alamb commented on code in PR #6979: URL: https://github.com/apache/arrow-rs/pull/6979#discussion_r1914914763
########## parquet/README.md: ########## @@ -51,17 +51,21 @@ major releases may contain breaking API changes. The `parquet` crate provides the following features which may be enabled in your `Cargo.toml`: -- `arrow` (default) - support for reading / writing [`arrow`](https://crates.io/crates/arrow) arrays to / from parquet -- `async` - support `async` APIs for reading parquet -- `json` - support for reading / writing `json` data to / from parquet -- `brotli` (default) - support for parquet using `brotli` compression -- `flate2` (default) - support for parquet using `gzip` compression -- `lz4` (default) - support for parquet using `lz4` compression -- `zstd` (default) - support for parquet using `zstd` compression -- `snap` (default) - support for parquet using `snappy` compression +- `arrow` (default) - support for reading / writing [`arrow`] arrays to / from Parquet Review Comment: this was a drive by cleanup b/c I can't help myself now that @etseidl pointed out the capitalization inconsistency with `Parquet` and `parquet` ########## parquet/README.md: ########## @@ -51,17 +51,21 @@ major releases may contain breaking API changes. The `parquet` crate provides the following features which may be enabled in your `Cargo.toml`: -- `arrow` (default) - support for reading / writing [`arrow`](https://crates.io/crates/arrow) arrays to / from parquet -- `async` - support `async` APIs for reading parquet -- `json` - support for reading / writing `json` data to / from parquet -- `brotli` (default) - support for parquet using `brotli` compression -- `flate2` (default) - support for parquet using `gzip` compression -- `lz4` (default) - support for parquet using `lz4` compression -- `zstd` (default) - support for parquet using `zstd` compression -- `snap` (default) - support for parquet using `snappy` compression +- `arrow` (default) - support for reading / writing [`arrow`] arrays to / from Parquet +- `async` - support `async` APIs for reading Parquet +- `json` - support for reading / writing `json` data to / from Parquet +- `brotli` (default) - support for Parquet using `brotli` compression +- `flate2` (default) - support for Parquet using `gzip` compression +- `lz4` (default) - support for Parquet using `lz4` compression +- `zstd` (default) - support for Parquet using `zstd` compression +- `snap` (default) - support for Parquet using `snappy` compression - `cli` - parquet [CLI tools](https://github.com/apache/arrow-rs/tree/main/parquet/src/bin) - `crc` - enables functionality to automatically verify checksums of each page (if present) when decoding - `experimental` - Experimental APIs which may change, even between minor releases +- `simdutf8` (default) - Use the [`simdutf8`] crate for SIMD-accelerated UTF-8 validation Review Comment: this is the new feature ########## parquet/src/util/utf8.rs: ########## @@ -0,0 +1,56 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +//! [`check_valid_utf8`] validation function +use crate::errors::{Result, ParquetError}; + +/// Check that `val` is a valid UTF-8 sequence. +/// +/// If the `simdutf8` feature is enabled, this function will use +/// SIMD-accelerated validation from the [`simdutf8`] crate. Otherwise, it will use +/// [`std::str::from_utf8`]. +/// +/// # Errors +/// +/// Returns `Err::General` with a message compatible with [`std::str::from_utf8`] on failure. +/// +/// # Example +/// ``` +/// use parquet::utf8::check_valid_utf8; +/// assert!(check_valid_utf8(b"hello").is_ok()); +/// assert!(check_valid_utf8(b"hello \xF0\x9F\x98\x8E").is_ok()); +/// // invalid UTF-8 +/// assert!(check_valid_utf8(b"hello \xF0\x9F\x98").is_err()); +/// ``` +/// +/// [`simdutf8`]: https://crates.io/crates/simdutf8 +#[inline(always)] +pub fn check_valid_utf8(val: &[u8]) -> Result<()> { Review Comment: I implemented @etseidl 's suggestion https://github.com/apache/arrow-rs/pull/6668#discussion_r1907995431 for encapsulation to make the code / use eaiser to understand ########## parquet/src/lib.rs: ########## @@ -131,6 +131,9 @@ pub mod data_type; pub use self::encodings::{decoding, encoding}; experimental!(#[macro_use] mod util); + +pub use util::utf8; Review Comment: This publically exports the `utf8` module as part of the `parquet `modules, which is needed for adding a doc test. I was thinking this might be useful for other users (to use the same utf8 validation library) but I can also be convinced to avoid adding this function to the public API of the -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
