apache · getChan · Oct 1, 2025 · Oct 1, 2025 · Oct 19, 2025 · Oct 19, 2025
diff --git a/Cargo.lock b/Cargo.lock
diff --git a/Cargo.toml b/Cargo.toml
@@ -90,20 +90,26 @@ version = "52.0.0"
 ahash = { version = "0.8", default-features = false, features = [
     "runtime-rng",
 ] }
-apache-avro = { version = "0.21", default-features = false }
-arrow = { version = "57.2.0", features = [
+arrow = { git = "https://github.com/apache/arrow-rs", rev = "1db1a8869cceb179aa885ed58da9f0b49c03eafe", features = [ # fixme
     "prettyprint",
     "chrono-tz",
 ] }
-arrow-buffer = { version = "57.2.0", default-features = false }
-arrow-flight = { version = "57.2.0", features = [
+arrow-avro = { git = "https://github.com/apache/arrow-rs", rev = "1db1a8869cceb179aa885ed58da9f0b49c03eafe", default-features = false, features = [ # fixme
+    "deflate",
+    "snappy",
+    "zstd",
+    "bzip2",
+    "xz",
+] }
+arrow-buffer = { git = "https://github.com/apache/arrow-rs", rev = "1db1a8869cceb179aa885ed58da9f0b49c03eafe", default-features = false } # fixme
+arrow-flight = { git = "https://github.com/apache/arrow-rs", rev = "1db1a8869cceb179aa885ed58da9f0b49c03eafe", features = [ # fixme
     "flight-sql-experimental",
 ] }
-arrow-ipc = { version = "57.2.0", default-features = false, features = [
+arrow-ipc = { git = "https://github.com/apache/arrow-rs", rev = "1db1a8869cceb179aa885ed58da9f0b49c03eafe", default-features = false, features = [ # fixme
     "lz4",
 ] }
-arrow-ord = { version = "57.2.0", default-features = false }
-arrow-schema = { version = "57.2.0", default-features = false }
+arrow-ord = { git = "https://github.com/apache/arrow-rs", rev = "1db1a8869cceb179aa885ed58da9f0b49c03eafe", default-features = false } # fixme
+arrow-schema = { git = "https://github.com/apache/arrow-rs", rev = "1db1a8869cceb179aa885ed58da9f0b49c03eafe", default-features = false } # fixme
 async-trait = "0.1.89"
 bigdecimal = "0.4.8"
 bytes = "1.11"
@@ -166,7 +172,7 @@ log = "^0.4"
 num-traits = { version = "0.2" }
 object_store = { version = "0.12.4", default-features = false }
 parking_lot = "0.12"
-parquet = { version = "57.2.0", default-features = false, features = [
+parquet = { git = "https://github.com/apache/arrow-rs", rev = "1db1a8869cceb179aa885ed58da9f0b49c03eafe", default-features = false, features = [ # fixme
     "arrow",
     "async",
     "object_store",

diff --git a/datafusion/common/Cargo.toml b/datafusion/common/Cargo.toml
@@ -41,7 +41,6 @@ workspace = true
 name = "datafusion_common"
 
 [features]
-avro = ["apache-avro"]
 backtrace = []
 parquet_encryption = [
     "parquet",
@@ -59,12 +58,6 @@ name = "with_hashes"
 
 [dependencies]
 ahash = { workspace = true }
-apache-avro = { workspace = true, features = [
-    "bzip",
-    "snappy",
-    "xz",
-    "zstandard",
-], optional = true }
 arrow = { workspace = true }
 arrow-ipc = { workspace = true }
 chrono = { workspace = true }

diff --git a/datafusion/common/src/error.rs b/datafusion/common/src/error.rs
@@ -48,8 +48,6 @@ use std::sync::Arc;
 use crate::utils::datafusion_strsim::normalized_levenshtein;
 use crate::utils::quote_identifier;
 use crate::{Column, DFSchema, Diagnostic, TableReference};
-#[cfg(feature = "avro")]
-use apache_avro::Error as AvroError;
 use arrow::error::ArrowError;
 #[cfg(feature = "parquet")]
 use parquet::errors::ParquetError;
@@ -76,9 +74,6 @@ pub enum DataFusionError {
     /// Error when reading / writing Parquet data.
     #[cfg(feature = "parquet")]
     ParquetError(Box<ParquetError>),
-    /// Error when reading Avro data.
-    #[cfg(feature = "avro")]
-    AvroError(Box<AvroError>),
     /// Error when reading / writing to / from an object_store (e.g. S3 or LocalFile)
     #[cfg(feature = "object_store")]
     ObjectStore(Box<object_store::Error>),
@@ -332,13 +327,6 @@ impl From<ParquetError> for DataFusionError {
     }
 }
 
-#[cfg(feature = "avro")]
-impl From<AvroError> for DataFusionError {
-    fn from(e: AvroError) -> Self {
-        DataFusionError::AvroError(Box::new(e))
-    }
-}
-
 #[cfg(feature = "object_store")]
 impl From<object_store::Error> for DataFusionError {
     fn from(e: object_store::Error) -> Self {
@@ -389,8 +377,6 @@ impl Error for DataFusionError {
             DataFusionError::ArrowError(e, _) => Some(e.as_ref()),
             #[cfg(feature = "parquet")]
             DataFusionError::ParquetError(e) => Some(e.as_ref()),
-            #[cfg(feature = "avro")]
-            DataFusionError::AvroError(e) => Some(e.as_ref()),
             #[cfg(feature = "object_store")]
             DataFusionError::ObjectStore(e) => Some(e.as_ref()),
             DataFusionError::IoError(e) => Some(e),
@@ -520,8 +506,6 @@ impl DataFusionError {
             DataFusionError::ArrowError(_, _) => "Arrow error: ",
             #[cfg(feature = "parquet")]
             DataFusionError::ParquetError(_) => "Parquet error: ",
-            #[cfg(feature = "avro")]
-            DataFusionError::AvroError(_) => "Avro error: ",
             #[cfg(feature = "object_store")]
             DataFusionError::ObjectStore(_) => "Object Store error: ",
             DataFusionError::IoError(_) => "IO error: ",
@@ -561,8 +545,6 @@ impl DataFusionError {
             }
             #[cfg(feature = "parquet")]
             DataFusionError::ParquetError(ref desc) => Cow::Owned(desc.to_string()),
-            #[cfg(feature = "avro")]
-            DataFusionError::AvroError(ref desc) => Cow::Owned(desc.to_string()),
             DataFusionError::IoError(ref desc) => Cow::Owned(desc.to_string()),
             #[cfg(feature = "sql")]
             DataFusionError::SQL(ref desc, ref backtrace) => {

diff --git a/datafusion/core/Cargo.toml b/datafusion/core/Cargo.toml
@@ -43,7 +43,7 @@ nested_expressions = ["datafusion-functions-nested"]
 # This feature is deprecated. Use the `nested_expressions` feature instead.
 array_expressions = ["nested_expressions"]
 # Used to enable the avro format
-avro = ["datafusion-common/avro", "datafusion-datasource-avro"]
+avro = ["datafusion-datasource-avro"]
 backtrace = ["datafusion-common/backtrace"]
 compression = [
     "liblzma",

diff --git a/datafusion/core/src/datasource/file_format/avro.rs b/datafusion/core/src/datasource/file_format/avro.rs
@@ -109,7 +109,7 @@ mod tests {
                 "double_col: Float64",
                 "date_string_col: Binary",
                 "string_col: Binary",
-                "timestamp_col: Timestamp(Microsecond, None)",
+                "timestamp_col: Timestamp(Microsecond, Some(\"+00:00\"))",
             ],
             x
         );
@@ -118,18 +118,18 @@ mod tests {
         assert_eq!(batches.len(), 1);
 
         assert_snapshot!(batches_to_string(&batches),@r"
-        +----+----------+-------------+--------------+---------+------------+-----------+------------+------------------+------------+---------------------+
-        | id | bool_col | tinyint_col | smallint_col | int_col | bigint_col | float_col | double_col | date_string_col  | string_col | timestamp_col       |
-        +----+----------+-------------+--------------+---------+------------+-----------+------------+------------------+------------+---------------------+
-        | 4  | true     | 0           | 0            | 0       | 0          | 0.0       | 0.0        | 30332f30312f3039 | 30         | 2009-03-01T00:00:00 |
-        | 5  | false    | 1           | 1            | 1       | 10         | 1.1       | 10.1       | 30332f30312f3039 | 31         | 2009-03-01T00:01:00 |
-        | 6  | true     | 0           | 0            | 0       | 0          | 0.0       | 0.0        | 30342f30312f3039 | 30         | 2009-04-01T00:00:00 |
-        | 7  | false    | 1           | 1            | 1       | 10         | 1.1       | 10.1       | 30342f30312f3039 | 31         | 2009-04-01T00:01:00 |
-        | 2  | true     | 0           | 0            | 0       | 0          | 0.0       | 0.0        | 30322f30312f3039 | 30         | 2009-02-01T00:00:00 |
-        | 3  | false    | 1           | 1            | 1       | 10         | 1.1       | 10.1       | 30322f30312f3039 | 31         | 2009-02-01T00:01:00 |
-        | 0  | true     | 0           | 0            | 0       | 0          | 0.0       | 0.0        | 30312f30312f3039 | 30         | 2009-01-01T00:00:00 |
-        | 1  | false    | 1           | 1            | 1       | 10         | 1.1       | 10.1       | 30312f30312f3039 | 31         | 2009-01-01T00:01:00 |
-        +----+----------+-------------+--------------+---------+------------+-----------+------------+------------------+------------+---------------------+
+        +----+----------+-------------+--------------+---------+------------+-----------+------------+------------------+------------+----------------------+
+        | id | bool_col | tinyint_col | smallint_col | int_col | bigint_col | float_col | double_col | date_string_col  | string_col | timestamp_col        |
+        +----+----------+-------------+--------------+---------+------------+-----------+------------+------------------+------------+----------------------+
+        | 4  | true     | 0           | 0            | 0       | 0          | 0.0       | 0.0        | 30332f30312f3039 | 30         | 2009-03-01T00:00:00Z |
+        | 5  | false    | 1           | 1            | 1       | 10         | 1.1       | 10.1       | 30332f30312f3039 | 31         | 2009-03-01T00:01:00Z |
+        | 6  | true     | 0           | 0            | 0       | 0          | 0.0       | 0.0        | 30342f30312f3039 | 30         | 2009-04-01T00:00:00Z |
+        | 7  | false    | 1           | 1            | 1       | 10         | 1.1       | 10.1       | 30342f30312f3039 | 31         | 2009-04-01T00:01:00Z |
+        | 2  | true     | 0           | 0            | 0       | 0          | 0.0       | 0.0        | 30322f30312f3039 | 30         | 2009-02-01T00:00:00Z |
+        | 3  | false    | 1           | 1            | 1       | 10         | 1.1       | 10.1       | 30322f30312f3039 | 31         | 2009-02-01T00:01:00Z |
+        | 0  | true     | 0           | 0            | 0       | 0          | 0.0       | 0.0        | 30312f30312f3039 | 30         | 2009-01-01T00:00:00Z |
+        | 1  | false    | 1           | 1            | 1       | 10         | 1.1       | 10.1       | 30312f30312f3039 | 31         | 2009-01-01T00:01:00Z |
+        +----+----------+-------------+--------------+---------+------------+-----------+------------+------------------+------------+----------------------+
         ");
         Ok(())
     }

diff --git a/datafusion/core/src/lib.rs b/datafusion/core/src/lib.rs
@@ -787,7 +787,7 @@ pub use object_store;
 pub use parquet;
 
 #[cfg(feature = "avro")]
-pub use datafusion_datasource_avro::apache_avro;
+pub use datafusion_datasource_avro::arrow_avro;
 
 // re-export DataFusion sub-crates at the top level. Use `pub use *`
 // so that the contents of the subcrates appears in rustdocs

diff --git a/datafusion/datasource-avro/Cargo.toml b/datafusion/datasource-avro/Cargo.toml
@@ -31,21 +31,18 @@ version.workspace = true
 all-features = true
 
 [dependencies]
-apache-avro = { workspace = true }
 arrow = { workspace = true }
+arrow-avro = { workspace = true }
 async-trait = { workspace = true }
 bytes = { workspace = true }
-datafusion-common = { workspace = true, features = ["object_store", "avro"] }
+datafusion-common = { workspace = true, features = ["object_store"] }
 datafusion-datasource = { workspace = true }
-datafusion-physical-expr-common = { workspace = true }
 datafusion-physical-plan = { workspace = true }
 datafusion-session = { workspace = true }
 futures = { workspace = true }
-num-traits = { workspace = true }
 object_store = { workspace = true }
 
 [dev-dependencies]
-serde_json = { workspace = true }
 
 # Note: add additional linter rules in lib.rs.
 # Rust does not support workspace + new linter rules in subcrates yet