#!/usr/local/bin/perl -w
# ----------------------------------------------------
# Summarize the *.txt Files in the  DATASETS directory
# ----------------------------------------------------
# © Martin Maechler, SfS, ETH Zurich

#open(DOCS, "/bin/ls a*.txt |") # <<< testing : only those with a*
# production: 
open(DOCS, "/bin/ls *.txt |") 
    || die "I couldn't open *.txt files (in `pwd`): $!\n";

print "Summary of '*.txt' files in ". `pwd`. "-------\n";
my @Flen = ( 15,   20,    20,    30,    12);
my $Form =  '%-'.$Flen[0].'s| %-'.$Flen[1]. 's| %-'.$Flen[2]. 's| %-'.$Flen[3]. 's| %-'.$Flen[4]. "s\n";
my $nFields = scalar @Flen;

printf $Form,"Filename(+.dat)", "TITEL", "KEYWORDS", "AnwendungsGebiet", "Verwendet";
printf $Form, '-' x $Flen[0],  '-'x $Flen[1], '-'x $Flen[2], '-'x $Flen[3], '-'x $Flen[4];
my @line = @Flen; # same length

FILE:
while($filename = <DOCS>) {
    chop $filename;
    next FILE unless -T $filename;
    if (!open(TEXTFILE, $filename)) {
	print STDERR "Can't open $filename --- continuing...\n"; next FILE;
    }
    $_ = $filename; s/\.txt$//; 
    # $out .= ":\t";
    # $out .= "\t" if length($filename) < 7+4; #-- an extra TAB if short entry
    $nl = 0; 
    $line[$nl] = substr($_,0, $Flen[$nl]);
  LINE:  
    while (<TEXTFILE>) {
	next LINE unless ++$nl < $nFields;
 	#### ------- I could do better: Also look at the 'Dim:' line ..
# 	next LINE if ($.>=4)&& !/^DIM\.(/;
#  	last LINE if /^DIM\.(/;
	chop;		#-- remove newline at end
	s/.*:\s+//;  
	s/\s+$//;	#-- remove trailing white space
	#print "$nl«$_»";
	$line[$nl] = substr($_,0, $Flen[$nl]);
    }				# 
    if($nl < $nFields - 1) {
	print STDERR "** $. : nl = $nl \n";
	for ($i = $nl; $i < $nFields; $i++) {
	    $line[$i] = ''; 
	}
    }
    printf $Form, $line[0], $line[1], $line[2], $line[3], $line[4];
}