Enhance serialization in CodeTide by adding support for cached elements and IDs, and update defaults for serialization paths.

Author: BrunoV21

codetide/__init__.py

@@ -1,4 +1,8 @@
-from codetide.core.defaults import DEFAULT_SERIALIZATION_PATH, LANGUAGE_EXTENSIONS, DEFAULT_MAX_CONCURRENT_TASKS, DEFAULT_BATCH_SIZE
+from codetide.core.defaults import (
+    DEFAULT_SERIALIZATION_PATH, DEFAULT_MAX_CONCURRENT_TASKS,
+    DEFAULT_BATCH_SIZE, DEFAULT_CACHED_ELEMENTS_FILE, DEFAULT_CACHED_IDS_FILE,
+    LANGUAGE_EXTENSIONS
+)
 from codetide.core.models import CodeFileModel, CodeBase
 from codetide.core.common import readFile, writeFile
 
@@ -12,6 +16,7 @@
 import logging
 import asyncio
 import time
+import json
 import os
 
 logging.basicConfig(
@@ -84,18 +89,35 @@ async def from_path(
 
         return codebase
 
-    def serialize(self, filepath :Optional[Union[str, Path]]=DEFAULT_SERIALIZATION_PATH):
+    def serialize(self, filepath :Optional[Union[str, Path]]=DEFAULT_SERIALIZATION_PATH, include_codebase_cached_elements :bool=False, include_cached_ids :bool=False):
         if not os.path.exists(filepath):
             os.makedirs(os.path.split(filepath)[0], exist_ok=True)
         writeFile(self.model_dump_json(indent=4), filepath)
+        if include_codebase_cached_elements or include_cached_ids:
+            dir_path = Path(os.path.split(filepath))[0]
+            if include_codebase_cached_elements:
+                cached_elements_path = dir_path / DEFAULT_CACHED_ELEMENTS_FILE
+                writeFile(self.codebase.serialize_cache_elements(), cached_elements_path)
+            
+            if include_cached_ids:
+                cached_ids_path = dir_path / DEFAULT_CACHED_IDS_FILE
+                writeFile(json.dumps(self.codebase.unique_ds, indent=4), cached_ids_path)
 
     @classmethod
     def deserialize(cls, filepath :Optional[Union[str, Path]]=DEFAULT_SERIALIZATION_PATH)->"CodeTide":
         if not os.path.exists(filepath):
             raise FileNotFoundError(f"{filepath} is not a valid path")
 
         kwargs = readFile(filepath)
-        return cls(**kwargs)
+        tideInstance = cls(**kwargs)
+        
+        # dir_path = Path(os.path.split(filepath))[0]
+        # cached_elements_path = dir_path / DEFAULT_CACHED_ELEMENTS_FILE
+        # if os.path.exists(cached_elements_path):
+        #     cached_elements = json.loads(readFile(cached_elements_path))
+        #     tideInstance.codebase._cached_elements = cached_elements
+
+        return tideInstance
 
     def _organize_files_by_language(
         self,

codetide/core/defaults.py

@@ -50,4 +50,6 @@
 
 DEFAULT_ENCODING = "utf8"
 
-DEFAULT_SERIALIZATION_PATH = "./storage/tide.json"
+DEFAULT_SERIALIZATION_PATH = "./storage/tide.json"
+DEFAULT_CACHED_ELEMENTS_FILE = "cached_elements.json"
+DEFAULT_CACHED_IDS_FILE = "cached_ids.json"

codetide/core/models.py

@@ -3,6 +3,7 @@
 from pydantic import BaseModel, Field, computed_field, field_validator
 from typing import Any, Dict, List, Optional, Literal, Union
 from collections import defaultdict
+import json
 
 class BaseCodeElement(BaseModel):
     file_path: str = ""
@@ -684,4 +685,29 @@ def get(self, unique_id :Union[str, List[str]], degree :int=0, as_string :bool=F
             return codeContext.as_list_str()
 
         else:
-            return codeContext
+            return codeContext
+        
+    def serialize_cache_elements(self, indent :int=4)->str:
+        return json.dumps(
+            {
+                key: value.model_dump()
+                for key, value in self._cached_elements
+            }
+        )
+
+    def deserialize_cache_elements(self, contents :str):
+        self._cached_elements = json.loads(contents)
+        ### TODO need to handle model validates and so on
+        # return json.dumps(
+        #     {
+        #         key: value.model_dump()
+        #         for key, value in self._cached_elements
+        #     }
+        # )
+
+
+    def unique_ds(self)->List[str]:
+        if not self._cached_elements:
+            self._build_cached_elements()
+
+        return list(self._cached_elements.keys())