Merge PR #39: Fix path regex and prevent backup file overwriting

caveman-compress/scripts/__init__.py

@@ -0,0 +1,9 @@
+"""Caveman compress scripts.
+
+This package provides tools to compress natural language markdown files
+into caveman format to save input tokens.
+"""
+
+__all__ = ["cli", "compress", "detect", "validate"]
+
+__version__ = "1.0.0"

caveman-compress/scripts/compress.py

@@ -94,6 +94,13 @@ def compress_file(filepath: Path) -> bool:
     original_text = filepath.read_text(errors="ignore")
     backup_path = filepath.with_name(filepath.stem + ".original.md")
 
+    # Check if backup already exists to prevent accidental overwriting
+    if backup_path.exists():
+        print(f"⚠️ Backup file already exists: {backup_path}")
+        print("The original backup may contain important content.")
+        print("Aborting to prevent data loss. Please remove or rename the backup file if you want to proceed.")
+        return False
+
     # Step 1: Compress
     print("🧠 Compressing with Claude...")
     compressed = call_claude(build_compress_prompt(original_text))

caveman-compress/scripts/validate.py

@@ -8,7 +8,8 @@ HEADING_REGEX = re.compile(r"^(#{1,6})\s+(.*)", re.MULTILINE)
 BULLET_REGEX = re.compile(r"^\s*[-*+]\s+", re.MULTILINE)
 
 # crude but effective path detection
-PATH_REGEX = re.compile(r"(\./|\../|/|[A-Za-z]:\\)[\w\-/\\\.]+")
+# Requires either a path prefix (./ ../ / or drive letter) or a slash/backslash within the match
+PATH_REGEX = re.compile(r"(?:\./|\.\./|/|[A-Za-z]:\\)[\w\-/\\\.]+|[\w\-\.]+[/\\][\w\-/\\\.]+")
 
 
 class ValidationResult: