hbase-rest-py 1.0.0

HBase client based on HBase REST

hbase-rest-py

hbase-rest-py is python library to interact with Apache HBase by using HBase REST API.

Prerequisites

hbase-rest-py requires at minimum Python 3.6 and above. HBase versions 2.4.2 and 2.4.8 have been used for library development and testing and all unit tests have been passing on this versions.

Installation

$ pip install hbase-rest-py

Quick start

Make sure you have running instance of HBase REST server by running hbase rest start

>>> from hbase.rest_client import HBaseRESTClient
>>> from hbase.admin import HBaseAdmin
>>> client = HBaseRESTClient(['http://localhost:8080'])
>>> admin = HBaseAdmin(client)
>>> admin.tables()
'{"table":[
            {"name":"message"},
            {"name":"py_test"},
            {"name":"tbl_int"},
            {"name":"test_scan"},
            {"name":"test_tb"},
            {"name":"test_tbl"},
            {"name":"users"}]}'

>>> admin.table_schema("message")
'{
	"name": "message",
	"ColumnSchema": [{
		"name": "d",
		"BLOOMFILTER": "ROW",
		"IN_MEMORY": "false",
		"VERSIONS": "1",
		"KEEP_DELETED_CELLS": "FALSE",
		"DATA_BLOCK_ENCODING": "NONE",
		"COMPRESSION": "NONE",
		"TTL": "2147483647",
		"MIN_VERSIONS": "0",
		"BLOCKCACHE": "true",
		"BLOCKSIZE": "65536",
		"REPLICATION_SCOPE": "0"
	}],
	"IS_META": "false"
}'
# Create table for example
>>> admin.table_create_or_update("messages", [{"name":"d"}])

# Write some data to messages table
>>> from hbase.put import Put
>>> put = Put(client=client)
>>> put.put('messages', "[e-mail]:22345", {"d:to":"[e-mail]"})
>>> put.put("messages", "[e-mail]:22345", {"d:m_id":23445, "d:body":"This is some message"})
''
# Get data from messages table
>>> from hbase.get import Get
>>> get = Get(client)
>>> get.get("messages", "[e-mail]:22345")
{'row': [{'key': b'[e-mail]:22345', 'cell': [{'column': b'd:body', 'timestamp': 1636442504076, '$': b'This is some message'}, {'column': b'd:m_id', 'timestamp': 1636442504076, '$': b'\x00\x00\x00\x00\x00\x00[\x95'}, {'column': b'd:to', 'timestamp': 1636436005215, '$': b'[e-mail]'}]}]}
>>> get.get("messages", "[e-mail]:22345", "d:body")
{'row': [{'key': b'[e-mail]:22345', 'cell': [{'column': b'd:body', 'timestamp': 1636442504076, '$': b'This is some message'}]}]}

# Put some more testing data
>>> for i in range(1, 1000):
>>>     put.put("messages", f"test{i}@example.com:{i}", {"d:m_id":i, "d:body":f"Message no {i}", "d:to":f"testx{i}@example.com"})

# Get data from messages table with scan 
# Get messages where m_id is LESS then 10
# First we build scanner filter payload
>>> from hbase.scan_filter_helper import *
>>> scan_filter= build_single_column_value_filter(family="d", qualifier="m_id", value=10, operation="LESS")
>>> scan_filter
'<Scanner batch="1000" maxVersions="1"><filter>{"op":"LESS","type":"SingleColumnValueFilter","family":"ZA==", "qualifier":"bV9pZA==", "comparator": {"value": "AAAAAAAAAAo=", "type": "BinaryComparator"}}</filter></Scanner>'
>>> from hbase.scan import Scan
>>> scan = Scan(client)
>>> result = scan.scan("messages", scan_filter)
>>> result
(True, {'row': [{'key': b'[e-mail]:1', 'cell': [{'column': b'd:body', 'timestamp': 1636445023120, '$': b'Message no 1'}, {'column': b'd:m_id', 'timestamp': 1636445023120, '$': b'\x00\x00\x00\x00\x00\x00\x00\x01'}, {'column': b'd:to', 'timestamp': 1636445023120, '$': b'[e-mail]'}]}, {'key': b'[e-mail]:2', 'cell': [{'column': b'd:body', 'timestamp': 1636445023129, '$': b'Message no 2'}, {'column': b'd:m_id', 'timestamp': 1636445023129, '$': b'\x00\x00\x00\x00\x00\x00\x00\x02'}, {'column': b'd:to', 'timestamp': 1636445023129, '$': b'[e-mail]'}]}, {'key': b'[e-mail]:3', 'cell': [{'column': b'd:body', 'timestamp': 1636445023142, '$': b'Message no 3'}, {'column': b'd:m_id', 'timestamp': 1636445023142, '$': b'\x00\x00\x00\x00\x00\x00\x00\x03'}, {'column': b'd:to', 'timestamp': 1636445023142, '$': b'[e-mail]'}]}, {'key': b'[e-mail]:4', 'cell': [{'column': b'd:body', 'timestamp': 1636445023151, '$': b'Message no 4'}, {'column': b'd:m_id', 'timestamp': 1636445023151, '$': b'\x00\x00\x00\x00\x00\x00\x00\x04'}, {'column': b'd:to', 'timestamp': 1636445023151, '$': b'[e-mail]'}]}, {'key': b'[e-mail]:5', 'cell': [{'column': b'd:body', 'timestamp': 1636445023164, '$': b'Message no 5'}, {'column': b'd:m_id', 'timestamp': 1636445023164, '$': b'\x00\x00\x00\x00\x00\x00\x00\x05'}, {'column': b'd:to', 'timestamp': 1636445023164, '$': b'[e-mail]'}]}, {'key': b'[e-mail]:6', 'cell': [{'column': b'd:body', 'timestamp': 1636445023174, '$': b'Message no 6'}, {'column': b'd:m_id', 'timestamp': 1636445023174, '$': b'\x00\x00\x00\x00\x00\x00\x00\x06'}, {'column': b'd:to', 'timestamp': 1636445023174, '$': b'[e-mail]'}]}, {'key': b'[e-mail]:7', 'cell': [{'column': b'd:body', 'timestamp': 1636445023182, '$': b'Message no 7'}, {'column': b'd:m_id', 'timestamp': 1636445023182, '$': b'\x00\x00\x00\x00\x00\x00\x00\x07'}, {'column': b'd:to', 'timestamp': 1636445023182, '$': b'[e-mail]'}]}, {'key': b'[e-mail]:8', 'cell': [{'column': b'd:body', 'timestamp': 1636445023189, '$': b'Message no 8'}, {'column': b'd:m_id', 'timestamp': 1636445023189, '$': b'\x00\x00\x00\x00\x00\x00\x00\x08'}, {'column': b'd:to', 'timestamp': 1636445023189, '$': b'[e-mail]'}]}, {'key': b'[e-mail]:9', 'cell': [{'column': b'd:body', 'timestamp': 1636445023197, '$': b'Message no 9'}, {'column': b'd:m_id', 'timestamp': 1636445023197, '$': b'\x00\x00\x00\x00\x00\x00\x00\t'}, {'column': b'd:to', 'timestamp': 1636445023197, '$': b'[e-mail]'}]}]})

# Releaase scanner resource
>>> >>> scan.delete_scanner()
200