Remove hudi (#313)

Author: matthewmturner

.github/workflows/test.yml

@@ -146,31 +146,31 @@ jobs:
       - name: Run Deltalake tests
         run: |
           cargo test --features=deltalake extension_cases::deltalake
-  test-hudi:
-    name: Extension / Hudi
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        arch: [amd64]
-    steps:
-      - uses: actions/checkout@v2
-        with:
-          submodules: true
-      - name: Cache Cargo
-        uses: actions/cache@v4
-        with:
-          path: /home/runner/.cargo
-          key: cargo-dft-cache-
-      - name: Cache Rust dependencies
-        uses: actions/cache@v4
-        with:
-          path: target
-          key: ${{ runner.os }}-cargo-target-${{ hashFiles('Cargo.lock') }}
-      - name: Setup Rust Toolchain
-        uses: ./.github/actions/setup-rust
-      - name: Run Hudi tests
-        run: |
-          cargo test --features=hudi extension_cases::hudi
+  # test-hudi:
+  #   name: Extension / Hudi
+  #   runs-on: ubuntu-latest
+  #   strategy:
+  #     matrix:
+  #       arch: [amd64]
+  #   steps:
+  #     - uses: actions/checkout@v2
+  #       with:
+  #         submodules: true
+  #     - name: Cache Cargo
+  #       uses: actions/cache@v4
+  #       with:
+  #         path: /home/runner/.cargo
+  #         key: cargo-dft-cache-
+  #     - name: Cache Rust dependencies
+  #       uses: actions/cache@v4
+  #       with:
+  #         path: target
+  #         key: ${{ runner.os }}-cargo-target-${{ hashFiles('Cargo.lock') }}
+  #     - name: Setup Rust Toolchain
+  #       uses: ./.github/actions/setup-rust
+  #     - name: Run Hudi tests
+  #       run: |
+  #         cargo test --features=hudi extension_cases::hudi
   test-udfs-wasm:
     name: Extension / UDFs-WASM
     runs-on: ubuntu-latest

Cargo.lock

@@ -101,7 +101,7 @@ http = [
   "dep:tower-http",
   "dep:uuid",
 ]
-hudi = ["datafusion-app/hudi"]
+# hudi = ["datafusion-app/hudi"]
 huggingface = ["datafusion-app/huggingface"]
 iceberg = ["datafusion-app/iceberg"]
 s3 = ["datafusion-app/s3", "url"]

Cargo.toml

@@ -8,7 +8,7 @@ Documentation is undergoing a significant revamp - the new documentation will be
 `dft` is a batteries-included suite of [DataFusion](https://github.com/apache/arrow-datafusion) applications that provides:
 
 - **Data Source Integration**: Query files from S3, local filesystems, or HuggingFace datasets
-- **Table Format Support**: Native support for Delta Lake, Iceberg, and Hudi
+- **Table Format Support**: Native support for Delta Lake and Iceberg
 - **Extensibility**: UDFs defined in WASM (and soon Python)
 - **Helper Functions**: Built-in functions for JSON and Parquet data processing
 
@@ -45,7 +45,7 @@ Common feature combinations:
 cargo install datafusion-dft --features=s3
 
 # Data lake formats
-cargo install datafusion-dft --features=deltalake,iceberg,hudi
+cargo install datafusion-dft --features=deltalake,iceberg
 
 # With JSON and Parquet functions
 cargo install datafusion-dft --features=function-json,functions-parquet

README.md

@@ -21,9 +21,9 @@ deltalake = { git = "https://github.com/delta-io/delta-rs", rev = "d8995e64c305d
 ], optional = true }
 directories = "5.0.1"
 futures = "0.3.30"
-hudi = { git = "https://github.com/apache/hudi-rs", rev = "eab36e2d3ea39372c52d2bf6fe41c9aa406c0bea", features = [
-  "datafusion",
-], optional = true }
+# hudi = { git = "https://github.com/apache/hudi-rs", rev = "eab36e2d3ea39372c52d2bf6fe41c9aa406c0bea", features = [
+#   "datafusion",
+# ], optional = true }
 iceberg-catalog-rest = { git = "https://github.com/apache/iceberg-rust", rev = "210134573569be0b6e49464aca076cb122e33e24", optional = true }
 iceberg-datafusion = { git = "https://github.com/apache/iceberg-rust", rev = "210134573569be0b6e49464aca076cb122e33e24", optional = true }
 indexmap = { version = "2.8.0", features = ["serde"] }
@@ -51,7 +51,7 @@ deltalake = ["dep:deltalake"]
 flightsql = ["dep:arrow-flight", "dep:base64", "dep:tonic"]
 functions-json = ["dep:datafusion-functions-json"]
 functions-parquet = ["dep:datafusion-functions-parquet"]
-hudi = ["dep:hudi"]
+# hudi = ["dep:hudi"]
 huggingface = ["object_store_opendal", "opendal", "url"]
 iceberg = ["dep:iceberg-catalog-rest", "dep:iceberg-datafusion"]
 observability = []

crates/datafusion-app/Cargo.toml

@@ -25,8 +25,8 @@ use std::{fmt::Debug, sync::Arc};
 mod builder;
 #[cfg(feature = "deltalake")]
 mod deltalake;
-#[cfg(feature = "hudi")]
-mod hudi;
+// #[cfg(feature = "hudi")]
+// mod hudi;
 #[cfg(feature = "huggingface")]
 mod huggingface;
 #[cfg(feature = "iceberg")]
@@ -60,8 +60,8 @@ pub fn enabled_extensions() -> Vec<Arc<dyn Extension>> {
         Arc::new(s3::AwsS3Extension::new()),
         #[cfg(feature = "deltalake")]
         Arc::new(deltalake::DeltaLakeExtension::new()),
-        #[cfg(feature = "hudi")]
-        Arc::new(hudi::HudiExtension::new()),
+        // #[cfg(feature = "hudi")]
+        // Arc::new(hudi::HudiExtension::new()),
         #[cfg(feature = "iceberg")]
         Arc::new(iceberg::IcebergExtension::new()),
         #[cfg(feature = "huggingface")]

crates/datafusion-app/src/extensions/mod.rs

@@ -92,7 +92,7 @@ The TUI is organized into several tabs that you can navigate between:
 
 ### Integration Support
 - **Object Store Support**: Query S3, local files, and more
-- **Table Formats**: Connect to Delta Lake, Iceberg, and Hudi tables
+- **Table Formats**: Connect to Delta Lake tables
 - **Extension System**: Load custom UDFs and table providers
 
 ## Limitations