mostlyright-data 0.9.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- mostlyright/data_harness/__init__.py +158 -0
- mostlyright/data_harness/acquisition/__init__.py +55 -0
- mostlyright/data_harness/acquisition/http.py +2773 -0
- mostlyright/data_harness/acquisition/parsing.py +809 -0
- mostlyright/data_harness/acquisition/ranges.py +495 -0
- mostlyright/data_harness/acquisition/result_download.py +360 -0
- mostlyright/data_harness/acquisition/retention_admission.py +248 -0
- mostlyright/data_harness/acquisition/sandbox.py +4888 -0
- mostlyright/data_harness/acquisition/url_policy.py +530 -0
- mostlyright/data_harness/agent_runtime.py +2743 -0
- mostlyright/data_harness/assets/logo-ink.svg +31 -0
- mostlyright/data_harness/backends/__init__.py +28 -0
- mostlyright/data_harness/backends/pandas_backend.py +350 -0
- mostlyright/data_harness/backends/polars_backend.py +366 -0
- mostlyright/data_harness/backends/protocol.py +124 -0
- mostlyright/data_harness/backends/reference.py +83 -0
- mostlyright/data_harness/backends/registry.py +55 -0
- mostlyright/data_harness/backends/restrictions.py +126 -0
- mostlyright/data_harness/canonical.py +333 -0
- mostlyright/data_harness/catalog_job.py +625 -0
- mostlyright/data_harness/cli.py +5398 -0
- mostlyright/data_harness/contracts.py +53 -0
- mostlyright/data_harness/coordinator.py +1307 -0
- mostlyright/data_harness/deploy.py +924 -0
- mostlyright/data_harness/deploy_target.py +312 -0
- mostlyright/data_harness/deployment_evidence.py +1067 -0
- mostlyright/data_harness/event_presentation.py +576 -0
- mostlyright/data_harness/events.py +2152 -0
- mostlyright/data_harness/fast_delimited.py +239 -0
- mostlyright/data_harness/fleet.py +237 -0
- mostlyright/data_harness/formats.py +236 -0
- mostlyright/data_harness/governors.py +1163 -0
- mostlyright/data_harness/hosted_bootstrap.py +972 -0
- mostlyright/data_harness/hosted_crawler.py +1115 -0
- mostlyright/data_harness/hosted_crawler_container_smoke.py +351 -0
- mostlyright/data_harness/hosted_crawler_fetch.py +423 -0
- mostlyright/data_harness/hosted_crawler_job.py +1277 -0
- mostlyright/data_harness/hosted_crawler_protocol.py +676 -0
- mostlyright/data_harness/hosted_dataset.py +1500 -0
- mostlyright/data_harness/hosted_deploy.py +3037 -0
- mostlyright/data_harness/hosted_handoff.py +62 -0
- mostlyright/data_harness/hosted_ingestion_contract.py +504 -0
- mostlyright/data_harness/hosted_ingestion_job.py +356 -0
- mostlyright/data_harness/hosted_ingestion_job_smoke.py +40 -0
- mostlyright/data_harness/hosted_session_container_smoke.py +194 -0
- mostlyright/data_harness/hosted_session_worker.py +3554 -0
- mostlyright/data_harness/hosted_session_worker_job_smoke.py +46 -0
- mostlyright/data_harness/hosted_worker.py +6784 -0
- mostlyright/data_harness/ingestion/__init__.py +56 -0
- mostlyright/data_harness/ingestion/contracts.py +461 -0
- mostlyright/data_harness/ingestion/faults.py +42 -0
- mostlyright/data_harness/ingestion/gcs_store.py +1162 -0
- mostlyright/data_harness/ingestion/spool.py +130 -0
- mostlyright/data_harness/ingestion/store.py +885 -0
- mostlyright/data_harness/key_seam.py +434 -0
- mostlyright/data_harness/linux_process_boundary.py +262 -0
- mostlyright/data_harness/local_contracts.py +2880 -0
- mostlyright/data_harness/local_search/__init__.py +5 -0
- mostlyright/data_harness/local_search/build_index.py +1087 -0
- mostlyright/data_harness/local_search/contracts.py +920 -0
- mostlyright/data_harness/local_search/query_trace.py +266 -0
- mostlyright/data_harness/local_search/retrieval.py +700 -0
- mostlyright/data_harness/local_search/sealed.py +474 -0
- mostlyright/data_harness/local_search/service.py +784 -0
- mostlyright/data_harness/nbrender/CONTRACT.md +212 -0
- mostlyright/data_harness/nbrender/__init__.py +12 -0
- mostlyright/data_harness/nbrender/chrome.py +359 -0
- mostlyright/data_harness/nbrender/code_body.py +266 -0
- mostlyright/data_harness/nbrender/document.py +407 -0
- mostlyright/data_harness/nbrender/frame.py +275 -0
- mostlyright/data_harness/nbrender/interactive.py +337 -0
- mostlyright/data_harness/nbrender/markdown_body.py +477 -0
- mostlyright/data_harness/nbrender/mr_components.py +134 -0
- mostlyright/data_harness/nbrender/outputs_data.py +595 -0
- mostlyright/data_harness/nbrender/outputs_rich.py +906 -0
- mostlyright/data_harness/nbrender/outputs_source.py +260 -0
- mostlyright/data_harness/nbrender/outputs_stage.py +176 -0
- mostlyright/data_harness/nbrender/outputs_text.py +400 -0
- mostlyright/data_harness/nbrender/parse.py +394 -0
- mostlyright/data_harness/nbrender/status.py +40 -0
- mostlyright/data_harness/nbrender/tokens.py +1295 -0
- mostlyright/data_harness/notebook.py +1710 -0
- mostlyright/data_harness/offline.py +2049 -0
- mostlyright/data_harness/operation_registry.py +1007 -0
- mostlyright/data_harness/operator_setup.py +239 -0
- mostlyright/data_harness/pipeline.py +6428 -0
- mostlyright/data_harness/plan_graph.py +2026 -0
- mostlyright/data_harness/preparation/__init__.py +104 -0
- mostlyright/data_harness/preparation/contracts.py +1017 -0
- mostlyright/data_harness/preparation/engine.py +221 -0
- mostlyright/data_harness/preparation/errors.py +14 -0
- mostlyright/data_harness/preparation/gates.py +751 -0
- mostlyright/data_harness/preparation/joins.py +574 -0
- mostlyright/data_harness/preparation/profile.py +384 -0
- mostlyright/data_harness/preparation/table.py +217 -0
- mostlyright/data_harness/preparation/transforms.py +568 -0
- mostlyright/data_harness/progress_events.py +534 -0
- mostlyright/data_harness/readers/__init__.py +46 -0
- mostlyright/data_harness/readers/containers.py +963 -0
- mostlyright/data_harness/readers/contracts.py +542 -0
- mostlyright/data_harness/readers/delimited.py +257 -0
- mostlyright/data_harness/readers/grib2/__init__.py +33 -0
- mostlyright/data_harness/readers/grib2/admission.py +722 -0
- mostlyright/data_harness/readers/grib2/decode.py +1009 -0
- mostlyright/data_harness/readers/grib2/geometry.py +1133 -0
- mostlyright/data_harness/readers/grib2/portable_math.py +501 -0
- mostlyright/data_harness/readers/json_tabular.py +485 -0
- mostlyright/data_harness/readers/registry.py +514 -0
- mostlyright/data_harness/readers/samples/README.md +110 -0
- mostlyright/data_harness/readers/samples/archive.gzip/1.0.0/cities_one_stream/cities.csv.gz +0 -0
- mostlyright/data_harness/readers/samples/archive.gzip/1.0.0/cities_one_stream/expected.json +24 -0
- mostlyright/data_harness/readers/samples/archive.gzip/1.1.0/cities_one_stream/cities.csv.gz +0 -0
- mostlyright/data_harness/readers/samples/archive.gzip/1.1.0/cities_one_stream/expected.json +24 -0
- mostlyright/data_harness/readers/samples/archive.tar/1.0.0/cities_beside_a_directory_entry/cities.tar +0 -0
- mostlyright/data_harness/readers/samples/archive.tar/1.0.0/cities_beside_a_directory_entry/expected.json +24 -0
- mostlyright/data_harness/readers/samples/archive.tar/1.1.0/cities_beside_a_directory_entry/cities.tar +0 -0
- mostlyright/data_harness/readers/samples/archive.tar/1.1.0/cities_beside_a_directory_entry/expected.json +24 -0
- mostlyright/data_harness/readers/samples/archive.zip/1.0.0/cities_beside_a_second_member/cities.zip +0 -0
- mostlyright/data_harness/readers/samples/archive.zip/1.0.0/cities_beside_a_second_member/expected.json +25 -0
- mostlyright/data_harness/readers/samples/archive.zip/1.1.0/dwd_semicolon_station_member/dwd-station.zip +0 -0
- mostlyright/data_harness/readers/samples/archive.zip/1.1.0/dwd_semicolon_station_member/expected.json +25 -0
- mostlyright/data_harness/readers/samples/archive.zip/1.2.0/dwd_semicolon_station_member/dwd-station.zip +0 -0
- mostlyright/data_harness/readers/samples/archive.zip/1.2.0/dwd_semicolon_station_member/expected.json +25 -0
- mostlyright/data_harness/readers/samples/delimited_text/1.0.0/an_ordinary_comma_separated_table/cities.csv +3 -0
- mostlyright/data_harness/readers/samples/delimited_text/1.0.0/an_ordinary_comma_separated_table/expected.json +23 -0
- mostlyright/data_harness/readers/samples/delimited_text/1.0.0/quoted_fields_holding_the_delimiter/cities.tsv +5 -0
- mostlyright/data_harness/readers/samples/delimited_text/1.0.0/quoted_fields_holding_the_delimiter/expected.json +25 -0
- mostlyright/data_harness/readers/samples/delimited_text/1.1.0/an_hourly_observation_table_served_as_plain_text/expected.json +30 -0
- mostlyright/data_harness/readers/samples/delimited_text/1.1.0/an_hourly_observation_table_served_as_plain_text/observations.csv +5 -0
- mostlyright/data_harness/readers/samples/json.tabular/1.0.0/nested_hourly_observations/expected.json +44 -0
- mostlyright/data_harness/readers/samples/json.tabular/1.0.0/nested_hourly_observations/stations.json +1 -0
- mostlyright/data_harness/readers/samples/json.tabular/1.1.0/an_observation_stream_served_as_plain_text/expected.json +48 -0
- mostlyright/data_harness/readers/samples/json.tabular/1.1.0/an_observation_stream_served_as_plain_text/observations.ndjson +4 -0
- mostlyright/data_harness/readers/samples/spreadsheet.xlsx/1.0.0/an_ordinary_table_beside_a_second_sheet/cities.xlsx +0 -0
- mostlyright/data_harness/readers/samples/spreadsheet.xlsx/1.0.0/an_ordinary_table_beside_a_second_sheet/expected.json +24 -0
- mostlyright/data_harness/readers/samples/spreadsheet.xlsx/1.0.0/shares_the_workbook_had_already_computed/expected.json +27 -0
- mostlyright/data_harness/readers/samples/spreadsheet.xlsx/1.0.0/shares_the_workbook_had_already_computed/shares.xlsx +0 -0
- mostlyright/data_harness/readers/samples/spreadsheet.xlsx/1.1.0/shares_the_workbook_had_already_computed/expected.json +27 -0
- mostlyright/data_harness/readers/samples/spreadsheet.xlsx/1.1.0/shares_the_workbook_had_already_computed/shares.xlsx +0 -0
- mostlyright/data_harness/readers/samples/weather.grib2/1.0.0/README.md +20 -0
- mostlyright/data_harness/readers/samples/weather.grib2/1.0.0/gfs_2m_temperature/expected.json +55 -0
- mostlyright/data_harness/readers/samples/weather.grib2/1.0.0/gfs_2m_temperature/gfs-2m-temperature.grib2 +0 -0
- mostlyright/data_harness/readers/samples/weather.grib2/1.0.0/hrrr_2m_temperature/expected.json +54 -0
- mostlyright/data_harness/readers/samples/weather.grib2/1.0.0/hrrr_2m_temperature/hrrr-2m-temperature.grib2 +0 -0
- mostlyright/data_harness/readers/samples/weather.grib2/1.0.0/hrrr_categorical_rain/expected.json +54 -0
- mostlyright/data_harness/readers/samples/weather.grib2/1.0.0/hrrr_categorical_rain/hrrr-categorical-rain.grib2 +0 -0
- mostlyright/data_harness/readers/samples/weather.grib2/2.0.0/hrrr_2m_temperature/expected.json +54 -0
- mostlyright/data_harness/readers/samples/weather.grib2/2.0.0/hrrr_2m_temperature/hrrr-2m-temperature.grib2 +0 -0
- mostlyright/data_harness/readers/samples.py +582 -0
- mostlyright/data_harness/readers/spreadsheet.py +803 -0
- mostlyright/data_harness/readers/tabular.py +510 -0
- mostlyright/data_harness/recipe.py +5321 -0
- mostlyright/data_harness/repair/__init__.py +78 -0
- mostlyright/data_harness/repair/adapters.py +274 -0
- mostlyright/data_harness/repair/contracts.py +872 -0
- mostlyright/data_harness/repair/coordinator.py +1099 -0
- mostlyright/data_harness/repair/errors.py +16 -0
- mostlyright/data_harness/review.py +2533 -0
- mostlyright/data_harness/rowset.py +283 -0
- mostlyright/data_harness/serving.py +1975 -0
- mostlyright/data_harness/serving_edge.py +590 -0
- mostlyright/data_harness/serving_http.py +1031 -0
- mostlyright/data_harness/session_probes.py +759 -0
- mostlyright/data_harness/signing.py +101 -0
- mostlyright/data_harness/source_discovery.py +898 -0
- mostlyright/data_harness/sources/__init__.py +209 -0
- mostlyright/data_harness/sources/_adapter_steps.py +213 -0
- mostlyright/data_harness/sources/adapters.py +1214 -0
- mostlyright/data_harness/sources/cadence.py +1428 -0
- mostlyright/data_harness/sources/cadence_emission.py +453 -0
- mostlyright/data_harness/sources/cadence_history.py +546 -0
- mostlyright/data_harness/sources/catalog/__init__.py +17 -0
- mostlyright/data_harness/sources/catalog/admission.py +477 -0
- mostlyright/data_harness/sources/catalog/authoring.py +1701 -0
- mostlyright/data_harness/sources/catalog/authoring_policy.py +701 -0
- mostlyright/data_harness/sources/catalog/authoring_shards.py +1217 -0
- mostlyright/data_harness/sources/catalog/bounded_io.py +231 -0
- mostlyright/data_harness/sources/catalog/channel.py +523 -0
- mostlyright/data_harness/sources/catalog/channel_client.py +296 -0
- mostlyright/data_harness/sources/catalog/contracts.py +825 -0
- mostlyright/data_harness/sources/catalog/coverage.py +137 -0
- mostlyright/data_harness/sources/catalog/delta.py +1340 -0
- mostlyright/data_harness/sources/catalog/embedding.py +532 -0
- mostlyright/data_harness/sources/catalog/entry_v2.py +1182 -0
- mostlyright/data_harness/sources/catalog/fill.py +3889 -0
- mostlyright/data_harness/sources/catalog/fill_partitions.py +459 -0
- mostlyright/data_harness/sources/catalog/fill_staging.py +1105 -0
- mostlyright/data_harness/sources/catalog/gating.py +374 -0
- mostlyright/data_harness/sources/catalog/generation_receipt.py +1607 -0
- mostlyright/data_harness/sources/catalog/harvest/__init__.py +7 -0
- mostlyright/data_harness/sources/catalog/harvest/ckan.py +384 -0
- mostlyright/data_harness/sources/catalog/harvest/datagov_v4.py +798 -0
- mostlyright/data_harness/sources/catalog/harvest/protocol.py +964 -0
- mostlyright/data_harness/sources/catalog/harvest/sdmx.py +445 -0
- mostlyright/data_harness/sources/catalog/harvest/stac.py +384 -0
- mostlyright/data_harness/sources/catalog/health.py +447 -0
- mostlyright/data_harness/sources/catalog/hosted_catalog.py +105 -0
- mostlyright/data_harness/sources/catalog/identity_history.py +1549 -0
- mostlyright/data_harness/sources/catalog/neural.py +1618 -0
- mostlyright/data_harness/sources/catalog/packed_catalog.py +2345 -0
- mostlyright/data_harness/sources/catalog/packed_retrieval.py +1517 -0
- mostlyright/data_harness/sources/catalog/packed_writer.py +2802 -0
- mostlyright/data_harness/sources/catalog/query_trace.py +1037 -0
- mostlyright/data_harness/sources/catalog/recommend.py +171 -0
- mostlyright/data_harness/sources/catalog/retrieval.py +230 -0
- mostlyright/data_harness/sources/catalog/retrieval_manifest.py +995 -0
- mostlyright/data_harness/sources/catalog/rights_decisions.py +254 -0
- mostlyright/data_harness/sources/catalog/sealed.py +560 -0
- mostlyright/data_harness/sources/catalog/search.py +230 -0
- mostlyright/data_harness/sources/catalog/streaming_delta.py +1097 -0
- mostlyright/data_harness/sources/catalog/update.py +891 -0
- mostlyright/data_harness/sources/collections.py +815 -0
- mostlyright/data_harness/sources/contracts.py +2223 -0
- mostlyright/data_harness/sources/deletion.py +761 -0
- mostlyright/data_harness/sources/fitness.py +162 -0
- mostlyright/data_harness/sources/governance.py +163 -0
- mostlyright/data_harness/sources/hosted.py +173 -0
- mostlyright/data_harness/sources/integration.py +218 -0
- mostlyright/data_harness/sources/range_reader.py +418 -0
- mostlyright/data_harness/sources/registry.py +514 -0
- mostlyright/data_harness/sources/rights_rule.py +59 -0
- mostlyright/data_harness/sources/source_cadence_vectors.v1.json +1 -0
- mostlyright/data_harness/sources/sports.py +521 -0
- mostlyright/data_harness/sources/stream.py +524 -0
- mostlyright/data_harness/sources/stream_connector.py +418 -0
- mostlyright/data_harness/sources/stream_recorder.py +1404 -0
- mostlyright/data_harness/studio_boundary.py +2019 -0
- mostlyright/data_harness/thin/__init__.py +37 -0
- mostlyright/data_harness/thin/acquire.py +1137 -0
- mostlyright/data_harness/thin/acquire_cancel.py +579 -0
- mostlyright/data_harness/thin/approvals.py +617 -0
- mostlyright/data_harness/thin/commands.py +406 -0
- mostlyright/data_harness/thin/download.py +194 -0
- mostlyright/data_harness/thin/narrative.py +589 -0
- mostlyright/data_harness/thin/parity.py +1070 -0
- mostlyright/data_harness/thin/propose.py +2759 -0
- mostlyright/data_harness/thin/research.py +1663 -0
- mostlyright/data_harness/thin/router.py +924 -0
- mostlyright/data_harness/thin/runs.py +519 -0
- mostlyright/data_harness/thin/session.py +281 -0
- mostlyright/data_harness/thin/stream.py +501 -0
- mostlyright/data_harness/thin/transport.py +187 -0
- mostlyright/data_harness/thin/vocabulary.py +368 -0
- mostlyright/data_harness/thin/workers.py +164 -0
- mostlyright/data_harness/ucum/TABLE-PIN.json +40 -0
- mostlyright/data_harness/ucum/ucum-subset.v1.json +632 -0
- mostlyright/data_harness/unit_flow.py +927 -0
- mostlyright/data_harness/units.py +572 -0
- mostlyright/data_harness/ux/__init__.py +9 -0
- mostlyright/data_harness/ux/approve.py +485 -0
- mostlyright/data_harness/ux/author_yaml.py +597 -0
- mostlyright/data_harness/ux/cloud_auth.py +447 -0
- mostlyright/data_harness/ux/commands/__init__.py +260 -0
- mostlyright/data_harness/ux/commands/approve.py +136 -0
- mostlyright/data_harness/ux/commands/auth.py +744 -0
- mostlyright/data_harness/ux/commands/author.py +79 -0
- mostlyright/data_harness/ux/commands/catalog_author.py +403 -0
- mostlyright/data_harness/ux/commands/catalog_fill.py +523 -0
- mostlyright/data_harness/ux/commands/catalog_harvest.py +545 -0
- mostlyright/data_harness/ux/commands/catalog_publish.py +1838 -0
- mostlyright/data_harness/ux/commands/catalog_search.py +71 -0
- mostlyright/data_harness/ux/commands/catalog_update.py +437 -0
- mostlyright/data_harness/ux/commands/deploy.py +134 -0
- mostlyright/data_harness/ux/commands/deploy_dataset.py +98 -0
- mostlyright/data_harness/ux/commands/deploy_plan.py +105 -0
- mostlyright/data_harness/ux/commands/deploy_status.py +104 -0
- mostlyright/data_harness/ux/commands/diff.py +74 -0
- mostlyright/data_harness/ux/commands/index.py +84 -0
- mostlyright/data_harness/ux/commands/inventory.py +47 -0
- mostlyright/data_harness/ux/commands/list_builds.py +143 -0
- mostlyright/data_harness/ux/commands/login.py +63 -0
- mostlyright/data_harness/ux/commands/peek.py +236 -0
- mostlyright/data_harness/ux/commands/plan_check.py +90 -0
- mostlyright/data_harness/ux/commands/preflight.py +97 -0
- mostlyright/data_harness/ux/commands/record.py +107 -0
- mostlyright/data_harness/ux/commands/review_setup.py +47 -0
- mostlyright/data_harness/ux/commands/search.py +440 -0
- mostlyright/data_harness/ux/commands/show.py +61 -0
- mostlyright/data_harness/ux/commands/whoami.py +37 -0
- mostlyright/data_harness/ux/credential_native.py +551 -0
- mostlyright/data_harness/ux/credential_store.py +1055 -0
- mostlyright/data_harness/ux/credentials.py +631 -0
- mostlyright/data_harness/ux/diffing.py +444 -0
- mostlyright/data_harness/ux/headline.py +671 -0
- mostlyright/data_harness/ux/hosted_acquisition.py +974 -0
- mostlyright/data_harness/ux/hosted_run_status.py +619 -0
- mostlyright/data_harness/ux/inventory.py +427 -0
- mostlyright/data_harness/ux/local_review.py +375 -0
- mostlyright/data_harness/ux/login.py +691 -0
- mostlyright/data_harness/ux/path_kind.py +147 -0
- mostlyright/data_harness/ux/peek.py +1000 -0
- mostlyright/data_harness/ux/plain_file.py +178 -0
- mostlyright/data_harness/ux/plan_check.py +311 -0
- mostlyright/data_harness/ux/preflight.py +918 -0
- mostlyright/data_harness/ux/readers.py +1124 -0
- mostlyright/data_harness/ux/remediation.py +2195 -0
- mostlyright/data_harness/ux/render.py +657 -0
- mostlyright/data_harness/ux/workload.py +1077 -0
- mostlyright/data_harness/viewer.py +3713 -0
- mostlyright/data_harness/visual_run/__init__.py +83 -0
- mostlyright/data_harness/visual_run/authoring.py +235 -0
- mostlyright/data_harness/visual_run/contracts.py +673 -0
- mostlyright/data_harness/visual_run/materialize.py +486 -0
- mostlyright/data_harness/visual_run/observations.py +874 -0
- mostlyright/data_harness/visual_run/query.py +259 -0
- mostlyright/data_harness/visual_run/reducer.py +280 -0
- mostlyright/data_harness/visual_run/sdk.py +892 -0
- mostlyright/data_harness/visual_run/store.py +584 -0
- mostlyright/data_harness/visual_run/transport.py +239 -0
- mostlyright/data_harness/watch.py +2999 -0
- mostlyright_data-0.9.0.dist-info/METADATA +607 -0
- mostlyright_data-0.9.0.dist-info/RECORD +314 -0
- mostlyright_data-0.9.0.dist-info/WHEEL +4 -0
- mostlyright_data-0.9.0.dist-info/entry_points.txt +12 -0
|
@@ -0,0 +1,266 @@
|
|
|
1
|
+
"""Canonical immutable-fact evidence for one private Build-index query."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
from dataclasses import dataclass
|
|
6
|
+
from typing import Any
|
|
7
|
+
|
|
8
|
+
from mostlyright.data_harness.canonical import canonical_sha256
|
|
9
|
+
from mostlyright.data_harness.local_search.contracts import (
|
|
10
|
+
BuildIndexEntry,
|
|
11
|
+
LocalSearchContractError,
|
|
12
|
+
)
|
|
13
|
+
from mostlyright.data_harness.local_search.retrieval import (
|
|
14
|
+
MAX_RETRIEVAL_LIMIT,
|
|
15
|
+
BuildRetrieval,
|
|
16
|
+
)
|
|
17
|
+
|
|
18
|
+
PRIVATE_BUILD_QUERY_TRACE_VERSION = "harness-private-build-query-trace.v1"
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
@dataclass(frozen=True)
|
|
22
|
+
class TracedBuildDisposition:
|
|
23
|
+
"""Immutable identities and fact-filter outcome for one considered Build."""
|
|
24
|
+
|
|
25
|
+
facts_sha256: str
|
|
26
|
+
candidate_sha256: str
|
|
27
|
+
table_sha256: str
|
|
28
|
+
disposition: str
|
|
29
|
+
failed_filters: tuple[str, ...]
|
|
30
|
+
|
|
31
|
+
def __post_init__(self) -> None:
|
|
32
|
+
for name in ("facts_sha256", "candidate_sha256", "table_sha256"):
|
|
33
|
+
_digest(getattr(self, name), f"trace.candidates.{name}")
|
|
34
|
+
if self.disposition not in {"eligible", "ineligible"}:
|
|
35
|
+
raise LocalSearchContractError(
|
|
36
|
+
"LOCAL_SEARCH_TRACE_DISPOSITION",
|
|
37
|
+
"trace.candidates.disposition",
|
|
38
|
+
"must be eligible or ineligible",
|
|
39
|
+
)
|
|
40
|
+
_strings(self.failed_filters, "trace.candidates.failed_filters", maximum=7)
|
|
41
|
+
if tuple(sorted(self.failed_filters)) != self.failed_filters:
|
|
42
|
+
raise LocalSearchContractError(
|
|
43
|
+
"LOCAL_SEARCH_TRACE_ORDER",
|
|
44
|
+
"trace.candidates.failed_filters",
|
|
45
|
+
"must be sorted in exact text order",
|
|
46
|
+
)
|
|
47
|
+
expected = "ineligible" if self.failed_filters else "eligible"
|
|
48
|
+
if self.disposition != expected:
|
|
49
|
+
raise LocalSearchContractError(
|
|
50
|
+
"LOCAL_SEARCH_TRACE_DISPOSITION",
|
|
51
|
+
"trace.candidates.disposition",
|
|
52
|
+
"must be derived from failed_filters",
|
|
53
|
+
)
|
|
54
|
+
|
|
55
|
+
def to_dict(self) -> dict[str, Any]:
|
|
56
|
+
return {
|
|
57
|
+
"facts_sha256": self.facts_sha256,
|
|
58
|
+
"candidate_sha256": self.candidate_sha256,
|
|
59
|
+
"table_sha256": self.table_sha256,
|
|
60
|
+
"disposition": self.disposition,
|
|
61
|
+
"failed_filters": list(self.failed_filters),
|
|
62
|
+
}
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
@dataclass(frozen=True)
|
|
66
|
+
class PrivateBuildQueryTrace:
|
|
67
|
+
"""Reproducible query evidence made solely from immutable identities."""
|
|
68
|
+
|
|
69
|
+
private_index_manifest_sha256: str
|
|
70
|
+
backend_coordinate: str
|
|
71
|
+
question_sha256: str
|
|
72
|
+
filters_sha256: str
|
|
73
|
+
candidates: tuple[TracedBuildDisposition, ...]
|
|
74
|
+
ordered_candidates: tuple[str, ...]
|
|
75
|
+
selected_facts_sha256: str | None
|
|
76
|
+
schema_version: str = PRIVATE_BUILD_QUERY_TRACE_VERSION
|
|
77
|
+
|
|
78
|
+
def __post_init__(self) -> None:
|
|
79
|
+
if self.schema_version != PRIVATE_BUILD_QUERY_TRACE_VERSION:
|
|
80
|
+
raise LocalSearchContractError(
|
|
81
|
+
"LOCAL_SEARCH_TRACE_VERSION",
|
|
82
|
+
"trace.schema_version",
|
|
83
|
+
f"must equal {PRIVATE_BUILD_QUERY_TRACE_VERSION!r}",
|
|
84
|
+
)
|
|
85
|
+
for name in (
|
|
86
|
+
"private_index_manifest_sha256",
|
|
87
|
+
"question_sha256",
|
|
88
|
+
"filters_sha256",
|
|
89
|
+
):
|
|
90
|
+
_digest(getattr(self, name), f"trace.{name}")
|
|
91
|
+
_coordinate(self.backend_coordinate)
|
|
92
|
+
if not isinstance(self.candidates, tuple) or any(
|
|
93
|
+
not isinstance(item, TracedBuildDisposition) for item in self.candidates
|
|
94
|
+
):
|
|
95
|
+
raise LocalSearchContractError(
|
|
96
|
+
"LOCAL_SEARCH_TRACE_TYPE",
|
|
97
|
+
"trace.candidates",
|
|
98
|
+
"must be an immutable tuple of traced Build dispositions",
|
|
99
|
+
)
|
|
100
|
+
candidate_ids = tuple(item.facts_sha256 for item in self.candidates)
|
|
101
|
+
if candidate_ids != tuple(sorted(candidate_ids)) or len(set(candidate_ids)) != len(
|
|
102
|
+
candidate_ids
|
|
103
|
+
):
|
|
104
|
+
raise LocalSearchContractError(
|
|
105
|
+
"LOCAL_SEARCH_TRACE_ORDER",
|
|
106
|
+
"trace.candidates",
|
|
107
|
+
"must have unique facts identities in exact sorted order",
|
|
108
|
+
)
|
|
109
|
+
_digests(
|
|
110
|
+
self.ordered_candidates,
|
|
111
|
+
"trace.ordered_candidates",
|
|
112
|
+
maximum=MAX_RETRIEVAL_LIMIT,
|
|
113
|
+
)
|
|
114
|
+
if len(set(self.ordered_candidates)) != len(self.ordered_candidates):
|
|
115
|
+
raise LocalSearchContractError(
|
|
116
|
+
"LOCAL_SEARCH_TRACE_DUPLICATE",
|
|
117
|
+
"trace.ordered_candidates",
|
|
118
|
+
"facts identities must be unique",
|
|
119
|
+
)
|
|
120
|
+
eligible = {item.facts_sha256 for item in self.candidates if item.disposition == "eligible"}
|
|
121
|
+
if not set(self.ordered_candidates) <= eligible:
|
|
122
|
+
raise LocalSearchContractError(
|
|
123
|
+
"LOCAL_SEARCH_TRACE_ELIGIBILITY",
|
|
124
|
+
"trace.ordered_candidates",
|
|
125
|
+
"may contain only facts-eligible identities",
|
|
126
|
+
)
|
|
127
|
+
expected_selection = self.ordered_candidates[0] if self.ordered_candidates else None
|
|
128
|
+
if self.selected_facts_sha256 != expected_selection:
|
|
129
|
+
raise LocalSearchContractError(
|
|
130
|
+
"LOCAL_SEARCH_TRACE_SELECTION",
|
|
131
|
+
"trace.selected_facts_sha256",
|
|
132
|
+
"must be the first ordered identity or null for an empty order",
|
|
133
|
+
)
|
|
134
|
+
|
|
135
|
+
@property
|
|
136
|
+
def digest(self) -> str:
|
|
137
|
+
return canonical_sha256(self.to_dict())
|
|
138
|
+
|
|
139
|
+
def to_dict(self) -> dict[str, Any]:
|
|
140
|
+
return {
|
|
141
|
+
"schema_version": self.schema_version,
|
|
142
|
+
"private_index_manifest_sha256": self.private_index_manifest_sha256,
|
|
143
|
+
"backend_coordinate": self.backend_coordinate,
|
|
144
|
+
"question_sha256": self.question_sha256,
|
|
145
|
+
"filters_sha256": self.filters_sha256,
|
|
146
|
+
"candidates": [item.to_dict() for item in self.candidates],
|
|
147
|
+
"ordered_candidates": list(self.ordered_candidates),
|
|
148
|
+
"selected_facts_sha256": self.selected_facts_sha256,
|
|
149
|
+
}
|
|
150
|
+
|
|
151
|
+
|
|
152
|
+
def build_private_query_trace(
|
|
153
|
+
*,
|
|
154
|
+
private_index_manifest_sha256: str,
|
|
155
|
+
entries: tuple[BuildIndexEntry, ...],
|
|
156
|
+
retrieval: BuildRetrieval,
|
|
157
|
+
) -> PrivateBuildQueryTrace:
|
|
158
|
+
"""Bind one private retrieval result to its index and complete fact dispositions."""
|
|
159
|
+
|
|
160
|
+
_digest(private_index_manifest_sha256, "private_index_manifest_sha256")
|
|
161
|
+
if not isinstance(entries, tuple) or any(
|
|
162
|
+
not isinstance(item, BuildIndexEntry) for item in entries
|
|
163
|
+
):
|
|
164
|
+
raise LocalSearchContractError(
|
|
165
|
+
"LOCAL_SEARCH_TRACE_TYPE", "entries", "must be an immutable tuple of Build facts"
|
|
166
|
+
)
|
|
167
|
+
if not isinstance(retrieval, BuildRetrieval):
|
|
168
|
+
raise LocalSearchContractError(
|
|
169
|
+
"LOCAL_SEARCH_TRACE_TYPE", "retrieval", "must be a BuildRetrieval"
|
|
170
|
+
)
|
|
171
|
+
by_identity = {entry.facts_sha256: entry for entry in entries}
|
|
172
|
+
if len(by_identity) != len(entries):
|
|
173
|
+
raise LocalSearchContractError(
|
|
174
|
+
"LOCAL_SEARCH_TRACE_DUPLICATE", "entries", "facts identities must be unique"
|
|
175
|
+
)
|
|
176
|
+
verdict_ids = {item.facts_sha256 for item in retrieval.filter_verdicts}
|
|
177
|
+
if verdict_ids != set(by_identity):
|
|
178
|
+
raise LocalSearchContractError(
|
|
179
|
+
"LOCAL_SEARCH_TRACE_BINDING",
|
|
180
|
+
"retrieval.filter_verdicts",
|
|
181
|
+
"must cover exactly the supplied immutable Build facts",
|
|
182
|
+
)
|
|
183
|
+
for verdict in retrieval.filter_verdicts:
|
|
184
|
+
entry = by_identity[verdict.facts_sha256]
|
|
185
|
+
if verdict.candidate_sha256 != entry.candidate_sha256:
|
|
186
|
+
raise LocalSearchContractError(
|
|
187
|
+
"LOCAL_SEARCH_TRACE_BINDING",
|
|
188
|
+
"retrieval.filter_verdicts",
|
|
189
|
+
"candidate identities must match the supplied immutable Build facts",
|
|
190
|
+
)
|
|
191
|
+
candidates = tuple(
|
|
192
|
+
TracedBuildDisposition(
|
|
193
|
+
facts_sha256=verdict.facts_sha256,
|
|
194
|
+
candidate_sha256=by_identity[verdict.facts_sha256].candidate_sha256,
|
|
195
|
+
table_sha256=by_identity[verdict.facts_sha256].table_sha256,
|
|
196
|
+
disposition=verdict.disposition,
|
|
197
|
+
failed_filters=tuple(
|
|
198
|
+
sorted(check.filter_name for check in verdict.checks if check.outcome == "fail")
|
|
199
|
+
),
|
|
200
|
+
)
|
|
201
|
+
for verdict in retrieval.filter_verdicts
|
|
202
|
+
)
|
|
203
|
+
return PrivateBuildQueryTrace(
|
|
204
|
+
private_index_manifest_sha256=private_index_manifest_sha256,
|
|
205
|
+
backend_coordinate=retrieval.backend_coordinate,
|
|
206
|
+
question_sha256=retrieval.question_sha256,
|
|
207
|
+
filters_sha256=retrieval.filters_sha256,
|
|
208
|
+
candidates=candidates,
|
|
209
|
+
ordered_candidates=retrieval.ordered_facts_sha256,
|
|
210
|
+
selected_facts_sha256=(
|
|
211
|
+
retrieval.ordered_facts_sha256[0] if retrieval.ordered_facts_sha256 else None
|
|
212
|
+
),
|
|
213
|
+
)
|
|
214
|
+
|
|
215
|
+
|
|
216
|
+
def _digest(value: Any, path: str) -> None:
|
|
217
|
+
if (
|
|
218
|
+
not isinstance(value, str)
|
|
219
|
+
or len(value) != 64
|
|
220
|
+
or any(character not in "0123456789abcdef" for character in value)
|
|
221
|
+
):
|
|
222
|
+
raise LocalSearchContractError(
|
|
223
|
+
"LOCAL_SEARCH_TRACE_DIGEST", path, "must be a lowercase SHA-256"
|
|
224
|
+
)
|
|
225
|
+
|
|
226
|
+
|
|
227
|
+
def _digests(value: Any, path: str, *, maximum: int) -> None:
|
|
228
|
+
if not isinstance(value, tuple) or len(value) > maximum:
|
|
229
|
+
raise LocalSearchContractError(
|
|
230
|
+
"LOCAL_SEARCH_TRACE_TYPE", path, f"must be a tuple of at most {maximum} digests"
|
|
231
|
+
)
|
|
232
|
+
for index, digest in enumerate(value):
|
|
233
|
+
_digest(digest, f"{path}[{index}]")
|
|
234
|
+
|
|
235
|
+
|
|
236
|
+
def _strings(value: Any, path: str, *, maximum: int) -> None:
|
|
237
|
+
if not isinstance(value, tuple) or len(value) > maximum:
|
|
238
|
+
raise LocalSearchContractError(
|
|
239
|
+
"LOCAL_SEARCH_TRACE_TYPE", path, f"must be a tuple of at most {maximum} strings"
|
|
240
|
+
)
|
|
241
|
+
if any(not isinstance(item, str) or not item or len(item) > 64 for item in value):
|
|
242
|
+
raise LocalSearchContractError(
|
|
243
|
+
"LOCAL_SEARCH_TRACE_TYPE", path, "items must be bounded non-empty strings"
|
|
244
|
+
)
|
|
245
|
+
|
|
246
|
+
|
|
247
|
+
def _coordinate(value: Any) -> None:
|
|
248
|
+
if (
|
|
249
|
+
not isinstance(value, str)
|
|
250
|
+
or not 1 <= len(value) <= 1_024
|
|
251
|
+
or "@" not in value
|
|
252
|
+
or any(ord(character) < 32 or character in "\x7f\u0085\u2028\u2029" for character in value)
|
|
253
|
+
):
|
|
254
|
+
raise LocalSearchContractError(
|
|
255
|
+
"LOCAL_SEARCH_TRACE_BACKEND",
|
|
256
|
+
"trace.backend_coordinate",
|
|
257
|
+
"must be the bounded exact one-line backend coordinate",
|
|
258
|
+
)
|
|
259
|
+
|
|
260
|
+
|
|
261
|
+
__all__ = [
|
|
262
|
+
"PRIVATE_BUILD_QUERY_TRACE_VERSION",
|
|
263
|
+
"PrivateBuildQueryTrace",
|
|
264
|
+
"TracedBuildDisposition",
|
|
265
|
+
"build_private_query_trace",
|
|
266
|
+
]
|