diff --git a/swh/loader/core/tests/test_loader.py b/swh/loader/core/tests/test_loader.py
index 8390396..46741c7 100644
--- a/swh/loader/core/tests/test_loader.py
+++ b/swh/loader/core/tests/test_loader.py
@@ -1,224 +1,224 @@
# Copyright (C) 2018-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import datetime
import hashlib
import logging
from swh.model.model import Origin, OriginVisit, Snapshot
from swh.loader.core.loader import BaseLoader, DVCSLoader
-from swh.loader.tests.common import assert_last_visit_matches
+from swh.loader.tests import assert_last_visit_matches
ORIGIN = Origin(url="some-url")
class DummyLoader:
def cleanup(self):
pass
def prepare(self, *args, **kwargs):
pass
def fetch_data(self):
pass
def get_snapshot_id(self):
return None
def prepare_origin_visit(self, *args, **kwargs):
self.origin = ORIGIN
self.origin_url = ORIGIN.url
self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc)
self.visit_type = "git"
self.storage.origin_add([ORIGIN])
visit = OriginVisit(
origin=self.origin_url, date=self.visit_date, type=self.visit_type,
)
self.visit = self.storage.origin_visit_add([visit])[0]
class DummyDVCSLoader(DummyLoader, DVCSLoader):
"""Unbuffered loader will send directly to storage new data
"""
def parse_config_file(self, *args, **kwargs):
return {
"max_content_size": 100 * 1024 * 1024,
"storage": {
"cls": "pipeline",
"steps": [{"cls": "retry",}, {"cls": "filter",}, {"cls": "memory",},],
},
}
def get_contents(self):
return []
def get_directories(self):
return []
def get_revisions(self):
return []
def get_releases(self):
return []
def get_snapshot(self):
return Snapshot(branches={})
def eventful(self):
return False
class DummyBaseLoader(DummyLoader, BaseLoader):
"""Buffered loader will send new data when threshold is reached
"""
def parse_config_file(self, *args, **kwargs):
return {
"max_content_size": 100 * 1024 * 1024,
"storage": {
"cls": "pipeline",
"steps": [
{"cls": "retry",},
{"cls": "filter",},
{
"cls": "buffer",
"min_batch_size": {
"content": 2,
"content_bytes": 8,
"directory": 2,
"revision": 2,
"release": 2,
},
},
{"cls": "memory",},
],
},
}
def store_data(self):
pass
def test_base_loader():
loader = DummyBaseLoader()
result = loader.load()
assert result == {"status": "eventful"}
def test_dvcs_loader():
loader = DummyDVCSLoader()
result = loader.load()
assert result == {"status": "eventful"}
def test_loader_logger_default_name():
loader = DummyBaseLoader()
assert isinstance(loader.log, logging.Logger)
assert loader.log.name == "swh.loader.core.tests.test_loader.DummyBaseLoader"
loader = DummyDVCSLoader()
assert isinstance(loader.log, logging.Logger)
assert loader.log.name == "swh.loader.core.tests.test_loader.DummyDVCSLoader"
def test_loader_logger_with_name():
loader = DummyBaseLoader("some.logger.name")
assert isinstance(loader.log, logging.Logger)
assert loader.log.name == "some.logger.name"
def test_loader_save_data_path(tmp_path):
loader = DummyBaseLoader("some.logger.name.1")
url = "http://bitbucket.org/something"
loader.origin = Origin(url=url)
loader.visit_date = datetime.datetime(year=2019, month=10, day=1)
loader.config = {
"save_data_path": tmp_path,
}
hash_url = hashlib.sha1(url.encode("utf-8")).hexdigest()
expected_save_path = "%s/sha1:%s/%s/2019" % (str(tmp_path), hash_url[0:2], hash_url)
save_path = loader.get_save_data_path()
assert save_path == expected_save_path
def _check_load_failure(caplog, loader, exc_class, exc_text):
"""Check whether a failed load properly logged its exception, and that the
snapshot didn't get referenced in storage"""
for record in caplog.records:
if record.levelname != "ERROR":
continue
assert "Loading failure" in record.message
assert record.exc_info
exc = record.exc_info[1]
assert isinstance(exc, exc_class)
assert exc_text in exc.args[0]
# Check that the get_snapshot operation would have succeeded
assert loader.get_snapshot() is not None
# But that the snapshot didn't get loaded
assert loader.loaded_snapshot_id is None
# And confirm that the visit doesn't reference a snapshot
visit = assert_last_visit_matches(loader.storage, ORIGIN.url, status="partial")
assert visit.snapshot is None
class DummyDVCSLoaderExc(DummyDVCSLoader):
"""A loader which raises an exception when loading some contents"""
def get_contents(self):
raise RuntimeError("Failed to get contents!")
def test_dvcs_loader_exc_partial_visit(caplog):
logger_name = "dvcsloaderexc"
caplog.set_level(logging.ERROR, logger=logger_name)
loader = DummyDVCSLoaderExc(logging_class=logger_name)
result = loader.load()
assert result == {"status": "failed"}
_check_load_failure(caplog, loader, RuntimeError, "Failed to get contents!")
class BrokenStorageProxy:
def __init__(self, storage):
self.storage = storage
def __getattr__(self, attr):
return getattr(self.storage, attr)
def snapshot_add(self, snapshots):
raise RuntimeError("Failed to add snapshot!")
class DummyDVCSLoaderStorageExc(DummyDVCSLoader):
"""A loader which raises an exception when loading some contents"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.storage = BrokenStorageProxy(self.storage)
def test_dvcs_loader_storage_exc_partial_visit(caplog):
logger_name = "dvcsloaderexc"
caplog.set_level(logging.ERROR, logger=logger_name)
loader = DummyDVCSLoaderStorageExc(logging_class=logger_name)
result = loader.load()
assert result == {"status": "failed"}
_check_load_failure(caplog, loader, RuntimeError, "Failed to add snapshot!")
diff --git a/swh/loader/package/archive/tests/test_archive.py b/swh/loader/package/archive/tests/test_archive.py
index bfa5d76..b948fb9 100644
--- a/swh/loader/package/archive/tests/test_archive.py
+++ b/swh/loader/package/archive/tests/test_archive.py
@@ -1,344 +1,344 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from swh.model.hashutil import hash_to_bytes
from swh.loader.package.archive.loader import ArchiveLoader
from swh.loader.package.tests.common import (
check_snapshot,
check_metadata_paths,
get_stats,
)
-from swh.loader.tests.common import assert_last_visit_matches
+from swh.loader.tests import assert_last_visit_matches
URL = "https://ftp.gnu.org/gnu/8sync/"
GNU_ARTIFACTS = [
{
"time": 944729610,
"url": "https://ftp.gnu.org/gnu/8sync/8sync-0.1.0.tar.gz",
"length": 221837,
"filename": "8sync-0.1.0.tar.gz",
"version": "0.1.0",
}
]
_expected_new_contents_first_visit = [
"e9258d81faf5881a2f96a77ba609396f82cb97ad",
"1170cf105b04b7e2822a0e09d2acf71da7b9a130",
"fbd27c3f41f2668624ffc80b7ba5db9b92ff27ac",
"0057bec9b5422aff9256af240b177ac0e3ac2608",
"2b8d0d0b43a1078fc708930c8ddc2956a86c566e",
"27de3b3bc6545d2a797aeeb4657c0e215a0c2e55",
"2e6db43f5cd764e677f416ff0d0c78c7a82ef19b",
"ae9be03bd2a06ed8f4f118d3fe76330bb1d77f62",
"edeb33282b2bffa0e608e9d2fd960fd08093c0ea",
"d64e64d4c73679323f8d4cde2643331ba6c20af9",
"7a756602914be889c0a2d3952c710144b3e64cb0",
"84fb589b554fcb7f32b806951dcf19518d67b08f",
"8624bcdae55baeef00cd11d5dfcfa60f68710a02",
"e08441aeab02704cfbd435d6445f7c072f8f524e",
"f67935bc3a83a67259cda4b2d43373bd56703844",
"809788434b433eb2e3cfabd5d591c9a659d5e3d8",
"7d7c6c8c5ebaeff879f61f37083a3854184f6c41",
"b99fec102eb24bffd53ab61fc30d59e810f116a2",
"7d149b28eaa228b3871c91f0d5a95a2fa7cb0c68",
"f0c97052e567948adf03e641301e9983c478ccff",
"7fb724242e2b62b85ca64190c31dcae5303e19b3",
"4f9709e64a9134fe8aefb36fd827b84d8b617ab5",
"7350628ccf194c2c3afba4ac588c33e3f3ac778d",
"0bb892d9391aa706dc2c3b1906567df43cbe06a2",
"49d4c0ce1a16601f1e265d446b6c5ea6b512f27c",
"6b5cc594ac466351450f7f64a0b79fdaf4435ad3",
"3046e5d1f70297e2a507b98224b6222c9688d610",
"1572607d456d7f633bc6065a2b3048496d679a31",
]
_expected_new_directories_first_visit = [
"daabc65ec75d487b1335ffc101c0ac11c803f8fc",
"263be23b4a8101d3ad0d9831319a3e0f2b065f36",
"7f6e63ba6eb3e2236f65892cd822041f1a01dd5c",
"4db0a3ecbc976083e2dac01a62f93729698429a3",
"dfef1c80e1098dd5deda664bb44a9ab1f738af13",
"eca971d346ea54d95a6e19d5051f900237fafdaa",
"3aebc29ed1fccc4a6f2f2010fb8e57882406b528",
]
_expected_new_revisions_first_visit = {
"44183488c0774ce3c957fa19ba695cf18a4a42b3": (
"3aebc29ed1fccc4a6f2f2010fb8e57882406b528"
)
}
_expected_branches_first_visit = {
"HEAD": {"target_type": "alias", "target": "releases/0.1.0",},
"releases/0.1.0": {
"target_type": "revision",
"target": "44183488c0774ce3c957fa19ba695cf18a4a42b3",
},
}
# hash is different then before as we changed the snapshot
# gnu used to use `release/` (singular) instead of plural
_expected_new_snapshot_first_visit_id = (
"c419397fd912039825ebdbea378bc6283f006bf5" # noqa
)
def visit_with_no_artifact_found(swh_config, requests_mock_datadir):
url = URL
unknown_artifact_url = "https://ftp.g.o/unknown/8sync-0.1.0.tar.gz"
loader = ArchiveLoader(
url,
artifacts=[
{
"time": 944729610,
"url": unknown_artifact_url, # unknown artifact
"length": 221837,
"filename": "8sync-0.1.0.tar.gz",
"version": "0.1.0",
}
],
)
actual_load_status = loader.load()
assert actual_load_status["status"] == "uneventful"
assert actual_load_status["snapshot_id"] is not None
stats = get_stats(loader.storage)
assert {
"content": 0,
"directory": 0,
"origin": 1,
"origin_visit": 1,
"person": 0,
"release": 0,
"revision": 0,
"skipped_content": 0,
"snapshot": 1,
} == stats
assert_last_visit_matches(loader.storage, url, status="partial", type="tar")
def test_check_revision_metadata_structure(swh_config, requests_mock_datadir):
loader = ArchiveLoader(url=URL, artifacts=GNU_ARTIFACTS)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["snapshot_id"] is not None
assert_last_visit_matches(loader.storage, URL, status="full", type="tar")
expected_revision_id = hash_to_bytes("44183488c0774ce3c957fa19ba695cf18a4a42b3")
revision = list(loader.storage.revision_get([expected_revision_id]))[0]
assert revision is not None
check_metadata_paths(
revision["metadata"],
paths=[
("intrinsic", dict),
("extrinsic.provider", str),
("extrinsic.when", str),
("extrinsic.raw", dict),
("original_artifact", list),
],
)
for original_artifact in revision["metadata"]["original_artifact"]:
check_metadata_paths(
original_artifact,
paths=[("filename", str), ("length", int), ("checksums", dict),],
)
def test_visit_with_release_artifact_no_prior_visit(swh_config, requests_mock_datadir):
"""With no prior visit, load a gnu project ends up with 1 snapshot
"""
loader = ArchiveLoader(url=URL, artifacts=GNU_ARTIFACTS)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert (
actual_load_status["snapshot_id"] == _expected_new_snapshot_first_visit_id
) # noqa
assert_last_visit_matches(loader.storage, URL, status="full", type="tar")
stats = get_stats(loader.storage)
assert {
"content": len(_expected_new_contents_first_visit),
"directory": len(_expected_new_directories_first_visit),
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": len(_expected_new_revisions_first_visit),
"skipped_content": 0,
"snapshot": 1,
} == stats
expected_contents = map(hash_to_bytes, _expected_new_contents_first_visit)
assert list(loader.storage.content_missing_per_sha1(expected_contents)) == []
expected_dirs = map(hash_to_bytes, _expected_new_directories_first_visit)
assert list(loader.storage.directory_missing(expected_dirs)) == []
expected_revs = map(hash_to_bytes, _expected_new_revisions_first_visit)
assert list(loader.storage.revision_missing(expected_revs)) == []
expected_snapshot = {
"id": _expected_new_snapshot_first_visit_id,
"branches": _expected_branches_first_visit,
}
check_snapshot(expected_snapshot, loader.storage)
def test_2_visits_without_change(swh_config, requests_mock_datadir):
"""With no prior visit, load a gnu project ends up with 1 snapshot
"""
url = URL
loader = ArchiveLoader(url, artifacts=GNU_ARTIFACTS)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["snapshot_id"] is not None
assert_last_visit_matches(loader.storage, url, status="full", type="tar")
actual_load_status2 = loader.load()
assert actual_load_status2["status"] == "uneventful"
assert actual_load_status2["snapshot_id"] is not None
assert actual_load_status["snapshot_id"] == actual_load_status2["snapshot_id"]
assert_last_visit_matches(loader.storage, url, status="full", type="tar")
urls = [
m.url
for m in requests_mock_datadir.request_history
if m.url.startswith("https://ftp.gnu.org")
]
assert len(urls) == 1
def test_2_visits_with_new_artifact(swh_config, requests_mock_datadir):
"""With no prior visit, load a gnu project ends up with 1 snapshot
"""
url = URL
artifact1 = GNU_ARTIFACTS[0]
loader = ArchiveLoader(url, [artifact1])
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["snapshot_id"] is not None
assert_last_visit_matches(loader.storage, url, status="full", type="tar")
stats = get_stats(loader.storage)
assert {
"content": len(_expected_new_contents_first_visit),
"directory": len(_expected_new_directories_first_visit),
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": len(_expected_new_revisions_first_visit),
"skipped_content": 0,
"snapshot": 1,
} == stats
urls = [
m.url
for m in requests_mock_datadir.request_history
if m.url.startswith("https://ftp.gnu.org")
]
assert len(urls) == 1
artifact2 = {
"time": 1480991830,
"url": "https://ftp.gnu.org/gnu/8sync/8sync-0.2.0.tar.gz",
"length": 238466,
"filename": "8sync-0.2.0.tar.gz",
"version": "0.2.0",
}
loader2 = ArchiveLoader(url, [artifact1, artifact2])
# implementation detail: share the storage in between visits
loader2.storage = loader.storage
stats2 = get_stats(loader2.storage)
assert stats == stats2 # ensure we share the storage
actual_load_status2 = loader2.load()
assert actual_load_status2["status"] == "eventful"
assert actual_load_status2["snapshot_id"] is not None
stats2 = get_stats(loader.storage)
assert {
"content": len(_expected_new_contents_first_visit) + 14,
"directory": len(_expected_new_directories_first_visit) + 8,
"origin": 1,
"origin_visit": 1 + 1,
"person": 1,
"release": 0,
"revision": len(_expected_new_revisions_first_visit) + 1,
"skipped_content": 0,
"snapshot": 1 + 1,
} == stats2
assert_last_visit_matches(loader.storage, url, status="full", type="tar")
urls = [
m.url
for m in requests_mock_datadir.request_history
if m.url.startswith("https://ftp.gnu.org")
]
# 1 artifact (2nd time no modification) + 1 new artifact
assert len(urls) == 2
def test_2_visits_without_change_not_gnu(swh_config, requests_mock_datadir):
"""Load a project archive (not gnu) ends up with 1 snapshot
"""
url = "https://something.else.org/8sync/"
artifacts = [ # this is not a gnu artifact
{
"time": "1999-12-09T09:53:30+00:00", # it's also not a timestamp
"sha256": "d5d1051e59b2be6f065a9fc6aedd3a391e44d0274b78b9bb4e2b57a09134dbe4", # noqa
# keep a gnu artifact reference to avoid adding other test files
"url": "https://ftp.gnu.org/gnu/8sync/8sync-0.2.0.tar.gz",
"length": 238466,
"filename": "8sync-0.2.0.tar.gz",
"version": "0.2.0",
}
]
# Here the loader defines the id_keys to use for existence in the snapshot
# It's not the default archive loader which
loader = ArchiveLoader(
url, artifacts=artifacts, identity_artifact_keys=["sha256", "length", "url"]
)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["snapshot_id"] is not None
assert_last_visit_matches(loader.storage, url, status="full", type="tar")
actual_load_status2 = loader.load()
assert actual_load_status2["status"] == "uneventful"
assert actual_load_status2["snapshot_id"] == actual_load_status["snapshot_id"]
assert_last_visit_matches(loader.storage, url, status="full", type="tar")
urls = [
m.url
for m in requests_mock_datadir.request_history
if m.url.startswith("https://ftp.gnu.org")
]
assert len(urls) == 1
diff --git a/swh/loader/package/cran/tests/test_cran.py b/swh/loader/package/cran/tests/test_cran.py
index 22f9724..a6cecb8 100644
--- a/swh/loader/package/cran/tests/test_cran.py
+++ b/swh/loader/package/cran/tests/test_cran.py
@@ -1,326 +1,326 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import os
import pytest
from datetime import datetime, timezone
from dateutil.tz import tzlocal
from os import path
from swh.loader.package.cran.loader import (
extract_intrinsic_metadata,
CRANLoader,
parse_date,
parse_debian_control,
)
from swh.core.tarball import uncompress
from swh.model.model import TimestampWithTimezone
from swh.loader.package.tests.common import (
check_snapshot,
get_stats,
)
-from swh.loader.tests.common import assert_last_visit_matches
+from swh.loader.tests import assert_last_visit_matches
def test_cran_parse_date():
data = [
# parsable, some have debatable results though
("2001-June-08", datetime(2001, 6, 8, 0, 0, tzinfo=timezone.utc)),
(
"Tue Dec 27 15:06:08 PST 2011",
datetime(2011, 12, 27, 15, 6, 8, tzinfo=timezone.utc),
),
("8-14-2013", datetime(2013, 8, 14, 0, 0, tzinfo=timezone.utc)),
("2011-01", datetime(2011, 1, 1, 0, 0, tzinfo=timezone.utc)),
("201109", datetime(2009, 11, 20, 0, 0, tzinfo=timezone.utc)),
("04-12-2014", datetime(2014, 4, 12, 0, 0, tzinfo=timezone.utc)),
(
"2018-08-24, 10:40:10",
datetime(2018, 8, 24, 10, 40, 10, tzinfo=timezone.utc),
),
("2013-October-16", datetime(2013, 10, 16, 0, 0, tzinfo=timezone.utc)),
("Aug 23, 2013", datetime(2013, 8, 23, 0, 0, tzinfo=timezone.utc)),
("27-11-2014", datetime(2014, 11, 27, 0, 0, tzinfo=timezone.utc)),
("2019-09-26,", datetime(2019, 9, 26, 0, 0, tzinfo=timezone.utc)),
("9/25/2014", datetime(2014, 9, 25, 0, 0, tzinfo=timezone.utc)),
(
"Fri Jun 27 17:23:53 2014",
datetime(2014, 6, 27, 17, 23, 53, tzinfo=timezone.utc),
),
("28-04-2014", datetime(2014, 4, 28, 0, 0, tzinfo=timezone.utc)),
("04-14-2014", datetime(2014, 4, 14, 0, 0, tzinfo=timezone.utc)),
(
"2019-05-08 14:17:31 UTC",
datetime(2019, 5, 8, 14, 17, 31, tzinfo=timezone.utc),
),
(
"Wed May 21 13:50:39 CEST 2014",
datetime(2014, 5, 21, 13, 50, 39, tzinfo=tzlocal()),
),
(
"2018-04-10 00:01:04 KST",
datetime(2018, 4, 10, 0, 1, 4, tzinfo=timezone.utc),
),
("2019-08-25 10:45", datetime(2019, 8, 25, 10, 45, tzinfo=timezone.utc)),
("March 9, 2015", datetime(2015, 3, 9, 0, 0, tzinfo=timezone.utc)),
("Aug. 18, 2012", datetime(2012, 8, 18, 0, 0, tzinfo=timezone.utc)),
("2014-Dec-17", datetime(2014, 12, 17, 0, 0, tzinfo=timezone.utc)),
("March 01, 2013", datetime(2013, 3, 1, 0, 0, tzinfo=timezone.utc)),
("2017-04-08.", datetime(2017, 4, 8, 0, 0, tzinfo=timezone.utc)),
("2014-Apr-22", datetime(2014, 4, 22, 0, 0, tzinfo=timezone.utc)),
(
"Mon Jan 12 19:54:04 2015",
datetime(2015, 1, 12, 19, 54, 4, tzinfo=timezone.utc),
),
("May 22, 2014", datetime(2014, 5, 22, 0, 0, tzinfo=timezone.utc)),
(
"2014-08-12 09:55:10 EDT",
datetime(2014, 8, 12, 9, 55, 10, tzinfo=timezone.utc),
),
# unparsable
("Fabruary 21, 2012", None),
('2019-05-28"', None),
("2017-03-01 today", None),
("2016-11-0110.1093/icesjms/fsw182", None),
("2019-07-010", None),
("2015-02.23", None),
("20013-12-30", None),
("2016-08-017", None),
("2019-02-07l", None),
("2018-05-010", None),
("2019-09-27 KST", None),
("$Date$", None),
("2019-09-27 KST", None),
("2019-06-22 $Date$", None),
("$Date: 2013-01-18 12:49:03 -0600 (Fri, 18 Jan 2013) $", None),
("2015-7-013", None),
("2018-05-023", None),
("Check NEWS file for changes: news(package='simSummary')", None),
]
for date, expected_date in data:
actual_tstz = parse_date(date)
if expected_date is None:
assert actual_tstz is None, date
else:
expected_tstz = TimestampWithTimezone.from_datetime(expected_date)
assert actual_tstz == expected_tstz, date
@pytest.mark.fs
def test_extract_intrinsic_metadata(tmp_path, datadir):
"""Parsing existing archive's PKG-INFO should yield results"""
uncompressed_archive_path = str(tmp_path)
# sample url
# https://cran.r-project.org/src_contrib_1.4.0_Recommended_KernSmooth_2.22-6.tar.gz # noqa
archive_path = path.join(
datadir,
"https_cran.r-project.org",
"src_contrib_1.4.0_Recommended_KernSmooth_2.22-6.tar.gz",
)
uncompress(archive_path, dest=uncompressed_archive_path)
actual_metadata = extract_intrinsic_metadata(uncompressed_archive_path)
expected_metadata = {
"Package": "KernSmooth",
"Priority": "recommended",
"Version": "2.22-6",
"Date": "2001-June-08",
"Title": "Functions for kernel smoothing for Wand & Jones (1995)",
"Author": "S original by Matt Wand.\n\tR port by Brian Ripley <ripley@stats.ox.ac.uk>.", # noqa
"Maintainer": "Brian Ripley <ripley@stats.ox.ac.uk>",
"Description": 'functions for kernel smoothing (and density estimation)\n corresponding to the book: \n Wand, M.P. and Jones, M.C. (1995) "Kernel Smoothing".', # noqa
"License": "Unlimited use and distribution (see LICENCE).",
"URL": "http://www.biostat.harvard.edu/~mwand",
}
assert actual_metadata == expected_metadata
@pytest.mark.fs
def test_extract_intrinsic_metadata_failures(tmp_path):
"""Parsing inexistent path/archive/PKG-INFO yield None"""
# inexistent first level path
assert extract_intrinsic_metadata("/something-inexistent") == {}
# inexistent second level path (as expected by pypi archives)
assert extract_intrinsic_metadata(tmp_path) == {}
# inexistent PKG-INFO within second level path
existing_path_no_pkginfo = str(tmp_path / "something")
os.mkdir(existing_path_no_pkginfo)
assert extract_intrinsic_metadata(tmp_path) == {}
def test_cran_one_visit(swh_config, requests_mock_datadir):
version = "2.22-6"
base_url = "https://cran.r-project.org"
origin_url = f"{base_url}/Packages/Recommended_KernSmooth/index.html"
artifact_url = (
f"{base_url}/src_contrib_1.4.0_Recommended_KernSmooth_{version}.tar.gz" # noqa
)
loader = CRANLoader(
origin_url, artifacts=[{"url": artifact_url, "version": version,}]
)
actual_load_status = loader.load()
expected_snapshot_id = "920adcccc78aaeedd3cfa4459dd900d8c3431a21"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": {
"HEAD": {"target": f"releases/{version}", "target_type": "alias"},
f"releases/{version}": {
"target": "42bdb16facd5140424359c8ce89a28ecfa1ce603",
"target_type": "revision",
},
},
}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, origin_url, status="full", type="cran")
visit_stats = get_stats(loader.storage)
assert {
"content": 33,
"directory": 7,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 1,
"skipped_content": 0,
"snapshot": 1,
} == visit_stats
urls = [
m.url
for m in requests_mock_datadir.request_history
if m.url.startswith(base_url)
]
# visited each artifact once across 2 visits
assert len(urls) == 1
def test_cran_2_visits_same_origin(swh_config, requests_mock_datadir):
"""Multiple visits on the same origin, only 1 archive fetch"""
version = "2.22-6"
base_url = "https://cran.r-project.org"
origin_url = f"{base_url}/Packages/Recommended_KernSmooth/index.html"
artifact_url = (
f"{base_url}/src_contrib_1.4.0_Recommended_KernSmooth_{version}.tar.gz" # noqa
)
loader = CRANLoader(
origin_url, artifacts=[{"url": artifact_url, "version": version}]
)
# first visit
actual_load_status = loader.load()
expected_snapshot_id = "920adcccc78aaeedd3cfa4459dd900d8c3431a21"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": {
"HEAD": {"target": f"releases/{version}", "target_type": "alias"},
f"releases/{version}": {
"target": "42bdb16facd5140424359c8ce89a28ecfa1ce603",
"target_type": "revision",
},
},
}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, origin_url, status="full", type="cran")
visit_stats = get_stats(loader.storage)
assert {
"content": 33,
"directory": 7,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 1,
"skipped_content": 0,
"snapshot": 1,
} == visit_stats
# second visit
actual_load_status2 = loader.load()
assert actual_load_status2 == {
"status": "uneventful",
"snapshot_id": expected_snapshot_id,
}
assert_last_visit_matches(loader.storage, origin_url, status="full", type="cran")
visit_stats2 = get_stats(loader.storage)
visit_stats["origin_visit"] += 1
assert visit_stats2 == visit_stats, "same stats as 1st visit, +1 visit"
urls = [
m.url
for m in requests_mock_datadir.request_history
if m.url.startswith(base_url)
]
assert len(urls) == 1, "visited one time artifact url (across 2 visits)"
def test_parse_debian_control(datadir):
description_file = os.path.join(datadir, "description", "acepack")
actual_metadata = parse_debian_control(description_file)
assert actual_metadata == {
"Package": "acepack",
"Maintainer": "Shawn Garbett",
"Version": "1.4.1",
"Author": "Phil Spector, Jerome Friedman, Robert Tibshirani...",
"Description": "Two nonparametric methods for multiple regression...",
"Title": "ACE & AVAS 4 Selecting Multiple Regression Transformations",
"License": "MIT + file LICENSE",
"Suggests": "testthat",
"Packaged": "2016-10-28 15:38:59 UTC; garbetsp",
"Repository": "CRAN",
"Date/Publication": "2016-10-29 00:11:52",
"NeedsCompilation": "yes",
}
def test_parse_debian_control_unicode_issue(datadir):
# iso-8859-1 caused failure, now fixed
description_file = os.path.join(datadir, "description", "KnownBR")
actual_metadata = parse_debian_control(description_file)
assert actual_metadata == {
"Package": "KnowBR",
"Version": "2.0",
"Title": """Discriminating Well Surveyed Spatial Units from Exhaustive
Biodiversity Databases""",
"Author": "Cástor Guisande González and Jorge M. Lobo",
"Maintainer": "Cástor Guisande González <castor@email.es>",
"Description": "It uses species accumulation curves and diverse estimators...",
"License": "GPL (>= 2)",
"Encoding": "latin1",
"Depends": "R (>= 3.0), fossil, mgcv, plotrix, sp, vegan",
"Suggests": "raster, rgbif",
"NeedsCompilation": "no",
"Packaged": "2019-01-30 13:27:29 UTC; castor",
"Repository": "CRAN",
"Date/Publication": "2019-01-31 20:53:50 UTC",
}
diff --git a/swh/loader/package/debian/tests/test_debian.py b/swh/loader/package/debian/tests/test_debian.py
index 5acc837..fb9d51b 100644
--- a/swh/loader/package/debian/tests/test_debian.py
+++ b/swh/loader/package/debian/tests/test_debian.py
@@ -1,466 +1,466 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import copy
import logging
import pytest
import random
from os import path
from swh.loader.package.debian.loader import (
DebianLoader,
download_package,
dsc_information,
uid_to_person,
prepare_person,
get_package_metadata,
extract_package,
)
from swh.loader.package.tests.common import (
check_snapshot,
get_stats,
)
-from swh.loader.tests.common import assert_last_visit_matches
+from swh.loader.tests import assert_last_visit_matches
from swh.loader.package.debian.loader import resolve_revision_from
from swh.model.model import Person
logger = logging.getLogger(__name__)
PACKAGE_FILES = {
"name": "cicero",
"version": "0.7.2-3",
"files": {
"cicero_0.7.2-3.diff.gz": {
"md5sum": "a93661b6a48db48d59ba7d26796fc9ce",
"name": "cicero_0.7.2-3.diff.gz",
"sha256": "f039c9642fe15c75bed5254315e2a29f9f2700da0e29d9b0729b3ffc46c8971c", # noqa
"size": 3964,
"uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-3.diff.gz", # noqa
},
"cicero_0.7.2-3.dsc": {
"md5sum": "d5dac83eb9cfc9bb52a15eb618b4670a",
"name": "cicero_0.7.2-3.dsc",
"sha256": "35b7f1048010c67adfd8d70e4961aefd8800eb9a83a4d1cc68088da0009d9a03", # noqa
"size": 1864,
"uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-3.dsc", # noqa
}, # noqa
"cicero_0.7.2.orig.tar.gz": {
"md5sum": "4353dede07c5728319ba7f5595a7230a",
"name": "cicero_0.7.2.orig.tar.gz",
"sha256": "63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786", # noqa
"size": 96527,
"uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2.orig.tar.gz", # noqa
},
},
}
PACKAGE_FILES2 = {
"name": "cicero",
"version": "0.7.2-4",
"files": {
"cicero_0.7.2-4.diff.gz": {
"md5sum": "1e7e6fc4a59d57c98082a3af78145734",
"name": "cicero_0.7.2-4.diff.gz",
"sha256": "2e6fa296ee7005473ff58d0971f4fd325617b445671480e9f2cfb738d5dbcd01", # noqa
"size": 4038,
"uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-4.diff.gz", # noqa
},
"cicero_0.7.2-4.dsc": {
"md5sum": "1a6c8855a73b4282bb31d15518f18cde",
"name": "cicero_0.7.2-4.dsc",
"sha256": "913ee52f7093913420de5cbe95d63cfa817f1a1daf997961149501894e754f8b", # noqa
"size": 1881,
"uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-4.dsc", # noqa
}, # noqa
"cicero_0.7.2.orig.tar.gz": {
"md5sum": "4353dede07c5728319ba7f5595a7230a",
"name": "cicero_0.7.2.orig.tar.gz",
"sha256": "63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786", # noqa
"size": 96527,
"uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2.orig.tar.gz", # noqa
},
},
}
PACKAGE_PER_VERSION = {
"stretch/contrib/0.7.2-3": PACKAGE_FILES,
}
PACKAGES_PER_VERSION = {
"stretch/contrib/0.7.2-3": PACKAGE_FILES,
"buster/contrib/0.7.2-4": PACKAGE_FILES2,
}
def test_debian_first_visit(swh_config, requests_mock_datadir):
"""With no prior visit, load a gnu project ends up with 1 snapshot
"""
url = "deb://Debian/packages/cicero"
loader = DebianLoader(
url=url, date="2019-10-12T05:58:09.165557+00:00", packages=PACKAGE_PER_VERSION,
)
actual_load_status = loader.load()
expected_snapshot_id = "3b6b66e6ee4e7d903a379a882684a2a50480c0b4"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
assert_last_visit_matches(loader.storage, url, status="full", type="deb")
stats = get_stats(loader.storage)
assert {
"content": 42,
"directory": 2,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 1, # all artifacts under 1 revision
"skipped_content": 0,
"snapshot": 1,
} == stats
expected_snapshot = {
"id": expected_snapshot_id,
"branches": {
"releases/stretch/contrib/0.7.2-3": {
"target_type": "revision",
"target": "2807f5b3f84368b4889a9ae827fe85854ffecf07",
}
},
} # different than the previous loader as no release is done
check_snapshot(expected_snapshot, loader.storage)
def test_debian_first_visit_then_another_visit(swh_config, requests_mock_datadir):
"""With no prior visit, load a debian project ends up with 1 snapshot
"""
url = "deb://Debian/packages/cicero"
loader = DebianLoader(
url=url, date="2019-10-12T05:58:09.165557+00:00", packages=PACKAGE_PER_VERSION
)
actual_load_status = loader.load()
expected_snapshot_id = "3b6b66e6ee4e7d903a379a882684a2a50480c0b4"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
assert_last_visit_matches(loader.storage, url, status="full", type="deb")
stats = get_stats(loader.storage)
assert {
"content": 42,
"directory": 2,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 1, # all artifacts under 1 revision
"skipped_content": 0,
"snapshot": 1,
} == stats
expected_snapshot = {
"id": expected_snapshot_id,
"branches": {
"releases/stretch/contrib/0.7.2-3": {
"target_type": "revision",
"target": "2807f5b3f84368b4889a9ae827fe85854ffecf07",
}
},
} # different than the previous loader as no release is done
check_snapshot(expected_snapshot, loader.storage)
# No change in between load
actual_load_status2 = loader.load()
assert actual_load_status2["status"] == "uneventful"
assert_last_visit_matches(loader.storage, url, status="full", type="deb")
stats2 = get_stats(loader.storage)
assert {
"content": 42 + 0,
"directory": 2 + 0,
"origin": 1,
"origin_visit": 1 + 1, # a new visit occurred
"person": 1,
"release": 0,
"revision": 1,
"skipped_content": 0,
"snapshot": 1, # same snapshot across 2 visits
} == stats2
urls = [
m.url
for m in requests_mock_datadir.request_history
if m.url.startswith("http://deb.debian.org")
]
# visited each package artifact twice across 2 visits
assert len(urls) == len(set(urls))
def test_uid_to_person():
uid = "Someone Name <someone@orga.org>"
actual_person = uid_to_person(uid)
assert actual_person == {
"name": "Someone Name",
"email": "someone@orga.org",
"fullname": uid,
}
def test_prepare_person():
actual_author = prepare_person(
{
"name": "Someone Name",
"email": "someone@orga.org",
"fullname": "Someone Name <someone@orga.org>",
}
)
assert actual_author == Person(
name=b"Someone Name",
email=b"someone@orga.org",
fullname=b"Someone Name <someone@orga.org>",
)
def test_download_package(datadir, tmpdir, requests_mock_datadir):
tmpdir = str(tmpdir) # py3.5 work around (LocalPath issue)
all_hashes = download_package(PACKAGE_FILES, tmpdir)
assert all_hashes == {
"cicero_0.7.2-3.diff.gz": {
"checksums": {
"sha1": "0815282053f21601b0ec4adf7a8fe47eace3c0bc",
"sha256": "f039c9642fe15c75bed5254315e2a29f9f2700da0e29d9b0729b3ffc46c8971c", # noqa
},
"filename": "cicero_0.7.2-3.diff.gz",
"length": 3964,
},
"cicero_0.7.2-3.dsc": {
"checksums": {
"sha1": "abbec4e8efbbc80278236e1dd136831eac08accd",
"sha256": "35b7f1048010c67adfd8d70e4961aefd8800eb9a83a4d1cc68088da0009d9a03", # noqa
},
"filename": "cicero_0.7.2-3.dsc",
"length": 1864,
},
"cicero_0.7.2.orig.tar.gz": {
"checksums": {
"sha1": "a286efd63fe2c9c9f7bb30255c3d6fcdcf390b43",
"sha256": "63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786", # noqa
},
"filename": "cicero_0.7.2.orig.tar.gz",
"length": 96527,
},
}
def test_dsc_information_ok():
fname = "cicero_0.7.2-3.dsc"
dsc_url, dsc_name = dsc_information(PACKAGE_FILES)
assert dsc_url == PACKAGE_FILES["files"][fname]["uri"]
assert dsc_name == PACKAGE_FILES["files"][fname]["name"]
def test_dsc_information_not_found():
fname = "cicero_0.7.2-3.dsc"
package_files = copy.deepcopy(PACKAGE_FILES)
package_files["files"].pop(fname)
dsc_url, dsc_name = dsc_information(package_files)
assert dsc_url is None
assert dsc_name is None
def test_dsc_information_too_many_dsc_entries():
# craft an extra dsc file
fname = "cicero_0.7.2-3.dsc"
package_files = copy.deepcopy(PACKAGE_FILES)
data = package_files["files"][fname]
fname2 = fname.replace("cicero", "ciceroo")
package_files["files"][fname2] = data
with pytest.raises(
ValueError,
match="Package %s_%s references several dsc"
% (package_files["name"], package_files["version"]),
):
dsc_information(package_files)
def test_get_package_metadata(requests_mock_datadir, datadir, tmp_path):
tmp_path = str(tmp_path) # py3.5 compat.
package = PACKAGE_FILES
logger.debug("package: %s", package)
# download the packages
all_hashes = download_package(package, tmp_path)
# Retrieve information from package
_, dsc_name = dsc_information(package)
dl_artifacts = [(tmp_path, hashes) for hashes in all_hashes.values()]
# Extract information from package
extracted_path = extract_package(dl_artifacts, tmp_path)
# Retrieve information on package
dsc_path = path.join(path.dirname(extracted_path), dsc_name)
actual_package_info = get_package_metadata(package, dsc_path, extracted_path)
logger.debug("actual_package_info: %s", actual_package_info)
assert actual_package_info == {
"changelog": {
"date": "2014-10-19T16:52:35+02:00",
"history": [
("cicero", "0.7.2-2"),
("cicero", "0.7.2-1"),
("cicero", "0.7-1"),
],
"person": {
"email": "sthibault@debian.org",
"fullname": "Samuel Thibault <sthibault@debian.org>",
"name": "Samuel Thibault",
},
},
"maintainers": [
{
"email": "debian-accessibility@lists.debian.org",
"fullname": "Debian Accessibility Team "
"<debian-accessibility@lists.debian.org>",
"name": "Debian Accessibility Team",
},
{
"email": "sthibault@debian.org",
"fullname": "Samuel Thibault <sthibault@debian.org>",
"name": "Samuel Thibault",
},
],
"name": "cicero",
"version": "0.7.2-3",
}
def test_debian_multiple_packages(swh_config, requests_mock_datadir):
url = "deb://Debian/packages/cicero"
loader = DebianLoader(
url=url, date="2019-10-12T05:58:09.165557+00:00", packages=PACKAGES_PER_VERSION
)
actual_load_status = loader.load()
expected_snapshot_id = "defc19021187f3727293121fcf6c5c82cb923604"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
assert_last_visit_matches(loader.storage, url, status="full", type="deb")
expected_snapshot = {
"id": expected_snapshot_id,
"branches": {
"releases/stretch/contrib/0.7.2-3": {
"target_type": "revision",
"target": "2807f5b3f84368b4889a9ae827fe85854ffecf07",
},
"releases/buster/contrib/0.7.2-4": {
"target_type": "revision",
"target": "8224139c274c984147ef4b09aa0e462c55a10bd3",
},
},
}
check_snapshot(expected_snapshot, loader.storage)
def test_resolve_revision_from_edge_cases():
"""Solving revision with empty data will result in unknown revision
"""
for package_artifacts in [{}, PACKAGE_FILES]:
actual_revision = resolve_revision_from(package_artifacts, {})
assert actual_revision is None
for known_artifacts in [{}, PACKAGE_FILES]:
actual_revision = resolve_revision_from({}, known_artifacts)
assert actual_revision is None
known_package_artifacts = {
b"(\x07\xf5\xb3\xf8Ch\xb4\x88\x9a\x9a\xe8'\xfe\x85\x85O\xfe\xcf\x07": {
"extrinsic": {
# empty
},
# ... removed the unnecessary intermediary data
}
}
assert not resolve_revision_from(known_package_artifacts, PACKAGE_FILES)
def test_resolve_revision_from_edge_cases_hit_and_miss():
"""Solving revision with inconsistent data will result in unknown revision
"""
artifact_metadata = PACKAGE_FILES2
expected_revision_id = (
b"(\x08\xf5\xb3\xf8Ch\xb4\x88\x9a\x9a\xe8'\xff\x85\x85O\xfe\xcf\x07" # noqa
)
known_package_artifacts = {
expected_revision_id: {
"extrinsic": {"raw": PACKAGE_FILES,},
# ... removed the unnecessary intermediary data
}
}
actual_revision = resolve_revision_from(known_package_artifacts, artifact_metadata)
assert actual_revision is None
def test_resolve_revision_from():
"""Solving revision with consistent data will solve the revision
"""
artifact_metadata = PACKAGE_FILES
expected_revision_id = (
b"(\x07\xf5\xb3\xf8Ch\xb4\x88\x9a\x9a\xe8'\xfe\x85\x85O\xfe\xcf\x07" # noqa
)
files = artifact_metadata["files"]
# shuffling dict's keys
keys = list(files.keys())
random.shuffle(keys)
package_files = {"files": {k: files[k] for k in keys}}
known_package_artifacts = {
expected_revision_id: {
"extrinsic": {"raw": package_files,},
# ... removed the unnecessary intermediary data
}
}
actual_revision = resolve_revision_from(known_package_artifacts, artifact_metadata)
assert actual_revision == expected_revision_id
diff --git a/swh/loader/package/deposit/tests/test_deposit.py b/swh/loader/package/deposit/tests/test_deposit.py
index 422fa0f..9ec01d6 100644
--- a/swh/loader/package/deposit/tests/test_deposit.py
+++ b/swh/loader/package/deposit/tests/test_deposit.py
@@ -1,367 +1,367 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import json
import re
import pytest
from swh.model.hashutil import hash_to_bytes, hash_to_hex
from swh.loader.package.deposit.loader import DepositLoader
from swh.loader.package.tests.common import (
check_snapshot,
check_metadata_paths,
get_stats,
)
-from swh.loader.tests.common import assert_last_visit_matches
+from swh.loader.tests import assert_last_visit_matches
from swh.core.pytest_plugin import requests_mock_datadir_factory
DEPOSIT_URL = "https://deposit.softwareheritage.org/1/private"
@pytest.fixture
def requests_mock_datadir(requests_mock_datadir):
"""Enhance default mock data to mock put requests as the loader does some
internal update queries there.
"""
requests_mock_datadir.put(re.compile("https"))
return requests_mock_datadir
def test_deposit_init_ok(swh_config, swh_loader_config):
url = "some-url"
deposit_id = 999
loader = DepositLoader(url, deposit_id) # Something that does not exist
assert loader.url == url
assert loader.client is not None
assert loader.client.base_url == swh_loader_config["deposit"]["url"]
def test_deposit_loading_unknown_deposit(swh_config, requests_mock_datadir):
"""Loading an unknown deposit should fail
no origin, no visit, no snapshot
"""
# private api url form: 'https://deposit.s.o/1/private/hal/666/raw/'
url = "some-url"
unknown_deposit_id = 667
loader = DepositLoader(url, unknown_deposit_id) # does not exist
actual_load_status = loader.load()
assert actual_load_status == {"status": "failed"}
stats = get_stats(loader.storage)
assert {
"content": 0,
"directory": 0,
"origin": 0,
"origin_visit": 0,
"person": 0,
"release": 0,
"revision": 0,
"skipped_content": 0,
"snapshot": 0,
} == stats
requests_mock_datadir_missing_one = requests_mock_datadir_factory(
ignore_urls=[f"{DEPOSIT_URL}/666/raw/",]
)
def test_deposit_loading_failure_to_retrieve_1_artifact(
swh_config, requests_mock_datadir_missing_one
):
"""Deposit with missing artifact ends up with an uneventful/partial visit
"""
# private api url form: 'https://deposit.s.o/1/private/hal/666/raw/'
url = "some-url-2"
deposit_id = 666
loader = DepositLoader(url, deposit_id)
actual_load_status = loader.load()
assert actual_load_status["status"] == "uneventful"
assert actual_load_status["snapshot_id"] is not None
assert_last_visit_matches(loader.storage, url, status="partial", type="deposit")
stats = get_stats(loader.storage)
assert {
"content": 0,
"directory": 0,
"origin": 1,
"origin_visit": 1,
"person": 0,
"release": 0,
"revision": 0,
"skipped_content": 0,
"snapshot": 1,
} == stats
def test_revision_metadata_structure(swh_config, requests_mock_datadir):
url = "https://hal-test.archives-ouvertes.fr/some-external-id"
deposit_id = 666
loader = DepositLoader(url, deposit_id)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["snapshot_id"] is not None
expected_revision_id = hash_to_bytes("637318680351f5d78856d13264faebbd91efe9bb")
revision = list(loader.storage.revision_get([expected_revision_id]))[0]
assert revision is not None
check_metadata_paths(
revision["metadata"],
paths=[
("extrinsic.provider", str),
("extrinsic.when", str),
("extrinsic.raw", dict),
("original_artifact", list),
],
)
# Only 2 top-level keys now
assert set(revision["metadata"].keys()) == {"extrinsic", "original_artifact"}
for original_artifact in revision["metadata"]["original_artifact"]:
check_metadata_paths(
original_artifact,
paths=[("filename", str), ("length", int), ("checksums", dict),],
)
def test_deposit_loading_ok(swh_config, requests_mock_datadir):
url = "https://hal-test.archives-ouvertes.fr/some-external-id"
deposit_id = 666
loader = DepositLoader(url, deposit_id)
actual_load_status = loader.load()
expected_snapshot_id = "b2b327b33dc85818bd23c3ccda8b7e675a66ecbd"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
assert_last_visit_matches(loader.storage, url, status="full", type="deposit")
stats = get_stats(loader.storage)
assert {
"content": 303,
"directory": 12,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 1,
"skipped_content": 0,
"snapshot": 1,
} == stats
revision_id = "637318680351f5d78856d13264faebbd91efe9bb"
expected_branches = {
"HEAD": {"target": revision_id, "target_type": "revision",},
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
check_snapshot(expected_snapshot, storage=loader.storage)
revision = next(loader.storage.revision_get([hash_to_bytes(revision_id)]))
assert revision
# check metadata
fetcher = {
"name": "swh-deposit",
"version": "0.0.1",
}
authority = {
"type": "deposit_client",
"url": "https://hal-test.archives-ouvertes.fr/",
}
orig_meta = loader.storage.origin_metadata_get(url, authority)
assert orig_meta is not None
assert isinstance(orig_meta, dict)
assert len(orig_meta["results"]) == 1
assert orig_meta["next_page_token"] is None
orig_meta0 = orig_meta["results"][0]
assert orig_meta0["authority"] == authority
assert orig_meta0["fetcher"] == fetcher
# Retrieve the information for deposit status update query to the deposit
urls = [
m
for m in requests_mock_datadir.request_history
if m.url == f"{DEPOSIT_URL}/{deposit_id}/update/"
]
assert len(urls) == 1
update_query = urls[0]
body = update_query.json()
expected_body = {
"status": "done",
"revision_id": revision_id,
"directory_id": hash_to_hex(revision["directory"]),
"snapshot_id": expected_snapshot_id,
"origin_url": url,
}
assert body == expected_body
def test_deposit_loading_ok_2(swh_config, requests_mock_datadir):
"""Field dates should be se appropriately
"""
external_id = "some-external-id"
url = f"https://hal-test.archives-ouvertes.fr/{external_id}"
deposit_id = 777
loader = DepositLoader(url, deposit_id)
actual_load_status = loader.load()
expected_snapshot_id = "3e68440fdd7c81d283f8f3aebb6f0c8657864192"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
assert_last_visit_matches(loader.storage, url, status="full", type="deposit")
revision_id = "564d18943d71be80d0d73b43a77cfb205bcde96c"
expected_branches = {"HEAD": {"target": revision_id, "target_type": "revision"}}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
check_snapshot(expected_snapshot, storage=loader.storage)
raw_meta = loader.client.metadata_get(deposit_id)
# Ensure the date fields are set appropriately in the revision
# Retrieve the revision
revision = next(loader.storage.revision_get([hash_to_bytes(revision_id)]))
assert revision
assert revision["date"] == raw_meta["deposit"]["author_date"]
assert revision["committer_date"] == raw_meta["deposit"]["committer_date"]
read_api = f"{DEPOSIT_URL}/{deposit_id}/meta/"
assert revision["metadata"] == {
"extrinsic": {
"provider": read_api,
"raw": {
"origin": {"type": "deposit", "url": url,},
"origin_metadata": {
"metadata": {
"@xmlns": ["http://www.w3.org/2005/Atom"],
"author": ["some awesome author", "another one", "no one",],
"codemeta:dateCreated": "2017-10-07T15:17:08Z",
"codemeta:datePublished": "2017-10-08T15:00:00Z",
"external_identifier": "some-external-id",
"url": url,
},
"provider": {
"metadata": None,
"provider_name": "hal",
"provider_type": "deposit_client",
"provider_url": "https://hal-test.archives-ouvertes.fr/",
},
"tool": {
"configuration": {"sword_version": "2"},
"name": "swh-deposit",
"version": "0.0.1",
},
},
},
"when": revision["metadata"]["extrinsic"]["when"], # dynamic
},
"original_artifact": [
{
"checksums": {
"sha1": "f8c63d7c890a7453498e6cf9fef215d85ec6801d",
"sha256": "474bf646aeeff6d945eb752b1a9f8a40f3d81a88909ee7bd2d08cc822aa361e6", # noqa
},
"filename": "archive.zip",
"length": 956830,
}
],
}
fetcher = {
"name": "swh-deposit",
"version": "0.0.1",
}
authority = {
"type": "deposit_client",
"url": "https://hal-test.archives-ouvertes.fr/",
}
# Check the metadata swh side
orig_meta = loader.storage.origin_metadata_get(url, authority)
assert orig_meta is not None
assert isinstance(orig_meta, dict)
assert len(orig_meta["results"]) == 1
assert orig_meta["next_page_token"] is None
assert len(orig_meta["results"]) == 1
orig_meta0 = orig_meta["results"][0]
# dynamic, a pain to display and not that interesting
orig_meta0.pop("discovery_date")
assert orig_meta0 == {
"origin_url": "https://hal-test.archives-ouvertes.fr/some-external-id",
"metadata": json.dumps(
{
"@xmlns": ["http://www.w3.org/2005/Atom"],
"author": ["some awesome author", "another one", "no one"],
"codemeta:dateCreated": "2017-10-07T15:17:08Z",
"codemeta:datePublished": "2017-10-08T15:00:00Z",
"external_identifier": "some-external-id",
"url": "https://hal-test.archives-ouvertes.fr/some-external-id",
}
).encode(),
"format": "sword-v2-atom-codemeta-v2-in-json",
"authority": authority,
"fetcher": fetcher,
}
# Retrieve the information for deposit status update query to the deposit
urls = [
m
for m in requests_mock_datadir.request_history
if m.url == f"{DEPOSIT_URL}/{deposit_id}/update/"
]
assert len(urls) == 1
update_query = urls[0]
body = update_query.json()
expected_body = {
"status": "done",
"revision_id": revision_id,
"directory_id": hash_to_hex(revision["directory"]),
"snapshot_id": expected_snapshot_id,
"origin_url": url,
}
assert body == expected_body
diff --git a/swh/loader/package/nixguix/tests/test_nixguix.py b/swh/loader/package/nixguix/tests/test_nixguix.py
index 8674556..7234657 100644
--- a/swh/loader/package/nixguix/tests/test_nixguix.py
+++ b/swh/loader/package/nixguix/tests/test_nixguix.py
@@ -1,554 +1,554 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import os
import json
import logging
import pytest
from json.decoder import JSONDecodeError
from typing import Dict, Optional, Tuple
from unittest.mock import patch
from swh.model.model import Snapshot
from swh.loader.package.archive.loader import ArchiveLoader
from swh.loader.package.nixguix.loader import (
NixGuixLoader,
retrieve_sources,
clean_sources,
)
from swh.loader.package.tests.common import (
get_stats,
check_snapshot,
)
from swh.loader.package.utils import download
from swh.model.hashutil import hash_to_bytes, hash_to_hex
from swh.storage.exc import HashCollision
-from swh.loader.tests.common import assert_last_visit_matches
+from swh.loader.tests import assert_last_visit_matches
sources_url = "https://nix-community.github.io/nixpkgs-swh/sources.json"
def test_retrieve_sources(swh_config, requests_mock_datadir):
j = retrieve_sources(sources_url)
assert "sources" in j.keys()
assert len(j["sources"]) == 2
def test_retrieve_non_existing(swh_config, requests_mock_datadir):
with pytest.raises(ValueError):
NixGuixLoader("https://non-existing-url")
def test_retrieve_non_json(swh_config, requests_mock_datadir):
with pytest.raises(JSONDecodeError):
NixGuixLoader("https://example.com/file.txt")
def test_clean_sources_invalid_schema(swh_config, requests_mock_datadir):
sources = {}
with pytest.raises(ValueError, match="sources structure invalid, missing: .*"):
clean_sources(sources)
def test_clean_sources_invalid_version(swh_config, requests_mock_datadir):
sources = {"version": 2, "sources": [], "revision": "my-revision"}
with pytest.raises(
ValueError, match="sources structure version .* is not supported"
):
clean_sources(sources)
def test_clean_sources_invalid_sources(swh_config, requests_mock_datadir):
sources = {
"version": 1,
"sources": [
# Valid source
{"type": "url", "urls": ["my-url"], "integrity": "my-integrity"},
# integrity is missing
{"type": "url", "urls": ["my-url"],},
# urls is not a list
{"type": "url", "urls": "my-url", "integrity": "my-integrity"},
# type is not url
{"type": "git", "urls": ["my-url"], "integrity": "my-integrity"},
],
"revision": "my-revision",
}
clean = clean_sources(sources)
assert len(clean["sources"]) == 1
def check_snapshot_revisions_ok(snapshot, storage):
"""Ensure the snapshot revisions are structurally as expected
"""
revision_ids = []
for name, branch in snapshot["branches"].items():
if name == b"evaluation":
continue # skipping that particular branch
if branch["target_type"] == "revision":
revision_ids.append(branch["target"])
revisions = storage.revision_get(revision_ids)
for rev in revisions:
metadata = rev["metadata"]
raw = metadata["extrinsic"]["raw"]
assert "url" in raw
assert "integrity" in raw
def test_loader_one_visit(swh_config, requests_mock_datadir):
loader = NixGuixLoader(sources_url)
res = loader.load()
assert res["status"] == "eventful"
stats = get_stats(loader.storage)
assert {
"content": 1,
"directory": 3,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 1,
"skipped_content": 0,
"snapshot": 1,
} == stats
# The visit is partial because urls pointing to non tarball file
# are not handled yet
assert_last_visit_matches(
loader.storage, sources_url, status="partial", type="nixguix"
)
def test_uncompress_failure(swh_config, requests_mock_datadir):
"""Non tarball files are currently not supported and the uncompress
function fails on such kind of files.
However, even in this case of failure (because of the url
https://example.com/file.txt), a snapshot and a visit has to be
created (with a status partial since all files are not archived).
"""
loader = NixGuixLoader(sources_url)
loader_status = loader.load()
urls = [s["urls"][0] for s in loader.sources]
assert "https://example.com/file.txt" in urls
assert loader_status["status"] == "eventful"
# The visit is partial because urls pointing to non tarball files
# are not handled yet
assert_last_visit_matches(
loader.storage, sources_url, status="partial", type="nixguix"
)
def test_loader_incremental(swh_config, requests_mock_datadir):
"""Ensure a second visit do not download artifact already
downloaded by the previous visit.
"""
loader = NixGuixLoader(sources_url)
load_status = loader.load()
loader.load()
expected_snapshot_id = "0c5881c74283793ebe9a09a105a9381e41380383"
assert load_status == {"status": "eventful", "snapshot_id": expected_snapshot_id}
assert_last_visit_matches(
loader.storage, sources_url, status="partial", type="nixguix"
)
expected_branches = {
"evaluation": {
"target": "cc4e04c26672dd74e5fd0fecb78b435fb55368f7",
"target_type": "revision",
},
"https://github.com/owner-1/repository-1/revision-1.tgz": {
"target": "488ad4e7b8e2511258725063cf43a2b897c503b4",
"target_type": "revision",
},
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
snapshot = check_snapshot(expected_snapshot, storage=loader.storage)
check_snapshot_revisions_ok(snapshot, loader.storage)
urls = [
m.url
for m in requests_mock_datadir.request_history
if m.url == ("https://github.com/owner-1/repository-1/revision-1.tgz")
]
# The artifact
# 'https://github.com/owner-1/repository-1/revision-1.tgz' is only
# visited one time
assert len(urls) == 1
def test_loader_two_visits(swh_config, requests_mock_datadir_visits):
"""To ensure there is only one origin, but two visits, two revisions
and two snapshots are created.
The first visit creates a snapshot containing one tarball. The
second visit creates a snapshot containing the same tarball and
another tarball.
"""
loader = NixGuixLoader(sources_url)
load_status = loader.load()
expected_snapshot_id = "0c5881c74283793ebe9a09a105a9381e41380383"
assert load_status == {"status": "eventful", "snapshot_id": expected_snapshot_id}
assert_last_visit_matches(
loader.storage, sources_url, status="partial", type="nixguix"
)
expected_branches = {
"evaluation": {
"target": "cc4e04c26672dd74e5fd0fecb78b435fb55368f7",
"target_type": "revision",
},
"https://github.com/owner-1/repository-1/revision-1.tgz": {
"target": "488ad4e7b8e2511258725063cf43a2b897c503b4",
"target_type": "revision",
},
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
snapshot = check_snapshot(expected_snapshot, storage=loader.storage)
check_snapshot_revisions_ok(snapshot, loader.storage)
stats = get_stats(loader.storage)
assert {
"content": 1,
"directory": 3,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 1,
"skipped_content": 0,
"snapshot": 1,
} == stats
loader = NixGuixLoader(sources_url)
load_status = loader.load()
expected_snapshot_id = "b0bfa75cbd0cc90aac3b9e95fb0f59c731176d97"
assert load_status == {"status": "eventful", "snapshot_id": expected_snapshot_id}
assert_last_visit_matches(
loader.storage, sources_url, status="partial", type="nixguix"
)
# This ensures visits are incremental. Indeed, if we request a
# second time an url, because of the requests_mock_datadir_visits
# fixture, the file has to end with `_visit1`.
expected_branches = {
"evaluation": {
"target": "602140776b2ce6c9159bcf52ada73a297c063d5e",
"target_type": "revision",
},
"https://github.com/owner-1/repository-1/revision-1.tgz": {
"target": "488ad4e7b8e2511258725063cf43a2b897c503b4",
"target_type": "revision",
},
"https://github.com/owner-2/repository-1/revision-1.tgz": {
"target": "85e0bad74e33e390aaeb74f139853ae3863ee544",
"target_type": "revision",
},
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
snapshot = check_snapshot(expected_snapshot, storage=loader.storage)
check_snapshot_revisions_ok(snapshot, loader.storage)
stats = get_stats(loader.storage)
assert {
"content": 2,
"directory": 5,
"origin": 1,
"origin_visit": 2,
"person": 1,
"release": 0,
"revision": 2,
"skipped_content": 0,
"snapshot": 2,
} == stats
def test_resolve_revision_from(swh_config, requests_mock_datadir):
loader = NixGuixLoader(sources_url)
known_artifacts = {
"id1": {"extrinsic": {"raw": {"url": "url1", "integrity": "integrity1"}}},
"id2": {"extrinsic": {"raw": {"url": "url2", "integrity": "integrity2"}}},
}
metadata = {"url": "url1", "integrity": "integrity1"}
assert loader.resolve_revision_from(known_artifacts, metadata) == "id1"
metadata = {"url": "url3", "integrity": "integrity3"}
assert loader.resolve_revision_from(known_artifacts, metadata) == None # noqa
def test_evaluation_branch(swh_config, requests_mock_datadir):
loader = NixGuixLoader(sources_url)
res = loader.load()
assert res["status"] == "eventful"
assert_last_visit_matches(
loader.storage, sources_url, status="partial", type="nixguix"
)
expected_branches = {
"https://github.com/owner-1/repository-1/revision-1.tgz": {
"target": "488ad4e7b8e2511258725063cf43a2b897c503b4",
"target_type": "revision",
},
"evaluation": {
"target": "cc4e04c26672dd74e5fd0fecb78b435fb55368f7",
"target_type": "revision",
},
}
expected_snapshot = {
"id": "0c5881c74283793ebe9a09a105a9381e41380383",
"branches": expected_branches,
}
snapshot = check_snapshot(expected_snapshot, storage=loader.storage)
check_snapshot_revisions_ok(snapshot, loader.storage)
def test_eoferror(swh_config, requests_mock_datadir):
"""Load a truncated archive which is invalid to make the uncompress
function raising the exception EOFError. We then check if a
snapshot is created, meaning this error is well managed.
"""
sources = (
"https://nix-community.github.io/nixpkgs-swh/sources-EOFError.json" # noqa
)
loader = NixGuixLoader(sources)
loader.load()
expected_branches = {
"evaluation": {
"target": "cc4e04c26672dd74e5fd0fecb78b435fb55368f7",
"target_type": "revision",
},
}
expected_snapshot = {
"id": "4257fa2350168c6bfec726a06452ea27a2c0cb33",
"branches": expected_branches,
}
snapshot = check_snapshot(expected_snapshot, storage=loader.storage)
check_snapshot_revisions_ok(snapshot, loader.storage)
def fake_download(
url: str,
dest: str,
hashes: Dict = {},
filename: Optional[str] = None,
auth: Optional[Tuple[str, str]] = None,
) -> Tuple[str, Dict]:
"""Fake download which raises HashCollision (for the sake of test simpliciy,
let's accept that makes sense)
For tests purpose only.
"""
if url == "https://example.com/file.txt":
# instead of failing because it's a file not dealt with by the nix guix
# loader, make it raise a hash collision
raise HashCollision("sha1", "f92d74e3874587aaf443d1db961d4e26dde13e9c", [])
return download(url, dest, hashes, filename, auth)
def test_raise_exception(swh_config, requests_mock_datadir, mocker):
mock_download = mocker.patch("swh.loader.package.loader.download")
mock_download.side_effect = fake_download
loader = NixGuixLoader(sources_url)
res = loader.load()
expected_snapshot_id = "0c5881c74283793ebe9a09a105a9381e41380383"
assert res == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
expected_branches = {
"https://github.com/owner-1/repository-1/revision-1.tgz": {
"target": "488ad4e7b8e2511258725063cf43a2b897c503b4",
"target_type": "revision",
},
"evaluation": {
"target": "cc4e04c26672dd74e5fd0fecb78b435fb55368f7",
"target_type": "revision",
},
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
snapshot = check_snapshot(expected_snapshot, storage=loader.storage)
check_snapshot_revisions_ok(snapshot, loader.storage)
assert len(mock_download.mock_calls) == 2
# The visit is partial because some artifact downloads failed
assert_last_visit_matches(
loader.storage, sources_url, status="partial", type="nixguix"
)
def test_load_nixguix_one_common_artifact_from_other_loader(
swh_config, datadir, requests_mock_datadir_visits, caplog
):
"""Misformatted revision should be caught and logged, then loading continues
"""
caplog.set_level(logging.ERROR, "swh.loader.package.nixguix.loader")
# 1. first ingest with for example the archive loader
gnu_url = "https://ftp.gnu.org/gnu/8sync/"
release = "0.1.0"
artifact_url = f"https://ftp.gnu.org/gnu/8sync/8sync-{release}.tar.gz"
gnu_artifacts = [
{
"time": 944729610,
"url": artifact_url,
"length": 221837,
"filename": f"8sync-{release}.tar.gz",
"version": release,
}
]
archive_loader = ArchiveLoader(url=gnu_url, artifacts=gnu_artifacts)
actual_load_status = archive_loader.load()
expected_snapshot_id = "c419397fd912039825ebdbea378bc6283f006bf5"
assert actual_load_status["status"] == "eventful"
assert actual_load_status["snapshot_id"] == expected_snapshot_id # noqa
assert_last_visit_matches(
archive_loader.storage, gnu_url, status="full", type="tar"
)
gnu_snapshot = archive_loader.storage.snapshot_get(
hash_to_bytes(expected_snapshot_id)
)
first_revision = gnu_snapshot["branches"][f"releases/{release}".encode("utf-8")]
# 2. Then ingest with the nixguix loader which lists the same artifact within its
# sources.json
# ensure test setup is ok
data_sources = os.path.join(
datadir, "https_nix-community.github.io", "nixpkgs-swh_sources_special.json"
)
all_sources = json.loads(open(data_sources).read())
found = False
for source in all_sources["sources"]:
if source["urls"][0] == artifact_url:
found = True
assert (
found is True
), f"test setup error: {artifact_url} must be in {data_sources}"
# first visit with a snapshot, ok
sources_url = "https://nix-community.github.io/nixpkgs-swh/sources_special.json"
loader = NixGuixLoader(sources_url)
actual_load_status2 = loader.load()
assert actual_load_status2["status"] == "eventful"
assert_last_visit_matches(
loader.storage, sources_url, status="full", type="nixguix"
)
snapshot_id = actual_load_status2["snapshot_id"]
snapshot = loader.storage.snapshot_get(hash_to_bytes(snapshot_id))
snapshot.pop("next_branch") # snapshot_get endpoint detail to drop
# simulate a snapshot already seen with a revision with the wrong metadata structure
# This revision should be skipped, thus making the artifact being ingested again.
with patch(
"swh.loader.package.loader.PackageLoader.last_snapshot"
) as last_snapshot:
# mutate the snapshot to target a revision with the wrong metadata structure
# snapshot["branches"][artifact_url.encode("utf-8")] = first_revision
old_revision = next(loader.storage.revision_get([first_revision["target"]]))
# assert that revision is not in the right format
assert old_revision["metadata"]["extrinsic"]["raw"].get("integrity", {}) == {}
# mutate snapshot to create a clash
snapshot["branches"][artifact_url.encode("utf-8")] = {
"target_type": "revision",
"target": old_revision["id"],
}
# modify snapshot to actually change revision metadata structure so we simulate
# a revision written by somebody else (structure different)
last_snapshot.return_value = Snapshot.from_dict(snapshot)
loader = NixGuixLoader(sources_url)
actual_load_status3 = loader.load()
assert last_snapshot.called
assert actual_load_status3["status"] == "eventful"
assert_last_visit_matches(
loader.storage, sources_url, status="full", type="nixguix"
)
new_snapshot_id = "32ff641e510aceefc3a6d0dcbf208b2854d2e965"
assert actual_load_status3["snapshot_id"] == new_snapshot_id
last_snapshot = loader.storage.snapshot_get(hash_to_bytes(new_snapshot_id))
new_revision_branch = last_snapshot["branches"][artifact_url.encode("utf-8")]
assert new_revision_branch["target_type"] == "revision"
new_revision = next(
loader.storage.revision_get([new_revision_branch["target"]])
)
# the new revision has the correct structure, so it got ingested alright by the
# new run
assert new_revision["metadata"]["extrinsic"]["raw"]["integrity"] is not None
nb_detections = 0
actual_detection: Dict
for record in caplog.records:
logtext = record.getMessage()
if "Unexpected metadata revision structure detected:" in logtext:
nb_detections += 1
actual_detection = record.args["context"]
assert actual_detection
# as many calls as there are sources listed in the sources.json
assert nb_detections == len(all_sources["sources"])
assert actual_detection == {
"revision": hash_to_hex(old_revision["id"]),
"reason": "'integrity'",
"known_artifact": old_revision["metadata"],
}
diff --git a/swh/loader/package/npm/tests/test_npm.py b/swh/loader/package/npm/tests/test_npm.py
index 7dc2abc..508f2cc 100644
--- a/swh/loader/package/npm/tests/test_npm.py
+++ b/swh/loader/package/npm/tests/test_npm.py
@@ -1,585 +1,585 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import json
import os
import pytest
from swh.model.hashutil import hash_to_bytes
from swh.model.model import Person
from swh.loader.package.npm.loader import (
NpmLoader,
extract_npm_package_author,
artifact_to_revision_id,
)
from swh.loader.package.tests.common import (
check_snapshot,
check_metadata_paths,
get_stats,
)
-from swh.loader.tests.common import assert_last_visit_matches
+from swh.loader.tests import assert_last_visit_matches
def test_extract_npm_package_author(datadir):
package_metadata_filepath = os.path.join(
datadir, "https_replicate.npmjs.com", "org_visit1"
)
with open(package_metadata_filepath) as json_file:
package_metadata = json.load(json_file)
extract_npm_package_author(package_metadata["versions"]["0.0.2"]) == Person(
fullname=b"mooz <stillpedant@gmail.com>",
name=b"mooz",
email=b"stillpedant@gmail.com",
)
assert extract_npm_package_author(package_metadata["versions"]["0.0.3"]) == Person(
fullname=b"Masafumi Oyamada <stillpedant@gmail.com>",
name=b"Masafumi Oyamada",
email=b"stillpedant@gmail.com",
)
package_json = json.loads(
"""
{
"name": "highlightjs-line-numbers.js",
"version": "2.7.0",
"description": "Highlight.js line numbers plugin.",
"main": "src/highlightjs-line-numbers.js",
"dependencies": {},
"devDependencies": {
"gulp": "^4.0.0",
"gulp-rename": "^1.4.0",
"gulp-replace": "^0.6.1",
"gulp-uglify": "^1.2.0"
},
"repository": {
"type": "git",
"url": "https://github.com/wcoder/highlightjs-line-numbers.js.git"
},
"author": "Yauheni Pakala <evgeniy.pakalo@gmail.com>",
"license": "MIT",
"bugs": {
"url": "https://github.com/wcoder/highlightjs-line-numbers.js/issues"
},
"homepage": "http://wcoder.github.io/highlightjs-line-numbers.js/"
}"""
) # noqa
assert extract_npm_package_author(package_json) == Person(
fullname=b"Yauheni Pakala <evgeniy.pakalo@gmail.com>",
name=b"Yauheni Pakala",
email=b"evgeniy.pakalo@gmail.com",
)
package_json = json.loads(
"""
{
"name": "3-way-diff",
"version": "0.0.1",
"description": "3-way diffing of JavaScript objects",
"main": "index.js",
"authors": [
{
"name": "Shawn Walsh",
"url": "https://github.com/shawnpwalsh"
},
{
"name": "Markham F Rollins IV",
"url": "https://github.com/mrollinsiv"
}
],
"keywords": [
"3-way diff",
"3 way diff",
"three-way diff",
"three way diff"
],
"devDependencies": {
"babel-core": "^6.20.0",
"babel-preset-es2015": "^6.18.0",
"mocha": "^3.0.2"
},
"dependencies": {
"lodash": "^4.15.0"
}
}"""
)
assert extract_npm_package_author(package_json) == Person(
fullname=b"Shawn Walsh", name=b"Shawn Walsh", email=None
)
package_json = json.loads(
"""
{
"name": "yfe-ynpm",
"version": "1.0.0",
"homepage": "http://gitlab.ywwl.com/yfe/yfe-ynpm",
"repository": {
"type": "git",
"url": "git@gitlab.ywwl.com:yfe/yfe-ynpm.git"
},
"author": [
"fengmk2 <fengmk2@gmail.com> (https://fengmk2.com)",
"xufuzi <xufuzi@ywwl.com> (https://7993.org)"
],
"license": "MIT"
}"""
)
assert extract_npm_package_author(package_json) == Person(
fullname=b"fengmk2 <fengmk2@gmail.com> (https://fengmk2.com)",
name=b"fengmk2",
email=b"fengmk2@gmail.com",
)
package_json = json.loads(
"""
{
"name": "umi-plugin-whale",
"version": "0.0.8",
"description": "Internal contract component",
"authors": {
"name": "xiaohuoni",
"email": "448627663@qq.com"
},
"repository": "alitajs/whale",
"devDependencies": {
"np": "^3.0.4",
"umi-tools": "*"
},
"license": "MIT"
}"""
)
assert extract_npm_package_author(package_json) == Person(
fullname=b"xiaohuoni <448627663@qq.com>",
name=b"xiaohuoni",
email=b"448627663@qq.com",
)
def normalize_hashes(hashes):
if isinstance(hashes, str):
return hash_to_bytes(hashes)
if isinstance(hashes, list):
return [hash_to_bytes(x) for x in hashes]
return {hash_to_bytes(k): hash_to_bytes(v) for k, v in hashes.items()}
_expected_new_contents_first_visit = normalize_hashes(
[
"4ce3058e16ab3d7e077f65aabf855c34895bf17c",
"858c3ceee84c8311adc808f8cdb30d233ddc9d18",
"0fa33b4f5a4e0496da6843a38ff1af8b61541996",
"85a410f8ef8eb8920f2c384a9555566ad4a2e21b",
"9163ac8025923d5a45aaac482262893955c9b37b",
"692cf623b8dd2c5df2c2998fd95ae4ec99882fb4",
"18c03aac6d3e910efb20039c15d70ab5e0297101",
"41265c42446aac17ca769e67d1704f99e5a1394d",
"783ff33f5882813dca9239452c4a7cadd4dba778",
"b029cfb85107aee4590c2434a3329bfcf36f8fa1",
"112d1900b4c2e3e9351050d1b542c9744f9793f3",
"5439bbc4bd9a996f1a38244e6892b71850bc98fd",
"d83097a2f994b503185adf4e719d154123150159",
"d0939b4898e83090ee55fd9d8a60e312cfadfbaf",
"b3523a26f7147e4af40d9d462adaae6d49eda13e",
"cd065fb435d6fb204a8871bcd623d0d0e673088c",
"2854a40855ad839a54f4b08f5cff0cf52fca4399",
"b8a53bbaac34ebb8c6169d11a4b9f13b05c583fe",
"0f73d56e1cf480bded8a1ecf20ec6fc53c574713",
"0d9882b2dfafdce31f4e77fe307d41a44a74cefe",
"585fc5caab9ead178a327d3660d35851db713df1",
"e8cd41a48d79101977e3036a87aeb1aac730686f",
"5414efaef33cceb9f3c9eb5c4cc1682cd62d14f7",
"9c3cc2763bf9e9e37067d3607302c4776502df98",
"3649a68410e354c83cd4a38b66bd314de4c8f5c9",
"e96ed0c091de1ebdf587104eaf63400d1974a1fe",
"078ca03d2f99e4e6eab16f7b75fbb7afb699c86c",
"38de737da99514de6559ff163c988198bc91367a",
]
)
_expected_new_directories_first_visit = normalize_hashes(
[
"3370d20d6f96dc1c9e50f083e2134881db110f4f",
"42753c0c2ab00c4501b552ac4671c68f3cf5aece",
"d7895533ef5edbcffdea3f057d9fef3a1ef845ce",
"80579be563e2ef3e385226fe7a3f079b377f142c",
"3b0ddc6a9e58b4b53c222da4e27b280b6cda591c",
"bcad03ce58ac136f26f000990fc9064e559fe1c0",
"5fc7e82a1bc72e074665c6078c6d3fad2f13d7ca",
"e3cd26beba9b1e02f6762ef54bd9ac80cc5f25fd",
"584b5b4b6cf7f038095e820b99386a9c232de931",
"184c8d6d0d242f2b1792ef9d3bf396a5434b7f7a",
"bb5f4ee143c970367eb409f2e4c1104898048b9d",
"1b95491047add1103db0dfdfa84a9735dcb11e88",
"a00c6de13471a2d66e64aca140ddb21ef5521e62",
"5ce6c1cd5cda2d546db513aaad8c72a44c7771e2",
"c337091e349b6ac10d38a49cdf8c2401ef9bb0f2",
"202fafcd7c0f8230e89d5496ad7f44ab12b807bf",
"775cc516543be86c15c1dc172f49c0d4e6e78235",
"ff3d1ead85a14f891e8b3fa3a89de39db1b8de2e",
]
)
_expected_new_revisions_first_visit = normalize_hashes(
{
"d8a1c7474d2956ac598a19f0f27d52f7015f117e": (
"42753c0c2ab00c4501b552ac4671c68f3cf5aece"
),
"5f9eb78af37ffd12949f235e86fac04898f9f72a": (
"3370d20d6f96dc1c9e50f083e2134881db110f4f"
),
"ba019b192bdb94bd0b5bd68b3a5f92b5acc2239a": (
"d7895533ef5edbcffdea3f057d9fef3a1ef845ce"
),
}
)
def package_url(package):
return "https://www.npmjs.com/package/%s" % package
def package_metadata_url(package):
return "https://replicate.npmjs.com/%s/" % package
def test_revision_metadata_structure(swh_config, requests_mock_datadir):
package = "org"
loader = NpmLoader(package_url(package))
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["snapshot_id"] is not None
expected_revision_id = hash_to_bytes("d8a1c7474d2956ac598a19f0f27d52f7015f117e")
revision = list(loader.storage.revision_get([expected_revision_id]))[0]
assert revision is not None
check_metadata_paths(
revision["metadata"],
paths=[
("intrinsic.tool", str),
("intrinsic.raw", dict),
("extrinsic.provider", str),
("extrinsic.when", str),
("extrinsic.raw", dict),
("original_artifact", list),
],
)
for original_artifact in revision["metadata"]["original_artifact"]:
check_metadata_paths(
original_artifact,
paths=[("filename", str), ("length", int), ("checksums", dict),],
)
def test_npm_loader_first_visit(swh_config, requests_mock_datadir):
package = "org"
loader = NpmLoader(package_url(package))
actual_load_status = loader.load()
expected_snapshot_id = "d0587e1195aed5a8800411a008f2f2d627f18e2d"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
stats = get_stats(loader.storage)
assert {
"content": len(_expected_new_contents_first_visit),
"directory": len(_expected_new_directories_first_visit),
"origin": 1,
"origin_visit": 1,
"person": 2,
"release": 0,
"revision": len(_expected_new_revisions_first_visit),
"skipped_content": 0,
"snapshot": 1,
} == stats
assert len(
list(loader.storage.content_get(_expected_new_contents_first_visit))
) == len(_expected_new_contents_first_visit)
assert (
list(loader.storage.directory_missing(_expected_new_directories_first_visit))
== []
)
assert (
list(loader.storage.revision_missing(_expected_new_revisions_first_visit)) == []
)
expected_snapshot = {
"id": expected_snapshot_id,
"branches": {
"HEAD": {"target": "releases/0.0.4", "target_type": "alias"},
"releases/0.0.2": {
"target": "d8a1c7474d2956ac598a19f0f27d52f7015f117e",
"target_type": "revision",
},
"releases/0.0.3": {
"target": "5f9eb78af37ffd12949f235e86fac04898f9f72a",
"target_type": "revision",
},
"releases/0.0.4": {
"target": "ba019b192bdb94bd0b5bd68b3a5f92b5acc2239a",
"target_type": "revision",
},
},
}
check_snapshot(expected_snapshot, loader.storage)
def test_npm_loader_incremental_visit(swh_config, requests_mock_datadir_visits):
package = "org"
url = package_url(package)
loader = NpmLoader(url)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["status"] is not None
assert_last_visit_matches(loader.storage, url, status="full", type="npm")
stats = get_stats(loader.storage)
assert {
"content": len(_expected_new_contents_first_visit),
"directory": len(_expected_new_directories_first_visit),
"origin": 1,
"origin_visit": 1,
"person": 2,
"release": 0,
"revision": len(_expected_new_revisions_first_visit),
"skipped_content": 0,
"snapshot": 1,
} == stats
loader._info = None # reset loader internal state
actual_load_status2 = loader.load()
assert actual_load_status2["status"] == "eventful"
snap_id2 = actual_load_status2["snapshot_id"]
assert snap_id2 is not None
assert snap_id2 != actual_load_status["snapshot_id"]
assert_last_visit_matches(loader.storage, url, status="full", type="npm")
stats = get_stats(loader.storage)
assert { # 3 new releases artifacts
"content": len(_expected_new_contents_first_visit) + 14,
"directory": len(_expected_new_directories_first_visit) + 15,
"origin": 1,
"origin_visit": 2,
"person": 2,
"release": 0,
"revision": len(_expected_new_revisions_first_visit) + 3,
"skipped_content": 0,
"snapshot": 2,
} == stats
urls = [
m.url
for m in requests_mock_datadir_visits.request_history
if m.url.startswith("https://registry.npmjs.org")
]
assert len(urls) == len(set(urls)) # we visited each artifact once across
@pytest.mark.usefixtures("requests_mock_datadir")
def test_npm_loader_version_divergence(swh_config):
package = "@aller_shared"
url = package_url(package)
loader = NpmLoader(url)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["status"] is not None
assert_last_visit_matches(loader.storage, url, status="full", type="npm")
stats = get_stats(loader.storage)
assert { # 1 new releases artifacts
"content": 534,
"directory": 153,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 2,
"skipped_content": 0,
"snapshot": 1,
} == stats
expected_snapshot = {
"id": "b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92",
"branches": {
"HEAD": {"target_type": "alias", "target": "releases/0.1.0"},
"releases/0.1.0": {
"target_type": "revision",
"target": "845673bfe8cbd31b1eaf757745a964137e6f9116",
},
"releases/0.1.1-alpha.14": {
"target_type": "revision",
"target": "05181c12cd8c22035dd31155656826b85745da37",
},
},
}
check_snapshot(expected_snapshot, loader.storage)
def test_npm_artifact_to_revision_id_none():
"""Current loader version should stop soon if nothing can be found
"""
artifact_metadata = {
"dist": {"shasum": "05181c12cd8c22035dd31155656826b85745da37",},
}
known_artifacts = {
"b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92": {},
}
assert artifact_to_revision_id(known_artifacts, artifact_metadata) is None
def test_npm_artifact_to_revision_id_old_loader_version():
"""Current loader version should solve old metadata scheme
"""
artifact_metadata = {
"dist": {"shasum": "05181c12cd8c22035dd31155656826b85745da37",}
}
known_artifacts = {
hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"): {
"package_source": {"sha1": "something-wrong"}
},
hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"): {
"package_source": {"sha1": "05181c12cd8c22035dd31155656826b85745da37",}
},
}
assert artifact_to_revision_id(known_artifacts, artifact_metadata) == hash_to_bytes(
"845673bfe8cbd31b1eaf757745a964137e6f9116"
)
def test_npm_artifact_to_revision_id_current_loader_version():
"""Current loader version should be able to solve current metadata scheme
"""
artifact_metadata = {
"dist": {"shasum": "05181c12cd8c22035dd31155656826b85745da37",}
}
known_artifacts = {
hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"): {
"original_artifact": [
{"checksums": {"sha1": "05181c12cd8c22035dd31155656826b85745da37"},}
],
},
hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"): {
"original_artifact": [{"checksums": {"sha1": "something-wrong"},}],
},
}
assert artifact_to_revision_id(known_artifacts, artifact_metadata) == hash_to_bytes(
"b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"
)
def test_npm_artifact_with_no_intrinsic_metadata(swh_config, requests_mock_datadir):
"""Skip artifact with no intrinsic metadata during ingestion
"""
package = "nativescript-telerik-analytics"
url = package_url(package)
loader = NpmLoader(url)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
# no branch as one artifact without any intrinsic metadata
expected_snapshot = {
"id": "1a8893e6a86f444e8be8e7bda6cb34fb1735a00e",
"branches": {},
}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, url, status="full", type="npm")
def test_npm_artifact_with_no_upload_time(swh_config, requests_mock_datadir):
"""With no time upload, artifact is skipped
"""
package = "jammit-no-time"
url = package_url(package)
loader = NpmLoader(url)
actual_load_status = loader.load()
assert actual_load_status["status"] == "uneventful"
# no branch as one artifact without any intrinsic metadata
expected_snapshot = {
"id": "1a8893e6a86f444e8be8e7bda6cb34fb1735a00e",
"branches": {},
}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, url, status="partial", type="npm")
def test_npm_artifact_use_mtime_if_no_time(swh_config, requests_mock_datadir):
"""With no time upload, artifact is skipped
"""
package = "jammit-express"
url = package_url(package)
loader = NpmLoader(url)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
# artifact is used
expected_snapshot = {
"id": "d6e08e19159f77983242877c373c75222d5ae9dd",
"branches": {
"HEAD": {"target_type": "alias", "target": "releases/0.0.1"},
"releases/0.0.1": {
"target_type": "revision",
"target": "9e4dd2b40d1b46b70917c0949aa2195c823a648e",
},
},
}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, url, status="full", type="npm")
def test_npm_no_artifact(swh_config, requests_mock_datadir):
"""If no artifacts at all is found for origin, the visit fails completely
"""
package = "catify"
url = package_url(package)
loader = NpmLoader(url)
actual_load_status = loader.load()
assert actual_load_status == {
"status": "failed",
}
assert_last_visit_matches(loader.storage, url, status="partial", type="npm")
diff --git a/swh/loader/package/pypi/tests/test_pypi.py b/swh/loader/package/pypi/tests/test_pypi.py
index 30743bb..6ddae1c 100644
--- a/swh/loader/package/pypi/tests/test_pypi.py
+++ b/swh/loader/package/pypi/tests/test_pypi.py
@@ -1,831 +1,831 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import os
from os import path
import pytest
from unittest.mock import patch
from swh.core.tarball import uncompress
from swh.core.pytest_plugin import requests_mock_datadir_factory
from swh.model.hashutil import hash_to_bytes
from swh.model.model import Person
from swh.loader.package.pypi.loader import (
PyPILoader,
pypi_api_url,
author,
extract_intrinsic_metadata,
artifact_to_revision_id,
)
from swh.loader.package.tests.common import (
check_snapshot,
check_metadata_paths,
get_stats,
)
-from swh.loader.tests.common import assert_last_visit_matches
+from swh.loader.tests import assert_last_visit_matches
def test_author_basic():
data = {
"author": "i-am-groot",
"author_email": "iam@groot.org",
}
actual_author = author(data)
expected_author = Person(
fullname=b"i-am-groot <iam@groot.org>",
name=b"i-am-groot",
email=b"iam@groot.org",
)
assert actual_author == expected_author
def test_author_empty_email():
data = {
"author": "i-am-groot",
"author_email": "",
}
actual_author = author(data)
expected_author = Person(fullname=b"i-am-groot", name=b"i-am-groot", email=b"",)
assert actual_author == expected_author
def test_author_empty_name():
data = {
"author": "",
"author_email": "iam@groot.org",
}
actual_author = author(data)
expected_author = Person(
fullname=b" <iam@groot.org>", name=b"", email=b"iam@groot.org",
)
assert actual_author == expected_author
def test_author_malformed():
data = {
"author": "['pierre', 'paul', 'jacques']",
"author_email": None,
}
actual_author = author(data)
expected_author = Person(
fullname=b"['pierre', 'paul', 'jacques']",
name=b"['pierre', 'paul', 'jacques']",
email=None,
)
assert actual_author == expected_author
def test_author_malformed_2():
data = {
"author": "[marie, jeanne]",
"author_email": "[marie@some, jeanne@thing]",
}
actual_author = author(data)
expected_author = Person(
fullname=b"[marie, jeanne] <[marie@some, jeanne@thing]>",
name=b"[marie, jeanne]",
email=b"[marie@some, jeanne@thing]",
)
assert actual_author == expected_author
def test_author_malformed_3():
data = {
"author": "[marie, jeanne, pierre]",
"author_email": "[marie@somewhere.org, jeanne@somewhere.org]",
}
actual_author = author(data)
expected_author = Person(
fullname=(
b"[marie, jeanne, pierre] " b"<[marie@somewhere.org, jeanne@somewhere.org]>"
),
name=b"[marie, jeanne, pierre]",
email=b"[marie@somewhere.org, jeanne@somewhere.org]",
)
actual_author == expected_author
# configuration error #
def test_badly_configured_loader_raise(monkeypatch):
"""Badly configured loader should raise"""
monkeypatch.delenv("SWH_CONFIG_FILENAME", raising=False)
with pytest.raises(ValueError) as e:
PyPILoader(url="some-url")
assert "Misconfiguration" in e.value.args[0]
def test_pypi_api_url():
"""Compute pypi api url from the pypi project url should be ok"""
url = pypi_api_url("https://pypi.org/project/requests")
assert url == "https://pypi.org/pypi/requests/json"
def test_pypi_api_url_with_slash():
"""Compute pypi api url from the pypi project url should be ok"""
url = pypi_api_url("https://pypi.org/project/requests/")
assert url == "https://pypi.org/pypi/requests/json"
@pytest.mark.fs
def test_extract_intrinsic_metadata(tmp_path, datadir):
"""Parsing existing archive's PKG-INFO should yield results"""
uncompressed_archive_path = str(tmp_path)
archive_path = path.join(
datadir, "https_files.pythonhosted.org", "0805nexter-1.1.0.zip"
)
uncompress(archive_path, dest=uncompressed_archive_path)
actual_metadata = extract_intrinsic_metadata(uncompressed_archive_path)
expected_metadata = {
"metadata_version": "1.0",
"name": "0805nexter",
"version": "1.1.0",
"summary": "a simple printer of nested lest",
"home_page": "http://www.hp.com",
"author": "hgtkpython",
"author_email": "2868989685@qq.com",
"platforms": ["UNKNOWN"],
}
assert actual_metadata == expected_metadata
@pytest.mark.fs
def test_extract_intrinsic_metadata_failures(tmp_path):
"""Parsing inexistent path/archive/PKG-INFO yield None"""
tmp_path = str(tmp_path) # py3.5 work around (PosixPath issue)
# inexistent first level path
assert extract_intrinsic_metadata("/something-inexistent") == {}
# inexistent second level path (as expected by pypi archives)
assert extract_intrinsic_metadata(tmp_path) == {}
# inexistent PKG-INFO within second level path
existing_path_no_pkginfo = path.join(tmp_path, "something")
os.mkdir(existing_path_no_pkginfo)
assert extract_intrinsic_metadata(tmp_path) == {}
# LOADER SCENARIO #
# "edge" cases (for the same origin) #
# no release artifact:
# {visit full, status: uneventful, no contents, etc...}
requests_mock_datadir_missing_all = requests_mock_datadir_factory(
ignore_urls=[
"https://files.pythonhosted.org/packages/ec/65/c0116953c9a3f47de89e71964d6c7b0c783b01f29fa3390584dbf3046b4d/0805nexter-1.1.0.zip", # noqa
"https://files.pythonhosted.org/packages/c4/a0/4562cda161dc4ecbbe9e2a11eb365400c0461845c5be70d73869786809c4/0805nexter-1.2.0.zip", # noqa
]
)
def test_no_release_artifact(swh_config, requests_mock_datadir_missing_all):
"""Load a pypi project with all artifacts missing ends up with no snapshot
"""
url = "https://pypi.org/project/0805nexter"
loader = PyPILoader(url)
actual_load_status = loader.load()
assert actual_load_status["status"] == "uneventful"
assert actual_load_status["snapshot_id"] is not None
stats = get_stats(loader.storage)
assert {
"content": 0,
"directory": 0,
"origin": 1,
"origin_visit": 1,
"person": 0,
"release": 0,
"revision": 0,
"skipped_content": 0,
"snapshot": 1,
} == stats
assert_last_visit_matches(loader.storage, url, status="partial", type="pypi")
# problem during loading:
# {visit: partial, status: uneventful, no snapshot}
def test_release_with_traceback(swh_config, requests_mock_datadir):
url = "https://pypi.org/project/0805nexter"
with patch(
"swh.loader.package.pypi.loader.PyPILoader.last_snapshot",
side_effect=ValueError("Fake problem to fail the visit"),
):
loader = PyPILoader(url)
actual_load_status = loader.load()
assert actual_load_status == {"status": "failed"}
stats = get_stats(loader.storage)
assert {
"content": 0,
"directory": 0,
"origin": 1,
"origin_visit": 1,
"person": 0,
"release": 0,
"revision": 0,
"skipped_content": 0,
"snapshot": 0,
} == stats
assert_last_visit_matches(loader.storage, url, status="partial", type="pypi")
# problem during loading: failure early enough in between swh contents...
# some contents (contents, directories, etc...) have been written in storage
# {visit: partial, status: eventful, no snapshot}
# problem during loading: failure late enough we can have snapshots (some
# revisions are written in storage already)
# {visit: partial, status: eventful, snapshot}
# "normal" cases (for the same origin) #
requests_mock_datadir_missing_one = requests_mock_datadir_factory(
ignore_urls=[
"https://files.pythonhosted.org/packages/ec/65/c0116953c9a3f47de89e71964d6c7b0c783b01f29fa3390584dbf3046b4d/0805nexter-1.1.0.zip", # noqa
]
)
# some missing release artifacts:
# {visit partial, status: eventful, 1 snapshot}
def test_revision_metadata_structure(swh_config, requests_mock_datadir):
url = "https://pypi.org/project/0805nexter"
loader = PyPILoader(url)
actual_load_status = loader.load()
assert actual_load_status["status"] == "eventful"
assert actual_load_status["snapshot_id"] is not None
expected_revision_id = hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21")
revision = list(loader.storage.revision_get([expected_revision_id]))[0]
assert revision is not None
check_metadata_paths(
revision["metadata"],
paths=[
("intrinsic.tool", str),
("intrinsic.raw", dict),
("extrinsic.provider", str),
("extrinsic.when", str),
("extrinsic.raw", dict),
("original_artifact", list),
],
)
for original_artifact in revision["metadata"]["original_artifact"]:
check_metadata_paths(
original_artifact,
paths=[("filename", str), ("length", int), ("checksums", dict),],
)
def test_visit_with_missing_artifact(swh_config, requests_mock_datadir_missing_one):
"""Load a pypi project with some missing artifacts ends up with 1 snapshot
"""
url = "https://pypi.org/project/0805nexter"
loader = PyPILoader(url)
actual_load_status = loader.load()
expected_snapshot_id = "dd0e4201a232b1c104433741dbf45895b8ac9355"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
stats = get_stats(loader.storage)
assert {
"content": 3,
"directory": 2,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 1,
"skipped_content": 0,
"snapshot": 1,
} == stats
expected_contents = map(
hash_to_bytes,
[
"405859113963cb7a797642b45f171d6360425d16",
"e5686aa568fdb1d19d7f1329267082fe40482d31",
"83ecf6ec1114fd260ca7a833a2d165e71258c338",
],
)
assert list(loader.storage.content_missing_per_sha1(expected_contents)) == []
expected_dirs = map(
hash_to_bytes,
[
"b178b66bd22383d5f16f4f5c923d39ca798861b4",
"c3a58f8b57433a4b56caaa5033ae2e0931405338",
],
)
assert list(loader.storage.directory_missing(expected_dirs)) == []
# {revision hash: directory hash}
expected_revs = {
hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"): hash_to_bytes(
"b178b66bd22383d5f16f4f5c923d39ca798861b4"
), # noqa
}
assert list(loader.storage.revision_missing(expected_revs)) == []
expected_branches = {
"releases/1.2.0": {
"target": "e445da4da22b31bfebb6ffc4383dbf839a074d21",
"target_type": "revision",
},
"HEAD": {"target": "releases/1.2.0", "target_type": "alias",},
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
check_snapshot(expected_snapshot, storage=loader.storage)
assert_last_visit_matches(loader.storage, url, status="partial", type="pypi")
def test_visit_with_1_release_artifact(swh_config, requests_mock_datadir):
"""With no prior visit, load a pypi project ends up with 1 snapshot
"""
url = "https://pypi.org/project/0805nexter"
loader = PyPILoader(url)
actual_load_status = loader.load()
expected_snapshot_id = "ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
stats = get_stats(loader.storage)
assert {
"content": 6,
"directory": 4,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 2,
"skipped_content": 0,
"snapshot": 1,
} == stats
expected_contents = map(
hash_to_bytes,
[
"a61e24cdfdab3bb7817f6be85d37a3e666b34566",
"938c33483285fd8ad57f15497f538320df82aeb8",
"a27576d60e08c94a05006d2e6d540c0fdb5f38c8",
"405859113963cb7a797642b45f171d6360425d16",
"e5686aa568fdb1d19d7f1329267082fe40482d31",
"83ecf6ec1114fd260ca7a833a2d165e71258c338",
],
)
assert list(loader.storage.content_missing_per_sha1(expected_contents)) == []
expected_dirs = map(
hash_to_bytes,
[
"05219ba38bc542d4345d5638af1ed56c7d43ca7d",
"cf019eb456cf6f78d8c4674596f1c9a97ece8f44",
"b178b66bd22383d5f16f4f5c923d39ca798861b4",
"c3a58f8b57433a4b56caaa5033ae2e0931405338",
],
)
assert list(loader.storage.directory_missing(expected_dirs)) == []
# {revision hash: directory hash}
expected_revs = {
hash_to_bytes("4c99891f93b81450385777235a37b5e966dd1571"): hash_to_bytes(
"05219ba38bc542d4345d5638af1ed56c7d43ca7d"
), # noqa
hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"): hash_to_bytes(
"b178b66bd22383d5f16f4f5c923d39ca798861b4"
), # noqa
}
assert list(loader.storage.revision_missing(expected_revs)) == []
expected_branches = {
"releases/1.1.0": {
"target": "4c99891f93b81450385777235a37b5e966dd1571",
"target_type": "revision",
},
"releases/1.2.0": {
"target": "e445da4da22b31bfebb6ffc4383dbf839a074d21",
"target_type": "revision",
},
"HEAD": {"target": "releases/1.2.0", "target_type": "alias",},
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, url, status="full", type="pypi")
def test_multiple_visits_with_no_change(swh_config, requests_mock_datadir):
"""Multiple visits with no changes results in 1 same snapshot
"""
url = "https://pypi.org/project/0805nexter"
loader = PyPILoader(url)
actual_load_status = loader.load()
snapshot_id = "ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": snapshot_id,
}
assert_last_visit_matches(loader.storage, url, status="full", type="pypi")
stats = get_stats(loader.storage)
assert {
"content": 6,
"directory": 4,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 2,
"skipped_content": 0,
"snapshot": 1,
} == stats
expected_branches = {
"releases/1.1.0": {
"target": "4c99891f93b81450385777235a37b5e966dd1571",
"target_type": "revision",
},
"releases/1.2.0": {
"target": "e445da4da22b31bfebb6ffc4383dbf839a074d21",
"target_type": "revision",
},
"HEAD": {"target": "releases/1.2.0", "target_type": "alias",},
}
expected_snapshot = {
"id": snapshot_id,
"branches": expected_branches,
}
check_snapshot(expected_snapshot, loader.storage)
actual_load_status2 = loader.load()
assert actual_load_status2 == {
"status": "uneventful",
"snapshot_id": actual_load_status2["snapshot_id"],
}
visit_status2 = assert_last_visit_matches(
loader.storage, url, status="full", type="pypi"
)
stats2 = get_stats(loader.storage)
expected_stats2 = stats.copy()
expected_stats2["origin_visit"] = 1 + 1
assert expected_stats2 == stats2
# same snapshot
actual_snapshot_id = visit_status2.snapshot
assert actual_snapshot_id == hash_to_bytes(snapshot_id)
def test_incremental_visit(swh_config, requests_mock_datadir_visits):
"""With prior visit, 2nd load will result with a different snapshot
"""
url = "https://pypi.org/project/0805nexter"
loader = PyPILoader(url)
visit1_actual_load_status = loader.load()
visit1_stats = get_stats(loader.storage)
expected_snapshot_id = "ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a"
assert visit1_actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
assert_last_visit_matches(loader.storage, url, status="full", type="pypi")
assert {
"content": 6,
"directory": 4,
"origin": 1,
"origin_visit": 1,
"person": 1,
"release": 0,
"revision": 2,
"skipped_content": 0,
"snapshot": 1,
} == visit1_stats
# Reset internal state
loader._info = None
visit2_actual_load_status = loader.load()
visit2_stats = get_stats(loader.storage)
assert visit2_actual_load_status["status"] == "eventful"
expected_snapshot_id2 = "2e5149a7b0725d18231a37b342e9b7c4e121f283"
assert visit2_actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id2,
}
assert_last_visit_matches(loader.storage, url, status="full", type="pypi")
assert {
"content": 6 + 1, # 1 more content
"directory": 4 + 2, # 2 more directories
"origin": 1,
"origin_visit": 1 + 1,
"person": 1,
"release": 0,
"revision": 2 + 1, # 1 more revision
"skipped_content": 0,
"snapshot": 1 + 1, # 1 more snapshot
} == visit2_stats
expected_contents = map(
hash_to_bytes,
[
"a61e24cdfdab3bb7817f6be85d37a3e666b34566",
"938c33483285fd8ad57f15497f538320df82aeb8",
"a27576d60e08c94a05006d2e6d540c0fdb5f38c8",
"405859113963cb7a797642b45f171d6360425d16",
"e5686aa568fdb1d19d7f1329267082fe40482d31",
"83ecf6ec1114fd260ca7a833a2d165e71258c338",
"92689fa2b7fb4d4fc6fb195bf73a50c87c030639",
],
)
assert list(loader.storage.content_missing_per_sha1(expected_contents)) == []
expected_dirs = map(
hash_to_bytes,
[
"05219ba38bc542d4345d5638af1ed56c7d43ca7d",
"cf019eb456cf6f78d8c4674596f1c9a97ece8f44",
"b178b66bd22383d5f16f4f5c923d39ca798861b4",
"c3a58f8b57433a4b56caaa5033ae2e0931405338",
"e226e7e4ad03b4fc1403d69a18ebdd6f2edd2b3a",
"52604d46843b898f5a43208045d09fcf8731631b",
],
)
assert list(loader.storage.directory_missing(expected_dirs)) == []
# {revision hash: directory hash}
expected_revs = {
hash_to_bytes("4c99891f93b81450385777235a37b5e966dd1571"): hash_to_bytes(
"05219ba38bc542d4345d5638af1ed56c7d43ca7d"
), # noqa
hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"): hash_to_bytes(
"b178b66bd22383d5f16f4f5c923d39ca798861b4"
), # noqa
hash_to_bytes("51247143b01445c9348afa9edfae31bf7c5d86b1"): hash_to_bytes(
"e226e7e4ad03b4fc1403d69a18ebdd6f2edd2b3a"
), # noqa
}
assert list(loader.storage.revision_missing(expected_revs)) == []
expected_branches = {
"releases/1.1.0": {
"target": "4c99891f93b81450385777235a37b5e966dd1571",
"target_type": "revision",
},
"releases/1.2.0": {
"target": "e445da4da22b31bfebb6ffc4383dbf839a074d21",
"target_type": "revision",
},
"releases/1.3.0": {
"target": "51247143b01445c9348afa9edfae31bf7c5d86b1",
"target_type": "revision",
},
"HEAD": {"target": "releases/1.3.0", "target_type": "alias",},
}
expected_snapshot = {
"id": expected_snapshot_id2,
"branches": expected_branches,
}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, url, status="full", type="pypi")
urls = [
m.url
for m in requests_mock_datadir_visits.request_history
if m.url.startswith("https://files.pythonhosted.org")
]
# visited each artifact once across 2 visits
assert len(urls) == len(set(urls))
# release artifact, no new artifact
# {visit full, status uneventful, same snapshot as before}
# release artifact, old artifact with different checksums
# {visit full, status full, new snapshot with shared history and some new
# different history}
# release with multiple sdist artifacts per pypi "version"
# snapshot branch output is different
def test_visit_1_release_with_2_artifacts(swh_config, requests_mock_datadir):
"""With no prior visit, load a pypi project ends up with 1 snapshot
"""
url = "https://pypi.org/project/nexter"
loader = PyPILoader(url)
actual_load_status = loader.load()
expected_snapshot_id = "a27e638a4dad6fbfa273c6ebec1c4bf320fb84c6"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
expected_branches = {
"releases/1.1.0/nexter-1.1.0.zip": {
"target": "4c99891f93b81450385777235a37b5e966dd1571",
"target_type": "revision",
},
"releases/1.1.0/nexter-1.1.0.tar.gz": {
"target": "0bf88f5760cca7665d0af4d6575d9301134fe11a",
"target_type": "revision",
},
}
expected_snapshot = {
"id": expected_snapshot_id,
"branches": expected_branches,
}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, url, status="full", type="pypi")
def test_pypi_artifact_to_revision_id_none():
"""Current loader version should stop soon if nothing can be found
"""
artifact_metadata = {
"digests": {
"sha256": "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec", # noqa
},
}
assert artifact_to_revision_id({}, artifact_metadata) is None
known_artifacts = {
"b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92": {
"original_artifact": {"sha256": "something-irrelevant",},
},
}
assert artifact_to_revision_id(known_artifacts, artifact_metadata) is None
def test_pypi_artifact_to_revision_id_old_loader_version():
"""Current loader version should solve old metadata scheme
"""
artifact_metadata = {
"digests": {
"sha256": "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec", # noqa
}
}
known_artifacts = {
hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"): {
"original_artifact": {"sha256": "something-wrong",},
},
hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"): {
"original_artifact": {
"sha256": "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec", # noqa
},
},
}
assert artifact_to_revision_id(known_artifacts, artifact_metadata) == hash_to_bytes(
"845673bfe8cbd31b1eaf757745a964137e6f9116"
)
def test_pypi_artifact_to_revision_id_current_loader_version():
"""Current loader version should be able to solve current metadata scheme
"""
artifact_metadata = {
"digests": {
"sha256": "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec", # noqa
}
}
known_artifacts = {
hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"): {
"original_artifact": [
{
"checksums": {
"sha256": "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec", # noqa
},
}
],
},
hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"): {
"original_artifact": [{"checksums": {"sha256": "something-wrong"},}],
},
}
assert artifact_to_revision_id(known_artifacts, artifact_metadata) == hash_to_bytes(
"b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"
)
def test_pypi_artifact_to_revision_id_failures():
with pytest.raises(KeyError, match="sha256"):
artifact_metadata = {
"digests": {},
}
assert artifact_to_revision_id({}, artifact_metadata)
with pytest.raises(KeyError, match="digests"):
artifact_metadata = {
"something": "wrong",
}
assert artifact_to_revision_id({}, artifact_metadata)
def test_pypi_artifact_with_no_intrinsic_metadata(swh_config, requests_mock_datadir):
"""Skip artifact with no intrinsic metadata during ingestion
"""
url = "https://pypi.org/project/upymenu"
loader = PyPILoader(url)
actual_load_status = loader.load()
expected_snapshot_id = "1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"
assert actual_load_status == {
"status": "eventful",
"snapshot_id": expected_snapshot_id,
}
# no branch as one artifact without any intrinsic metadata
expected_snapshot = {"id": expected_snapshot_id, "branches": {}}
check_snapshot(expected_snapshot, loader.storage)
assert_last_visit_matches(loader.storage, url, status="full", type="pypi")
diff --git a/swh/loader/tests/__init__.py b/swh/loader/tests/__init__.py
index 7b55abd..78a334c 100644
--- a/swh/loader/tests/__init__.py
+++ b/swh/loader/tests/__init__.py
@@ -1,31 +1,79 @@
# Copyright (C) 2018-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import os
import subprocess
from pathlib import PosixPath
from typing import Optional, Union
+from swh.model.model import OriginVisitStatus
+
+from swh.storage.algos.origin import origin_get_latest_visit_status
+
+
+def assert_last_visit_matches(
+ storage,
+ url: str,
+ status: str,
+ type: Optional[str] = None,
+ snapshot: Optional[bytes] = None,
+) -> OriginVisitStatus:
+ """This retrieves the last visit and visit_status which are expected to exist.
+
+ This also checks that the {visit|visit_status} have their respective properties
+ correctly set.
+
+ This returns the last visit_status for that given origin.
+
+ Args:
+ url: Origin url
+ status: Check that the visit status has the given status
+ type: Check that the returned visit has the given type
+ snapshot: Check that the visit status points to the given snapshot
+
+ Raises:
+ AssertionError in case visit or visit status is not found, or any of the type,
+ status and snapshot mismatch
+
+ Returns:
+ the visit status for further check during the remaining part of the test.
+
+ """
+ visit_and_status = origin_get_latest_visit_status(storage, url)
+ assert visit_and_status is not None, f"Origin {url} has no visits"
+ visit, visit_status = visit_and_status
+ if type:
+ assert visit.type == type, f"Visit has type {visit.type} instead of {type}"
+ assert (
+ visit_status.status == status
+ ), f"Visit_status has status {visit_status.status} instead of {status}"
+ if snapshot is not None:
+ assert visit_status.snapshot is not None
+ assert visit_status.snapshot == snapshot, (
+ f"Visit_status points to snapshot {visit_status.snapshot.hex()} "
+ f"instead of {snapshot.hex()}"
+ )
+ return visit_status
def prepare_repository_from_archive(
archive_path: str,
filename: Optional[str] = None,
tmp_path: Union[PosixPath, str] = "/tmp",
) -> str:
"""Given an existing archive_path, uncompress it.
Returns a file repo url which can be used as origin url.
This does not deal with the case where the archive passed along does not exist.
"""
if not isinstance(tmp_path, str):
tmp_path = str(tmp_path)
# uncompress folder/repositories/dump for the loader to ingest
subprocess.check_output(["tar", "xf", archive_path, "-C", tmp_path])
# build the origin url (or some derivative form)
_fname = filename if filename else os.path.basename(archive_path)
repo_url = f"file://{tmp_path}/{_fname}"
return repo_url
diff --git a/swh/loader/tests/common.py b/swh/loader/tests/common.py
deleted file mode 100644
index 97f9401..0000000
--- a/swh/loader/tests/common.py
+++ /dev/null
@@ -1,53 +0,0 @@
-# Copyright (C) 2020 The Software Heritage developers
-# See the AUTHORS file at the top-level directory of this distribution
-# License: GNU General Public License version 3, or any later version
-# See top-level LICENSE file for more information
-
-from typing import Optional
-
-from swh.model.model import OriginVisitStatus
-from swh.storage.algos.origin import origin_get_latest_visit_status
-
-
-def assert_last_visit_matches(
- storage,
- url: str,
- status: str,
- type: Optional[str] = None,
- snapshot: Optional[bytes] = None,
-) -> OriginVisitStatus:
- """This retrieves the last visit and visit_status which are expected to exist.
-
- This also checks that the {visit|visit_status} have their respective properties
- correctly set.
-
- This returns the last visit_status for that given origin.
-
- Args:
- url: Origin url
- status: Check that the visit status has the given status
- type: Check that the returned visit has the given type
- snapshot: Check that the visit status points to the given snapshot
-
- Raises:
- AssertionError in case visit or visit status is not found, or any of the type,
- status and snapshot mismatch
-
- Returns:
- the visit status for further check during the remaining part of the test.
-
- """
- visit_and_status = origin_get_latest_visit_status(storage, url)
- assert visit_and_status is not None, f"Origin {url} has no visits"
- visit, visit_status = visit_and_status
- if type:
- assert visit.type == type, f"Visit has type {visit.type} instead of {type}"
- assert (
- visit_status.status == status
- ), f"Visit_status has status {visit_status.status} instead of {status}"
- if snapshot:
- assert visit_status.snapshot == snapshot, (
- "Visit_status points to snapshot {visit_status.snapshot!r} "
- f"instead of {snapshot!r}"
- )
- return visit_status
diff --git a/swh/loader/tests/test_common.py b/swh/loader/tests/test_common.py
deleted file mode 100644
index 4cf31b7..0000000
--- a/swh/loader/tests/test_common.py
+++ /dev/null
@@ -1,118 +0,0 @@
-# Copyright (C) 2019-2020 The Software Heritage developers
-# See the AUTHORS file at the top-level directory of this distribution
-# License: GNU General Public License version 3, or any later version
-# See top-level LICENSE file for more information
-
-import datetime
-import pytest
-
-from swh.loader.tests.common import assert_last_visit_matches
-from swh.model.model import OriginVisit, OriginVisitStatus
-from swh.model.hashutil import hash_to_bytes
-
-
-ORIGIN_VISIT = OriginVisit(
- origin="some-url",
- visit=1,
- date=datetime.datetime.now(tz=datetime.timezone.utc),
- type="archive",
-)
-
-
-ORIGIN_VISIT_STATUS = OriginVisitStatus(
- origin="some-url",
- visit=1,
- date=datetime.datetime.now(tz=datetime.timezone.utc),
- status="full",
- snapshot=hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"),
- metadata=None,
-)
-
-
-@pytest.fixture
-def mock_storage(mocker):
- mock_storage = mocker.patch(
- "swh.loader.tests.common.origin_get_latest_visit_status"
- )
- mock_storage.return_value = ORIGIN_VISIT, ORIGIN_VISIT_STATUS
- return mock_storage
-
-
-def test_assert_last_visit_matches_raise(mock_storage, mocker):
- """Not finding origin visit_and_statu should raise
-
- """
- # overwrite so we raise because we do not find the right visit
- mock_storage.return_value = None
-
- with pytest.raises(AssertionError, match="Origin url has no visits"):
- assert_last_visit_matches(mock_storage, "url", status="full")
-
- assert mock_storage.called is True
-
-
-def test_assert_last_visit_matches_wrong_status(mock_storage, mocker):
- """Wrong visit detected should raise AssertionError
-
- """
- expected_status = "partial"
- assert ORIGIN_VISIT_STATUS.status != expected_status
- with pytest.raises(AssertionError, match="Visit_status has status"):
- assert_last_visit_matches(mock_storage, "url", status=expected_status)
-
- assert mock_storage.called is True
-
-
-def test_assert_last_visit_matches_wrong_type(mock_storage, mocker):
- """Wrong visit detected should raise AssertionError
-
- """
- expected_type = "git"
- assert ORIGIN_VISIT.type != expected_type
- with pytest.raises(AssertionError, match="Visit has type"):
- assert_last_visit_matches(
- mock_storage,
- "url",
- status=ORIGIN_VISIT_STATUS.status,
- type=expected_type, # mismatched type will raise
- )
-
- assert mock_storage.called is True
-
-
-def test_assert_last_visit_matches_wrong_snapshot(mock_storage, mocker):
- """Wrong visit detected should raise AssertionError
-
- """
- expected_snapshot_id = hash_to_bytes("e92cc0710eb6cf9efd5b920a8453e1e07157b6cd")
- assert ORIGIN_VISIT_STATUS.snapshot != expected_snapshot_id
-
- with pytest.raises(AssertionError, match="Visit_status points to snapshot"):
- assert_last_visit_matches(
- mock_storage,
- "url",
- status=ORIGIN_VISIT_STATUS.status,
- snapshot=expected_snapshot_id, # mismatched snapshot will raise
- )
-
- assert mock_storage.called is True
-
-
-def test_assert_last_visit_matches(mock_storage, mocker):
- """Correct visit detected should return the visit_status
-
- """
- visit_type = ORIGIN_VISIT.type
- visit_status = ORIGIN_VISIT_STATUS.status
- visit_snapshot = ORIGIN_VISIT_STATUS.snapshot
-
- actual_visit_status = assert_last_visit_matches(
- mock_storage,
- "url",
- type=visit_type,
- status=visit_status,
- snapshot=visit_snapshot,
- )
-
- assert actual_visit_status == ORIGIN_VISIT_STATUS
- assert mock_storage.called is True
diff --git a/swh/loader/tests/test_init.py b/swh/loader/tests/test_init.py
index 4a9845c..9192f61 100644
--- a/swh/loader/tests/test_init.py
+++ b/swh/loader/tests/test_init.py
@@ -1,50 +1,158 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
+import datetime
+import pytest
+
import os
import subprocess
-import pytest
+from swh.loader.tests import prepare_repository_from_archive, assert_last_visit_matches
+from swh.model.model import OriginVisit, OriginVisitStatus
+from swh.model.hashutil import hash_to_bytes
+
+
+ORIGIN_VISIT = OriginVisit(
+ origin="some-url",
+ visit=1,
+ date=datetime.datetime.now(tz=datetime.timezone.utc),
+ type="archive",
+)
+
+
+ORIGIN_VISIT_STATUS = OriginVisitStatus(
+ origin="some-url",
+ visit=1,
+ date=datetime.datetime.now(tz=datetime.timezone.utc),
+ status="full",
+ snapshot=hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"),
+ metadata=None,
+)
+
+
+@pytest.fixture
+def mock_storage(mocker):
+ mock_storage = mocker.patch("swh.loader.tests.origin_get_latest_visit_status")
+ mock_storage.return_value = ORIGIN_VISIT, ORIGIN_VISIT_STATUS
+ return mock_storage
+
+
+def test_assert_last_visit_matches_raise(mock_storage, mocker):
+ """Not finding origin visit_and_statu should raise
+
+ """
+ # overwrite so we raise because we do not find the right visit
+ mock_storage.return_value = None
+
+ with pytest.raises(AssertionError, match="Origin url has no visits"):
+ assert_last_visit_matches(mock_storage, "url", status="full")
+
+ assert mock_storage.called is True
+
+
+def test_assert_last_visit_matches_wrong_status(mock_storage, mocker):
+ """Wrong visit detected should raise AssertionError
+
+ """
+ expected_status = "partial"
+ assert ORIGIN_VISIT_STATUS.status != expected_status
+ with pytest.raises(AssertionError, match="Visit_status has status"):
+ assert_last_visit_matches(mock_storage, "url", status=expected_status)
+
+ assert mock_storage.called is True
+
+
+def test_assert_last_visit_matches_wrong_type(mock_storage, mocker):
+ """Wrong visit detected should raise AssertionError
+
+ """
+ expected_type = "git"
+ assert ORIGIN_VISIT.type != expected_type
+ with pytest.raises(AssertionError, match="Visit has type"):
+ assert_last_visit_matches(
+ mock_storage,
+ "url",
+ status=ORIGIN_VISIT_STATUS.status,
+ type=expected_type, # mismatched type will raise
+ )
+
+ assert mock_storage.called is True
+
+
+def test_assert_last_visit_matches_wrong_snapshot(mock_storage, mocker):
+ """Wrong visit detected should raise AssertionError
+
+ """
+ expected_snapshot_id = hash_to_bytes("e92cc0710eb6cf9efd5b920a8453e1e07157b6cd")
+ assert ORIGIN_VISIT_STATUS.snapshot != expected_snapshot_id
+
+ with pytest.raises(AssertionError, match="Visit_status points to snapshot"):
+ assert_last_visit_matches(
+ mock_storage,
+ "url",
+ status=ORIGIN_VISIT_STATUS.status,
+ snapshot=expected_snapshot_id, # mismatched snapshot will raise
+ )
+
+ assert mock_storage.called is True
+
+
+def test_assert_last_visit_matches(mock_storage, mocker):
+ """Correct visit detected should return the visit_status
+
+ """
+ visit_type = ORIGIN_VISIT.type
+ visit_status = ORIGIN_VISIT_STATUS.status
+ visit_snapshot = ORIGIN_VISIT_STATUS.snapshot
+
+ actual_visit_status = assert_last_visit_matches(
+ mock_storage,
+ "url",
+ type=visit_type,
+ status=visit_status,
+ snapshot=visit_snapshot,
+ )
-from swh.loader.tests import prepare_repository_from_archive
+ assert actual_visit_status == ORIGIN_VISIT_STATUS
+ assert mock_storage.called is True
def test_prepare_repository_from_archive_failure():
# does not deal with inexistent archive so raise
assert os.path.exists("unknown-archive") is False
with pytest.raises(subprocess.CalledProcessError, match="exit status 2"):
prepare_repository_from_archive("unknown-archive")
def test_prepare_repository_from_archive(datadir, tmp_path):
archive_name = "0805nexter-1.1.0"
archive_path = os.path.join(str(datadir), f"{archive_name}.tar.gz")
assert os.path.exists(archive_path) is True
tmp_path = str(tmp_path) # deals with path string
repo_url = prepare_repository_from_archive(
archive_path, filename=archive_name, tmp_path=tmp_path
)
expected_uncompressed_archive_path = os.path.join(tmp_path, archive_name)
assert repo_url == f"file://{expected_uncompressed_archive_path}"
assert os.path.exists(expected_uncompressed_archive_path)
def test_prepare_repository_from_archive_no_filename(datadir, tmp_path):
archive_name = "0805nexter-1.1.0"
archive_path = os.path.join(str(datadir), f"{archive_name}.tar.gz")
assert os.path.exists(archive_path) is True
# deals with path as posix path (for tmp_path)
repo_url = prepare_repository_from_archive(archive_path, tmp_path=tmp_path)
tmp_path = str(tmp_path)
expected_uncompressed_archive_path = os.path.join(tmp_path, archive_name)
expected_repo_url = os.path.join(tmp_path, f"{archive_name}.tar.gz")
assert repo_url == f"file://{expected_repo_url}"
# passing along the filename does not influence the on-disk extraction
# just the repo-url computation
assert os.path.exists(expected_uncompressed_archive_path)