remote/sqlite-utils
1
0
Fork 0
mirror of https://github.com/simonw/sqlite-utils.git synced 2026-07-23 01:14:31 +02:00
Code Issues Projects Releases Packages Wiki Activity

No need to show common values if everything is null

Browse source 
Closes #547
This commit is contained in:
Simon Willison 2023-05-21 10:19:16 -07:00
commit 6027f3ea69
3 changed files with 44 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

8
sqlite_utils/cli.py
View file

@ -2691,9 +2691,11 @@ def _analyze(db, tables, columns, save, common_limit=10, no_most=False, no_least
db["_analyze_tables_"].insert(
column_details._asdict(), pk=("table", "column"), replace=True
)
most_common_rendered = _render_common(
"\n\n Most common:", column_details.most_common
)
most_common_rendered = ""
if column_details.num_null != column_details.total_rows:
most_common_rendered = _render_common(
"\n\n Most common:", column_details.most_common
)
least_common_rendered = _render_common(
"\n\n Least common:", column_details.least_common
)

24
sqlite_utils/db.py
View file

@ -3470,18 +3470,22 @@ class Table(Queryable):
most_common_results = [(truncate(value), total_rows)]
elif num_distinct != total_rows:
if most_common:
most_common_results = [
(truncate(r[0]), r[1])
for r in db.execute(
"select [{}], count(*) from [{}] group by [{}] order by count(*) desc, [{}] limit {}".format(
column, table, column, column, common_limit
)
).fetchall()
]
most_common_results.sort(key=lambda p: (p[1], p[0]), reverse=True)
# Optimization - if all rows are null, don't run this query
if num_null == total_rows:
most_common_results = [(None, total_rows)]
else:
most_common_results = [
(truncate(r[0]), r[1])
for r in db.execute(
"select [{}], count(*) from [{}] group by [{}] order by count(*) desc, [{}] limit {}".format(
column, table, column, column, common_limit
)
).fetchall()
]
most_common_results.sort(key=lambda p: (p[1], p[0]), reverse=True)
if least_common:
if num_distinct <= common_limit:
# No need to run the query if it will just return the results in revers order
# No need to run the query if it will just return the results in reverse order
least_common_results = None
else:
least_common_results = [