icexelloss commented on code in PR #34373:
URL: https://github.com/apache/arrow/pull/34373#discussion_r1120170593
##########
python/pyarrow/tests/test_udf.py:
##########
@@ -613,3 +614,180 @@ def test_udt_datasource1_generator():
def test_udt_datasource1_exception():
with pytest.raises(RuntimeError, match='datasource1_exception'):
_test_datasource1_udt(datasource1_exception)
+
+
[email protected]("use_threads", [True, False])
+def test_udf_via_substrait(unary_func_fixture, use_threads):
+ test_table_1 = pa.Table.from_pydict({"t": [1, 2, 3], "p": [4, 5, 6]})
+
+ def table_provider(names, _):
+ if not names:
+ raise Exception("No names provided")
+ elif names[0] == "t1":
+ return test_table_1
+ else:
+ raise Exception("Unrecognized table name")
+
+ substrait_query = """
+ {
+ "extensionUris": [
+ {
+ "extensionUriAnchor": 1
+ },
+ {
+ "extensionUriAnchor": 2,
+ "uri": "urn:arrow:substrait_simple_extension_function"
+ }
+ ],
+ "extensions": [
+ {
+ "extensionFunction": {
+ "extensionUriReference": 2,
+ "functionAnchor": 1,
+ "name": "y=x+1"
+ }
+ }
+ ],
+ "relations": [
+ {
+ "root": {
+ "input": {
+ "project": {
Review Comment:
Not a very good reason, mostly because I was reusing my existing code to
generate the json that has two projections:
```
dt = ...
dt = dt[['p', 't']]
dt = dt.assign(p2=...)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
