Migrate parquet to Rust 2024 (#8506)

# Which issue does this PR close?

- Contribute to #6827

# Rationale for this change

Splitting up #8227.

# What changes are included in this PR?

Migrate `parquet` to Rust 2024

# Are these changes tested?

CI

# Are there any user-facing changes?

Yes

Author: mbrobbel

parquet/Cargo.toml

@@ -25,7 +25,7 @@ repository = { workspace = true }
 authors = { workspace = true }
 keywords = ["arrow", "parquet", "hadoop"]
 readme = "README.md"
-edition = { workspace = true }
+edition = "2024"
 rust-version = { workspace = true }
 
 [target.'cfg(target_arch = "wasm32")'.dependencies]

parquet/benches/arrow_reader.rs

@@ -19,13 +19,13 @@ use arrow::array::Array;
 use arrow::datatypes::DataType;
 use arrow_schema::Field;
 use criterion::measurement::WallTime;
-use criterion::{criterion_group, criterion_main, BenchmarkGroup, Criterion};
+use criterion::{BenchmarkGroup, Criterion, criterion_group, criterion_main};
 use half::f16;
 use num_bigint::BigInt;
 use num_traits::FromPrimitive;
 use parquet::arrow::array_reader::{
-    make_byte_array_reader, make_byte_view_array_reader, make_fixed_len_byte_array_reader,
-    ListArrayReader,
+    ListArrayReader, make_byte_array_reader, make_byte_view_array_reader,
+    make_fixed_len_byte_array_reader,
 };
 use parquet::basic::Type;
 use parquet::data_type::{ByteArray, FixedLenByteArrayType};
@@ -38,7 +38,7 @@ use parquet::{
     schema::types::{ColumnDescPtr, SchemaDescPtr},
 };
 use rand::distr::uniform::SampleUniform;
-use rand::{rngs::StdRng, Rng, SeedableRng};
+use rand::{Rng, SeedableRng, rngs::StdRng};
 use std::{collections::VecDeque, sync::Arc};
 
 fn build_test_schema() -> SchemaDescPtr {

parquet/benches/arrow_reader_clickbench.rs

@@ -35,7 +35,7 @@ use arrow::compute::{like, nlike, or};
 use arrow_array::types::{Int16Type, Int32Type, Int64Type};
 use arrow_array::{ArrayRef, ArrowPrimitiveType, BooleanArray, PrimitiveArray, StringViewArray};
 use arrow_schema::{ArrowError, DataType, Schema};
-use criterion::{criterion_group, criterion_main, Criterion};
+use criterion::{Criterion, criterion_group, criterion_main};
 use futures::StreamExt;
 use parquet::arrow::arrow_reader::{
     ArrowPredicate, ArrowPredicateFn, ArrowReaderMetadata, ArrowReaderOptions,

parquet/benches/arrow_reader_row_filter.rs

@@ -57,11 +57,11 @@ use arrow::compute::and;
 use arrow::compute::kernels::cmp::{eq, gt, lt, neq};
 use arrow::datatypes::{DataType, Field, Schema, TimeUnit};
 use arrow::record_batch::RecordBatch;
-use arrow_array::builder::{ArrayBuilder, StringViewBuilder};
 use arrow_array::StringViewArray;
+use arrow_array::builder::{ArrayBuilder, StringViewBuilder};
 use arrow_cast::pretty::pretty_format_batches;
 use bytes::Bytes;
-use criterion::{criterion_group, criterion_main, BenchmarkId, Criterion};
+use criterion::{BenchmarkId, Criterion, criterion_group, criterion_main};
 use futures::future::BoxFuture;
 use futures::{FutureExt, StreamExt};
 use parquet::arrow::arrow_reader::{
@@ -72,7 +72,7 @@ use parquet::arrow::{ArrowWriter, ParquetRecordBatchStreamBuilder, ProjectionMas
 use parquet::basic::Compression;
 use parquet::file::metadata::{PageIndexPolicy, ParquetMetaData, ParquetMetaDataReader};
 use parquet::file::properties::WriterProperties;
-use rand::{rngs::StdRng, Rng, SeedableRng};
+use rand::{Rng, SeedableRng, rngs::StdRng};
 use std::ops::Range;
 use std::sync::Arc;
 

parquet/benches/arrow_statistics.rs

@@ -23,10 +23,10 @@ use arrow_schema::{
     DataType::{self, *},
     Field, Schema,
 };
-use criterion::{criterion_group, criterion_main, BenchmarkId, Criterion};
+use criterion::{BenchmarkId, Criterion, criterion_group, criterion_main};
 use parquet::{arrow::arrow_reader::ArrowReaderOptions, file::properties::WriterProperties};
 use parquet::{
-    arrow::{arrow_reader::ArrowReaderBuilder, ArrowWriter},
+    arrow::{ArrowWriter, arrow_reader::ArrowReaderBuilder},
     file::properties::EnabledStatistics,
 };
 use std::sync::Arc;

parquet/benches/encoding.rs

@@ -21,7 +21,7 @@ use parquet::basic::{Encoding, Type as ParquetType};
 use parquet::data_type::{
     DataType, DoubleType, FixedLenByteArray, FixedLenByteArrayType, FloatType,
 };
-use parquet::decoding::{get_decoder, Decoder};
+use parquet::decoding::{Decoder, get_decoder};
 use parquet::encoding::get_encoder;
 use parquet::schema::types::{ColumnDescPtr, ColumnDescriptor, ColumnPath, Type};
 use rand::prelude::*;

parquet/examples/read_with_rowgroup.rs

@@ -19,7 +19,7 @@ use arrow::util::pretty::print_batches;
 use bytes::{Buf, Bytes};
 use parquet::arrow::arrow_reader::{ParquetRecordBatchReader, RowGroups, RowSelection};
 use parquet::arrow::async_reader::AsyncFileReader;
-use parquet::arrow::{parquet_to_arrow_field_levels, ProjectionMask};
+use parquet::arrow::{ProjectionMask, parquet_to_arrow_field_levels};
 use parquet::column::page::{PageIterator, PageReader};
 use parquet::errors::{ParquetError, Result};
 use parquet::file::metadata::RowGroupMetaData;

parquet/src/arrow/array_reader/builder.rs

@@ -19,20 +19,20 @@ use std::sync::{Arc, Mutex};
 
 use arrow_schema::{DataType, Fields, SchemaBuilder};
 
+use crate::arrow::ProjectionMask;
 use crate::arrow::array_reader::byte_view_array::make_byte_view_array_reader;
 use crate::arrow::array_reader::cached_array_reader::CacheRole;
 use crate::arrow::array_reader::cached_array_reader::CachedArrayReader;
 use crate::arrow::array_reader::empty_array::make_empty_array_reader;
 use crate::arrow::array_reader::fixed_len_byte_array::make_fixed_len_byte_array_reader;
 use crate::arrow::array_reader::row_group_cache::RowGroupCache;
 use crate::arrow::array_reader::{
-    make_byte_array_dictionary_reader, make_byte_array_reader, ArrayReader,
-    FixedSizeListArrayReader, ListArrayReader, MapArrayReader, NullArrayReader,
-    PrimitiveArrayReader, RowGroups, StructArrayReader,
+    ArrayReader, FixedSizeListArrayReader, ListArrayReader, MapArrayReader, NullArrayReader,
+    PrimitiveArrayReader, RowGroups, StructArrayReader, make_byte_array_dictionary_reader,
+    make_byte_array_reader,
 };
 use crate::arrow::arrow_reader::metrics::ArrowReaderMetrics;
 use crate::arrow::schema::{ParquetField, ParquetFieldType};
-use crate::arrow::ProjectionMask;
 use crate::basic::Type as PhysicalType;
 use crate::data_type::{BoolType, DoubleType, FloatType, Int32Type, Int64Type, Int96Type};
 use crate::errors::{ParquetError, Result};

parquet/src/arrow/array_reader/byte_array.rs

@@ -15,7 +15,7 @@
 // specific language governing permissions and limitations
 // under the License.
 
-use crate::arrow::array_reader::{read_records, skip_records, ArrayReader};
+use crate::arrow::array_reader::{ArrayReader, read_records, skip_records};
 use crate::arrow::buffer::bit_util::sign_extend_be;
 use crate::arrow::buffer::offset_buffer::OffsetBuffer;
 use crate::arrow::decoder::{DeltaByteArrayDecoder, DictIndexDecoder};
@@ -286,7 +286,7 @@ impl ByteArrayDecoder {
                 return Err(general_err!(
                     "unsupported encoding for byte array: {}",
                     encoding
-                ))
+                ));
             }
         };
 

parquet/src/arrow/array_reader/byte_array_dictionary.rs

@@ -19,13 +19,13 @@ use std::any::Any;
 use std::marker::PhantomData;
 use std::sync::Arc;
 
-use arrow_array::{new_empty_array, Array, ArrayRef, OffsetSizeTrait};
+use arrow_array::{Array, ArrayRef, OffsetSizeTrait, new_empty_array};
 use arrow_buffer::ArrowNativeType;
 use arrow_schema::DataType as ArrowType;
 use bytes::Bytes;
 
 use crate::arrow::array_reader::byte_array::{ByteArrayDecoder, ByteArrayDecoderPlain};
-use crate::arrow::array_reader::{read_records, skip_records, ArrayReader};
+use crate::arrow::array_reader::{ArrayReader, read_records, skip_records};
 use crate::arrow::buffer::{dictionary_buffer::DictionaryBuffer, offset_buffer::OffsetBuffer};
 use crate::arrow::record_reader::GenericRecordReader;
 use crate::arrow::schema::parquet_to_arrow_field;