spark: add text_stats.py - JSON utility to count lines, words, chars in files

wizard-work/spark/text_stats.py

@@ -1,34 +1,38 @@
 #!/usr/bin/env python3
 """
-text_stats.py - Quick utility to count lines, words, and characters in text files.
-Usage: python text_stats.py <file1> [file2] ...
+text_stats.py - Quick utility to count lines, words, and characters in a file.
+
+Usage: python3 text_stats.py <file_path>
+Output: JSON with {path, lines, words, chars}
 """
+
 import sys
+import json
+from pathlib import Path
 
-def analyze_text(filepath):
-    """Return (lines, words, chars) for a text file."""
-    try:
-        with open(filepath, 'r', encoding='utf-8', errors='replace') as f:
-            content = f.read()
-        lines = content.count('\n') + (1 if content and not content.endswith('\n') else 0)
-        lines = len(content.splitlines()) if content.strip() else 0
-        words = len(content.split())
-        chars = len(content)
-        return lines, words, chars
-    except Exception as e:
-        return None, None, None
 
-def main():
-    if len(sys.argv) < 2:
-        print("Usage: python text_stats.py <file1> [file2] ...")
+def text_stats(path: str) -> dict:
+    """Return dict with lines, words, and chars count for given file."""
+    p = Path(path)
+    if not p.is_file():
+        raise FileNotFoundError(f"No such file: {path}")
+
+    content = p.read_text()
+    lines = len(content.splitlines()) if content.strip() else 0
+    words = len(content.split())
+    chars = len(content)
+
+    return {"path": str(p.resolve()), "lines": lines, "words": words, "chars": chars}
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print(json.dumps({"error": "Usage: text_stats.py <file_path>"}))
         sys.exit(1)
 
-    for filepath in sys.argv[1:]:
-        lines, words, chars = analyze_text(filepath)
-        if lines is None:
-            print(f"{filepath}: error reading file")
-            continue
-        print(f"{filepath}: {lines} lines, {words} words, {chars} chars")
-
-if __name__ == '__main__':
-    main()
+    try:
+        result = text_stats(sys.argv[1])
+        print(json.dumps(result, indent=2))
+    except Exception as e:
+        print(json.dumps({"error": str(e)}))
+        sys.exit(1)