diff --git a/python/pyspark/sql/column.py b/python/pyspark/sql/column.py index ec059d6258439b3e2aeedb5fe918f247e9dde7e9..73c8672eff5b62f45746f88382b24ab51be6d9ce 100644 --- a/python/pyspark/sql/column.py +++ b/python/pyspark/sql/column.py @@ -180,7 +180,6 @@ class Column(object): # container operators __contains__ = _bin_op("contains") - __getitem__ = _bin_op("apply") # bitwise operators bitwiseOR = _bin_op("bitwiseOR") @@ -236,6 +235,14 @@ class Column(object): raise AttributeError(item) return self.getField(item) + def __getitem__(self, k): + if isinstance(k, slice): + if k.step is not None: + raise ValueError("slice with step is not supported.") + return self.substr(k.start, k.stop) + else: + return _bin_op("apply")(self, k) + def __iter__(self): raise TypeError("Column is not iterable") @@ -267,8 +274,6 @@ class Column(object): raise TypeError("Unexpected type: %s" % type(startPos)) return Column(jc) - __getslice__ = substr - @ignore_unicode_prefix @since(1.5) def isin(self, *cols): diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index ab9d3f6c94473b721b36aa8e34b81056d4977e68..d9d03337ffd99a6ce5f32a8653d44d6c6da2f567 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -874,6 +874,14 @@ class SQLTests(ReusedPySparkTestCase): self.assertTrue(all(isinstance(c, Column) for c in css)) self.assertTrue(isinstance(ci.cast(LongType()), Column)) + def test_column_getitem(self): + from pyspark.sql.functions import col + + self.assertIsInstance(col("foo")[1:3], Column) + self.assertIsInstance(col("foo")[0], Column) + self.assertIsInstance(col("foo")["bar"], Column) + self.assertRaises(ValueError, lambda: col("foo")[0:10:2]) + def test_column_select(self): df = self.df self.assertEqual(self.testData, df.select("*").collect())