From de20cc04f999154e97f8f0d041f536f048aed256 Mon Sep 17 00:00:00 2001 From: Mischa POSLAWSKY Date: Sun, 1 Feb 2015 08:00:32 +0100 Subject: [PATCH] countries: preliminary script to recreate include Parse Wikipedia page to compare output to current data. Lacks insular and reserved codes. --- tools/mkcountries-wikipedia | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100755 tools/mkcountries-wikipedia diff --git a/tools/mkcountries-wikipedia b/tools/mkcountries-wikipedia new file mode 100755 index 0000000..67916dc --- /dev/null +++ b/tools/mkcountries-wikipedia @@ -0,0 +1,32 @@ +#!/usr/bin/env perl +use 5.012; +use warnings; + +my %cc; # map of country code to info array + +while (<>) { + /
/ .. /<\/pre>/ or next;  # data is in preformatted block
+	m{
+		\A (? [A-Z]{2})
+		\h (? [A-Z]{2})
+		\h \S* \h \d*  # skip other iso codes
+		\h (? .+)
+	}x or next;
+	$cc{ lc $+{codea2} } = [ $+{name}, "c-\L$+{continent}" ];
+}
+
+use Data::Dump 'dd';
+$Data::Dump::INDENT = '';
+dd \%cc;
+
+__END__
+
+=head1 NAME
+
+mkcountryinfo - Create Perl include of country info from Wikipedia page
+
+=head1 SYNOPSIS
+
+	curl http://en.wikipedia.org/wiki/List_of_sovereign_states_and_dependent_territories_by_continent_%28data_file%29 |
+	tools/mkcountryinfo > countries.inc.pl
+
-- 
2.30.0