Cleanup and more output

notebooks/enterprise-search/elastic_crawler_to_open_crawler_migration.ipynb

@@ -233,7 +233,8 @@
     "        # populate the in-memory data structure\n",
     "        inflight_configuration_data[crawler_oid][\"domains_temp\"][\n",
     "            domain_oid\n",
-    "        ] = temp_domain_conf"
+    "        ] = temp_domain_conf\n",
+    "        print()"
    ]
   },
   {
@@ -258,7 +259,7 @@
     "    _source=[\"configuration_oid\", \"domain_oid\", \"rules\", \"url_filters\"],\n",
     ")\n",
     "\n",
-    "extr_count = 0\n",
+    "extr_count = 1\n",
     "for exr_rule in extraction_rules[\"hits\"][\"hits\"]:\n",
     "    source = exr_rule[\"_source\"]\n",
     "\n",
@@ -306,12 +307,14 @@
     "            \"rules\": ruleset,\n",
     "        }\n",
     "    ]\n",
+    "\n",
+    "    print(\n",
+    "        f\"{extr_count}.) Crawler {config_oid} has extraction rules {temp_extraction_rulesets}\\n\"\n",
+    "    )\n",
     "    extr_count += 1\n",
     "    inflight_configuration_data[config_oid][\"domains_temp\"][domain_oid][\n",
     "        \"extraction_rulesets\"\n",
-    "    ] = temp_extraction_rulesets\n",
-    "\n",
-    "print(f\"{extr_count} total extraction rules found!\")"
+    "    ] = temp_extraction_rulesets"
    ]
   },
   {
@@ -348,7 +351,6 @@
     "\n",
     "    # ? comes from Quartz Cron, regular cron doesn't handle it well\n",
     "    repackaged_definition = repackaged_definition.replace(\"?\", \"*\")\n",
-    "    print(repackaged_definition)\n",
     "    return repackaged_definition\n",
     "\n",
     "\n",
@@ -402,15 +404,16 @@
    "source": [
     "# Final transform of the in-memory data structure to a form we can dump to YAML\n",
     "# for each crawler, collect all of its domain configurations into a list\n",
-    "for crawler_config in inflight_configuration_data.values():\n",
+    "for crawler_oid, crawler_config in inflight_configuration_data.items():\n",
     "    all_crawler_domains = []\n",
     "\n",
     "    for domain_config in crawler_config[\"domains_temp\"].values():\n",
     "        all_crawler_domains.append(domain_config)\n",
     "    # create a new key called \"domains\" that points to a list of domain configs only - no domain_oid values as keys\n",
     "    crawler_config[\"domains\"] = all_crawler_domains\n",
     "    # delete the temporary domain key\n",
-    "    del crawler_config[\"domains_temp\"]"
+    "    del crawler_config[\"domains_temp\"]\n",
+    "    print(f\"Transform for {crawler_oid} complete!\")"
    ]
   },
   {
@@ -518,6 +521,14 @@
     "        \"--------------------------------------------------------------------------------\"\n",
     "    )"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7aaee4e8-c388-4b22-a8ad-a657550d92c7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {