<?php

/**
 * Returns the number of words in a string.
 * As far as I have tested, it is very accurate.
 * The string can have HTML in it,
 * but you should do something like this first:
 *
 *    $search = array(
 *      '@<script[^>]*?>.*?</script>@si',
 *      '@<style[^>]*?>.*?</style>@siU',
 *      '@<![\s\S]*?--[ \t\n\r]*>@'
 *    );
 *    $html = preg_replace($search, '', $html);
 *
 */

function word_count($html) {

  # strip all html tags
  $wc = strip_tags($html);

  # remove 'words' that don't consist of alphanumerical characters or punctuation
  $pattern = "#[^(\w|\d|\'|\"|\.|\!|\?|;|,|\\|\/|\-|:|\&|@)]+#";
  $wc = trim(preg_replace($pattern, " ", $wc));

  # remove one-letter 'words' that consist only of punctuation
  $wc = trim(preg_replace("#\s*[(\'|\"|\.|\!|\?|;|,|\\|\/|\-|:|\&|@)]\s*#", " ", $wc));

  # remove superfluous whitespace
  $wc = preg_replace("/\s\s+/", " ", $wc);

  # split string into an array of words
  $wc = explode(" ", $wc);

  # remove empty elements
  $wc = array_filter($wc);

  # return the number of words
  return count($wc);

}

?>