spark: add file_analyzer.py - text file statistics utility

wizard-work/spark/file_analyzer.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+"""Text file analyzer - counts lines, words, characters, bytes.
+Usage: python3 file_analyzer.py <filepath>
+Outputs JSON to stdout."""
+
+import sys
+import json
+import os
+
+def analyze_file(filepath):
+    """Analyze a text file and return stats."""
+    if not os.path.exists(filepath):
+        return {"error": f"File not found: {filepath}"}
+    
+    if not os.path.isfile(filepath):
+        return {"error": f"Not a file: {filepath}"}
+    
+    stats = {
+        "path": os.path.abspath(filepath),
+        "size_bytes": os.path.getsize(filepath),
+    }
+    
+    try:
+        with open(filepath, 'r', encoding='utf-8') as f:
+            content = f.read()
+    except Exception as e:
+        return {"error": f"Cannot read file: {e}"}
+    
+    stats["size_chars"] = len(content)
+    stats["lines"] = content.count('\n') + (1 if content and not content.endswith('\n') else 0)
+    stats["words"] = len(content.split())
+    stats["unique_chars"] = len(set(content))
+    
+    return stats
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print(json.dumps({"error": "Usage: file_analyzer.py <filepath>"}))
+        sys.exit(1)
+    
+    result = analyze_file(sys.argv[1])
+    print(json.dumps(result, indent=2))
+    
+    if "error" in result:
+        sys.exit(1)