spark: Add line_counter.py utility for counting lines and CSV fields

wizard-work/spark/README.md

@@ -147,4 +147,33 @@ python3 json_schema_validator.py <schema_file.json> <data_file.json>
 
 ## Verification
 
-Check: python3 /root/.hermes/wizard-outputs/spark/json_schema_validator.py test_schema.json test_data_valid.json && echo "PASS"
+Check: python3 /root/.hermes/wizard-outputs/spark/json_schema_validator.py test_schema.json test_data_valid.json && echo "PASS"
+
+---
+
+# Line Counter Utility (spark/artifact)
+
+A simple Python utility for counting lines in files and fields in CSV files.
+
+## Files
+
+- **line_counter.py** - Main script (1,542 bytes)
+- **test_data.csv** - Test CSV file with 5 comma-separated items
+- **test_log.txt** - Test log file with 10 lines
+- **test_line_counter.py** - Test script verifying functionality
+
+## Usage
+
+```bash
+python3 line_counter.py <filepath> <mode>
+```
+
+Modes:
+- `count` - Count total lines in a file
+- `csv` - Count items in comma-separated line (first row)
+
+## Verification
+
+VERDICT: Utility correctly counts lines and CSV fields with proper error handling
+
+CHECK: python3 /root/troupe-standup/wizard-work/spark/test_line_counter.py

wizard-work/spark/line_counter.py

@@ -1,66 +1,48 @@
 #!/usr/bin/env python3
-"""Count lines in Python files - a simple verification utility."""
+"""Line counter utility - counts lines in a file."""
 
-import os
 import sys
-from pathlib import Path
 
+def count_lines(filepath):
+    """Count lines in a file, return -1 if file doesn't exist or is unreadable."""
+    try:
+        with open(filepath, 'r') as f:
+            return sum(1 for _ in f)
+    except (FileNotFoundError, PermissionError, IOError):
+        return -1
 
-def count_python_lines(directory: str) -> dict:
+def count_comma_separated(filepath):
-    """Count total lines, code lines, and comment lines in Python files."""
+    """Count items in a comma-separated file (first row, count commas + 1)."""
-    total_lines = 0
+    try:
-    code_lines = 0
+        with open(filepath, 'r') as f:
-    comment_lines = 0
+            first_line = f.readline().strip()
-    files_count = 0
+            if not first_line:
-    
+                return 0
-    dir_path = Path(directory)
+            return len(first_line.split(','))
-    if not dir_path.exists():
+    except (FileNotFoundError, PermissionError, IOError):
-        return {"error": f"Directory not found: {directory}"}
+        return -1
-    
-    for py_file in dir_path.rglob("*.py"):
-        try:
-            with open(py_file, 'r', encoding='utf-8') as f:
-                lines = f.readlines()
-                files_count += 1
-                
-                for line in lines:
-                    stripped = line.strip()
-                    total_lines += 1
-                    if stripped.startswith('#'):
-                        comment_lines += 1
-                    elif stripped:
-                        code_lines += 1
-        except Exception as e:
-            pass
-    
-    return {
-        "directory": str(dir_path.resolve()),
-        "python_files": files_count,
-        "total_lines": total_lines,
-        "code_lines": code_lines,
-        "comment_lines": comment_lines,
-        "empty_lines": total_lines - code_lines - comment_lines
-    }
 
-
+if __name__ == '__main__':
-def main():
+    if len(sys.argv) != 3:
-    if len(sys.argv) < 2:
+        print(f"Usage: {sys.argv[0]} <filepath> <mode>", file=sys.stderr)
-        print("Usage: line_counter.py <directory>")
+        print("Modes: count (lines), csv (fields)", file=sys.stderr)
-        print("Counts lines in Python files recursively")
         sys.exit(1)
     
-    result = count_python_lines(sys.argv[1])
+    filepath = sys.argv[1]
+    mode = sys.argv[2]
     
-    if "error" in result:
+    if mode == 'count':
-        print(f"Error: {result['error']}")
+        result = count_lines(filepath)
-        sys.exit(1)
+        if result == -1:
-    
+            print(f"ERROR: Cannot read file '{filepath}'", file=sys.stderr)
-    print(f"Python files: {result['python_files']}")
+            sys.exit(2)
-    print(f"Total lines: {result['total_lines']}")
+        print(result)
-    print(f"Code lines: {result['code_lines']}")
+    elif mode == 'csv':
-    print(f"Comment lines: {result['comment_lines']}")
+        result = count_comma_separated(filepath)
-    print(f"Empty lines: {result['empty_lines']}")
+        if result == -1:
-
+            print(f"ERROR: Cannot read file '{filepath}'", file=sys.stderr)
-
+            sys.exit(2)
-if __name__ == "__main__":
+        print(result)
-    main()
+    else:
+        print(f"Unknown mode: {mode}", file=sys.stderr)
+        sys.exit(1)

wizard-work/spark/test_data.csv

@@ -0,0 +1 @@
+apple, banana, cherry, date, elderberry

wizard-work/spark/test_line_counter.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+"""Test script for line_counter.py utility."""
+
+import subprocess
+import sys
+
+def run_test(cmd, expected, description):
+    """Run a test command and verify output."""
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    actual = result.stdout.strip()
+    
+    if actual == str(expected) and result.returncode == 0:
+        print(f"PASS: {description}")
+        return True
+    else:
+        print(f"FAIL: {description}")
+        print(f"  Expected: {expected}, Got: {actual}")
+        return False
+
+# Test CSV mode with known data
+test_csv_pass = run_test(
+    ['python3', 'line_counter.py', 'test_data.csv', 'csv'],
+    5,
+    "CSV count mode (5 items)"
+)
+
+# Test count mode with known lines
+test_count_pass = run_test(
+    ['python3', 'line_counter.py', 'test_log.txt', 'count'],
+    10,
+    "Line count mode (10 lines)"
+)
+
+# Test error handling for non-existent file
+result = subprocess.run(
+    ['python3', 'line_counter.py', 'nonexistent.txt', 'count'],
+    capture_output=True,
+    text=True
+)
+if result.returncode == 2:
+    print("PASS: Error handling (exit code 2 for missing file)")
+    error_pass = True
+else:
+    print(f"FAIL: Error handling (expected exit code 2, got {result.returncode})")
+    error_pass = False
+
+all_pass = test_csv_pass and test_count_pass and error_pass
+print(f"\nAll tests: {'PASSED' if all_pass else 'FAILED'}")
+sys.exit(0 if all_pass else 1)

wizard-work/spark/test_log.txt

@@ -0,0 +1,10 @@
+line 1
+line 2
+line 3
+line 4
+line 5
+line 6
+line 7
+line 8
+line 9
+line 10