Skip to content

fix(dbgap): dbgap accession parser #290

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
WilsonnnTan wants to merge 3 commits into
base: master
Choose a base branch
from
+67 −1
Open

fix(dbgap): dbgap accession parser #290

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ea416a8
fix: dbgap accession parser
WilsonnnTan Feb 9, 2026
8158a28
Merge branch 'master' into fix/dbgap-accession-parser
k-burt-uch Apr 24, 2026
1bf2e62
test: add test cases for get_dbgap_accession_as_parts util
WilsonnnTan Apr 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion gen3/external/nih/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,8 @@
# For more details about this regex, see the function that uses it
DBGAP_ACCESSION_REGEX = (
"(?P<phsid>phs(?P<phsid_number>[0-9]+))"
"(.(?P<participant_set>p(?P<participant_set_number>[0-9]+))){0,1}"
"(.(?P<version>v(?P<version_number>[0-9]+))){0,1}"
"(.(?P<participant_set>p(?P<participant_set_number>[0-9]+))){0,1}"
Comment thread
WilsonnnTan marked this conversation as resolved.
"(.(?P<consent>c(?P<consent_number>[0-9]+)+)){0,1}"
)

Expand Down
66 changes: 66 additions & 0 deletions tests/test_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
import pytest

from gen3.external.nih.utils import get_dbgap_accession_as_parts


@pytest.mark.parametrize("test_input, expected", [
(
'phs000123',
{
'phsid': 'phs000123',
'phsid_number': '000123',
'version': '',
'version_number': '',
'participant_set': '',
'participant_set_number': '',
'consent': '',
'consent_number': ''
}
),
(
'phs000123.p1.c3',
{
'phsid': 'phs000123',
'phsid_number': '000123',
'version': '',
'version_number': '',
'participant_set': 'p1',
'participant_set_number': '1',
'consent': 'c3',
'consent_number': '3'
}
),
(
'phs000123.v3.c3',
{
'phsid': 'phs000123',
'phsid_number': '000123',
'version': 'v3',
'version_number': '3',
'participant_set': '',
'participant_set_number': '',
'consent': 'c3',
'consent_number': '3'
}
),
(
'phs000123.v3.p1.c3',
{
'phsid': 'phs000123',
'phsid_number': '000123',
'version': 'v3',
'version_number': '3',
'participant_set': 'p1',
'participant_set_number': '1',
'consent': 'c3',
'consent_number': '3'
}
),

])
def test_get_dbgap_accession_as_parts(test_input, expected):
"""
Test dbgap accession parsing works and outputs expected fields and values.
"""

assert get_dbgap_accession_as_parts(test_input) == expected