1
0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-01 11:50:28 +02:00

[2.0.1] Improve special case handling for <script>

- DirectLex now honors comments with greater than or less than signs in them
- Comments are transformed into script elements, ending comments are scrapped
- Buggy generator code rewritten to be more error-proof
- AttrValidator checks if token has attributes before processing
- Remove invalid documentation from Scripting
- "Commenting" of script elements switched to the more advanced version

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@1189 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2007-06-21 14:44:26 +00:00
parent e55551ecdd
commit bf0d659c47
13 changed files with 179 additions and 32 deletions

View File

@@ -83,10 +83,13 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
// intercept non element nodes. WE MUST catch all of them,
// but we're not getting the character reference nodes because
// those should have been preprocessed
if ($node->nodeType === XML_TEXT_NODE ||
$node->nodeType === XML_CDATA_SECTION_NODE) {
if ($node->nodeType === XML_TEXT_NODE) {
$tokens[] = $this->factory->createText($node->data);
return;
} elseif ($node->nodeType === XML_CDATA_SECTION_NODE) {
// undo DOM's special treatment of <script> tags
$tokens[] = $this->factory->createText($this->parseData($node->data));
return;
} elseif ($node->nodeType === XML_COMMENT_NODE) {
$tokens[] = $this->factory->createComment($node->data);
return;

View File

@@ -126,22 +126,34 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
// Check if it's a comment
if (
substr($segment, 0, 3) == '!--' &&
substr($segment, $strlen_segment-2, 2) == '--'
substr($segment, 0, 3) == '!--'
) {
// re-determine segment length, looking for -->
$position_comment_end = strpos($html, '-->', $cursor);
if ($position_comment_end === false) {
// uh oh, we have a comment that extends to
// infinity. Can't be helped: set comment
// end position to end of string
$position_comment_end = strlen($html);
$end = true;
} else {
$end = false;
}
$strlen_segment = $position_comment_end - $cursor;
$segment = substr($html, $cursor, $strlen_segment);
$token = new
HTMLPurifier_Token_Comment(
substr(
$segment, 3, $strlen_segment - 5
$segment, 3, $strlen_segment - 3
)
);
if ($maintain_line_numbers) {
$token->line = $current_line;
$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
$current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment);
}
$array[] = $token;
$cursor = $end ? $position_comment_end : $position_comment_end + 3;
$inside_tag = false;
$cursor = $position_next_gt + 1;
continue;
}