mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-07-31 19:30:21 +02:00
Code Issues Releases Wiki Activity

Implement EntityLookup and put in the Lexer. Some behavior was migrated, since it looks like it will have to be used in all Lexers, not just DirectLex (which is the only one that uses it).

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@105 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2006-07-23 21:07:30 +00:00
parent 7268987846
commit 5ce0ae7056
9 changed files with 196 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
tests/HTMLPurifier/EntityLookupTest.php Normal file
View File

@@ -0,0 +1,29 @@
<?php
// this page is UTF-8 encoded!
require_once 'HTMLPurifier/EntityLookup.php';
class HTMLPurifier_EntityLookupTest extends UnitTestCase
{
function test() {
$lookup = HTMLPurifier_EntityLookup::instance();
// latin char
$this->assertIdentical('â', $lookup->table['acirc']);
// special char
$this->assertIdentical('"', $lookup->table['quot']);
$this->assertIdentical('“', $lookup->table['ldquo']);
$this->assertIdentical('<', $lookup->table['lt']); //expressed strangely
// symbol char
$this->assertIdentical('θ', $lookup->table['theta']);
}
}
?>

12
tests/HTMLPurifier/LexerTest.php
View File

@@ -7,6 +7,7 @@ class HTMLPurifier_LexerTest extends UnitTestCase
{
var $DirectLex, $PEARSax3, $DOMLex;
var $_entity_lookup;
var $_has_dom;
function setUp() {
@@ -14,12 +15,13 @@ class HTMLPurifier_LexerTest extends UnitTestCase
$this->PEARSax3 = new HTMLPurifier_Lexer_PEARSax3();
$this->_has_dom = version_compare(PHP_VERSION, '5', '>=');
if ($this->_has_dom) {
require_once 'HTMLPurifier/Lexer/DOMLex.php';
$this->DOMLex = new HTMLPurifier_Lexer_DOMLex();
}
$this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
}
function test_tokenizeHTML() {
@@ -152,8 +154,12 @@ class HTMLPurifier_LexerTest extends UnitTestCase
// compare with this valid one:
$input[12] = '&quot;';
$expect[12] = array( new HTMLPurifier_Token_Text('"') );
$sax_expect[12] = false;
// SAX chokes on this? We do have entity parsing on, so it should work!
$sax_expect[12] = false; // choked!
// DOM and SAX choke on this
//$char_circ = $this->_entity_lookup->table['circ'];
//$input[13] = '&circ;';
//$expect[13] = array( new HTMLPurifier_Token_Text($char_circ) );
foreach($input as $i => $discard) {
$result = $this->DirectLex->tokenizeHTML($input[$i]);