Getting Started

uv tool install codegen

# Navigate to your repository
cd path/to/git/repository

# Initialize codegen and launch Jupyter
codegen notebook

from codegen import Codebase

# Parse a codebase
codebase = Codebase("./")

# Print overall stats
print("🔍 Codebase Analysis")
print("=" * 50)
print(f"📚 Total Classes: {len(codebase.classes)}")
print(f"⚡ Total Functions: {len(codebase.functions)}")
print(f"🔄 Total Imports: {len(codebase.imports)}")

# Find class with most inheritance
if codebase.classes:
    deepest_class = max(codebase.classes, key=lambda x: len(x.superclasses))
    print(f"\n🌳 Class with most inheritance: {deepest_class.name}")
    print(f"   📊 Chain Depth: {len(deepest_class.superclasses)}")
    print(f"   ⛓️ Chain: {' -> '.join(s.name for s in deepest_class.superclasses)}")

# Find first 5 recursive functions
recursive = [f for f in codebase.functions
            if any(call.name == f.name for call in f.function_calls)][:5]
if recursive:
    print(f"\n🔄 Recursive functions:")
    for func in recursive:
        print(f"  - {func.name}")

from collections import Counter

# Filter to all test functions and classes
test_functions = [x for x in codebase.functions if x.name.startswith('test_')]
test_classes = [x for x in codebase.classes if x.name.startswith('Test')]

print("🧪 Test Analysis")
print("=" * 50)
print(f"📝 Total Test Functions: {len(test_functions)}")
print(f"🔬 Total Test Classes: {len(test_classes)}")
print(f"📊 Tests per File: {len(test_functions) / len(codebase.files):.1f}")

# Find files with the most tests
print("\n📚 Top Test Files by Class Count")
print("-" * 50)
file_test_counts = Counter([x.file for x in test_classes])
for file, num_tests in file_test_counts.most_common()[:5]:
    print(f"🔍 {num_tests} test classes: {file.filepath}")
    print(f"   📏 File Length: {len(file.source)} lines")
    print(f"   💡 Functions: {len(file.functions)}")

print("\n📦 Splitting Test Files")
print("=" * 50)

# Process top 5 largest test files
for file, num_tests in file_test_counts.most_common()[:5]:
    # Create a new directory based on the file name
    base_name = file.path.replace('.py', '')
    print(f"\n🔄 Processing: {file.filepath}")
    print(f"   📊 {num_tests} test classes to split")

    # Move each test class to its own file
    for test_class in file.classes:
        if test_class.name.startswith('Test'):
            # Create descriptive filename from test class name
            new_file = f"{base_name}/{test_class.name.lower()}.py"
            print(f"   📝 Moving {test_class.name} -> {new_file}")

            # Codegen handles all the complexity:
            # - Creates directories if needed
            # - Updates all imports automatically
            # - Maintains test dependencies
            # - Preserves decorators and docstrings
            test_class.move_to_file(new_file)

# Commit changes to disk
codebase.commit()

# Grab specific content by name
my_resource = codebase.get_symbol('TestResource')

# Find classes that inherit from a specific base
resource_classes = [
    cls for cls in codebase.classes
    if cls.is_subclass_of('Resource')
]

# Find functions with specific decorators
test_functions = [
    f for f in codebase.functions
    if any('pytest' in d.source for d in f.decorators)
]

# Find files matching certain patterns
test_files = [
    f for f in codebase.files
    if f.name.startswith('test_')
]

# Move all Enum classes to a dedicated file
for cls in codebase.classes:
    if cls.is_subclass_of('Enum'):
        # Codegen automatically:
        # - Updates all imports that reference this class
        # - Maintains the class's dependencies
        # - Preserves comments and decorators
        # - Generally performs this in a sane manner
        cls.move_to_file(f'enums.py')

# Rename a function and all its usages
old_function = codebase.get_function('process_data')
old_function.rename('process_resource')  # Updates all references automatically

# Change a function's signature
handler = codebase.get_function('event_handler')
handler.get_parameter('e').rename('event') # Automatically updates all call-sites
handler.add_parameter('timeout: int = 30')  # Handles formatting and edge cases
handler.add_return_type('Response | None')

# Perform surgery on call-sites
for fcall in handler.call_sites:
    arg = fcall.get_arg_by_parameter_name('env')
    # f(..., env={ data: x }) => f(..., env={ data: x or None })
    if isinstance(arg.value, Collection):
        data_key = arg.value.get('data')
        data_key.value.edit(f'{data_key.value} or None')

# Find dead code
for func in codebase.functions:
    if len(function.usages) == 0:
        print(f'🗑️ Dead code: {func.name}')
        func.remove()

# Analyze import relationships
file = codebase.get_file('api/endpoints.py')
print("\nFiles that import endpoints.py:")
for import_stmt in file.inbound_imports:
    print(f"  {import_stmt.file.path}")

print("\nFiles that endpoints.py imports:")
for import_stmt in file.imports:
    if import_stmt.resolved_symbol:
        print(f"  {import_stmt.resolved_symbol.file.path}")

# Explore class hierarchies
base_class = codebase.get_class('BaseModel')
if base_class:
    print(f"\nClasses that inherit from {base_class.name}:")
    for subclass in base_class.subclasses:
        print(f"  {subclass.name}")
        # We can go deeper in the inheritance tree
        for sub_subclass in subclass.subclasses:
            print(f"    └─ {sub_subclass.name}")