Skip to content
This repository was archived by the owner on May 30, 2025. It is now read-only.

XMLProcessor: Support namespaces #23

Draft
wants to merge 6 commits into
base: trunk
Choose a base branch
from
Draft

XMLProcessor: Support namespaces #23

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
8514222
XMLProcessor: Support namespaces
adamziel May 26, 2025
8c0dcdc
Introduce XMLStackOfOpenElements
adamziel May 27, 2025
44cf981
Support namespaces in all methods
adamziel May 27, 2025
8d8d8b6
Remove qualified name argument from XMLAttributeToken
adamziel May 27, 2025
c2940bd
Test setting the default namespace
adamziel May 28, 2025
6ad78bc
Start refactoring WXREntityReader
adamziel May 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions components/DataLiberation/EntityReader/EPubEntityReader.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,13 +161,13 @@ private function parse_manifest() {
);
while ( $xml->next_tag() ) {
$parsed_entry = array();
$keys = $xml->get_attribute_names_with_prefix( '' );
$keys = $xml->get_attribute_qualified_names_with_prefix( '' );
foreach ( $keys as $key ) {
$parsed_entry[ $key ] = $xml->get_attribute( $key );
}
if ( $xml->matches_breadcrumbs( array( 'metadata', '*' ) ) ) {
$parsed['metadata'][] = array(
'tag' => $xml->get_tag(),
'tag' => $xml->get_tag_local_name(),
'attributes' => $parsed_entry,
);
} elseif ( $xml->matches_breadcrumbs( array( 'manifest', 'item' ) ) ) {
Expand Down
178 changes: 94 additions & 84 deletions components/DataLiberation/EntityReader/WXREntityReader.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,6 +243,14 @@ class WXREntityReader implements EntityReader {
*/
private $is_finished = false;

const NAMESPACES = array(
'excerpt' => 'http://wordpress.org/export/1.2/excerpt/',
'content' => 'http://purl.org/rss/1.0/modules/content/',
'wfw' => 'http://wellformedweb.org/CommentAPI/',
'dc' => 'http://purl.org/dc/elements/1.1/',
'wp' => 'http://wordpress.org/export/1.2/',
);

/**
* Mapping of WXR tags representing site options to their WordPress options names.
* These tags are only matched if they are children of the <channel> element.
Expand All @@ -251,8 +259,8 @@ class WXREntityReader implements EntityReader {
* @var array
*/
const KNOWN_SITE_OPTIONS = array(
'wp:base_blog_url' => 'home',
'wp:base_site_url' => 'siteurl',
'{http://wordpress.org/export/1.2/}base_blog_url' => 'home',
'{http://wordpress.org/export/1.2/}base_site_url' => 'siteurl',
'title' => 'blogname',
);

Expand All @@ -263,39 +271,39 @@ class WXREntityReader implements EntityReader {
* @var array
*/
const KNOWN_ENITIES = array(
'wp:comment' => array(
'{http://wordpress.org/export/1.2/}comment' => array(
'type' => 'comment',
'fields' => array(
'wp:comment_id' => 'comment_id',
'wp:comment_author' => 'comment_author',
'wp:comment_author_email' => 'comment_author_email',
'wp:comment_author_url' => 'comment_author_url',
'wp:comment_author_IP' => 'comment_author_IP',
'wp:comment_date' => 'comment_date',
'wp:comment_date_gmt' => 'comment_date_gmt',
'wp:comment_content' => 'comment_content',
'wp:comment_approved' => 'comment_approved',
'wp:comment_type' => 'comment_type',
'wp:comment_parent' => 'comment_parent',
'wp:comment_user_id' => 'comment_user_id',
'{http://wordpress.org/export/1.2/}comment_id' => 'comment_id',
'{http://wordpress.org/export/1.2/}comment_author' => 'comment_author',
'{http://wordpress.org/export/1.2/}comment_author_email' => 'comment_author_email',
'{http://wordpress.org/export/1.2/}comment_author_url' => 'comment_author_url',
'{http://wordpress.org/export/1.2/}comment_author_IP' => 'comment_author_IP',
'{http://wordpress.org/export/1.2/}comment_date' => 'comment_date',
'{http://wordpress.org/export/1.2/}comment_date_gmt' => 'comment_date_gmt',
'{http://wordpress.org/export/1.2/}comment_content' => 'comment_content',
'{http://wordpress.org/export/1.2/}comment_approved' => 'comment_approved',
'{http://wordpress.org/export/1.2/}comment_type' => 'comment_type',
'{http://wordpress.org/export/1.2/}comment_parent' => 'comment_parent',
'{http://wordpress.org/export/1.2/}comment_user_id' => 'comment_user_id',
),
),
'wp:commentmeta' => array(
'{http://wordpress.org/export/1.2/}commentmeta' => array(
'type' => 'comment_meta',
'fields' => array(
'wp:meta_key' => 'meta_key',
'wp:meta_value' => 'meta_value',
'{http://wordpress.org/export/1.2/}meta_key' => 'meta_key',
'{http://wordpress.org/export/1.2/}meta_value' => 'meta_value',
),
),
'wp:author' => array(
'{http://wordpress.org/export/1.2/}author' => array(
'type' => 'user',
'fields' => array(
'wp:author_id' => 'ID',
'wp:author_login' => 'user_login',
'wp:author_email' => 'user_email',
'wp:author_display_name' => 'display_name',
'wp:author_first_name' => 'first_name',
'wp:author_last_name' => 'last_name',
'{http://wordpress.org/export/1.2/}author_id' => 'ID',
'{http://wordpress.org/export/1.2/}author_login' => 'user_login',
'{http://wordpress.org/export/1.2/}author_email' => 'user_email',
'{http://wordpress.org/export/1.2/}author_display_name' => 'display_name',
'{http://wordpress.org/export/1.2/}author_first_name' => 'first_name',
'{http://wordpress.org/export/1.2/}author_last_name' => 'last_name',
),
),
'item' => array(
Expand All @@ -306,59 +314,59 @@ class WXREntityReader implements EntityReader {
'guid' => 'guid',
'description' => 'post_excerpt',
'pubDate' => 'post_published_at',
'dc:creator' => 'post_author',
'content:encoded' => 'post_content',
'excerpt:encoded' => 'post_excerpt',
'wp:post_id' => 'post_id',
'wp:status' => 'post_status',
'wp:post_date' => 'post_date',
'wp:post_date_gmt' => 'post_date_gmt',
'wp:post_modified' => 'post_modified',
'wp:post_modified_gmt' => 'post_modified_gmt',
'wp:comment_status' => 'comment_status',
'wp:ping_status' => 'ping_status',
'wp:post_name' => 'post_name',
'wp:post_parent' => 'post_parent',
'wp:menu_order' => 'menu_order',
'wp:post_type' => 'post_type',
'wp:post_password' => 'post_password',
'wp:is_sticky' => 'is_sticky',
'wp:attachment_url' => 'attachment_url',
'{http://purl.org/dc/elements/1.1/}creator' => 'post_author',
'{http://purl.org/rss/1.0/modules/content/}encoded' => 'post_content',
'{http://wordpress.org/export/1.2/excerpt/}encoded' => 'post_excerpt',
'{http://wordpress.org/export/1.2/}post_id' => 'post_id',
'{http://wordpress.org/export/1.2/}status' => 'post_status',
'{http://wordpress.org/export/1.2/}post_date' => 'post_date',
'{http://wordpress.org/export/1.2/}post_date_gmt' => 'post_date_gmt',
'{http://wordpress.org/export/1.2/}post_modified' => 'post_modified',
'{http://wordpress.org/export/1.2/}post_modified_gmt' => 'post_modified_gmt',
'{http://wordpress.org/export/1.2/}comment_status' => 'comment_status',
'{http://wordpress.org/export/1.2/}ping_status' => 'ping_status',
'{http://wordpress.org/export/1.2/}post_name' => 'post_name',
'{http://wordpress.org/export/1.2/}post_parent' => 'post_parent',
'{http://wordpress.org/export/1.2/}menu_order' => 'menu_order',
'{http://wordpress.org/export/1.2/}post_type' => 'post_type',
'{http://wordpress.org/export/1.2/}post_password' => 'post_password',
'{http://wordpress.org/export/1.2/}is_sticky' => 'is_sticky',
'{http://wordpress.org/export/1.2/}attachment_url' => 'attachment_url',
),
),
'wp:postmeta' => array(
'{http://wordpress.org/export/1.2/}postmeta' => array(
'type' => 'post_meta',
'fields' => array(
'wp:meta_key' => 'meta_key',
'wp:meta_value' => 'meta_value',
'{http://wordpress.org/export/1.2/}meta_key' => 'meta_key',
'{http://wordpress.org/export/1.2/}meta_value' => 'meta_value',
),
),
'wp:term' => array(
'{http://wordpress.org/export/1.2/}term' => array(
'type' => 'term',
'fields' => array(
'wp:term_id' => 'term_id',
'wp:term_taxonomy' => 'taxonomy',
'wp:term_slug' => 'slug',
'wp:term_parent' => 'parent',
'wp:term_name' => 'name',
'{http://wordpress.org/export/1.2/}term_id' => 'term_id',
'{http://wordpress.org/export/1.2/}term_taxonomy' => 'taxonomy',
'{http://wordpress.org/export/1.2/}term_slug' => 'slug',
'{http://wordpress.org/export/1.2/}term_parent' => 'parent',
'{http://wordpress.org/export/1.2/}term_name' => 'name',
),
),
'wp:tag' => array(
'{http://wordpress.org/export/1.2/}tag' => array(
'type' => 'tag',
'fields' => array(
'wp:term_id' => 'term_id',
'wp:tag_slug' => 'slug',
'wp:tag_name' => 'name',
'wp:tag_description' => 'description',
'{http://wordpress.org/export/1.2/}term_id' => 'term_id',
'{http://wordpress.org/export/1.2/}tag_slug' => 'slug',
'{http://wordpress.org/export/1.2/}tag_name' => 'name',
'{http://wordpress.org/export/1.2/}tag_description' => 'description',
),
),
'wp:category' => array(
'{http://wordpress.org/export/1.2/}category' => array(
'type' => 'category',
'fields' => array(
'wp:category_nicename' => 'slug',
'wp:category_parent' => 'parent',
'wp:cat_name' => 'name',
'wp:category_description' => 'description',
'{http://wordpress.org/export/1.2/}category_nicename' => 'slug',
'{http://wordpress.org/export/1.2/}category_parent' => 'parent',
'{http://wordpress.org/export/1.2/}cat_name' => 'name',
'{http://wordpress.org/export/1.2/}category_description' => 'description',
),
),
);
Expand Down Expand Up @@ -629,8 +637,8 @@ private function read_next_entity() {
// Don't process anything outside the <rss> <channel> hierarchy.
if (
count( $breadcrumbs ) < 2 ||
$breadcrumbs[0] !== 'rss' ||
$breadcrumbs[1] !== 'channel'
$breadcrumbs[0] !== ['', 'rss'] ||
$breadcrumbs[1] !== ['', 'channel']
) {
continue;
}
Expand Down Expand Up @@ -659,7 +667,8 @@ private function read_next_entity() {
$this->last_xml_cursor_outside_of_entity = $this->xml->get_reentrancy_cursor();
}

$tag = $this->xml->get_tag();
$tag_with_namespace = $this->xml->get_tag_name_with_namespace();

/**
* Custom adjustment: the Accessibility WXR file uses a non-standard
* wp:wp_author tag.
Expand All @@ -668,16 +677,16 @@ private function read_next_entity() {
* the regular WXR importer would ignore them? Perhaps a warning
* and an upstream PR would be a better solution.
*/
if ( $tag === 'wp:wp_author' ) {
$tag = 'wp:author';
if ( $tag_with_namespace === '{http://wordpress.org/export/1.2/}wp_author' ) {
$tag_with_namespace = '{http://wordpress.org/export/1.2/}author';
}

/**
* If the tag is a known entity root, assume the previous entity is
* finished, emit it, and start processing the new entity the next
* time this function is called.
*/
if ( array_key_exists( $tag, static::KNOWN_ENITIES ) ) {
if ( array_key_exists( $tag_with_namespace, static::KNOWN_ENITIES ) ) {
if ( $this->entity_type && ! $this->entity_finished ) {
$this->emit_entity();

Expand All @@ -687,7 +696,7 @@ private function read_next_entity() {
// Only tag openers indicate a new entity. Closers just mean
// the previous entity is finished.
if ( $this->xml->is_tag_opener() ) {
$this->set_entity_tag( $tag );
$this->set_entity_tag( $tag_with_namespace );
$this->last_xml_byte_offset_outside_of_entity = $this->xml->get_token_byte_offset_in_the_input_stream();
$this->last_xml_cursor_outside_of_entity = $this->xml->get_reentrancy_cursor();
}
Expand Down Expand Up @@ -732,18 +741,19 @@ private function read_next_entity() {
*/
if ( $this->xml->is_tag_opener() ) {
$this->last_opener_attributes = array();
$names = $this->xml->get_attribute_names_with_prefix( '' );
foreach ( $names as $name ) {
$this->last_opener_attributes[ $name ] = $this->xml->get_attribute( $name );
// Get non-namespaced attributes.
$names = $this->xml->get_attribute_names_with_prefix( '', '' );
foreach ( $names as list($namespace, $name) ) {
$this->last_opener_attributes[ $name ] = $this->xml->get_attribute( $namespace, $name );
}
$this->text_buffer = '';

$is_site_option_opener = (
count( $this->xml->get_breadcrumbs() ) === 3 &&
$this->xml->matches_breadcrumbs( array( 'rss', 'channel', '*' ) ) &&
array_key_exists( $this->xml->get_tag(), static::KNOWN_SITE_OPTIONS )
array_key_exists( $this->xml->get_tag_name_with_namespace(), static::KNOWN_SITE_OPTIONS )
);
if ( $is_site_option_opener ) {
if ( $is_site_option_opener ) {
$this->last_xml_byte_offset_outside_of_entity = $this->xml->get_token_byte_offset_in_the_input_stream();
}
continue;
Expand All @@ -759,7 +769,7 @@ private function read_next_entity() {

if (
! $this->entity_finished &&
$this->xml->get_breadcrumbs() === array( 'rss', 'channel' )
$this->xml->get_breadcrumbs() === array( array( '', 'rss' ), array( '', 'channel' ) )
) {
// Look for site options in children of the <channel> tag.
if ( $this->parse_site_option() ) {
Expand Down Expand Up @@ -790,7 +800,7 @@ private function read_next_entity() {
*/
if (
$this->entity_type === 'post' &&
$tag === 'category' &&
$tag_with_namespace === '{http://wordpress.org/export/1.2/}category' &&
array_key_exists( 'domain', $this->last_opener_attributes ) &&
array_key_exists( 'nicename', $this->last_opener_attributes )
) {
Expand All @@ -812,11 +822,11 @@ private function read_next_entity() {
* The WXR format is extensible so this reader could potentially
* support registering custom handlers for unknown tags in the future.
*/
if ( ! isset( static::KNOWN_ENITIES[ $this->entity_tag ]['fields'][ $tag ] ) ) {
if ( ! isset( static::KNOWN_ENITIES[ $this->entity_tag ]['fields'][ $tag_with_namespace ] ) ) {
continue;
}

$key = static::KNOWN_ENITIES[ $this->entity_tag ]['fields'][ $tag ];
$key = static::KNOWN_ENITIES[ $this->entity_tag ]['fields'][ $tag_with_namespace ];
$this->entity_data[ $key ] = $this->text_buffer;
$this->text_buffer = '';
} while ( $this->xml->next_token() );
Expand Down Expand Up @@ -848,13 +858,13 @@ private function read_next_entity() {
* @return bool Whether a site_option entity was emitted.
*/
private function parse_site_option() {
if ( ! array_key_exists( $this->xml->get_tag(), static::KNOWN_SITE_OPTIONS ) ) {
if ( ! array_key_exists( $this->xml->get_tag_name_with_namespace(), static::KNOWN_SITE_OPTIONS ) ) {
return false;
}

$this->entity_type = 'site_option';
$this->entity_data = array(
'option_name' => static::KNOWN_SITE_OPTIONS[ $this->xml->get_tag() ],
'option_name' => static::KNOWN_SITE_OPTIONS[ $this->xml->get_tag_name_with_namespace() ],
'option_value' => $this->text_buffer,
);
$this->emit_entity();
Expand Down Expand Up @@ -924,10 +934,10 @@ private function emit_entity() {
* @since WP_VERSION
*
*/
private function set_entity_tag( string $tag ) {
$this->entity_tag = $tag;
if ( array_key_exists( $tag, static::KNOWN_ENITIES ) ) {
$this->entity_type = static::KNOWN_ENITIES[ $tag ]['type'];
private function set_entity_tag( string $tag_with_namespace ) {
$this->entity_tag = $tag_with_namespace;
if ( array_key_exists( $tag_with_namespace, static::KNOWN_ENITIES ) ) {
$this->entity_type = static::KNOWN_ENITIES[ $tag_with_namespace ]['type'];
}
}

Expand Down
Loading
Loading