This is an automated email from the ASF dual-hosted git repository.
github-merge-queue[bot] pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new aca4d1377b feat: Add Protobuf support for Explain node (#21994)
aca4d1377b is described below
commit aca4d1377bf9785e6fa9a154c579cc761ca7b54b
Author: Daniel Tu <[email protected]>
AuthorDate: Thu May 7 11:16:10 2026 -0700
feat: Add Protobuf support for Explain node (#21994)
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->
- Closes #.
## Rationale for this change
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->
`EXPLAIN FORMAT TREE` is supported in logical plans, but protobuf
serialization did not preserve the explain format.
In Datafusion Ballista, we need the format field to generate
corresponding distributed plan.
https://github.com/apache/datafusion-ballista/issues/1627#issuecomment-4355988101
## What changes are included in this PR?
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
- Add `ExplainFormat` to protobuf common definitions.
- Add the `format` field to protobuf `ExplainNode`.
- Regenerate protobuf code.
## Are these changes tested?
Yes, we add a roundtrip test for `EXPLAIN FORMAT TREE`.
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
## Are there any user-facing changes?
No
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
---------
Co-authored-by: Kumar Ujjawal <[email protected]>
---
.../proto-common/proto/datafusion_common.proto | 7 ++
datafusion/proto-common/src/generated/pbjson.rs | 77 ++++++++++++++++++++++
datafusion/proto-common/src/generated/prost.rs | 32 +++++++++
datafusion/proto/proto/datafusion.proto | 1 +
.../proto/src/generated/datafusion_proto_common.rs | 32 +++++++++
datafusion/proto/src/generated/pbjson.rs | 19 ++++++
datafusion/proto/src/generated/prost.rs | 2 +
datafusion/proto/src/logical_plan/mod.rs | 31 ++++++++-
.../proto/tests/cases/roundtrip_logical_plan.rs | 22 +++++++
9 files changed, 222 insertions(+), 1 deletion(-)
diff --git a/datafusion/proto-common/proto/datafusion_common.proto
b/datafusion/proto-common/proto/datafusion_common.proto
index 87bcf3c144..5f4ba2b9ac 100644
--- a/datafusion/proto-common/proto/datafusion_common.proto
+++ b/datafusion/proto-common/proto/datafusion_common.proto
@@ -669,3 +669,10 @@ message ColumnStats {
Precision distinct_count = 4;
Precision byte_size = 6;
}
+
+enum ExplainFormat {
+ EXPLAIN_FORMAT_INDENT = 0;
+ EXPLAIN_FORMAT_TREE = 1;
+ EXPLAIN_FORMAT_PGJSON = 2;
+ EXPLAIN_FORMAT_GRAPHVIZ = 3;
+}
\ No newline at end of file
diff --git a/datafusion/proto-common/src/generated/pbjson.rs
b/datafusion/proto-common/src/generated/pbjson.rs
index 6112c55793..f6b5bbeaf3 100644
--- a/datafusion/proto-common/src/generated/pbjson.rs
+++ b/datafusion/proto-common/src/generated/pbjson.rs
@@ -4116,6 +4116,83 @@ impl<'de> serde::Deserialize<'de> for EmptyMessage {
deserializer.deserialize_struct("datafusion_common.EmptyMessage",
FIELDS, GeneratedVisitor)
}
}
+impl serde::Serialize for ExplainFormat {
+ #[allow(deprecated)]
+ fn serialize<S>(&self, serializer: S) -> std::result::Result<S::Ok,
S::Error>
+ where
+ S: serde::Serializer,
+ {
+ let variant = match self {
+ Self::Indent => "EXPLAIN_FORMAT_INDENT",
+ Self::Tree => "EXPLAIN_FORMAT_TREE",
+ Self::Pgjson => "EXPLAIN_FORMAT_PGJSON",
+ Self::Graphviz => "EXPLAIN_FORMAT_GRAPHVIZ",
+ };
+ serializer.serialize_str(variant)
+ }
+}
+impl<'de> serde::Deserialize<'de> for ExplainFormat {
+ #[allow(deprecated)]
+ fn deserialize<D>(deserializer: D) -> std::result::Result<Self, D::Error>
+ where
+ D: serde::Deserializer<'de>,
+ {
+ const FIELDS: &[&str] = &[
+ "EXPLAIN_FORMAT_INDENT",
+ "EXPLAIN_FORMAT_TREE",
+ "EXPLAIN_FORMAT_PGJSON",
+ "EXPLAIN_FORMAT_GRAPHVIZ",
+ ];
+
+ struct GeneratedVisitor;
+
+ impl serde::de::Visitor<'_> for GeneratedVisitor {
+ type Value = ExplainFormat;
+
+ fn expecting(&self, formatter: &mut std::fmt::Formatter<'_>) ->
std::fmt::Result {
+ write!(formatter, "expected one of: {:?}", &FIELDS)
+ }
+
+ fn visit_i64<E>(self, v: i64) -> std::result::Result<Self::Value,
E>
+ where
+ E: serde::de::Error,
+ {
+ i32::try_from(v)
+ .ok()
+ .and_then(|x| x.try_into().ok())
+ .ok_or_else(|| {
+
serde::de::Error::invalid_value(serde::de::Unexpected::Signed(v), &self)
+ })
+ }
+
+ fn visit_u64<E>(self, v: u64) -> std::result::Result<Self::Value,
E>
+ where
+ E: serde::de::Error,
+ {
+ i32::try_from(v)
+ .ok()
+ .and_then(|x| x.try_into().ok())
+ .ok_or_else(|| {
+
serde::de::Error::invalid_value(serde::de::Unexpected::Unsigned(v), &self)
+ })
+ }
+
+ fn visit_str<E>(self, value: &str) ->
std::result::Result<Self::Value, E>
+ where
+ E: serde::de::Error,
+ {
+ match value {
+ "EXPLAIN_FORMAT_INDENT" => Ok(ExplainFormat::Indent),
+ "EXPLAIN_FORMAT_TREE" => Ok(ExplainFormat::Tree),
+ "EXPLAIN_FORMAT_PGJSON" => Ok(ExplainFormat::Pgjson),
+ "EXPLAIN_FORMAT_GRAPHVIZ" => Ok(ExplainFormat::Graphviz),
+ _ => Err(serde::de::Error::unknown_variant(value, FIELDS)),
+ }
+ }
+ }
+ deserializer.deserialize_any(GeneratedVisitor)
+ }
+}
impl serde::Serialize for Field {
#[allow(deprecated)]
fn serialize<S>(&self, serializer: S) -> std::result::Result<S::Ok,
S::Error>
diff --git a/datafusion/proto-common/src/generated/prost.rs
b/datafusion/proto-common/src/generated/prost.rs
index 4472ff0cde..f09af1db34 100644
--- a/datafusion/proto-common/src/generated/prost.rs
+++ b/datafusion/proto-common/src/generated/prost.rs
@@ -1313,3 +1313,35 @@ impl PrecisionInfo {
}
}
}
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, PartialOrd, Ord,
::prost::Enumeration)]
+#[repr(i32)]
+pub enum ExplainFormat {
+ Indent = 0,
+ Tree = 1,
+ Pgjson = 2,
+ Graphviz = 3,
+}
+impl ExplainFormat {
+ /// String value of the enum field names used in the ProtoBuf definition.
+ ///
+ /// The values are not transformed in any way and thus are considered
stable
+ /// (if the ProtoBuf definition does not change) and safe for programmatic
use.
+ pub fn as_str_name(&self) -> &'static str {
+ match self {
+ Self::Indent => "EXPLAIN_FORMAT_INDENT",
+ Self::Tree => "EXPLAIN_FORMAT_TREE",
+ Self::Pgjson => "EXPLAIN_FORMAT_PGJSON",
+ Self::Graphviz => "EXPLAIN_FORMAT_GRAPHVIZ",
+ }
+ }
+ /// Creates an enum from field names used in the ProtoBuf definition.
+ pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
+ match value {
+ "EXPLAIN_FORMAT_INDENT" => Some(Self::Indent),
+ "EXPLAIN_FORMAT_TREE" => Some(Self::Tree),
+ "EXPLAIN_FORMAT_PGJSON" => Some(Self::Pgjson),
+ "EXPLAIN_FORMAT_GRAPHVIZ" => Some(Self::Graphviz),
+ _ => None,
+ }
+ }
+}
diff --git a/datafusion/proto/proto/datafusion.proto
b/datafusion/proto/proto/datafusion.proto
index 511e8eb1b0..865887d41e 100644
--- a/datafusion/proto/proto/datafusion.proto
+++ b/datafusion/proto/proto/datafusion.proto
@@ -229,6 +229,7 @@ message AnalyzeNode {
message ExplainNode {
LogicalPlanNode input = 1;
bool verbose = 2;
+ datafusion_common.ExplainFormat format = 3;
}
message AggregateNode {
diff --git a/datafusion/proto/src/generated/datafusion_proto_common.rs
b/datafusion/proto/src/generated/datafusion_proto_common.rs
index 4472ff0cde..f09af1db34 100644
--- a/datafusion/proto/src/generated/datafusion_proto_common.rs
+++ b/datafusion/proto/src/generated/datafusion_proto_common.rs
@@ -1313,3 +1313,35 @@ impl PrecisionInfo {
}
}
}
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, PartialOrd, Ord,
::prost::Enumeration)]
+#[repr(i32)]
+pub enum ExplainFormat {
+ Indent = 0,
+ Tree = 1,
+ Pgjson = 2,
+ Graphviz = 3,
+}
+impl ExplainFormat {
+ /// String value of the enum field names used in the ProtoBuf definition.
+ ///
+ /// The values are not transformed in any way and thus are considered
stable
+ /// (if the ProtoBuf definition does not change) and safe for programmatic
use.
+ pub fn as_str_name(&self) -> &'static str {
+ match self {
+ Self::Indent => "EXPLAIN_FORMAT_INDENT",
+ Self::Tree => "EXPLAIN_FORMAT_TREE",
+ Self::Pgjson => "EXPLAIN_FORMAT_PGJSON",
+ Self::Graphviz => "EXPLAIN_FORMAT_GRAPHVIZ",
+ }
+ }
+ /// Creates an enum from field names used in the ProtoBuf definition.
+ pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
+ match value {
+ "EXPLAIN_FORMAT_INDENT" => Some(Self::Indent),
+ "EXPLAIN_FORMAT_TREE" => Some(Self::Tree),
+ "EXPLAIN_FORMAT_PGJSON" => Some(Self::Pgjson),
+ "EXPLAIN_FORMAT_GRAPHVIZ" => Some(Self::Graphviz),
+ _ => None,
+ }
+ }
+}
diff --git a/datafusion/proto/src/generated/pbjson.rs
b/datafusion/proto/src/generated/pbjson.rs
index c05d3283ea..b8639afd04 100644
--- a/datafusion/proto/src/generated/pbjson.rs
+++ b/datafusion/proto/src/generated/pbjson.rs
@@ -6197,6 +6197,9 @@ impl serde::Serialize for ExplainNode {
if self.verbose {
len += 1;
}
+ if self.format != 0 {
+ len += 1;
+ }
let mut struct_ser =
serializer.serialize_struct("datafusion.ExplainNode", len)?;
if let Some(v) = self.input.as_ref() {
struct_ser.serialize_field("input", v)?;
@@ -6204,6 +6207,11 @@ impl serde::Serialize for ExplainNode {
if self.verbose {
struct_ser.serialize_field("verbose", &self.verbose)?;
}
+ if self.format != 0 {
+ let v =
super::datafusion_common::ExplainFormat::try_from(self.format)
+ .map_err(|_| serde::ser::Error::custom(format!("Invalid
variant {}", self.format)))?;
+ struct_ser.serialize_field("format", &v)?;
+ }
struct_ser.end()
}
}
@@ -6216,12 +6224,14 @@ impl<'de> serde::Deserialize<'de> for ExplainNode {
const FIELDS: &[&str] = &[
"input",
"verbose",
+ "format",
];
#[allow(clippy::enum_variant_names)]
enum GeneratedField {
Input,
Verbose,
+ Format,
}
impl<'de> serde::Deserialize<'de> for GeneratedField {
fn deserialize<D>(deserializer: D) ->
std::result::Result<GeneratedField, D::Error>
@@ -6245,6 +6255,7 @@ impl<'de> serde::Deserialize<'de> for ExplainNode {
match value {
"input" => Ok(GeneratedField::Input),
"verbose" => Ok(GeneratedField::Verbose),
+ "format" => Ok(GeneratedField::Format),
_ => Err(serde::de::Error::unknown_field(value,
FIELDS)),
}
}
@@ -6266,6 +6277,7 @@ impl<'de> serde::Deserialize<'de> for ExplainNode {
{
let mut input__ = None;
let mut verbose__ = None;
+ let mut format__ = None;
while let Some(k) = map_.next_key()? {
match k {
GeneratedField::Input => {
@@ -6280,11 +6292,18 @@ impl<'de> serde::Deserialize<'de> for ExplainNode {
}
verbose__ = Some(map_.next_value()?);
}
+ GeneratedField::Format => {
+ if format__.is_some() {
+ return
Err(serde::de::Error::duplicate_field("format"));
+ }
+ format__ =
Some(map_.next_value::<super::datafusion_common::ExplainFormat>()? as i32);
+ }
}
}
Ok(ExplainNode {
input: input__,
verbose: verbose__.unwrap_or_default(),
+ format: format__.unwrap_or_default(),
})
}
}
diff --git a/datafusion/proto/src/generated/prost.rs
b/datafusion/proto/src/generated/prost.rs
index af9b1404bb..b742e82ea2 100644
--- a/datafusion/proto/src/generated/prost.rs
+++ b/datafusion/proto/src/generated/prost.rs
@@ -351,6 +351,8 @@ pub struct ExplainNode {
pub input:
::core::option::Option<::prost::alloc::boxed::Box<LogicalPlanNode>>,
#[prost(bool, tag = "2")]
pub verbose: bool,
+ #[prost(enumeration = "super::datafusion_common::ExplainFormat", tag =
"3")]
+ pub format: i32,
}
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct AggregateNode {
diff --git a/datafusion/proto/src/logical_plan/mod.rs
b/datafusion/proto/src/logical_plan/mod.rs
index 7ae5cbeed3..8228e8e6f2 100644
--- a/datafusion/proto/src/logical_plan/mod.rs
+++ b/datafusion/proto/src/logical_plan/mod.rs
@@ -37,6 +37,7 @@ use arrow::datatypes::{DataType, Field, Schema,
SchemaBuilder, SchemaRef};
use datafusion_catalog::cte_worktable::CteWorkTable;
use datafusion_catalog::empty::EmptyTable;
use datafusion_common::file_options::file_type::FileType;
+use datafusion_common::format::ExplainFormat;
use datafusion_common::{
Result, TableReference, ToDFSchema, assert_or_internal_err, context,
internal_datafusion_err, internal_err, not_impl_err, plan_err,
@@ -801,8 +802,25 @@ impl AsLogicalPlan for LogicalPlanNode {
LogicalPlanType::Explain(explain) => {
let input: LogicalPlan =
into_logical_plan!(explain.input, ctx, extension_codec)?;
+ let pb_format =
protobuf::ExplainFormat::try_from(explain.format)
+ .map_err(|_| {
+ proto_error(format!(
+ "Received an ExplainNode message with unknown
ExplainFormat {}",
+ explain.format
+ ))
+ })?;
+ let explain_format = match pb_format {
+ protobuf::ExplainFormat::Indent => ExplainFormat::Indent,
+ protobuf::ExplainFormat::Tree => ExplainFormat::Tree,
+ protobuf::ExplainFormat::Pgjson =>
ExplainFormat::PostgresJSON,
+ protobuf::ExplainFormat::Graphviz =>
ExplainFormat::Graphviz,
+ };
+ let explain_option =
+ datafusion_expr::logical_plan::ExplainOption::default()
+ .with_verbose(explain.verbose)
+ .with_format(explain_format);
LogicalPlanBuilder::from(input)
- .explain(explain.verbose, false)?
+ .explain_option_format(explain_option)?
.build()
}
LogicalPlanType::SubqueryAlias(aliased_relation) => {
@@ -1758,6 +1776,17 @@ impl AsLogicalPlan for LogicalPlanNode {
protobuf::ExplainNode {
input: Some(Box::new(input)),
verbose: a.verbose,
+ format: match &a.explain_format {
+ ExplainFormat::Indent =>
protobuf::ExplainFormat::Indent,
+ ExplainFormat::Tree =>
protobuf::ExplainFormat::Tree,
+ ExplainFormat::PostgresJSON => {
+ protobuf::ExplainFormat::Pgjson
+ }
+ ExplainFormat::Graphviz => {
+ protobuf::ExplainFormat::Graphviz
+ }
+ }
+ .into(),
},
))),
})
diff --git a/datafusion/proto/tests/cases/roundtrip_logical_plan.rs
b/datafusion/proto/tests/cases/roundtrip_logical_plan.rs
index dbc95536f0..3e79ddab72 100644
--- a/datafusion/proto/tests/cases/roundtrip_logical_plan.rs
+++ b/datafusion/proto/tests/cases/roundtrip_logical_plan.rs
@@ -68,6 +68,7 @@ use datafusion::physical_expr::PhysicalExpr;
use datafusion::prelude::*;
use datafusion::test_util::{TestTableFactory, TestTableProvider};
use datafusion_common::config::TableOptions;
+use datafusion_common::format::ExplainFormat;
use datafusion_common::scalar::ScalarStructBuilder;
use datafusion_common::{
DFSchema, DFSchemaRef, DataFusionError, Result, ScalarValue,
TableReference,
@@ -277,6 +278,27 @@ async fn roundtrip_custom_memory_tables() -> Result<()> {
Ok(())
}
+#[tokio::test]
+async fn roundtrip_explain_format_tree() -> Result<()> {
+ let ctx = SessionContext::new();
+ let plan = ctx
+ .state()
+ .create_logical_plan("EXPLAIN FORMAT TREE SELECT 1")
+ .await?;
+
+ let bytes = logical_plan_to_bytes(&plan)?;
+ let logical_round_trip = logical_plan_from_bytes(&bytes, &ctx.task_ctx())?;
+
+ match logical_round_trip {
+ LogicalPlan::Explain(explain) => {
+ assert_eq!(explain.explain_format, ExplainFormat::Tree);
+ }
+ plan => panic!("expected Explain plan, got {plan:?}"),
+ }
+
+ Ok(())
+}
+
#[tokio::test]
async fn roundtrip_custom_listing_tables() -> Result<()> {
let ctx = SessionContext::new();
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
