mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-03 20:58:11 +02:00
Code Issues Releases Wiki Activity

Add an attribute entity parse test to Lexer and change PEARSax3 to a proof of concept.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@158 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2006-08-04 02:59:15 +00:00
parent a2fc5da060
commit b267b0c202
2 changed files with 12 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
library/HTMLPurifier/Lexer/PEARSax3.php
View File

@@ -4,13 +4,14 @@ require_once 'XML/HTMLSax3.php'; // PEAR
require_once 'HTMLPurifier/Lexer.php'; require_once 'HTMLPurifier/Lexer.php';
/** /**
* Lexer that uses the PEAR package XML_HTMLSax3 to parse * Proof-of-concept lexer that uses the PEAR package XML_HTMLSax3 to parse HTML.
* *
* PEAR, not suprisingly, also has a SAX parser for HTML. I don't know * PEAR, not suprisingly, also has a SAX parser for HTML. I don't know
* very much about implementation, but it's fairly well written. However, that * very much about implementation, but it's fairly well written. However, that
* abstraction comes at a price: performance. You need to have it installed, * abstraction comes at a price: performance. You need to have it installed,
* and if the API changes, it might break our adapter. Not sure whether or not * and if the API changes, it might break our adapter. Not sure whether or not
* it's UTF-8 aware, but it has some entity parsing trouble. * it's UTF-8 aware, but it has some entity parsing trouble (in all areas,
* text and attributes).
* *
* Quite personally, I don't recommend using the PEAR class, and the defaults * Quite personally, I don't recommend using the PEAR class, and the defaults
* don't use it. The unit tests do perform the tests on the SAX parser too, but * don't use it. The unit tests do perform the tests on the SAX parser too, but

9
tests/HTMLPurifier/LexerTest.php
View File

@@ -202,6 +202,15 @@ class HTMLPurifier_LexerTest extends UnitTestCase
new HTMLPurifier_Token_Text('rarr;') new HTMLPurifier_Token_Text('rarr;')
); );
// test entity resolution in attributes
$input[16] = '<a href="index.php?title=foo&amp;id=bar">Link</a>';
$expect[16] = array(
new HTMLPurifier_Token_Start('a',array('href' => 'index.php?title=foo&id=bar'))
,new HTMLPurifier_Token_Text('Link')
,new HTMLPurifier_Token_End('a')
);
$sax_expect[16] = false; // PEARSax doesn't support it!
foreach($input as $i => $discard) { foreach($input as $i => $discard) {
$result = $this->DirectLex->tokenizeHTML($input[$i]); $result = $this->DirectLex->tokenizeHTML($input[$i]);
$this->assertEqual($expect[$i], $result, 'DirectLexTest '.$i.': %s'); $this->assertEqual($expect[$i], $result, 'DirectLexTest '.$i.': %s');