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
2026-08-03 13:15:35 +08:00
commit a10442d78c
78 changed files with 12860 additions and 0 deletions
@@ -0,0 +1,131 @@
+"""抽取层测试：Schema 校验、坏 JSON 重试与降级、多源投票、离线抽取与别名归一。"""
+from __future__ import annotations
+
+import pytest
+from pydantic import ValidationError
+
+from app.extract.base import SkillMatcher, load_lexicon, vote_field
+from app.extract.llm import LLMExtractor
+from app.extract.offline import OfflineExtractor
+from app.models import ExtractionResult, JDRecord
+
+SAMPLE_TEXT = """岗位名称：Java开发工程师
+某科技公司诚邀优秀人才加入。
+岗位职责：
+1、负责后端服务的设计与开发；
+2、参与核心系统的性能优化；
+任职要求：
+1、3年以上相关工作经验；
+2、熟练掌握Java、Spring Boot、MySQL、Redis；
+3、具有电商或金融行业经验者优先；
+加分项：
+1、了解Docker、Kubernetes者优先；
+"""
+
+
+def _record(text: str = SAMPLE_TEXT) -> JDRecord:
+    return JDRecord(jid="X1", job_title="Java开发工程师", company="某科技",
+                    publish_date="2024-05-01", text=text)
+
+
+def test_offline_extract_fields_and_evidence():
+    ext = OfflineExtractor(load_lexicon())
+    r = ext.extract(_record())
+    assert r.job_title == "Java开发工程师"
+    assert set(r.required_skills) == {"Java", "Spring Boot", "MySQL", "Redis"}
+    assert set(r.preferred_skills) == {"Docker", "Kubernetes"}
+    assert r.responsibilities == ["负责后端服务的设计与开发；", "参与核心系统的性能优化；"]
+    assert set(r.scenarios) == {"电商", "金融"}
+    assert r.evidence["required_skills"]          # 每字段附证据片段
+    assert r.confidence == 1.0
+
+
+def test_alias_normalization():
+    matcher = SkillMatcher(load_lexicon())
+    text = "要求LLM应用开发经验，熟悉K8s与SpringBoot，了解检索增强生成"
+    names = matcher.find_names(text)
+    assert "大模型应用开发" in names   # LLM应用开发 归一化
+    assert "Kubernetes" in names       # K8s 归一化
+    assert "Spring Boot" in names      # SpringBoot 归一化
+    assert "RAG" in names              # 检索增强生成 归一化
+
+
+def test_tail_section_not_mixed_into_preferred():
+    """尾部“团队与福利/福利待遇”段落不属于加分区：其中的技能词不得混入加分技能。"""
+    text = SAMPLE_TEXT + "团队与福利：\n团队标配Kubernetes与Terraform，提供外部培训预算。\n"
+    ext = OfflineExtractor(load_lexicon())
+    r = ext.extract(_record(text))
+    assert set(r.preferred_skills) == {"Docker", "Kubernetes"}
+    assert "Terraform" not in r.preferred_skills
+
+
+def test_java_not_confused_with_javascript():
+    matcher = SkillMatcher(load_lexicon())
+    names = matcher.find_names("精通JavaScript与Vue，不写Java后端")
+    assert "JavaScript" in names
+    assert "Java" in names  # “Java后端”中的 Java 是独立词
+    only_js = matcher.find_names("精通JavaScript与Vue")
+    assert "Java" not in only_js
+
+
+def test_schema_validation_rejects_bad_payload():
+    with pytest.raises(ValidationError):
+        ExtractionResult(job_title="X", required_skills="不是列表")
+    with pytest.raises(ValidationError):
+        ExtractionResult(job_title="X", confidence="不是数字")
+
+
+def _make_llm() -> LLMExtractor:
+    return LLMExtractor(api_key="fake", base_url="http://localhost:1", model="m",
+                        timeout=0.1, fallback=OfflineExtractor(load_lexicon()))
+
+
+def test_llm_bad_json_retries_then_success(monkeypatch):
+    """坏 JSON 触发重试，第 3 次返回合法 JSON 则成功。"""
+    llm = _make_llm()
+    calls = {"n": 0}
+    good = ('{"job_title": "Java开发工程师", "responsibilities": [], '
+            '"required_skills": ["Java"], "preferred_skills": [], "scenarios": []}')
+
+    def fake_call(text):
+        calls["n"] += 1
+        return "{坏JSON" if calls["n"] < 3 else good
+
+    monkeypatch.setattr(llm, "_call_api", fake_call)
+    r = llm.extract(_record())
+    assert calls["n"] == 3
+    assert r.extractor == "llm"
+    assert r.required_skills == ["Java"]
+
+
+def test_llm_all_fail_fallback_offline(monkeypatch):
+    """重试耗尽（含超时/坏 JSON）降级到离线抽取，链路不断。"""
+    llm = _make_llm()
+    monkeypatch.setattr(llm, "_call_api", lambda text: (_ for _ in ()).throw(TimeoutError("超时")))
+    r = llm.extract(_record())
+    assert r.extractor == "offline"
+    assert "Java" in r.required_skills
+
+
+def test_llm_schema_invalid_retries(monkeypatch):
+    """返回 JSON 合法但不符合 Schema（类型错误）同样重试并降级。"""
+    llm = _make_llm()
+    monkeypatch.setattr(llm, "_call_api",
+                        lambda text: '{"job_title": 123, "required_skills": "wrong"}')
+    r = llm.extract(_record())
+    assert r.extractor == "offline"
+
+
+def test_vote_field_requires_agreement():
+    """关键字段多源一致才入选：A 三源全票，B 两票，C 一票出局。"""
+    chosen, conf = vote_field([
+        (["A", "B", "C"], 1.0),
+        (["A", "B"], 1.0),
+        (["A"], 1.0),
+    ], min_agreement=0.5)
+    assert chosen == ["A", "B"]
+    assert conf == 1.0
+    chosen2, _ = vote_field([(["A"], 1.0), (["B"], 1.0)], min_agreement=0.5)
+    assert chosen2 == ["A", "B"]  # 平票 0.5 恰好达到门槛
+    chosen3, conf3 = vote_field([(["A"], 1.0), (["B"], 1.0), (["C"], 1.0)], min_agreement=0.5)
+    assert chosen3 == []