pronoiac

#!/usr/bin/perl

# call with, say, "./parse-tags.pl tagdata_mefi.txt" or "tagdata_*"

$debug = 0;

while (<>) {
  chomp;
  if ($_ =~ /^(.+?)\t(.+?)\t(.+?)\t(\S+)/) {
    ($tag_id, $link_id, $link_date, $tag_name) =
      ($1, $2, $3, $4);
    if ($debug) {print "parsed: $tag_id, $link_id, $link_date, $tag_name\n";}
    if ($tag_name =~ /[\x00-\x19]|[\x7F-\xFF]|\"/ ) {
      # quotes, & characters outside POSIX [:print:] [\x20-\x7E]
      #  (Visible characters and spaces outside usual printable area)
      print "tag_name: $tag_id, $link_id, $link_date, $tag_name\n";
    } # end tag_name check
  }
} # end <>