"""The upload split into the run context and its listed files, as parse_assessment_files renders them (ADR 0018).""" import io import sys from pathlib import Path import pandas as pd import pytest ROOT = Path(__file__).resolve().parents[1] sys.path.insert(0, str(ROOT)) from app import run_context as rc # noqa: E402 CASE = ROOT.parent / "workflows" / "cases" / "azure-crucible-kab-dev-cmdb" SEP = "\n\n---\n\n" def rendered_csv(path): return pd.read_csv(path).to_string() # what data_file_processing.parse_csv hands on def rendered_xlsx(frames): buffer = io.BytesIO() with pd.ExcelWriter(buffer) as writer: for name, frame in frames.items(): frame.to_excel(writer, sheet_name=name, index=False) parts = [] for name, frame in pd.read_excel(io.BytesIO(buffer.getvalue()), sheet_name=None).items(): parts += [f"=== Sheet: {name} ===", frame.to_string(), ""] return "\n".join(parts) # data_file_processing.parse_excel def upload(*files): return SEP.join(files) FULL_CONTEXT = (CASE / "context.yaml").read_text() # The case lists a CI export and a relationship export; most tests here need a context with one listed upload. CONTEXT = FULL_CONTEXT.replace(""" - name: cmdb-relationships.csv source: cmdb_relationships format: servicenow_cmdb_rel_ci_csv taken: 2026-11-04 """, "") assert CONTEXT != FULL_CONTEXT def test_a_context_alone_reads_as_before(): single = (ROOT.parent / "workflows" / "cases" / "azure-crucible-kab-dev" / "context.yaml").read_text() out = rc.split(single) assert out["context"]["workflow_inputs"]["provider"] == "azure" and out["uploads"] == [] assert rc.context_section(single)["sources"]["cmdb"] == "not available" def test_a_csv_after_the_context_leaves_the_context_readable(): text = upload(CONTEXT, rendered_csv(CASE / "cmdb-export.csv")) out = rc.split(text) assert out["context"]["plan"]["name"].endswith("with CMDB") [cmdb] = rc.uploads_from(text, "cmdb") [table] = rc.tables(cmdb) assert table["sheet"] is None and "object_id" in table["header"] and len(table["rows"]) == 12 assert table["rows"][0][0] == 0 and "CI0010001" in table["rows"][0][1] assert table["rows"][11][0] == 11 and "Retired" in table["rows"][11][1] def test_two_files_in_order_and_an_xlsx_has_one_table_per_sheet(): ctx = CONTEXT.replace("uploads:\n", "uploads:\n - {name: assets.xlsx, source: cmdb}\n") sheets = rendered_xlsx({"Servers": pd.DataFrame({"Name": ["a", "b"], "Env": ["prod", "dev"]}), "Cloud": pd.DataFrame({"Id": ["/subscriptions/s/x"], "Env": ["dev"]})}) text = upload(ctx, sheets, rendered_csv(CASE / "cmdb-export.csv")) names = [u["name"] for u in rc.uploads_from(text, "cmdb")] assert names == ["assets.xlsx", "cmdb-export.csv"] tables = rc.tables(rc.uploads_from(text, "cmdb")[0]) assert [(t["sheet"], len(t["rows"])) for t in tables] == [("Servers", 2), ("Cloud", 1)] assert "Env" in tables[1]["header"] def test_a_separator_inside_the_last_upload_is_kept(): text = upload(CONTEXT, "h\n0 a" + SEP + "1 b") assert rc.split(text)["uploads"][0]["text"] == "h\n0 a" + SEP + "1 b" def test_a_listed_upload_that_never_arrived_is_unreadable(): [cmdb] = rc.uploads_from(CONTEXT, "cmdb") assert cmdb["text"] is None with pytest.raises(rc.UploadUnreadable, match="not uploaded"): rc.tables(cmdb) def test_a_platform_parse_error_is_unreadable(): [cmdb] = rc.uploads_from(upload(CONTEXT, "CSV parsing error: bad line 3"), "cmdb") with pytest.raises(rc.UploadUnreadable, match="could not parse"): rc.tables(cmdb) def test_an_empty_export_has_no_rows(): [cmdb] = rc.uploads_from(upload(CONTEXT, pd.DataFrame(columns=["a", "b"]).to_string()), "cmdb") assert rc.tables(cmdb)[0]["rows"] == [] def test_a_raw_csv_is_numbered_by_position(): [cmdb] = rc.uploads_from(upload(CONTEXT, "id,name\n123,a\n456,b"), "cmdb") assert rc.tables(cmdb)[0]["rows"] == [(0, "123,a"), (1, "456,b")] def test_a_text_brief_is_not_a_context(): assert rc.split("Meridian brief\n\nSome text.")["context"] == {} def test_the_case_lists_two_cmdb_uploads_in_order(): rels = " sys_id parent child\n0 R1 CI1 CI2" text = upload(FULL_CONTEXT, rendered_csv(CASE / "cmdb-export.csv"), rels) assert [u["name"] for u in rc.split(text)["uploads"]] == ["cmdb-export.csv", "cmdb-relationships.csv"] [rel] = rc.uploads_from(text, "cmdb_relationships") assert rc.tables(rel)[0]["rows"] == [(0, "0 R1 CI1 CI2")]