def test_upload_documents_new(self, api_key, endpoint, index_name,
**kwargs):
client = SearchClient(endpoint, index_name,
AzureKeyCredential(api_key))
DOCUMENTS = [
{
"hotelId": "1000",
"rating": 5,
"rooms": [],
"hotelName": "Azure Inn"
},
{
"hotelId": "1001",
"rating": 4,
"rooms": [],
"hotelName": "Redmond Hotel"
},
]
results = client.upload_documents(DOCUMENTS)
assert len(results) == 2
assert set(x.status_code for x in results) == {201}
# There can be some lag before a document is searchable
if self.is_live:
time.sleep(TIME_TO_SLEEP)
assert client.get_document_count() == 12
for doc in DOCUMENTS:
result = client.get_document(key=doc["hotelId"])
assert result["hotelId"] == doc["hotelId"]
assert result["hotelName"] == doc["hotelName"]
assert result["rating"] == doc["rating"]
assert result["rooms"] == doc["rooms"]
def test_upload_documents_existing(self, api_key, endpoint, index_name, **kwargs):
client = SearchClient(
endpoint, index_name, AzureKeyCredential(api_key)
)
DOCUMENTS = [
{"hotelId": "1000", "rating": 5, "rooms": [], "hotelName": "Azure Inn"},
{"hotelId": "3", "rating": 4, "rooms": [], "hotelName": "Redmond Hotel"},
]
results = client.upload_documents(DOCUMENTS)
assert len(results) == 2
assert set(x.status_code for x in results) == {200, 201}
def upload_docs(Data_Frame, index_name, endpoint, key):
dataframe2 = list(Data_Frame.to_dict('records'))
# Create a client
credential = AzureKeyCredential(key)
client = SearchClient(endpoint=endpoint,
index_name=index_name,
credential=credential)
df = pd.read_csv('TrackerFiles/{}.csv'.format(index_name))
i = df.shape[0] + 1
for e in dataframe2:
DOCUMENT = {
'Id': str(i),
'FileName': e['FileName'],
'FilePath': e['FilePath'],
'KeyPhrases': e['KeyPhrases'],
'People': e['people'],
'Organisation': e['org'],
'Location': e['loc'],
}
i += 1
result = client.upload_documents(
documents=[DOCUMENT]) # documents = [document1,...,documentN]
