#!/usr/bin/perl open(E, "<:utf8", "ingtur-ing.utf8") || die("can't open ingtur-ing: $!"); open(T, "<:utf8", "ingtur-tur.utf8") || die("can't open ingtur-tur: $!"); binmode(STDOUT, ":utf8"); sub escape { my $s = shift; $s =~ s/&/&/; return $s; } while() { $e = $_; $e =~ tr/\x{FEFF}//d;# remove Byte Order Mark $e =~ s/\s*\r\n//;# remove trailing space & newline $t = ; # `ingtur-tur.utf' contains an invalid unicode character, which # leads to `make validation` complaining, if it stays unreplaced: # > nsgmls:eng-tur.tei:136233:13:E: non SGML character number 149 $t =~ tr/\x{95}\x{FEFF}/'/d;# remove Byte Order Mark $t =~ s/\s*\r\n//; $t =~ s/^\s*//;# remove leading space @senses = split /;/, $t; print "\n"; print "
\n"; print ' ' . escape($e) . "\n"; print "
\n"; $s = 0; foreach(@senses) { $s++; s/\s*$//;# remove trailing space s/^\s*//;# remove leading space print " \n"; print " \n"; @equiv = split /,/; foreach(@equiv) { s/\s*$//;# remove trailing space s/^\s*//;# remove leading space print ' ' . escape($_) . "\n"; } print " \n"; print " \n"; } print "
\n"; }