#!/usr/bin/perl

# http://www.census.gov/support/SF1ASCII.html

%CENSUSSTATES = (1 => AL, 2 => AK, 4 => AZ, 5 => AR, 6 => CA, 8 => CO,
9 => CT, 10 => DE, 11 => DC, 12 => FL, 13 => GA, 15 => HI, 16 => ID, 17
=> IL, 18 => IN, 19 => IA, 20 => KS, 21 => KY, 22 => LA, 23 => ME, 24 =>
MD, 25 => MA, 26 => MI, 27 => MN, 28 => MS, 29 => MO, 30 => MT, 31 =>
NE, 32 => NV, 33 => NH, 34 => NJ, 35 => NM, 36 => NY, 37 => NC, 38 =>
ND, 39 => OH, 40 => OK, 41 => OR, 42 => PA, 44 => RI, 45 => SC, 46 =>
SD, 47 => TN, 48 => TX, 49 => UT, 50 => VT, 51 => VA, 53 => WA, 54 =>
WV, 55 => WI, 56 => WY, 60 => AS, 66 => GU, 69 => MP, 72 => PR, 78 => VI); 

my @FIELDS = split(/,/, "FILEID:6,STUSAB:2,SUMLEV:3,GEOCOMP:2,CHARITER:3,CIFSN:2,LOGRECNO:7,REGION:1,DIVISION:1,STATECE:2,STATE:2,COUNTY:3,COUNTYSC:2,COUSUB:5,COUSUBCC:2,COUSUBSC:2,PLACE:5,PLACECC:2,PLACEDC:1,PLACESC:2,TRACT:6,BLKGRP:1,BLOCK:4,IUC:2,CONCIT:5,CONCITCC:2,CONCITSC:2,AIANHH:4,AIANHHFP:5,AIANHHCC:2,AIHHTLI:1,AITSCE:3,AITS:5,AITSCC:2,ANRC:5,ANRCCC:2,MSACMSA:4,MASC:2,CMSA:2,MACCI:1,PMSA:4,NECMA:4,NECMACCI:1,NECMASC:2,EXI:1,UA:5,UASC:2,UATYPE:1,UR:1,CD106:2,CD108:2,CD109:2,CD110:2,SLDU:3,SLDL:3,VTD:6,VTDI:1,ZCTA3:3,ZCTA5:5,SUBMCD:5,SUBMCDCC:2,AREALAND:14,AREAWATR:14,NAME:90,FUNCSTAT:1,GCUNI:1,POP100:9,HU100:9,INTPLAT:9,INTPLON:10,LSADC:2,PARTFLAG:1,SDELEM:5,SDSEC:5,SDUNI:5,TAZ:6,UGA:5,PUMA5:5,PUMA1:5,RESERVE2:15,MACC:5,UACP:5,RESERVED:7");
foreach my $f (@FIELDS) {
	$f =~ /(\w+):(\d+)/;
	$f = $1;
	$FIELDSIZE{$f} = $2;
}

my %URI; # tracks the last state seen, the last county seen, etc.

open STATE, ">states.n3";
open COUNTY, ">counties.n3";
open COUNTYSUB, ">towns.n3";
open COUNTYSUBPLACE, ">villages.n3";

foreach my $file (STATE, COUNTY, COUNTYSUB, COUNTYSUBPLACE) {
print $file <<EOF;
\@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
\@prefix dc: <http://purl.org/dc/elements/1.1/> .
\@prefix dcterms: <http://purl.org/dc/terms/> .
\@prefix geo: <http://www.w3.org/2003/01/geo/wgs84_pos#> .
\@prefix census: <tag:govshare.info,2005:rdf/census/> .
\@prefix usgovt: <tag:govshare.info,2005:rdf/usgovt/> .
EOF
}

open CENSUS, "<usgeo.uf1";
while (!eof(CENSUS)) {
	$line = <CENSUS>; chop $line;
	my $start = 0;
	my %info;
	foreach my $f (@FIELDS) {
		my $val = substr($line, $start, $FIELDSIZE{$f});
		$val =~ s/^\s+//;
		$val =~ s/\s+$//;
		$start += $FIELDSIZE{$f};
		$info{$f} = ESC($val);
	}
	
	if ($info{GEOCOMP} ne "00") { next; }
	if ($info{NAME} =~ / \(part\)/) { next; }
	
	my $file;
	my $isa;
	my $uri;
	my $parent;
	
	if ($info{SUMLEV} eq "010") {
		$file  = "US";
		$uri = "tag:govshare.info,2005:data/us";
		$isa = "<tag:govshare.info,2005:rdf/politico/Country>";
	} elsif ($info{SUMLEV} eq "040") {
		$file  = "STATE";
		$parent = $URI{US};
		$uri = "$URI{US}/" . lc($CENSUSSTATES{0+$info{STATE}});
		$isa = "usgovt:State";
		print lc($CENSUSSTATES{0+$info{STATE}}) . "\n";
	} elsif ($info{SUMLEV} eq "050") {
		$file  = "COUNTY";
		$parent = $URI{STATE};
		$uri = "$URI{STATE}/counties/" . URI($info{NAME});
		$isa = "usgovt:County";
	} elsif ($info{SUMLEV} eq "060") {
		$file  = "COUNTYSUB";
		$parent = $URI{COUNTY};
		$uri = "$URI{COUNTY}/" . URI($info{NAME});
		$isa = "usgovt:Town";
	} elsif ($info{SUMLEV} eq "070") {
		$file  = "COUNTYSUBPLACE";
		if ($info{NAME} =~ /Remainder of/) { next; }
		$parent = $URI{COUNTYSUB};
		$uri = "$URI{COUNTYSUB}/" . URI($info{NAME});
		$isa = "usgovt:Village";
	}
	else { next; }

	$URI{$file} = $uri;
	
	$info{STATEUSPS} = $CENSUSSTATES{0+$info{STATE}};
	
	my $file2 = $file;
	if ($file eq "US") { $file = "STATE" } # Put the US node in the states file
		
	$info{INTPLAT} /= 1000000;
	$info{INTPLON} /= 1000000;

	print $file "<$uri> \n";
	print $file "	rdf:type $isa ;\n";
	print $file "	usgovt:censusStateCode \"$info{STATECE}\" ;\n" if ($file2 eq "STATE");
	print $file "	usgovt:fipsStateCode \"$info{STATE}\" ;\n" if ($file2 eq "STATE");
	print $file "	usgovt:uspsStateCode \"$info{STATEUSPS}\" ;\n" if ($file2 eq "STATE");
	print $file "	usgovt:fipsCountyCode \"$info{COUNTY}\" ;\n" if ($file2 eq "COUNTY");
	print $file "	usgovt:fipsStateCountyCode \"$info{STATE}:$info{COUNTY}\" ;\n" if ($file2 eq "COUNTY");
	print $file "	dc:title \"$info{NAME}\" ;\n" if ($file2 ne "US");
	print $file "	dcterms:isPartOf <$parent> ;\n" if ($file2 ne "US");
	print $file "	geo:lat \"$info{INTPLAT}\" ;\n" if ($file ne "STATE");
	print $file "	geo:long \"$info{INTPLON}\" ;\n" if ($file ne "STATE");
	print $file "	census:population \"$info{POP100}\" ;\n";
	print $file "	census:households \"$info{HU100}\" ;\n";
	print $file "	census:landArea \"$info{AREALAND} m^2\" ;\n";
	print $file "	census:waterArea \"$info{AREAWATR} m^2\" .\n";
	
}
close CENSUS;

close STATE;
close COUNTY;
close COUNTYSUB;
close COUNTYSUBPLACE;

sub ESC {
	my $lit = shift;
	$lit =~ /([^ A-Za-z0-9\+\-().,\/'#x])/;
	#if (defined($1)) { warn $1; }
	return $lit;
}

sub URI {
	my $name = shift;
	$name = lc($name);
	$name =~ s/\.//g;
	$name =~ s/ county//g;
	$name =~ s/ town//g;
	$name =~ s/ city//g;
	$name =~ s/ ccd//g;
	$name =~ s/ cdp//g;
	$name =~ s/\W/_/g;
	return $name;
}