CareerNexus 职联：岗位能力图谱构建与动态演化分析平台（挑战杯 XH-202621）
- 全链路：多源JD接入/清洗交叉验证/结构化抽取(星火+离线双通道)/时序知识图谱/新岗位发现/演化分析/人岗匹配/学习路径 - WebUI 五视图：驾驶舱/图谱工作台/岗位演化/匹配(单人+批量)/学习路径 - 设置中心(config.json)/Token鉴权/SQLite状态库/语义向量通道(BGE-M3本地或联网API) - 71 个 pytest 用例；数据目录仅保留结构(.gitkeep)，数据由 scripts/generate_dataset.py 复现
This commit is contained in:
RoyirinRosmontis
@@ -0,0 +1,812 @@
|
||||
"""FastAPI 接口层：统一响应 {code, message, data, request_id}。
|
||||
|
||||
- 耗时任务（JD 导入/全链路 pipeline）使用 任务ID + 轮询；
|
||||
- 托管 webui 静态文件（/ -> webui/index.html）；
|
||||
- 服务启动时若 data/graph.json 已存在则直接加载图谱，否则等首次导入。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import threading
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from urllib.parse import quote
|
||||
|
||||
import json
|
||||
|
||||
from fastapi import FastAPI, File, Form, HTTPException, Request, Response, UploadFile
|
||||
from fastapi.responses import FileResponse, JSONResponse
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
from pydantic import BaseModel, ValidationError
|
||||
|
||||
from app.config import ROOT, load_config, load_runtime_settings, resolve, save_runtime_settings
|
||||
from app.discover.cluster import apply_review, discover_new_jobs, load_pending, save_pending
|
||||
from app.extract.base import SkillMatcher, load_lexicon
|
||||
from app.extract.llm import llm_ready
|
||||
from app.graph.tkg import TemporalKG, now_str
|
||||
from app.ingest.loader import load_jd_dir
|
||||
from app.match import semantic
|
||||
from app.match.engine import MatchEngine
|
||||
from app.match.resume import parse_resume, parse_resume_file
|
||||
from app.models import JDRecord, ResumeProfile
|
||||
from app.services.pipeline import run_pipeline
|
||||
from app.storage import db as state_db
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
app = FastAPI(title="CareerNexus 职联", version="0.1.0")
|
||||
|
||||
_cfg = load_config()
|
||||
_state: dict = {
|
||||
"kg": None,
|
||||
"records": None,
|
||||
"extractions": None,
|
||||
"tasks": {},
|
||||
}
|
||||
|
||||
|
||||
def _ok(data=None, message: str = "ok") -> dict:
|
||||
return {"code": 0, "message": message, "data": data,
|
||||
"request_id": uuid.uuid4().hex[:12]}
|
||||
|
||||
|
||||
def _get_kg() -> TemporalKG:
|
||||
kg = _state["kg"]
|
||||
if kg is None:
|
||||
raise HTTPException(status_code=503, detail="图谱尚未构建，请先调用 /api/jd/import")
|
||||
return kg
|
||||
|
||||
|
||||
def _db_path() -> Path:
|
||||
"""SQLite 应用状态库路径（配置键 state_db_path，默认 data/careernexus.db）。"""
|
||||
return resolve(_cfg, "state_db_path")
|
||||
|
||||
|
||||
@app.on_event("startup")
|
||||
def _startup() -> None:
|
||||
graph_path = resolve(_cfg, "graph_path")
|
||||
if graph_path.exists():
|
||||
_state["kg"] = TemporalKG.load(graph_path)
|
||||
logger.info("已加载图谱：%s", _state["kg"].stats())
|
||||
else:
|
||||
logger.warning("图谱文件不存在（%s），请先执行 pipeline 或 /api/jd/import", graph_path)
|
||||
# SQLite 状态库：幂等建表 + 旧 JSONL/JSON 一次性迁移（原文件保留）
|
||||
state_db.connect(
|
||||
_db_path(),
|
||||
legacy_audit=resolve(_cfg, "audit_path"),
|
||||
legacy_pending=resolve(_cfg, "pending_path"),
|
||||
).close()
|
||||
# 重启后从 tasks 表恢复任务清单；中断的任务标记为失败
|
||||
for row in state_db.list_tasks(_db_path()):
|
||||
payload = row["payload"]
|
||||
if payload.get("status") in ("pending", "running"):
|
||||
payload = {**payload, "status": "failed", "error": "服务重启，任务中断"}
|
||||
_state["tasks"][row["task_id"]] = payload
|
||||
|
||||
|
||||
# ---------- 健康与图谱 ----------
|
||||
@app.get("/api/health")
|
||||
def health() -> dict:
|
||||
kg = _state["kg"]
|
||||
ready = llm_ready(_cfg)
|
||||
return _ok({"status": "ok", "graph": kg.stats() if kg else None,
|
||||
"llm_ready": ready, "offline_fallback": not ready,
|
||||
"embed": semantic.status(_cfg),
|
||||
"guided": bool(_cfg.get("guided")),
|
||||
"mode": "online" if ready else "offline"})
|
||||
|
||||
|
||||
# ---------- 静态资源缓存控制（避免浏览器用旧版前端） ----------
|
||||
@app.middleware("http")
|
||||
async def static_no_cache(request, call_next):
|
||||
resp = await call_next(request)
|
||||
if not request.url.path.startswith("/api/"):
|
||||
resp.headers["Cache-Control"] = "no-cache" # 每次加载都回源校验（ETag 命中仍 304，成本低）
|
||||
return resp
|
||||
|
||||
|
||||
# ---------- 访问令牌鉴权 ----------
|
||||
@app.middleware("http")
|
||||
async def access_token_guard(request, call_next):
|
||||
"""设置 access_token 后，/api/*（health 除外）必须携带 X-Access-Token 头。
|
||||
|
||||
仅在用户显式配置令牌时启用；默认无令牌、本地使用无感知。
|
||||
"""
|
||||
token = str(_cfg.get("access_token") or "").strip()
|
||||
path = request.url.path
|
||||
# 豁免：health 探活、GET /api/config（只读脱敏值，打开设置面板需要）
|
||||
exempt = path == "/api/health" or (path == "/api/config" and request.method == "GET")
|
||||
if token and path.startswith("/api/") and not exempt:
|
||||
if request.headers.get("x-access-token", "") != token:
|
||||
return JSONResponse({"detail": "未授权：缺少或错误的访问令牌"}, status_code=401)
|
||||
return await call_next(request)
|
||||
|
||||
|
||||
# ---------- 语义环境一键配置（按需下载，基础镜像不打包重依赖） ----------
|
||||
_semantic_setup: dict = {"running": False, "stage": "", "log": [], "error": "", "done": False}
|
||||
_semantic_setup_lock = threading.Lock()
|
||||
|
||||
|
||||
def _setup_log(msg: str) -> None:
|
||||
_semantic_setup["log"].append(msg)
|
||||
_semantic_setup["log"] = _semantic_setup["log"][-20:]
|
||||
logger.info("语义环境配置: %s", msg)
|
||||
|
||||
|
||||
def _run_semantic_setup() -> None:
|
||||
"""后台执行：装依赖 → 下载权重 → 写入配置并热生效。任一阶段失败记 error。"""
|
||||
import importlib
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
weights_dir = ROOT / "models" / "bge-m3"
|
||||
try:
|
||||
# 已就绪则直接写配置收尾（幂等）
|
||||
if not semantic.status(_cfg)["ready"]:
|
||||
_semantic_setup["stage"] = "deps"
|
||||
_setup_log("安装 Python 依赖 sentence-transformers / modelscope（镜像站）…")
|
||||
pip = [sys.executable, "-m", "pip", "install", "-q",
|
||||
"sentence-transformers", "modelscope",
|
||||
"-i", "https://pypi.tuna.tsinghua.edu.cn/simple"]
|
||||
proc = subprocess.run(pip, capture_output=True, text=True, timeout=1800)
|
||||
if proc.returncode != 0: # 镜像站失败退回官方源
|
||||
_setup_log("镜像站安装失败，改用官方源重试…")
|
||||
proc = subprocess.run(pip[:-2], capture_output=True, text=True, timeout=1800)
|
||||
if proc.returncode != 0:
|
||||
raise RuntimeError(f"依赖安装失败：{(proc.stderr or proc.stdout)[-300:]}")
|
||||
importlib.invalidate_caches()
|
||||
_setup_log("依赖安装完成")
|
||||
|
||||
if not semantic.weights_present(weights_dir):
|
||||
_semantic_setup["stage"] = "download"
|
||||
_setup_log("从 ModelScope 下载 BGE-M3 权重（约 2.2GB，数分钟）…")
|
||||
from modelscope import snapshot_download
|
||||
weights_dir.parent.mkdir(parents=True, exist_ok=True)
|
||||
snapshot_download("BAAI/bge-m3", local_dir=str(weights_dir))
|
||||
_setup_log("权重下载完成")
|
||||
else:
|
||||
_setup_log("检测到已有权重，跳过下载")
|
||||
|
||||
_semantic_setup["stage"] = "config"
|
||||
save_runtime_settings({"embed_provider": "local",
|
||||
"embed_model_path": str(weights_dir)})
|
||||
_cfg["embed_provider"] = "local"
|
||||
_cfg["embed_model_path"] = str(weights_dir)
|
||||
ready = semantic.status(_cfg)["ready"]
|
||||
_semantic_setup["done"] = ready
|
||||
_semantic_setup["stage"] = "done" if ready else "error"
|
||||
if not ready:
|
||||
_semantic_setup["error"] = "配置已写入但就绪检测未通过，请检查依赖与权重文件"
|
||||
_setup_log("配置完成" if ready else "就绪检测未通过")
|
||||
except Exception as exc: # noqa: BLE001 - 任何失败都要落到状态里供前端展示
|
||||
_semantic_setup["error"] = str(exc)
|
||||
_semantic_setup["stage"] = "error"
|
||||
_setup_log(f"失败：{exc}")
|
||||
finally:
|
||||
_semantic_setup["running"] = False
|
||||
|
||||
|
||||
@app.post("/api/semantic/setup")
|
||||
def semantic_setup() -> dict:
|
||||
"""启动语义环境一键配置（异步）。已运行中则返回当前状态。"""
|
||||
with _semantic_setup_lock:
|
||||
if not _semantic_setup["running"]:
|
||||
_semantic_setup.update({"running": True, "stage": "start",
|
||||
"log": [], "error": "", "done": False})
|
||||
threading.Thread(target=_run_semantic_setup, daemon=True).start()
|
||||
return _ok({"started": True})
|
||||
|
||||
|
||||
@app.get("/api/semantic/setup/status")
|
||||
def semantic_setup_status() -> dict:
|
||||
return _ok({** _semantic_setup, "embed": semantic.status(_cfg)})
|
||||
|
||||
|
||||
# ---------- 运行时设置（config.json） ----------
|
||||
def _mask(secret: str) -> str:
|
||||
s = (secret or "").strip()
|
||||
return ("••••" + s[-4:]) if s else ""
|
||||
|
||||
|
||||
class ConfigBody(BaseModel):
|
||||
host: str | None = None # 127.0.0.1 | 0.0.0.0
|
||||
port: int | None = None
|
||||
access_token: str | None = None # 空串 = 清除令牌
|
||||
llm_api_key: str | None = None
|
||||
llm_base_url: str | None = None
|
||||
llm_model: str | None = None
|
||||
embed_model_path: str | None = None # BGE-M3 本地权重目录，空串 = 清除
|
||||
embed_provider: str | None = None # local | api
|
||||
embed_api_key: str | None = None # 联网 Embedding API 密钥（如 DashScope）
|
||||
embed_api_base_url: str | None = None
|
||||
embed_api_model: str | None = None
|
||||
guided: bool | None = None # 初始设置引导完成标记
|
||||
mode: str | None = None # demo | live
|
||||
|
||||
|
||||
def _public_config() -> dict:
|
||||
saved = load_runtime_settings()
|
||||
ready = llm_ready(_cfg)
|
||||
running = {"host": str(_cfg.get("host")), "port": int(_cfg.get("port", 9008))}
|
||||
saved_hp = {"host": saved.get("host", running["host"]), "port": int(saved.get("port", running["port"]))}
|
||||
return {
|
||||
"running": running, # 当前进程实际监听
|
||||
"saved": saved_hp, # config.json 中保存的监听（重启后生效）
|
||||
"restart_required": saved_hp != running,
|
||||
"has_access_token": bool(str(_cfg.get("access_token") or "").strip()),
|
||||
"access_token_masked": _mask(str(_cfg.get("access_token") or "")),
|
||||
"llm": {
|
||||
"configured": ready,
|
||||
"api_key_masked": _mask(str(_cfg.get("llm_api_key") or "")),
|
||||
"base_url": str(_cfg.get("llm_base_url") or ""),
|
||||
"model": str(_cfg.get("llm_model") or ""),
|
||||
},
|
||||
"embed": semantic.status(_cfg),
|
||||
"mode": str(_cfg.get("mode", "demo")),
|
||||
"offline_fallback": not ready,
|
||||
}
|
||||
|
||||
|
||||
@app.get("/api/config")
|
||||
def get_config() -> dict:
|
||||
return _ok(_public_config())
|
||||
|
||||
|
||||
@app.post("/api/config")
|
||||
def save_config(body: ConfigBody) -> dict:
|
||||
"""保存运行时设置到 config.json；LLM/令牌热生效，监听地址与端口需重启。"""
|
||||
updates: dict = {}
|
||||
if body.host is not None:
|
||||
if body.host not in ("127.0.0.1", "0.0.0.0"):
|
||||
raise HTTPException(status_code=400, detail="host 仅支持 127.0.0.1 或 0.0.0.0")
|
||||
updates["host"] = body.host
|
||||
if body.port is not None:
|
||||
if not (1024 <= body.port <= 65535):
|
||||
raise HTTPException(status_code=400, detail="端口需在 1024-65535 之间")
|
||||
updates["port"] = body.port
|
||||
if body.mode is not None:
|
||||
if body.mode not in ("demo", "live"):
|
||||
raise HTTPException(status_code=400, detail="mode 仅支持 demo 或 live")
|
||||
updates["mode"] = body.mode
|
||||
if body.access_token is not None:
|
||||
updates["access_token"] = body.access_token.strip()
|
||||
if body.llm_api_key is not None:
|
||||
updates["llm_api_key"] = body.llm_api_key.strip()
|
||||
if body.llm_base_url is not None:
|
||||
updates["llm_base_url"] = body.llm_base_url.strip()
|
||||
if body.llm_model is not None:
|
||||
updates["llm_model"] = body.llm_model.strip()
|
||||
if body.embed_model_path is not None:
|
||||
updates["embed_model_path"] = body.embed_model_path.strip()
|
||||
if body.embed_provider is not None:
|
||||
if body.embed_provider not in ("local", "api"):
|
||||
raise HTTPException(status_code=400, detail="embed_provider 仅支持 local 或 api")
|
||||
updates["embed_provider"] = body.embed_provider
|
||||
if body.embed_api_key is not None:
|
||||
updates["embed_api_key"] = body.embed_api_key.strip()
|
||||
if body.embed_api_base_url is not None:
|
||||
updates["embed_api_base_url"] = body.embed_api_base_url.strip()
|
||||
if body.embed_api_model is not None:
|
||||
updates["embed_api_model"] = body.embed_api_model.strip()
|
||||
if body.guided is not None:
|
||||
updates["guided"] = bool(body.guided)
|
||||
|
||||
save_runtime_settings(updates)
|
||||
# 热生效：令牌、模式与 LLM/语义模型配置立即更新到运行配置（下次调用即读取）
|
||||
for k in ("access_token", "mode", "llm_api_key", "llm_base_url", "llm_model",
|
||||
"embed_model_path", "embed_provider", "embed_api_key",
|
||||
"embed_api_base_url", "embed_api_model", "guided"):
|
||||
if k in updates:
|
||||
if updates[k]:
|
||||
_cfg[k] = updates[k]
|
||||
else:
|
||||
_cfg.pop(k, None)
|
||||
logger.info("运行时设置已保存到 config.json: %s", sorted(updates))
|
||||
return _ok(_public_config(), message="设置已保存")
|
||||
|
||||
|
||||
@app.post("/api/config/restart")
|
||||
def restart_service() -> dict:
|
||||
"""延迟 1 秒后原地重启进程（os.execv），使监听地址/端口变更生效。"""
|
||||
import os
|
||||
import sys
|
||||
|
||||
def _reexec() -> None:
|
||||
threading.Event().wait(1.0)
|
||||
logger.info("按用户请求重启服务……")
|
||||
os.execv(sys.executable, [sys.executable] + sys.argv)
|
||||
|
||||
threading.Thread(target=_reexec, daemon=True).start()
|
||||
return _ok({"restarting": True}, message="服务将在 1 秒后重启，请稍后刷新页面")
|
||||
|
||||
|
||||
@app.get("/api/graph")
|
||||
def graph() -> dict:
|
||||
"""返回节点与边（含时间区间）与演化事件，供前端渲染全景图谱。"""
|
||||
kg = _get_kg()
|
||||
nodes = [{"id": n, **d} for n, d in kg.g.nodes(data=True)]
|
||||
edges = [{"source": u, "target": v, **d} for u, v, d in kg.g.edges(data=True)]
|
||||
events = sorted((e.model_dump() for e in kg.events), key=lambda e: e["window"])
|
||||
return _ok({"nodes": nodes, "edges": edges, "events": events, "stats": kg.stats()})
|
||||
|
||||
|
||||
# ---------- JD 导入（异步任务） ----------
|
||||
def _run_task(task_id: str) -> None:
|
||||
task = _state["tasks"][task_id]
|
||||
try:
|
||||
task["status"] = "running"
|
||||
state_db.upsert_task(_db_path(), task_id, kind="jd_import",
|
||||
status="running", payload=task)
|
||||
stats = run_pipeline(_cfg)
|
||||
graph_path = resolve(_cfg, "graph_path")
|
||||
_state["kg"] = TemporalKG.load(graph_path)
|
||||
task.update(status="done", result=stats)
|
||||
except Exception as exc: # noqa: BLE001 - 任务失败必须可查询原因
|
||||
logger.exception("pipeline 任务失败")
|
||||
task.update(status="failed", error=str(exc))
|
||||
state_db.upsert_task(_db_path(), task_id, kind="jd_import",
|
||||
status=task["status"], payload=task)
|
||||
|
||||
|
||||
def _start_import_task(import_stats: dict | None = None) -> str:
|
||||
"""登记并启动异步 pipeline 重建任务，返回 task_id。"""
|
||||
task_id = uuid.uuid4().hex[:12]
|
||||
payload: dict = {"status": "pending"}
|
||||
if import_stats:
|
||||
payload["import"] = import_stats
|
||||
_state["tasks"][task_id] = payload
|
||||
state_db.upsert_task(_db_path(), task_id, kind="jd_import",
|
||||
status="pending", payload=payload)
|
||||
threading.Thread(target=_run_task, args=(task_id,), daemon=True).start()
|
||||
return task_id
|
||||
|
||||
|
||||
@app.post("/api/jd/import")
|
||||
async def import_jd(request: Request) -> dict:
|
||||
"""JD 导入：支持 multipart 文件上传（.jsonl/.csv/.txt）、JSON 文本粘贴，
|
||||
或不带内容直接触发全量重建（旧行为）。
|
||||
|
||||
合格记录写入 data/jd_raw/import_时间戳.jsonl（保留来源标记），
|
||||
坏行返回前端并写入 logs/import_bad_时间戳.jsonl；随后异步重建图谱。
|
||||
"""
|
||||
from app.ingest.loader import IMPORT_EXTS, IMPORT_MAX_BYTES, save_import
|
||||
text, filename = "", "paste.txt"
|
||||
if "multipart/form-data" in request.headers.get("content-type", ""):
|
||||
form = await request.form()
|
||||
upload = form.get("file")
|
||||
if upload is not None and hasattr(upload, "read"):
|
||||
filename = upload.filename or ""
|
||||
suffix = Path(filename).suffix.lower()
|
||||
if suffix not in IMPORT_EXTS:
|
||||
raise HTTPException(status_code=400,
|
||||
detail=f"不支持的格式 {suffix or '(无扩展名)'}，支持 {sorted(IMPORT_EXTS)}")
|
||||
content = await upload.read()
|
||||
if not content:
|
||||
raise HTTPException(status_code=400, detail="文件为空")
|
||||
if len(content) > IMPORT_MAX_BYTES:
|
||||
raise HTTPException(status_code=400, detail="文件超过 10MB 限制")
|
||||
try:
|
||||
text = content.decode("utf-8-sig")
|
||||
except UnicodeDecodeError as exc:
|
||||
raise HTTPException(status_code=400, detail="文件需为 UTF-8 编码") from exc
|
||||
elif form.get("text"):
|
||||
text = str(form["text"])
|
||||
else:
|
||||
raw = await request.body()
|
||||
if raw:
|
||||
try:
|
||||
payload = json.loads(raw)
|
||||
except json.JSONDecodeError as exc:
|
||||
raise HTTPException(status_code=400, detail=f"请求体不是合法 JSON：{exc}") from exc
|
||||
text = str(payload.get("text") or "")
|
||||
|
||||
import_stats: dict | None = None
|
||||
if text.strip():
|
||||
import_stats = save_import(text, filename, resolve(_cfg, "jd_raw_dir"), ROOT / "logs")
|
||||
if not import_stats["imported"] and not import_stats["bad_lines"]:
|
||||
raise HTTPException(status_code=400, detail="没有可导入的内容")
|
||||
task_id = _start_import_task(import_stats)
|
||||
data: dict = {"task_id": task_id}
|
||||
if import_stats:
|
||||
data.update(imported=import_stats["imported"], skipped=import_stats["skipped"],
|
||||
bad_lines=import_stats["bad_lines"],
|
||||
file=import_stats["file"], bad_log=import_stats["bad_log"])
|
||||
return _ok(data, message="导入任务已启动")
|
||||
|
||||
|
||||
@app.get("/api/tasks/{task_id}")
|
||||
def task_status(task_id: str) -> dict:
|
||||
task = _state["tasks"].get(task_id)
|
||||
if task is None:
|
||||
row = state_db.get_task(_db_path(), task_id) # 重启前的任务从状态库回查
|
||||
task = row["payload"] if row else None
|
||||
if task is None:
|
||||
raise HTTPException(status_code=404, detail="任务不存在")
|
||||
return _ok(task)
|
||||
|
||||
|
||||
# ---------- 岗位 ----------
|
||||
@app.get("/api/jobs")
|
||||
def list_jobs(category: str = "", skill: str = "", keyword: str = "") -> dict:
|
||||
kg = _get_kg()
|
||||
jobs = list(kg.jobs.values())
|
||||
if category:
|
||||
jobs = [j for j in jobs if j.category == category]
|
||||
if skill:
|
||||
jobs = [j for j in jobs if skill in j.required_skills or skill in j.preferred_skills]
|
||||
if keyword:
|
||||
jobs = [j for j in jobs if keyword in j.title]
|
||||
return _ok([j.model_dump() for j in jobs])
|
||||
|
||||
|
||||
@app.get("/api/jobs/{job_id}")
|
||||
def job_detail(job_id: str) -> dict:
|
||||
kg = _get_kg()
|
||||
job = kg.jobs.get(job_id)
|
||||
if job is None:
|
||||
raise HTTPException(status_code=404, detail="岗位不存在")
|
||||
return _ok({"definition": job.model_dump(),
|
||||
"snapshot": kg.latest_snapshot(job_id)})
|
||||
|
||||
|
||||
@app.get("/api/jobs/{job_id}/evolution")
|
||||
def job_evolution(job_id: str) -> dict:
|
||||
kg = _get_kg()
|
||||
if job_id not in kg.jobs:
|
||||
raise HTTPException(status_code=404, detail="岗位不存在")
|
||||
events = [e.model_dump() for e in kg.events_of(job_id)]
|
||||
events.sort(key=lambda e: e["window"])
|
||||
return _ok({"job_id": job_id, "events": events})
|
||||
|
||||
|
||||
@app.get("/api/jobs/{job_id}/snapshot")
|
||||
def job_snapshot(job_id: str, at: str = "") -> dict:
|
||||
"""任意时间点能力画像切片（用于演化页时点对比）。"""
|
||||
kg = _get_kg()
|
||||
if job_id not in kg.jobs:
|
||||
raise HTTPException(status_code=404, detail="岗位不存在")
|
||||
return _ok(kg.snapshot(job_id, at or "9999"))
|
||||
|
||||
|
||||
# ---------- 新岗位发现与审核 ----------
|
||||
@app.post("/api/jobs/discover")
|
||||
def discover() -> dict:
|
||||
"""对当前原始数据重新跑新岗位发现，结果进待审核分区。"""
|
||||
jd_dir = resolve(_cfg, "jd_raw_dir")
|
||||
if not jd_dir.exists():
|
||||
raise HTTPException(status_code=400, detail="原始数据目录不存在")
|
||||
from app.extract.offline import OfflineExtractor
|
||||
records, _ = load_jd_dir(jd_dir)
|
||||
extractor = OfflineExtractor(load_lexicon(resolve(_cfg, "lexicon_path")))
|
||||
extractions = {r.jid: extractor.extract(r) for r in records if not r.is_noise}
|
||||
known = {j.title for j in (_state["kg"].jobs.values() if _state["kg"] else [])}
|
||||
candidates = discover_new_jobs(records, extractions, known)
|
||||
save_pending(candidates, _db_path())
|
||||
return _ok({"candidates": [c.model_dump() for c in candidates]})
|
||||
|
||||
|
||||
class ReviewBody(BaseModel):
|
||||
candidate_id: str
|
||||
action: str # accept | modify | reject
|
||||
operator: str
|
||||
reason: str = ""
|
||||
modify: dict | None = None
|
||||
|
||||
|
||||
@app.post("/api/review")
|
||||
def review(body: ReviewBody) -> dict:
|
||||
"""人机协同审核：通过后写入正式图谱（真实区间/来源/场景行业边/演化事件），
|
||||
并写入覆写层保证跨重建持久化，全程留痕。"""
|
||||
from app.services.overrides import apply_accepted_job, record_job_accept
|
||||
kg = _get_kg()
|
||||
try:
|
||||
accepted, record = apply_review(
|
||||
_db_path(), resolve(_cfg, "audit_path"),
|
||||
body.candidate_id, body.action, body.operator, body.reason, body.modify)
|
||||
except KeyError as exc:
|
||||
raise HTTPException(status_code=404, detail=str(exc)) from exc
|
||||
if accepted is not None:
|
||||
from app.services.overrides import normalize_job_id
|
||||
candidate_id = accepted.job_id
|
||||
accepted.job_id = normalize_job_id(accepted) # cand_X → job_<岗位名>，全图唯一节点
|
||||
apply_accepted_job(kg, accepted) # 真实窗口/来源入库 + 场景行业边 + 新增事件
|
||||
record_job_accept(_db_path(), accepted, candidate_id=candidate_id) # 覆写层持久化，重建后自动重放
|
||||
kg.save(resolve(_cfg, "graph_path"))
|
||||
return _ok({"review": record.model_dump(),
|
||||
"accepted": accepted.model_dump() if accepted else None})
|
||||
|
||||
|
||||
@app.get("/api/review/pending")
|
||||
def pending_list() -> dict:
|
||||
return _ok([c.model_dump() for c in load_pending(_db_path())])
|
||||
|
||||
|
||||
# ---------- 图谱节点编辑（人机协同，留痕） ----------
|
||||
ALLOWED_NODE_FIELDS = {"title", "category", "level", "importance", "weight"}
|
||||
|
||||
|
||||
class NodeUpdateBody(BaseModel):
|
||||
node_id: str
|
||||
updates: dict # 仅允许 ALLOWED_NODE_FIELDS 中的键
|
||||
operator: str
|
||||
reason: str = ""
|
||||
|
||||
|
||||
def _append_audit(record: dict) -> None:
|
||||
"""向审核留痕追加一条记录（与审核流同一 SQLite 状态库 audit_log 表）。"""
|
||||
state_db.append_audit(_db_path(), record)
|
||||
|
||||
|
||||
@app.post("/api/graph/node/update")
|
||||
def node_update(body: NodeUpdateBody) -> dict:
|
||||
"""编辑节点展示属性（名称/类别/级别/重要性/权重），写图谱并留痕。
|
||||
|
||||
只改属性不改结构：节点 id、边与演化历史不受影响。
|
||||
Job 节点同步 kg.jobs 的 JobDefinition（title/category/级别），
|
||||
编辑写入覆写层（job_overrides 表），pipeline 重建后自动重放。
|
||||
"""
|
||||
from app.services.overrides import apply_node_updates, record_node_update
|
||||
kg = _get_kg()
|
||||
updates = {k: v for k, v in body.updates.items() if k in ALLOWED_NODE_FIELDS}
|
||||
if body.node_id not in kg.g:
|
||||
raise HTTPException(status_code=404, detail="节点不存在")
|
||||
if not updates:
|
||||
raise HTTPException(status_code=400, detail="没有可更新的字段")
|
||||
attrs = kg.g.nodes[body.node_id]
|
||||
before = {k: attrs.get(k) for k in updates}
|
||||
apply_node_updates(kg, body.node_id, updates)
|
||||
record_node_update(_db_path(), body.node_id, updates)
|
||||
kg.save(resolve(_cfg, "graph_path"))
|
||||
record = {"kind": "node_update", "node_id": body.node_id,
|
||||
"operator": body.operator, "reason": body.reason,
|
||||
"before": before, "after": updates, "time": now_str()}
|
||||
_append_audit(record)
|
||||
return _ok({"node": {"id": body.node_id, **attrs}, "audit": record},
|
||||
message="节点已更新")
|
||||
|
||||
|
||||
@app.get("/api/audit")
|
||||
def audit_list(node_id: str = "", limit: int = 50) -> dict:
|
||||
"""读取审核/编辑留痕（新→旧排序），可按节点过滤。返回结构与旧 audit.jsonl 行一致。"""
|
||||
records = state_db.get_audit(_db_path(), node_id=node_id or None,
|
||||
limit=max(1, min(limit, 200)))
|
||||
return _ok(records)
|
||||
|
||||
|
||||
# ---------- JD 原文回查（证据来源弹窗） ----------
|
||||
@app.get("/api/jd")
|
||||
def jd_by_source(sid: str) -> dict:
|
||||
"""按 source_id（形如 batch_2019.jsonl#17）回查 JD 原文片段。"""
|
||||
if "#" not in sid:
|
||||
raise HTTPException(status_code=400, detail="source_id 格式应为 文件名#行号")
|
||||
fname, _, lineno_s = sid.partition("#")
|
||||
if Path(fname).name != fname or not fname.endswith(".jsonl"):
|
||||
raise HTTPException(status_code=400, detail="非法文件名")
|
||||
try:
|
||||
lineno = int(lineno_s)
|
||||
except ValueError as exc:
|
||||
raise HTTPException(status_code=400, detail="非法行号") from exc
|
||||
path = resolve(_cfg, "jd_raw_dir") / fname
|
||||
if not path.exists():
|
||||
raise HTTPException(status_code=404, detail="数据文件不存在")
|
||||
lines = path.read_text(encoding="utf-8").splitlines()
|
||||
if not (1 <= lineno <= len(lines)):
|
||||
raise HTTPException(status_code=404, detail="记录不存在")
|
||||
try:
|
||||
rec = JDRecord(**json.loads(lines[lineno - 1]))
|
||||
except (json.JSONDecodeError, ValidationError, TypeError) as exc:
|
||||
raise HTTPException(status_code=404, detail=f"记录解析失败：{exc}") from exc
|
||||
rec.source_id = sid
|
||||
return _ok(rec.model_dump())
|
||||
|
||||
|
||||
# ---------- 简历 / 匹配 / 学习路径 ----------
|
||||
class ResumeBody(BaseModel):
|
||||
text: str
|
||||
|
||||
|
||||
@app.post("/api/resume/parse")
|
||||
def resume_parse(body: ResumeBody) -> dict:
|
||||
matcher = SkillMatcher(load_lexicon(resolve(_cfg, "lexicon_path")))
|
||||
profile = parse_resume(body.text, matcher)
|
||||
return _ok(profile.model_dump())
|
||||
|
||||
|
||||
_RESUME_EXTS = {".txt", ".md", ".docx", ".pdf"}
|
||||
_RESUME_MAX_BYTES = 5 * 1024 * 1024 # 5MB
|
||||
|
||||
|
||||
@app.post("/api/resume/parse/file")
|
||||
async def resume_parse_file(file: UploadFile) -> dict:
|
||||
"""上传简历文件（.txt/.md/.docx/.pdf）并解析：脱敏 + 技能抽取归一化。
|
||||
|
||||
文件名随机化落临时目录，解析完成即删除；临时文件不进入日志。
|
||||
"""
|
||||
suffix = Path(file.filename or "").suffix.lower()
|
||||
if suffix not in _RESUME_EXTS:
|
||||
raise HTTPException(status_code=400,
|
||||
detail=f"不支持的格式 {suffix or '(无扩展名)'}，支持 {sorted(_RESUME_EXTS)}")
|
||||
content = await file.read()
|
||||
if not content:
|
||||
raise HTTPException(status_code=400, detail="文件为空")
|
||||
if len(content) > _RESUME_MAX_BYTES:
|
||||
raise HTTPException(status_code=400, detail="文件超过 5MB 限制")
|
||||
tmp_dir = ROOT / "data" / "tmp"
|
||||
tmp_dir.mkdir(parents=True, exist_ok=True)
|
||||
tmp_path = tmp_dir / f"resume_{uuid.uuid4().hex[:12]}{suffix}"
|
||||
try:
|
||||
tmp_path.write_bytes(content)
|
||||
matcher = SkillMatcher(load_lexicon(resolve(_cfg, "lexicon_path")))
|
||||
profile = parse_resume_file(tmp_path, matcher)
|
||||
except RuntimeError as exc: # 如 pdf 依赖缺失、文件损坏等
|
||||
raise HTTPException(status_code=422, detail=str(exc)) from exc
|
||||
except Exception as exc:
|
||||
raise HTTPException(status_code=422, detail=f"简历文件解析失败：{exc}") from exc
|
||||
finally:
|
||||
tmp_path.unlink(missing_ok=True)
|
||||
logger.info("简历文件解析完成: 格式=%s, 技能=%d 项", suffix, len(profile.skills))
|
||||
return _ok(profile.model_dump())
|
||||
|
||||
|
||||
class MatchBody(BaseModel):
|
||||
job_id: str
|
||||
text: str = "" # 简历原文（与 skills 二选一）
|
||||
skills: list[str] = []
|
||||
years: float = 0.0
|
||||
scenarios: list[str] = []
|
||||
|
||||
|
||||
class ResumeExportBody(BaseModel):
|
||||
profile: dict # ResumeProfile 序列化结果
|
||||
match: dict | None = None # 可选：匹配结果，用于关键词高亮与诊断摘要
|
||||
|
||||
|
||||
_BATCH_MAX_FILES = 50
|
||||
|
||||
|
||||
@app.post("/api/match/batch")
|
||||
async def match_batch(job_id: str = Form(...), files: list[UploadFile] = File(...)) -> dict:
|
||||
"""批量人岗匹配：多份简历（.txt/.md/.docx/.pdf，≤50 份）对同一岗位打分排序。
|
||||
|
||||
每份简历独立解析（含脱敏）与匹配，单份失败不影响整批（记 error 返回）。
|
||||
"""
|
||||
kg = _get_kg()
|
||||
job = kg.jobs.get(job_id)
|
||||
if job is None:
|
||||
raise HTTPException(status_code=404, detail="岗位不存在")
|
||||
if not files:
|
||||
raise HTTPException(status_code=400, detail="未收到简历文件")
|
||||
if len(files) > _BATCH_MAX_FILES:
|
||||
raise HTTPException(status_code=400, detail=f"单批最多 {_BATCH_MAX_FILES} 份简历")
|
||||
|
||||
engine = _engine()
|
||||
matcher = SkillMatcher(load_lexicon(resolve(_cfg, "lexicon_path")))
|
||||
tmp_dir = ROOT / "data" / "tmp"
|
||||
tmp_dir.mkdir(parents=True, exist_ok=True)
|
||||
results: list[dict] = []
|
||||
for f in files:
|
||||
name = f.filename or "未命名"
|
||||
suffix = Path(name).suffix.lower()
|
||||
if suffix not in _RESUME_EXTS:
|
||||
results.append({"filename": name, "error": f"不支持的格式 {suffix or '(无扩展名)'}"})
|
||||
continue
|
||||
content = await f.read()
|
||||
if not content or len(content) > _RESUME_MAX_BYTES:
|
||||
results.append({"filename": name, "error": "文件为空或超过 5MB"})
|
||||
continue
|
||||
tmp_path = tmp_dir / f"batch_{uuid.uuid4().hex[:12]}{suffix}"
|
||||
try:
|
||||
tmp_path.write_bytes(content)
|
||||
profile = parse_resume_file(tmp_path, matcher)
|
||||
m = engine.match(profile, job)
|
||||
results.append({
|
||||
"filename": name,
|
||||
"name": profile.name or "（未识别）",
|
||||
"years": profile.years,
|
||||
"skills_count": len(profile.skills),
|
||||
"total_score": m.total_score,
|
||||
"dimension_scores": m.dimension_scores,
|
||||
"matched": m.matched_required + m.matched_preferred,
|
||||
"missing": m.missing_required + m.missing_preferred,
|
||||
"is_match": m.is_match,
|
||||
})
|
||||
except Exception as exc: # noqa: BLE001 - 单份失败不拖垮整批
|
||||
logger.warning("批量匹配：%s 解析失败: %s", name, exc)
|
||||
results.append({"filename": name, "error": f"解析失败：{exc}"})
|
||||
finally:
|
||||
tmp_path.unlink(missing_ok=True)
|
||||
ok = [r for r in results if "error" not in r]
|
||||
ok.sort(key=lambda r: r["total_score"], reverse=True)
|
||||
logger.info("批量匹配完成: 岗位=%s, 成功 %d/%d", job.title, len(ok), len(files))
|
||||
return _ok({"job_id": job_id, "job_title": job.title,
|
||||
"total": len(results), "ok": len(ok), "results": ok + [r for r in results if "error" in r]})
|
||||
|
||||
|
||||
@app.post("/api/resume/export")
|
||||
def resume_export(body: ResumeExportBody) -> Response:
|
||||
"""把脱敏简历画像导出为规范 DOCX（照片+基本信息+分节+关键词高亮）。"""
|
||||
from app.match.resume_docx import build_resume_docx
|
||||
try:
|
||||
profile = ResumeProfile(**body.profile)
|
||||
except ValidationError as exc:
|
||||
raise HTTPException(status_code=400, detail=f"简历画像格式错误：{exc}") from exc
|
||||
data = build_resume_docx(profile, body.match)
|
||||
fname = quote("简历_脱敏结构化.docx")
|
||||
return Response(
|
||||
content=data,
|
||||
media_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
headers={"Content-Disposition": f"attachment; filename*=utf-8''{fname}"})
|
||||
|
||||
|
||||
def _profile_of(body: MatchBody) -> ResumeProfile:
|
||||
matcher = SkillMatcher(load_lexicon(resolve(_cfg, "lexicon_path")))
|
||||
if body.text:
|
||||
return parse_resume(body.text, matcher)
|
||||
# 手动录入的技能清单：三级归一化（大小写/别名→包含容错）；
|
||||
# 仍未命中的，若语义通道就绪则做 BGE-M3 语义召回兜底（可选增强）
|
||||
lexicon = load_lexicon(resolve(_cfg, "lexicon_path"))
|
||||
skills: list[str] = []
|
||||
for s in body.skills:
|
||||
if not s or not s.strip():
|
||||
continue
|
||||
norm = matcher.normalize(s)
|
||||
if norm == s.strip():
|
||||
sem = semantic.most_similar(norm, _cfg, lexicon)
|
||||
if sem:
|
||||
logger.info("语义召回: %s → %s (%.3f)", norm, sem[0], sem[1])
|
||||
norm = sem[0]
|
||||
skills.append(norm)
|
||||
return ResumeProfile(skills=skills, years=body.years, scenarios=body.scenarios)
|
||||
|
||||
|
||||
def _engine() -> MatchEngine:
|
||||
return MatchEngine(
|
||||
lexicon=load_lexicon(resolve(_cfg, "lexicon_path")),
|
||||
weights={
|
||||
"required": float(_cfg.get("match_weight_required", 0.5)),
|
||||
"preferred": float(_cfg.get("match_weight_preferred", 0.15)),
|
||||
"experience": float(_cfg.get("match_weight_experience", 0.2)),
|
||||
"scenario": float(_cfg.get("match_weight_scenario", 0.15)),
|
||||
},
|
||||
threshold=float(_cfg.get("match_threshold", 60.0)),
|
||||
)
|
||||
|
||||
|
||||
@app.post("/api/match")
|
||||
def match(body: MatchBody) -> dict:
|
||||
kg = _get_kg()
|
||||
job = kg.jobs.get(body.job_id)
|
||||
if job is None:
|
||||
raise HTTPException(status_code=404, detail="岗位不存在")
|
||||
result = _engine().match(_profile_of(body), job)
|
||||
return _ok(result.model_dump())
|
||||
|
||||
|
||||
class LearnBody(BaseModel):
|
||||
job_id: str
|
||||
known_skills: list[str] = []
|
||||
|
||||
|
||||
@app.post("/api/learning-path")
|
||||
def learning_path(body: LearnBody) -> dict:
|
||||
kg = _get_kg()
|
||||
job = kg.jobs.get(body.job_id)
|
||||
if job is None:
|
||||
raise HTTPException(status_code=404, detail="岗位不存在")
|
||||
profile = ResumeProfile(skills=body.known_skills)
|
||||
result = _engine().match(profile, job)
|
||||
return _ok({"job_id": job.job_id, "title": job.title,
|
||||
"learning_path": result.learning_path,
|
||||
"missing_required": result.missing_required})
|
||||
|
||||
|
||||
# ---------- webui 静态托管 ----------
|
||||
WEBUI = ROOT / "webui"
|
||||
|
||||
|
||||
@app.get("/", include_in_schema=False)
|
||||
def index():
|
||||
return FileResponse(WEBUI / "index.html")
|
||||
|
||||
|
||||
app.mount("/static", StaticFiles(directory=WEBUI), name="static")
|
||||
Reference in New Issue
Block a user