diff --git a/apachesolr_attachments.admin.inc b/apachesolr_attachments.admin.inc index aa408b0..8f0095a 100644 --- a/apachesolr_attachments.admin.inc +++ b/apachesolr_attachments.admin.inc @@ -95,6 +95,36 @@ function apachesolr_attachments_settings_submit($form, &$form_state) { } /** + * Form callback for content type settings. +*/ +function apachesolr_attachments_entity_bundle_settings() { + $env_id = apachesolr_default_environment(); + + foreach (entity_get_info() as $entity_type => $entity_info) { + if (!empty($entity_info['apachesolr']['indexable'])) { + $indexed_bundles = apachesolr_get_index_bundles($env_id, $entity_type); + + foreach ($indexed_bundles as $bundle) { + if ($bundle != 'file') { + $form['apachesolr_attachments_entity_bundle_indexing_' . $bundle] = array( + '#type' => 'select', + '#title' => $bundle, + '#default_value' => variable_get('apachesolr_attachments_entity_bundle_indexing_' . $bundle, 'seperate'), + '#options' => array( + 'seperate' => t('Attachments as separate entities'), + 'parent' => t('Attachments as part of parent entity'), + 'none' => t("Don't index attachments"), + ), + ); + } + } + } + } + + return system_settings_form($form); +} + +/** * Form builder for the Apachesolr Attachments actions form. * */ diff --git a/apachesolr_attachments.index.inc b/apachesolr_attachments.index.inc index 180d274..7c6bb69 100644 --- a/apachesolr_attachments.index.inc +++ b/apachesolr_attachments.index.inc @@ -87,7 +87,7 @@ function apachesolr_attachments_get_attachment_text($file) { } catch (Exception $e) { // Exceptions from Solr may be transient, or indicate a problem with a specific file. - watchdog('Apache Solr Attachments', "Exception occurred sending %filepath to Solr\n!message", array('%filepath' => $file->uri, '!message' => nl2br(check_plain($e->getMessage()))), WATCHDOG_ERROR); + watchdog('Apache Solr Attachments', "Exception occurred sending %filepath to Solr\n!message", array('%filepath' => $filepath, '!message' => nl2br(check_plain($e->getMessage()))), WATCHDOG_ERROR); return FALSE; } } diff --git a/apachesolr_attachments.install b/apachesolr_attachments.install index 1bd0592..15a3b30 100644 --- a/apachesolr_attachments.install +++ b/apachesolr_attachments.install @@ -20,6 +20,10 @@ function apachesolr_attachments_uninstall() { variable_del('apachesolr_attachments_excluded_extensions'); variable_del('apachesolr_attachments_extract_using'); variable_del('apachesolr_attachments_excluded_mime'); + + db_delete('variable') + ->condition('name', db_like('apachesolr_attachments_enity_bundle_indexing_') , '%', 'LIKE') + ->execute(); } /** diff --git a/apachesolr_attachments.module b/apachesolr_attachments.module index 7824904..6f5a4f9 100644 --- a/apachesolr_attachments.module +++ b/apachesolr_attachments.module @@ -43,6 +43,20 @@ function apachesolr_attachments_menu() { 'file' => 'apachesolr_attachments.admin.inc', 'type' => MENU_CALLBACK, ); + $items['admin/config/search/apachesolr/attachments/general'] = array( + 'title' => 'General', + 'type' => MENU_DEFAULT_LOCAL_TASK, + ); + $items['admin/config/search/apachesolr/attachments/entity_bundle'] = array( + 'title' => 'Bundle', + 'description' => 'Administer Apache Solr Attachments per bundle settings.', + 'page callback' => 'drupal_get_form', + 'page arguments' => array('apachesolr_attachments_entity_bundle_settings'), + 'access arguments' => array('administer search'), + 'file' => 'apachesolr_attachments.admin.inc', + 'type' => MENU_LOCAL_TASK, + 'weight' => 1, + ); return $items; } @@ -58,6 +72,8 @@ function apachesolr_attachments_apachesolr_entity_info_alter(&$entity_info) { $entity_info['file']['reindex callback'] = 'apachesolr_attachments_solr_reindex'; $entity_info['file']['index_table'] = 'apachesolr_index_entities_file'; $entity_info['file']['result callback'] = 'apachesolr_attachments_file_result'; + + $entity_info['node']['document callback'][] = 'apachesolr_attachments_node_solr_document'; } /** @@ -100,61 +116,115 @@ function apachesolr_attachments_solr_document(ApacheSolrDocument $document, $fil // Retrieve the parent entity id and bundle list($parent_entity_id, $parent_entity_vid, $parent_entity_bundle) = entity_extract_ids($parent_entity_type, $parent_entity); - // Get a clone of the bare minimum document - $filedocument = clone $document; + // proceed with building this document only if the parent entity is not flagged for + //indexing attachments with parent entity or not indexing attachements + if (variable_get('apachesolr_attachments_entity_bundle_indexing_' . $parent_entity_bundle, 'seperate') == 'seperate') { + // Get a clone of the bare minimum document + $filedocument = clone $document; + + //Get the callback array to add stuff to the document + $callbacks = apachesolr_entity_get_callback($parent_entity_type, 'document callback'); + $build_documents = array(); + foreach ($callbacks as $callback) { + // Call a type-specific callback to add stuff to the document. + $build_documents = array_merge($build_documents, $callback($filedocument, $parent_entity, $parent_entity_type, $env_id)); + } + + // Take the top document from the stack + $filedocument = reset($build_documents); + + // Build our separate document and overwrite basic information + $filedocument->id = apachesolr_document_id($file->fid . '-' . $parent_entity_id, 'file'); + $filedocument->url = file_create_url($file->uri); + $filedocument->path = file_stream_wrapper_get_instance_by_uri($file->uri)->getExternalUrl(); + + // Add extra info to our document + $filedocument->label = apachesolr_clean_text($file->filename); + $filedocument->content = apachesolr_clean_text($file->filename) . ' ' . $text; + + $filedocument->ds_created = apachesolr_date_iso($file->timestamp); + $filedocument->ds_changed = $filedocument->ds_created; + + $filedocument->created = apachesolr_date_iso($file->timestamp); + $filedocument->changed = $filedocument->created; + + // Add Parent information fields. See http://drupal.org/node/1515822 for explanation + $parent_entity_info = entity_get_info($parent_entity_type); + $small_parent_entity = new stdClass(); + $small_parent_entity->entity_type = $parent_entity_type; + $small_parent_entity->{$parent_entity_info['entity keys']['id']} = $parent_entity_id; + $small_parent_entity->{$parent_entity_info['entity keys']['bundle']} = $parent_entity_bundle; + $small_parent_entity->{$parent_entity_info['entity keys']['label']} = $parent_entity->{$parent_entity_info['entity keys']['label']}; + + // Add all to one field because if it is spread out over + // multiple fields there is no way of knowing which multifield value + // belongs to which entity + // It does not load the complete entity in to the index because that + // would dramatically increase the index size and processing time + $filedocument->zm_parent_entity = serialize($small_parent_entity); + $filedocument->sm_parent_entity_bundle = $parent_entity_type . "-" . $parent_entity_bundle; + $filedocument->sm_parent_entity_type = $parent_entity_type; + + // Add Apachesolr Attachments specific fields. + $filedocument->ss_filemime = $file->filemime; + $filedocument->ss_filesize = $file->filesize; + + $documents[] = $filedocument; + } + } + } + } + return $documents; +} - //Get the callback array to add stuff to the document - $callbacks = apachesolr_entity_get_callback($parent_entity_type, 'document callback'); - $build_documents = array(); - foreach ($callbacks as $callback) { - // Call a type-specific callback to add stuff to the document. - $build_documents = array_merge($build_documents, $callback($filedocument, $parent_entity, $parent_entity_type, $env_id)); +function apachesolr_attachments_node_solr_document(ApacheSolrDocument &$document, $parent_entity, $env_id) { + module_load_include('inc', 'apachesolr_attachments', 'apachesolr_attachments.index'); + + list($parent_entity_id, $parent_entity_vid, $parent_entity_bundle) = entity_extract_ids('node', $parent_entity); + + // proceed with combining attachment content to entity document only if the parent entity is flagged for + //indexing attachments with parent entity + if (variable_get('apachesolr_attachments_entity_bundle_indexing_' . $parent_entity_bundle, 'seperate') == 'parent') { + + + $file_field_names = array(); + $fields = field_info_field_by_ids(); + foreach ($fields as $field_id => $field_info) { + if ($field_info['type'] == 'file') { + foreach ($field_info['bundles'] as $entity_type => $bundles) { + if (in_array($parent_entity_bundle, $bundles)) { + $file_field_names[$field_info['field_name']] = $field_info['field_name']; + } } + } + } - // Take the top document from the stack - $filedocument = reset($build_documents); - - // Build our separate document and overwrite basic information - $filedocument->id = apachesolr_document_id($file->fid . '-' . $parent_entity_id, 'file'); - $filedocument->url = file_create_url($file->uri); - $filedocument->path = file_stream_wrapper_get_instance_by_uri($file->uri)->getExternalUrl(); - - // Add extra info to our document - $filedocument->label = apachesolr_clean_text($file->filename); - $filedocument->content = apachesolr_clean_text($file->filename) . ' ' . $text; - - $filedocument->ds_created = apachesolr_date_iso($file->timestamp); - $filedocument->ds_changed = $filedocument->ds_created; - - $filedocument->created = apachesolr_date_iso($file->timestamp); - $filedocument->changed = $filedocument->created; - - // Add Parent information fields. See http://drupal.org/node/1515822 for explanation - $parent_entity_info = entity_get_info($parent_entity_type); - $small_parent_entity = new stdClass(); - $small_parent_entity->entity_type = $parent_entity_type; - $small_parent_entity->{$parent_entity_info['entity keys']['id']} = $parent_entity_id; - $small_parent_entity->{$parent_entity_info['entity keys']['bundle']} = $parent_entity_bundle; - $small_parent_entity->{$parent_entity_info['entity keys']['label']} = $parent_entity->{$parent_entity_info['entity keys']['label']}; - - // Add all to one field because if it is spread out over - // multiple fields there is no way of knowing which multifield value - // belongs to which entity - // It does not load the complete entity in to the index because that - // would dramatically increase the index size and processing time - $filedocument->zm_parent_entity = serialize($small_parent_entity); - $filedocument->sm_parent_entity_bundle = $parent_entity_type . "-" . $parent_entity_bundle; - $filedocument->sm_parent_entity_type = $parent_entity_type; - - // Add Apachesolr Attachments specific fields. - $filedocument->ss_filemime = $file->filemime; - $filedocument->ss_filesize = $file->filesize; - - $documents[] = $filedocument; + foreach ($file_field_names as $file_field) { + if (isset($parent_entity->$file_field)) { + $parent_entity_file_fields = $parent_entity->$file_field; + //@todo deal with different languages properly + foreach($parent_entity_file_fields as $language => $files) { + foreach ($files as $file) { + + $file = (object)$file; + // perform some basic validation that the file is ok to extract text from + $status = ($file->status == 1 ? 1 : 0); + // Check if the mimetype is allowed + $status = $status & apachesolr_attachments_is_file($file); + $status = $status & apachesolr_attachments_allowed_mime($file->filemime); + + if ($status) { + $text = apachesolr_attachments_get_attachment_text($file); + // append extracted text to index content field + $document->content .= $text; + } + } + } } } } - return $documents; + + return array(); // all alterations are made to $document passed in by reference } /** @@ -373,10 +443,14 @@ function apachesolr_attachments_apachesolr_query_alter(DrupalSolrQueryInterface function apachesolr_attachments_entity_update($entity, $type) { module_load_include('inc', 'apachesolr_attachments', 'apachesolr_attachments.index'); apachesolr_attachments_clean_index_table(); + + _apachesolr_attachments_update_parent_entity($entity, $type); } function apachesolr_attachments_entity_insert($entity, $type) { apachesolr_attachments_entity_update($entity, $type); + + _apachesolr_attachments_update_parent_entity($entity, $type); } function apachesolr_attachments_entity_delete($entity, $type) { @@ -385,6 +459,38 @@ function apachesolr_attachments_entity_delete($entity, $type) { } /** +* trigger an apachesolr_entity_update of parents where the parents are flagged for indexing attachments with the parent +**/ +function _apachesolr_attachments_update_parent_entity($entity, $type) { + // if this entity was being indexed with its parent, we need to trigger a reindex of the parent + $parents = file_get_file_references($entity, NULL, FIELD_LOAD_CURRENT); + $parents_list = $parents ? reset($parents) : NULL; + + if (!empty($parents_list)) { + foreach ($parents_list as $parent_entity_type => $parent) { + foreach ($parent as $parent_entity_id => $parent_info) { + // load the parent entity and reset cache + $parent_entities = entity_load($parent_entity_type, array($parent_entity_id), NULL, TRUE); + // Take the first entity from the stack + $parent_entity = reset($parent_entities); + + // Skip invalid entities + if (empty($parent_entity)) { + continue; + } + + // get the bundle + list($parent_entity_id, $parent_entity_vid, $parent_entity_bundle) = entity_extract_ids('node', $parent_entity); + + if (variable_get('apachesolr_attachments_entity_bundle_indexing_' . $parent_entity_bundle, 'seperate') == 'parent') { + apachesolr_entity_update($parent_entity, $parent_entity_type); + } + } + } + } +} + +/** * Hook into the field operations * - we want to save the same data in a shadow copy table for easier indexing. * - We do not delete the file / media entity when its usage count goes to 0