#!/opt/bin/perl # AELalight (last update Jul 27, 2001) # Transforms text of the form # # Zero or more lines, possibly containing the string #DATE# # # ### # # version = # # some transliteration (zero or more lines) # ; # some translation (zero or more lines) # # some transliteration2 (zero or more lines) # ; # some translation2 (zero or more lines) # # .... # # version = # # some transliteration3 (zero or more lines) # ; # some translation3 (zero or more lines) # # ..... # # into XML format, in keeping with AELalign. # The part before ### is kept unaltered, as the header of the XML file, but # possible occurrences in the header of string #DATE# are replaced by the # current date. # After a transliteration, the ";" and following translation may # be omitted, but this transliteration is then ignored. # Input is standard input or the file indicated by a possible first argument, # output is standard output or the file indicated by a possible second argument. my $input_file = $ARGV[0]; my $output_file = $ARGV[1]; if ($input_file) { open(INPUT, "$input_file") || die "cannot open $input_file"; } if ($output_file) { open(OUTPUT, ">$output_file") || die "cannot open $output_file"; } # Needed for date: my $thisday = (localtime)[3]; my $thismonth = (Jan,Feb,Mar,Apr,May,Jun,Jul,Aug,Sep,Oct,Nov,Dec)[(localtime)[4]]; my $thisyear = (localtime)[5] + 1900; my $thisdate = "$thismonth $thisday, $thisyear"; my $not_eof; # whether end-of-file reached my $line; # current line initiate_reading(); while ($not_eof && not($line =~ /^\s*###\s*$/)) { $line =~ s/#DATE#/$thisdate/g; output_line($line); shift_line(); } output_line("\n\n"); shift_line(); do { read_white_space(); while ($not_eof && $line =~ /^\s*version\s*=\s*([^\s]+)/) { my $version = $1; output_line("\n\n"); shift_line(); read_white_space(); } my $al = ""; my $tr = ""; while ($not_eof && not($line =~ /^\s*(;|)\s*$/)) { $al .= $line; shift_line() } if ($not_eof && ($line =~ /^\s*;\s*$/)) { shift_line(); } else { $al = ""; } while ($not_eof && not($line =~ /^\s*$/)) { $tr .= $line; shift_line() } if ($al || $tr) { $al =~ s/<([0-9][^>]*)>//g; $tr =~ s/<([0-9][^>]*)>//g; output_line("\n"); output_line($al); output_line("\n\n"); output_line($tr); output_line("\n\n"); } } while $not_eof; ####################################################################### # Closing files: output_line("\n"); output_line("\n"); if ($input_file) { close(INPUT); } if ($output_file) { close(OUTPUT); } #################################### # library: sub initiate_reading { $not_eof = 1; shift_line(); } sub shift_line { if ($not_eof) { unless (defined($line = next_line())) { $not_eof = 0; $line = ""; } } } sub next_line { if ($input_file) { return } else { return } } # read away empty lines sub read_white_space { while ($not_eof && ($line =~ /^\s*$/)) { shift_line() } } sub output_line { my ($line) = @_; if ($output_file) { print OUTPUT $line; } else { print STDOUT $line; } }