feat: 完成 issue #46 RAG 知识库模板化接入（工艺规范/SOP/国标）

- core/rag-kb：领域 RAG 知识库按模板配置（PRD 5.4/7.3，EPIC #6 子任务） - templating.py：知识源三类分类 + 模板命名推导 + 零依赖轻量 YAML 配置加载 - documents.py：文档段落抽取分块，chunk 携带文档/章节/段落溯源信息 - store.py：from_template_config 按模板自动构建 + 中英混合词频检索 + 类别过滤 - config/kb.template.yaml：ti-cl4 模板 RAG 库资产示例（工艺规范/SOP/国标） - tests：29 用例全绿（模板化/分块溯源/检索排序/类别过滤/配置校验）
2026-08-04 16:31:31 +08:00
parent 9c3e59695a
commit 1fb1d278d5
11 changed files with 1135 additions and 0 deletions
@@ -0,0 +1,126 @@
+# -*- coding: utf-8 -*-
+"""模板化（templating）单元测试：知识源分类 / 命名推导 / YAML 配置加载。"""
+import os
+import sys
+import unittest
+
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+import _bootstrap  # noqa: F401
+
+from rag_kb.templating import (  # noqa: E402
+    KbTemplateConfig,
+    KbTemplateNaming,
+    KnowledgeSourceKind,
+    SOURCE_KINDS,
+    load_kb_config,
+    sanitize,
+)
+
+CONFIG_PATH = os.path.join(
+    os.path.dirname(os.path.dirname(os.path.abspath(__file__))),
+    "config", "kb.template.yaml",
+)
+
+
+class SanitizeTest(unittest.TestCase):
+    def test_lower_and_replace_unsafe(self):
+        # 小写 + 空格等非安全字符替换为 `_`；RAG 命名**保留中文**（文档对象键）
+        self.assertEqual(sanitize("Ti-Cl4 模板"), "ti-cl4_模板")
+        self.assertEqual(sanitize("A.B-c_d"), "a.b-c_d")
+
+    def test_chinese_kept(self):
+        self.assertEqual(sanitize("沸腾氯化工艺规范"), "沸腾氯化工艺规范")
+        # `/` 属非安全字符，替换为 `_`
+        self.assertEqual(sanitize("GB/T 氯气安全使用标准"), "gb_t_氯气安全使用标准")
+
+    def test_empty_fallback(self):
+        self.assertEqual(sanitize(""), "kb")
+        self.assertEqual(sanitize("..."), "kb")
+
+
+class SourceKindTest(unittest.TestCase):
+    def test_kinds_registered(self):
+        # 三类知识源固定注册（PRD 7.3：工艺规范 / SOP / 国标）
+        self.assertEqual(
+            set(SOURCE_KINDS),
+            {"process", "sop", "standard"},
+        )
+
+    def test_labels(self):
+        self.assertEqual(KnowledgeSourceKind.PROCESS.label, "工艺规范")
+        self.assertEqual(KnowledgeSourceKind.SOP.label, "SOP/操作手册")
+        self.assertEqual(KnowledgeSourceKind.STANDARD.label, "国标/标准")
+
+
+class NamingTest(unittest.TestCase):
+    def setUp(self):
+        self.naming = KbTemplateNaming(template="ti-cl4")
+
+    def test_collection(self):
+        # 向量库 collection：下划线形态（对齐 data-bus `tpl_{tpl}` schema）
+        self.assertEqual(self.naming.collection(), "ti_cl4_kb")
+
+    def test_index_and_namespace(self):
+        self.assertEqual(self.naming.index_name(), "ti_cl4_kb_idx")
+        self.assertEqual(self.naming.namespace(), "tpl-ti-cl4-kb")
+
+    def test_doc_object_key(self):
+        self.assertEqual(
+            self.naming.doc_object_key("沸腾氯化工艺规范"),
+            "kb/沸腾氯化工艺规范.md",
+        )
+
+    def test_default_template(self):
+        self.assertEqual(KbTemplateNaming("").collection(), "kb_kb")
+
+
+class YamlLoadTest(unittest.TestCase):
+    def test_load_example_config(self):
+        config = load_kb_config(CONFIG_PATH)
+        self.assertEqual(config.template, "ti-cl4")
+        self.assertEqual(config.version, "1.0.0")
+        # 三类知识源各至少声明一份文档
+        self.assertIn(KnowledgeSourceKind.PROCESS, {s.kind for s in config.sources})
+        self.assertIn(KnowledgeSourceKind.SOP, {s.kind for s in config.sources})
+        self.assertIn(KnowledgeSourceKind.STANDARD, {s.kind for s in config.sources})
+        self.assertGreaterEqual(len(config.all_documents()), 3)
+
+    def test_documents_for_kind(self):
+        config = load_kb_config(CONFIG_PATH)
+        docs = config.documents_for(KnowledgeSourceKind.PROCESS)
+        self.assertIn("沸腾氯化工艺规范", docs)
+        self.assertEqual(
+            config.documents_for(KnowledgeSourceKind.STANDARD),
+            ["GB/T 氯气安全使用标准", "GB/T 钛及钛合金加工标准"],
+        )
+
+    def test_unknown_kind_rejected(self):
+        # 未知知识源类别必须报错（杜绝配置拼写漂移）
+        import tempfile
+
+        with tempfile.NamedTemporaryFile("w", suffix=".yaml", delete=False,
+                                         encoding="utf-8") as fh:
+            fh.write("template: ti-cl4\nsources:\n  - kind: hmm\n    documents: [a]\n")
+            path = fh.name
+        try:
+            with self.assertRaises(ValueError):
+                load_kb_config(path)
+        finally:
+            os.unlink(path)
+
+    def test_missing_template_rejected(self):
+        import tempfile
+
+        with tempfile.NamedTemporaryFile("w", suffix=".yaml", delete=False,
+                                         encoding="utf-8") as fh:
+            fh.write("version: 1.0.0\nsources: []\n")
+            path = fh.name
+        try:
+            with self.assertRaises(ValueError):
+                load_kb_config(path)
+        finally:
+            os.unlink(path)
+
+
+if __name__ == "__main__":
+    unittest.main()