Newsgroups: php.internals
Path: news.php.net
Xref: news.php.net php.internals:34614
Mailing-List: contact internals-help@lists.php.net; run by ezmlm
Received-SPF: pass (pb1.pair.com: domain redhat.com designates 66.187.233.31 as permitted sender)
Date: Wed, 9 Jan 2008 14:15:41 +0000
To: derick@php.net, internals@lists.php.net
Message-ID: <20080109141541.GA14571@redhat.com>
Mail-Followup-To: derick@php.net, internals@lists.php.net
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
User-Agent: Mutt/1.5.17 (2007-11-01)
Organization: Red Hat UK Ltd, Amberley Place, 107-111 Peascod Street, Windsor, Berkshire, SL4 1TE, United Kingdom.
  Registered in UK and Wales under Company Registration No. 03798903
  Directors: Michael Cunningham (USA), Brendan Lane (Ireland), Matt Parson (USA), Charlie Peters (USA)
Subject: [PATCH] date/timelib: use system timezone database
From: jorton@redhat.com (Joe Orton)

Hi folks.  It's a bit of a maintenance headache for distributions when 
packages include their own copy of the timezone database, since this 
needs to be updated frequently.

I've prepared a patch to allow the timelib code to use the system 
timezone database directly; would something like this be acceptable, any 
thoughts?  This passes the ext/date tests, and reduces the PHP binary 
size by about 300K to boot.

Notes:

1) I've not implemented timelib_timezone_builtin_identifiers_list() here 
since it doesn't seem to be used, is it there for third-party 
extensions?  It could be implemented by iterating through the directory.

2) there's no general way that I can find to obtain the database 
version, so I just invented a string here.

joe

Index: ext/date/lib/parse_tz.c
===================================================================
RCS file: /repository/php-src/ext/date/lib/parse_tz.c,v
retrieving revision 1.35
diff -u -r1.35 parse_tz.c
--- ext/date/lib/parse_tz.c	31 Dec 2007 07:12:08 -0000	1.35
+++ ext/date/lib/parse_tz.c	9 Jan 2008 14:04:28 -0000
@@ -20,6 +20,14 @@
 
 #include "timelib.h"
 
+#ifdef HAVE_SYSTEM_TZDATA
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <unistd.h>
+#endif
+
 #include <stdio.h>
 
 #ifdef HAVE_STRING_H
@@ -27,7 +35,10 @@
 #else
 #include <strings.h>
 #endif
+
+#ifndef HAVE_SYSTEM_TZDATA
 #include "timezonedb.h"
+#endif
 
 #if (defined(__APPLE__) || defined(__APPLE_CC__)) && (defined(__BIG_ENDIAN__) || defined(__LITTLE_ENDIAN__))
 # if defined(__LITTLE_ENDIAN__)
@@ -202,6 +213,86 @@
 	}
 }
 
+#ifdef HAVE_SYSTEM_TZDATA
+
+#ifdef HAVE_SYSTEM_TZDATA_PREFIX
+#define ZONEINFO_PREFIX HAVE_SYSTEM_TZDATA_PREFIX
+#else
+#define ZONEINFO_PREFIX "/usr/share/zoneinfo"
+#endif
+
+static const timelib_tzdb timezonedb_system = { "0.system", 0, NULL, NULL };
+
+/* Return the mmap()ed tzfile if found, else NULL.  On success, the
+ * length of the mapped data is placed in *length. */
+static char *map_tzfile(const char *timezone, size_t *length)
+{
+	char fname[PATH_MAX];
+	struct stat st;
+	char *p;
+	int fd;
+	
+	snprintf(fname, sizeof fname, ZONEINFO_PREFIX "/%s", timezone);
+	
+	fd = open(fname, O_RDONLY);
+	if (fd == -1) {
+		return NULL;
+	} else if (fstat(fd, &st) != 0 || st.st_size < 21) {
+		close(fd);
+		return NULL;
+	}
+
+	*length = st.st_size;
+	p = mmap(NULL, st.st_size, PROT_READ, MAP_SHARED, fd, 0);
+	close(fd);
+	
+	return p != MAP_FAILED ? p : NULL;
+}
+
+const timelib_tzdb *timelib_builtin_db(void)
+{
+	return &timezonedb_system;
+}
+
+const timelib_tzdb_index_entry *timelib_timezone_builtin_identifiers_list(int *count)
+{
+	*count = 0;
+	return NULL;
+}
+
+int timelib_timezone_id_is_valid(char *timezone, const timelib_tzdb *tzdb)
+{
+	char fname[PATH_MAX];
+	
+	snprintf(fname, sizeof fname, ZONEINFO_PREFIX "/%s", timezone);
+
+	return access(fname, R_OK) == 0 ? 1 : 0;
+}
+
+timelib_tzinfo *timelib_parse_tzfile(char *timezone, const timelib_tzdb *tzdb)
+{
+	char *tzf, *orig;
+	timelib_tzinfo *tmp;
+	size_t len;
+
+	orig = map_tzfile(timezone, &len);
+	if (orig == NULL) {
+		return NULL;
+	}
+
+	tmp = timelib_tzinfo_ctor(timezone);
+
+	tzf = orig + 20;
+	read_header(&tzf, tmp);
+	read_transistions(&tzf, tmp);
+	read_types(&tzf, tmp);
+
+	munmap(orig, len);
+
+	return tmp;
+}
+#else
+
 static int seek_to_tz_position(const unsigned char **tzf, char *timezone, const timelib_tzdb *tzdb)
 {
 	int left = 0, right = tzdb->index_size - 1;
@@ -258,6 +349,7 @@
 
 	return tmp;
 }
+#endif
 
 static ttinfo* fetch_timezone_offset(timelib_tzinfo *tz, timelib_sll ts, timelib_sll *transition_time)
 {
Index: ext/date/lib/timelib.m4
===================================================================
RCS file: /repository/php-src/ext/date/lib/timelib.m4,v
retrieving revision 1.4
diff -u -r1.4 timelib.m4
--- ext/date/lib/timelib.m4	3 Jul 2005 23:30:52 -0000	1.4
+++ ext/date/lib/timelib.m4	9 Jan 2008 14:04:28 -0000
@@ -78,3 +78,17 @@
 
 dnl Check for strtoll, atoll
 AC_CHECK_FUNCS(strtoll atoll strftime)
+
+PHP_ARG_WITH(system-tzdata, for use of system timezone data,
+[  --with-system-tzdata[=DIR]      to specify use of system timezone data],
+no, no)
+
+if test "$PHP_SYSTEM_TZDATA" != "no"; then
+   AC_DEFINE(HAVE_SYSTEM_TZDATA, 1, [Define if system timezone data is used])
+
+   if test "$PHP_SYSTEM_TZDATA" != "yes"; then
+      AC_DEFINE_UNQUOTED(HAVE_SYSTEM_TZDATA_PREFIX, "$PHP_SYSTEM_TZDATA",
+                         [Define for location of system timezone data])
+   fi
+fi
+