File: parse_olson

package info (click to toggle)
libdatetime-timezone-perl 1:1.20-1+2010k
  • links: PTS, VCS
  • area: main
  • in suites: squeeze
  • size: 4,508 kB
  • ctags: 2,667
  • sloc: perl: 2,340; sh: 68; makefile: 5
file content (573 lines) | stat: -rwxr-xr-x 14,063 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
#!/usr/bin/perl -w

use strict;

use lib './lib';

use Data::Dumper;
use DateTime::TimeZone::OlsonDB;
use File::Copy;
use File::Find::Rule;
use File::Path;
use File::Spec;
use Getopt::Long;
use Locale::Country 3.11 qw( code2country );

$Data::Dumper::Indent   = 1;
$Data::Dumper::Sortkeys = 1;
$Data::Dumper::Terse    = 1;

my $VERSION = "0.07";

my $INFINITY = 100**100**100;

my %opts;
GetOptions(
    'dir:s'     => \$opts{dir},
    'clean'     => \$opts{clean},
    'version:s' => \$opts{version},
    'old'       => \$opts{old},
    'file:s'    => \$opts{file},
    'name:s'    => \$opts{name},
    'debug'     => \$opts{debug},
    'help'      => \$opts{help},
);

$opts{help} = 1
    unless defined $opts{dir} && -d $opts{dir};

$opts{help} = 1
    unless defined $opts{version} || $opts{file} || $opts{name};

$opts{version} ||= 'test';

if ( $opts{help} ) {
    print <<'EOF';

This script parses the Olson time zone database files and turns them
into a set of Perl modules.  It also generates the MANIFEST and the
DateTime::TimeZone::Catalog module, which contains a list of all the
available time zone names.

By default, it looks for files named africa, antarctica, asia,
australasia, europe, northamerica, pacificnew, southamerica, and
backward.  All other files are ignored.

It takes the following arguments:

  --dir      A directory containing Olson db files.

  --version  The version of the Olson data files being used.
             Required unless one of the debugging options is given.

  --clean    Remove old generated modules (which may not be valid with
             the latest Olson database)

  --file     Parse just the file with the given name.  For debugging.

  --name     Only create the specified time zone.  For debugging.

  --old      Also look for files named etcetera, factory, and systemv

  --debug    Turn on debugging in Olson parser

  --help     What you are reading

If the --file or --name options are specified, the MANIFEST and
DateTime::TimeZone::Catalog files will not be generated.

EOF

    exit;
}

clean() if $opts{clean};

my @files;

if ( $opts{file} ) {
    @files = $opts{file};
}
else {
    @files = qw( africa antarctica asia australasia
        europe northamerica pacificnew
        southamerica backward
    );

    push @files, qw( etcetera factory systemv )
        if $opts{old};
}

my $man;
unless ( $opts{name} || $opts{file} ) {
    copy( 'MANIFEST.base', 'MANIFEST' );
    open $man, ">>MANIFEST" or die "Cannot write to MANIFEST: $!";
}

my ( @zones, %categories, %links );

my $autogen_warning = <<"EOF";
# This file is auto-generated by the Perl DateTime Suite time zone
# code generator ($VERSION) This code generator comes with the
# DateTime::TimeZone module distribution in the tools/ directory
EOF

parse_file($_) for sort @files;

exit if $opts{name};

clean_links();

make_catalog_pm();

sub clean {
    for my $f (
        File::Find::Rule->file->name('*.pm')
        ->grep('This file is auto-generated')->in('lib'),
        File::Find::Rule->file->name('zd*.t')->in('t')
        ) {
        unlink $f or die "Cannot unlink $f: $!";
    }
}

sub parse_file {
    my $file = File::Spec->catfile( $opts{dir}, shift );

    die "No such file $file\n" unless -e $file;

    print "Now parsing $file\n";

    $DateTime::TimeZone::OlsonDB::DEBUG = 1
        if $opts{debug};

    my $odb = DateTime::TimeZone::OlsonDB->new;

    $odb->parse_file($file);

    %links = ( %links, $odb->links );

    foreach my $zone_name ( sort $odb->zone_names ) {
        if ( $opts{name} ) {
            next unless $zone_name eq $opts{name};
        }
        print "  creating zone $zone_name\n";

        push @zones, $zone_name;

        my $name;
        my @dir;
        if ( $zone_name =~ m{/} ) {
            my $category;
            ( $category, $name ) = split /\//, $zone_name, 2;
            push @{ $categories{$category} }, $name;

            ( $dir[0] = $category ) =~ tr/-/_/;
        }
        else {
            $name = $zone_name;
        }

        ( my $outfile1 = $name ) =~ tr/-/_/;

        ( my $mod_name = $zone_name ) =~ s/\//::/g;
        $mod_name =~ tr/-/_/;

        my $max_year = (localtime)[5] + 1910;
        my $zone     = $odb->expanded_zone(
            name           => $zone_name,
            expand_to_year => $max_year,
        );

        my $spans = serialize_spans( zone_as_spans($zone) );

        $spans =~ s/-inf/DateTime::TimeZone::NEG_INFINITY/g;
        $spans =~ s/inf/DateTime::TimeZone::INFINITY/g;

        $spans =~ s/('(?:start|end)_date'\s+=>\s+)'(\d+)'/$1$2/g;

        my $generator = zone_generator($zone);

        my $has_dst_changes = grep { $_->is_dst } $zone->sorted_changes;

        my $from = "Generated from $file.";
        $from .= "  Olson data version $opts{version}"
            if defined $opts{version};

        my $body = <<"EOF";
$autogen_warning
#
# $from
#
# Do not edit this file directly.
#
package DateTime::TimeZone::$mod_name;

use strict;

use Class::Singleton;
use DateTime::TimeZone;
use DateTime::TimeZone::OlsonDB;

\@DateTime::TimeZone::${mod_name}::ISA = ( 'Class::Singleton', 'DateTime::TimeZone' );

my \$spans =
$spans;

sub olson_version { '$opts{version}' }

sub has_dst_changes { $has_dst_changes }

sub _max_year { $max_year }

sub _new_instance
{
    return shift->_init( \@_, spans => \$spans );
}

$generator

1;

EOF

        my @name_pieces = split /\//, $outfile1;
        my $filename = ( pop @name_pieces ) . '.pm';

        my $outdir = File::Spec->catdir(
            qw( lib DateTime TimeZone ),
            @dir, @name_pieces
        );

        mkpath( $outdir, 1, 0755 );

        my $outfile2 = File::Spec->catfile( $outdir, $filename );

        open my $fh, ">$outfile2" or die "Cannot write to $outfile2: $!";
        print $fh $body or die "Cannot write to $outfile2: $!";
        close $fh or die "Cannot write to $outfile2: $!";

        unless ( $opts{name} || $opts{file} ) {
            print $man "$outfile2\n" or die "Cannot write to MANIFEST: $!";
        }
    }
}

sub zone_as_spans {
    my $zone = shift;

    my @spans;

    my @changes = $zone->sorted_changes;

    for ( my $x = 1; $x < @changes; $x++ ) {
        my $last_total_offset
            = $x > 1 ? $changes[ $x - 2 ]->total_offset : undef;

        my $span = DateTime::TimeZone::OlsonDB::Change::two_changes_as_span(
            @changes[ $x - 1, $x ], $last_total_offset );

        push @spans, $span;

        if ( @spans > 2 ) {
            die "Gap in UTC end/start datetime for " . $zone->name
                unless $spans[-2]{utc_end} == $spans[-1]{utc_start};
        }
    }

    unless ( $zone->infinite_rules ) {
        my $last_change = $changes[-1];

        my $last_observance = $last_change->observance;

        if ( $last_change->utc_start_datetime ) {
            push @spans, {
                utc_start =>
                    $last_change->utc_start_datetime->utc_rd_as_seconds,
                utc_end => $INFINITY,
                local_start =>
                    $last_change->local_start_datetime->utc_rd_as_seconds,
                local_end  => $INFINITY,
                short_name => $last_change->short_name,
                offset     => $last_change->total_offset,
                is_dst     => $last_change->is_dst,
                };
        }

        # This happens with zones that have only one rule and no real changes (Pacific/Johnston)
        else {
            my $utc_start = @spans ? $spans[-1]{utc_end} : -1 * $INFINITY;

            push @spans, {
                utc_start   => $utc_start,
                utc_end     => $INFINITY,
                local_start => $utc_start - $last_observance->total_offset,
                local_end   => $INFINITY,
                short_name  => sprintf( $last_observance->format, '' ),
                offset      => $last_observance->total_offset,
                is_dst      => 0,
                };
        }
    }

    return \@spans;
}

sub serialize_spans {
    my $spans = shift;

    my $string = "[\n";
    $string .= join "\n", map { serialize_span($_) } @$spans;
    $string .= "\n]";

    return $string;
}

sub serialize_span {
    my $span = shift;

    # must correspond to constants in DT::TZ, and short_name is always last
    my @keys   = qw( utc_start utc_end local_start local_end offset is_dst );
    my $string = "    [\n";
    $string .= join ",\n", @$span{@keys};
    $string .= ",\n'$span->{short_name}'";
    $string .= "\n    ],";

    return $string;
}

sub zone_generator {
    my $zone = shift;

    return '' unless $zone->infinite_rules;

    my $generator = <<'EOF';
sub _last_offset { !OFFSET }

my $last_observance = !LAST_OBSERVANCE;
sub _last_observance { $last_observance }

my $rules = !RULES;
sub _rules { $rules }
EOF

    my $last_observance = ( $zone->sorted_changes )[-1]->observance;

    # hack to trim size of dumped object
    delete $last_observance->{utc_start_datetime}{locale};
    delete $last_observance->{local_start_datetime}{locale};
    delete $last_observance->{utc_start_datetime}{local_c};
    delete $last_observance->{local_start_datetime}{local_c};
    delete $last_observance->{rules};
    delete $last_observance->{first_rule};

    # This assumes that there is only one observance from end of
    # changes til end of time, which should be guaranteed by code in
    # OlsonDB module.
    my $offset = $last_observance->total_offset;

    my @rules = $zone->infinite_rules;

    # This is cleaner than making the above a double-quoted string
    $generator =~ s/!RULES/Dumper \@rules/eg;
    $generator =~ s/!LAST_OBSERVANCE/Dumper $last_observance/eg;
    $generator =~ s/\$VAR1->{'local_start_datetime'}{'tz'}/bless( {
      'name' => 'floating',
      'offset' => 0
    }, 'DateTime::TimeZone::Floating' )/;
    $generator =~ s/\$VAR1->{'utc_start_datetime'}{'tz'}/bless( {
      'name' => 'floating',
      'offset' => 0
    }, 'DateTime::TimeZone::Floating' )/;
    $generator =~ s/!OFFSET/$offset/g;

    return $generator;
}

sub clean_links {

    # override some links and add others
    %links = (
        %links,
        'Etc/GMT'       => 'UTC',
        'Etc/GMT+0'     => 'UTC',
        'Etc/Universal' => 'UTC',
        'Etc/UCT'       => 'UTC',
        'Etc/UTC'       => 'UTC',
        'Etc/Zulu'      => 'UTC',
        'GMT0'          => 'UTC',
        'GMT'           => 'UTC',
        'AKST9AKDT'     => 'America/Anchorage',
        'JST-9'         => 'Asia/Tokyo',
    );

    delete $links{UTC};

    # Some links resolve to other links - chase them down until they point
    # to a real zone.
    while ( my @k = grep { $links{ $links{$_} } } keys %links ) {
        for my $k (@k) {
            $links{$k} = $links{ $links{$k} };
        }
    }
}

sub make_catalog_pm {
    my $links = Dumper \%links;
    $links =~ s/{/(/;
    $links =~ s/}/)/;

    my $zones     = join "\n", map {"  $_"} sort @zones;
    my $cat_names = join "\n", map {"  $_"} sort keys %categories;
    my $cat       = '';
    foreach my $c ( sort keys %categories ) {
        $cat .= qq|  '$c' => [ qw(\n|;
        $cat .= join "\n", map {"    $_"} sort @{ $categories{$c} };
        $cat .= "\n) ],\n";
    }

    my %countries = parse_zone_tab();

    # hard-code this alias per request of David Cantrell on the list.
    $countries{UK} = $countries{GB};

    my $countries = '';
    for my $c ( sort keys %countries ) {
        $countries .= qq|  '\L$c' => [ qw(\n|;

        # We explicitly do not sort these because the order in
        # zones.tab is by population.
        $countries .= join "\n",
            map {"    $_"} map { $_->[0] } @{ $countries{$c} };
        $countries .= "\n) ],\n";
    }

    my $zonecatalog = <<"EOF";
$autogen_warning
#
# Do not edit this file directly.

package DateTime::TimeZone::Catalog;

use strict;

use vars qw( \@ALL \@CATEGORY_NAMES \%CATEGORIES \%ZONES_BY_COUNTRY \%LINKS );

\@ALL =
qw(
$zones
);

\@CATEGORY_NAMES =
qw(
$cat_names
);

\%CATEGORIES =
(
$cat
);

\%ZONES_BY_COUNTRY =
(
$countries
);

\%LINKS =
$links
;

sub OlsonVersion { '$opts{version}' }


1;

__END__

=head1 NAME

DateTime::TimeZone::Catalog - Provides a list of all valid time zone names

=head1 SYNOPSIS

See DateTime::TimeZone for API details.

=head1 DESCRIPTION

This module contains an enumerated list of all known system timezones,
so that applications can easily present a list of timezones.

=head1 AVAILABLE ZONES

=head2 Zones by Continent/Region

EOF

    for my $category ( sort keys %categories ) {
        $zonecatalog .= "=head3 $category\n\n";

        for my $zone ( @{ $categories{$category} } ) {
            $zonecatalog .= "  $category/$zone\n";
        }

        $zonecatalog .= "\n";
    }

    $zonecatalog .= <<'EOF';
=head2 Zones by Country

EOF

    for my $country (
        sort { lc $a->[0] cmp lc $b->[0] }
        map { [ code2country($_), $_ ] } keys %countries
        ) {
        next if $country->[1] eq 'UK';

        $zonecatalog .= "=head3 $country->[0] ($country->[1])\n\n";

        for my $zone ( sort { lc $a->[0] cmp $b->[0] }
            @{ $countries{ $country->[1] } } ) {
            my $line = join ' - ', grep {defined} @{$zone};
            $zonecatalog .= "  $line\n";
        }

        $zonecatalog .= "\n";
    }

    $zonecatalog .= <<'EOF';
=head2 Linked Zones

A linked zone is an alias from one name to another.

EOF

    for my $from ( sort keys %links ) {
        $zonecatalog .= "  $from => $links{$from}\n";
    }

    $zonecatalog .= "\n";

    $zonecatalog .= "=cut\n";

    open my $fh, ">lib/DateTime/TimeZone/Catalog.pm" or die $!;
    print $fh $zonecatalog or die $!;
    close $fh or die $!;
}

sub parse_zone_tab {
    my $file = File::Spec->catfile( $opts{dir}, 'zone.tab' );

    open my $fh, "<$file" or die "Cannot read $file: $!";

    my %countries;
    while (<$fh>) {
        next if /^\#/;
        chomp;

        my ( $cc, undef, $tz, $desc ) = split /\t/, $_;

        push @{ $countries{$cc} }, [ $tz, $desc ];
    }

    return %countries;
}