RoyirinRosmontis
1722c00249
- scripts/expand_real_dataset.py：AutoWeakS 全量 2215 条 + 500 条分层评测集 + 简历扩量（seed=2026 可复现） - pipeline 被动语料机制（passive_sources）：真实无日期 JD 参与接入/清洗/抽取验证（2915 条命中率 99.8%），不进图谱/演化/发现 - 新岗位发现第四指标'差异度'与双年窗口增长率口径 - 评测新增 real_jd_500 维度（99.91%）；测试会话隔离 jd_extra_dirs 防止本机配置拖慢套件
112 lines
4.3 KiB
Python
112 lines
4.3 KiB
Python
"""极简配置加载：解析平铺的 ``key: value`` 格式 config.yaml，避免额外依赖。
|
||
|
||
运行时设置（监听地址/端口/访问令牌/LLM 密钥）保存在 config.json，
|
||
由设置接口写入、启动时合并读取，优先级：config.json > config.yaml > DEFAULTS。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
from pathlib import Path
|
||
|
||
ROOT = Path(__file__).resolve().parents[1]
|
||
CONFIG_JSON = ROOT / "config.json" # 运行时设置文件（测试可 monkeypatch 此路径）
|
||
|
||
# 允许通过设置面板/config.json 覆盖的键白名单
|
||
RUNTIME_KEYS = {
|
||
"mode", "host", "port", "access_token",
|
||
"llm_api_key", "llm_base_url", "llm_model", "llm_timeout",
|
||
"embed_model_path", "embed_provider", "embed_api_key",
|
||
"embed_api_base_url", "embed_api_model",
|
||
"guided", "jd_extra_dirs", "passive_sources",
|
||
}
|
||
|
||
DEFAULTS: dict = {
|
||
"mode": "demo", # demo | live
|
||
"host": "127.0.0.1",
|
||
"port": 9008,
|
||
"data_dir": "data",
|
||
"jd_raw_dir": "data/jd_raw",
|
||
"jd_extra_dirs": "", # 附加 JD 数据源目录（逗号分隔，可切换到真实数据集）
|
||
"passive_sources": "autoweaks", # 被动语料来源（无日期真实数据，不进图谱/演化/发现）
|
||
"graph_path": "data/graph.json",
|
||
"lexicon_path": "data/skills_lexicon.json",
|
||
"pending_path": "data/review/pending.json", # 旧待审核文件（仅作 SQLite 一次性迁移种子）
|
||
"audit_path": "data/review/audit.jsonl", # 旧留痕文件（仅作 SQLite 一次性迁移种子）
|
||
"state_db_path": "data/careernexus.db", # SQLite 应用状态库（审核留痕/候选/任务）
|
||
"decay_lambda": 0.35, # 时间衰减系数 w = exp(-λ·age)
|
||
"match_weight_required": 0.50, # 人岗匹配四维权重
|
||
"match_weight_preferred": 0.15,
|
||
"match_weight_experience": 0.20,
|
||
"match_weight_scenario": 0.15,
|
||
"match_threshold": 60.0, # 总分 >= 阈值视为匹配
|
||
"llm_api_key_env": "SPARK_API_KEY", # 密钥只从环境变量读取
|
||
"llm_base_url": "https://spark-api-open.xf-yun.com/v1",
|
||
"llm_model": "4.0Ultra",
|
||
"llm_timeout": 20,
|
||
}
|
||
|
||
|
||
def _coerce(value: str):
|
||
v = value.strip()
|
||
# 行内注释：值中第一个 " #" 之后的内容丢弃（URL 等含 # 的值不受影响）
|
||
if " #" in v:
|
||
v = v.split(" #", 1)[0].strip()
|
||
if v.lower() in ("true", "false"):
|
||
return v.lower() == "true"
|
||
try:
|
||
return int(v)
|
||
except ValueError:
|
||
pass
|
||
try:
|
||
return float(v)
|
||
except ValueError:
|
||
pass
|
||
return v
|
||
|
||
|
||
def load_config(path: str | Path | None = None) -> dict:
|
||
"""加载配置：DEFAULTS ← config.yaml ← config.json（运行时设置，优先级最高）。"""
|
||
cfg = dict(DEFAULTS)
|
||
p = Path(path) if path else ROOT / "config.yaml"
|
||
if p.exists():
|
||
for line in p.read_text(encoding="utf-8").splitlines():
|
||
line = line.strip()
|
||
if not line or line.startswith("#") or ":" not in line:
|
||
continue
|
||
key, _, value = line.partition(":")
|
||
cfg[key.strip()] = _coerce(value)
|
||
cfg.update(load_runtime_settings())
|
||
return cfg
|
||
|
||
|
||
def load_runtime_settings() -> dict:
|
||
"""读取 config.json 中的白名单键；文件不存在或损坏时返回空 dict。"""
|
||
try:
|
||
if CONFIG_JSON.exists():
|
||
data = json.loads(CONFIG_JSON.read_text(encoding="utf-8"))
|
||
return {k: v for k, v in data.items() if k in RUNTIME_KEYS}
|
||
except (json.JSONDecodeError, OSError):
|
||
pass
|
||
return {}
|
||
|
||
|
||
def save_runtime_settings(updates: dict) -> dict:
|
||
"""把白名单内的设置合并写入 config.json，返回保存后的完整运行时设置。"""
|
||
current = load_runtime_settings()
|
||
for k, v in updates.items():
|
||
if k not in RUNTIME_KEYS:
|
||
continue
|
||
if v is None or (isinstance(v, str) and not v.strip()):
|
||
current.pop(k, None) # 空值视为清除该设置
|
||
else:
|
||
current[k] = v
|
||
CONFIG_JSON.write_text(json.dumps(current, ensure_ascii=False, indent=2),
|
||
encoding="utf-8")
|
||
return current
|
||
|
||
|
||
def resolve(cfg: dict, key: str) -> Path:
|
||
"""把配置中的相对路径解析为工程根目录下的绝对路径。"""
|
||
p = Path(str(cfg[key]))
|
||
return p if p.is_absolute() else ROOT / p
|