<?php
/**
* WordPress Export Administration API
*
* @package WordPress
* @subpackage Administration
*/
/**
* Version number for the export format.
*
* Bump this when something changes that might affect compatibility.
*
* @since 2.5.0
*/
define( 'WXR_VERSION', '1.2' );
/**
* Generates the WXR export file for download.
*
* Default behavior is to export all content, however, note that post content will only
* be exported for post types with the `can_export` argument enabled. Any posts with the
* 'auto-draft' status will be skipped.
*
* @since 2.1.0
* @since 5.7.0 Added the `post_modified` and `post_modified_gmt` fields to the export file.
*
* @global wpdb $wpdb WordPress database abstraction object.
* @global WP_Post $post Global post object.
*
* @param array $args {
* Optional. Arguments for generating the WXR export file for download. Default empty array.
*
* @type string $content Type of content to export. If set, only the post content of this post type
* will be exported. Accepts 'all', 'post', 'page', 'attachment', or a defined
* custom post. If an invalid custom post type is supplied, every post type for
* which `can_export` is enabled will be exported instead. If a valid custom post
* type is supplied but `can_export` is disabled, then 'posts' will be exported
* instead. When 'all' is supplied, only post types with `can_export` enabled will
* be exported. Default 'all'.
* @type string $author Author to export content for. Only used when `$content` is 'post', 'page', or
* 'attachment'. Accepts false (all) or a specific author ID. Default false (all).
* @type string $category Category (slug) to export content for. Used only when `$content` is 'post'. If
* set, only post content assigned to `$category` will be exported. Accepts false
* or a specific category slug. Default is false (all categories).
* @type string $start_date Start date to export content from. Expected date format is 'Y-m-d'. Used only
* when `$content` is 'post', 'page' or 'attachment'. Default false (since the
* beginning of time).
* @type string $end_date End date to export content to. Expected date format is 'Y-m-d'. Used only when
* `$content` is 'post', 'page' or 'attachment'. Default false (latest publish date).
* @type string $status Post status to export posts for. Used only when `$content` is 'post' or 'page'.
* Accepts false (all statuses except 'auto-draft'), or a specific status, i.e.
* 'publish', 'pending', 'draft', 'auto-draft', 'future', 'private', 'inherit', or
* 'trash'. Default false (all statuses except 'auto-draft').
* }
*/
function export_wp( $args = array() ) {
global $wpdb, $post;
$defaults = array(
'content' => 'all',
'author' => false,
'category' => false,
'start_date' => false,
'end_date' => false,
'status' => false,
);
$args = wp_parse_args( $args, $defaults );
/**
* Fires at the beginning of an export, before any headers are sent.
*
* @since 2.3.0
*
* @param array $args An array of export arguments.
*/
do_action( 'export_wp', $args );
$sitename = sanitize_key( get_bloginfo( 'name' ) );
if ( ! empty( $sitename ) ) {
$sitename .= '.';
}
$date = gmdate( 'Y-m-d' );
$wp_filename = $sitename . 'WordPress.' . $date . '.xml';
/**
* Filters the export filename.
*
* @since 4.4.0
*
* @param string $wp_filename The name of the file for download.
* @param string $sitename The site name.
* @param string $date Today's date, formatted.
*/
$filename = apply_filters( 'export_wp_filename', $wp_filename, $sitename, $date );
header( 'Content-Description: File Transfer' );
header( 'Content-Disposition: attachment; filename=' . $filename );
header( 'Content-Type: text/xml; charset=' . get_option( 'blog_charset' ), true );
if ( 'all' !== $args['content'] && post_type_exists( $args['content'] ) ) {
$ptype = get_post_type_object( $args['content'] );
if ( ! $ptype->can_export ) {
$args['content'] = 'post';
}
$where = $wpdb->prepare( "{$wpdb->posts}.post_type = %s", $args['content'] );
} else {
$post_types = get_post_types( array( 'can_export' => true ) );
$esses = array_fill( 0, count( $post_types ), '%s' );
// phpcs:ignore WordPress.DB.PreparedSQLPlaceholders.UnfinishedPrepare
$where = $wpdb->prepare( "{$wpdb->posts}.post_type IN (" . implode( ',', $esses ) . ')', $post_types );
}
if ( $args['status'] && ( 'post' === $args['content'] || 'page' === $args['content'] ) ) {
$where .= $wpdb->prepare( " AND {$wpdb->posts}.post_status = %s", $args['status'] );
} else {
$where .= " AND {$wpdb->posts}.post_status != 'auto-draft'";
}
$join = '';
if ( $args['category'] && 'post' === $args['content'] ) {
$term = term_exists( $args['category'], 'category' );
if ( $term ) {
$join = "INNER JOIN {$wpdb->term_relationships} ON ({$wpdb->posts}.ID = {$wpdb->term_relationships}.object_id)";
$where .= $wpdb->prepare( " AND {$wpdb->term_relationships}.term_taxonomy_id = %d", $term['term_taxonomy_id'] );
}
}
if ( in_array( $args['content'], array( 'post', 'page', 'attachment' ), true ) ) {
if ( $args['author'] ) {
$where .= $wpdb->prepare( " AND {$wpdb->posts}.post_author = %d", $args['author'] );
}
if ( $args['start_date'] ) {
$where .= $wpdb->prepare( " AND {$wpdb->posts}.post_date >= %s", gmdate( 'Y-m-d', strtotime( $args['start_date'] ) ) );
}
if ( $args['end_date'] ) {
$where .= $wpdb->prepare( " AND {$wpdb->posts}.post_date < %s", gmdate( 'Y-m-d', strtotime( '+1 month', strtotime( $args['end_date'] ) ) ) );
}
}
// Grab a snapshot of post IDs, just in case it changes during the export.
$post_ids = $wpdb->get_col( "SELECT ID FROM {$wpdb->posts} $join WHERE $where" );
// Get IDs for the attachments of each post, unless all content is already being exported.
if ( ! in_array( $args['content'], array( 'all', 'attachment' ), true ) ) {
// Array to hold all additional IDs (attachments and thumbnails).
$additional_ids = array();
// Create a copy of the post IDs array to avoid modifying the original array.
$processing_ids = $post_ids;
while ( $next_posts = array_splice( $processing_ids, 0, 20 ) ) {
$posts_in = array_map( 'absint', $next_posts );
$placeholders = array_fill( 0, count( $posts_in ), '%d' );
// Create a string for the placeholders.
$in_placeholder = implode( ',', $placeholders );
// Prepare the SQL statement for attachment ids.
$attachment_ids = $wpdb->get_col(
$wpdb->prepare(
"
SELECT ID
FROM $wpdb->posts
WHERE post_parent IN ($in_placeholder) AND post_type = 'attachment'
",
$posts_in
)
);
$thumbnails_ids = $wpdb->get_col(
$wpdb->prepare(
"
SELECT meta_value
FROM $wpdb->postmeta
WHERE $wpdb->postmeta.post_id IN ($in_placeholder)
AND $wpdb->postmeta.meta_key = '_thumbnail_id'
",
$posts_in
)
);
$additional_ids = array_merge( $additional_ids, $attachment_ids, $thumbnails_ids );
}
// Merge the additional IDs back with the original post IDs after processing all posts
$post_ids = array_unique( array_merge( $post_ids, $additional_ids ) );
}
/*
* Get the requested terms ready, empty unless posts filtered by category
* or all content.
*/
$cats = array();
$tags = array();
$terms = array();
if ( isset( $term ) && $term ) {
$cat = get_term( $term['term_id'], 'category' );
$cats = array( $cat->term_id => $cat );
unset( $term, $cat );
} elseif ( 'all' === $args['content'] ) {
$categories = (array) get_categories( array( 'get' => 'all' ) );
$tags = (array) get_tags( array( 'get' => 'all' ) );
$custom_taxonomies = get_taxonomies( array( '_builtin' => false ) );
$custom_terms = (array) get_terms(
array(
'taxonomy' => $custom_taxonomies,
'get' => 'all',
)
);
// Put categories in order with no child going before its parent.
while ( $cat = array_shift( $categories ) ) {
if ( ! $cat->parent || isset( $cats[ $cat->parent ] ) ) {
$cats[ $cat->term_id ] = $cat;
} else {
$categories[] = $cat;
}
}
// Put terms in order with no child going before its parent.
while ( $t = array_shift( $custom_terms ) ) {
if ( ! $t->parent || isset( $terms[ $t->parent ] ) ) {
$terms[ $t->term_id ] = $t;
} else {
$custom_terms[] = $t;
}
}
unset( $categories, $custom_taxonomies, $custom_terms );
}
/**
* Wraps given string in XML CDATA tag.
*
* @since 2.1.0
*
* @param string|null $str String to wrap in XML CDATA tag. May be null.
* @return string
*/
function wxr_cdata( $str ) {
$str = (string) $str;
if ( ! wp_is_valid_utf8( $str ) ) {
$str = utf8_encode( $str );
}
// $str = ent2ncr(esc_html($str));
$str = '<![CDATA[' . str_replace( ']]>', ']]]]><![CDATA[>', $str ) . ']]>';
return $str;
}
/**
* Returns the URL of the site.
*
* @since 2.5.0
*
* @return string Site URL.
*/
function wxr_site_url() {
if ( is_multisite() ) {
// Multisite: the base URL.
return network_home_url();
} else {
// WordPress (single site): the site URL.
return get_bloginfo_rss( 'url' );
}
}
/**
* Outputs a cat_name XML tag from a given category object.
*
* @since 2.1.0
*
* @param WP_Term $category Category Object.
*/
function wxr_cat_name( $category ) {
if ( empty( $category->name ) ) {
return;
}
echo '<wp:cat_name>' . wxr_cdata( $category->name ) . "</wp:cat_name>\n";
}
/**
* Outputs a category_description XML tag from a given category object.
*
* @since 2.1.0
*
* @param WP_Term $category Category Object.
*/
function wxr_category_description( $category ) {
if ( empty( $category->description ) ) {
return;
}
echo '<wp:category_description>' . wxr_cdata( $category->description ) . "</wp:category_description>\n";
}
/**
* Outputs a tag_name XML tag from a given tag object.
*
* @since 2.3.0
*
* @param WP_Term $tag Tag Object.
*/
function wxr_tag_name( $tag ) {
if ( empty( $tag->name ) ) {
return;
}
echo '<wp:tag_name>' . wxr_cdata( $tag->name ) . "</wp:tag_name>\n";
}
/**
* Outputs a tag_description XML tag from a given tag object.
*
* @since 2.3.0
*
* @param WP_Term $tag Tag Object.
*/
function wxr_tag_description( $tag ) {
if ( empty( $tag->description ) ) {
return;
}
echo '<wp:tag_description>' . wxr_cdata( $tag->description ) . "</wp:tag_description>\n";
}
/**
* Outputs a term_name XML tag from a given term object.
*
* @since 2.9.0
*
* @param WP_Term $term Term Object.
*/
function wxr_term_name( $term ) {
if ( empty( $term->name ) ) {
return;
}
echo '<wp:term_name>' . wxr_cdata( $term->name ) . "</wp:term_name>\n";
}
/**
* Outputs a term_description XML tag from a given term object.
*
* @since 2.9.0
*
* @param WP_Term $term Term Object.
*/
function wxr_term_description( $term ) {
if ( empty( $term->description ) ) {
return;
}
echo "\t\t<wp:term_description>" . wxr_cdata( $term->description ) . "</wp:term_description>\n";
}
/**
* Outputs term meta XML tags for a given term object.
*
* @since 4.6.0
*
* @global wpdb $wpdb WordPress database abstraction object.
*
* @param WP_Term $term Term object.
*/
function wxr_term_meta( $term ) {
global $wpdb;
$termmeta = $wpdb->get_results( $wpdb->prepare( "SELECT * FROM $wpdb->termmeta WHERE term_id = %d", $term->term_id ) );
foreach ( $termmeta as $meta ) {
/**
* Filters whether to selectively skip term meta used for WXR exports.
*
* Returning a truthy value from the filter will skip the current meta
* object from being exported.
*
* @since 4.6.0
*
* @param bool $skip Whether to skip the current piece of