Spaces:
Sleeping
Sleeping
File size: 7,132 Bytes
f84a02d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | #!/usr/bin/env python3
"""
Database Session Migration Script
Identifies and helps migrate manual database session management to the
context manager pattern.
Usage:
python scripts/migrate_db_sessions.py # Identify files to migrate
python scripts/migrate_db_sessions.py --fix # Auto-fix simple cases
"""
import ast
import os
from pathlib import Path
import re
from typing import List, Tuple
def find_manual_session_patterns(file_path: str) -> List[Tuple[int, str, str]]:
"""
Find manual session management patterns in a Python file.
Returns list of (line_number, pattern_type, matched_line)
"""
patterns = [
(r'SessionLocal\(\)', 'Direct SessionLocal() call'),
(r'with\s+SessionLocal\(\)', 'Manual with SessionLocal()'),
(r'db\s*=\s*SessionLocal\(\)', 'Variable assignment'),
(r'\.close\(\)', 'Manual close() call'),
(r'\.commit\(\)', 'Manual commit() call'),
]
findings = []
try:
with open(file_path, 'r', encoding='utf-8') as f:
lines = f.readlines()
for line_num, line in enumerate(lines, 1):
for pattern, description in patterns:
if re.search(pattern, line):
findings.append((line_num, description, line.strip()))
break # Only report first match per line
except Exception as e:
print(f"Error reading {file_path}: {e}")
return findings
def scan_directory(directory: str, exclude_dirs: List[str] = None) -> dict:
"""
Scan directory for Python files with manual session management.
"""
if exclude_dirs is None:
exclude_dirs = ['venv', '__pycache__', '.pytest_cache',
'node_modules', '.git', 'migrations', 'alembic']
results = {
'files_with_manual_sessions': [],
'total_files_scanned': 0,
'files_with_issues': {}
}
for root, dirs, files in os.walk(directory):
# Remove excluded directories
dirs[:] = [d for d in dirs if d not in exclude_dirs]
for file in files:
if file.endswith('.py'):
file_path = os.path.join(root, file)
results['total_files_scanned'] += 1
findings = find_manual_session_patterns(file_path)
if findings:
results['files_with_manual_sessions'].append(file_path)
results['files_with_issues'][file_path] = findings
return results
def categorize_by_priority(results: dict) -> dict:
"""
Categorize files by migration priority.
"""
high_priority = []
medium_priority = []
low_priority = []
for file_path, issues in results['files_with_issues'].items():
line_count = len(issues)
# High priority: Service layer files with multiple issues
if any(path in file_path for path in ['service', 'services', 'core']):
if line_count >= 3:
high_priority.append((file_path, line_count))
else:
medium_priority.append((file_path, line_count))
# Medium priority: API routes, integrations
elif any(path in file_path for path in ['api', 'integrations']):
if line_count >= 3:
medium_priority.append((file_path, line_count))
else:
low_priority.append((file_path, line_count))
# Low priority: Scripts, tests, tools
else:
low_priority.append((file_path, line_count))
# Sort by issue count (descending)
high_priority.sort(key=lambda x: x[1], reverse=True)
medium_priority.sort(key=lambda x: x[1], reverse=True)
low_priority.sort(key=lambda x: x[1], reverse=True)
return {
'high': high_priority,
'medium': medium_priority,
'low': low_priority
}
def main():
"""Main entry point."""
import argparse
parser = argparse.ArgumentParser(description='Migrate database session management')
parser.add_argument('--directory', default='.', help='Directory to scan')
parser.add_argument('--fix', action='store_true', help='Auto-fix simple cases')
parser.add_argument('--output', help='Output file for results')
args = parser.parse_args()
print("=" * 80)
print("Database Session Migration Scanner")
print("=" * 80)
print()
print(f"Scanning directory: {args.directory}")
print()
results = scan_directory(args.directory)
print(f"Files scanned: {results['total_files_scanned']}")
print(f"Files with manual sessions: {len(results['files_with_manual_sessions'])}")
print()
if not results['files_with_manual_sessions']:
print("✅ No files with manual session management found!")
return
# Categorize by priority
categorized = categorize_by_priority(results)
# Print results
print("Priority Classification:")
print("-" * 80)
if categorized['high']:
print(f"\n🔴 HIGH PRIORITY ({len(categorized['high'])} files):")
print(" Service layer files with multiple manual session patterns")
for file_path, count in categorized['high'][:10]:
rel_path = os.path.relpath(file_path, args.directory)
print(f" - {rel_path} ({count} issues)")
if categorized['medium']:
print(f"\n🟡 MEDIUM PRIORITY ({len(categorized['medium'])} files):")
print(" API routes and integrations")
for file_path, count in categorized['medium'][:10]:
rel_path = os.path.relpath(file_path, args.directory)
print(f" - {rel_path} ({count} issues)")
if categorized['low']:
print(f"\n🟢 LOW PRIORITY ({len(categorized['low'])} files):")
print(" Scripts, tests, and tools")
for file_path, count in categorized['low'][:10]:
rel_path = os.path.relpath(file_path, args.directory)
print(f" - {rel_path} ({count} issues)")
print()
print("=" * 80)
print(f"Total: {len(results['files_with_manual_sessions'])} files need migration")
print("=" * 80)
# Write output file if requested
if args.output:
with open(args.output, 'w') as f:
f.write("# Database Session Migration Report\n\n")
f.write(f"Total files: {len(results['files_with_manual_sessions'])}\n\n")
f.write("## High Priority\n\n")
for file_path, count in categorized['high']:
rel_path = os.path.relpath(file_path, args.directory)
f.write(f"- {rel_path} ({count} issues)\n")
f.write("\n## Medium Priority\n\n")
for file_path, count in categorized['medium']:
rel_path = os.path.relpath(file_path, args.directory)
f.write(f"- {rel_path} ({count} issues)\n")
f.write("\n## Low Priority\n\n")
for file_path, count in categorized['low']:
rel_path = os.path.relpath(file_path, args.directory)
f.write(f"- {rel_path} ({count} issues)\n")
print(f"\nReport written to: {args.output}")
if __name__ == '__main__':
main()
|