}
MODEL_USER_FIELDS = MAIN_USER_FIELDS + list(BOOL_USER_FIELDS.keys())
COMPUTED_USER_FIELDS = {
'is_anvil':
lambda user, is_anvil=None, **kwargs: is_anvil_authenticated(user)
if is_anvil is None else is_anvil,
'display_name':
lambda user, **kwargs: user.get_full_name(),
'is_analyst':
lambda user, analyst_users=None, **kwargs: user in analyst_users
if analyst_users is not None else user_is_analyst(user),
'is_data_manager':
lambda user, **kwargs: user_is_data_manager(user),
'is_pm':
lambda user, pm_users=None, **kwargs: user in pm_users
if pm_users is not None else user_is_pm(user),
}
DEFAULT_USER = {_to_camel_case(field): '' for field in MAIN_USER_FIELDS}
DEFAULT_USER.update(
{_to_camel_case(field): val
for field, val in BOOL_USER_FIELDS.items()})
DEFAULT_USER.update(
{_to_camel_case(field): False
for field in COMPUTED_USER_FIELDS.keys()})
def _get_json_for_user(user,
is_anvil=None,
fields=None,
analyst_users=None,
'is_superuser': False,
'is_active': True,
}
MODEL_USER_FIELDS = MAIN_USER_FIELDS + list(BOOL_USER_FIELDS.keys())
COMPUTED_USER_FIELDS = {
'is_anvil':
lambda user, is_anvil=None: is_anvil_authenticated(user)
if is_anvil is None else is_anvil,
'display_name':
lambda user, **kwargs: user.get_full_name(),
'is_analyst':
lambda user, **kwargs: user_is_analyst(user),
'is_data_manager':
lambda user, **kwargs: user_is_data_manager(user),
'is_pm':
lambda user, **kwargs: user_is_pm(user),
}
DEFAULT_USER = {_to_camel_case(field): '' for field in MAIN_USER_FIELDS}
DEFAULT_USER.update(
{_to_camel_case(field): val
for field, val in BOOL_USER_FIELDS.items()})
DEFAULT_USER.update(
{_to_camel_case(field): False
for field in COMPUTED_USER_FIELDS.keys()})
def _get_json_for_user(user, is_anvil=None, fields=None):
"""Returns JSON representation of the given User object
Args:
def parse_pedigree_table(parsed_file, filename, user, project=None):
"""Validates and parses pedigree information from a .fam, .tsv, or Excel file.
Args:
parsed_file (array): The parsed output from the raw file.
filename (string): The original filename - used to determine the file format based on the suffix.
user (User): (optional) Django User object
project (Project): (optional) Django Project object
Return:
A 3-tuple that contains:
(
json_records (list): list of dictionaries, with each dictionary containing info about
one of the individuals in the input data
errors (list): list of error message strings
warnings (list): list of warning message strings
)
"""
json_records = []
errors = []
warnings = []
is_merged_pedigree_sample_manifest = False
# parse rows from file
try:
rows = [
row for row in parsed_file[1:]
if row and not (row[0] or '').startswith('#')
]
header_string = str(parsed_file[0])
is_datstat_upload = 'DATSTAT' in header_string
is_merged_pedigree_sample_manifest = "do not modify" in header_string.lower(
) and "Broad" in header_string
if is_merged_pedigree_sample_manifest:
if not user_is_pm(user):
raise ValueError('Unsupported file format')
# the merged pedigree/sample manifest has 3 header rows, so use the known header and skip the next 2 rows.
headers = rows[:2]
rows = rows[2:]
# validate manifest_header_row1
expected_header_columns = MergedPedigreeSampleManifestConstants.MERGED_PEDIGREE_SAMPLE_MANIFEST_COLUMN_NAMES
expected_header_1_columns = expected_header_columns[:4] + [
"Alias", "Alias"
] + expected_header_columns[6:]
expected = expected_header_1_columns
actual = headers[0]
if expected == actual:
expected = expected_header_columns[4:6]
actual = headers[1][4:6]
unexpected_header_columns = '|'.join(
difflib.unified_diff(expected, actual)).split('\n')[3:]
if unexpected_header_columns:
raise ValueError(
"Expected vs. actual header columns: {}".format(
"\t".join(unexpected_header_columns)))
header = expected_header_columns
else:
if _is_header_row(header_string):
header_row = parsed_file[0]
else:
header_row = next(
(row for row in parsed_file[1:] if row[0].startswith('#')
and _is_header_row(','.join(row))), [
'family_id', 'individual_id', 'paternal_id',
'maternal_id', 'sex', 'affected'
])
header = [(field or '').strip('#') for field in header_row]
for i, row in enumerate(rows):
if len(row) != len(header):
raise ValueError(
"Row {} contains {} columns: {}, while header contains {}: {}"
.format(i + 1, len(row), ', '.join(row), len(header),
', '.join(header)))
rows = [dict(zip(header, row)) for row in rows]
except Exception as e:
errors.append("Error while parsing file: %(filename)s. %(e)s" %
locals())
return json_records, errors, warnings
# convert to json and validate
try:
if is_merged_pedigree_sample_manifest:
logger.info("Parsing merged pedigree-sample-manifest file")
rows, sample_manifest_rows, kit_id = _parse_merged_pedigree_sample_manifest_format(
rows)
elif is_datstat_upload:
logger.info("Parsing datstat export file")
rows = _parse_datstat_export_format(rows)
else:
logger.info("Parsing regular pedigree file")
json_records = _convert_fam_file_rows_to_json(rows)
except Exception as e:
errors.append(
"Error while converting %(filename)s rows to json: %(e)s" %
locals())
return json_records, errors, warnings
errors, warnings = validate_fam_file_records(json_records)
if not errors and is_merged_pedigree_sample_manifest:
_send_sample_manifest(sample_manifest_rows, kit_id, filename,
parsed_file, user, project)
return json_records, errors, warnings
from seqr.models import Individual, IgvSample
from seqr.utils.file_utils import file_iter, does_file_exist
from seqr.views.utils.file_utils import save_uploaded_file
from seqr.views.utils.json_to_orm_utils import get_or_create_model_from_json
from seqr.views.utils.json_utils import create_json_response
from seqr.views.utils.orm_to_json_utils import get_json_for_sample
from seqr.views.utils.permissions_utils import get_project_and_check_permissions, check_project_permissions, \
user_is_data_manager, user_is_pm
from settings import API_LOGIN_REQUIRED_URL
import logging
logger = logging.getLogger(__name__)
pm_or_data_manager_required = user_passes_test(
lambda user: user_is_data_manager(user) or user_is_pm(user),
login_url=API_LOGIN_REQUIRED_URL)
@pm_or_data_manager_required
def receive_igv_table_handler(request, project_guid):
project = get_project_and_check_permissions(project_guid,
request.user,
can_edit=True)
info = []
def _process_alignment_records(rows, **kwargs):
invalid_row = next((row for row in rows if not 2 <= len(row) <= 3),
None)
if invalid_row:
raise ValueError("Must contain 2 or 3 columns: " +