From 397bcb3c99f91c3c9b5109a294da66831c01e6aa Mon Sep 17 00:00:00 2001
From: spark <spark@agents.invalid>
Date: Sat, 31 Oct 2026 01:22:14 +0000
Subject: [PATCH] spark: add wordcount utility verified against wc output

---
 wizard-work/spark/test_sample.txt          |  9 ++---
 wizard-work/spark/verify_wordcount_test.py | 40 ++++++++++++++++++++++
 wizard-work/spark/wordcount.py             | 39 ++++++++++-----------
 3 files changed, 61 insertions(+), 27 deletions(-)
 create mode 100644 wizard-work/spark/verify_wordcount_test.py

diff --git a/wizard-work/spark/test_sample.txt b/wizard-work/spark/test_sample.txt
index 812a421..ba442ae 100644
--- a/wizard-work/spark/test_sample.txt
+++ b/wizard-work/spark/test_sample.txt
@@ -1,6 +1,3 @@
-# Test file with known content
-This is a test.
-Multiple lines here.
-And a third line.
-
-Total: 4 lines, 8 words, 37 chars including newlines.
\ No newline at end of file
+Hello world
+This is a test file
+With three lines
\ No newline at end of file
diff --git a/wizard-work/spark/verify_wordcount_test.py b/wizard-work/spark/verify_wordcount_test.py
new file mode 100644
index 0000000..bbb8a3b
--- /dev/null
+++ b/wizard-work/spark/verify_wordcount_test.py
@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+"""Verification test for wordcount.py - must match wc output exactly."""
+import subprocess
+import sys
+import tempfile
+import os
+
+# Create test file with known content
+test_content = "Hello world\nThis is a test file\nWith three lines\n"
+test_file = "/root/troupe-standup/test_verification.txt"
+with open(test_file, 'w') as f:
+    f.write(test_content)
+
+# Get wc output
+wc_result = subprocess.run(['wc', test_file], capture_output=True, text=True)
+wc_lines, wc_words, wc_chars = map(int, wc_result.stdout.strip().split()[:3])
+
+# Get wordcount.py output
+pyc_result = subprocess.run(
+    ['python3', '/root/.hermes/wizard-outputs/spark/wordcount.py', test_file],
+    capture_output=True, text=True
+)
+
+if pyc_result.returncode != 0:
+    print(f"FAIL: wordcount.py returned {pyc_result.returncode}")
+    print(pyc_result.stderr)
+    sys.exit(1)
+
+parts = pyc_result.stdout.strip().split()
+py_lines, py_words, py_chars = int(parts[0]), int(parts[1]), int(parts[2])
+
+print(f"wc:    {wc_lines} lines, {wc_words} words, {wc_chars} chars")
+print(f"wordcount.py: {py_lines} lines, {py_words} words, {py_chars} chars")
+
+if (wc_lines == py_lines and wc_words == py_words and wc_chars == py_chars):
+    print("PASS: outputs match")
+    sys.exit(0)
+else:
+    print("FAIL: outputs do not match")
+    sys.exit(1)
\ No newline at end of file
diff --git a/wizard-work/spark/wordcount.py b/wizard-work/spark/wordcount.py
index 749def1..0c71814 100644
--- a/wizard-work/spark/wordcount.py
+++ b/wizard-work/spark/wordcount.py
@@ -1,31 +1,28 @@
 #!/usr/bin/env python3
-"""Word count utility - counts words in a file and outputs JSON result."""
-import json
+"""Simple word/line/char counter for files."""
 import sys
 from pathlib import Path
 
-def word_count(filepath):
-    """Count words in file and return stats."""
-    path = Path(filepath)
-    if not path.exists():
-        return {"error": f"File not found: {filepath}"}
-    
-    content = path.read_text()
-    words = content.split()
-    lines = content.splitlines()
-    
+
+def count_file(path: str) -> dict:
+    """Return line, word, and char counts for a file (wc-style)."""
+    content = Path(path).read_text()
+    # wc -l counts newline characters, not lines
     return {
-        "file": str(path),
-        "bytes": path.stat().st_size,
-        "lines": len(lines),
-        "words": len(words),
-        "characters": len(content)
+        'lines': content.count('\n'),
+        'words': len(content.split()),
+        'chars': len(content)
     }
 
-if __name__ == "__main__":
+
+def main():
     if len(sys.argv) < 2:
-        print(json.dumps({"error": "Usage: wordcount.py <file>"}))
+        print("Usage: wordcount.py <file>", file=sys.stderr)
         sys.exit(1)
     
-    result = word_count(sys.argv[1])
-    print(json.dumps(result, indent=2))
\ No newline at end of file
+    result = count_file(sys.argv[1])
+    print(f"{result['lines']} {result['words']} {result['chars']} {sys.argv[1]}")
+
+
+if __name__ == '__main__':
+    main()
\ No newline at end of file