search_keywords_split

Versions

4.6

search_keywords_split($text)

Splits a string into component words according to indexing rules.

Code

modules/search.module, line 236

<?php
function search_keywords_split($text) {
  static $last = null;
  static $lastsplit = null;

  if ($last == $text) {
    return $lastsplit;
  }

  // Decode entities to UTF-8
  $text = decode_entities($text);

  // Call an external processor for word handling.
  search_preprocess($text);

  // To improve searching for numerical data such as dates, IP addresses
  // or version numbers, we consider a group of numerical characters
  // separated only by punctuation characters to be one piece.
  // This also means that searching for e.g. '20/03/1984' also returns
  // results with '20-03-1984' in them.
  // Readable regexp: ([number]+)[punctuation]+(?=[number])
  $text = preg_replace('/(['. PREG_CLASS_NUMBERS .']+)['. PREG_CLASS_PUNCTUATION .']+(?=['. PREG_CLASS_NUMBERS .'])/u', '\1', $text);

  // The dot, underscore and dash are simply removed. This allows meaningful
  // search behaviour with acronyms and URLs.
  $text = preg_replace('/[._-]+/', '', $text);

  // With the exception of the rules above, we consider all punctuation,
  // marks, spacers, etc, to be a word boundary.
  $text = preg_replace('/['. PREG_CLASS_SEARCH_EXCLUDE . ']+/u', ' ', $text);

  // Process words
  $words = explode(' ', $text);
  array_walk($words, '_search_keywords_truncate');

  // Save last keyword result
  $last = $text;
  $lastsplit = $words;

  return $words;
}
?>

Login or register to post comments