Files
AgentLab/backend/tests/fixtures/acceptance/multi_source_ontology.py
T
ThearchyHelios 8d9a712eae 业务本体与标准实体:跨源键值对齐、对账共变算子、健康证据链与实体助手
- 新增标准业务实体(CanonicalEntity)模型、确定性跨源编码翻译、后台候选实体扫描与文档驱动实体智能助手
- 新增指标本体图谱(factor / reconciles_with / upstream_driver)、DAG 防环校验以及 ontology_neighbors / source_health 内置工具
- 新增跨源对账(analysis_reconcile)与滞后共变(analysis_cochange)分析算子,打通 [[h:H1]] 数据源健康证据链、报告导出与本体消融评测
- 数据目录新增「标准业务实体」视图与候选审阅工作台,口径页集成指标本体拓扑面板与端到端浏览器检查
2026-11-12 12:57:53 +08:00

694 lines
32 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""跨源指标本体穿透验收与回归评测用的三源虚构制造库(与任何真实业务无关)。
python -m tests.fixtures.acceptance.multi_source_ontology <输出目录> [--today YYYY-MM-DD]
生成「今天」之前 24 天(截止昨天)的三份独立 SQLite 业务库,随机数种子固定:同一个「今天」生成的三份库逐字节一致。
三个数据源使用异构物理列名与编码格式,只能经标准实体 `production_line`(产线)对齐:
1. `ops_shift`(班次报工库):
- `shift_output(id, shift_date, line_code, actual_qty, good_qty, scrap_qty, run_hours, operator_phone)`
其中 `line_code` 取值 `L1..L4`,`operator_phone` 为遮罩敏感列。
- `energy_readings(id, shift_date, line_code, meter_kwh, settled_mwh)`
用于核对跨量纲换算(千瓦时 vs 兆瓦时,`unit_factor = 1000`)的对账场景。
2. `equip_master`(设备与停机主数据库):
- `line_specs(equip_line_id, line_name, rated_hourly_qty, updated_day)`
其中 `equip_line_id` 取值 `EQ-L1..EQ-L4`。
- `downtime_events(id, event_date, equip_line_id, net_run_ratio, unplanned_min, fault_category)`
记录各设备产线每日有效运转率与非计划停机分钟数。
3. `quality_scrap`(质量报废台账库):
- `scrap_ledger(id, inspect_date, workcenter_code, scrap_units, defect_family, inspector_id)`
其中 `workcenter_code` 取值 `WC-01..WC-04`,`inspector_id` 为遮罩敏感列。
埋入的确定性效应(互不干扰):
- **S1(契约越界 → 跨库主数据过期失配)**:`ops_shift` 中 `L3` 昨日实际每小时产量 `108` 件(8 小时产 864 件),但 `equip_master.line_specs`
中 `EQ-L3` 的 `rated_hourly_qty` 仍停留在旧版 `80` 件/小时,导致负荷率算得 `135%`(违反 `[0, 100]` 契约上界)。
- **S2a(跨源对账断更 → 对侧源停更早停)**:`quality_scrap.scrap_ledger` 截止于「今天 - 3 天」(最近两天断更,0 行),而 `ops_shift`
照常落库;健康检查应识别 `date_stalled` 并在阶段一停止,不误判为业务报废清零。
- **S2b(跨源量纲与超差对账)**:`ops_shift.energy_readings` 昨日 `L1..L3` 按 `1000 kWh = 1 MWh` 完全对齐,`L4` 抄表 `14800 kWh`
但结算导入记为 `12.5 MWh`(换算后相差 `+2300 kWh`,`+18.4%`),`reconcile` 应判 `diverged`。
- **S3(统计异动 → 切片定位 `L2` → 跨源设备停机同步异动 `EQ-L2`)**:昨日 `L2` 合格产量从常态约 `900` 跌至 `612`(`-32%`),
穿透标准实体 `L2 -> EQ-L2` 后,`equip_master.downtime_events` 中 `EQ-L2` 非计划停机从常态 `11..14` 分钟飙升至 `96` 分钟,
`cochange` 判 `co_anomalous`(仅陈述同期同步异动,不下因果断言)。
- **对照 1(常规波动不误报)**:`L1` 过去 24 天合格产量在 `892..916` 窄幅波动,昨日 `898` 相对前日 `908` 属常规波动(`within_band`)。
- **对照 2(主指标异动但上游正常 → `target_normal`)**:`今天 - 3 天` 时 `EQ-L4` 有效运转率从 `0.90` 跌至 `0.73`,但同期非计划停机
仍为常态 `12` 分钟,`cochange` 判 `target_normal`,不强行归咎于设备非计划停机。
"""
from __future__ import annotations
import argparse
import random
import sqlite3
from dataclasses import dataclass
from datetime import date, timedelta
from pathlib import Path
from typing import Any
DAYS = 24
SEED = 20261022
SOURCE_OPS = "ops_shift"
SOURCE_EQUIP = "equip_master"
SOURCE_QUALITY = "quality_scrap"
ALL_SOURCES = (SOURCE_OPS, SOURCE_EQUIP, SOURCE_QUALITY)
LINES: tuple[tuple[str, str, str, str], ...] = (
("L1", "EQ-L1", "WC-01", "星梭一线"),
("L2", "EQ-L2", "WC-02", "星梭二线"),
("L3", "EQ-L3", "WC-03", "星梭三线"),
("L4", "EQ-L4", "WC-04", "星梭四线"),
)
OPS_SCHEMA = """
CREATE TABLE shift_output (
id INTEGER PRIMARY KEY,
shift_date DATE NOT NULL,
line_code TEXT NOT NULL,
actual_qty INTEGER NOT NULL,
good_qty INTEGER NOT NULL,
scrap_qty INTEGER NOT NULL,
run_hours REAL NOT NULL,
operator_phone TEXT NOT NULL
);
CREATE TABLE energy_readings (
id INTEGER PRIMARY KEY,
shift_date DATE NOT NULL,
line_code TEXT NOT NULL,
meter_kwh REAL NOT NULL,
settled_mwh REAL NOT NULL
);
"""
EQUIP_SCHEMA = """
CREATE TABLE line_specs (
equip_line_id TEXT PRIMARY KEY,
line_name TEXT NOT NULL,
rated_hourly_qty REAL NOT NULL,
updated_day DATE NOT NULL
);
CREATE TABLE downtime_events (
id INTEGER PRIMARY KEY,
event_date DATE NOT NULL,
equip_line_id TEXT NOT NULL,
net_run_ratio REAL NOT NULL,
unplanned_min REAL NOT NULL,
fault_category TEXT NOT NULL
);
"""
QUALITY_SCHEMA = """
CREATE TABLE scrap_ledger (
id INTEGER PRIMARY KEY,
inspect_date DATE NOT NULL,
workcenter_code TEXT NOT NULL,
scrap_units INTEGER NOT NULL,
defect_family TEXT NOT NULL,
inspector_id TEXT NOT NULL
);
"""
@dataclass(frozen=True)
class BuiltDatabases:
today: date
ops_path: Path
equip_path: Path
quality_path: Path
def build(out_dir: Path | str, today: date | None = None) -> BuiltDatabases:
"""在 out_dir 下生成 ops_shift.db、equip_master.db、quality_scrap.db(已存在则覆盖)。"""
root = Path(out_dir)
root.mkdir(parents=True, exist_ok=True)
today = today or date(2026, 10, 22)
rng = random.Random(SEED)
ops_path = root / f"{SOURCE_OPS}.db"
equip_path = root / f"{SOURCE_EQUIP}.db"
quality_path = root / f"{SOURCE_QUALITY}.db"
for p in (ops_path, equip_path, quality_path):
if p.exists():
p.unlink()
yesterday = today - timedelta(days=1)
control2_day = yesterday - timedelta(days=2)
stalled_after = yesterday - timedelta(days=2) # quality_scrap 停在 yesterday - 2 天,最近两天缺失
days = [today - timedelta(days=offset) for offset in range(DAYS, 0, -1)]
shift_rows: list[tuple[Any, ...]] = []
energy_rows: list[tuple[Any, ...]] = []
downtime_rows: list[tuple[Any, ...]] = []
scrap_rows: list[tuple[Any, ...]] = []
base_good = {"L1": 904, "L2": 900, "L3": 844, "L4": 888}
base_scrap = {"L1": 18, "L2": 20, "L3": 19, "L4": 17}
phones = {
"L1": "138-0010-0101",
"L2": "138-0010-0102",
"L3": "138-0010-0103",
"L4": "138-0010-0104",
}
inspectors = {
"WC-01": "INSP-9001",
"WC-02": "INSP-9002",
"WC-03": "INSP-9003",
"WC-04": "INSP-9004",
}
shift_id = 1
energy_id = 1
downtime_id = 1
scrap_id = 1
for idx, d in enumerate(days):
ds = d.isoformat()
wave = (-1 if idx % 2 else 1) * (4 + (idx % 3) * 2) # 确定性小幅波动 ±4..±8
for line_code, equip_id, wc_code, _ in LINES:
noise = rng.choice((-3, -1, 1, 3))
good = base_good[line_code] + wave + noise
scrap = base_scrap[line_code] + (idx % 3) - 1
run_hours = 8.0
net_ratio = round(0.905 + ((idx % 4) - 1.5) * 0.006 + noise * 0.001, 4)
unplanned = float(12 + (-1 if idx % 2 else 1) * (1 + (idx % 3)) + (0.5 if noise > 0 else -0.5))
fault_cat = "routine_check"
# 对照 1:L1 末尾两日固定为平缓常规波动(前日 908 → 昨日 898,-1.1%)
if line_code == "L1" and d == yesterday - timedelta(days=1):
good = 908
elif line_code == "L1" and d == yesterday:
good = 898
# S1:L3 昨日实际产率 108 件/小时(864 件 / 8 小时),对比 equip_master 过期额定 80 件/小时 = 135%
if line_code == "L3" and d == yesterday:
good = 844
scrap = 20
# S3:L2 昨日产率显著下跌,同时 EQ-L2 非计划停机飙升至 96 分钟(统计伴随异动)
if line_code == "L2" and d == yesterday:
good = 612
net_ratio = 0.6320
unplanned = 96.0
fault_cat = "feeder_jam"
# 对照 2:EQ-L4 在 control2_day 有效运转率明显下跌,但非计划停机保持常态 12 分钟(target_normal)
if line_code == "L4" and d == control2_day:
good = 720
net_ratio = 0.7280
unplanned = 12.0
fault_cat = "routine_check"
actual = good + scrap
shift_rows.append((shift_id, ds, line_code, actual, good, scrap, run_hours, phones[line_code]))
shift_id += 1
# 能耗表:昨日 L4 出现结算导入偏差(14800 kWh vs 12.5 MWh),其余对齐
kwh = round(actual * 14.0, 1)
mwh = round(kwh / 1000.0, 4)
if line_code == "L4" and d == yesterday:
kwh = 14800.0
mwh = 12.5
elif d == yesterday:
kwh = 12000.0 + (LINES.index((line_code, equip_id, wc_code, _)) * 500.0)
mwh = round(kwh / 1000.0, 4)
energy_rows.append((energy_id, ds, line_code, kwh, mwh))
energy_id += 1
downtime_rows.append((downtime_id, ds, equip_id, net_ratio, unplanned, fault_cat))
downtime_id += 1
# S2a:quality_scrap 在 stalled_after 之后断更(最近两天 0 行)
if d <= stalled_after:
scrap_rows.append((scrap_id, ds, wc_code, scrap, "surface_burr", inspectors[wc_code]))
scrap_id += 1
specs_rows = [
("EQ-L1", "星梭一线", 120.0, (today - timedelta(days=30)).isoformat()),
("EQ-L2", "星梭二线", 120.0, (today - timedelta(days=30)).isoformat()),
# S1 根因:EQ-L3 技改提速后主数据未更新,仍为 80 件/小时
("EQ-L3", "星梭三线", 80.0, "2026-06-01"),
("EQ-L4", "星梭四线", 120.0, (today - timedelta(days=30)).isoformat()),
]
ops_db = sqlite3.connect(ops_path)
ops_db.executescript(OPS_SCHEMA)
ops_db.executemany("INSERT INTO shift_output VALUES (?, ?, ?, ?, ?, ?, ?, ?)", shift_rows)
ops_db.executemany("INSERT INTO energy_readings VALUES (?, ?, ?, ?, ?)", energy_rows)
ops_db.commit()
ops_db.close()
equip_db = sqlite3.connect(equip_path)
equip_db.executescript(EQUIP_SCHEMA)
equip_db.executemany("INSERT INTO line_specs VALUES (?, ?, ?, ?)", specs_rows)
equip_db.executemany("INSERT INTO downtime_events VALUES (?, ?, ?, ?, ?, ?)", downtime_rows)
equip_db.commit()
equip_db.close()
quality_db = sqlite3.connect(quality_path)
quality_db.executescript(QUALITY_SCHEMA)
quality_db.executemany("INSERT INTO scrap_ledger VALUES (?, ?, ?, ?, ?, ?)", scrap_rows)
quality_db.commit()
quality_db.close()
return BuiltDatabases(today=today, ops_path=ops_path, equip_path=equip_path, quality_path=quality_path)
async def seed_ontology_fixture(
tmp_path: Path,
scratch_source: Any,
*,
today: date | None = None,
) -> dict[str, Any]:
"""登记三源 SQLite、标准实体 `production_line`、断更变更记录及三条跨源已发布口径工作流。"""
from app.api.workflows import commit_publish
from app.data import source_changes as sc
from app.data.entities import create_entity, entity_to_dict
from app.db.base import SessionLocal
from app.db.models import DataSource, Workflow, WorkflowVersion
built = build(tmp_path, today=today)
ops_id = await scratch_source(
SOURCE_OPS, built.ops_path, options={"mask_columns": ["operator_phone"]}, schema=True
)
equip_id = await scratch_source(SOURCE_EQUIP, built.equip_path, schema=True)
quality_id = await scratch_source(
SOURCE_QUALITY, built.quality_path, options={"mask_columns": ["inspector_id"]}, schema=True
)
stalled_day = (built.today - timedelta(days=3)).isoformat()
async with SessionLocal() as session:
quality_src = await session.get(DataSource, quality_id)
await sc.record(
session,
quality_src,
sc.NewChange(
kind=sc.DATE_STALLED,
table="scrap_ledger",
column="inspect_date",
severity="action",
before={"max_date": stalled_day},
after={"max_date": stalled_day, "missing_days": 2},
key=stalled_day,
),
sc.Detected(job_kind="profile", trigger="manual", actor="fixture_builder"),
)
await session.commit()
async with SessionLocal() as session:
# 建三条分属不同数据源的口径工作流:先落基础工作流以拿到固定 workflow_id,再互相挂本体边
wf_equip = Workflow(name="设备主数据与停机口径", description="设备额定产能与非计划停机口径", graph={"nodes": [], "edges": []})
wf_quality = Workflow(name="质量报废台账口径", description="质量检验报废台账口径", graph={"nodes": [], "edges": []})
wf_ops = Workflow(name="班次产率与负荷率口径", description="班次合格产率、负荷率与报工报废口径", graph={"nodes": [], "edges": []})
session.add_all([wf_equip, wf_quality, wf_ops])
await session.flush()
equip_graph = {
"nodes": [
{
"id": "in_eq",
"type": "input",
"position": {"x": 0, "y": 0},
"data": {
"label": "入口",
"config": {
"fields": [
{"name": "equip_line", "label": "设备产线", "type": "text", "default": "EQ-L3"},
{"name": "stat_day", "label": "统计日期", "type": "text", "default": (built.today - timedelta(days=1)).isoformat()},
]
},
},
},
{
"id": "q_spec",
"type": "tool",
"position": {"x": 220, "y": 0},
"data": {
"label": "查额定产能",
"config": {
"tool": f"db_query__{SOURCE_EQUIP}",
"args": {
"sql": "SELECT equip_line_id, rated_hourly_qty FROM line_specs WHERE equip_line_id = '{{ input.equip_line }}'",
},
},
},
},
{
"id": "q_down",
"type": "tool",
"position": {"x": 220, "y": 140},
"data": {
"label": "查停机时长",
"config": {
"tool": f"db_query__{SOURCE_EQUIP}",
"args": {
"sql": "SELECT event_date, unplanned_min FROM downtime_events WHERE equip_line_id = '{{ input.equip_line }}' AND event_date = '{{ input.stat_day }}'",
},
},
},
},
{
"id": "m_equip",
"type": "metrics",
"position": {"x": 480, "y": 60},
"data": {
"label": "设备指标卡",
"config": {
"caliber": "设备主数据与非计划停机日口径",
"metrics": [
{
"id": "rated_hourly_qty",
"name": "额定每小时产量",
"expression": "cell(nodes.q_spec, 0, 'rated_hourly_qty')",
"unit": "件/小时",
"semantic": {
"entities": [{"name": "产线", "key": "equip_line_id", "entity_key": "production_line"}]
},
},
{
"id": "unplanned_downtime_min",
"name": "非计划停机时长",
"expression": "cell(nodes.q_down, 0, 'unplanned_min')",
"unit": "分钟",
"semantic": {
"grain": "day",
"time": {"column": "event_date", "timezone": "Asia/Shanghai"},
"entities": [{"name": "产线", "key": "equip_line_id", "entity_key": "production_line"}],
},
},
],
},
},
},
{"id": "out_eq", "type": "output", "position": {"x": 720, "y": 60}, "data": {"label": "出口", "config": {}}},
],
"edges": [
{"source": "in_eq", "target": "q_spec"},
{"source": "in_eq", "target": "q_down"},
{"source": "q_spec", "target": "m_equip"},
{"source": "q_down", "target": "m_equip"},
{"source": "m_equip", "target": "out_eq"},
],
}
quality_graph = {
"nodes": [
{
"id": "in_q",
"type": "input",
"position": {"x": 0, "y": 0},
"data": {
"label": "入口",
"config": {
"fields": [
{"name": "workcenter", "label": "工作中心", "type": "text", "default": "WC-02"},
{"name": "inspect_day", "label": "检验日期", "type": "text", "default": (built.today - timedelta(days=1)).isoformat()},
]
},
},
},
{
"id": "q_scrap",
"type": "tool",
"position": {"x": 240, "y": 0},
"data": {
"label": "查质量报废",
"config": {
"tool": f"db_query__{SOURCE_QUALITY}",
"args": {
"sql": "SELECT COALESCE(SUM(scrap_units), 0) AS scrap_units FROM scrap_ledger WHERE workcenter_code = '{{ input.workcenter }}' AND inspect_date = '{{ input.inspect_day }}'",
},
},
},
},
{
"id": "m_quality",
"type": "metrics",
"position": {"x": 480, "y": 0},
"data": {
"label": "质量报废卡",
"config": {
"caliber": "质量检验台账日报废口径",
"metrics": [
{
"id": "ledger_scrap_units",
"name": "台账报废件数",
"expression": "cell(nodes.q_scrap, 0, 'scrap_units')",
"unit": "件",
"semantic": {
"grain": "day",
"time": {"column": "inspect_date", "timezone": "Asia/Shanghai"},
"entities": [{"name": "产线", "key": "workcenter_code", "entity_key": "production_line"}],
},
}
],
},
},
},
{"id": "out_q", "type": "output", "position": {"x": 720, "y": 0}, "data": {"label": "出口", "config": {}}},
],
"edges": [
{"source": "in_q", "target": "q_scrap"},
{"source": "q_scrap", "target": "m_quality"},
{"source": "m_quality", "target": "out_q"},
],
}
ops_graph = {
"nodes": [
{
"id": "in_ops",
"type": "input",
"position": {"x": 0, "y": 0},
"data": {
"label": "入口",
"config": {
"fields": [
{"name": "line_code", "label": "产线编码", "type": "text", "default": "L3"},
{"name": "shift_day", "label": "班次日期", "type": "text", "default": (built.today - timedelta(days=1)).isoformat()},
]
},
},
},
{
"id": "q_ops",
"type": "tool",
"position": {"x": 240, "y": 0},
"data": {
"label": "查班次产出",
"config": {
"tool": f"db_query__{SOURCE_OPS}",
"args": {
"sql": "SELECT actual_qty, good_qty, scrap_qty, run_hours FROM shift_output WHERE line_code = '{{ input.line_code }}' AND shift_date = '{{ input.shift_day }}'",
},
},
},
},
{
"id": "m_ops",
"type": "metrics",
"position": {"x": 500, "y": 0},
"data": {
"label": "班次指标卡",
"config": {
"caliber": "班次负荷率、合格产量与报工报废口径",
"metrics": [
{
"id": "load_rate_pct",
"name": "产线负荷率",
"expression": "round((cell(nodes.q_ops, 0, 'actual_qty') / cell(nodes.q_ops, 0, 'run_hours')) / 80.0 * 100, 2)",
"unit": "%",
"contract": {"minimum": 0, "maximum": 100, "unit": "%"},
"semantic": {
"grain": "day",
"time": {"column": "shift_date", "timezone": "Asia/Shanghai"},
"entities": [{"name": "产线", "key": "line_code", "entity_key": "production_line"}],
},
"links": [
{
"kind": "factor",
"target": {
"workflow_id": wf_equip.id,
"card_id": "m_equip",
"metric_id": "rated_hourly_qty",
},
"role": "denominator",
"entity_key": "production_line",
"status": "confirmed",
"rationale": "负荷率分母取设备主数据的额定每小时产量",
},
{
"kind": "upstream_driver",
"target": {
"workflow_id": wf_equip.id,
"card_id": "m_equip",
"metric_id": "unplanned_downtime_min",
},
"entity_key": "production_line",
"status": "proposed",
"rationale": "候选未确认边:验证运行期不会自动沿 proposed 边穿透",
},
],
},
{
"id": "good_output_qty",
"name": "班次合格产量",
"expression": "cell(nodes.q_ops, 0, 'good_qty')",
"unit": "件",
"semantic": {
"grain": "day",
"time": {"column": "shift_date", "timezone": "Asia/Shanghai"},
"entities": [{"name": "产线", "key": "line_code", "entity_key": "production_line"}],
},
"links": [
{
"kind": "upstream_driver",
"target": {
"workflow_id": wf_equip.id,
"card_id": "m_equip",
"metric_id": "unplanned_downtime_min",
},
"entity_key": "production_line",
"lag_periods": 0,
"status": "confirmed",
"rationale": "设备非计划停机时长升高会同步压缩班次有效产出时间",
}
],
},
{
"id": "shift_scrap_qty",
"name": "报工报废件数",
"expression": "cell(nodes.q_ops, 0, 'scrap_qty')",
"unit": "件",
"semantic": {
"grain": "day",
"time": {"column": "shift_date", "timezone": "Asia/Shanghai"},
"entities": [{"name": "产线", "key": "line_code", "entity_key": "production_line"}],
},
"links": [
{
"kind": "reconciles_with",
"target": {
"workflow_id": wf_quality.id,
"card_id": "m_quality",
"metric_id": "ledger_scrap_units",
},
"entity_key": "production_line",
"rel_tol": 0.02,
"status": "confirmed",
"rationale": "班次报工报废数应与质量检验台账日报废件数在 2% 容差内对齐",
}
],
},
],
},
},
},
{"id": "out_ops", "type": "output", "position": {"x": 740, "y": 0}, "data": {"label": "出口", "config": {}}},
],
"edges": [
{"source": "in_ops", "target": "q_ops"},
{"source": "q_ops", "target": "m_ops"},
{"source": "m_ops", "target": "out_ops"},
],
}
snapshots: list[tuple[Workflow, WorkflowVersion]] = []
for wf, graph in ((wf_equip, equip_graph), (wf_quality, quality_graph), (wf_ops, ops_graph)):
wf.graph = graph
wf.version = 1
snap = WorkflowVersion(workflow_id=wf.id, version=1, graph=graph, note="初始版本")
session.add(snap)
snapshots.append((wf, snap))
# 先提交未写锁的草稿行,再逐一走 commit_publish(避免 SQLite 单写锁下嵌套会话写工件抢锁)
await session.commit()
for wf, snap in snapshots:
await session.refresh(wf)
await session.refresh(snap)
await commit_publish(session, wf, snap, "published", "fixture_builder")
entity_row = await create_entity(
session,
{
"key": "production_line",
"label": "产线",
"description": "星梭示范装配厂标准产线实体,桥接班次报工、设备主数据与质量报废台账三套异构编码",
"aliases": ["装配产线", "车间产线", "工作中心"],
"bindings": [
{
"source_name": SOURCE_OPS,
"table_name": "shift_output",
"column_name": "line_code",
"status": "confirmed",
},
{
"source_name": SOURCE_OPS,
"table_name": "energy_readings",
"column_name": "line_code",
"status": "confirmed",
},
{
"source_name": SOURCE_EQUIP,
"table_name": "line_specs",
"column_name": "equip_line_id",
"status": "confirmed",
},
{
"source_name": SOURCE_EQUIP,
"table_name": "downtime_events",
"column_name": "equip_line_id",
"status": "confirmed",
},
{
"source_name": SOURCE_QUALITY,
"table_name": "scrap_ledger",
"column_name": "workcenter_code",
"status": "confirmed",
},
{
"source_name": SOURCE_QUALITY,
"table_name": "unverified_archive",
"column_name": "legacy_line",
"status": "proposed",
},
],
"caliber_params": [
{"workflow_id": wf_ops.id, "param_name": "line_code", "status": "confirmed"},
{"workflow_id": wf_equip.id, "param_name": "equip_line", "status": "confirmed"},
{"workflow_id": wf_quality.id, "param_name": "workcenter", "status": "confirmed"},
],
"members": [
{
"value": code,
"label": name,
"aliases": [code, equip_id, wc_code],
"source_codes": {SOURCE_OPS: code, SOURCE_EQUIP: equip_id, SOURCE_QUALITY: wc_code},
}
for code, equip_id, wc_code, name in LINES
],
},
actor="fixture_builder",
)
entity_dict = entity_to_dict(entity_row)
await session.commit()
return {
"today": built.today,
"paths": {"ops": built.ops_path, "equip": built.equip_path, "quality": built.quality_path},
"source_ids": {SOURCE_OPS: ops_id, SOURCE_EQUIP: equip_id, SOURCE_QUALITY: quality_id},
"workflow_ids": {"ops": wf_ops.id, "equip": wf_equip.id, "quality": wf_quality.id},
"entity_id": entity_dict["id"],
"entity": entity_dict,
}
def main() -> None:
parser = argparse.ArgumentParser(description="生成跨源指标本体穿透用的三源虚构制造库")
parser.add_argument("out_dir")
parser.add_argument("--today", type=date.fromisoformat, default=None)
args = parser.parse_args()
built = build(args.out_dir, args.today)
print(f"{built.ops_path}\n{built.equip_path}\n{built.quality_path}")
if __name__ == "__main__":
main()