guarddog-nexus/guarddog_nexus/nexus_client.py

"""Sonatype Nexus REST API client using httpx async."""

import hashlib
import os

import httpx

from guarddog_nexus.config import config
from guarddog_nexus.constants import (
    NPM_PATH_PREFIX,
    PYPI_PATH_PREFIX,
    SHA256_CHUNK_SIZE,
)
from guarddog_nexus.logging_setup import log


def extract_pypi_info(asset_path: str) -> tuple[str, str] | None:
    """Extract package name and version from a PyPI asset path.

    Path format: packages/requests/2.31.0/requests-2.31.0.tar.gz
    """
    parts = asset_path.strip("/").split("/")
    if len(parts) >= 3 and parts[0] == PYPI_PATH_PREFIX:
        return parts[1], parts[2]
    return None


def extract_go_info(asset_path: str) -> tuple[str, str] | None:
    """Extract module and version from a Go proxy asset path.

    Path format: packages/github.com/gin-gonic/gin/@v/v1.9.0.zip
    """
    cleaned = asset_path.strip("/")
    # Find @v/ marker
    idx = cleaned.find("/@v/")
    if idx == -1:
        return None
    if cleaned.startswith(PYPI_PATH_PREFIX + "/"):
        module = cleaned[len(PYPI_PATH_PREFIX) + 1 : idx]
    else:
        module = cleaned[:idx]
    if not module:
        return None
    # Version: after @v/ up to the next / or end
    ver_start = idx + 4  # len("/@v/")
    rest = cleaned[ver_start:]
    version = rest.split("/")[0] if "/" in rest else rest
    if version.endswith(".zip"):
        version = version[:-4]
    return module, version


def extract_npm_info(asset_path: str) -> tuple[str, str] | None:
    """Extract package name and version from an npm proxy asset path.

    Path format: packages/react/-/react-18.2.0.tgz
    """
    parts = asset_path.strip("/").split("/")
    if len(parts) < 4 or parts[0] != NPM_PATH_PREFIX:
        return None
    name = parts[1]
    # Last segment: <name>-<version>.tgz
    last = parts[-1]
    if last.startswith(name + "-"):
        raw = last[len(name) + 1 :]
        for ext in (".tgz", ".tar.gz"):
            if raw.endswith(ext):
                return name, raw[: -len(ext)]
    return None


# Map of ecosystem → extractor function
EXTRACTORS = {
    "pypi": extract_pypi_info,
    "go": extract_go_info,
    "npm": extract_npm_info,
}


def extract_package_info(asset_path: str, ecosystem: str) -> tuple[str, str] | None:
    """Extract package name and version based on ecosystem."""
    extractor = EXTRACTORS.get(ecosystem)
    if extractor:
        return extractor(asset_path)
    # Fallback for unknown ecosystems — try simple parts split
    parts = asset_path.strip("/").split("/")
    if len(parts) >= 3:
        return parts[1], parts[2]
    return None


async def download_asset(download_url: str, dest_dir: str) -> str | None:
    """Download an asset from Nexus using async httpx."""
    dest_path = os.path.join(dest_dir, os.path.basename(download_url.split("?")[0]))

    auth = httpx.BasicAuth(config.nexus_username, config.nexus_password)
    async with httpx.AsyncClient(
        auth=auth, timeout=config.nexus_download_timeout, follow_redirects=True
    ) as client:
        try:
            response = await client.get(download_url)
            response.raise_for_status()
            with open(dest_path, "wb") as f:
                f.write(response.content)
            return dest_path
        except Exception as e:
            log.warning("Failed to download %s: %s", download_url, e)
            return None


async def nexus_get(path: str) -> httpx.Response:
    """Make an authenticated GET request to Nexus REST API."""
    auth = httpx.BasicAuth(config.nexus_username, config.nexus_password)
    async with httpx.AsyncClient(
        auth=auth, timeout=config.nexus_api_timeout
    ) as client:
        return await client.get(f"{config.nexus_url.rstrip('/')}{path}")


def compute_sha256(filepath: str) -> str:
    h = hashlib.sha256()
    with open(filepath, "rb") as f:
        for chunk in iter(lambda: f.read(SHA256_CHUNK_SIZE), b""):
            h.update(chunk)
    return h.hexdigest()