From 184e40bfa1ac838f9751be5f226554f9473466c7 Mon Sep 17 00:00:00 2001
From: Matt Nowzari <matt.nowzari@elastic.co>
Date: Wed, 26 Feb 2025 13:32:07 -0500
Subject: [PATCH] Bugfix in Crawler Migration Notebook extraction rule cell
 (#410)

---
 ...ic-crawler-to-open-crawler-migration.ipynb | 99 +++++++++++--------
 1 file changed, 56 insertions(+), 43 deletions(-)

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 0c1d48ed..9c47bc86 100644
--- a/notebooks/enterprise-search/elastic-crawler-to-open-crawler-migration.ipynb
+++ b/notebooks/enterprise-search/elastic-crawler-to-open-crawler-migration.ipynb
@@ -269,55 +269,68 @@
     "    config_oid = source[\"configuration_oid\"]\n",
     "    domain_oid = source[\"domain_oid\"]\n",
     "\n",
-    "    all_rules = source[\"rules\"]\n",
-    "    all_url_filters = source[\"url_filters\"]\n",
-    "\n",
-    "    # extract url filters\n",
-    "    url_filters = []\n",
-    "    if all_url_filters:\n",
-    "        url_filters = [\n",
-    "            {\n",
-    "                \"type\": all_url_filters[0][\"filter\"],\n",
-    "                \"pattern\": all_url_filters[0][\"pattern\"],\n",
-    "            }\n",
-    "        ]\n",
-    "\n",
-    "    # extract rulesets\n",
-    "    action_translation_map = {\n",
-    "        \"fixed\": \"set\",\n",
-    "        \"extracted\": \"extract\",\n",
-    "    }\n",
+    "    # ensure the config and domain oids actually exist in our in-memory data structure\n",
+    "    if (\n",
+    "        config_oid in inflight_configuration_data\n",
+    "        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",
+    "        # extract url filters\n",
+    "        url_filters = []\n",
+    "        if all_url_filters:\n",
+    "            url_filters = [\n",
+    "                {\n",
+    "                    \"type\": all_url_filters[0][\"filter\"],\n",
+    "                    \"pattern\": all_url_filters[0][\"pattern\"],\n",
+    "                }\n",
+    "            ]\n",
     "\n",
-    "    ruleset = {}\n",
-    "    if all_rules:\n",
-    "        ruleset = [\n",
-    "            {\n",
-    "                \"action\": action_translation_map[\n",
-    "                    all_rules[0][\"content_from\"][\"value_type\"]\n",
-    "                ],\n",
-    "                \"field_name\": all_rules[0][\"field_name\"],\n",
-    "                \"selector\": all_rules[0][\"selector\"],\n",
-    "                \"join_as\": all_rules[0][\"multiple_objects_handling\"],\n",
-    "                \"value\": all_rules[0][\"content_from\"][\"value\"],\n",
-    "                \"source\": all_rules[0][\"source_type\"],\n",
-    "            }\n",
-    "        ]\n",
+    "        # extract rulesets\n",
+    "        action_translation_map = {\n",
+    "            \"fixed\": \"set\",\n",
+    "            \"extracted\": \"extract\",\n",
+    "        }\n",
     "\n",
-    "    # populate the in-memory data structure\n",
-    "    temp_extraction_rulesets = [\n",
-    "        {\n",
+    "        ruleset = []\n",
+    "        if all_rules:\n",
+    "            ruleset = [\n",
+    "                {\n",
+    "                    \"action\": action_translation_map[\n",
+    "                        all_rules[0][\"content_from\"][\"value_type\"]\n",
+    "                    ],\n",
+    "                    \"field_name\": all_rules[0][\"field_name\"],\n",
+    "                    \"selector\": all_rules[0][\"selector\"],\n",
+    "                    \"join_as\": all_rules[0][\"multiple_objects_handling\"],\n",
+    "                    \"value\": all_rules[0][\"content_from\"][\"value\"],\n",
+    "                    \"source\": all_rules[0][\"source_type\"],\n",
+    "                }\n",
+    "            ]\n",
+    "\n",
+    "        temp_extraction_rulesets = {\n",
     "            \"url_filters\": url_filters,\n",
     "            \"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"
+    "        print(\n",
+    "            f\"{extr_count}.) Crawler {config_oid} has extraction rules {temp_extraction_rulesets}\\n\"\n",
+    "        )\n",
+    "        extr_count += 1\n",
+    "\n",
+    "        inflight_configuration_data[config_oid][\"domains_temp\"][domain_oid][\n",
+    "            \"extraction_rulesets\"\n",
+    "        ].append(temp_extraction_rulesets)"
    ]
   },
   {