depaudit-cli/depaudit/checks/unused.py

from __future__ import annotations

import ast
import re
from dataclasses import dataclass
from pathlib import Path
from typing import Any

from depaudit.checks import UnusedDependency


@dataclass
class ImportStatement:
    module_name: str
    names: list[str]
    line_number: int
    is_from: bool
    alias: str | None = None


class SourceParser:
    def __init__(self, language: str):
        self.language = language

    def parse_file(self, file_path: Path) -> list[ImportStatement]:
        raise NotImplementedError


class PythonSourceParser(SourceParser):
    def __init__(self):
        super().__init__("python")

    def parse_file(self, file_path: Path) -> list[ImportStatement]:
        imports = []
        try:
            with open(file_path, "r", encoding="utf-8") as f:
                content = f.read()

            tree = ast.parse(content)
            for node in ast.walk(tree):
                if isinstance(node, ast.Import):
                    for alias in node.names:
                        imports.append(
                            ImportStatement(
                                module_name=alias.name,
                                names=[alias.asname or alias.name],
                                line_number=node.lineno,
                                is_from=False,
                                alias=alias.asname,
                            )
                        )
                elif isinstance(node, ast.ImportFrom):
                    module = node.module or ""
                    names = [alias.asname or alias.name for alias in node.names]
                    for alias in node.names:
                        imports.append(
                            ImportStatement(
                                module_name=f"{module}.{alias.name}" if module else alias.name,
                                names=[alias.asname or alias.name],
                                line_number=node.lineno,
                                is_from=True,
                                alias=alias.asname,
                            )
                        )
        except Exception:
            pass
        return imports


class JavaScriptSourceParser(SourceParser):
    def __init__(self):
        super().__init__("javascript")

    def parse_file(self, file_path: Path) -> list[ImportStatement]:
        imports = []
        content = file_path.read_text(encoding="utf-8")

        import_patterns = [
            (r"import\s+(?:\{[^}]*\}|\*\s+as\s+\w+|\w+)\s+from\s+[\"\']([^\"\']+)[\"\']", True),
            (r"import\s+[\"\']([^\"\']+)[\"\']", True),
            (r"require\s*\(\s*[\"\']([^\"\']+)[\"\']\s*\)", False),
        ]

        for pattern, is_from in import_patterns:
            for match in re.finditer(pattern, content):
                module_name = match.group(1)
                imports.append(
                    ImportStatement(
                        module_name=module_name,
                        names=[module_name.split("/")[-1].split("@")[0]],
                        line_number=content[:match.start()].count("\n") + 1,
                        is_from=is_from,
                    )
                )

        return imports


class GoSourceParser(SourceParser):
    def __init__(self):
        super().__init__("go")

    def parse_file(self, file_path: Path) -> list[ImportStatement]:
        imports = []
        content = file_path.read_text(encoding="utf-8")

        import_pattern = r"import\s*\(([^)]+)\)"
        block_match = re.search(import_pattern, content, re.DOTALL)

        if block_match:
            block = block_match.group(1)
            for line in block.split("\n"):
                import_match = re.search(r'"([^"]+)"', line)
                if import_match:
                    module_name = import_match.group(1)
                    imports.append(
                        ImportStatement(
                            module_name=module_name,
                            names=[module_name.split("/")[-1]],
                            line_number=content[:block_match.start()].count("\n") + 1,
                            is_from=True,
                        )
                    )

        inline_imports = re.findall(r'\bimport\s+["\']([^"\']+)["\']', content)
        for module_name in inline_imports:
            imports.append(
                ImportStatement(
                    module_name=module_name,
                    names=[module_name.split("/")[-1]],
                    line_number=1,
                    is_from=True,
                )
            )

        return imports


PARSERS = {
    "python": PythonSourceParser,
    "javascript": JavaScriptSourceParser,
    "go": GoSourceParser,
}


def get_source_parser(language: str) -> SourceParser | None:
    parser_class = PARSERS.get(language)
    if parser_class:
        return parser_class()
    return None


def check_unused_dependencies(
    dependencies: list[tuple[str, str]],
    source_dir: Path,
    language: str,
    exclude_patterns: list[str] | None = None,
) -> list[UnusedDependency]:
    exclude_patterns = exclude_patterns or []

    parser = get_source_parser(language)
    if parser is None:
        return []

    all_imports: set[str] = set()

    for file_path in source_dir.rglob("*"):
        if file_path.is_file():
            skip = False
            for pattern in exclude_patterns:
                if file_path.match(pattern):
                    skip = True
                    break
            if skip:
                continue

            if language == "python" and file_path.suffix == ".py":
                file_imports = parser.parse_file(file_path)
                all_imports.update(imp.module_name.split(".")[0] for imp in file_imports)
            elif language == "javascript" and file_path.suffix in (".js", ".jsx", ".ts", ".tsx"):
                file_imports = parser.parse_file(file_path)
                all_imports.update(imp.module_name.split("/")[0].split("@")[0] for imp in file_imports)
            elif language == "go" and file_path.suffix == ".go":
                file_imports = parser.parse_file(file_path)
                all_imports.update(imp.module_name.split("/")[-1] for imp in file_imports)

    unused = []
    for name, version in dependencies:
        normalized_name = name.lower().replace("_", "-").split("/")[-1].split("@")[0]

        found = False
        for imp in all_imports:
            normalized_imp = imp.lower().replace("_", "-")
            if normalized_name in normalized_imp or normalized_imp in normalized_name:
                found = True
                break

        if not found:
            unused.append(
                UnusedDependency(
                    package_name=name,
                    version=version,
                    language=language,
                    declared_in="dependency file",
                    file_path=str(source_dir),
                    reason=f"Package '{name}' is declared but never imported or required",
                )
            )

    return unused