mirror of
https://github.com/moodle/moodle.git
synced 2025-07-04 14:07:55 +02:00
Prior to this change, all the line endings in the imported HTMLPurifier library were using CRLF (\r\n aka Windows style), but the HTMLPurifier source and also the downloadable artefacts use LF (\n aka Linux style) as line endings. This has been the case since510d190382
when with the commit "MDL-38672 import HTML Purifier 4.5.0" all line endings were changed from LF to CRLF. There was no comment in the commit on why this change was done. As the original source uses LF, this commit partly reverts510d190382
and goes back to LF as line endings. Signed-off-by: Daniel Ziegenberg <daniel@ziegenberg.at>
137 lines
3.6 KiB
PHP
137 lines
3.6 KiB
PHP
<?php
|
|
|
|
/**
|
|
* Parses string hash files. File format is as such:
|
|
*
|
|
* DefaultKeyValue
|
|
* KEY: Value
|
|
* KEY2: Value2
|
|
* --MULTILINE-KEY--
|
|
* Multiline
|
|
* value.
|
|
*
|
|
* Which would output something similar to:
|
|
*
|
|
* array(
|
|
* 'ID' => 'DefaultKeyValue',
|
|
* 'KEY' => 'Value',
|
|
* 'KEY2' => 'Value2',
|
|
* 'MULTILINE-KEY' => "Multiline\nvalue.\n",
|
|
* )
|
|
*
|
|
* We use this as an easy to use file-format for configuration schema
|
|
* files, but the class itself is usage agnostic.
|
|
*
|
|
* You can use ---- to forcibly terminate parsing of a single string-hash;
|
|
* this marker is used in multi string-hashes to delimit boundaries.
|
|
*/
|
|
class HTMLPurifier_StringHashParser
|
|
{
|
|
|
|
/**
|
|
* @type string
|
|
*/
|
|
public $default = 'ID';
|
|
|
|
/**
|
|
* Parses a file that contains a single string-hash.
|
|
* @param string $file
|
|
* @return array
|
|
*/
|
|
public function parseFile($file)
|
|
{
|
|
if (!file_exists($file)) {
|
|
return false;
|
|
}
|
|
$fh = fopen($file, 'r');
|
|
if (!$fh) {
|
|
return false;
|
|
}
|
|
$ret = $this->parseHandle($fh);
|
|
fclose($fh);
|
|
return $ret;
|
|
}
|
|
|
|
/**
|
|
* Parses a file that contains multiple string-hashes delimited by '----'
|
|
* @param string $file
|
|
* @return array
|
|
*/
|
|
public function parseMultiFile($file)
|
|
{
|
|
if (!file_exists($file)) {
|
|
return false;
|
|
}
|
|
$ret = array();
|
|
$fh = fopen($file, 'r');
|
|
if (!$fh) {
|
|
return false;
|
|
}
|
|
while (!feof($fh)) {
|
|
$ret[] = $this->parseHandle($fh);
|
|
}
|
|
fclose($fh);
|
|
return $ret;
|
|
}
|
|
|
|
/**
|
|
* Internal parser that acepts a file handle.
|
|
* @note While it's possible to simulate in-memory parsing by using
|
|
* custom stream wrappers, if such a use-case arises we should
|
|
* factor out the file handle into its own class.
|
|
* @param resource $fh File handle with pointer at start of valid string-hash
|
|
* block.
|
|
* @return array
|
|
*/
|
|
protected function parseHandle($fh)
|
|
{
|
|
$state = false;
|
|
$single = false;
|
|
$ret = array();
|
|
do {
|
|
$line = fgets($fh);
|
|
if ($line === false) {
|
|
break;
|
|
}
|
|
$line = rtrim($line, "\n\r");
|
|
if (!$state && $line === '') {
|
|
continue;
|
|
}
|
|
if ($line === '----') {
|
|
break;
|
|
}
|
|
if (strncmp('--#', $line, 3) === 0) {
|
|
// Comment
|
|
continue;
|
|
} elseif (strncmp('--', $line, 2) === 0) {
|
|
// Multiline declaration
|
|
$state = trim($line, '- ');
|
|
if (!isset($ret[$state])) {
|
|
$ret[$state] = '';
|
|
}
|
|
continue;
|
|
} elseif (!$state) {
|
|
$single = true;
|
|
if (strpos($line, ':') !== false) {
|
|
// Single-line declaration
|
|
list($state, $line) = explode(':', $line, 2);
|
|
$line = trim($line);
|
|
} else {
|
|
// Use default declaration
|
|
$state = $this->default;
|
|
}
|
|
}
|
|
if ($single) {
|
|
$ret[$state] = $line;
|
|
$single = false;
|
|
$state = false;
|
|
} else {
|
|
$ret[$state] .= "$line\n";
|
|
}
|
|
} while (!feof($fh));
|
|
return $ret;
|
|
}
|
|
}
|
|
|
|
// vim: et sw=4 sts=4
|