def guess_format(request):
file_format = json.loads(request.POST.get('fileFormat', '{}'))
if file_format['inputFormat'] == 'file':
indexer = MorphlineIndexer(request.user, request.fs)
if not request.fs.isfile(file_format["path"]):
raise PopupException(_('Path %(path)s is not a file') % file_format)
stream = request.fs.open(file_format["path"])
format_ = indexer.guess_format({
"file": {
"stream": stream,
"name": file_format['path']
}
})
_convert_format(format_)
elif file_format['inputFormat'] == 'table':
db = dbms.get(request.user)
table_metadata = db.get_table(database=file_format['databaseName'], table_name=file_format['tableName'])
storage = dict([(delim['data_type'], delim['comment']) for delim in table_metadata.storage_details])
if table_metadata.details['properties']['format'] == 'text':
format_ = {"quoteChar": "\"", "recordSeparator": '\\n', "type": "csv", "hasHeader": False, "fieldSeparator": storage['serialization.format']}
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_ = RdbmsIndexer(request.user, file_format['rdbmsType']).guess_format()
format_['status'] = 0
return JsonResponse(format_)
def setup_class(cls):
if not ENABLE_SQOOP.get():
raise SkipTest
if not rdbms.get_query_server_config(server='mysql'):
raise SkipTest
cls.client = make_logged_in_client()
cls.user = User.objects.get(username='******')
cls.user = rewrite_user(cls.user)
cls.indexer = RdbmsIndexer(cls.user, db_conf_name='mysql')
def guess_field_types(request):
file_format = json.loads(request.POST.get('fileFormat', '{}'))
if file_format['inputFormat'] == 'file':
indexer = MorphlineIndexer(request.user, request.fs)
stream = request.fs.open(file_format["path"])
_convert_format(file_format["format"], inverse=True)
format_ = indexer.guess_field_types({
"file": {
"stream": stream,
"name": file_format['path']
},
"format": file_format['format']
})
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': # Only support open query history
# TODO get schema from explain query, which is not possible
notebook = Notebook(document=Document2.objects.get(id=file_format['query'])).get_data()
snippet = notebook['snippets'][0]
sample = get_api(request, snippet).fetch_result(notebook, snippet, 4, start_over=True)
format_ = {
"sample": sample['rows'][:4],
"sample_cols": sample.meta,
"columns": [
Field(col['name'], HiveFormat.FIELD_TYPE_TRANSLATE.get(col['type'], 'string')).to_dict()
for col in sample.meta
]
}
elif file_format['inputFormat'] == 'rdbms':
query_server = rdbms.get_query_server_config(server=file_format['rdbmsType'])
db = rdbms.get(request.user, query_server=query_server)
sample = RdbmsIndexer(request.user, file_format['rdbmsType']).get_sample_data(mode=file_format['rdbmsMode'], database=file_format['rdbmsDatabaseName'], table=file_format['rdbmsTableName'])
table_metadata = db.get_columns(file_format['rdbmsDatabaseName'], file_format['rdbmsTableName'], names_only=False)
format_ = {
"sample": list(sample['rows'])[:4],
"columns": [
Field(col['name'], HiveFormat.FIELD_TYPE_TRANSLATE.get(col['type'], 'string')).to_dict()
for col in table_metadata
]
}
return JsonResponse(format_)
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_ = RdbmsIndexer(request.user, file_format['rdbmsType']).guess_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)
stream = request.fs.open(file_format["path"])
_convert_format(file_format["format"], inverse=True)
format_ = indexer.guess_field_types({
"file": {
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_ = 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_)