Perl script to build cross-index files from SIMBAD data.

src/tools/xindex/buildxindices.pl

@@ -0,0 +1,71 @@
+#!/usr/bin/perl
+
+# buildcrossidx.pl by Andrew Tribick
+# version 1.0 - 2008-08-26
+
+open XIDS, '<', 'crossids.txt';
+
+@HDtoHIP  = ();
+@HDlevels = ();
+@SAOtoHIP = ();
+
+while($curLine = <XIDS>) {
+	chomp $curLine;
+
+	# get Hipparcos designation
+	$HIP = '';
+	$HIP = $2 if($curLine =~ m/(^|:)HIP ([0-9]+)(:|$)/);
+	next if($HIP eq ''); # ignore entries which are not Hipparcos stars
+
+	@dList = split(/:/, $curLine);
+	for($i = 0; $i <= $#dList; $i++) {
+		# no component identifiers on SAO designations - makes things easy...
+		$SAOtoHIP{$1} = $HIP if($dList[$i] =~ m/^SAO ([0-9]+)$/);
+
+		# only use HD designations with component identifiers A,J or none
+		if($dList[$i] =~ m/^HD ([0-9]+)([AJ]?)$/) {
+			$HDnum = $1;
+			$Level = HDlevel($2);
+			if(!exists($HDtoHIP{$HDnum})) {
+				# if this HD number is not already assigned, add it to list
+				$HDtoHIP{$HDnum}  = $HIP;
+				$HDlevels{$HDnum} = $Level;
+			} elsif($Level > $HDlevels{$HDnum}) {
+				# otherwise we prefer A over none over J.
+				$HDtoHIP{$HDnum}  = $HIP;
+				$HDlevels{$HDnum} = $Level;
+			}
+		}
+	}
+}
+
+close XIDS;
+
+# write out HD index file
+open HDX,  '>', 'hdxindex.dat';
+binmode HDX;
+print HDX pack('a8S', 'CELINDEX', 0x0100);
+foreach $HD (sort { $a <=> $b } keys %HDtoHIP) {
+	print HDX pack('LL', $HD, $HDtoHIP{$HD});
+}
+close HDX;
+
+# write out SAO index file
+open SAOX, '>', 'saoxindex.dat';
+binmode SAOX;
+print SAOX pack('a8S', 'CELINDEX', 0x0100);
+foreach $SAO (sort { $a <=> $b } keys %SAOtoHIP) {
+	print SAOX pack('LL', $SAO, $SAOtoHIP{$SAO});
+}
+close SAOX;
+
+# ---END OF MAIN PROGRAM---
+
+sub HDlevel {
+	# return a score based on component identifier
+	my $d = shift;
+	return 0 if($d eq 'J');
+	return 1 if($d eq '');
+	return 2 if($d eq 'A');
+	return -999;
+}

src/tools/xindex/readme.txt

@@ -0,0 +1,19 @@
+BUILDXINDICES.PL
+
+This script builds the HD and SAO cross-indices (hdxindex.dat and
+saoxindex.dat). It takes as its input a file containing a colon-separated list
+of star designations called crossids.txt. Each star's designations should be on
+one line. This file can be created using script queries to the SIMBAD database
+(SIMBATCH, at http://simbad.u-strasbg.fr/simbad/sim-fscript).
+
+Because of the limited number of output rows, the crossids.txt file must be
+assembled from the results of several SIMBATCH queries. It is probably best to
+use a query size of 20000. For example, to return all stars with HIP IDs
+between 20000 and 39999, the following SIMBATCH script may be used:
+
+format object "%IDLIST[%*(S):]"
+set limit 20000
+query id wildcard HIP [23]????
+
+The header of each returned file should be discarded. The resultant files can
+then be concatenated to produce the crossids.txt file.