test: 添加 PDFSplitter 和 HTMLSplitter 测试

2026-07-10 14:25:40 +08:00
parent 9db0c15dee
commit b8afc9043d
2 changed files with 91 additions and 0 deletions
@@ -0,0 +1,42 @@
+"""HTMLSplitter 测试."""
+import pytest
+
+bs4 = pytest.importorskip("bs4", reason="beautifulsoup4 未安装")
+
+
+class TestHTMLSplitter:
+    """HTMLSplitter 测试（需 beautifulsoup4）."""
+
+    def test_split_simple_html(self):
+        from src.core.splitters.html import HTMLSplitter
+        html = "<html><body><h1>标题</h1><p>这是段落内容。</p><p>第二段。</p></body></html>"
+        s = HTMLSplitter(max_size=500)
+        chunks = s.split(html, source_file="test.html")
+        assert len(chunks) >= 1
+        all_text = "".join(c["content"] for c in chunks)
+        assert "标题" in all_text
+        assert "段落内容" in all_text
+        assert "第二段" in all_text
+
+    def test_strips_script_and_style(self):
+        from src.core.splitters.html import HTMLSplitter
+        html = """<html><head><style>.a{color:red}</style><script>alert('xss')</script></head>
+<body><p>可见内容。</p></body></html>"""
+        s = HTMLSplitter()
+        chunks = s.split(html, source_file="test.html")
+        all_text = "".join(c["content"] for c in chunks)
+        assert "可见内容" in all_text
+        assert "alert" not in all_text
+        assert ".a{color:red}" not in all_text
+
+    def test_empty_html(self):
+        from src.core.splitters.html import HTMLSplitter
+        s = HTMLSplitter()
+        assert s.split("<html></html>") == []
+        assert s.split("") == []
+
+    def test_html_has_split_method(self):
+        """HTMLSplitter 遵循 Splitter Protocol."""
+        from src.core.splitters.html import HTMLSplitter
+        s = HTMLSplitter()
+        assert hasattr(s, "split")