WordPress-C
/
WordPress
mirror of https://github.com/WordPress/WordPress.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

HTML API: Accumulate shift for internal parsing pointer. 

A bug was discovered where where the parser wasn't returning to the
start of the affected tag after making some updates.

In few words, the Tag Processor has not been treating its own internal
pointer `bytes_already_parsed` the same way it treats its bookmarks.
That is, when updates are applied to the input document and then
`get_updated_html()` is called, the internal pointer transfers to
the newly-updated content as if no updates had been applied since
the previous call to `get_updated_html()`.

In this patch we're creating a new "shift accumulator" to account for
all of the updates that accrue before calling `get_updated_html()`.
This accumulated shift will be applied when swapping the input document
with the output buffer, which should result in the pointer pointing to
the same logical spot in the document it did before the udpate.

In effect this patch adds a single workaround for treating the
internal pointer like a bookmark, plus a temporary pointer which points
to the beginning of the current tag when calling `get_updated_html()`.
This will preserve the assumption that updating a document doesn't
move that pointer, or shift which tag is currently matched.

Props dmsnell, zieladam.
Fixes #58179.
Built from https://develop.svn.wordpress.org/trunk@55706


git-svn-id: http://core.svn.wordpress.org/trunk@55218 1a063a9b-81f0-0310-95a4-ce76da25c4cd
This commit is contained in:
Bernhard Reiter 2023-05-03 11:31:18 +00:00
parent 59e90bba48
commit 5a32396d8f
2 changed files with 49 additions and 75 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

122
wp-includes/html-api/class-wp-html-tag-processor.php
View File

@ -317,23 +317,6 @@ class WP_HTML_Tag_Processor {
*/ */
private $stop_on_tag_closers; private $stop_on_tag_closers;
/**
* Holds updated HTML as updates are applied.
*
* Updates and unmodified portions of the input document are
* appended to this value as they are applied. It will hold
* a copy of the updated document up until the point of the
* latest applied update. The fully-updated HTML document
* will comprise this value plus the part of the input document
* which follows that latest update.
*
* @see $bytes_already_copied
*
* @since 6.2.0
* @var string
*/
private $output_buffer = '';
/** /**
* How many bytes from the original HTML document have been read and parsed. * How many bytes from the original HTML document have been read and parsed.
* *
@ -346,23 +329,6 @@ class WP_HTML_Tag_Processor {
*/ */
private $bytes_already_parsed = 0; private $bytes_already_parsed = 0;
/**
* How many bytes from the input HTML document have already been
* copied into the output buffer.
*
* Lexical updates are enqueued and processed in batches. Prior
* to any given update in the input document, there might exist
* a span of HTML unaffected by any changes. This span ought to
* be copied verbatim into the output buffer before applying the
* following update. This value will point to the starting byte
* offset in the input document where that unaffected span of
* HTML starts.
*
* @since 6.2.0
* @var int
*/
private $bytes_already_copied = 0;
/** /**
* Byte offset in input document where current tag name starts. * Byte offset in input document where current tag name starts.
* *
@ -1303,8 +1269,7 @@ class WP_HTML_Tag_Processor {
* @return void * @return void
*/ */
private function after_tag() { private function after_tag() {
$this->class_name_updates_to_attributes_updates(); $this->get_updated_html();
$this->apply_attributes_updates();
$this->tag_name_starts_at = null; $this->tag_name_starts_at = null;
$this->tag_name_length = null; $this->tag_name_length = null;
$this->tag_ends_at = null; $this->tag_ends_at = null;
@ -1460,15 +1425,19 @@ class WP_HTML_Tag_Processor {
* Applies attribute updates to HTML document. * Applies attribute updates to HTML document.
* *
* @since 6.2.0 * @since 6.2.0
* @since 6.2.1 Accumulates shift for internal cursor and passed pointer.
* @since 6.3.0 Invalidate any bookmarks whose targets are overwritten. * @since 6.3.0 Invalidate any bookmarks whose targets are overwritten.
* *
* @return void * @param int $shift_this_point Accumulate and return shift for this position.
* @return int How many bytes the given pointer moved in response to the updates.
*/ */
private function apply_attributes_updates() { private function apply_attributes_updates( $shift_this_point = 0 ) {
if ( ! count( $this->lexical_updates ) ) { if ( ! count( $this->lexical_updates ) ) {
return; return 0;
} }
$accumulated_shift_for_given_point = 0;
/* /*
* Attribute updates can be enqueued in any order but updates * Attribute updates can be enqueued in any order but updates
* to the document must occur in lexical order; that is, each * to the document must occur in lexical order; that is, each
@ -1481,12 +1450,28 @@ class WP_HTML_Tag_Processor {
*/ */
usort( $this->lexical_updates, array( self::class, 'sort_start_ascending' ) ); usort( $this->lexical_updates, array( self::class, 'sort_start_ascending' ) );
$bytes_already_copied = 0;
$output_buffer = '';
foreach ( $this->lexical_updates as $diff ) { foreach ( $this->lexical_updates as $diff ) {
$this->output_buffer .= substr( $this->html, $this->bytes_already_copied, $diff->start - $this->bytes_already_copied ); $shift = strlen( $diff->text ) - ( $diff->end - $diff->start );
$this->output_buffer .= $diff->text;
$this->bytes_already_copied = $diff->end; // Adjust the cursor position by however much an update affects it.
if ( $diff->start <= $this->bytes_already_parsed ) {
$this->bytes_already_parsed += $shift;
}
// Accumulate shift of the given pointer within this function call.
if ( $diff->start <= $shift_this_point ) {
$accumulated_shift_for_given_point += $shift;
}
$output_buffer .= substr( $this->html, $bytes_already_copied, $diff->start - $bytes_already_copied );
$output_buffer .= $diff->text;
$bytes_already_copied = $diff->end;
} }
$this->html = $output_buffer . substr( $this->html, $bytes_already_copied );
/* /*
* Adjust bookmark locations to account for how the text * Adjust bookmark locations to account for how the text
* replacements adjust offsets in the input document. * replacements adjust offsets in the input document.
@ -1527,6 +1512,8 @@ class WP_HTML_Tag_Processor {
} }
$this->lexical_updates = array(); $this->lexical_updates = array();
return $accumulated_shift_for_given_point;
} }
/** /**
@ -1576,8 +1563,6 @@ class WP_HTML_Tag_Processor {
// Point this tag processor before the sought tag opener and consume it. // Point this tag processor before the sought tag opener and consume it.
$this->bytes_already_parsed = $this->bookmarks[ $bookmark_name ]->start; $this->bytes_already_parsed = $this->bookmarks[ $bookmark_name ]->start;
$this->bytes_already_copied = $this->bytes_already_parsed;
$this->output_buffer = substr( $this->html, 0, $this->bytes_already_copied );
return $this->next_tag( array( 'tag_closers' => 'visit' ) ); return $this->next_tag( array( 'tag_closers' => 'visit' ) );
} }
@ -2122,6 +2107,7 @@ class WP_HTML_Tag_Processor {
* Returns the string representation of the HTML Tag Processor. * Returns the string representation of the HTML Tag Processor.
* *
* @since 6.2.0 * @since 6.2.0
* @since 6.2.1 Shifts the internal cursor corresponding to the applied updates.
* *
* @return string The processed HTML. * @return string The processed HTML.
*/ */
@ -2132,46 +2118,24 @@ class WP_HTML_Tag_Processor {
* When there is nothing more to update and nothing has already been * When there is nothing more to update and nothing has already been
* updated, return the original document and avoid a string copy. * updated, return the original document and avoid a string copy.
*/ */
if ( $requires_no_updating && 0 === $this->bytes_already_copied ) { if ( $requires_no_updating ) {
return $this->html; return $this->html;
} }
/* /*
* If there are no updates left to apply, but some have already * Keep track of the position right before the current tag. This will
* been applied, then finish by copying the rest of the input * be necessary for reparsing the current tag after updating the HTML.
* to the end of the updated document and return.
*/ */
if ( $requires_no_updating && $this->bytes_already_copied > 0 ) { $before_current_tag = $this->tag_name_starts_at - 1;
$this->html = $this->output_buffer . substr( $this->html, $this->bytes_already_copied );
$this->bytes_already_copied = strlen( $this->output_buffer );
return $this->output_buffer . substr( $this->html, $this->bytes_already_copied );
}
// Apply the updates, rewind to before the current tag, and reparse the attributes.
$content_up_to_opened_tag_name = $this->output_buffer . substr(
$this->html,
$this->bytes_already_copied,
$this->tag_name_starts_at + $this->tag_name_length - $this->bytes_already_copied
);
/* /*
* 1. Apply the edits by flushing them to the output buffer and updating the copied byte count. * 1. Apply the enqueued edits and update all the pointers to reflect those changes.
*
* Note: `apply_attributes_updates()` modifies `$this->output_buffer`.
*/ */
$this->class_name_updates_to_attributes_updates(); $this->class_name_updates_to_attributes_updates();
$this->apply_attributes_updates(); $before_current_tag += $this->apply_attributes_updates( $before_current_tag );
/* /*
* 2. Replace the original HTML with the now-updated HTML so that it's possible to * 2. Rewind to before the current tag and reparse to get updated attributes.
* seek to a previous location and have a consistent view of the updated document.
*/
$this->html = $this->output_buffer . substr( $this->html, $this->bytes_already_copied );
$this->output_buffer = $content_up_to_opened_tag_name;
$this->bytes_already_copied = strlen( $this->output_buffer );
/*
* 3. Point this tag processor at the original tag opener and consume it
* *
* At this point the internal cursor points to the end of the tag name. * At this point the internal cursor points to the end of the tag name.
* Rewind before the tag name starts so that it's as if the cursor didn't * Rewind before the tag name starts so that it's as if the cursor didn't
@ -2183,9 +2147,19 @@ class WP_HTML_Tag_Processor {
* ^ | back up by the length of the tag name plus the opening < * ^ | back up by the length of the tag name plus the opening <
* \<-/ back up by strlen("em") + 1 ==> 3 * \<-/ back up by strlen("em") + 1 ==> 3
*/ */
$this->bytes_already_parsed = strlen( $content_up_to_opened_tag_name ) - $this->tag_name_length - 1;
// Store existing state so it can be restored after reparsing.
$previous_parsed_byte_count = $this->bytes_already_parsed;
$previous_query = $this->last_query;
// Reparse attributes.
$this->bytes_already_parsed = $before_current_tag;
$this->next_tag(); $this->next_tag();
// Restore previous state.
$this->bytes_already_parsed = $previous_parsed_byte_count;
$this->parse_query( $previous_query );
return $this->html; return $this->html;
} }

2
wp-includes/version.php
View File

@ -16,7 +16,7 @@
* *
* @global string $wp_version * @global string $wp_version
*/ */
$wp_version = '6.3-alpha-55705'; $wp_version = '6.3-alpha-55706';
/** /**
* Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema. * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.