knowledge(마스터): 조달청 2022하 시설자재가격 받기 · 표 빌더 · 12 재료·없는 재료 대조

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PAdA5ThqmtVSsbzjusk1cJ
2026-09-20 23:01:18 +09:00
parent 53151917ba
commit eb88cf9a67
12 changed files with 7071 additions and 0 deletions
@@ -0,0 +1,86 @@
+# -*- coding: utf-8 -*-
+"""조달청 시설공통자재 xlsx(4분야) → 품명·규격·단위·금액 csv (지식DB 폴더 안). 마스터 JSON 은 안 만짐.
+
+쓰기: ./venv/Scripts/python.exe resources/master_data/scripts/build_시설자재가격.py
+세기: ... build_시설자재가격.py --count  (12 재료 · ref/_없는_재료.md 이름이 자료에 몇 줄인지 출력)
+"""
+
+from __future__ import annotations
+
+import csv
+import re
+import sys
+from pathlib import Path
+
+import openpyxl
+
+ROOT = Path(__file__).resolve().parents[3]
+DIR = ROOT / "resources/knowledge/original/원가계산/자재단가/조달청_시설자재_22하"
+OUT = DIR / "시설공통자재_22하.csv"
+MISSING = ROOT / "resources/master_data/ref/_없는_재료.md"
+TWELVE = [
+    "합판",
+    "각재",
+    "건설용거푸집",
+    "동바리",
+    "파이프서포트",
+    "비계",
+    "클램프",
+    "철선",
+    "못",
+    "폼타이",
+    "유공관",
+    "종자",
+    "방부",
+    "잡석",
+]
+
+
+def rows():
+    for f in sorted(DIR.glob("시설공통자재_*.xlsx")):
+        ws = openpyxl.load_workbook(f, read_only=True, data_only=True).worksheets[0]
+        head = None
+        for r in ws.iter_rows(values_only=True):
+            if head is None:
+                head = r if r and r[0] == "물품분류번호" else None
+                continue
+            if r[2]:
+                yield (
+                    f.stem.split("_")[1],
+                    r[2],
+                    r[3] or "",
+                    r[4] or "",
+                    str(r[5] or "").replace(",", ""),
+                )
+
+
+def count(data, words):
+    return {w: sum(1 for d in data if w in f"{d[1]}{d[2]}") for w in words}
+
+
+def main():
+    data = list(rows())
+    if "--count" in sys.argv:
+        print(len(data), "줄")
+        for w, n in count(data, TWELVE).items():
+            print("12재료", w, n)
+        for m in re.finditer(
+            r"^\| MP\d+ \| ([^|]+?) \|", MISSING.read_text(encoding="utf-8"), re.M
+        ):
+            name = re.sub(r"\(.*", "", m.group(1)).strip()
+            n = (
+                count(data, [name])[name]
+                if len(name) >= 3
+                else sum(1 for d in data if d[1] == name)
+            )  # 짧은 이름은 품명 전체 일치만
+            print(f"없는재료	{name}	{n}")
+        return
+    with OUT.open("w", encoding="utf-8-sig", newline="") as fp:
+        w = csv.writer(fp)
+        w.writerow(["분야", "품명", "규격", "단위", "금액"])
+        w.writerows(data)
+    print(OUT.name, len(data), "줄")
+
+
+if __name__ == "__main__":
+    main()