def test_export_table(self):
header = ['column1', 'column2']
rows = [['row1_v1', 'row1_v2'], ['row2_v1', 'row2_v2']]
# test tsv format
response = export_table('test_file', header, rows, file_format='tsv')
self.assertEqual(response.status_code, 200)
self.assertEqual(response.get('content-disposition'),
'attachment; filename="test_file.tsv"')
self.assertEqual(
response.content,
'\n'.join(['\t'.join(row) for row in [header] + rows]) + '\n')
# test Excel format
response = export_table('test_file', header, rows, file_format='xls')
self.assertEqual(response.status_code, 200)
self.assertEqual(response.get('content-disposition'),
'attachment; filename="test_file.xlsx"')
wb = load_workbook(StringIO(response.content))
worksheet = wb.active
self.assertListEqual([cell.value for cell in worksheet['A']],
['Column1', 'row1_v1', 'row2_v1'])
self.assertListEqual([cell.value for cell in worksheet['B']],
['Column2', 'row1_v2', 'row2_v2'])
self.assertEqual([cell.value for cell in worksheet['C']],
[None, None, None])
# test unknown format
self.assertRaisesRegexp(
ValueError, '.*format.*', lambda: export_table(
'test_file', header, rows, file_format='unknown_format'))
def export_projects_table_handler(request):
file_format = request.GET.get('file_format', 'tsv')
projects_by_guid = _get_projects_json(request.user)
project_categories_by_guid = _retrieve_project_categories_by_guid(
projects_by_guid.keys())
header = [
'Project',
'Description',
'Categories',
'Created Date',
'Families',
'Individuals',
'Tagged Variants',
'WES Samples',
'WGS Samples',
'RNA Samples',
]
header.extend(
[label for key, label in Family.ANALYSIS_STATUS_CHOICES if key != 'S'])
rows = []
for project in sorted(projects_by_guid.values(),
key=lambda project: project.get('name') or project.
get('deprecatedProjectId')):
project_categories = ', '.join([
project_categories_by_guid[category_guid]['name']
for category_guid in project.get('projectCategoryGuids')
])
row = [
project.get('name') or project.get('deprecatedProjectId'),
project.get('description'),
project_categories,
project.get('createdDate'),
project.get('numFamilies'),
project.get('numIndividuals'),
project.get('numVariantTags'),
project.get('sampleTypeCounts', {}).get(Sample.SAMPLE_TYPE_WES, 0),
project.get('sampleTypeCounts', {}).get(Sample.SAMPLE_TYPE_WGS, 0),
project.get('sampleTypeCounts', {}).get(Sample.SAMPLE_TYPE_RNA, 0),
]
row.extend([
project.get('analysisStatusCounts', {}).get(key, 0)
for key, _ in Family.ANALYSIS_STATUS_CHOICES if key != 'S'
])
rows.append(row)
try:
response = export_table('projects', header, rows, file_format)
except ValueError as e:
response = create_json_response({'error': str(e)}, status=400)
return response
def export_variants_handler(request, search_hash):
results_model = VariantSearchResults.objects.get(search_hash=search_hash)
_check_results_permission(results_model, request.user)
families = results_model.families.all()
family_ids_by_guid = {family.guid: family.family_id for family in families}
variants, _ = get_es_variants(results_model, page=1, load_all=True)
variants = _flatten_variants(variants)
json, variants_to_saved_variants = _get_saved_variants(variants, families)
max_families_per_variant = max([len(variant['familyGuids']) for variant in variants])
max_samples_per_variant = max([len(variant['genotypes']) for variant in variants])
rows = []
for variant in variants:
row = [_get_field_value(variant, config) for config in VARIANT_EXPORT_DATA]
for i in range(max_families_per_variant):
family_guid = variant['familyGuids'][i] if i < len(variant['familyGuids']) else ''
variant_guid = variants_to_saved_variants.get(variant['variantId'], {}).get(family_guid, '')
family_tags = {
'family_id': family_ids_by_guid.get(family_guid),
'tags': [tag for tag in json['variantTagsByGuid'].values() if variant_guid in tag['variantGuids']],
'notes': [note for note in json['variantNotesByGuid'].values() if variant_guid in note['variantGuids']],
}
row += [_get_field_value(family_tags, config) for config in VARIANT_FAMILY_EXPORT_DATA]
genotypes = variant['genotypes'].values()
for i in range(max_samples_per_variant):
if i < len(genotypes):
row.append('{sampleId}:{numAlt}:{gq}:{ab}'.format(**genotypes[i]))
else:
row.append('')
rows.append(row)
header = [config['header'] for config in VARIANT_EXPORT_DATA]
for i in range(max_families_per_variant):
header += ['{}_{}'.format(config['header'], i+1) for config in VARIANT_FAMILY_EXPORT_DATA]
header += ['sample_{}:num_alt_alleles:gq:ab'.format(i+1) for i in range(max_samples_per_variant)]
file_format = request.GET.get('file_format', 'tsv')
return export_table('search_results_{}'.format(search_hash), header, rows, file_format, titlecase_header=False)
def test_export_table(self):
header = ['column1', 'column2']
rows = [['row1_v1\xe2', 'row1_v2'], ['row2_v1', 'row2_v2']]
# test tsv format
response = export_table('test_file', header, rows, file_format='tsv')
self.assertEqual(response.status_code, 200)
self.assertEqual(response.get('content-disposition'),
'attachment; filename="test_file.tsv"')
self.assertEqual(
response.content,
('\n'.join(['\t'.join(row)
for row in [header] + rows]) + '\n').encode('utf-8'))
# test Excel format
response = export_table('test_file', header, rows, file_format='xls')
self.assertEqual(response.status_code, 200)
self.assertEqual(response.get('content-disposition'),
'attachment; filename="test_file.xlsx"')
wb = load_workbook(BytesIO(response.content))
worksheet = wb.active
self.assertListEqual([cell.value for cell in worksheet['A']],
['Column1', 'row1_v1\xe2', 'row2_v1'])
self.assertListEqual([cell.value for cell in worksheet['B']],
['Column2', 'row1_v2', 'row2_v2'])
self.assertEqual([cell.value for cell in worksheet['C']],
[None, None, None])
# test invalid input
with self.assertRaises(ValueError) as cm:
export_table('test_file',
header,
rows,
file_format='unknown_format')
self.assertEqual(str(cm.exception),
'Invalid file_format: unknown_format')
with self.assertRaises(ValueError) as cm:
export_table('test_file', ['column1'], rows)
self.assertEqual(
str(cm.exception),
'len(header) != len(row): 1 != 2\ncolumn1\nrow1_v1\xe2,row1_v2')