This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
The following commit(s) were added to refs/heads/master by this push:
new b9e4497258 Rename `Schema::all_fields` to `flattened_fields` (#6001)
b9e4497258 is described below
commit b9e449725863a214a935b27b8b7056133f13fe6c
Author: 张林伟 <[email protected]>
AuthorDate: Tue Jul 9 02:55:23 2024 +0800
Rename `Schema::all_fields` to `flattened_fields` (#6001)
* Rename Schema::all_fields to flattened_fields
* Add doc example for Schema::flattened_fields
* fmt doc example
* Update arrow-schema/src/schema.rs
---------
Co-authored-by: Andrew Lamb <[email protected]>
---
arrow-flight/tests/flight_sql_client_cli.rs | 2 +-
arrow-ipc/src/writer.rs | 2 +-
arrow-json/src/reader/mod.rs | 2 +-
arrow-schema/src/schema.rs | 44 ++++++++++++++++++++++++++++-
parquet/src/arrow/async_reader/mod.rs | 2 +-
5 files changed, 47 insertions(+), 5 deletions(-)
diff --git a/arrow-flight/tests/flight_sql_client_cli.rs
b/arrow-flight/tests/flight_sql_client_cli.rs
index 50a4ec0d8c..317eb39004 100644
--- a/arrow-flight/tests/flight_sql_client_cli.rs
+++ b/arrow-flight/tests/flight_sql_client_cli.rs
@@ -568,7 +568,7 @@ impl FlightSqlService for FlightSqlServiceImpl {
.try_collect::<Vec<_>>()
.await?;
- for (left, right) in
parameters[0].schema().all_fields().iter().zip(vec![
+ for (left, right) in
parameters[0].schema().flattened_fields().iter().zip(vec![
Field::new("$1", DataType::Utf8, false),
Field::new("$2", DataType::Int64, true),
]) {
diff --git a/arrow-ipc/src/writer.rs b/arrow-ipc/src/writer.rs
index c078219599..d0a78ca270 100644
--- a/arrow-ipc/src/writer.rs
+++ b/arrow-ipc/src/writer.rs
@@ -411,7 +411,7 @@ impl IpcDataGenerator {
write_options: &IpcWriteOptions,
) -> Result<(Vec<EncodedData>, EncodedData), ArrowError> {
let schema = batch.schema();
- let mut encoded_dictionaries =
Vec::with_capacity(schema.all_fields().len());
+ let mut encoded_dictionaries =
Vec::with_capacity(schema.flattened_fields().len());
let mut dict_id = dictionary_tracker.dict_ids.clone().into_iter();
diff --git a/arrow-json/src/reader/mod.rs b/arrow-json/src/reader/mod.rs
index 0a50cfac65..3e1c5d2fc8 100644
--- a/arrow-json/src/reader/mod.rs
+++ b/arrow-json/src/reader/mod.rs
@@ -289,7 +289,7 @@ impl ReaderBuilder {
let decoder = make_decoder(data_type, self.coerce_primitive,
self.strict_mode, nullable)?;
- let num_fields = self.schema.all_fields().len();
+ let num_fields = self.schema.flattened_fields().len();
Ok(Decoder {
decoder,
diff --git a/arrow-schema/src/schema.rs b/arrow-schema/src/schema.rs
index 3bb076aa54..9a9ef45d8b 100644
--- a/arrow-schema/src/schema.rs
+++ b/arrow-schema/src/schema.rs
@@ -324,11 +324,53 @@ impl Schema {
}
/// Returns a vector with references to all fields (including nested
fields)
+ ///
+ /// # Example
+ ///
+ /// ```
+ /// use std::sync::Arc;
+ /// use arrow_schema::{DataType, Field, Fields, Schema};
+ ///
+ /// let f1 = Arc::new(Field::new("a", DataType::Boolean, false));
+ ///
+ /// let f2_inner = Arc::new(Field::new("b_inner", DataType::Int8, false));
+ /// let f2 = Arc::new(Field::new("b", DataType::List(f2_inner.clone()),
false));
+ ///
+ /// let f3_inner1 = Arc::new(Field::new("c_inner1", DataType::Int8,
false));
+ /// let f3_inner2 = Arc::new(Field::new("c_inner2", DataType::Int8,
false));
+ /// let f3 = Arc::new(Field::new(
+ /// "c",
+ /// DataType::Struct(vec![f3_inner1.clone(),
f3_inner2.clone()].into()),
+ /// false
+ /// ));
+ ///
+ /// let mut schema = Schema::new(vec![
+ /// f1.clone(), f2.clone(), f3.clone()
+ /// ]);
+ /// assert_eq!(
+ /// schema.flattened_fields(),
+ /// vec![
+ /// f1.as_ref(),
+ /// f2.as_ref(),
+ /// f2_inner.as_ref(),
+ /// f3.as_ref(),
+ /// f3_inner1.as_ref(),
+ /// f3_inner2.as_ref()
+ /// ]
+ /// );
+ /// ```
#[inline]
- pub fn all_fields(&self) -> Vec<&Field> {
+ pub fn flattened_fields(&self) -> Vec<&Field> {
self.fields.iter().flat_map(|f| f.fields()).collect()
}
+ /// Returns a vector with references to all fields (including nested
fields)
+ #[deprecated(since = "52.2.0", note = "Use `flattened_fields` instead")]
+ #[inline]
+ pub fn all_fields(&self) -> Vec<&Field> {
+ self.flattened_fields()
+ }
+
/// Returns an immutable reference of a specific [`Field`] instance
selected using an
/// offset within the internal `fields` vector.
///
diff --git a/parquet/src/arrow/async_reader/mod.rs
b/parquet/src/arrow/async_reader/mod.rs
index 0a72583b90..e4205b7ef2 100644
--- a/parquet/src/arrow/async_reader/mod.rs
+++ b/parquet/src/arrow/async_reader/mod.rs
@@ -1650,7 +1650,7 @@ mod tests {
#[tokio::test]
async fn test_parquet_record_batch_stream_schema() {
fn get_all_field_names(schema: &Schema) -> Vec<&String> {
- schema.all_fields().iter().map(|f| f.name()).collect()
+ schema.flattened_fields().iter().map(|f| f.name()).collect()
}
// ParquetRecordBatchReaderBuilder::schema differs from
