def test_tmp(self):
tables = sch.get_tables(
sch.get_connection('10.12.250.116', 'edwread', 'readedw',
'brm_ods'))
self.assertTrue(len(tables) > 0)
for tab_name in tables:
all_idx = sch.get_indexes(
sch.get_connection('10.12.250.116', 'edwread', 'readedw',
'BRM_ODS'), tab_name)
print str(len(all_idx))
def test_get_record_count(self):
self.assertTrue(
sch.get_record_count(
sch.get_connection('10.12.250.116', 'edwread', 'readedw',
'Cloud_Usage_Events'),
'dbo.CBS_USAGE_EVENTS'.lower()) > 0)
self.assertTrue(
sch.get_record_count(
sch.get_connection('10.12.250.116', 'edwread', 'readedw',
'BRM_ODS'),
'dbo.staging_EVENT_BAL_IMPACTS_T_partition_20151009-134325'.
lower()) > 0)
def test_get_min_date(self):
min_date = sch.get_min_date(
sch.get_connection('10.12.250.116', 'edwread', 'readedw',
'Cloud_Usage_Events'),
'CBS_USAGE_EVENTS'.lower(), 'dw_timestamp', 'dbo', False)
self.assertTrue(len(min_date) == 10)
def test_get_columns(self):
oneresult = sch.get_columns(
sch.get_connection('10.12.250.116', 'edwread', 'readedw',
'Cloud_Usage_Events'),
'vw_BACKUP_BANDWIDTHIN_USAGE_EVENTS'.lower(), 'dbo')
self.assertTrue(len(oneresult) > 0)
for (name, type) in oneresult:
print(name.lower(), type)
def test_compare_table_columns(self):
sqlcolumns = sch.get_columns(
sch.get_connection('10.12.250.116', 'edwread', 'readedw',
'Cloud_Usage_Events'),
'vw_BACKUP_BANDWIDTHOUT_USAGE_EVENTS'.lower(), 'dbo')
hcolumns = hcat.get_table_columns('cloud_usage_events',
'backup_bandwidthout_usage_events')
self.assertTrue(len(sqlcolumns) == len(hcolumns))
for i in range(0, len(sqlcolumns)):
print 'SQL: {}, Hive:{}'.format(sqlcolumns[i][0], hcolumns[i][0])
self.assertTrue(sqlcolumns[i][0] == hcolumns[i][0])
def test_get_sql_tables(self):
self.assertTrue(
len(
sch.get_tables(
sch.get_connection('10.12.250.116', 'edwread', 'readedw',
'Cloud_Usage_Events'))) > 0)
'''
Created on Apr 6, 2016
@author: natasha.gajic
'''
import datetime
import pypyodbc as odbc
import hive.schema.maintenence.sqlserver_api as sch
run_date = datetime.datetime(2013, 07, 20)
end_date = datetime.datetime(2015, 10, 10)
run_date += datetime.timedelta(days=1)
conn = sch.get_connection('10.12.250.116', 'edwread', 'readedw', 'brm_ods')
output_file = open('r_count_output.txt', 'w')
while (run_date < end_date):
next_date = run_date + datetime.timedelta(days=1)
stmt = "select '" + run_date.__str__(
)[0:
10] + "', count_big(*) from [dbo].[EVENT_BAL_IMPACTS_T_Archive] where dw_timestamp >= '" + run_date.__str__(
) + "' and dw_timestamp < '" + next_date.__str__() + "';"
print stmt
curr = conn.cursor()
curr.execute(stmt)
for row in curr.fetchall():
o = row[0].encode('ascii') + "," + str(row[1]).encode('ascii') + "\n"
print o
output_file.write(o)
run_date = next_date