feat: read_blob (#2902)

closes #2683

Cargo.toml

@@ -41,6 +41,7 @@ tempfile = "3.10.1"
 thiserror = "1.0"
 tracing = "0.1"
 url = "2.5.0"
+bytes = "1.6.0"
 
 [workspace.dependencies.deltalake]
 git = "https://github.com/GlareDB/delta-rs.git"

bindings/nodejs/Cargo.toml

@@ -32,7 +32,7 @@ lzma-sys = { version = "*", features = ["static"] } # Prevent dynamic linking of
 napi = { version = "2.16.2", default-features = false, features = ["full"] }
 napi-derive = "2.16.2"
 once_cell = "1.19.0"
-bytes = "1.6.0"
+bytes = { workspace = true }
 async-once-cell = "0.5.3"
 
 [build-dependencies]

crates/bytesutil/Cargo.toml

@@ -7,4 +7,4 @@ edition = {workspace = true}
 workspace = true
 
 [dependencies]
-bytes = "1.6.0"
+bytes = { workspace = true }

crates/datasources/Cargo.toml

@@ -15,7 +15,7 @@ async-stream = "0.3.5"
 async-trait = { workspace = true }
 bigquery-storage = { git = "https://github.com/glaredb/bigquery-storage", branch = "deps/2023-10-27-update" }
 bitvec = "1"
-bytes = "1.6.0"
+bytes = { workspace = true }
 chrono = { workspace = true }
 chrono-tz = "0.8.6"
 datafusion = { workspace = true }

crates/ioutil/Cargo.toml

@@ -7,5 +7,5 @@ edition = {workspace = true}
 workspace = true
 
 [dependencies]
-bytes = "1.6.0"
+bytes = { workspace = true }
 home = "0.5.9"

crates/metastore/Cargo.toml

@@ -24,7 +24,7 @@ tokio = { workspace = true }
 tonic = { workspace = true }
 tracing = { workspace = true }
 uuid = { version = "1.8.0", features = ["v4", "fast-rng", "macro-diagnostics"] }
-bytes = "1.6"
+bytes = { workspace = true }
 once_cell = "1.19.0"
 tower = "0.4"
 dashmap = "5.5.0"

crates/object_store_util/Cargo.toml

@@ -15,6 +15,6 @@ thiserror = { workspace = true }
 tracing = { workspace = true }
 tokio = { workspace = true }
 tempfile = "3"
-bytes = "1.6.0"
+bytes = { workspace = true }
 moka = { version = "0.12.5", features = ["future"] }
 uuid = { version = "1.8.0", features = ["v4", "fast-rng", "macro-diagnostics"] }

crates/pgprototest/Cargo.toml

@@ -13,5 +13,5 @@ clap = { workspace = true }
 anyhow = { workspace = true }
 datadriven = "0.6.0"
 postgres-protocol = "0.6.5"
-bytes = "1.6.0"
+bytes = { workspace = true }
 fallible-iterator = "0.2.0"

crates/pgrepr/Cargo.toml

@@ -17,6 +17,6 @@ decimal = { path = "../decimal" }
 num-traits = "0.2.18"
 dtoa = "1.0.9"
 chrono-tz = "0.8.6"
-bytes = "1.6.0"
+bytes = { workspace = true }
 const_format = "0.2.32"
 once_cell = "1.19.0"

crates/pgsrv/Cargo.toml

@@ -21,7 +21,7 @@ bytesutil = { path = "../bytesutil" }
 parser = { path = "../parser" }
 pgrepr = { path = "../pgrepr" }
 datafusion_ext = { path = "../datafusion_ext" }
-bytes = "1.6.0"
+bytes = { workspace = true }
 rustls = "0.21.10"
 webpki-roots = "0.26.1"
 tokio-rustls = "0.24.1"

crates/sqlbuiltins/Cargo.toml

@@ -26,6 +26,7 @@ tracing = { workspace = true }
 tempfile = { workspace = true }
 tokio = { workspace = true }
 reqwest = { workspace = true }
+bytes = { workspace = true }
 async-openai = "0.20.0"
 once_cell = "1.19.0"
 num-traits = "0.2.18"

crates/sqlbuiltins/src/functions/table/mod.rs

@@ -14,6 +14,7 @@ mod mysql;
 mod object_store;
 mod parquet_metadata;
 mod postgres;
+mod read_blob;
 mod snowflake;
 
 mod sqlite;
@@ -52,6 +53,7 @@ use self::mysql::ReadMysql;
 use self::object_store::{CloudUpload, READ_CSV, READ_JSON, READ_PARQUET};
 use self::parquet_metadata::ParquetMetadataFunc;
 use self::postgres::ReadPostgres;
+use self::read_blob::READ_BLOB;
 use self::snowflake::ReadSnowflake;
 use self::sqlite::ReadSqlite;
 use self::sqlserver::ReadSqlServer;
@@ -101,6 +103,7 @@ impl BuiltinTableFuncs {
             Arc::new(ReadSqlServer),
             Arc::new(ReadCassandra),
             // Object store
+            Arc::new(READ_BLOB),
             Arc::new(READ_PARQUET),
             Arc::new(READ_CSV),
             Arc::new(READ_JSON),

crates/sqlbuiltins/src/functions/table/object_store.rs

@@ -170,15 +170,15 @@ impl WithCompression for ParquetFormat {
 #[derive(Debug, Clone)]
 pub struct ObjScanTableFunc<Opts> {
     /// Primary name for the function.
-    name: &'static str,
+    pub(super) name: &'static str,
 
     /// Additional aliases for this function.
-    aliases: &'static [&'static str],
+    pub(super) aliases: &'static [&'static str],
 
-    description: &'static str,
-    example: &'static str,
+    pub(super) description: &'static str,
+    pub(super) example: &'static str,
 
-    phantom: PhantomData<Opts>,
+    pub(super) phantom: PhantomData<Opts>,
 }
 
 impl<Opts: OptionReader> BuiltinFunction for ObjScanTableFunc<Opts> {