chore(dev): archive blueprint refactor session docs

scidk/app.py

@@ -8,14 +8,7 @@
 from .core.graph import InMemoryGraph
 from .core.filesystem import FilesystemManager
 from .core.registry import InterpreterRegistry
-from .interpreters.python_code import PythonCodeInterpreter
-from .interpreters.csv_interpreter import CsvInterpreter
-from .interpreters.json_interpreter import JsonInterpreter
-from .interpreters.yaml_interpreter import YamlInterpreter
-from .interpreters.ipynb_interpreter import IpynbInterpreter
-from .interpreters.txt_interpreter import TxtInterpreter
-from .interpreters.xlsx_interpreter import XlsxInterpreter
-from .core.pattern_matcher import Rule
+from .interpreters import register_all as register_interpreters
 from .core.providers import ProviderRegistry as FsProviderRegistry, LocalFSProvider, MountedFSProvider, RcloneProvider
 from .web.helpers import commit_to_neo4j_batched
 
@@ -118,33 +111,8 @@ def create_app():
     except Exception:
         settings = None
 
-    # Register interpreters
-    py_interp = PythonCodeInterpreter()
-    csv_interp = CsvInterpreter()
-    json_interp = JsonInterpreter()
-    yaml_interp = YamlInterpreter()
-    ipynb_interp = IpynbInterpreter()
-    txt_interp = TxtInterpreter()
-    xlsx_interp = XlsxInterpreter()
-    registry.register_extension(".py", py_interp)
-    registry.register_extension(".csv", csv_interp)
-    registry.register_extension(".json", json_interp)
-    registry.register_extension(".yml", yaml_interp)
-    registry.register_extension(".yaml", yaml_interp)
-    registry.register_extension(".ipynb", ipynb_interp)
-    registry.register_extension(".txt", txt_interp)
-    registry.register_extension(".xlsx", xlsx_interp)
-    registry.register_extension(".xlsm", xlsx_interp)
-    # Register simple rules to prefer interpreters for extensions
-    registry.register_rule(Rule(id="rule.py.default", interpreter_id=py_interp.id, pattern="*.py", priority=10, conditions={"ext": ".py"}))
-    registry.register_rule(Rule(id="rule.csv.default", interpreter_id=csv_interp.id, pattern="*.csv", priority=10, conditions={"ext": ".csv"}))
-    registry.register_rule(Rule(id="rule.json.default", interpreter_id=json_interp.id, pattern="*.json", priority=10, conditions={"ext": ".json"}))
-    registry.register_rule(Rule(id="rule.yml.default", interpreter_id=yaml_interp.id, pattern="*.yml", priority=10, conditions={"ext": ".yml"}))
-    registry.register_rule(Rule(id="rule.yaml.default", interpreter_id=yaml_interp.id, pattern="*.yaml", priority=10, conditions={"ext": ".yaml"}))
-    registry.register_rule(Rule(id="rule.ipynb.default", interpreter_id=ipynb_interp.id, pattern="*.ipynb", priority=10, conditions={"ext": ".ipynb"}))
-    registry.register_rule(Rule(id="rule.txt.default", interpreter_id=txt_interp.id, pattern="*.txt", priority=10, conditions={"ext": ".txt"}))
-    registry.register_rule(Rule(id="rule.xlsx.default", interpreter_id=xlsx_interp.id, pattern="*.xlsx", priority=10, conditions={"ext": ".xlsx"}))
-    registry.register_rule(Rule(id="rule.xlsm.default", interpreter_id=xlsx_interp.id, pattern="*.xlsm", priority=10, conditions={"ext": ".xlsm"}))
+    # Register interpreters with extensions and rules
+    register_interpreters(registry)
 
     # Compute effective interpreter enablement (CLI envs > global settings > defaults)
     testing_env = bool(os.environ.get('PYTEST_CURRENT_TEST')) or bool(os.environ.get('SCIDK_DISABLE_SETTINGS'))

scidk/interpreters/__init__.py

@@ -0,0 +1,69 @@
+"""
+Auto-discovery for SciDK interpreters.
+
+Each interpreter declares its extensions and metadata as class attributes.
+Adding a new interpreter requires only:
+1. Create the interpreter class file
+2. Add import and class to INTERPRETERS list
+3. Define extensions = [...] on the class
+"""
+
+from .python_code import PythonCodeInterpreter
+from .csv_interpreter import CsvInterpreter
+from .json_interpreter import JsonInterpreter
+from .yaml_interpreter import YamlInterpreter
+from .ipynb_interpreter import IpynbInterpreter
+from .txt_interpreter import TxtInterpreter
+from .xlsx_interpreter import XlsxInterpreter
+
+# Centralized interpreter registry
+INTERPRETERS = [
+    PythonCodeInterpreter,
+    CsvInterpreter,
+    JsonInterpreter,
+    YamlInterpreter,
+    IpynbInterpreter,
+    TxtInterpreter,
+    XlsxInterpreter,
+]
+
+
+def register_all(registry):
+    """
+    Register all interpreters with their extensions and rules.
+
+    This replaces ~60 lines of manual registration code in app.py.
+    Each interpreter is:
+    1. Instantiated
+    2. Registered for each of its extensions
+    3. Auto-assigned rules for pattern matching
+
+    Args:
+        registry: InterpreterRegistry instance to register with
+    """
+    from ..core.pattern_matcher import Rule
+
+    for interp_class in INTERPRETERS:
+        instance = interp_class()
+
+        # Get extensions from class metadata
+        extensions = getattr(interp_class, 'extensions', [])
+
+        # Register by each extension
+        for ext in extensions:
+            registry.register_extension(ext, instance)
+
+        # Auto-create default rules for each extension
+        for ext in extensions:
+            pattern = f"*{ext}"
+            # Convert '.py' → 'py' for rule id
+            ext_name = ext.lstrip('.')
+            rule_id = f"rule.{ext_name}.default"
+
+            registry.register_rule(Rule(
+                id=rule_id,
+                interpreter_id=instance.id,
+                pattern=pattern,
+                priority=10,
+                conditions={"ext": ext}
+            ))

scidk/interpreters/csv_interpreter.py

@@ -6,6 +6,7 @@ class CsvInterpreter:
     id = "csv"
     name = "CSV Interpreter"
     version = "0.1.0"
+    extensions = [".csv"]
 
     def __init__(self, max_bytes: int = 10 * 1024 * 1024):
         self.max_bytes = max_bytes

scidk/interpreters/ipynb_interpreter.py

@@ -13,6 +13,7 @@ class IpynbInterpreter:
     id = "ipynb"
     name = "Jupyter Notebook Interpreter"
     version = "0.3.0"
+    extensions = [".ipynb"]
 
     def __init__(self, max_bytes: int = 5 * 1024 * 1024):
         self.max_bytes = max_bytes

scidk/interpreters/json_interpreter.py

@@ -6,6 +6,7 @@ class JsonInterpreter:
     id = "json"
     name = "JSON Interpreter"
     version = "0.1.0"
+    extensions = [".json"]
 
     def __init__(self, max_bytes: int = 5 * 1024 * 1024):
         self.max_bytes = max_bytes

scidk/interpreters/python_code.py

@@ -6,6 +6,7 @@ class PythonCodeInterpreter:
     id = "python_code"
     name = "Python Code Analyzer"
     version = "0.1.0"
+    extensions = [".py"]
 
     def interpret(self, file_path: Path):
         with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:

scidk/interpreters/txt_interpreter.py

@@ -6,6 +6,7 @@ class TxtInterpreter:
     id = "txt"
     name = "Text File Interpreter"
     version = "0.1.0"
+    extensions = [".txt"]
 
     def __init__(self, max_bytes: int = 10 * 1024 * 1024, max_preview_bytes: int = 4096, max_preview_lines: int = 100):
         self.max_bytes = max_bytes

scidk/interpreters/xlsx_interpreter.py

@@ -11,6 +11,7 @@ class XlsxInterpreter:
     id = "xlsx"
     name = "Excel Workbook Interpreter"
     version = "0.1.0"
+    extensions = [".xlsx", ".xlsm"]
 
     def __init__(self, max_bytes: int = 20 * 1024 * 1024):
         self.max_bytes = max_bytes

scidk/interpreters/yaml_interpreter.py

@@ -10,6 +10,7 @@ class YamlInterpreter:
     id = "yaml"
     name = "YAML Interpreter"
     version = "0.1.0"
+    extensions = [".yml", ".yaml"]
 
     def __init__(self, max_bytes: int = 5 * 1024 * 1024):
         self.max_bytes = max_bytes