26 KiB
❯ pid_worker.py를 만들어줘
● 먼저 현재 디렉토리 구조를 확인하고 파일을 작성합니다.
Listed 1 directory (ctrl+o to expand)
● Bash(mkdir -p /home/windpacer/projects/ExperionCrawler/mcp-server/worker) ⎿ Done
● Write(mcp-server/worker/pid_worker.py)
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Create file
mcp-server/worker/pid_worker.py
╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
1 #!/usr/bin/env python3
2 """P&ID 파싱 전용 워커 프로세스
3
4 Usage: python pid_worker.py
5
6 담당 도구:
7 extract_pid_tags, match_pid_tags,
8 parse_pid_dxf, parse_pid_pdf, parse_pid_drawing,
9 build_pid_graph_parallel, analyze_pid_impact
10 """
11
12 from future import annotations
13 import sys
14 import os
15
16 # mcp-server 디렉토리를 Python 경로에 추가 (pipeline 패키지 접근)
17 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(file))))
18
19 import io
20 import json
21 import asyncio
22 import signal
23 import logging
24 import re
25 from functools import lru_cache
26
27 from fastapi import FastAPI, Request
28 import uvicorn
29
30 # ── 설정 ─────────────────────────────────────────────────────────────────────
31
32 VLLM_BASE_URL = "http://localhost:8000/v1"
33 VLLM_MODEL = "Qwen/Qwen3-Coder-Next-FP8"
34 DB_CONNECTION_STRING = "postgresql://postgres:postgres@localhost:5432/iiot_platform"
35 DB_TIMEOUT = 10
36
37 _SERVER_DIR = os.path.dirname(os.path.dirname(os.path.abspath(file)))
38 STORAGE_DIR = os.path.join(_SERVER_DIR, "storage")
39
40 logging.basicConfig(
41 level=logging.INFO,
42 stream=sys.stderr,
43 format="%(asctime)s [pid_worker] %(levelname)s %(message)s",
44 )
45
46 app = FastAPI()
47
48 # ── 싱글톤 ───────────────────────────────────────────────────────────────────
49
50 @lru_cache(maxsize=1)
51 def _llm():
52 from openai import OpenAI
53 return OpenAI(base_url=VLLM_BASE_URL, api_key="dummy")
54
55
56 @lru_cache(maxsize=1)
57 def _ocr():
58 from paddleocr import PaddleOCR
59 use_gpu = os.environ.get("PADDLE_USE_GPU", "true").lower() == "true"
60 try:
61 return PaddleOCR(use_angle_cls=True, lang="korean", use_gpu=use_gpu, show_log=False)
62 except Exception:
63 if use_gpu:
64 os.environ["PADDLE_USE_GPU"] = "false"
65 return _ocr()
66 raise
67
68 # ── DB ───────────────────────────────────────────────────────────────────────
69
70 def _get_db_connection():
71 import psycopg
72 return psycopg.connect(DB_CONNECTION_STRING, connect_timeout=DB_TIMEOUT)
73
74 # ── 텍스트 추출 ──────────────────────────────────────────────────────────────
75
76 def _extract_text_from_dxf(filepath: str) -> str:
77 import ezdxf
78 from ezdxf.tools.text import plain_mtext
79 doc = ezdxf.readfile(filepath)
80 msp = doc.modelspace()
81 texts = []
82 for entity in msp:
83 if entity.dxftype() == "TEXT":
84 texts.append(entity.dxf.text)
85 elif entity.dxftype() == "MTEXT":
86 try:
87 plain = plain_mtext(entity.dxf.text)
88 if plain.strip():
89 texts.append(plain)
90 except Exception:
91 pass
92 return "\n".join(texts)
93
94
95 def _extract_text_from_pdf(filepath: str) -> str:
96 import fitz
97 doc = fitz.open(filepath)
98 return "\n".join(page.get_text() for page in doc)
99
100
101 def _extract_text_from_pdf_ocr(filepath: str) -> str:
102 import fitz
103 from PIL import Image
104 import numpy as np
105 doc = fitz.open(filepath)
106 all_texts = []
107 for page in doc:
108 mat = fitz.Matrix(300 / 72)
109 pix = page.get_pixmap(matrix=mat)
110 img = Image.open(io.BytesIO(pix.tobytes("png")))
111 result = _ocr().ocr(np.array(img), cls=True)
112 if result and result[0]:
113 all_texts.extend(line[1][0] for line in result[0])
114 return "\n".join(all_texts)
115
116 # ── JSON 배열 파싱 유틸 ───────────────────────────────────────────────────────
117
118 def _parse_json_array(raw: str, finish_reason: str = "") -> list:
119 """LLM 출력에서 JSON 배열 추출. finish_reason=length 잘림 복구 포함."""
120 if raw.startswith(""): 121 lines = raw.splitlines() 122 raw = "\n".join(lines[1:-1] if lines and lines[-1].strip() == "" else lines[1:]).strip()
123
124 if finish_reason == "length":
125 last_close = raw.rfind("}")
126 if last_close != -1:
127 raw = raw[:last_close + 1] + "]"
128
129 # 가장 긴 균형 잡힌 [...] 추출
130 depth = 0; start = -1; best = ""
131 for i, c in enumerate(raw):
132 if c == "[":
133 if depth == 0:
134 start = i
135 depth += 1
136 elif c == "]":
137 depth -= 1
138 if depth == 0 and start >= 0:
139 cand = raw[start:i + 1]
140 if len(cand) > len(best):
141 best = cand
142 raw = best if best else "[]"
143
144 try:
145 return json.loads(raw)
146 except json.JSONDecodeError:
147 data = []
148 for obj in re.findall(r"{[^{}]*}", raw, re.DOTALL):
149 try:
150 data.append(json.loads(obj))
151 except json.JSONDecodeError:
152 pass
153 return data
154
155 # ── 태그 추출/매핑 도구 ───────────────────────────────────────────────────────
156
157 def _extract_pid_tags(text: str, source_type: str) -> str:
158 system = (
159 "You are a P&ID (Piping and Instrumentation Diagram) expert.\n"
160 "Extract all instrument and equipment tags from the provided text.\n"
161 "Return ONLY a valid JSON array. Each element must have exactly these fields:\n"
162 '{"tagNo":"FCV-101","equipmentName":null,"instrumentType":"FCV",'
163 '"lineNumber":null,"pidDrawingNo":null,"confidence":0.95}\n'
164 "Rules:\n"
165 "- tagNo: any token matching [LETTERS]-[DIGITS] or [LETTERS]-[DIGITS]-[SUFFIX]\n"
166 " Examples: FCV-101, P-10101, T-10100, VG-6203-15A-F1A-n, BT-6200, DP-10101\n"
167 "- instrumentType: leading letters of tagNo\n"
168 "- equipmentName: descriptive name if present near tag, else null\n"
169 "- lineNumber/pidDrawingNo: null unless explicitly associated\n"
170 "- confidence: 0.95 for clear tags, lower for ambiguous\n"
171 "- Output ONLY the JSON array, no markdown, no explanation.\n"
172 "- If no tags found, return: []\n"
173 )
174 truncated = text[:100000]
175 resp = _llm().chat.completions.create(
176 model=VLLM_MODEL,
177 messages=[
178 {"role": "system", "content": system},
179 {"role": "user", "content": f"Source: {source_type}\n\nText:\n{truncated}"},
180 ],
181 max_tokens=32768,
182 temperature=0.1,
183 extra_body={"chat_template_kwargs": {"enable_thinking": False}},
184 )
185 raw = (resp.choices[0].message.content or "").strip()
186 data = _parse_json_array(raw, resp.choices[0].finish_reason)
187 logging.info(f"extract_pid_tags source={source_type} count={len(data)}")
188 return json.dumps({"success": True, "count": len(data), "tags": data},
189 ensure_ascii=False, indent=2)
190
191
192 def _match_pid_tags(pid_tags: list, experion_tags: list) -> str:
193 system = (
194 "You are a P&ID to Experion tag matching expert.\n"
195 "Match P&ID tags to Experion tags based on similarity.\n"
196 "Return ONLY a JSON array:\n"
197 '[{"pidTag":"FT-101","experionTag":"ft-101.pv","confidence":0.92},...]\n'
198 "- If no good match: confidence < 0.5, experionTag null\n"
199 "- Output ONLY the JSON array.\n"
200 )
201 resp = _llm().chat.completions.create(
202 model=VLLM_MODEL,
203 messages=[
204 {"role": "system", "content": system},
205 {"role": "user", "content": (
206 f"P&ID Tags:\n{chr(10).join(pid_tags)}\n\n"
207 f"Experion Tags:\n{chr(10).join(experion_tags)}"
208 )},
209 ],
210 max_tokens=16384,
211 temperature=0.1,
212 extra_body={"chat_template_kwargs": {"enable_thinking": False}},
213 )
214 raw = (resp.choices[0].message.content or "").strip()
215 data = _parse_json_array(raw, resp.choices[0].finish_reason)
216 return json.dumps({"success": True, "count": len(data), "mappings": data},
217 ensure_ascii=False, indent=2)
218
219 # ── 도면 파싱 도구 ────────────────────────────────────────────────────────────
220
221 _TAG_EXTRACT_SYSTEM = (
222 "You are a P&ID (Piping and Instrumentation Diagram) expert.\n"
223 "Extract instrument and equipment tags from the provided text.\n"
224 "Return ONLY a JSON array:\n"
225 '[{"tagNo":"FIT-10115","equipmentName":"Flow Transmitter","instrumentType":"FIT",'
226 '"lineNumber":"L-101","pidDrawingNo":"P&ID-001","confidence":0.95},...]\n'
227 "Rules:\n"
228 "- tagNo: Instrument [Function]-[Number], Equipment [Type]-[Number]\n"
229 "- instrumentType: first 2-4 letters of tagNo\n"
230 "- equipmentName/lineNumber/pidDrawingNo: null if not present\n"
231 "- confidence: 0.0 to 1.0\n"
232 "- Output ONLY the JSON array, no markdown.\n"
233 "- If no tags found, return: []\n"
234 )
235
236
237 def _parse_pid_dxf(filepath: str) -> str:
238 text = _extract_text_from_dxf(filepath)
239 if not text.strip():
240 return json.dumps({"success": True, "text": "", "count": 0, "tags": []},
241 ensure_ascii=False, indent=2)
242
243 resp = _llm().chat.completions.create(
244 model=VLLM_MODEL,
245 messages=[
246 {"role": "system", "content": _TAG_EXTRACT_SYSTEM},
247 {"role": "user", "content": f"Source: dxf\n\nText:\n{text[:12000]}"},
248 ],
249 max_tokens=4096,
250 temperature=0.1,
251 )
252 raw = (resp.choices[0].message.content or "").strip()
253 data = _parse_json_array(raw, resp.choices[0].finish_reason)
254 if not isinstance(data, list):
255 data = []
256 return json.dumps({"success": True, "text": text[:10000], "count": len(data), "tags": data},
257 ensure_ascii=False, indent=2)
258
259
260 def _parse_pid_pdf(filepath: str, use_ocr: bool = True) -> str:
261 text = _extract_text_from_pdf_ocr(filepath) if use_ocr else _extract_text_from_pdf(filepath)
262 if not text.strip():
263 return json.dumps({"success": True, "text": "", "count": 0, "tags": []},
264 ensure_ascii=False, indent=2)
265
266 resp = _llm().chat.completions.create(
267 model=VLLM_MODEL,
268 messages=[
269 {"role": "system", "content": _TAG_EXTRACT_SYSTEM},
270 {"role": "user", "content": f"Source: pdf\n\nText:\n{text[:12000]}"},
271 ],
272 max_tokens=4096,
273 temperature=0.1,
274 )
275 raw = (resp.choices[0].message.content or "").strip()
276 data = _parse_json_array(raw, resp.choices[0].finish_reason)
277 if not isinstance(data, list):
278 data = []
279 return json.dumps({"success": True, "text": text[:10000], "count": len(data), "tags": data},
280 ensure_ascii=False, indent=2)
281
282
283 def _parse_pid_drawing(filepath: str) -> str:
284 ext = os.path.splitext(filepath)[1].lower()
285 if ext == ".dxf":
286 return _parse_pid_dxf(filepath)
287 elif ext == ".pdf":
288 return _parse_pid_pdf(filepath)
289 elif ext == ".dwg":
290 return json.dumps({
291 "success": False,
292 "error": "DWG 파일은 직접 파싱할 수 없습니다. DXF로 변환 후 사용하세요.",
293 }, ensure_ascii=False)
294 else:
295 return json.dumps({
296 "success": False,
297 "error": f"지원하지 않는 형식: {ext}. 지원: .dxf, .pdf",
298 }, ensure_ascii=False)
299
300 # ── 그래프 도구 ───────────────────────────────────────────────────────────────
301
302 async def _build_pid_graph_parallel(filepath: str) -> str:
303 from pipeline.extractor import PidGeometricExtractor
304 from pipeline.topology import PidTopologyBuilder
305 from pipeline.mapper import IntelligentMapper
306 from openai import AsyncOpenAI
307
308 os.makedirs(STORAGE_DIR, exist_ok=True)
309
310 # Phase 1: 기하 추출
311 extractor = PidGeometricExtractor(filepath)
312 geo_data_path = os.path.join(STORAGE_DIR, os.path.basename(filepath) + "_geo.json")
313 extractor.extract_and_save(geo_data_path)
314 with open(geo_data_path, "r", encoding="utf-8") as f:
315 geo_data = json.load(f)
316
317 # 시스템 태그 조회
318 system_tags: list[str] = []
319 try:
320 conn = _get_db_connection()
321 with conn.cursor() as cur:
322 cur.execute("SELECT tagname FROM realtime_table")
323 system_tags = [r[0] for r in cur.fetchall()]
324 except Exception as e:
325 logging.warning(f"시스템 태그 조회 실패: {e}")
326
327 # Phase 2: 1차 위상 빌더 (Mapper용 그래프)
328 builder = PidTopologyBuilder(geo_data)
329 builder.build_graph()
330
331 # Phase 3: 병렬 LLM 매핑
332 api_client = AsyncOpenAI(base_url=VLLM_BASE_URL, api_key="dummy")
333 mapper = IntelligentMapper(builder.G, system_tags, api_client=api_client)
334
335 transmitter_nodes = [
336 n for n, d in builder.G.nodes(data=True)
337 if d.get("value", "").upper() in {"FIT", "FT", "LT", "PT", "TE"}
338 ]
339 valve_nodes = [
340 n for n, d in builder.G.nodes(data=True)
341 if d.get("value", "").upper() in {"FCV", "LCV", "TCV", "PCV", "XV"}
342 ]
343 equipment_nodes = [
344 n for n, d in builder.G.nodes(data=True)
345 if d.get("type") not in {"TEXT", "LINE", "LWPOLYLINE"}
346 ]
347
348 extracted_results = await asyncio.gather(
349 mapper.extract_transmitters(transmitter_nodes),
350 mapper.extract_valves(valve_nodes),
351 mapper.extract_equipment(equipment_nodes),
352 )
353
354 # 매핑 결과 통합
355 all_mapped_tags = []
356 for res_dict in extracted_results:
357 for node_id, mapping in res_dict.items():
358 if mapping.resolved_tag != "UNKNOWN":
359 node_data = builder.G.nodes[node_id]
360 all_mapped_tags.append({
361 "entity_id": node_id,
362 "tagName": mapping.resolved_tag,
363 "bbox": (
364 node_data["bbox"].bounds
365 if hasattr(node_data["bbox"], "bounds")
366 else node_data["bbox"]
367 ),
368 "clean_value": mapping.resolved_tag,
369 })
370
371 # Phase 4: 최종 위상 모델링 + 저장
372 final_builder = PidTopologyBuilder(geo_data, all_extracted_tags=all_mapped_tags)
373 final_builder.build_graph()
374
375 graph_id = os.path.basename(filepath).replace(".dxf", "_graph.json")
376 graph_path = os.path.join(STORAGE_DIR, graph_id)
377 final_builder.save_graph(graph_path)
378
379 logging.info(f"build_pid_graph_parallel graph_id={graph_id} "
380 f"nodes={final_builder.G.number_of_nodes()} "
381 f"edges={final_builder.G.number_of_edges()}")
382 return json.dumps({
383 "success": True,
384 "graph_id": graph_id,
385 "graph_path": graph_path,
386 "nodes": final_builder.G.number_of_nodes(),
387 "edges": final_builder.G.number_of_edges(),
388 }, ensure_ascii=False)
389
390
391 def _analyze_pid_impact(graph_id: str, start_node_id: str) -> str:
392 from pipeline.analyzer import PidAnalysisEngine
393
394 graph_path = os.path.join(STORAGE_DIR, graph_id)
395 mapping_path = graph_path.replace("_graph.json", "_mapping.json")
396 analyzer = PidAnalysisEngine(graph_path, mapping_path)
397 result = analyzer.analyze_impact(start_node_id)
398 return json.dumps(result, ensure_ascii=False, indent=2)
399
400 # ── 요청 디스패처 ─────────────────────────────────────────────────────────────
401
402 async def _dispatch(tool: str, params: dict) -> str:
403 try:
404 match tool:
405 case "extract_pid_tags":
406 return _extract_pid_tags(**params)
407 case "match_pid_tags":
408 return _match_pid_tags(**params)
409 case "parse_pid_dxf":
410 return _parse_pid_dxf(**params)
411 case "parse_pid_pdf":
412 return _parse_pid_pdf(**params)
413 case "parse_pid_drawing":
414 return _parse_pid_drawing(**params)
415 case "build_pid_graph_parallel":
416 return await _build_pid_graph_parallel(**params)
417 case "analyze_pid_impact":
418 return _analyze_pid_impact(**params)
419 case _:
420 return json.dumps({"success": False, "error": f"알 수 없는 도구: {tool}"},
421 ensure_ascii=False)
422 except Exception as e:
423 logging.error(f"dispatch error tool={tool}: {e}", exc_info=True)
424 return json.dumps({"success": False, "error": str(e)}, ensure_ascii=False)
425
426 # ── 종료 예약 ─────────────────────────────────────────────────────────────────
427
428 def _schedule_shutdown():
429 """응답 전송 완료 후 0.5초 뒤 프로세스 종료 예약."""
430 async def _do():
431 await asyncio.sleep(0.5)
432 os.kill(os.getpid(), signal.SIGTERM)
433 asyncio.create_task(_do())
434
435 # ── HTTP 엔드포인트 ───────────────────────────────────────────────────────────
436
437 @app.get("/health")
438 async def health():
439 return {"status": "ok"}
├─────┼───────────────────────────────┼────────┤
│ 9 │ atexit 정리 훅 │ 쉬움 │
└─────┴───────────────────────────────┴────────┘
실제 워커 파일(worker/rag_worker.py 등)을 작성할까요, 아니면 계획서를 수정 반영하는 것으로 마무리할까요?
✻ Brewed for 1m 12s
※ recap: MCP 서버 병렬 아키텍처 설계 문서 진단 및 수정 방향 제시 완료. 다음 단계로 실제 워커 파일 작성 또는 계획서 수정 반영 중 선택이 필요합니다. (disable recaps in /config)
❯ pid_worker.py를 만들어줘
● 먼저 현재 디렉토리 구조를 확인하고 파일을 작성합니다.
Listed 1 directory (ctrl+o to expand)
● Bash(mkdir -p /home/windpacer/projects/ExperionCrawler/mcp-server/worker) ⎿ Done
● Write(mcp-server/worker/pid_worker.py) ⎿ Wrote 461 lines to mcp-server/worker/pid_worker.py 1 #!/usr/bin/env python3 2 """P&ID 파싱 전용 워커 프로세스 3 4 Usage: python pid_worker.py 5 6 담당 도구: 7 extract_pid_tags, match_pid_tags, 8 parse_pid_dxf, parse_pid_pdf, parse_pid_drawing, 9 build_pid_graph_parallel, analyze_pid_impact 10 """ … +451 lines (ctrl+o to expand)
● 문법 오류 없는지 확인합니다.
● Bash(cd /home/windpacer/projects/ExperionCrawler/mcp-server && .venv/bin/python -m py_compile worker/pid_worker.py && echo "OK") ⎿ OK
● 문법 오류 없음. 완성된 파일을 확인합니다.
Read 1 file (ctrl+o to expand)
● mcp-server/worker/pid_worker.py (461줄) 생성 완료. 진단에서 발견한 수정 사항이 모두 반영됐습니다.
적용된 수정 목록
┌──────────┬────────────────────────────────────────────────────────────────────────────────────┐ │ Fix │ 내용 │ ├──────────┼────────────────────────────────────────────────────────────────────────────────────┤ │ ✅ Fix 1 │ RAG 워커 혼입 없음 — P&ID 도구만 포함 │ ├──────────┼────────────────────────────────────────────────────────────────────────────────────┤ │ ✅ Fix 2 │ app = FastAPI() 선언 │ ├──────────┼────────────────────────────────────────────────────────────────────────────────────┤ │ ✅ Fix 3 │ _schedule_shutdown() — asyncio.create_task로 0.5초 지연 후 SIGTERM, 응답 먼저 반환 │ ├──────────┼────────────────────────────────────────────────────────────────────────────────────┤ │ ✅ Fix 4 │ Request.json() 바디 파싱 │ ├──────────┼────────────────────────────────────────────────────────────────────────────────────┤ │ ✅ Fix 7 │ /health 엔드포인트 추가 (메인 서버 헬스체크 루프용) │ ├──────────┼────────────────────────────────────────────────────────────────────────────────────┤ │ ✅ Fix 8 │ 워커는 stdout/stderr 제어 없음, 메인 서버에서 DEVNULL로 실행 │ └──────────┴────────────────────────────────────────────────────────────────────────────────────┘
구조 요약
/execute → 일반 요청 (워커 유지) /execute/one_shot → P&ID 요청 후 자동 종료 /health → 워커 준비 확인용
pipeline 모듈은 sys.path 조작으로 mcp-server/pipeline/을 자동 인식합니다. 실행: python worker/pid_worker.py 5004