Merge pull request #21 from constellation-rs/list

Vec -> List to optimize List<u8>

Cargo.toml

@@ -2,7 +2,7 @@
 
 [package]
 name = "amadeus"
-version = "0.1.4"
+version = "0.1.5"
 license = "Apache-2.0"
 authors = ["Alec Mocatta <[email protected]>"]
 categories = ["concurrency", "science", "database", "parser-implementations", "text-processing"]
@@ -14,7 +14,7 @@ parquet postgres aws s3 cloudfront elb json csv logs hadoop hdfs arrow common cr
 """
 repository = "https://github.com/alecmocatta/amadeus"
 homepage = "https://github.com/alecmocatta/amadeus"
-documentation = "https://docs.rs/amadeus/0.1.4"
+documentation = "https://docs.rs/amadeus/0.1.5"
 readme = "README.md"
 edition = "2018"
 
@@ -37,14 +37,14 @@ doc = ["amadeus-aws/doc", "amadeus-commoncrawl/doc", "amadeus-postgres/doc", "am
 features = ["doc", "constellation", "aws", "commoncrawl", "postgres", "csv", "json"]
 
 [dependencies]
-amadeus-core = { version = "=0.1.4", path = "amadeus-core" }
-amadeus-derive = { version = "=0.1.4", path = "amadeus-derive" }
-amadeus-types = { version = "=0.1.4", path = "amadeus-types" }
-amadeus-aws = { version = "=0.1.4", path = "amadeus-aws", optional = true }
-amadeus-commoncrawl = { version = "=0.1.4", path = "amadeus-commoncrawl", optional = true }
-amadeus-parquet = { version = "=0.1.4", path = "amadeus-parquet", optional = true }
-amadeus-postgres = { version = "=0.1.4", path = "amadeus-postgres", optional = true }
-amadeus-serde = { version = "=0.1.4", path = "amadeus-serde", optional = true }
+amadeus-core = { version = "=0.1.5", path = "amadeus-core" }
+amadeus-derive = { version = "=0.1.5", path = "amadeus-derive" }
+amadeus-types = { version = "=0.1.5", path = "amadeus-types" }
+amadeus-aws = { version = "=0.1.5", path = "amadeus-aws", optional = true }
+amadeus-commoncrawl = { version = "=0.1.5", path = "amadeus-commoncrawl", optional = true }
+amadeus-parquet = { version = "=0.1.5", path = "amadeus-parquet", optional = true }
+amadeus-postgres = { version = "=0.1.5", path = "amadeus-postgres", optional = true }
+amadeus-serde = { version = "=0.1.5", path = "amadeus-serde", optional = true }
 constellation-rs = { version = "0.1", default-features = false, optional = true }
 futures = "0.3"
 serde = { version = "1.0", features = ["derive"] }

README.md

@@ -13,7 +13,7 @@
 </p>
 
 <p align="center">
-    <a href="https://docs.rs/amadeus/0.1.4">📖 Docs</a> | <a href="https://constellation.rs/amadeus">🌐 Home</a> | <a href="https://constellation.zulipchat.com/#narrow/stream/213231-amadeus">💬 Chat</a>
+    <a href="https://docs.rs/amadeus/0.1.5">📖 Docs</a> | <a href="https://constellation.rs/amadeus">🌐 Home</a> | <a href="https://constellation.zulipchat.com/#narrow/stream/213231-amadeus">💬 Chat</a>
 </p>
 
 ## Amadeus provides:
@@ -50,7 +50,7 @@ We aim to create a community that is welcoming and helpful to anyone that is int
 
 Amadeus has deep, pluggable, integration with various file formats, databases and interfaces:
 
-| Data format | [`Source`](https://docs.rs/amadeus/0.1.4/amadeus/trait.Source.html) | [`Sink`](https://docs.rs/amadeus/0.1.4/amadeus/trait.Sink.html) |
+| Data format | [`Source`](https://docs.rs/amadeus/0.1.5/amadeus/trait.Source.html) | [`Sink`](https://docs.rs/amadeus/0.1.5/amadeus/trait.Sink.html) |
 |---|---|---|
 | CSV | ✔ | ✔ |
 | JSON | ✔ | ✔ |

amadeus-aws/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "amadeus-aws"
-version = "0.1.4"
+version = "0.1.5"
 license = "Apache-2.0"
 authors = ["Alec Mocatta <[email protected]>"]
 categories = ["concurrency", "science", "database", "parser-implementations", "text-processing"]
@@ -10,7 +10,7 @@ Harmonious distributed data analysis in Rust.
 """
 repository = "https://github.com/alecmocatta/amadeus"
 homepage = "https://github.com/alecmocatta/amadeus"
-documentation = "https://docs.rs/amadeus/0.1.4"
+documentation = "https://docs.rs/amadeus/0.1.5"
 readme = "README.md"
 edition = "2018"
 
@@ -22,12 +22,12 @@ maintenance = { status = "actively-developed" }
 doc = []
 
 [dependencies]
-amadeus-core = { version = "=0.1.4", path = "../amadeus-core" }
-amadeus-types = { version = "=0.1.4", path = "../amadeus-types" }
+amadeus-core = { version = "=0.1.5", path = "../amadeus-core" }
+amadeus-types = { version = "=0.1.5", path = "../amadeus-types" }
 chrono = { version = "0.4", default-features = false }
 flate2 = "1.0"
 futures-01 = { package = "futures", version = "0.1" }
-futures-preview = { version = "=0.3.0-alpha.19", features = ["compat"] }
+futures = { version = "0.3", features = ["compat"] }
 http = "0.2"
 once_cell = "1.0"
 rusoto_core = "0.42"

amadeus-aws/src/lib.rs

@@ -1,4 +1,4 @@
-#![doc(html_root_url = "https://docs.rs/amadeus-aws/0.1.4")]
+#![doc(html_root_url = "https://docs.rs/amadeus-aws/0.1.5")]
 #![feature(type_alias_impl_trait)]
 
 mod cloudfront;

amadeus-commoncrawl/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "amadeus-commoncrawl"
-version = "0.1.4"
+version = "0.1.5"
 license = "MIT OR Apache-2.0"
 authors = ["Stephen Becker IV <[email protected]>", "Alec Mocatta <[email protected]>"]
 categories = ["concurrency", "science", "database", "parser-implementations", "text-processing"]
@@ -10,7 +10,7 @@ Harmonious distributed data analysis in Rust.
 """
 repository = "https://github.com/alecmocatta/amadeus"
 homepage = "https://github.com/alecmocatta/amadeus"
-documentation = "https://docs.rs/amadeus/0.1.4"
+documentation = "https://docs.rs/amadeus/0.1.5"
 readme = "README.md"
 edition = "2018"
 
@@ -22,8 +22,8 @@ maintenance = { status = "actively-developed" }
 doc = []
 
 [dependencies]
-amadeus-core = { version = "=0.1.4", path = "../amadeus-core" }
-amadeus-types = { version = "=0.1.4", path = "../amadeus-types" }
+amadeus-core = { version = "=0.1.5", path = "../amadeus-core" }
+amadeus-types = { version = "=0.1.5", path = "../amadeus-types" }
 flate2 = "1.0"
 reqwest = "0.9"
 reqwest_resume = "0.2"

amadeus-commoncrawl/src/lib.rs

@@ -1,4 +1,4 @@
-#![doc(html_root_url = "https://docs.rs/amadeus-commoncrawl/0.1.4")]
+#![doc(html_root_url = "https://docs.rs/amadeus-commoncrawl/0.1.5")]
 #![feature(type_alias_impl_trait)]
 
 mod commoncrawl;

amadeus-core/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "amadeus-core"
-version = "0.1.4"
+version = "0.1.5"
 license = "Apache-2.0"
 authors = ["Alec Mocatta <[email protected]>"]
 categories = ["concurrency", "science", "database", "parser-implementations", "text-processing"]
@@ -10,7 +10,7 @@ Harmonious distributed data analysis in Rust.
 """
 repository = "https://github.com/alecmocatta/amadeus"
 homepage = "https://github.com/alecmocatta/amadeus"
-documentation = "https://docs.rs/amadeus/0.1.4"
+documentation = "https://docs.rs/amadeus/0.1.5"
 readme = "README.md"
 edition = "2018"
 
@@ -20,7 +20,7 @@ maintenance = { status = "actively-developed" }
 
 [dependencies]
 either = { version = "1.5", features = ["serde"] }
-futures-preview = "=0.3.0-alpha.19"
+futures = "0.3"
 owned_chars = "0.3"
 rand = "0.7"
 replace_with = "0.1"

amadeus-core/src/lib.rs

@@ -1,4 +1,4 @@
-#![doc(html_root_url = "https://docs.rs/amadeus-core/0.1.4")]
+#![doc(html_root_url = "https://docs.rs/amadeus-core/0.1.5")]
 #![feature(atomic_min_max)]
 #![feature(specialization)]
 #![feature(read_initializer)]

amadeus-derive/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "amadeus-derive"
-version = "0.1.4"
+version = "0.1.5"
 license = "Apache-2.0"
 authors = ["Alec Mocatta <[email protected]>"]
 categories = ["concurrency", "science", "database", "parser-implementations", "text-processing"]
@@ -10,7 +10,7 @@ Harmonious distributed data analysis in Rust.
 """
 repository = "https://github.com/alecmocatta/amadeus"
 homepage = "https://github.com/alecmocatta/amadeus"
-documentation = "https://docs.rs/amadeus/0.1.4"
+documentation = "https://docs.rs/amadeus/0.1.5"
 readme = "README.md"
 edition = "2018"
 

amadeus-derive/src/lib.rs

@@ -15,7 +15,7 @@
 // specific language governing permissions and limitations
 // under the License.
 
-#![doc(html_root_url = "https://docs.rs/amadeus-derive/0.1.4")]
+#![doc(html_root_url = "https://docs.rs/amadeus-derive/0.1.5")]
 #![recursion_limit = "400"]
 #![allow(clippy::useless_let_if_seq)]
 

amadeus-parquet/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "amadeus-parquet"
-version = "0.1.4"
+version = "0.1.5"
 license = "Apache-2.0"
 authors = ["Alec Mocatta <[email protected]>", "Apache Arrow <[email protected]>"]
 categories = ["concurrency", "science", "database", "parser-implementations", "text-processing"]
@@ -10,7 +10,7 @@ An Apache Parquet implementation in Rust.
 """
 repository = "https://github.com/alecmocatta/amadeus"
 homepage = "https://github.com/alecmocatta/amadeus"
-documentation = "https://docs.rs/amadeus/0.1.4"
+documentation = "https://docs.rs/amadeus/0.1.5"
 readme = "README.md"
 edition = "2018"
 
@@ -22,8 +22,8 @@ maintenance = { status = "actively-developed" }
 doc = []
 
 [dependencies]
-amadeus-core = { version = "=0.1.4", path = "../amadeus-core" }
-amadeus-types = { version = "=0.1.4", path = "../amadeus-types" }
+amadeus-core = { version = "=0.1.5", path = "../amadeus-core" }
+amadeus-types = { version = "=0.1.5", path = "../amadeus-types" }
 brotli = "3.3"
 byteorder = "1.2"
 chrono = { version = "0.4", default-features = false }

amadeus-parquet/src/internal/file/reader.rs

@@ -667,7 +667,7 @@ mod tests {
 	use std::collections::HashMap;
 	use test::Bencher;
 
-	use amadeus_types::{DateTime, Group};
+	use amadeus_types::{DateTime, Group, List};
 
 	use super::*;
 	use crate::internal::{
@@ -1120,7 +1120,7 @@ mod tests {
 
 		bench.bytes = len;
 		bench.iter(|| {
-			type RowTyped = (Vec<u8>, i32, i64, bool, f32, f64, Vec<u8>, DateTime); // [u8; 1024]
+			type RowTyped = (List<u8>, i32, i64, bool, f32, f64, List<u8>, DateTime); // [u8; 1024]
 			(&parquet_reader)
 				.get_row_iter::<RowTyped>(None)
 				.unwrap()

amadeus-parquet/src/internal/record/impls.rs

@@ -6,7 +6,7 @@ use sum::{Sum2, Sum3};
 
 use amadeus_core::util::type_coerce;
 use amadeus_types::{
-	Bson, Date, DateTime, DateTimeWithoutTimezone, DateWithoutTimezone, Decimal, Enum, Group, IpAddr, Json, Time, TimeWithoutTimezone, Timezone, Url, Value, Webpage
+	Bson, Date, DateTime, DateTimeWithoutTimezone, DateWithoutTimezone, Decimal, Enum, Group, IpAddr, Json, List, Time, TimeWithoutTimezone, Timezone, Url, Value, Webpage
 };
 
 #[cfg(debug_assertions)]
@@ -467,7 +467,7 @@ pub(super) fn parse_list<T: ParquetData>(schema: &Type) -> Result<ListSchema<T::
 	Err(ParquetError::General(String::from("Couldn't parse Vec<T>")))
 }
 
-impl<T> ParquetData for Vec<T>
+impl<T> ParquetData for List<T>
 where
 	T: ParquetData,
 {
@@ -576,7 +576,7 @@ fn byte_array_reader(
 	}
 }
 
-impl ParquetData for Vec<u8> {
+impl ParquetData for List<u8> {
 	type Schema = VecU8Schema;
 	type Reader = VecU8Reader;
 
@@ -1913,7 +1913,7 @@ impl ParquetData for Value {
 				schema, path, def_level, rep_level, paths, batch_size,
 			)),
 			ValueSchema::List(ref schema) => {
-				ValueReader::List(Box::new(<Vec<Value> as ParquetData>::reader(
+				ValueReader::List(Box::new(<List<Value> as ParquetData>::reader(
 					type_coerce(&**schema),
 					path,
 					def_level,