Merge pull request #112 from rossdonald/utf-bom-handling

fix: update file opening encoding to utf-8-sig to handle files with BOM

Author: zachary62

utils/call_llm.py

@@ -15,7 +15,7 @@
 logger = logging.getLogger("llm_logger")
 logger.setLevel(logging.INFO)
 logger.propagate = False  # Prevent propagation to root logger
-file_handler = logging.FileHandler(log_file)
+file_handler = logging.FileHandler(log_file, encoding='utf-8')
 file_handler.setFormatter(
     logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
 )
@@ -36,7 +36,7 @@ def call_llm(prompt: str, use_cache: bool = True) -> str:
         cache = {}
         if os.path.exists(cache_file):
             try:
-                with open(cache_file, "r") as f:
+                with open(cache_file, "r", encoding="utf-8") as f:
                     cache = json.load(f)
             except:
                 logger.warning(f"Failed to load cache, starting with empty cache")
@@ -73,15 +73,15 @@ def call_llm(prompt: str, use_cache: bool = True) -> str:
         cache = {}
         if os.path.exists(cache_file):
             try:
-                with open(cache_file, "r") as f:
+                with open(cache_file, "r", encoding="utf-8") as f:
                     cache = json.load(f)
             except:
                 pass
 
         # Add to cache and save
         cache[prompt] = response_text
         try:
-            with open(cache_file, "w") as f:
+            with open(cache_file, "w", encoding="utf-8") as f:
                 json.dump(cache, f)
         except Exception as e:
             logger.error(f"Failed to save cache: {e}")
@@ -161,7 +161,7 @@ def call_llm(prompt: str, use_cache: bool = True) -> str:
 #         cache = {}
 #         if os.path.exists(cache_file):
 #             try:
-#                 with open(cache_file, "r") as f:
+#                 with open(cache_file, "r", encoding="utf-8") as f:
 #                     cache = json.load(f)
 #             except:
 #                 logger.warning(f"Failed to load cache, starting with empty cache")
@@ -211,15 +211,15 @@ def call_llm(prompt: str, use_cache: bool = True) -> str:
 #         cache = {}
 #         if os.path.exists(cache_file):
 #             try:
-#                 with open(cache_file, "r") as f:
+#                 with open(cache_file, "r", encoding="utf-8") as f:
 #                     cache = json.load(f)
 #             except:
 #                 pass
 
 #         # Add to cache and save
 #         cache[prompt] = response_text
 #         try:
-#             with open(cache_file, "w") as f:
+#             with open(cache_file, "w", encoding="utf-8") as f:
 #                 json.dump(cache, f)
 #         except Exception as e:
 #             logger.error(f"Failed to save cache: {e}")

utils/crawl_github_files.py

@@ -104,7 +104,7 @@ def should_include_file(file_path: str, file_name: str) -> bool:
 
                     # Read content
                     try:
-                        with open(abs_path, "r", encoding="utf-8") as f:
+                        with open(abs_path, "r", encoding="utf-8-sig") as f:
                             content = f.read()
                         files[rel_path] = content
                         print(f"Added {rel_path} ({file_size} bytes)")

utils/crawl_local_files.py

@@ -32,7 +32,7 @@ def crawl_local_files(
     gitignore_spec = None
     if os.path.exists(gitignore_path):
         try:
-            with open(gitignore_path, "r", encoding="utf-8") as f:
+            with open(gitignore_path, "r", encoding="utf-8-sig") as f:
                 gitignore_patterns = f.readlines()
             gitignore_spec = pathspec.PathSpec.from_lines("gitwildmatch", gitignore_patterns)
             print(f"Loaded .gitignore patterns from {gitignore_path}")
@@ -113,7 +113,7 @@ def crawl_local_files(
 
         # --- File is being processed ---        
         try:
-            with open(filepath, "r", encoding="utf-8") as f:
+            with open(filepath, "r", encoding="utf-8-sig") as f:
                 content = f.read()
             files_dict[relpath] = content
         except Exception as e: