def test_dataset3():
import batch_validator
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/library_batch_full_test.tsv")
assert (passes_validation == True)
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/smalltest.tsv")
assert (passes_validation == True)
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/smalltest_failing.tsv")
assert (passes_validation == True)
def test_datat2():
import batch_validator
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/GNPS00001_output_batch.tsv")
assert (passes_validation == True)
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/GNPS00002_output_batch.tsv")
assert (passes_validation == True)
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/GNPS00003_output_batch.tsv")
assert (passes_validation == False)
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/GNPS00004_output_batch.tsv")
assert (passes_validation == False)
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/GNPS00005_output_batch.tsv")
assert (passes_validation == False)
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/GNPS00006_output_batch.tsv")
assert (passes_validation == False)
def validatebatchpost():
request_file = request.files['file']
#Invalid File Types
if not allowed_file_metadata(request_file.filename):
error_dict = {}
error_dict["header"] = "Incorrect File Type"
error_dict["line_number"] = "N/A"
error_dict["error_string"] = "Please provide a tab separated file"
validation_dict = {}
validation_dict["status"] = False
validation_dict["errors"] = [error_dict]
validation_dict["stats"] = []
validation_dict["stats"].append({"type":"total_rows", "value": 0})
validation_dict["stats"].append({"type":"valid_rows", "value": 0})
return json.dumps(validation_dict)
local_filename = os.path.join(app.config['UPLOAD_FOLDER'], str(uuid.uuid4()))
request_file.save(local_filename)
"""Trying stuff out with pandas"""
metadata_df = pd.read_csv(local_filename, sep="\t")
metadata_df.to_csv(local_filename, index=False, sep="\t")
pass_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(local_filename)
validation_dict = {}
validation_dict["status"] = pass_validation
validation_dict["errors"] = errors_list
validation_dict["stats"] = []
validation_dict["stats"].append({"type":"total_rows", "value":total_rows})
validation_dict["stats"].append({"type":"valid_rows", "value":len(valid_rows)})
return json.dumps(validation_dict)
def test_dataset4():
import batch_validator
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/sarcophyton.tsv")
assert (passes_validation == True)
def test_datat1_failure():
import batch_validator
passes_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
"reference_data/bile_acid_ref_failure.tsv")
assert (passes_validation == False)
def validatebatchpost():
request_file = request.files['file']
#Invalid File Types
if not allowed_file_metadata(request_file.filename):
error_dict = {}
error_dict["header"] = "Incorrect File Type"
error_dict["line_number"] = "N/A"
error_dict["error_string"] = "Please provide a tab separated file"
validation_dict = {}
validation_dict["status"] = False
validation_dict["errors"] = [error_dict]
validation_dict["stats"] = []
validation_dict["stats"].append({"type": "total_rows", "value": 0})
validation_dict["stats"].append({"type": "valid_rows", "value": 0})
return json.dumps(validation_dict)
local_filename = os.path.join(app.config['UPLOAD_FOLDER'],
str(uuid.uuid4()))
request_file.save(local_filename)
truncate_value = 2000
if "full" in request.values:
truncate_value = 50000
"""Trying stuff out with pandas"""
try:
metadata_df = pd.read_csv(local_filename,
keep_default_na=False,
sep="\t")
metadata_df = metadata_df.truncate(after=truncate_value)
metadata_df.to_csv(local_filename,
index=False,
sep="\t",
encoding='ascii')
except:
error_dict = {}
error_dict["header"] = "Error Reading Data"
error_dict["line_number"] = "N/A"
error_dict["error_string"] = "Please fix your file"
validation_dict = {}
validation_dict["status"] = False
validation_dict["errors"] = [error_dict]
validation_dict["stats"] = []
validation_dict["stats"].append({"type": "total_rows", "value": 0})
validation_dict["stats"].append({"type": "valid_rows", "value": 0})
return json.dumps(validation_dict)
pass_validation, failures, errors_list, valid_rows, total_rows = batch_validator.perform_batch_validation(
local_filename)
validation_dict = {}
validation_dict["status"] = pass_validation
validation_dict["errors"] = errors_list
validation_dict["stats"] = []
validation_dict["stats"].append({
"type": "total_rows",
"value": total_rows
})
validation_dict["stats"].append({
"type": "valid_rows",
"value": len(valid_rows)
})
return json.dumps(validation_dict)