Skip to content

Bugfix in Crawler Migration Notebook extraction rule cell #410

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Feb 26, 2025
Merged

Bugfix in Crawler Migration Notebook extraction rule cell #410

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ccedd54
Minor tweak to the extraction rule cell to handle an edge case
mattnowzari Feb 25, 2025
a3bd8fe
Moved domain_oid check to prevent an unnecessary extraction rule from…
mattnowzari Feb 26, 2025
5ca678d
Revised the if statement to check config_oids too
mattnowzari Feb 26, 2025
8cf33a7
Fixed related bug where a crawler with multiple extraction rules was …
mattnowzari Feb 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
99 changes: 56 additions & 43 deletions notebooks/enterprise-search/elastic-crawler-to-open-crawler-migration.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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)"
]
},
{
Expand Down