This is an automated email from the ASF dual-hosted git repository.
jiayu pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/sedona-db.git
The following commit(s) were added to refs/heads/main by this push:
new f3a0a81 Add more python integration tests + fix pre-commit
ruff-format (#8)
f3a0a81 is described below
commit f3a0a81a0385f47660ebfdf0bf769a4383ecbf08
Author: Peter Nguyen <petern0...@gmail.com>
AuthorDate: Tue Sep 2 12:56:42 2025 -0700
Add more python integration tests + fix pre-commit ruff-format (#8)
* Move test_st_dwithin to test_predicates.py
* Add test_st_buffer
* Add test_st_asbinary
* Add test_st_geomfromwkb
* pre-commit
* Remove duplicate pre-commit ruff-format entry causing conflicts
* pre-commit testing.py
* Simplify testing.py and use escaped byte strings
* Add numeric_epsilon parameter for st_buffer to conditionally use
math.isclose
* Check exact strings in test_st_astext
* Compare bytes for st_geom/gfromwkb using shapely
* Pr feedback
* Decrease to epsilon 1e-9
---
.pre-commit-config.yaml | 7 -
python/sedonadb/python/sedonadb/testing.py | 23 ++-
python/sedonadb/tests/functions/test_functions.py | 209 +++++++++++++++++----
python/sedonadb/tests/functions/test_predicates.py | 36 +++-
4 files changed, 229 insertions(+), 46 deletions(-)
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 8fdb0bc..fefea8b 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -44,13 +44,6 @@ repos:
name: rustfmt
args: ["--all", "--"]
- - repo: https://github.com/astral-sh/ruff-pre-commit
- rev: v0.1.5
- hooks:
- - id: ruff
- args: [ --fix ]
- - id: ruff-format
-
- repo: https://github.com/cheshirekow/cmake-format-precommit
rev: v0.6.13
hooks:
diff --git a/python/sedonadb/python/sedonadb/testing.py
b/python/sedonadb/python/sedonadb/testing.py
index fe90910..8c2176d 100644
--- a/python/sedonadb/python/sedonadb/testing.py
+++ b/python/sedonadb/python/sedonadb/testing.py
@@ -15,6 +15,7 @@
# specific language governing permissions and limitations
# under the License.
import os
+import math
import warnings
from pathlib import Path
from typing import TYPE_CHECKING, List, Tuple
@@ -170,7 +171,9 @@ class DBEngine:
else:
return tab.to_pandas()
- def result_to_tuples(self, result, *, wkt_precision=None) ->
List[Tuple[str]]:
+ def result_to_tuples(
+ self, result, *, wkt_precision=None, **kwargs
+ ) -> List[Tuple[str]]:
"""Convert a query result into row tuples
This option strips away fine-grained type information but is helpful
for
@@ -202,7 +205,8 @@ class DBEngine:
- A tuple of strings as the string output of a single row
- A string as the string output of a single column of a single row
- A bool for a single boolean value
- - An int or float for single numeric values
+ - An int or float for single numeric values (optionally with a
numeric_epsilon)
+ - bytes for single binary values
Using Arrow table equality is the most strict (ensures exact type
equality and
byte-for-byte value equality); however, string output is most useful
for checking
@@ -260,11 +264,22 @@ class DBEngine:
self.assert_result(result, [(expected,)], **kwargs)
elif isinstance(expected, bool):
self.assert_result(result, [(str(expected).lower(),)], **kwargs)
- elif isinstance(expected, (int, float)):
+ elif isinstance(expected, (int, float, bytes)):
result_df = self.result_to_pandas(result)
assert result_df.shape == (1, 1)
result_value = result_df.iloc[0, 0]
- assert result_value == expected, f"Expected {expected}, got
{result_value}"
+ eps = kwargs.get("numeric_epsilon", None)
+ if eps is not None:
+ assert isinstance(expected, (int, float)), (
+ f"numeric_epsilon is only supported for int or float, not
{type(expected).__name__}"
+ )
+ assert math.isclose(result_value, expected, rel_tol=eps), (
+ f"Expected {expected}, got {result_value}"
+ )
+ else:
+ assert result_value == expected, (
+ f"Expected {expected}, got {result_value}"
+ )
elif expected is None:
self.assert_result(result, [(None,)], **kwargs)
else:
diff --git a/python/sedonadb/tests/functions/test_functions.py
b/python/sedonadb/tests/functions/test_functions.py
index f4dda6b..306e0c5 100644
--- a/python/sedonadb/tests/functions/test_functions.py
+++ b/python/sedonadb/tests/functions/test_functions.py
@@ -15,6 +15,7 @@
# specific language governing permissions and limitations
# under the License.
import pytest
+import shapely
from sedonadb.testing import geom_or_null, PostGIS, SedonaDB, val_or_null
@@ -50,6 +51,108 @@ def test_st_area(eng, geom, expected):
eng.assert_query_result(f"SELECT ST_Area({geom_or_null(geom)})", expected)
+@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
+@pytest.mark.parametrize(
+ ("geom", "expected"),
+ [
+ (
+ "POINT (1 1)",
+
b"\x01\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\xf0\x3f\x00\x00\x00\x00\x00\x00\xf0\x3f",
+ ),
+ (
+ "POINT EMPTY",
+
b"\x01\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\xf8\x7f\x00\x00\x00\x00\x00\x00\xf8\x7f",
+ ),
+ (
+ "LINESTRING (0 0, 1 2, 3 4)",
+
b"\x01\x02\x00\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xf0\x3f\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x08\x40\x00\x00\x00\x00\x00\x00\x10\x40",
+ ),
+ ("LINESTRING EMPTY", b"\x01\x02\x00\x00\x00\x00\x00\x00\x00"),
+ (
+ "POINT ZM (0 0 0 0)",
+
b"\x01\xb9\x0b\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00",
+ ),
+ (
+ "GEOMETRYCOLLECTION (POINT (0 0), POLYGON ((0 0, 1 0, 1 1, 0 1, 0
0)))",
+
b"\x01\x07\x00\x00\x00\x02\x00\x00\x00\x01\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x03\x00\x00\x00\x01\x00\x00\x00\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xf0?\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xf0?\x00\x00\x00\x00\x00\x00\xf0?\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xf0?\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00",
+ ),
+ ],
+)
+def test_st_asbinary(eng, geom, expected):
+ eng = eng.create_or_skip()
+ eng.assert_query_result(f"SELECT ST_AsBinary({geom_or_null(geom)})",
expected)
+
+
+@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
+@pytest.mark.parametrize(
+ ("geom"),
+ [
+ None,
+ # geoarrow-c returns POINT (nan nan) instead of POINT EMPTY
+ "POINT EMPTY",
+ "LINESTRING EMPTY",
+ "POLYGON EMPTY",
+ "MULTIPOINT EMPTY",
+ "MULTILINESTRING EMPTY",
+ "MULTIPOLYGON EMPTY",
+ "GEOMETRYCOLLECTION EMPTY",
+ "POINT(1 1)",
+ "LINESTRING(0 0,1 1)",
+ "POLYGON((0 0,1 0,1 1,0 1,0 0))",
+ "MULTIPOINT((0 0),(1 1))",
+ "MULTILINESTRING((0 0,1 1),(1 1,2 2))",
+ "MULTIPOLYGON(((0 0,1 0,1 1,0 1,0 0)),((0 0,1 0,1 1,0 1,0 0)))",
+ "GEOMETRYCOLLECTION(POINT(0 0),POLYGON((0 0,1 0,1 1,0 1,0
0)),LINESTRING(0 0,1 1),GEOMETRYCOLLECTION(POLYGON((0 0,-1 0,-1 -1,0 -1,0
0))))",
+ "POINT Z(0 0 0)",
+ "POINT ZM(0 0 0 0)",
+ "LINESTRING M(0 0 0,1 1 1)",
+ ],
+)
+def test_st_astext(eng, geom):
+ eng = eng.create_or_skip()
+ expected = geom
+
+ if isinstance(eng, PostGIS) and expected is not None:
+ expected = expected.replace(r"M(", r"M (")
+ expected = expected.replace(r"Z(", r"Z (")
+
+ eng.assert_query_result(f"SELECT ST_AsText({geom_or_null(geom)})",
expected)
+
+
+@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
+@pytest.mark.parametrize(
+ ("geom", "dist", "expected_area"),
+ [
+ (None, None, None),
+ (None, 1.0, None),
+ ("POINT (1 1)", None, None),
+ ("POINT (1 1)", 0.0, 0),
+ ("POINT EMPTY", 1.0, 0),
+ ("LINESTRING EMPTY", 1.0, 0),
+ ("POLYGON EMPTY", 1.0, 0),
+ ("POINT (0 0)", 1.0, 3.121445152258052),
+ ("POINT (0 0)", 2.0, 12.485780609032208),
+ ("LINESTRING (0 0, 1 1)", 1.0, 5.949872277004242),
+ ("LINESTRING (0 0, 1 1)", 2.0, 18.14263485852459),
+ ("POLYGON ((0 0, 1 0, 1 1, 0 1, 0 0))", 2.0, 21.48578060903221),
+ ("MULTIPOINT ((0 0), (1 1))", 1.0, 5.682167728387077),
+ (
+ "GEOMETRYCOLLECTION (POINT (0 0), LINESTRING (0 0, 1 1), POLYGON
((0 0, 1 0, 1 1, 0 1, 0 0)))",
+ 1.0,
+ 8.121445152256216,
+ ),
+ ],
+)
+def test_st_buffer(eng, geom, dist, expected_area):
+ eng = eng.create_or_skip()
+
+ eng.assert_query_result(
+ f"SELECT ST_Area(ST_Buffer({geom_or_null(geom)},
{val_or_null(dist)}))",
+ expected_area,
+ numeric_epsilon=1e-9,
+ )
+
+
@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
@pytest.mark.parametrize(
("geom", "expected"),
@@ -123,40 +226,6 @@ def test_st_dimension(eng, geom, expected):
eng.assert_query_result(f"SELECT ST_Dimension({geom_or_null(geom)})",
expected)
-@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
-@pytest.mark.parametrize(
- ("geom1", "geom2", "distance", "expected"),
- [
- (None, "POINT (0 0)", 1.0, None),
- ("POINT (1 1)", None, 1.0, None),
- ("POINT (0 0)", "POINT (0 0)", None, None),
- (None, None, None, None),
- ("POINT (0 0)", "POINT (0 0)", 1.0, True),
- ("POINT (0 0)", "POINT (5 0)", 2.0, False),
- ("LINESTRING (0 0, 1 1)", "LINESTRING (2 2, 3 3)", 1.0, False),
- ("LINESTRING (0 0, 1 1)", "LINESTRING (10 0, 11 1)", 2.0, False),
- (
- "POLYGON ((0 0, 1 0, 1 1, 0 1, 0 0))",
- "POLYGON ((5 5, 6 5, 6 6, 5 6, 5 5))",
- 6.0,
- True,
- ),
- (
- "GEOMETRYCOLLECTION (POINT (0 0), LINESTRING (0 0, 1 1))",
- "GEOMETRYCOLLECTION (POINT (0 0), LINESTRING (0 0, 1 1))",
- 1.0,
- True,
- ),
- ],
-)
-def test_st_dwithin(eng, geom1, geom2, distance, expected):
- eng = eng.create_or_skip()
- eng.assert_query_result(
- f"SELECT ST_DWithin({geom_or_null(geom1)}, {geom_or_null(geom2)},
{val_or_null(distance)})",
- expected,
- )
-
-
@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
@pytest.mark.parametrize(
("geom", "expected"),
@@ -261,6 +330,78 @@ def test_st_geomfromtext(eng, wkt, expected):
eng.assert_query_result(f"SELECT ST_GeomFromText({val_or_null(wkt)})",
expected)
+@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
+@pytest.mark.parametrize(
+ ("geom"),
+ [
+ "POINT (1 1)",
+ "POINT EMPTY",
+ "LINESTRING EMPTY",
+ "POLYGON EMPTY",
+ "GEOMETRYCOLLECTION EMPTY",
+ "POLYGON ((0 0, 1 0, 1 1, 0 1, 0 0))",
+ "MULTILINESTRING ((0 0, 1 1), (1 1, 2 2))",
+ "GEOMETRYCOLLECTION (POINT (0 0), LINESTRING (0 0, 1 1), POLYGON ((0
0, 0 1, 1 1, 1 0, 0 0)))",
+ ],
+)
+def test_st_geogfromwkb(eng, geom):
+ eng = eng.create_or_skip()
+
+ expected = geom
+ if geom == "POINT EMPTY":
+ # arrow-c returns POINT (nan nan) instead of POINT EMPTY
+ expected = "POINT (nan nan)"
+
+ if geom is None:
+ wkb = val_or_null(None)
+ else:
+ wkb = shapely.from_wkt(geom).wkb
+ if isinstance(eng, SedonaDB):
+ wkb = "0x" + wkb.hex()
+ elif isinstance(eng, PostGIS):
+ wkb = r"\x" + wkb.hex()
+ wkb = f"'{wkb}'::bytea"
+ else:
+ raise
+ eng.assert_query_result(f"SELECT ST_GeogFromWKB({wkb})", expected)
+
+
+@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
+@pytest.mark.parametrize(
+ ("geom"),
+ [
+ "POINT (1 1)",
+ "POINT EMPTY",
+ "LINESTRING EMPTY",
+ "POLYGON EMPTY",
+ "GEOMETRYCOLLECTION EMPTY",
+ "POLYGON ((0 0, 1 0, 1 1, 0 1, 0 0))",
+ "MULTILINESTRING ((0 0, 1 1), (1 1, 2 2))",
+ "GEOMETRYCOLLECTION (POINT (0 0), LINESTRING (0 0, 1 1), POLYGON ((0
0, 0 1, 1 1, 1 0, 0 0)))",
+ ],
+)
+def test_st_geomfromwkb(eng, geom):
+ eng = eng.create_or_skip()
+
+ expected = geom
+ if geom == "POINT EMPTY":
+ # arrow-c returns POINT (nan nan) instead of POINT EMPTY
+ expected = "POINT (nan nan)"
+
+ if geom is None:
+ wkb = val_or_null(None)
+ else:
+ wkb = shapely.from_wkt(geom).wkb
+ if isinstance(eng, SedonaDB):
+ wkb = "0x" + wkb.hex()
+ elif isinstance(eng, PostGIS):
+ wkb = r"\x" + wkb.hex()
+ wkb = f"'{wkb}'::bytea"
+ else:
+ raise
+ eng.assert_query_result(f"SELECT ST_GeomFromWKB({wkb})", expected)
+
+
@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
@pytest.mark.parametrize(
("geom", "expected"),
diff --git a/python/sedonadb/tests/functions/test_predicates.py
b/python/sedonadb/tests/functions/test_predicates.py
index 2ad4976..fafe9f5 100644
--- a/python/sedonadb/tests/functions/test_predicates.py
+++ b/python/sedonadb/tests/functions/test_predicates.py
@@ -15,7 +15,7 @@
# specific language governing permissions and limitations
# under the License.
import pytest
-from sedonadb.testing import geom_or_null, PostGIS, SedonaDB
+from sedonadb.testing import geom_or_null, PostGIS, SedonaDB, val_or_null
@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
@@ -150,6 +150,40 @@ def test_st_disjoint(eng, geom1, geom2, expected):
)
+@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
+@pytest.mark.parametrize(
+ ("geom1", "geom2", "distance", "expected"),
+ [
+ (None, "POINT (0 0)", 1.0, None),
+ ("POINT (1 1)", None, 1.0, None),
+ ("POINT (0 0)", "POINT (0 0)", None, None),
+ (None, None, None, None),
+ ("POINT (0 0)", "POINT (0 0)", 1.0, True),
+ ("POINT (0 0)", "POINT (5 0)", 2.0, False),
+ ("LINESTRING (0 0, 1 1)", "LINESTRING (2 2, 3 3)", 1.0, False),
+ ("LINESTRING (0 0, 1 1)", "LINESTRING (10 0, 11 1)", 2.0, False),
+ (
+ "POLYGON ((0 0, 1 0, 1 1, 0 1, 0 0))",
+ "POLYGON ((5 5, 6 5, 6 6, 5 6, 5 5))",
+ 6.0,
+ True,
+ ),
+ (
+ "GEOMETRYCOLLECTION (POINT (0 0), LINESTRING (0 0, 1 1))",
+ "GEOMETRYCOLLECTION (POINT (0 0), LINESTRING (0 0, 1 1))",
+ 1.0,
+ True,
+ ),
+ ],
+)
+def test_st_dwithin(eng, geom1, geom2, distance, expected):
+ eng = eng.create_or_skip()
+ eng.assert_query_result(
+ f"SELECT ST_DWithin({geom_or_null(geom1)}, {geom_or_null(geom2)},
{val_or_null(distance)})",
+ expected,
+ )
+
+
@pytest.mark.parametrize("eng", [SedonaDB, PostGIS])
@pytest.mark.parametrize(
("geom1", "geom2", "expected"),
