Index of PHP tokens for Emacs and beyond

I’ve been using Emacs as my primary editor for a while now. A lot of people prefer IDE’s, but I’ve never been comfortable with them. I kind of like the ability to show a list of classes & functions in a file though. Emacs can use ctags to generate a list of tokens for a file, but I weren’t really satisfied with its output.
As you probably know, PHP has a ridiculous amount of functions for all kinds of things, and as it happens, token_get_all gives access to the Zend Engine tokenizer. In other words, the same chunk of code, which PHP itself uses, when reading a .php file. This provides an excellent base for writing a script, which can parse the socks off ctags.

So without further ado: ~/scripts/tokens.php parses a file and prints the classes and functions found in there. It also prints a small excerpt of any docblocks, which precedes the item. This makes for a nice table of contents.

if (!defined('T_UNSPECIFIED_STRING')) {
  define('T_UNSPECIFIED_STRING', -1);
function token_get_all_improved($data) {
  $tokens = array();
  $line = 1;
  $col = 0;
  $level = 0;
  $scope_level = null;
  $in_scope = false;
  foreach (token_get_all($data) as $token) {
    if (is_array($token)) {
      list ($token, $text) = $token;
    } else if (is_string($token)) {
      $text = $token;
      $token = T_UNSPECIFIED_STRING;
    if ($token === T_CURLY_OPEN || $token === T_DOLLAR_OPEN_CURLY_BRACES || $text === '{') {
      if (is_null($scope_level)) {
        $scope_level = $level;
    } else if ($text == '}') {
      if ($in_scope && $level < $scope_level) {
        $in_scope = false;
    $tmp = $text;
    $num_new_lines = substr_count($tmp, "n");
    if (1 <= $num_new_lines) {
      $line += $num_new_lines;
      $col =  1;
      $tmp = substr($tmp, strrpos($tmp, "n") + 1);
      if ($tmp === false) {
        $tmp = '';
    $col += strlen($tmp);

    if ($token === T_INTERFACE || $token === T_CLASS) {
      $in_scope = true;
      $scope_level = null;

    $xtoken = new StdClass();
    $xtoken->type = $token;
    $xtoken->text = $text;
    $xtoken->line = $line;
    $xtoken->col = $col;
    $xtoken->blockLevel = $level;
    $xtoken->isClassScope = $in_scope && !is_null($scope_level);
    $tokens[] = $xtoken;
  return $tokens;

function docblock_excerpt($str) {
  if (preg_match('~*{2}[sn*]+(.*)~', trim($str, '/'), $matches)) {
    return $matches[1];

function transform_tokens_to_list($tokens) {
  $buffer = null;
  $docblock = null;
  $results = array();
  $access = '+';
  foreach ($tokens as $token) {
    switch ($token->type) {
    case T_PUBLIC:
      $access = '+';
    case T_PRIVATE:
      $access = '-';
    case T_PROTECTED:
      $access = '#';
    case T_DOC_COMMENT:
      $docblock = $token->text;
    case T_INTERFACE:
    case T_CLASS:
    case T_FUNCTION:
      $buffer = $token;
      $buffer->access = $access;
      $access = '+';
    case T_STRING:
      if (!is_null($buffer)) {
        $buffer->isMember = $buffer->isClassScope || ($buffer->type != T_FUNCTION);
        $buffer->docblock = $docblock;
        $buffer->name = $token->text;
        $results[] = $buffer;
        $buffer = null;
        $docblock = null;
  return $results;

function list_to_table($results) {
  $view = array();
  $last = null;
  foreach ($results as $token) {
    if ($last && ((!$token->isMember && $last->isMember) || (in_array($token->type, array(T_INTERFACE, T_CLASS))))) {
      $view[] = array('', '', '', '', '');
    $last = $token;

    $view[] = array(
      $token->isMember ? $token->access : '',
      strtolower(str_replace('T_', '', token_name($token->type))),
  return $view;

function format_table($map) {
  $out = array();
  $column_widths = array_fill(0, count($map[0]), 0);
  foreach ($map as $row) {
    foreach ($row as $num => $col) {
      $column_widths[$num] = max($column_widths[$num], strlen($col));
  foreach ($map as $row) {
    $line = '';
    foreach ($row as $num => $col) {
      $line .= str_pad($col, $column_widths[$num] + 2);
    $out[] = trim($line);
  return implode("n", $out);

            isset($argv[1]) ? $argv[1] : 'php://stdin')))))
  . "n");

You can use the script alone, but I have also written an accompanying emacs-mode, which loads the result into a buffer and makes each line “clickable”, so you can jump to the relevant position in the file. This could probably be improved on — I’m still a novice, when it comes to lisp. Save it as ~/site-lisp/php-tokens.el (Or where your custom elisp scripts reside).

(defvar php-tokens-mode-target-buffer nil)
(defun php-tokens-mode-find-occurrence ()
  (let ((pos (get-text-property (point) 'occur-target)))
    (when pos
      (unless (buffer-live-p (get-buffer php-tokens-mode-target-buffer))
        (error "Buffer for this occurrence was killed"))

(defun php-tokens-mode-goto-occurrence (&optional event)
  "Go to the occurrence the current line describes."
  (interactive (list last-nonmenu-event))
  (let ((pos
         (if (null event)
             ;; Actually `event-end' works correctly with a nil argument as
             ;; well, so we could dispense with this test, but let's not
             ;; rely on this undocumented behavior.
           (with-current-buffer (window-buffer (posn-window (event-end event)))
               (goto-char (posn-point (event-end event)))
    (pop-to-buffer php-tokens-mode-target-buffer)
    (goto-line pos)))

(defun php-tokens-mode (buffer-name regexp)
  (pop-to-buffer buffer-name)
  (setq buffer-read-only nil)
  (let ((matchbeg 0)
        (origpt nil)
        (begpt nil)
        (contloop t)
        (endpt nil))
      (goto-char (point-min)) ;; begin searching in the buffer
      (while (and contloop (not (eobp)))
        (setq origpt (point))
        (if (setq endpt (re-search-forward regexp nil t))
            (add-text-properties (line-beginning-position) (line-end-position)
                                  `(mouse-face (highlight))
                                  `(occur-target ,(string-to-number (match-string 0)))))
          (setq contloop nil)))))
  (local-set-key '[return] 'php-tokens-mode-goto-occurrence)
  (local-set-key '[mouse-1] 'php-tokens-mode-goto-occurrence))

(defgroup php-tokens nil
  "Generates an overview of PHP tokens"
  :group 'convenience)

(defun php-tokens ()
  "Lists tokens for a PHP-buffer"
  (let* ((source-buffername (buffer-name))
         (buffername "*php-tokens*")
         (contents (buffer-substring-no-properties (point-min) (point-max))))
    (when (get-buffer buffername)
      (kill-buffer buffername))
      (pop-to-buffer buffername)
        (insert contents)
        (shell-command-on-region (point-min) (point-max)
                                 (format "php %s" (shell-quote-argument (expand-file-name "~/scripts/tokens.php")))
                                 buffername nil))
      (setq php-tokens-mode-target-buffer source-buffername)
      (php-tokens-mode buffername "^\([0-9]+\)[ ]+"))))

(provide 'php-tokens)

To use it, you must bind the function to a key. Make the following modifications to your .emacs file:

(require 'php-tokens)
(global-set-key '[f7] 'php-tokens)