From e8ce0ccc1da304117b65068ffe398ac808385804 Mon Sep 17 00:00:00 2001
From: 7000pctAUTO <lukems3823@gmail.com>
Date: Sun, 1 Feb 2026 23:46:51 +0000
Subject: [PATCH] Add utils and tests

---
 codechunk/utils/file_utils.py | 60 +++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)
 create mode 100644 codechunk/utils/file_utils.py

diff --git a/codechunk/utils/file_utils.py b/codechunk/utils/file_utils.py
new file mode 100644
index 0000000..74bf579
--- /dev/null
+++ b/codechunk/utils/file_utils.py
@@ -0,0 +1,60 @@
+from pathlib import Path
+from typing import Optional
+import hashlib
+
+
+def read_file_safe(file_path: Path, encoding: str = "utf-8") -> Optional[str]:
+    """Safely read a file, handling encoding errors."""
+    try:
+        return file_path.read_text(encoding=encoding, errors="replace")
+    except Exception:
+        return None
+
+
+def write_file_safe(content: str, file_path: Path, encoding: str = "utf-8") -> bool:
+    """Safely write to a file."""
+    try:
+        ensure_directory(file_path.parent)
+        file_path.write_text(content, encoding=encoding)
+        return True
+    except Exception:
+        return False
+
+
+def ensure_directory(path: Path) -> None:
+    """Ensure directory exists."""
+    path.mkdir(parents=True, exist_ok=True)
+
+
+def get_file_hash(file_path: Path, algorithm: str = "md5") -> Optional[str]:
+    """Get hash of file contents."""
+    try:
+        content = file_path.read_bytes()
+        if algorithm == "md5":
+            return hashlib.md5(content).hexdigest()
+        elif algorithm == "sha256":
+            return hashlib.sha256(content).hexdigest()
+        elif algorithm == "sha1":
+            return hashlib.sha1(content).hexdigest()
+        else:
+            return hashlib.md5(content).hexdigest()
+    except Exception:
+        return None
+
+
+def find_files_pattern(directory: Path, patterns: list) -> list:
+    """Find files matching patterns using fnmatch."""
+    from fnmatch import fnmatch
+    matches = []
+
+    for root, dirs, files in directory.walk():
+        for file in files:
+            file_path = Path(root) / file
+            rel_path = str(file_path.relative_to(directory))
+
+            for pattern in patterns:
+                if fnmatch(file, pattern) or fnmatch(rel_path, pattern):
+                    matches.append(file_path)
+                    break
+
+    return matches