sync with OpenBSD -current

share/zoneinfo/Makefile

@@ -1,32 +1,49 @@
-#	$OpenBSD: Makefile,v 1.15 2020/10/07 22:33:31 millert Exp $
-#	$NetBSD: Makefile,v 1.14 1995/04/22 12:10:17 cgd Exp $
+#	$OpenBSD: Makefile,v 1.18 2023/11/18 07:18:07 anton Exp $
 
-# Change the line below for your time zone (after finding the zone you want in
-# the time zone files, or adding it to a time zone file).
-# Alternately, if you discover you've got the wrong time zone, you can just
-#	zic -l rightzone
-
-# This line has been moved to /usr/src/etc/Makefile
-LOCALTIME=	US/Pacific
-
-# If you want something other than Eastern United States time as a template
-# for handling POSIX-style time zone environment variables,
-# change the line below (after finding the zone you want in the
-# time zone files, or adding it to a time zone file).
-# Alternately, if you discover you've got the wrong time zone, you can just
-#	zic -p rightzone
+# DATAFORM selects the data format.  OpenBSD always uses "main"
+# Available formats represent essentially the same data, albeit
+# possibly with minor discrepancies that users are not likely to notice.
+# To get new features and the best data right away, use:
+#	DATAFORM=	vanguard
+# To wait a while before using new features, to give downstream users
+# time to upgrade zic (the default), use:
+#	DATAFORM=	main
+# To wait even longer for new features, use:
+#	DATAFORM=	rearguard
+# Rearguard users might also want "ZFLAGS = -b fat"; see below.
+DATAFORM=	main
 
+# The POSIXRULES macro controls interpretation of POSIX-like TZ
+# settings like TZ='EET-2EEST' that lack DST transition rules.
+# If POSIXRULES is '-', no template is installed; this is the default.
+# Any other value for POSIXRULES is obsolete and should not be relied on, as:
+# * It does not work correctly in popular implementations such as GNU/Linux.
+# * It does not work even in tzcode, except for historical timestamps
+#   that precede the last explicit transition in the POSIXRULES file.
+#   Hence it typically does not work for current and future timestamps.
+# If, despite the above, you want a template for handling these settings,
+# you can change the line below (after finding the timezone you want in the
+# one of the $(TDATA) source files, or adding it to a source file).
+# Alternatively, if you discover you've got the wrong timezone, you can just
+# 'zic -p -' to remove it, or 'zic -p rightzone' to change it.
+# Use the command
+#	make zonenames
+# to get a list of the values you can use for POSIXRULES.
 POSIXRULES=	US/Pacific
 
-# Use an absolute path name for TZDIR unless you're just testing the software.
-
+# "Compiled" timezone information is placed in the "TZDIR" directory
+# (and subdirectories).
+# TZDIR_BASENAME should not contain "/" and should not be ".", ".." or empty.
+TZDIR_BASENAME=	zoneinfo
 TZDIR=	${DESTDIR}/usr/share/zoneinfo
 
-# If you always want time values interpreted as "seconds since the epoch
-# (not counting leap seconds)", use
-# 	REDO=		posix_only
-# below.  If you always want right time values interpreted as "seconds since
-# the epoch" (counting leap seconds)", use
+# What kind of TZif data files to generate.  (TZif is the binary time
+# zone data format that zic generates; see Internet RFC 8536.)
+# If you want only POSIX time, with time values interpreted as
+# seconds since the epoch (not counting leap seconds), use
+#	REDO=		posix_only
+# below.  If you want only "right" time, with values interpreted
+# as seconds since the epoch (counting leap seconds), use
 #	REDO=		right_only
 # below.  If you want both sets of data available, with leap seconds not
 # counted normally, use
@@ -34,20 +51,66 @@ TZDIR=	${DESTDIR}/usr/share/zoneinfo
 # below.  If you want both sets of data available, with leap seconds counted
 # normally, use
 #	REDO=		right_posix
-# below.
-
+# below.  POSIX mandates that leap seconds not be counted; for compatibility
+# with it, use "posix_only" or "posix_right".  Use POSIX time on systems with
+# leap smearing; this can work better than unsmeared "right" time with
+# applications that are not leap second aware, and is closer to unsmeared
+# "right" time than unsmeared POSIX time is (e.g., 0.5 vs 1.0 s max error).
 REDO=		posix_only
 
+# Whether to put an "Expires" line in the leapseconds file.
+# Use EXPIRES_LINE=1 to put the line in, 0 to omit it.
+# The EXPIRES_LINE value matters only if REDO's value contains "right".
+# If you change EXPIRES_LINE, remove the leapseconds file before running "make".
+# zic's support for the Expires line was introduced in tzdb 2020a,
+# and was modified in tzdb 2021b to generate version 4 TZif files.
+# EXPIRES_LINE defaults to 0 for now so that the leapseconds file
+# can be given to pre-2020a zic implementations and so that TZif files
+# built by newer zic implementations can be read by pre-2021b libraries.
+EXPIRES_LINE=	0
+
+# To install data in text form that has all the information of the TZif data,
+# (optionally incorporating leap second information), use
+#	TZDATA_TEXT=	tzdata.zi leapseconds
+# To install text data without leap second information (e.g., because
+# REDO='posix_only'), use
+#	TZDATA_TEXT=	tzdata.zi
+# To avoid installing text data, use
+#	TZDATA_TEXT=
+TZDATA_TEXT=	leapseconds tzdata.zi
+
 TDATA=		africa antarctica asia australasia \
 		europe northamerica southamerica etcetera factory \
 		backward
-TABDATA=	iso3166.tab zone.tab zone1970.tab
-DATA=		$(TDATA) $(TABDATA) leapseconds
-USNO=		usno1988 usno1989 usno1989a usno1995 usno1997
+TABDATA=	iso3166.tab zone.tab zone1970.tab $(TZDATA_TEXT)
+DATA=		$(TDATA) $(TABDATA)
+DSTDATA_ZI_DEPS= ziguard.awk $(TDATA)
 
 ZIC=		zic
 
-all:
+all: leapseconds tzdata.zi
+
+$(DATAFORM).zi:	$(DSTDATA_ZI_DEPS)
+		(cd ${.CURDIR}/datfiles && \
+		    awk -v DATAFORM=`expr $@ : '\(.*\).zi'` -f ../ziguard.awk \
+		    $(TDATA) >${.OBJDIR}/$@.out)
+		mv -f ${.OBJDIR}/$@.out ${.OBJDIR}/$@
+
+tzdata.zi:	$(DATAFORM).zi version zishrink.awk
+		(cd ${.CURDIR}/datfiles && version=`sed 1q ../version` && \
+		  LC_ALL=C awk \
+		    -v dataform='$(DATAFORM)' \
+		    -v deps='$(DSTDATA_ZI_DEPS) zishrink.awk' \
+		    -v redo='$(REDO)' \
+		    -v version="$$version" \
+		    -f ../zishrink.awk \
+		    ${.OBJDIR}/$(DATAFORM).zi >${.OBJDIR}/$@.out)
+		mv -f ${.OBJDIR}/$@.out ${.OBJDIR}/$@
+
+leapseconds: leapseconds.awk datfiles/leap-seconds.list
+	awk -v EXPIRES_LINE=$(EXPIRES_LINE) -f ${.CURDIR}/leapseconds.awk \
+	    ${.CURDIR}/datfiles/leap-seconds.list >${.OBJDIR}/$@.out
+	mv -f ${.OBJDIR}/$@.out ${.OBJDIR}/$@
 
 posix_only: ${TDATA}
 	(cd ${.CURDIR}/datfiles; \
@@ -61,7 +124,7 @@ other_two: leapseconds ${TDATA}
 	(cd ${.CURDIR}/datfiles; \
 	    ${ZIC} -d ${TZDIR}/posix -L /dev/null ${TDATA})
 	(cd ${.CURDIR}/datfiles; \
-	    ${ZIC} -d ${TZDIR}/right -L leapseconds ${TDATA})
+	    ${ZIC} -d ${TZDIR}/right -L ${.OBJDIR}/leapseconds ${TDATA})
 
 posix_right: posix_only other_two
 
@@ -76,11 +139,19 @@ realinstall: ${DATA} ${REDO}
 		-type d -exec chmod a=rx,u+w {} +
 	${INSTALL} -c -o root -g bin -m 644 ${.CURDIR}/datfiles/iso3166.tab \
 	    ${DESTDIR}/usr/share/misc
+	${INSTALL} -c -o root -g bin -m 644 leapseconds \
+	    ${DESTDIR}/usr/share/zoneinfo
+	${INSTALL} -c -o root -g bin -m 644 ${.CURDIR}/datfiles/leap-seconds.list \
+	    ${DESTDIR}/usr/share/zoneinfo
+	${INSTALL} -c -o root -g bin -m 644 tzdata.zi \
+	    ${DESTDIR}/usr/share/zoneinfo
 	${INSTALL} -c -o root -g bin -m 644 ${.CURDIR}/datfiles/zone.tab \
 	    ${DESTDIR}/usr/share/zoneinfo
 	${INSTALL} -c -o root -g bin -m 644 ${.CURDIR}/datfiles/zone1970.tab \
 	    ${DESTDIR}/usr/share/zoneinfo
 
+clean:
+	rm -f leapseconds *.zi
 
 .PATH:	${.CURDIR}/datfiles
 .include <bsd.prog.mk>

share/zoneinfo/datfiles/leap-seconds.list

@@ -0,0 +1,256 @@
+#	$OpenBSD: leap-seconds.list,v 1.1 2023/11/17 21:51:37 millert Exp $
+#
+#	In the following text, the symbol '#' introduces
+#	a comment, which continues from that symbol until
+#	the end of the line. A plain comment line has a
+#	whitespace character following the comment indicator.
+#	There are also special comment lines defined below.
+#	A special comment will always have a non-whitespace
+#	character in column 2.
+#
+#	A blank line should be ignored.
+#
+#	The following table shows the corrections that must
+#	be applied to compute International Atomic Time (TAI)
+#	from the Coordinated Universal Time (UTC) values that
+#	are transmitted by almost all time services.
+#
+#	The first column shows an epoch as a number of seconds
+#	since 1 January 1900, 00:00:00 (1900.0 is also used to
+#	indicate the same epoch.) Both of these time stamp formats
+#	ignore the complexities of the time scales that were
+#	used before the current definition of UTC at the start
+#	of 1972. (See note 3 below.)
+#	The second column shows the number of seconds that
+#	must be added to UTC to compute TAI for any timestamp
+#	at or after that epoch. The value on each line is
+#	valid from the indicated initial instant until the
+#	epoch given on the next one or indefinitely into the
+#	future if there is no next line.
+#	(The comment on each line shows the representation of
+#	the corresponding initial epoch in the usual
+#	day-month-year format. The epoch always begins at
+#	00:00:00 UTC on the indicated day. See Note 5 below.)
+#
+#	Important notes:
+#
+#	1. Coordinated Universal Time (UTC) is often referred to
+#	as Greenwich Mean Time (GMT). The GMT time scale is no
+#	longer used, and the use of GMT to designate UTC is
+#	discouraged.
+#
+#	2. The UTC time scale is realized by many national
+#	laboratories and timing centers. Each laboratory
+#	identifies its realization with its name: Thus
+#	UTC(NIST), UTC(USNO), etc. The differences among
+#	these different realizations are typically on the
+#	order of a few nanoseconds (i.e., 0.000 000 00x s)
+#	and can be ignored for many purposes. These differences
+#	are tabulated in Circular T, which is published monthly
+#	by the International Bureau of Weights and Measures
+#	(BIPM). See www.bipm.org for more information.
+#
+#	3. The current definition of the relationship between UTC
+#	and TAI dates from 1 January 1972. A number of different
+#	time scales were in use before that epoch, and it can be
+#	quite difficult to compute precise timestamps and time
+#	intervals in those "prehistoric" days. For more information,
+#	consult:
+#
+#		The Explanatory Supplement to the Astronomical
+#		Ephemeris.
+#	or
+#		Terry Quinn, "The BIPM and the Accurate Measurement
+#		of Time," Proc. of the IEEE, Vol. 79, pp. 894-905,
+#		July, 1991. <http://dx.doi.org/10.1109/5.84965>
+#		reprinted in:
+#		   Christine Hackman and Donald B Sullivan (eds.)
+#		   Time and Frequency Measurement
+#		   American Association of Physics Teachers (1996)
+#		   <http://tf.nist.gov/general/pdf/1168.pdf>, pp. 75-86
+#
+#	4. The decision to insert a leap second into UTC is currently
+#	the responsibility of the International Earth Rotation and
+#	Reference Systems Service. (The name was changed from the
+#	International Earth Rotation Service, but the acronym IERS
+#	is still used.)
+#
+#	Leap seconds are announced by the IERS in its Bulletin C.
+#
+#	See www.iers.org for more details.
+#
+#	Every national laboratory and timing center uses the
+#	data from the BIPM and the IERS to construct UTC(lab),
+#	their local realization of UTC.
+#
+#	Although the definition also includes the possibility
+#	of dropping seconds ("negative" leap seconds), this has
+#	never been done and is unlikely to be necessary in the
+#	foreseeable future.
+#
+#	5. If your system keeps time as the number of seconds since
+#	some epoch (e.g., NTP timestamps), then the algorithm for
+#	assigning a UTC time stamp to an event that happens during a positive
+#	leap second is not well defined. The official name of that leap
+#	second is 23:59:60, but there is no way of representing that time
+#	in these systems.
+#	Many systems of this type effectively stop the system clock for
+#	one second during the leap second and use a time that is equivalent
+#	to 23:59:59 UTC twice. For these systems, the corresponding TAI
+#	timestamp would be obtained by advancing to the next entry in the
+#	following table when the time equivalent to 23:59:59 UTC
+#	is used for the second time. Thus the leap second which
+#	occurred on 30 June 1972 at 23:59:59 UTC would have TAI
+#	timestamps computed as follows:
+#
+#	...
+#	30 June 1972 23:59:59 (2287785599, first time):	TAI= UTC + 10 seconds
+#	30 June 1972 23:59:60 (2287785599,second time):	TAI= UTC + 11 seconds
+#	1  July 1972 00:00:00 (2287785600)		TAI= UTC + 11 seconds
+#	...
+#
+#	If your system realizes the leap second by repeating 00:00:00 UTC twice
+#	(this is possible but not usual), then the advance to the next entry
+#	in the table must occur the second time that a time equivalent to
+#	00:00:00 UTC is used. Thus, using the same example as above:
+#
+#	...
+#       30 June 1972 23:59:59 (2287785599):		TAI= UTC + 10 seconds
+#       30 June 1972 23:59:60 (2287785600, first time):	TAI= UTC + 10 seconds
+#       1  July 1972 00:00:00 (2287785600,second time):	TAI= UTC + 11 seconds
+#	...
+#
+#	in both cases the use of timestamps based on TAI produces a smooth
+#	time scale with no discontinuity in the time interval. However,
+#	although the long-term behavior of the time scale is correct in both
+#	methods, the second method is technically not correct because it adds
+#	the extra second to the wrong day.
+#
+#	This complexity would not be needed for negative leap seconds (if they
+#	are ever used). The UTC time would skip 23:59:59 and advance from
+#	23:59:58 to 00:00:00 in that case. The TAI offset would decrease by
+#	1 second at the same instant. This is a much easier situation to deal
+#	with, since the difficulty of unambiguously representing the epoch
+#	during the leap second does not arise.
+#
+#	Some systems implement leap seconds by amortizing the leap second
+#	over the last few minutes of the day. The frequency of the local
+#	clock is decreased (or increased) to realize the positive (or
+#	negative) leap second. This method removes the time step described
+#	above. Although the long-term behavior of the time scale is correct
+#	in this case, this method introduces an error during the adjustment
+#	period both in time and in frequency with respect to the official
+#	definition of UTC.
+#
+#	Questions or comments to:
+#		Judah Levine
+#		Time and Frequency Division
+#		NIST
+#		Boulder, Colorado
+#		Judah.Levine@nist.gov
+#
+#	Last Update of leap second values:   8 July 2016
+#
+#	The following line shows this last update date in NTP timestamp
+#	format. This is the date on which the most recent change to
+#	the leap second data was added to the file. This line can
+#	be identified by the unique pair of characters in the first two
+#	columns as shown below.
+#
+#$	 3676924800
+#
+#	The NTP timestamps are in units of seconds since the NTP epoch,
+#	which is 1 January 1900, 00:00:00. The Modified Julian Day number
+#	corresponding to the NTP time stamp, X, can be computed as
+#
+#	X/86400 + 15020
+#
+#	where the first term converts seconds to days and the second
+#	term adds the MJD corresponding to the time origin defined above.
+#	The integer portion of the result is the integer MJD for that
+#	day, and any remainder is the time of day, expressed as the
+#	fraction of the day since 0 hours UTC. The conversion from day
+#	fraction to seconds or to hours, minutes, and seconds may involve
+#	rounding or truncation, depending on the method used in the
+#	computation.
+#
+#	The data in this file will be updated periodically as new leap
+#	seconds are announced. In addition to being entered on the line
+#	above, the update time (in NTP format) will be added to the basic
+#	file name leap-seconds to form the name leap-seconds.<NTP TIME>.
+#	In addition, the generic name leap-seconds.list will always point to
+#	the most recent version of the file.
+#
+#	This update procedure will be performed only when a new leap second
+#	is announced.
+#
+#	The following entry specifies the expiration date of the data
+#	in this file in units of seconds since the origin at the instant
+#	1 January 1900, 00:00:00. This expiration date will be changed
+#	at least twice per year whether or not a new leap second is
+#	announced. These semi-annual changes will be made no later
+#	than 1 June and 1 December of each year to indicate what
+#	action (if any) is to be taken on 30 June and 31 December,
+#	respectively. (These are the customary effective dates for new
+#	leap seconds.) This expiration date will be identified by a
+#	unique pair of characters in columns 1 and 2 as shown below.
+#	In the unlikely event that a leap second is announced with an
+#	effective date other than 30 June or 31 December, then this
+#	file will be edited to include that leap second as soon as it is
+#	announced or at least one month before the effective date
+#	(whichever is later).
+#	If an announcement by the IERS specifies that no leap second is
+#	scheduled, then only the expiration date of the file will
+#	be advanced to show that the information in the file is still
+#	current -- the update time stamp, the data and the name of the file
+#	will not change.
+#
+#	Updated through IERS Bulletin C65
+#	File expires on:  28 December 2023
+#
+#@	3912710400
+#
+2272060800	10	# 1 Jan 1972
+2287785600	11	# 1 Jul 1972
+2303683200	12	# 1 Jan 1973
+2335219200	13	# 1 Jan 1974
+2366755200	14	# 1 Jan 1975
+2398291200	15	# 1 Jan 1976
+2429913600	16	# 1 Jan 1977
+2461449600	17	# 1 Jan 1978
+2492985600	18	# 1 Jan 1979
+2524521600	19	# 1 Jan 1980
+2571782400	20	# 1 Jul 1981
+2603318400	21	# 1 Jul 1982
+2634854400	22	# 1 Jul 1983
+2698012800	23	# 1 Jul 1985
+2776982400	24	# 1 Jan 1988
+2840140800	25	# 1 Jan 1990
+2871676800	26	# 1 Jan 1991
+2918937600	27	# 1 Jul 1992
+2950473600	28	# 1 Jul 1993
+2982009600	29	# 1 Jul 1994
+3029443200	30	# 1 Jan 1996
+3076704000	31	# 1 Jul 1997
+3124137600	32	# 1 Jan 1999
+3345062400	33	# 1 Jan 2006
+3439756800	34	# 1 Jan 2009
+3550089600	35	# 1 Jul 2012
+3644697600	36	# 1 Jul 2015
+3692217600	37	# 1 Jan 2017
+#
+#	the following special comment contains the
+#	hash value of the data in this file computed
+#	use the secure hash algorithm as specified
+#	by FIPS 180-1. See the files in ~/pub/sha for
+#	the details of how this hash value is
+#	computed. Note that the hash computation
+#	ignores comments and whitespace characters
+#	in data lines. It includes the NTP values
+#	of both the last modification time and the
+#	expiration time of the file, but not the
+#	white space on those lines.
+#	the hash line is also ignored in the
+#	computation.
+#
+#h 	e76a99dc 65f15cc7 e613e040 f5078b5e b23834fe

share/zoneinfo/datfiles/leapseconds

@@ -1,83 +0,0 @@
-# $OpenBSD: leapseconds,v 1.48 2023/03/23 16:12:11 millert Exp $
-# Allowance for leap seconds added to each time zone file.
-
-# This file is in the public domain.
-
-# This file is generated automatically from the data in the public-domain
-# NIST format leap-seconds.list file, which can be copied from
-# <ftp://ftp.nist.gov/pub/time/leap-seconds.list>
-# or <ftp://ftp.boulder.nist.gov/pub/time/leap-seconds.list>.
-# The NIST file is used instead of its IERS upstream counterpart
-# <https://hpiers.obspm.fr/iers/bul/bulc/ntp/leap-seconds.list>
-# because under US law the NIST file is public domain
-# whereas the IERS file's copyright and license status is unclear.
-# For more about leap-seconds.list, please see
-# The NTP Timescale and Leap Seconds
-# <https://www.eecis.udel.edu/~mills/leap.html>.
-
-# The rules for leap seconds are specified in Annex 1 (Time scales) of:
-# Standard-frequency and time-signal emissions.
-# International Telecommunication Union - Radiocommunication Sector
-# (ITU-R) Recommendation TF.460-6 (02/2002)
-# <https://www.itu.int/rec/R-REC-TF.460-6-200202-I/>.
-# The International Earth Rotation and Reference Systems Service (IERS)
-# periodically uses leap seconds to keep UTC to within 0.9 s of UT1
-# (a proxy for Earth's angle in space as measured by astronomers)
-# and publishes leap second data in a copyrighted file
-# <https://hpiers.obspm.fr/iers/bul/bulc/Leap_Second.dat>.
-# See: Levine J. Coordinated Universal Time and the leap second.
-# URSI Radio Sci Bull. 2016;89(4):30-6. doi:10.23919/URSIRSB.2016.7909995
-# <https://ieeexplore.ieee.org/document/7909995>.
-
-# There were no leap seconds before 1972, as no official mechanism
-# accounted for the discrepancy between atomic time (TAI) and the earth's
-# rotation.  The first ("1 Jan 1972") data line in leap-seconds.list
-# does not denote a leap second; it denotes the start of the current definition
-# of UTC.
-
-# All leap-seconds are Stationary (S) at the given UTC time.
-# The correction (+ or -) is made at the given time, so in the unlikely
-# event of a negative leap second, a line would look like this:
-# Leap	YEAR	MON	DAY	23:59:59	-	S
-# Typical lines look like this:
-# Leap	YEAR	MON	DAY	23:59:60	+	S
-Leap	1972	Jun	30	23:59:60	+	S
-Leap	1972	Dec	31	23:59:60	+	S
-Leap	1973	Dec	31	23:59:60	+	S
-Leap	1974	Dec	31	23:59:60	+	S
-Leap	1975	Dec	31	23:59:60	+	S
-Leap	1976	Dec	31	23:59:60	+	S
-Leap	1977	Dec	31	23:59:60	+	S
-Leap	1978	Dec	31	23:59:60	+	S
-Leap	1979	Dec	31	23:59:60	+	S
-Leap	1981	Jun	30	23:59:60	+	S
-Leap	1982	Jun	30	23:59:60	+	S
-Leap	1983	Jun	30	23:59:60	+	S
-Leap	1985	Jun	30	23:59:60	+	S
-Leap	1987	Dec	31	23:59:60	+	S
-Leap	1989	Dec	31	23:59:60	+	S
-Leap	1990	Dec	31	23:59:60	+	S
-Leap	1992	Jun	30	23:59:60	+	S
-Leap	1993	Jun	30	23:59:60	+	S
-Leap	1994	Jun	30	23:59:60	+	S
-Leap	1995	Dec	31	23:59:60	+	S
-Leap	1997	Jun	30	23:59:60	+	S
-Leap	1998	Dec	31	23:59:60	+	S
-Leap	2005	Dec	31	23:59:60	+	S
-Leap	2008	Dec	31	23:59:60	+	S
-Leap	2012	Jun	30	23:59:60	+	S
-Leap	2015	Jun	30	23:59:60	+	S
-Leap	2016	Dec	31	23:59:60	+	S
-
-# UTC timestamp when this leap second list expires.
-# Any additional leap seconds will come after this.
-# This Expires line is commented out for now,
-# so that pre-2020a zic implementations do not reject this file.
-#Expires 2023	Dec	28	00:00:00
-
-# POSIX timestamps for the data in this file:
-#updated 1467936000 (2016-07-08 00:00:00 UTC)
-#expires 1703721600 (2023-12-28 00:00:00 UTC)
-
-#	Updated through IERS Bulletin C65
-#	File expires on:  28 December 2023

share/zoneinfo/leapseconds.awk

@@ -0,0 +1,252 @@
+# Generate zic format 'leapseconds' from NIST format 'leap-seconds.list'.
+
+# This file is in the public domain.
+
+# This program uses awk arithmetic.  POSIX requires awk to support
+# exact integer arithmetic only through 10**10, which means for NTP
+# timestamps this program works only to the year 2216, which is the
+# year 1900 plus 10**10 seconds.  However, in practice
+# POSIX-conforming awk implementations invariably use IEEE-754 double
+# and so support exact integers through 2**53.  By the year 2216,
+# POSIX will almost surely require at least 2**53 for awk, so for NTP
+# timestamps this program should be good until the year 285,428,681
+# (the year 1900 plus 2**53 seconds).  By then leap seconds will be
+# long obsolete, as the Earth will likely slow down so much that
+# there will be more than 25 hours per day and so some other scheme
+# will be needed.
+
+BEGIN {
+  print "# Allowance for leap seconds added to each time zone file."
+  print ""
+  print "# This file is in the public domain."
+  print ""
+  print "# This file is generated automatically from the data in the public-domain"
+  print "# NIST format leap-seconds.list file, which can be copied from"
+  print "# <ftp://ftp.nist.gov/pub/time/leap-seconds.list>"
+  print "# or <ftp://ftp.boulder.nist.gov/pub/time/leap-seconds.list>."
+  print "# The NIST file is used instead of its IERS upstream counterpart"
+  print "# <https://hpiers.obspm.fr/iers/bul/bulc/ntp/leap-seconds.list>"
+  print "# because under US law the NIST file is public domain"
+  print "# whereas the IERS file's copyright and license status is unclear."
+  print "# For more about leap-seconds.list, please see"
+  print "# The NTP Timescale and Leap Seconds"
+  print "# <https://www.eecis.udel.edu/~mills/leap.html>."
+  print ""
+  print "# The rules for leap seconds are specified in Annex 1 (Time scales) of:"
+  print "# Standard-frequency and time-signal emissions."
+  print "# International Telecommunication Union - Radiocommunication Sector"
+  print "# (ITU-R) Recommendation TF.460-6 (02/2002)"
+  print "# <https://www.itu.int/rec/R-REC-TF.460-6-200202-I/>."
+  print "# The International Earth Rotation and Reference Systems Service (IERS)"
+  print "# periodically uses leap seconds to keep UTC to within 0.9 s of UT1"
+  print "# (a proxy for Earth's angle in space as measured by astronomers)"
+  print "# and publishes leap second data in a copyrighted file"
+  print "# <https://hpiers.obspm.fr/iers/bul/bulc/Leap_Second.dat>."
+  print "# See: Levine J. Coordinated Universal Time and the leap second."
+  print "# URSI Radio Sci Bull. 2016;89(4):30-6. doi:10.23919/URSIRSB.2016.7909995"
+  print "# <https://ieeexplore.ieee.org/document/7909995>."
+  print ""
+  print "# There were no leap seconds before 1972, as no official mechanism"
+  print "# accounted for the discrepancy between atomic time (TAI) and the earth's"
+  print "# rotation.  The first (\"1 Jan 1972\") data line in leap-seconds.list"
+  print "# does not denote a leap second; it denotes the start of the current definition"
+  print "# of UTC."
+  print ""
+  print "# All leap-seconds are Stationary (S) at the given UTC time."
+  print "# The correction (+ or -) is made at the given time, so in the unlikely"
+  print "# event of a negative leap second, a line would look like this:"
+  print "# Leap	YEAR	MON	DAY	23:59:59	-	S"
+  print "# Typical lines look like this:"
+  print "# Leap	YEAR	MON	DAY	23:59:60	+	S"
+
+  monthabbr[ 1] = "Jan"
+  monthabbr[ 2] = "Feb"
+  monthabbr[ 3] = "Mar"
+  monthabbr[ 4] = "Apr"
+  monthabbr[ 5] = "May"
+  monthabbr[ 6] = "Jun"
+  monthabbr[ 7] = "Jul"
+  monthabbr[ 8] = "Aug"
+  monthabbr[ 9] = "Sep"
+  monthabbr[10] = "Oct"
+  monthabbr[11] = "Nov"
+  monthabbr[12] = "Dec"
+
+  sstamp_init()
+}
+
+# In case the input has CRLF form a la NIST.
+{ sub(/\r$/, "") }
+
+/^#[ \t]*[Uu]pdated through/ || /^#[ \t]*[Ff]ile expires on/ {
+    last_lines = last_lines $0 "\n"
+}
+
+/^#[$][ \t]/ { updated = $2 }
+/^#[@][ \t]/ { expires = $2 }
+
+/^[ \t]*#/ { next }
+
+{
+    NTP_timestamp = $1
+    TAI_minus_UTC = $2
+    if (old_TAI_minus_UTC) {
+	if (old_TAI_minus_UTC < TAI_minus_UTC) {
+	    sign = "23:59:60\t+"
+	} else {
+	    sign = "23:59:59\t-"
+	}
+	sstamp_to_ymdhMs(NTP_timestamp - 1, ss_NTP)
+	printf "Leap\t%d\t%s\t%d\t%s\tS\n", \
+	  ss_year, monthabbr[ss_month], ss_mday, sign
+    }
+    old_TAI_minus_UTC = TAI_minus_UTC
+}
+
+END {
+    print ""
+
+    if (expires) {
+      sstamp_to_ymdhMs(expires, ss_NTP)
+
+      print "# UTC timestamp when this leap second list expires."
+      print "# Any additional leap seconds will come after this."
+      if (! EXPIRES_LINE) {
+	print "# This Expires line is commented out for now,"
+	print "# so that pre-2020a zic implementations do not reject this file."
+      }
+      printf "%sExpires %.4d\t%s\t%.2d\t%.2d:%.2d:%.2d\n", \
+	EXPIRES_LINE ? "" : "#", \
+	ss_year, monthabbr[ss_month], ss_mday, ss_hour, ss_min, ss_sec
+    } else {
+      print "# (No Expires line, since the expires time is unknown.)"
+    }
+
+    # The difference between the NTP and POSIX epochs is 70 years
+    # (including 17 leap days), each 24 hours of 60 minutes of 60
+    # seconds each.
+    epoch_minus_NTP = ((1970 - 1900) * 365 + 17) * 24 * 60 * 60
+
+    print ""
+    print "# POSIX timestamps for the data in this file:"
+    if (updated) {
+      sstamp_to_ymdhMs(updated, ss_NTP)
+      printf "#updated %d (%.4d-%.2d-%.2d %.2d:%.2d:%.2d UTC)\n", \
+	updated - epoch_minus_NTP, \
+	ss_year, ss_month, ss_mday, ss_hour, ss_min, ss_sec
+    } else {
+      print "#(updated time unknown)"
+    }
+    if (expires) {
+      sstamp_to_ymdhMs(expires, ss_NTP)
+      printf "#expires %d (%.4d-%.2d-%.2d %.2d:%.2d:%.2d UTC)\n", \
+	expires - epoch_minus_NTP, \
+	ss_year, ss_month, ss_mday, ss_hour, ss_min, ss_sec
+    } else {
+      print "#(expires time unknown)"
+    }
+    printf "\n%s", last_lines
+}
+
+# sstamp_to_ymdhMs - convert seconds timestamp to date and time
+#
+# Call as:
+#
+#    sstamp_to_ymdhMs(sstamp, epoch_days)
+#
+# where:
+#
+#    sstamp - is the seconds timestamp.
+#    epoch_days - is the timestamp epoch in Gregorian days since 1600-03-01.
+#	ss_NTP is appropriate for an NTP sstamp.
+#
+# Both arguments should be nonnegative integers.
+# On return, the following variables are set based on sstamp:
+#
+#    ss_year	- Gregorian calendar year
+#    ss_month	- month of the year (1-January to 12-December)
+#    ss_mday	- day of the month (1-31)
+#    ss_hour	- hour (0-23)
+#    ss_min	- minute (0-59)
+#    ss_sec	- second (0-59)
+#    ss_wday	- day of week (0-Sunday to 6-Saturday)
+#
+# The function sstamp_init should be called prior to using sstamp_to_ymdhMs.
+
+function sstamp_init()
+{
+  # Days in month N, where March is month 0 and January month 10.
+  ss_mon_days[ 0] = 31
+  ss_mon_days[ 1] = 30
+  ss_mon_days[ 2] = 31
+  ss_mon_days[ 3] = 30
+  ss_mon_days[ 4] = 31
+  ss_mon_days[ 5] = 31
+  ss_mon_days[ 6] = 30
+  ss_mon_days[ 7] = 31
+  ss_mon_days[ 8] = 30
+  ss_mon_days[ 9] = 31
+  ss_mon_days[10] = 31
+
+  # Counts of days in a Gregorian year, quad-year, century, and quad-century.
+  ss_year_days = 365
+  ss_quadyear_days = ss_year_days * 4 + 1
+  ss_century_days = ss_quadyear_days * 25 - 1
+  ss_quadcentury_days = ss_century_days * 4 + 1
+
+  # Standard day epochs, suitable for epoch_days.
+  # ss_MJD = 94493
+  # ss_POSIX = 135080
+  ss_NTP = 109513
+}
+
+function sstamp_to_ymdhMs(sstamp, epoch_days, \
+			  quadcentury, century, quadyear, year, month, day)
+{
+  ss_hour = int(sstamp / 3600) % 24
+  ss_min = int(sstamp / 60) % 60
+  ss_sec = sstamp % 60
+
+  # Start with a count of days since 1600-03-01 Gregorian.
+  day = epoch_days + int(sstamp / (24 * 60 * 60))
+
+  # Compute a year-month-day date with days of the month numbered
+  # 0-30, months (March-February) numbered 0-11, and years that start
+  # start March 1 and end after the last day of February.  A quad-year
+  # starts on March 1 of a year evenly divisible by 4 and ends after
+  # the last day of February 4 years later.  A century starts on and
+  # ends before March 1 in years evenly divisible by 100.
+  # A quad-century starts on and ends before March 1 in years divisible
+  # by 400.  While the number of days in a quad-century is a constant,
+  # the number of days in each other time period can vary by 1.
+  # Any variation is in the last day of the time period (there might
+  # or might not be a February 29) where it is easy to deal with.
+
+  quadcentury = int(day / ss_quadcentury_days)
+  day -= quadcentury * ss_quadcentury_days
+  ss_wday = (day + 3) % 7
+  century = int(day / ss_century_days)
+  century -= century == 4
+  day -= century * ss_century_days
+  quadyear = int(day / ss_quadyear_days)
+  day -= quadyear * ss_quadyear_days
+  year = int(day / ss_year_days)
+  year -= year == 4
+  day -= year * ss_year_days
+  for (month = 0; month < 11; month++) {
+    if (day < ss_mon_days[month])
+      break
+    day -= ss_mon_days[month]
+  }
+
+  # Convert the date to a conventional day of month (1-31),
+  # month (1-12, January-December) and Gregorian year.
+  ss_mday = day + 1
+  if (month <= 9) {
+    ss_month = month + 3
+  } else {
+    ss_month = month - 9
+    year++
+  }
+  ss_year = 1600 + quadcentury * 400 + century * 100 + quadyear * 4 + year
+}

share/zoneinfo/version

@@ -0,0 +1 @@
+2023cgtz

share/zoneinfo/ziguard.awk

@@ -0,0 +1,386 @@
+# Convert tzdata source into vanguard or rearguard form.
+
+# Contributed by Paul Eggert.  This file is in the public domain.
+
+# This is not a general-purpose converter; it is designed for current tzdata.
+# It just converts from current source to main, vanguard, and rearguard forms.
+# Although it might be nice for it to be idempotent, or to be useful
+# for converting back and forth between vanguard and rearguard formats,
+# it does not do these nonessential tasks now.
+#
+# Although main and vanguard forms are currently equivalent,
+# this need not always be the case.  When the two forms differ,
+# this script can convert either from main to vanguard form (needed then),
+# or from vanguard to main form (this conversion would be needed later,
+# after main became rearguard and vanguard became main).
+# There is no need to convert rearguard to other forms.
+#
+# When converting to vanguard form, the output can use the line
+# "Zone GMT 0 - GMT" which TZUpdater 2.3.2 mistakenly rejects.
+#
+# When converting to vanguard form, the output can use negative SAVE
+# values.
+#
+# When converting to rearguard form, the output uses only nonnegative
+# SAVE values.  The idea is for the output data to simulate the behavior
+# of the input data as best it can within the constraints of the
+# rearguard format.
+
+# Given a FIELD like "-0:30", return a minute count like -30.
+function get_minutes(field, \
+		     sign, hours, minutes)
+{
+  sign = field ~ /^-/ ? -1 : 1
+  hours = +field
+  if (field ~ /:/) {
+    minutes = field
+    sub(/[^:]*:/, "", minutes)
+  }
+  return 60 * hours + sign * minutes
+}
+
+# Given an OFFSET, which is a minute count like 300 or 330,
+# return a %z-style abbreviation like "+05" or "+0530".
+function offset_abbr(offset, \
+		     hours, minutes, sign)
+{
+  hours = int(offset / 60)
+  minutes = offset % 60
+  if (minutes) {
+    return sprintf("%+.4d", hours * 100 + minutes);
+  } else {
+    return sprintf("%+.2d", hours)
+  }
+}
+
+# Round TIMESTAMP (a +-hh:mm:ss.dddd string) to the nearest second.
+function round_to_second(timestamp, \
+			 hh, mm, ss, seconds, dot_dddd, subseconds)
+{
+  dot_dddd = timestamp
+  if (!sub(/^[+-]?[0-9]+:[0-9]+:[0-9]+\./, ".", dot_dddd))
+    return timestamp
+  hh = mm = ss = timestamp
+  sub(/^[-+]?[0-9]+:[0-9]+:/, "", ss)
+  sub(/^[-+]?[0-9]+:/, "", mm)
+  sub(/^[-+]?/, "", hh)
+  seconds = 3600 * hh + 60 * mm + ss
+  subseconds = +dot_dddd
+  seconds += 0.5 < subseconds || ((subseconds == 0.5) && (seconds % 2));
+  return sprintf("%s%d:%.2d:%.2d", timestamp ~ /^-/ ? "-" : "", \
+		 seconds / 3600, seconds / 60 % 60, seconds % 60)
+}
+
+BEGIN {
+  dataform_type["vanguard"] = 1
+  dataform_type["main"] = 1
+  dataform_type["rearguard"] = 1
+
+  if (PACKRATLIST) {
+    while (getline <PACKRATLIST) {
+      if ($0 ~ /^#/) continue
+      packratlist[$3] = 1
+    }
+  }
+
+  # The command line should set DATAFORM.
+  if (!dataform_type[DATAFORM]) exit 1
+}
+
+$1 == "#PACKRATLIST" && $2 == PACKRATLIST {
+  sub(/^#PACKRATLIST[\t ]+[^\t ]+[\t ]+/, "")
+}
+
+/^Zone/ { zone = $2 }
+
+DATAFORM != "main" {
+  in_comment = $0 ~ /^#/
+  uncomment = comment_out = 0
+
+  # If this line should differ due to Czechoslovakia using negative SAVE values,
+  # uncomment the desired version and comment out the undesired one.
+  if (zone == "Europe/Prague" && $0 ~ /^#?[\t ]+[01]:00[\t ]/ \
+      && $0 ~ /1947 Feb 23/) {
+    if (($(in_comment + 2) != "-") == (DATAFORM != "rearguard")) {
+      uncomment = in_comment
+    } else {
+      comment_out = !in_comment
+    }
+  }
+
+  # If this line should differ due to Ireland using negative SAVE values,
+  # uncomment the desired version and comment out the undesired one.
+  Rule_Eire = $0 ~ /^#?Rule[\t ]+Eire[\t ]/
+  Zone_Dublin_post_1968 \
+    = (zone == "Europe/Dublin" && $0 ~ /^#?[\t ]+[01]:00[\t ]/ \
+       && (!$(in_comment + 4) || 1968 < $(in_comment + 4)))
+  if (Rule_Eire || Zone_Dublin_post_1968) {
+    if ((Rule_Eire \
+	 || (Zone_Dublin_post_1968 && $(in_comment + 3) == "IST/GMT"))	\
+	== (DATAFORM != "rearguard")) {
+      uncomment = in_comment
+    } else {
+      comment_out = !in_comment
+    }
+  }
+
+  # If this line should differ due to Namibia using negative SAVE values,
+  # uncomment the desired version and comment out the undesired one.
+  Rule_Namibia = $0 ~ /^#?Rule[\t ]+Namibia[\t ]/
+  Zone_using_Namibia_rule \
+    = (zone == "Africa/Windhoek" && $0 ~ /^#?[\t ]+[12]:00[\t ]/ \
+       && ($(in_comment + 2) == "Namibia" \
+	   || ($(in_comment + 2) == "-" && $(in_comment + 3) == "CAT" \
+	       && ((1994 <= $(in_comment + 4) && $(in_comment + 4) <= 2017) \
+		   || in_comment + 3 == NF))))
+  if (Rule_Namibia || Zone_using_Namibia_rule) {
+    if ((Rule_Namibia \
+	 ? ($9 ~ /^-/ || ($9 == 0 && $10 == "CAT")) \
+	 : $(in_comment + 1) == "2:00" && $(in_comment + 2) == "Namibia") \
+	== (DATAFORM != "rearguard")) {
+      uncomment = in_comment
+    } else {
+      comment_out = !in_comment
+    }
+  }
+
+  # If this line should differ due to Portugal benefiting from %z if supported,
+  # uncomment the desired version and comment out the undesired one.
+  if ($0 ~ /^#?[\t ]+-[12]:00[\t ]+Port[\t ]+[%+-]/) {
+    if (($0 ~ /%z/) == (DATAFORM == "vanguard")) {
+      uncomment = in_comment
+    } else {
+      comment_out = !in_comment
+    }
+  }
+
+  # In vanguard form, use the line "Zone GMT 0 - GMT" instead of
+  # "Zone Etc/GMT 0 - GMT" and adjust Link lines accordingly.
+  # This works around a bug in TZUpdater 2.3.2.
+  if (/^#?(Zone|Link)[\t ]+(Etc\/)?GMT[\t ]/) {
+    if (($2 == "GMT") == (DATAFORM == "vanguard")) {
+      uncomment = in_comment
+    } else {
+      comment_out = !in_comment
+    }
+  }
+
+  if (uncomment) {
+    sub(/^#/, "")
+  }
+  if (comment_out) {
+    sub(/^/, "#")
+  }
+
+  # Prefer %z in vanguard form, explicit abbreviations otherwise.
+  if (DATAFORM == "vanguard") {
+    sub(/^(Zone[\t ]+[^\t ]+)?[\t ]+[^\t ]+[\t ]+[^\t ]+[\t ]+[-+][^\t ]+/, \
+	"&CHANGE-TO-%z")
+    sub(/-00CHANGE-TO-%z/, "-00")
+    sub(/[-+][^\t ]+CHANGE-TO-/, "")
+  } else {
+    if ($0 ~ /^[^#]*%z/) {
+      stdoff_column = 2 * ($0 ~ /^Zone/) + 1
+      rules_column = stdoff_column + 1
+      stdoff = get_minutes($stdoff_column)
+      rules = $rules_column
+      stdabbr = offset_abbr(stdoff)
+      if (rules == "-") {
+	abbr = stdabbr
+      } else {
+	dstabbr_only = rules ~ /^[+0-9-]/
+	if (dstabbr_only) {
+	  dstoff = get_minutes(rules)
+	} else {
+	  # The DST offset is normally an hour, but there are special cases.
+	  if (rules == "Morocco" && NF == 3) {
+	    dstoff = -60
+	  } else if (rules == "NBorneo") {
+	    dstoff = 20
+	  } else if (((rules == "Cook" || rules == "LH") && NF == 3) \
+		     || (rules == "Uruguay" \
+			 && $0 ~ /[\t ](1942 Dec 14|1960|1970|1974 Dec 22)$/)) {
+	    dstoff = 30
+	  } else if (rules == "Uruguay" && $0 ~ /[\t ]1974 Mar 10$/) {
+	    dstoff = 90
+	  } else {
+	    dstoff = 60
+	  }
+	}
+	dstabbr = offset_abbr(stdoff + dstoff)
+	if (dstabbr_only) {
+	  abbr = dstabbr
+	} else {
+	  abbr = stdabbr "/" dstabbr
+	}
+      }
+      sub(/%z/, abbr)
+    }
+  }
+
+  # Normally, prefer whole seconds.  However, prefer subseconds
+  # if generating vanguard form and the otherwise-undocumented
+  # VANGUARD_SUBSECONDS environment variable is set.
+  # This relies on #STDOFF comment lines in the data.
+  # It is for hypothetical clients that support UT offsets that are
+  # not integer multiples of one second (e.g., Europe/Lisbon, 1884 to 1912).
+  # No known clients need this currently, and this experimental
+  # feature may be changed or withdrawn in future releases.
+  if ($1 == "#STDOFF") {
+    stdoff = $2
+    rounded_stdoff = round_to_second(stdoff)
+    if (DATAFORM == "vanguard" && ENVIRON["VANGUARD_SUBSECONDS"]) {
+      stdoff_subst[0] = rounded_stdoff
+      stdoff_subst[1] = stdoff
+    } else {
+      stdoff_subst[0] = stdoff
+      stdoff_subst[1] = rounded_stdoff
+    }
+  } else if (stdoff_subst[0]) {
+    stdoff_column = 2 * ($0 ~ /^Zone/) + 1
+    stdoff_column_val = $stdoff_column
+    if (stdoff_column_val == stdoff_subst[0]) {
+      sub(stdoff_subst[0], stdoff_subst[1])
+    } else if (stdoff_column_val != stdoff_subst[1]) {
+      stdoff_subst[0] = 0
+    }
+  }
+
+  # In rearguard form, change the Japan rule line with "Sat>=8 25:00"
+  # to "Sun>=9 1:00", to cater to zic before 2007 and to older Java.
+  if ($0 ~ /^Rule/ && $2 == "Japan") {
+    if (DATAFORM == "rearguard") {
+      if ($7 == "Sat>=8" && $8 == "25:00") {
+	sub(/Sat>=8/, "Sun>=9")
+	sub(/25:00/, " 1:00")
+      }
+    } else {
+      if ($7 == "Sun>=9" && $8 == "1:00") {
+	sub(/Sun>=9/, "Sat>=8")
+	sub(/ 1:00/, "25:00")
+      }
+    }
+  }
+
+  # In rearguard form, change the Morocco lines with negative SAVE values
+  # to use positive SAVE values.
+  if ($2 == "Morocco") {
+    if ($0 ~ /^Rule/) {
+      if ($4 ~ /^201[78]$/ && $6 == "Oct") {
+	if (DATAFORM == "rearguard") {
+	  sub(/\t2018\t/, "\t2017\t")
+	} else {
+	  sub(/\t2017\t/, "\t2018\t")
+	}
+      }
+
+      if (2019 <= $3) {
+	if ($8 == "2:00") {
+	  if (DATAFORM == "rearguard") {
+	    sub(/\t0\t/, "\t1:00\t")
+	  } else {
+	    sub(/\t1:00\t/, "\t0\t")
+	  }
+	} else {
+	  if (DATAFORM == "rearguard") {
+	    sub(/\t-1:00\t/, "\t0\t")
+	  } else {
+	    sub(/\t0\t/, "\t-1:00\t")
+	  }
+	}
+      }
+    }
+    if ($1 ~ /^[+0-9-]/ && NF == 3) {
+      if (DATAFORM == "rearguard") {
+	sub(/1:00\tMorocco/, "0:00\tMorocco")
+	sub(/\t\+01\/\+00$/, "\t+00/+01")
+      } else {
+	sub(/0:00\tMorocco/, "1:00\tMorocco")
+	sub(/\t\+00\/+01$/, "\t+01/+00")
+      }
+    }
+  }
+}
+
+/^Zone/ {
+  packrat_ignored = FILENAME == PACKRATDATA && PACKRATLIST && !packratlist[$2];
+}
+{
+  if (packrat_ignored && $0 !~ /^Rule/) {
+    sub(/^/, "#")
+  }
+}
+
+# Return a link line resulting by changing OLDLINE to link to TARGET
+# from LINKNAME, instead of linking to OLDTARGET from LINKNAME.
+# Align data columns the same as they were in OLDLINE.
+# Also, replace any existing white space followed by comment with COMMENT.
+function make_linkline(oldline, target, linkname, oldtarget, comment, \
+		       oldprefix, oldprefixlen, oldtargettabs, \
+		       replsuffix, targettabs)
+{
+  oldprefix = "Link\t" oldtarget "\t"
+  oldprefixlen = length(oldprefix)
+  if (substr(oldline, 1, oldprefixlen) == oldprefix) {
+    # Use tab stops to preserve LINKNAME's column.
+    replsuffix = substr(oldline, oldprefixlen + 1)
+    sub(/[\t ]*#.*/, "", replsuffix)
+    oldtargettabs = int(length(oldtarget) / 8) + 1
+    targettabs = int(length(target) / 8) + 1
+    for (; targettabs < oldtargettabs; targettabs++) {
+      replsuffix = "\t" replsuffix
+    }
+    for (; oldtargettabs < targettabs && replsuffix ~ /^\t/; targettabs--) {
+      replsuffix = substr(replsuffix, 2)
+    }
+  } else {
+    # Odd format line; don't bother lining up its replacement nicely.
+    replsuffix = linkname
+  }
+  return "Link\t" target "\t" replsuffix comment
+}
+
+/^Link/ && $4 == "#=" && DATAFORM == "vanguard" {
+  $0 = make_linkline($0, $5, $3, $2)
+}
+
+# If a Link line is followed by a Link or Zone line for the same data, comment
+# out the Link line.  This can happen if backzone overrides a Link
+# with a Zone or a different Link.
+/^Zone/ {
+  sub(/^Link/, "#Link", line[linkline[$2]])
+}
+/^Link/ {
+  sub(/^Link/, "#Link", line[linkline[$3]])
+  linkline[$3] = NR
+  linktarget[$3] = $2
+}
+
+{ line[NR] = $0 }
+
+function cut_link_chains_short( \
+			       l, linkname, t, target)
+{
+  for (linkname in linktarget) {
+    target = linktarget[linkname]
+    t = linktarget[target]
+    if (t) {
+      # TARGET is itself a link name.  Replace the line "Link TARGET LINKNAME"
+      # with "Link T LINKNAME #= TARGET", where T is at the end of the chain
+      # of links that LINKNAME points to.
+      while ((u = linktarget[t])) {
+	t = u
+      }
+      l = linkline[linkname]
+      line[l] = make_linkline(line[l], t, linkname, target, "\t#= " target)
+    }
+  }
+}
+
+END {
+  if (DATAFORM != "vanguard") {
+    cut_link_chains_short()
+  }
+  for (i = 1; i <= NR; i++)
+    print line[i]
+}

share/zoneinfo/zishrink.awk

@@ -0,0 +1,356 @@
+# Convert tzdata source into a smaller version of itself.
+
+# Contributed by Paul Eggert.  This file is in the public domain.
+
+# This is not a general-purpose converter; it is designed for current tzdata.
+# 'zic' should treat this script's output as if it were identical to
+# this script's input.
+
+# Record a hash N for the new name NAME, checking for collisions.
+
+function record_hash(n, name)
+{
+  if (used_hashes[n]) {
+    printf "# ! collision: %s %s\n", used_hashes[n], name
+    exit 1
+  }
+  used_hashes[n] = name
+}
+
+# Return a shortened rule name representing NAME,
+# and record this relationship to the hash table.
+
+function gen_rule_name(name, \
+		       n)
+{
+  # Use a simple mnemonic: the first two letters.
+  n = substr(name, 1, 2)
+  record_hash(n, name)
+  # printf "# %s = %s\n", n, name
+  return n
+}
+
+function prehash_rule_names( \
+			    name)
+{
+  # Rule names are not part of the tzdb API, so substitute shorter
+  # ones.  Shortening them consistently from one release to the next
+  # simplifies comparison of the output.  That being said, the
+  # 1-letter names below are not standardized in any way, and can
+  # change arbitrarily from one release to the next, as the main goal
+  # here is compression not comparison.
+
+  # Abbreviating these rules names to one letter saved the most space
+  # circa 2018e.
+  rule["Arg"] = "A"
+  rule["Brazil"] = "B"
+  rule["Canada"] = "C"
+  rule["Denmark"] = "D"
+  rule["EU"] = "E"
+  rule["France"] = "F"
+  rule["GB-Eire"] = "G"
+  rule["Halifax"] = "H"
+  rule["Italy"] = "I"
+  rule["Jordan"] = "J"
+  rule["Egypt"] = "K" # "Kemet" in ancient Egyptian
+  rule["Libya"] = "L"
+  rule["Morocco"] = "M"
+  rule["Neth"] = "N"
+  rule["Poland"] = "O" # arbitrary
+  rule["Palestine"] = "P"
+  rule["Cuba"] = "Q" # Its start sounds like "Q".
+  rule["Russia"] = "R"
+  rule["Syria"] = "S"
+  rule["Turkey"] = "T"
+  rule["Uruguay"] = "U"
+  rule["Vincennes"] = "V"
+  rule["Winn"] = "W"
+  rule["Mongol"] = "X" # arbitrary
+  rule["NT_YK"] = "Y"
+  rule["Zion"] = "Z"
+  rule["Austria"] = "a"
+  rule["Belgium"] = "b"
+  rule["C-Eur"] = "c"
+  rule["Algeria"] = "d" # country code DZ
+  rule["E-Eur"] = "e"
+  rule["Taiwan"] = "f" # Formosa
+  rule["Greece"] = "g"
+  rule["Hungary"] = "h"
+  rule["Iran"] = "i"
+  rule["StJohns"] = "j"
+  rule["Chatham"] = "k" # arbitrary
+  rule["Lebanon"] = "l"
+  rule["Mexico"] = "m"
+  rule["Tunisia"] = "n" # country code TN
+  rule["Moncton"] = "o" # arbitrary
+  rule["Port"] = "p"
+  rule["Albania"] = "q" # arbitrary
+  rule["Regina"] = "r"
+  rule["Spain"] = "s"
+  rule["Toronto"] = "t"
+  rule["US"] = "u"
+  rule["Louisville"] = "v" # ville
+  rule["Iceland"] = "w" # arbitrary
+  rule["Chile"] = "x" # arbitrary
+  rule["Para"] = "y" # country code PY
+  rule["Romania"] = "z" # arbitrary
+  rule["Macau"] = "_" # arbitrary
+
+  # Use ISO 3166 alpha-2 country codes for remaining names that are countries.
+  # This is more systematic, and avoids collisions (e.g., Malta and Moldova).
+  rule["Armenia"] = "AM"
+  rule["Aus"] = "AU"
+  rule["Azer"] = "AZ"
+  rule["Barb"] = "BB"
+  rule["Dhaka"] = "BD"
+  rule["Bulg"] = "BG"
+  rule["Bahamas"] = "BS"
+  rule["Belize"] = "BZ"
+  rule["Swiss"] = "CH"
+  rule["Cook"] = "CK"
+  rule["PRC"] = "CN"
+  rule["Cyprus"] = "CY"
+  rule["Czech"] = "CZ"
+  rule["Germany"] = "DE"
+  rule["DR"] = "DO"
+  rule["Ecuador"] = "EC"
+  rule["Finland"] = "FI"
+  rule["Fiji"] = "FJ"
+  rule["Falk"] = "FK"
+  rule["Ghana"] = "GH"
+  rule["Guat"] = "GT"
+  rule["Hond"] = "HN"
+  rule["Haiti"] = "HT"
+  rule["Eire"] = "IE"
+  rule["Iraq"] = "IQ"
+  rule["Japan"] = "JP"
+  rule["Kyrgyz"] = "KG"
+  rule["ROK"] = "KR"
+  rule["Latvia"] = "LV"
+  rule["Lux"] = "LX"
+  rule["Moldova"] = "MD"
+  rule["Malta"] = "MT"
+  rule["Mauritius"] = "MU"
+  rule["Namibia"] = "NA"
+  rule["Nic"] = "NI"
+  rule["Norway"] = "NO"
+  rule["Peru"] = "PE"
+  rule["Phil"] = "PH"
+  rule["Pakistan"] = "PK"
+  rule["Sudan"] = "SD"
+  rule["Salv"] = "SV"
+  rule["Tonga"] = "TO"
+  rule["Vanuatu"] = "VU"
+
+  # Avoid collisions.
+  rule["Detroit"] = "Dt" # De = Denver
+
+  for (name in rule) {
+    record_hash(rule[name], name)
+  }
+}
+
+function make_line(n, field, \
+		   f, r)
+{
+  r = field[1]
+  for (f = 2; f <= n; f++)
+    r = r " " field[f]
+  return r
+}
+
+# Process the input line LINE and save it for later output.
+
+function process_input_line(line, \
+			    f, field, end, i, n, r, startdef, \
+			    linkline, ruleline, zoneline)
+{
+  # Remove comments, normalize spaces, and append a space to each line.
+  sub(/#.*/, "", line)
+  line = line " "
+  gsub(/[\t ]+/, " ", line)
+
+  # Abbreviate keywords and determine line type.
+  linkline = sub(/^Link /, "L ", line)
+  ruleline = sub(/^Rule /, "R ", line)
+  zoneline = sub(/^Zone /, "Z ", line)
+
+  # Replace FooAsia rules with the same rules without "Asia", as they
+  # are duplicates.
+  if (match(line, /[^ ]Asia /)) {
+    if (ruleline) return
+    line = substr(line, 1, RSTART) substr(line, RSTART + 5)
+  }
+
+  # Abbreviate times.
+  while (match(line, /[: ]0+[0-9]/))
+    line = substr(line, 1, RSTART) substr(line, RSTART + RLENGTH - 1)
+  while (match(line, /:0[^:]/))
+    line = substr(line, 1, RSTART - 1) substr(line, RSTART + 2)
+
+  # Abbreviate weekday names.
+  while (match(line, / (last)?(Mon|Wed|Fri)[ <>]/)) {
+    end = RSTART + RLENGTH
+    line = substr(line, 1, end - 4) substr(line, end - 1)
+  }
+  while (match(line, / (last)?(Sun|Tue|Thu|Sat)[ <>]/)) {
+    end = RSTART + RLENGTH
+    line = substr(line, 1, end - 3) substr(line, end - 1)
+  }
+
+  # Abbreviate "max", "min", "only" and month names.
+  gsub(/ max /, " ma ", line)
+  gsub(/ min /, " mi ", line)
+  gsub(/ only /, " o ", line)
+  gsub(/ Jan /, " Ja ", line)
+  gsub(/ Feb /, " F ", line)
+  gsub(/ Apr /, " Ap ", line)
+  gsub(/ Aug /, " Au ", line)
+  gsub(/ Sep /, " S ", line)
+  gsub(/ Oct /, " O ", line)
+  gsub(/ Nov /, " N ", line)
+  gsub(/ Dec /, " D ", line)
+
+  # Strip leading and trailing space.
+  sub(/^ /, "", line)
+  sub(/ $/, "", line)
+
+  # Remove unnecessary trailing zero fields.
+  sub(/ 0+$/, "", line)
+
+  # Remove unnecessary trailing days-of-month "1".
+  if (match(line, /[A-Za-z] 1$/))
+    line = substr(line, 1, RSTART)
+
+  # Remove unnecessary trailing " Ja" (for January).
+  sub(/ Ja$/, "", line)
+
+  n = split(line, field)
+
+  # Record which rule names are used, and generate their abbreviations.
+  f = zoneline ? 4 : linkline || ruleline ? 0 : 2
+  r = field[f]
+  if (r ~ /^[^-+0-9]/) {
+    rule_used[r] = 1
+  }
+
+  # If this zone supersedes an earlier one, delete the earlier one
+  # from the saved output lines.
+  startdef = ""
+  if (zoneline)
+    zonename = startdef = field[2]
+  else if (linkline)
+    zonename = startdef = field[3]
+  else if (ruleline)
+    zonename = ""
+  if (startdef) {
+    i = zonedef[startdef]
+    if (i) {
+      do
+	output_line[i - 1] = ""
+      while (output_line[i++] ~ /^[-+0-9]/);
+    }
+  }
+  zonedef[zonename] = nout + 1
+
+  # Save the line for later output.
+  output_line[nout++] = make_line(n, field)
+}
+
+function omit_unused_rules( \
+			   i, field)
+{
+  for (i = 0; i < nout; i++) {
+    split(output_line[i], field)
+    if (field[1] == "R" && !rule_used[field[2]]) {
+      output_line[i] = ""
+    }
+  }
+}
+
+function abbreviate_rule_names( \
+			       abbr, f, field, i, n, r)
+{
+  for (i = 0; i < nout; i++) {
+    n = split(output_line[i], field)
+    if (n) {
+      f = field[1] == "Z" ? 4 : field[1] == "L" ? 0 : 2
+      r = field[f]
+      if (r ~ /^[^-+0-9]/) {
+	abbr = rule[r]
+	if (!abbr) {
+	  rule[r] = abbr = gen_rule_name(r)
+	}
+	field[f] = abbr
+	output_line[i] = make_line(n, field)
+      }
+    }
+  }
+}
+
+function output_saved_lines( \
+			    i)
+{
+  for (i = 0; i < nout; i++)
+    if (output_line[i])
+      print output_line[i]
+}
+
+BEGIN {
+  # Files that the output normally depends on.
+  default_dep["africa"] = 1
+  default_dep["antarctica"] = 1
+  default_dep["asia"] = 1
+  default_dep["australasia"] = 1
+  default_dep["backward"] = 1
+  default_dep["etcetera"] = 1
+  default_dep["europe"] = 1
+  default_dep["factory"] = 1
+  default_dep["northamerica"] = 1
+  default_dep["southamerica"] = 1
+  default_dep["ziguard.awk"] = 1
+  default_dep["zishrink.awk"] = 1
+
+  # Output a version string from 'version' and related configuration variables
+  # supported by tzdb's Makefile.  If you change the makefile or any other files
+  # that affect the output of this script, you should append '-SOMETHING'
+  # to the contents of 'version', where SOMETHING identifies what was changed.
+
+  ndeps = split(deps, dep)
+  ddeps = ""
+  for (i = 1; i <= ndeps; i++) {
+    if (default_dep[dep[i]]) {
+      default_dep[dep[i]]++
+    } else {
+      ddeps = ddeps " " dep[i]
+    }
+  }
+  for (d in default_dep) {
+    if (default_dep[d] == 1) {
+      ddeps = ddeps " !" d
+    }
+  }
+  print "# version", version
+  if (dataform != "main") {
+    print "# dataform", dataform
+  }
+  if (redo != "posix_right") {
+    print "# redo " redo
+  }
+  if (ddeps) {
+    print "# ddeps" ddeps
+  }
+  print "# This zic input file is in the public domain."
+
+  prehash_rule_names()
+}
+
+/^[\t ]*[^#\t ]/ {
+  process_input_line($0)
+}
+
+END {
+  omit_unused_rules()
+  abbreviate_rule_names()
+  output_saved_lines()
+}