Add ERP enrichment dry run

2026-07-29 14:32:15 +02:00
parent d92dc61277
commit caf36a76cb
9 changed files with 930 additions and 1 deletions
@@ -0,0 +1,77 @@
+import csv
+import json
+from pathlib import Path
+
+from article_data_manager.enrichment.erp import (
+    enrich_rollcalc_articles_from_erp,
+    write_enrichment_outputs,
+)
+
+
+def test_enrichment_dry_run_writes_json_and_csv_outputs(tmp_path: Path) -> None:
+    rollcalc_path = tmp_path / "article-data.json"
+    erp_path = tmp_path / "erp.csv"
+    json_path = tmp_path / "generated" / "article-data.erp-enriched-dry-run.json"
+    report_path = tmp_path / "reports" / "erp-enrichment-report.csv"
+
+    rollcalc_path.write_text(
+        json.dumps(
+            [
+                {
+                    "nr": "214700",
+                    "name": "RollCalc A",
+                    "thickness": 6.722,
+                    "area_weight": 750.0,
+                    "core_type": 0.0,
+                },
+                {
+                    "nr": "999999",
+                    "name": "RollCalc Only",
+                    "thickness": 1.0,
+                    "area_weight": 0.0,
+                    "core_type": 0.0,
+                },
+            ],
+            ensure_ascii=False,
+            indent=2,
+        )
+        + "\n",
+        encoding="utf-8",
+    )
+    erp_path.write_text(
+        "\n".join(
+            [
+                "SL_ITEM_NO,ROP_PRODUCT_WIDTH,ROP_RATE_OF_PRODUCTION,"
+                "SL_MINIMUM_PRODUCTION_QUANTITY,WPL_WORKPLACE_TEXT,kg_qm,SL_PRODUCTION_SPEED",
+                "214700,\"6,00\",\"18,5\",5000,Anlage 3,999,999",
+                "ERPONLY,9.99,1.0,1,Anlage X,1,1",
+            ]
+        ),
+        encoding="utf-8",
+    )
+
+    result = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path)
+    write_enrichment_outputs(result, json_path, report_path)
+
+    output_articles = json.loads(json_path.read_text(encoding="utf-8"))
+    assert [article["nr"] for article in output_articles] == ["214700", "999999"]
+    assert output_articles[0]["area_weight"] == 750.0
+    assert output_articles[0]["erp"] == {
+        "product_width_m": 6.0,
+        "line_speed_m_min": 18.5,
+        "minimum_production_quantity": 5000.0,
+        "workplace": "Anlage 3",
+    }
+    assert output_articles[1]["erp"] == {
+        "product_width_m": None,
+        "line_speed_m_min": None,
+        "minimum_production_quantity": None,
+        "workplace": None,
+    }
+
+    with report_path.open("r", encoding="utf-8-sig", newline="") as report_file:
+        rows = list(csv.DictReader(report_file, delimiter=";"))
+
+    assert [row["nr"] for row in rows] == ["214700", "999999"]
+    assert rows[0]["status"] == "complete"
+    assert rows[1]["status"] == "no_erp_match"
@@ -0,0 +1,387 @@
+import csv
+import json
+from pathlib import Path
+
+from article_data_manager.enrichment.erp import (
+    enrich_rollcalc_articles_from_erp,
+    write_enrichment_outputs,
+)
+
+
+def write_rollcalc(path: Path, article_numbers: list[str]) -> Path:
+    payload = [
+        {
+            "nr": nr,
+            "name": f"RollCalc {nr}",
+            "thickness": float(index + 1),
+            "area_weight": 100.0 + index,
+            "core_type": 0.0,
+        }
+        for index, nr in enumerate(article_numbers)
+    ]
+    path.write_text(json.dumps(payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    return path
+
+
+def write_erp(path: Path, rows: list[dict[str, str]]) -> Path:
+    fieldnames = [
+        "SL_ITEM_NO",
+        "ROP_PRODUCT_WIDTH",
+        "ROP_RATE_OF_PRODUCTION",
+        "SL_MINIMUM_PRODUCTION_QUANTITY",
+        "WPL_WORKPLACE_TEXT",
+        "SL_PRODUCTION_SPEED",
+        "kg_qm",
+    ]
+    with path.open("w", encoding="utf-8", newline="") as csv_file:
+        writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
+        writer.writeheader()
+        for row in rows:
+            writer.writerow({field: row.get(field, "") for field in fieldnames})
+    return path
+
+
+def test_unique_erp_match_enriches_selected_fields(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {
+                "SL_ITEM_NO": "214700",
+                "ROP_PRODUCT_WIDTH": "6,00",
+                "ROP_RATE_OF_PRODUCTION": "18.5",
+                "SL_MINIMUM_PRODUCTION_QUANTITY": "5000",
+                "WPL_WORKPLACE_TEXT": "Anlage 3",
+            }
+        ],
+    )
+
+    article = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0]
+
+    assert article.status == "complete"
+    assert article.to_output_dict()["erp"] == {
+        "product_width_m": 6.0,
+        "line_speed_m_min": 18.5,
+        "minimum_production_quantity": 5000.0,
+        "workplace": "Anlage 3",
+    }
+
+
+def test_no_erp_match_keeps_rollcalc_article_with_null_erp_object(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["999999"])
+    erp_path = write_erp(tmp_path / "erp.csv", [{"SL_ITEM_NO": "214700"}])
+
+    article = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0]
+
+    assert article.status == "no_erp_match"
+    assert article.erp_match_count == 0
+    assert article.to_output_dict()["erp"] == {
+        "product_width_m": None,
+        "line_speed_m_min": None,
+        "minimum_production_quantity": None,
+        "workplace": None,
+    }
+    assert {field.status for field in article.fields.values()} == {"no_erp_match"}
+
+
+def test_multiple_erp_rows_with_identical_width_are_collapsed(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": "6,00"},
+            {"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": "6.00"},
+        ],
+    )
+
+    field = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0].fields[
+        "product_width_m"
+    ]
+
+    assert field.value == 6.0
+    assert field.status == "same_value_multiple_rows"
+
+
+def test_conflicting_width_is_reported_as_null_field(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": "6,00"},
+            {"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": "6.10"},
+        ],
+    )
+
+    article = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0]
+
+    assert article.status == "conflict"
+    assert article.fields["product_width_m"].value is None
+    assert article.fields["product_width_m"].status == "conflict"
+
+
+def test_identical_line_speeds_in_multiple_rows_are_collapsed(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "ROP_RATE_OF_PRODUCTION": "18,5"},
+            {"SL_ITEM_NO": "214700", "ROP_RATE_OF_PRODUCTION": "18.50"},
+        ],
+    )
+
+    field = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0].fields[
+        "line_speed_m_min"
+    ]
+
+    assert field.value == 18.5
+    assert field.status == "same_value_multiple_rows"
+
+
+def test_conflicting_line_speeds_are_reported(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "ROP_RATE_OF_PRODUCTION": "18,5"},
+            {"SL_ITEM_NO": "214700", "ROP_RATE_OF_PRODUCTION": "19,0"},
+        ],
+    )
+
+    article = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0]
+
+    assert article.status == "conflict"
+    assert article.fields["line_speed_m_min"].status == "conflict"
+
+
+def test_missing_minimum_production_quantity_is_reported(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(tmp_path / "erp.csv", [{"SL_ITEM_NO": "214700"}])
+
+    field = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0].fields[
+        "minimum_production_quantity"
+    ]
+
+    assert field.value is None
+    assert field.status == "missing"
+
+
+def test_identical_workplaces_in_multiple_rows_are_collapsed(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "WPL_WORKPLACE_TEXT": "Anlage 3"},
+            {"SL_ITEM_NO": "214700", "WPL_WORKPLACE_TEXT": "Anlage 3"},
+        ],
+    )
+
+    field = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0].fields[
+        "workplace"
+    ]
+
+    assert field.value == "Anlage 3"
+    assert field.status == "same_value_multiple_rows"
+
+
+def test_different_workplaces_are_reported_as_conflict(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "WPL_WORKPLACE_TEXT": "Anlage 3"},
+            {"SL_ITEM_NO": "214700", "WPL_WORKPLACE_TEXT": "Anlage 4"},
+        ],
+    )
+
+    field = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0].fields[
+        "workplace"
+    ]
+
+    assert field.value is None
+    assert field.status == "conflict"
+
+
+def test_decimal_values_with_comma_and_point_are_supported(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700", "000123"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": "6,00"},
+            {"SL_ITEM_NO": "000123", "ROP_PRODUCT_WIDTH": "1.20"},
+        ],
+    )
+
+    articles = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles
+
+    assert articles[0].fields["product_width_m"].value == 6.0
+    assert articles[1].fields["product_width_m"].value == 1.2
+
+
+def test_invalid_numeric_value_sets_field_to_null(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [{"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": "not-a-number"}],
+    )
+
+    article = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0]
+
+    assert article.status == "conflict"
+    assert article.fields["product_width_m"].value is None
+    assert article.fields["product_width_m"].status == "invalid"
+
+
+def test_empty_erp_fields_do_not_create_conflicts(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": ""},
+            {"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": "6.00"},
+        ],
+    )
+
+    field = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0].fields[
+        "product_width_m"
+    ]
+
+    assert field.value == 6.0
+    assert field.status == "unique"
+
+
+def test_leading_zero_article_number_matches_exactly(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["000123"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [{"SL_ITEM_NO": "000123", "ROP_PRODUCT_WIDTH": "1.20"}],
+    )
+
+    article = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0]
+
+    assert article.nr == "000123"
+    assert article.fields["product_width_m"].value == 1.2
+
+
+def test_erp_article_without_rollcalc_match_is_not_output(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "214700", "ROP_PRODUCT_WIDTH": "6.00"},
+            {"SL_ITEM_NO": "ERPONLY", "ROP_PRODUCT_WIDTH": "9.99"},
+        ],
+    )
+
+    result = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path)
+
+    assert [article.nr for article in result.articles] == ["214700"]
+
+
+def test_rollcalc_order_is_preserved(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["300", "100", "200"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {"SL_ITEM_NO": "100"},
+            {"SL_ITEM_NO": "200"},
+            {"SL_ITEM_NO": "300"},
+        ],
+    )
+
+    result = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path)
+
+    assert [article.nr for article in result.articles] == ["300", "100", "200"]
+
+
+def test_existing_area_weight_remains_unchanged_and_erp_weight_fields_are_ignored(
+    tmp_path: Path,
+) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {
+                "SL_ITEM_NO": "214700",
+                "kg_qm": "999",
+                "SL_PRODUCTION_SPEED": "999",
+                "ROP_PRODUCT_WIDTH": "6.00",
+            }
+        ],
+    )
+
+    output = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).articles[0].to_output_dict()
+
+    assert output["area_weight"] == 100.0
+    assert "kg_qm" not in output["erp"]
+    assert "SL_PRODUCTION_SPEED" not in output["erp"]
+
+
+def test_source_files_remain_unchanged(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(tmp_path / "erp.csv", [{"SL_ITEM_NO": "214700"}])
+    original_rollcalc = rollcalc_path.read_bytes()
+    original_erp = erp_path.read_bytes()
+
+    result = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path)
+    write_enrichment_outputs(result, tmp_path / "generated.json", tmp_path / "report.csv")
+
+    assert rollcalc_path.read_bytes() == original_rollcalc
+    assert erp_path.read_bytes() == original_erp
+
+
+def test_json_output_is_deterministic(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(tmp_path / "erp.csv", [{"SL_ITEM_NO": "214700"}])
+    result = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path)
+    first_json = tmp_path / "first.json"
+    second_json = tmp_path / "second.json"
+
+    write_enrichment_outputs(result, first_json, tmp_path / "first.csv")
+    write_enrichment_outputs(result, second_json, tmp_path / "second.csv")
+
+    assert first_json.read_text(encoding="utf-8") == second_json.read_text(encoding="utf-8")
+
+
+def test_csv_report_is_deterministic_and_contains_statuses(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["214700"])
+    erp_path = write_erp(tmp_path / "erp.csv", [{"SL_ITEM_NO": "214700"}])
+    result = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path)
+    first_report = tmp_path / "first.csv"
+    second_report = tmp_path / "second.csv"
+
+    write_enrichment_outputs(result, tmp_path / "first.json", first_report)
+    write_enrichment_outputs(result, tmp_path / "second.json", second_report)
+
+    first_content = first_report.read_text(encoding="utf-8-sig")
+    assert first_content == second_report.read_text(encoding="utf-8-sig")
+    assert "nr;name;erp_match_count;status" in first_content
+    assert "missing" in first_content
+
+
+def test_summary_counts_articles_and_field_statuses(tmp_path: Path) -> None:
+    rollcalc_path = write_rollcalc(tmp_path / "article-data.json", ["A", "B", "C"])
+    erp_path = write_erp(
+        tmp_path / "erp.csv",
+        [
+            {
+                "SL_ITEM_NO": "A",
+                "ROP_PRODUCT_WIDTH": "1.0",
+                "ROP_RATE_OF_PRODUCTION": "2.0",
+                "SL_MINIMUM_PRODUCTION_QUANTITY": "3",
+                "WPL_WORKPLACE_TEXT": "Anlage",
+            },
+            {"SL_ITEM_NO": "B", "ROP_PRODUCT_WIDTH": "bad"},
+        ],
+    )
+
+    summary = enrich_rollcalc_articles_from_erp(rollcalc_path, erp_path).summary
+
+    assert summary.rollcalc_article_count == 3
+    assert summary.with_erp_match_count == 2
+    assert summary.without_erp_match_count == 1
+    assert summary.complete_count == 1
+    assert summary.partial_count == 0
+    assert summary.conflict_count == 1
+    assert summary.field_summaries["product_width_m"].unique == 1
+    assert summary.field_summaries["product_width_m"].invalid == 1
+    assert summary.field_summaries["product_width_m"].no_erp_match == 1