def guess_field_types(request):
file_format = json.loads(request.POST.get('fileFormat', '{}'))
if file_format['inputFormat'] == 'file':
indexer = MorphlineIndexer(request.user, request.fs)
path = urllib_unquote(file_format["path"])
stream = request.fs.open(path)
encoding = check_encoding(stream.read(10000))
stream.seek(0)
_convert_format(file_format["format"], inverse=True)
format_ = indexer.guess_field_types({
"file": {
"stream": stream,
"name": path
},
"format": file_format['format']
})
# Note: Would also need to set charset to table (only supported in Hive)
if 'sample' in format_ and format_['sample']:
format_['sample'] = escape_rows(format_['sample'],
nulls_only=True,
encoding=encoding)
for col in format_['columns']:
col['name'] = smart_unicode(col['name'],
errors='replace',
encoding=encoding)
elif file_format['inputFormat'] == 'table':
sample = get_api(request, {
'type': 'hive'
}).get_sample_data({'type': 'hive'},
database=file_format['databaseName'],
table=file_format['tableName'])
db = dbms.get(request.user)
table_metadata = db.get_table(database=file_format['databaseName'],
table_name=file_format['tableName'])
format_ = {
"sample":
sample['rows'][:4],
"columns": [
Field(col.name,
HiveFormat.FIELD_TYPE_TRANSLATE.get(col.type,
'string')).to_dict()
for col in table_metadata.cols
]
}
elif file_format['inputFormat'] == 'query':
query_id = file_format['query']['id'] if file_format['query'].get(
'id') else file_format['query']
notebook = Notebook(document=Document2.objects.document(
user=request.user, doc_id=query_id)).get_data()
snippet = notebook['snippets'][0]
db = get_api(request, snippet)
if file_format.get('sampleCols'):
columns = file_format.get('sampleCols')
sample = file_format.get('sample')
else:
snippet['query'] = snippet['statement']
try:
sample = db.fetch_result(notebook, snippet, 4,
start_over=True)['rows'][:4]
except Exception as e:
LOG.warning(
'Skipping sample data as query handle might be expired: %s'
% e)
sample = [[], [], [], [], []]
columns = db.autocomplete(snippet=snippet, database='', table='')
columns = [
Field(
col['name'],
HiveFormat.FIELD_TYPE_TRANSLATE.get(col['type'],
'string')).to_dict()
for col in columns['extended_columns']
]
format_ = {
"sample": sample,
"columns": columns,
}
elif file_format['inputFormat'] == 'rdbms':
api = _get_api(request)
sample = api.get_sample_data(None,
database=file_format['rdbmsDatabaseName'],
table=file_format['tableName'])
format_ = {
"sample":
list(sample['rows'])[:4],
"columns": [
Field(col['name'], col['type']).to_dict()
for col in sample['full_headers']
]
}
elif file_format['inputFormat'] == 'stream':
if file_format['streamSelection'] == 'kafka':
data = get_topic_data(request.user,
file_format.get('kafkaSelectedTopics'))
kafkaFieldNames = [col['name'] for col in data['full_headers']]
kafkaFieldTypes = [col['type'] for col in data['full_headers']]
topics_data = data['rows']
format_ = {
"sample":
topics_data,
"columns": [
Field(col, 'string', unique=False).to_dict()
for col in kafkaFieldNames
]
}
# data = """%(kafkaFieldNames)s
# %(data)s""" % {
# 'kafkaFieldNames': ','.join(kafkaFieldNames),
# 'data': '\n'.join([','.join(cols) for cols in topics_data])
# }
# stream = string_io()
# stream.write(data)
# _convert_format(file_format["format"], inverse=True)
# indexer = MorphlineIndexer(request.user, request.fs)
# format_ = indexer.guess_field_types({
# "file": {
# "stream": stream,
# "name": file_format['path']
# },
# "format": file_format['format']
# })
# type_mapping = dict(
# list(
# zip(kafkaFieldNames, kafkaFieldTypes)
# )
# )
# for col in format_['columns']:
# col['keyType'] = type_mapping[col['name']]
# col['type'] = type_mapping[col['name']]
elif file_format['streamSelection'] == 'flume':
if 'hue-httpd/access_log' in file_format['channelSourcePath']:
columns = [{
'name': 'id',
'type': 'string',
'unique': True
}, {
'name': 'client_ip',
'type': 'string'
}, {
'name': 'time',
'type': 'date'
}, {
'name': 'request',
'type': 'string'
}, {
'name': 'code',
'type': 'plong'
}, {
'name': 'bytes',
'type': 'plong'
}, {
'name': 'method',
'type': 'string'
}, {
'name': 'url',
'type': 'string'
}, {
'name': 'protocol',
'type': 'string'
}, {
'name': 'app',
'type': 'string'
}, {
'name': 'subapp',
'type': 'string'
}]
else:
columns = [{'name': 'message', 'type': 'string'}]
format_ = {
"sample": [['...'] * len(columns)] * 4,
"columns": [
Field(col['name'],
HiveFormat.FIELD_TYPE_TRANSLATE.get(
col['type'], 'string'),
unique=col.get('unique')).to_dict()
for col in columns
]
}
elif file_format['inputFormat'] == 'connector':
if file_format['connectorSelection'] == 'sfdc':
sf = Salesforce(username=file_format['streamUsername'],
password=file_format['streamPassword'],
security_token=file_format['streamToken'])
table_metadata = [{
'name': column['name'],
'type': column['type']
} for column in sf.restful('sobjects/%(streamObject)s/describe/' %
file_format)['fields']]
query = 'SELECT %s FROM %s LIMIT 4' % (', '.join(
[col['name']
for col in table_metadata]), file_format['streamObject'])
print(query)
try:
records = sf.query_all(query)
except SalesforceRefusedRequest as e:
raise PopupException(message=str(e))
format_ = {
"sample":
[list(row.values())[1:] for row in records['records']],
"columns": [
Field(
col['name'],
HiveFormat.FIELD_TYPE_TRANSLATE.get(
col['type'], 'string')).to_dict()
for col in table_metadata
]
}
else:
raise PopupException(
_('Connector format not recognized: %(connectorSelection)s') %
file_format)
else:
raise PopupException(
_('Input format not recognized: %(inputFormat)s') % file_format)
return JsonResponse(format_)
def guess_format(request):
file_format = json.loads(request.POST.get('fileFormat', '{}'))
if file_format['inputFormat'] == 'file':
path = urllib_unquote(file_format["path"])
indexer = MorphlineIndexer(request.user, request.fs)
if not request.fs.isfile(path):
raise PopupException(
_('Path %(path)s is not a file') % file_format)
stream = request.fs.open(path)
format_ = indexer.guess_format(
{"file": {
"stream": stream,
"name": path
}})
_convert_format(format_)
elif file_format['inputFormat'] == 'table':
db = dbms.get(request.user)
try:
table_metadata = db.get_table(database=file_format['databaseName'],
table_name=file_format['tableName'])
except Exception as e:
raise PopupException(
e.message if hasattr(e, 'message') and e.message else e)
storage = {}
for delim in table_metadata.storage_details:
if delim['data_type']:
if '=' in delim['data_type']:
key, val = delim['data_type'].split('=', 1)
storage[key] = val
else:
storage[delim['data_type']] = delim['comment']
if table_metadata.details['properties']['format'] == 'text':
format_ = {
"quoteChar": "\"",
"recordSeparator": '\\n',
"type": "csv",
"hasHeader": False,
"fieldSeparator": storage.get('field.delim', ',')
}
elif table_metadata.details['properties']['format'] == 'parquet':
format_ = {
"type": "parquet",
"hasHeader": False,
}
else:
raise PopupException(
'Hive table format %s is not supported.' %
table_metadata.details['properties']['format'])
elif file_format['inputFormat'] == 'query':
format_ = {
"quoteChar": "\"",
"recordSeparator": "\\n",
"type": "csv",
"hasHeader": False,
"fieldSeparator": "\u0001"
}
elif file_format['inputFormat'] == 'rdbms':
format_ = {"type": "csv"}
elif file_format['inputFormat'] == 'stream':
if file_format['streamSelection'] == 'kafka':
format_ = {
"type": "json",
# "fieldSeparator": ",",
# "hasHeader": True,
# "quoteChar": "\"",
# "recordSeparator": "\\n",
'topics': get_topics(request.user)
}
elif file_format['streamSelection'] == 'flume':
format_ = {
"type": "csv",
"fieldSeparator": ",",
"hasHeader": True,
"quoteChar": "\"",
"recordSeparator": "\\n"
}
elif file_format['inputFormat'] == 'connector':
if file_format['connectorSelection'] == 'sfdc':
sf = Salesforce(username=file_format['streamUsername'],
password=file_format['streamPassword'],
security_token=file_format['streamToken'])
format_ = {
"type":
"csv",
"fieldSeparator":
",",
"hasHeader":
True,
"quoteChar":
"\"",
"recordSeparator":
"\\n",
'objects': [
sobject['name']
for sobject in sf.restful('sobjects/')['sobjects']
if sobject['queryable']
]
}
else:
raise PopupException(
_('Input format %(inputFormat)s connector not recognized: $(connectorSelection)s'
) % file_format)
else:
raise PopupException(
_('Input format not recognized: %(inputFormat)s') % file_format)
format_['status'] = 0
return JsonResponse(format_)
else:
raise PopupException('Hive table format %s is not supported.' % table_metadata.details['properties']['format'])
elif file_format['inputFormat'] == 'query':
format_ = {"quoteChar": "\"", "recordSeparator": "\\n", "type": "csv", "hasHeader": False, "fieldSeparator": "\u0001"}
elif file_format['inputFormat'] == 'rdbms':
format_ = RdbmsIndexer(request.user, file_format['rdbmsType']).guess_format()
elif file_format['inputFormat'] == 'stream':
if file_format['streamSelection'] == 'kafka':
format_ = {"type": "csv", "fieldSeparator": ",", "hasHeader": True, "quoteChar": "\"", "recordSeparator": "\\n", 'topics': get_topics()}
elif file_format['streamSelection'] == 'sfdc':
sf = Salesforce(
username=file_format['streamUsername'],
password=file_format['streamPassword'],
security_token=file_format['streamToken']
)
format_ = {"type": "csv", "fieldSeparator": ",", "hasHeader": True, "quoteChar": "\"", "recordSeparator": "\\n", 'objects': [sobject['name'] for sobject in sf.restful('sobjects/')['sobjects'] if sobject['queryable']]}
format_['status'] = 0
return JsonResponse(format_)
def guess_field_types(request):
file_format = json.loads(request.POST.get('fileFormat', '{}'))
if file_format['inputFormat'] == 'file':
indexer = MorphlineIndexer(request.user, request.fs)
path = urllib.unquote(file_format["path"])
stream = request.fs.open(path)
encoding = chardet.detect(stream.read(10000)).get('encoding')
stream.seek(0)
_convert_format(file_format["format"], inverse=True)
password=file_format['streamPassword'],
security_token=file_format['streamToken'])
format_ = {
"type":
"csv",
"fieldSeparator":
",",
"hasHeader":
True,
"quoteChar":
"\"",
"recordSeparator":
"\\n",
'objects': [
sobject['name']
for sobject in sf.restful('sobjects/')['sobjects']
if sobject['queryable']
]
}
format_['status'] = 0
return JsonResponse(format_)
def guess_field_types(request):
file_format = json.loads(request.POST.get('fileFormat', '{}'))
if file_format['inputFormat'] == 'file':
indexer = MorphlineIndexer(request.user, request.fs)
path = urllib.unquote(file_format["path"])
stream = request.fs.open(path)
def guess_format(request):
file_format = json.loads(request.POST.get('fileFormat', '{}'))
file_type = file_format['file_type']
path = urllib_unquote(file_format["path"])
if sys.version_info[0] < 3 and (file_type == 'excel' or path[-3:] == 'xls'
or path[-4:] == 'xlsx'):
return JsonResponse({
'status':
-1,
'message':
'Python2 based Hue does not support Excel file importer'
})
if file_format['inputFormat'] == 'localfile':
if file_type == 'excel':
format_ = {"type": "excel", "hasHeader": True}
else:
format_ = {
"quoteChar": "\"",
"recordSeparator": '\\n',
"type": "csv",
"hasHeader": True,
"fieldSeparator": ","
}
elif file_format['inputFormat'] == 'file':
if path[-3:] == 'xls' or path[-4:] == 'xlsx':
file_obj = request.fs.open(path)
if path[-3:] == 'xls':
df = pd.read_excel(file_obj.read(1024 * 1024 * 1024),
engine='xlrd')
else:
df = pd.read_excel(file_obj.read(1024 * 1024 * 1024),
engine='openpyxl')
_csv_data = df.to_csv(index=False)
path = excel_to_csv_file_name_change(path)
request.fs.create(path, overwrite=True, data=_csv_data)
indexer = MorphlineIndexer(request.user, request.fs)
if not request.fs.isfile(path):
raise PopupException(
_('Path %(path)s is not a file') % file_format)
stream = request.fs.open(path)
format_ = indexer.guess_format(
{"file": {
"stream": stream,
"name": path
}})
_convert_format(format_)
if file_format["path"][-3:] == 'xls' or file_format["path"][
-4:] == 'xlsx':
format_ = {
"quoteChar": "\"",
"recordSeparator": '\\n',
"type": "excel",
"hasHeader": True,
"fieldSeparator": ","
}
elif file_format['inputFormat'] == 'table':
db = dbms.get(request.user)
try:
table_metadata = db.get_table(database=file_format['databaseName'],
table_name=file_format['tableName'])
except Exception as e:
raise PopupException(
e.message if hasattr(e, 'message') and e.message else e)
storage = {}
for delim in table_metadata.storage_details:
if delim['data_type']:
if '=' in delim['data_type']:
key, val = delim['data_type'].split('=', 1)
storage[key] = val
else:
storage[delim['data_type']] = delim['comment']
if table_metadata.details['properties']['format'] == 'text':
format_ = {
"quoteChar": "\"",
"recordSeparator": '\\n',
"type": "csv",
"hasHeader": False,
"fieldSeparator": storage.get('field.delim', ',')
}
elif table_metadata.details['properties']['format'] == 'parquet':
format_ = {
"type": "parquet",
"hasHeader": False,
}
else:
raise PopupException(
'Hive table format %s is not supported.' %
table_metadata.details['properties']['format'])
elif file_format['inputFormat'] == 'query':
format_ = {
"quoteChar": "\"",
"recordSeparator": "\\n",
"type": "csv",
"hasHeader": False,
"fieldSeparator": "\u0001"
}
elif file_format['inputFormat'] == 'rdbms':
format_ = {"type": "csv"}
elif file_format['inputFormat'] == 'stream':
if file_format['streamSelection'] == 'kafka':
format_ = {
"type": "json",
# "fieldSeparator": ",",
# "hasHeader": True,
# "quoteChar": "\"",
# "recordSeparator": "\\n",
'topics': get_topics(request.user)
}
elif file_format['streamSelection'] == 'flume':
format_ = {
"type": "csv",
"fieldSeparator": ",",
"hasHeader": True,
"quoteChar": "\"",
"recordSeparator": "\\n"
}
elif file_format['inputFormat'] == 'connector':
if file_format['connectorSelection'] == 'sfdc':
sf = Salesforce(username=file_format['streamUsername'],
password=file_format['streamPassword'],
security_token=file_format['streamToken'])
format_ = {
"type":
"csv",
"fieldSeparator":
",",
"hasHeader":
True,
"quoteChar":
"\"",
"recordSeparator":
"\\n",
'objects': [
sobject['name']
for sobject in sf.restful('sobjects/')['sobjects']
if sobject['queryable']
]
}
else:
raise PopupException(
_('Input format %(inputFormat)s connector not recognized: $(connectorSelection)s'
) % file_format)
else:
raise PopupException(
_('Input format not recognized: %(inputFormat)s') % file_format)
format_['status'] = 0
return JsonResponse(format_)
def guess_field_types(request):
file_format = json.loads(request.POST.get('fileFormat', '{}'))
if file_format['inputFormat'] == 'file':
indexer = MorphlineIndexer(request.user, request.fs)
path = urllib_unquote(file_format["path"])
stream = request.fs.open(path)
encoding = chardet.detect(stream.read(10000)).get('encoding')
stream.seek(0)
_convert_format(file_format["format"], inverse=True)
format_ = indexer.guess_field_types({
"file": {
"stream": stream,
"name": path
},
"format": file_format['format']
})
# Note: Would also need to set charset to table (only supported in Hive)
if 'sample' in format_ and format_['sample']:
format_['sample'] = escape_rows(format_['sample'],
nulls_only=True,
encoding=encoding)
for col in format_['columns']:
col['name'] = smart_unicode(col['name'],
errors='replace',
encoding=encoding)
elif file_format['inputFormat'] == 'table':
sample = get_api(request, {
'type': 'hive'
}).get_sample_data({'type': 'hive'},
database=file_format['databaseName'],
table=file_format['tableName'])
db = dbms.get(request.user)
table_metadata = db.get_table(database=file_format['databaseName'],
table_name=file_format['tableName'])
format_ = {
"sample":
sample['rows'][:4],
"columns": [
Field(col.name,
HiveFormat.FIELD_TYPE_TRANSLATE.get(col.type,
'string')).to_dict()
for col in table_metadata.cols
]
}
elif file_format['inputFormat'] == 'query':
query_id = file_format['query']['id'] if file_format['query'].get(
'id') else file_format['query']
notebook = Notebook(document=Document2.objects.document(
user=request.user, doc_id=query_id)).get_data()
snippet = notebook['snippets'][0]
db = get_api(request, snippet)
if file_format.get('sampleCols'):
columns = file_format.get('sampleCols')
sample = file_format.get('sample')
else:
snippet['query'] = snippet['statement']
try:
sample = db.fetch_result(notebook, snippet, 4,
start_over=True)['rows'][:4]
except Exception as e:
LOG.warn(
'Skipping sample data as query handle might be expired: %s'
% e)
sample = [[], [], [], [], []]
columns = db.autocomplete(snippet=snippet, database='', table='')
columns = [
Field(
col['name'],
HiveFormat.FIELD_TYPE_TRANSLATE.get(col['type'],
'string')).to_dict()
for col in columns['extended_columns']
]
format_ = {
"sample": sample,
"columns": columns,
}
elif file_format['inputFormat'] == 'rdbms':
api = _get_api(request)
sample = api.get_sample_data(None,
database=file_format['rdbmsDatabaseName'],
table=file_format['tableName'])
format_ = {
"sample":
list(sample['rows'])[:4],
"columns": [
Field(col['name'], col['type']).to_dict()
for col in sample['full_headers']
]
}
elif file_format['inputFormat'] == 'stream':
if file_format['streamSelection'] == 'kafka':
if file_format.get(
'kafkaSelectedTopics') == 'NavigatorAuditEvents':
kafkaFieldNames = [
'id', 'additionalInfo', 'allowed', 'collectionName',
'databaseName', 'db', 'DELEGATION_TOKEN_ID', 'dst',
'entityId', 'family', 'impersonator', 'ip', 'name',
'objectType', 'objType', 'objUsageType', 'operationParams',
'operationText', 'op', 'opText', 'path', 'perms',
'privilege', 'qualifier', 'QUERY_ID', 'resourcePath',
'service', 'SESSION_ID', 'solrVersion', 'src', 'status',
'subOperation', 'tableName', 'table', 'time', 'type',
'url', 'user'
]
kafkaFieldTypes = ['string'] * len(kafkaFieldNames)
kafkaFieldNames.append('timeDate')
kafkaFieldTypes.append('date')
else:
# Note: mocked here, should come from SFDC or Kafka API or sampling job
kafkaFieldNames = file_format.get('kafkaFieldNames',
'').split(',')
kafkaFieldTypes = file_format.get('kafkaFieldTypes',
'').split(',')
data = """%(kafkaFieldNames)s
%(data)s""" % {
'kafkaFieldNames': ','.join(kafkaFieldNames),
'data': '\n'.join(
[','.join(['...'] * len(kafkaFieldTypes))] * 5)
}
stream = string_io()
stream.write(data)
_convert_format(file_format["format"], inverse=True)
indexer = MorphlineIndexer(request.user, request.fs)
format_ = indexer.guess_field_types({
"file": {
"stream": stream,
"name": file_format['path']
},
"format": file_format['format']
})
type_mapping = dict(list(zip(kafkaFieldNames, kafkaFieldTypes)))
for col in format_['columns']:
col['keyType'] = type_mapping[col['name']]
col['type'] = type_mapping[col['name']]
elif file_format['streamSelection'] == 'flume':
if 'hue-httpd/access_log' in file_format['channelSourcePath']:
columns = [{
'name': 'id',
'type': 'string',
'unique': True
}, {
'name': 'client_ip',
'type': 'string'
}, {
'name': 'time',
'type': 'date'
}, {
'name': 'request',
'type': 'string'
}, {
'name': 'code',
'type': 'plong'
}, {
'name': 'bytes',
'type': 'plong'
}, {
'name': 'method',
'type': 'string'
}, {
'name': 'url',
'type': 'string'
}, {
'name': 'protocol',
'type': 'string'
}, {
'name': 'app',
'type': 'string'
}, {
'name': 'subapp',
'type': 'string'
}]
else:
columns = [{'name': 'message', 'type': 'string'}]
format_ = {
"sample": [['...'] * len(columns)] * 4,
"columns": [
Field(col['name'],
HiveFormat.FIELD_TYPE_TRANSLATE.get(
col['type'], 'string'),
unique=col.get('unique')).to_dict()
for col in columns
]
}
elif file_format['inputFormat'] == 'connector':
if file_format['connectorSelection'] == 'sfdc':
sf = Salesforce(username=file_format['streamUsername'],
password=file_format['streamPassword'],
security_token=file_format['streamToken'])
table_metadata = [{
'name': column['name'],
'type': column['type']
} for column in sf.restful('sobjects/%(streamObject)s/describe/' %
file_format)['fields']]
query = 'SELECT %s FROM %s LIMIT 4' % (', '.join(
[col['name']
for col in table_metadata]), file_format['streamObject'])
print(query)
try:
records = sf.query_all(query)
except SalesforceRefusedRequest as e:
raise PopupException(message=str(e))
format_ = {
"sample":
[list(row.values())[1:] for row in records['records']],
"columns": [
Field(
col['name'],
HiveFormat.FIELD_TYPE_TRANSLATE.get(
col['type'], 'string')).to_dict()
for col in table_metadata
]
}
else:
raise PopupException(
_('Connector format not recognized: %(connectorSelection)s') %
file_format)
else:
raise PopupException(
_('Input format not recognized: %(inputFormat)s') % file_format)
return JsonResponse(format_)
