remote/sqlite-utils
1
0
Fork 0
mirror of https://github.com/simonw/sqlite-utils.git synced 2026-07-25 18:34:32 +02:00
Code Issues Projects Releases Packages Wiki Activity

Truncate values longer than 100 characters

Browse source
This commit is contained in:
Simon Willison 2020-12-12 20:58:05 -08:00
commit 955daaaf05
2 changed files with 24 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

19
sqlite_utils/db.py
View file

@ -1943,11 +1943,22 @@ class Table(Queryable):
)
return self
def analyze_column(self, column, common_limit=10, total_rows=None):
def analyze_column(
self, column, common_limit=10, value_truncate=100, total_rows=None
):
db = self.db
table = self.name
if total_rows is None:
total_rows = db[table].count
def truncate(value):
if value_truncate is None or isinstance(value, (float, int)):
return value
value = str(value)
if len(value) > value_truncate:
value = value[:value_truncate] + "..."
return value
num_null = db.execute(
"select count(*) from [{}] where [{}] is null".format(table, column)
).fetchone()[0]
@ -1963,10 +1974,10 @@ class Table(Queryable):
value = db.execute(
"select [{}] from [{}] limit 1".format(column, table)
).fetchone()[0]
most_common = [(value, total_rows)]
most_common = [(truncate(value), total_rows)]
elif num_distinct != total_rows:
most_common = [
(r[0], r[1])
(truncate(r[0]), r[1])
for r in db.execute(
"select [{}], count(*) from [{}] group by [{}] order by count(*) desc limit {}".format(
column, table, column, common_limit
@ -1978,7 +1989,7 @@ class Table(Queryable):
least_common = None
else:
least_common = [
(r[0], r[1])
(truncate(r[0]), r[1])
for r in db.execute(
"select [{}], count(*) from [{}] group by [{}] order by count(*) limit {}".format(
column, table, column, common_limit

15
tests/test_analyze_tables.py
View file

@ -12,11 +12,11 @@ def db_to_analyze(fresh_db):
stuff = fresh_db["stuff"]
stuff.insert_all(
[
{"id": 1, "owner": "Terry", "size": 5},
{"id": 1, "owner": "Terryterryterry", "size": 5},
{"id": 2, "owner": "Joan", "size": 4},
{"id": 3, "owner": "Kumar", "size": 5},
{"id": 4, "owner": "Anne", "size": 5},
{"id": 5, "owner": "Terry", "size": 5},
{"id": 5, "owner": "Terryterryterry", "size": 5},
{"id": 6, "owner": "Joan", "size": 4},
{"id": 7, "owner": "Kumar", "size": 5},
{"id": 8, "owner": "Joan", "size": 4},
@ -51,7 +51,7 @@ def db_to_analyze(fresh_db):
num_null=0,
num_blank=0,
num_distinct=4,
most_common=[("Joan", 3), ("Terry", 2)],
most_common=[("Joan", 3), ("Terry...", 2)],
least_common=[("Anne", 1), ("Kumar", 2)],
),
),
@ -71,7 +71,10 @@ def db_to_analyze(fresh_db):
],
)
def test_analyze_column(db_to_analyze, column, expected):
assert db_to_analyze["stuff"].analyze_column(column, common_limit=2) == expected
assert (
db_to_analyze["stuff"].analyze_column(column, common_limit=2, value_truncate=5)
== expected
)
@pytest.fixture
@ -89,7 +92,7 @@ def test_analyze_table(db_to_analyze_path):
== textwrap.dedent(
"""
1/3: ColumnDetails(table='stuff', column='id', total_rows=8, num_null=0, num_blank=0, num_distinct=8, most_common=None, least_common=None)
2/3: ColumnDetails(table='stuff', column='owner', total_rows=8, num_null=0, num_blank=0, num_distinct=4, most_common=[('Joan', 3), ('Terry', 2), ('Kumar', 2), ('Anne', 1)], least_common=None)
2/3: ColumnDetails(table='stuff', column='owner', total_rows=8, num_null=0, num_blank=0, num_distinct=4, most_common=[('Joan', 3), ('Terryterryterry', 2), ('Kumar', 2), ('Anne', 1)], least_common=None)
3/3: ColumnDetails(table='stuff', column='size', total_rows=8, num_null=0, num_blank=0, num_distinct=2, most_common=[(5, 5), (4, 3)], least_common=None)
"""
).strip()
@ -119,7 +122,7 @@ def test_analyze_table_save(db_to_analyze_path):
"num_null": 0,
"num_blank": 0,
"num_distinct": 4,
"most_common": '[["Joan", 3], ["Terry", 2], ["Kumar", 2], ["Anne", 1]]',
"most_common": '[["Joan", 3], ["Terryterryterry", 2], ["Kumar", 2], ["Anne", 1]]',
"least_common": None,
},
{