chore: Release

* Added per-field size details.

This also does a bunch of refactoring.

merging field metadata does not silently asserts that arguments should be sorted.
merging does not set `stored`.

We do not rely on a hashmap to group fields, but instead rely on the fact that
the term dictionary is sorted.

The inverted level method that exposes field metadata is not exposed
as public anymore.

* CR comment

---------

Co-authored-by: Paul Masurel <paul.masurel@datadoghq.com>

CHANGELOG.md

@@ -1,6 +1,22 @@
-Tantivy 0.23 - Unreleased
+Tantivy 0.25
 ================================
-Tantivy 0.23 will be backwards compatible with indices created with v0.22 and v0.21. The new minimum rust version will be 1.75.
+
+## Bugfixes
+- fix union performance regression in tantivy 0.24 [#2663](https://github.com/quickwit-oss/tantivy/pull/2663)(@PSeitz)
+- make zstd optional in sstable [#2633](https://github.com/quickwit-oss/tantivy/pull/2633)(@Parth)
+- Fix TopDocs::order_by_string_fast_field for asc order [#2672](https://github.com/quickwit-oss/tantivy/pull/2672)(@stuhood @PSeitz)
+
+## Features/Improvements
+- add docs/example and Vec<u32> values to sstable [#2660](https://github.com/quickwit-oss/tantivy/pull/2660)(@PSeitz)
+- Add string fast field support to `TopDocs`. [#2642](https://github.com/quickwit-oss/tantivy/pull/2642)(@stuhood)
+- update edition to 2024 [#2620](https://github.com/quickwit-oss/tantivy/pull/2620)(@PSeitz)
+- Allow optional spaces between the field name and the value in the query parser [#2678](https://github.com/quickwit-oss/tantivy/pull/2678)(@Darkheir)
+- Support mixed field types in query parser [#2676](https://github.com/quickwit-oss/tantivy/pull/2676)(@trinity-1686a)
+- Add per-field size details [#2679](https://github.com/quickwit-oss/tantivy/pull/2679)(@fulmicoton)
+
+Tantivy 0.24
+================================
+Tantivy 0.24 will be backwards compatible with indices created with v0.22 and v0.21. The new minimum rust version will be 1.75. Tantivy 0.23 will be skipped.
 
 #### Bugfixes
 - fix potential endless loop in merge [#2457](https://github.com/quickwit-oss/tantivy/pull/2457)(@PSeitz)

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy"
-version = "0.22.0"
+version = "0.25.0"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
@@ -11,7 +11,7 @@ repository = "https://github.com/quickwit-oss/tantivy"
 readme = "README.md"
 keywords = ["search", "information", "retrieval"]
 edition = "2021"
-rust-version = "1.75"
+rust-version = "1.85"
 exclude = ["benches/*.json", "benches/*.txt"]
 
 [dependencies]
@@ -33,7 +33,7 @@ tempfile = { version = "3.12.0", optional = true }
 log = "0.4.16"
 serde = { version = "1.0.219", features = ["derive"] }
 serde_json = "1.0.140"
-fs4 = { version = "0.8.0", optional = true }
+fs4 = { version = "0.13.1", optional = true }
 levenshtein_automata = "0.2.1"
 uuid = { version = "1.0.0", features = ["v4", "serde"] }
 crossbeam-channel = "0.5.4"
@@ -57,13 +57,13 @@ measure_time = "0.9.0"
 arc-swap = "1.5.0"
 bon = "3.3.1"
 
-columnar = { version = "0.3", path = "./columnar", package = "tantivy-columnar" }
-sstable = { version = "0.3", path = "./sstable", package = "tantivy-sstable", optional = true }
-stacker = { version = "0.3", path = "./stacker", package = "tantivy-stacker" }
-query-grammar = { version = "0.22.0", path = "./query-grammar", package = "tantivy-query-grammar" }
-tantivy-bitpacker = { version = "0.6", path = "./bitpacker" }
-common = { version = "0.7", path = "./common/", package = "tantivy-common" }
-tokenizer-api = { version = "0.3", path = "./tokenizer-api", package = "tantivy-tokenizer-api" }
+columnar = { version = "0.6", path = "./columnar", package = "tantivy-columnar" }
+sstable = { version = "0.6", path = "./sstable", package = "tantivy-sstable", optional = true }
+stacker = { version = "0.6", path = "./stacker", package = "tantivy-stacker" }
+query-grammar = { version = "0.25.0", path = "./query-grammar", package = "tantivy-query-grammar" }
+tantivy-bitpacker = { version = "0.9", path = "./bitpacker" }
+common = { version = "0.10", path = "./common/", package = "tantivy-common" }
+tokenizer-api = { version = "0.6", path = "./tokenizer-api", package = "tantivy-tokenizer-api" }
 sketches-ddsketch = { version = "0.3.0", features = ["use_serde"] }
 hyperloglogplus = { version = "0.4.1", features = ["const-loop"] }
 futures-util = { version = "0.3.28", optional = true }
@@ -112,13 +112,16 @@ debug-assertions = true
 overflow-checks = true
 
 [features]
-default = ["mmap", "stopwords", "lz4-compression"]
+default = ["mmap", "stopwords", "lz4-compression", "columnar-zstd-compression"]
 mmap = ["fs4", "tempfile", "memmap2"]
 stopwords = []
 
 lz4-compression = ["lz4_flex"]
 zstd-compression = ["zstd"]
 
+# enable zstd-compression in columnar (and sstable)
+columnar-zstd-compression = ["columnar/zstd-compression"]
+
 failpoints = ["fail", "fail/failpoints"]
 unstable = []                            # useful for benches.
 

bitpacker/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "tantivy-bitpacker"
-version = "0.6.0"
-edition = "2021"
+version = "0.9.0"
+edition = "2024"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = []

bitpacker/src/blocked_bitpacker.rs

@@ -1,6 +1,6 @@
 use super::bitpacker::BitPacker;
 use super::compute_num_bits;
-use crate::{minmax, BitUnpacker};
+use crate::{BitUnpacker, minmax};
 
 const BLOCK_SIZE: usize = 128;
 

bitpacker/src/lib.rs

@@ -33,11 +33,7 @@ pub use crate::blocked_bitpacker::BlockedBitpacker;
 /// number of bits.
 pub fn compute_num_bits(n: u64) -> u8 {
     let amplitude = (64u32 - n.leading_zeros()) as u8;
-    if amplitude <= 64 - 8 {
-        amplitude
-    } else {
-        64
-    }
+    if amplitude <= 64 - 8 { amplitude } else { 64 }
 }
 
 /// Computes the (min, max) of an iterator of `PartialOrd` values.

columnar/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "tantivy-columnar"
-version = "0.3.0"
-edition = "2021"
+version = "0.6.0"
+edition = "2024"
 license = "MIT"
 homepage = "https://github.com/quickwit-oss/tantivy"
 repository = "https://github.com/quickwit-oss/tantivy"
@@ -12,10 +12,10 @@ categories = ["database-implementations", "data-structures", "compression"]
 itertools = "0.14.0"
 fastdivide = "0.4.0"
 
-stacker = { version= "0.3", path = "../stacker", package="tantivy-stacker"}
-sstable = { version= "0.3", path = "../sstable", package = "tantivy-sstable" }
-common = { version= "0.7", path = "../common", package = "tantivy-common" }
-tantivy-bitpacker = { version= "0.6", path = "../bitpacker/" }
+stacker = { version= "0.6", path = "../stacker", package="tantivy-stacker"}
+sstable = { version= "0.6", path = "../sstable", package = "tantivy-sstable" }
+common = { version= "0.10", path = "../common", package = "tantivy-common" }
+tantivy-bitpacker = { version= "0.9", path = "../bitpacker/" }
 serde = "1.0.152"
 downcast-rs = "2.0.1"
 
@@ -33,6 +33,29 @@ harness = false
 name = "bench_access"
 harness = false
 
+[[bench]]
+name = "bench_first_vals"
+harness = false
+
+[[bench]]
+name = "bench_values_u64"
+harness = false
+
+[[bench]]
+name = "bench_values_u128"
+harness = false
+
+[[bench]]
+name = "bench_create_column_values"
+harness = false
+
+[[bench]]
+name = "bench_column_values_get"
+harness = false
+
+[[bench]]
+name = "bench_optional_index"
+harness = false
 
 [features]
-unstable = []
+zstd-compression = ["sstable/zstd-compression"]

columnar/benches/bench_access.rs

@@ -1,4 +1,4 @@
-use binggan::{black_box, InputGroup};
+use binggan::{InputGroup, black_box};
 use common::*;
 use tantivy_columnar::Column;
 
@@ -19,7 +19,7 @@ fn main() {
 
     let mut add_card = |card1: Card| {
         inputs.push((
-            format!("{card1}"),
+            card1.to_string(),
             generate_columnar_and_open(card1, NUM_DOCS),
         ));
     };
@@ -50,6 +50,7 @@ fn bench_group(mut runner: InputGroup<Column>) {
         let mut buffer = vec![None; BLOCK_SIZE];
         for i in (0..NUM_DOCS).step_by(BLOCK_SIZE) {
             // fill docs
+            #[allow(clippy::needless_range_loop)]
             for idx in 0..BLOCK_SIZE {
                 docs[idx] = idx as u32 + i;
             }

columnar/benches/bench_column_values_get.rs

@@ -0,0 +1,61 @@
+use std::sync::Arc;
+
+use binggan::{InputGroup, black_box};
+use rand::rngs::StdRng;
+use rand::{Rng, SeedableRng};
+use tantivy_columnar::ColumnValues;
+use tantivy_columnar::column_values::{CodecType, serialize_and_load_u64_based_column_values};
+
+fn get_data() -> Vec<u64> {
+    let mut rng = StdRng::seed_from_u64(2u64);
+    let mut data: Vec<_> = (100..55_000_u64)
+        .map(|num| num + rng.r#gen::<u8>() as u64)
+        .collect();
+    data.push(99_000);
+    data.insert(1000, 2000);
+    data.insert(2000, 100);
+    data.insert(3000, 4100);
+    data.insert(4000, 100);
+    data.insert(5000, 800);
+    data
+}
+
+#[inline(never)]
+fn value_iter() -> impl Iterator<Item = u64> {
+    0..20_000
+}
+
+type Col = Arc<dyn ColumnValues<u64>>;
+
+fn main() {
+    let data = get_data();
+    let inputs: Vec<(String, Col)> = vec![
+        (
+            "bitpacked".to_string(),
+            serialize_and_load_u64_based_column_values(&data.as_slice(), &[CodecType::Bitpacked]),
+        ),
+        (
+            "linear".to_string(),
+            serialize_and_load_u64_based_column_values(&data.as_slice(), &[CodecType::Linear]),
+        ),
+        (
+            "blockwise_linear".to_string(),
+            serialize_and_load_u64_based_column_values(
+                &data.as_slice(),
+                &[CodecType::BlockwiseLinear],
+            ),
+        ),
+    ];
+
+    let mut group: InputGroup<Col> = InputGroup::new_with_inputs(inputs);
+
+    group.register("fastfield_get", |col: &Col| {
+        let mut sum = 0u64;
+        for pos in value_iter() {
+            sum = sum.wrapping_add(col.get_val(pos as u32));
+        }
+        black_box(sum);
+    });
+
+    group.run();
+}

columnar/benches/bench_create_column_values.rs

@@ -0,0 +1,44 @@
+use binggan::{InputGroup, black_box};
+use rand::rngs::StdRng;
+use rand::{Rng, SeedableRng};
+use tantivy_columnar::column_values::{CodecType, serialize_u64_based_column_values};
+
+fn get_data() -> Vec<u64> {
+    let mut rng = StdRng::seed_from_u64(2u64);
+    let mut data: Vec<_> = (100..55_000_u64)
+        .map(|num| num + rng.r#gen::<u8>() as u64)
+        .collect();
+    data.push(99_000);
+    data.insert(1000, 2000);
+    data.insert(2000, 100);
+    data.insert(3000, 4100);
+    data.insert(4000, 100);
+    data.insert(5000, 800);
+    data
+}
+
+fn main() {
+    let data = get_data();
+    let mut group: InputGroup<(CodecType, Vec<u64>)> = InputGroup::new_with_inputs(vec![
+        (
+            "bitpacked codec".to_string(),
+            (CodecType::Bitpacked, data.clone()),
+        ),
+        (
+            "linear codec".to_string(),
+            (CodecType::Linear, data.clone()),
+        ),
+        (
+            "blockwise linear codec".to_string(),
+            (CodecType::BlockwiseLinear, data.clone()),
+        ),
+    ]);
+
+    group.register("serialize column_values", |data| {
+        let mut buffer = Vec::new();
+        serialize_u64_based_column_values(&data.1.as_slice(), &[data.0], &mut buffer).unwrap();
+        black_box(buffer.len());
+    });
+
+    group.run();
+}

columnar/benches/bench_first_vals.rs

@@ -1,12 +1,9 @@
-#![feature(test)]
-extern crate test;
-
 use std::sync::Arc;
 
+use binggan::{InputGroup, black_box};
 use rand::prelude::*;
-use tantivy_columnar::column_values::{serialize_and_load_u64_based_column_values, CodecType};
+use tantivy_columnar::column_values::{CodecType, serialize_and_load_u64_based_column_values};
 use tantivy_columnar::*;
-use test::{black_box, Bencher};
 
 struct Columns {
     pub optional: Column,
@@ -68,88 +65,45 @@ pub fn serialize_and_load(column: &[u64], codec_type: CodecType) -> Arc<dyn Colu
     serialize_and_load_u64_based_column_values(&column, &[codec_type])
 }
 
-fn run_bench_on_column_full_scan(b: &mut Bencher, column: Column) {
-    let num_iter = black_box(NUM_VALUES);
-    b.iter(|| {
+fn main() {
+    let Columns {
+        optional,
+        full,
+        multi,
+    } = get_test_columns();
+
+    let inputs = vec![
+        ("full".to_string(), full),
+        ("optional".to_string(), optional),
+        ("multi".to_string(), multi),
+    ];
+
+    let mut group = InputGroup::new_with_inputs(inputs);
+
+    group.register("first_full_scan", |column| {
         let mut sum = 0u64;
-        for i in 0..num_iter as u32 {
+        for i in 0..NUM_VALUES as u32 {
             let val = column.first(i);
             sum += val.unwrap_or(0);
         }
-        sum
+        black_box(sum);
     });
-}
-fn run_bench_on_column_block_fetch(b: &mut Bencher, column: Column) {
-    let mut block: Vec<Option<u64>> = vec![None; 64];
-    let fetch_docids = (0..64).collect::<Vec<_>>();
-    b.iter(move || {
+
+    group.register("first_block_fetch", |column| {
+        let mut block: Vec<Option<u64>> = vec![None; 64];
+        let fetch_docids = (0..64).collect::<Vec<_>>();
         column.first_vals(&fetch_docids, &mut block);
-        block[0]
+        black_box(block[0]);
     });
-}
-fn run_bench_on_column_block_single_calls(b: &mut Bencher, column: Column) {
-    let mut block: Vec<Option<u64>> = vec![None; 64];
-    let fetch_docids = (0..64).collect::<Vec<_>>();
-    b.iter(move || {
+
+    group.register("first_block_single_calls", |column| {
+        let mut block: Vec<Option<u64>> = vec![None; 64];
+        let fetch_docids = (0..64).collect::<Vec<_>>();
         for i in 0..fetch_docids.len() {
             block[i] = column.first(fetch_docids[i]);
         }
-        block[0]
+        black_box(block[0]);
     });
-}
 
-/// Column first method
-#[bench]
-fn bench_get_first_on_full_column_full_scan(b: &mut Bencher) {
-    let column = get_test_columns().full;
-    run_bench_on_column_full_scan(b, column);
-}
-
-#[bench]
-fn bench_get_first_on_optional_column_full_scan(b: &mut Bencher) {
-    let column = get_test_columns().optional;
-    run_bench_on_column_full_scan(b, column);
-}
-
-#[bench]
-fn bench_get_first_on_multi_column_full_scan(b: &mut Bencher) {
-    let column = get_test_columns().multi;
-    run_bench_on_column_full_scan(b, column);
-}
-
-/// Block fetch column accessor
-#[bench]
-fn bench_get_block_first_on_optional_column(b: &mut Bencher) {
-    let column = get_test_columns().optional;
-    run_bench_on_column_block_fetch(b, column);
-}
-
-#[bench]
-fn bench_get_block_first_on_multi_column(b: &mut Bencher) {
-    let column = get_test_columns().multi;
-    run_bench_on_column_block_fetch(b, column);
-}
-
-#[bench]
-fn bench_get_block_first_on_full_column(b: &mut Bencher) {
-    let column = get_test_columns().full;
-    run_bench_on_column_block_fetch(b, column);
-}
-
-#[bench]
-fn bench_get_block_first_on_optional_column_single_calls(b: &mut Bencher) {
-    let column = get_test_columns().optional;
-    run_bench_on_column_block_single_calls(b, column);
-}
-
-#[bench]
-fn bench_get_block_first_on_multi_column_single_calls(b: &mut Bencher) {
-    let column = get_test_columns().multi;
-    run_bench_on_column_block_single_calls(b, column);
-}
-
-#[bench]
-fn bench_get_block_first_on_full_column_single_calls(b: &mut Bencher) {
-    let column = get_test_columns().full;
-    run_bench_on_column_block_single_calls(b, column);
+    group.run();
 }

columnar/benches/bench_merge.rs

@@ -1,7 +1,7 @@
 pub mod common;
 
 use binggan::BenchRunner;
-use common::{generate_columnar_with_name, Card};
+use common::{Card, generate_columnar_with_name};
 use tantivy_columnar::*;
 
 const NUM_DOCS: u32 = 100_000;

columnar/benches/bench_optional_index.rs

@@ -0,0 +1,106 @@
+use binggan::{InputGroup, black_box};
+use rand::rngs::StdRng;
+use rand::{Rng, SeedableRng};
+use tantivy_columnar::column_index::{OptionalIndex, Set};
+
+const TOTAL_NUM_VALUES: u32 = 1_000_000;
+
+fn gen_optional_index(fill_ratio: f64) -> OptionalIndex {
+    let mut rng: StdRng = StdRng::from_seed([1u8; 32]);
+    let vals: Vec<u32> = (0..TOTAL_NUM_VALUES)
+        .map(|_| rng.gen_bool(fill_ratio))
+        .enumerate()
+        .filter(|(_pos, val)| *val)
+        .map(|(pos, _)| pos as u32)
+        .collect();
+    OptionalIndex::for_test(TOTAL_NUM_VALUES, &vals)
+}
+
+fn random_range_iterator(
+    start: u32,
+    end: u32,
+    avg_step_size: u32,
+    avg_deviation: u32,
+) -> impl Iterator<Item = u32> {
+    let mut rng: StdRng = StdRng::from_seed([1u8; 32]);
+    let mut current = start;
+    std::iter::from_fn(move || {
+        current += rng.gen_range(avg_step_size - avg_deviation..=avg_step_size + avg_deviation);
+        if current >= end { None } else { Some(current) }
+    })
+}
+
+fn n_percent_step_iterator(percent: f32, num_values: u32) -> impl Iterator<Item = u32> {
+    let ratio = percent / 100.0;
+    let step_size = (1f32 / ratio) as u32;
+    let deviation = step_size - 1;
+    random_range_iterator(0, num_values, step_size, deviation)
+}
+
+fn walk_over_data(codec: &OptionalIndex, avg_step_size: u32) -> Option<u32> {
+    walk_over_data_from_positions(
+        codec,
+        random_range_iterator(0, TOTAL_NUM_VALUES, avg_step_size, 0),
+    )
+}
+
+fn walk_over_data_from_positions(
+    codec: &OptionalIndex,
+    positions: impl Iterator<Item = u32>,
+) -> Option<u32> {
+    let mut dense_idx: Option<u32> = None;
+    for idx in positions {
+        dense_idx = dense_idx.or(codec.rank_if_exists(idx));
+    }
+    dense_idx
+}
+
+fn main() {
+    // Build separate inputs for each fill ratio.
+    let inputs: Vec<(String, OptionalIndex)> = vec![
+        ("fill=1%".to_string(), gen_optional_index(0.01)),
+        ("fill=5%".to_string(), gen_optional_index(0.05)),
+        ("fill=10%".to_string(), gen_optional_index(0.10)),
+        ("fill=50%".to_string(), gen_optional_index(0.50)),
+        ("fill=90%".to_string(), gen_optional_index(0.90)),
+    ];
+
+    let mut group: InputGroup<OptionalIndex> = InputGroup::new_with_inputs(inputs);
+
+    // Translate orig->codec (rank_if_exists) with sampling
+    group.register("orig_to_codec_10pct_hit", |codec: &OptionalIndex| {
+        black_box(walk_over_data(codec, 100));
+    });
+    group.register("orig_to_codec_1pct_hit", |codec: &OptionalIndex| {
+        black_box(walk_over_data(codec, 1000));
+    });
+    group.register("orig_to_codec_full_scan", |codec: &OptionalIndex| {
+        black_box(walk_over_data_from_positions(codec, 0..TOTAL_NUM_VALUES));
+    });
+
+    // Translate codec->orig (select/select_batch) on sampled ranks
+    fn bench_translate_codec_to_orig_util(codec: &OptionalIndex, percent_hit: f32) {
+        let num_non_nulls = codec.num_non_nulls();
+        let idxs: Vec<u32> = if percent_hit == 100.0f32 {
+            (0..num_non_nulls).collect()
+        } else {
+            n_percent_step_iterator(percent_hit, num_non_nulls).collect()
+        };
+        let mut output = vec![0u32; idxs.len()];
+        output.copy_from_slice(&idxs[..]);
+        codec.select_batch(&mut output);
+        black_box(output);
+    }
+
+    group.register("codec_to_orig_0.005pct_hit", |codec: &OptionalIndex| {
+        bench_translate_codec_to_orig_util(codec, 0.005);
+    });
+    group.register("codec_to_orig_10pct_hit", |codec: &OptionalIndex| {
+        bench_translate_codec_to_orig_util(codec, 10.0);
+    });
+    group.register("codec_to_orig_full_scan", |codec: &OptionalIndex| {
+        bench_translate_codec_to_orig_util(codec, 100.0);
+    });
+
+    group.run();
+}

columnar/benches/bench_values_u128.rs

@@ -1,15 +1,12 @@
-#![feature(test)]
-
 use std::ops::RangeInclusive;
 use std::sync::Arc;
 
+use binggan::{InputGroup, black_box};
 use common::OwnedBytes;
 use rand::rngs::StdRng;
 use rand::seq::SliceRandom;
-use rand::{random, Rng, SeedableRng};
+use rand::{Rng, SeedableRng, random};
 use tantivy_columnar::ColumnValues;
-use test::Bencher;
-extern crate test;
 
 // TODO does this make sense for IPv6 ?
 fn generate_random() -> Vec<u64> {
@@ -47,78 +44,77 @@ fn get_data_50percent_item() -> Vec<u128> {
     }
     data.push(SINGLE_ITEM);
     data.shuffle(&mut rng);
-    let data = data.iter().map(|el| *el as u128).collect::<Vec<_>>();
-    data
+    data.iter().map(|el| *el as u128).collect::<Vec<_>>()
 }
 
-#[bench]
-fn bench_intfastfield_getrange_u128_50percent_hit(b: &mut Bencher) {
+fn main() {
     let data = get_data_50percent_item();
-    let column = get_u128_column_from_data(&data);
+    let column_range = get_u128_column_from_data(&data);
+    let column_random = get_u128_column_random();
 
-    b.iter(|| {
+    struct Inputs {
+        data: Vec<u128>,
+        column_range: Arc<dyn ColumnValues<u128>>,
+        column_random: Arc<dyn ColumnValues<u128>>,
+    }
+
+    let inputs = Inputs {
+        data,
+        column_range,
+        column_random,
+    };
+    let mut group: InputGroup<Inputs> =
+        InputGroup::new_with_inputs(vec![("u128 benches".to_string(), inputs)]);
+
+    group.register(
+        "intfastfield_getrange_u128_50percent_hit",
+        |inp: &Inputs| {
+            let mut positions = Vec::new();
+            inp.column_range.get_row_ids_for_value_range(
+                *FIFTY_PERCENT_RANGE.start() as u128..=*FIFTY_PERCENT_RANGE.end() as u128,
+                0..inp.data.len() as u32,
+                &mut positions,
+            );
+            black_box(positions.len());
+        },
+    );
+
+    group.register("intfastfield_getrange_u128_single_hit", |inp: &Inputs| {
         let mut positions = Vec::new();
-        column.get_row_ids_for_value_range(
-            *FIFTY_PERCENT_RANGE.start() as u128..=*FIFTY_PERCENT_RANGE.end() as u128,
-            0..data.len() as u32,
-            &mut positions,
-        );
-        positions
-    });
-}
-
-#[bench]
-fn bench_intfastfield_getrange_u128_single_hit(b: &mut Bencher) {
-    let data = get_data_50percent_item();
-    let column = get_u128_column_from_data(&data);
-
-    b.iter(|| {
-        let mut positions = Vec::new();
-        column.get_row_ids_for_value_range(
+        inp.column_range.get_row_ids_for_value_range(
             *SINGLE_ITEM_RANGE.start() as u128..=*SINGLE_ITEM_RANGE.end() as u128,
-            0..data.len() as u32,
+            0..inp.data.len() as u32,
             &mut positions,
         );
-        positions
+        black_box(positions.len());
     });
-}
 
-#[bench]
-fn bench_intfastfield_getrange_u128_hit_all(b: &mut Bencher) {
-    let data = get_data_50percent_item();
-    let column = get_u128_column_from_data(&data);
-
-    b.iter(|| {
+    group.register("intfastfield_getrange_u128_hit_all", |inp: &Inputs| {
         let mut positions = Vec::new();
-        column.get_row_ids_for_value_range(0..=u128::MAX, 0..data.len() as u32, &mut positions);
-        positions
+        inp.column_range.get_row_ids_for_value_range(
+            0..=u128::MAX,
+            0..inp.data.len() as u32,
+            &mut positions,
+        );
+        black_box(positions.len());
     });
-}
-// U128 RANGE END
 
-#[bench]
-fn bench_intfastfield_scan_all_fflookup_u128(b: &mut Bencher) {
-    let column = get_u128_column_random();
-
-    b.iter(|| {
+    group.register("intfastfield_scan_all_fflookup_u128", |inp: &Inputs| {
         let mut a = 0u128;
-        for i in 0u64..column.num_vals() as u64 {
-            a += column.get_val(i as u32);
+        for i in 0u64..inp.column_random.num_vals() as u64 {
+            a += inp.column_random.get_val(i as u32);
         }
-        a
+        black_box(a);
     });
-}
 
-#[bench]
-fn bench_intfastfield_jumpy_stride5_u128(b: &mut Bencher) {
-    let column = get_u128_column_random();
-
-    b.iter(|| {
-        let n = column.num_vals();
+    group.register("intfastfield_jumpy_stride5_u128", |inp: &Inputs| {
+        let n = inp.column_random.num_vals();
         let mut a = 0u128;
         for i in (0..n / 5).map(|val| val * 5) {
-            a += column.get_val(i);
+            a += inp.column_random.get_val(i);
         }
-        a
+        black_box(a);
     });
+
+    group.run();
 }

columnar/benches/bench_values_u64.rs

@@ -1,13 +1,10 @@
-#![feature(test)]
-extern crate test;
-
 use std::ops::RangeInclusive;
 use std::sync::Arc;
 
+use binggan::{InputGroup, black_box};
 use rand::prelude::*;
-use tantivy_columnar::column_values::{serialize_and_load_u64_based_column_values, CodecType};
+use tantivy_columnar::column_values::{CodecType, serialize_and_load_u64_based_column_values};
 use tantivy_columnar::*;
-use test::Bencher;
 
 // Warning: this generates the same permutation at each call
 fn generate_permutation() -> Vec<u64> {
@@ -27,37 +24,11 @@ pub fn serialize_and_load(column: &[u64], codec_type: CodecType) -> Arc<dyn Colu
     serialize_and_load_u64_based_column_values(&column, &[codec_type])
 }
 
-#[bench]
-fn bench_intfastfield_jumpy_veclookup(b: &mut Bencher) {
-    let permutation = generate_permutation();
-    let n = permutation.len();
-    b.iter(|| {
-        let mut a = 0u64;
-        for _ in 0..n {
-            a = permutation[a as usize];
-        }
-        a
-    });
-}
-
-#[bench]
-fn bench_intfastfield_jumpy_fflookup_bitpacked(b: &mut Bencher) {
-    let permutation = generate_permutation();
-    let n = permutation.len();
-    let column: Arc<dyn ColumnValues<u64>> = serialize_and_load(&permutation, CodecType::Bitpacked);
-    b.iter(|| {
-        let mut a = 0u64;
-        for _ in 0..n {
-            a = column.get_val(a as u32);
-        }
-        a
-    });
-}
-
 const FIFTY_PERCENT_RANGE: RangeInclusive<u64> = 1..=50;
 const SINGLE_ITEM: u64 = 90;
 const SINGLE_ITEM_RANGE: RangeInclusive<u64> = 90..=90;
 const ONE_PERCENT_ITEM_RANGE: RangeInclusive<u64> = 49..=49;
+
 fn get_data_50percent_item() -> Vec<u128> {
     let mut rng = StdRng::from_seed([1u8; 32]);
 
@@ -69,135 +40,122 @@ fn get_data_50percent_item() -> Vec<u128> {
     data.push(SINGLE_ITEM);
 
     data.shuffle(&mut rng);
-    let data = data.iter().map(|el| *el as u128).collect::<Vec<_>>();
-    data
+    data.iter().map(|el| *el as u128).collect::<Vec<_>>()
 }
 
-// U64 RANGE START
-#[bench]
-fn bench_intfastfield_getrange_u64_50percent_hit(b: &mut Bencher) {
-    let data = get_data_50percent_item();
-    let data = data.iter().map(|el| *el as u64).collect::<Vec<_>>();
-    let column: Arc<dyn ColumnValues<u64>> = serialize_and_load(&data, CodecType::Bitpacked);
-    b.iter(|| {
-        let mut positions = Vec::new();
-        column.get_row_ids_for_value_range(
-            FIFTY_PERCENT_RANGE,
-            0..data.len() as u32,
-            &mut positions,
-        );
-        positions
-    });
-}
+type VecCol = (Vec<u64>, Arc<dyn ColumnValues<u64>>);
 
-#[bench]
-fn bench_intfastfield_getrange_u64_1percent_hit(b: &mut Bencher) {
-    let data = get_data_50percent_item();
-    let data = data.iter().map(|el| *el as u64).collect::<Vec<_>>();
-    let column: Arc<dyn ColumnValues<u64>> = serialize_and_load(&data, CodecType::Bitpacked);
-
-    b.iter(|| {
-        let mut positions = Vec::new();
-        column.get_row_ids_for_value_range(
-            ONE_PERCENT_ITEM_RANGE,
-            0..data.len() as u32,
-            &mut positions,
-        );
-        positions
-    });
-}
-
-#[bench]
-fn bench_intfastfield_getrange_u64_single_hit(b: &mut Bencher) {
-    let data = get_data_50percent_item();
-    let data = data.iter().map(|el| *el as u64).collect::<Vec<_>>();
-    let column: Arc<dyn ColumnValues<u64>> = serialize_and_load(&data, CodecType::Bitpacked);
-
-    b.iter(|| {
-        let mut positions = Vec::new();
-        column.get_row_ids_for_value_range(SINGLE_ITEM_RANGE, 0..data.len() as u32, &mut positions);
-        positions
-    });
-}
-
-#[bench]
-fn bench_intfastfield_getrange_u64_hit_all(b: &mut Bencher) {
-    let data = get_data_50percent_item();
-    let data = data.iter().map(|el| *el as u64).collect::<Vec<_>>();
-    let column: Arc<dyn ColumnValues<u64>> = serialize_and_load(&data, CodecType::Bitpacked);
-
-    b.iter(|| {
-        let mut positions = Vec::new();
-        column.get_row_ids_for_value_range(0..=u64::MAX, 0..data.len() as u32, &mut positions);
-        positions
-    });
-}
-// U64 RANGE END
-
-#[bench]
-fn bench_intfastfield_stride7_vec(b: &mut Bencher) {
+fn bench_access() {
     let permutation = generate_permutation();
-    let n = permutation.len();
-    b.iter(|| {
+    let column_perm: Arc<dyn ColumnValues<u64>> =
+        serialize_and_load(&permutation, CodecType::Bitpacked);
+
+    let permutation_gcd = generate_permutation_gcd();
+    let column_perm_gcd: Arc<dyn ColumnValues<u64>> =
+        serialize_and_load(&permutation_gcd, CodecType::Bitpacked);
+
+    let mut group: InputGroup<VecCol> = InputGroup::new_with_inputs(vec![
+        (
+            "access".to_string(),
+            (permutation.clone(), column_perm.clone()),
+        ),
+        (
+            "access_gcd".to_string(),
+            (permutation_gcd.clone(), column_perm_gcd.clone()),
+        ),
+    ]);
+
+    group.register("stride7_vec", |inp: &VecCol| {
+        let n = inp.0.len();
         let mut a = 0u64;
         for i in (0..n / 7).map(|val| val * 7) {
-            a += permutation[i as usize];
+            a += inp.0[i];
         }
-        a
+        black_box(a);
     });
-}
 
-#[bench]
-fn bench_intfastfield_stride7_fflookup(b: &mut Bencher) {
-    let permutation = generate_permutation();
-    let n = permutation.len();
-    let column: Arc<dyn ColumnValues<u64>> = serialize_and_load(&permutation, CodecType::Bitpacked);
-    b.iter(|| {
-        let mut a = 0;
+    group.register("fullscan_vec", |inp: &VecCol| {
+        let mut a = 0u64;
+        for i in 0..inp.0.len() {
+            a += inp.0[i];
+        }
+        black_box(a);
+    });
+
+    group.register("stride7_column_values", |inp: &VecCol| {
+        let n = inp.1.num_vals() as usize;
+        let mut a = 0u64;
         for i in (0..n / 7).map(|val| val * 7) {
-            a += column.get_val(i as u32);
+            a += inp.1.get_val(i as u32);
         }
-        a
+        black_box(a);
     });
-}
 
-#[bench]
-fn bench_intfastfield_scan_all_fflookup(b: &mut Bencher) {
-    let permutation = generate_permutation();
-    let n = permutation.len();
-    let column: Arc<dyn ColumnValues<u64>> = serialize_and_load(&permutation, CodecType::Bitpacked);
-    let column_ref = column.as_ref();
-    b.iter(|| {
-        let mut a = 0u64;
-        for i in 0u32..n as u32 {
-            a += column_ref.get_val(i);
-        }
-        a
-    });
-}
-
-#[bench]
-fn bench_intfastfield_scan_all_fflookup_gcd(b: &mut Bencher) {
-    let permutation = generate_permutation_gcd();
-    let n = permutation.len();
-    let column: Arc<dyn ColumnValues<u64>> = serialize_and_load(&permutation, CodecType::Bitpacked);
-    b.iter(|| {
+    group.register("fullscan_column_values", |inp: &VecCol| {
         let mut a = 0u64;
+        let n = inp.1.num_vals() as usize;
         for i in 0..n {
-            a += column.get_val(i as u32);
+            a += inp.1.get_val(i as u32);
         }
-        a
+        black_box(a);
     });
+
+    group.run();
 }
 
-#[bench]
-fn bench_intfastfield_scan_all_vec(b: &mut Bencher) {
-    let permutation = generate_permutation();
-    b.iter(|| {
-        let mut a = 0u64;
-        for i in 0..permutation.len() {
-            a += permutation[i as usize] as u64;
-        }
-        a
-    });
+fn bench_range() {
+    let data_50 = get_data_50percent_item();
+    let data_u64 = data_50.iter().map(|el| *el as u64).collect::<Vec<_>>();
+    let column_data: Arc<dyn ColumnValues<u64>> =
+        serialize_and_load(&data_u64, CodecType::Bitpacked);
+
+    let mut group: InputGroup<Arc<dyn ColumnValues<u64>>> =
+        InputGroup::new_with_inputs(vec![("dist_50pct_item".to_string(), column_data.clone())]);
+
+    group.register(
+        "fastfield_getrange_u64_50percent_hit",
+        |col: &Arc<dyn ColumnValues<u64>>| {
+            let mut positions = Vec::new();
+            col.get_row_ids_for_value_range(FIFTY_PERCENT_RANGE, 0..col.num_vals(), &mut positions);
+            black_box(positions.len());
+        },
+    );
+
+    group.register(
+        "fastfield_getrange_u64_1percent_hit",
+        |col: &Arc<dyn ColumnValues<u64>>| {
+            let mut positions = Vec::new();
+            col.get_row_ids_for_value_range(
+                ONE_PERCENT_ITEM_RANGE,
+                0..col.num_vals(),
+                &mut positions,
+            );
+            black_box(positions.len());
+        },
+    );
+
+    group.register(
+        "fastfield_getrange_u64_single_hit",
+        |col: &Arc<dyn ColumnValues<u64>>| {
+            let mut positions = Vec::new();
+            col.get_row_ids_for_value_range(SINGLE_ITEM_RANGE, 0..col.num_vals(), &mut positions);
+            black_box(positions.len());
+        },
+    );
+
+    group.register(
+        "fastfield_getrange_u64_hit_all",
+        |col: &Arc<dyn ColumnValues<u64>>| {
+            let mut positions = Vec::new();
+            col.get_row_ids_for_value_range(0..=u64::MAX, 0..col.num_vals(), &mut positions);
+            black_box(positions.len());
+        },
+    );
+
+    group.run();
+}
+
+fn main() {
+    bench_access();
+    bench_range();
 }

columnar/src/block_accessor.rs

@@ -66,7 +66,7 @@ impl<T: PartialOrd + Copy + std::fmt::Debug + Send + Sync + 'static + Default>
         &'a self,
         docs: &'a [u32],
         accessor: &Column<T>,
-    ) -> impl Iterator<Item = (DocId, T)> + 'a {
+    ) -> impl Iterator<Item = (DocId, T)> + 'a + use<'a, T> {
         if accessor.index.get_cardinality().is_full() {
             docs.iter().cloned().zip(self.val_cache.iter().cloned())
         } else {

columnar/src/column/dictionary_encoded.rs

@@ -4,8 +4,8 @@ use std::{fmt, io};
 
 use sstable::{Dictionary, VoidSSTable};
 
-use crate::column::Column;
 use crate::RowId;
+use crate::column::Column;
 
 /// Dictionary encoded column.
 ///

columnar/src/column/mod.rs

@@ -9,13 +9,14 @@ use std::sync::Arc;
 use common::BinarySerializable;
 pub use dictionary_encoded::{BytesColumn, StrColumn};
 pub use serialize::{
-    open_column_bytes, open_column_str, open_column_u128, open_column_u128_as_compact_u64,
-    open_column_u64, serialize_column_mappable_to_u128, serialize_column_mappable_to_u64,
+    open_column_bytes, open_column_str, open_column_u64, open_column_u128,
+    open_column_u128_as_compact_u64, serialize_column_mappable_to_u64,
+    serialize_column_mappable_to_u128,
 };
 
 use crate::column_index::{ColumnIndex, Set};
 use crate::column_values::monotonic_mapping::StrictlyMonotonicMappingToInternal;
-use crate::column_values::{monotonic_map_column, ColumnValues};
+use crate::column_values::{ColumnValues, monotonic_map_column};
 use crate::{Cardinality, DocId, EmptyColumnValues, MonotonicallyMappableToU64, RowId};
 
 #[derive(Clone)]
@@ -113,7 +114,7 @@ impl<T: PartialOrd + Copy + Debug + Send + Sync + 'static> Column<T> {
         }
     }
 
-    /// Translates a block of docis to row_ids.
+    /// Translates a block of docids to row_ids.
     ///
     /// returns the row_ids and the matching docids on the same index
     /// e.g.

columnar/src/column/serialize.rs

@@ -6,10 +6,10 @@ use common::OwnedBytes;
 use sstable::Dictionary;
 
 use crate::column::{BytesColumn, Column};
-use crate::column_index::{serialize_column_index, SerializableColumnIndex};
+use crate::column_index::{SerializableColumnIndex, serialize_column_index};
 use crate::column_values::{
+    CodecType, MonotonicallyMappableToU64, MonotonicallyMappableToU128,
     load_u64_based_column_values, serialize_column_values_u128, serialize_u64_based_column_values,
-    CodecType, MonotonicallyMappableToU128, MonotonicallyMappableToU64,
 };
 use crate::iterable::Iterable;
 use crate::{StrColumn, Version};

columnar/src/column_index/merge/mod.rs

@@ -99,9 +99,9 @@ mod tests {
 
     use crate::column_index::merge::detect_cardinality;
     use crate::column_index::multivalued_index::{
-        open_multivalued_index, serialize_multivalued_index, MultiValueIndex,
+        MultiValueIndex, open_multivalued_index, serialize_multivalued_index,
     };
-    use crate::column_index::{merge_column_index, OptionalIndex, SerializableColumnIndex};
+    use crate::column_index::{OptionalIndex, SerializableColumnIndex, merge_column_index};
     use crate::{
         Cardinality, ColumnIndex, MergeRowOrder, RowAddr, RowId, ShuffleMergeOrder, StackMergeOrder,
     };

columnar/src/column_index/merge/shuffled.rs

@@ -137,8 +137,8 @@ impl Iterable<u32> for ShuffledMultivaluedIndex<'_> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::column_index::OptionalIndex;
     use crate::RowAddr;
+    use crate::column_index::OptionalIndex;
 
     #[test]
     fn test_integrate_num_vals_empty() {

columnar/src/column_index/merge/stacked.rs

@@ -1,8 +1,8 @@
 use std::ops::Range;
 
+use crate::column_index::SerializableColumnIndex;
 use crate::column_index::multivalued_index::{MultiValueIndex, SerializableMultivalueIndex};
 use crate::column_index::serialize::SerializableOptionalIndex;
-use crate::column_index::SerializableColumnIndex;
 use crate::iterable::Iterable;
 use crate::{Cardinality, ColumnIndex, RowId, StackMergeOrder};
 

columnar/src/column_index/mod.rs

@@ -14,7 +14,7 @@ pub use merge::merge_column_index;
 pub(crate) use multivalued_index::SerializableMultivalueIndex;
 pub use optional_index::{OptionalIndex, Set};
 pub use serialize::{
-    open_column_index, serialize_column_index, SerializableColumnIndex, SerializableOptionalIndex,
+    SerializableColumnIndex, SerializableOptionalIndex, open_column_index, serialize_column_index,
 };
 
 use crate::column_index::multivalued_index::MultiValueIndex;

columnar/src/column_index/multivalued_index.rs

@@ -8,7 +8,7 @@ use common::{CountingWriter, OwnedBytes};
 use super::optional_index::{open_optional_index, serialize_optional_index};
 use super::{OptionalIndex, SerializableOptionalIndex, Set};
 use crate::column_values::{
-    load_u64_based_column_values, serialize_u64_based_column_values, CodecType, ColumnValues,
+    CodecType, ColumnValues, load_u64_based_column_values, serialize_u64_based_column_values,
 };
 use crate::iterable::Iterable;
 use crate::{DocId, RowId, Version};

columnar/src/column_index/optional_index/mod.rs

@@ -7,7 +7,7 @@ mod set_block;
 use common::{BinarySerializable, OwnedBytes, VInt};
 pub use set::{SelectCursor, Set, SetCodec};
 use set_block::{
-    DenseBlock, DenseBlockCodec, SparseBlock, SparseBlockCodec, DENSE_BLOCK_NUM_BYTES,
+    DENSE_BLOCK_NUM_BYTES, DenseBlock, DenseBlockCodec, SparseBlock, SparseBlockCodec,
 };
 
 use crate::iterable::Iterable;
@@ -259,11 +259,13 @@ impl Set<RowId> for OptionalIndex {
 
 impl OptionalIndex {
     pub fn for_test(num_rows: RowId, row_ids: &[RowId]) -> OptionalIndex {
-        assert!(row_ids
-            .last()
-            .copied()
-            .map(|last_row_id| last_row_id < num_rows)
-            .unwrap_or(true));
+        assert!(
+            row_ids
+                .last()
+                .copied()
+                .map(|last_row_id| last_row_id < num_rows)
+                .unwrap_or(true)
+        );
         let mut buffer = Vec::new();
         serialize_optional_index(&row_ids, num_rows, &mut buffer).unwrap();
         let bytes = OwnedBytes::new(buffer);

columnar/src/column_index/optional_index/set_block/dense.rs

@@ -2,7 +2,7 @@ use std::io::{self, Write};
 
 use common::BinarySerializable;
 
-use crate::column_index::optional_index::{SelectCursor, Set, SetCodec, ELEMENTS_PER_BLOCK};
+use crate::column_index::optional_index::{ELEMENTS_PER_BLOCK, SelectCursor, Set, SetCodec};
 
 #[inline(always)]
 fn get_bit_at(input: u64, n: u16) -> bool {

columnar/src/column_index/optional_index/set_block/mod.rs

@@ -1,7 +1,7 @@
 mod dense;
 mod sparse;
 
-pub use dense::{DenseBlock, DenseBlockCodec, DENSE_BLOCK_NUM_BYTES};
+pub use dense::{DENSE_BLOCK_NUM_BYTES, DenseBlock, DenseBlockCodec};
 pub use sparse::{SparseBlock, SparseBlockCodec};
 
 #[cfg(test)]

columnar/src/column_index/optional_index/tests.rs

@@ -219,174 +219,3 @@ fn test_optional_index_for_tests() {
     assert!(!optional_index.contains(3));
     assert_eq!(optional_index.num_docs(), 4);
 }
-
-#[cfg(all(test, feature = "unstable"))]
-mod bench {
-
-    use rand::rngs::StdRng;
-    use rand::{Rng, SeedableRng};
-    use test::Bencher;
-
-    use super::*;
-
-    const TOTAL_NUM_VALUES: u32 = 1_000_000;
-    fn gen_bools(fill_ratio: f64) -> OptionalIndex {
-        let mut out = Vec::new();
-        let mut rng: StdRng = StdRng::from_seed([1u8; 32]);
-        let vals: Vec<RowId> = (0..TOTAL_NUM_VALUES)
-            .map(|_| rng.gen_bool(fill_ratio))
-            .enumerate()
-            .filter(|(_pos, val)| *val)
-            .map(|(pos, _)| pos as RowId)
-            .collect();
-        serialize_optional_index(&&vals[..], TOTAL_NUM_VALUES, &mut out).unwrap();
-
-        open_optional_index(OwnedBytes::new(out)).unwrap()
-    }
-
-    fn random_range_iterator(
-        start: u32,
-        end: u32,
-        avg_step_size: u32,
-        avg_deviation: u32,
-    ) -> impl Iterator<Item = u32> {
-        let mut rng: StdRng = StdRng::from_seed([1u8; 32]);
-        let mut current = start;
-        std::iter::from_fn(move || {
-            current += rng.gen_range(avg_step_size - avg_deviation..=avg_step_size + avg_deviation);
-            if current >= end {
-                None
-            } else {
-                Some(current)
-            }
-        })
-    }
-
-    fn n_percent_step_iterator(percent: f32, num_values: u32) -> impl Iterator<Item = u32> {
-        let ratio = percent / 100.0;
-        let step_size = (1f32 / ratio) as u32;
-        let deviation = step_size - 1;
-        random_range_iterator(0, num_values, step_size, deviation)
-    }
-
-    fn walk_over_data(codec: &OptionalIndex, avg_step_size: u32) -> Option<u32> {
-        walk_over_data_from_positions(
-            codec,
-            random_range_iterator(0, TOTAL_NUM_VALUES, avg_step_size, 0),
-        )
-    }
-
-    fn walk_over_data_from_positions(
-        codec: &OptionalIndex,
-        positions: impl Iterator<Item = u32>,
-    ) -> Option<u32> {
-        let mut dense_idx: Option<u32> = None;
-        for idx in positions {
-            dense_idx = dense_idx.or(codec.rank_if_exists(idx));
-        }
-        dense_idx
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_1percent_filled_10percent_hit(bench: &mut Bencher) {
-        let codec = gen_bools(0.01f64);
-        bench.iter(|| walk_over_data(&codec, 100));
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_5percent_filled_10percent_hit(bench: &mut Bencher) {
-        let codec = gen_bools(0.05f64);
-        bench.iter(|| walk_over_data(&codec, 100));
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_5percent_filled_1percent_hit(bench: &mut Bencher) {
-        let codec = gen_bools(0.05f64);
-        bench.iter(|| walk_over_data(&codec, 1000));
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_full_scan_1percent_filled(bench: &mut Bencher) {
-        let codec = gen_bools(0.01f64);
-        bench.iter(|| walk_over_data_from_positions(&codec, 0..TOTAL_NUM_VALUES));
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_full_scan_10percent_filled(bench: &mut Bencher) {
-        let codec = gen_bools(0.1f64);
-        bench.iter(|| walk_over_data_from_positions(&codec, 0..TOTAL_NUM_VALUES));
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_full_scan_90percent_filled(bench: &mut Bencher) {
-        let codec = gen_bools(0.9f64);
-        bench.iter(|| walk_over_data_from_positions(&codec, 0..TOTAL_NUM_VALUES));
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_10percent_filled_1percent_hit(bench: &mut Bencher) {
-        let codec = gen_bools(0.1f64);
-        bench.iter(|| walk_over_data(&codec, 100));
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_50percent_filled_1percent_hit(bench: &mut Bencher) {
-        let codec = gen_bools(0.5f64);
-        bench.iter(|| walk_over_data(&codec, 100));
-    }
-
-    #[bench]
-    fn bench_translate_orig_to_codec_90percent_filled_1percent_hit(bench: &mut Bencher) {
-        let codec = gen_bools(0.9f64);
-        bench.iter(|| walk_over_data(&codec, 100));
-    }
-
-    #[bench]
-    fn bench_translate_codec_to_orig_1percent_filled_0comma005percent_hit(bench: &mut Bencher) {
-        bench_translate_codec_to_orig_util(0.01f64, 0.005f32, bench);
-    }
-
-    #[bench]
-    fn bench_translate_codec_to_orig_10percent_filled_0comma005percent_hit(bench: &mut Bencher) {
-        bench_translate_codec_to_orig_util(0.1f64, 0.005f32, bench);
-    }
-
-    #[bench]
-    fn bench_translate_codec_to_orig_1percent_filled_10percent_hit(bench: &mut Bencher) {
-        bench_translate_codec_to_orig_util(0.01f64, 10f32, bench);
-    }
-
-    #[bench]
-    fn bench_translate_codec_to_orig_1percent_filled_full_scan(bench: &mut Bencher) {
-        bench_translate_codec_to_orig_util(0.01f64, 100f32, bench);
-    }
-
-    fn bench_translate_codec_to_orig_util(
-        percent_filled: f64,
-        percent_hit: f32,
-        bench: &mut Bencher,
-    ) {
-        let codec = gen_bools(percent_filled);
-        let num_non_nulls = codec.num_non_nulls();
-        let idxs: Vec<u32> = if percent_hit == 100.0f32 {
-            (0..num_non_nulls).collect()
-        } else {
-            n_percent_step_iterator(percent_hit, num_non_nulls).collect()
-        };
-        let mut output = vec![0u32; idxs.len()];
-        bench.iter(|| {
-            output.copy_from_slice(&idxs[..]);
-            codec.select_batch(&mut output);
-        });
-    }
-
-    #[bench]
-    fn bench_translate_codec_to_orig_90percent_filled_0comma005percent_hit(bench: &mut Bencher) {
-        bench_translate_codec_to_orig_util(0.9f64, 0.005, bench);
-    }
-
-    #[bench]
-    fn bench_translate_codec_to_orig_90percent_filled_full_scan(bench: &mut Bencher) {
-        bench_translate_codec_to_orig_util(0.9f64, 100.0f32, bench);
-    }
-}

columnar/src/column_index/serialize.rs

@@ -3,11 +3,11 @@ use std::io::Write;
 
 use common::{CountingWriter, OwnedBytes};
 
-use super::multivalued_index::SerializableMultivalueIndex;
 use super::OptionalIndex;
+use super::multivalued_index::SerializableMultivalueIndex;
+use crate::column_index::ColumnIndex;
 use crate::column_index::multivalued_index::serialize_multivalued_index;
 use crate::column_index::optional_index::serialize_optional_index;
-use crate::column_index::ColumnIndex;
 use crate::iterable::Iterable;
 use crate::{Cardinality, RowId, Version};
 

columnar/src/column_values/bench.rs

@@ -1,139 +0,0 @@
-use std::sync::Arc;
-
-use common::OwnedBytes;
-use rand::rngs::StdRng;
-use rand::{Rng, SeedableRng};
-use test::{self, Bencher};
-
-use super::*;
-use crate::column_values::u64_based::*;
-
-fn get_data() -> Vec<u64> {
-    let mut rng = StdRng::seed_from_u64(2u64);
-    let mut data: Vec<_> = (100..55000_u64)
-        .map(|num| num + rng.gen::<u8>() as u64)
-        .collect();
-    data.push(99_000);
-    data.insert(1000, 2000);
-    data.insert(2000, 100);
-    data.insert(3000, 4100);
-    data.insert(4000, 100);
-    data.insert(5000, 800);
-    data
-}
-
-fn compute_stats(vals: impl Iterator<Item = u64>) -> ColumnStats {
-    let mut stats_collector = StatsCollector::default();
-    for val in vals {
-        stats_collector.collect(val);
-    }
-    stats_collector.stats()
-}
-
-#[inline(never)]
-fn value_iter() -> impl Iterator<Item = u64> {
-    0..20_000
-}
-
-fn get_reader_for_bench<Codec: ColumnCodec>(data: &[u64]) -> Codec::ColumnValues {
-    let mut bytes = Vec::new();
-    let stats = compute_stats(data.iter().cloned());
-    let mut codec_serializer = Codec::estimator();
-    for val in data {
-        codec_serializer.collect(*val);
-    }
-    codec_serializer
-        .serialize(&stats, Box::new(data.iter().copied()).as_mut(), &mut bytes)
-        .unwrap();
-
-    Codec::load(OwnedBytes::new(bytes)).unwrap()
-}
-
-fn bench_get<Codec: ColumnCodec>(b: &mut Bencher, data: &[u64]) {
-    let col = get_reader_for_bench::<Codec>(data);
-    b.iter(|| {
-        let mut sum = 0u64;
-        for pos in value_iter() {
-            let val = col.get_val(pos as u32);
-            sum = sum.wrapping_add(val);
-        }
-        sum
-    });
-}
-
-#[inline(never)]
-fn bench_get_dynamic_helper(b: &mut Bencher, col: Arc<dyn ColumnValues>) {
-    b.iter(|| {
-        let mut sum = 0u64;
-        for pos in value_iter() {
-            let val = col.get_val(pos as u32);
-            sum = sum.wrapping_add(val);
-        }
-        sum
-    });
-}
-
-fn bench_get_dynamic<Codec: ColumnCodec>(b: &mut Bencher, data: &[u64]) {
-    let col = Arc::new(get_reader_for_bench::<Codec>(data));
-    bench_get_dynamic_helper(b, col);
-}
-fn bench_create<Codec: ColumnCodec>(b: &mut Bencher, data: &[u64]) {
-    let stats = compute_stats(data.iter().cloned());
-
-    let mut bytes = Vec::new();
-    b.iter(|| {
-        bytes.clear();
-        let mut codec_serializer = Codec::estimator();
-        for val in data.iter().take(1024) {
-            codec_serializer.collect(*val);
-        }
-
-        codec_serializer.serialize(&stats, Box::new(data.iter().copied()).as_mut(), &mut bytes)
-    });
-}
-
-#[bench]
-fn bench_fastfield_bitpack_create(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_create::<BitpackedCodec>(b, &data);
-}
-#[bench]
-fn bench_fastfield_linearinterpol_create(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_create::<LinearCodec>(b, &data);
-}
-#[bench]
-fn bench_fastfield_multilinearinterpol_create(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_create::<BlockwiseLinearCodec>(b, &data);
-}
-#[bench]
-fn bench_fastfield_bitpack_get(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_get::<BitpackedCodec>(b, &data);
-}
-#[bench]
-fn bench_fastfield_bitpack_get_dynamic(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_get_dynamic::<BitpackedCodec>(b, &data);
-}
-#[bench]
-fn bench_fastfield_linearinterpol_get(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_get::<LinearCodec>(b, &data);
-}
-#[bench]
-fn bench_fastfield_linearinterpol_get_dynamic(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_get_dynamic::<LinearCodec>(b, &data);
-}
-#[bench]
-fn bench_fastfield_multilinearinterpol_get(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_get::<BlockwiseLinearCodec>(b, &data);
-}
-#[bench]
-fn bench_fastfield_multilinearinterpol_get_dynamic(b: &mut Bencher) {
-    let data: Vec<_> = get_data();
-    bench_get_dynamic::<BlockwiseLinearCodec>(b, &data);
-}

columnar/src/column_values/mod.rs

@@ -26,13 +26,13 @@ mod monotonic_column;
 
 pub(crate) use merge::MergedColumnValues;
 pub use stats::ColumnStats;
-pub use u128_based::{
-    open_u128_as_compact_u64, open_u128_mapped, serialize_column_values_u128,
-    CompactSpaceU64Accessor,
-};
 pub use u64_based::{
-    load_u64_based_column_values, serialize_and_load_u64_based_column_values,
-    serialize_u64_based_column_values, CodecType, ALL_U64_CODEC_TYPES,
+    ALL_U64_CODEC_TYPES, CodecType, load_u64_based_column_values,
+    serialize_and_load_u64_based_column_values, serialize_u64_based_column_values,
+};
+pub use u128_based::{
+    CompactSpaceU64Accessor, open_u128_as_compact_u64, open_u128_mapped,
+    serialize_column_values_u128,
 };
 pub use vec_column::VecColumn;
 
@@ -242,6 +242,3 @@ impl<T: Copy + PartialOrd + Debug + 'static> ColumnValues<T> for Arc<dyn ColumnV
             .get_row_ids_for_value_range(range, doc_id_range, positions)
     }
 }
-
-#[cfg(all(test, feature = "unstable"))]
-mod bench;

columnar/src/column_values/monotonic_column.rs

@@ -2,8 +2,8 @@ use std::fmt::Debug;
 use std::marker::PhantomData;
 use std::ops::{Range, RangeInclusive};
 
-use crate::column_values::monotonic_mapping::StrictlyMonotonicFn;
 use crate::ColumnValues;
+use crate::column_values::monotonic_mapping::StrictlyMonotonicFn;
 
 struct MonotonicMappingColumn<C, T, Input> {
     from_column: C,
@@ -99,10 +99,10 @@ where
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::column_values::VecColumn;
     use crate::column_values::monotonic_mapping::{
         StrictlyMonotonicMappingInverter, StrictlyMonotonicMappingToInternal,
     };
-    use crate::column_values::VecColumn;
 
     #[test]
     fn test_monotonic_mapping_iter() {

columnar/src/column_values/u128_based/compact_space/mod.rs

@@ -24,8 +24,8 @@ use build_compact_space::get_compact_space;
 use common::{BinarySerializable, CountingWriter, OwnedBytes, VInt, VIntU128};
 use tantivy_bitpacker::{BitPacker, BitUnpacker};
 
-use crate::column_values::ColumnValues;
 use crate::RowId;
+use crate::column_values::ColumnValues;
 
 /// The cost per blank is quite hard actually, since blanks are delta encoded, the actual cost of
 /// blanks depends on the number of blanks.
@@ -653,12 +653,14 @@ mod tests {
             ),
             &[3]
         );
-        assert!(get_positions_for_value_range_helper(
-            &decomp,
-            99998u128..=99998u128,
-            complete_range.clone()
-        )
-        .is_empty());
+        assert!(
+            get_positions_for_value_range_helper(
+                &decomp,
+                99998u128..=99998u128,
+                complete_range.clone()
+            )
+            .is_empty()
+        );
         assert_eq!(
             &get_positions_for_value_range_helper(
                 &decomp,

columnar/src/column_values/u128_based/mod.rs

@@ -130,11 +130,11 @@ pub fn open_u128_as_compact_u64(mut bytes: OwnedBytes) -> io::Result<Arc<dyn Col
 #[cfg(test)]
 pub(crate) mod tests {
     use super::*;
-    use crate::column_values::u64_based::{
-        serialize_and_load_u64_based_column_values, serialize_u64_based_column_values,
-        ALL_U64_CODEC_TYPES,
-    };
     use crate::column_values::CodecType;
+    use crate::column_values::u64_based::{
+        ALL_U64_CODEC_TYPES, serialize_and_load_u64_based_column_values,
+        serialize_u64_based_column_values,
+    };
 
     #[test]
     fn test_serialize_deserialize_u128_header() {

columnar/src/column_values/u64_based/bitpacked.rs

@@ -4,7 +4,7 @@ use std::ops::{Range, RangeInclusive};
 
 use common::{BinarySerializable, OwnedBytes};
 use fastdivide::DividerU64;
-use tantivy_bitpacker::{compute_num_bits, BitPacker, BitUnpacker};
+use tantivy_bitpacker::{BitPacker, BitUnpacker, compute_num_bits};
 
 use crate::column_values::u64_based::{ColumnCodec, ColumnCodecEstimator, ColumnStats};
 use crate::{ColumnValues, RowId};
@@ -23,11 +23,7 @@ const fn div_ceil(n: u64, q: NonZeroU64) -> u64 {
     // copied from unstable rust standard library.
     let d = n / q.get();
     let r = n % q.get();
-    if r > 0 {
-        d + 1
-    } else {
-        d
-    }
+    if r > 0 { d + 1 } else { d }
 }
 
 // The bitpacked codec applies a linear transformation `f` over data that are bitpacked.

columnar/src/column_values/u64_based/blockwise_linear.rs

@@ -4,12 +4,12 @@ use std::{io, iter};
 
 use common::{BinarySerializable, CountingWriter, DeserializeFrom, OwnedBytes};
 use fastdivide::DividerU64;
-use tantivy_bitpacker::{compute_num_bits, BitPacker, BitUnpacker};
+use tantivy_bitpacker::{BitPacker, BitUnpacker, compute_num_bits};
 
+use crate::MonotonicallyMappableToU64;
 use crate::column_values::u64_based::line::Line;
 use crate::column_values::u64_based::{ColumnCodec, ColumnCodecEstimator, ColumnStats};
 use crate::column_values::{ColumnValues, VecColumn};
-use crate::MonotonicallyMappableToU64;
 
 const BLOCK_SIZE: u32 = 512u32;
 

columnar/src/column_values/u64_based/linear.rs

@@ -1,13 +1,13 @@
 use std::io;
 
 use common::{BinarySerializable, OwnedBytes};
-use tantivy_bitpacker::{compute_num_bits, BitPacker, BitUnpacker};
+use tantivy_bitpacker::{BitPacker, BitUnpacker, compute_num_bits};
 
-use super::line::Line;
 use super::ColumnValues;
-use crate::column_values::u64_based::{ColumnCodec, ColumnCodecEstimator, ColumnStats};
-use crate::column_values::VecColumn;
+use super::line::Line;
 use crate::RowId;
+use crate::column_values::VecColumn;
+use crate::column_values::u64_based::{ColumnCodec, ColumnCodecEstimator, ColumnStats};
 
 const HALF_SPACE: u64 = u64::MAX / 2;
 const LINE_ESTIMATION_BLOCK_LEN: usize = 512;

columnar/src/column_values/u64_based/mod.rs

@@ -17,7 +17,7 @@ pub use crate::column_values::u64_based::bitpacked::BitpackedCodec;
 pub use crate::column_values::u64_based::blockwise_linear::BlockwiseLinearCodec;
 pub use crate::column_values::u64_based::linear::LinearCodec;
 pub use crate::column_values::u64_based::stats_collector::StatsCollector;
-use crate::column_values::{monotonic_map_column, ColumnStats};
+use crate::column_values::{ColumnStats, monotonic_map_column};
 use crate::iterable::Iterable;
 use crate::{ColumnValues, MonotonicallyMappableToU64};
 

columnar/src/column_values/u64_based/stats_collector.rs

@@ -2,8 +2,8 @@ use std::num::NonZeroU64;
 
 use fastdivide::DividerU64;
 
-use crate::column_values::ColumnStats;
 use crate::RowId;
+use crate::column_values::ColumnStats;
 
 /// Compute the gcd of two non null numbers.
 ///
@@ -96,8 +96,8 @@ impl StatsCollector {
 mod tests {
     use std::num::NonZeroU64;
 
-    use crate::column_values::u64_based::stats_collector::{compute_gcd, StatsCollector};
     use crate::column_values::u64_based::ColumnStats;
+    use crate::column_values::u64_based::stats_collector::{StatsCollector, compute_gcd};
 
     fn compute_stats(vals: impl Iterator<Item = u64>) -> ColumnStats {
         let mut stats_collector = StatsCollector::default();

columnar/src/column_values/u64_based/tests.rs

@@ -1,5 +1,6 @@
 use proptest::prelude::*;
 use proptest::{prop_oneof, proptest};
+use rand::Rng;
 
 #[test]
 fn test_serialize_and_load_simple() {

columnar/src/columnar/column_type.rs

@@ -4,8 +4,8 @@ use std::net::Ipv6Addr;
 
 use serde::{Deserialize, Serialize};
 
-use crate::value::NumericalType;
 use crate::InvalidData;
+use crate::value::NumericalType;
 
 /// The column type represents the column type.
 /// Any changes need to be propagated to `COLUMN_TYPES`.

columnar/src/columnar/merge/mod.rs

@@ -10,11 +10,11 @@ use std::sync::Arc;
 pub use merge_mapping::{MergeRowOrder, ShuffleMergeOrder, StackMergeOrder};
 
 use super::writer::ColumnarSerializer;
-use crate::column::{serialize_column_mappable_to_u128, serialize_column_mappable_to_u64};
+use crate::column::{serialize_column_mappable_to_u64, serialize_column_mappable_to_u128};
 use crate::column_values::MergedColumnValues;
+use crate::columnar::ColumnarReader;
 use crate::columnar::merge::merge_dict_column::merge_bytes_or_str_column;
 use crate::columnar::writer::CompatibleNumericalTypes;
-use crate::columnar::ColumnarReader;
 use crate::dynamic_column::DynamicColumn;
 use crate::{
     BytesColumn, Column, ColumnIndex, ColumnType, ColumnValues, DynamicColumnHandle, NumericalType,
@@ -144,16 +144,17 @@ fn merge_column(
             let mut column_values: Vec<Option<Arc<dyn ColumnValues>>> =
                 Vec::with_capacity(columns_to_merge.len());
             for (i, dynamic_column_opt) in columns_to_merge.into_iter().enumerate() {
-                if let Some(Column { index: idx, values }) =
-                    dynamic_column_opt.and_then(dynamic_column_to_u64_monotonic)
-                {
-                    column_indexes.push(idx);
-                    column_values.push(Some(values));
-                } else {
-                    column_indexes.push(ColumnIndex::Empty {
-                        num_docs: num_docs_per_column[i],
-                    });
-                    column_values.push(None);
+                match dynamic_column_opt.and_then(dynamic_column_to_u64_monotonic) {
+                    Some(Column { index: idx, values }) => {
+                        column_indexes.push(idx);
+                        column_values.push(Some(values));
+                    }
+                    None => {
+                        column_indexes.push(ColumnIndex::Empty {
+                            num_docs: num_docs_per_column[i],
+                        });
+                        column_values.push(None);
+                    }
                 }
             }
             let merged_column_index =
@@ -253,11 +254,13 @@ impl GroupedColumns {
         }
         // At the moment, only the numerical column type category has more than one possible
         // column type.
-        assert!(self
-            .columns
-            .iter()
-            .flatten()
-            .all(|el| ColumnTypeCategory::from(el.column_type()) == ColumnTypeCategory::Numerical));
+        assert!(
+            self.columns
+                .iter()
+                .flatten()
+                .all(|el| ColumnTypeCategory::from(el.column_type())
+                    == ColumnTypeCategory::Numerical)
+        );
         merged_numerical_columns_type(self.columns.iter().flatten()).into()
     }
 }

columnar/src/columnar/merge/term_merger.rs

@@ -74,18 +74,19 @@ impl<'a> TermMerger<'a> {
     /// False if there is none.
     pub fn advance(&mut self) -> bool {
         self.advance_segments();
-        if let Some(head) = self.heap.pop() {
-            self.term_streams_with_segment.push(head);
-            while let Some(next_streamer) = self.heap.peek() {
-                if self.term_streams_with_segment[0].terms.key() != next_streamer.terms.key() {
-                    break;
+        match self.heap.pop() {
+            Some(head) => {
+                self.term_streams_with_segment.push(head);
+                while let Some(next_streamer) = self.heap.peek() {
+                    if self.term_streams_with_segment[0].terms.key() != next_streamer.terms.key() {
+                        break;
+                    }
+                    let next_heap_it = self.heap.pop().unwrap(); // safe : we peeked beforehand
+                    self.term_streams_with_segment.push(next_heap_it);
                 }
-                let next_heap_it = self.heap.pop().unwrap(); // safe : we peeked beforehand
-                self.term_streams_with_segment.push(next_heap_it);
+                true
             }
-            true
-        } else {
-            false
+            _ => false,
         }
     }
 

columnar/src/columnar/merge/tests.rs

@@ -3,7 +3,7 @@ use proptest::collection::vec;
 use proptest::prelude::*;
 
 use super::*;
-use crate::columnar::{merge_columnar, ColumnarReader, MergeRowOrder, StackMergeOrder};
+use crate::columnar::{ColumnarReader, MergeRowOrder, StackMergeOrder, merge_columnar};
 use crate::{Cardinality, ColumnarWriter, DynamicColumn, HasAssociatedColumnType, RowId};
 
 fn make_columnar<T: Into<NumericalValue> + HasAssociatedColumnType + Copy>(

columnar/src/columnar/mod.rs

@@ -5,9 +5,9 @@ mod reader;
 mod writer;
 
 pub use column_type::{ColumnType, HasAssociatedColumnType};
-pub use format_version::{Version, CURRENT_VERSION};
+pub use format_version::{CURRENT_VERSION, Version};
 #[cfg(test)]
 pub(crate) use merge::ColumnTypeCategory;
-pub use merge::{merge_columnar, MergeRowOrder, ShuffleMergeOrder, StackMergeOrder};
+pub use merge::{MergeRowOrder, ShuffleMergeOrder, StackMergeOrder, merge_columnar};
 pub use reader::ColumnarReader;
 pub use writer::ColumnarWriter;

columnar/src/columnar/reader/mod.rs

@@ -1,11 +1,11 @@
 use std::{fmt, io, mem};
 
+use common::BinarySerializable;
 use common::file_slice::FileSlice;
 use common::json_path_writer::JSON_PATH_SEGMENT_SEP;
-use common::BinarySerializable;
 use sstable::{Dictionary, RangeSSTable};
 
-use crate::columnar::{format_version, ColumnType};
+use crate::columnar::{ColumnType, format_version};
 use crate::dynamic_column::DynamicColumnHandle;
 use crate::{RowId, Version};
 

columnar/src/columnar/writer/column_writers.rs

@@ -42,7 +42,7 @@ impl ColumnWriter {
         &self,
         arena: &MemoryArena,
         buffer: &'a mut Vec<u8>,
-    ) -> impl Iterator<Item = ColumnOperation<V>> + 'a {
+    ) -> impl Iterator<Item = ColumnOperation<V>> + 'a + use<'a, V> {
         buffer.clear();
         self.values.read_to_end(arena, buffer);
         let mut cursor: &[u8] = &buffer[..];
@@ -104,9 +104,10 @@ pub(crate) struct NumericalColumnWriter {
 
 impl NumericalColumnWriter {
     pub fn force_numerical_type(&mut self, numerical_type: NumericalType) {
-        assert!(self
-            .compatible_numerical_types
-            .is_type_accepted(numerical_type));
+        assert!(
+            self.compatible_numerical_types
+                .is_type_accepted(numerical_type)
+        );
         self.compatible_numerical_types = CompatibleNumericalTypes::StaticType(numerical_type);
     }
 }
@@ -211,7 +212,7 @@ impl NumericalColumnWriter {
         self,
         arena: &MemoryArena,
         buffer: &'a mut Vec<u8>,
-    ) -> impl Iterator<Item = ColumnOperation<NumericalValue>> + 'a {
+    ) -> impl Iterator<Item = ColumnOperation<NumericalValue>> + 'a + use<'a> {
         self.column_writer.operation_iterator(arena, buffer)
     }
 }
@@ -255,7 +256,7 @@ impl StrOrBytesColumnWriter {
         &self,
         arena: &MemoryArena,
         byte_buffer: &'a mut Vec<u8>,
-    ) -> impl Iterator<Item = ColumnOperation<UnorderedId>> + 'a {
+    ) -> impl Iterator<Item = ColumnOperation<UnorderedId>> + 'a + use<'a> {
         self.column_writer.operation_iterator(arena, byte_buffer)
     }
 }

columnar/src/columnar/writer/mod.rs

@@ -8,13 +8,13 @@ use std::net::Ipv6Addr;
 
 use column_operation::ColumnOperation;
 pub(crate) use column_writers::CompatibleNumericalTypes;
-use common::json_path_writer::JSON_END_OF_PATH;
 use common::CountingWriter;
+use common::json_path_writer::JSON_END_OF_PATH;
 pub(crate) use serializer::ColumnarSerializer;
 use stacker::{Addr, ArenaHashMap, MemoryArena};
 
 use crate::column_index::{SerializableColumnIndex, SerializableOptionalIndex};
-use crate::column_values::{MonotonicallyMappableToU128, MonotonicallyMappableToU64};
+use crate::column_values::{MonotonicallyMappableToU64, MonotonicallyMappableToU128};
 use crate::columnar::column_type::ColumnType;
 use crate::columnar::writer::column_writers::{
     ColumnWriter, NumericalColumnWriter, StrOrBytesColumnWriter,

columnar/src/columnar/writer/serializer.rs

@@ -3,11 +3,11 @@ use std::io::Write;
 
 use common::json_path_writer::JSON_END_OF_PATH;
 use common::{BinarySerializable, CountingWriter};
-use sstable::value::RangeValueWriter;
 use sstable::RangeSSTable;
+use sstable::value::RangeValueWriter;
 
-use crate::columnar::ColumnType;
 use crate::RowId;
+use crate::columnar::ColumnType;
 
 pub struct ColumnarSerializer<W: io::Write> {
     wrt: CountingWriter<W>,

columnar/src/columnar/writer/value_index.rs

@@ -1,6 +1,6 @@
+use crate::RowId;
 use crate::column_index::{SerializableMultivalueIndex, SerializableOptionalIndex};
 use crate::iterable::Iterable;
-use crate::RowId;
 
 /// The `IndexBuilder` interprets a sequence of
 /// calls of the form:
@@ -31,12 +31,13 @@ pub struct OptionalIndexBuilder {
 
 impl OptionalIndexBuilder {
     pub fn finish(&mut self, num_rows: RowId) -> impl Iterable<RowId> + '_ {
-        debug_assert!(self
-            .docs
-            .last()
-            .copied()
-            .map(|last_doc| last_doc < num_rows)
-            .unwrap_or(true));
+        debug_assert!(
+            self.docs
+                .last()
+                .copied()
+                .map(|last_doc| last_doc < num_rows)
+                .unwrap_or(true)
+        );
         &self.docs[..]
     }
 
@@ -48,12 +49,13 @@ impl OptionalIndexBuilder {
 impl IndexBuilder for OptionalIndexBuilder {
     #[inline(always)]
     fn record_row(&mut self, doc: RowId) {
-        debug_assert!(self
-            .docs
-            .last()
-            .copied()
-            .map(|prev_doc| doc > prev_doc)
-            .unwrap_or(true));
+        debug_assert!(
+            self.docs
+                .last()
+                .copied()
+                .map(|prev_doc| doc > prev_doc)
+                .unwrap_or(true)
+        );
         self.docs.push(doc);
     }
 }

columnar/src/compat_tests.rs

@@ -3,8 +3,8 @@ use std::path::PathBuf;
 use itertools::Itertools;
 
 use crate::{
-    merge_columnar, Cardinality, Column, ColumnarReader, DynamicColumn, StackMergeOrder,
-    CURRENT_VERSION,
+    CURRENT_VERSION, Cardinality, Column, ColumnarReader, DynamicColumn, StackMergeOrder,
+    merge_columnar,
 };
 
 const NUM_DOCS: u32 = u16::MAX as u32;

columnar/src/dynamic_column.rs

@@ -6,7 +6,7 @@ use common::file_slice::FileSlice;
 use common::{ByteCount, DateTime, HasLen, OwnedBytes};
 
 use crate::column::{BytesColumn, Column, StrColumn};
-use crate::column_values::{monotonic_map_column, StrictlyMonotonicFn};
+use crate::column_values::{StrictlyMonotonicFn, monotonic_map_column};
 use crate::columnar::ColumnType;
 use crate::{Cardinality, ColumnIndex, ColumnValues, NumericalType, Version};
 

columnar/src/lib.rs

@@ -17,15 +17,10 @@
 //!       column.
 //!     - [column_values]: Stores the values of a column in a dense format.
 
-#![cfg_attr(all(feature = "unstable", test), feature(test))]
-
 #[cfg(test)]
 #[macro_use]
 extern crate more_asserts;
 
-#[cfg(all(test, feature = "unstable"))]
-extern crate test;
-
 use std::fmt::Display;
 use std::io;
 
@@ -44,11 +39,11 @@ pub use block_accessor::ColumnBlockAccessor;
 pub use column::{BytesColumn, Column, StrColumn};
 pub use column_index::ColumnIndex;
 pub use column_values::{
-    ColumnValues, EmptyColumnValues, MonotonicallyMappableToU128, MonotonicallyMappableToU64,
+    ColumnValues, EmptyColumnValues, MonotonicallyMappableToU64, MonotonicallyMappableToU128,
 };
 pub use columnar::{
-    merge_columnar, ColumnType, ColumnarReader, ColumnarWriter, HasAssociatedColumnType,
-    MergeRowOrder, ShuffleMergeOrder, StackMergeOrder, Version, CURRENT_VERSION,
+    CURRENT_VERSION, ColumnType, ColumnarReader, ColumnarWriter, HasAssociatedColumnType,
+    MergeRowOrder, ShuffleMergeOrder, StackMergeOrder, Version, merge_columnar,
 };
 use sstable::VoidSSTable;
 pub use value::{NumericalType, NumericalValue};

columnar/src/tests.rs

@@ -716,8 +716,8 @@ fn test_columnar_merging_number_columns() {
 // TODO document edge case: required_columns incompatible with values.
 
 #[allow(clippy::type_complexity)]
-fn columnar_docs_and_remap(
-) -> impl Strategy<Value = (Vec<Vec<Vec<(&'static str, ColumnValue)>>>, Vec<RowAddr>)> {
+fn columnar_docs_and_remap()
+-> impl Strategy<Value = (Vec<Vec<Vec<(&'static str, ColumnValue)>>>, Vec<RowAddr>)> {
     proptest::collection::vec(columnar_docs_strategy(), 2..=3).prop_flat_map(
         |columnars_docs: Vec<Vec<Vec<(&str, ColumnValue)>>>| {
             let row_addrs: Vec<RowAddr> = columnars_docs

common/Cargo.toml

@@ -1,9 +1,9 @@
 [package]
 name = "tantivy-common"
-version = "0.7.0"
+version = "0.10.0"
 authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
 license = "MIT"
-edition = "2021"
+edition = "2024"
 description = "common traits and utility functions used by multiple tantivy subcrates"
 documentation = "https://docs.rs/tantivy_common/"
 homepage = "https://github.com/quickwit-oss/tantivy"
@@ -13,7 +13,7 @@ repository = "https://github.com/quickwit-oss/tantivy"
 
 [dependencies]
 byteorder = "1.4.3"
-ownedbytes = { version= "0.7", path="../ownedbytes" }
+ownedbytes = { version= "0.9", path="../ownedbytes" }
 async-trait = "0.1"
 time = { version = "0.3.10", features = ["serde-well-known"] }
 serde = { version = "1.0.136", features = ["derive"] }

common/benches/bench.rs

@@ -1,7 +1,7 @@
-use binggan::{black_box, BenchRunner};
+use binggan::{BenchRunner, black_box};
 use rand::seq::IteratorRandom;
 use rand::thread_rng;
-use tantivy_common::{serialize_vint_u32, BitSet, TinySet};
+use tantivy_common::{BitSet, TinySet, serialize_vint_u32};
 
 fn bench_vint() {
     let mut runner = BenchRunner::new();

common/src/bounds.rs

@@ -65,11 +65,11 @@ pub fn transform_bound_inner_res<TFrom, TTo>(
 ) -> io::Result<Bound<TTo>> {
     use self::Bound::*;
     Ok(match bound {
-        Excluded(ref from_val) => match transform(from_val)? {
+        Excluded(from_val) => match transform(from_val)? {
             TransformBound::NewBound(new_val) => new_val,
             TransformBound::Existing(new_val) => Excluded(new_val),
         },
-        Included(ref from_val) => match transform(from_val)? {
+        Included(from_val) => match transform(from_val)? {
             TransformBound::NewBound(new_val) => new_val,
             TransformBound::Existing(new_val) => Included(new_val),
         },
@@ -85,11 +85,11 @@ pub fn transform_bound_inner<TFrom, TTo>(
 ) -> Bound<TTo> {
     use self::Bound::*;
     match bound {
-        Excluded(ref from_val) => match transform(from_val) {
+        Excluded(from_val) => match transform(from_val) {
             TransformBound::NewBound(new_val) => new_val,
             TransformBound::Existing(new_val) => Excluded(new_val),
         },
-        Included(ref from_val) => match transform(from_val) {
+        Included(from_val) => match transform(from_val) {
             TransformBound::NewBound(new_val) => new_val,
             TransformBound::Existing(new_val) => Included(new_val),
         },
@@ -111,8 +111,8 @@ pub fn map_bound<TFrom, TTo>(
 ) -> Bound<TTo> {
     use self::Bound::*;
     match bound {
-        Excluded(ref from_val) => Bound::Excluded(transform(from_val)),
-        Included(ref from_val) => Bound::Included(transform(from_val)),
+        Excluded(from_val) => Bound::Excluded(transform(from_val)),
+        Included(from_val) => Bound::Included(transform(from_val)),
         Unbounded => Unbounded,
     }
 }
@@ -123,8 +123,8 @@ pub fn map_bound_res<TFrom, TTo, Err>(
 ) -> Result<Bound<TTo>, Err> {
     use self::Bound::*;
     Ok(match bound {
-        Excluded(ref from_val) => Excluded(transform(from_val)?),
-        Included(ref from_val) => Included(transform(from_val)?),
+        Excluded(from_val) => Excluded(transform(from_val)?),
+        Included(from_val) => Included(transform(from_val)?),
         Unbounded => Unbounded,
     })
 }

common/src/file_slice.rs

@@ -74,7 +74,7 @@ impl FileHandle for WrapFile {
         {
             use std::io::{Read, Seek};
             let mut file = self.file.try_clone()?; // Clone the file to read from it separately
-                                                   // Seek to the start position in the file
+            // Seek to the start position in the file
             file.seek(io::SeekFrom::Start(start as u64))?;
             // Read the data into the buffer
             file.read_exact(&mut buffer)?;
@@ -346,8 +346,8 @@ mod tests {
     use std::sync::Arc;
 
     use super::{FileHandle, FileSlice};
-    use crate::file_slice::combine_ranges;
     use crate::HasLen;
+    use crate::file_slice::combine_ranges;
 
     #[test]
     fn test_file_slice() -> io::Result<()> {

common/src/lib.rs

@@ -22,7 +22,7 @@ pub use json_path_writer::JsonPathWriter;
 pub use ownedbytes::{OwnedBytes, StableDeref};
 pub use serialize::{BinarySerializable, DeserializeFrom, FixedSize};
 pub use vint::{
-    read_u32_vint, read_u32_vint_no_advance, serialize_vint_u32, write_u32_vint, VInt, VIntU128,
+    VInt, VIntU128, read_u32_vint, read_u32_vint_no_advance, serialize_vint_u32, write_u32_vint,
 };
 pub use writer::{AntiCallToken, CountingWriter, TerminatingWrite};
 
@@ -177,8 +177,10 @@ pub(crate) mod test {
 
     #[test]
     fn test_f64_order() {
-        assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY))
-            .contains(&f64_to_u64(f64::NAN))); // nan is not a number
+        assert!(
+            !(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY))
+                .contains(&f64_to_u64(f64::NAN))
+        ); // nan is not a number
         assert!(f64_to_u64(1.5) > f64_to_u64(1.0)); // same exponent, different mantissa
         assert!(f64_to_u64(2.0) > f64_to_u64(1.0)); // same mantissa, different exponent
         assert!(f64_to_u64(2.0) > f64_to_u64(1.5)); // different exponent and mantissa

common/src/vint.rs

@@ -222,7 +222,7 @@ impl BinarySerializable for VInt {
 #[cfg(test)]
 mod tests {
 
-    use super::{serialize_vint_u32, BinarySerializable, VInt};
+    use super::{BinarySerializable, VInt, serialize_vint_u32};
 
     fn aux_test_vint(val: u64) {
         let mut v = [14u8; 10];

examples/basic_search.rs

@@ -51,7 +51,7 @@ fn main() -> tantivy::Result<()> {
 
     // Our second field is body.
     // We want full-text search for it, but we do not
-    // need to be able to be able to retrieve it
+    // need to be able to retrieve it
     // for our application.
     //
     // We can make our index lighter by omitting the `STORED` flag.

ownedbytes/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
 name = "ownedbytes"
-version = "0.7.0"
+version = "0.9.0"
 edition = "2021"
 description = "Expose data as static slice"
 license = "MIT"

query-grammar/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy-query-grammar"
-version = "0.22.0"
+version = "0.25.0"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
@@ -9,7 +9,7 @@ homepage = "https://github.com/quickwit-oss/tantivy"
 repository = "https://github.com/quickwit-oss/tantivy"
 readme = "README.md"
 keywords = ["search", "information", "retrieval"]
-edition = "2021"
+edition = "2024"
 
 [dependencies]
 nom = "7"

query-grammar/src/infallible.rs

@@ -186,19 +186,19 @@ macro_rules! tuple_trait_impl(
 );
 
 macro_rules! tuple_trait_inner(
-  ($it:tt, $self:expr, $input:expr, (), $error_list:expr, $head:ident $($id:ident)+) => ({
+  ($it:tt, $self:expr_2021, $input:expr_2021, (), $error_list:expr_2021, $head:ident $($id:ident)+) => ({
     let (i, (o, mut err)) = $self.$it.parse($input.clone())?;
     $error_list.append(&mut err);
 
     succ!($it, tuple_trait_inner!($self, i, ( o ), $error_list, $($id)+))
   });
-  ($it:tt, $self:expr, $input:expr, ($($parsed:tt)*), $error_list:expr, $head:ident $($id:ident)+) => ({
+  ($it:tt, $self:expr_2021, $input:expr_2021, ($($parsed:tt)*), $error_list:expr_2021, $head:ident $($id:ident)+) => ({
     let (i, (o, mut err)) = $self.$it.parse($input.clone())?;
     $error_list.append(&mut err);
 
     succ!($it, tuple_trait_inner!($self, i, ($($parsed)* , o), $error_list, $($id)+))
   });
-  ($it:tt, $self:expr, $input:expr, ($($parsed:tt)*), $error_list:expr, $head:ident) => ({
+  ($it:tt, $self:expr_2021, $input:expr_2021, ($($parsed:tt)*), $error_list:expr_2021, $head:ident) => ({
     let (i, (o, mut err)) = $self.$it.parse($input.clone())?;
     $error_list.append(&mut err);
 
@@ -328,13 +328,13 @@ macro_rules! alt_trait_impl(
 );
 
 macro_rules! alt_trait_inner(
-  ($it:tt, $self:expr, $input:expr, $head_cond:ident $head:ident, $($id_cond:ident $id:ident),+) => (
+  ($it:tt, $self:expr_2021, $input:expr_2021, $head_cond:ident $head:ident, $($id_cond:ident $id:ident),+) => (
     match $self.$it.0.parse($input.clone()) {
       Err(_) => succ!($it, alt_trait_inner!($self, $input, $($id_cond $id),+)),
       Ok((input_left, _)) => Some($self.$it.1.parse(input_left)),
     }
   );
-  ($it:tt, $self:expr, $input:expr, $head_cond:ident $head:ident) => (
+  ($it:tt, $self:expr_2021, $input:expr_2021, $head_cond:ident $head:ident) => (
     None
   );
 );

query-grammar/src/query_grammar.rs

@@ -1,6 +1,7 @@
 use std::borrow::Cow;
 use std::iter::once;
 
+use nom::IResult;
 use nom::branch::alt;
 use nom::bytes::complete::tag;
 use nom::character::complete::{
@@ -10,12 +11,11 @@ use nom::combinator::{eof, map, map_res, opt, peek, recognize, value, verify};
 use nom::error::{Error, ErrorKind};
 use nom::multi::{many0, many1, separated_list0};
 use nom::sequence::{delimited, preceded, separated_pair, terminated, tuple};
-use nom::IResult;
 
 use super::user_input_ast::{UserInputAst, UserInputBound, UserInputLeaf, UserInputLiteral};
+use crate::Occur;
 use crate::infallible::*;
 use crate::user_input_ast::Delimiter;
-use crate::Occur;
 
 // Note: '-' char is only forbidden at the beginning of a field name, would be clearer to add it to
 // special characters.
@@ -36,7 +36,7 @@ fn field_name(inp: &str) -> IResult<&str, String> {
                 alt((first_char, escape_sequence())),
                 many0(alt((simple_char, escape_sequence(), char('\\')))),
             )),
-            char(':'),
+            tuple((multispace0, char(':'), multispace0)),
         ),
         |(first_char, next)| once(first_char).chain(next).collect(),
     )(inp)
@@ -1030,7 +1030,7 @@ fn rewrite_ast(mut input: UserInputAst) -> UserInputAst {
 
 fn rewrite_ast_clause(input: &mut (Option<Occur>, UserInputAst)) {
     match input {
-        (None, UserInputAst::Clause(ref mut clauses)) if clauses.len() == 1 => {
+        (None, UserInputAst::Clause(clauses)) if clauses.len() == 1 => {
             *input = clauses.pop().unwrap(); // safe because clauses.len() == 1
         }
         _ => {}
@@ -1283,6 +1283,10 @@ mod test {
             super::field_name("~my~field:a"),
             Ok(("a", "~my~field".to_string()))
         );
+        assert_eq!(
+            super::field_name(".my.field.name : a"),
+            Ok(("a", ".my.field.name".to_string()))
+        );
         for special_char in SPECIAL_CHARS.iter() {
             let query = &format!("\\{special_char}my\\{special_char}field:a");
             assert_eq!(
@@ -1376,7 +1380,7 @@ mod test {
 
     #[test]
     fn test_range_parser_lenient() {
-        let literal = |query| literal_infallible(query).unwrap().1 .0.unwrap();
+        let literal = |query| literal_infallible(query).unwrap().1.0.unwrap();
 
         // same tests as non-lenient
         let res = literal("title: <hello");
@@ -1689,4 +1693,15 @@ mod test {
     fn test_invalid_field() {
         test_is_parse_err(r#"!bc:def"#, "!bc:def");
     }
+
+    #[test]
+    fn test_space_before_value() {
+        test_parse_query_to_ast_helper("field : a", r#""field":a"#);
+        test_parse_query_to_ast_helper("field:    a", r#""field":a"#);
+        test_parse_query_to_ast_helper("field         :a", r#""field":a"#);
+        test_parse_query_to_ast_helper(
+            "field : 'happy tax payer' AND other_field  : 1",
+            r#"(+"field":'happy tax payer' +"other_field":1)"#,
+        );
+    }
 }

query-grammar/src/user_input_ast.rs

@@ -51,7 +51,7 @@ impl UserInputLeaf {
 
     pub(crate) fn set_default_field(&mut self, default_field: String) {
         match self {
-            UserInputLeaf::Literal(ref mut literal) if literal.field_name.is_none() => {
+            UserInputLeaf::Literal(literal) if literal.field_name.is_none() => {
                 literal.field_name = Some(default_field)
             }
             UserInputLeaf::All => {
@@ -59,12 +59,8 @@ impl UserInputLeaf {
                     field: default_field,
                 }
             }
-            UserInputLeaf::Range { ref mut field, .. } if field.is_none() => {
-                *field = Some(default_field)
-            }
-            UserInputLeaf::Set { ref mut field, .. } if field.is_none() => {
-                *field = Some(default_field)
-            }
+            UserInputLeaf::Range { field, .. } if field.is_none() => *field = Some(default_field),
+            UserInputLeaf::Set { field, .. } if field.is_none() => *field = Some(default_field),
             _ => (), // field was already set, do nothing
         }
     }
@@ -75,11 +71,11 @@ impl Debug for UserInputLeaf {
         match self {
             UserInputLeaf::Literal(literal) => literal.fmt(formatter),
             UserInputLeaf::Range {
-                ref field,
-                ref lower,
-                ref upper,
+                field,
+                lower,
+                upper,
             } => {
-                if let Some(ref field) = field {
+                if let Some(field) = field {
                     // TODO properly escape field (in case of \")
                     write!(formatter, "\"{field}\":")?;
                 }
@@ -89,7 +85,7 @@ impl Debug for UserInputLeaf {
                 Ok(())
             }
             UserInputLeaf::Set { field, elements } => {
-                if let Some(ref field) = field {
+                if let Some(field) = field {
                     // TODO properly escape field (in case of \")
                     write!(formatter, "\"{field}\": ")?;
                 }
@@ -267,7 +263,7 @@ impl UserInputAst {
                 .iter_mut()
                 .for_each(|(_, ast)| ast.set_default_field(field.clone())),
             UserInputAst::Leaf(leaf) => leaf.set_default_field(field),
-            UserInputAst::Boost(ref mut ast, _) => ast.set_default_field(field),
+            UserInputAst::Boost(ast, _) => ast.set_default_field(field),
         }
     }
 }

src/aggregation/bucket/term_agg.rs

@@ -518,7 +518,7 @@ impl SegmentTermCollector {
                 |term| {
                     let entry = entries[idx];
                     let intermediate_entry = into_intermediate_bucket_entry(entry.0, entry.1)
-                        .map_err(|err| io::Error::new(io::ErrorKind::Other, err))?;
+                        .map_err(io::Error::other)?;
                     dict.insert(
                         IntermediateKey::Str(
                             String::from_utf8(term.to_vec()).expect("could not convert to String"),

src/aggregation/metric/top_hits.rs

@@ -229,6 +229,7 @@ impl TopHitsAggregationReq {
         self.sort
             .iter()
             .map(|KeyOrder { field, .. }| field.as_str())
+            .chain(self.doc_value_fields.iter().map(|s| s.as_str()))
             .collect()
     }
 

src/collector/facet_collector.rs

@@ -739,7 +739,7 @@ mod tests {
                 .flat_map(|(c, count)| {
                     let facet = Facet::from(&format!("/facet/{c}"));
                     let doc = doc!(facet_field => facet);
-                    iter::repeat(doc).take(count)
+                    std::iter::repeat_n(doc, count)
                 })
                 .map(|mut doc| {
                     doc.add_facet(
@@ -787,7 +787,7 @@ mod tests {
             .flat_map(|(c, count)| {
                 let facet = Facet::from(&format!("/facet/{c}"));
                 let doc = doc!(facet_field => facet);
-                iter::repeat(doc).take(count)
+                std::iter::repeat_n(doc, count)
             })
             .collect();
 

src/collector/top_score_collector.rs

@@ -2,11 +2,13 @@ use std::fmt;
 use std::marker::PhantomData;
 use std::sync::Arc;
 
-use columnar::ColumnValues;
+use columnar::{ColumnValues, StrColumn};
 use serde::{Deserialize, Serialize};
 
 use super::Collector;
-use crate::collector::custom_score_top_collector::CustomScoreTopCollector;
+use crate::collector::custom_score_top_collector::{
+    CustomScoreTopCollector, CustomScoreTopSegmentCollector,
+};
 use crate::collector::top_collector::{ComparableDoc, TopCollector, TopSegmentCollector};
 use crate::collector::tweak_score_top_collector::TweakedScoreTopCollector;
 use crate::collector::{
@@ -14,6 +16,7 @@ use crate::collector::{
 };
 use crate::fastfield::{FastFieldNotAvailableError, FastValue};
 use crate::query::Weight;
+use crate::termdict::TermOrdinal;
 use crate::{DocAddress, DocId, Order, Score, SegmentOrdinal, SegmentReader, TantivyError};
 
 struct FastFieldConvertCollector<
@@ -83,6 +86,163 @@ where
     }
 }
 
+struct StringConvertCollector {
+    pub collector: CustomScoreTopCollector<ScorerByField, u64>,
+    pub field: String,
+    order: Order,
+    limit: usize,
+    offset: usize,
+}
+
+impl Collector for StringConvertCollector {
+    type Fruit = Vec<(String, DocAddress)>;
+
+    type Child = StringConvertSegmentCollector;
+
+    fn for_segment(
+        &self,
+        segment_local_id: crate::SegmentOrdinal,
+        segment: &SegmentReader,
+    ) -> crate::Result<Self::Child> {
+        let schema = segment.schema();
+        let field = schema.get_field(&self.field)?;
+        let field_entry = schema.get_field_entry(field);
+        if !field_entry.is_fast() {
+            return Err(TantivyError::SchemaError(format!(
+                "Field {:?} is not a fast field.",
+                field_entry.name()
+            )));
+        }
+        let requested_type = crate::schema::Type::Str;
+        let schema_type = field_entry.field_type().value_type();
+        if schema_type != requested_type {
+            return Err(TantivyError::SchemaError(format!(
+                "Field {:?} is of type {schema_type:?}!={requested_type:?}",
+                field_entry.name()
+            )));
+        }
+        let ff = segment
+            .fast_fields()
+            .str(&self.field)?
+            .expect("ff should be a str field");
+        Ok(StringConvertSegmentCollector {
+            collector: self.collector.for_segment(segment_local_id, segment)?,
+            ff,
+            order: self.order.clone(),
+        })
+    }
+
+    fn requires_scoring(&self) -> bool {
+        self.collector.requires_scoring()
+    }
+
+    fn merge_fruits(
+        &self,
+        child_fruits: Vec<<Self::Child as SegmentCollector>::Fruit>,
+    ) -> crate::Result<Self::Fruit> {
+        if self.limit == 0 {
+            return Ok(Vec::new());
+        }
+        if self.order.is_desc() {
+            let mut top_collector: TopNComputer<_, _, true> =
+                TopNComputer::new(self.limit + self.offset);
+            for child_fruit in child_fruits {
+                for (feature, doc) in child_fruit {
+                    top_collector.push(feature, doc);
+                }
+            }
+            Ok(top_collector
+                .into_sorted_vec()
+                .into_iter()
+                .skip(self.offset)
+                .map(|cdoc| (cdoc.feature, cdoc.doc))
+                .collect())
+        } else {
+            let mut top_collector: TopNComputer<_, _, false> =
+                TopNComputer::new(self.limit + self.offset);
+            for child_fruit in child_fruits {
+                for (feature, doc) in child_fruit {
+                    top_collector.push(feature, doc);
+                }
+            }
+
+            Ok(top_collector
+                .into_sorted_vec()
+                .into_iter()
+                .skip(self.offset)
+                .map(|cdoc| (cdoc.feature, cdoc.doc))
+                .collect())
+        }
+    }
+}
+
+struct StringConvertSegmentCollector {
+    pub collector: CustomScoreTopSegmentCollector<ScorerByFastFieldReader, u64>,
+    ff: StrColumn,
+    order: Order,
+}
+
+impl SegmentCollector for StringConvertSegmentCollector {
+    type Fruit = Vec<(String, DocAddress)>;
+
+    fn collect(&mut self, doc: DocId, score: Score) {
+        self.collector.collect(doc, score);
+    }
+
+    fn harvest(self) -> Vec<(String, DocAddress)> {
+        let top_ordinals: Vec<(TermOrdinal, DocAddress)> = self.collector.harvest();
+
+        // Collect terms.
+        let mut terms: Vec<String> = Vec::with_capacity(top_ordinals.len());
+        let result = if self.order.is_asc() {
+            self.ff.dictionary().sorted_ords_to_term_cb(
+                top_ordinals.iter().map(|(term_ord, _)| u64::MAX - term_ord),
+                |term| {
+                    terms.push(
+                        std::str::from_utf8(term)
+                            .expect("Failed to decode term as unicode")
+                            .to_owned(),
+                    );
+                    Ok(())
+                },
+            )
+        } else {
+            self.ff.dictionary().sorted_ords_to_term_cb(
+                top_ordinals.iter().rev().map(|(term_ord, _)| *term_ord),
+                |term| {
+                    terms.push(
+                        std::str::from_utf8(term)
+                            .expect("Failed to decode term as unicode")
+                            .to_owned(),
+                    );
+                    Ok(())
+                },
+            )
+        };
+
+        assert!(
+            result.expect("Failed to read terms from term dictionary"),
+            "Not all terms were matched in segment."
+        );
+
+        // Zip them back with their docs.
+        if self.order.is_asc() {
+            terms
+                .into_iter()
+                .zip(top_ordinals)
+                .map(|(term, (_, doc))| (term, doc))
+                .collect()
+        } else {
+            terms
+                .into_iter()
+                .rev()
+                .zip(top_ordinals)
+                .map(|(term, (_, doc))| (term, doc))
+                .collect()
+        }
+    }
+}
+
 /// The `TopDocs` collector keeps track of the top `K` documents
 /// sorted by their score.
 ///
@@ -410,6 +570,30 @@ impl TopDocs {
         }
     }
 
+    /// Like `order_by_fast_field`, but for a `String` fast field.
+    pub fn order_by_string_fast_field(
+        self,
+        fast_field: impl ToString,
+        order: Order,
+    ) -> impl Collector<Fruit = Vec<(String, DocAddress)>> {
+        let limit = self.0.limit;
+        let offset = self.0.offset;
+        let u64_collector = CustomScoreTopCollector::new(
+            ScorerByField {
+                field: fast_field.to_string(),
+                order: order.clone(),
+            },
+            self.0.into_tscore(),
+        );
+        StringConvertCollector {
+            collector: u64_collector,
+            field: fast_field.to_string(),
+            order,
+            limit,
+            offset,
+        }
+    }
+
     /// Ranks the documents using a custom score.
     ///
     /// This method offers a convenient way to tweak or replace
@@ -786,7 +970,7 @@ impl<Score, D, const R: bool> From<TopNComputerDeser<Score, D, R>> for TopNCompu
     }
 }
 
-impl<Score, D, const R: bool> TopNComputer<Score, D, R>
+impl<Score, D, const REVERSE_ORDER: bool> TopNComputer<Score, D, REVERSE_ORDER>
 where
     Score: PartialOrd + Clone,
     D: Ord,
@@ -807,7 +991,10 @@ where
     #[inline]
     pub fn push(&mut self, feature: Score, doc: D) {
         if let Some(last_median) = self.threshold.clone() {
-            if feature < last_median {
+            if !REVERSE_ORDER && feature > last_median {
+                return;
+            }
+            if REVERSE_ORDER && feature < last_median {
                 return;
             }
         }
@@ -842,7 +1029,7 @@ where
     }
 
     /// Returns the top n elements in sorted order.
-    pub fn into_sorted_vec(mut self) -> Vec<ComparableDoc<Score, D, R>> {
+    pub fn into_sorted_vec(mut self) -> Vec<ComparableDoc<Score, D, REVERSE_ORDER>> {
         if self.buffer.len() > self.top_n {
             self.truncate_top_n();
         }
@@ -853,7 +1040,7 @@ where
     /// Returns the top n elements in stored order.
     /// Useful if you do not need the elements in sorted order,
     /// for example when merging the results of multiple segments.
-    pub fn into_vec(mut self) -> Vec<ComparableDoc<Score, D, R>> {
+    pub fn into_vec(mut self) -> Vec<ComparableDoc<Score, D, REVERSE_ORDER>> {
         if self.buffer.len() > self.top_n {
             self.truncate_top_n();
         }
@@ -863,9 +1050,11 @@ where
 
 #[cfg(test)]
 mod tests {
+    use proptest::prelude::*;
+
     use super::{TopDocs, TopNComputer};
     use crate::collector::top_collector::ComparableDoc;
-    use crate::collector::Collector;
+    use crate::collector::{Collector, DocSetCollector};
     use crate::query::{AllQuery, Query, QueryParser};
     use crate::schema::{Field, Schema, FAST, STORED, TEXT};
     use crate::time::format_description::well_known::Rfc3339;
@@ -960,6 +1149,44 @@ mod tests {
         }
     }
 
+    proptest! {
+        #[test]
+        fn test_topn_computer_asc_prop(
+          limit in 0..10_usize,
+          docs in proptest::collection::vec((0..100_u64, 0..100_u64), 0..100_usize),
+        ) {
+            let mut computer: TopNComputer<_, _, false> = TopNComputer::new(limit);
+            for (feature, doc) in &docs {
+                computer.push(*feature, *doc);
+            }
+            let mut comparable_docs = docs.into_iter().map(|(feature, doc)| ComparableDoc { feature, doc }).collect::<Vec<_>>();
+            comparable_docs.sort();
+            comparable_docs.truncate(limit);
+            prop_assert_eq!(
+                computer.into_sorted_vec(),
+                comparable_docs,
+            );
+        }
+
+        #[test]
+        fn test_topn_computer_desc_prop(
+          limit in 0..10_usize,
+          docs in proptest::collection::vec((0..100_u64, 0..100_u64), 0..100_usize),
+        ) {
+            let mut computer: TopNComputer<_, _, true> = TopNComputer::new(limit);
+            for (feature, doc) in &docs {
+                computer.push(*feature, *doc);
+            }
+            let mut comparable_docs = docs.into_iter().map(|(feature, doc)| ComparableDoc { feature, doc }).collect::<Vec<_>>();
+            comparable_docs.sort();
+            comparable_docs.truncate(limit);
+            prop_assert_eq!(
+                computer.into_sorted_vec(),
+                comparable_docs,
+            );
+        }
+    }
+
     #[test]
     fn test_top_collector_not_at_capacity_without_offset() -> crate::Result<()> {
         let index = make_index()?;
@@ -1066,6 +1293,220 @@ mod tests {
         assert_eq!(page_0, &page_2[..page_0.len()]);
     }
 
+    proptest! {
+        #![proptest_config(ProptestConfig::with_cases(20))]
+        /// Build multiple segments with equal-scoring docs and verify stable ordering
+        /// across pages when increasing limit or offset.
+        #[test]
+        fn proptest_stable_ordering_across_segments_with_pagination(
+            docs_per_segment in proptest::collection::vec(1usize..50, 2..5)
+        ) {
+            use crate::indexer::NoMergePolicy;
+
+            // Build an index with multiple segments; all docs will have the same score using AllQuery.
+            let mut schema_builder = Schema::builder();
+            let text = schema_builder.add_text_field("text", TEXT);
+            let schema = schema_builder.build();
+            let index = Index::create_in_ram(schema);
+            let mut writer = index.writer_for_tests().unwrap();
+            writer.set_merge_policy(Box::new(NoMergePolicy));
+
+            for num_docs in &docs_per_segment {
+                for _ in 0..*num_docs {
+                    writer.add_document(doc!(text => "x")).unwrap();
+                }
+                writer.commit().unwrap();
+            }
+
+            let reader = index.reader().unwrap();
+            let searcher = reader.searcher();
+
+            let total_docs: usize = docs_per_segment.iter().sum();
+            // Full result set, first assert all scores are identical.
+            let full_with_scores: Vec<(Score, DocAddress)> = searcher
+                .search(&AllQuery, &TopDocs::with_limit(total_docs))
+                .unwrap();
+            // Sanity: at least one document was returned.
+            prop_assert!(!full_with_scores.is_empty());
+            let first_score = full_with_scores[0].0;
+            prop_assert!(full_with_scores.iter().all(|(score, _)| *score == first_score));
+
+            // Keep only the addresses for the remaining checks.
+            let full: Vec<DocAddress> = full_with_scores
+                .into_iter()
+                .map(|(_score, addr)| addr)
+                .collect();
+
+            // Sanity: we actually created multiple segments and have documents.
+            prop_assert!(docs_per_segment.len() >= 2);
+            prop_assert!(total_docs >= 2);
+
+            // 1) Increasing limit should preserve prefix ordering.
+            for k in 1..=total_docs {
+                let page: Vec<DocAddress> = searcher
+                    .search(&AllQuery, &TopDocs::with_limit(k))
+                    .unwrap()
+                    .into_iter()
+                    .map(|(_score, addr)| addr)
+                    .collect();
+                prop_assert_eq!(page, full[..k].to_vec());
+            }
+
+            // 2) Offset + limit pages should always match the corresponding slice.
+            //    For each offset, check three representative page sizes:
+            //    - first page (size 1)
+            //    - a middle page (roughly half of remaining)
+            //    - the last page (size = remaining)
+            for offset in 0..total_docs {
+                let remaining = total_docs - offset;
+
+                let assert_page_eq = |limit: usize| -> proptest::test_runner::TestCaseResult {
+                    let page: Vec<DocAddress> = searcher
+                        .search(&AllQuery, &TopDocs::with_limit(limit).and_offset(offset))
+                        .unwrap()
+                        .into_iter()
+                        .map(|(_score, addr)| addr)
+                        .collect();
+                    prop_assert_eq!(page, full[offset..offset + limit].to_vec());
+                    Ok(())
+                };
+
+                // Smallest page.
+                assert_page_eq(1)?;
+                // A middle-sized page (dedupes to 1 if remaining == 1).
+                assert_page_eq((remaining / 2).max(1))?;
+                // Largest page for this offset.
+                assert_page_eq(remaining)?;
+            }
+
+            // 3) Concatenating fixed-size pages by offset reproduces the full order.
+            for page_size in 1..=total_docs.min(5) {
+                let mut concat: Vec<DocAddress> = Vec::new();
+                let mut offset = 0;
+                while offset < total_docs {
+                    let size = page_size.min(total_docs - offset);
+                    let page: Vec<DocAddress> = searcher
+                        .search(&AllQuery, &TopDocs::with_limit(size).and_offset(offset))
+                        .unwrap()
+                        .into_iter()
+                        .map(|(_score, addr)| addr)
+                        .collect();
+                    concat.extend(page);
+                    offset += size;
+                }
+                // Avoid moving `full` across loop iterations.
+                prop_assert_eq!(concat, full.clone());
+            }
+        }
+    }
+
+    proptest! {
+        #![proptest_config(ProptestConfig::with_cases(20))]
+        /// Build multiple segments with same-scoring term matches and verify stable ordering
+        /// across pages for a real scoring query (TermQuery with identical TF and fieldnorm).
+        #[test]
+        fn proptest_stable_ordering_across_segments_with_term_query_and_pagination(
+            docs_per_segment in proptest::collection::vec(1usize..50, 2..5)
+        ) {
+            use crate::indexer::NoMergePolicy;
+            use crate::schema::IndexRecordOption;
+            use crate::query::TermQuery;
+            use crate::Term;
+
+            // Build an index with multiple segments; each doc has exactly one token "x",
+            // ensuring equal BM25 scores across all matching docs (same TF=1 and fieldnorm=1).
+            let mut schema_builder = Schema::builder();
+            let text = schema_builder.add_text_field("text", TEXT);
+            let schema = schema_builder.build();
+            let index = Index::create_in_ram(schema);
+            let mut writer = index.writer_for_tests().unwrap();
+            writer.set_merge_policy(Box::new(NoMergePolicy));
+
+            for num_docs in &docs_per_segment {
+                for _ in 0..*num_docs {
+                    writer.add_document(doc!(text => "x")).unwrap();
+                }
+                writer.commit().unwrap();
+            }
+
+            let reader = index.reader().unwrap();
+            let searcher = reader.searcher();
+
+            let total_docs: usize = docs_per_segment.iter().sum();
+            let term = Term::from_field_text(text, "x");
+            let tq = TermQuery::new(term, IndexRecordOption::WithFreqs);
+
+            // Full result set, first assert all scores are identical across docs.
+            let full_with_scores: Vec<(Score, DocAddress)> = searcher
+                .search(&tq, &TopDocs::with_limit(total_docs))
+                .unwrap();
+            // Sanity: at least one document was returned.
+            prop_assert!(!full_with_scores.is_empty());
+            let first_score = full_with_scores[0].0;
+            prop_assert!(full_with_scores.iter().all(|(score, _)| *score == first_score));
+
+            // Keep only the addresses for the remaining checks.
+            let full: Vec<DocAddress> = full_with_scores
+                .into_iter()
+                .map(|(_score, addr)| addr)
+                .collect();
+
+            // Sanity: we actually created multiple segments and have documents.
+            prop_assert!(docs_per_segment.len() >= 2);
+            prop_assert!(total_docs >= 2);
+
+            // 1) Increasing limit should preserve prefix ordering.
+            for k in 1..=total_docs {
+                let page: Vec<DocAddress> = searcher
+                    .search(&tq, &TopDocs::with_limit(k))
+                    .unwrap()
+                    .into_iter()
+                    .map(|(_score, addr)| addr)
+                    .collect();
+                prop_assert_eq!(page, full[..k].to_vec());
+            }
+
+            // 2) Offset + limit pages should always match the corresponding slice.
+            //    Check three representative page sizes for each offset: 1, ~half, and remaining.
+            for offset in 0..total_docs {
+                let remaining = total_docs - offset;
+
+                let assert_page_eq = |limit: usize| -> proptest::test_runner::TestCaseResult {
+                    let page: Vec<DocAddress> = searcher
+                        .search(&tq, &TopDocs::with_limit(limit).and_offset(offset))
+                        .unwrap()
+                        .into_iter()
+                        .map(|(_score, addr)| addr)
+                        .collect();
+                    prop_assert_eq!(page, full[offset..offset + limit].to_vec());
+                    Ok(())
+                };
+
+                assert_page_eq(1)?;
+                assert_page_eq((remaining / 2).max(1))?;
+                assert_page_eq(remaining)?;
+            }
+
+            // 3) Concatenating fixed-size pages by offset reproduces the full order.
+            for page_size in 1..=total_docs.min(5) {
+                let mut concat: Vec<DocAddress> = Vec::new();
+                let mut offset = 0;
+                while offset < total_docs {
+                    let size = page_size.min(total_docs - offset);
+                    let page: Vec<DocAddress> = searcher
+                        .search(&tq, &TopDocs::with_limit(size).and_offset(offset))
+                        .unwrap()
+                        .into_iter()
+                        .map(|(_score, addr)| addr)
+                        .collect();
+                    concat.extend(page);
+                    offset += size;
+                }
+                prop_assert_eq!(concat, full.clone());
+            }
+        }
+    }
+
     #[test]
     #[should_panic]
     fn test_top_0() {
@@ -1214,6 +1655,160 @@ mod tests {
         Ok(())
     }
 
+    #[test]
+    fn test_top_field_collector_string() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let city = schema_builder.add_text_field("city", TEXT | FAST);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(
+                city => "austin",
+        ))?;
+        index_writer.add_document(doc!(
+                city => "greenville",
+        ))?;
+        index_writer.add_document(doc!(
+            city => "tokyo",
+        ))?;
+        index_writer.commit()?;
+
+        fn query(
+            index: &Index,
+            order: Order,
+            limit: usize,
+            offset: usize,
+        ) -> crate::Result<Vec<(String, DocAddress)>> {
+            let searcher = index.reader()?.searcher();
+            let top_collector = TopDocs::with_limit(limit)
+                .and_offset(offset)
+                .order_by_string_fast_field("city", order);
+            searcher.search(&AllQuery, &top_collector)
+        }
+
+        assert_eq!(
+            &query(&index, Order::Desc, 3, 0)?,
+            &[
+                ("tokyo".to_owned(), DocAddress::new(0, 2)),
+                ("greenville".to_owned(), DocAddress::new(0, 1)),
+                ("austin".to_owned(), DocAddress::new(0, 0)),
+            ]
+        );
+
+        assert_eq!(
+            &query(&index, Order::Desc, 2, 0)?,
+            &[
+                ("tokyo".to_owned(), DocAddress::new(0, 2)),
+                ("greenville".to_owned(), DocAddress::new(0, 1)),
+            ]
+        );
+
+        assert_eq!(&query(&index, Order::Desc, 3, 3)?, &[]);
+
+        assert_eq!(
+            &query(&index, Order::Desc, 2, 1)?,
+            &[
+                ("greenville".to_owned(), DocAddress::new(0, 1)),
+                ("austin".to_owned(), DocAddress::new(0, 0)),
+            ]
+        );
+
+        assert_eq!(
+            &query(&index, Order::Asc, 3, 0)?,
+            &[
+                ("austin".to_owned(), DocAddress::new(0, 0)),
+                ("greenville".to_owned(), DocAddress::new(0, 1)),
+                ("tokyo".to_owned(), DocAddress::new(0, 2)),
+            ]
+        );
+
+        assert_eq!(
+            &query(&index, Order::Asc, 2, 1)?,
+            &[
+                ("greenville".to_owned(), DocAddress::new(0, 1)),
+                ("tokyo".to_owned(), DocAddress::new(0, 2)),
+            ]
+        );
+
+        assert_eq!(
+            &query(&index, Order::Asc, 2, 0)?,
+            &[
+                ("austin".to_owned(), DocAddress::new(0, 0)),
+                ("greenville".to_owned(), DocAddress::new(0, 1)),
+            ]
+        );
+
+        assert_eq!(&query(&index, Order::Asc, 3, 3)?, &[]);
+
+        Ok(())
+    }
+
+    proptest! {
+        #[test]
+        fn test_top_field_collect_string_prop(
+          order in prop_oneof!(Just(Order::Desc), Just(Order::Asc)),
+          limit in 1..256_usize,
+          offset in 0..256_usize,
+          segments_terms in
+            proptest::collection::vec(
+                proptest::collection::vec(0..32_u8, 1..32_usize),
+                0..8_usize,
+            )
+        ) {
+            let mut schema_builder = Schema::builder();
+            let city = schema_builder.add_text_field("city", TEXT | FAST);
+            let schema = schema_builder.build();
+            let index = Index::create_in_ram(schema);
+            let mut index_writer = index.writer_for_tests()?;
+
+            // A Vec<Vec<u8>>, where the outer Vec represents segments, and the inner Vec
+            // represents terms.
+            for segment_terms in segments_terms.into_iter() {
+                for term in segment_terms.into_iter() {
+                    let term = format!("{term:0>3}");
+                    index_writer.add_document(doc!(
+                        city => term,
+                    ))?;
+                }
+                index_writer.commit()?;
+            }
+
+            let searcher = index.reader()?.searcher();
+            let top_n_results = searcher.search(&AllQuery, &TopDocs::with_limit(limit)
+                .and_offset(offset)
+                .order_by_string_fast_field("city", order.clone()))?;
+            let all_results = searcher.search(&AllQuery, &DocSetCollector)?.into_iter().map(|doc_address| {
+                // Get the term for this address.
+                // NOTE: We can't determine the SegmentIds that will be generated for Segments
+                // ahead of time, so we can't pre-compute the expected `DocAddress`es.
+                let column = searcher.segment_readers()[doc_address.segment_ord as usize].fast_fields().str("city").unwrap().unwrap();
+                let term_ord = column.term_ords(doc_address.doc_id).next().unwrap();
+                let mut city = Vec::new();
+                column.dictionary().ord_to_term(term_ord, &mut city).unwrap();
+                (String::try_from(city).unwrap(), doc_address)
+            });
+
+            // Using the TopDocs collector should always be equivalent to sorting, skipping the
+            // offset, and then taking the limit.
+            let sorted_docs: Vec<_> = if order.is_desc() {
+                let mut comparable_docs: Vec<ComparableDoc<_, _, true>> =
+                    all_results.into_iter().map(|(feature, doc)| ComparableDoc { feature, doc}).collect();
+                comparable_docs.sort();
+                comparable_docs.into_iter().map(|cd| (cd.feature, cd.doc)).collect()
+            } else {
+                let mut comparable_docs: Vec<ComparableDoc<_, _, false>> =
+                    all_results.into_iter().map(|(feature, doc)| ComparableDoc { feature, doc}).collect();
+                comparable_docs.sort();
+                comparable_docs.into_iter().map(|cd| (cd.feature, cd.doc)).collect()
+            };
+            let expected_docs = sorted_docs.into_iter().skip(offset).take(limit).collect::<Vec<_>>();
+            prop_assert_eq!(
+                expected_docs,
+                top_n_results
+            );
+        }
+    }
+
     #[test]
     #[should_panic]
     fn test_field_does_not_exist() {
@@ -1373,4 +1968,29 @@ mod tests {
         );
         Ok(())
     }
+
+    #[test]
+    fn test_topn_computer_asc() {
+        let mut computer: TopNComputer<u32, u32, false> = TopNComputer::new(2);
+
+        computer.push(1u32, 1u32);
+        computer.push(2u32, 2u32);
+        computer.push(3u32, 3u32);
+        computer.push(2u32, 4u32);
+        computer.push(4u32, 5u32);
+        computer.push(1u32, 6u32);
+        assert_eq!(
+            computer.into_sorted_vec(),
+            &[
+                ComparableDoc {
+                    feature: 1u32,
+                    doc: 1u32,
+                },
+                ComparableDoc {
+                    feature: 1u32,
+                    doc: 6u32,
+                }
+            ]
+        );
+    }
 }

src/compat_tests.rs

@@ -30,7 +30,7 @@ fn create_format() {
 }
 
 fn path_for_version(version: &str) -> String {
-    format!("./tests/compat_tests_data/index_v{}/", version)
+    format!("./tests/compat_tests_data/index_v{version}/")
 }
 
 /// feature flag quickwit uses a different dictionary type

src/core/executor.rs

@@ -65,8 +65,7 @@ impl Executor {
                                 if let Err(err) = fruit_sender_ref.send((idx, fruit)) {
                                     error!(
                                         "Failed to send search task. It probably means all search \
-                                         threads have panicked. {:?}",
-                                        err
+                                         threads have panicked. {err:?}"
                                     );
                                 }
                             });

src/core/searcher.rs

@@ -214,7 +214,7 @@ impl Searcher {
     /// It is powerless at making search faster if your index consists in
     /// one large segment.
     ///
-    /// Also, keep in my multithreading a single query on several
+    /// Also, keep in mind multithreading a single query on several
     /// threads will not improve your throughput. It can actually
     /// hurt it. It will however, decrease the average response time.
     pub fn search_with_executor<C: Collector>(

src/directory/directory.rs

@@ -56,7 +56,7 @@ impl<T: Send + Sync + 'static> From<Box<T>> for DirectoryLock {
 impl Drop for DirectoryLockGuard {
     fn drop(&mut self) {
         if let Err(e) = self.directory.delete(&self.path) {
-            error!("Failed to remove the lock file. {:?}", e);
+            error!("Failed to remove the lock file. {e:?}");
         }
     }
 }

src/directory/file_watcher.rs

@@ -51,7 +51,7 @@ impl FileWatcher {
                             .map(|current_checksum| current_checksum != checksum)
                             .unwrap_or(true);
                         if metafile_has_changed {
-                            info!("Meta file {:?} was modified", path);
+                            info!("Meta file {path:?} was modified");
                             current_checksum_opt = Some(checksum);
                             // We actually ignore callbacks failing here.
                             // We just wait for the end of their execution.
@@ -75,7 +75,7 @@ impl FileWatcher {
         let reader = match fs::File::open(path) {
             Ok(f) => io::BufReader::new(f),
             Err(e) => {
-                warn!("Failed to open meta file {:?}: {:?}", path, e);
+                warn!("Failed to open meta file {path:?}: {e:?}");
                 return Err(e);
             }
         };

src/directory/managed_directory.rs

@@ -157,7 +157,7 @@ impl ManagedDirectory {
         for file_to_delete in files_to_delete {
             match self.delete(&file_to_delete) {
                 Ok(_) => {
-                    info!("Deleted {:?}", file_to_delete);
+                    info!("Deleted {file_to_delete:?}");
                     deleted_files.push(file_to_delete);
                 }
                 Err(file_error) => {
@@ -170,7 +170,7 @@ impl ManagedDirectory {
                             if !cfg!(target_os = "windows") {
                                 // On windows, delete is expected to fail if the file
                                 // is mmapped.
-                                error!("Failed to delete {:?}", file_to_delete);
+                                error!("Failed to delete {file_to_delete:?}");
                             }
                         }
                     }

src/directory/mmap_directory.rs

@@ -7,7 +7,7 @@ use std::path::{Path, PathBuf};
 use std::sync::{Arc, RwLock, Weak};
 
 use common::StableDeref;
-use fs4::FileExt;
+use fs4::fs_std::FileExt;
 #[cfg(all(feature = "mmap", unix))]
 pub use memmap2::Advice;
 use memmap2::Mmap;
@@ -29,7 +29,7 @@ pub type WeakArcBytes = Weak<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
 
 /// Create a default io error given a string.
 pub(crate) fn make_io_err(msg: String) -> io::Error {
-    io::Error::new(io::ErrorKind::Other, msg)
+    io::Error::other(msg)
 }
 
 /// Returns `None` iff the file exists, can be read, but is empty (and hence
@@ -369,7 +369,7 @@ pub(crate) fn atomic_write(path: &Path, content: &[u8]) -> io::Result<()> {
 
 impl Directory for MmapDirectory {
     fn get_file_handle(&self, path: &Path) -> Result<Arc<dyn FileHandle>, OpenReadError> {
-        debug!("Open Read {:?}", path);
+        debug!("Open Read {path:?}");
         let full_path = self.resolve_path(path);
 
         let mut mmap_cache = self.inner.mmap_cache.write().map_err(|_| {
@@ -414,7 +414,7 @@ impl Directory for MmapDirectory {
     }
 
     fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError> {
-        debug!("Open Write {:?}", path);
+        debug!("Open Write {path:?}");
         let full_path = self.resolve_path(path);
 
         let open_res = OpenOptions::new()
@@ -467,7 +467,7 @@ impl Directory for MmapDirectory {
     }
 
     fn atomic_write(&self, path: &Path, content: &[u8]) -> io::Result<()> {
-        debug!("Atomic Write {:?}", path);
+        debug!("Atomic Write {path:?}");
         let full_path = self.resolve_path(path);
         atomic_write(&full_path, content)?;
         Ok(())
@@ -485,7 +485,9 @@ impl Directory for MmapDirectory {
         if lock.is_blocking {
             file.lock_exclusive().map_err(LockError::wrap_io_error)?;
         } else {
-            file.try_lock_exclusive().map_err(|_| LockError::LockBusy)?
+            if !file.try_lock_exclusive().map_err(|_| LockError::LockBusy)? {
+                return Err(LockError::LockBusy);
+            }
         }
         // dropping the file handle will release the lock.
         Ok(DirectoryLock::from(Box::new(ReleaseLockFile {

src/directory/ram_directory.rs

@@ -191,7 +191,7 @@ impl Directory for RamDirectory {
             .fs
             .read()
             .map_err(|e| OpenReadError::IoError {
-                io_error: Arc::new(io::Error::new(io::ErrorKind::Other, e.to_string())),
+                io_error: Arc::new(io::Error::other(e.to_string())),
                 filepath: path.to_path_buf(),
             })?
             .exists(path))

src/directory/watch_event_router.rs

@@ -90,10 +90,7 @@ impl WatchCallbackList {
                 let _ = sender.send(Ok(()));
             });
         if let Err(err) = spawn_res {
-            error!(
-                "Failed to spawn thread to call watch callbacks. Cause: {:?}",
-                err
-            );
+            error!("Failed to spawn thread to call watch callbacks. Cause: {err:?}");
         }
         result
     }

src/index/index.rs

@@ -216,7 +216,7 @@ impl IndexBuilder {
 
     /// Opens or creates a new index in the provided directory
     pub fn open_or_create<T: Into<Box<dyn Directory>>>(self, dir: T) -> crate::Result<Index> {
-        let dir = dir.into();
+        let dir: Box<dyn Directory> = dir.into();
         if !Index::exists(&*dir)? {
             return self.create(dir);
         }
@@ -494,7 +494,7 @@ impl Index {
             .into_iter()
             .map(|segment| SegmentReader::open(&segment)?.fields_metadata())
             .collect::<Result<_, _>>()?;
-        Ok(merge_field_meta_data(fields_metadata, &self.schema()))
+        Ok(merge_field_meta_data(fields_metadata))
     }
 
     /// Creates a new segment_meta (Advanced user only).

src/index/inverted_index_reader.rs

@@ -1,8 +1,7 @@
 use std::io;
 
 use common::json_path_writer::JSON_END_OF_PATH;
-use common::BinarySerializable;
-use fnv::FnvHashSet;
+use common::{BinarySerializable, ByteCount};
 #[cfg(feature = "quickwit")]
 use futures_util::{FutureExt, StreamExt, TryStreamExt};
 #[cfg(feature = "quickwit")]
@@ -36,6 +35,33 @@ pub struct InvertedIndexReader {
     total_num_tokens: u64,
 }
 
+/// Object that records the amount of space used by a field in an inverted index.
+pub(crate) struct InvertedIndexFieldSpace {
+    pub field_name: String,
+    pub field_type: Type,
+    pub postings_size: ByteCount,
+    pub positions_size: ByteCount,
+    pub num_terms: u64,
+}
+
+/// Returns None if the term is not a valid JSON path.
+fn extract_field_name_and_field_type_from_json_path(term: &[u8]) -> Option<(String, Type)> {
+    let index = term.iter().position(|&byte| byte == JSON_END_OF_PATH)?;
+    let field_type_code = term.get(index + 1).copied()?;
+    let field_type = Type::from_code(field_type_code)?;
+    // Let's flush the current field.
+    let field_name = String::from_utf8_lossy(&term[..index]).to_string();
+    Some((field_name, field_type))
+}
+
+impl InvertedIndexFieldSpace {
+    fn record(&mut self, term_info: &TermInfo) {
+        self.postings_size += ByteCount::from(term_info.posting_num_bytes() as u64);
+        self.positions_size += ByteCount::from(term_info.positions_num_bytes() as u64);
+        self.num_terms += 1;
+    }
+}
+
 impl InvertedIndexReader {
     pub(crate) fn new(
         termdict: TermDictionary,
@@ -81,20 +107,56 @@ impl InvertedIndexReader {
     ///
     /// Notice: This requires a full scan and therefore **very expensive**.
     /// TODO: Move to sstable to use the index.
-    pub fn list_encoded_fields(&self) -> io::Result<Vec<(String, Type)>> {
+    pub(crate) fn list_encoded_json_fields(&self) -> io::Result<Vec<InvertedIndexFieldSpace>> {
         let mut stream = self.termdict.stream()?;
-        let mut fields = Vec::new();
-        let mut fields_set = FnvHashSet::default();
-        while let Some((term, _term_info)) = stream.next() {
-            if let Some(index) = term.iter().position(|&byte| byte == JSON_END_OF_PATH) {
-                if !fields_set.contains(&term[..index + 2]) {
-                    fields_set.insert(term[..index + 2].to_vec());
-                    let typ = Type::from_code(term[index + 1]).unwrap();
-                    fields.push((String::from_utf8_lossy(&term[..index]).to_string(), typ));
+        let mut fields: Vec<InvertedIndexFieldSpace> = Vec::new();
+
+        let mut current_field_opt: Option<InvertedIndexFieldSpace> = None;
+        // Current field bytes, including the JSON_END_OF_PATH.
+        let mut current_field_bytes: Vec<u8> = Vec::new();
+
+        while let Some((term, term_info)) = stream.next() {
+            if let Some(current_field) = &mut current_field_opt {
+                if term.starts_with(&current_field_bytes) {
+                    // We are still in the same field.
+                    current_field.record(term_info);
+                    continue;
                 }
             }
+
+            // This is a new field!
+            // Let's flush the current field.
+            fields.extend(current_field_opt.take());
+            current_field_bytes.clear();
+
+            // And create a new one.
+            let Some((field_name, field_type)) =
+                extract_field_name_and_field_type_from_json_path(term)
+            else {
+                error!(
+                    "invalid term bytes encountered {term:?}. this only happens if the term \
+                     dictionary is corrupted. please report"
+                );
+                continue;
+            };
+            let mut field_space = InvertedIndexFieldSpace {
+                field_name,
+                field_type,
+                postings_size: ByteCount::default(),
+                positions_size: ByteCount::default(),
+                num_terms: 0u64,
+            };
+            field_space.record(&term_info);
+
+            // We include the json type and the json end of path to make sure the prefix check
+            // is meaningful.
+            current_field_bytes.extend_from_slice(&term[..field_space.field_name.len() + 2]);
+            current_field_opt = Some(field_space);
         }
 
+        // We need to flush the last field as well.
+        fields.extend(current_field_opt.take());
+
         Ok(fields)
     }
 

src/index/segment_reader.rs

@@ -1,8 +1,8 @@
 use std::collections::HashMap;
-use std::ops::BitOrAssign;
 use std::sync::{Arc, RwLock};
 use std::{fmt, io};
 
+use common::{ByteCount, HasLen};
 use fnv::FnvHashMap;
 use itertools::Itertools;
 
@@ -304,12 +304,16 @@ impl SegmentReader {
         for (field, field_entry) in self.schema().fields() {
             let field_name = field_entry.name().to_string();
             let is_indexed = field_entry.is_indexed();
-
             if is_indexed {
                 let is_json = field_entry.field_type().value_type() == Type::Json;
                 if is_json {
+                    let term_dictionary_json_field_num_bytes: u64 = self
+                        .termdict_composite
+                        .open_read(field)
+                        .map(|file_slice| file_slice.len() as u64)
+                        .unwrap_or(0u64);
                     let inv_index = self.inverted_index(field)?;
-                    let encoded_fields_in_index = inv_index.list_encoded_fields()?;
+                    let encoded_fields_in_index = inv_index.list_encoded_json_fields()?;
                     let mut build_path = |field_name: &str, mut json_path: String| {
                         // In this case we need to map the potential fast field to the field name
                         // accepted by the query parser.
@@ -328,30 +332,65 @@ impl SegmentReader {
                             format!("{field_name}.{json_path}")
                         }
                     };
-                    indexed_fields.extend(
-                        encoded_fields_in_index
-                            .into_iter()
-                            .map(|(name, typ)| (build_path(&field_name, name), typ))
-                            .map(|(field_name, typ)| FieldMetadata {
-                                indexed: true,
-                                stored: false,
-                                field_name,
-                                fast: false,
-                                typ,
-                            }),
-                    );
+                    let total_num_terms = encoded_fields_in_index
+                        .iter()
+                        .map(|field_space| field_space.num_terms)
+                        .sum();
+                    indexed_fields.extend(encoded_fields_in_index.into_iter().map(|field_space| {
+                        let field_name = build_path(&field_name, field_space.field_name);
+                        // It is complex to attribute the exact amount of bytes required by specific
+                        // field in the json field. Instead, as a proxy, we
+                        // attribute the total amount of bytes for the entire json field,
+                        // proportionally to the number of terms in each
+                        // fields.
+                        let term_dictionary_size = (term_dictionary_json_field_num_bytes
+                            * field_space.num_terms)
+                            .checked_div(total_num_terms)
+                            .unwrap_or(0);
+                        FieldMetadata {
+                            postings_size: Some(field_space.postings_size),
+                            positions_size: Some(field_space.positions_size),
+                            term_dictionary_size: Some(ByteCount::from(term_dictionary_size)),
+                            fast_size: None,
+                            // The stored flag will be set at the end of this function!
+                            stored: field_entry.is_stored(),
+                            field_name,
+                            typ: field_space.field_type,
+                        }
+                    }));
                 } else {
+                    let postings_size: ByteCount = self
+                        .postings_composite
+                        .open_read(field)
+                        .map(|posting_fileslice| posting_fileslice.len())
+                        .unwrap_or(0)
+                        .into();
+                    let positions_size: ByteCount = self
+                        .positions_composite
+                        .open_read(field)
+                        .map(|positions_fileslice| positions_fileslice.len())
+                        .unwrap_or(0)
+                        .into();
+                    let term_dictionary_size: ByteCount = self
+                        .termdict_composite
+                        .open_read(field)
+                        .map(|term_dictionary_fileslice| term_dictionary_fileslice.len())
+                        .unwrap_or(0)
+                        .into();
                     indexed_fields.push(FieldMetadata {
-                        indexed: true,
-                        stored: false,
                         field_name: field_name.to_string(),
-                        fast: false,
                         typ: field_entry.field_type().value_type(),
+                        // The stored flag will be set at the end of this function!
+                        stored: field_entry.is_stored(),
+                        fast_size: None,
+                        term_dictionary_size: Some(term_dictionary_size),
+                        postings_size: Some(postings_size),
+                        positions_size: Some(positions_size),
                     });
                 }
             }
         }
-        let mut fast_fields: Vec<FieldMetadata> = self
+        let fast_fields: Vec<FieldMetadata> = self
             .fast_fields()
             .columnar()
             .iter_columns()?
@@ -363,23 +402,21 @@ impl SegmentReader {
                     .get(&field_name)
                     .unwrap_or(&field_name)
                     .to_string();
+                let stored = is_field_stored(&field_name, &self.schema);
                 FieldMetadata {
-                    indexed: false,
-                    stored: false,
                     field_name,
-                    fast: true,
                     typ: Type::from(handle.column_type()),
+                    stored,
+                    fast_size: Some(handle.num_bytes()),
+                    term_dictionary_size: None,
+                    postings_size: None,
+                    positions_size: None,
                 }
             })
             .collect();
-        // Since the type is encoded differently in the fast field and in the inverted index,
-        // the order of the fields is not guaranteed to be the same. Therefore, we sort the fields.
-        // If we are sure that the order is the same, we can remove this sort.
-        indexed_fields.sort_unstable();
-        fast_fields.sort_unstable();
-        let merged = merge_field_meta_data(vec![indexed_fields, fast_fields], &self.schema);
-
-        Ok(merged)
+        let merged_field_metadatas: Vec<FieldMetadata> =
+            merge_field_meta_data(vec![indexed_fields, fast_fields]);
+        Ok(merged_field_metadatas)
     }
 
     /// Returns the segment id
@@ -443,20 +480,47 @@ pub struct FieldMetadata {
     // Notice: Don't reorder the declaration of 1.field_name 2.typ, as it is used for ordering by
     // field_name then typ.
     pub typ: Type,
-    /// Is the field indexed for search
-    pub indexed: bool,
     /// Is the field stored in the doc store
     pub stored: bool,
-    /// Is the field stored in the columnar storage
-    pub fast: bool,
+    /// Size occupied in the columnar storage (None if not fast)
+    pub fast_size: Option<ByteCount>,
+    /// term_dictionary
+    pub term_dictionary_size: Option<ByteCount>,
+    /// Size occupied in the index postings storage (None if not indexed)
+    pub postings_size: Option<ByteCount>,
+    /// Size occupied in the index postings storage (None if positions are not recorded)
+    pub positions_size: Option<ByteCount>,
 }
-impl BitOrAssign for FieldMetadata {
-    fn bitor_assign(&mut self, rhs: Self) {
-        assert!(self.field_name == rhs.field_name);
-        assert!(self.typ == rhs.typ);
-        self.indexed |= rhs.indexed;
+
+fn merge_options(left: Option<ByteCount>, right: Option<ByteCount>) -> Option<ByteCount> {
+    match (left, right) {
+        (Some(l), Some(r)) => Some(l + r),
+        (None, right) => right,
+        (left, None) => left,
+    }
+}
+
+impl FieldMetadata {
+    /// Returns true if and only if the field is indexed.
+    pub fn is_indexed(&self) -> bool {
+        self.postings_size.is_some()
+    }
+
+    /// Returns true if and only if the field is a fast field (i.e.: recorded in  columnar format).
+    pub fn is_fast(&self) -> bool {
+        self.fast_size.is_some()
+    }
+
+    /// Merges two field metadata.
+    pub fn merge(&mut self, rhs: Self) {
+        assert_eq!(self.field_name, rhs.field_name);
+        assert_eq!(self.typ, rhs.typ);
         self.stored |= rhs.stored;
-        self.fast |= rhs.fast;
+        self.fast_size = merge_options(self.fast_size, rhs.fast_size);
+        self.term_dictionary_size =
+            merge_options(self.term_dictionary_size, rhs.term_dictionary_size);
+        self.postings_size = merge_options(self.postings_size, rhs.postings_size);
+        self.positions_size = merge_options(self.positions_size, rhs.positions_size);
     }
 }
 
@@ -469,23 +533,29 @@ fn is_field_stored(field_name: &str, schema: &Schema) -> bool {
 }
 
 /// Helper to merge the field metadata from multiple segments.
-pub fn merge_field_meta_data(
-    field_metadatas: Vec<Vec<FieldMetadata>>,
-    schema: &Schema,
-) -> Vec<FieldMetadata> {
+pub fn merge_field_meta_data(mut field_metadatas: Vec<Vec<FieldMetadata>>) -> Vec<FieldMetadata> {
+    // READ BEFORE REMOVING THIS!
+    //
+    // Because we replace field sep by `.`, fields are not always sorted.
+    // Also, to enforce such an implicit contract, we would have to add
+    // assert here.
+    //
+    // Sorting is linear time on pre-sorted data, so we are simply better off sorting data here.
+    for field_metadatas in &mut field_metadatas {
+        field_metadatas.sort_unstable();
+    }
     let mut merged_field_metadata = Vec::new();
     for (_key, mut group) in &field_metadatas
         .into_iter()
-        .kmerge_by(|left, right| left < right)
+        .kmerge()
         // TODO: Remove allocation
         .chunk_by(|el| (el.field_name.to_string(), el.typ))
     {
         let mut merged: FieldMetadata = group.next().unwrap();
         for el in group {
-            merged |= el;
+            merged.merge(el);
         }
         // Currently is_field_stored is maybe too slow for the high cardinality case
-        merged.stored = is_field_stored(&merged.field_name, schema);
         merged_field_metadata.push(merged);
     }
     merged_field_metadata
@@ -507,7 +577,7 @@ fn intersect_alive_bitset(
 }
 
 impl fmt::Debug for SegmentReader {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         write!(f, "SegmentReader({:?})", self.segment_id)
     }
 }
@@ -516,122 +586,168 @@ impl fmt::Debug for SegmentReader {
 mod test {
     use super::*;
     use crate::index::Index;
-    use crate::schema::{SchemaBuilder, Term, STORED, TEXT};
+    use crate::schema::{Term, STORED, TEXT};
     use crate::IndexWriter;
 
+    #[track_caller]
+    fn assert_merge(fields_metadatas: &[Vec<FieldMetadata>], expected: &[FieldMetadata]) {
+        use itertools::Itertools;
+        let num_els = fields_metadatas.len();
+        for permutation in fields_metadatas.iter().cloned().permutations(num_els) {
+            let res = merge_field_meta_data(permutation);
+            assert_eq!(&res, &expected);
+        }
+    }
+
     #[test]
-    fn test_merge_field_meta_data_same() {
-        let schema = SchemaBuilder::new().build();
+    fn test_merge_field_meta_data_same_field() {
         let field_metadata1 = FieldMetadata {
             field_name: "a".to_string(),
             typ: crate::schema::Type::Str,
-            indexed: true,
             stored: false,
-            fast: true,
+            term_dictionary_size: Some(ByteCount::from(100u64)),
+            postings_size: Some(ByteCount::from(1_000u64)),
+            positions_size: Some(ByteCount::from(2_000u64)),
+            fast_size: Some(ByteCount::from(1_000u64).into()),
         };
         let field_metadata2 = FieldMetadata {
             field_name: "a".to_string(),
             typ: crate::schema::Type::Str,
-            indexed: true,
             stored: false,
-            fast: true,
+            term_dictionary_size: Some(ByteCount::from(80u64)),
+            postings_size: Some(ByteCount::from(1_500u64)),
+            positions_size: Some(ByteCount::from(2_500u64)),
+            fast_size: Some(ByteCount::from(3_000u64).into()),
         };
-        let res = merge_field_meta_data(
-            vec![vec![field_metadata1.clone()], vec![field_metadata2]],
-            &schema,
+        let expected = FieldMetadata {
+            field_name: "a".to_string(),
+            typ: crate::schema::Type::Str,
+            stored: false,
+            term_dictionary_size: Some(ByteCount::from(180u64)),
+            postings_size: Some(ByteCount::from(2_500u64)),
+            positions_size: Some(ByteCount::from(4_500u64)),
+            fast_size: Some(ByteCount::from(4_000u64).into()),
+        };
+        assert_merge(
+            &[vec![field_metadata1.clone()], vec![field_metadata2]],
+            &[expected],
         );
-        assert_eq!(res, vec![field_metadata1]);
     }
+
+    #[track_caller]
     #[test]
     fn test_merge_field_meta_data_different() {
-        let schema = SchemaBuilder::new().build();
         let field_metadata1 = FieldMetadata {
             field_name: "a".to_string(),
             typ: crate::schema::Type::Str,
-            indexed: false,
             stored: false,
-            fast: true,
+            fast_size: Some(1_000u64.into()),
+            term_dictionary_size: Some(100u64.into()),
+            postings_size: Some(2_000u64.into()),
+            positions_size: Some(4_000u64.into()),
         };
         let field_metadata2 = FieldMetadata {
             field_name: "b".to_string(),
             typ: crate::schema::Type::Str,
-            indexed: false,
             stored: false,
-            fast: true,
+            fast_size: Some(1_002u64.into()),
+            term_dictionary_size: None,
+            postings_size: None,
+            positions_size: None,
         };
         let field_metadata3 = FieldMetadata {
             field_name: "a".to_string(),
             typ: crate::schema::Type::Str,
-            indexed: true,
+            term_dictionary_size: Some(101u64.into()),
+            postings_size: Some(2_001u64.into()),
+            positions_size: Some(4_001u64.into()),
             stored: false,
-            fast: false,
+            fast_size: None,
         };
-        let res = merge_field_meta_data(
-            vec![
+        let expected = vec![
+            FieldMetadata {
+                field_name: "a".to_string(),
+                typ: crate::schema::Type::Str,
+                stored: false,
+                term_dictionary_size: Some(201u64.into()),
+                postings_size: Some(4_001u64.into()),
+                positions_size: Some(8_001u64.into()),
+                fast_size: Some(1_000u64.into()),
+            },
+            FieldMetadata {
+                field_name: "b".to_string(),
+                typ: crate::schema::Type::Str,
+                stored: false,
+                term_dictionary_size: None,
+                postings_size: None,
+                positions_size: None,
+                fast_size: Some(1_002u64.into()),
+            },
+        ];
+        assert_merge(
+            &[
                 vec![field_metadata1.clone(), field_metadata2.clone()],
                 vec![field_metadata3],
             ],
-            &schema,
+            &expected,
         );
-        let field_metadata_expected1 = FieldMetadata {
-            field_name: "a".to_string(),
-            typ: crate::schema::Type::Str,
-            indexed: true,
-            stored: false,
-            fast: true,
-        };
-        assert_eq!(res, vec![field_metadata_expected1, field_metadata2.clone()]);
     }
+
     #[test]
     fn test_merge_field_meta_data_merge() {
-        use pretty_assertions::assert_eq;
         let get_meta_data = |name: &str, typ: Type| FieldMetadata {
             field_name: name.to_string(),
             typ,
-            indexed: false,
+            term_dictionary_size: None,
+            postings_size: None,
+            positions_size: None,
             stored: false,
-            fast: true,
+            fast_size: Some(1u64.into()),
         };
-        let schema = SchemaBuilder::new().build();
-        let mut metas = vec![get_meta_data("d", Type::Str), get_meta_data("e", Type::U64)];
-        metas.sort();
-        let res = merge_field_meta_data(vec![vec![get_meta_data("e", Type::Str)], metas], &schema);
-        assert_eq!(
-            res,
-            vec![
+        let metas = vec![get_meta_data("d", Type::Str), get_meta_data("e", Type::U64)];
+        assert_merge(
+            &[vec![get_meta_data("e", Type::Str)], metas],
+            &[
                 get_meta_data("d", Type::Str),
                 get_meta_data("e", Type::Str),
                 get_meta_data("e", Type::U64),
-            ]
+            ],
         );
     }
+
     #[test]
     fn test_merge_field_meta_data_bitxor() {
         let field_metadata1 = FieldMetadata {
             field_name: "a".to_string(),
             typ: crate::schema::Type::Str,
-            indexed: false,
+            term_dictionary_size: None,
+            postings_size: None,
+            positions_size: None,
             stored: false,
-            fast: true,
+            fast_size: Some(10u64.into()),
         };
         let field_metadata2 = FieldMetadata {
             field_name: "a".to_string(),
             typ: crate::schema::Type::Str,
-            indexed: true,
+            term_dictionary_size: Some(10u64.into()),
+            postings_size: Some(11u64.into()),
+            positions_size: Some(12u64.into()),
             stored: false,
-            fast: false,
+            fast_size: None,
         };
         let field_metadata_expected = FieldMetadata {
             field_name: "a".to_string(),
             typ: crate::schema::Type::Str,
-            indexed: true,
+            term_dictionary_size: Some(10u64.into()),
+            postings_size: Some(11u64.into()),
+            positions_size: Some(12u64.into()),
             stored: false,
-            fast: true,
+            fast_size: Some(10u64.into()),
         };
         let mut res1 = field_metadata1.clone();
-        res1 |= field_metadata2.clone();
+        res1.merge(field_metadata2.clone());
         let mut res2 = field_metadata2.clone();
-        res2 |= field_metadata1;
+        res2.merge(field_metadata1);
         assert_eq!(res1, field_metadata_expected);
         assert_eq!(res2, field_metadata_expected);
     }
@@ -662,6 +778,7 @@ mod test {
         assert_eq!(4, searcher.segment_reader(0).max_doc());
         Ok(())
     }
+
     #[test]
     fn test_alive_docs_iterator() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();

src/indexer/index_writer.rs

@@ -370,7 +370,7 @@ impl<D: Document> IndexWriter<D> {
             .map_err(|_| error_in_index_worker_thread("Failed to join merging thread."));
 
         if let Err(ref e) = result {
-            error!("Some merging thread failed {:?}", e);
+            error!("Some merging thread failed {e:?}");
         }
 
         result
@@ -644,7 +644,7 @@ impl<D: Document> IndexWriter<D> {
 
         let commit_opstamp = self.stamper.stamp();
         let prepared_commit = PreparedCommit::new(self, commit_opstamp);
-        info!("Prepared commit {}", commit_opstamp);
+        info!("Prepared commit {commit_opstamp}");
         Ok(prepared_commit)
     }
 

src/indexer/mod.rs

@@ -61,6 +61,8 @@ type AddBatchReceiver<D> = channel::Receiver<AddBatch<D>>;
 #[cfg(test)]
 mod tests_mmap {
 
+    use common::ByteCount;
+
     use crate::aggregation::agg_req::Aggregations;
     use crate::aggregation::agg_result::AggregationResults;
     use crate::aggregation::AggregationCollector;
@@ -280,11 +282,14 @@ mod tests_mmap {
             field_name_out
         };
 
-        let mut fields = reader.searcher().segment_readers()[0]
+        let mut fields: Vec<(String, Type)> = reader.searcher().segment_readers()[0]
             .inverted_index(field)
             .unwrap()
-            .list_encoded_fields()
-            .unwrap();
+            .list_encoded_json_fields()
+            .unwrap()
+            .into_iter()
+            .map(|field_space| (field_space.field_name, field_space.field_type))
+            .collect();
         assert_eq!(fields.len(), 8);
         fields.sort();
         let mut expected_fields = vec![
@@ -385,7 +390,12 @@ mod tests_mmap {
         let reader = &searcher.segment_readers()[0];
         let inverted_index = reader.inverted_index(json_field).unwrap();
         assert_eq!(
-            inverted_index.list_encoded_fields().unwrap(),
+            inverted_index
+                .list_encoded_json_fields()
+                .unwrap()
+                .into_iter()
+                .map(|field_space| (field_space.field_name, field_space.field_type))
+                .collect::<Vec<_>>(),
             [
                 ("k8s.container.name".to_string(), Type::Str),
                 ("sub\u{1}a".to_string(), Type::I64),
@@ -402,19 +412,41 @@ mod tests_mmap {
     fn test_json_fields_metadata_expanded_dots_one_segment() {
         test_json_fields_metadata(true, true);
     }
+
     #[test]
     fn test_json_fields_metadata_expanded_dots_multi_segment() {
         test_json_fields_metadata(true, false);
     }
+
     #[test]
     fn test_json_fields_metadata_no_expanded_dots_one_segment() {
         test_json_fields_metadata(false, true);
     }
+
     #[test]
     fn test_json_fields_metadata_no_expanded_dots_multi_segment() {
         test_json_fields_metadata(false, false);
     }
 
+    #[track_caller]
+    fn assert_size_eq(lhs: Option<ByteCount>, rhs: Option<ByteCount>) {
+        let ignore_actual_values = |size_opt: Option<ByteCount>| size_opt.map(|val| val > 0);
+        assert_eq!(ignore_actual_values(lhs), ignore_actual_values(rhs));
+    }
+
+    #[track_caller]
+    fn assert_field_metadata_eq_but_ignore_field_size(
+        expected: &FieldMetadata,
+        actual: &FieldMetadata,
+    ) {
+        assert_eq!(&expected.field_name, &actual.field_name);
+        assert_eq!(&expected.typ, &actual.typ);
+        assert_eq!(&expected.stored, &actual.stored);
+        assert_size_eq(expected.postings_size, actual.postings_size);
+        assert_size_eq(expected.positions_size, actual.positions_size);
+        assert_size_eq(expected.fast_size, actual.fast_size);
+    }
+
     fn test_json_fields_metadata(expanded_dots: bool, one_segment: bool) {
         use pretty_assertions::assert_eq;
         let mut schema_builder = Schema::builder();
@@ -453,81 +485,101 @@ mod tests_mmap {
         assert_eq!(searcher.num_docs(), 3);
 
         let fields_metadata = index.fields_metadata().unwrap();
-        assert_eq!(
-            fields_metadata,
-            [
-                FieldMetadata {
-                    field_name: "empty".to_string(),
-                    indexed: true,
-                    stored: true,
-                    fast: true,
-                    typ: Type::U64
+
+        let expected_fields = &[
+            FieldMetadata {
+                field_name: "empty".to_string(),
+                stored: true,
+                typ: Type::U64,
+                term_dictionary_size: Some(0u64.into()),
+                fast_size: Some(1u64.into()),
+                postings_size: Some(0u64.into()),
+                positions_size: Some(0u64.into()),
+            },
+            FieldMetadata {
+                field_name: if expanded_dots {
+                    "json.shadow.k8s.container.name".to_string()
+                } else {
+                    "json.shadow.k8s\\.container\\.name".to_string()
                 },
-                FieldMetadata {
-                    field_name: if expanded_dots {
-                        "json.shadow.k8s.container.name".to_string()
-                    } else {
-                        "json.shadow.k8s\\.container\\.name".to_string()
-                    },
-                    indexed: true,
-                    stored: true,
-                    fast: true,
-                    typ: Type::Str
-                },
-                FieldMetadata {
-                    field_name: "json.shadow.sub.a".to_string(),
-                    indexed: true,
-                    stored: true,
-                    fast: true,
-                    typ: Type::I64
-                },
-                FieldMetadata {
-                    field_name: "json.shadow.sub.b".to_string(),
-                    indexed: true,
-                    stored: true,
-                    fast: true,
-                    typ: Type::I64
-                },
-                FieldMetadata {
-                    field_name: "json.shadow.suber.a".to_string(),
-                    indexed: true,
-                    stored: true,
-                    fast: true,
-                    typ: Type::I64
-                },
-                FieldMetadata {
-                    field_name: "json.shadow.suber.a".to_string(),
-                    indexed: true,
-                    stored: true,
-                    fast: true,
-                    typ: Type::Str
-                },
-                FieldMetadata {
-                    field_name: "json.shadow.suber.b".to_string(),
-                    indexed: true,
-                    stored: true,
-                    fast: true,
-                    typ: Type::I64
-                },
-                FieldMetadata {
-                    field_name: "json.shadow.val".to_string(),
-                    indexed: true,
-                    stored: true,
-                    fast: true,
-                    typ: Type::Str
-                },
-                FieldMetadata {
-                    field_name: "numbers".to_string(),
-                    indexed: false,
-                    stored: false,
-                    fast: true,
-                    typ: Type::U64
-                }
-            ]
-        );
+                stored: true,
+                typ: Type::Str,
+                term_dictionary_size: Some(1u64.into()),
+                fast_size: Some(1u64.into()),
+                postings_size: Some(1u64.into()),
+                positions_size: Some(1u64.into()),
+            },
+            FieldMetadata {
+                field_name: "json.shadow.sub.a".to_string(),
+                typ: Type::I64,
+                stored: true,
+                fast_size: Some(1u64.into()),
+                term_dictionary_size: Some(1u64.into()),
+                postings_size: Some(1u64.into()),
+                positions_size: Some(1u64.into()),
+            },
+            FieldMetadata {
+                field_name: "json.shadow.sub.b".to_string(),
+                typ: Type::I64,
+                stored: true,
+                fast_size: Some(1u64.into()),
+                term_dictionary_size: Some(1u64.into()),
+                postings_size: Some(1u64.into()),
+                positions_size: Some(1u64.into()),
+            },
+            FieldMetadata {
+                field_name: "json.shadow.suber.a".to_string(),
+                stored: true,
+                typ: Type::I64,
+                fast_size: Some(1u64.into()),
+                term_dictionary_size: Some(1u64.into()),
+                postings_size: Some(1u64.into()),
+                positions_size: Some(1u64.into()),
+            },
+            FieldMetadata {
+                field_name: "json.shadow.suber.a".to_string(),
+                typ: Type::Str,
+                stored: true,
+                fast_size: Some(1u64.into()),
+                term_dictionary_size: Some(1u64.into()),
+                postings_size: Some(1u64.into()),
+                positions_size: Some(1u64.into()),
+            },
+            FieldMetadata {
+                field_name: "json.shadow.suber.b".to_string(),
+                typ: Type::I64,
+                stored: true,
+                fast_size: Some(1u64.into()),
+                term_dictionary_size: Some(1u64.into()),
+                postings_size: Some(1u64.into()),
+                positions_size: Some(1u64.into()),
+            },
+            FieldMetadata {
+                field_name: "json.shadow.val".to_string(),
+                typ: Type::Str,
+                stored: true,
+                fast_size: Some(1u64.into()),
+                term_dictionary_size: Some(1u64.into()),
+                postings_size: Some(1u64.into()),
+                positions_size: Some(1u64.into()),
+            },
+            FieldMetadata {
+                field_name: "numbers".to_string(),
+                stored: false,
+                typ: Type::U64,
+                fast_size: Some(1u64.into()),
+                term_dictionary_size: None,
+                postings_size: None,
+                positions_size: None,
+            },
+        ];
+        assert_eq!(fields_metadata.len(), expected_fields.len());
+        for (expected, value) in expected_fields.iter().zip(fields_metadata.iter()) {
+            assert_field_metadata_eq_but_ignore_field_size(expected, value);
+        }
         let query_parser = QueryParser::for_index(&index, vec![]);
         // Test if returned field name can be queried
-        for indexed_field in fields_metadata.iter().filter(|meta| meta.indexed) {
+        for indexed_field in fields_metadata.iter().filter(|meta| meta.is_indexed()) {
             let val = if indexed_field.typ == Type::Str {
                 "a"
             } else {
@@ -543,7 +595,10 @@ mod tests_mmap {
             }
         }
         // Test if returned field name can be used for aggregation
-        for fast_field in fields_metadata.iter().filter(|meta| meta.fast) {
+        for fast_field in fields_metadata
+            .iter()
+            .filter(|field_metadata| field_metadata.is_fast())
+        {
             let agg_req_str = json!(
             {
               "termagg": {

src/indexer/segment_updater.rs

@@ -501,8 +501,7 @@ impl SegmentUpdater {
             Ok(segment_entries) => segment_entries,
             Err(err) => {
                 warn!(
-                    "Starting the merge failed for the following reason. This is not fatal. {}",
-                    err
+                    "Starting the merge failed for the following reason. This is not fatal. {err}"
                 );
                 return err.into();
             }

src/indexer/segment_writer.rs

@@ -873,8 +873,8 @@ mod tests {
 
         fn assert_type(reader: &SegmentReader, field: &str, typ: ColumnType) {
             let cols = reader.fast_fields().dynamic_column_handles(field).unwrap();
-            assert_eq!(cols.len(), 1, "{}", field);
-            assert_eq!(cols[0].column_type(), typ, "{}", field);
+            assert_eq!(cols.len(), 1, "{field}");
+            assert_eq!(cols[0].column_type(), typ, "{field}");
         }
         assert_type(segment_reader, "json.toto", ColumnType::Str);
         assert_type(segment_reader, "json.float", ColumnType::F64);

src/lib.rs

@@ -165,7 +165,7 @@ mod macros;
 mod future_result;
 
 // Re-exports
-pub use common::DateTime;
+pub use common::{ByteCount, DateTime};
 pub use {columnar, query_grammar, time};
 
 pub use crate::error::TantivyError;

src/positions/mod.rs

@@ -206,7 +206,7 @@ pub(crate) mod tests {
     #[test]
     fn test_position() -> crate::Result<()> {
         const CONST_VAL: u32 = 9u32;
-        let positions_delta: Vec<u32> = iter::repeat(CONST_VAL).take(2_000_000).collect();
+        let positions_delta: Vec<u32> = std::iter::repeat_n(CONST_VAL, 2_000_000).collect();
         let positions_data = create_positions_data(&positions_delta[..])?;
         assert_eq!(positions_data.len(), 1_015_627);
         let mut position_reader = PositionReader::open(positions_data)?;

src/query/boolean_query/block_wand.rs

@@ -436,7 +436,7 @@ mod tests {
         let fieldnorms_expanded = fieldnorms
             .iter()
             .cloned()
-            .flat_map(|fieldnorm| iter::repeat(fieldnorm).take(REPEAT))
+            .flat_map(|fieldnorm| std::iter::repeat_n(fieldnorm, REPEAT))
             .collect::<Vec<u32>>();
 
         let postings_lists_expanded: Vec<Vec<(DocId, u32)>> = posting_lists

src/query/boolean_query/boolean_query.rs

@@ -180,7 +180,7 @@ impl BooleanQuery {
     pub fn new(subqueries: Vec<(Occur, Box<dyn Query>)>) -> BooleanQuery {
         // If the bool query includes at least one should clause
         // and no Must or MustNot clauses, the default value is 1. Otherwise, the default value is
-        // 0. Keep pace with Elasticsearch.
+        // 0. Keep compatible with Elasticsearch.
         let mut minimum_required = 0;
         for (occur, _) in &subqueries {
             match occur {

src/query/boolean_query/boolean_weight.rs

@@ -157,8 +157,7 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
             Ignored,
             // Only contributes to final score.
             Optional(SpecializedScorer),
-            // Must be fitted.
-            Required(Box<dyn Scorer>),
+            Required(SpecializedScorer),
         }
         let mut must_scorers = per_occur_scorers.remove(&Occur::Must);
         let should_opt = if let Some(mut should_scorers) = per_occur_scorers.remove(&Occur::Should)
@@ -169,10 +168,10 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
             }
             match self.minimum_number_should_match {
                 0 => CombinationMethod::Optional(scorer_union(should_scorers, &score_combiner_fn)),
-                1 => CombinationMethod::Required(into_box_scorer(
-                    scorer_union(should_scorers, &score_combiner_fn),
-                    &score_combiner_fn,
-                )),
+                1 => {
+                    let scorer_union = scorer_union(should_scorers, &score_combiner_fn);
+                    CombinationMethod::Required(scorer_union)
+                }
                 n if num_of_should_scorers == n => {
                     // When num_of_should_scorers equals the number of should clauses,
                     // they are no different from must clauses.
@@ -185,11 +184,11 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
                     };
                     CombinationMethod::Ignored
                 }
-                _ => CombinationMethod::Required(scorer_disjunction(
+                _ => CombinationMethod::Required(SpecializedScorer::Other(scorer_disjunction(
                     should_scorers,
                     score_combiner_fn(),
                     self.minimum_number_should_match,
-                )),
+                ))),
             }
         } else {
             // None of should clauses are provided.
@@ -223,15 +222,13 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
                 }
             }
             (CombinationMethod::Required(should_scorer), Some(mut must_scorers)) => {
-                must_scorers.push(should_scorer);
+                must_scorers.push(into_box_scorer(should_scorer, &score_combiner_fn));
                 SpecializedScorer::Other(intersect_scorers(must_scorers))
             }
             (CombinationMethod::Ignored, None) => {
                 return Ok(SpecializedScorer::Other(Box::new(EmptyScorer)))
             }
-            (CombinationMethod::Required(should_scorer), None) => {
-                SpecializedScorer::Other(should_scorer)
-            }
+            (CombinationMethod::Required(should_scorer), None) => should_scorer,
             // Optional options are promoted to required if no must scorers exists.
             (CombinationMethod::Optional(should_scorer), None) => should_scorer,
         };

src/query/exist_query.rs

@@ -384,7 +384,7 @@ mod tests {
                 .search(&ExistsQuery::new(field.to_string(), json_subpaths), &Count)
                 .unwrap_err()
                 .to_string(),
-            format!("The field does not exist: '{}'", field)
+            format!("The field does not exist: '{field}'")
         );
     }
 }

src/query/phrase_query/regex_phrase_query.rs

@@ -124,8 +124,7 @@ impl RegexPhraseQuery {
         if field_type != Type::Str {
             return Err(crate::TantivyError::SchemaError(format!(
                 "RegexPhraseQuery can only be used with a field of type text currently, but got \
-                 {:?}",
-                field_type
+                 {field_type:?}"
             )));
         }
 

src/query/phrase_query/regex_phrase_weight.rs

@@ -81,8 +81,7 @@ impl RegexPhraseWeight {
             num_terms += term_infos.len();
             if num_terms > self.max_expansions as usize {
                 return Err(crate::TantivyError::InvalidArgument(format!(
-                    "Phrase query exceeded max expansions {}",
-                    num_terms
+                    "Phrase query exceeded max expansions {num_terms}"
                 )));
             }
             let union = Self::get_union_from_term_infos(&term_infos, reader, &inverted_index)?;

src/query/query_parser/query_parser.rs

@@ -778,6 +778,12 @@ impl QueryParser {
                         asts.push(LogicalAst::Leaf(Box::new(ast)).boost(boost));
                     }
                 }
+                if !asts.is_empty() {
+                    // if some fields failed but other succeeded, we consider this a success, it
+                    // probably means the default_fields contains
+                    // text and non-text fields, and the non-text ones failed
+                    errors.clear();
+                }
                 let result_ast: LogicalAst = if asts.len() == 1 {
                     asts.into_iter().next().unwrap()
                 } else {
@@ -1090,25 +1096,58 @@ mod test {
         make_query_parser_with_default_fields(&["title", "text"])
     }
 
-    fn parse_query_to_logical_ast(
+    fn parse_query_to_logical_ast_with_default_fields(
         query: &str,
         default_conjunction: bool,
+        default_fields: &[&'static str],
     ) -> Result<LogicalAst, QueryParserError> {
-        let mut query_parser = make_query_parser();
+        let mut query_parser = make_query_parser_with_default_fields(default_fields);
         if default_conjunction {
             query_parser.set_conjunction_by_default();
         }
         query_parser.parse_query_to_logical_ast(query)
     }
 
+    fn parse_query_to_logical_ast(
+        query: &str,
+        default_conjunction: bool,
+    ) -> Result<LogicalAst, QueryParserError> {
+        parse_query_to_logical_ast_with_default_fields(
+            query,
+            default_conjunction,
+            &["title", "text"],
+        )
+    }
+
+    #[track_caller]
+    fn test_parse_query_to_logical_ast_helper_with_default_fields(
+        query: &str,
+        expected: &str,
+        default_conjunction: bool,
+        default_fields: &[&'static str],
+    ) {
+        let query = parse_query_to_logical_ast_with_default_fields(
+            query,
+            default_conjunction,
+            default_fields,
+        )
+        .unwrap();
+        let query_str = format!("{query:?}");
+        assert_eq!(query_str, expected);
+    }
+
+    #[track_caller]
     fn test_parse_query_to_logical_ast_helper(
         query: &str,
         expected: &str,
         default_conjunction: bool,
     ) {
-        let query = parse_query_to_logical_ast(query, default_conjunction).unwrap();
-        let query_str = format!("{query:?}");
-        assert_eq!(query_str, expected);
+        test_parse_query_to_logical_ast_helper_with_default_fields(
+            query,
+            expected,
+            default_conjunction,
+            &["title", "text"],
+        )
     }
 
     #[test]
@@ -1751,6 +1790,15 @@ mod test {
         }
     }
 
+    #[test]
+    fn test_space_before_value() {
+        test_parse_query_to_logical_ast_helper(
+            "title: a",
+            r#"Term(field=0, type=Str, "a")"#,
+            false,
+        );
+    }
+
     #[test]
     fn test_escaped_field() {
         let mut schema_builder = Schema::builder();
@@ -1922,4 +1970,27 @@ mod test {
             );
         }
     }
+
+    #[test]
+    pub fn test_set_default_field_integer() {
+        test_parse_query_to_logical_ast_helper_with_default_fields(
+            "2324",
+            "(Term(field=0, type=Str, \"2324\") Term(field=2, type=I64, 2324))",
+            false,
+            &["title", "signed"],
+        );
+
+        test_parse_query_to_logical_ast_helper_with_default_fields(
+            "abc",
+            "Term(field=0, type=Str, \"abc\")",
+            false,
+            &["title", "signed"],
+        );
+
+        let query_parser = make_query_parser_with_default_fields(&["signed"]);
+        assert_matches!(
+            query_parser.parse_query("abc"),
+            Err(QueryParserError::ExpectedInt(_))
+        );
+    }
 }

src/query/range_query/range_query_fastfield.rs

@@ -177,8 +177,7 @@ impl Weight for FastFieldRangeWeight {
         } else {
             assert!(
                 maps_to_u64_fastfield(field_type.value_type()),
-                "{:?}",
-                field_type
+                "{field_type:?}"
             );
 
             let bounds = self.bounds.map_bound_res(|term| {
@@ -193,8 +192,7 @@ impl Weight for FastFieldRangeWeight {
                     val.to_u64()
                 } else {
                     return Err(TantivyError::InvalidArgument(format!(
-                        "Expected term with u64, i64, f64 or date, but got {:?}",
-                        term
+                        "Expected term with u64, i64, f64 or date, but got {term:?}"
                     )));
                 };
                 Ok(val)
@@ -254,12 +252,9 @@ fn search_on_json_numerical_field(
     else {
         return Ok(Box::new(EmptyScorer));
     };
-    let actual_column_type: NumericalType = col_type.numerical_type().unwrap_or_else(|| {
-        panic!(
-            "internal error: couldn't cast to numerical_type: {:?}",
-            col_type
-        )
-    });
+    let actual_column_type: NumericalType = col_type
+        .numerical_type()
+        .unwrap_or_else(|| panic!("internal error: couldn't cast to numerical_type: {col_type:?}"));
 
     let bounds = match typ.numerical_type().unwrap() {
         NumericalType::I64 => {
@@ -1058,7 +1053,7 @@ mod tests {
     fn doc_from_id_1(id: u64) -> Doc {
         let id = id * 1000;
         Doc {
-            id_name: format!("id_name{:010}", id),
+            id_name: format!("id_name{id:010}"),
             id,
         }
     }
@@ -1242,7 +1237,7 @@ mod tests {
 
         let field_path = |field: &str| {
             if json {
-                format!("json.{}", field)
+                format!("json.{field}")
             } else {
                 field.to_string()
             }

src/query/set_query.rs

@@ -52,7 +52,7 @@ impl TermSetQuery {
                     .iter()
                     .map(|key| (key.serialized_value_bytes(), 0)),
             )
-            .map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e))?;
+            .map_err(std::io::Error::other)?;
 
             sub_queries.push((
                 Occur::Should,

src/query/term_query/term_scorer.rs

@@ -172,7 +172,7 @@ mod tests {
             let doc = i * 10;
             doc_and_tfs.push((doc, 1u32 + doc % 3u32));
         }
-        let fieldnorms: Vec<u32> = std::iter::repeat(10u32).take(3_000).collect();
+        let fieldnorms: Vec<u32> = std::iter::repeat_n(10u32, 3_000).collect();
         let mut term_scorer = TermScorer::create_for_test(&doc_and_tfs, &fieldnorms, bm25_weight);
         assert_eq!(term_scorer.doc(), 0u32);
         term_scorer.shallow_seek(1289);
@@ -238,7 +238,7 @@ mod tests {
         doc_tfs.push((257, 3u32));
         doc_tfs.push((258, 1u32));
 
-        let fieldnorms: Vec<u32> = std::iter::repeat(20u32).take(300).collect();
+        let fieldnorms: Vec<u32> = std::iter::repeat_n(20u32, 300).collect();
         let bm25_weight = Bm25Weight::for_one_term(10, 129, 20.0);
         let mut docs = TermScorer::create_for_test(&doc_tfs[..], &fieldnorms[..], bm25_weight);
         assert_nearly_equals!(docs.block_max_score(), 2.5161593);
@@ -304,7 +304,7 @@ mod tests {
         writer.set_merge_policy(Box::new(NoMergePolicy));
         for _ in 0..3_000 {
             let term_freq = rng.gen_range(1..10000);
-            let words: Vec<&str> = std::iter::repeat("bbbb").take(term_freq).collect();
+            let words: Vec<&str> = std::iter::repeat_n("bbbb", term_freq).collect();
             let text = words.join(" ");
             writer.add_document(doc!(text_field=>text))?;
         }

src/reader/mod.rs

@@ -86,10 +86,7 @@ impl IndexReaderBuilder {
                 let inner_reader_arc_clone = inner_reader_arc.clone();
                 let callback = move || {
                     if let Err(err) = inner_reader_arc_clone.reload() {
-                        error!(
-                            "Error while loading searcher after commit was detected. {:?}",
-                            err
-                        );
+                        error!("Error while loading searcher after commit was detected. {err:?}");
                     }
                 };
                 let watch_handle = inner_reader_arc

src/reader/warming.rs

@@ -152,7 +152,7 @@ impl WarmingStateInner {
                 // rely on deterministic gc in tests
                 #[cfg(not(test))]
                 if let Err(err) = std::panic::catch_unwind(|| inner.lock().unwrap().gc_maybe()) {
-                    error!("Panic in Warmer GC {:?}", err);
+                    error!("Panic in Warmer GC {err:?}");
                 }
                 // avoid unused var warning in tests
                 #[cfg(test)]