diff --git a/notebooks/enterprise-search/elastic-crawler-to-open-crawler-migration.ipynb b/notebooks/enterprise-search/elastic-crawler-to-open-crawler-migration.ipynb index f19ddf99..9c47bc86 100644 --- a/notebooks/enterprise-search/elastic-crawler-to-open-crawler-migration.ipynb +++ b/notebooks/enterprise-search/elastic-crawler-to-open-crawler-migration.ipynb @@ -275,6 +275,15 @@ " and domain_oid in inflight_configuration_data[config_oid][\"domains_temp\"]\n", " ):\n", "\n", + " # initialize extraction rulesets an empty array if it doesn't exist yet\n", + " if (\n", + " not \"extraction_rulesets\"\n", + " in inflight_configuration_data[config_oid][\"domains_temp\"][domain_oid]\n", + " ):\n", + " inflight_configuration_data[config_oid][\"domains_temp\"][domain_oid][\n", + " \"extraction_rulesets\"\n", + " ] = []\n", + "\n", " all_rules = source[\"rules\"]\n", " all_url_filters = source[\"url_filters\"]\n", "\n", @@ -294,7 +303,7 @@ " \"extracted\": \"extract\",\n", " }\n", "\n", - " ruleset = {}\n", + " ruleset = []\n", " if all_rules:\n", " ruleset = [\n", " {\n", @@ -309,13 +318,10 @@ " }\n", " ]\n", "\n", - " # populate the in-memory data structure\n", - " temp_extraction_rulesets = [\n", - " {\n", - " \"url_filters\": url_filters,\n", - " \"rules\": ruleset,\n", - " }\n", - " ]\n", + " temp_extraction_rulesets = {\n", + " \"url_filters\": url_filters,\n", + " \"rules\": ruleset,\n", + " }\n", "\n", " print(\n", " f\"{extr_count}.) Crawler {config_oid} has extraction rules {temp_extraction_rulesets}\\n\"\n", @@ -324,7 +330,7 @@ "\n", " inflight_configuration_data[config_oid][\"domains_temp\"][domain_oid][\n", " \"extraction_rulesets\"\n", - " ] = temp_extraction_rulesets" + " ].append(temp_extraction_rulesets)" ] }, {