Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Datasources] Add: Add query runner for Yandex ClickHouse #1409

Merged
merged 5 commits into from
Nov 24, 2016
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
120 changes: 120 additions & 0 deletions redash/query_runner/clickhouse.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,120 @@
import json
import logging
from redash.query_runner import *
from redash.utils import JSONEncoder
logger = logging.getLogger(__name__)

try:
import requests
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No need to wrap this in try/except. requests is a direct dependency of the project.

enabled = True
except ImportError as e:
logger.info(str(e))
enabled = False


class ClickHouse(BaseSQLQueryRunner):
noop_query = "SELECT 1"

@classmethod
def configuration_schema(cls):
return {
"type": "object",
"properties": {
"user": {
"type": "string",
"default": "default"
},
"password": {
"type": "string"
},
"host": {
"type": "string",
"default": "127.0.0.1"
},
"port": {
"type": "number",
"default": 8123
},
"dbname": {
"type": "string",
"title": "Database Name"
}
},
"required": ["dbname"],
"secret": ["password"]
}

@classmethod
def type(cls):
return "clickhouse"

def __init__(self, configuration):
super(ClickHouse, self).__init__(configuration)

def _get_tables(self, schema):
query = "SELECT database, table, name FROM system.columns WHERE database NOT IN ('system')"

results, error = self.run_query(query, None)

if error is not None:
raise Exception("Failed getting schema.")

results = json.loads(results)

for row in results['rows']:
table_name = '{}.{}'.format(row['database'], row['table'])

if table_name not in schema:
schema[table_name] = {'name': table_name, 'columns': []}

schema[table_name]['columns'].append(row['name'])

return schema.values()

def _send_query(self, data, stream=False):
url = 'http://{host}:{port}'.format(host=self.configuration['host'], port=self.configuration['port'])
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

http and not https? why not let the user specify the full url instead of host/port pair?

r = requests.post(url, data=data, stream=stream, params={
'user': self.configuration['user'], 'password': self.configuration['password'],
'database': self.configuration['dbname']
})
if r.status_code != 200:
raise Exception(r.text)
return r.json()

@staticmethod
def _define_column_type(column):
c = column.lower()
if 'int' in c:
return TYPE_INTEGER
elif 'float' in c:
return TYPE_FLOAT
elif 'datetime' == c:
return TYPE_DATETIME
elif 'date' == c:
return TYPE_DATE
else:
return TYPE_STRING

def _clickhouse_query(self, query):
query += ' FORMAT JSON'
result = self._send_query(query)
columns = [{'name': r['name'], 'friendly_name': r['name'],
'type': self._define_column_type(r['type'])} for r in result['meta']]
return {'columns': columns, 'rows': result['data']}

def run_query(self, query, user):
logger.info("Clickhouse is about to execute query: %s", query)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's change this to logger.debug.

if query == "":
json_data = None
error = "Query is empty"
return json_data, error
try:
q = self._clickhouse_query(query)
data = json.dumps(q, cls=JSONEncoder)
error = None
except Exception as exc:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If we just return the exception as the error value, we can let it bubble up and handle it there.

data = None
error = str(exc)
return data, error

register(ClickHouse)
1 change: 1 addition & 0 deletions redash/settings.py
Original file line number Diff line number Diff line change
Expand Up @@ -169,6 +169,7 @@ def all_settings():
'redash.query_runner.hive_ds',
'redash.query_runner.impala_ds',
'redash.query_runner.vertica',
'redash.query_runner.clickhouse',
'redash.query_runner.treasuredata',
'redash.query_runner.sqlite',
'redash.query_runner.dynamodb_sql',
Expand Down