<?php
$fileStr = file_get_contents('filepath');
$newStr = '';
$commentTokens = array(T_COMMENT);
if (defined('T_DOC_COMMENT'))
$commentTokens[] = T_DOC_COMMENT; // PHP 5
if (defined('T_ML_COMMENT'))
$commentTokens[] = T_ML_COMMENT; // PHP 4
$tokens = token_get_all($fileStr);
foreach ($tokens as $token) {
if (is_array($token)) {
if (in_array($token[0], $commentTokens))
continue;
$token = $token[1];
}
$newStr .= $token;
}
$newfile = file_put_contents('newfilename',$newStr);
//echo $newStr;die;
?>
Examples
Here is a simple example PHP script using the tokenizer that will read in a PHP file, strip all comments from the source and print the pure code only.
Example #1 Strip comments with the tokenizer
<?php
$source = file_get_contents('example.php');
$tokens = token_get_all($source);
foreach ($tokens as $token) {
if (is_string($token)) {
// simple 1-character token
echo $token;
} else {
// token array
list($id, $text) = $token;
switch ($id) {
case T_COMMENT:
case T_DOC_COMMENT:
// no action on comments
break;
default:
// anything else -> output "as is"
echo $text;
break;
}
}
}
?>
add a note
User Contributed Notes 1 note
anant kumar singh ¶
9 years ago
