def checkInstitutionRetentionsbyOCLCNumber(event, context):
item_file = handle_files.readFilesFromBucket(event)
csv_read = handle_files.loadCSV(item_file)
csv_read = process_data.retrieveInstitutionRetentionsbyOCLCNumber(
processConfig, csv_read)
handle_files.saveFileToBucket(fileInfo['bucket'],
fileInfo['key'] + "_updated", csv_read)
def process(args):
item_file = handle_files.readFileFromLocal(args.itemFile)
operation = args.operation
output_dir = args.outputDir
# get a token
scope = ['WorldCatMetadataAPI']
try:
oauth_session = make_requests.createOAuthSession(config, scope)
config.update({"oauth-session": oauth_session})
processConfig = config
csv_read = handle_files.loadCSV(item_file)
if operation == "getCurrentOCLCNumbers":
csv_read = process_data.retrieveCurrentOCLCNumbers(processConfig, csv_read)
elif operation == "retrieveMergedOCLCNumbers":
csv_read = process_data.retrieveMergedOCLCNumbers(processConfig, csv_read)
elif operation == "setHoldingsbyOCLCNumber":
csv_read = process_data.setHoldingsbyOCLCNumber(processConfig, csv_read)
elif operation == "deleteHoldingsbyOCLCNumber":
csv_read = process_data.deleteHoldingsbyOCLCNumber(processConfig, csv_read)
elif operation == "addLBDs":
csv_read = process_data.addLBDs(processConfig, csv_read)
return handle_files.saveFileLocal(csv_read, output_dir)
except BaseException as err:
result = 'no access token ' + str(err)
return result
def addLBDs(event, context):
item_file = handle_files.readFilesFromBucket(event)
csv_read = handle_files.loadCSV(item_file)
csv_read = process_data.addLBDs(processConfig, csv_read)
handle_files.saveFileToBucket(fileInfo['bucket'],
fileInfo['key'] + "_updated", csv_read)
return saveFile(bucket, key + "_updated", csv_read)
def deleteHoldingsbyOCLCNumber(event, context):
item_file = handle_files.readFilesFromBucket(event)
csv_read = handle_files.loadCSV(item_file)
csv_read = process_data.deleteHoldingsbyOCLCNumber(processConfig, csv_read)
handle_files.saveFileToBucket(fileInfo['bucket'],
fileInfo['key'] + "_updated", csv_read)
return saveFile(bucket, key + "_updated", csv_read)
def test_retrieveInstitutionRetentionsbyOCLCNumber(mockOAuthSession, getTestConfig, tmpdir, requests_mock):
oclcSymbol = 'CCO'
requests_mock.register_uri('GET', 'https://americas.discovery.api.oclc.org/worldcat/v2/retained-holdings?oclcNumber=776775878&heldBy=' + oclcSymbol, status_code=200, json=retained_bySymbol)
requests_mock.register_uri('GET', 'https://americas.discovery.api.oclc.org/worldcat/v2/retained-holdings?oclcNumber=1702614&heldBy=' + oclcSymbol, status_code=200, json=retained_bySymbol2)
item_file = "oclcNumber\n776775878\n1702614"
csv_read = handle_files.loadCSV(item_file)
getTestConfig.update({"oauth-session": mockOAuthSession})
result = process_data.retrieveInstitutionRetentionsbyOCLCNumber(getTestConfig, csv_read, oclcSymbol)
assert type(result) is pandas.DataFrame
final_result = pandas.DataFrame(data={"oclcNumber": [776775878, 1702614], "accession_numbers":['236528690', '272142932'], "barcodes": [None, None], "locations": [None, None], "status": ['success', 'success']})
def test_retrieveSPByOCLCNumber(mockOAuthSession, getTestConfig, tmpdir, requests_mock):
heldInState = "CA"
requests_mock.register_uri('GET', 'https://americas.discovery.api.oclc.org/worldcat/v2/bibs-retained-holdings?oclcNumber=776775878&heldInState=' + heldInState, status_code=200, json=retained_byState)
requests_mock.register_uri('GET', 'https://americas.discovery.api.oclc.org/worldcat/v2/bibs-retained-holdings?oclcNumber=1702614&heldInState=' + heldInState, status_code=200, json=retained_byState2)
item_file = "oclcNumber\n776775878\n1702614"
csv_read = handle_files.loadCSV(item_file)
getTestConfig.update({"oauth-session": mockOAuthSession})
result = process_data.retrieveSPByOCLCNumber(getTestConfig, csv_read, heldInState=heldInState)
assert type(result) is pandas.DataFrame
final_result = pandas.DataFrame(data={"oclcNumber": [776775878, 1702614], "total_holding_count":[50, 395], "retained_symbols": ['CCO', 'CCO'], "status": ['success', 'success']})
def process(args):
with open(config_file, 'r') as stream:
config = yaml.safe_load(stream)
item_file = handle_files.readFileFromLocal(args.itemFile)
operation = args.operation
output_dir = args.outputDir
try:
oauth_session = make_requests.createOAuthSession(
config, [config.read('scope')])
config.update({"oauth-session": oauth_session})
processConfig = config
csv_read = handle_files.loadCSV(item_file)
if operation == "retrieveAllInstitutionRetentions":
results = []
for index, row in csv_read.iterrows():
csv_read_institution = process_data.retrieveAllInstitutionRetentions(
processConfig, row['symbol'])
result = handle_files.saveFileLocal(csv_read_institution,
output_dir)
results.append(row['symbol'] + ": " + result)
return ",".join(results)
else:
if operation == "retrieveMergedOCLCNumbers":
csv_read = process_data.retrieveMergedOCLCNumbers(
processConfig, csv_read)
elif operation == "retrieveHoldingsByOCLCNumber":
if hasattr(args, 'heldBy'):
heldBy = args.heldBy
elif hasattr(args, 'heldByGroup'):
heldByGroup = args.heldByGroup
csv_read = process_data.retrieveHoldingsByOCLCNumber(
processConfig, csv_read, heldByGroup, heldBy)
elif operation == "retrieveSPByOCLCNumber":
csv_read = process_data.retrieveSPByOCLCNumber(
processConfig, csv_read, heldByGroup, heldInState)
if hasattr(args, 'heldByGroup'):
heldByGroup = args.heldByGroup
elif hasattr(args, 'heldInState'):
heldInState = args.heldInState
elif operation == "retrieveInstitutionRetentionsbyOCLCNumber":
heldBy = args.heldBy
csv_read = process_data.retrieveInstitutionRetentionsbyOCLCNumber(
processConfig, csv_read, heldBy)
return handle_files.saveFileLocal(csv_read, output_dir)
except BaseException as err:
result = 'no access token ' + str(err)
return result
def test_retrieveHoldingsByOCLCNumber(mockOAuthSession, getTestConfig, tmpdir, requests_mock):
oclcSymbol = "OCPSB"
requests_mock.register_uri('GET', 'https://americas.discovery.api.oclc.org/worldcat/v2/bibs-detailed-holdings?oclcNumber=318877925&heldBy=' + oclcSymbol, status_code=200, json=institution_holdings)
requests_mock.register_uri('GET', 'https://americas.discovery.api.oclc.org/worldcat/v2/bibs-detailed-holdings?oclcNumber=191865523&heldBy=' + oclcSymbol, status_code=200, json=institution_holdings2)
item_file = "oclcNumber\n318877925\n191865523"
csv_read = handle_files.loadCSV(item_file)
getTestConfig.update({"oauth-session": mockOAuthSession})
result = process_data.retrieveHoldingsByOCLCNumber(getTestConfig, csv_read, heldBy=oclcSymbol)
assert type(result) is pandas.DataFrame
final_result = pandas.DataFrame(data={"oclcNumber": [318877925, 191865523], "total_holding_count":[246, 3355], "holding_symbols": ['OCPSB', 'OCPSB'], "status": ['success', 'success']})
assert_frame_equal(result, final_result)
def test_retrieveMergedOCLCNumbers(mockOAuthSession, getTestConfig, tmpdir, requests_mock):
requests_mock.register_uri('GET', 'https://americas.discovery.api.oclc.org/worldcat/v2/bibs/311684437', status_code=200, json=merged_oclcnumbers)
requests_mock.register_uri('GET', 'https://americas.discovery.api.oclc.org/worldcat/v2/bibs/318877925', status_code=200, json=merged_oclcnumbers2)
item_file = "oclcNumber\n311684437\n318877925"
csv_read = handle_files.loadCSV(item_file)
getTestConfig.update({"oauth-session": mockOAuthSession})
result = process_data.retrieveMergedOCLCNumbers(getTestConfig, csv_read)
assert type(result) is pandas.DataFrame
#assert result.columns == ["oclcNumber", "mergedOCNs", "status"]
final_result = pandas.DataFrame(data={"oclcNumber": [311684437, 318877925], "mergedOCNs":['261176486,330361568,377707240,426228842,701739996,716923895,731216527,887752101,945738851', '877908501,979175514,981548811,990719089,993246604,1005002644,1011917725,1016539262,1020206933,1057597575'], "status": ['success', 'success']})
assert_frame_equal(result, final_result)
def getInstitutionRetentions(event, context):
item_file = handle_files.readFilesFromBucket(event)
csv_read = handle_files.loadCSV(item_file)
results = []
for index, row in csv_read.iterrows():
retained_holdings = process_data.retrieveAllInstitutionRetentions(
processConfig, row['symbol'])
result = handle_files.saveFileToBucket(
fileInfo['bucket'],
fileInfo['key'] + "_" + row['symbol'] + "_retained",
retained_holdings)
results.append(row['symbol'] + ": " + result)
return ",".join(results)
def getMergedOCLCNumbers(event, context):
item_file = handle_files.readFilesFromBucket(event)
csv_read = handle_files.loadCSV(item_file)
csv_read = process_data.retrieveMergedOCLCNumbers(processConfig, csv_read)
handle_files.saveFileToBucket(fileInfo['bucket'],
fileInfo['key'] + "_updated", csv_read)
