revert branch UNPICK

Author: kosiew

docs/source/user-guide/dataframe/index.rst

@@ -145,31 +145,10 @@ To materialize the results of your DataFrame operations:
     
     # Display results
     df.show()                         # Print tabular format to console
-
+    
     # Count rows
     count = df.count()
 
-PyArrow Streaming
------------------
-
-DataFusion DataFrames implement the ``__arrow_c_stream__`` protocol, enabling
-zero-copy streaming into libraries like `PyArrow <https://arrow.apache.org/>`_.
-Earlier versions eagerly converted the entire DataFrame when exporting to
-PyArrow, which could exhaust memory on large datasets. With streaming, batches
-are produced lazily so you can process arbitrarily large results without
-out-of-memory errors.
-
-.. code-block:: python
-
-    import pyarrow as pa
-
-    # Create a PyArrow RecordBatchReader without materializing all batches
-    reader = pa.RecordBatchReader._import_from_c(df.__arrow_c_stream__())
-    for batch in reader:
-        ...  # process each batch as it is produced
-
-See :doc:`../io/arrow` for additional details on the Arrow interface.
-
 HTML Rendering
 --------------
 

python/tests/test_dataframe.py

@@ -1582,29 +1582,6 @@ def test_empty_to_arrow_table(df):
     assert set(pyarrow_table.column_names) == {"a", "b", "c"}
 
 
-def test_arrow_c_stream_to_table(monkeypatch):
-    ctx = SessionContext()
-
-    # Create a DataFrame with two separate record batches
-    batch1 = pa.record_batch([pa.array([1])], names=["a"])
-    batch2 = pa.record_batch([pa.array([2])], names=["a"])
-    df = ctx.create_dataframe([[batch1], [batch2]])
-
-    # Fail if the DataFrame is pre-collected
-    def fail_collect(self):  # pragma: no cover - failure path
-        msg = "collect should not be called"
-        raise AssertionError(msg)
-
-    monkeypatch.setattr(DataFrame, "collect", fail_collect)
-
-    table = pa.Table.from_batches(df)
-    expected = pa.Table.from_batches([batch1, batch2])
-
-    assert table.equals(expected)
-    assert table.schema == df.schema()
-    assert table.column("a").num_chunks == 2
-
-
 def test_to_pylist(df):
     # Convert datafusion dataframe to Python list
     pylist = df.to_pylist()

src/dataframe.rs

@@ -19,13 +19,13 @@ use std::collections::HashMap;
 use std::ffi::CString;
 use std::sync::Arc;
 
-use arrow::array::{new_null_array, RecordBatch, RecordBatchReader};
+use arrow::array::{new_null_array, RecordBatch, RecordBatchIterator, RecordBatchReader};
 use arrow::compute::can_cast_types;
 use arrow::error::ArrowError;
 use arrow::ffi::FFI_ArrowSchema;
 use arrow::ffi_stream::FFI_ArrowArrayStream;
 use arrow::pyarrow::FromPyArrow;
-use datafusion::arrow::datatypes::{Schema, SchemaRef};
+use datafusion::arrow::datatypes::Schema;
 use datafusion::arrow::pyarrow::{PyArrowType, ToPyArrow};
 use datafusion::arrow::util::pretty;
 use datafusion::common::UnnestOptions;
@@ -42,7 +42,7 @@ use pyo3::exceptions::PyValueError;
 use pyo3::prelude::*;
 use pyo3::pybacked::PyBackedStr;
 use pyo3::types::{PyCapsule, PyList, PyTuple, PyTupleMethods};
-use tokio::{runtime::Handle, task::JoinHandle};
+use tokio::task::JoinHandle;
 
 use crate::catalog::PyTable;
 use crate::errors::{py_datafusion_err, to_datafusion_err, PyDataFusionError};
@@ -354,41 +354,6 @@ impl PyDataFrame {
     }
 }
 
-struct DataFrameStreamReader {
-    stream: SendableRecordBatchStream,
-    runtime: Handle,
-    schema: SchemaRef,
-    projection: Option<SchemaRef>,
-}
-
-impl Iterator for DataFrameStreamReader {
-    type Item = Result<RecordBatch, ArrowError>;
-
-    fn next(&mut self) -> Option<Self::Item> {
-        match self.runtime.block_on(self.stream.next()) {
-            Some(Ok(batch)) => {
-                let batch = if let Some(ref schema) = self.projection {
-                    match record_batch_into_schema(batch, schema.as_ref()) {
-                        Ok(b) => b,
-                        Err(e) => return Some(Err(e)),
-                    }
-                } else {
-                    batch
-                };
-                Some(Ok(batch))
-            }
-            Some(Err(e)) => Some(Err(ArrowError::ExternalError(Box::new(e)))),
-            None => None,
-        }
-    }
-}
-
-impl RecordBatchReader for DataFrameStreamReader {
-    fn schema(&self) -> SchemaRef {
-        self.schema.clone()
-    }
-}
-
 #[pymethods]
 impl PyDataFrame {
     /// Enable selection for `df[col]`, `df[col1, col2, col3]`, and `df[[col1, col2, col3]]`
@@ -914,14 +879,8 @@ impl PyDataFrame {
         py: Python<'py>,
         requested_schema: Option<Bound<'py, PyCapsule>>,
     ) -> PyDataFusionResult<Bound<'py, PyCapsule>> {
-        let rt = &get_tokio_runtime().0;
-        let df = self.df.as_ref().clone();
-        let fut: JoinHandle<datafusion::common::Result<SendableRecordBatchStream>> =
-            rt.spawn(async move { df.execute_stream().await });
-        let stream = wait_for_future(py, async { fut.await.map_err(to_datafusion_err) })???;
-
+        let mut batches = wait_for_future(py, self.df.as_ref().clone().collect())??;
         let mut schema: Schema = self.df.schema().to_owned().into();
-        let mut projection: Option<SchemaRef> = None;
 
         if let Some(schema_capsule) = requested_schema {
             validate_pycapsule(&schema_capsule, "arrow_schema")?;
@@ -930,17 +889,16 @@ impl PyDataFrame {
             let desired_schema = Schema::try_from(schema_ptr)?;
 
             schema = project_schema(schema, desired_schema)?;
-            projection = Some(Arc::new(schema.clone()));
+
+            batches = batches
+                .into_iter()
+                .map(|record_batch| record_batch_into_schema(record_batch, &schema))
+                .collect::<Result<Vec<RecordBatch>, ArrowError>>()?;
         }
 
-        let schema_ref = projection.clone().unwrap_or_else(|| Arc::new(schema));
+        let batches_wrapped = batches.into_iter().map(Ok);
 
-        let reader = DataFrameStreamReader {
-            stream,
-            runtime: rt.handle().clone(),
-            schema: schema_ref,
-            projection,
-        };
+        let reader = RecordBatchIterator::new(batches_wrapped, Arc::new(schema));
         let reader: Box<dyn RecordBatchReader + Send> = Box::new(reader);
 
         let ffi_stream = FFI_ArrowArrayStream::new(reader);