"""원문 ↔ 기초단가 다섯 갈래(노임·기계·자재·유가·제비율) 맞대기 — 2026-09-18 랩탑 메인. 사람이 손으로 하던 값 대조를 시험으로 옮김. 원문 자리는 자료 `sources[].path` 를 그대로 씀. - 어긋남·셈 틀어짐은 `fixtures/base_prices_source_known.json` 에 적어 두고 **그 목록 밖**이면 빨강. ⚠ 목록에 있는데 고쳐졌거나 모습이 바뀐 것도 빨강 — 목록이 낡지 않게. 고친 뒤 목록 지우기: `python resources/tester/test_base_prices_source_match.py --prune` (지우기만 함 · 새 어긋남은 안 보탬). - `*_blind` 갈래 = **시험이 못 보는 자리**. 못 보는 것을 본 척하지 않고 목록에 까닭과 함께 둠. 자료에 안 재는 칸이 새로 생겨도 목록 밖이라 빨강. ⚠ 빌더 코드를 안 씀 — 원문 읽기를 여기서 따로 함. 표 읽기(`md_tables`)만 옆 시험 한 벌. """ from __future__ import annotations import json import re import sys from pathlib import Path import openpyxl import pytest from openpyxl.utils import get_column_letter from test_work_item_master_source_match import ROOT, _without_why, md_tables DATA = ROOT / "resources/data_cost_input_value" KNOWN = Path(__file__).resolve().parent / "fixtures/base_prices_source_known.json" FILES = { "labor_const": "labor_const_2026-01-01.json", "labor_mfg": "labor_mfg_2026-07-01.json", "mach": "mach_base_2026.json", "mat": "mat_price_public_2026-08-14.json", "oil": "oil_2026-08-14.json", "oil_regional": "oil_regional_2026-09-09.json", "rates": "rates_2026.json", } KINDS = ["labor", "machine", "material", "oil", "rate"] KIND_NAMES = { "labor": "노임", "machine": "기계", "material": "자재", "oil": "유가", "rate": "제비율", **{f"{k}_blind": f"{n} — 못 보는 자리" for k, n in {"labor": "노임", "machine": "기계", "material": "자재", "oil": "유가", "rate": "제비율"}.items()}, } # fmt: skip # ── 공통 ──────────────────────────────────────────────────────────────── def _num(text): """`12,000` · `0.9` · `(1.8)` · `16%` → 수. `-` · `*` · 빈 칸 → None. 수가 아니면 ValueError.""" t = str(text).strip().strip("()%").replace(",", "") if t in ("", "-", "*", "None"): return None return float(t) if "." in t else int(t) def _t(value) -> str: return re.sub(r"\s+", "", str(value)) def _compare(out: dict, key: str, source: dict | None, data: dict | None, fields) -> None: """한 줄 맞대기 — 한쪽에만 있으면 줄 통째로, 둘 다 있으면 칸마다 `{source, data}`.""" if source is None or data is None: if source != data: out[key] = {"source": source, "data": data} return for f in fields: if source.get(f) != data.get(f): out[f"{key} {f}"] = {"source": source.get(f), "data": data.get(f)} def _unchecked(blind: dict, where: str, records, checked) -> None: """자료에 있는데 원문과 안 맞대는 칸 — 못 본다고 적음.""" for field in sorted({k for r in records for k in r} - set(checked)): blind[f"안 잰 칸 {where}.{field}"] = {"what": "원문과 안 맞댐"} def _lines(path: Path) -> list[str]: return path.read_text(encoding="utf-8").splitlines() # ── 노임 ──────────────────────────────────────────────────────────────── def read_labor_const(path: Path) -> dict: """건설업 md — `| 직종코드 | 직종명 | 신뢰도 | 2026.1.1 | …` 표 한 벌 · 맨 앞 열이 적용일 노임.""" lines = _lines(path) table = next(t for t in md_tables(lines) if t["headers"][:2] == ["직종코드", "직종명"]) head = "\n".join(lines[: table["line"]]) hours = int(re.search(r"1일 (\d+)시간 기준", head).group(1)) rows = { code: { "occupation_name": name, "reliability": mark or None, "hours_per_day": hours, "daily_wage_krw": _num(wage), "status": "not_published" if wage == "-" else "published", } for code, name, mark, wage, *_ in table["rows"] } y, m, d = table["headers"][3].split(".") published, effective = re.search(r"공표 ([\d-]+), 적용 ([\d-]+)", head).groups() dates = {"publication_date": published, "effective_date": effective} return {"rows": rows, "wage_column": f"{y}-{int(m):02d}-{int(d):02d}", "dates": dates} _JOB = re.compile(r"^(\d+)\.(.+)$") def read_labor_mfg(path: Path) -> dict: """제조업 md — `업 종` 표들. 업종 칸은 빈 줄이 위 칸을 이어받음 · 하위 업종(`화학 공학`)은 `상위 / 하위`.""" lines = _lines(path) rows, main, sub = {}, "", "" for table in md_tables(lines): if table["headers"][0] != "업 종": continue for r in table["rows"]: i = next((k for k, c in enumerate(r) if _JOB.match(c)), None) if i is None: continue if r[0]: main, sub = r[0], "" if i == 2 and r[1]: sub = r[1] code, name = _JOB.match(r[i]).groups() wage = r[i + 1] rows[code] = { "occupation_name": name, "industry": f"{main} / {sub}" if sub else main, "daily_wage_krw": _num(wage.lstrip("*")), "variation_coefficient": _num(r[i + 2]), "status": "not_published" if wage == "*" else "published", "source_flag": re.match(r"\**", wage).group() or None, } text = "\n".join(lines) y, m, d = re.search(r"적용시점 : (\d{4})\. (\d+)\. (\d+)\.", text).groups() sy, sm = re.search(r"조사 기 준 일 : (\d{4})\. (\d+)\.", text).groups() return { "rows": rows, "dates": {"effective_date": f"{y}-{int(m):02d}-{int(d):02d}", "survey_month": f"{sy}-{int(sm):02d}"}, } # fmt: skip LABOR = { "labor_const": ("건설", "labor_rate", ("occupation_name", "reliability", "hours_per_day", "daily_wage_krw", "status")), "labor_mfg": ("제조", "labor_mfg", ("occupation_name", "industry", "daily_wage_krw", "variation_coefficient", "status", "source_flag")), } # fmt: skip def check_labor(src: dict, bad: dict, blind: dict) -> dict: counts = {} for name, (label, var, fields) in LABOR.items(): source, data = src[name]["source"], src[name]["data"] rows = source["rows"] records = {r["occupation_code"]: r for r in data["variables"][var]["records"]} for code in rows | records: _compare(bad, f"{label} {code}", rows.get(code), records.get(code), fields) _compare(bad, f"{label} 날짜", source["dates"], data, source["dates"]) if source.get("wage_column", data["effective_date"]) != data["effective_date"]: bad[f"{label} 노임 열"] = { "source": source["wage_column"], "data": data["effective_date"], } for alias, code in data["variables"].get("aliases", {}).items(): if code not in rows: bad[f"{label} 별칭 {alias}"] = {"source": None, "data": code} counts[f"{label} 직종 수"] = (len(rows), len(records)) counts[f"{label} 원문에 없는 자료 줄"] = (0, len(set(records) - set(rows))) blind[f"{label} pdf"] = {"what": src[name]["paths"][0].name} _unchecked(blind, var, records.values(), {"occupation_code", *fields}) blind["건설 별칭 이름"] = {"what": sorted(src["labor_const"]["data"]["variables"]["aliases"])} return counts # ── 기계 ──────────────────────────────────────────────────────────────── def _codes(cell: str, prefix: str | None) -> tuple[list[str] | None, str | None]: """`0101-0007 0010 0012` → 코드 목록 · 머리(`0101`)는 앞 코드를 이어받음(앞 표에서도). `9020- 0010` 처럼 머리만 떨어진 토막도 받음. 코드 아닌 토막이 끼면 `(None, None)`. """ codes = [] for tok in cell.split(): m = re.fullmatch(r"-?(?:(\d{4})-)?(\d{4})?", tok) prefix = (m.group(1) or prefix) if m and tok.strip("-") else None if prefix is None: return None, None if m.group(2): codes.append(f"{prefix}-{m.group(2)}") return codes, prefix LOSS_COLS = {"economic_life_hours": "내용시간", "annual_standard_hours": "가동시간", "depreciation_ratio": "상각비율", "maintenance_ratio": "정비비율", "annual_management_ratio": "관리비율"} # fmt: skip LOSS_COEF = ("depreciation_coefficient_1e_minus_7", "maintenance_coefficient_1e_minus_7", "management_coefficient_1e_minus_7", "source_coefficient_1e_minus_7") # fmt: skip FUEL_FIELDS = ("fuel_type", "fuel_rate_l_per_hour", "misc_material_percent_of_fuel", "operator_person_per_day") # fmt: skip def _fuel(tok: str) -> tuple: """주연료 토막 — `9.0` 경유([주]① ㉰: 표시 없는 것은 경유) · `휘발유0.7` · `중유487.2` · `-` 없음.""" if tok == "-": return None, None m = re.fullmatch(r"(휘발유|중유)?(\d+(?:\.\d+)?)", tok) if m is None: raise ValueError(tok) kind = {"휘발유": "gasoline", "중유": "heavy_oil", None: "diesel"}[m.group(1)] return kind, float(m.group(2)) def read_machine(path: Path) -> dict: """제8장 md — 8-3 손료 · 8-4 운전경비 · 8-5 가격. 여러 코드가 한 칸에 뭉친 줄은 토막 수가 맞을 때만 읽음.""" lines = _lines(path) tables = md_tables(lines) at = {w: next(i for i, x in enumerate(lines, 1) if w in x) for w in ("8-3 기계손료", "8-4 운전경비", "8-4-9 [90]", "8-5 기계가격")} # fmt: skip out = {k: {} for k in ("price", "loss", "fuel", "fuel_tables", "skipped", "names")} out["lines"] = lines name_at = re.compile(r"\((\d{4})\) ?(.+?)(?=시 간 당\(10-7\)|\((?:'\d\d|\d{4}\))|$)") for x in lines[ at["8-3 기계손료"] - 1 : at["8-4 운전경비"] ]: # 손료 표 머리 `(0101) 불도저(무한궤도)` for m in name_at.finditer("" if x.lstrip().startswith("|") else x): out["names"].setdefault(m.group(1), m.group(2).strip()) prefix = None for t in tables: if t["line"] > at["8-5 기계가격"] and t["headers"] == ["기 종", "분류번호", "가격(￦)"]: for n, r in enumerate(t["rows"]): codes, prefix = _codes(r[1], prefix) prices = r[2].split() if codes is None or len(codes) != len(prices): out["skipped"][f"가격 줄 {_t(r[1])[:24]}"] = {"what": r[1][:40]} continue out["price"].update( (c, {"price_thousand_krw": _num(p)}) for c, p in zip(codes, prices) ) prefix = None for t in tables: head = [_t(h) for h in t["headers"]] if not (at["8-3 기계손료"] < t["line"] < at["8-4 운전경비"] and head[0] == "분류번호"): continue cols = {f: next(i for i, h in enumerate(head) if w in h) for f, w in LOSS_COLS.items() if any(w in h for h in head)} # fmt: skip sub = next((r for r in t["rows"] if not r[0]), []) if "상각비 계수" in sub: cols.update(zip(LOSS_COEF, range(sub.index("상각비 계수"), 99))) elif "시간당(10-7)" in head: cols[LOSS_COEF[3]] = head.index("시간당(10-7)") else: # 원문 표에 계수 칸이 없음(5220·7995 — 머리 「시 간 당(10-7)」 은 표 위 글줄로만 남음) out["skipped"][f"손료 계수 칸 없는 표 {t['rows'][0][0][:4] if t['rows'] else '?'}"] = {"what": t["headers"]} # fmt: skip continue for n, r in enumerate(t["rows"]): if not r[0]: continue codes, prefix = _codes(r[0], prefix) try: values = {f: [_num(x) for x in r[i].split()] for f, i in cols.items()} if not codes or any(len(v) != len(codes) for v in values.values()): raise ValueError(r[0]) except ValueError: out["skipped"][f"손료 줄 {_t(r[0])[:24]}"] = {"what": r[0][:40]} continue out["loss"].update( (c, {f: v[k] for f, v in values.items()}) for k, c in enumerate(codes) ) for k in range(at["8-3 기계손료"], at["8-4 운전경비"]): if not lines[k - 1].lstrip().startswith("|") and "시 간 당(10-7)" in lines[k - 1]: heads = re.findall(r"\((\d{4})\) ?(?:[^|()]{0,30}\([^)]*\)){0,2}[^|()]{0,30}?시 간 당\(10-7\)", lines[k - 1]) # fmt: skip if heads: # 표 위 머리 글줄(`시 간 당(10-7)` 한 줄)은 표로 읽힘 — 뭉개진 글만 out["skipped"][f"손료 뭉개진 글 {'·'.join(heads)}"] = {"what": heads} prefix = None for t in tables: if not at["8-4 운전경비"] < t["line"] < at["8-5 기계가격"]: continue out["fuel_tables"][len(out["fuel_tables"])] = {"headers": t["headers"], "rows": t["rows"]} if t["line"] > at["8-4-9 [90]"] or t["headers"][0] != "분류번호": continue for r in t["rows"]: codes, prefix = _codes(r[0], prefix) cols = [r[3].split(), r[4].split(), r[5].split()] try: if not codes or any(len(c) != len(codes) for c in cols): raise ValueError(r[0]) parsed = [(*_fuel(f), _num(m), _num(o)) for f, m, o in zip(*cols)] except ValueError: out["skipped"][f"연료 표 {codes[0] if codes else _t(r[0])[:24]}"] = { "codes": codes and [codes[0], codes[-1]] } out["fuel_unread"] = out.get("fuel_unread", set()) | set(codes or ()) continue out["fuel"].update((c, dict(zip(FUEL_FIELDS, p))) for c, p in zip(codes, parsed) if p[1] is not None) # fmt: skip return out #: 손료보정 표는 글로 뭉개짐 — 기종 글 바로 뒤에 `암석작업` `전석섞인토사` 두 수가 붙어 있음(`덤프트럭2510`). ROCK = {"bulldozer_under_19_ton": "불도저(19톤이상제외)", "crawler_excavator_or_loader": "굴착기(무한궤도)및로더(무한궤도)", "dump_truck": "덤프트럭"} # fmt: skip def check_machine(src: dict, bad: dict, blind: dict) -> dict: source, v = src["mach"]["source"], src["mach"]["data"]["variables"] counts = {} for label, var, rows, fields in ( ("가격", "mach_price", source["price"], ("price_thousand_krw",)), ("손료", "mach_loss_coef", source["loss"], (*LOSS_COLS, *LOSS_COEF)), ("연료", "mach_fuel_rate", source["fuel"], FUEL_FIELDS), ): records = v[var].get("records") or v[var]["parsed_records"] by_code = {r["machine_code"]: r for r in records} unread = source.get("fuel_unread", set()) if label == "연료" else set() missing: dict[str, list] = {} for code in rows | by_code: if code in unread and code not in rows: blind[f"연료 못 읽은 줄 {code}"] = {"what": "원문 표 토막 수가 안 맞음"} continue if code not in by_code: missing.setdefault(code[:4], []).append(code) continue if code in rows: # 원문에 칸이 없는 표(축약 손료표)는 있는 칸만 맞댐 rows_code = {f: rows[code].get(f, by_code[code].get(f)) for f in fields} _compare(bad, f"{label} {code}", rows_code, by_code[code], fields) else: _compare(bad, f"{label} {code}", None, by_code[code], fields) heading, name = source["names"].get(code[:4]), by_code[code].get("machine_name") if _t(heading) != _t(name): bad[f"{label} {code} machine_name"] = {"source": heading, "data": name} for head, codes in missing.items(): bad[f"{label} {head} 자료에 없음"] = {"source": codes, "data": None} counts[f"{label} 코드 수"] = (len(rows), len(by_code)) counts[f"{label} 원문에 없는 자료 줄"] = (0, len(set(by_code) - set(rows) - unread)) _unchecked(blind, var, records, {"machine_code", "machine_name", *fields}) blind.update(source["skipped"]) tables = v["mach_fuel_rate"]["source_tables"] for n, st in enumerate( tables ): # ⚠ 줄 번호로 안 맞댐 — md 가 고쳐지면 통째로 밀림. 8-4 안 표 차례로 t = source["fuel_tables"].get(n) if t != {"headers": st["headers"], "rows": st["rows"]}: bad[f"운전경비 원표 {n + 1}번째"] = { "source": t, "data": {k: st[k] for k in ("headers", "rows")}, } counts["운전경비 원표 수"] = (len(source["fuel_tables"]), len(tables)) _unchecked(blind, "mach_fuel_rate.source_tables", tables, {"line", "headers", "rows"}) op = next(t for t in md_tables(source["lines"]) if t["headers"] == ["구 분", "해 당 기 계"]) labels = [_t(r[0]) for r in op["rows"]] names = src["labor_const"]["source"]["rows"] for rule in v["mach_operator_map"]["rules"]: name = names.get(rule["occupation_code"], {}).get("occupation_name") if name not in labels: bad[f"운전사 {rule['rule_id']}"] = {"source": labels, "data": [rule["occupation_code"], name]} # fmt: skip blind["운전사 기종별 판단"] = {"what": len(v["mach_operator_map"]["explicit_mappings"])} _unchecked( blind, "mach_operator_map.rules", v["mach_operator_map"]["rules"], {"occupation_code"} ) text = _t("".join(source["lines"])) for rule in v["mach_rock_adj"]["rules"]: group, pair = rule["machine_group"], f"{rule['rock_work']}{rule['boulder_mixed_soil']}" if group in ROCK: ok = f"{ROCK[group]}{pair}" in text else: ok = pair == "00" and "불도저(19톤이상)의경우는보정하지않는다" in text if not ok: bad[f"손료보정 {group}"] = {"source": ROCK.get(group), "data": pair} blind["손료보정 수 자리 가름"] = {"what": "뭉개진 글의 이어 붙은 수(2510)를 통째로 맞댐"} _unchecked(blind, "mach_rock_adj.rules", v["mach_rock_adj"]["rules"], {"machine_group", "rock_work", "boulder_mixed_soil"}) # fmt: skip return counts # ── 자재 ──────────────────────────────────────────────────────────────── MAT_FIELDS = { "classification_code": "prdctClsfcNo", "classification_name": "prdctClsfcNoNm", "specification": "krnPrdctNm", "unit": "unit", "price_krw": "prce", "notice_datetime": "nticeDt", "notice_number": "prceNticeNo", "business_division_code": "bsnsDivCd", "business_division_name": "bsnsDivNm", "vat_basis": "vatYnNm", "price_type": "prceDiv", "delivery_condition": "dlvryCndtnNm", "field": "분야", } # fmt: skip def read_material(path: Path) -> dict: """나라장터 API 스냅숏 — 물품식별번호마다 **값이 실린 공시 중 가장 나중** 것(같은 때가 둘이면 둘 다). 값 없는 공시(`0`·빈 칸)를 건너뜀은 자료 `selection_policy` 가 밝힌 규칙. """ raw = json.loads(path.read_text(encoding="utf-8")) latest: dict[str, list[dict]] = {} for row in raw: if not _num(row["prce"]): continue mapped = {k: (_num(row[f]) if k == "price_krw" else row[f]) for k, f in MAT_FIELDS.items()} best = latest.setdefault(row["prdctIdntNo"], []) if best and best[0]["notice_datetime"] > mapped["notice_datetime"]: continue if best and best[0]["notice_datetime"] < mapped["notice_datetime"]: best.clear() if mapped not in best: best.append(mapped) return {"rows": len(raw), "ids": len({r["prdctIdntNo"] for r in raw}), "latest": latest} def check_material(src: dict, bad: dict, blind: dict) -> dict: source, data = src["mat"]["source"], src["mat"]["data"] records = {r["item_code"]: r for r in data["variables"]["mat_price"]["records"]} latest = source["latest"] for code in latest | records: cands, rec = latest.get(code, []), records.get(code) if len(cands) > 1: if rec and any(all(rec.get(k) == c[k] for k in MAT_FIELDS) for c in cands): blind[f"같은 때 공시 {code}"] = {"what": len(cands)} else: bad[code] = {"source": cands, "data": rec} continue _compare(bad, code, cands[0] if cands else None, rec, MAT_FIELDS) blind["API 스냅숏"] = {"what": src["mat"]["paths"][0].name} blind["원천 없는 묶음"] = {"what": [g["group"] for g in data.get("excluded_named_groups", [])]} _unchecked(blind, "mat_price", records.values(), {"item_code", *MAT_FIELDS}) return { "원천 줄 수": (source["rows"], data["source_row_count"]), "물품코드 수": (source["ids"], len(records)), "원문에 없는 자료 줄": (0, len(set(records) - set(latest))), } # ── 유가 ──────────────────────────────────────────────────────────────── def check_oil(src: dict, bad: dict, blind: dict) -> dict: counts = {} raw, data = src["oil"]["source"], src["oil"]["data"] prices = {r["PRODCD"]: r for r in raw["전국평균"]} for var, v in data["variables"].items(): row = prices.get(v["source_product_code"]) d = row and row["TRADE_DT"] source = row and {"value": _num(row["PRICE"]), "source_product_name": row["PRODNM"], "date": f"{d[:4]}-{d[4:6]}-{d[6:]}"} # fmt: skip _compare(bad, f"전국 {var}", source, v, ("value", "source_product_name", "date")) _compare(bad, "전국 적용일", {"effective_date": raw["수집일"]}, data, ("effective_date",)) _unchecked(blind, "oil", data["variables"].values(), {"value", "source_product_name", "date", "source_product_code"}) # fmt: skip raw, data = src["oil_regional"]["source"], src["oil_regional"]["data"] for var, v in data["variables"].items(): rows = {r["SIDOCD"]: {"sido_name": r["SIDONM"], "value": r["PRICE"]} for r in raw["시도별"].get(v["source_product_code"], [])} # fmt: skip records = {r["sido_code"]: r for r in v["records"]} for code in rows | records: _compare(bad, f"시도 {var} {code}", rows.get(code), records.get(code), ("sido_name", "value")) # fmt: skip _compare(bad, f"시도 {var} 날짜", {"date": raw["수집일"]}, v, ("date",)) counts[f"시도 {var} 줄 수"] = (len(rows), len(records)) _unchecked(blind, f"oil_regional.{var}.records", v["records"], {"sido_code", "sido_name", "value"}) # fmt: skip _unchecked(blind, "oil_regional", data["variables"].values(), {"records", "date", "source_product_code"}) # fmt: skip blind["API 스냅숏"] = {"what": [src[n]["paths"][0].name for n in ("oil", "oil_regional")]} blind["시도 거래일"] = {"what": "시도별 원천에 거래일 칸이 없음 — 수집일과만 맞댐"} return counts # ── 제비율 ────────────────────────────────────────────────────────────── def read_xlsx(path: Path) -> dict: """첫 시트 칸 — `raw` 는 적힌 칸만, `filled` 는 병합 칸 전체에 왼쪽 위 값을 퍼뜨림.""" ws = openpyxl.load_workbook(path, data_only=True).worksheets[0] raw = {c.coordinate: c.value for row in ws.iter_rows() for c in row if c.value not in (None, "")} # fmt: skip filled = dict(raw) for m in ws.merged_cells.ranges: top = ws.cell(m.min_row, m.min_col).value for row in range(m.min_row, m.max_row + 1): for col in range(m.min_col, m.max_col + 1): if top not in (None, ""): filled[f"{get_column_letter(col)}{row}"] = top return {"raw": raw, "filled": filled} def read_pension(path: Path) -> dict: """국민연금법 — 부칙 제4조① 해마다 사용자 부담률(1만분의) · 제88조③ 그 뒤 부담률(1천분의).""" text = path.read_text(encoding="utf-8") part = re.search(r"제4조\(연금보험료에 관한 특례\) ①(.*?)②", text, re.S).group(1) years = {int(y): int(n) / 100 for y, n in re.findall(r"(\d{4})년은 1만분의 (\d+)", part)} after = re.search(r"사용자가 각각 부담하되, 그 금액은 각각 기준소득월액의 1천분의 (\d+)", text) return {"years": years, "after": int(after.group(1)) / 10} BASE = {"노": "total_labor_cost", "직노": "direct_labor_cost", "건강보험료": "health_insurance_amount", "재+노": "material_cost_plus_total_labor_cost", "재+노+경": "material_plus_labor_plus_expense", "노+경+일": "labor_plus_expense_plus_overhead", "직접공사비": "direct_construction_cost", "재+직노": "material_cost_plus_direct_labor_cost"} # fmt: skip BASE_CELLS = {"rate_goyong.base": "B63", "rate_indirect_labor.base": "AC7", "rate_other_expense.base": "AL7", "rate_overhead.base": "BD7", "rate_profit.base": "BS7", "rate_equipment_payment_guarantee.base": "BZ7", "rate_subcontract_payment_guarantee.base": "BZ63", "rate_environment.base": "AU63", "rate_performance_guarantee_fee.base": "B95", "rate_safety_pct.base_without_owner_supplied_material": "EB7"} # fmt: skip SINGLE = {"rate_sanjae": "BZ51", "rate_health": "AU51", "rate_care": "BD51", "rate_retirement_mutual_aid": "AU110", "rate_wage_claim_contribution": "CS99", "rate_asbestos_contribution": "BZ99", "rate_pension": "BR51"} # fmt: skip SCALE = {"10억미만": "lt_1_billion", "10억-50억미만": "1_to_5_billion", "50억-300억미만": "5_to_30_billion", "300억-1000억미만": "30_to_100_billion", "1000억이상": "gte_100_billion"} # fmt: skip TERM = {"6개월이하(183일)": "lte_183_days", "7~12개월(365일)": "184_to_365_days", "13~36개월(1095일)": "366_to_1095_days", "36개월초과(1096일)": "gte_1096_days"} # fmt: skip WORK_TYPE = {"토목": "civil", "조경": "landscape", "산업설비(토목)": "industrial_facilities_civil"} SAFETY_SCALE = {"5억미만": "lt_500_million", "5억~50억미만": "500_million_to_5_billion", "50억이상": "gte_5_billion", "추정금액800억미만건설공사(주공종이토목인경우1,000억)": "gte_5_billion_below_manager_threshold", "추정금액800억이상건설공사(주공종이토목인경우1,000억)": "gte_5_billion_at_or_above_manager_threshold"} # fmt: skip SAFETY_WORK = {"건축공사": "building", "토목공사": "civil", "중건설공사": "heavy_construction", "특수건설공사": "special_construction"} # fmt: skip CIVIL_PRICE = {"5억미만": "lt_5_billion", "5억-30억미만": "lt_5_billion", "30억-50억미만": "lt_5_billion", "50억-100억미만": "5_to_30_billion", "100억-300억미만": "5_to_30_billion", "300억-1000억미만": "30_to_100_billion", "1000억이상": "gte_100_billion"} # fmt: skip SPECIAL_PRICE = {"5억미만": "lt_500_million", "5억-30억미만": "500_million_to_3_billion", "30억-50억미만": "3_to_10_billion", "50억-100억미만": "3_to_10_billion", "100억-300억미만": "10_to_30_billion", "300억-1000억미만": "30_to_100_billion", "1000억이상": "gte_100_billion"} # fmt: skip #: (라벨 열, 첫 줄, 끝 줄, 값 열, 라벨→자료 구간, 자료 열쇠 틀) BANDS = [ ("B", 67, 82, "AH", {"[1등급]1400억이상": "1|gte_140_billion", "[2등급]900억~1400억미만": "2|90_to_140_billion", "[3등급]570억~900억미만": "3|57_to_90_billion", "[4등급]370억~570억미만": "4|37_to_57_billion", "[5등급]220억~370억미만": "5|22_to_37_billion", "[6등급]140억~220억미만": "6|14_to_22_billion", "[7등급]고시금액~140억미만": "7|official_threshold_to_14_billion", "7등급미만": "below_7|below_official_threshold"}, "rate_goyong.brackets[{}].rate_percent"), ("AZ", 68, 94, "BU", {"도로(예시:교량,터널,활주로등)": "civil_road", "플랜트(예시:발전소,쓰레기소각장등)": "civil_plant", "지하철": "civil_subway", "철도": "civil_railway", "상하수도(예시:폐수,하수처리장,정수장등)": "civil_water_and_sewer", "항만": "civil_port", "(오탁방지막또는준설토방지막을설치하는경우)": "civil_port_with_silt_screen", "댐": "civil_dam", "택지개발": "civil_land_development", "그밖의토목공사(하천등)": "civil_other", "조경": "landscape", "주택(재개발및재건축)": "building_housing_redevelopment", "주택(신축)": "building_new_housing", "그밖의건축공사": "building_other"}, "rate_environment.all_work_types[{}].rate_percent"), ("BZ", 68, 83, "DC", {"50억미만": "lt_5_billion", "50억이상-100억미만": "5_to_10_billion", "100억이상-300억미만": "10_to_30_billion", "300억이상종심∙종평제(토목및산업설비)": "gte_30_billion_integrated_civil_or_industrial", "300억이상종심∙종평제(건축)": "gte_30_billion_integrated_building", "턴키∙대안공사": "turnkey_or_alternative"}, "rate_subcontract_payment_guarantee.brackets[{}].rate_percent"), ("BZ", 19, 30, "CI", {"토목공사(토건)": "civil_general", "산업∙설비공사": "industrial_facilities", "조경공사": "landscape"}, "rate_equipment_payment_guarantee.general_construction[{}].rate_percent"), ("CN", 19, 38, "DE", {"준설공사,포장공사": "dredging_or_paving_or_earthwork_or_scaffolding_dismantling", "토공사,비계구조물해제공사": "dredging_or_paving_or_earthwork_or_scaffolding_dismantling", "상하수도설비공사,수중공사": "water_sewer_or_underwater_or_boring_grouting", "보링그라우팅공사": "water_sewer_or_underwater_or_boring_grouting", "석공사,철근콘크리트공사": "stone_or_reinforced_concrete", "조경시설물설치,조경식재공사": "landscape_facility_or_planting_or_painting_or_rail_track_or_steel_installation", "도장공사,철도궤도공사": "landscape_facility_or_planting_or_painting_or_rail_track_or_steel_installation", "철강재설치공사": "landscape_facility_or_planting_or_painting_or_rail_track_or_steel_installation", "그외": "other"}, "rate_equipment_payment_guarantee.specialty_construction[{}].rate_percent"), ("B", 98, 112, "P", {"70억미만": "lt_7_billion", "70억이상-120억미만": "7_to_12_billion", "120억이상-250억미만": "12_to_25_billion", "250억이상-500억미만": "25_to_50_billion", "500억이상": "gte_50_billion"}, "rate_performance_guarantee_fee.brackets[{}].formula"), ("AU", 15, 46, "BD", CIVIL_PRICE, "rate_overhead.civil_landscape_industrial[{}].rate_percent"), ("AU", 15, 46, "BL", SPECIAL_PRICE, "rate_overhead.specialty_electric_communication_fire_other[{}].rate_percent"), ("AU", 15, 46, "BS", CIVIL_PRICE, "rate_profit.brackets[{}].rate_percent"), ] # fmt: skip def _formula(text) -> tuple[float, ...]: """수수료 식 속 수 — `79만원`·`75억원` 은 원으로. 원문 `[79만원+(직공비-75억원)x0.0070%]` ↔ 자료 식 글.""" unit = {"만원": 10**4, "억원": 10**8, "": 1} return tuple(float(n.replace(",", "")) * unit[u] for n, u in re.findall(r"(\d[\d,.]*)(만원|억원)?", str(text))) # fmt: skip def rates_expected(xlsx: dict, pension: dict) -> dict: """조달청 제비율 xlsx · 국민연금법 → 자료 `variables` 를 편 열쇠(`flatten`)와 같은 꼴의 값.""" raw, filled = xlsx["raw"], xlsx["filled"] exp = {key: BASE[re.search(r"\(([^)]*)\)", _t(raw[cell])).group(1)] for key, cell in BASE_CELLS.items()} # fmt: skip for var, cell in SINGLE.items(): base, rate = re.fullmatch(r"\(([^)]*)\)x([\d.]+)", _t(raw[cell])).groups() exp[f"{var}.base"] = BASE[base] exp["연금 2026 xlsx" if var == "rate_pension" else f"{var}.rate_percent"] = float(rate) for year, rate in (pension["years"] | {2033: pension["after"]}).items(): exp[f"rate_pension.annual_rates[{year}].rate_percent"] = rate exp["rate_pension.rate_from_2033_percent"] = pension["after"] for r in range(15, 55): if (term := raw.get(f"M{r}")) is None: continue for var, cols in (("rate_indirect_labor", "AC AF AI"), ("rate_other_expense", "AL AO AR")): for col in cols.split(): key = f"{SCALE[_t(filled[f'B{r}'])]}|{TERM[_t(term)]}|{WORK_TYPE[_t(raw[f'{col}9'])]}" # fmt: skip exp[f"{var}.brackets[{key}].rate_percent"] = _num(filled[f"{col}{r}"]) unit = 1000 if "천원" in raw["FA15"] else 1 for r in range(19, 51): if (label := raw.get(f"EB{r}")) is None: continue scale = SAFETY_SCALE[_t(filled.get(f"DR{r}", filled[f"DK{r}"]))] key = f"rate_safety_pct.brackets[{scale}|{SAFETY_WORK[_t(label)]}]" exp[f"{key}.rate_percent"] = _num(filled[f"ES{r}"]) if f"FA{r}" in filled: exp[f"{key}.base_amount_krw"] = _num(filled[f"FA{r}"]) * unit default, civil = re.findall(r"([\d,]+)억", _t(raw["DR35"])) exp["rate_safety_pct.manager_thresholds.default_estimated_amount_krw"] = _num(default) * 10**8 exp["rate_safety_pct.manager_thresholds.civil_main_work_estimated_amount_krw"] = _num(civil) * 10**8 # fmt: skip exp["rate_safety_pct.minimum_total_construction_amount_krw"] = int(re.search(r"(\d+)천만원", raw["DK51"]).group(1)) * 10**7 # fmt: skip exp["rate_retirement_mutual_aid.minimum_estimated_amount_krw"] = int(re.search(r"(\d+)억", raw["AU113"]).group(1)) * 10**8 # fmt: skip for col, first, last, value_col, groups, template in BANDS: got: dict[str, set] = {} for r in range(first, last + 1): if (label := raw.get(f"{col}{r}")) is None: continue value = filled.get(f"{value_col}{r}") value = _formula(value) if template.endswith("formula") else _num(value) got.setdefault(groups.get(_t(label), f"({_t(label)})"), set()).add(value) for group, values in got.items(): if not (group.startswith("(") and values == {None}): value = values.pop() if len(values) == 1 else sorted(values, key=str) exp[template.format(group)] = list(value) if isinstance(value, tuple) else value for candidate, work_type in (("road", "civil_road"), ("other_civil_work", "civil_other")): exp[f"rate_environment.forest_road_candidates[{candidate}].rate_percent"] = exp[f"rate_environment.all_work_types[{work_type}].rate_percent"] # fmt: skip return exp def flatten(obj, path: str = "", out: dict | None = None) -> dict: """자료 `variables` 를 `이름.칸[구간|종류].rate_percent` 꼴로 폄 — 목록 줄은 값 아닌 칸을 이어 열쇠로.""" out = {} if out is None else out if isinstance(obj, dict): for k, v in obj.items(): flatten(v, f"{path}.{k}" if path else k, out) elif isinstance(obj, list) and obj and isinstance(obj[0], dict): values = {"rate_percent", "base_amount_krw", "formula"} for item in obj: label = "|".join(str(v) for k, v in item.items() if k not in values) for k in values & item.keys(): out[f"{path}[{label}].{k}"] = item[k] else: out[path] = obj return out def check_rate(src: dict, bad: dict, blind: dict) -> dict: exp = dict(src["rates"]["source"]) data = flatten(src["rates"]["data"]["variables"]) xlsx_2026 = exp.pop("연금 2026 xlsx") law_2026 = exp.get("rate_pension.annual_rates[2026].rate_percent") if xlsx_2026 != law_2026: bad["연금 2026 xlsx↔법"] = {"source": xlsx_2026, "data": law_2026} for key in exp | data: if key not in exp: blind[f"안 잰 칸 {key}"] = {"what": data[key]} continue value = list(_formula(data[key])) if key.endswith("formula") and key in data else data.get(key) # fmt: skip if exp[key] != value: bad[key] = {"source": exp[key], "data": value} blind["processing_rules"] = {"what": sorted(src["rates"]["data"].get("processing_rules", {}))} blind["조달청 요약표"] = {"what": src["rates"]["paths"][0].name} return {"원문 값 수": (len(exp), len(set(exp) & set(data)))} # ── 맞대기 ────────────────────────────────────────────────────────────── READERS = { "labor_const": read_labor_const, "labor_mfg": read_labor_mfg, "mach": read_machine, "mat": read_material, "oil": lambda p: json.loads(p.read_text(encoding="utf-8")), "oil_regional": lambda p: json.loads(p.read_text(encoding="utf-8")), } # fmt: skip CHECKS = {"labor": check_labor, "machine": check_machine, "material": check_material, "oil": check_oil, "rate": check_rate} # fmt: skip def load_sources() -> dict: src = {} for name, file in FILES.items(): data = json.loads((DATA / file).read_text(encoding="utf-8")) paths = [ROOT / s["path"] for s in data["sources"]] src[name] = {"data": data, "paths": paths} if name == "rates": src[name]["source"] = rates_expected(read_xlsx(paths[0]), read_pension(paths[1])) else: src[name]["source"] = READERS[name](paths[0]) return src @pytest.fixture(scope="module") def src() -> dict: return load_sources() def run_checks(src: dict) -> tuple[dict[str, dict], dict[str, dict]]: """(갈래별 어긋남·못 보는 자리, 갈래별 셈 `(원문, 자료)`). 틀어진 셈은 어긋남에 `셈 …` 으로도 들어감.""" out: dict[str, dict] = {kind: {} for kind in KIND_NAMES} counts = {} for kind, check in CHECKS.items(): counts[kind] = check(src, out[kind], out[f"{kind}_blind"]) for name, (s, d) in counts[kind].items(): if s != d: out[kind][f"셈 {name}"] = {"source": s, "data": d} return out, counts def current_mismatches(src: dict) -> dict[str, dict]: return run_checks(src)[0] def load_known() -> dict[str, dict]: return json.loads(KNOWN.read_text(encoding="utf-8")) # ── 시험 ──────────────────────────────────────────────────────────────── @pytest.mark.parametrize("kind", list(KIND_NAMES)) def test_알려진_어긋남_밖은_없음(src: dict, kind: str) -> None: """알려진 목록과 똑같아야 함 — 새로 어긋남 · 모습 바뀜 · 고쳐짐 셋 다 빨강. `why` 는 맞대기에서 뺌.""" now = current_mismatches(src)[kind] known = {k: _without_why(v) for k, v in load_known()[kind].items()} lines: list[str] = [] for key in sorted(set(now) - set(known)): lines.append(f" 새로 어긋남 {key}: {json.dumps(now[key], ensure_ascii=False)}") for key in sorted(set(now) & set(known)): if now[key] != known[key]: lines.append( f" 모습 바뀜 {key}: 목록 {json.dumps(known[key], ensure_ascii=False)}" f"\n 지금 {json.dumps(now[key], ensure_ascii=False)}" ) for key in sorted(set(known) - set(now)): lines.append(f" 고쳐짐 {key} — 목록에서 지울 것(--prune)") assert not lines, f"{KIND_NAMES[kind]} {len(lines)}건 — 원문 ↔ 자료:\n" + "\n".join(lines) @pytest.mark.parametrize("kind", KINDS) def test_셈이_맞음(src: dict, kind: str) -> None: """원문 줄 수 = 자료 줄 수 · 자료 줄은 모두 원문에서 찾음 — 틀어진 셈은 목록 `셈 …` 과 똑같을 때만 통과.""" known = load_known()[kind] wrong = [ f" {name}: 원문 {s} · 자료 {d}" for name, (s, d) in run_checks(src)[1][kind].items() if s != d and _without_why(known.get(f"셈 {name}", {})) != {"source": s, "data": d} ] assert not wrong, f"{KIND_NAMES[kind]} 셈 틀어짐(목록 밖):\n" + "\n".join(wrong) if __name__ == "__main__" and "--prune" in sys.argv: # 고쳐졌거나 모습이 바뀐 줄만 지움 — 새 어긋남은 안 보탬(보태면 빨강이 조용히 묻힘). current = current_mismatches(load_sources()) data = load_known() for kind in KIND_NAMES: before = len(data[kind]) data[kind] = {k: v for k, v in data[kind].items() if current[kind].get(k) == _without_why(v)} # fmt: skip print(f"{KIND_NAMES[kind]}: {before} → {len(data[kind])}") KNOWN.write_text(json.dumps(data, ensure_ascii=False, indent=1) + "\n", encoding="utf-8")