Better compile errors for missing sources or segments.

Author: travis-bauer

CHANGELOG.md

@@ -1,6 +1,6 @@
 # Changelog
 
-## 0.10.0 (in progress)
+## in progress
 ### Improvements
 - Changes several logging statements to make the consistent with the rest of the code
 - Refactored **lambda** to use AbstractFieldSegment for consistency
@@ -15,6 +15,8 @@
 - Updated the ollama embedding and chat connector so that it uses the OLLAMA_SERVER_URL configuration
   variable as the host where ollama is installed.  So OLLAMA_SERVER_URL can be set in the TOML configuration
   file or TALKPIPE_OLLAMA_SERVER_URL can be set as an environment variable.
+- Implemented better compile errors for when sources or segments are not found.  It had been a key error.
+  It will now be a compile error.
 
 ## 0.9.3 
 ### Improvements

src/talkpipe/chatterlang/compiler.py

@@ -16,6 +16,10 @@
 
 logger = logging.getLogger(__name__)
 
+class CompileError(Exception):
+    """ Exception raised when a compilation error occurs in chatterlang """
+    pass
+
 @singledispatch
 def compile(script: ParsedScript, runtime: RuntimeComponent = None) -> Callable:
     """ Compile a parsed script into a callable function 
@@ -58,7 +62,10 @@ def _(pipeline: ParsedPipeline, runtime: RuntimeComponent) -> Pipeline:
             ans = VariableSource(pipeline.input_node.source.name)
             logger.debug(f"Created variable source with name {pipeline.input_node.source.name}")
         else:
-            ans = registry.input_registry.get(pipeline.input_node.source.name)(**_resolve_params(pipeline.input_node.params, runtime=runtime))
+            try:
+                ans = registry.input_registry.get(pipeline.input_node.source.name)(**_resolve_params(pipeline.input_node.params, runtime=runtime))
+            except KeyError:
+                raise CompileError(f"Source '{pipeline.input_node.source.name}' not found")
             logger.debug(f"Created registered input {pipeline.input_node.source.name}")
         ans.runtime = runtime
 
@@ -68,7 +75,10 @@ def _(pipeline: ParsedPipeline, runtime: RuntimeComponent) -> Pipeline:
             next_transform = VariableSetSegment(transform.name)
             logger.debug(f"Created variable set segment for {transform.name}")
         elif isinstance(transform, SegmentNode):
-            next_transform = registry.segment_registry.get(transform.operation.name)(**_resolve_params(transform.params, runtime=runtime))
+            try:
+                next_transform = registry.segment_registry.get(transform.operation.name)(**_resolve_params(transform.params, runtime=runtime))
+            except KeyError:
+                raise CompileError(f"Segment '{transform.operation.name}' not found")
             logger.debug(f"Created segment {transform.operation.name}")
         elif isinstance(transform, ForkNode):
             next_transform = compile(transform, runtime)

src/talkpipe/util/config.py

@@ -327,7 +327,7 @@ def load_script(script_input: str) -> str:
     try:
         is_file = script_path.is_file()
     except OSError as e:
-        logger.warning(f"Script path could not be checked as a file {script_input[0:25]}...: {e}")
+        logger.debug(f"Script path could not be checked as a file {script_input[0:25]}...: {e}")
         is_file = False
     if is_file:
         try:

tests/talkpipe/app/test_chatterlang_script.py

@@ -52,22 +52,51 @@ def test_main_with_extra_module(capsys, tmp_path):
 
 def test_main_with_constant_injection(capsys):
     test_script = """INPUT FROM echo[data=$TEST] | print"""
-    
+
     with patch('argparse.ArgumentParser.parse_known_args') as mock_args:
         # Mock the return value of parse_known_args to simulate --script "INPUT FROM echo[data=TEST] | print" --TEST "hello"
         mock_namespace = type('MockNamespace', (), {})()
         mock_namespace.script = test_script
         mock_namespace.load_module = []
         mock_namespace.logger_levels = None
         mock_namespace.logger_files = None
-        
+
         # Return the parsed args and unknown args (the constant)
         mock_args.return_value = (mock_namespace, ['--TEST', 'hello'])
-        
+
         main()
-        
+
         captured = capsys.readouterr()
         assert captured.out == "hello\n"
 
 
+def test_warning_messages_should_not_include_full_script_content(caplog):
+    """
+    Test that warning messages use elegant formatting and do not include
+    the full script content, which could clutter logs and expose sensitive information.
+    """
+    test_script = 'INPUT FROM echo[data="test1,test2,test3"] ' + ''.join(['| print ' for _ in range(100)])  # Long script
+
+    with caplog.at_level(logging.WARNING):
+        with patch('argparse.ArgumentParser.parse_known_args') as mock_args:
+            mock_namespace = type('MockNamespace', (), {})()
+            mock_namespace.script = test_script
+            mock_namespace.load_module = []
+            mock_namespace.logger_levels = None
+            mock_namespace.logger_files = None
+
+            # Return the parsed args and no unknown args
+            mock_args.return_value = (mock_namespace, [])
+
+            main()
+
+    # Verify that NO warning messages contain the full script content
+    warning_messages = [record.message for record in caplog.records if record.levelname == 'WARNING']
+
+    for warning_msg in warning_messages:
+        assert test_script not in warning_msg, (
+            f"Warning message should not include full script content. "
+            f"Found script in warning: {warning_msg}"
+        )
+
 

tests/talkpipe/chatterlang/test_compiler.py

@@ -293,3 +293,19 @@ def test_environment_variable_support():
         f = f.as_function(single_out=False)
         ans = list(f())
         assert ans == ['a', 'b', 'c', 'd']
+
+def test_compile_error_missing_segment():
+    try:
+        compiler.compile("""INPUT FROM "test" | unknownSegment""")
+    except compiler.CompileError as e:
+        assert "Segment 'unknownSegment' not found" in str(e)
+    else:
+        assert False, "Expected CompileError was not raised"
+
+def test_compile_error_in_source():
+    try:
+        compiler.compile("""INPUT FROM unknownSource""")
+    except compiler.CompileError as e:
+        assert "Source 'unknownSource' not found" in str(e)
+    else:
+        assert False, "Expected CompileError was not raised"