79 lines
4.6 KiB
Python
79 lines
4.6 KiB
Python
|
"""Same read-only query/alignment contract for mock data and approved SQL sources."""
|
||
|
|
from copy import deepcopy
|
||
|
|
from decimal import Decimal
|
||
|
|
from api import risk_agent_config as catalog
|
||
|
|
from services.assistant_store import uid, digest
|
||
|
|
from services.assistant_materials import NUMERIC, scalar
|
||
|
|
from services.skill_executor import number
|
||
|
|
from api.risk_agent_alignment import MONEY_FIELDS, SCALE
|
||
|
|
|
||
|
|
|
||
|
|
def load_catalog():
|
||
|
|
with catalog._db() as db:
|
||
|
|
return {kind: catalog._all(db, kind) for kind in catalog.SEED}
|
||
|
|
|
||
|
|
|
||
|
|
def read_cards(project, components):
|
||
|
|
values, sources = deepcopy(project["values"]), {}
|
||
|
|
for field, refs in project["sources"].items():
|
||
|
|
sources[field] = [r for r in refs if r["id"] == project["selected_sources"].get(field)]
|
||
|
|
datasets, errors = [], []
|
||
|
|
if project.get("pending_candidates"):
|
||
|
|
errors.append({"card_id": "materials", "message": "存在尚未人工确认的材料候选，本次仍使用已确认事实"})
|
||
|
|
samples = {}
|
||
|
|
for (table, rows), mapping in zip(catalog.SAMPLES.items(), catalog.MAPPINGS):
|
||
|
|
row = {key: None for key in rows[0]}
|
||
|
|
row["project_id"] = project["id"]
|
||
|
|
for field, column in mapping.items():
|
||
|
|
row[column] = values.get(field)
|
||
|
|
row.update(project_id=project["id"])
|
||
|
|
if table == "project":
|
||
|
|
row["customer_name"] = project["customer"]
|
||
|
|
if table == "finance":
|
||
|
|
row.update(period=project.get("period", "2025"), scope=project.get("scope", "合并"))
|
||
|
|
samples[table] = [row]
|
||
|
|
for card in components.get("legacy_cards", []):
|
||
|
|
connection = next(c for c in components["legacy_connections"] if c["id"] == card["connection"])
|
||
|
|
if connection.get("data_domain", "demo" if connection.get("type") == "demo" else "production") != project["data_domain"]:
|
||
|
|
raise ValueError("演示数据与正式数据源不可混用")
|
||
|
|
try:
|
||
|
|
rows = catalog.query_card(card, connection, project["id"], demo_samples=samples, exact_decimals=True)
|
||
|
|
records, selected = catalog.align(card, rows, project["id"], project.get("period", "2025"))
|
||
|
|
datasets.append({"card_id": card["id"], "name": card["name"], "version": card["version"], "records": records, "row_hash": digest(rows)})
|
||
|
|
if selected is None:
|
||
|
|
errors.append({"card_id": card["id"], "message": "多期或多口径记录未选择，未合并计算"})
|
||
|
|
continue
|
||
|
|
for field, column in card.get("mapping", {}).items():
|
||
|
|
raw = selected["values"].get(field)
|
||
|
|
if field in NUMERIC:
|
||
|
|
raw = selected["raw"].get(column)
|
||
|
|
unit = card.get("field_units", {}).get(field, card.get("unit") if field in MONEY_FIELDS else None)
|
||
|
|
if raw is not None and unit:
|
||
|
|
raw = number(raw) * SCALE[unit]
|
||
|
|
raw = scalar(field, raw)
|
||
|
|
# Mock SQL uses the actual parsed fixture values; retain their file locators.
|
||
|
|
if connection.get("type") == "demo" and field in sources:
|
||
|
|
same = values.get(field) == raw
|
||
|
|
if field in NUMERIC and values.get(field) is not None and raw is not None:
|
||
|
|
same = number(values[field]) == number(raw)
|
||
|
|
if not same:
|
||
|
|
values[field] = None
|
||
|
|
errors.append({"card_id": card["id"], "message": field + "映射结果与原始材料冲突"})
|
||
|
|
continue
|
||
|
|
ref = {"id": uid("ev"), "project_id": project["id"], "field": field, "value": raw,
|
||
|
|
"source": card["name"], "locator": "数据卡字段 " + column, "card_id": card["id"], "version": card["version"],
|
||
|
|
"period": selected["period"], "scope": selected["scope"], "unit": selected["units"].get(field), "currency": card.get("currency", "CNY")}
|
||
|
|
same = values.get(field) == raw
|
||
|
|
if field in NUMERIC and values.get(field) is not None and raw is not None:
|
||
|
|
same = number(values[field]) == number(raw)
|
||
|
|
if field in values and not same:
|
||
|
|
values[field] = None
|
||
|
|
errors.append({"card_id": card["id"], "message": field + "多来源冲突，请人工确认"})
|
||
|
|
else:
|
||
|
|
values[field] = raw
|
||
|
|
sources.setdefault(field, []).append(ref)
|
||
|
|
except Exception as exc:
|
||
|
|
# No connection strings/credentials in project-facing diagnostics.
|
||
|
|
errors.append({"card_id": card["id"], "message": "数据卡读取或口径校验失败", "error_type": type(exc).__name__})
|
||
|
|
return values, sources, datasets, errors
|