gergely/astrognome
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Created geonames_process.pl Perl script to download and process geonames.org data

Browse Source 
It is *NOT* ready for distribution yet! The script must be finished with
downloading real data, or separate rules must be added to create
(download) dependency files like timeZones.txt, allCountries.zip and
countryInfo.txt.
This commit is contained in:
Gergely Polonkai
2013-09-06 16:22:16 +02:00
parent ecfac69a67
commit 6595f0f961
5 changed files with 166 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
data/geonames/Makefile.am Normal file
View File

@@ -0,0 +1,19 @@
geodatadir = $(pkgdatadir)
geodata_DATA = geodata.xml
EXTRA_DIST = geodata.xml
MAINTAINERCLEANFILES = geodata.xml
geodata.xml:
$(AM_V_GEN) if test -x "$(PERL)"; then \
if test "x$(have_geonames_perl_modules)" = "xyes" -o "x$(I_HAVE_PERL_MODULES)" = "xyes"; then \
$(PERL) geonames_process.pl; \
else \
echo "XML::Writer and IO::File perl modules are required to process geonames data."; \
echo "configure reported they are not installed. If you are sure they are,"; \
echo "set the I_HAVE_PERL_MODULES environment variable to yes"; \
fi; \
else \
echo "perl5 is required to create geodata.xml!"; \
fi

59
data/geonames/geonames_process.pl Normal file
View File

@@ -0,0 +1,59 @@
#! /usr/bin/perl -w
use strict;
use IO::File;
use XML::Writer;
# TODO: Download http://download.geonames.org/export/dump/countryInfo.txt
# TODO: Download http://download.geonames.org/export/dump/timeZones.txt
# TODO: Download http://download.geonames.org/export/dump/allCountries.zip
# TODO: Unzip allCountries.zip
my %time_zones = ();
my %countries = ();
open(TIMEZONES, 'timeZones.txt');
while (<TIMEZONES>) {
my ($country_code, $timezone_id, $gmt_offset_january, $gmt_offset_july, $gmt_offset_raw) = split(/\t/, $_);
$time_zones{$country_code . '_' . $timezone_id} = {offset => $gmt_offset_january, dst_offset => $gmt_offset_july};
}
close(TIMEZONES);
open(COUNTRIES, 'countryInfo.txt');
while (<COUNTRIES>) {
my ($country_code, $iso3, $iso_numeric, $fips, $name, $capital, $area, $population, $continent, $tld, $currency_code, $currency_name, $phone, $postal_code_format, $postal_code_regex, $languages, $geonameid, $neighbours, $equivalent_fips_code) = split(/\t/, $_);
if ($country_code =~ /^[A-Z]{2}$/) {
$countries{$country_code} = $name;
}
}
close(COUNTRIES);
my $xml_file = IO::File->new('>geodata.xml');
my $writer = XML::Writer->new(OUTPUT => $xml_file, NEWLINES => 0);
$writer->xmlDecl('utf-8');
$writer->startTag('geodata');
# TODO: process all files, not just HU.txt!
open(GEONAMES, "HU.txt");
while (<GEONAMES>) {
my ($geonameid, $name, $asciiname, $alternatenames, $latitude, $longitude, $feature_class, $feature_code, $country_code, $alt_country_code, $admin1, $admin2, $admin3, $admin4, $population, $elevation, $dem, $timezone, $mod_date) = split(/\t/, $_);
if (($feature_class eq 'P') && ($feature_code eq 'PPL')) {
$writer->emptyTag('place',
'name' => $name,
'latitude' => $latitude,
'longitude' => $longitude,
'elevation' => $elevation,
'country' => $countries{$country_code},
'time_offset' => $time_zones{$country_code . '_' . $timezone}->{offset},
'time_offset_dst' => $time_zones{$country_code . '_' . $timezone}->{dst_offset}
);
}
}
close GEONAMES;
$writer->endTag('geodata');