Migrate Site

migrate_site.migrate.inc.php

<?php

function migrate_site_migrate_api() {
  $api = array(
    'api' => 2,
    'groups' => array(
      'site' => array(
        'title' => t('Site'),
      )
    ),

    'migrations' => array(
      'SiteFiles' => array(
        'class_name' => 'SiteFilesMigration',
        'group_name' => 'site'
      ),
      'SitePages' => array(
        'class_name' => 'SitePagesMigration',
        'group_name' => 'site',
        //'dependencies' => array(
        //  'SiteFiles',
        //)
      ),
    ),
  );
  return $api;
}

site.inc.php

<?php

// Include SourceParser.
require_once drupal_get_path('module', 'migrate_site') . '/source_parser.inc';

abstract class SiteMigration extends Migration {
  public function __construct($arguments) {
    parent::__construct($arguments);

    $this->team = array(
      new MigrateTeamMember('Artiom Neganov', 'aneganov@gmail.com', t('Implementor'))
    );

    $this->issuePattern = 'http://drupal.org/node/:id:';
  }
}

class SitePagesMigration extends SiteMigration {
  public $base_dir;
  public $base_url;

  public function __construct($arguments) {
    parent::__construct($arguments);
    $this->description = t('Migrate site page into Drupal node');

    // A map of source HTML filename -> destination node id.
    $this->map = new MigrateSQLMap($this->machineName,
      array(
        'sourceid' => array(
          'type' => 'varchar',
          'length' => 255,
          'not null' => TRUE,
        )
      ),
      MigrateDestinationNode::getKeySchema()
    );

    $directories = array(
      '/var/www/sites/brassens',
    );
    $this->base_dir = '/var/www/sites/brassens/www/123/subdir';
    $this->base_url = 'http://brassens.ru/123/subdir';
    $regex = '/(.*\.htm$|.*\.html$)/i';

    $list = new MigrateListFiles(array($this->base_dir), $this->base_dir, $regex);
    $item = new MigrateItemFile($this->base_dir);
    $fields = array(
      'title' => t('Title'),
      'body' => t('Body'),
      'links' => t('Links'),
      'files' => t('Files'),
      'format' => t('Text Format'),
    );
    $this->source = new MigrateSourceList($list, $item, $fields);

    $this->destination =
      new MigrateDestinationNode('migrate_site_page');

     // Map the fields, pretty straightforward in this case.
    $this->addFieldMapping('title', 'title');
    $this->addFieldMapping('body', 'body');
    $this->addFieldMapping('body:format', 'format');
    $this->addFieldMapping('field_migrate_site_page_refs', 'links');
    $this->addFieldMapping('field_migrate_site_page_files', 'files');
    $this->addFieldMapping('field_migrate_site_page_files:file_class')
      ->defaultValue('MigrateFileFid');
  }

  protected function createStub($migration, array $source_id) {
    $node = new stdClass();
    $node->title = t('Stub for @id', array('@id' => $source_id[0]));
    $node->language = LANGUAGE_NONE;
    $node->body[LANGUAGE_NONE][0]['value'] = t('Stub body');
    $node->type = $this->destination->getBundle();
    $node->uid = 1;
    $node->status = 0;
    node_save($node);
    if (isset($node->nid)) {
      return array($node->nid);
    }
    else {
      return FALSE;
    }
  }

   /**
   * Prepare a row.
   */
  public function prepareRow($row) {

    // Create a new SourceParser to handle HTML content.
    $source_parser = new SourceParser(substr($row->sourceid, 1), $row->filedata, $this->base_url, drupal_dirname($row->sourceid));

    $source_ids = $source_parser->getLinks();
    if (count($source_ids)) {
      $row->links = $this->handleSourceMigration('SitePages', $source_ids);
      if (!is_array($row->links)) {
        $row->links = array($row->links);
      }
    }

    $files = $source_parser->getFiles();
    $row->files = $this->handleSourceMigration('SiteFiles', $files);
    if (!is_array($row->files)) {
      $row->files = array($row->files);
    }

    $row->body = $source_parser->getBody();
    $row->format = 'raw';

    // Replacing links
    if (count($row->links)) {
      foreach($row->links as $id => $nid) {
        $row->body = str_replace('[#%' .$id . ']', '[#' .$nid . ']', $row->body);
      }
    }

    // Replacing files
    if (count($row->files)) {
      foreach($row->files as $id => $fid) {
        $row->body = str_replace('{#%' .$id . '}', '{#' .$fid . '}', $row->body);
      }
    }

    // The title is the filename.
    $row->title = $row->sourceid;
  }
}

class SiteFilesMigration extends SiteMigration {
  public $base_dir;
  public $base_url;

  public function __construct($arguments) {
    parent::__construct($arguments);

    $this->description = t('Migrate sites files into Drupal.');

    // A map of source HTML filename -> destination node id.
    $this->map = new MigrateSQLMap($this->machineName,
      array(
        'sourceid' => array(
          'type' => 'varchar',
          'length' => 255,
          'not null' => TRUE,
        )
      ),
      MigrateDestinationNode::getKeySchema()
    );

    $directories = array(
      '/var/www/sites/brassens',
    );
    $this->base_dir = '/var/www/sites/brassens/www/123/subdir';
    $this->base_url = 'http://brassens.ru/123/subdir';
    $regex = '/asdasd/';

    $list = new MigrateListFiles(array($this->base_dir), $this->base_dir, $regex);
    $item = new MigrateItemFile($this->base_dir);
    $fields = array(
      'sourceid' => t('File name with path'),
      'file_url' => t('Path to the file'),
    );
    $this->source = new MigrateSourceList($list, $item, $fields);
    $this->destination = new MigrateDestinationFile('file', 'MigrateFileLink');
    $this->addFieldMapping('value', 'file_url');
  }
  public function prepareRow($row) {
    if (parent::prepareRow($row) === FALSE) {
      return FALSE;
    }
    $row->file_url = $this->base_url . $row->sourceid;
    // Remove the leading forward slash.
    //$row->destination_file = substr($row->sourceid, 1);
  }
  protected function createStub($migration, array $source_id) {
    $file = FALSE;
    $url = $this->base_url . $source_id[0];
    $scheme = file_uri_scheme($url);
    $class = file_stream_wrapper_get_class($scheme);
    if (!class_exists($class)) {
      return FALSE;
    }
    $file = remote_stream_wrapper_file_create_by_uri($url);
    if (!$file) {
      return FALSE;
    }
    $file = file_save($file);

    if (is_object($file) && isset($file->fid)) {
      return array($file->fid);
    }
    else {
      return FALSE;
    }
  }
}

class MigrateFileLink implements MigrateFileInterface {
  /**
   * We have no custom fields
   */
  static public function fields() {
    return array();
  }
  /**
   * Implementation of MigrateFileInterface::processFiles().
   *
   * @param $value
   *  The URI or local filespec of a file to be imported.
   * @param $owner
   *  User ID (uid) to be the owner of the file.
   * @return object
   *  The file entity being created or referenced.
   */
  public function processFile($url, $owner) {
    $file = FALSE;
    $scheme = file_uri_scheme($url);
    $class = file_stream_wrapper_get_class($scheme);
    if (!class_exists($class)) {
      return FALSE;
    }
    $file = remote_stream_wrapper_file_create_by_uri($url);
    if (!$file) {
      return FALSE;
    }
    $file = file_save($file);

    if (is_object($file)) {
      return $file;
    }
    else {
      return FALSE;
    }
  }
}