alamb commented on code in PR #9197:
URL: https://github.com/apache/arrow-datafusion/pull/9197#discussion_r1486271065
##########
datafusion/core/tests/dataframe/mod.rs:
##########
@@ -1431,6 +1432,89 @@ async fn unnest_analyze_metrics() -> Result<()> {
Ok(())
}
+#[tokio::test]
+async fn test_read_batches() -> Result<()> {
+ let config = SessionConfig::new();
+ let runtime = Arc::new(RuntimeEnv::default());
+ let state = SessionState::new_with_config_rt(config, runtime);
+ let ctx = SessionContext::new_with_state(state);
+
+ let schema = Arc::new(Schema::new(vec![
+ Field::new("id", DataType::Int32, false),
+ Field::new("number", DataType::Float32, false),
+ ]));
+
+ let batches = vec![
+ RecordBatch::try_new(
+ schema.clone(),
+ vec![
+ Arc::new(Int32Array::from(vec![1, 2, 3, 4, 5])),
+ Arc::new(Float32Array::from(vec![1.12, 3.40, 2.33, 9.10,
6.66])),
+ ],
+ )
+ .unwrap(),
+ RecordBatch::try_new(
+ schema.clone(),
+ vec![
+ Arc::new(Int32Array::from(vec![3, 4, 5])),
+ Arc::new(Float32Array::from(vec![1.11, 2.22, 3.33])),
+ ],
+ )
+ .unwrap(),
+ RecordBatch::try_new(
Review Comment:
Minor: I suggest making the test shorter by feeding in 2 batches rather than
5
##########
datafusion/core/src/execution/context/mod.rs:
##########
@@ -934,7 +934,26 @@ impl SessionContext {
.build()?,
))
}
-
+ /// Create a [`DataFrame`] for reading a [`Vec[`RecordBatch`]`]
+ pub fn read_batches(
+ &self,
+ batches: impl IntoIterator<Item = RecordBatch>,
+ ) -> Result<DataFrame> {
+ // check schema uniqueness
+ let mut batches = batches.into_iter().peekable();
+ let schema: SchemaRef = batches.peek().unwrap().schema().clone();
Review Comment:
Perhaps something like
```suggestion
let schema: SchemaRef = if let Some(schema) = batches.peek() {
schema.clone()
} else {
// use empty schema)
Arc::new(Schema::new())
};
```
--
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]
