Skip to content

Instantly share code, notes, and snippets.

@dubeyji10
Created June 3, 2022 05:07
Show Gist options
  • Save dubeyji10/ce513f8171c0dc69e77dccb04a139683 to your computer and use it in GitHub Desktop.
Save dubeyji10/ce513f8171c0dc69e77dccb04a139683 to your computer and use it in GitHub Desktop.
create shards of tabes and save payloads(indexed)
import mysql.connector
from mysql.connector import Error
import logging
import re
print('creating shards of huge amount of data\n')
sizeOfShard = 100
index = 0
counter = 0
lastIndex = 1000
alpha = re.compile(r"[a-z|A-Z]|[!@#$%^&*/]")
clients = 'select * from clients'
leads = 'select * from leads'
conversation = 'select * from conversation'
invoiceInfo = 'select * from invoice_info'
invoiceItems = 'select * from invoice_items'
for i in range(index , lastIndex ,sizeOfShard):
print(' ------------- {} -------------- '.format(counter))
# print('{} -> running for limit {},{}'.format(counter,i,sizeOfShard))
print('{} -> limit {} OFFSET {}'.format(counter,sizeOfShard , i))
offSet = ' LIMIT {} OFFSET {} '.format(sizeOfShard,i)
with mysql.connector.connect() as connectPointer:
with connectPointer.cursor() as aCursor:
query = clients+offSet
print('running - ',query)
clientsFile = 'clients/clients_data_{}.json'.format(i)
print(f' . .. writing to {clientsFile}')
with mysql.connector.connect() as connectPointer:
with connectPointer.cursor() as aCursor:
query = leads+offSet
print('running - ',query)
# aCursor.execute(query)
# result = aCursor.fetchall()
print(f' . .. writing to {clientsFile}')
leadsFile = 'leads/leads_data_{}.json'.format(i)
print(f' . .. writing to {leadsFile}')
with mysql.connector.connect() as connectPointer:
with connectPointer.cursor() as aCursor:
query = conversation+offSet
print('running - ',query)
# aCursor.execute(query)
# result = aCursor.fetchall()
conversationFile = 'conversations/conversation_data_{}.json'.format(i)
print(f' . .. writing to {conversationFile}')
with mysql.connector.connect() as connectPointer:
with connectPointer.cursor() as aCursor:
query = invoiceInfo + offSet
print('running - ',query)
# aCursor.execute(query)
# result = aCursor.fetchall()
invoiceInfoFile = 'invoiceInfo/invoiceInfo_data_{}.json'.format(i)
print(f' . .. writing to {invoiceInfoFile}')
with mysql.connector.connect() as connectPointer:
with connectPointer.cursor() as aCursor:
query = invoiceItems+offSet
print('running - ',query)
# aCursor.execute(query)
# result = aCursor.fetchall()
invoiceItemsFile = 'invoiceItems/invoiceItems_data_{}.json'.format(i)
print(f' . .. writing to {invoiceItemsFile}')
counter+=1
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment