Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
S
swh-indexer
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Platform
Development
swh-indexer
Merge requests
!511
ExtrinsicMetadataIndexer: Add workaround for mistakenly escaped origin URLs
Code
Review changes
Check out branch
Download
Patches
Plain diff
Merged
ExtrinsicMetadataIndexer: Add workaround for mistakenly escaped origin URLs
escaped-url
into
master
Overview
6
Commits
5
Pipelines
5
Changes
2
Merged
vlorentz
requested to merge
escaped-url
into
master
10 months ago
Overview
6
Commits
5
Pipelines
5
Changes
2
Expand
Fixes
#4738 (closed)
for existing metadata objects
0
0
Merge request reports
Compare
master
version 4
f733942a
10 months ago
version 3
b5f35e8e
10 months ago
version 2
31f3da7e
10 months ago
version 1
6a6e8906
10 months ago
master (base)
and
latest version
latest version
acda91c1
5 commits,
10 months ago
version 4
f733942a
4 commits,
10 months ago
version 3
b5f35e8e
3 commits,
10 months ago
version 2
31f3da7e
2 commits,
10 months ago
version 1
6a6e8906
1 commit,
10 months ago
2 files
+
73
−
4
Inline
Compare changes
Side-by-side
Inline
Show whitespace changes
Show one file at a time
Files
2
Search (e.g. *.vue) (Ctrl+P)
swh/indexer/tests/test_metadata.py
+
47
−
1
Options
# Copyright (C) 2017-202
2
The Software Heritage developers
# Copyright (C) 2017-202
4
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
from
unittest.mock
import
call
import
attr
@@ -350,6 +351,51 @@ class TestMetadata:
)
assert
results
==
[]
def
test_extrinsic_metadata_indexer_thirdparty_deposit_unescaped_origin
(
self
,
mocker
):
"""
Tests the workaround for REMD objects created from `incorrectly parsing SWHID
<https://gitlab.softwareheritage.org/swh/devel/swh-model/-/merge_requests/348>`_
"""
origin
=
"
https://cran.r-project.org/package=airGR
"
metadata_indexer
=
ExtrinsicMetadataIndexer
(
config
=
DIRECTORY_METADATA_CONFIG
)
metadata_indexer
.
catch_exceptions
=
False
metadata_indexer
.
storage
=
mocker
.
patch
.
object
(
metadata_indexer
,
"
storage
"
)
metadata_indexer
.
storage
.
origin_get_by_sha1
.
return_value
=
[{
"
url
"
:
origin
}]
tool
=
metadata_indexer
.
idx_storage
.
indexer_configuration_get
(
{
f
"
tool_
{
k
}
"
:
v
for
(
k
,
v
)
in
TRANSLATOR_TOOL
.
items
()}
)
assert
tool
is
not
None
assert
metadata_indexer
.
process_journal_objects
(
{
"
raw_extrinsic_metadata
"
:
[
attr
.
evolve
(
DEPOSIT_REMD
,
fetcher
=
attr
.
evolve
(
DEPOSIT_REMD
.
fetcher
,
name
=
"
swh-deposit
"
,
),
origin
=
"
https://cran.r-project.org/package%3DairGR
"
,
discovery_date
=
datetime
.
datetime
(
2024
,
5
,
13
,
8
,
4
,
8
,
tzinfo
=
datetime
.
timezone
.
utc
),
).
to_dict
(),
]
}
)
==
{
"
status
"
:
"
uneventful
"
,
"
origin_extrinsic_metadata:add
"
:
0
}
assert
metadata_indexer
.
storage
.
method_calls
==
[
call
.
origin_get_by_sha1
([
hashlib
.
sha1
(
origin
.
encode
()).
digest
()])
]
results
=
list
(
metadata_indexer
.
idx_storage
.
origin_extrinsic_metadata_get
([
origin
])
)
assert
results
==
[]
def
test_extrinsic_metadata_indexer_nonforge_authority
(
self
,
mocker
):
"""
Early abort on non-forge authorities
"""
metadata_indexer
=
ExtrinsicMetadataIndexer
(
config
=
DIRECTORY_METADATA_CONFIG
)
Loading