mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-06 14:16:32 +02:00
Code Issues Releases Wiki Activity

[3.1.0] Revamp URI handling of percent encoding and validation.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@1709 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2008-05-14 02:19:00 +00:00
parent 77ce3e8b4a
commit cb5d5d0648
13 changed files with 261 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
library/HTMLPurifier/URIParser.php
View File

@@ -2,24 +2,39 @@
/**
* Parses a URI into the components and fragment identifier as specified
* by RFC 2396.
* @todo Replace regexps with a native PHP parser
* by RFC 3986.
*/
class HTMLPurifier_URIParser
{
/**
* Parses a URI
* Instance of HTMLPurifier_PercentEncoder to do normalization with.
*/
protected $percentEncoder;
public function __construct() {
$this->percentEncoder = new HTMLPurifier_PercentEncoder();
}
/**
* Parses a URI.
* @param $uri string URI to parse
* @return HTMLPurifier_URI representation of URI
* @return HTMLPurifier_URI representation of URI. This representation has
* not been validated yet and may not conform to RFC.
*/
public function parse($uri) {
$uri = $this->percentEncoder->normalize($uri);
// Regexp is as per Appendix B.
// Note that ["<>] are an addition to the RFC's recommended
// characters, because they represent external delimeters.
$r_URI = '!'.
'(([^:/?#<>\'"]+):)?'. // 2. Scheme
'(//([^/?#<>\'"]*))?'. // 4. Authority
'([^?#<>\'"]*)'. // 5. Path
'(\?([^#<>\'"]*))?'. // 7. Query
'(#([^<>\'"]*))?'. // 8. Fragment
'(([^:/?#"<>]+):)?'. // 2. Scheme
'(//([^/?#"<>]*))?'. // 4. Authority
'([^?#"<>]*)'. // 5. Path
'(\?([^#"<>]*))?'. // 7. Query
'(#([^"<>]*))?'. // 8. Fragment
'!';
$matches = array();
@@ -36,13 +51,7 @@ class HTMLPurifier_URIParser
// further parse authority
if ($authority !== null) {
// ridiculously inefficient: it's a stacked regex!
$HEXDIG = '[A-Fa-f0-9]';
$unreserved = 'A-Za-z0-9-._~'; // make sure you wrap with []
$sub_delims = '!$&\'()'; // needs []
$pct_encoded = "%$HEXDIG$HEXDIG";
$r_userinfo = "(?:[$unreserved$sub_delims:]|$pct_encoded)*";
$r_authority = "/^(($r_userinfo)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/";
$r_authority = "/^((.+?)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/";
$matches = array();
preg_match($r_authority, $authority, $matches);
$userinfo = !empty($matches[1]) ? $matches[2] : null;