mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2024-12-23 00:41:52 +00:00
71326abec1
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@1080 48356398-32a2-884e-a903-53898d9a118a
74 lines
2.1 KiB
PHP
74 lines
2.1 KiB
PHP
#!/usr/bin/php
|
|
<?php
|
|
|
|
/**
|
|
* Parses *.ent files into an entity lookup table, and then serializes and
|
|
* writes the whole kaboodle to a file. The resulting file should be versioned.
|
|
*/
|
|
|
|
if (php_sapi_name() != 'cli') {
|
|
echo 'Script cannot be called from web-browser.';
|
|
exit;
|
|
}
|
|
|
|
chdir( dirname(__FILE__) );
|
|
|
|
// here's where the entity files are located, assuming working directory
|
|
// is the same as the location of this PHP file. Needs trailing slash.
|
|
$entity_dir = '../docs/entities/';
|
|
|
|
// defines the output file for the serialized content.
|
|
$output_file = '../library/HTMLPurifier/EntityLookup/entities.ser';
|
|
|
|
// courtesy of a PHP manual comment
|
|
function unichr($dec) {
|
|
if ($dec < 128) {
|
|
$utf = chr($dec);
|
|
} else if ($dec < 2048) {
|
|
$utf = chr(192 + (($dec - ($dec % 64)) / 64));
|
|
$utf .= chr(128 + ($dec % 64));
|
|
} else {
|
|
$utf = chr(224 + (($dec - ($dec % 4096)) / 4096));
|
|
$utf .= chr(128 + ((($dec % 4096) - ($dec % 64)) / 64));
|
|
$utf .= chr(128 + ($dec % 64));
|
|
}
|
|
return $utf;
|
|
}
|
|
|
|
if ( !is_dir($entity_dir) ) exit("Fatal Error: Can't find entity directory.\n");
|
|
if ( file_exists($output_file) ) exit("Fatal Error: entity-lookup.txt already exists.\n");
|
|
|
|
$dh = @opendir($entity_dir);
|
|
if ( !$dh ) exit("Fatal Error: Cannot read entity directory.\n");
|
|
|
|
$entity_files = array();
|
|
while (($file = readdir($dh)) !== false) {
|
|
if (@$file[0] === '.') continue;
|
|
if (substr(strrchr($file, "."), 1) !== 'ent') continue;
|
|
$entity_files[] = $file;
|
|
}
|
|
closedir($dh);
|
|
|
|
if ( !$entity_files ) exit("Fatal Error: No entity files to parse.\n");
|
|
|
|
$entity_table = array();
|
|
$regexp = '/<!ENTITY\s+([A-Za-z]+)\s+"&#(?:38;#)?([0-9]+);">/';
|
|
|
|
foreach ( $entity_files as $file ) {
|
|
$contents = file_get_contents($entity_dir . $file);
|
|
$matches = array();
|
|
preg_match_all($regexp, $contents, $matches, PREG_SET_ORDER);
|
|
foreach ($matches as $match) {
|
|
$entity_table[$match[1]] = unichr($match[2]);
|
|
}
|
|
}
|
|
|
|
$output = serialize($entity_table);
|
|
|
|
$fh = fopen($output_file, 'w');
|
|
fwrite($fh, $output);
|
|
fclose($fh);
|
|
|
|
echo "Completed successfully.";
|
|
|
|
?>
|