[Woc-commit] CVS: woc/data/wml mkwml,NONE,1.1

[Egon W. <eg...@us...>]

Update of /cvsroot/woc/woc/data/wml
In directory usw-pr-cvs1:/tmp/cvs-serv28392

Added Files:
	mkwml 
Log Message:
Some final clean ups.


--- NEW FILE: mkwml ---
#!/usr/local/bin/perl -w

use strict;
use check_digit;

# location of the item files and the templates #
my $wmldatadir = "/vol/www/woc/data/wml";
my $templatedir = "$wmldatadir/templates";


### MAIN ###
  my $flag;
  my $type = "short"; # use chemical template if no type is given #
  my $item;
  my $cas = "";
  my $template;

  &process_arguments();

  print "Creating new item $wmldatadir/$item.xml with ID=";

  my $wocnumber = &get_next_wocnumber;

  print "$wocnumber...$/";

  $template = &read_template ("$templatedir/$type.xml");
  $template = &expand_variables ($template, ("item" => $item,
                                             "wocnumber" => $wocnumber,
                                             "cas" => $cas,
                                             "code" => $item));

  &save_item ($template, "$wmldatadir/$item.xml");

  chmod 0775, "$wmldatadir/$item.xml";
  `chgrp wwwwoc "$wmldatadir/$item.xml"`;

  print "Done!$/";
### END ###


sub process_arguments {
  if (@ARGV < 1) {

    print "Usage: $0 [-cas <casnumber>] [-type (group|chemical|short|term)] <item>$/";
    print "  -cas     may be shortened to -c$/";
    print "  -type    may be shortened to -t$/";
    print "  group    may be shortened to g$/";
    print "  chemical may be shortened to c$/";
    print "  short    may be shortened to s$/";
    print "  element  may be shortened to e$/";
    print "  word     may be shortened to w$/";
    die   "  term     may be shortened to t$/";

  } elsif (@ARGV == 1) {
    $item = $ARGV[0];
  } elsif (@ARGV == 3) {
    $flag = $ARGV[0];
    $type = $ARGV[1] if ($flag =~ /^-t/i);
    $cas  = $ARGV[1] if ($flag =~ /^-c/i);
    $item = $ARGV[2];

    die "Incorrect flag $flag! (type '$0' for usage)$/" if ($flag !~ /^-[tc]/i);
  } elsif (@ARGV == 5) {
    if (($ARGV[0] =~ /^-[tc]/i) && ($ARGV[2] =~ /^-[tc]/i)) {
      if ($ARGV[0] =~ /^-t/i) {
        $type = $ARGV[1];
        $flag = $ARGV[2];
        $cas  = $ARGV[3];
        $item = $ARGV[4];

        die "Incorrect flag $flag! (type '$0' for usage)$/" if ($flag !~ /^-c/i);
      } elsif ($ARGV[0] =~ /^-c/i) {
        $cas  = $ARGV[1];
        $flag = $ARGV[2];
        $type = $ARGV[3];
        $item = $ARGV[4];

        die "Incorrect flag $flag! (type '$0' for usage)$/" if ($flag !~ /^-t/i);
      }
    } else {
      die "Incorrect usage of arguments! (type '$0' for usage)$/";
    }
  } else {
    die "Incorrect number of arguments! (type '$0' for usage)$/";
  }

  die "Must provide an item! (type '$0' for usage)$/" if ($item =~ /^-/i);
  die "Must be a new item! (type '$0' for usage)$/" if (-e "$wmldatadir/$item.xml");

  if ($cas) {
    my $check = &check_digit ($cas);
    if (!$check) {
      die "CAS NUMBER: Wrong check digit or typing error in $cas!$/";
    } elsif ($check =~ /Error/i) {
      die "CAS NUMBER $check in $cas$/";
    } elsif ($check !~ /Correct/i) {
      print "CAS NUMBER: Missing check digit in $cas! ";
      $cas = &check_digit ($cas);
      print "Using $cas instead...$/";
    }
    
    my $match = &already_exists (("CAS-NUMBER" => ">$cas<"));
    die "CAS NUMBER: Already found in$/\t$match$/" if ($match);
  }

  if      ($type =~ /^c/i) {
    $type = "chemical";
  } elsif ($type =~ /^g/i) {
    $type = "group";
  } elsif ($type =~ /^s/i) {
    $type = "short";
  } elsif ($type =~ /^t/i) {
    $type = "term";
  } elsif ($type =~ /^e/i) {
    $type = "element";
  } elsif ($type =~ /^w/i) {
    $type = "word";
  } else {
    die "Unknown type $type! (type '$0' for usage)$/";
  }
}

sub get_next_wocnumber {
  my @item_start_elements = `grep -i "ITEM\.*ID=" $wmldatadir/*.xml`;

  # make a list of current ID's
  my @idlist;
  foreach (@item_start_elements) {
    /ID=\"WOC(.*?)\".*/i;
    push (@idlist, $1);
  }

  # sort thislist
  @idlist = sort @idlist;

  # what is the highest ID?
  my $highestid = $idlist[-1];

  my $nextfree = sprintf "WOC%08i", $highestid + 1;
  return ($nextfree);
}

sub read_template {
  my $file = shift;
  my $template = "";
  
  open (FILE, $file) || die "$file: $!$?";
  while (<FILE>) {
    $template = "$template$_";
  }
  close (FILE) || die "$file: $!$?";
  
  return ($template);
}

sub expand_variables {
  my $template = shift;
  my %variables = @_;

  foreach my $key (keys %variables) {
    $template =~ s/\$$key/$variables{$key}/ig;
  }

  return ($template);
}

sub save_item {
  my $template = shift;
  my $file = shift;
  
  open (FILE, ">$file") || die "$file: $!$?";
  print FILE $template;
  close (FILE) || die "$file: $!$?";
}

sub already_exists {
  my %filters = @_;
  
  foreach my $key (keys %filters) {
    my $out = `grep -i "$key" $wmldatadir/*.xml | grep -i "$filters{$key}"`;
    chomp ($out);
    return "$out" if $out;
  }

  return "";
}