FabledCurator/tests/test_backup_s3.py

"""The backup destination's S3 client (services/backup_s3.py): signatures match
AWS's published Signature Version 4 examples, and the calls send and read what
S3 expects, over a real HTTP connection to a local stand-in server."""
import hashlib
import socket
import threading
from datetime import UTC, datetime
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer

import pytest

from backend.app.services import backup_s3 as s3

# AWS's example credentials and moment ("Signature Calculations for the
# Authorization Header", Amazon S3 API reference).
KEY_ID = "AKIAIOSFODNN7EXAMPLE"
SECRET = "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY"
AT = datetime(2013, 5, 24, tzinfo=UTC)


def _signature(headers):
    return headers["Authorization"].rsplit("Signature=", 1)[1]


def test_aws_example_get_object():
    h = s3.sign("GET", "https://examplebucket.s3.amazonaws.com/test.txt",
                {"Range": "bytes=0-9"}, s3.EMPTY_SHA256, KEY_ID, SECRET, "us-east-1", AT)
    assert "SignedHeaders=host;range;x-amz-content-sha256;x-amz-date," in h["Authorization"]
    assert "Credential=AKIAIOSFODNN7EXAMPLE/20130524/us-east-1/s3/aws4_request" in h[
        "Authorization"]
    assert _signature(h) == "f0e8bdb87c964420e857bd35b5d6ed310bd44f0170aba48dd91039c6036bdb41"


def test_aws_example_list_objects():
    h = s3.sign("GET", "https://examplebucket.s3.amazonaws.com/?max-keys=2&prefix=J", {},
                s3.EMPTY_SHA256, KEY_ID, SECRET, "us-east-1", AT)
    assert _signature(h) == "34b48302e7b5fa45bde8084f4b7868a86f0a534bc59db6670ed5711ef69dc6f7"


def test_a_changed_secret_changes_the_signature():
    url = "https://examplebucket.s3.amazonaws.com/test.txt"
    a = s3.sign("GET", url, {}, s3.EMPTY_SHA256, KEY_ID, SECRET, "us-east-1", AT)
    b = s3.sign("GET", url, {}, s3.EMPTY_SHA256, KEY_ID, SECRET + "x", "us-east-1", AT)
    assert _signature(a) != _signature(b)


def test_paths_are_path_style_and_keys_are_escaped():
    t = s3.S3Target("http://archives.example:8081/s3", "curator", KEY_ID, SECRET)
    assert t.url("media/ab/cd/abcd.jpg") == "http://archives.example:8081/s3/curator/media/ab/cd/abcd.jpg"
    assert t.url() == "http://archives.example:8081/s3/curator/"
    assert t.url("a b+c.jpg") == "http://archives.example:8081/s3/curator/a%20b%2Bc.jpg"


# ── Calls, against a local stand-in ─────────────────────────────────────────


class _Server:
    """A local HTTP server that records each request and answers with
    `reply(handler) -> (status, body)` or `(status, body, headers)`."""

    def __init__(self, reply):
        self.seen = []
        outer = self

        class Handler(BaseHTTPRequestHandler):
            def _serve(self):
                length = int(self.headers.get("Content-Length") or 0)
                outer.seen.append({
                    "method": self.command, "path": self.path,
                    "headers": {k.lower(): v for k, v in self.headers.items()},
                    "body": self.rfile.read(length) if length else b"",
                })
                status, body, *extra = reply(self)
                self.send_response(status)
                for name, value in (extra[0] if extra else {}).items():
                    self.send_header(name, value)
                self.send_header("Content-Length", str(len(body)))
                self.end_headers()
                self.wfile.write(body)

            do_GET = do_PUT = do_POST = do_DELETE = _serve

            def log_message(self, *args):
                pass

        self.httpd = ThreadingHTTPServer(("127.0.0.1", 0), Handler)
        self.thread = threading.Thread(target=self.httpd.serve_forever, daemon=True)

    def __enter__(self):
        self.thread.start()
        return self

    def __exit__(self, *exc):
        self.httpd.shutdown()
        self.httpd.server_close()

    def target(self, bucket="curator"):
        host, port = self.httpd.server_address
        return s3.S3Target(f"http://{host}:{port}", bucket, KEY_ID, SECRET)


def test_put_streams_the_file_signed(tmp_path):
    f = tmp_path / "abcd.jpg"
    f.write_bytes(b"x" * 5000)
    with _Server(lambda h: (200, b"")) as srv:
        s3.put_file(srv.target(), "media/ab/cd/abcd.jpg", f, content_type="image/jpeg")
    req = srv.seen[0]
    assert req["method"] == "PUT"
    assert req["path"] == "/curator/media/ab/cd/abcd.jpg"
    assert req["body"] == b"x" * 5000
    assert req["headers"]["x-amz-content-sha256"] == s3.file_sha256(f)
    assert req["headers"]["content-type"] == "image/jpeg"
    assert req["headers"]["authorization"].startswith(
        "AWS4-HMAC-SHA256 Credential=AKIAIOSFODNN7EXAMPLE/")


def test_put_signs_with_a_known_sha_without_rereading(tmp_path, monkeypatch):
    f = tmp_path / "b.bin"
    f.write_bytes(b"y")
    monkeypatch.setattr(s3, "file_sha256", lambda p: pytest.fail("read the file twice"))
    with _Server(lambda h: (200, b"")) as srv:
        s3.put_file(srv.target(), "b.bin", f, payload_sha256="a" * 64)
    assert srv.seen[0]["headers"]["x-amz-content-sha256"] == "a" * 64


def test_a_refusal_says_why(tmp_path):
    f = tmp_path / "b.bin"
    f.write_bytes(b"x")
    body = b"<Error><Code>SignatureDoesNotMatch</Code><Message>no</Message></Error>"
    with _Server(lambda h: (403, body)) as srv, pytest.raises(
        s3.S3Error, match="HTTP 403 SignatureDoesNotMatch: the secret key is wrong",
    ):
        s3.put_file(srv.target(), "b.bin", f)


def test_a_web_server_at_the_address_is_named_as_not_s3():
    """An address without the S3 port lands on whatever serves the default
    port, and its plain 404 says nothing about S3."""
    page = b"<html><body><h1>404 Not Found</h1></body></html>"
    with _Server(lambda h: (404, page)) as srv, pytest.raises(
        s3.S3Error,
        match=r"HTTP 404: the address answered, but not as S3 — check the scheme and the port",
    ):
        s3.list_objects(srv.target())


def test_a_server_error_without_a_body_is_not_blamed_on_the_port():
    with _Server(lambda h: (503, b"")) as srv, pytest.raises(
        s3.S3Error, match="HTTP 503: Service Unavailable",
    ) as err:
        s3.list_objects(srv.target())
    assert "port" not in str(err.value)


def test_nothing_listening_says_check_the_port():
    with socket.socket() as sock:
        sock.bind(("127.0.0.1", 0))
        port = sock.getsockname()[1]
    target = s3.S3Target(f"http://127.0.0.1:{port}", "curator", KEY_ID, SECRET)
    with pytest.raises(s3.S3Error, match="nothing is listening there"):
        s3.list_objects(target)


def test_list_reads_contents_and_the_next_page_token():
    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
<ListBucketResult xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
  <Name>curator</Name><KeyCount>2</KeyCount><IsTruncated>true</IsTruncated>
  <NextContinuationToken>tok-2</NextContinuationToken>
  <Contents><Key>database/fabledcurator-20261105T030000Z.dump</Key><Size>1200</Size>
    <LastModified>2026-11-05T03:00:01.000Z</LastModified></Contents>
  <Contents><Key>database/fabledcurator-20261106T030000Z.dump</Key><Size>1300</Size>
    <LastModified>2026-11-06T03:00:01.000Z</LastModified></Contents>
</ListBucketResult>"""
    with _Server(lambda h: (200, xml)) as srv:
        page = s3.list_objects(srv.target(), "database/", continuation="tok-1")
    path = srv.seen[0]["path"]
    assert path.startswith("/curator/?")
    assert "list-type=2" in path and "prefix=database%2F" in path
    assert "continuation-token=tok-1" in path
    assert page.next_token == "tok-2"
    assert page.objects == [
        s3.StoredObject("database/fabledcurator-20261105T030000Z.dump", 1200,
                        "2026-11-05T03:00:01.000Z"),
        s3.StoredObject("database/fabledcurator-20261106T030000Z.dump", 1300,
                        "2026-11-06T03:00:01.000Z"),
    ]


def test_a_listing_that_isnt_xml_is_named():
    with _Server(lambda h: (200, b"hello")) as srv, pytest.raises(
        s3.S3Error, match="isn't S3's XML",
    ):
        s3.list_objects(srv.target())


def test_get_streams_the_object_to_disk(tmp_path):
    with _Server(lambda h: (200, b"y" * 3000)) as srv:
        out = tmp_path / "b.dump"
        s3.get_file(srv.target(), "database/b.dump", out)
    assert srv.seen[0]["path"] == "/curator/database/b.dump"
    assert srv.seen[0]["headers"]["x-amz-content-sha256"] == s3.EMPTY_SHA256
    assert out.read_bytes() == b"y" * 3000
    assert not (tmp_path / "b.dump.partial").exists()


def test_a_refused_get_says_so_and_writes_nothing(tmp_path):
    body = b"<Error><Code>AccessDenied</Code></Error>"
    out = tmp_path / "b.dump"
    with _Server(lambda h: (403, body)) as srv, pytest.raises(s3.S3Error, match="b.dump"):
        s3.get_file(srv.target(), "b.dump", out)
    assert not out.exists()
    assert not (tmp_path / "b.dump.partial").exists()


def test_a_missing_object_is_named_as_missing(tmp_path):
    body = b"<Error><Code>NoSuchKey</Code></Error>"
    with _Server(lambda h: (404, body)) as srv, pytest.raises(s3.ObjectMissing):
        s3.get_file(srv.target(), "media/ab/cd/x.jpg", tmp_path / "x.jpg")


def test_a_fetched_file_is_kept_only_when_its_fingerprint_matches(tmp_path):
    good = b"picture bytes"
    sha = hashlib.sha256(good).hexdigest()
    with _Server(lambda h: (200, good)) as srv:
        s3.get_file(srv.target(), "k", tmp_path / "ok.jpg", sha256=sha, size=len(good))
    assert (tmp_path / "ok.jpg").read_bytes() == good

    with _Server(lambda h: (200, b"other bytes!!")) as srv, \
            pytest.raises(s3.S3Error, match="different fingerprint"):
        s3.get_file(srv.target(), "k", tmp_path / "bad.jpg", sha256=sha, size=len(good))
    assert not (tmp_path / "bad.jpg").exists()
    assert not (tmp_path / "bad.jpg.partial").exists()


def test_a_short_download_is_not_kept(tmp_path):
    with _Server(lambda h: (200, b"abc")) as srv, pytest.raises(s3.S3Error, match="3 bytes"):
        s3.get_file(srv.target(), "k", tmp_path / "x", size=10)
    assert not (tmp_path / "x").exists()


def test_a_paced_download_counts_its_bytes(tmp_path):
    pacer = s3.Pacer(None)
    taken = []
    pacer.take = taken.append
    with _Server(lambda h: (200, b"z" * 2500)) as srv:
        s3.get_file(srv.target(), "k", tmp_path / "z", pacer=pacer)
    assert sum(taken) == 2500


# ── Multipart ───────────────────────────────────────────────────────────────

_STARTED = b"<InitiateMultipartUploadResult><UploadId>up1</UploadId></InitiateMultipartUploadResult>"


def _bucket(parts_reply=None, complete=(200, b"<CompleteMultipartUploadResult/>")):
    """A stand-in bucket for one multipart upload: starts it, takes parts (each
    answered by `parts_reply(n)`, an ETag by default) and completes it."""
    def reply(h):
        if h.command == "POST" and h.path.endswith("?uploads"):
            return 200, _STARTED
        if h.command == "PUT":
            n = int(h.path.split("partNumber=")[1].split("&")[0])
            return parts_reply(n) if parts_reply else (200, b"", {"ETag": f'"e{n}"'})
        if h.command == "POST":
            return complete
        return 204, b""
    return reply


def test_an_upload_sends_its_parts_then_joins_them_in_order():
    with _Server(_bucket()) as srv:
        up = s3.Upload(srv.target(), "database/x.dump")
        up.add(b"first,")
        up.add(b"second")
        up.complete()
    start, one, two, done = srv.seen
    assert (start["method"], start["path"]) == ("POST", "/curator/database/x.dump?uploads")
    assert one["path"] == "/curator/database/x.dump?partNumber=1&uploadId=up1"
    assert two["body"] == b"second"
    assert two["headers"]["x-amz-content-sha256"] == hashlib.sha256(b"second").hexdigest()
    assert done["path"] == "/curator/database/x.dump?uploadId=up1"
    assert done["body"].index(b'"e1"') < done["body"].index(b'"e2"')
    assert (up.parts, up.size) == (2, len(b"first,second"))


def test_a_refused_start_says_why():
    with _Server(lambda h: (403, b"<Error><Code>AccessDenied</Code></Error>")) as srv:
        with pytest.raises(s3.S3Error, match="the key isn't allowed"):
            s3.Upload(srv.target(), "database/x.dump")


def test_a_completion_refused_under_a_200_is_a_failure():
    error = (200, b"<Error><Code>InternalError</Code><Message>disk full</Message></Error>")
    with _Server(_bucket(complete=error)) as srv:
        up = s3.Upload(srv.target(), "database/x.dump")
        up.add(b"data")
        with pytest.raises(s3.S3Error, match="Finishing the upload"):
            up.complete()


def test_nothing_sent_is_not_completed():
    with _Server(_bucket()) as srv:
        up = s3.Upload(srv.target(), "database/x.dump")
        with pytest.raises(s3.S3Error, match="Nothing was sent"):
            up.complete()


def test_a_busy_bucket_gets_the_part_again_after_a_rest(monkeypatch):
    rests = []
    monkeypatch.setattr(s3.time, "sleep", rests.append)
    answers = iter([(503, b"", {"Retry-After": "7"}), (200, b"", {"ETag": '"e1"'})])
    with _Server(_bucket(parts_reply=lambda n: next(answers))) as srv:
        up = s3.Upload(srv.target(), "database/x.dump")
        up.add(b"data")
    assert rests == [7]
    assert up.parts == 1


def test_a_part_refused_outright_is_not_sent_again(monkeypatch):
    monkeypatch.setattr(s3.time, "sleep", lambda s: pytest.fail("rested on a refusal"))
    refused = (403, b"<Error><Code>AccessDenied</Code></Error>")
    with _Server(_bucket(parts_reply=lambda n: refused)) as srv:
        up = s3.Upload(srv.target(), "database/x.dump")
        with pytest.raises(s3.S3Error, match="Part 1"):
            up.add(b"data")


def test_a_part_that_never_lands_gives_up_after_the_rests(monkeypatch):
    rests = []
    monkeypatch.setattr(s3.time, "sleep", rests.append)
    with _Server(_bucket(parts_reply=lambda n: (503, b""))) as srv:
        up = s3.Upload(srv.target(), "database/x.dump")
        with pytest.raises(s3.S3Error, match="Part 1"):
            up.add(b"data")
    assert rests == list(s3.PART_RETRY_WAITS)


def test_abort_asks_the_bucket_to_drop_the_parts_and_never_raises():
    with _Server(_bucket()) as srv:
        up = s3.Upload(srv.target(), "database/x.dump")
        up.abort()
        assert srv.seen[-1]["method"] == "DELETE"
        assert srv.seen[-1]["path"] == "/curator/database/x.dump?uploadId=up1"
    up.abort()  # the server is gone now: still no exception


def test_the_pacer_holds_bytes_to_the_limit(monkeypatch):
    clock = [0.0]
    monkeypatch.setattr(s3.time, "monotonic", lambda: clock[0])
    monkeypatch.setattr(s3.time, "sleep", lambda secs: clock.__setitem__(0, clock[0] + secs))
    pacer = s3.Pacer(8)                     # 8 Mbit/s = 1,000,000 bytes/s
    data = b"x" * (3 * s3.CHUNK)
    assert b"".join(pacer.chunks(data)) == data
    assert clock[0] == pytest.approx(len(data) / 1_000_000)


def test_no_limit_never_waits(monkeypatch):
    monkeypatch.setattr(s3.time, "sleep", lambda secs: pytest.fail("waited without a limit"))
    assert b"".join(s3.Pacer(0).chunks(b"y" * (2 * s3.CHUNK + 1))) == b"y" * (2 * s3.CHUNK + 1)


def test_a_large_file_is_sent_in_parts_and_checked_against_its_sha(tmp_path, monkeypatch):
    monkeypatch.setattr(s3, "PART_SIZE", 4)
    f = tmp_path / "big.zip"
    f.write_bytes(b"0123456789")
    with _Server(_bucket()) as srv:
        sent = s3.put_file_in_parts(srv.target(), "media/x.zip", f,
                                    sha256=hashlib.sha256(b"0123456789").hexdigest())
    assert sent == 10
    assert [r["body"] for r in srv.seen if r["method"] == "PUT"] == [b"0123", b"4567", b"89"]
    assert srv.seen[-1]["method"] == "POST"             # completed


def test_a_file_that_changed_since_import_is_not_completed(tmp_path, monkeypatch):
    monkeypatch.setattr(s3, "PART_SIZE", 4)
    f = tmp_path / "big.zip"
    f.write_bytes(b"0123456789")
    with _Server(_bucket()) as srv:
        with pytest.raises(s3.S3Error, match="recorded checksum"):
            s3.put_file_in_parts(srv.target(), "media/x.zip", f, sha256="0" * 64)
    assert srv.seen[-1]["method"] == "DELETE"           # aborted, nothing stored


def test_a_paced_put_sends_the_same_bytes(tmp_path):
    f = tmp_path / "a.bin"
    f.write_bytes(b"z" * (s3.CHUNK + 5))
    with _Server(lambda h: (200, b"")) as srv:
        s3.put_file(srv.target(), "a.bin", f, pacer=s3.Pacer(0))
    assert srv.seen[0]["body"] == b"z" * (s3.CHUNK + 5)


def test_presence_is_the_exact_key_at_the_exact_size():
    listing = (b"<ListBucketResult><Contents><Key>media/a.jpg</Key><Size>3</Size>"
               b"</Contents></ListBucketResult>")
    with _Server(lambda h: (200, listing)) as srv:
        assert s3.object_present(srv.target(), "media/a.jpg", 3)
        assert not s3.object_present(srv.target(), "media/a.jpg", 4)
        assert not s3.object_present(srv.target(), "media/a.jp", 3)