This is an automated email from the ASF dual-hosted git repository. xushiyan pushed a commit to branch release/0.2.x in repository https://gitbox.apache.org/repos/asf/hudi-rs.git
commit 90f7498fa41bc858070a64fbbadbf72a293b8f14 Author: Shiyan Xu <[email protected]> AuthorDate: Fri Nov 22 06:04:55 2024 -1000 docs: update README examples (#194) --- README.md | 58 +++++++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 45 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index d59947d..6e1fd57 100644 --- a/README.md +++ b/README.md @@ -62,29 +62,30 @@ users and projects. Read a Hudi table into a PyArrow table. ```python -from hudi import HudiTable - -hudi_table = HudiTable("/tmp/trips_table") -records = hudi_table.read_snapshot() - +from hudi import HudiTableBuilder import pyarrow as pa -import pyarrow.compute as pc + +hudi_table = ( + HudiTableBuilder + .from_base_uri("/tmp/trips_table") + .with_option("hoodie.read.as.of.timestamp", "0") + .build() +) +records = hudi_table.read_snapshot(filters=[("city", "=", "san_francisco")]) arrow_table = pa.Table.from_batches(records) -result = arrow_table.select( - ["rider", "ts", "fare"]).filter( - pc.field("fare") > 20.0) +result = arrow_table.select(["rider", "city", "ts", "fare"]) print(result) ``` -### Rust +### Rust (DataFusion) <details> <summary>Add crate hudi with datafusion feature to your application to query a Hudi table.</summary> ```shell cargo new my_project --bin && cd my_project -cargo add tokio@1 datafusion@39 +cargo add tokio@1 datafusion@42 cargo add hudi --features datafusion ``` @@ -102,9 +103,11 @@ use hudi::HudiDataSource; #[tokio::main] async fn main() -> Result<()> { let ctx = SessionContext::new(); - let hudi = HudiDataSource::new("/tmp/trips_table").await?; + let hudi = HudiDataSource::new_with_options( + "/tmp/trips_table", + [("hoodie.read.as.of.timestamp", "20241122010827898")]).await?; ctx.register_table("trips_table", Arc::new(hudi))?; - let df: DataFrame = ctx.sql("SELECT * from trips_table where fare > 20.0").await?; + let df: DataFrame = ctx.sql("SELECT * from trips_table where city = 'san_francisco'").await?; df.show().await?; Ok(()) } @@ -116,6 +119,35 @@ Ensure cloud storage credentials are set properly as environment variables, e.g. Relevant storage environment variables will then be picked up. The target table's base uri with schemes such as `s3://`, `az://`, or `gs://` will be processed accordingly. +Alternatively, you can pass the storage configuration as options to the `HudiTableBuilder` or `HudiDataSource`. + +### Python + +```python +from hudi import HudiTableBuilder + +hudi_table = ( + HudiTableBuilder + .from_base_uri("s3://bucket/trips_table") + .with_option("aws_region", "us-west-2") + .build() +) +``` + +### Rust (DataFusion) + +```rust +use hudi::HudiDataSource; + +async fn main() -> Result<()> { + let hudi = HudiDataSource::new_with_options( + "s3://bucket/trips_table", + [("aws_region", "us-west-2")] + ).await?; +} + +``` + ## Contributing Check out the [contributing guide](./CONTRIBUTING.md) for all the details about making contributions to the project.
