Page Menu
Home
Software Heritage
Search
Configure Global Search
Log In
Files
F7124384
D6750.id24511.diff
No One
Temporary
Actions
View File
Edit File
Delete File
View Transforms
Subscribe
Mute Notifications
Award Token
Flag For Later
Size
5 KB
Subscribers
None
D6750.id24511.diff
View Options
diff --git a/swh/loader/package/debian/loader.py b/swh/loader/package/debian/loader.py
--- a/swh/loader/package/debian/loader.py
+++ b/swh/loader/package/debian/loader.py
@@ -16,8 +16,8 @@
from debian.deb822 import Dsc
from swh.loader.package.loader import BasePackageInfo, PackageLoader, PartialExtID
-from swh.loader.package.utils import download, release_name
-from swh.model.hashutil import hash_to_bytes
+from swh.loader.package.utils import DOWNLOAD_HASHES, download, release_name
+from swh.model.hashutil import ALGORITHMS, hash_to_bytes
from swh.model.model import ObjectType, Person, Release, Sha1Git, TimestampWithTimezone
from swh.storage.interface import StorageInterface
@@ -37,15 +37,14 @@
class DebianFileMetadata:
name = attr.ib(type=str)
"""Filename"""
- sha256 = attr.ib(type=str)
+
size = attr.ib(type=int)
uri = attr.ib(type=str)
"""URL of this specific file"""
- # md5sum is not always available, make it optional
+ # all checksums are not always available, make them optional
+ sha256 = attr.ib(type=str, default="")
md5sum = attr.ib(type=str, default="")
-
- # sha1 is not always available, make it optional
sha1 = attr.ib(type=str, default="")
# Some of the DSC files imported in swh apparently had a Checksums-SHA512
@@ -173,6 +172,9 @@
"""
super().__init__(storage=storage, url=url, max_content_size=max_content_size)
self.packages = packages
+ # add md5 support in swh.model.hashutil.MultiHash
+ ALGORITHMS.add("md5")
+ DOWNLOAD_HASHES.add("md5")
def get_versions(self) -> Sequence[str]:
"""Returns the keys of the packages input (e.g.
@@ -307,9 +309,14 @@
for filename, fileinfo in p_info.files.items():
uri = fileinfo.uri
logger.debug("fileinfo: %s", fileinfo)
- extrinsic_hashes = {"sha256": fileinfo.sha256}
+ if fileinfo.sha256:
+ extrinsic_hashes = {"sha256": fileinfo.sha256}
+ elif fileinfo.sha1:
+ extrinsic_hashes = {"sha1": fileinfo.sha1}
+ else:
+ extrinsic_hashes = {"md5": fileinfo.md5sum}
logger.debug("extrinsic_hashes(%s): %s", filename, extrinsic_hashes)
- filepath, hashes = download(
+ _, hashes = download(
uri, dest=tmpdir, filename=filename, hashes=extrinsic_hashes
)
all_hashes[filename] = hashes
diff --git a/swh/loader/package/debian/tests/test_debian.py b/swh/loader/package/debian/tests/test_debian.py
--- a/swh/loader/package/debian/tests/test_debian.py
+++ b/swh/loader/package/debian/tests/test_debian.py
@@ -287,6 +287,7 @@
assert all_hashes == {
"cicero_0.7.2-3.diff.gz": {
"checksums": {
+ "md5": "a93661b6a48db48d59ba7d26796fc9ce",
"sha1": "0815282053f21601b0ec4adf7a8fe47eace3c0bc",
"sha256": "f039c9642fe15c75bed5254315e2a29f9f2700da0e29d9b0729b3ffc46c8971c", # noqa
},
@@ -299,6 +300,7 @@
},
"cicero_0.7.2-3.dsc": {
"checksums": {
+ "md5": "d5dac83eb9cfc9bb52a15eb618b4670a",
"sha1": "abbec4e8efbbc80278236e1dd136831eac08accd",
"sha256": "35b7f1048010c67adfd8d70e4961aefd8800eb9a83a4d1cc68088da0009d9a03", # noqa
},
@@ -310,6 +312,7 @@
},
"cicero_0.7.2.orig.tar.gz": {
"checksums": {
+ "md5": "4353dede07c5728319ba7f5595a7230a",
"sha1": "a286efd63fe2c9c9f7bb30255c3d6fcdcf390b43",
"sha256": "63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786", # noqa
},
@@ -476,3 +479,44 @@
)
check_snapshot(expected_snapshot, swh_storage)
+
+
+def test_debian_loader_only_md5_sum_in_dsc(swh_storage, requests_mock_datadir):
+
+ packages_per_version = deepcopy(PACKAGES_PER_VERSION)
+ for package_files in packages_per_version.values():
+ for package_data in package_files["files"].values():
+ del package_data["sha256"]
+
+ loader = DebianLoader(swh_storage, URL, packages=packages_per_version)
+
+ actual_load_status = loader.load()
+ expected_snapshot_id = "a83fa5c089b048161f0677b9614a4aae96a6ca18"
+ assert actual_load_status == {
+ "status": "eventful",
+ "snapshot_id": expected_snapshot_id,
+ }
+
+ assert_last_visit_matches(
+ swh_storage,
+ URL,
+ status="full",
+ type="deb",
+ snapshot=hash_to_bytes(expected_snapshot_id),
+ )
+
+ expected_snapshot = Snapshot(
+ id=hash_to_bytes(expected_snapshot_id),
+ branches={
+ b"releases/stretch/contrib/0.7.2-3": SnapshotBranch(
+ target_type=TargetType.RELEASE,
+ target=hash_to_bytes("73e0ede9c21f7074ad1f9c81a774cfcb9e02addf"),
+ ),
+ b"releases/buster/contrib/0.7.2-4": SnapshotBranch(
+ target_type=TargetType.RELEASE,
+ target=hash_to_bytes("9f6d8d868514f991af0d9f5d7173aba1236a5a75"),
+ ),
+ },
+ )
+
+ check_snapshot(expected_snapshot, swh_storage)
File Metadata
Details
Attached
Mime Type
text/plain
Expires
Dec 21 2024, 9:30 AM (11 w, 4 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3229718
Attached To
D6750: debian: Add md5 sum fallback when sha* checksum is missing in metadata
Event Timeline
Log In to Comment