lement, meaning that * when SVG and MathML support is added, this needs to differentiate between an * HTML element of the given name, such as `
`, and a foreign element of * the same given name. */ if ( ! $this->state->stack_of_open_elements->current_node_is( $tag_name ) ) { // @todo Indicate a parse error once it's possible. } $this->state->stack_of_open_elements->pop_until( $tag_name ); $this->state->active_formatting_elements->clear_up_to_last_marker(); $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW; return true; /* * > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "td", * > "tfoot", "th", "thead", "tr" */ case '+CAPTION': case '+COL': case '+COLGROUP': case '+TBODY': case '+TD': case '+TFOOT': case '+TH': case '+THEAD': case '+TR': /* * > Assert: The stack of open elements has a td or th element in table scope. * * Nothing to do here, except to verify in tests that this never appears. */ $this->close_cell(); return $this->step( self::REPROCESS_CURRENT_NODE ); /* * > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html" */ case '-BODY': case '-CAPTION': case '-COL': case '-COLGROUP': case '-HTML': // Parse error: ignore the token. return $this->step(); /* * > An end tag whose tag name is one of: "table", "tbody", "tfoot", "thead", "tr" */ case '-TABLE': case '-TBODY': case '-TFOOT': case '-THEAD': case '-TR': if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) { // Parse error: ignore the token. return $this->step(); } $this->close_cell(); return $this->step( self::REPROCESS_CURRENT_NODE ); } /* * > Anything else * > Process the token using the rules for the "in body" insertion mode. */ return $this->step_in_body(); } /** * Parses next element in the 'in select' insertion mode. * * This internal function performs the 'in select' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inselect * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_in_select(): bool { $token_name = $this->get_token_name(); $token_type = $this->get_token_type(); $op_sigil = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : ''; $op = "{$op_sigil}{$token_name}"; switch ( $op ) { /* * > Any other character token */ case '#text': /* * > A character token that is U+0000 NULL * * If a text node only comprises null bytes then it should be * entirely ignored and should not return to calling code. */ if ( parent::TEXT_IS_NULL_SEQUENCE === $this->text_node_classification ) { // Parse error: ignore the token. return $this->step(); } $this->insert_html_element( $this->state->current_token ); return true; /* * > A comment token */ case '#comment': case '#funky-comment': case '#presumptuous-tag': $this->insert_html_element( $this->state->current_token ); return true; /* * > A DOCTYPE token */ case 'html': // Parse error: ignore the token. return $this->step(); /* * > A start tag whose tag name is "html" */ case '+HTML': return $this->step_in_body(); /* * > A start tag whose tag name is "option" */ case '+OPTION': if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) { $this->state->stack_of_open_elements->pop(); } $this->insert_html_element( $this->state->current_token ); return true; /* * > A start tag whose tag name is "optgroup" * > A start tag whose tag name is "hr" * * These rules are identical except for the treatment of the self-closing flag and * the subsequent pop of the HR void element, all of which is handled elsewhere in the processor. */ case '+OPTGROUP': case '+HR': if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) { $this->state->stack_of_open_elements->pop(); } if ( $this->state->stack_of_open_elements->current_node_is( 'OPTGROUP' ) ) { $this->state->stack_of_open_elements->pop(); } $this->insert_html_element( $this->state->current_token ); return true; /* * > An end tag whose tag name is "optgroup" */ case '-OPTGROUP': $current_node = $this->state->stack_of_open_elements->current_node(); if ( $current_node && 'OPTION' === $current_node->node_name ) { foreach ( $this->state->stack_of_open_elements->walk_up( $current_node ) as $parent ) { break; } if ( $parent && 'OPTGROUP' === $parent->node_name ) { $this->state->stack_of_open_elements->pop(); } } if ( $this->state->stack_of_open_elements->current_node_is( 'OPTGROUP' ) ) { $this->state->stack_of_open_elements->pop(); return true; } // Parse error: ignore the token. return $this->step(); /* * > An end tag whose tag name is "option" */ case '-OPTION': if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) { $this->state->stack_of_open_elements->pop(); return true; } // Parse error: ignore the token. return $this->step(); /* * > An end tag whose tag name is "select" * > A start tag whose tag name is "select" * * > It just gets treated like an end tag. */ case '-SELECT': case '+SELECT': if ( ! $this->state->stack_of_open_elements->has_element_in_select_scope( 'SELECT' ) ) { // Parse error: ignore the token. return $this->step(); } $this->state->stack_of_open_elements->pop_until( 'SELECT' ); $this->reset_insertion_mode_appropriately(); return true; /* * > A start tag whose tag name is one of: "input", "keygen", "textarea" * * All three of these tags are considered a parse error when found in this insertion mode. */ case '+INPUT': case '+KEYGEN': case '+TEXTAREA': if ( ! $this->state->stack_of_open_elements->has_element_in_select_scope( 'SELECT' ) ) { // Ignore the token. return $this->step(); } $this->state->stack_of_open_elements->pop_until( 'SELECT' ); $this->reset_insertion_mode_appropriately(); return $this->step( self::REPROCESS_CURRENT_NODE ); /* * > A start tag whose tag name is one of: "script", "template" * > An end tag whose tag name is "template" */ case '+SCRIPT': case '+TEMPLATE': case '-TEMPLATE': return $this->step_in_head(); } /* * > Anything else * > Parse error: ignore the token. */ return $this->step(); } /** * Parses next element in the 'in select in table' insertion mode. * * This internal function performs the 'in select in table' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#parsing-main-inselectintable * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_in_select_in_table(): bool { $token_name = $this->get_token_name(); $token_type = $this->get_token_type(); $op_sigil = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : ''; $op = "{$op_sigil}{$token_name}"; switch ( $op ) { /* * > A start tag whose tag name is one of: "caption", "table", "tbody", "tfoot", "thead", "tr", "td", "th" */ case '+CAPTION': case '+TABLE': case '+TBODY': case '+TFOOT': case '+THEAD': case '+TR': case '+TD': case '+TH': // @todo Indicate a parse error once it's possible. $this->state->stack_of_open_elements->pop_until( 'SELECT' ); $this->reset_insertion_mode_appropriately(); return $this->step( self::REPROCESS_CURRENT_NODE ); /* * > An end tag whose tag name is one of: "caption", "table", "tbody", "tfoot", "thead", "tr", "td", "th" */ case '-CAPTION': case '-TABLE': case '-TBODY': case '-TFOOT': case '-THEAD': case '-TR': case '-TD': case '-TH': // @todo Indicate a parse error once it's possible. if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $token_name ) ) { return $this->step(); } $this->state->stack_of_open_elements->pop_until( 'SELECT' ); $this->reset_insertion_mode_appropriately(); return $this->step( self::REPROCESS_CURRENT_NODE ); } /* * > Anything else */ return $this->step_in_select(); } /** * Parses next element in the 'in template' insertion mode. * * This internal function performs the 'in template' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 Stub implementation. * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#parsing-main-intemplate * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_in_template(): bool { $token_name = $this->get_token_name(); $token_type = $this->get_token_type(); $is_closer = $this->is_tag_closer(); $op_sigil = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : ''; $op = "{$op_sigil}{$token_name}"; switch ( $op ) { /* * > A character token * > A comment token * > A DOCTYPE token */ case '#text': case '#comment': case '#funky-comment': case '#presumptuous-tag': case 'html': return $this->step_in_body(); /* * > A start tag whose tag name is one of: "base", "basefont", "bgsound", "link", * > "meta", "noframes", "script", "style", "template", "title" * > An end tag whose tag name is "template" */ case '+BASE': case '+BASEFONT': case '+BGSOUND': case '+LINK': case '+META': case '+NOFRAMES': case '+SCRIPT': case '+STYLE': case '+TEMPLATE': case '+TITLE': case '-TEMPLATE': return $this->step_in_head(); /* * > A start tag whose tag name is one of: "caption", "colgroup", "tbody", "tfoot", "thead" */ case '+CAPTION': case '+COLGROUP': case '+TBODY': case '+TFOOT': case '+THEAD': array_pop( $this->state->stack_of_template_insertion_modes ); $this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE; $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE; return $this->step( self::REPROCESS_CURRENT_NODE ); /* * > A start tag whose tag name is "col" */ case '+COL': array_pop( $this->state->stack_of_template_insertion_modes ); $this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP; $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP; return $this->step( self::REPROCESS_CURRENT_NODE ); /* * > A start tag whose tag name is "tr" */ case '+TR': array_pop( $this->state->stack_of_template_insertion_modes ); $this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY; $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY; return $this->step( self::REPROCESS_CURRENT_NODE ); /* * > A start tag whose tag name is one of: "td", "th" */ case '+TD': case '+TH': array_pop( $this->state->stack_of_template_insertion_modes ); $this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW; $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW; return $this->step( self::REPROCESS_CURRENT_NODE ); } /* * > Any other start tag */ if ( ! $is_closer ) { array_pop( $this->state->stack_of_template_insertion_modes ); $this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; return $this->step( self::REPROCESS_CURRENT_NODE ); } /* * > Any other end tag */ if ( $is_closer ) { // Parse error: ignore the token. return $this->step(); } /* * > An end-of-file token */ if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) { // Stop parsing. return false; } // @todo Indicate a parse error once it's possible. $this->state->stack_of_open_elements->pop_until( 'TEMPLATE' ); $this->state->active_formatting_elements->clear_up_to_last_marker(); array_pop( $this->state->stack_of_template_insertion_modes ); $this->reset_insertion_mode_appropriately(); return $this->step( self::REPROCESS_CURRENT_NODE ); } /** * Parses next element in the 'after body' insertion mode. * * This internal function performs the 'after body' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 Stub implementation. * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#parsing-main-afterbody * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_after_body(): bool { $tag_name = $this->get_token_name(); $token_type = $this->get_token_type(); $op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : ''; $op = "{$op_sigil}{$tag_name}"; switch ( $op ) { /* * > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF), * > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE * * > Process the token using the rules for the "in body" insertion mode. */ case '#text': if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) { return $this->step_in_body(); } goto after_body_anything_else; break; /* * > A comment token */ case '#comment': case '#funky-comment': case '#presumptuous-tag': $this->bail( 'Content outside of BODY is unsupported.' ); break; /* * > A DOCTYPE token */ case 'html': // Parse error: ignore the token. return $this->step(); /* * > A start tag whose tag name is "html" */ case '+HTML': return $this->step_in_body(); /* * > An end tag whose tag name is "html" * * > If the parser was created as part of the HTML fragment parsing algorithm, * > this is a parse error; ignore the token. (fragment case) * > * > Otherwise, switch the insertion mode to "after after body". */ case '-HTML': if ( isset( $this->context_node ) ) { return $this->step(); } $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_BODY; return true; } /* * > Parse error. Switch the insertion mode to "in body" and reprocess the token. */ after_body_anything_else: $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; return $this->step( self::REPROCESS_CURRENT_NODE ); } /** * Parses next element in the 'in frameset' insertion mode. * * This internal function performs the 'in frameset' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 Stub implementation. * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#parsing-main-inframeset * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_in_frameset(): bool { $tag_name = $this->get_token_name(); $token_type = $this->get_token_type(); $op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : ''; $op = "{$op_sigil}{$tag_name}"; switch ( $op ) { /* * > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF), * > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE * > * > Insert the character. * * This algorithm effectively strips non-whitespace characters from text and inserts * them under HTML. This is not supported at this time. */ case '#text': if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) { return $this->step_in_body(); } $this->bail( 'Non-whitespace characters cannot be handled in frameset.' ); break; /* * > A comment token */ case '#comment': case '#funky-comment': case '#presumptuous-tag': $this->insert_html_element( $this->state->current_token ); return true; /* * > A DOCTYPE token */ case 'html': // Parse error: ignore the token. return $this->step(); /* * > A start tag whose tag name is "html" */ case '+HTML': return $this->step_in_body(); /* * > A start tag whose tag name is "frameset" */ case '+FRAMESET': $this->insert_html_element( $this->state->current_token ); return true; /* * > An end tag whose tag name is "frameset" */ case '-FRAMESET': /* * > If the current node is the root html element, then this is a parse error; * > ignore the token. (fragment case) */ if ( $this->state->stack_of_open_elements->current_node_is( 'HTML' ) ) { return $this->step(); } /* * > Otherwise, pop the current node from the stack of open elements. */ $this->state->stack_of_open_elements->pop(); /* * > If the parser was not created as part of the HTML fragment parsing algorithm * > (fragment case), and the current node is no longer a frameset element, then * > switch the insertion mode to "after frameset". */ if ( ! isset( $this->context_node ) && ! $this->state->stack_of_open_elements->current_node_is( 'FRAMESET' ) ) { $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_FRAMESET; } return true; /* * > A start tag whose tag name is "frame" * * > Insert an HTML element for the token. Immediately pop the * > current node off the stack of open elements. * > * > Acknowledge the token's self-closing flag, if it is set. */ case '+FRAME': $this->insert_html_element( $this->state->current_token ); $this->state->stack_of_open_elements->pop(); return true; /* * > A start tag whose tag name is "noframes" */ case '+NOFRAMES': return $this->step_in_head(); } // Parse error: ignore the token. return $this->step(); } /** * Parses next element in the 'after frameset' insertion mode. * * This internal function performs the 'after frameset' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 Stub implementation. * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#parsing-main-afterframeset * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_after_frameset(): bool { $tag_name = $this->get_token_name(); $token_type = $this->get_token_type(); $op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : ''; $op = "{$op_sigil}{$tag_name}"; switch ( $op ) { /* * > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF), * > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE * > * > Insert the character. * * This algorithm effectively strips non-whitespace characters from text and inserts * them under HTML. This is not supported at this time. */ case '#text': if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) { return $this->step_in_body(); } $this->bail( 'Non-whitespace characters cannot be handled in after frameset' ); break; /* * > A comment token */ case '#comment': case '#funky-comment': case '#presumptuous-tag': $this->insert_html_element( $this->state->current_token ); return true; /* * > A DOCTYPE token */ case 'html': // Parse error: ignore the token. return $this->step(); /* * > A start tag whose tag name is "html" */ case '+HTML': return $this->step_in_body(); /* * > An end tag whose tag name is "html" */ case '-HTML': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_FRAMESET; return true; /* * > A start tag whose tag name is "noframes" */ case '+NOFRAMES': return $this->step_in_head(); } // Parse error: ignore the token. return $this->step(); } /** * Parses next element in the 'after after body' insertion mode. * * This internal function performs the 'after after body' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 Stub implementation. * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#the-after-after-body-insertion-mode * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_after_after_body(): bool { $tag_name = $this->get_token_name(); $token_type = $this->get_token_type(); $op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : ''; $op = "{$op_sigil}{$tag_name}"; switch ( $op ) { /* * > A comment token */ case '#comment': case '#funky-comment': case '#presumptuous-tag': $this->bail( 'Content outside of HTML is unsupported.' ); break; /* * > A DOCTYPE token * > A start tag whose tag name is "html" * * > Process the token using the rules for the "in body" insertion mode. */ case 'html': case '+HTML': return $this->step_in_body(); /* * > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF), * > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE * > * > Process the token using the rules for the "in body" insertion mode. */ case '#text': if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) { return $this->step_in_body(); } goto after_after_body_anything_else; break; } /* * > Parse error. Switch the insertion mode to "in body" and reprocess the token. */ after_after_body_anything_else: $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; return $this->step( self::REPROCESS_CURRENT_NODE ); } /** * Parses next element in the 'after after frameset' insertion mode. * * This internal function performs the 'after after frameset' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 Stub implementation. * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#the-after-after-frameset-insertion-mode * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_after_after_frameset(): bool { $tag_name = $this->get_token_name(); $token_type = $this->get_token_type(); $op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : ''; $op = "{$op_sigil}{$tag_name}"; switch ( $op ) { /* * > A comment token */ case '#comment': case '#funky-comment': case '#presumptuous-tag': $this->bail( 'Content outside of HTML is unsupported.' ); break; /* * > A DOCTYPE token * > A start tag whose tag name is "html" * * > Process the token using the rules for the "in body" insertion mode. */ case 'html': case '+HTML': return $this->step_in_body(); /* * > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF), * > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE * > * > Process the token using the rules for the "in body" insertion mode. * * This algorithm effectively strips non-whitespace characters from text and inserts * them under HTML. This is not supported at this time. */ case '#text': if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) { return $this->step_in_body(); } $this->bail( 'Non-whitespace characters cannot be handled in after after frameset.' ); break; /* * > A start tag whose tag name is "noframes" */ case '+NOFRAMES': return $this->step_in_head(); } // Parse error: ignore the token. return $this->step(); } /** * Parses next element in the 'in foreign content' insertion mode. * * This internal function performs the 'in foreign content' insertion mode * logic for the generalized WP_HTML_Processor::step() function. * * @since 6.7.0 Stub implementation. * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#parsing-main-inforeign * @see WP_HTML_Processor::step * * @return bool Whether an element was found. */ private function step_in_foreign_content(): bool { $tag_name = $this->get_token_name(); $token_type = $this->get_token_type(); $op_sigil = '#tag' === $token_type ? ( $this->is_tag_closer() ? '-' : '+' ) : ''; $op = "{$op_sigil}{$tag_name}"; /* * > A start tag whose name is "font", if the token has any attributes named "color", "face", or "size" * * This section drawn out above the switch to more easily incorporate * the additional rules based on the presence of the attributes. */ if ( '+FONT' === $op && ( null !== $this->get_attribute( 'color' ) || null !== $this->get_attribute( 'face' ) || null !== $this->get_attribute( 'size' ) ) ) { $op = '+FONT with attributes'; } switch ( $op ) { case '#text': /* * > A character token that is U+0000 NULL * * This is handled by `get_modifiable_text()`. */ /* * Whitespace-only text does not affect the frameset-ok flag. * It is probably inter-element whitespace, but it may also * contain character references which decode only to whitespace. */ if ( parent::TEXT_IS_GENERIC === $this->text_node_classification ) { $this->state->frameset_ok = false; } $this->insert_foreign_element( $this->state->current_token, false ); return true; /* * CDATA sections are alternate wrappers for text content and therefore * ought to follow the same rules as text nodes. */ case '#cdata-section': /* * NULL bytes and whitespace do not change the frameset-ok flag. */ $current_token = $this->bookmarks[ $this->state->current_token->bookmark_name ]; $cdata_content_start = $current_token->start + 9; $cdata_content_length = $current_token->length - 12; if ( strspn( $this->html, "\0 \t\n\f\r", $cdata_content_start, $cdata_content_length ) !== $cdata_content_length ) { $this->state->frameset_ok = false; } $this->insert_foreign_element( $this->state->current_token, false ); return true; /* * > A comment token */ case '#comment': case '#funky-comment': case '#presumptuous-tag': $this->insert_foreign_element( $this->state->current_token, false ); return true; /* * > A DOCTYPE token */ case 'html': // Parse error: ignore the token. return $this->step(); /* * > A start tag whose tag name is "b", "big", "blockquote", "body", "br", "center", * > "code", "dd", "div", "dl", "dt", "em", "embed", "h1", "h2", "h3", "h4", "h5", * > "h6", "head", "hr", "i", "img", "li", "listing", "menu", "meta", "nobr", "ol", * > "p", "pre", "ruby", "s", "small", "span", "strong", "strike", "sub", "sup", * > "table", "tt", "u", "ul", "var" * * > A start tag whose name is "font", if the token has any attributes named "color", "face", or "size" * * > An end tag whose tag name is "br", "p" * * Closing BR tags are always reported by the Tag Processor as opening tags. */ case '+B': case '+BIG': case '+BLOCKQUOTE': case '+BODY': case '+BR': case '+CENTER': case '+CODE': case '+DD': case '+DIV': case '+DL': case '+DT': case '+EM': case '+EMBED': case '+H1': case '+H2': case '+H3': case '+H4': case '+H5': case '+H6': case '+HEAD': case '+HR': case '+I': case '+IMG': case '+LI': case '+LISTING': case '+MENU': case '+META': case '+NOBR': case '+OL': case '+P': case '+PRE': case '+RUBY': case '+S': case '+SMALL': case '+SPAN': case '+STRONG': case '+STRIKE': case '+SUB': case '+SUP': case '+TABLE': case '+TT': case '+U': case '+UL': case '+VAR': case '+FONT with attributes': case '-BR': case '-P': // @todo Indicate a parse error once it's possible. foreach ( $this->state->stack_of_open_elements->walk_up() as $current_node ) { if ( 'math' === $current_node->integration_node_type || 'html' === $current_node->integration_node_type || 'html' === $current_node->namespace ) { break; } $this->state->stack_of_open_elements->pop(); } goto in_foreign_content_process_in_current_insertion_mode; } /* * > Any other start tag */ if ( ! $this->is_tag_closer() ) { $this->insert_foreign_element( $this->state->current_token, false ); /* * > If the token has its self-closing flag set, then run * > the appropriate steps from the following list: * > * > ↪ the token's tag name is "script", and the new current node is in the SVG namespace * > Acknowledge the token's self-closing flag, and then act as * > described in the steps for a "script" end tag below. * > * > ↪ Otherwise * > Pop the current node off the stack of open elements and * > acknowledge the token's self-closing flag. * * Since the rules for SCRIPT below indicate to pop the element off of the stack of * open elements, which is the same for the Otherwise condition, there's no need to * separate these checks. The difference comes when a parser operates with the scripting * flag enabled, and executes the script, which this parser does not support. */ if ( $this->state->current_token->has_self_closing_flag ) { $this->state->stack_of_open_elements->pop(); } return true; } /* * > An end tag whose name is "script", if the current node is an SVG script element. */ if ( $this->is_tag_closer() && 'SCRIPT' === $this->state->current_token->node_name && 'svg' === $this->state->current_token->namespace ) { $this->state->stack_of_open_elements->pop(); return true; } /* * > Any other end tag */ if ( $this->is_tag_closer() ) { $node = $this->state->stack_of_open_elements->current_node(); if ( $tag_name !== $node->node_name ) { // @todo Indicate a parse error once it's possible. } in_foreign_content_end_tag_loop: if ( $node === $this->state->stack_of_open_elements->at( 1 ) ) { return true; } /* * > If node's tag name, converted to ASCII lowercase, is the same as the tag name * > of the token, pop elements from the stack of open elements until node has * > been popped from the stack, and then return. */ if ( 0 === strcasecmp( $node->node_name, $tag_name ) ) { foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) { $this->state->stack_of_open_elements->pop(); if ( $node === $item ) { return true; } } } foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $item ) { $node = $item; break; } if ( 'html' !== $node->namespace ) { goto in_foreign_content_end_tag_loop; } in_foreign_content_process_in_current_insertion_mode: switch ( $this->state->insertion_mode ) { case WP_HTML_Processor_State::INSERTION_MODE_INITIAL: return $this->step_initial(); case WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HTML: return $this->step_before_html(); case WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD: return $this->step_before_head(); case WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD: return $this->step_in_head(); case WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD_NOSCRIPT: return $this->step_in_head_noscript(); case WP_HTML_Processor_State::INSERTION_MODE_AFTER_HEAD: return $this->step_after_head(); case WP_HTML_Processor_State::INSERTION_MODE_IN_BODY: return $this->step_in_body(); case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE: return $this->step_in_table(); case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_TEXT: return $this->step_in_table_text(); case WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION: return $this->step_in_caption(); case WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP: return $this->step_in_column_group(); case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY: return $this->step_in_table_body(); case WP_HTML_Processor_State::INSERTION_MODE_IN_ROW: return $this->step_in_row(); case WP_HTML_Processor_State::INSERTION_MODE_IN_CELL: return $this->step_in_cell(); case WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT: return $this->step_in_select(); case WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT_IN_TABLE: return $this->step_in_select_in_table(); case WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE: return $this->step_in_template(); case WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY: return $this->step_after_body(); case WP_HTML_Processor_State::INSERTION_MODE_IN_FRAMESET: return $this->step_in_frameset(); case WP_HTML_Processor_State::INSERTION_MODE_AFTER_FRAMESET: return $this->step_after_frameset(); case WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_BODY: return $this->step_after_after_body(); case WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_FRAMESET: return $this->step_after_after_frameset(); // This should be unreachable but PHP doesn't have total type checking on switch. default: $this->bail( "Unaware of the requested parsing mode: '{$this->state->insertion_mode}'." ); } } $this->bail( 'Should not have been able to reach end of IN FOREIGN CONTENT processing. Check HTML API code.' ); // This unnecessary return prevents tools from inaccurately reporting type errors. return false; } /* * Internal helpers */ /** * Creates a new bookmark for the currently-matched token and returns the generated name. * * @since 6.4.0 * @since 6.5.0 Renamed from bookmark_tag() to bookmark_token(). * * @throws Exception When unable to allocate requested bookmark. * * @return string|false Name of created bookmark, or false if unable to create. */ private function bookmark_token() { if ( ! parent::set_bookmark( ++$this->bookmark_counter ) ) { $this->last_error = self::ERROR_EXCEEDED_MAX_BOOKMARKS; throw new Exception( 'could not allocate bookmark' ); } return "{$this->bookmark_counter}"; } /* * HTML semantic overrides for Tag Processor */ /** * Indicates the namespace of the current token, or "html" if there is none. * * @return string One of "html", "math", or "svg". */ public function get_namespace(): string { if ( ! isset( $this->current_element ) ) { return parent::get_namespace(); } return $this->current_element->token->namespace; } /** * Returns the uppercase name of the matched tag. * * The semantic rules for HTML specify that certain tags be reprocessed * with a different tag name. Because of this, the tag name presented * by the HTML Processor may differ from the one reported by the HTML * Tag Processor, which doesn't apply these semantic rules. * * Example: * * $processor = new WP_HTML_Tag_Processor( '
Test
' ); * $processor->next_tag() === true; * $processor->get_tag() === 'DIV'; * * $processor->next_tag() === false; * $processor->get_tag() === null; * * @since 6.4.0 * * @return string|null Name of currently matched tag in input HTML, or `null` if none found. */ public function get_tag(): ?string { if ( null !== $this->last_error ) { return null; } if ( $this->is_virtual() ) { return $this->current_element->token->node_name; } $tag_name = parent::get_tag(); /* * > A start tag whose tag name is "image" * > Change the token's tag name to "img" and reprocess it. (Don't ask.) */ return ( 'IMAGE' === $tag_name && 'html' === $this->get_namespace() ) ? 'IMG' : $tag_name; } /** * Indicates if the currently matched tag contains the self-closing flag. * * No HTML elements ought to have the self-closing flag and for those, the self-closing * flag will be ignored. For void elements this is benign because they "self close" * automatically. For non-void HTML elements though problems will appear if someone * intends to use a self-closing element in place of that element with an empty body. * For HTML foreign elements and custom elements the self-closing flag determines if * they self-close or not. * * This function does not determine if a tag is self-closing, * but only if the self-closing flag is present in the syntax. * * @since 6.6.0 Subclassed for the HTML Processor. * * @return bool Whether the currently matched tag contains the self-closing flag. */ public function has_self_closing_flag(): bool { return $this->is_virtual() ? false : parent::has_self_closing_flag(); } /** * Returns the node name represented by the token. * * This matches the DOM API value `nodeName`. Some values * are static, such as `#text` for a text node, while others * are dynamically generated from the token itself. * * Dynamic names: * - Uppercase tag name for tag matches. * - `html` for DOCTYPE declarations. * * Note that if the Tag Processor is not matched on a token * then this function will return `null`, either because it * hasn't yet found a token or because it reached the end * of the document without matching a token. * * @since 6.6.0 Subclassed for the HTML Processor. * * @return string|null Name of the matched token. */ public function get_token_name(): ?string { return $this->is_virtual() ? $this->current_element->token->node_name : parent::get_token_name(); } /** * Indicates the kind of matched token, if any. * * This differs from `get_token_name()` in that it always * returns a static string indicating the type, whereas * `get_token_name()` may return values derived from the * token itself, such as a tag name or processing * instruction tag. * * Possible values: * - `#tag` when matched on a tag. * - `#text` when matched on a text node. * - `#cdata-section` when matched on a CDATA node. * - `#comment` when matched on a comment. * - `#doctype` when matched on a DOCTYPE declaration. * - `#presumptuous-tag` when matched on an empty tag closer. * - `#funky-comment` when matched on a funky comment. * * @since 6.6.0 Subclassed for the HTML Processor. * * @return string|null What kind of token is matched, or null. */ public function get_token_type(): ?string { if ( $this->is_virtual() ) { /* * This logic comes from the Tag Processor. * * @todo It would be ideal not to repeat this here, but it's not clearly * better to allow passing a token name to `get_token_type()`. */ $node_name = $this->current_element->token->node_name; $starting_char = $node_name[0]; if ( 'A' <= $starting_char && 'Z' >= $starting_char ) { return '#tag'; } if ( 'html' === $node_name ) { return '#doctype'; } return $node_name; } return parent::get_token_type(); } /** * Returns the value of a requested attribute from a matched tag opener if that attribute exists. * * Example: * * $p = WP_HTML_Processor::create_fragment( '
Test
' ); * $p->next_token() === true; * $p->get_attribute( 'data-test-id' ) === '14'; * $p->get_attribute( 'enabled' ) === true; * $p->get_attribute( 'aria-label' ) === null; * * $p->next_tag() === false; * $p->get_attribute( 'class' ) === null; * * @since 6.6.0 Subclassed for HTML Processor. * * @param string $name Name of attribute whose value is requested. * @return string|true|null Value of attribute or `null` if not available. Boolean attributes return `true`. */ public function get_attribute( $name ) { return $this->is_virtual() ? null : parent::get_attribute( $name ); } /** * Updates or creates a new attribute on the currently matched tag with the passed value. * * For boolean attributes special handling is provided: * - When `true` is passed as the value, then only the attribute name is added to the tag. * - When `false` is passed, the attribute gets removed if it existed before. * * For string attributes, the value is escaped using the `esc_attr` function. * * @since 6.6.0 Subclassed for the HTML Processor. * * @param string $name The attribute name to target. * @param string|bool $value The new attribute value. * @return bool Whether an attribute value was set. */ public function set_attribute( $name, $value ): bool { return $this->is_virtual() ? false : parent::set_attribute( $name, $value ); } /** * Remove an attribute from the currently-matched tag. * * @since 6.6.0 Subclassed for HTML Processor. * * @param string $name The attribute name to remove. * @return bool Whether an attribute was removed. */ public function remove_attribute( $name ): bool { return $this->is_virtual() ? false : parent::remove_attribute( $name ); } /** * Gets lowercase names of all attributes matching a given prefix in the current tag. * * Note that matching is case-insensitive. This is in accordance with the spec: * * > There must never be two or more attributes on * > the same start tag whose names are an ASCII * > case-insensitive match for each other. * - HTML 5 spec * * Example: * * $p = new WP_HTML_Tag_Processor( '
Test
' ); * $p->next_tag( array( 'class_name' => 'test' ) ) === true; * $p->get_attribute_names_with_prefix( 'data-' ) === array( 'data-enabled', 'data-test-id' ); * * $p->next_tag() === false; * $p->get_attribute_names_with_prefix( 'data-' ) === null; * * @since 6.6.0 Subclassed for the HTML Processor. * * @see https://html.spec.whatwg.org/multipage/syntax.html#attributes-2:ascii-case-insensitive * * @param string $prefix Prefix of requested attribute names. * @return array|null List of attribute names, or `null` when no tag opener is matched. */ public function get_attribute_names_with_prefix( $prefix ): ?array { return $this->is_virtual() ? null : parent::get_attribute_names_with_prefix( $prefix ); } /** * Adds a new class name to the currently matched tag. * * @since 6.6.0 Subclassed for the HTML Processor. * * @param string $class_name The class name to add. * @return bool Whether the class was set to be added. */ public function add_class( $class_name ): bool { return $this->is_virtual() ? false : parent::add_class( $class_name ); } /** * Removes a class name from the currently matched tag. * * @since 6.6.0 Subclassed for the HTML Processor. * * @param string $class_name The class name to remove. * @return bool Whether the class was set to be removed. */ public function remove_class( $class_name ): bool { return $this->is_virtual() ? false : parent::remove_class( $class_name ); } /** * Returns if a matched tag contains the given ASCII case-insensitive class name. * * @since 6.6.0 Subclassed for the HTML Processor. * * @todo When reconstructing active formatting elements with attributes, find a way * to indicate if the virtually-reconstructed formatting elements contain the * wanted class name. * * @param string $wanted_class Look for this CSS class name, ASCII case-insensitive. * @return bool|null Whether the matched tag contains the given class name, or null if not matched. */ public function has_class( $wanted_class ): ?bool { return $this->is_virtual() ? null : parent::has_class( $wanted_class ); } /** * Generator for a foreach loop to step through each class name for the matched tag. * * This generator function is designed to be used inside a "foreach" loop. * * Example: * * $p = WP_HTML_Processor::create_fragment( "
" ); * $p->next_tag(); * foreach ( $p->class_list() as $class_name ) { * echo "{$class_name} "; * } * // Outputs: "free lang-en " * * @since 6.6.0 Subclassed for the HTML Processor. */ public function class_list() { return $this->is_virtual() ? null : parent::class_list(); } /** * Returns the modifiable text for a matched token, or an empty string. * * Modifiable text is text content that may be read and changed without * changing the HTML structure of the document around it. This includes * the contents of `#text` nodes in the HTML as well as the inner * contents of HTML comments, Processing Instructions, and others, even * though these nodes aren't part of a parsed DOM tree. They also contain * the contents of SCRIPT and STYLE tags, of TEXTAREA tags, and of any * other section in an HTML document which cannot contain HTML markup (DATA). * * If a token has no modifiable text then an empty string is returned to * avoid needless crashing or type errors. An empty string does not mean * that a token has modifiable text, and a token with modifiable text may * have an empty string (e.g. a comment with no contents). * * @since 6.6.0 Subclassed for the HTML Processor. * * @return string */ public function get_modifiable_text(): string { return $this->is_virtual() ? '' : parent::get_modifiable_text(); } /** * Indicates what kind of comment produced the comment node. * * Because there are different kinds of HTML syntax which produce * comments, the Tag Processor tracks and exposes this as a type * for the comment. Nominally only regular HTML comments exist as * they are commonly known, but a number of unrelated syntax errors * also produce comments. * * @see self::COMMENT_AS_ABRUPTLY_CLOSED_COMMENT * @see self::COMMENT_AS_CDATA_LOOKALIKE * @see self::COMMENT_AS_INVALID_HTML * @see self::COMMENT_AS_HTML_COMMENT * @see self::COMMENT_AS_PI_NODE_LOOKALIKE * * @since 6.6.0 Subclassed for the HTML Processor. * * @return string|null */ public function get_comment_type(): ?string { return $this->is_virtual() ? null : parent::get_comment_type(); } /** * Removes a bookmark that is no longer needed. * * Releasing a bookmark frees up the small * performance overhead it requires. * * @since 6.4.0 * * @param string $bookmark_name Name of the bookmark to remove. * @return bool Whether the bookmark already existed before removal. */ public function release_bookmark( $bookmark_name ): bool { return parent::release_bookmark( "_{$bookmark_name}" ); } /** * Moves the internal cursor in the HTML Processor to a given bookmark's location. * * Be careful! Seeking backwards to a previous location resets the parser to the * start of the document and reparses the entire contents up until it finds the * sought-after bookmarked location. * * In order to prevent accidental infinite loops, there's a * maximum limit on the number of times seek() can be called. * * @throws Exception When unable to allocate a bookmark for the next token in the input HTML document. * * @since 6.4.0 * * @param string $bookmark_name Jump to the place in the document identified by this bookmark name. * @return bool Whether the internal cursor was successfully moved to the bookmark's location. */ public function seek( $bookmark_name ): bool { // Flush any pending updates to the document before beginning. $this->get_updated_html(); $actual_bookmark_name = "_{$bookmark_name}"; $processor_started_at = $this->state->current_token ? $this->bookmarks[ $this->state->current_token->bookmark_name ]->start : 0; $bookmark_starts_at = $this->bookmarks[ $actual_bookmark_name ]->start; $direction = $bookmark_starts_at > $processor_started_at ? 'forward' : 'backward'; /* * If seeking backwards, it's possible that the sought-after bookmark exists within an element * which has been closed before the current cursor; in other words, it has already been removed * from the stack of open elements. This means that it's insufficient to simply pop off elements * from the stack of open elements which appear after the bookmarked location and then jump to * that location, as the elements which were open before won't be re-opened. * * In order to maintain consistency, the HTML Processor rewinds to the start of the document * and reparses everything until it finds the sought-after bookmark. * * There are potentially better ways to do this: cache the parser state for each bookmark and * restore it when seeking; store an immutable and idempotent register of where elements open * and close. * * If caching the parser state it will be essential to properly maintain the cached stack of * open elements and active formatting elements when modifying the document. This could be a * tedious and time-consuming process as well, and so for now will not be performed. * * It may be possible to track bookmarks for where elements open and close, and in doing so * be able to quickly recalculate breadcrumbs for any element in the document. It may even * be possible to remove the stack of open elements and compute it on the fly this way. * If doing this, the parser would need to track the opening and closing locations for all * tokens in the breadcrumb path for any and all bookmarks. By utilizing bookmarks themselves * this list could be automatically maintained while modifying the document. Finding the * breadcrumbs would then amount to traversing that list from the start until the token * being inspected. Once an element closes, if there are no bookmarks pointing to locations * within that element, then all of these locations may be forgotten to save on memory use * and computation time. */ if ( 'backward' === $direction ) { /* * Instead of clearing the parser state and starting fresh, calling the stack methods * maintains the proper flags in the parser. */ foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) { if ( 'context-node' === $item->bookmark_name ) { break; } $this->state->stack_of_open_elements->remove_node( $item ); } foreach ( $this->state->active_formatting_elements->walk_up() as $item ) { if ( 'context-node' === $item->bookmark_name ) { break; } $this->state->active_formatting_elements->remove_node( $item ); } parent::seek( 'context-node' ); $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; $this->state->frameset_ok = true; $this->element_queue = array(); $this->current_element = null; if ( isset( $this->context_node ) ) { $this->breadcrumbs = array_slice( $this->breadcrumbs, 0, 2 ); } else { $this->breadcrumbs = array(); } } // When moving forwards, reparse the document until reaching the same location as the original bookmark. if ( $bookmark_starts_at === $this->bookmarks[ $this->state->current_token->bookmark_name ]->start ) { return true; } while ( $this->next_token() ) { if ( $bookmark_starts_at === $this->bookmarks[ $this->state->current_token->bookmark_name ]->start ) { while ( isset( $this->current_element ) && WP_HTML_Stack_Event::POP === $this->current_element->operation ) { $this->current_element = array_shift( $this->element_queue ); } return true; } } return false; } /** * Sets a bookmark in the HTML document. * * Bookmarks represent specific places or tokens in the HTML * document, such as a tag opener or closer. When applying * edits to a document, such as setting an attribute, the * text offsets of that token may shift; the bookmark is * kept updated with those shifts and remains stable unless * the entire span of text in which the token sits is removed. * * Release bookmarks when they are no longer needed. * * Example: * *

Surprising fact you may not know!

* ^ ^ * \-|-- this `H2` opener bookmark tracks the token * *

Surprising fact you may no… * ^ ^ * \-|-- it shifts with edits * * Bookmarks provide the ability to seek to a previously-scanned * place in the HTML document. This avoids the need to re-scan * the entire document. * * Example: * *
  • One
  • Two
  • Three
* ^^^^ * want to note this last item * * $p = new WP_HTML_Tag_Processor( $html ); * $in_list = false; * while ( $p->next_tag( array( 'tag_closers' => $in_list ? 'visit' : 'skip' ) ) ) { * if ( 'UL' === $p->get_tag() ) { * if ( $p->is_tag_closer() ) { * $in_list = false; * $p->set_bookmark( 'resume' ); * if ( $p->seek( 'last-li' ) ) { * $p->add_class( 'last-li' ); * } * $p->seek( 'resume' ); * $p->release_bookmark( 'last-li' ); * $p->release_bookmark( 'resume' ); * } else { * $in_list = true; * } * } * * if ( 'LI' === $p->get_tag() ) { * $p->set_bookmark( 'last-li' ); * } * } * * Bookmarks intentionally hide the internal string offsets * to which they refer. They are maintained internally as * updates are applied to the HTML document and therefore * retain their "position" - the location to which they * originally pointed. The inability to use bookmarks with * functions like `substr` is therefore intentional to guard * against accidentally breaking the HTML. * * Because bookmarks allocate memory and require processing * for every applied update, they are limited and require * a name. They should not be created with programmatically-made * names, such as "li_{$index}" with some loop. As a general * rule they should only be created with string-literal names * like "start-of-section" or "last-paragraph". * * Bookmarks are a powerful tool to enable complicated behavior. * Consider double-checking that you need this tool if you are * reaching for it, as inappropriate use could lead to broken * HTML structure or unwanted processing overhead. * * @since 6.4.0 * * @param string $bookmark_name Identifies this particular bookmark. * @return bool Whether the bookmark was successfully created. */ public function set_bookmark( $bookmark_name ): bool { return parent::set_bookmark( "_{$bookmark_name}" ); } /** * Checks whether a bookmark with the given name exists. * * @since 6.5.0 * * @param string $bookmark_name Name to identify a bookmark that potentially exists. * @return bool Whether that bookmark exists. */ public function has_bookmark( $bookmark_name ): bool { return parent::has_bookmark( "_{$bookmark_name}" ); } /* * HTML Parsing Algorithms */ /** * Closes a P element. * * @since 6.4.0 * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#close-a-p-element */ private function close_a_p_element(): void { $this->generate_implied_end_tags( 'P' ); $this->state->stack_of_open_elements->pop_until( 'P' ); } /** * Closes elements that have implied end tags. * * @since 6.4.0 * @since 6.7.0 Full spec support. * * @see https://html.spec.whatwg.org/#generate-implied-end-tags * * @param string|null $except_for_this_element Perform as if this element doesn't exist in the stack of open elements. */ private function generate_implied_end_tags( ?string $except_for_this_element = null ): void { $elements_with_implied_end_tags = array( 'DD', 'DT', 'LI', 'OPTGROUP', 'OPTION', 'P', 'RB', 'RP', 'RT', 'RTC', ); $no_exclusions = ! isset( $except_for_this_element ); while ( ( $no_exclusions || ! $this->state->stack_of_open_elements->current_node_is( $except_for_this_element ) ) && in_array( $this->state->stack_of_open_elements->current_node()->node_name, $elements_with_implied_end_tags, true ) ) { $this->state->stack_of_open_elements->pop(); } } /** * Closes elements that have implied end tags, thoroughly. * * See the HTML specification for an explanation why this is * different from generating end tags in the normal sense. * * @since 6.4.0 * @since 6.7.0 Full spec support. * * @see WP_HTML_Processor::generate_implied_end_tags * @see https://html.spec.whatwg.org/#generate-implied-end-tags */ private function generate_implied_end_tags_thoroughly(): void { $elements_with_implied_end_tags = array( 'CAPTION', 'COLGROUP', 'DD', 'DT', 'LI', 'OPTGROUP', 'OPTION', 'P', 'RB', 'RP', 'RT', 'RTC', 'TBODY', 'TD', 'TFOOT', 'TH', 'THEAD', 'TR', ); while ( in_array( $this->state->stack_of_open_elements->current_node()->node_name, $elements_with_implied_end_tags, true ) ) { $this->state->stack_of_open_elements->pop(); } } /** * Returns the adjusted current node. * * > The adjusted current node is the context element if the parser was created as * > part of the HTML fragment parsing algorithm and the stack of open elements * > has only one element in it (fragment case); otherwise, the adjusted current * > node is the current node. * * @see https://html.spec.whatwg.org/#adjusted-current-node * * @since 6.7.0 * * @return WP_HTML_Token|null The adjusted current node. */ private function get_adjusted_current_node(): ?WP_HTML_Token { if ( isset( $this->context_node ) && 1 === $this->state->stack_of_open_elements->count() ) { return $this->context_node; } return $this->state->stack_of_open_elements->current_node(); } /** * Reconstructs the active formatting elements. * * > This has the effect of reopening all the formatting elements that were opened * > in the current body, cell, or caption (whichever is youngest) that haven't * > been explicitly closed. * * @since 6.4.0 * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#reconstruct-the-active-formatting-elements * * @return bool Whether any formatting elements needed to be reconstructed. */ private function reconstruct_active_formatting_elements(): bool { /* * > If there are no entries in the list of active formatting elements, then there is nothing * > to reconstruct; stop this algorithm. */ if ( 0 === $this->state->active_formatting_elements->count() ) { return false; } $last_entry = $this->state->active_formatting_elements->current_node(); if ( /* * > If the last (most recently added) entry in the list of active formatting elements is a marker; * > stop this algorithm. */ 'marker' === $last_entry->node_name || /* * > If the last (most recently added) entry in the list of active formatting elements is an * > element that is in the stack of open elements, then there is nothing to reconstruct; * > stop this algorithm. */ $this->state->stack_of_open_elements->contains_node( $last_entry ) ) { return false; } $this->bail( 'Cannot reconstruct active formatting elements when advancing and rewinding is required.' ); } /** * Runs the reset the insertion mode appropriately algorithm. * * @since 6.7.0 * * @see https://html.spec.whatwg.org/multipage/parsing.html#reset-the-insertion-mode-appropriately */ private function reset_insertion_mode_appropriately(): void { // Set the first node. $first_node = null; foreach ( $this->state->stack_of_open_elements->walk_down() as $first_node ) { break; } /* * > 1. Let _last_ be false. */ $last = false; foreach ( $this->state->stack_of_open_elements->walk_up() as $node ) { /* * > 2. Let _node_ be the last node in the stack of open elements. * > 3. _Loop_: If _node_ is the first node in the stack of open elements, then set _last_ * > to true, and, if the parser was created as part of the HTML fragment parsing * > algorithm (fragment case), set node to the context element passed to * > that algorithm. * > … */ if ( $node === $first_node ) { $last = true; if ( isset( $this->context_node ) ) { $node = $this->context_node; } } // All of the following rules are for matching HTML elements. if ( 'html' !== $node->namespace ) { continue; } switch ( $node->node_name ) { /* * > 4. If node is a `select` element, run these substeps: * > 1. If _last_ is true, jump to the step below labeled done. * > 2. Let _ancestor_ be _node_. * > 3. _Loop_: If _ancestor_ is the first node in the stack of open elements, * > jump to the step below labeled done. * > 4. Let ancestor be the node before ancestor in the stack of open elements. * > … * > 7. Jump back to the step labeled _loop_. * > 8. _Done_: Switch the insertion mode to "in select" and return. */ case 'SELECT': if ( ! $last ) { foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $ancestor ) { if ( 'html' !== $ancestor->namespace ) { continue; } switch ( $ancestor->node_name ) { /* * > 5. If _ancestor_ is a `template` node, jump to the step below * > labeled _done_. */ case 'TEMPLATE': break 2; /* * > 6. If _ancestor_ is a `table` node, switch the insertion mode to * > "in select in table" and return. */ case 'TABLE': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT_IN_TABLE; return; } } } $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT; return; /* * > 5. If _node_ is a `td` or `th` element and _last_ is false, then switch the * > insertion mode to "in cell" and return. */ case 'TD': case 'TH': if ( ! $last ) { $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_CELL; return; } break; /* * > 6. If _node_ is a `tr` element, then switch the insertion mode to "in row" * > and return. */ case 'TR': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW; return; /* * > 7. If _node_ is a `tbody`, `thead`, or `tfoot` element, then switch the * > insertion mode to "in table body" and return. */ case 'TBODY': case 'THEAD': case 'TFOOT': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY; return; /* * > 8. If _node_ is a `caption` element, then switch the insertion mode to * > "in caption" and return. */ case 'CAPTION': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION; return; /* * > 9. If _node_ is a `colgroup` element, then switch the insertion mode to * > "in column group" and return. */ case 'COLGROUP': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP; return; /* * > 10. If _node_ is a `table` element, then switch the insertion mode to * > "in table" and return. */ case 'TABLE': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE; return; /* * > 11. If _node_ is a `template` element, then switch the insertion mode to the * > current template insertion mode and return. */ case 'TEMPLATE': $this->state->insertion_mode = end( $this->state->stack_of_template_insertion_modes ); return; /* * > 12. If _node_ is a `head` element and _last_ is false, then switch the * > insertion mode to "in head" and return. */ case 'HEAD': if ( ! $last ) { $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD; return; } break; /* * > 13. If _node_ is a `body` element, then switch the insertion mode to "in body" * > and return. */ case 'BODY': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; return; /* * > 14. If _node_ is a `frameset` element, then switch the insertion mode to * > "in frameset" and return. (fragment case) */ case 'FRAMESET': $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_FRAMESET; return; /* * > 15. If _node_ is an `html` element, run these substeps: * > 1. If the head element pointer is null, switch the insertion mode to * > "before head" and return. (fragment case) * > 2. Otherwise, the head element pointer is not null, switch the insertion * > mode to "after head" and return. */ case 'HTML': $this->state->insertion_mode = isset( $this->state->head_element ) ? WP_HTML_Processor_State::INSERTION_MODE_AFTER_HEAD : WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD; return; } } /* * > 16. If _last_ is true, then switch the insertion mode to "in body" * > and return. (fragment case) * * This is only reachable if `$last` is true, as per the fragment parsing case. */ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; } /** * Runs the adoption agency algorithm. * * @since 6.4.0 * * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input. * * @see https://html.spec.whatwg.org/#adoption-agency-algorithm */ private function run_adoption_agency_algorithm(): void { $budget = 1000; $subject = $this->get_tag(); $current_node = $this->state->stack_of_open_elements->current_node(); if ( // > If the current node is an HTML element whose tag name is subject $current_node && $subject === $current_node->node_name && // > the current node is not in the list of active formatting elements ! $this->state->active_formatting_elements->contains_node( $current_node ) ) { $this->state->stack_of_open_elements->pop(); return; } $outer_loop_counter = 0; while ( $budget-- > 0 ) { if ( $outer_loop_counter++ >= 8 ) { return; } /* * > Let formatting element be the last element in the list of active formatting elements that: * > - is between the end of the list and the last marker in the list, * > if any, or the start of the list otherwise, * > - and has the tag name subject. */ $formatting_element = null; foreach ( $this->state->active_formatting_elements->walk_up() as $item ) { if ( 'marker' === $item->node_name ) { break; } if ( $subject === $item->node_name ) { $formatting_element = $item; break; } } // > If there is no such element, then return and instead act as described in the "any other end tag" entry above. if ( null === $formatting_element ) { $this->bail( 'Cannot run adoption agency when "any other end tag" is required.' ); } // > If formatting element is not in the stack of open elements, then this is a parse error; remove the element from the list, and return. if ( ! $this->state->stack_of_open_elements->contains_node( $formatting_element ) ) { $this->state->active_formatting_elements->remove_node( $formatting_element ); return; } // > If formatting element is in the stack of open elements, but the element is not in scope, then this is a parse error; return. if ( ! $this->state->stack_of_open_elements->has_element_in_scope( $formatting_element->node_name ) ) { return; } /* * > Let furthest block be the topmost node in the stack of open elements that is lower in the stack * > than formatting element, and is an element in the special category. There might not be one. */ $is_above_formatting_element = true; $furthest_block = null; foreach ( $this->state->stack_of_open_elements->walk_down() as $item ) { if ( $is_above_formatting_element && $formatting_element->bookmark_name !== $item->bookmark_name ) { continue; } if ( $is_above_formatting_element ) { $is_above_formatting_element = false; continue; } if ( self::is_special( $item ) ) { $furthest_block = $item; break; } } /* * > If there is no furthest block, then the UA must first pop all the nodes from the bottom of the * > stack of open elements, from the current node up to and including formatting element, then * > remove formatting element from the list of active formatting elements, and finally return. */ if ( null === $furthest_block ) { foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) { $this->state->stack_of_open_elements->pop(); if ( $formatting_element->bookmark_name === $item->bookmark_name ) { $this->state->active_formatting_elements->remove_node( $formatting_element ); return; } } } $this->bail( 'Cannot extract common ancestor in adoption agency algorithm.' ); } $this->bail( 'Cannot run adoption agency when looping required.' ); } /** * Runs the "close the cell" algorithm. * * > Where the steps above say to close the cell, they mean to run the following algorithm: * > 1. Generate implied end tags. * > 2. If the current node is not now a td element or a th element, then this is a parse error. * > 3. Pop elements from the stack of open elements stack until a td element or a th element has been popped from the stack. * > 4. Clear the list of active formatting elements up to the last marker. * > 5. Switch the insertion mode to "in row". * * @see https://html.spec.whatwg.org/multipage/parsing.html#close-the-cell * * @since 6.7.0 */ private function close_cell(): void { $this->generate_implied_end_tags(); // @todo Parse error if the current node is a "td" or "th" element. foreach ( $this->state->stack_of_open_elements->walk_up() as $element ) { $this->state->stack_of_open_elements->pop(); if ( 'TD' === $element->node_name || 'TH' === $element->node_name ) { break; } } $this->state->active_formatting_elements->clear_up_to_last_marker(); $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW; } /** * Inserts an HTML element on the stack of open elements. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#insert-a-foreign-element * * @param WP_HTML_Token $token Name of bookmark pointing to element in original input HTML. */ private function insert_html_element( WP_HTML_Token $token ): void { $this->state->stack_of_open_elements->push( $token ); } /** * Inserts a foreign element on to the stack of open elements. * * @since 6.7.0 * * @see https://html.spec.whatwg.org/#insert-a-foreign-element * * @param WP_HTML_Token $token Insert this token. The token's namespace and * insertion point will be updated correctly. * @param bool $only_add_to_element_stack Whether to skip the "insert an element at the adjusted * insertion location" algorithm when adding this element. */ private function insert_foreign_element( WP_HTML_Token $token, bool $only_add_to_element_stack ): void { $adjusted_current_node = $this->get_adjusted_current_node(); $token->namespace = $adjusted_current_node ? $adjusted_current_node->namespace : 'html'; if ( $this->is_mathml_integration_point() ) { $token->integration_node_type = 'math'; } elseif ( $this->is_html_integration_point() ) { $token->integration_node_type = 'html'; } if ( false === $only_add_to_element_stack ) { /* * @todo Implement the "appropriate place for inserting a node" and the * "insert an element at the adjusted insertion location" algorithms. * * These algorithms mostly impacts DOM tree construction and not the HTML API. * Here, there's no DOM node onto which the element will be appended, so the * parser will skip this step. * * @see https://html.spec.whatwg.org/#insert-an-element-at-the-adjusted-insertion-location */ } $this->insert_html_element( $token ); } /** * Inserts a virtual element on the stack of open elements. * * @since 6.7.0 * * @param string $token_name Name of token to create and insert into the stack of open elements. * @param string|null $bookmark_name Optional. Name to give bookmark for created virtual node. * Defaults to auto-creating a bookmark name. * @return WP_HTML_Token Newly-created virtual token. */ private function insert_virtual_node( $token_name, $bookmark_name = null ): WP_HTML_Token { $here = $this->bookmarks[ $this->state->current_token->bookmark_name ]; $name = $bookmark_name ?? $this->bookmark_token(); $this->bookmarks[ $name ] = new WP_HTML_Span( $here->start, 0 ); $token = new WP_HTML_Token( $name, $token_name, false ); $this->insert_html_element( $token ); return $token; } /* * HTML Specification Helpers */ /** * Indicates if the current token is a MathML integration point. * * @since 6.7.0 * * @see https://html.spec.whatwg.org/#mathml-text-integration-point * * @return bool Whether the current token is a MathML integration point. */ private function is_mathml_integration_point(): bool { $current_token = $this->state->current_token; if ( ! isset( $current_token ) ) { return false; } if ( 'math' !== $current_token->namespace || 'M' !== $current_token->node_name[0] ) { return false; } $tag_name = $current_token->node_name; return ( 'MI' === $tag_name || 'MO' === $tag_name || 'MN' === $tag_name || 'MS' === $tag_name || 'MTEXT' === $tag_name ); } /** * Indicates if the current token is an HTML integration point. * * Note that this method must be an instance method with access * to the current token, since it needs to examine the attributes * of the currently-matched tag, if it's in the MathML namespace. * Otherwise it would be required to scan the HTML and ensure that * no other accounting is overlooked. * * @since 6.7.0 * * @see https://html.spec.whatwg.org/#html-integration-point * * @return bool Whether the current token is an HTML integration point. */ private function is_html_integration_point(): bool { $current_token = $this->state->current_token; if ( ! isset( $current_token ) ) { return false; } if ( 'html' === $current_token->namespace ) { return false; } $tag_name = $current_token->node_name; if ( 'svg' === $current_token->namespace ) { return ( 'DESC' === $tag_name || 'FOREIGNOBJECT' === $tag_name || 'TITLE' === $tag_name ); } if ( 'math' === $current_token->namespace ) { if ( 'ANNOTATION-XML' !== $tag_name ) { return false; } $encoding = $this->get_attribute( 'encoding' ); return ( is_string( $encoding ) && ( 0 === strcasecmp( $encoding, 'application/xhtml+xml' ) || 0 === strcasecmp( $encoding, 'text/html' ) ) ); } $this->bail( 'Should not have reached end of HTML Integration Point detection: check HTML API code.' ); // This unnecessary return prevents tools from inaccurately reporting type errors. return false; } /** * Returns whether an element of a given name is in the HTML special category. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#special * * @param WP_HTML_Token|string $tag_name Node to check, or only its name if in the HTML namespace. * @return bool Whether the element of the given name is in the special category. */ public static function is_special( $tag_name ): bool { if ( is_string( $tag_name ) ) { $tag_name = strtoupper( $tag_name ); } else { $tag_name = 'html' === $tag_name->namespace ? strtoupper( $tag_name->node_name ) : "{$tag_name->namespace} {$tag_name->node_name}"; } return ( 'ADDRESS' === $tag_name || 'APPLET' === $tag_name || 'AREA' === $tag_name || 'ARTICLE' === $tag_name || 'ASIDE' === $tag_name || 'BASE' === $tag_name || 'BASEFONT' === $tag_name || 'BGSOUND' === $tag_name || 'BLOCKQUOTE' === $tag_name || 'BODY' === $tag_name || 'BR' === $tag_name || 'BUTTON' === $tag_name || 'CAPTION' === $tag_name || 'CENTER' === $tag_name || 'COL' === $tag_name || 'COLGROUP' === $tag_name || 'DD' === $tag_name || 'DETAILS' === $tag_name || 'DIR' === $tag_name || 'DIV' === $tag_name || 'DL' === $tag_name || 'DT' === $tag_name || 'EMBED' === $tag_name || 'FIELDSET' === $tag_name || 'FIGCAPTION' === $tag_name || 'FIGURE' === $tag_name || 'FOOTER' === $tag_name || 'FORM' === $tag_name || 'FRAME' === $tag_name || 'FRAMESET' === $tag_name || 'H1' === $tag_name || 'H2' === $tag_name || 'H3' === $tag_name || 'H4' === $tag_name || 'H5' === $tag_name || 'H6' === $tag_name || 'HEAD' === $tag_name || 'HEADER' === $tag_name || 'HGROUP' === $tag_name || 'HR' === $tag_name || 'HTML' === $tag_name || 'IFRAME' === $tag_name || 'IMG' === $tag_name || 'INPUT' === $tag_name || 'KEYGEN' === $tag_name || 'LI' === $tag_name || 'LINK' === $tag_name || 'LISTING' === $tag_name || 'MAIN' === $tag_name || 'MARQUEE' === $tag_name || 'MENU' === $tag_name || 'META' === $tag_name || 'NAV' === $tag_name || 'NOEMBED' === $tag_name || 'NOFRAMES' === $tag_name || 'NOSCRIPT' === $tag_name || 'OBJECT' === $tag_name || 'OL' === $tag_name || 'P' === $tag_name || 'PARAM' === $tag_name || 'PLAINTEXT' === $tag_name || 'PRE' === $tag_name || 'SCRIPT' === $tag_name || 'SEARCH' === $tag_name || 'SECTION' === $tag_name || 'SELECT' === $tag_name || 'SOURCE' === $tag_name || 'STYLE' === $tag_name || 'SUMMARY' === $tag_name || 'TABLE' === $tag_name || 'TBODY' === $tag_name || 'TD' === $tag_name || 'TEMPLATE' === $tag_name || 'TEXTAREA' === $tag_name || 'TFOOT' === $tag_name || 'TH' === $tag_name || 'THEAD' === $tag_name || 'TITLE' === $tag_name || 'TR' === $tag_name || 'TRACK' === $tag_name || 'UL' === $tag_name || 'WBR' === $tag_name || 'XMP' === $tag_name || // MathML. 'math MI' === $tag_name || 'math MO' === $tag_name || 'math MN' === $tag_name || 'math MS' === $tag_name || 'math MTEXT' === $tag_name || 'math ANNOTATION-XML' === $tag_name || // SVG. 'svg DESC' === $tag_name || 'svg FOREIGNOBJECT' === $tag_name || 'svg TITLE' === $tag_name ); } /** * Returns whether a given element is an HTML Void Element * * > area, base, br, col, embed, hr, img, input, link, meta, source, track, wbr * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#void-elements * * @param string $tag_name Name of HTML tag to check. * @return bool Whether the given tag is an HTML Void Element. */ public static function is_void( $tag_name ): bool { $tag_name = strtoupper( $tag_name ); return ( 'AREA' === $tag_name || 'BASE' === $tag_name || 'BASEFONT' === $tag_name || // Obsolete but still treated as void. 'BGSOUND' === $tag_name || // Obsolete but still treated as void. 'BR' === $tag_name || 'COL' === $tag_name || 'EMBED' === $tag_name || 'FRAME' === $tag_name || 'HR' === $tag_name || 'IMG' === $tag_name || 'INPUT' === $tag_name || 'KEYGEN' === $tag_name || // Obsolete but still treated as void. 'LINK' === $tag_name || 'META' === $tag_name || 'PARAM' === $tag_name || // Obsolete but still treated as void. 'SOURCE' === $tag_name || 'TRACK' === $tag_name || 'WBR' === $tag_name ); } /** * Gets an encoding from a given string. * * This is an algorithm defined in the WHAT-WG specification. * * Example: * * 'UTF-8' === self::get_encoding( 'utf8' ); * 'UTF-8' === self::get_encoding( " \tUTF-8 " ); * null === self::get_encoding( 'UTF-7' ); * null === self::get_encoding( 'utf8; charset=' ); * * @see https://encoding.spec.whatwg.org/#concept-encoding-get * * @todo As this parser only supports UTF-8, only the UTF-8 * encodings are detected. Add more as desired, but the * parser will bail on non-UTF-8 encodings. * * @since 6.7.0 * * @param string $label A string which may specify a known encoding. * @return string|null Known encoding if matched, otherwise null. */ protected static function get_encoding( string $label ): ?string { /* * > Remove any leading and trailing ASCII whitespace from label. */ $label = trim( $label, " \t\f\r\n" ); /* * > If label is an ASCII case-insensitive match for any of the labels listed in the * > table below, then return the corresponding encoding; otherwise return failure. */ switch ( strtolower( $label ) ) { case 'unicode-1-1-utf-8': case 'unicode11utf8': case 'unicode20utf8': case 'utf-8': case 'utf8': case 'x-unicode20utf8': return 'UTF-8'; default: return null; } } /* * Constants that would pollute the top of the class if they were found there. */ /** * Indicates that the next HTML token should be parsed and processed. * * @since 6.4.0 * * @var string */ const PROCESS_NEXT_NODE = 'process-next-node'; /** * Indicates that the current HTML token should be reprocessed in the newly-selected insertion mode. * * @since 6.4.0 * * @var string */ const REPROCESS_CURRENT_NODE = 'reprocess-current-node'; /** * Indicates that the current HTML token should be processed without advancing the parser. * * @since 6.5.0 * * @var string */ const PROCESS_CURRENT_NODE = 'process-current-node'; /** * Indicates that the parser encountered unsupported markup and has bailed. * * @since 6.4.0 * * @var string */ const ERROR_UNSUPPORTED = 'unsupported'; /** * Indicates that the parser encountered more HTML tokens than it * was able to process and has bailed. * * @since 6.4.0 * * @var string */ const ERROR_EXCEEDED_MAX_BOOKMARKS = 'exceeded-max-bookmarks'; /** * Unlock code that must be passed into the constructor to create this class. * * This class extends the WP_HTML_Tag_Processor, which has a public class * constructor. Therefore, it's not possible to have a private constructor here. * * This unlock code is used to ensure that anyone calling the constructor is * doing so with a full understanding that it's intended to be a private API. * * @access private */ const CONSTRUCTOR_UNLOCK_CODE = 'Use WP_HTML_Processor::create_fragment() instead of calling the class constructor directly.'; } ['dependencies'] : array(); $block_version = isset( $metadata['version'] ) ? $metadata['version'] : false; $script_version = isset( $script_asset['version'] ) ? $script_asset['version'] : $block_version; $script_args = array(); if ( 'viewScript' === $field_name && $script_uri ) { $script_args['strategy'] = 'defer'; } $result = wp_register_script( $script_handle, $script_uri, $script_dependencies, $script_version, $script_args ); if ( ! $result ) { return false; } if ( ! empty( $metadata['textdomain'] ) && in_array( 'wp-i18n', $script_dependencies, true ) ) { wp_set_script_translations( $script_handle, $metadata['textdomain'] ); } return $script_handle; } /** * Finds a style handle for the block metadata field. It detects when a path * to file was provided and registers the style under automatically * generated handle name. It returns unprocessed style handle otherwise. * * @since 5.5.0 * @since 6.1.0 Added `$index` parameter. * * @param array $metadata Block metadata. * @param string $field_name Field name to pick from metadata. * @param int $index Optional. Index of the style to register when multiple items passed. * Default 0. * @return string|false Style handle provided directly or created through * style's registration, or false on failure. */ function register_block_style_handle( $metadata, $field_name, $index = 0 ) { if ( empty( $metadata[ $field_name ] ) ) { return false; } $style_handle = $metadata[ $field_name ]; if ( is_array( $style_handle ) ) { if ( empty( $style_handle[ $index ] ) ) { return false; } $style_handle = $style_handle[ $index ]; } $style_handle_name = generate_block_asset_handle( $metadata['name'], $field_name, $index ); // If the style handle is already registered, skip re-registering. if ( wp_style_is( $style_handle_name, 'registered' ) ) { return $style_handle_name; } static $wpinc_path_norm = ''; if ( ! $wpinc_path_norm ) { $wpinc_path_norm = wp_normalize_path( realpath( ABSPATH . WPINC ) ); } $is_core_block = isset( $metadata['file'] ) && str_starts_with( $metadata['file'], $wpinc_path_norm ); // Skip registering individual styles for each core block when a bundled version provided. if ( $is_core_block && ! wp_should_load_separate_core_block_assets() ) { return false; } $style_path = remove_block_asset_path_prefix( $style_handle ); $is_style_handle = $style_handle === $style_path; // Allow only passing style handles for core blocks. if ( $is_core_block && ! $is_style_handle ) { return false; } // Return the style handle unless it's the first item for every core block that requires special treatment. if ( $is_style_handle && ! ( $is_core_block && 0 === $index ) ) { return $style_handle; } // Check whether styles should have a ".min" suffix or not. $suffix = SCRIPT_DEBUG ? '' : '.min'; if ( $is_core_block ) { $style_path = ( 'editorStyle' === $field_name ) ? "editor{$suffix}.css" : "style{$suffix}.css"; } $style_path_norm = wp_normalize_path( realpath( dirname( $metadata['file'] ) . '/' . $style_path ) ); $style_uri = get_block_asset_url( $style_path_norm ); $version = ! $is_core_block && isset( $metadata['version'] ) ? $metadata['version'] : false; $result = wp_register_style( $style_handle_name, $style_uri, array(), $version ); if ( ! $result ) { return false; } if ( $style_uri ) { wp_style_add_data( $style_handle_name, 'path', $style_path_norm ); if ( $is_core_block ) { $rtl_file = str_replace( "{$suffix}.css", "-rtl{$suffix}.css", $style_path_norm ); } else { $rtl_file = str_replace( '.css', '-rtl.css', $style_path_norm ); } if ( is_rtl() && file_exists( $rtl_file ) ) { wp_style_add_data( $style_handle_name, 'rtl', 'replace' ); wp_style_add_data( $style_handle_name, 'suffix', $suffix ); wp_style_add_data( $style_handle_name, 'path', $rtl_file ); } } return $style_handle_name; } /** * Gets i18n schema for block's metadata read from `block.json` file. * * @since 5.9.0 * * @return object The schema for block's metadata. */ function get_block_metadata_i18n_schema() { static $i18n_block_schema; if ( ! isset( $i18n_block_schema ) ) { $i18n_block_schema = wp_json_file_decode( __DIR__ . '/block-i18n.json' ); } return $i18n_block_schema; } /** * Registers a block metadata collection. * * This function allows core and third-party plugins to register their block metadata * collections in a centralized location. Registering collections can improve performance * by avoiding multiple reads from the filesystem and parsing JSON. * * @since 6.7.0 * * @param string $path The base path in which block files for the collection reside. * @param string $manifest The path to the manifest file for the collection. */ function wp_register_block_metadata_collection( $path, $manifest ) { WP_Block_Metadata_Registry::register_collection( $path, $manifest ); } /** * Registers a block type from the metadata stored in the `block.json` file. * * @since 5.5.0 * @since 5.7.0 Added support for `textdomain` field and i18n handling for all translatable fields. * @since 5.9.0 Added support for `variations` and `viewScript` fields. * @since 6.1.0 Added support for `render` field. * @since 6.3.0 Added `selectors` field. * @since 6.4.0 Added support for `blockHooks` field. * @since 6.5.0 Added support for `allowedBlocks`, `viewScriptModule`, and `viewStyle` fields. * @since 6.7.0 Allow PHP filename as `variations` argument. * * @param string $file_or_folder Path to the JSON file with metadata definition for * the block or path to the folder where the `block.json` file is located. * If providing the path to a JSON file, the filename must end with `block.json`. * @param array $args Optional. Array of block type arguments. Accepts any public property * of `WP_Block_Type`. See WP_Block_Type::__construct() for information * on accepted arguments. Default empty array. * @return WP_Block_Type|false The registered block type on success, or false on failure. */ function register_block_type_from_metadata( $file_or_folder, $args = array() ) { /* * Get an array of metadata from a PHP file. * This improves performance for core blocks as it's only necessary to read a single PHP file * instead of reading a JSON file per-block, and then decoding from JSON to PHP. * Using a static variable ensures that the metadata is only read once per request. */ $metadata_file = ( ! str_ends_with( $file_or_folder, 'block.json' ) ) ? trailingslashit( $file_or_folder ) . 'block.json' : $file_or_folder; $is_core_block = str_starts_with( $file_or_folder, ABSPATH . WPINC ); $metadata_file_exists = $is_core_block || file_exists( $metadata_file ); $registry_metadata = WP_Block_Metadata_Registry::get_metadata( $file_or_folder ); if ( $registry_metadata ) { $metadata = $registry_metadata; } elseif ( $metadata_file_exists ) { $metadata = wp_json_file_decode( $metadata_file, array( 'associative' => true ) ); } else { $metadata = array(); } if ( ! is_array( $metadata ) || ( empty( $metadata['name'] ) && empty( $args['name'] ) ) ) { return false; } $metadata['file'] = $metadata_file_exists ? wp_normalize_path( realpath( $metadata_file ) ) : null; /** * Filters the metadata provided for registering a block type. * * @since 5.7.0 * * @param array $metadata Metadata for registering a block type. */ $metadata = apply_filters( 'block_type_metadata', $metadata ); // Add `style` and `editor_style` for core blocks if missing. if ( ! empty( $metadata['name'] ) && str_starts_with( $metadata['name'], 'core/' ) ) { $block_name = str_replace( 'core/', '', $metadata['name'] ); if ( ! isset( $metadata['style'] ) ) { $metadata['style'] = "wp-block-$block_name"; } if ( current_theme_supports( 'wp-block-styles' ) && wp_should_load_separate_core_block_assets() ) { $metadata['style'] = (array) $metadata['style']; $metadata['style'][] = "wp-block-{$block_name}-theme"; } if ( ! isset( $metadata['editorStyle'] ) ) { $metadata['editorStyle'] = "wp-block-{$block_name}-editor"; } } $settings = array(); $property_mappings = array( 'apiVersion' => 'api_version', 'name' => 'name', 'title' => 'title', 'category' => 'category', 'parent' => 'parent', 'ancestor' => 'ancestor', 'icon' => 'icon', 'description' => 'description', 'keywords' => 'keywords', 'attributes' => 'attributes', 'providesContext' => 'provides_context', 'usesContext' => 'uses_context', 'selectors' => 'selectors', 'supports' => 'supports', 'styles' => 'styles', 'variations' => 'variations', 'example' => 'example', 'allowedBlocks' => 'allowed_blocks', ); $textdomain = ! empty( $metadata['textdomain'] ) ? $metadata['textdomain'] : null; $i18n_schema = get_block_metadata_i18n_schema(); foreach ( $property_mappings as $key => $mapped_key ) { if ( isset( $metadata[ $key ] ) ) { $settings[ $mapped_key ] = $metadata[ $key ]; if ( $metadata_file_exists && $textdomain && isset( $i18n_schema->$key ) ) { $settings[ $mapped_key ] = translate_settings_using_i18n_schema( $i18n_schema->$key, $settings[ $key ], $textdomain ); } } } if ( ! empty( $metadata['render'] ) ) { $template_path = wp_normalize_path( realpath( dirname( $metadata['file'] ) . '/' . remove_block_asset_path_prefix( $metadata['render'] ) ) ); if ( $template_path ) { /** * Renders the block on the server. * * @since 6.1.0 * * @param array $attributes Block attributes. * @param string $content Block default content. * @param WP_Block $block Block instance. * * @return string Returns the block content. */ $settings['render_callback'] = static function ( $attributes, $content, $block ) use ( $template_path ) { ob_start(); require $template_path; return ob_get_clean(); }; } } // If `variations` is a string, it's the name of a PHP file that // generates the variations. if ( ! empty( $metadata['variations'] ) && is_string( $metadata['variations'] ) ) { $variations_path = wp_normalize_path( realpath( dirname( $metadata['file'] ) . '/' . remove_block_asset_path_prefix( $metadata['variations'] ) ) ); if ( $variations_path ) { /** * Generates the list of block variations. * * @since 6.7.0 * * @return string Returns the list of block variations. */ $settings['variation_callback'] = static function () use ( $variations_path ) { $variations = require $variations_path; return $variations; }; // The block instance's `variations` field is only allowed to be an array // (of known block variations). We unset it so that the block instance will // provide a getter that returns the result of the `variation_callback` instead. unset( $settings['variations'] ); } } $settings = array_merge( $settings, $args ); $script_fields = array( 'editorScript' => 'editor_script_handles', 'script' => 'script_handles', 'viewScript' => 'view_script_handles', ); foreach ( $script_fields as $metadata_field_name => $settings_field_name ) { if ( ! empty( $settings[ $metadata_field_name ] ) ) { $metadata[ $metadata_field_name ] = $settings[ $metadata_field_name ]; } if ( ! empty( $metadata[ $metadata_field_name ] ) ) { $scripts = $metadata[ $metadata_field_name ]; $processed_scripts = array(); if ( is_array( $scripts ) ) { for ( $index = 0; $index < count( $scripts ); $index++ ) { $result = register_block_script_handle( $metadata, $metadata_field_name, $index ); if ( $result ) { $processed_scripts[] = $result; } } } else { $result = register_block_script_handle( $metadata, $metadata_field_name ); if ( $result ) { $processed_scripts[] = $result; } } $settings[ $settings_field_name ] = $processed_scripts; } } $module_fields = array( 'viewScriptModule' => 'view_script_module_ids', ); foreach ( $module_fields as $metadata_field_name => $settings_field_name ) { if ( ! empty( $settings[ $metadata_field_name ] ) ) { $metadata[ $metadata_field_name ] = $settings[ $metadata_field_name ]; } if ( ! empty( $metadata[ $metadata_field_name ] ) ) { $modules = $metadata[ $metadata_field_name ]; $processed_modules = array(); if ( is_array( $modules ) ) { for ( $index = 0; $index < count( $modules ); $index++ ) { $result = register_block_script_module_id( $metadata, $metadata_field_name, $index ); if ( $result ) { $processed_modules[] = $result; } } } else { $result = register_block_script_module_id( $metadata, $metadata_field_name ); if ( $result ) { $processed_modules[] = $result; } } $settings[ $settings_field_name ] = $processed_modules; } } $style_fields = array( 'editorStyle' => 'editor_style_handles', 'style' => 'style_handles', 'viewStyle' => 'view_style_handles', ); foreach ( $style_fields as $metadata_field_name => $settings_field_name ) { if ( ! empty( $settings[ $metadata_field_name ] ) ) { $metadata[ $metadata_field_name ] = $settings[ $metadata_field_name ]; } if ( ! empty( $metadata[ $metadata_field_name ] ) ) { $styles = $metadata[ $metadata_field_name ]; $processed_styles = array(); if ( is_array( $styles ) ) { for ( $index = 0; $index < count( $styles ); $index++ ) { $result = register_block_style_handle( $metadata, $metadata_field_name, $index ); if ( $result ) { $processed_styles[] = $result; } } } else { $result = register_block_style_handle( $metadata, $metadata_field_name ); if ( $result ) { $processed_styles[] = $result; } } $settings[ $settings_field_name ] = $processed_styles; } } if ( ! empty( $metadata['blockHooks'] ) ) { /** * Map camelCased position string (from block.json) to snake_cased block type position. * * @var array */ $position_mappings = array( 'before' => 'before', 'after' => 'after', 'firstChild' => 'first_child', 'lastChild' => 'last_child', ); $settings['block_hooks'] = array(); foreach ( $metadata['blockHooks'] as $anchor_block_name => $position ) { // Avoid infinite recursion (hooking to itself). if ( $metadata['name'] === $anchor_block_name ) { _doing_it_wrong( __METHOD__, __( 'Cannot hook block to itself.' ), '6.4.0' ); continue; } if ( ! isset( $position_mappings[ $position ] ) ) { continue; } $settings['block_hooks'][ $anchor_block_name ] = $position_mappings[ $position ]; } } /** * Filters the settings determined from the block type metadata. * * @since 5.7.0 * * @param array $settings Array of determined settings for registering a block type. * @param array $metadata Metadata provided for registering a block type. */ $settings = apply_filters( 'block_type_metadata_settings', $settings, $metadata ); $metadata['name'] = ! empty( $settings['name'] ) ? $settings['name'] : $metadata['name']; return WP_Block_Type_Registry::get_instance()->register( $metadata['name'], $settings ); } /** * Registers a block type. The recommended way is to register a block type using * the metadata stored in the `block.json` file. * * @since 5.0.0 * @since 5.8.0 First parameter now accepts a path to the `block.json` file. * * @param string|WP_Block_Type $block_type Block type name including namespace, or alternatively * a path to the JSON file with metadata definition for the block, * or a path to the folder where the `block.json` file is located, * or a complete WP_Block_Type instance. * In case a WP_Block_Type is provided, the $args parameter will be ignored. * @param array $args Optional. Array of block type arguments. Accepts any public property * of `WP_Block_Type`. See WP_Block_Type::__construct() for information * on accepted arguments. Default empty array. * * @return WP_Block_Type|false The registered block type on success, or false on failure. */ function register_block_type( $block_type, $args = array() ) { if ( is_string( $block_type ) && file_exists( $block_type ) ) { return register_block_type_from_metadata( $block_type, $args ); } return WP_Block_Type_Registry::get_instance()->register( $block_type, $args ); } /** * Unregisters a block type. * * @since 5.0.0 * * @param string|WP_Block_Type $name Block type name including namespace, or alternatively * a complete WP_Block_Type instance. * @return WP_Block_Type|false The unregistered block type on success, or false on failure. */ function unregister_block_type( $name ) { return WP_Block_Type_Registry::get_instance()->unregister( $name ); } /** * Determines whether a post or content string has blocks. * * This test optimizes for performance rather than strict accuracy, detecting * the pattern of a block but not validating its structure. For strict accuracy, * you should use the block parser on post content. * * @since 5.0.0 * * @see parse_blocks() * * @param int|string|WP_Post|null $post Optional. Post content, post ID, or post object. * Defaults to global $post. * @return bool Whether the post has blocks. */ function has_blocks( $post = null ) { if ( ! is_string( $post ) ) { $wp_post = get_post( $post ); if ( ! $wp_post instanceof WP_Post ) { return false; } $post = $wp_post->post_content; } return str_contains( (string) $post, '' ) + strlen( '-->' ); $end = strrpos( $serialized_block, '' ) + strlen( '-->' ); $end = strrpos( $serialized_block, '', $serialized_block_name, $serialized_attributes ); } return sprintf( '%s', $serialized_block_name, $serialized_attributes, $block_content, $serialized_block_name ); } /** * Returns the content of a block, including comment delimiters, serializing all * attributes from the given parsed block. * * This should be used when preparing a block to be saved to post content. * Prefer `render_block` when preparing a block for display. Unlike * `render_block`, this does not evaluate a block's `render_callback`, and will * instead preserve the markup as parsed. * * @since 5.3.1 * * @param array $block { * An associative array of a single parsed block object. See WP_Block_Parser_Block. * * @type string $blockName Name of block. * @type array $attrs Attributes from block comment delimiters. * @type array[] $innerBlocks List of inner blocks. An array of arrays that * have the same structure as this one. * @type string $innerHTML HTML from inside block comment delimiters. * @type array $innerContent List of string fragments and null markers where * inner blocks were found. * } * @return string String of rendered HTML. */ function serialize_block( $block ) { $block_content = ''; $index = 0; foreach ( $block['innerContent'] as $chunk ) { $block_content .= is_string( $chunk ) ? $chunk : serialize_block( $block['innerBlocks'][ $index++ ] ); } if ( ! is_array( $block['attrs'] ) ) { $block['attrs'] = array(); } return get_comment_delimited_block_content( $block['blockName'], $block['attrs'], $block_content ); } /** * Returns a joined string of the aggregate serialization of the given * parsed blocks. * * @since 5.3.1 * * @param array[] $blocks { * Array of block structures. * * @type array ...$0 { * An associative array of a single parsed block object. See WP_Block_Parser_Block. * * @type string $blockName Name of block. * @type array $attrs Attributes from block comment delimiters. * @type array[] $innerBlocks List of inner blocks. An array of arrays that * have the same structure as this one. * @type string $innerHTML HTML from inside block comment delimiters. * @type array $innerContent List of string fragments and null markers where * inner blocks were found. * } * } * @return string String of rendered HTML. */ function serialize_blocks( $blocks ) { return implode( '', array_map( 'serialize_block', $blocks ) ); } /** * Traverses a parsed block tree and applies callbacks before and after serializing it. * * Recursively traverses the block and its inner blocks and applies the two callbacks provided as * arguments, the first one before serializing the block, and the second one after serializing it. * If either callback returns a string value, it will be prepended and appended to the serialized * block markup, respectively. * * The callbacks will receive a reference to the current block as their first argument, so that they * can also modify it, and the current block's parent block as second argument. Finally, the * `$pre_callback` receives the previous block, whereas the `$post_callback` receives * the next block as third argument. * * Serialized blocks are returned including comment delimiters, and with all attributes serialized. * * This function should be used when there is a need to modify the saved block, or to inject markup * into the return value. Prefer `serialize_block` when preparing a block to be saved to post content. * * This function is meant for internal use only. * * @since 6.4.0 * @access private * * @see serialize_block() * * @param array $block An associative array of a single parsed block object. See WP_Block_Parser_Block. * @param callable $pre_callback Callback to run on each block in the tree before it is traversed and serialized. * It is called with the following arguments: &$block, $parent_block, $previous_block. * Its string return value will be prepended to the serialized block markup. * @param callable $post_callback Callback to run on each block in the tree after it is traversed and serialized. * It is called with the following arguments: &$block, $parent_block, $next_block. * Its string return value will be appended to the serialized block markup. * @return string Serialized block markup. */ function traverse_and_serialize_block( $block, $pre_callback = null, $post_callback = null ) { $block_content = ''; $block_index = 0; foreach ( $block['innerContent'] as $chunk ) { if ( is_string( $chunk ) ) { $block_content .= $chunk; } else { $inner_block = $block['innerBlocks'][ $block_index ]; if ( is_callable( $pre_callback ) ) { $prev = 0 === $block_index ? null : $block['innerBlocks'][ $block_index - 1 ]; $block_content .= call_user_func_array( $pre_callback, array( &$inner_block, &$block, $prev ) ); } if ( is_callable( $post_callback ) ) { $next = count( $block['innerBlocks'] ) - 1 === $block_index ? null : $block['innerBlocks'][ $block_index + 1 ]; $post_markup = call_user_func_array( $post_callback, array( &$inner_block, &$block, $next ) ); } $block_content .= traverse_and_serialize_block( $inner_block, $pre_callback, $post_callback ); $block_content .= isset( $post_markup ) ? $post_markup : ''; ++$block_index; } } if ( ! is_array( $block['attrs'] ) ) { $block['attrs'] = array(); } return get_comment_delimited_block_content( $block['blockName'], $block['attrs'], $block_content ); } /** * Replaces patterns in a block tree with their content. * * @since 6.6.0 * * @param array $blocks An array blocks. * * @return array An array of blocks with patterns replaced by their content. */ function resolve_pattern_blocks( $blocks ) { static $inner_content; // Keep track of seen references to avoid infinite loops. static $seen_refs = array(); $i = 0; while ( $i < count( $blocks ) ) { if ( 'core/pattern' === $blocks[ $i ]['blockName'] ) { $attrs = $blocks[ $i ]['attrs']; if ( empty( $attrs['slug'] ) ) { ++$i; continue; } $slug = $attrs['slug']; if ( isset( $seen_refs[ $slug ] ) ) { // Skip recursive patterns. array_splice( $blocks, $i, 1 ); continue; } $registry = WP_Block_Patterns_Registry::get_instance(); $pattern = $registry->get_registered( $slug ); // Skip unknown patterns. if ( ! $pattern ) { ++$i; continue; } $blocks_to_insert = parse_blocks( $pattern['content'] ); $seen_refs[ $slug ] = true; $prev_inner_content = $inner_content; $inner_content = null; $blocks_to_insert = resolve_pattern_blocks( $blocks_to_insert ); $inner_content = $prev_inner_content; unset( $seen_refs[ $slug ] ); array_splice( $blocks, $i, 1, $blocks_to_insert ); // If we have inner content, we need to insert nulls in the // inner content array, otherwise serialize_blocks will skip // blocks. if ( $inner_content ) { $null_indices = array_keys( $inner_content, null, true ); $content_index = $null_indices[ $i ]; $nulls = array_fill( 0, count( $blocks_to_insert ), null ); array_splice( $inner_content, $content_index, 1, $nulls ); } // Skip inserted blocks. $i += count( $blocks_to_insert ); } else { if ( ! empty( $blocks[ $i ]['innerBlocks'] ) ) { $prev_inner_content = $inner_content; $inner_content = $blocks[ $i ]['innerContent']; $blocks[ $i ]['innerBlocks'] = resolve_pattern_blocks( $blocks[ $i ]['innerBlocks'] ); $blocks[ $i ]['innerContent'] = $inner_content; $inner_content = $prev_inner_content; } ++$i; } } return $blocks; } /** * Given an array of parsed block trees, applies callbacks before and after serializing them and * returns their concatenated output. * * Recursively traverses the blocks and their inner blocks and applies the two callbacks provided as * arguments, the first one before serializing a block, and the second one after serializing. * If either callback returns a string value, it will be prepended and appended to the serialized * block markup, respectively. * * The callbacks will receive a reference to the current block as their first argument, so that they * can also modify it, and the current block's parent block as second argument. Finally, the * `$pre_callback` receives the previous block, whereas the `$post_callback` receives * the next block as third argument. * * Serialized blocks are returned including comment delimiters, and with all attributes serialized. * * This function should be used when there is a need to modify the saved blocks, or to inject markup * into the return value. Prefer `serialize_blocks` when preparing blocks to be saved to post content. * * This function is meant for internal use only. * * @since 6.4.0 * @access private * * @see serialize_blocks() * * @param array[] $blocks An array of parsed blocks. See WP_Block_Parser_Block. * @param callable $pre_callback Callback to run on each block in the tree before it is traversed and serialized. * It is called with the following arguments: &$block, $parent_block, $previous_block. * Its string return value will be prepended to the serialized block markup. * @param callable $post_callback Callback to run on each block in the tree after it is traversed and serialized. * It is called with the following arguments: &$block, $parent_block, $next_block. * Its string return value will be appended to the serialized block markup. * @return string Serialized block markup. */ function traverse_and_serialize_blocks( $blocks, $pre_callback = null, $post_callback = null ) { $result = ''; $parent_block = null; // At the top level, there is no parent block to pass to the callbacks; yet the callbacks expect a reference. $pre_callback_is_callable = is_callable( $pre_callback ); $post_callback_is_callable = is_callable( $post_callback ); foreach ( $blocks as $index => $block ) { if ( $pre_callback_is_callable ) { $prev = 0 === $index ? null : $blocks[ $index - 1 ]; $result .= call_user_func_array( $pre_callback, array( &$block, &$parent_block, $prev ) ); } if ( $post_callback_is_callable ) { $next = count( $blocks ) - 1 === $index ? null : $blocks[ $index + 1 ]; $post_markup = call_user_func_array( $post_callback, array( &$block, &$parent_block, $next ) ); } $result .= traverse_and_serialize_block( $block, $pre_callback, $post_callback ); $result .= isset( $post_markup ) ? $post_markup : ''; } return $result; } /** * Filters and sanitizes block content to remove non-allowable HTML * from parsed block attribute values. * * @since 5.3.1 * * @param string $text Text that may contain block content. * @param array[]|string $allowed_html Optional. An array of allowed HTML elements and attributes, * or a context name such as 'post'. See wp_kses_allowed_html() * for the list of accepted context names. Default 'post'. * @param string[] $allowed_protocols Optional. Array of allowed URL protocols. * Defaults to the result of wp_allowed_protocols(). * @return string The filtered and sanitized content result. */ function filter_block_content( $text, $allowed_html = 'post', $allowed_protocols = array() ) { $result = ''; if ( str_contains( $text, '' ) ) { $text = preg_replace_callback( '%%', '_filter_block_content_callback', $text ); } $blocks = parse_blocks( $text ); foreach ( $blocks as $block ) { $block = filter_block_kses( $block, $allowed_html, $allowed_protocols ); $result .= serialize_block( $block ); } return $result; } /** * Callback used for regular expression replacement in filter_block_content(). * * @since 6.2.1 * @access private * * @param array $matches Array of preg_replace_callback matches. * @return string Replacement string. */ function _filter_block_content_callback( $matches ) { return ''; } /** * Filters and sanitizes a parsed block to remove non-allowable HTML * from block attribute values. * * @since 5.3.1 * * @param WP_Block_Parser_Block $block The parsed block object. * @param array[]|string $allowed_html An array of allowed HTML elements and attributes, * or a context name such as 'post'. See wp_kses_allowed_html() * for the list of accepted context names. * @param string[] $allowed_protocols Optional. Array of allowed URL protocols. * Defaults to the result of wp_allowed_protocols(). * @return array The filtered and sanitized block object result. */ function filter_block_kses( $block, $allowed_html, $allowed_protocols = array() ) { $block['attrs'] = filter_block_kses_value( $block['attrs'], $allowed_html, $allowed_protocols, $block ); if ( is_array( $block['innerBlocks'] ) ) { foreach ( $block['innerBlocks'] as $i => $inner_block ) { $block['innerBlocks'][ $i ] = filter_block_kses( $inner_block, $allowed_html, $allowed_protocols ); } } return $block; } /** * Filters and sanitizes a parsed block attribute value to remove * non-allowable HTML. * * @since 5.3.1 * @since 6.5.5 Added the `$block_context` parameter. * * @param string[]|string $value The attribute value to filter. * @param array[]|string $allowed_html An array of allowed HTML elements and attributes, * or a context name such as 'post'. See wp_kses_allowed_html() * for the list of accepted context names. * @param string[] $allowed_protocols Optional. Array of allowed URL protocols. * Defaults to the result of wp_allowed_protocols(). * @param array $block_context Optional. The block the attribute belongs to, in parsed block array format. * @return string[]|string The filtered and sanitized result. */ function filter_block_kses_value( $value, $allowed_html, $allowed_protocols = array(), $block_context = null ) { if ( is_array( $value ) ) { foreach ( $value as $key => $inner_value ) { $filtered_key = filter_block_kses_value( $key, $allowed_html, $allowed_protocols, $block_context ); $filtered_value = filter_block_kses_value( $inner_value, $allowed_html, $allowed_protocols, $block_context ); if ( isset( $block_context['blockName'] ) && 'core/template-part' === $block_context['blockName'] ) { $filtered_value = filter_block_core_template_part_attributes( $filtered_value, $filtered_key, $allowed_html ); } if ( $filtered_key !== $key ) { unset( $value[ $key ] ); } $value[ $filtered_key ] = $filtered_value; } } elseif ( is_string( $value ) ) { return wp_kses( $value, $allowed_html, $allowed_protocols ); } return $value; } /** * Sanitizes the value of the Template Part block's `tagName` attribute. * * @since 6.5.5 * * @param string $attribute_value The attribute value to filter. * @param string $attribute_name The attribute name. * @param array[]|string $allowed_html An array of allowed HTML elements and attributes, * or a context name such as 'post'. See wp_kses_allowed_html() * for the list of accepted context names. * @return string The sanitized attribute value. */ function filter_block_core_template_part_attributes( $attribute_value, $attribute_name, $allowed_html ) { if ( empty( $attribute_value ) || 'tagName' !== $attribute_name ) { return $attribute_value; } if ( ! is_array( $allowed_html ) ) { $allowed_html = wp_kses_allowed_html( $allowed_html ); } return isset( $allowed_html[ $attribute_value ] ) ? $attribute_value : ''; } /** * Parses blocks out of a content string, and renders those appropriate for the excerpt. * * As the excerpt should be a small string of text relevant to the full post content, * this function renders the blocks that are most likely to contain such text. * * @since 5.0.0 * * @param string $content The content to parse. * @return string The parsed and filtered content. */ function excerpt_remove_blocks( $content ) { if ( ! has_blocks( $content ) ) { return $content; } $allowed_inner_blocks = array( // Classic blocks have their blockName set to null. null, 'core/freeform', 'core/heading', 'core/html', 'core/list', 'core/media-text', 'core/paragraph', 'core/preformatted', 'core/pullquote', 'core/quote', 'core/table', 'core/verse', ); $allowed_wrapper_blocks = array( 'core/columns', 'core/column', 'core/group', ); /** * Filters the list of blocks that can be used as wrapper blocks, allowing * excerpts to be generated from the `innerBlocks` of these wrappers. * * @since 5.8.0 * * @param string[] $allowed_wrapper_blocks The list of names of allowed wrapper blocks. */ $allowed_wrapper_blocks = apply_filters( 'excerpt_allowed_wrapper_blocks', $allowed_wrapper_blocks ); $allowed_blocks = array_merge( $allowed_inner_blocks, $allowed_wrapper_blocks ); /** * Filters the list of blocks that can contribute to the excerpt. * * If a dynamic block is added to this list, it must not generate another * excerpt, as this will cause an infinite loop to occur. * * @since 5.0.0 * * @param string[] $allowed_blocks The list of names of allowed blocks. */ $allowed_blocks = apply_filters( 'excerpt_allowed_blocks', $allowed_blocks ); $blocks = parse_blocks( $content ); $output = ''; foreach ( $blocks as $block ) { if ( in_array( $block['blockName'], $allowed_blocks, true ) ) { if ( ! empty( $block['innerBlocks'] ) ) { if ( in_array( $block['blockName'], $allowed_wrapper_blocks, true ) ) { $output .= _excerpt_render_inner_blocks( $block, $allowed_blocks ); continue; } // Skip the block if it has disallowed or nested inner blocks. foreach ( $block['innerBlocks'] as $inner_block ) { if ( ! in_array( $inner_block['blockName'], $allowed_inner_blocks, true ) || ! empty( $inner_block['innerBlocks'] ) ) { continue 2; } } } $output .= render_block( $block ); } } return $output; } /** * Parses footnotes markup out of a content string, * and renders those appropriate for the excerpt. * * @since 6.3.0 * * @param string $content The content to parse. * @return string The parsed and filtered content. */ function excerpt_remove_footnotes( $content ) { if ( ! str_contains( $content, 'data-fn=' ) ) { return $content; } return preg_replace( '_\s*\d+\s*_', '', $content ); } /** * Renders inner blocks from the allowed wrapper blocks * for generating an excerpt. * * @since 5.8.0 * @access private * * @param array $parsed_block The parsed block. * @param array $allowed_blocks The list of allowed inner blocks. * @return string The rendered inner blocks. */ function _excerpt_render_inner_blocks( $parsed_block, $allowed_blocks ) { $output = ''; foreach ( $parsed_block['innerBlocks'] as $inner_block ) { if ( ! in_array( $inner_block['blockName'], $allowed_blocks, true ) ) { continue; } if ( empty( $inner_block['innerBlocks'] ) ) { $output .= render_block( $inner_block ); } else { $output .= _excerpt_render_inner_blocks( $inner_block, $allowed_blocks ); } } return $output; } /** * Renders a single block into a HTML string. * * @since 5.0.0 * * @global WP_Post $post The post to edit. * * @param array $parsed_block { * An associative array of the block being rendered. See WP_Block_Parser_Block. * * @type string $blockName Name of block. * @type array $attrs Attributes from block comment delimiters. * @type array[] $innerBlocks List of inner blocks. An array of arrays that * have the same structure as this one. * @type string $innerHTML HTML from inside block comment delimiters. * @type array $innerContent List of string fragments and null markers where * inner blocks were found. * } * @return string String of rendered HTML. */ function render_block( $parsed_block ) { global $post; $parent_block = null; /** * Allows render_block() to be short-circuited, by returning a non-null value. * * @since 5.1.0 * @since 5.9.0 The `$parent_block` parameter was added. * * @param string|null $pre_render The pre-rendered content. Default null. * @param array $parsed_block { * An associative array of the block being rendered. See WP_Block_Parser_Block. * * @type string $blockName Name of block. * @type array $attrs Attributes from block comment delimiters. * @type array[] $innerBlocks List of inner blocks. An array of arrays that * have the same structure as this one. * @type string $innerHTML HTML from inside block comment delimiters. * @type array $innerContent List of string fragments and null markers where * inner blocks were found. * } * @param WP_Block|null $parent_block If this is a nested block, a reference to the parent block. */ $pre_render = apply_filters( 'pre_render_block', null, $parsed_block, $parent_block ); if ( ! is_null( $pre_render ) ) { return $pre_render; } $source_block = $parsed_block; /** * Filters the block being rendered in render_block(), before it's processed. * * @since 5.1.0 * @since 5.9.0 The `$parent_block` parameter was added. * * @param array $parsed_block { * An associative array of the block being rendered. See WP_Block_Parser_Block. * * @type string $blockName Name of block. * @type array $attrs Attributes from block comment delimiters. * @type array[] $innerBlocks List of inner blocks. An array of arrays that * have the same structure as this one. * @type string $innerHTML HTML from inside block comment delimiters. * @type array $innerContent List of string fragments and null markers where * inner blocks were found. * } * @param array $source_block { * An un-modified copy of `$parsed_block`, as it appeared in the source content. * See WP_Block_Parser_Block. * * @type string $blockName Name of block. * @type array $attrs Attributes from block comment delimiters. * @type array[] $innerBlocks List of inner blocks. An array of arrays that * have the same structure as this one. * @type string $innerHTML HTML from inside block comment delimiters. * @type array $innerContent List of string fragments and null markers where * inner blocks were found. * } * @param WP_Block|null $parent_block If this is a nested block, a reference to the parent block. */ $parsed_block = apply_filters( 'render_block_data', $parsed_block, $source_block, $parent_block ); $context = array(); if ( $post instanceof WP_Post ) { $context['postId'] = $post->ID; /* * The `postType` context is largely unnecessary server-side, since the ID * is usually sufficient on its own. That being said, since a block's * manifest is expected to be shared between the server and the client, * it should be included to consistently fulfill the expectation. */ $context['postType'] = $post->post_type; } /** * Filters the default context provided to a rendered block. * * @since 5.5.0 * @since 5.9.0 The `$parent_block` parameter was added. * * @param array $context Default context. * @param array $parsed_block { * An associative array of the block being rendered. See WP_Block_Parser_Block. * * @type string $blockName Name of block. * @type array $attrs Attributes from block comment delimiters. * @type array[] $innerBlocks List of inner blocks. An array of arrays that * have the same structure as this one. * @type string $innerHTML HTML from inside block comment delimiters. * @type array $innerContent List of string fragments and null markers where * inner blocks were found. * } * @param WP_Block|null $parent_block If this is a nested block, a reference to the parent block. */ $context = apply_filters( 'render_block_context', $context, $parsed_block, $parent_block ); $block = new WP_Block( $parsed_block, $context ); return $block->render(); } /** * Parses blocks out of a content string. * * @since 5.0.0 * * @param string $content Post content. * @return array[] { * Array of block structures. * * @type array ...$0 { * An associative array of a single parsed block object. See WP_Block_Parser_Block. * * @type string $blockName Name of block. * @type array $attrs Attributes from block comment delimiters. * @type array[] $innerBlocks List of inner blocks. An array of arrays that * have the same structure as this one. * @type string $innerHTML HTML from inside block comment delimiters. * @type array $innerContent List of string fragments and null markers where * inner blocks were found. * } * } */ function parse_blocks( $content ) { /** * Filter to allow plugins to replace the server-side block parser. * * @since 5.0.0 * * @param string $parser_class Name of block parser class. */ $parser_class = apply_filters( 'block_parser_class', 'WP_Block_Parser' ); $parser = new $parser_class(); return $parser->parse( $content ); } /** * Parses dynamic blocks out of `post_content` and re-renders them. * * @since 5.0.0 * * @param string $content Post content. * @return string Updated post content. */ function do_blocks( $content ) { $blocks = parse_blocks( $content ); $output = ''; foreach ( $blocks as $block ) { $output .= render_block( $block ); } // If there are blocks in this content, we shouldn't run wpautop() on it later. $priority = has_filter( 'the_content', 'wpautop' ); if ( false !== $priority && doing_filter( 'the_content' ) && has_blocks( $content ) ) { remove_filter( 'the_content', 'wpautop', $priority ); add_filter( 'the_content', '_restore_wpautop_hook', $priority + 1 ); } return $output; } /** * If do_blocks() needs to remove wpautop() from the `the_content` filter, this re-adds it afterwards, * for subsequent `the_content` usage. * * @since 5.0.0 * @access private * * @param string $content The post content running through this filter. * @return string The unmodified content. */ function _restore_wpautop_hook( $content ) { $current_priority = has_filter( 'the_content', '_restore_wpautop_hook' ); add_filter( 'the_content', 'wpautop', $current_priority - 1 ); remove_filter( 'the_content', '_restore_wpautop_hook', $current_priority ); return $content; } /** * Returns the current version of the block format that the content string is using. * * If the string doesn't contain blocks, it returns 0. * * @since 5.0.0 * * @param string $content Content to test. * @return int The block format version is 1 if the content contains one or more blocks, 0 otherwise. */ function block_version( $content ) { return has_blocks( $content ) ? 1 : 0; } /** * Registers a new block style. * * @since 5.3.0 * @since 6.6.0 Added support for registering styles for multiple block types. * * @link https://developer.wordpress.org/block-editor/reference-guides/block-api/block-styles/ * * @param string|string[] $block_name Block type name including namespace or array of namespaced block type names. * @param array $style_properties Array containing the properties of the style name, label, * style_handle (name of the stylesheet to be enqueued), * inline_style (string containing the CSS to be added), * style_data (theme.json-like array to generate CSS from). * See WP_Block_Styles_Registry::register(). * @return bool True if the block style was registered with success and false otherwise. */ function register_block_style( $block_name, $style_properties ) { return WP_Block_Styles_Registry::get_instance()->register( $block_name, $style_properties ); } /** * Unregisters a block style. * * @since 5.3.0 * * @param string $block_name Block type name including namespace. * @param string $block_style_name Block style name. * @return bool True if the block style was unregistered with success and false otherwise. */ function unregister_block_style( $block_name, $block_style_name ) { return WP_Block_Styles_Registry::get_instance()->unregister( $block_name, $block_style_name ); } /** * Checks whether the current block type supports the feature requested. * * @since 5.8.0 * @since 6.4.0 The `$feature` parameter now supports a string. * * @param WP_Block_Type $block_type Block type to check for support. * @param string|array $feature Feature slug, or path to a specific feature to check support for. * @param mixed $default_value Optional. Fallback value for feature support. Default false. * @return bool Whether the feature is supported. */ function block_has_support( $block_type, $feature, $default_value = false ) { $block_support = $default_value; if ( $block_type instanceof WP_Block_Type ) { if ( is_array( $feature ) && count( $feature ) === 1 ) { $feature = $feature[0]; } if ( is_array( $feature ) ) { $block_support = _wp_array_get( $block_type->supports, $feature, $default_value ); } elseif ( isset( $block_type->supports[ $feature ] ) ) { $block_support = $block_type->supports[ $feature ]; } } return true === $block_support || is_array( $block_support ); } /** * Converts typography keys declared under `supports.*` to `supports.typography.*`. * * Displays a `_doing_it_wrong()` notice when a block using the older format is detected. * * @since 5.8.0 * * @param array $metadata Metadata for registering a block type. * @return array Filtered metadata for registering a block type. */ function wp_migrate_old_typography_shape( $metadata ) { if ( ! isset( $metadata['supports'] ) ) { return $metadata; } $typography_keys = array( '__experimentalFontFamily', '__experimentalFontStyle', '__experimentalFontWeight', '__experimentalLetterSpacing', '__experimentalTextDecoration', '__experimentalTextTransform', 'fontSize', 'lineHeight', ); foreach ( $typography_keys as $typography_key ) { $support_for_key = isset( $metadata['supports'][ $typography_key ] ) ? $metadata['supports'][ $typography_key ] : null; if ( null !== $support_for_key ) { _doing_it_wrong( 'register_block_type_from_metadata()', sprintf( /* translators: 1: Block type, 2: Typography supports key, e.g: fontSize, lineHeight, etc. 3: block.json, 4: Old metadata key, 5: New metadata key. */ __( 'Block "%1$s" is declaring %2$s support in %3$s file under %4$s. %2$s support is now declared under %5$s.' ), $metadata['name'], "$typography_key", 'block.json', "supports.$typography_key", "supports.typography.$typography_key" ), '5.8.0' ); _wp_array_set( $metadata['supports'], array( 'typography', $typography_key ), $support_for_key ); unset( $metadata['supports'][ $typography_key ] ); } } return $metadata; } /** * Helper function that constructs a WP_Query args array from * a `Query` block properties. * * It's used in Query Loop, Query Pagination Numbers and Query Pagination Next blocks. * * @since 5.8.0 * @since 6.1.0 Added `query_loop_block_query_vars` filter and `parents` support in query. * @since 6.7.0 Added support for the `format` property in query. * * @param WP_Block $block Block instance. * @param int $page Current query's page. * * @return array Returns the constructed WP_Query arguments. */ function build_query_vars_from_query_block( $block, $page ) { $query = array( 'post_type' => 'post', 'order' => 'DESC', 'orderby' => 'date', 'post__not_in' => array(), 'tax_query' => array(), ); if ( isset( $block->context['query'] ) ) { if ( ! empty( $block->context['query']['postType'] ) ) { $post_type_param = $block->context['query']['postType']; if ( is_post_type_viewable( $post_type_param ) ) { $query['post_type'] = $post_type_param; } } if ( isset( $block->context['query']['sticky'] ) && ! empty( $block->context['query']['sticky'] ) ) { $sticky = get_option( 'sticky_posts' ); if ( 'only' === $block->context['query']['sticky'] ) { /* * Passing an empty array to post__in will return have_posts() as true (and all posts will be returned). * Logic should be used before hand to determine if WP_Query should be used in the event that the array * being passed to post__in is empty. * * @see https://core.trac.wordpress.org/ticket/28099 */ $query['post__in'] = ! empty( $sticky ) ? $sticky : array( 0 ); $query['ignore_sticky_posts'] = 1; } else { $query['post__not_in'] = array_merge( $query['post__not_in'], $sticky ); } } if ( ! empty( $block->context['query']['exclude'] ) ) { $excluded_post_ids = array_map( 'intval', $block->context['query']['exclude'] ); $excluded_post_ids = array_filter( $excluded_post_ids ); $query['post__not_in'] = array_merge( $query['post__not_in'], $excluded_post_ids ); } if ( isset( $block->context['query']['perPage'] ) && is_numeric( $block->context['query']['perPage'] ) ) { $per_page = absint( $block->context['query']['perPage'] ); $offset = 0; if ( isset( $block->context['query']['offset'] ) && is_numeric( $block->context['query']['offset'] ) ) { $offset = absint( $block->context['query']['offset'] ); } $query['offset'] = ( $per_page * ( $page - 1 ) ) + $offset; $query['posts_per_page'] = $per_page; } // Migrate `categoryIds` and `tagIds` to `tax_query` for backwards compatibility. if ( ! empty( $block->context['query']['categoryIds'] ) || ! empty( $block->context['query']['tagIds'] ) ) { $tax_query_back_compat = array(); if ( ! empty( $block->context['query']['categoryIds'] ) ) { $tax_query_back_compat[] = array( 'taxonomy' => 'category', 'terms' => array_filter( array_map( 'intval', $block->context['query']['categoryIds'] ) ), 'include_children' => false, ); } if ( ! empty( $block->context['query']['tagIds'] ) ) { $tax_query_back_compat[] = array( 'taxonomy' => 'post_tag', 'terms' => array_filter( array_map( 'intval', $block->context['query']['tagIds'] ) ), 'include_children' => false, ); } $query['tax_query'] = array_merge( $query['tax_query'], $tax_query_back_compat ); } if ( ! empty( $block->context['query']['taxQuery'] ) ) { $tax_query = array(); foreach ( $block->context['query']['taxQuery'] as $taxonomy => $terms ) { if ( is_taxonomy_viewable( $taxonomy ) && ! empty( $terms ) ) { $tax_query[] = array( 'taxonomy' => $taxonomy, 'terms' => array_filter( array_map( 'intval', $terms ) ), 'include_children' => false, ); } } $query['tax_query'] = array_merge( $query['tax_query'], $tax_query ); } if ( ! empty( $block->context['query']['format'] ) && is_array( $block->context['query']['format'] ) ) { $formats = $block->context['query']['format']; /* * Validate that the format is either `standard` or a supported post format. * - First, add `standard` to the array of valid formats. * - Then, remove any invalid formats. */ $valid_formats = array_merge( array( 'standard' ), get_post_format_slugs() ); $formats = array_intersect( $formats, $valid_formats ); /* * The relation needs to be set to `OR` since the request can contain * two separate conditions. The user may be querying for items that have * either the `standard` format or a specific format. */ $formats_query = array( 'relation' => 'OR' ); /* * The default post format, `standard`, is not stored in the database. * If `standard` is part of the request, the query needs to exclude all post items that * have a format assigned. */ if ( in_array( 'standard', $formats, true ) ) { $formats_query[] = array( 'taxonomy' => 'post_format', 'field' => 'slug', 'operator' => 'NOT EXISTS', ); // Remove the `standard` format, since it cannot be queried. unset( $formats[ array_search( 'standard', $formats, true ) ] ); } // Add any remaining formats to the formats query. if ( ! empty( $formats ) ) { // Add the `post-format-` prefix. $terms = array_map( static function ( $format ) { return "post-format-$format"; }, $formats ); $formats_query[] = array( 'taxonomy' => 'post_format', 'field' => 'slug', 'terms' => $terms, 'operator' => 'IN', ); } /* * Add `$formats_query` to `$query`, as long as it contains more than one key: * If `$formats_query` only contains the initial `relation` key, there are no valid formats to query, * and the query should not be modified. */ if ( count( $formats_query ) > 1 ) { // Enable filtering by both post formats and other taxonomies by combining them with `AND`. if ( empty( $query['tax_query'] ) ) { $query['tax_query'] = $formats_query; } else { $query['tax_query'] = array( 'relation' => 'AND', $query['tax_query'], $formats_query, ); } } } if ( isset( $block->context['query']['order'] ) && in_array( strtoupper( $block->context['query']['order'] ), array( 'ASC', 'DESC' ), true ) ) { $query['order'] = strtoupper( $block->context['query']['order'] ); } if ( isset( $block->context['query']['orderBy'] ) ) { $query['orderby'] = $block->context['query']['orderBy']; } if ( isset( $block->context['query']['author'] ) ) { if ( is_array( $block->context['query']['author'] ) ) { $query['author__in'] = array_filter( array_map( 'intval', $block->context['query']['author'] ) ); } elseif ( is_string( $block->context['query']['author'] ) ) { $query['author__in'] = array_filter( array_map( 'intval', explode( ',', $block->context['query']['author'] ) ) ); } elseif ( is_int( $block->context['query']['author'] ) && $block->context['query']['author'] > 0 ) { $query['author'] = $block->context['query']['author']; } } if ( ! empty( $block->context['query']['search'] ) ) { $query['s'] = $block->context['query']['search']; } if ( ! empty( $block->context['query']['parents'] ) && is_post_type_hierarchical( $query['post_type'] ) ) { $query['post_parent__in'] = array_filter( array_map( 'intval', $block->context['query']['parents'] ) ); } } /** * Filters the arguments which will be passed to `WP_Query` for the Query Loop Block. * * Anything to this filter should be compatible with the `WP_Query` API to form * the query context which will be passed down to the Query Loop Block's children. * This can help, for example, to include additional settings or meta queries not * directly supported by the core Query Loop Block, and extend its capabilities. * * Please note that this will only influence the query that will be rendered on the * front-end. The editor preview is not affected by this filter. Also, worth noting * that the editor preview uses the REST API, so, ideally, one should aim to provide * attributes which are also compatible with the REST API, in order to be able to * implement identical queries on both sides. * * @since 6.1.0 * * @param array $query Array containing parameters for `WP_Query` as parsed by the block context. * @param WP_Block $block Block instance. * @param int $page Current query's page. */ return apply_filters( 'query_loop_block_query_vars', $query, $block, $page ); } /** * Helper function that returns the proper pagination arrow HTML for * `QueryPaginationNext` and `QueryPaginationPrevious` blocks based * on the provided `paginationArrow` from `QueryPagination` context. * * It's used in QueryPaginationNext and QueryPaginationPrevious blocks. * * @since 5.9.0 * * @param WP_Block $block Block instance. * @param bool $is_next Flag for handling `next/previous` blocks. * @return string|null The pagination arrow HTML or null if there is none. */ function get_query_pagination_arrow( $block, $is_next ) { $arrow_map = array( 'none' => '', 'arrow' => array( 'next' => '→', 'previous' => '←', ), 'chevron' => array( 'next' => '»', 'previous' => '«', ), ); if ( ! empty( $block->context['paginationArrow'] ) && array_key_exists( $block->context['paginationArrow'], $arrow_map ) && ! empty( $arrow_map[ $block->context['paginationArrow'] ] ) ) { $pagination_type = $is_next ? 'next' : 'previous'; $arrow_attribute = $block->context['paginationArrow']; $arrow = $arrow_map[ $block->context['paginationArrow'] ][ $pagination_type ]; $arrow_classes = "wp-block-query-pagination-$pagination_type-arrow is-arrow-$arrow_attribute"; return ""; } return null; } /** * Helper function that constructs a comment query vars array from the passed * block properties. * * It's used with the Comment Query Loop inner blocks. * * @since 6.0.0 * * @param WP_Block $block Block instance. * @return array Returns the comment query parameters to use with the * WP_Comment_Query constructor. */ function build_comment_query_vars_from_block( $block ) { $comment_args = array( 'orderby' => 'comment_date_gmt', 'order' => 'ASC', 'status' => 'approve', 'no_found_rows' => false, ); if ( is_user_logged_in() ) { $comment_args['include_unapproved'] = array( get_current_user_id() ); } else { $unapproved_email = wp_get_unapproved_comment_author_email(); if ( $unapproved_email ) { $comment_args['include_unapproved'] = array( $unapproved_email ); } } if ( ! empty( $block->context['postId'] ) ) { $comment_args['post_id'] = (int) $block->context['postId']; } if ( get_option( 'thread_comments' ) ) { $comment_args['hierarchical'] = 'threaded'; } else { $comment_args['hierarchical'] = false; } if ( get_option( 'page_comments' ) === '1' || get_option( 'page_comments' ) === true ) { $per_page = get_option( 'comments_per_page' ); $default_page = get_option( 'default_comments_page' ); if ( $per_page > 0 ) { $comment_args['number'] = $per_page; $page = (int) get_query_var( 'cpage' ); if ( $page ) { $comment_args['paged'] = $page; } elseif ( 'oldest' === $default_page ) { $comment_args['paged'] = 1; } elseif ( 'newest' === $default_page ) { $max_num_pages = (int) ( new WP_Comment_Query( $comment_args ) )->max_num_pages; if ( 0 !== $max_num_pages ) { $comment_args['paged'] = $max_num_pages; } } } } return $comment_args; } /** * Helper function that returns the proper pagination arrow HTML for * `CommentsPaginationNext` and `CommentsPaginationPrevious` blocks based on the * provided `paginationArrow` from `CommentsPagination` context. * * It's used in CommentsPaginationNext and CommentsPaginationPrevious blocks. * * @since 6.0.0 * * @param WP_Block $block Block instance. * @param string $pagination_type Optional. Type of the arrow we will be rendering. * Accepts 'next' or 'previous'. Default 'next'. * @return string|null The pagination arrow HTML or null if there is none. */ function get_comments_pagination_arrow( $block, $pagination_type = 'next' ) { $arrow_map = array( 'none' => '', 'arrow' => array( 'next' => '→', 'previous' => '←', ), 'chevron' => array( 'next' => '»', 'previous' => '«', ), ); if ( ! empty( $block->context['comments/paginationArrow'] ) && ! empty( $arrow_map[ $block->context['comments/paginationArrow'] ][ $pagination_type ] ) ) { $arrow_attribute = $block->context['comments/paginationArrow']; $arrow = $arrow_map[ $block->context['comments/paginationArrow'] ][ $pagination_type ]; $arrow_classes = "wp-block-comments-pagination-$pagination_type-arrow is-arrow-$arrow_attribute"; return ""; } return null; } /** * Strips all HTML from the content of footnotes, and sanitizes the ID. * * This function expects slashed data on the footnotes content. * * @access private * @since 6.3.2 * * @param string $footnotes JSON-encoded string of an array containing the content and ID of each footnote. * @return string Filtered content without any HTML on the footnote content and with the sanitized ID. */ function _wp_filter_post_meta_footnotes( $footnotes ) { $footnotes_decoded = json_decode( $footnotes, true ); if ( ! is_array( $footnotes_decoded ) ) { return ''; } $footnotes_sanitized = array(); foreach ( $footnotes_decoded as $footnote ) { if ( ! empty( $footnote['content'] ) && ! empty( $footnote['id'] ) ) { $footnotes_sanitized[] = array( 'id' => sanitize_key( $footnote['id'] ), 'content' => wp_unslash( wp_filter_post_kses( wp_slash( $footnote['content'] ) ) ), ); } } return wp_json_encode( $footnotes_sanitized ); } /** * Adds the filters for footnotes meta field. * * @access private * @since 6.3.2 */ function _wp_footnotes_kses_init_filters() { add_filter( 'sanitize_post_meta_footnotes', '_wp_filter_post_meta_footnotes' ); } /** * Removes the filters for footnotes meta field. * * @access private * @since 6.3.2 */ function _wp_footnotes_remove_filters() { remove_filter( 'sanitize_post_meta_footnotes', '_wp_filter_post_meta_footnotes' ); } /** * Registers the filter of footnotes meta field if the user does not have `unfiltered_html` capability. * * @access private * @since 6.3.2 */ function _wp_footnotes_kses_init() { _wp_footnotes_remove_filters(); if ( ! current_user_can( 'unfiltered_html' ) ) { _wp_footnotes_kses_init_filters(); } } /** * Initializes the filters for footnotes meta field when imported data should be filtered. * * This filter is the last one being executed on {@see 'force_filtered_html_on_import'}. * If the input of the filter is true, it means we are in an import situation and should * enable kses, independently of the user capabilities. So in that case we call * _wp_footnotes_kses_init_filters(). * * @access private * @since 6.3.2 * * @param string $arg Input argument of the filter. * @return string Input argument of the filter. */ function _wp_footnotes_force_filtered_html_on_import_filter( $arg ) { // If `force_filtered_html_on_import` is true, we need to init the global styles kses filters. if ( $arg ) { _wp_footnotes_kses_init_filters(); } return $arg; }