Make clippy and fmt happy (#2)

* Make clippy and fmt happy

* Add pre-commit conf

* Add cache for clippy job

Author: rampage644

.github/workflows/check.yml

@@ -64,6 +64,7 @@ jobs:
         with:
           toolchain: ${{ matrix.toolchain }}
           components: clippy
+      - uses: Swatinem/rust-cache@v2
       - name: Install Dependencies
         run: | 
           sudo apt install -y llvm-18 libclang-18-dev

.pre-commit-config.yaml

@@ -0,0 +1,9 @@
+repos:
+  - repo: https://github.com/doublify/pre-commit-rust
+    rev: v1.0
+    hooks:
+      - id: cargo-check
+        args: [ "--workspace" ]
+      - id: fmt
+        args: [ "--", "--check"]
+      - id: clippy

README.md

@@ -3,8 +3,6 @@
 **Run Snowflake SQL dialect on your data lake in 30 seconds. Zero dependencies.**
 
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
-[![SQL Logic Test Coverage](https://raw.githubusercontent.com/Embucket/embucket/assets/assets/badge.svg)](test/README.md)
-[![dbt Gitlab run results](https://raw.githubusercontent.com/Embucket/embucket/assets_dbt/assets_dbt/dbt_success_badge.svg)](test/dbt_integration_tests/dbt-gitlab/README.md)
 
 ## Quick start
 
@@ -17,26 +15,50 @@ docker run --name embucket --rm -p 3000:3000 embucket/embucket
 Run the Snowflake CLI against the local endpoint:
 
 ```bash
+pip install snowflake-cli
 snow sql -c local -a local -u embucket -p embucket -q "select 1;"
 ```
 
 **Done.** You just ran Snowflake SQL dialect against the local Embucket instance with zero configuration.
 
-### Bootstrap external volumes via config
+### Create external volumes via config
 
-You can pre-create volumes, databases, and schemas by pointing `embucketd` at a YAML config file. This
-is handy when you want to mount an S3 Tables bucket at startup without sending API calls after the
-process is online.
+**Important**: External volumes must be created via YAML configuration at startup. REST API-based volume creation is not supported.
+
+Pre-create volumes, databases, and schemas by pointing `embucketd` at a YAML config file:
 
 ```bash
 cargo run -p embucketd -- \
   --no-bootstrap \
-  --metastore-config config/metastore.s3tables.demo.yaml
+  --metastore-config config/metastore.yaml
+```
+
+**Sample configuration** (`config/metastore.yaml`):
+
+```yaml
+volumes:
+  # S3 Tables volume - connects to AWS S3 Table Bucket
+  - ident: demo
+    type: s3-tables
+    database: demo
+    credentials:
+      credential_type: access_key
+      aws-access-key-id: YOUR_ACCESS_KEY
+      aws-secret-access-key: YOUR_SECRET_KEY
+    arn: arn:aws:s3tables:us-east-2:123456789012:bucket/my-table-bucket
+
+  # S3 volume - connects to standard S3 bucket
+  # - ident: s3_volume
+  #   type: s3
+  #   bucket: my-data-bucket
+  #   endpoint: https://s3.amazonaws.com
+  #   credentials:
+  #     credential_type: access_key
+  #     aws-access-key-id: YOUR_ACCESS_KEY
+  #     aws-secret-access-key: YOUR_SECRET_KEY
 ```
 
-The sample config under `config/metastore.s3tables.demo.yaml` provisions a `demo` database backed by an
-S3 Tables bucket using the credentials provided in the file. Update the file with your own secrets
-for real deployments.
+Update the credentials and ARN/bucket details with your own values for real deployments.
 
 ## What just happened?
 
@@ -58,7 +80,6 @@ Perfect for teams who want Snowflake's simplicity with bring-your-own-cloud cont
 Built on proven open source:
 - [Apache DataFusion](https://datafusion.apache.org/) for SQL execution
 - [Apache Iceberg](https://iceberg.apache.org/) for ACID table metadata  
-- A lightweight in-memory metastore purpose-built for Embucket
 
 ## Why Embucket?
 
@@ -70,16 +91,8 @@ Built on proven open source:
 - **Horizontal scaling** - Add nodes for more throughput  
 - **Zero operations** - No external dependencies to manage
 
-## Next steps
-
-**Ready for more?** Check out the comprehensive documentation:
-
-[Quick start](https://docs.embucket.com/essentials/quick-start/) - Detailed setup and first queries  
-[Architecture](https://docs.embucket.com/essentials/architecture/) - How the zero-disk lakehouse works  
-[Configuration](https://docs.embucket.com/essentials/configuration/) - Production deployment options  
-[dbt Integration](https://docs.embucket.com/guides/dbt-snowplow/) - Run existing dbt projects  
+## Build from source
 
-**From source:**
 ```bash
 git clone https://github.com/Embucket/embucket.git
 cd embucket && cargo build

crates/api-snowflake-rest/src/server/error.rs

@@ -2,14 +2,14 @@ use crate::SqlState;
 use crate::models::JsonResponse;
 use crate::models::ResponseData;
 use axum::{Json, http, response::IntoResponse};
-use executor::QueryRecordId;
-use executor::error::OperationOn;
-use executor::error_code::ErrorCode;
-use executor::snowflake_error::Entity;
 use datafusion::arrow::error::ArrowError;
 use error_stack::ErrorChainExt;
 use error_stack::ErrorExt;
 use error_stack_trace;
+use executor::QueryRecordId;
+use executor::error::OperationOn;
+use executor::error_code::ErrorCode;
+use executor::snowflake_error::Entity;
 use snafu::Location;
 use snafu::prelude::*;
 

crates/api-snowflake-rest/src/server/helpers.rs

@@ -5,11 +5,11 @@ use axum::Json;
 use base64;
 use base64::engine::general_purpose::STANDARD as engine_base64;
 use base64::prelude::*;
-use executor::models::QueryResult;
-use executor::utils::{DataSerializationFormat, convert_record_batches};
 use datafusion::arrow::ipc::MetadataVersion;
 use datafusion::arrow::ipc::writer::{IpcWriteOptions, StreamWriter};
 use datafusion::arrow::record_batch::RecordBatch;
+use executor::models::QueryResult;
+use executor::utils::{DataSerializationFormat, convert_record_batches};
 use snafu::ResultExt;
 use uuid::Uuid;
 

crates/api-snowflake-rest/src/server/router.rs

@@ -7,9 +7,9 @@ use super::layer::require_auth;
 use super::server_models::Config;
 use super::state;
 use axum::middleware;
+use catalog_metastore::Metastore;
 use executor::service::CoreExecutionService;
 use executor::utils::Config as UtilsConfig;
-use catalog_metastore::Metastore;
 use std::sync::Arc;
 use tower::ServiceBuilder;
 use tower_http::compression::CompressionLayer;

crates/api-snowflake-rest/src/server/test_server.rs

@@ -1,7 +1,7 @@
 use super::server_models::Config;
 use crate::server::router::make_app;
-use executor::utils::Config as UtilsConfig;
 use catalog_metastore::{InMemoryMetastore, Metastore};
+use executor::utils::Config as UtilsConfig;
 use std::net::SocketAddr;
 use std::sync::Arc;
 use tracing_subscriber::fmt::format::FmtSpan;

crates/catalog/src/catalog_list.rs

@@ -11,7 +11,9 @@ use crate::table::CachingTable;
 use aws_config::{BehaviorVersion, Region, SdkConfig};
 use aws_credential_types::Credentials;
 use aws_credential_types::provider::SharedCredentialsProvider;
-use catalog_metastore::{AwsCredentials, Database, Metastore, RwObject, S3TablesVolume, VolumeType};
+use catalog_metastore::{
+    AwsCredentials, Database, Metastore, RwObject, S3TablesVolume, VolumeType,
+};
 use catalog_metastore::{SchemaIdent, TableIdent};
 use dashmap::DashMap;
 use datafusion::{

crates/catalog/src/catalogs/embucket/catalog.rs

@@ -51,16 +51,15 @@ impl CatalogProvider for EmbucketCatalog {
         let database = self.database.clone();
 
         block_in_new_runtime(async move {
-            metastore
-                .list_schemas(&database)
-                .await
-                .map(|schemas| {
+            metastore.list_schemas(&database).await.map_or_else(
+                |_| vec![],
+                |schemas| {
                     schemas
                         .into_iter()
                         .map(|s| s.ident.schema.clone())
                         .collect()
-                })
-                .unwrap_or_else(|_| vec![])
+                },
+            )
         })
         .unwrap_or_else(|_| vec![])
     }

crates/catalog/src/catalogs/embucket/schema.rs

@@ -50,8 +50,10 @@ impl SchemaProvider for EmbucketSchema {
             metastore
                 .list_tables(&SchemaIdent::new(database, schema))
                 .await
-                .map(|tables| tables.into_iter().map(|s| s.ident.table.clone()).collect())
-                .unwrap_or_else(|_| vec![])
+                .map_or_else(
+                    |_| vec![],
+                    |tables| tables.into_iter().map(|s| s.ident.table.clone()).collect(),
+                )
         })
         .unwrap_or_else(|_| vec![]);