Commit fac65c85 authored by agata's avatar agata

[auto] plugin: wordpress-importer 0.7

parent fc2083ed
This diff is collapsed.
<?php
/**
* Implementation for WordPress functions missing in older WordPress versions.
*
* @package WordPress
* @subpackage Importer
*/
if ( ! function_exists( 'wp_slash_strings_only' ) ) {
/**
* Adds slashes to only string values in an array of values.
*
* Compat for WordPress < 5.3.0.
*
* @since 0.7.0
*
* @param mixed $value Scalar or array of scalars.
* @return mixed Slashes $value
*/
function wp_slash_strings_only( $value ) {
return map_deep( $value, 'addslashes_strings_only' );
}
}
if ( ! function_exists( 'addslashes_strings_only' ) ) {
/**
* Adds slashes only if the provided value is a string.
*
* Compat for WordPress < 5.3.0.
*
* @since 0.7.0
*
* @param mixed $value
* @return mixed
*/
function addslashes_strings_only( $value ) {
return is_string( $value ) ? addslashes( $value ) : $value;
}
}
if ( ! function_exists( 'map_deep' ) ) {
/**
* Maps a function to all non-iterable elements of an array or an object.
*
* Compat for WordPress < 4.4.0.
*
* @since 0.7.0
*
* @param mixed $value The array, object, or scalar.
* @param callable $callback The function to map onto $value.
* @return mixed The value with the callback applied to all non-arrays and non-objects inside it.
*/
function map_deep( $value, $callback ) {
if ( is_array( $value ) ) {
foreach ( $value as $index => $item ) {
$value[ $index ] = map_deep( $item, $callback );
}
} elseif ( is_object( $value ) ) {
$object_vars = get_object_vars( $value );
foreach ( $object_vars as $property_name => $property_value ) {
$value->$property_name = map_deep( $property_value, $callback );
}
} else {
$value = call_user_func( $callback, $value );
}
return $value;
}
}
<?php
/**
* WordPress eXtended RSS file parser implementations
*
* @package WordPress
* @subpackage Importer
*/
/**
* WXR Parser that uses regular expressions. Fallback for installs without an XML parser.
*/
class WXR_Parser_Regex {
var $authors = array();
var $posts = array();
var $categories = array();
var $tags = array();
var $terms = array();
var $base_url = '';
var $base_blog_url = '';
function __construct() {
$this->has_gzip = is_callable( 'gzopen' );
}
function parse( $file ) {
$wxr_version = $in_multiline = false;
$multiline_content = '';
$multiline_tags = array(
'item' => array( 'posts', array( $this, 'process_post' ) ),
'wp:category' => array( 'categories', array( $this, 'process_category' ) ),
'wp:tag' => array( 'tags', array( $this, 'process_tag' ) ),
'wp:term' => array( 'terms', array( $this, 'process_term' ) ),
);
$fp = $this->fopen( $file, 'r' );
if ( $fp ) {
while ( ! $this->feof( $fp ) ) {
$importline = rtrim( $this->fgets( $fp ) );
if ( ! $wxr_version && preg_match( '|<wp:wxr_version>(\d+\.\d+)</wp:wxr_version>|', $importline, $version ) )
$wxr_version = $version[1];
if ( false !== strpos( $importline, '<wp:base_site_url>' ) ) {
preg_match( '|<wp:base_site_url>(.*?)</wp:base_site_url>|is', $importline, $url );
$this->base_url = $url[1];
continue;
}
if ( false !== strpos( $importline, '<wp:base_blog_url>' ) ) {
preg_match( '|<wp:base_blog_url>(.*?)</wp:base_blog_url>|is', $importline, $blog_url );
$this->base_blog_url = $blog_url[1];
continue;
} else {
$this->base_blog_url = $this->base_url;
}
if ( false !== strpos( $importline, '<wp:author>' ) ) {
preg_match( '|<wp:author>(.*?)</wp:author>|is', $importline, $author );
$a = $this->process_author( $author[1] );
$this->authors[$a['author_login']] = $a;
continue;
}
foreach ( $multiline_tags as $tag => $handler ) {
// Handle multi-line tags on a singular line
if ( preg_match( '|<' . $tag . '>(.*?)</' . $tag . '>|is', $importline, $matches ) ) {
$this->{$handler[0]}[] = call_user_func( $handler[1], $matches[1] );
} elseif ( false !== ( $pos = strpos( $importline, "<$tag>" ) ) ) {
// Take note of any content after the opening tag
$multiline_content = trim( substr( $importline, $pos + strlen( $tag ) + 2 ) );
// We don't want to have this line added to `$is_multiline` below.
$importline = '';
$in_multiline = $tag;
} elseif ( false !== ( $pos = strpos( $importline, "</$tag>" ) ) ) {
$in_multiline = false;
$multiline_content .= trim( substr( $importline, 0, $pos ) );
$this->{$handler[0]}[] = call_user_func( $handler[1], $multiline_content );
}
}
if ( $in_multiline && $importline ) {
$multiline_content .= $importline . "\n";
}
}
$this->fclose($fp);
}
if ( ! $wxr_version )
return new WP_Error( 'WXR_parse_error', __( 'This does not appear to be a WXR file, missing/invalid WXR version number', 'wordpress-importer' ) );
return array(
'authors' => $this->authors,
'posts' => $this->posts,
'categories' => $this->categories,
'tags' => $this->tags,
'terms' => $this->terms,
'base_url' => $this->base_url,
'base_blog_url' => $this->base_blog_url,
'version' => $wxr_version
);
}
function get_tag( $string, $tag ) {
preg_match( "|<$tag.*?>(.*?)</$tag>|is", $string, $return );
if ( isset( $return[1] ) ) {
if ( substr( $return[1], 0, 9 ) == '<![CDATA[' ) {
if ( strpos( $return[1], ']]]]><![CDATA[>' ) !== false ) {
preg_match_all( '|<!\[CDATA\[(.*?)\]\]>|s', $return[1], $matches );
$return = '';
foreach( $matches[1] as $match )
$return .= $match;
} else {
$return = preg_replace( '|^<!\[CDATA\[(.*)\]\]>$|s', '$1', $return[1] );
}
} else {
$return = $return[1];
}
} else {
$return = '';
}
return $return;
}
function process_category( $c ) {
$term = array(
'term_id' => $this->get_tag( $c, 'wp:term_id' ),
'cat_name' => $this->get_tag( $c, 'wp:cat_name' ),
'category_nicename' => $this->get_tag( $c, 'wp:category_nicename' ),
'category_parent' => $this->get_tag( $c, 'wp:category_parent' ),
'category_description' => $this->get_tag( $c, 'wp:category_description' ),
);
$term_meta = $this->process_meta( $c, 'wp:termmeta' );
if ( ! empty( $term_meta ) ) {
$term['termmeta'] = $term_meta;
}
return $term;
}
function process_tag( $t ) {
$term = array(
'term_id' => $this->get_tag( $t, 'wp:term_id' ),
'tag_name' => $this->get_tag( $t, 'wp:tag_name' ),
'tag_slug' => $this->get_tag( $t, 'wp:tag_slug' ),
'tag_description' => $this->get_tag( $t, 'wp:tag_description' ),
);
$term_meta = $this->process_meta( $t, 'wp:termmeta' );
if ( ! empty( $term_meta ) ) {
$term['termmeta'] = $term_meta;
}
return $term;
}
function process_term( $t ) {
$term = array(
'term_id' => $this->get_tag( $t, 'wp:term_id' ),
'term_taxonomy' => $this->get_tag( $t, 'wp:term_taxonomy' ),
'slug' => $this->get_tag( $t, 'wp:term_slug' ),
'term_parent' => $this->get_tag( $t, 'wp:term_parent' ),
'term_name' => $this->get_tag( $t, 'wp:term_name' ),
'term_description' => $this->get_tag( $t, 'wp:term_description' ),
);
$term_meta = $this->process_meta( $t, 'wp:termmeta' );
if ( ! empty( $term_meta ) ) {
$term['termmeta'] = $term_meta;
}
return $term;
}
function process_meta( $string, $tag ) {
$parsed_meta = array();
preg_match_all( "|<$tag>(.+?)</$tag>|is", $string, $meta );
if ( ! isset( $meta[1] ) ) {
return $parsed_meta;
}
foreach ( $meta[1] as $m ) {
$parsed_meta[] = array(
'key' => $this->get_tag( $m, 'wp:meta_key' ),
'value' => $this->get_tag( $m, 'wp:meta_value' ),
);
}
return $parsed_meta;
}
function process_author( $a ) {
return array(
'author_id' => $this->get_tag( $a, 'wp:author_id' ),
'author_login' => $this->get_tag( $a, 'wp:author_login' ),
'author_email' => $this->get_tag( $a, 'wp:author_email' ),
'author_display_name' => $this->get_tag( $a, 'wp:author_display_name' ),
'author_first_name' => $this->get_tag( $a, 'wp:author_first_name' ),
'author_last_name' => $this->get_tag( $a, 'wp:author_last_name' ),
);
}
function process_post( $post ) {
$post_id = $this->get_tag( $post, 'wp:post_id' );
$post_title = $this->get_tag( $post, 'title' );
$post_date = $this->get_tag( $post, 'wp:post_date' );
$post_date_gmt = $this->get_tag( $post, 'wp:post_date_gmt' );
$comment_status = $this->get_tag( $post, 'wp:comment_status' );
$ping_status = $this->get_tag( $post, 'wp:ping_status' );
$status = $this->get_tag( $post, 'wp:status' );
$post_name = $this->get_tag( $post, 'wp:post_name' );
$post_parent = $this->get_tag( $post, 'wp:post_parent' );
$menu_order = $this->get_tag( $post, 'wp:menu_order' );
$post_type = $this->get_tag( $post, 'wp:post_type' );
$post_password = $this->get_tag( $post, 'wp:post_password' );
$is_sticky = $this->get_tag( $post, 'wp:is_sticky' );
$guid = $this->get_tag( $post, 'guid' );
$post_author = $this->get_tag( $post, 'dc:creator' );
$post_excerpt = $this->get_tag( $post, 'excerpt:encoded' );
$post_excerpt = preg_replace_callback( '|<(/?[A-Z]+)|', array( &$this, '_normalize_tag' ), $post_excerpt );
$post_excerpt = str_replace( '<br>', '<br />', $post_excerpt );
$post_excerpt = str_replace( '<hr>', '<hr />', $post_excerpt );
$post_content = $this->get_tag( $post, 'content:encoded' );
$post_content = preg_replace_callback( '|<(/?[A-Z]+)|', array( &$this, '_normalize_tag' ), $post_content );
$post_content = str_replace( '<br>', '<br />', $post_content );
$post_content = str_replace( '<hr>', '<hr />', $post_content );
$postdata = compact( 'post_id', 'post_author', 'post_date', 'post_date_gmt', 'post_content', 'post_excerpt',
'post_title', 'status', 'post_name', 'comment_status', 'ping_status', 'guid', 'post_parent',
'menu_order', 'post_type', 'post_password', 'is_sticky'
);
$attachment_url = $this->get_tag( $post, 'wp:attachment_url' );
if ( $attachment_url )
$postdata['attachment_url'] = $attachment_url;
preg_match_all( '|<category domain="([^"]+?)" nicename="([^"]+?)">(.+?)</category>|is', $post, $terms, PREG_SET_ORDER );
foreach ( $terms as $t ) {
$post_terms[] = array(
'slug' => $t[2],
'domain' => $t[1],
'name' => str_replace( array( '<![CDATA[', ']]>' ), '', $t[3] ),
);
}
if ( ! empty( $post_terms ) ) $postdata['terms'] = $post_terms;
preg_match_all( '|<wp:comment>(.+?)</wp:comment>|is', $post, $comments );
$comments = $comments[1];
if ( $comments ) {
foreach ( $comments as $comment ) {
$post_comments[] = array(
'comment_id' => $this->get_tag( $comment, 'wp:comment_id' ),
'comment_author' => $this->get_tag( $comment, 'wp:comment_author' ),
'comment_author_email' => $this->get_tag( $comment, 'wp:comment_author_email' ),
'comment_author_IP' => $this->get_tag( $comment, 'wp:comment_author_IP' ),
'comment_author_url' => $this->get_tag( $comment, 'wp:comment_author_url' ),
'comment_date' => $this->get_tag( $comment, 'wp:comment_date' ),
'comment_date_gmt' => $this->get_tag( $comment, 'wp:comment_date_gmt' ),
'comment_content' => $this->get_tag( $comment, 'wp:comment_content' ),
'comment_approved' => $this->get_tag( $comment, 'wp:comment_approved' ),
'comment_type' => $this->get_tag( $comment, 'wp:comment_type' ),
'comment_parent' => $this->get_tag( $comment, 'wp:comment_parent' ),
'comment_user_id' => $this->get_tag( $comment, 'wp:comment_user_id' ),
'commentmeta' => $this->process_meta( $comment, 'wp:commentmeta' ),
);
}
}
if ( ! empty( $post_comments ) ) {
$postdata['comments'] = $post_comments;
}
$post_meta = $this->process_meta( $post, 'wp:postmeta' );
if ( ! empty( $post_meta ) ) {
$postdata['postmeta'] = $post_meta;
}
return $postdata;
}
function _normalize_tag( $matches ) {
return '<' . strtolower( $matches[1] );
}
function fopen( $filename, $mode = 'r' ) {
if ( $this->has_gzip )
return gzopen( $filename, $mode );
return fopen( $filename, $mode );
}
function feof( $fp ) {
if ( $this->has_gzip )
return gzeof( $fp );
return feof( $fp );
}
function fgets( $fp, $len = 8192 ) {
if ( $this->has_gzip )
return gzgets( $fp, $len );
return fgets( $fp, $len );
}
function fclose( $fp ) {
if ( $this->has_gzip )
return gzclose( $fp );
return fclose( $fp );
}
}
<?php
/**
* WordPress eXtended RSS file parser implementations
*
* @package WordPress
* @subpackage Importer
*/
/**
* WXR Parser that makes use of the SimpleXML PHP extension.
*/
class WXR_Parser_SimpleXML {
function parse( $file ) {
$authors = $posts = $categories = $tags = $terms = array();
$internal_errors = libxml_use_internal_errors(true);
$dom = new DOMDocument;
$old_value = null;
if ( function_exists( 'libxml_disable_entity_loader' ) ) {
$old_value = libxml_disable_entity_loader( true );
}
$success = $dom->loadXML( file_get_contents( $file ) );
if ( ! is_null( $old_value ) ) {
libxml_disable_entity_loader( $old_value );
}
if ( ! $success || isset( $dom->doctype ) ) {
return new WP_Error( 'SimpleXML_parse_error', __( 'There was an error when reading this WXR file', 'wordpress-importer' ), libxml_get_errors() );
}
$xml = simplexml_import_dom( $dom );
unset( $dom );
// halt if loading produces an error
if ( ! $xml )
return new WP_Error( 'SimpleXML_parse_error', __( 'There was an error when reading this WXR file', 'wordpress-importer' ), libxml_get_errors() );
$wxr_version = $xml->xpath('/rss/channel/wp:wxr_version');
if ( ! $wxr_version )
return new WP_Error( 'WXR_parse_error', __( 'This does not appear to be a WXR file, missing/invalid WXR version number', 'wordpress-importer' ) );
$wxr_version = (string) trim( $wxr_version[0] );
// confirm that we are dealing with the correct file format
if ( ! preg_match( '/^\d+\.\d+$/', $wxr_version ) )
return new WP_Error( 'WXR_parse_error', __( 'This does not appear to be a WXR file, missing/invalid WXR version number', 'wordpress-importer' ) );
$base_url = $xml->xpath('/rss/channel/wp:base_site_url');
$base_url = (string) trim( isset( $base_url[0] ) ? $base_url[0] : '' );
$base_blog_url = $xml->xpath('/rss/channel/wp:base_blog_url');
if ( $base_blog_url ) {
$base_blog_url = (string) trim( $base_blog_url[0] );
} else {
$base_blog_url = $base_url;
}
$namespaces = $xml->getDocNamespaces();
if ( ! isset( $namespaces['wp'] ) )
$namespaces['wp'] = 'http://wordpress.org/export/1.1/';
if ( ! isset( $namespaces['excerpt'] ) )
$namespaces['excerpt'] = 'http://wordpress.org/export/1.1/excerpt/';
// grab authors
foreach ( $xml->xpath('/rss/channel/wp:author') as $author_arr ) {
$a = $author_arr->children( $namespaces['wp'] );
$login = (string) $a->author_login;
$authors[$login] = array(
'author_id' => (int) $a->author_id,
'author_login' => $login,
'author_email' => (string) $a->author_email,
'author_display_name' => (string) $a->author_display_name,
'author_first_name' => (string) $a->author_first_name,
'author_last_name' => (string) $a->author_last_name
);
}
// grab cats, tags and terms
foreach ( $xml->xpath('/rss/channel/wp:category') as $term_arr ) {
$t = $term_arr->children( $namespaces['wp'] );
$category = array(
'term_id' => (int) $t->term_id,
'category_nicename' => (string) $t->category_nicename,
'category_parent' => (string) $t->category_parent,
'cat_name' => (string) $t->cat_name,
'category_description' => (string) $t->category_description
);
foreach ( $t->termmeta as $meta ) {
$category['termmeta'][] = array(
'key' => (string) $meta->meta_key,
'value' => (string) $meta->meta_value
);
}
$categories[] = $category;
}
foreach ( $xml->xpath('/rss/channel/wp:tag') as $term_arr ) {
$t = $term_arr->children( $namespaces['wp'] );
$tag = array(
'term_id' => (int) $t->term_id,
'tag_slug' => (string) $t->tag_slug,
'tag_name' => (string) $t->tag_name,
'tag_description' => (string) $t->tag_description
);
foreach ( $t->termmeta as $meta ) {
$tag['termmeta'][] = array(
'key' => (string) $meta->meta_key,
'value' => (string) $meta->meta_value
);
}
$tags[] = $tag;
}
foreach ( $xml->xpath('/rss/channel/wp:term') as $term_arr ) {
$t = $term_arr->children( $namespaces['wp'] );
$term = array(
'term_id' => (int) $t->term_id,
'term_taxonomy' => (string) $t->term_taxonomy,
'slug' => (string) $t->term_slug,
'term_parent' => (string) $t->term_parent,
'term_name' => (string) $t->term_name,
'term_description' => (string) $t->term_description
);
foreach ( $t->termmeta as $meta ) {
$term['termmeta'][] = array(
'key' => (string) $meta->meta_key,
'value' => (string) $meta->meta_value
);
}
$terms[] = $term;
}
// grab posts
foreach ( $xml->channel->item as $item ) {
$post = array(
'post_title' => (string) $item->title,
'guid' => (string) $item->guid,
);
$dc = $item->children( 'http://purl.org/dc/elements/1.1/' );
$post['post_author'] = (string) $dc->creator;
$content = $item->children( 'http://purl.org/rss/1.0/modules/content/' );
$excerpt = $item->children( $namespaces['excerpt'] );
$post['post_content'] = (string) $content->encoded;
$post['post_excerpt'] = (string) $excerpt->encoded;
$wp = $item->children( $namespaces['wp'] );
$post['post_id'] = (int) $wp->post_id;
$post['post_date'] = (string) $wp->post_date;
$post['post_date_gmt'] = (string) $wp->post_date_gmt;
$post['comment_status'] = (string) $wp->comment_status;
$post['ping_status'] = (string) $wp->ping_status;
$post['post_name'] = (string) $wp->post_name;
$post['status'] = (string) $wp->status;
$post['post_parent'] = (int) $wp->post_parent;
$post['menu_order'] = (int) $wp->menu_order;
$post['post_type'] = (string) $wp->post_type;
$post['post_password'] = (string) $wp->post_password;
$post['is_sticky'] = (int) $wp->is_sticky;
if ( isset($wp->attachment_url) )
$post['attachment_url'] = (string) $wp->attachment_url;
foreach ( $item->category as $c ) {
$att = $c->attributes();
if ( isset( $att['nicename'] ) )
$post['terms'][] = array(
'name' => (string) $c,
'slug' => (string) $att['nicename'],
'domain' => (string) $att['domain']
);
}
foreach ( $wp->postmeta as $meta ) {
$post['postmeta'][] = array(
'key' => (string) $meta->meta_key,
'value' => (string) $meta->meta_value
);
}
foreach ( $wp->comment as $comment ) {
$meta = array();
if ( isset( $comment->commentmeta ) ) {
foreach ( $comment->commentmeta as $m ) {
$meta[] = array(
'key' => (string) $m->meta_key,
'value' => (string) $m->meta_value
);
}
}
$post['comments'][] = array(
'comment_id' => (int) $comment->comment_id,