Skip to content

add partition key marker for Athena and Presto schemas #2764

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.

Sign up for GitHub

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

Closed
wants to merge 3 commits into from
Closed

add partition key marker for Athena and Presto schemas #2764

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9c00499
add partition key marker for athena and presto
alison985 Aug 26, 2018
30b969b
refactor format_schema for athena and presto
alison985 Aug 26, 2018
7ad3782
add blank line for codeclimate
alison985 Aug 26, 2018
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
11 changes: 3 additions & 8 deletions redash/query_runner/athena.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
from redash.query_runner import *
from redash.settings import parse_boolean
from redash.utils import JSONEncoder
from .presto import format_schema

logger = logging.getLogger(__name__)
ANNOTATE_QUERY = parse_boolean(os.environ.get('ATHENA_ANNOTATE_QUERY', 'true'))
Expand Down Expand Up @@ -140,9 +141,8 @@ def get_schema(self, get_stats=False):
if self.configuration.get('glue', False):
return self.__get_schema_from_glue()

schema = {}
query = """
SELECT table_schema, table_name, column_name
SELECT table_schema, table_name, column_name, data_type as column_type, extra_info
FROM information_schema.columns
WHERE table_schema NOT IN ('information_schema')
"""
Expand All @@ -151,12 +151,7 @@ def get_schema(self, get_stats=False):
if error is not None:
raise Exception("Failed getting schema.")

results = json.loads(results)
for row in results['rows']:
table_name = '{0}.{1}'.format(row['table_schema'], row['table_name'])
if table_name not in schema:
schema[table_name] = {'name': table_name, 'columns': []}
schema[table_name]['columns'].append(row['column_name'])
schema = format_schema(json.loads(results))

return schema.values()

Expand Down
28 changes: 17 additions & 11 deletions redash/query_runner/presto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,21 @@
}


# for athena and presto
Copy link
Contributor

Choose a reason for hiding this comment

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

No need to have this extra code comment.

def format_schema(results):
schema = {}
Copy link
Contributor

Choose a reason for hiding this comment

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

I'm sorry but the docstring changes from 17b9a0a didn't make it here, could you please add it?

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

if table_name not in schema:
schema[table_name] = {'name': table_name, 'columns': []}
row_to_add = row['column_name'] + ' (' + row['column_type'] + ')'
if row['extra_info'] == 'partition key':
row_to_add = '[P] ' + row_to_add
schema[table_name]['columns'].append(row_to_add)
return schema


class Presto(BaseQueryRunner):
noop_query = 'SHOW TABLES'

Expand Down Expand Up @@ -67,9 +82,8 @@ def type(cls):
return "presto"

def get_schema(self, get_stats=False):
schema = {}
query = """
SELECT table_schema, table_name, column_name
SELECT table_schema, table_name, column_name, data_type as column_type, extra_info
FROM information_schema.columns
WHERE table_schema NOT IN ('pg_catalog', 'information_schema')
"""
Expand All @@ -79,15 +93,7 @@ def get_schema(self, get_stats=False):
if error is not None:
raise Exception("Failed getting schema.")

results = json.loads(results)

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

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

schema[table_name]['columns'].append(row['column_name'])
schema = format_schema(json.loads(results))

return schema.values()

Expand Down