procurement-ingest/lambdas/api/handler.py

"""Procurement API Lambda (API Gateway REST proxy integration).

Auth is split by route class and enforced at two layers:
- Data routes: AWS_IAM at the gateway (SigV4; cross-account callers allowed by
  the API resource policy). The handler does NOT re-check a token there --
  authorization is API Gateway's job on those routes.
- Docs routes (/docs, /openapi.json): reachable at the gateway (auth NONE +
  resource-policy carve-out) but the handler fails closed on the shared
  header token via web_ui_auth (same secret + constant-time compare as the
  web UIs), so they are never an unauthenticated data path (INFRA-74).
"""

import logging
from pathlib import Path

import po_repo
import wo_repo
from botocore.exceptions import ClientError
from pagination import BadCursor, clamp_limit
from router import DATA_ROUTES, DOCS_ROUTES, PLANNED_ROUTES
from serialization import error_response, json_response
from web_ui_auth import is_authenticated

logger = logging.getLogger()
logger.setLevel(logging.INFO)

_MODULE_DIR = Path(__file__).resolve().parent
_SPEC_PATH = _MODULE_DIR / "openapi.json"
_DOCS_PATH = _MODULE_DIR / "docs.html"
_SWAGGER_CSS_PATH = _MODULE_DIR / "swagger-ui.css"
_SWAGGER_JS_PATH = _MODULE_DIR / "swagger-ui-bundle.js"
_SWAGGER_PRESET_PATH = _MODULE_DIR / "swagger-ui-standalone-preset.js"
# The docs page template carries these placeholders, filled server-side so
# /docs is a single token-gated request (a browser can't attach the auth
# header to a follow-up asset fetch) with the stock Swagger UI + spec inlined,
# no CDN.
_SPEC_PLACEHOLDER = "__OPENAPI_SPEC_JSON__"
_CSS_PLACEHOLDER = "__SWAGGER_UI_CSS__"
_JS_PLACEHOLDER = "__SWAGGER_UI_JS__"
_PRESET_PLACEHOLDER = "__SWAGGER_UI_STANDALONE_PRESET_JS__"

_spec_cache = None
_docs_shell_cache = None
# The server URL committed in openapi.json; swapped for the live invoke URL
# (derived from the request) when the spec is served, so the docs page shows a
# correct, current endpoint even if the RestApi is recreated.
_COMMITTED_SERVER_URL = "https://mvul1efda2.execute-api.us-east-1.amazonaws.com/prod"

_REPO_FUNCS = {
    "list_work_orders": wo_repo.list_work_orders,
    "get_work_order": wo_repo.get_work_order,
    "list_comments": wo_repo.list_comments,
    "list_purchase_orders": po_repo.list_purchase_orders,
    "get_purchase_order": po_repo.get_purchase_order,
    "list_verified_sites": po_repo.list_verified_sites,
    "get_verified_site": po_repo.get_verified_site,
}

_PATH_PARAM_BY_RESOURCE = {
    "/work-orders/{workOrderId}": "workOrderId",
    "/work-orders/{workOrderId}/comments": "workOrderId",
    "/purchase-orders/{poNumber}": "poNumber",
    "/verified-sites/{siteCode}": "siteCode",
}


# Headers on the docs responses: the token rides in the ?token= query shim,
# so keep the token-keyed URL and page out of shared/browser caches and out of
# any Referer sent to a followed link.
_DOCS_SECURITY_HEADERS = {
    "Cache-Control": "no-store",
    "Referrer-Policy": "no-referrer",
}


def _load_spec() -> str:
    """The committed spec text (cached)."""
    global _spec_cache
    if _spec_cache is None:
        _spec_cache = _SPEC_PATH.read_text(encoding="utf-8")
    return _spec_cache


def _base_url(event: dict) -> str | None:
    rc = event.get("requestContext") or {}
    domain, stage = rc.get("domainName"), rc.get("stage")
    return f"https://{domain}/{stage}" if domain and stage else None


def _spec_for_request(event: dict) -> str:
    """Committed spec with servers[0].url set to the live invoke URL when the
    request context provides it (falls back to the committed literal)."""
    raw = _load_spec()
    base = _base_url(event)
    return raw.replace(_COMMITTED_SERVER_URL, base) if base else raw


def _docs_shell() -> str:
    """The Swagger UI page with the vendored CSS/JS/preset inlined; the SPEC
    placeholder is left intact so the per-request server-injected spec splices
    in cheaply (the heavy ~1.8MB assets are assembled once and cached).

    Each blob is spliced into a <style>/<script> block, where the HTML parser
    ends the element at the first literal "</style"/"</script" regardless of
    quoting, so guard each against a breakout a future asset update could add
    (the pinned assets have none today): JS/preset "</script" -> "<\\/script"
    (equivalent inside JS string/regex), CSS "</style" -> "<\\/style".
    """
    global _docs_shell_cache
    if _docs_shell_cache is None:
        css = _SWAGGER_CSS_PATH.read_text(encoding="utf-8").replace(
            "</style", "<\\/style"
        )
        js = _SWAGGER_JS_PATH.read_text(encoding="utf-8").replace(
            "</script", "<\\/script"
        )
        preset = _SWAGGER_PRESET_PATH.read_text(encoding="utf-8").replace(
            "</script", "<\\/script"
        )
        _docs_shell_cache = (
            _DOCS_PATH.read_text(encoding="utf-8")
            .replace(_CSS_PLACEHOLDER, css)
            .replace(_JS_PLACEHOLDER, js)
            .replace(_PRESET_PLACEHOLDER, preset)
        )
    return _docs_shell_cache


def _render_docs_html(event: dict) -> str:
    # "<" -> < so a spec string can never close the <script> block (same
    # value to JSON.parse); the spec object is inlined into SwaggerUIBundle.
    spec = _spec_for_request(event).replace("<", "\\u003c")
    return _docs_shell().replace(_SPEC_PLACEHOLDER, spec)


def _with_token_shim(event: dict) -> dict:
    """Copy a ?token= query parameter into an x-auth-token header.

    Browsers can't set headers on plain navigation, so /docs accepts the
    shared token as a query parameter too. The constant-time compare still
    happens inside web_ui_auth -- this only synthesizes the header on a
    shallow copy. Acceptable only while API Gateway access logging stays off
    (nothing at the gateway records the query string); rotate the token if
    access logging is ever enabled.
    """
    qs = event.get("queryStringParameters") or {}
    token = qs.get("token")
    if not token:
        return event
    shimmed = dict(event)
    headers = dict(event.get("headers") or {})
    headers["x-auth-token"] = token
    shimmed["headers"] = headers
    return shimmed


def _docs_response(resource: str, event: dict) -> dict:
    # SECURITY INVARIANT: these routes serve ONLY the committed spec and the
    # static docs page -- never table data. The gateway resource policy allows
    # Principal "*" on exactly these two GETs on the strength of that; serving
    # anything dynamic here requires a resource-policy + security re-review.
    if not is_authenticated(_with_token_shim(event)):
        return error_response(401, "unauthorized")
    if resource == "/openapi.json":
        return {
            "statusCode": 200,
            "headers": {"Content-Type": "application/json", **_DOCS_SECURITY_HEADERS},
            "body": _spec_for_request(event),
        }
    return {
        "statusCode": 200,
        "headers": {
            "Content-Type": "text/html; charset=utf-8",
            **_DOCS_SECURITY_HEADERS,
        },
        "body": _render_docs_html(event),
    }


def _data_response(route_key: tuple, event: dict) -> dict:
    method, resource = route_key
    func = _REPO_FUNCS[DATA_ROUTES[route_key]]
    qs = event.get("queryStringParameters") or {}
    path_params = event.get("pathParameters") or {}

    if DATA_ROUTES[route_key].startswith("list_"):
        limit = clamp_limit(qs.get("limit"))
        cursor = qs.get("cursor")
        if resource in _PATH_PARAM_BY_RESOURCE:
            entity_id = path_params.get(_PATH_PARAM_BY_RESOURCE[resource], "")
            items, next_cursor = func(entity_id, limit, cursor)
        else:
            items, next_cursor = func(limit, cursor)
        return json_response(200, {"items": items, "next_cursor": next_cursor})

    entity_id = path_params.get(_PATH_PARAM_BY_RESOURCE[resource], "")
    item = func(entity_id)
    if item is None:
        return error_response(404, "not found")
    return json_response(200, item)


def _dispatch(route_key: tuple, event: dict) -> dict:
    if route_key in PLANNED_ROUTES:
        return error_response(501, "planned endpoint - not implemented (phase 2)")
    if route_key in DOCS_ROUTES:
        return _docs_response(route_key[1], event)
    if route_key in DATA_ROUTES:
        return _data_response(route_key, event)
    return error_response(404, "not found")


def handler(event, context):
    # Deploy-guard healthcheck: a direct-invoke {"healthcheck": true} probe
    # returns before any routing/auth so the post-deploy smoke gate can verify
    # the bundle imports and the runtime boots.
    if isinstance(event, dict) and event.get("healthcheck") is True:
        return {"healthcheck": "ok"}

    method = (event.get("httpMethod") or "").upper()
    resource = event.get("resource") or ""

    try:
        return _dispatch((method, resource), event)
    except BadCursor as exc:
        return error_response(400, str(exc))
    except ClientError as exc:
        # A client-supplied cursor that survives validation but is still
        # inconsistent at the data layer makes DynamoDB raise
        # ValidationException; map it to 400, not 500, so a crafted cursor
        # can't drive the 5xx alarm. Any other AWS error is a real 500.
        if exc.response.get("Error", {}).get("Code") == "ValidationException":
            return error_response(400, "cursor is not valid")
        logger.exception("AWS error serving %s %s", method, resource)
        return error_response(500, "internal error")
    except Exception:
        # A raised exception would surface as an opaque 502 from the proxy
        # integration; return a clean 500 instead. The API Gateway 5XX alarm
        # pages on these; the exception (never the request token) is logged.
        logger.exception("Unhandled error serving %s %s", method, resource)
        return error_response(500, "internal error")