Initial MVP

tests/test_ingest_code.py

@@ -0,0 +1,172 @@
+"""Tests for code chunking — Python, Bash, Go."""
+
+from kb_search.ingest.code import chunk_code, _chunk_python, _chunk_bash, _chunk_go, _fixed_chunk
+
+CFG = {"chunking": {"code": {"strategy": "ast", "include_context": True, "max_tokens": 1024}}}
+
+
+class TestPythonChunking:
+    def test_functions(self):
+        code = '''
+def hello():
+    """Say hello."""
+    print("hello")
+
+def goodbye():
+    """Say goodbye."""
+    print("bye")
+'''
+        chunks = _chunk_python(code, include_context=True)
+        assert len(chunks) == 2
+        assert chunks[0]["metadata"]["symbol_name"] == "hello"
+        assert chunks[1]["metadata"]["symbol_name"] == "goodbye"
+
+    def test_class_with_methods(self):
+        code = '''
+class MyClass:
+    """A test class."""
+
+    def method_a(self):
+        pass
+
+    def method_b(self):
+        pass
+'''
+        chunks = _chunk_python(code, include_context=True)
+        assert len(chunks) == 2
+        assert chunks[0]["metadata"]["symbol_name"] == "MyClass.method_a"
+        assert chunks[1]["metadata"]["symbol_name"] == "MyClass.method_b"
+        # Context should include class docstring
+        assert "A test class" in chunks[0]["text"]
+
+    def test_class_without_methods(self):
+        code = '''
+class Config:
+    """Configuration."""
+    DEBUG = True
+    PORT = 8080
+'''
+        chunks = _chunk_python(code, include_context=True)
+        assert len(chunks) == 1
+        assert chunks[0]["metadata"]["symbol_name"] == "Config"
+
+    def test_syntax_error_returns_empty(self):
+        chunks = _chunk_python("def broken(:\n  pass", include_context=True)
+        assert chunks == []
+
+    def test_no_context(self):
+        code = '''
+class Foo:
+    """Docstring."""
+    def bar(self):
+        pass
+'''
+        chunks = _chunk_python(code, include_context=False)
+        assert len(chunks) == 1
+        assert "Docstring" not in chunks[0]["text"]
+
+
+class TestBashChunking:
+    def test_function_keyword(self):
+        code = '''#!/bin/bash
+
+function deploy() {
+    echo "deploying"
+}
+
+function rollback() {
+    echo "rolling back"
+}
+'''
+        chunks = _chunk_bash(code, include_context=True)
+        assert len(chunks) == 2
+        assert chunks[0]["metadata"]["symbol_name"] == "deploy"
+        assert chunks[1]["metadata"]["symbol_name"] == "rollback"
+
+    def test_shorthand_syntax(self):
+        code = '''
+setup() {
+    echo "setup"
+}
+
+cleanup() {
+    echo "cleanup"
+}
+'''
+        chunks = _chunk_bash(code, include_context=True)
+        assert len(chunks) == 2
+
+    def test_no_functions(self):
+        code = "#!/bin/bash\necho hello\nexit 0"
+        chunks = _chunk_bash(code, include_context=True)
+        assert chunks == []
+
+    def test_with_preceding_comments(self):
+        code = '''
+# Deploy to production
+# Requires valid credentials
+function deploy() {
+    echo "deploying"
+}
+'''
+        chunks = _chunk_bash(code, include_context=True)
+        assert len(chunks) == 1
+        assert "Deploy to production" in chunks[0]["text"]
+
+
+class TestGoChunking:
+    def test_basic_funcs(self):
+        code = '''package main
+
+func main() {
+    fmt.Println("hello")
+}
+
+func helper() string {
+    return "help"
+}
+'''
+        chunks = _chunk_go(code, include_context=True)
+        assert len(chunks) == 2
+        assert chunks[0]["metadata"]["symbol_name"] == "main"
+        assert chunks[1]["metadata"]["symbol_name"] == "helper"
+
+    def test_method_receiver(self):
+        code = '''
+func (s *Server) Start() error {
+    return nil
+}
+
+func (s *Server) Stop() {
+}
+'''
+        chunks = _chunk_go(code, include_context=True)
+        assert len(chunks) == 2
+        assert chunks[0]["metadata"]["symbol_name"] == "Start"
+
+    def test_no_funcs(self):
+        code = "package main\n\nvar x = 1"
+        chunks = _chunk_go(code, include_context=True)
+        assert chunks == []
+
+
+class TestFallback:
+    def test_unknown_language_uses_fixed(self):
+        code = "line1\nline2\nline3"
+        chunks = chunk_code(code, "ruby", CFG)
+        assert len(chunks) >= 1
+
+    def test_python_no_functions_uses_fixed(self):
+        code = "x = 1\ny = 2\nprint(x + y)"
+        chunks = chunk_code(code, "python", CFG)
+        assert len(chunks) >= 1
+
+    def test_fixed_strategy_config(self):
+        cfg = {"chunking": {"code": {"strategy": "fixed", "max_tokens": 10}}}
+        code = "\n".join(f"x_{i} = {i}" for i in range(50))
+        chunks = chunk_code(code, "python", cfg)
+        assert len(chunks) > 1
+
+    def test_empty_code(self):
+        chunks = chunk_code("", "python", CFG)
+        assert len(chunks) == 0