This is an automated email from the ASF dual-hosted git repository.
xudong963 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 081e95cc70 doc: add diagram to describe how DataSource, FileSource,
and DataSourceExec are related (#16181)
081e95cc70 is described below
commit 081e95cc707e9949900ee254552f104e1b9d05ee
Author: Andy Yen <38731840+onlyjackfr...@users.noreply.github.com>
AuthorDate: Thu May 29 00:11:43 2025 +0800
doc: add diagram to describe how DataSource, FileSource, and DataSourceExec
are related (#16181)
* doc: add diagram to describe how DataSource, FileSource, and
DataSourceExec are related
* update link
* format doc
* fix ci doc test
* update doc
* update diagram
---------
Co-authored-by: Andrew Lamb <and...@nerdnetworks.org>
---
datafusion/datasource/src/source.rs | 54 ++++++++++++++++++++++++++++++++++++-
1 file changed, 53 insertions(+), 1 deletion(-)
diff --git a/datafusion/datasource/src/source.rs
b/datafusion/datasource/src/source.rs
index 1afe3b3edb..30ecc38709 100644
--- a/datafusion/datasource/src/source.rs
+++ b/datafusion/datasource/src/source.rs
@@ -58,8 +58,60 @@ use datafusion_physical_plan::filter_pushdown::{
/// Requires `Debug` to assist debugging
///
/// [`FileScanConfig`]:
https://docs.rs/datafusion/latest/datafusion/datasource/physical_plan/struct.FileScanConfig.html
-/// [`MemorySourceConfig`]:
https://docs.rs/datafusion/latest//datafusion/datasource/memory/struct.MemorySourceConfig.html
+/// [`MemorySourceConfig`]:
https://docs.rs/datafusion/latest/datafusion/datasource/memory/struct.MemorySourceConfig.html
/// [`FileSource`]: crate::file::FileSource
+/// [`FileFormat``]:
https://docs.rs/datafusion/latest/datafusion/datasource/file_format/index.html
+/// [`TableProvider`]:
https://docs.rs/datafusion/latest/datafusion/catalog/trait.TableProvider.html
+///
+/// The following diagram shows how DataSource, FileSource, and DataSourceExec
are related
+/// ```text
+/// ┌─────────────────────┐
-----► execute path
+/// │ │
┄┄┄┄┄► init path
+/// │ DataSourceExec │
+/// │ │
+/// └───────▲─────────────┘
+/// ┊ │
+/// ┊ │
+/// ┌──────────▼──────────┐
┌──────────-──────────┐
+/// │ │ |
|
+/// │ DataSource(trait) │ |
TableProvider(trait)|
+/// │ │ |
|
+/// └───────▲─────────────┘
└─────────────────────┘
+/// ┊ │
┊
+/// ┌───────────────┿──┴────────────────┐
┊
+/// | ┌┄┄┄┄┄┄┄┄┄┄┄┘ |
┊
+/// | ┊ |
┊
+/// ┌──────────▼──────────┐ ┌──────────▼──────────┐
┊
+/// │ │ │ │
┌──────────▼──────────┐
+/// │ FileScanConfig │ │ MemorySourceConfig │ |
|
+/// │ │ │ │ |
FileFormat(trait) |
+/// └──────────────▲──────┘ └─────────────────────┘ |
|
+/// │ ┊
└─────────────────────┘
+/// │ ┊
┊
+/// │ ┊
┊
+/// ┌──────────▼──────────┐
┌──────────▼──────────┐
+/// │ │ │
ArrowSource │
+/// │ FileSource(trait) ◄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄│
... │
+/// │ │ │
ParquetSource │
+/// └─────────────────────┘
└─────────────────────┘
+/// │
+/// │
+/// │
+/// │
+/// ┌──────────▼──────────┐
+/// │ ArrowSource │
+/// │ ... │
+/// │ ParquetSource │
+/// └─────────────────────┘
+/// |
+/// FileOpener (called by FileStream)
+/// │
+/// ┌──────────▼──────────┐
+/// │ │
+/// │ RecordBatch │
+/// │ │
+/// └─────────────────────┘
+/// ```
pub trait DataSource: Send + Sync + Debug {
fn open(
&self,
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@datafusion.apache.org
For additional commands, e-mail: commits-h...@datafusion.apache.org
