{"api_version":2,"name":"piflow_person_id_expansion","version":"1.0","role":"transform","type":"sdk","description":"Split a document type and number pair into the corresponding identity field and append deterministic source identifiers.","icon":{"path":"M3 5h18v14H3zM3 10h18M9 5v14"},"inputs":{"source":{"representations":["records"],"formats":[]}},"outputs":{"result":{"view":"records"}},"parameters":{"type":"object","properties":{"expandIDField":{"type":"string","description":"Field containing the document number."},"expandIDType":{"type":"string","description":"Field holding the document type code, from 0 through 6."},"sourceLabel":{"type":"string","description":"Origin label used for the source column and deterministic UUID."}},"required":["expandIDField","expandIDType","sourceLabel"],"additionalProperties":false},"documentation":{"inputs":{"source":"Arrow records. The example uses id_type, code, label."},"outputs":{"result":"Records stream. Split a document type and number pair into the corresponding identity field and append deterministic source identifiers."},"parameters":{"expandIDField":{"description":"Field containing the document number.","help":"Field containing the document number.","example":"code"},"expandIDType":{"description":"Field holding the document type code, from 0 through 6.","help":"Field holding the document type code, from 0 through 6.","example":"id_type"},"sourceLabel":{"description":"Origin label used for the source column and deterministic UUID.","help":"Origin label used for the source column and deterministic UUID.","example":"fixture"}},"example_job":"name: Expand typed document columns\nsteps:\n- id: read_source\n  operator: item_source@1.0\n  inputs: {}\n  params:\n    uri: context:/piflow/source.jsonl\n    view: records\n- id: process\n  operator: piflow_person_id_expansion@1.0\n  inputs:\n    source: read_source\n  params:\n    expandIDField: code\n    expandIDType: id_type\n    sourceLabel: fixture\n- id: receive_result\n  operator: client_sink@1.0\n  inputs:\n    result: process\n"},"runtime":{"image":"sha256:40db7fee594f1452790d1cc99c2e5429e187eb64633c716b8c6f903c47576975","archive":{"sha256":"e1844833e35390f2eaf9fc9ec7b67057ad0305ad713c0da6c8b055980a66946c","size":73825792,"filename":"python-arrow-2.0-runtime.tar"}},"execution":{"executor":"python","entrypoint":"xstream_piflow_person_id_expansion","config":{}},"source_public":true,"provenance":{"license":"Apache-2.0","source_repository":"https://github.com/cas-bigdatalab/piflow","source_revision":"f9bb5542e253fddea75a338a8dd476270f86ce59","build_instructions":"Build the Python SDK adapter in src/ with python-arrow@2.0. See job.yaml for an example using the supplied fixtures.","source_archive":{"sha256":"620a51a3047068519f577555f7e45cec7e9fc02062d89c96087da6f67f417c5c","size":19946,"filename":"piflow_person_id_expansion-sources.zip"},"license_file":{"sha256":"c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4","size":11357,"filename":"LICENSE.txt"}},"artifact":{"sha256":"3e932ccb603a5e4b4bd70ea2460995b9dc84a4dd850efd89b6fd162af633de18","size":30987,"filename":"operator.zip"},"categories":["PiFlow","Data cleaning"],"trust":{"score":4,"assessed_by":"administrator","reviewed_at_ms":1795080182028},"publication":{"author":"dacp-examples","submitted_at_ms":1795080161046,"approved_at_ms":1795080182028,"last_submitted_at_ms":1795080161046,"last_approved_at_ms":1795080182028},"download_count":4}