This is an automated email from the ASF dual-hosted git repository. blaginin pushed a commit to branch annarose/dict-coercion in repository https://gitbox.apache.org/repos/asf/datafusion-sandbox.git
commit 613f87d61bd785178940c31e40b0904abe365f3d Author: Jeffrey Vo <[email protected]> AuthorDate: Wed Feb 4 22:52:47 2026 +0900 minor: remove unused crypto functions & narrow public API (#20045) ## Which issue does this PR close? <!-- We generally require a GitHub issue to be filed for all bug fixes and enhancements and this helps us generate change logs for our releases. You can link an issue to this PR using the GitHub syntax. For example `Closes #123` indicates that this PR will close issue #123. --> N/A ## Rationale for this change <!-- Why are you proposing this change? If this is already explained clearly in the issue then this section is not needed. Explaining clearly why changes are proposed helps reviewers understand your changes and offer better suggestions for fixes. --> Removing dead code and remove functions from public API. ## What changes are included in this PR? <!-- There is no need to duplicate the description in the issue here but it is sometimes worth providing a summary of the individual changes in this PR. --> See comments. ## Are these changes tested? <!-- We typically require tests for all PRs in order to: 1. Prevent the code from being accidentally broken by subsequent changes 2. Serve as another way to document the expected behavior of the code If tests are not included in your PR, please explain why (for example, are they covered by existing tests)? --> Existing tests. ## Are there any user-facing changes? <!-- If there are user-facing changes then we may require documentation to be updated before approving the PR. --> Yes, some functions removed from public API, but they likely weren't intended to be in our public API. <!-- If there are any breaking changes to public APIs, please add the `api change` label. --> --- datafusion/functions/src/crypto/basic.rs | 97 ++------------------------------ datafusion/functions/src/crypto/md5.rs | 47 ++++++++++++++-- 2 files changed, 47 insertions(+), 97 deletions(-) diff --git a/datafusion/functions/src/crypto/basic.rs b/datafusion/functions/src/crypto/basic.rs index bda16684c..abb86b824 100644 --- a/datafusion/functions/src/crypto/basic.rs +++ b/datafusion/functions/src/crypto/basic.rs @@ -17,19 +17,13 @@ //! "crypto" DataFusion functions -use arrow::array::{ - Array, ArrayRef, AsArray, BinaryArray, BinaryArrayType, StringViewArray, -}; +use arrow::array::{Array, ArrayRef, AsArray, BinaryArray, BinaryArrayType}; use arrow::datatypes::DataType; use blake2::{Blake2b512, Blake2s256, Digest}; use blake3::Hasher as Blake3; -use datafusion_common::cast::as_binary_array; use arrow::compute::StringArrayType; -use datafusion_common::{ - DataFusionError, Result, ScalarValue, exec_err, internal_err, plan_err, - utils::take_function_args, -}; +use datafusion_common::{DataFusionError, Result, ScalarValue, exec_err, plan_err}; use datafusion_expr::ColumnarValue; use md5::Md5; use sha2::{Sha224, Sha256, Sha384, Sha512}; @@ -37,53 +31,8 @@ use std::fmt; use std::str::FromStr; use std::sync::Arc; -macro_rules! define_digest_function { - ($NAME: ident, $METHOD: ident, $DOC: expr) => { - #[doc = $DOC] - pub fn $NAME(args: &[ColumnarValue]) -> Result<ColumnarValue> { - let [data] = take_function_args(&DigestAlgorithm::$METHOD.to_string(), args)?; - digest_process(data, DigestAlgorithm::$METHOD) - } - }; -} -define_digest_function!( - sha224, - Sha224, - "computes sha224 hash digest of the given input" -); -define_digest_function!( - sha256, - Sha256, - "computes sha256 hash digest of the given input" -); -define_digest_function!( - sha384, - Sha384, - "computes sha384 hash digest of the given input" -); -define_digest_function!( - sha512, - Sha512, - "computes sha512 hash digest of the given input" -); -define_digest_function!( - blake2b, - Blake2b, - "computes blake2b hash digest of the given input" -); -define_digest_function!( - blake2s, - Blake2s, - "computes blake2s hash digest of the given input" -); -define_digest_function!( - blake3, - Blake3, - "computes blake3 hash digest of the given input" -); - #[derive(Debug, Copy, Clone, PartialEq, Eq, Hash)] -pub enum DigestAlgorithm { +pub(crate) enum DigestAlgorithm { Md5, Sha224, Sha256, @@ -135,44 +84,6 @@ impl fmt::Display for DigestAlgorithm { } } -/// computes md5 hash digest of the given input -pub fn md5(args: &[ColumnarValue]) -> Result<ColumnarValue> { - let [data] = take_function_args("md5", args)?; - let value = digest_process(data, DigestAlgorithm::Md5)?; - - // md5 requires special handling because of its unique utf8view return type - Ok(match value { - ColumnarValue::Array(array) => { - let binary_array = as_binary_array(&array)?; - let string_array: StringViewArray = binary_array - .iter() - .map(|opt| opt.map(hex_encode::<_>)) - .collect(); - ColumnarValue::Array(Arc::new(string_array)) - } - ColumnarValue::Scalar(ScalarValue::Binary(opt)) => { - ColumnarValue::Scalar(ScalarValue::Utf8View(opt.map(hex_encode::<_>))) - } - _ => return internal_err!("Impossibly got invalid results from digest"), - }) -} - -/// Hex encoding lookup table for fast byte-to-hex conversion -const HEX_CHARS_LOWER: &[u8; 16] = b"0123456789abcdef"; - -/// Fast hex encoding using a lookup table instead of format strings. -/// This is significantly faster than using `write!("{:02x}")` for each byte. -#[inline] -fn hex_encode<T: AsRef<[u8]>>(data: T) -> String { - let bytes = data.as_ref(); - let mut s = String::with_capacity(bytes.len() * 2); - for &b in bytes { - s.push(HEX_CHARS_LOWER[(b >> 4) as usize] as char); - s.push(HEX_CHARS_LOWER[(b & 0x0f) as usize] as char); - } - s -} - macro_rules! digest_to_array { ($METHOD:ident, $INPUT:expr) => {{ let binary_array: BinaryArray = $INPUT @@ -269,7 +180,7 @@ impl DigestAlgorithm { } } -pub fn digest_process( +pub(crate) fn digest_process( value: &ColumnarValue, digest_algorithm: DigestAlgorithm, ) -> Result<ColumnarValue> { diff --git a/datafusion/functions/src/crypto/md5.rs b/datafusion/functions/src/crypto/md5.rs index 728e0d4a3..355e3e287 100644 --- a/datafusion/functions/src/crypto/md5.rs +++ b/datafusion/functions/src/crypto/md5.rs @@ -15,11 +15,13 @@ // specific language governing permissions and limitations // under the License. -use crate::crypto::basic::md5; -use arrow::datatypes::DataType; +use arrow::{array::StringViewArray, datatypes::DataType}; use datafusion_common::{ - Result, + Result, ScalarValue, + cast::as_binary_array, + internal_err, types::{logical_binary, logical_string}, + utils::take_function_args, }; use datafusion_expr::{ ColumnarValue, Documentation, ScalarFunctionArgs, ScalarUDFImpl, Signature, @@ -27,7 +29,9 @@ use datafusion_expr::{ }; use datafusion_expr_common::signature::{Coercion, TypeSignatureClass}; use datafusion_macros::user_doc; -use std::any::Any; +use std::{any::Any, sync::Arc}; + +use crate::crypto::basic::{DigestAlgorithm, digest_process}; #[user_doc( doc_section(label = "Hashing Functions"), @@ -97,3 +101,38 @@ impl ScalarUDFImpl for Md5Func { self.doc() } } + +/// Hex encoding lookup table for fast byte-to-hex conversion +const HEX_CHARS_LOWER: &[u8; 16] = b"0123456789abcdef"; + +/// Fast hex encoding using a lookup table instead of format strings. +/// This is significantly faster than using `write!("{:02x}")` for each byte. +#[inline] +fn hex_encode(data: impl AsRef<[u8]>) -> String { + let bytes = data.as_ref(); + let mut s = String::with_capacity(bytes.len() * 2); + for &b in bytes { + s.push(HEX_CHARS_LOWER[(b >> 4) as usize] as char); + s.push(HEX_CHARS_LOWER[(b & 0x0f) as usize] as char); + } + s +} + +fn md5(args: &[ColumnarValue]) -> Result<ColumnarValue> { + let [data] = take_function_args("md5", args)?; + let value = digest_process(data, DigestAlgorithm::Md5)?; + + // md5 requires special handling because of its unique utf8view return type + Ok(match value { + ColumnarValue::Array(array) => { + let binary_array = as_binary_array(&array)?; + let string_array: StringViewArray = + binary_array.iter().map(|opt| opt.map(hex_encode)).collect(); + ColumnarValue::Array(Arc::new(string_array)) + } + ColumnarValue::Scalar(ScalarValue::Binary(opt)) => { + ColumnarValue::Scalar(ScalarValue::Utf8View(opt.map(hex_encode))) + } + _ => return internal_err!("Impossibly got invalid results from digest"), + }) +} --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
