From d37c921f2939e454dd3735e639ec8da1c8087ae4 Mon Sep 17 00:00:00 2001
From: Test User <test@example.com>
Date: Wed, 8 Apr 2026 16:32:37 +0800
Subject: [PATCH 1/2] Fix path regex and prevent backup file overwriting

- Fix PATH_REGEX in validate.py: The regex was incorrectly matching
  relative paths like 'src/file.js' as 'rc/' instead of the full path.
  Changed to use non-capturing group with optional prefix.

- Add safety check in compress.py: Prevent silent overwriting of
  existing .original.md backup files. Now aborts with a warning
  instead of overwriting potentially important backup content.

- Add proper module initialization in __init__.py: Previously empty,
  now includes __all__ exports and __version__ for proper imports.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 caveman-compress/scripts/__init__.py | 9 +++++++++
 caveman-compress/scripts/compress.py | 7 +++++++
 caveman-compress/scripts/validate.py | 3 ++-
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/caveman-compress/scripts/__init__.py b/caveman-compress/scripts/__init__.py
index e69de29..16b8c53 100644
--- a/caveman-compress/scripts/__init__.py
+++ b/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"
diff --git a/caveman-compress/scripts/compress.py b/caveman-compress/scripts/compress.py
index 2a19760..977a4ea 100644
--- a/caveman-compress/scripts/compress.py
+++ b/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))
diff --git a/caveman-compress/scripts/validate.py b/caveman-compress/scripts/validate.py
index 361156b..090b5ed 100644
--- a/caveman-compress/scripts/validate.py
+++ b/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\-/\\\.]+")
+# Fixed: use non-capturing group for prefix, and handle relative paths without leading ./ or /
+PATH_REGEX = re.compile(r"(?:\./|\.\./|/|[A-Za-z]:)?[\w\-/\\\.]+")
 
 
 class ValidationResult:

From 8195e1a4a04ecbe8bb39e67030624d023da5b6fb Mon Sep 17 00:00:00 2001
From: Julius Brussee <juliusbrussee@gmail.com>
Date: Thu, 9 Apr 2026 01:05:31 +0200
Subject: [PATCH 2/2] fix: PATH_REGEX must require path separator to avoid
 false positives

Making the prefix optional matched every English word as a path.
Now requires either a path prefix (./ ../ / drive:) or contains / or \.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 caveman-compress/scripts/validate.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/caveman-compress/scripts/validate.py b/caveman-compress/scripts/validate.py
index 090b5ed..e9fff3f 100644
--- a/caveman-compress/scripts/validate.py
+++ b/caveman-compress/scripts/validate.py
@@ -8,8 +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
-# Fixed: use non-capturing group for prefix, and handle relative paths without leading ./ or /
-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: