Update timezone code to track the upstream changes since 2003. In particular

this adds support for 64-bit tzdata files, which is needed to support DST
calculations beyond 2038.  Add a regression test case to give some minimal
confidence that that really works.

Heikki Linnakangas

src/test/regress/expected/timestamptz.out

@@ -114,6 +114,31 @@ INSERT INTO TIMESTAMPTZ_TBL VALUES ('19970710 173201 America/Does_not_exist');
 ERROR:  time zone "america/does_not_exist" not recognized
 SELECT '19970710 173201' AT TIME ZONE 'America/Does_not_exist';
 ERROR:  time zone "America/Does_not_exist" not recognized
+-- Daylight saving time for timestamps beyond 32-bit time_t range.
+SELECT '20500710 173201 Europe/Helsinki'::timestamptz; -- DST
+         timestamptz          
+------------------------------
+ Sun Jul 10 07:32:01 2050 PDT
+(1 row)
+
+SELECT '20500110 173201 Europe/Helsinki'::timestamptz; -- non-DST
+         timestamptz          
+------------------------------
+ Mon Jan 10 07:32:01 2050 PST
+(1 row)
+
+SELECT '205000-07-10 17:32:01 Europe/Helsinki'::timestamptz; -- DST
+          timestamptz           
+--------------------------------
+ Thu Jul 10 07:32:01 205000 PDT
+(1 row)
+
+SELECT '205000-01-10 17:32:01 Europe/Helsinki'::timestamptz; -- non-DST
+          timestamptz           
+--------------------------------
+ Fri Jan 10 07:32:01 205000 PST
+(1 row)
+
 -- Check date conversion and date arithmetic
 INSERT INTO TIMESTAMPTZ_TBL VALUES ('1997-06-10 18:32:01 PDT');
 INSERT INTO TIMESTAMPTZ_TBL VALUES ('Feb 10 17:32:01 1997');

src/test/regress/sql/timestamptz.sql

@@ -86,6 +86,13 @@ SELECT '19970710 173201' AT TIME ZONE 'America/New_York';
 INSERT INTO TIMESTAMPTZ_TBL VALUES ('19970710 173201 America/Does_not_exist');
 SELECT '19970710 173201' AT TIME ZONE 'America/Does_not_exist';
 
+-- Daylight saving time for timestamps beyond 32-bit time_t range.
+SELECT '20500710 173201 Europe/Helsinki'::timestamptz; -- DST
+SELECT '20500110 173201 Europe/Helsinki'::timestamptz; -- non-DST
+
+SELECT '205000-07-10 17:32:01 Europe/Helsinki'::timestamptz; -- DST
+SELECT '205000-01-10 17:32:01 Europe/Helsinki'::timestamptz; -- non-DST
+
 -- Check date conversion and date arithmetic
 INSERT INTO TIMESTAMPTZ_TBL VALUES ('1997-06-10 18:32:01 PDT');
 

src/timezone/README

-This is a PostgreSQL adapted version of the timezone library
-from:
+This is a PostgreSQL adapted version of the timezone library from:
 
 	ftp://elsie.nci.nih.gov/pub/tzcode*.tar.gz
 
-The data files under data/ are an exact copy of the latest data set
-from
+The code is currently synced with release 2007k.  There are many cosmetic
+(and not so cosmetic) differences from the original tzcode library, but
+diffs in the upstream version should usually be propagated to our version.
+
+The data files under data/ are an exact copy of the latest data set from:
 
 	ftp://elsie.nci.nih.gov/pub/tzdata*.tar.gz
 

src/timezone/ialloc.c

 /*
  * This file is in the public domain, so clarified as of
- * 1996-06-05 by Arthur David Olson (arthur_david_olson@nih.gov).
+ * 2006-07-17 by Arthur David Olson.
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/timezone/ialloc.c,v 1.9 2007/10/26 13:30:10 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/timezone/ialloc.c,v 1.10 2008/02/16 21:16:04 tgl Exp $
  */
 
 #include "postgres_fe.h"

src/timezone/pgtz.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/timezone/pgtz.c,v 1.58 2008/02/11 19:55:11 mha Exp $
+ *	  $PostgreSQL: pgsql/src/timezone/pgtz.c,v 1.59 2008/02/16 21:16:04 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -287,7 +287,7 @@ score_timezone(const char *tzname, struct tztry * tt)
 	 * Load timezone directly. Don't use pg_tzset, because we don't want all
 	 * timezones loaded in the cache at startup.
 	 */
-	if (tzload(tzname, NULL, &tz.state) != 0)
+	if (tzload(tzname, NULL, &tz.state, TRUE) != 0)
 	{
 		if (tzname[0] == ':' || tzparse(tzname, &tz.state, FALSE) != 0)
 		{
@@ -1191,7 +1191,7 @@ pg_tzset(const char *name)
 		return &tzp->tz;
 	}
 
-	if (tzload(uppername, canonname, &tzstate) != 0)
+	if (tzload(uppername, canonname, &tzstate, TRUE) != 0)
 	{
 		if (uppername[0] == ':' || tzparse(uppername, &tzstate, FALSE) != 0)
 		{
@@ -1463,7 +1463,8 @@ pg_tzenumerate_next(pg_tzenum *dir)
 		 * Load this timezone using tzload() not pg_tzset(), so we don't fill
 		 * the cache
 		 */
-		if (tzload(fullname + dir->baselen, dir->tz.TZname, &dir->tz.state) != 0)
+		if (tzload(fullname + dir->baselen, dir->tz.TZname, &dir->tz.state, 
+				   TRUE) != 0)
 		{
 			/* Zone could not be loaded, ignore it */
 			continue;

src/timezone/pgtz.h

@@ -9,7 +9,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/timezone/pgtz.h,v 1.21 2008/01/01 19:46:01 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/timezone/pgtz.h,v 1.22 2008/02/16 21:16:04 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -43,6 +43,8 @@ struct state
 	int			timecnt;
 	int			typecnt;
 	int			charcnt;
+	int			goback;
+	int			goahead;
 	pg_time_t	ats[TZ_MAX_TIMES];
 	unsigned char types[TZ_MAX_TIMES];
 	struct ttinfo ttis[TZ_MAX_TYPES];
@@ -64,7 +66,8 @@ struct pg_tz
 extern int	pg_open_tzfile(const char *name, char *canonname);
 
 /* in localtime.c */
-extern int	tzload(const char *name, char *canonname, struct state * sp);
+extern int	tzload(const char *name, char *canonname, struct state * sp, 
+				   int doextend);
 extern int	tzparse(const char *name, struct state * sp, int lastditch);
 
 #endif   /* _PGTZ_H */

src/timezone/private.h

@@ -3,10 +3,10 @@
 
 /*
  * This file is in the public domain, so clarified as of
- * 1996-06-05 by Arthur David Olson (arthur_david_olson@nih.gov).
+ * 1996-06-05 by Arthur David Olson.
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/timezone/private.h,v 1.11 2005/02/23 04:34:21 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/timezone/private.h,v 1.12 2008/02/16 21:16:04 tgl Exp $
  */
 
 /*
@@ -17,12 +17,13 @@
  * Thank you!
  */
 
-#include <limits.h>				/* for CHAR_BIT */
+#include <limits.h>				/* for CHAR_BIT et al. */
 #include <sys/wait.h>			/* for WIFEXITED and WEXITSTATUS */
 #include <unistd.h>				/* for F_OK and R_OK */
 
 #include "pgtime.h"
 
+#define GRANDPARENTED	"Local time zone must be set--see zic manual page"
 
 #ifndef WIFEXITED
 #define WIFEXITED(status)	(((status) & 0xff) == 0)
@@ -34,22 +35,6 @@
 /* Unlike <ctype.h>'s isdigit, this also works if c < 0 | c > UCHAR_MAX. */
 #define is_digit(c) ((unsigned)(c) - '0' <= 9)
 
-/*
- * SunOS 4.1.1 headers lack EXIT_SUCCESS.
- */
-
-#ifndef EXIT_SUCCESS
-#define EXIT_SUCCESS	0
-#endif   /* !defined EXIT_SUCCESS */
-
-/*
- * SunOS 4.1.1 headers lack EXIT_FAILURE.
- */
-
-#ifndef EXIT_FAILURE
-#define EXIT_FAILURE	1
-#endif   /* !defined EXIT_FAILURE */
-
 /*
  * SunOS 4.1.1 libraries lack remove.
  */
@@ -70,7 +55,7 @@ extern char *imalloc(int n);
 extern void *irealloc(void *pointer, int size);
 extern void icfree(char *pointer);
 extern void ifree(char *pointer);
-extern char *scheck(const char *string, const char *format);
+extern const char *scheck(const char *string, const char *format);
 
 
 /*
@@ -93,6 +78,15 @@ extern char *scheck(const char *string, const char *format);
 #define TYPE_SIGNED(type) (((type) -1) < 0)
 #endif   /* !defined TYPE_SIGNED */
 
+/*
+ * Since the definition of TYPE_INTEGRAL contains floating point numbers,
+ * it cannot be used in preprocessor directives.
+ */
+
+#ifndef TYPE_INTEGRAL
+#define TYPE_INTEGRAL(type) (((type) 0.5) != 0.5)
+#endif /* !defined TYPE_INTEGRAL */
+
 #ifndef INT_STRLEN_MAXIMUM
 /*
  * 302 / 1000 is log10(2.0) rounded up.
@@ -107,6 +101,26 @@ extern char *scheck(const char *string, const char *format);
 #undef _
 #define _(msgid) (msgid)
 
+#ifndef YEARSPERREPEAT
+#define YEARSPERREPEAT          400     /* years before a Gregorian repeat */
+#endif /* !defined YEARSPERREPEAT */
+
+/*
+** The Gregorian year averages 365.2425 days, which is 31556952 seconds.
+*/
+
+#ifndef AVGSECSPERYEAR
+#define AVGSECSPERYEAR          31556952L
+#endif /* !defined AVGSECSPERYEAR */
+
+#ifndef SECSPERREPEAT
+#define SECSPERREPEAT           ((int64) YEARSPERREPEAT * (int64) AVGSECSPERYEAR)
+#endif /* !defined SECSPERREPEAT */
+
+#ifndef SECSPERREPEAT_BITS
+#define SECSPERREPEAT_BITS      34      /* ceil(log2(SECSPERREPEAT)) */
+#endif /* !defined SECSPERREPEAT_BITS */
+
 /*
  * UNIX was a registered trademark of The Open Group in 2003.
  */

src/timezone/scheck.c

 /*
  * This file is in the public domain, so clarified as of
- * 1996-06-05 by Arthur David Olson (arthur_david_olson@nih.gov).
+ * 2006-07-17 by Arthur David Olson.
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/timezone/scheck.c,v 1.8 2007/10/26 13:30:10 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/timezone/scheck.c,v 1.9 2008/02/16 21:16:04 tgl Exp $
  */
 
 #include "postgres_fe.h"
@@ -11,18 +11,17 @@
 #include "private.h"
 
 
-char *
+const char *
 scheck(const char *string, const char *format)
 {
 	char	   *fbuf;
 	const char *fp;
 	char	   *tp;
 	int			c;
-	char	   *result;
+	const char *result;
 	char		dummy;
-	static char nada;
 
-	result = &nada;
+	result = "";
 	if (string == NULL || format == NULL)
 		return result;
 	fbuf = imalloc((int) (2 * strlen(format) + 4));

src/timezone/strftime.c

@@ -15,7 +15,7 @@
  * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/timezone/strftime.c,v 1.11 2006/07/14 14:52:27 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/timezone/strftime.c,v 1.12 2008/02/16 21:16:04 tgl Exp $
  */
 
 #include "postgres.h"
@@ -92,6 +92,7 @@ static char *_add(const char *, char *, const char *);
 static char *_conv(int, const char *, char *, const char *);
 static char *_fmt(const char *, const struct pg_tm *, char *,
 	 const char *, int *);
+static char * _yconv(int, int, int, int, char *, const char *);
 
 #define IN_NONE 0
 #define IN_SOME 1
@@ -160,8 +161,8 @@ _fmt(const char *format, const struct pg_tm * t, char *pt, const char *ptlim,
 					 * ...whereas now POSIX 1003.2 calls for something
 					 * completely different. (ado, 1993-05-24)
 					 */
-					pt = _conv((t->tm_year + TM_YEAR_BASE) / 100,
-							   "%02d", pt, ptlim);
+					pt = _yconv(t->tm_year, TM_YEAR_BASE, 1, 0,
+								pt, ptlim);
 					continue;
 				case 'c':
 					{
@@ -308,11 +309,13 @@ _fmt(const char *format, const struct pg_tm * t, char *pt, const char *ptlim,
  */
 					{
 						int			year;
+						int			base;
 						int			yday;
 						int			wday;
 						int			w;
 
-						year = t->tm_year + TM_YEAR_BASE;
+						year = t->tm_year;
+						base = TM_YEAR_BASE;
 						yday = t->tm_yday;
 						wday = t->tm_wday;
 						for (;;)
@@ -321,7 +324,7 @@ _fmt(const char *format, const struct pg_tm * t, char *pt, const char *ptlim,
 							int			bot;
 							int			top;
 
-							len = isleap(year) ?
+							len = isleap_sum(year, base) ?
 								DAYSPERLYEAR :
 								DAYSPERNYEAR;
 
@@ -342,7 +345,7 @@ _fmt(const char *format, const struct pg_tm * t, char *pt, const char *ptlim,
 							top += len;
 							if (yday >= top)
 							{
-								++year;
+								++base;
 								w = 1;
 								break;
 							}
@@ -352,8 +355,8 @@ _fmt(const char *format, const struct pg_tm * t, char *pt, const char *ptlim,
 										 DAYSPERWEEK);
 								break;
 							}
-							--year;
-							yday += isleap(year) ?
+							--base;
+							yday += isleap_sum(year, base) ?
 								DAYSPERLYEAR :
 								DAYSPERNYEAR;
 						}
@@ -363,11 +366,11 @@ _fmt(const char *format, const struct pg_tm * t, char *pt, const char *ptlim,
 						else if (*format == 'g')
 						{
 							*warnp = IN_ALL;
-							pt = _conv(year % 100, "%02d",
+							pt = _yconv(year, base, 0, 1,
 									   pt, ptlim);
 						}
 						else
-							pt = _conv(year, "%04d",
+							pt = _yconv(year, base, 1, 1,
 									   pt, ptlim);
 					}
 					continue;
@@ -405,11 +408,11 @@ _fmt(const char *format, const struct pg_tm * t, char *pt, const char *ptlim,
 					continue;
 				case 'y':
 					*warnp = IN_ALL;
-					pt = _conv((t->tm_year + TM_YEAR_BASE) % 100,
-							   "%02d", pt, ptlim);
+					pt = _yconv(t->tm_year, TM_YEAR_BASE, 0, 1,
+								pt, ptlim);
 					continue;
 				case 'Y':
-					pt = _conv(t->tm_year + TM_YEAR_BASE, "%04d",
+					pt = _yconv(t->tm_year, TM_YEAR_BASE, 1, 1,
 								pt, ptlim);
 					continue;
 				case 'Z':
@@ -480,3 +483,43 @@ _add(const char *str, char *pt, const char *ptlim)
 		++pt;
 	return pt;
 }
+
+/*
+ * POSIX and the C Standard are unclear or inconsistent about
+ * what %C and %y do if the year is negative or exceeds 9999.
+ * Use the convention that %C concatenated with %y yields the
+ * same output as %Y, and that %Y contains at least 4 bytes,
+ * with more only if necessary.
+ */
+static char *
+_yconv(const int a, const int b, const int convert_top, 
+	   const int convert_yy, char *pt, const char * const ptlim)
+{
+	int    lead;
+	int    trail;
+ 
+#define DIVISOR       100
+	trail = a % DIVISOR + b % DIVISOR;
+	lead = a / DIVISOR + b / DIVISOR + trail / DIVISOR;
+	trail %= DIVISOR;
+	if (trail < 0 && lead > 0)
+	{
+		trail += DIVISOR;
+		--lead;
+	}
+	else if (lead < 0 && trail > 0)
+	{
+		trail -= DIVISOR;
+		++lead;
+	}
+	if (convert_top)
+	{
+		if (lead == 0 && trail < 0)
+			pt = _add("-0", pt, ptlim);
+		else    pt = _conv(lead, "%02d", pt, ptlim);
+	}
+	if (convert_yy)
+		pt = _conv(((trail < 0) ? -trail : trail), "%02d", pt, ptlim);
+	return pt;
+}
+ 

src/timezone/tzfile.h

@@ -3,10 +3,10 @@
 
 /*
  * This file is in the public domain, so clarified as of
- * 1996-06-05 by Arthur David Olson (arthur_david_olson@nih.gov).
+ * 1996-06-05 by Arthur David Olson.
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/timezone/tzfile.h,v 1.6 2005/10/15 02:49:51 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/timezone/tzfile.h,v 1.7 2008/02/16 21:16:04 tgl Exp $
  */
 
 /*
@@ -33,7 +33,8 @@
 struct tzhead
 {
 	char		tzh_magic[4];	/* TZ_MAGIC */
-	char		tzh_reserved[16];		/* reserved for future use */
+	char		tzh_version[1]; /* '\0' or '2' as of 2005 */
+	char		tzh_reserved[15];		/* reserved--must be zero */
 	char		tzh_ttisgmtcnt[4];		/* coded number of trans. time flags */
 	char		tzh_ttisstdcnt[4];		/* coded number of trans. time flags */
 	char		tzh_leapcnt[4]; /* coded number of leap seconds */
@@ -69,17 +70,21 @@ struct tzhead
  */
 
 /*
- * In the current implementation, "tzset()" refuses to deal with files that
- * exceed any of the limits below.
+ * If tzh_version is '2' or greater, the above is followed by a second instance
+ * of tzhead and a second instance of the data in which each coded transition
+ * time uses 8 rather than 4 chars,
+ * then a POSIX-TZ-environment-variable-style string for use in handling
+ * instants after the last transition time stored in the file
+ * (with nothing between the newlines if there is no POSIX representation for
+ * such instants).
  */
 
 /*
- * The TZ_MAX_TIMES value below is enough to handle a bit more than a
- * year's worth of solar time (corrected daily to the nearest second) or
- * 138 years of Pacific Presidential Election time
- * (where there are three time zone transitions every fourth year).
+ * In the current implementation, "tzset()" refuses to deal with files that
+ * exceed any of the limits below.
  */
-#define TZ_MAX_TIMES	370
+
+#define TZ_MAX_TIMES	1200
 
 #define TZ_MAX_TYPES	256		/* Limited by what (unsigned char)'s can hold */
 
@@ -124,11 +129,20 @@ struct tzhead
 #define EPOCH_YEAR	1970
 #define EPOCH_WDAY	TM_THURSDAY
 
+#define isleap(y) (((y) % 4) == 0 && (((y) % 100) != 0 || ((y) % 400) == 0))
+
 /*
- * Accurate only for the past couple of centuries;
- * that will probably do.
+ * Since everything in isleap is modulo 400 (or a factor of 400), we know that
+ *    isleap(y) == isleap(y % 400)
+ * and so
+ *    isleap(a + b) == isleap((a + b) % 400)
+ * or
+ *    isleap(a + b) == isleap(a % 400 + b % 400)
+ * This is true even if % means modulo rather than Fortran remainder
+ * (which is allowed by C89 but not C99).
+ * We use this to avoid addition overflow problems.
  */
 
-#define isleap(y) (((y) % 4) == 0 && (((y) % 100) != 0 || ((y) % 400) == 0))
+#define isleap_sum(a, b)      isleap((a) % 400 + (b) % 400)
 
 #endif   /* !defined TZFILE_H */