QT/superset2
1
0
Fork 0
mirror of https://github.com/apache/superset.git synced 2026-04-20 00:24:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

Match viz dataframe column case to form_data fields for Snowflake, Oracle and Redshift (#5487)

Browse Source 
* Add function to fix dataframe column case

* Fix broken handle_nulls method

* Add case sensitivity option to dedup

* Refactor function definition and call location

* Remove added blank line

* Move df column rename logit to db_engine_spec

* Remove redundant variable

* Update comments in db_engine_specs

* Tie df adjustment to db_engine_spec class attribute

* Fix dedup error

* Linting

* Check for db_engine_spec attribute prior to adjustment

* Rename case sensitivity flag

* Linting

* Remove function that was moved to db_engine_specs

* Get metrics names from utils

* Remove double import and rename dedup variable
This commit is contained in:
Ville Brofeldt
2018-08-03 19:53:56 +03:00
committed by Maxime Beauchemin
parent aa9b30cf55
commit e1f4db8e24
4 changed files with 91 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
superset/dataframe.py
View File

@@ -27,23 +27,26 @@ INFER_COL_TYPES_THRESHOLD = 95
INFER_COL_TYPES_SAMPLE_SIZE = 100
def dedup(l, suffix='__'):
def dedup(l, suffix='__', case_sensitive=True):
"""De-duplicates a list of string by suffixing a counter
Always returns the same number of entries as provided, and always returns
unique values.
unique values. Case sensitive comparison by default.
>>> print(','.join(dedup(['foo', 'bar', 'bar', 'bar'])))
foo,bar,bar__1,bar__2
>>> print(','.join(dedup(['foo', 'bar', 'bar', 'bar', 'Bar'])))
foo,bar,bar__1,bar__2,Bar
>>> print(','.join(dedup(['foo', 'bar', 'bar', 'bar', 'Bar'], case_sensitive=False)))
foo,bar,bar__1,bar__2,Bar__3
"""
new_l = []
seen = {}
for s in l:
if s in seen:
seen[s] += 1
s += suffix + str(seen[s])
s_fixed_case = s if case_sensitive else s.lower()
if s_fixed_case in seen:
seen[s_fixed_case] += 1
s += suffix + str(seen[s_fixed_case])
else:
seen[s] = 0
seen[s_fixed_case] = 0
new_l.append(s)
return new_l
@@ -70,7 +73,9 @@ class SupersetDataFrame(object):
if cursor_description:
column_names = [col[0] for col in cursor_description]
self.column_names = dedup(column_names)
case_sensitive = db_engine_spec.consistent_case_sensitivity
self.column_names = dedup(column_names,
case_sensitive=case_sensitive)
data = data or []
self.df = (