Create an index output from Wikipedia_stuff.pdf

compactindex.php

#!/usr/bin/env php
<?php

$words = array();
while ($line = fgets(STDIN)) {
  $word = explode("-", $line);
  $words[$word[0]][] = trim($word[1]);
}

foreach ( $words as $word => $pages ) {
  if (!empty($word)) {
    $pagesoutput = implode(",", $pages);
    fwrite(STDOUT, "$word - $pagesoutput\n");
  }
}

pdfindex.php

#!/usr/bin/env php
<?php

$args = getopt('p:');
$page = !empty($args['p']) ? $args['p'] : '--';
$trimchars = ",().";
while ($line = fgets(STDIN)) {
  foreach (explode(" ", $line) as $word) {
    fwrite(STDOUT, trim(trim(trim(trim(strtolower($word)), $trimchars)), $trimchars) . " - ${page}\n");
  }
}

pdfindex.sh

for i in $(seq 334);
do
  pdftotext -f $i -l $i Wikipedia_stuff.pdf;
  ./pdfindex.php -p $i < Wikipedia_stuff.txt >> output.txt
done;
cat output.txt | sort | uniq | ./compactindex.php > index.txt;
rm output.txt Wikipedia_stuff.txt