spark: add text analyzer utility with verification test

wizard-work/spark/test_text_analyzer.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python3
+"""Verification test for text_analyzer.py"""
+import subprocess
+import sys
+
+# Run the analyzer
+result = subprocess.run(
+    ['python3', '/root/.hermes/wizard-outputs/spark/text_analyzer.py', 
+     '/root/.hermes/wizard-outputs/spark/test_input.txt'],
+    capture_output=True, text=True
+)
+
+output = result.stdout.strip()
+print("Analyzer output:")
+print(output)
+print()
+
+# Verify against wc (ground truth)
+lines = result.stdout.count('Lines: 1')
+words = result.stdout.count('Words: 24')
+chars = result.stdout.count('Characters: 125')
+
+print(f"Lines check: {lines > 0}")
+print(f"Words check: {words > 0}")
+print(f"Chars check: {chars > 0}")
+
+# Check exit code
+assert result.returncode == 0, f"Expected exit code 0, got {result.returncode}"
+assert lines > 0, "Missing Lines: 1"
+assert words > 0, "Missing Words: 24"
+assert chars > 0, "Missing Characters: 125"
+
+print("\nAll verifications passed!")
+sys.exit(0)

wizard-work/spark/text_analyzer.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+"""Text file analyzer: count words, lines, characters."""
+
+import sys
+from pathlib import Path
+
+
+def analyze_file(filepath: str) -> dict:
+    """Analyze a text file and return counts."""
+    p = Path(filepath)
+    if not p.exists():
+        raise FileNotFoundError(f"File not found: {filepath}")
+    
+    content = p.read_text(encoding='utf-8')
+    lines = content.splitlines()
+    
+    return {
+        'filepath': filepath,
+        'lines': len(lines),
+        'words': len(content.split()),
+        'characters': len(content),
+        'bytes': len(content.encode('utf-8'))
+    }
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: text_analyzer.py <file>", file=sys.stderr)
+        sys.exit(1)
+    
+    try:
+        result = analyze_file(sys.argv[1])
+        print(f"File: {result['filepath']}")
+        print(f"Lines: {result['lines']}")
+        print(f"Words: {result['words']}")
+        print(f"Characters: {result['characters']}")
+        print(f"Bytes (UTF-8): {result['bytes']}")
+    except FileNotFoundError as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(2)
+
+
+if __name__ == '__main__':
+    main()