<?php
// $Id: pathauto.inc,v 1.1.2.7 2007-10-16 14:31:55 greggles Exp $

/**
 * Copied from search.module's PREG_CLASS_SEARCH_EXCLUDE
 * 
 * Matches Unicode character classes to exclude from the search index.
 *
 * See: http://www.unicode.org/Public/UNIDATA/UCD.html#General_Category_Values
 *
 * The index only contains the following character classes:
 * Lu     Letter, Uppercase
 * Ll     Letter, Lowercase
 * Lt     Letter, Titlecase
 * Lo     Letter, Other
 * Nd     Number, Decimal Digit
 * No     Number, Other
 */
define('PREG_CLASS_ALNUM',
'\x{0}-\x{2f}\x{3a}-\x{40}\x{5b}-\x{60}\x{7b}-\x{bf}\x{d7}\x{f7}\x{2b0}-'.
'\x{385}\x{387}\x{3f6}\x{482}-\x{489}\x{559}-\x{55f}\x{589}-\x{5c7}\x{5f3}-'.
'\x{61f}\x{640}\x{64b}-\x{65e}\x{66a}-\x{66d}\x{670}\x{6d4}\x{6d6}-\x{6ed}'.
'\x{6fd}\x{6fe}\x{700}-\x{70f}\x{711}\x{730}-\x{74a}\x{7a6}-\x{7b0}\x{901}-'.
'\x{903}\x{93c}\x{93e}-\x{94d}\x{951}-\x{954}\x{962}-\x{965}\x{970}\x{981}-'.
'\x{983}\x{9bc}\x{9be}-\x{9cd}\x{9d7}\x{9e2}\x{9e3}\x{9f2}-\x{a03}\x{a3c}-'.
'\x{a4d}\x{a70}\x{a71}\x{a81}-\x{a83}\x{abc}\x{abe}-\x{acd}\x{ae2}\x{ae3}'.
'\x{af1}-\x{b03}\x{b3c}\x{b3e}-\x{b57}\x{b70}\x{b82}\x{bbe}-\x{bd7}\x{bf0}-'.
'\x{c03}\x{c3e}-\x{c56}\x{c82}\x{c83}\x{cbc}\x{cbe}-\x{cd6}\x{d02}\x{d03}'.
'\x{d3e}-\x{d57}\x{d82}\x{d83}\x{dca}-\x{df4}\x{e31}\x{e34}-\x{e3f}\x{e46}-'.
'\x{e4f}\x{e5a}\x{e5b}\x{eb1}\x{eb4}-\x{ebc}\x{ec6}-\x{ecd}\x{f01}-\x{f1f}'.
'\x{f2a}-\x{f3f}\x{f71}-\x{f87}\x{f90}-\x{fd1}\x{102c}-\x{1039}\x{104a}-'.
'\x{104f}\x{1056}-\x{1059}\x{10fb}\x{10fc}\x{135f}-\x{137c}\x{1390}-\x{1399}'.
'\x{166d}\x{166e}\x{1680}\x{169b}\x{169c}\x{16eb}-\x{16f0}\x{1712}-\x{1714}'.
'\x{1732}-\x{1736}\x{1752}\x{1753}\x{1772}\x{1773}\x{17b4}-\x{17db}\x{17dd}'.
'\x{17f0}-\x{180e}\x{1843}\x{18a9}\x{1920}-\x{1945}\x{19b0}-\x{19c0}\x{19c8}'.
'\x{19c9}\x{19de}-\x{19ff}\x{1a17}-\x{1a1f}\x{1d2c}-\x{1d61}\x{1d78}\x{1d9b}-'.
'\x{1dc3}\x{1fbd}\x{1fbf}-\x{1fc1}\x{1fcd}-\x{1fcf}\x{1fdd}-\x{1fdf}\x{1fed}-'.
'\x{1fef}\x{1ffd}-\x{2070}\x{2074}-\x{207e}\x{2080}-\x{2101}\x{2103}-\x{2106}'.
'\x{2108}\x{2109}\x{2114}\x{2116}-\x{2118}\x{211e}-\x{2123}\x{2125}\x{2127}'.
'\x{2129}\x{212e}\x{2132}\x{213a}\x{213b}\x{2140}-\x{2144}\x{214a}-\x{2b13}'.
'\x{2ce5}-\x{2cff}\x{2d6f}\x{2e00}-\x{3005}\x{3007}-\x{303b}\x{303d}-\x{303f}'.
'\x{3099}-\x{309e}\x{30a0}\x{30fb}-\x{30fe}\x{3190}-\x{319f}\x{31c0}-\x{31cf}'.
'\x{3200}-\x{33ff}\x{4dc0}-\x{4dff}\x{a015}\x{a490}-\x{a716}\x{a802}\x{a806}'.
'\x{a80b}\x{a823}-\x{a82b}\x{d800}-\x{f8ff}\x{fb1e}\x{fb29}\x{fd3e}\x{fd3f}'.
'\x{fdfc}-\x{fe6b}\x{feff}-\x{ff0f}\x{ff1a}-\x{ff20}\x{ff3b}-\x{ff40}\x{ff5b}-'.
'\x{ff65}\x{ff70}\x{ff9e}\x{ff9f}\x{ffe0}-\x{fffd}');


/**
 * Check to see if there is already an alias pointing to a different item
 * 
 * @param string $alias
 *   A string alias (i.e. dst)
 * @param string $src
 *   A string that is the internal path
 * 
 *
 */
function _pathauto_alias_exists($alias, $src) {
  return db_result(db_query(
    "SELECT COUNT(dst) FROM {url_alias} WHERE dst = '%s' AND src != '%s'",
    $alias, $src));
}

/**
 * Clean up a string value provided by a module, resulting in a
 * string containing only alphanumerics and separators
 * @param $string
 *   A string to clean.
 * 
 */
function pathauto_cleanstring($string, $clean_slash = TRUE) {
  // Default words to ignore
  $ignore_words = array(
    "a", "an", "as", "at", "before", "but", "by", "for", "from",
    "is", "in", "into", "like", "of", "off", "on", "onto", "per",
    "since", "than", "the", "this", "that", "to", "up", "via",
    "with"
  );

  // Replace or drop punctuation based on user settings
  $separator = variable_get('pathauto_separator', '-');
  $output = $string;
  $punctuation = pathauto_punctuation_chars();
  foreach ($punctuation as $name => $details) {
    $action = variable_get("pathauto_punctuation_". $name, 0);
    // 2 is the action for "do nothing" with the punctuation
    if ($action != 2) {
      // Slightly tricky inline if which either replaces with the separator or nothing
      $output = str_replace($details['value'], ($action ? $separator : ''), $output);
    }
  }

  // If something is already urlsafe then don't remove 
  if ($clean_slash) {
    $output = str_replace('/', '', $output);
  }

  
  // Optionally remove accents and transliterate to a subset of ASCII-96 characters.
  if (variable_get('pathauto_transliterate', FALSE)) { 

    static $i18n_loaded = false;
    static $translations = array();
    if (!$i18n_loaded) {
      $path = drupal_get_path('module', 'pathauto');
      if (is_file($path. '/i18n-ascii.txt')) {
        $translations = parse_ini_file($path. '/i18n-ascii.txt');
      }
      $i18n_loaded = true;
    }
  
    $output = strtr($output, $translations);
  
    // Preserve alphanumerics, everything else becomes a separator.
    $pattern = '/[^a-zA-Z0-9]+/ ';
    $output = preg_replace($pattern, $separator, $output);
  }

  // Get rid of words that are on the ignore list
  $ignore_re = "\b". preg_replace("/,/", "\b|\b", variable_get('pathauto_ignore_words', $ignore_words)) ."\b";
  $output = preg_replace("/$ignore_re/ie", "", $output);

  // Always replace whitespace with the separator.
  $output = preg_replace("/\s+/", $separator, $output);

  // In preparation for pattern matching, 
  // escape the separator if and only if it is not alphanumeric)
  if (isset($separator)) {
    if (preg_match('/^[^'. PREG_CLASS_ALNUM .']+$/uD',$separator)) {
      $seppattern = $separator;
    } 
    else {
      $seppattern = '\\'. $separator;
    }
    // Trim any leading or trailing separators (note the need to
    $output = preg_replace("/^$seppattern+|$seppattern+$/", "", $output);

    // Replace multiple separators with a single one
    $output = preg_replace("/$seppattern+/", "$separator", $output);

  }


  // Enforce the maximum component length
  $maxlength = min(variable_get('pathauto_max_component_length', 100), 128);
  $output = drupal_substr($output, 0, $maxlength);

  return $output;
}

/**
 * Apply patterns to create an alias
 *
 * @param $module
 *   The name of your module (e.g., 'node')
 * @param $op
 *   Operation being performed on the content being aliased ('insert',
 *   'update', or 'bulkupdate')
 * @param $placeholders
 *   An array whose keys consist of the translated placeholders
 *   which appear in patterns (e.g., t('[title]')) and values are the
 *   actual values to be substituted into the pattern (e.g., $node->title)
 * @param $src
 *   The "real" URI of the content to be aliased (e.g., "node/$node->nid")
 * @param $type
 *   For modules which provided patternitems in hook_pathauto(),
 *   the relevant identifier for the specific item to be aliased (e.g.,
 *   $node->type)
 * @return
 *   The alias that was created
 */
function pathauto_create_alias($module, $op, $placeholders, $src, $type = NULL) {
  if (($op != 'bulkupdate') and variable_get('pathauto_verbose', FALSE)) {
    $verbose = TRUE;
  } 
  else {
    $verbose = FALSE;
  }

  // Retrieve and apply the pattern for this content type
  $pattern = '';
  if ($type) {
    $pattern = drupal_strtolower(variable_get('pathauto_'. $module .'_'. $type .'_pattern', ''));
  }
  if (!trim($pattern)) {
    $pattern = drupal_strtolower(variable_get('pathauto_'. $module .'_pattern', ''));
  }
  
  // No pattern? Do nothing (otherwise we may blow away existing aliases...)
  if (!trim($pattern)) {
    return '';
  }

  // Special handling when updating an item which is already aliased.
  $pid = NULL;
  if ($op == 'update' or $op == 'bulkupdate') {
    $result = db_query("SELECT pid, dst FROM {url_alias} WHERE src='%s'", $src);
    if ($data = db_fetch_object($result)) {
      // The item is already aliased, check what to do...
      switch (variable_get('pathauto_update_action', 2)) {
        // Do nothing
        case 0:
          return '';
        // Add new alias in addition to old one
        case 1:
          $oldalias = $data->dst;
          break;
        // Replace old alias - remember the pid to update
        case 2:
          $pid = $data->pid;
          $oldalias = $data->dst;
          break;
        default:
          break;
      }
    }
  }

  // Replace the placeholders with the values provided by the module,
  // and optionally lower-case the result
  $alias = str_replace($placeholders['tokens'], $placeholders['values'], $pattern);

  if (variable_get('pathauto_case',1)) {
    $alias = drupal_strtolower($alias);
  }

  // Two or more slashes should be collapsed into one
  $alias = preg_replace("/\/+/", "/", $alias);
  
  // Trim any leading or trailing slashes
  $alias = preg_replace("/^\/|\/+$/", "", $alias);

  $maxlength = min(variable_get('pathauto_max_length', 100), 128);
  $alias = drupal_substr($alias, 0, $maxlength);

  // If the alias already exists, generate a new variant
  $separator = variable_get('pathauto_separator', '-');
  if (_pathauto_alias_exists($alias, $src)) {
    for ($i = 0; _pathauto_alias_exists($alias . $separator . $i, $src); $i++) {
    }
    // Make room for the sequence number
    $alias = drupal_substr($alias, 0, $maxlength - strlen($i));
    $alias = $alias . $separator . $i;
  }

  // If $pid is NULL, a new alias is created - otherwise, the existing
  // alias for the designated src is replaced
  _pathauto_set_alias($src, $alias, $pid, $verbose, $oldalias);

  // Also create a related feed alias if requested, and if supported
  // by the module
  if (variable_get('pathauto_'. $module .'_applytofeeds', FALSE)) {
    $feedappend = variable_get('pathauto_'. $module .'_supportsfeeds', '');
    // Handle replace case (get existing pid)
    _pathauto_set_alias("$src/$feedappend", "$alias/feed", NULL, $verbose);
  }

  return $alias;
}

/**
 * Verifies if the given path is a valid menu callback.
 * Taken from menu_execute_active_handler().
 *
 * @param $path
 *   A string containing a relative path.
 *
 * @return
 *   TRUE if the path already exists.
 */
function _pathauto_path_is_callback($path) {
  static $menu = NULL;
  if (is_null($menu)) {
    $menu = menu_get_menu();
  }
  
  // Determine the menu item containing the callback.
  return isset($menu["callbacks"][$path]);
}

/**
 * Private function for pathauto to create an alias
 * 
 * @param $src
 *   The internal path 
 * @param $dst
 *   The visible externally used path. 
 * @param $pid
 *   If the item is currently aliased, the pid for that item.
 * @param $verbose
 *   If the admin has enabled verbose, should be TRUE.  Else FALSE or NULL.
 * @param $oldalias
 *   If the item is currently aliased, the existing alias for that item.
 * 
 */
function _pathauto_set_alias($src, $dst, $pid = NULL, $verbose = FALSE, $oldalias = NULL) {
  // Alert users that an existing callback cannot be overridden automatically
  if (_pathauto_path_is_callback($dst)) {
    if ($verbose and user_access('create url aliases')) {
      drupal_set_message(t('Ignoring alias '). $dst .t(' due to existing path conflict'));
    }
    return;
  }

  // Skip replacing the current alias with an identical alias
  if ($oldalias != $dst) {
    path_set_alias($src, $dst, $pid, 1, 10);
    if ($verbose and user_access('create url aliases')) {
      if ($pid) {
        drupal_set_message(t('Created new alias %dst for %src, replacing %oldalias', array('%dst' => $dst, '%src' => $src, '%oldalias' => $oldalias)));
      } 
      else {
        drupal_set_message(t('Created new alias %dst for %src', array('%dst' => $dst, '%src' => $src)));
      }
    }
  }
}

/**
 * Generalized function to get tokens across all Pathauto types
 * 
 * @param $object
 *   A user, node, or category object.
 * 
 * @return
 *   tokens for that object formatted in the way that Pathauto expects to see them.
 *  
 */
function pathauto_get_placeholders($type, $object) {
  $full = token_get_values($type, $object, TRUE);
  $tokens = token_prepare_tokens($full->tokens);
  $values = pathauto_clean_token_values($full);
  
  return array('tokens' => $tokens, 'values' => $values);
}

/**
 * Cleans tokens so they are URL friendly
 * 
 * @param $values
 *   An array of token values that need to be "cleaned" for use in the URL 
 * 
 */
function pathauto_clean_token_values($full) {
  foreach ($full->values as $key => $value) {
    
    if (substr($full->tokens[$key], -4, 4) === 'path' || substr($full->tokens[$key], -8, 8) === 'path-raw') {
      $full->values[$key] = pathauto_cleanstring($value, FALSE);
    }
    else {
      $full->values[$key] = pathauto_cleanstring($value);
    }

  }
  return $full->values;
}

/**
 * Returns an array of arrays for punctuation values keyed by a name
 *   including the value and a textual description
 *   Can and should be expanded to include "all" non text punctuation values
 * 
 */
function pathauto_punctuation_chars() {
  $punctuation = array();

  // Handle " ' , . - _ : ; | { { } ] + = * & % $ Ł # @ ! ~ ( ) ? < > \
  $punctuation['double_quotes']     = array('value' => '"', 'name' => t('Double quotes "'));
  $punctuation['quotes']            = array('value' => "'", 'name' => t("Single quotes (apostrophe) '"));
  $punctuation['backtick']          = array('value' => "`", 'name' => t("Back tick `"));
  $punctuation['comma']             = array('value' => ",", 'name' => t('Comma ,'));
  $punctuation['period']            = array('value' => ".", 'name' => t('Period .'));
  $punctuation['hyphen']            = array('value' => "-", 'name' => t('Hyphen -'));
  $punctuation['underscore']        = array('value' => "_", 'name' => t('Underscore _'));
  $punctuation['colon']             = array('value' => ":", 'name' => t('Colon :'));
  $punctuation['semicolon']         = array('value' => ";", 'name' => t('Semicolon ;'));
  $punctuation['pipe']              = array('value' => "|", 'name' => t('Pipe |'));
  $punctuation['left_curly']        = array('value' => "{", 'name' => t('Left curly bracket {'));
  $punctuation['left_square']       = array('value' => "[", 'name' => t('Left square bracket ['));
  $punctuation['right_curly']       = array('value' => "}", 'name' => t('Right curly bracket }'));
  $punctuation['right_square']      = array('value' => "]", 'name' => t('Right square bracket ]'));
  $punctuation['plus']              = array('value' => "+", 'name' => t('Plus +'));
  $punctuation['equal']             = array('value' => "=", 'name' => t('Equal ='));
  $punctuation['asterisk']          = array('value' => "*", 'name' => t('Asterisk *'));
  $punctuation['ampersand']         = array('value' => "&", 'name' => t('Ampersand &'));
  $punctuation['percent']           = array('value' => "%", 'name' => t('Percent %'));
  $punctuation['caret']             = array('value' => "^", 'name' => t('Caret ^'));
  $punctuation['dollar']            = array('value' => "$", 'name' => t('Dollar $'));
  $punctuation['hash']              = array('value' => "#", 'name' => t('Hash #'));
  $punctuation['at']                = array('value' => "@", 'name' => t('At @'));
  $punctuation['exclamation']       = array('value' => "!", 'name' => t('Exclamation !'));
  $punctuation['tilde']             = array('value' => "~", 'name' => t('Tilde ~'));
  $punctuation['left_parenthesis']  = array('value' => "(", 'name' => t('Left parenthesis ('));
  $punctuation['right_parenthesis'] = array('value' => ")", 'name' => t('right parenthesis )'));
  $punctuation['question_mark']     = array('value' => "?", 'name' => t('Question mark ?'));
  $punctuation['less_than']         = array('value' => "<", 'name' => t('Less than <'));
  $punctuation['greater_than']      = array('value' => ">", 'name' => t('Greater than >'));
  $punctuation['back_slash']        = array('value' => '\\', 'name' => t('Back slash \\'));

  return $punctuation;
}