3)
+#define	FLAG_MDAY	(1 << 4)
+#define	FLAG_WDAY	(1 << 5)
+
+/*
+ * Calculate the week day of the first day of a year. Valid for
+ * the Gregorian calendar, which began Sept 14, 1752 in the UK
+ * and its colonies. Ref:
+ * http://en.wikipedia.org/wiki/Determination_of_the_day_of_the_week
+ */
+
+static int
+first_wday_of(int year)
+{
+	return (((2 * (3 - (year / 100) % 4)) + (year % 100) +
+		((year % 100) / 4) + (isleap(year) ? 6 : 0) + 1) % 7);
+}
 
 static char *
 _strptime(const char *buf, const char *fmt, struct tm *tm, int *GMTp,
@@ -66,9 +88,18 @@ _strptime(const char *buf, const char *fmt, struct tm *tm, int *GMTp,
 {
 	char	c;
 	const char *ptr;
+	int	day_offset = -1, wday_offset;
+	int week_offset;
 	int	i, len;
+	int flags;
 	int Ealternative, Oalternative;
-	struct lc_time_T *tptr = __get_current_time_locale(locale);
+	const struct lc_time_T *tptr = __get_current_time_locale(locale);
+	static int start_of_month[2][13] = {
+		{0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365},
+		{0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366}
+	};
+
+	flags = FLAG_NONE;
 
 	ptr = fmt;
 	while (*ptr != 0) {
@@ -102,6 +133,7 @@ label:
 			buf = _strptime(buf, tptr->date_fmt, tm, GMTp, locale);
 			if (buf == NULL)
 				return (NULL);
+			flags |= FLAG_WDAY | FLAG_MONTH | FLAG_MDAY | FLAG_YEAR;
 			break;
 
 		case 'C':
@@ -119,19 +151,23 @@ label:
 			if (i < 19)
 				return (NULL);
 
-			tm->tm_year = i * 100 - 1900;
+			tm->tm_year = i * 100 - TM_YEAR_BASE;
+			flags |= FLAG_YEAR;
+
 			break;
 
 		case 'c':
 			buf = _strptime(buf, tptr->c_fmt, tm, GMTp, locale);
 			if (buf == NULL)
 				return (NULL);
+			flags |= FLAG_WDAY | FLAG_MONTH | FLAG_MDAY | FLAG_YEAR;
 			break;
 
 		case 'D':
 			buf = _strptime(buf, "%m/%d/%y", tm, GMTp, locale);
 			if (buf == NULL)
 				return (NULL);
+			flags |= FLAG_MONTH | FLAG_MDAY | FLAG_YEAR;
 			break;
 
 		case 'E':
@@ -150,6 +186,7 @@ label:
 			buf = _strptime(buf, "%Y-%m-%d", tm, GMTp, locale);
 			if (buf == NULL)
 				return (NULL);
+			flags |= FLAG_MONTH | FLAG_MDAY | FLAG_YEAR;
 			break;
 
 		case 'R':
@@ -180,6 +217,7 @@ label:
 			buf = _strptime(buf, tptr->x_fmt, tm, GMTp, locale);
 			if (buf == NULL)
 				return (NULL);
+			flags |= FLAG_MONTH | FLAG_MDAY | FLAG_YEAR;
 			break;
 
 		case 'j':
@@ -197,6 +235,8 @@ label:
 				return (NULL);
 
 			tm->tm_yday = i - 1;
+			flags |= FLAG_YDAY;
+
 			break;
 
 		case 'M':
@@ -303,7 +343,7 @@ label:
 				return (NULL);
 
 			tm->tm_wday = i;
-			buf += len;
+			flags |= FLAG_WDAY;
 			break;
 
 		case 'U':
@@ -327,6 +367,14 @@ label:
 			if (i > 53)
 				return (NULL);
 
+			if (c == 'U')
+				day_offset = TM_SUNDAY;
+			else
+				day_offset = TM_MONDAY;
+
+
+			week_offset = i;
+
 			break;
 
 		case 'w':
@@ -338,6 +386,7 @@ label:
 				return (NULL);
 
 			tm->tm_wday = i;
+			flags |= FLAG_WDAY;
 
 			break;
 
@@ -374,6 +423,7 @@ label:
 				return (NULL);
 
 			tm->tm_mday = i;
+			flags |= FLAG_MDAY;
 
 			break;
 
@@ -413,6 +463,8 @@ label:
 
 			tm->tm_mon = i;
 			buf += len;
+			flags |= FLAG_MONTH;
+
 			break;
 
 		case 'm':
@@ -430,6 +482,7 @@ label:
 				return (NULL);
 
 			tm->tm_mon = i - 1;
+			flags |= FLAG_MONTH;
 
 			break;
 
@@ -471,13 +524,14 @@ label:
 				len--;
 			}
 			if (c == 'Y')
-				i -= 1900;
+				i -= TM_YEAR_BASE;
 			if (c == 'y' && i < 69)
 				i += 100;
 			if (i < 0)
 				return (NULL);
 
 			tm->tm_year = i;
+			flags |= FLAG_YEAR;
 
 			break;
 
@@ -543,10 +597,67 @@ label:
 			break;
 		}
 	}
+
+	if (!(flags & FLAG_YDAY) && (flags & FLAG_YEAR)) {
+		if ((flags & (FLAG_MONTH | FLAG_MDAY)) ==
+		    (FLAG_MONTH | FLAG_MDAY)) {
+			tm->tm_yday = start_of_month[isleap(tm->tm_year +
+			    TM_YEAR_BASE)][tm->tm_mon] + (tm->tm_mday - 1);
+			flags |= FLAG_YDAY;
+		} else if (day_offset != -1) {
+			/* Set the date to the first Sunday (or Monday)
+			 * of the specified week of the year.
+			 */
+			if (!(flags & FLAG_WDAY)) {
+				tm->tm_wday = day_offset;
+				flags |= FLAG_WDAY;
+			}
+			tm->tm_yday = (7 -
+			    first_wday_of(tm->tm_year + TM_YEAR_BASE) +
+			    day_offset) % 7 + (week_offset - 1) * 7 +
+			    tm->tm_wday - day_offset;
+			flags |= FLAG_YDAY;
+		}
+	}
+
+	if ((flags & (FLAG_YEAR | FLAG_YDAY)) == (FLAG_YEAR | FLAG_YDAY)) {
+		if (!(flags & FLAG_MONTH)) {
+			i = 0;
+			while (tm->tm_yday >=
+			    start_of_month[isleap(tm->tm_year +
+			    TM_YEAR_BASE)][i])
+				i++;
+			if (i > 12) {
+				i = 1;
+				tm->tm_yday -=
+				    start_of_month[isleap(tm->tm_year +
+				    TM_YEAR_BASE)][12];
+				tm->tm_year++;
+			}
+			tm->tm_mon = i - 1;
+			flags |= FLAG_MONTH;
+		}
+		if (!(flags & FLAG_MDAY)) {
+			tm->tm_mday = tm->tm_yday -
+			    start_of_month[isleap(tm->tm_year + TM_YEAR_BASE)]
+			    [tm->tm_mon] + 1;
+			flags |= FLAG_MDAY;
+		}
+		if (!(flags & FLAG_WDAY)) {
+			i = 0;
+			wday_offset = first_wday_of(tm->tm_year);
+			while (i++ <= tm->tm_yday) {
+				if (wday_offset++ >= 6)
+					wday_offset = 0;
+			}
+			tm->tm_wday = wday_offset;
+			flags |= FLAG_WDAY;
+		}
+	}
+
 	return ((char *)buf);
 }
 
-
 char *
 strptime_l(const char * __restrict buf, const char * __restrict fmt,
     struct tm * __restrict tm, locale_t loc)
@@ -564,6 +675,7 @@ strptime_l(const char * __restrict buf, const char * __restrict fmt,
 
 	return (ret);
 }
+
 char *
 strptime(const char * __restrict buf, const char * __restrict fmt,
     struct tm * __restrict tm)