alamb commented on a change in pull request #524:
URL: https://github.com/apache/arrow-datafusion/pull/524#discussion_r684441579
##########
File path: python/tests/test_sql.py
##########
@@ -33,12 +33,63 @@ def test_no_table(ctx):
ctx.sql("SELECT a FROM b").collect()
-def test_register(ctx, tmp_path):
+def test_register_csv(ctx, tmp_path):
+ path = tmp_path / "test.csv"
+
+ table = pa.Table.from_arrays(
+ [
+ [1, 2, 3, 4],
+ ["a", "b", "c", "d"],
+ [1.1, 2.2, 3.3, 4.4],
+ ],
+ names=["int", "str", "float"],
+ )
+ pa.csv.write_csv(table, path)
+
+ ctx.register_csv("csv", path)
+ ctx.register_csv("csv1", str(path))
+ ctx.register_csv(
+ "csv2",
+ path,
+ has_header=True,
+ delimiter=",",
+ schema_infer_max_records=10,
+ )
+ alternative_schema = pa.schema(
+ [
+ ("some_int", pa.int16()),
+ ("some_bytes", pa.string()),
+ ("some_floats", pa.float32()),
+ ]
+ )
+ ctx.register_csv("csv3", path, schema=alternative_schema)
+
+ assert ctx.tables() == {"csv", "csv1", "csv2", "csv3"}
+
+ for table in ["csv", "csv1", "csv2"]:
+ result = ctx.sql(f"SELECT COUNT(int) FROM {table}").collect()
+ result = pa.Table.from_batches(result)
+ assert result.to_pydict() == {"COUNT(int)": [4]}
Review comment:
👍
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
