SegmentReader as trait

A bug was added with the `seek_into_the_danger_zone()` optimization

(Spotted and fixed by Stu)

The contract says seek_into_the_danger_zone returns true if do is part of the docset.

The blanket implementation goes like this.

```
let current_doc = self.doc();
if current_doc < target {
     self.seek(target);
}
self.doc() == target
```

So it will return true if target is TERMINATED, where really TERMINATED does not belong to the docset.


The fix tries to clarify the contracts and fixes the intersection algorithm.
We observe a small but all over the board improvement in intersection performance.

---------

Co-authored-by: Stu Hood <stuhood@gmail.com>
Co-authored-by: Paul Masurel <paul.masurel@datadoghq.com>

.github/workflows/coverage.yml

@@ -15,11 +15,11 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Install Rust
-        run: rustup toolchain install nightly-2024-07-01 --profile minimal --component llvm-tools-preview
+        run: rustup toolchain install nightly-2025-12-01 --profile minimal --component llvm-tools-preview
       - uses: Swatinem/rust-cache@v2
       - uses: taiki-e/install-action@cargo-llvm-cov
       - name: Generate code coverage
-        run: cargo +nightly-2024-07-01 llvm-cov --all-features --workspace --doctests --lcov --output-path lcov.info
+        run: cargo +nightly-2025-12-01 llvm-cov --all-features --workspace --doctests --lcov --output-path lcov.info
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v3
         continue-on-error: true

.github/workflows/test.yml

@@ -39,11 +39,11 @@ jobs:
 
     - name: Check Formatting
       run: cargo +nightly fmt --all -- --check
-    
+
     - name: Check Stable Compilation
       run: cargo build --all-features
 
-    
+
     - name: Check Bench Compilation
       run: cargo +nightly bench --no-run --profile=dev --all-features
 
@@ -59,10 +59,10 @@ jobs:
 
     strategy:
       matrix:
-        features: [
-            { label: "all", flags: "mmap,stopwords,lz4-compression,zstd-compression,failpoints" },
-            { label: "quickwit", flags: "mmap,quickwit,failpoints" }
-        ]
+        features:
+          - { label: "all", flags: "mmap,stopwords,lz4-compression,zstd-compression,failpoints,stemmer" }
+          - { label: "quickwit", flags: "mmap,quickwit,failpoints" }
+          - { label: "none", flags: "" }
 
     name: test-${{ matrix.features.label}}
 
@@ -80,7 +80,21 @@ jobs:
     - uses: Swatinem/rust-cache@v2
 
     - name: Run tests
-      run: cargo +stable nextest run --features ${{ matrix.features.flags }} --verbose --workspace
+      run: |
+        # if matrix.feature.flags is empty then run on --lib to avoid compiling examples
+        # (as most of them rely on mmap) otherwise run all
+        if [ -z "${{ matrix.features.flags }}" ]; then
+          cargo +stable nextest run --lib --no-default-features --verbose --workspace
+        else
+          cargo +stable nextest run --features ${{ matrix.features.flags }} --no-default-features --verbose --workspace
+        fi
 
     - name: Run doctests
-      run: cargo +stable test --doc --features ${{ matrix.features.flags }} --verbose --workspace
+      run: |
+        # if matrix.feature.flags is empty then run on --lib to avoid compiling examples
+        # (as most of them rely on mmap) otherwise run all
+        if [ -z "${{ matrix.features.flags }}" ]; then
+          echo "no doctest for no feature flag"
+        else
+          cargo +stable test --doc --features ${{ matrix.features.flags }} --verbose --workspace
+        fi

Cargo.toml

@@ -27,7 +27,7 @@ regex = { version = "1.5.5", default-features = false, features = [
 aho-corasick = "1.0"
 tantivy-fst = "0.5"
 memmap2 = { version = "0.9.0", optional = true }
-lz4_flex = { version = "0.11", default-features = false, optional = true }
+lz4_flex = { version = "0.12", default-features = false, optional = true }
 zstd = { version = "0.13", optional = true, default-features = false }
 tempfile = { version = "3.12.0", optional = true }
 log = "0.4.16"
@@ -37,9 +37,9 @@ 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"
-rust-stemmers = "1.2.0"
+rust-stemmers = { version = "1.2.0", optional = true }
 downcast-rs = "2.0.1"
-bitpacking = { version = "0.9.2", default-features = false, features = [
+bitpacking = { version = "0.9.3", default-features = false, features = [
     "bitpacker4x",
 ] }
 census = "0.4.2"
@@ -50,7 +50,7 @@ fail = { version = "0.5.0", optional = true }
 time = { version = "0.3.35", features = ["serde-well-known"] }
 smallvec = "1.8.0"
 rayon = "1.5.2"
-lru = "0.12.0"
+lru = "0.16.3"
 fastdivide = "0.4.0"
 itertools = "0.14.0"
 measure_time = "0.9.0"
@@ -75,17 +75,17 @@ typetag = "0.2.21"
 winapi = "0.3.9"
 
 [dev-dependencies]
-binggan = "0.14.0"
-rand = "0.8.5"
+binggan = "0.14.2"
+rand = "0.9"
 maplit = "1.0.2"
 matches = "0.1.9"
 pretty_assertions = "1.2.1"
-proptest = "1.0.0"
+proptest = "1.7.0"
 test-log = "0.2.10"
 futures = "0.3.21"
 paste = "1.0.11"
 more-asserts = "0.3.1"
-rand_distr = "0.4.3"
+rand_distr = "0.5"
 time = { version = "0.3.10", features = ["serde-well-known", "macros"] }
 postcard = { version = "1.0.4", features = [
     "use-std",
@@ -113,7 +113,8 @@ debug-assertions = true
 overflow-checks = true
 
 [features]
-default = ["mmap", "stopwords", "lz4-compression", "columnar-zstd-compression"]
+default = ["mmap", "stopwords", "lz4-compression", "columnar-zstd-compression", "stemmer"]
+stemmer = ["rust-stemmers"]
 mmap = ["fs4", "tempfile", "memmap2"]
 stopwords = []
 
@@ -173,6 +174,22 @@ harness = false
 name = "exists_json"
 harness = false
 
+[[bench]]
+name = "range_query"
+harness = false
+
 [[bench]]
 name = "and_or_queries"
 harness = false
+
+[[bench]]
+name = "range_queries"
+harness = false
+
+[[bench]]
+name = "bool_queries_with_range"
+harness = false
+
+[[bench]]
+name = "str_search_and_get"
+harness = false

README.md

@@ -123,6 +123,7 @@ You can also find other bindings on [GitHub](https://github.com/search?q=tantivy
 - [seshat](https://github.com/matrix-org/seshat/): A matrix message database/indexer
 - [tantiny](https://github.com/baygeldin/tantiny): Tiny full-text search for Ruby
 - [lnx](https://github.com/lnx-search/lnx): adaptable, typo tolerant search engine with a REST API
+- [Bichon](https://github.com/rustmailer/bichon): A lightweight, high-performance Rust email archiver with WebUI
 - and [more](https://github.com/search?q=tantivy)!
 
 ### On average, how much faster is Tantivy compared to Lucene?

benches/agg_bench.rs

@@ -1,7 +1,8 @@
 use binggan::plugins::PeakMemAllocPlugin;
 use binggan::{black_box, InputGroup, PeakMemAlloc, INSTRUMENTED_SYSTEM};
-use rand::prelude::SliceRandom;
+use rand::distr::weighted::WeightedIndex;
 use rand::rngs::StdRng;
+use rand::seq::IndexedRandom;
 use rand::{Rng, SeedableRng};
 use rand_distr::Distribution;
 use serde_json::json;
@@ -53,27 +54,33 @@ fn bench_agg(mut group: InputGroup<Index>) {
     register!(group, stats_f64);
     register!(group, extendedstats_f64);
     register!(group, percentiles_f64);
-    register!(group, terms_few);
-    register!(group, terms_many);
+    register!(group, terms_7);
+    register!(group, terms_all_unique);
+    register!(group, terms_150_000);
     register!(group, terms_many_top_1000);
     register!(group, terms_many_order_by_term);
     register!(group, terms_many_with_top_hits);
+    register!(group, terms_all_unique_with_avg_sub_agg);
     register!(group, terms_many_with_avg_sub_agg);
-    register!(group, terms_few_with_avg_sub_agg);
+    register!(group, terms_status_with_avg_sub_agg);
+    register!(group, terms_status_with_histogram);
+    register!(group, terms_zipf_1000);
+    register!(group, terms_zipf_1000_with_histogram);
+    register!(group, terms_zipf_1000_with_avg_sub_agg);
 
     register!(group, terms_many_json_mixed_type_with_avg_sub_agg);
 
     register!(group, cardinality_agg);
-    register!(group, terms_few_with_cardinality_agg);
+    register!(group, terms_status_with_cardinality_agg);
 
     register!(group, range_agg);
     register!(group, range_agg_with_avg_sub_agg);
-    register!(group, range_agg_with_term_agg_few);
+    register!(group, range_agg_with_term_agg_status);
     register!(group, range_agg_with_term_agg_many);
     register!(group, histogram);
     register!(group, histogram_hard_bounds);
     register!(group, histogram_with_avg_sub_agg);
-    register!(group, histogram_with_term_agg_few);
+    register!(group, histogram_with_term_agg_status);
     register!(group, avg_and_range_with_avg_sub_agg);
 
     // Filter aggregation benchmarks
@@ -132,12 +139,12 @@ fn extendedstats_f64(index: &Index) {
 }
 fn percentiles_f64(index: &Index) {
     let agg_req = json!({
-      "mypercentiles": {
-        "percentiles": {
-          "field": "score_f64",
-          "percents": [ 95, 99, 99.9 ]
+        "mypercentiles": {
+            "percentiles": {
+                "field": "score_f64",
+                "percents": [ 95, 99, 99.9 ]
+            }
         }
-      }
     });
     execute_agg(index, agg_req);
 }
@@ -152,10 +159,10 @@ fn cardinality_agg(index: &Index) {
     });
     execute_agg(index, agg_req);
 }
-fn terms_few_with_cardinality_agg(index: &Index) {
+fn terms_status_with_cardinality_agg(index: &Index) {
     let agg_req = json!({
         "my_texts": {
-            "terms": { "field": "text_few_terms" },
+            "terms": { "field": "text_few_terms_status" },
             "aggs": {
                 "cardinality": {
                     "cardinality": {
@@ -168,13 +175,20 @@ fn terms_few_with_cardinality_agg(index: &Index) {
     execute_agg(index, agg_req);
 }
 
-fn terms_few(index: &Index) {
+fn terms_7(index: &Index) {
     let agg_req = json!({
-        "my_texts": { "terms": { "field": "text_few_terms" } },
+        "my_texts": { "terms": { "field": "text_few_terms_status" } },
     });
     execute_agg(index, agg_req);
 }
-fn terms_many(index: &Index) {
+fn terms_all_unique(index: &Index) {
+    let agg_req = json!({
+        "my_texts": { "terms": { "field": "text_all_unique_terms" } },
+    });
+    execute_agg(index, agg_req);
+}
+
+fn terms_150_000(index: &Index) {
     let agg_req = json!({
         "my_texts": { "terms": { "field": "text_many_terms" } },
     });
@@ -222,11 +236,10 @@ fn terms_many_with_avg_sub_agg(index: &Index) {
     });
     execute_agg(index, agg_req);
 }
-
-fn terms_few_with_avg_sub_agg(index: &Index) {
+fn terms_all_unique_with_avg_sub_agg(index: &Index) {
     let agg_req = json!({
         "my_texts": {
-            "terms": { "field": "text_few_terms" },
+            "terms": { "field": "text_all_unique_terms" },
             "aggs": {
                 "average_f64": { "avg": { "field": "score_f64" } }
             }
@@ -234,6 +247,60 @@ fn terms_few_with_avg_sub_agg(index: &Index) {
     });
     execute_agg(index, agg_req);
 }
+fn terms_status_with_histogram(index: &Index) {
+    let agg_req = json!({
+        "my_texts": {
+            "terms": { "field": "text_few_terms_status" },
+            "aggs": {
+                "histo": {"histogram": { "field": "score_f64", "interval": 10 }}
+            }
+        }
+    });
+    execute_agg(index, agg_req);
+}
+
+fn terms_zipf_1000_with_histogram(index: &Index) {
+    let agg_req = json!({
+        "my_texts": {
+            "terms": { "field": "text_1000_terms_zipf" },
+            "aggs": {
+                "histo": {"histogram": { "field": "score_f64", "interval": 10 }}
+            }
+        }
+    });
+    execute_agg(index, agg_req);
+}
+
+fn terms_status_with_avg_sub_agg(index: &Index) {
+    let agg_req = json!({
+        "my_texts": {
+            "terms": { "field": "text_few_terms_status" },
+            "aggs": {
+                "average_f64": { "avg": { "field": "score_f64" } }
+            }
+        },
+    });
+    execute_agg(index, agg_req);
+}
+
+fn terms_zipf_1000_with_avg_sub_agg(index: &Index) {
+    let agg_req = json!({
+        "my_texts": {
+            "terms": { "field": "text_1000_terms_zipf" },
+            "aggs": {
+                "average_f64": { "avg": { "field": "score_f64" } }
+            }
+        },
+    });
+    execute_agg(index, agg_req);
+}
+
+fn terms_zipf_1000(index: &Index) {
+    let agg_req = json!({
+        "my_texts": { "terms": { "field": "text_1000_terms_zipf" } },
+    });
+    execute_agg(index, agg_req);
+}
 
 fn terms_many_json_mixed_type_with_avg_sub_agg(index: &Index) {
     let agg_req = json!({
@@ -290,7 +357,7 @@ fn range_agg_with_avg_sub_agg(index: &Index) {
     execute_agg(index, agg_req);
 }
 
-fn range_agg_with_term_agg_few(index: &Index) {
+fn range_agg_with_term_agg_status(index: &Index) {
     let agg_req = json!({
         "rangef64": {
             "range": {
@@ -305,7 +372,7 @@ fn range_agg_with_term_agg_few(index: &Index) {
                 ]
             },
             "aggs": {
-                "my_texts": { "terms": { "field": "text_few_terms" } },
+                "my_texts": { "terms": { "field": "text_few_terms_status" } },
             }
         },
     });
@@ -361,12 +428,12 @@ fn histogram_with_avg_sub_agg(index: &Index) {
     });
     execute_agg(index, agg_req);
 }
-fn histogram_with_term_agg_few(index: &Index) {
+fn histogram_with_term_agg_status(index: &Index) {
     let agg_req = json!({
         "rangef64": {
             "histogram": { "field": "score_f64", "interval": 10 },
             "aggs": {
-                "my_texts": { "terms": { "field": "text_few_terms" } }
+                "my_texts": { "terms": { "field": "text_few_terms_status" } }
             }
         }
     });
@@ -411,6 +478,13 @@ fn get_collector(agg_req: Aggregations) -> AggregationCollector {
 }
 
 fn get_test_index_bench(cardinality: Cardinality) -> tantivy::Result<Index> {
+    // Flag to use existing index
+    let reuse_index = std::env::var("REUSE_AGG_BENCH_INDEX").is_ok();
+    if reuse_index && std::path::Path::new("agg_bench").exists() {
+        return Index::open_in_dir("agg_bench");
+    }
+    // crreate dir
+    std::fs::create_dir_all("agg_bench")?;
     let mut schema_builder = Schema::builder();
     let text_fieldtype = tantivy::schema::TextOptions::default()
         .set_indexing_options(
@@ -419,20 +493,47 @@ fn get_test_index_bench(cardinality: Cardinality) -> tantivy::Result<Index> {
         .set_stored();
     let text_field = schema_builder.add_text_field("text", text_fieldtype);
     let json_field = schema_builder.add_json_field("json", FAST);
+    let text_field_all_unique_terms =
+        schema_builder.add_text_field("text_all_unique_terms", STRING | FAST);
     let text_field_many_terms = schema_builder.add_text_field("text_many_terms", STRING | FAST);
-    let text_field_few_terms = schema_builder.add_text_field("text_few_terms", STRING | FAST);
+    let text_field_few_terms_status =
+        schema_builder.add_text_field("text_few_terms_status", STRING | FAST);
+    let text_field_1000_terms_zipf =
+        schema_builder.add_text_field("text_1000_terms_zipf", STRING | FAST);
     let score_fieldtype = tantivy::schema::NumericOptions::default().set_fast();
     let score_field = schema_builder.add_u64_field("score", score_fieldtype.clone());
     let score_field_f64 = schema_builder.add_f64_field("score_f64", score_fieldtype.clone());
     let score_field_i64 = schema_builder.add_i64_field("score_i64", score_fieldtype);
-    let index = Index::create_from_tempdir(schema_builder.build())?;
-    let few_terms_data = ["INFO", "ERROR", "WARN", "DEBUG"];
+    // use tmp dir
+    let index = if reuse_index {
+        Index::create_in_dir("agg_bench", schema_builder.build())?
+    } else {
+        Index::create_from_tempdir(schema_builder.build())?
+    };
+    // Approximate log proportions
+    let status_field_data = [
+        ("INFO", 8000),
+        ("ERROR", 300),
+        ("WARN", 1200),
+        ("DEBUG", 500),
+        ("OK", 500),
+        ("CRITICAL", 20),
+        ("EMERGENCY", 1),
+    ];
+    let log_level_distribution =
+        WeightedIndex::new(status_field_data.iter().map(|item| item.1)).unwrap();
 
     let lg_norm = rand_distr::LogNormal::new(2.996f64, 0.979f64).unwrap();
 
     let many_terms_data = (0..150_000)
         .map(|num| format!("author{num}"))
         .collect::<Vec<_>>();
+
+    // Prepare 1000 unique terms sampled using a Zipf distribution.
+    // Exponent ~1.1 approximates top-20 terms covering around ~20%.
+    let terms_1000: Vec<String> = (1..=1000).map(|i| format!("term_{i}")).collect();
+    let zipf_1000 = rand_distr::Zipf::new(1000.0, 1.1f64).unwrap();
+
     {
         let mut rng = StdRng::from_seed([1u8; 32]);
         let mut index_writer = index.writer_with_num_threads(1, 200_000_000)?;
@@ -442,15 +543,25 @@ fn get_test_index_bench(cardinality: Cardinality) -> tantivy::Result<Index> {
             index_writer.add_document(doc!())?;
         }
         if cardinality == Cardinality::Multivalued {
+            let log_level_sample_a = status_field_data[log_level_distribution.sample(&mut rng)].0;
+            let log_level_sample_b = status_field_data[log_level_distribution.sample(&mut rng)].0;
+            let idx_a = zipf_1000.sample(&mut rng) as usize - 1;
+            let idx_b = zipf_1000.sample(&mut rng) as usize - 1;
+            let term_1000_a = &terms_1000[idx_a];
+            let term_1000_b = &terms_1000[idx_b];
             index_writer.add_document(doc!(
                 json_field => json!({"mixed_type": 10.0}),
                 json_field => json!({"mixed_type": 10.0}),
                 text_field => "cool",
                 text_field => "cool",
+                text_field_all_unique_terms => "cool",
+                text_field_all_unique_terms => "coolo",
                 text_field_many_terms => "cool",
                 text_field_many_terms => "cool",
-                text_field_few_terms => "cool",
-                text_field_few_terms => "cool",
+                text_field_few_terms_status => log_level_sample_a,
+                text_field_few_terms_status => log_level_sample_b,
+                text_field_1000_terms_zipf => term_1000_a.as_str(),
+                text_field_1000_terms_zipf => term_1000_b.as_str(),
                 score_field => 1u64,
                 score_field => 1u64,
                 score_field_f64 => lg_norm.sample(&mut rng),
@@ -465,8 +576,8 @@ fn get_test_index_bench(cardinality: Cardinality) -> tantivy::Result<Index> {
         }
         let _val_max = 1_000_000.0;
         for _ in 0..doc_with_value {
-            let val: f64 = rng.gen_range(0.0..1_000_000.0);
-            let json = if rng.gen_bool(0.1) {
+            let val: f64 = rng.random_range(0.0..1_000_000.0);
+            let json = if rng.random_bool(0.1) {
                 // 10% are numeric values
                 json!({ "mixed_type": val })
             } else {
@@ -475,8 +586,10 @@ fn get_test_index_bench(cardinality: Cardinality) -> tantivy::Result<Index> {
             index_writer.add_document(doc!(
                 text_field => "cool",
                 json_field => json,
+                text_field_all_unique_terms => format!("unique_term_{}", rng.random::<u64>()),
                 text_field_many_terms => many_terms_data.choose(&mut rng).unwrap().to_string(),
-                text_field_few_terms => few_terms_data.choose(&mut rng).unwrap().to_string(),
+                text_field_few_terms_status => status_field_data[log_level_distribution.sample(&mut rng)].0,
+                text_field_1000_terms_zipf => terms_1000[zipf_1000.sample(&mut rng) as usize - 1].as_str(),
                 score_field => val as u64,
                 score_field_f64 => lg_norm.sample(&mut rng),
                 score_field_i64 => val as i64,
@@ -528,7 +641,7 @@ fn filter_agg_all_query_with_sub_aggs(index: &Index) {
                 "avg_score": { "avg": { "field": "score" } },
                 "stats_score": { "stats": { "field": "score_f64" } },
                 "terms_text": {
-                    "terms": { "field": "text_few_terms" }
+                    "terms": { "field": "text_few_terms_status" }
                 }
             }
         }
@@ -544,7 +657,7 @@ fn filter_agg_term_query_with_sub_aggs(index: &Index) {
                 "avg_score": { "avg": { "field": "score" } },
                 "stats_score": { "stats": { "field": "score_f64" } },
                 "terms_text": {
-                    "terms": { "field": "text_few_terms" }
+                    "terms": { "field": "text_few_terms_status" }
                 }
             }
         }

benches/and_or_queries.rs

@@ -55,29 +55,29 @@ fn build_shared_indices(num_docs: usize, p_a: f32, p_b: f32, p_c: f32) -> (Bench
     {
         let mut writer = index.writer_with_num_threads(1, 500_000_000).unwrap();
         for _ in 0..num_docs {
-            let has_a = rng.gen_bool(p_a as f64);
-            let has_b = rng.gen_bool(p_b as f64);
-            let has_c = rng.gen_bool(p_c as f64);
-            let score = rng.gen_range(0u64..100u64);
-            let score2 = rng.gen_range(0u64..100_000u64);
+            let has_a = rng.random_bool(p_a as f64);
+            let has_b = rng.random_bool(p_b as f64);
+            let has_c = rng.random_bool(p_c as f64);
+            let score = rng.random_range(0u64..100u64);
+            let score2 = rng.random_range(0u64..100_000u64);
             let mut title_tokens: Vec<&str> = Vec::new();
             let mut body_tokens: Vec<&str> = Vec::new();
             if has_a {
-                if rng.gen_bool(0.1) {
+                if rng.random_bool(0.1) {
                     title_tokens.push("a");
                 } else {
                     body_tokens.push("a");
                 }
             }
             if has_b {
-                if rng.gen_bool(0.1) {
+                if rng.random_bool(0.1) {
                     title_tokens.push("b");
                 } else {
                     body_tokens.push("b");
                 }
             }
             if has_c {
-                if rng.gen_bool(0.1) {
+                if rng.random_bool(0.1) {
                     title_tokens.push("c");
                 } else {
                     body_tokens.push("c");

benches/bool_queries_with_range.rs

@@ -0,0 +1,288 @@
+use binggan::{black_box, BenchGroup, BenchRunner};
+use rand::prelude::*;
+use rand::rngs::StdRng;
+use rand::SeedableRng;
+use tantivy::collector::{Collector, Count, DocSetCollector, TopDocs};
+use tantivy::query::{Query, QueryParser};
+use tantivy::schema::{Schema, FAST, INDEXED, TEXT};
+use tantivy::{doc, Index, Order, ReloadPolicy, Searcher};
+
+#[derive(Clone)]
+struct BenchIndex {
+    #[allow(dead_code)]
+    index: Index,
+    searcher: Searcher,
+    query_parser: QueryParser,
+}
+
+fn build_shared_indices(num_docs: usize, p_title_a: f32, distribution: &str) -> BenchIndex {
+    // Unified schema
+    let mut schema_builder = Schema::builder();
+    let f_title = schema_builder.add_text_field("title", TEXT);
+    let f_num_rand = schema_builder.add_u64_field("num_rand", INDEXED);
+    let f_num_asc = schema_builder.add_u64_field("num_asc", INDEXED);
+    let f_num_rand_fast = schema_builder.add_u64_field("num_rand_fast", INDEXED | FAST);
+    let f_num_asc_fast = schema_builder.add_u64_field("num_asc_fast", INDEXED | FAST);
+    let schema = schema_builder.build();
+    let index = Index::create_in_ram(schema.clone());
+
+    // Populate index with stable RNG for reproducibility.
+    let mut rng = StdRng::from_seed([7u8; 32]);
+
+    {
+        let mut writer = index.writer_with_num_threads(1, 4_000_000_000).unwrap();
+
+        match distribution {
+            "dense" => {
+                for doc_id in 0..num_docs {
+                    // Always add title to avoid empty documents
+                    let title_token = if rng.random_bool(p_title_a as f64) {
+                        "a"
+                    } else {
+                        "b"
+                    };
+
+                    let num_rand = rng.random_range(0u64..1000u64);
+
+                    let num_asc = (doc_id / 10000) as u64;
+
+                    writer
+                        .add_document(doc!(
+                            f_title=>title_token,
+                            f_num_rand=>num_rand,
+                            f_num_asc=>num_asc,
+                            f_num_rand_fast=>num_rand,
+                            f_num_asc_fast=>num_asc,
+                        ))
+                        .unwrap();
+                }
+            }
+            "sparse" => {
+                for doc_id in 0..num_docs {
+                    // Always add title to avoid empty documents
+                    let title_token = if rng.random_bool(p_title_a as f64) {
+                        "a"
+                    } else {
+                        "b"
+                    };
+
+                    let num_rand = rng.random_range(0u64..10000000u64);
+
+                    let num_asc = doc_id as u64;
+
+                    writer
+                        .add_document(doc!(
+                            f_title=>title_token,
+                            f_num_rand=>num_rand,
+                            f_num_asc=>num_asc,
+                            f_num_rand_fast=>num_rand,
+                            f_num_asc_fast=>num_asc,
+                        ))
+                        .unwrap();
+                }
+            }
+            _ => {
+                panic!("Unsupported distribution type");
+            }
+        }
+        writer.commit().unwrap();
+    }
+
+    // Prepare reader/searcher once.
+    let reader = index
+        .reader_builder()
+        .reload_policy(ReloadPolicy::Manual)
+        .try_into()
+        .unwrap();
+    let searcher = reader.searcher();
+
+    // Build query parser for title field
+    let qp_title = QueryParser::for_index(&index, vec![f_title]);
+
+    BenchIndex {
+        index,
+        searcher,
+        query_parser: qp_title,
+    }
+}
+
+fn main() {
+    // Prepare corpora with varying scenarios
+    let scenarios = vec![
+        (
+            "dense and 99% a".to_string(),
+            10_000_000,
+            0.99,
+            "dense",
+            0,
+            9,
+        ),
+        (
+            "dense and 99% a".to_string(),
+            10_000_000,
+            0.99,
+            "dense",
+            990,
+            999,
+        ),
+        (
+            "sparse and 99% a".to_string(),
+            10_000_000,
+            0.99,
+            "sparse",
+            0,
+            9,
+        ),
+        (
+            "sparse and 99% a".to_string(),
+            10_000_000,
+            0.99,
+            "sparse",
+            9_999_990,
+            9_999_999,
+        ),
+    ];
+
+    let mut runner = BenchRunner::new();
+    for (scenario_id, n, p_title_a, num_rand_distribution, range_low, range_high) in scenarios {
+        // Build index for this scenario
+        let bench_index = build_shared_indices(n, p_title_a, num_rand_distribution);
+
+        // Create benchmark group
+        let mut group = runner.new_group();
+
+        // Now set the name (this moves scenario_id)
+        group.set_name(scenario_id);
+
+        // Define all four field types
+        let field_names = ["num_rand", "num_asc", "num_rand_fast", "num_asc_fast"];
+
+        // Define the three terms we want to test with
+        let terms = ["a", "b", "z"];
+
+        // Generate all combinations of terms and field names
+        let mut queries = Vec::new();
+        for &term in &terms {
+            for &field_name in &field_names {
+                let query_str = format!(
+                    "{} AND {}:[{} TO {}]",
+                    term, field_name, range_low, range_high
+                );
+                queries.push((query_str, field_name.to_string()));
+            }
+        }
+
+        let query_str = format!(
+            "{}:[{} TO {}] AND {}:[{} TO {}]",
+            "num_rand_fast", range_low, range_high, "num_asc_fast", range_low, range_high
+        );
+        queries.push((query_str, "num_asc_fast".to_string()));
+
+        // Run all benchmark tasks for each query and its corresponding field name
+        for (query_str, field_name) in queries {
+            run_benchmark_tasks(&mut group, &bench_index, &query_str, &field_name);
+        }
+
+        group.run();
+    }
+}
+
+/// Run all benchmark tasks for a given query string and field name
+fn run_benchmark_tasks(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query_str: &str,
+    field_name: &str,
+) {
+    // Test count
+    add_bench_task(bench_group, bench_index, query_str, Count, "count");
+
+    // Test all results
+    add_bench_task(
+        bench_group,
+        bench_index,
+        query_str,
+        DocSetCollector,
+        "all results",
+    );
+
+    // Test top 100 by the field (if it's a FAST field)
+    if field_name.ends_with("_fast") {
+        // Ascending order
+        {
+            let collector_name = format!("top100_by_{}_asc", field_name);
+            let field_name_owned = field_name.to_string();
+            add_bench_task(
+                bench_group,
+                bench_index,
+                query_str,
+                TopDocs::with_limit(100).order_by_fast_field::<u64>(field_name_owned, Order::Asc),
+                &collector_name,
+            );
+        }
+
+        // Descending order
+        {
+            let collector_name = format!("top100_by_{}_desc", field_name);
+            let field_name_owned = field_name.to_string();
+            add_bench_task(
+                bench_group,
+                bench_index,
+                query_str,
+                TopDocs::with_limit(100).order_by_fast_field::<u64>(field_name_owned, Order::Desc),
+                &collector_name,
+            );
+        }
+    }
+}
+
+fn add_bench_task<C: Collector + 'static>(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query_str: &str,
+    collector: C,
+    collector_name: &str,
+) {
+    let task_name = format!("{}_{}", query_str.replace(" ", "_"), collector_name);
+    let query = bench_index.query_parser.parse_query(query_str).unwrap();
+    let search_task = SearchTask {
+        searcher: bench_index.searcher.clone(),
+        collector,
+        query,
+    };
+    bench_group.register(task_name, move |_| black_box(search_task.run()));
+}
+
+struct SearchTask<C: Collector> {
+    searcher: Searcher,
+    collector: C,
+    query: Box<dyn Query>,
+}
+
+impl<C: Collector> SearchTask<C> {
+    #[inline(never)]
+    pub fn run(&self) -> usize {
+        let result = self.searcher.search(&self.query, &self.collector).unwrap();
+        if let Some(count) = (&result as &dyn std::any::Any).downcast_ref::<usize>() {
+            *count
+        } else if let Some(top_docs) = (&result as &dyn std::any::Any)
+            .downcast_ref::<Vec<(Option<u64>, tantivy::DocAddress)>>()
+        {
+            top_docs.len()
+        } else if let Some(top_docs) =
+            (&result as &dyn std::any::Any).downcast_ref::<Vec<(u64, tantivy::DocAddress)>>()
+        {
+            top_docs.len()
+        } else if let Some(doc_set) = (&result as &dyn std::any::Any)
+            .downcast_ref::<std::collections::HashSet<tantivy::DocAddress>>()
+        {
+            doc_set.len()
+        } else {
+            eprintln!(
+                "Unknown collector result type: {:?}",
+                std::any::type_name::<C::Fruit>()
+            );
+            0
+        }
+    }
+}

benches/range_queries.rs

@@ -0,0 +1,365 @@
+use std::ops::Bound;
+
+use binggan::{black_box, BenchGroup, BenchRunner};
+use rand::prelude::*;
+use rand::rngs::StdRng;
+use rand::SeedableRng;
+use tantivy::collector::{Count, DocSetCollector, TopDocs};
+use tantivy::query::RangeQuery;
+use tantivy::schema::{Schema, FAST, INDEXED};
+use tantivy::{doc, Index, Order, ReloadPolicy, Searcher, Term};
+
+#[derive(Clone)]
+struct BenchIndex {
+    #[allow(dead_code)]
+    index: Index,
+    searcher: Searcher,
+}
+
+fn build_shared_indices(num_docs: usize, distribution: &str) -> BenchIndex {
+    // Schema with fast fields only
+    let mut schema_builder = Schema::builder();
+    let f_num_rand_fast = schema_builder.add_u64_field("num_rand_fast", INDEXED | FAST);
+    let f_num_asc_fast = schema_builder.add_u64_field("num_asc_fast", INDEXED | FAST);
+    let schema = schema_builder.build();
+    let index = Index::create_in_ram(schema.clone());
+
+    // Populate index with stable RNG for reproducibility.
+    let mut rng = StdRng::from_seed([7u8; 32]);
+
+    {
+        let mut writer = index.writer_with_num_threads(1, 4_000_000_000).unwrap();
+
+        match distribution {
+            "dense" => {
+                for doc_id in 0..num_docs {
+                    let num_rand = rng.random_range(0u64..1000u64);
+                    let num_asc = (doc_id / 10000) as u64;
+
+                    writer
+                        .add_document(doc!(
+                            f_num_rand_fast=>num_rand,
+                            f_num_asc_fast=>num_asc,
+                        ))
+                        .unwrap();
+                }
+            }
+            "sparse" => {
+                for doc_id in 0..num_docs {
+                    let num_rand = rng.random_range(0u64..10000000u64);
+                    let num_asc = doc_id as u64;
+
+                    writer
+                        .add_document(doc!(
+                            f_num_rand_fast=>num_rand,
+                            f_num_asc_fast=>num_asc,
+                        ))
+                        .unwrap();
+                }
+            }
+            _ => {
+                panic!("Unsupported distribution type");
+            }
+        }
+        writer.commit().unwrap();
+    }
+
+    // Prepare reader/searcher once.
+    let reader = index
+        .reader_builder()
+        .reload_policy(ReloadPolicy::Manual)
+        .try_into()
+        .unwrap();
+    let searcher = reader.searcher();
+
+    BenchIndex { index, searcher }
+}
+
+fn main() {
+    // Prepare corpora with varying scenarios
+    let scenarios = vec![
+        // Dense distribution - random values in small range (0-999)
+        (
+            "dense_values_search_low_value_range".to_string(),
+            10_000_000,
+            "dense",
+            0,
+            9,
+        ),
+        (
+            "dense_values_search_high_value_range".to_string(),
+            10_000_000,
+            "dense",
+            990,
+            999,
+        ),
+        (
+            "dense_values_search_out_of_range".to_string(),
+            10_000_000,
+            "dense",
+            1000,
+            1002,
+        ),
+        (
+            "sparse_values_search_low_value_range".to_string(),
+            10_000_000,
+            "sparse",
+            0,
+            9,
+        ),
+        (
+            "sparse_values_search_high_value_range".to_string(),
+            10_000_000,
+            "sparse",
+            9_999_990,
+            9_999_999,
+        ),
+        (
+            "sparse_values_search_out_of_range".to_string(),
+            10_000_000,
+            "sparse",
+            10_000_000,
+            10_000_002,
+        ),
+    ];
+
+    let mut runner = BenchRunner::new();
+    for (scenario_id, n, num_rand_distribution, range_low, range_high) in scenarios {
+        // Build index for this scenario
+        let bench_index = build_shared_indices(n, num_rand_distribution);
+
+        // Create benchmark group
+        let mut group = runner.new_group();
+
+        // Now set the name (this moves scenario_id)
+        group.set_name(scenario_id);
+
+        // Define fast field types
+        let field_names = ["num_rand_fast", "num_asc_fast"];
+
+        // Generate range queries for fast fields
+        for &field_name in &field_names {
+            // Create the range query
+            let field = bench_index.searcher.schema().get_field(field_name).unwrap();
+            let lower_term = Term::from_field_u64(field, range_low);
+            let upper_term = Term::from_field_u64(field, range_high);
+
+            let query = RangeQuery::new(Bound::Included(lower_term), Bound::Included(upper_term));
+
+            run_benchmark_tasks(
+                &mut group,
+                &bench_index,
+                query,
+                field_name,
+                range_low,
+                range_high,
+            );
+        }
+
+        group.run();
+    }
+}
+
+/// Run all benchmark tasks for a given range query and field name
+fn run_benchmark_tasks(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    field_name: &str,
+    range_low: u64,
+    range_high: u64,
+) {
+    // Test count
+    add_bench_task_count(
+        bench_group,
+        bench_index,
+        query.clone(),
+        "count",
+        field_name,
+        range_low,
+        range_high,
+    );
+
+    // Test top 100 by the field (ascending order)
+    {
+        let collector_name = format!("top100_by_{}_asc", field_name);
+        let field_name_owned = field_name.to_string();
+        add_bench_task_top100_asc(
+            bench_group,
+            bench_index,
+            query.clone(),
+            &collector_name,
+            field_name,
+            range_low,
+            range_high,
+            field_name_owned,
+        );
+    }
+
+    // Test top 100 by the field (descending order)
+    {
+        let collector_name = format!("top100_by_{}_desc", field_name);
+        let field_name_owned = field_name.to_string();
+        add_bench_task_top100_desc(
+            bench_group,
+            bench_index,
+            query,
+            &collector_name,
+            field_name,
+            range_low,
+            range_high,
+            field_name_owned,
+        );
+    }
+}
+
+fn add_bench_task_count(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    collector_name: &str,
+    field_name: &str,
+    range_low: u64,
+    range_high: u64,
+) {
+    let task_name = format!(
+        "range_{}_[{} TO {}]_{}",
+        field_name, range_low, range_high, collector_name
+    );
+
+    let search_task = CountSearchTask {
+        searcher: bench_index.searcher.clone(),
+        query,
+    };
+    bench_group.register(task_name, move |_| black_box(search_task.run()));
+}
+
+fn add_bench_task_docset(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    collector_name: &str,
+    field_name: &str,
+    range_low: u64,
+    range_high: u64,
+) {
+    let task_name = format!(
+        "range_{}_[{} TO {}]_{}",
+        field_name, range_low, range_high, collector_name
+    );
+
+    let search_task = DocSetSearchTask {
+        searcher: bench_index.searcher.clone(),
+        query,
+    };
+    bench_group.register(task_name, move |_| black_box(search_task.run()));
+}
+
+fn add_bench_task_top100_asc(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    collector_name: &str,
+    field_name: &str,
+    range_low: u64,
+    range_high: u64,
+    field_name_owned: String,
+) {
+    let task_name = format!(
+        "range_{}_[{} TO {}]_{}",
+        field_name, range_low, range_high, collector_name
+    );
+
+    let search_task = Top100AscSearchTask {
+        searcher: bench_index.searcher.clone(),
+        query,
+        field_name: field_name_owned,
+    };
+    bench_group.register(task_name, move |_| black_box(search_task.run()));
+}
+
+fn add_bench_task_top100_desc(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    collector_name: &str,
+    field_name: &str,
+    range_low: u64,
+    range_high: u64,
+    field_name_owned: String,
+) {
+    let task_name = format!(
+        "range_{}_[{} TO {}]_{}",
+        field_name, range_low, range_high, collector_name
+    );
+
+    let search_task = Top100DescSearchTask {
+        searcher: bench_index.searcher.clone(),
+        query,
+        field_name: field_name_owned,
+    };
+    bench_group.register(task_name, move |_| black_box(search_task.run()));
+}
+
+struct CountSearchTask {
+    searcher: Searcher,
+    query: RangeQuery,
+}
+
+impl CountSearchTask {
+    #[inline(never)]
+    pub fn run(&self) -> usize {
+        self.searcher.search(&self.query, &Count).unwrap()
+    }
+}
+
+struct DocSetSearchTask {
+    searcher: Searcher,
+    query: RangeQuery,
+}
+
+impl DocSetSearchTask {
+    #[inline(never)]
+    pub fn run(&self) -> usize {
+        let result = self.searcher.search(&self.query, &DocSetCollector).unwrap();
+        result.len()
+    }
+}
+
+struct Top100AscSearchTask {
+    searcher: Searcher,
+    query: RangeQuery,
+    field_name: String,
+}
+
+impl Top100AscSearchTask {
+    #[inline(never)]
+    pub fn run(&self) -> usize {
+        let collector =
+            TopDocs::with_limit(100).order_by_fast_field::<u64>(&self.field_name, Order::Asc);
+        let result = self.searcher.search(&self.query, &collector).unwrap();
+        for (_score, doc_address) in &result {
+            let _doc: tantivy::TantivyDocument = self.searcher.doc(*doc_address).unwrap();
+        }
+        result.len()
+    }
+}
+
+struct Top100DescSearchTask {
+    searcher: Searcher,
+    query: RangeQuery,
+    field_name: String,
+}
+
+impl Top100DescSearchTask {
+    #[inline(never)]
+    pub fn run(&self) -> usize {
+        let collector =
+            TopDocs::with_limit(100).order_by_fast_field::<u64>(&self.field_name, Order::Desc);
+        let result = self.searcher.search(&self.query, &collector).unwrap();
+        for (_score, doc_address) in &result {
+            let _doc: tantivy::TantivyDocument = self.searcher.doc(*doc_address).unwrap();
+        }
+        result.len()
+    }
+}

benches/range_query.rs

@@ -0,0 +1,260 @@
+use std::fmt::Display;
+use std::net::Ipv6Addr;
+use std::ops::RangeInclusive;
+
+use binggan::plugins::PeakMemAllocPlugin;
+use binggan::{black_box, BenchRunner, OutputValue, PeakMemAlloc, INSTRUMENTED_SYSTEM};
+use columnar::MonotonicallyMappableToU128;
+use rand::rngs::StdRng;
+use rand::{Rng, SeedableRng};
+use tantivy::collector::{Count, TopDocs};
+use tantivy::query::QueryParser;
+use tantivy::schema::*;
+use tantivy::{doc, Index};
+
+#[global_allocator]
+pub static GLOBAL: &PeakMemAlloc<std::alloc::System> = &INSTRUMENTED_SYSTEM;
+
+fn main() {
+    bench_range_query();
+}
+
+fn bench_range_query() {
+    let index = get_index_0_to_100();
+    let mut runner = BenchRunner::new();
+    runner.add_plugin(PeakMemAllocPlugin::new(GLOBAL));
+
+    runner.set_name("range_query on u64");
+    let field_name_and_descr: Vec<_> = vec![
+        ("id", "Single Valued Range Field"),
+        ("ids", "Multi Valued Range Field"),
+    ];
+    let range_num_hits = vec![
+        ("90_percent", get_90_percent()),
+        ("10_percent", get_10_percent()),
+        ("1_percent", get_1_percent()),
+    ];
+
+    test_range(&mut runner, &index, &field_name_and_descr, range_num_hits);
+
+    runner.set_name("range_query on ip");
+    let field_name_and_descr: Vec<_> = vec![
+        ("ip", "Single Valued Range Field"),
+        ("ips", "Multi Valued Range Field"),
+    ];
+    let range_num_hits = vec![
+        ("90_percent", get_90_percent_ip()),
+        ("10_percent", get_10_percent_ip()),
+        ("1_percent", get_1_percent_ip()),
+    ];
+
+    test_range(&mut runner, &index, &field_name_and_descr, range_num_hits);
+}
+
+fn test_range<T: Display>(
+    runner: &mut BenchRunner,
+    index: &Index,
+    field_name_and_descr: &[(&str, &str)],
+    range_num_hits: Vec<(&str, RangeInclusive<T>)>,
+) {
+    for (field, suffix) in field_name_and_descr {
+        let term_num_hits = vec![
+            ("", ""),
+            ("1_percent", "veryfew"),
+            ("10_percent", "few"),
+            ("90_percent", "most"),
+        ];
+        let mut group = runner.new_group();
+        group.set_name(suffix);
+        // all intersect combinations
+        for (range_name, range) in &range_num_hits {
+            for (term_name, term) in &term_num_hits {
+                let index = &index;
+                let test_name = if term_name.is_empty() {
+                    format!("id_range_hit_{}", range_name)
+                } else {
+                    format!(
+                        "id_range_hit_{}_intersect_with_term_{}",
+                        range_name, term_name
+                    )
+                };
+                group.register(test_name, move |_| {
+                    let query = if term_name.is_empty() {
+                        "".to_string()
+                    } else {
+                        format!("AND id_name:{}", term)
+                    };
+                    black_box(execute_query(field, range, &query, index));
+                });
+            }
+        }
+        group.run();
+    }
+}
+
+fn get_index_0_to_100() -> Index {
+    let mut rng = StdRng::from_seed([1u8; 32]);
+    let num_vals = 100_000;
+    let docs: Vec<_> = (0..num_vals)
+        .map(|_i| {
+            let id_name = if rng.random_bool(0.01) {
+                "veryfew".to_string() // 1%
+            } else if rng.random_bool(0.1) {
+                "few".to_string() // 9%
+            } else {
+                "most".to_string() // 90%
+            };
+            Doc {
+                id_name,
+                id: rng.random_range(0..100),
+                // Multiply by 1000, so that we create most buckets in the compact space
+                // The benches depend on this range to select n-percent of elements with the
+                // methods below.
+                ip: Ipv6Addr::from_u128(rng.random_range(0..100) * 1000),
+            }
+        })
+        .collect();
+
+    create_index_from_docs(&docs)
+}
+
+#[derive(Clone, Debug)]
+pub struct Doc {
+    pub id_name: String,
+    pub id: u64,
+    pub ip: Ipv6Addr,
+}
+
+pub fn create_index_from_docs(docs: &[Doc]) -> Index {
+    let mut schema_builder = Schema::builder();
+    let id_u64_field = schema_builder.add_u64_field("id", INDEXED | STORED | FAST);
+    let ids_u64_field =
+        schema_builder.add_u64_field("ids", NumericOptions::default().set_fast().set_indexed());
+
+    let id_f64_field = schema_builder.add_f64_field("id_f64", INDEXED | STORED | FAST);
+    let ids_f64_field = schema_builder.add_f64_field(
+        "ids_f64",
+        NumericOptions::default().set_fast().set_indexed(),
+    );
+
+    let id_i64_field = schema_builder.add_i64_field("id_i64", INDEXED | STORED | FAST);
+    let ids_i64_field = schema_builder.add_i64_field(
+        "ids_i64",
+        NumericOptions::default().set_fast().set_indexed(),
+    );
+
+    let text_field = schema_builder.add_text_field("id_name", STRING | STORED);
+    let text_field2 = schema_builder.add_text_field("id_name_fast", STRING | STORED | FAST);
+
+    let ip_field = schema_builder.add_ip_addr_field("ip", FAST);
+    let ips_field = schema_builder.add_ip_addr_field("ips", FAST);
+
+    let schema = schema_builder.build();
+
+    let index = Index::create_in_ram(schema);
+
+    {
+        let mut index_writer = index.writer_with_num_threads(1, 50_000_000).unwrap();
+        for doc in docs.iter() {
+            index_writer
+                .add_document(doc!(
+                    ids_i64_field => doc.id as i64,
+                    ids_i64_field => doc.id as i64,
+                    ids_f64_field => doc.id as f64,
+                    ids_f64_field => doc.id as f64,
+                    ids_u64_field => doc.id,
+                    ids_u64_field => doc.id,
+                    id_u64_field => doc.id,
+                    id_f64_field => doc.id as f64,
+                    id_i64_field => doc.id as i64,
+                    text_field => doc.id_name.to_string(),
+                    text_field2 => doc.id_name.to_string(),
+                    ips_field => doc.ip,
+                    ips_field => doc.ip,
+                    ip_field => doc.ip,
+                ))
+                .unwrap();
+        }
+
+        index_writer.commit().unwrap();
+    }
+    index
+}
+
+fn get_90_percent() -> RangeInclusive<u64> {
+    0..=90
+}
+
+fn get_10_percent() -> RangeInclusive<u64> {
+    0..=10
+}
+
+fn get_1_percent() -> RangeInclusive<u64> {
+    10..=10
+}
+
+fn get_90_percent_ip() -> RangeInclusive<Ipv6Addr> {
+    let start = Ipv6Addr::from_u128(0);
+    let end = Ipv6Addr::from_u128(90 * 1000);
+    start..=end
+}
+
+fn get_10_percent_ip() -> RangeInclusive<Ipv6Addr> {
+    let start = Ipv6Addr::from_u128(0);
+    let end = Ipv6Addr::from_u128(10 * 1000);
+    start..=end
+}
+
+fn get_1_percent_ip() -> RangeInclusive<Ipv6Addr> {
+    let start = Ipv6Addr::from_u128(10 * 1000);
+    let end = Ipv6Addr::from_u128(10 * 1000);
+    start..=end
+}
+
+struct NumHits {
+    count: usize,
+}
+impl OutputValue for NumHits {
+    fn column_title() -> &'static str {
+        "NumHits"
+    }
+    fn format(&self) -> Option<String> {
+        Some(self.count.to_string())
+    }
+}
+
+fn execute_query<T: Display>(
+    field: &str,
+    id_range: &RangeInclusive<T>,
+    suffix: &str,
+    index: &Index,
+) -> NumHits {
+    let gen_query_inclusive = |from: &T, to: &T| {
+        format!(
+            "{}:[{} TO {}] {}",
+            field,
+            &from.to_string(),
+            &to.to_string(),
+            suffix
+        )
+    };
+
+    let query = gen_query_inclusive(id_range.start(), id_range.end());
+    execute_query_(&query, index)
+}
+
+fn execute_query_(query: &str, index: &Index) -> NumHits {
+    let query_from_text = |text: &str| {
+        QueryParser::for_index(index, vec![])
+            .parse_query(text)
+            .unwrap()
+    };
+    let query = query_from_text(query);
+    let reader = index.reader().unwrap();
+    let searcher = reader.searcher();
+    let num_hits = searcher
+        .search(&query, &(TopDocs::with_limit(10).order_by_score(), Count))
+        .unwrap()
+        .1;
+    NumHits { count: num_hits }
+}

benches/str_search_and_get.rs

@@ -0,0 +1,421 @@
+// This benchmark compares different approaches for retrieving string values:
+//
+// 1. Fast Field Approach: retrieves string values via term_ords() and ord_to_str()
+//
+// 2. Doc Store Approach: retrieves string values via searcher.doc() and field extraction
+//
+// The benchmark includes various data distributions:
+// - Dense Sequential: Sequential document IDs with dense data
+// - Dense Random: Random document IDs with dense data
+// - Sparse Sequential: Sequential document IDs with sparse data
+// - Sparse Random: Random document IDs with sparse data
+use std::ops::Bound;
+
+use binggan::{black_box, BenchGroup, BenchRunner};
+use rand::prelude::*;
+use rand::rngs::StdRng;
+use rand::SeedableRng;
+use tantivy::collector::{Count, DocSetCollector};
+use tantivy::query::RangeQuery;
+use tantivy::schema::document::TantivyDocument;
+use tantivy::schema::{Schema, Value, FAST, STORED, STRING};
+use tantivy::{doc, Index, ReloadPolicy, Searcher, Term};
+
+#[derive(Clone)]
+struct BenchIndex {
+    #[allow(dead_code)]
+    index: Index,
+    searcher: Searcher,
+}
+
+fn build_shared_indices(num_docs: usize, distribution: &str) -> BenchIndex {
+    // Schema with string fast field and stored field for doc access
+    let mut schema_builder = Schema::builder();
+    let f_str_fast = schema_builder.add_text_field("str_fast", STRING | STORED | FAST);
+    let f_str_stored = schema_builder.add_text_field("str_stored", STRING | STORED);
+    let schema = schema_builder.build();
+    let index = Index::create_in_ram(schema.clone());
+
+    // Populate index with stable RNG for reproducibility.
+    let mut rng = StdRng::from_seed([7u8; 32]);
+
+    {
+        let mut writer = index.writer_with_num_threads(1, 4_000_000_000).unwrap();
+
+        match distribution {
+            "dense_random" => {
+                for _doc_id in 0..num_docs {
+                    let suffix = rng.gen_range(0u64..1000u64);
+                    let str_val = format!("str_{:03}", suffix);
+
+                    writer
+                        .add_document(doc!(
+                            f_str_fast=>str_val.clone(),
+                            f_str_stored=>str_val,
+                        ))
+                        .unwrap();
+                }
+            }
+            "dense_sequential" => {
+                for doc_id in 0..num_docs {
+                    let suffix = doc_id as u64 % 1000;
+                    let str_val = format!("str_{:03}", suffix);
+
+                    writer
+                        .add_document(doc!(
+                            f_str_fast=>str_val.clone(),
+                            f_str_stored=>str_val,
+                        ))
+                        .unwrap();
+                }
+            }
+            "sparse_random" => {
+                for _doc_id in 0..num_docs {
+                    let suffix = rng.gen_range(0u64..1000000u64);
+                    let str_val = format!("str_{:07}", suffix);
+
+                    writer
+                        .add_document(doc!(
+                            f_str_fast=>str_val.clone(),
+                            f_str_stored=>str_val,
+                        ))
+                        .unwrap();
+                }
+            }
+            "sparse_sequential" => {
+                for doc_id in 0..num_docs {
+                    let suffix = doc_id as u64;
+                    let str_val = format!("str_{:07}", suffix);
+
+                    writer
+                        .add_document(doc!(
+                            f_str_fast=>str_val.clone(),
+                            f_str_stored=>str_val,
+                        ))
+                        .unwrap();
+                }
+            }
+            _ => {
+                panic!("Unsupported distribution type");
+            }
+        }
+        writer.commit().unwrap();
+    }
+
+    // Prepare reader/searcher once.
+    let reader = index
+        .reader_builder()
+        .reload_policy(ReloadPolicy::Manual)
+        .try_into()
+        .unwrap();
+    let searcher = reader.searcher();
+
+    BenchIndex { index, searcher }
+}
+
+fn main() {
+    // Prepare corpora with varying scenarios
+    let scenarios = vec![
+        (
+            "dense_random_search_low_range".to_string(),
+            1_000_000,
+            "dense_random",
+            0,
+            9,
+        ),
+        (
+            "dense_random_search_high_range".to_string(),
+            1_000_000,
+            "dense_random",
+            990,
+            999,
+        ),
+        (
+            "dense_sequential_search_low_range".to_string(),
+            1_000_000,
+            "dense_sequential",
+            0,
+            9,
+        ),
+        (
+            "dense_sequential_search_high_range".to_string(),
+            1_000_000,
+            "dense_sequential",
+            990,
+            999,
+        ),
+        (
+            "sparse_random_search_low_range".to_string(),
+            1_000_000,
+            "sparse_random",
+            0,
+            9999,
+        ),
+        (
+            "sparse_random_search_high_range".to_string(),
+            1_000_000,
+            "sparse_random",
+            990_000,
+            999_999,
+        ),
+        (
+            "sparse_sequential_search_low_range".to_string(),
+            1_000_000,
+            "sparse_sequential",
+            0,
+            9999,
+        ),
+        (
+            "sparse_sequential_search_high_range".to_string(),
+            1_000_000,
+            "sparse_sequential",
+            990_000,
+            999_999,
+        ),
+    ];
+
+    let mut runner = BenchRunner::new();
+    for (scenario_id, n, distribution, range_low, range_high) in scenarios {
+        let bench_index = build_shared_indices(n, distribution);
+        let mut group = runner.new_group();
+        group.set_name(scenario_id);
+
+        let field = bench_index.searcher.schema().get_field("str_fast").unwrap();
+
+        let (lower_str, upper_str) =
+            if distribution == "dense_sequential" || distribution == "dense_random" {
+                (
+                    format!("str_{:03}", range_low),
+                    format!("str_{:03}", range_high),
+                )
+            } else {
+                (
+                    format!("str_{:07}", range_low),
+                    format!("str_{:07}", range_high),
+                )
+            };
+
+        let lower_term = Term::from_field_text(field, &lower_str);
+        let upper_term = Term::from_field_text(field, &upper_str);
+
+        let query = RangeQuery::new(Bound::Included(lower_term), Bound::Included(upper_term));
+
+        run_benchmark_tasks(&mut group, &bench_index, query, range_low, range_high);
+
+        group.run();
+    }
+}
+
+/// Run all benchmark tasks for a given range query
+fn run_benchmark_tasks(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    range_low: u64,
+    range_high: u64,
+) {
+    // Test count of matching documents
+    add_bench_task_count(
+        bench_group,
+        bench_index,
+        query.clone(),
+        range_low,
+        range_high,
+    );
+
+    // Test fetching all DocIds of matching documents
+    add_bench_task_docset(
+        bench_group,
+        bench_index,
+        query.clone(),
+        range_low,
+        range_high,
+    );
+
+    // Test fetching all string fast field values of matching documents
+    add_bench_task_fetch_all_strings(
+        bench_group,
+        bench_index,
+        query.clone(),
+        range_low,
+        range_high,
+    );
+
+    // Test fetching all string values of matching documents through doc() method
+    add_bench_task_fetch_all_strings_from_doc(
+        bench_group,
+        bench_index,
+        query,
+        range_low,
+        range_high,
+    );
+}
+
+fn add_bench_task_count(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    range_low: u64,
+    range_high: u64,
+) {
+    let task_name = format!("string_search_count_[{}-{}]", range_low, range_high);
+
+    let search_task = CountSearchTask {
+        searcher: bench_index.searcher.clone(),
+        query,
+    };
+    bench_group.register(task_name, move |_| black_box(search_task.run()));
+}
+
+fn add_bench_task_docset(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    range_low: u64,
+    range_high: u64,
+) {
+    let task_name = format!("string_fetch_all_docset_[{}-{}]", range_low, range_high);
+
+    let search_task = DocSetSearchTask {
+        searcher: bench_index.searcher.clone(),
+        query,
+    };
+    bench_group.register(task_name, move |_| black_box(search_task.run()));
+}
+
+fn add_bench_task_fetch_all_strings(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    range_low: u64,
+    range_high: u64,
+) {
+    let task_name = format!(
+        "string_fastfield_fetch_all_strings_[{}-{}]",
+        range_low, range_high
+    );
+
+    let search_task = FetchAllStringsSearchTask {
+        searcher: bench_index.searcher.clone(),
+        query,
+    };
+
+    bench_group.register(task_name, move |_| {
+        let result = black_box(search_task.run());
+        result.len()
+    });
+}
+
+fn add_bench_task_fetch_all_strings_from_doc(
+    bench_group: &mut BenchGroup,
+    bench_index: &BenchIndex,
+    query: RangeQuery,
+    range_low: u64,
+    range_high: u64,
+) {
+    let task_name = format!(
+        "string_doc_fetch_all_strings_[{}-{}]",
+        range_low, range_high
+    );
+
+    let search_task = FetchAllStringsFromDocTask {
+        searcher: bench_index.searcher.clone(),
+        query,
+    };
+
+    bench_group.register(task_name, move |_| {
+        let result = black_box(search_task.run());
+        result.len()
+    });
+}
+
+struct CountSearchTask {
+    searcher: Searcher,
+    query: RangeQuery,
+}
+
+impl CountSearchTask {
+    #[inline(never)]
+    pub fn run(&self) -> usize {
+        self.searcher.search(&self.query, &Count).unwrap()
+    }
+}
+
+struct DocSetSearchTask {
+    searcher: Searcher,
+    query: RangeQuery,
+}
+
+impl DocSetSearchTask {
+    #[inline(never)]
+    pub fn run(&self) -> usize {
+        let result = self.searcher.search(&self.query, &DocSetCollector).unwrap();
+        result.len()
+    }
+}
+
+struct FetchAllStringsSearchTask {
+    searcher: Searcher,
+    query: RangeQuery,
+}
+
+impl FetchAllStringsSearchTask {
+    #[inline(never)]
+    pub fn run(&self) -> Vec<String> {
+        let doc_addresses = self.searcher.search(&self.query, &DocSetCollector).unwrap();
+        let mut docs = doc_addresses.into_iter().collect::<Vec<_>>();
+        docs.sort();
+        let mut strings = Vec::with_capacity(docs.len());
+
+        for doc_address in docs {
+            let segment_reader = &self.searcher.segment_readers()[doc_address.segment_ord as usize];
+            let str_column_opt = segment_reader.fast_fields().str("str_fast");
+
+            if let Ok(Some(str_column)) = str_column_opt {
+                let doc_id = doc_address.doc_id;
+                let term_ord = str_column.term_ords(doc_id).next().unwrap();
+                let mut str_buffer = String::new();
+                if str_column.ord_to_str(term_ord, &mut str_buffer).is_ok() {
+                    strings.push(str_buffer);
+                }
+            }
+        }
+
+        strings
+    }
+}
+
+struct FetchAllStringsFromDocTask {
+    searcher: Searcher,
+    query: RangeQuery,
+}
+
+impl FetchAllStringsFromDocTask {
+    #[inline(never)]
+    pub fn run(&self) -> Vec<String> {
+        let doc_addresses = self.searcher.search(&self.query, &DocSetCollector).unwrap();
+        let mut docs = doc_addresses.into_iter().collect::<Vec<_>>();
+        docs.sort();
+        let mut strings = Vec::with_capacity(docs.len());
+
+        let str_stored_field = self
+            .searcher
+            .schema()
+            .get_field("str_stored")
+            .expect("str_stored field should exist");
+
+        for doc_address in docs {
+            // Get the document from the doc store (row store access)
+            if let Ok(doc) = self.searcher.doc::<TantivyDocument>(doc_address) {
+                // Extract string values from the stored field
+                if let Some(field_value) = doc.get_first(str_stored_field) {
+                    if let Some(text) = field_value.as_value().as_str() {
+                        strings.push(text.to_string());
+                    }
+                }
+            }
+        }
+
+        strings
+    }
+}

bitpacker/Cargo.toml

@@ -18,5 +18,5 @@ homepage = "https://github.com/quickwit-oss/tantivy"
 bitpacking = { version = "0.9.2", default-features = false, features = ["bitpacker1x"] }
 
 [dev-dependencies]
-rand = "0.8"
+rand = "0.9"
 proptest = "1"

bitpacker/benches/bench.rs

@@ -4,8 +4,8 @@ extern crate test;
 
 #[cfg(test)]
 mod tests {
+    use rand::rng;
     use rand::seq::IteratorRandom;
-    use rand::thread_rng;
     use tantivy_bitpacker::{BitPacker, BitUnpacker, BlockedBitpacker};
     use test::Bencher;
 
@@ -27,7 +27,7 @@ mod tests {
         let num_els = 1_000_000u32;
         let bit_unpacker = BitUnpacker::new(bit_width);
         let data = create_bitpacked_data(bit_width, num_els);
-        let idxs: Vec<u32> = (0..num_els).choose_multiple(&mut thread_rng(), 100_000);
+        let idxs: Vec<u32> = (0..num_els).choose_multiple(&mut rng(), 100_000);
         b.iter(|| {
             let mut out = 0u64;
             for &idx in &idxs {

bitpacker/src/filter_vec/avx2.rs

@@ -19,7 +19,7 @@ fn u32_to_i32(val: u32) -> i32 {
 #[inline]
 unsafe fn u32_to_i32_avx2(vals_u32x8s: DataType) -> DataType {
     const HIGHEST_BIT_MASK: DataType = from_u32x8([HIGHEST_BIT; NUM_LANES]);
-    op_xor(vals_u32x8s, HIGHEST_BIT_MASK)
+    unsafe { op_xor(vals_u32x8s, HIGHEST_BIT_MASK) }
 }
 
 pub fn filter_vec_in_place(range: RangeInclusive<u32>, offset: u32, output: &mut Vec<u32>) {
@@ -66,17 +66,19 @@ unsafe fn filter_vec_avx2_aux(
     ]);
     const SHIFT: __m256i = from_u32x8([NUM_LANES as u32; NUM_LANES]);
     for _ in 0..num_words {
-        let word = load_unaligned(input);
-        let word = u32_to_i32_avx2(word);
-        let keeper_bitset = compute_filter_bitset(word, range_simd.clone());
-        let added_len = keeper_bitset.count_ones();
-        let filtered_doc_ids = compact(ids, keeper_bitset);
-        store_unaligned(output_tail as *mut __m256i, filtered_doc_ids);
-        output_tail = output_tail.offset(added_len as isize);
-        ids = op_add(ids, SHIFT);
-        input = input.offset(1);
+        unsafe {
+            let word = load_unaligned(input);
+            let word = u32_to_i32_avx2(word);
+            let keeper_bitset = compute_filter_bitset(word, range_simd.clone());
+            let added_len = keeper_bitset.count_ones();
+            let filtered_doc_ids = compact(ids, keeper_bitset);
+            store_unaligned(output_tail as *mut __m256i, filtered_doc_ids);
+            output_tail = output_tail.offset(added_len as isize);
+            ids = op_add(ids, SHIFT);
+            input = input.offset(1);
+        }
     }
-    output_tail.offset_from(output) as usize
+    unsafe { output_tail.offset_from(output) as usize }
 }
 
 #[inline]
@@ -92,8 +94,7 @@ unsafe fn compute_filter_bitset(val: __m256i, range: std::ops::RangeInclusive<__
     let too_low = op_greater(*range.start(), val);
     let too_high = op_greater(val, *range.end());
     let inside = op_or(too_low, too_high);
-    255 - std::arch::x86_64::_mm256_movemask_ps(std::mem::transmute::<DataType, __m256>(inside))
-        as u8
+    255 - std::arch::x86_64::_mm256_movemask_ps(_mm256_castsi256_ps(inside)) as u8
 }
 
 union U8x32 {

columnar/Cargo.toml

@@ -22,7 +22,7 @@ downcast-rs = "2.0.1"
 [dev-dependencies]
 proptest = "1"
 more-asserts = "0.3.1"
-rand = "0.8"
+rand = "0.9"
 binggan = "0.14.0"
 
 [[bench]]

columnar/benches/bench_column_values_get.rs

@@ -9,7 +9,7 @@ use tantivy_columnar::column_values::{CodecType, serialize_and_load_u64_based_co
 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)
+        .map(|num| num + rng.random::<u8>() as u64)
         .collect();
     data.push(99_000);
     data.insert(1000, 2000);

columnar/benches/bench_create_column_values.rs

@@ -6,7 +6,7 @@ use tantivy_columnar::column_values::{CodecType, serialize_u64_based_column_valu
 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)
+        .map(|num| num + rng.random::<u8>() as u64)
         .collect();
     data.push(99_000);
     data.insert(1000, 2000);

columnar/benches/bench_optional_index.rs

@@ -8,7 +8,7 @@ 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))
+        .map(|_| rng.random_bool(fill_ratio))
         .enumerate()
         .filter(|(_pos, val)| *val)
         .map(|(pos, _)| pos as u32)
@@ -25,7 +25,7 @@ fn random_range_iterator(
     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);
+        current += rng.random_range(avg_step_size - avg_deviation..=avg_step_size + avg_deviation);
         if current >= end { None } else { Some(current) }
     })
 }

columnar/benches/bench_values_u128.rs

@@ -39,7 +39,7 @@ fn get_data_50percent_item() -> Vec<u128> {
 
     let mut data = vec![];
     for _ in 0..300_000 {
-        let val = rng.gen_range(1..=100);
+        let val = rng.random_range(1..=100);
         data.push(val);
     }
     data.push(SINGLE_ITEM);

columnar/benches/bench_values_u64.rs

@@ -34,7 +34,7 @@ fn get_data_50percent_item() -> Vec<u128> {
 
     let mut data = vec![];
     for _ in 0..300_000 {
-        let val = rng.gen_range(1..=100);
+        let val = rng.random_range(1..=100);
         data.push(val);
     }
     data.push(SINGLE_ITEM);

columnar/src/block_accessor.rs

@@ -29,12 +29,20 @@ impl<T: PartialOrd + Copy + std::fmt::Debug + Send + Sync + 'static + Default>
         }
     }
     #[inline]
-    pub fn fetch_block_with_missing(&mut self, docs: &[u32], accessor: &Column<T>, missing: T) {
+    pub fn fetch_block_with_missing(
+        &mut self,
+        docs: &[u32],
+        accessor: &Column<T>,
+        missing: Option<T>,
+    ) {
         self.fetch_block(docs, accessor);
         // no missing values
         if accessor.index.get_cardinality().is_full() {
             return;
         }
+        let Some(missing) = missing else {
+            return;
+        };
 
         // We can compare docid_cache length with docs to find missing docs
         // For multi value columns we can't rely on the length and always need to scan

columnar/src/column/mod.rs

@@ -85,8 +85,8 @@ impl<T: PartialOrd + Copy + Debug + Send + Sync + 'static> Column<T> {
     }
 
     #[inline]
-    pub fn first(&self, row_id: RowId) -> Option<T> {
-        self.values_for_doc(row_id).next()
+    pub fn first(&self, doc_id: DocId) -> Option<T> {
+        self.values_for_doc(doc_id).next()
     }
 
     /// Load the first value for each docid in the provided slice.

columnar/src/column_values/u64_based/bitpacked.rs

@@ -41,12 +41,6 @@ fn transform_range_before_linear_transformation(
     if range.is_empty() {
         return None;
     }
-    if stats.min_value > *range.end() {
-        return None;
-    }
-    if stats.max_value < *range.start() {
-        return None;
-    }
     let shifted_range =
         range.start().saturating_sub(stats.min_value)..=range.end().saturating_sub(stats.min_value);
     let start_before_gcd_multiplication: u64 = div_ceil(*shifted_range.start(), stats.gcd);

columnar/src/column_values/u64_based/linear.rs

@@ -268,7 +268,7 @@ mod tests {
 
     #[test]
     fn linear_interpol_fast_field_rand() {
-        let mut rng = rand::thread_rng();
+        let mut rng = rand::rng();
         for _ in 0..50 {
             let mut data = (0..10_000).map(|_| rng.next_u64()).collect::<Vec<_>>();
             create_and_validate::<LinearCodec>(&data, "random");

columnar/src/column_values/u64_based/tests.rs

@@ -122,7 +122,7 @@ pub(crate) fn create_and_validate<TColumnCodec: ColumnCodec>(
     assert_eq!(vals, buffer);
 
     if !vals.is_empty() {
-        let test_rand_idx = rand::thread_rng().gen_range(0..=vals.len() - 1);
+        let test_rand_idx = rand::rng().random_range(0..=vals.len() - 1);
         let expected_positions: Vec<u32> = vals
             .iter()
             .enumerate()

columnar/src/dynamic_column.rs

@@ -3,7 +3,8 @@ use std::sync::Arc;
 use std::{fmt, io};
 
 use common::file_slice::FileSlice;
-use common::{ByteCount, DateTime, HasLen, OwnedBytes};
+use common::{ByteCount, DateTime, OwnedBytes};
+use serde::{Deserialize, Serialize};
 
 use crate::column::{BytesColumn, Column, StrColumn};
 use crate::column_values::{StrictlyMonotonicFn, monotonic_map_column};
@@ -317,10 +318,89 @@ impl DynamicColumnHandle {
     }
 
     pub fn num_bytes(&self) -> ByteCount {
-        self.file_slice.len().into()
+        self.file_slice.num_bytes()
+    }
+
+    /// Legacy helper returning the column space usage.
+    pub fn column_and_dictionary_num_bytes(&self) -> io::Result<ColumnSpaceUsage> {
+        self.space_usage()
+    }
+
+    /// Return the space usage of the column, optionally broken down by dictionary and column
+    /// values.
+    ///
+    /// For dictionary encoded columns (strings and bytes), this splits the total footprint into
+    /// the dictionary and the remaining column data (including index and values).
+    /// For all other column types, the dictionary size is `None` and the column size
+    /// equals the total bytes.
+    pub fn space_usage(&self) -> io::Result<ColumnSpaceUsage> {
+        let total_num_bytes = self.num_bytes();
+        let dynamic_column = self.open()?;
+        let dictionary_num_bytes = match &dynamic_column {
+            DynamicColumn::Bytes(bytes_column) => bytes_column.dictionary().num_bytes(),
+            DynamicColumn::Str(str_column) => str_column.dictionary().num_bytes(),
+            _ => {
+                return Ok(ColumnSpaceUsage::new(self.num_bytes(), None));
+            }
+        };
+        assert!(dictionary_num_bytes <= total_num_bytes);
+        let column_num_bytes =
+            ByteCount::from(total_num_bytes.get_bytes() - dictionary_num_bytes.get_bytes());
+        Ok(ColumnSpaceUsage::new(
+            column_num_bytes,
+            Some(dictionary_num_bytes),
+        ))
     }
 
     pub fn column_type(&self) -> ColumnType {
         self.column_type
     }
 }
+
+/// Represents space usage of a column.
+///
+/// `column_num_bytes` tracks the column payload (index, values and footer).
+/// For dictionary encoded columns, `dictionary_num_bytes` captures the dictionary footprint.
+/// [`ColumnSpaceUsage::total_num_bytes`] returns the sum of both parts.
+#[derive(Clone, Debug, Serialize, Deserialize)]
+pub struct ColumnSpaceUsage {
+    column_num_bytes: ByteCount,
+    dictionary_num_bytes: Option<ByteCount>,
+}
+
+impl ColumnSpaceUsage {
+    pub(crate) fn new(
+        column_num_bytes: ByteCount,
+        dictionary_num_bytes: Option<ByteCount>,
+    ) -> Self {
+        ColumnSpaceUsage {
+            column_num_bytes,
+            dictionary_num_bytes,
+        }
+    }
+
+    pub fn column_num_bytes(&self) -> ByteCount {
+        self.column_num_bytes
+    }
+
+    pub fn dictionary_num_bytes(&self) -> Option<ByteCount> {
+        self.dictionary_num_bytes
+    }
+
+    pub fn total_num_bytes(&self) -> ByteCount {
+        self.column_num_bytes + self.dictionary_num_bytes.unwrap_or_default()
+    }
+
+    /// Merge two space usage values by summing their components.
+    pub fn merge(&self, other: &ColumnSpaceUsage) -> ColumnSpaceUsage {
+        let dictionary_num_bytes = match (self.dictionary_num_bytes, other.dictionary_num_bytes) {
+            (Some(lhs), Some(rhs)) => Some(lhs + rhs),
+            (Some(val), None) | (None, Some(val)) => Some(val),
+            (None, None) => None,
+        };
+        ColumnSpaceUsage {
+            column_num_bytes: self.column_num_bytes + other.column_num_bytes,
+            dictionary_num_bytes,
+        }
+    }
+}

columnar/src/lib.rs

@@ -48,7 +48,7 @@ pub use columnar::{
 use sstable::VoidSSTable;
 pub use value::{NumericalType, NumericalValue};
 
-pub use self::dynamic_column::{DynamicColumn, DynamicColumnHandle};
+pub use self::dynamic_column::{ColumnSpaceUsage, DynamicColumn, DynamicColumnHandle};
 
 pub type RowId = u32;
 pub type DocId = u32;

columnar/src/tests.rs

@@ -60,7 +60,7 @@ fn test_dataframe_writer_bool() {
     let DynamicColumn::Bool(bool_col) = dyn_bool_col else {
         panic!();
     };
-    let vals: Vec<Option<bool>> = (0..5).map(|row_id| bool_col.first(row_id)).collect();
+    let vals: Vec<Option<bool>> = (0..5).map(|doc_id| bool_col.first(doc_id)).collect();
     assert_eq!(&vals, &[None, Some(false), None, Some(true), None,]);
 }
 
@@ -108,7 +108,7 @@ fn test_dataframe_writer_ip_addr() {
     let DynamicColumn::IpAddr(ip_col) = dyn_bool_col else {
         panic!();
     };
-    let vals: Vec<Option<Ipv6Addr>> = (0..5).map(|row_id| ip_col.first(row_id)).collect();
+    let vals: Vec<Option<Ipv6Addr>> = (0..5).map(|doc_id| ip_col.first(doc_id)).collect();
     assert_eq!(
         &vals,
         &[
@@ -169,7 +169,7 @@ fn test_dictionary_encoded_str() {
     let DynamicColumn::Str(str_col) = col_handles[0].open().unwrap() else {
         panic!();
     };
-    let index: Vec<Option<u64>> = (0..5).map(|row_id| str_col.ords().first(row_id)).collect();
+    let index: Vec<Option<u64>> = (0..5).map(|doc_id| str_col.ords().first(doc_id)).collect();
     assert_eq!(index, &[None, Some(0), None, Some(2), Some(1)]);
     assert_eq!(str_col.num_rows(), 5);
     let mut term_buffer = String::new();
@@ -204,7 +204,7 @@ fn test_dictionary_encoded_bytes() {
         panic!();
     };
     let index: Vec<Option<u64>> = (0..5)
-        .map(|row_id| bytes_col.ords().first(row_id))
+        .map(|doc_id| bytes_col.ords().first(doc_id))
         .collect();
     assert_eq!(index, &[None, Some(0), None, Some(2), Some(1)]);
     assert_eq!(bytes_col.num_rows(), 5);

common/Cargo.toml

@@ -21,5 +21,5 @@ serde = { version = "1.0.136", features = ["derive"] }
 [dev-dependencies]
 binggan = "0.14.0"
 proptest = "1.0.0"
-rand = "0.8.4"
+rand = "0.9"
 

common/benches/bench.rs

@@ -1,6 +1,6 @@
 use binggan::{BenchRunner, black_box};
+use rand::rng;
 use rand::seq::IteratorRandom;
-use rand::thread_rng;
 use tantivy_common::{BitSet, TinySet, serialize_vint_u32};
 
 fn bench_vint() {
@@ -17,7 +17,7 @@ fn bench_vint() {
         black_box(out);
     });
 
-    let vals: Vec<u32> = (0..20_000).choose_multiple(&mut thread_rng(), 100_000);
+    let vals: Vec<u32> = (0..20_000).choose_multiple(&mut rng(), 100_000);
     runner.bench_function("bench_vint_rand", move |_| {
         let mut out = 0u64;
         for val in vals.iter().cloned() {

common/src/bitset.rs

@@ -181,6 +181,14 @@ pub struct BitSet {
     len: u64,
     max_value: u32,
 }
+impl std::fmt::Debug for BitSet {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.debug_struct("BitSet")
+            .field("len", &self.len)
+            .field("max_value", &self.max_value)
+            .finish()
+    }
+}
 
 fn num_buckets(max_val: u32) -> u32 {
     max_val.div_ceil(64u32)
@@ -408,7 +416,7 @@ mod tests {
     use std::collections::HashSet;
 
     use ownedbytes::OwnedBytes;
-    use rand::distributions::Bernoulli;
+    use rand::distr::Bernoulli;
     use rand::rngs::StdRng;
     use rand::{Rng, SeedableRng};
 

examples/custom_collector.rs

@@ -70,7 +70,7 @@ impl Collector for StatsCollector {
     fn for_segment(
         &self,
         _segment_local_id: u32,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> tantivy::Result<StatsSegmentCollector> {
         let fast_field_reader = segment_reader.fast_fields().u64(&self.field)?;
         Ok(StatsSegmentCollector {

examples/faceted_search_with_tweaked_score.rs

@@ -65,7 +65,7 @@ fn main() -> tantivy::Result<()> {
         );
         let top_docs_by_custom_score =
             // Call TopDocs with a custom tweak score
-            TopDocs::with_limit(2).tweak_score(move |segment_reader: &SegmentReader| {
+            TopDocs::with_limit(2).tweak_score(move |segment_reader: &dyn SegmentReader| {
                 let ingredient_reader = segment_reader.facet_reader("ingredient").unwrap();
                 let facet_dict = ingredient_reader.facet_dict();
 

examples/warmer.rs

@@ -43,7 +43,7 @@ impl DynamicPriceColumn {
         }
     }
 
-    pub fn price_for_segment(&self, segment_reader: &SegmentReader) -> Option<Arc<Vec<Price>>> {
+    pub fn price_for_segment(&self, segment_reader: &dyn SegmentReader) -> Option<Arc<Vec<Price>>> {
         let segment_key = (segment_reader.segment_id(), segment_reader.delete_opstamp());
         self.price_cache.read().unwrap().get(&segment_key).cloned()
     }
@@ -157,7 +157,7 @@ fn main() -> tantivy::Result<()> {
     let query = query_parser.parse_query("cooking")?;
 
     let searcher = reader.searcher();
-    let score_by_price = move |segment_reader: &SegmentReader| {
+    let score_by_price = move |segment_reader: &dyn SegmentReader| {
         let price = price_dynamic_column
             .price_for_segment(segment_reader)
             .unwrap();

src/aggregation/accessor_helpers.rs

@@ -57,7 +57,7 @@ pub(crate) fn get_numeric_or_date_column_types() -> &'static [ColumnType] {
 
 /// Get fast field reader or empty as default.
 pub(crate) fn get_ff_reader(
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     field_name: &str,
     allowed_column_types: Option<&[ColumnType]>,
 ) -> crate::Result<(columnar::Column<u64>, ColumnType)> {
@@ -74,7 +74,7 @@ pub(crate) fn get_ff_reader(
 }
 
 pub(crate) fn get_dynamic_columns(
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     field_name: &str,
 ) -> crate::Result<Vec<columnar::DynamicColumn>> {
     let ff_fields = reader.fast_fields().dynamic_column_handles(field_name)?;
@@ -90,7 +90,7 @@ pub(crate) fn get_dynamic_columns(
 ///
 /// Is guaranteed to return at least one column.
 pub(crate) fn get_all_ff_reader_or_empty(
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     field_name: &str,
     allowed_column_types: Option<&[ColumnType]>,
     fallback_type: ColumnType,

src/aggregation/agg_data.rs

@@ -1,4 +1,4 @@
-use columnar::{Column, ColumnType, StrColumn};
+use columnar::{Column, ColumnBlockAccessor, ColumnType, StrColumn};
 use common::BitSet;
 use rustc_hash::FxHashSet;
 use serde::Serialize;
@@ -10,16 +10,16 @@ use crate::aggregation::accessor_helpers::{
 };
 use crate::aggregation::agg_req::{Aggregation, AggregationVariants, Aggregations};
 use crate::aggregation::bucket::{
-    FilterAggReqData, HistogramAggReqData, HistogramBounds, IncludeExcludeParam,
-    MissingTermAggReqData, RangeAggReqData, SegmentFilterCollector, SegmentHistogramCollector,
-    SegmentRangeCollector, TermMissingAgg, TermsAggReqData, TermsAggregation,
+    build_segment_filter_collector, build_segment_range_collector, FilterAggReqData,
+    HistogramAggReqData, HistogramBounds, IncludeExcludeParam, MissingTermAggReqData,
+    RangeAggReqData, SegmentHistogramCollector, TermMissingAgg, TermsAggReqData, TermsAggregation,
     TermsAggregationInternal,
 };
 use crate::aggregation::metric::{
-    AverageAggregation, CardinalityAggReqData, CardinalityAggregationReq, CountAggregation,
-    ExtendedStatsAggregation, MaxAggregation, MetricAggReqData, MinAggregation,
-    SegmentCardinalityCollector, SegmentExtendedStatsCollector, SegmentPercentilesCollector,
-    SegmentStatsCollector, StatsAggregation, StatsType, SumAggregation, TopHitsAggReqData,
+    build_segment_stats_collector, AverageAggregation, CardinalityAggReqData,
+    CardinalityAggregationReq, CountAggregation, ExtendedStatsAggregation, MaxAggregation,
+    MetricAggReqData, MinAggregation, SegmentCardinalityCollector, SegmentExtendedStatsCollector,
+    SegmentPercentilesCollector, StatsAggregation, StatsType, SumAggregation, TopHitsAggReqData,
     TopHitsSegmentCollector,
 };
 use crate::aggregation::segment_agg_result::{
@@ -35,6 +35,7 @@ pub struct AggregationsSegmentCtx {
     /// Request data for each aggregation type.
     pub per_request: PerRequestAggSegCtx,
     pub context: AggContextParams,
+    pub column_block_accessor: ColumnBlockAccessor<u64>,
 }
 
 impl AggregationsSegmentCtx {
@@ -107,21 +108,14 @@ impl AggregationsSegmentCtx {
             .as_deref()
             .expect("range_req_data slot is empty (taken)")
     }
-    #[inline]
-    pub(crate) fn get_filter_req_data(&self, idx: usize) -> &FilterAggReqData {
-        self.per_request.filter_req_data[idx]
-            .as_deref()
-            .expect("filter_req_data slot is empty (taken)")
-    }
 
     // ---------- mutable getters ----------
 
     #[inline]
-    pub(crate) fn get_term_req_data_mut(&mut self, idx: usize) -> &mut TermsAggReqData {
-        self.per_request.term_req_data[idx]
-            .as_deref_mut()
-            .expect("term_req_data slot is empty (taken)")
+    pub(crate) fn get_metric_req_data_mut(&mut self, idx: usize) -> &mut MetricAggReqData {
+        &mut self.per_request.stats_metric_req_data[idx]
     }
+
     #[inline]
     pub(crate) fn get_cardinality_req_data_mut(
         &mut self,
@@ -129,10 +123,7 @@ impl AggregationsSegmentCtx {
     ) -> &mut CardinalityAggReqData {
         &mut self.per_request.cardinality_req_data[idx]
     }
-    #[inline]
-    pub(crate) fn get_metric_req_data_mut(&mut self, idx: usize) -> &mut MetricAggReqData {
-        &mut self.per_request.stats_metric_req_data[idx]
-    }
+
     #[inline]
     pub(crate) fn get_histogram_req_data_mut(&mut self, idx: usize) -> &mut HistogramAggReqData {
         self.per_request.histogram_req_data[idx]
@@ -142,21 +133,6 @@ impl AggregationsSegmentCtx {
 
     // ---------- take / put (terms, histogram, range) ----------
 
-    /// Move out the boxed Terms request at `idx`, leaving `None`.
-    #[inline]
-    pub(crate) fn take_term_req_data(&mut self, idx: usize) -> Box<TermsAggReqData> {
-        self.per_request.term_req_data[idx]
-            .take()
-            .expect("term_req_data slot is empty (taken)")
-    }
-
-    /// Put back a Terms request into an empty slot at `idx`.
-    #[inline]
-    pub(crate) fn put_back_term_req_data(&mut self, idx: usize, value: Box<TermsAggReqData>) {
-        debug_assert!(self.per_request.term_req_data[idx].is_none());
-        self.per_request.term_req_data[idx] = Some(value);
-    }
-
     /// Move out the boxed Histogram request at `idx`, leaving `None`.
     #[inline]
     pub(crate) fn take_histogram_req_data(&mut self, idx: usize) -> Box<HistogramAggReqData> {
@@ -320,6 +296,7 @@ impl PerRequestAggSegCtx {
 
     /// Convert the aggregation tree into a serializable struct representation.
     /// Each node contains: { name, kind, children }.
+    #[allow(dead_code)]
     pub fn get_view_tree(&self) -> Vec<AggTreeViewNode> {
         fn node_to_view(node: &AggRefNode, pr: &PerRequestAggSegCtx) -> AggTreeViewNode {
             let mut children: Vec<AggTreeViewNode> =
@@ -345,12 +322,19 @@ impl PerRequestAggSegCtx {
 pub(crate) fn build_segment_agg_collectors_root(
     req: &mut AggregationsSegmentCtx,
 ) -> crate::Result<Box<dyn SegmentAggregationCollector>> {
-    build_segment_agg_collectors(req, &req.per_request.agg_tree.clone())
+    build_segment_agg_collectors_generic(req, &req.per_request.agg_tree.clone())
 }
 
 pub(crate) fn build_segment_agg_collectors(
     req: &mut AggregationsSegmentCtx,
     nodes: &[AggRefNode],
+) -> crate::Result<Box<dyn SegmentAggregationCollector>> {
+    build_segment_agg_collectors_generic(req, nodes)
+}
+
+fn build_segment_agg_collectors_generic(
+    req: &mut AggregationsSegmentCtx,
+    nodes: &[AggRefNode],
 ) -> crate::Result<Box<dyn SegmentAggregationCollector>> {
     let mut collectors = Vec::new();
     for node in nodes.iter() {
@@ -388,6 +372,8 @@ pub(crate) fn build_segment_agg_collector(
             Ok(Box::new(SegmentCardinalityCollector::from_req(
                 req_data.column_type,
                 node.idx_in_req_data,
+                req_data.accessor.clone(),
+                req_data.missing_value_for_accessor,
             )))
         }
         AggKind::StatsKind(stats_type) => {
@@ -398,20 +384,21 @@ pub(crate) fn build_segment_agg_collector(
                 | StatsType::Count
                 | StatsType::Max
                 | StatsType::Min
-                | StatsType::Stats => Ok(Box::new(SegmentStatsCollector::from_req(
-                    node.idx_in_req_data,
-                ))),
-                StatsType::ExtendedStats(sigma) => {
-                    Ok(Box::new(SegmentExtendedStatsCollector::from_req(
-                        req_data.field_type,
-                        sigma,
-                        node.idx_in_req_data,
-                        req_data.missing,
-                    )))
-                }
-                StatsType::Percentiles => Ok(Box::new(
-                    SegmentPercentilesCollector::from_req_and_validate(node.idx_in_req_data)?,
+                | StatsType::Stats => build_segment_stats_collector(req_data),
+                StatsType::ExtendedStats(sigma) => Ok(Box::new(
+                    SegmentExtendedStatsCollector::from_req(req_data, sigma),
                 )),
+                StatsType::Percentiles => {
+                    let req_data = req.get_metric_req_data_mut(node.idx_in_req_data);
+                    Ok(Box::new(
+                        SegmentPercentilesCollector::from_req_and_validate(
+                            req_data.field_type,
+                            req_data.missing_u64,
+                            req_data.accessor.clone(),
+                            node.idx_in_req_data,
+                        ),
+                    ))
+                }
             }
         }
         AggKind::TopHits => {
@@ -428,12 +415,8 @@ pub(crate) fn build_segment_agg_collector(
         AggKind::DateHistogram => Ok(Box::new(SegmentHistogramCollector::from_req_and_validate(
             req, node,
         )?)),
-        AggKind::Range => Ok(Box::new(SegmentRangeCollector::from_req_and_validate(
-            req, node,
-        )?)),
-        AggKind::Filter => Ok(Box::new(SegmentFilterCollector::from_req_and_validate(
-            req, node,
-        )?)),
+        AggKind::Range => Ok(build_segment_range_collector(req, node)?),
+        AggKind::Filter => build_segment_filter_collector(req, node),
     }
 }
 
@@ -486,13 +469,14 @@ impl AggKind {
 /// Build AggregationsData by walking the request tree.
 pub(crate) fn build_aggregations_data_from_req(
     aggs: &Aggregations,
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     segment_ordinal: SegmentOrdinal,
     context: AggContextParams,
 ) -> crate::Result<AggregationsSegmentCtx> {
     let mut data = AggregationsSegmentCtx {
         per_request: Default::default(),
         context,
+        column_block_accessor: ColumnBlockAccessor::default(),
     };
 
     for (name, agg) in aggs.iter() {
@@ -505,7 +489,7 @@ pub(crate) fn build_aggregations_data_from_req(
 fn build_nodes(
     agg_name: &str,
     req: &Aggregation,
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     segment_ordinal: SegmentOrdinal,
     data: &mut AggregationsSegmentCtx,
     is_top_level: bool,
@@ -521,9 +505,9 @@ fn build_nodes(
             let idx_in_req_data = data.push_range_req_data(RangeAggReqData {
                 accessor,
                 field_type,
-                column_block_accessor: Default::default(),
                 name: agg_name.to_string(),
                 req: range_req.clone(),
+                is_top_level,
             });
             let children = build_children(&req.sub_aggregation, reader, segment_ordinal, data)?;
             Ok(vec![AggRefNode {
@@ -541,9 +525,7 @@ fn build_nodes(
             let idx_in_req_data = data.push_histogram_req_data(HistogramAggReqData {
                 accessor,
                 field_type,
-                column_block_accessor: Default::default(),
                 name: agg_name.to_string(),
-                sub_aggregation_blueprint: None,
                 req: histo_req.clone(),
                 is_date_histogram: false,
                 bounds: HistogramBounds {
@@ -568,9 +550,7 @@ fn build_nodes(
             let idx_in_req_data = data.push_histogram_req_data(HistogramAggReqData {
                 accessor,
                 field_type,
-                column_block_accessor: Default::default(),
                 name: agg_name.to_string(),
-                sub_aggregation_blueprint: None,
                 req: histo_req,
                 is_date_histogram: true,
                 bounds: HistogramBounds {
@@ -650,7 +630,6 @@ fn build_nodes(
             let idx_in_req_data = data.push_metric_req_data(MetricAggReqData {
                 accessor,
                 field_type,
-                column_block_accessor: Default::default(),
                 name: agg_name.to_string(),
                 collecting_for,
                 missing: *missing,
@@ -678,7 +657,6 @@ fn build_nodes(
             let idx_in_req_data = data.push_metric_req_data(MetricAggReqData {
                 accessor,
                 field_type,
-                column_block_accessor: Default::default(),
                 name: agg_name.to_string(),
                 collecting_for: StatsType::Percentiles,
                 missing: percentiles_req.missing,
@@ -750,9 +728,9 @@ fn build_nodes(
             let idx_in_req_data = data.push_filter_req_data(FilterAggReqData {
                 name: agg_name.to_string(),
                 req: filter_req.clone(),
-                segment_reader: reader.clone(),
                 evaluator,
                 matching_docs_buffer,
+                is_top_level,
             });
             let children = build_children(&req.sub_aggregation, reader, segment_ordinal, data)?;
             Ok(vec![AggRefNode {
@@ -766,7 +744,7 @@ fn build_nodes(
 
 fn build_children(
     aggs: &Aggregations,
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     segment_ordinal: SegmentOrdinal,
     data: &mut AggregationsSegmentCtx,
 ) -> crate::Result<Vec<AggRefNode>> {
@@ -785,7 +763,7 @@ fn build_children(
 }
 
 fn get_term_agg_accessors(
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     field_name: &str,
     missing: &Option<Key>,
 ) -> crate::Result<Vec<(Column<u64>, ColumnType)>> {
@@ -838,7 +816,7 @@ fn build_terms_or_cardinality_nodes(
     agg_name: &str,
     field_name: &str,
     missing: &Option<Key>,
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     segment_ordinal: SegmentOrdinal,
     data: &mut AggregationsSegmentCtx,
     sub_aggs: &Aggregations,
@@ -895,7 +873,7 @@ fn build_terms_or_cardinality_nodes(
         });
     }
 
-    // Add one node per accessor to mirror previous behavior and allow per-type missing handling.
+    // Add one node per accessor
     for (accessor, column_type) in column_and_types {
         let missing_value_for_accessor = if use_special_missing_agg {
             None
@@ -926,11 +904,8 @@ fn build_terms_or_cardinality_nodes(
                     column_type,
                     str_dict_column: str_dict_column.clone(),
                     missing_value_for_accessor,
-                    column_block_accessor: Default::default(),
                     name: agg_name.to_string(),
                     req: TermsAggregationInternal::from_req(req),
-                    // Will be filled later when building collectors
-                    sub_aggregation_blueprint: None,
                     sug_aggregations: sub_aggs.clone(),
                     allowed_term_ids,
                     is_top_level,
@@ -943,7 +918,6 @@ fn build_terms_or_cardinality_nodes(
                     column_type,
                     str_dict_column: str_dict_column.clone(),
                     missing_value_for_accessor,
-                    column_block_accessor: Default::default(),
                     name: agg_name.to_string(),
                     req: req.clone(),
                 });

src/aggregation/agg_tests.rs

@@ -2,15 +2,441 @@ use serde_json::Value;
 
 use crate::aggregation::agg_req::{Aggregation, Aggregations};
 use crate::aggregation::agg_result::AggregationResults;
-use crate::aggregation::buf_collector::DOC_BLOCK_SIZE;
 use crate::aggregation::collector::AggregationCollector;
 use crate::aggregation::intermediate_agg_result::IntermediateAggregationResults;
 use crate::aggregation::tests::{get_test_index_2_segments, get_test_index_from_values_and_terms};
 use crate::aggregation::DistributedAggregationCollector;
+use crate::docset::COLLECT_BLOCK_BUFFER_LEN;
 use crate::query::{AllQuery, TermQuery};
 use crate::schema::{IndexRecordOption, Schema, FAST};
 use crate::{Index, IndexWriter, Term};
 
+// The following tests ensure that each bucket aggregation type correctly functions as a
+// sub-aggregation of another bucket aggregation in two scenarios:
+// 1) The parent has more buckets than the child sub-aggregation
+// 2) The child sub-aggregation has more buckets than the parent
+//
+// These scenarios exercise the bucket id mapping and sub-aggregation routing logic.
+
+#[test]
+fn test_terms_as_subagg_parent_more_vs_child_more() -> crate::Result<()> {
+    let index = get_test_index_2_segments(false)?;
+
+    // Case A: parent has more buckets than child
+    // Parent: range with 4 buckets
+    // Child: terms on text -> 2 buckets
+    let agg_parent_more: Aggregations = serde_json::from_value(json!({
+        "parent_range": {
+            "range": {
+                "field": "score",
+                "ranges": [
+                    {"to": 3.0},
+                    {"from": 3.0, "to": 7.0},
+                    {"from": 7.0, "to": 20.0},
+                    {"from": 20.0}
+                ]
+            },
+            "aggs": {
+                "child_terms": {"terms": {"field": "text", "order": {"_key": "asc"}}}
+            }
+        }
+    }))
+    .unwrap();
+
+    let res = crate::aggregation::tests::exec_request(agg_parent_more, &index)?;
+    // Exact expected structure and counts
+    assert_eq!(
+        res["parent_range"]["buckets"],
+        json!([
+            {
+                "key": "*-3",
+                "doc_count": 1,
+                "to": 3.0,
+                "child_terms": {
+                    "buckets": [
+                        {"doc_count": 1, "key": "cool"}
+                    ],
+                    "sum_other_doc_count": 0
+                }
+            },
+            {
+                "key": "3-7",
+                "doc_count": 3,
+                "from": 3.0,
+                "to": 7.0,
+                "child_terms": {
+                    "buckets": [
+                        {"doc_count": 2, "key": "cool"},
+                        {"doc_count": 1, "key": "nohit"}
+                    ],
+                    "sum_other_doc_count": 0
+                }
+            },
+            {
+                "key": "7-20",
+                "doc_count": 3,
+                "from": 7.0,
+                "to": 20.0,
+                "child_terms": {
+                    "buckets": [
+                        {"doc_count": 3, "key": "cool"}
+                    ],
+                    "sum_other_doc_count": 0
+                }
+            },
+            {
+                "key": "20-*",
+                "doc_count": 2,
+                "from": 20.0,
+                "child_terms": {
+                    "buckets": [
+                        {"doc_count": 1, "key": "cool"},
+                        {"doc_count": 1, "key": "nohit"}
+                    ],
+                    "sum_other_doc_count": 0
+                }
+            }
+        ])
+    );
+
+    // Case B: child has more buckets than parent
+    // Parent: histogram on score with large interval -> 1 bucket
+    // Child: terms on text -> 2 buckets (cool/nohit)
+    let agg_child_more: Aggregations = serde_json::from_value(json!({
+        "parent_hist": {
+            "histogram": {"field": "score", "interval": 100.0},
+            "aggs": {
+                "child_terms": {"terms": {"field": "text", "order": {"_key": "asc"}}}
+            }
+        }
+    }))
+    .unwrap();
+
+    let res = crate::aggregation::tests::exec_request(agg_child_more, &index)?;
+    assert_eq!(
+        res["parent_hist"],
+        json!({
+            "buckets": [
+                {
+                    "key": 0.0,
+                    "doc_count": 9,
+                    "child_terms": {
+                        "buckets": [
+                            {"doc_count": 7, "key": "cool"},
+                            {"doc_count": 2, "key": "nohit"}
+                        ],
+                        "sum_other_doc_count": 0
+                    }
+                }
+            ]
+        })
+    );
+
+    Ok(())
+}
+
+#[test]
+fn test_range_as_subagg_parent_more_vs_child_more() -> crate::Result<()> {
+    let index = get_test_index_2_segments(false)?;
+
+    // Case A: parent has more buckets than child
+    // Parent: range with 5 buckets
+    // Child: coarse range with 3 buckets
+    let agg_parent_more: Aggregations = serde_json::from_value(json!({
+        "parent_range": {
+            "range": {
+                "field": "score",
+                "ranges": [
+                    {"to": 3.0},
+                    {"from": 3.0, "to": 7.0},
+                    {"from": 7.0, "to": 11.0},
+                    {"from": 11.0, "to": 20.0},
+                    {"from": 20.0}
+                ]
+            },
+            "aggs": {
+                "child_range": {
+                    "range": {
+                        "field": "score",
+                        "ranges": [
+                            {"to": 3.0},
+                            {"from": 3.0, "to": 20.0}
+                        ]
+                    }
+                }
+            }
+        }
+    }))
+    .unwrap();
+    let res = crate::aggregation::tests::exec_request(agg_parent_more, &index)?;
+    assert_eq!(
+        res["parent_range"]["buckets"],
+        json!([
+            {"key": "*-3", "doc_count": 1, "to": 3.0,
+                "child_range": {"buckets": [
+                    {"key": "*-3", "doc_count": 1, "to": 3.0},
+                    {"key": "3-20", "doc_count": 0, "from": 3.0, "to": 20.0},
+                    {"key": "20-*", "doc_count": 0, "from": 20.0}
+                ]}
+            },
+            {"key": "3-7", "doc_count": 3, "from": 3.0, "to": 7.0,
+                "child_range": {"buckets": [
+                    {"key": "*-3", "doc_count": 0, "to": 3.0},
+                    {"key": "3-20", "doc_count": 3, "from": 3.0, "to": 20.0},
+                    {"key": "20-*", "doc_count": 0, "from": 20.0}
+                ]}
+            },
+            {"key": "7-11", "doc_count": 1, "from": 7.0, "to": 11.0,
+                "child_range": {"buckets": [
+                    {"key": "*-3", "doc_count": 0, "to": 3.0},
+                    {"key": "3-20", "doc_count": 1, "from": 3.0, "to": 20.0},
+                    {"key": "20-*", "doc_count": 0, "from": 20.0}
+                ]}
+            },
+            {"key": "11-20", "doc_count": 2, "from": 11.0, "to": 20.0,
+                "child_range": {"buckets": [
+                    {"key": "*-3", "doc_count": 0, "to": 3.0},
+                    {"key": "3-20", "doc_count": 2, "from": 3.0, "to": 20.0},
+                    {"key": "20-*", "doc_count": 0, "from": 20.0}
+                ]}
+            },
+            {"key": "20-*", "doc_count": 2, "from": 20.0,
+                "child_range": {"buckets": [
+                    {"key": "*-3", "doc_count": 0, "to": 3.0},
+                    {"key": "3-20", "doc_count": 0, "from": 3.0, "to": 20.0},
+                    {"key": "20-*", "doc_count": 2, "from": 20.0}
+                ]}
+            }
+        ])
+    );
+
+    // Case B: child has more buckets than parent
+    // Parent: terms on text (2 buckets)
+    // Child: range with 4 buckets
+    let agg_child_more: Aggregations = serde_json::from_value(json!({
+        "parent_terms": {
+            "terms": {"field": "text"},
+            "aggs": {
+                "child_range": {
+                    "range": {
+                        "field": "score",
+                        "ranges": [
+                            {"to": 3.0},
+                            {"from": 3.0, "to": 7.0},
+                            {"from": 7.0, "to": 20.0}
+                        ]
+                    }
+                }
+            }
+        }
+    }))
+    .unwrap();
+    let res = crate::aggregation::tests::exec_request(agg_child_more, &index)?;
+
+    assert_eq!(
+        res["parent_terms"],
+        json!({
+            "buckets": [
+                {
+                    "key": "cool",
+                    "doc_count": 7,
+                    "child_range": {
+                        "buckets": [
+                            {"key": "*-3", "doc_count": 1, "to": 3.0},
+                            {"key": "3-7", "doc_count": 2, "from": 3.0, "to": 7.0},
+                            {"key": "7-20", "doc_count": 3, "from": 7.0, "to": 20.0},
+                            {"key": "20-*", "doc_count": 1, "from": 20.0}
+                        ]
+                    }
+                },
+                {
+                    "key": "nohit",
+                    "doc_count": 2,
+                    "child_range": {
+                        "buckets": [
+                            {"key": "*-3", "doc_count": 0, "to": 3.0},
+                            {"key": "3-7", "doc_count": 1, "from": 3.0, "to": 7.0},
+                            {"key": "7-20", "doc_count": 0, "from": 7.0, "to": 20.0},
+                            {"key": "20-*", "doc_count": 1, "from": 20.0}
+                        ]
+                    }
+                }
+            ],
+            "doc_count_error_upper_bound": 0,
+            "sum_other_doc_count": 0
+        })
+    );
+
+    Ok(())
+}
+
+#[test]
+fn test_histogram_as_subagg_parent_more_vs_child_more() -> crate::Result<()> {
+    let index = get_test_index_2_segments(false)?;
+
+    // Case A: parent has more buckets than child
+    // Parent: range with several ranges
+    // Child: histogram with large interval (single bucket per parent)
+    let agg_parent_more: Aggregations = serde_json::from_value(json!({
+        "parent_range": {
+            "range": {
+                "field": "score",
+                "ranges": [
+                    {"to": 3.0},
+                    {"from": 3.0, "to": 7.0},
+                    {"from": 7.0, "to": 11.0},
+                    {"from": 11.0, "to": 20.0},
+                    {"from": 20.0}
+                ]
+            },
+            "aggs": {
+                "child_hist": {"histogram": {"field": "score", "interval": 100.0}}
+            }
+        }
+    }))
+    .unwrap();
+    let res = crate::aggregation::tests::exec_request(agg_parent_more, &index)?;
+    assert_eq!(
+        res["parent_range"]["buckets"],
+        json!([
+            {"key": "*-3", "doc_count": 1, "to": 3.0,
+                "child_hist": {"buckets": [ {"key": 0.0, "doc_count": 1} ]}
+            },
+            {"key": "3-7", "doc_count": 3, "from": 3.0, "to": 7.0,
+                "child_hist": {"buckets": [ {"key": 0.0, "doc_count": 3} ]}
+            },
+            {"key": "7-11", "doc_count": 1, "from": 7.0, "to": 11.0,
+                "child_hist": {"buckets": [ {"key": 0.0, "doc_count": 1} ]}
+            },
+            {"key": "11-20", "doc_count": 2, "from": 11.0, "to": 20.0,
+                "child_hist": {"buckets": [ {"key": 0.0, "doc_count": 2} ]}
+            },
+            {"key": "20-*", "doc_count": 2, "from": 20.0,
+                "child_hist": {"buckets": [ {"key": 0.0, "doc_count": 2} ]}
+            }
+        ])
+    );
+
+    // Case B: child has more buckets than parent
+    // Parent: terms on text -> 2 buckets
+    // Child: histogram with small interval -> multiple buckets including empties
+    let agg_child_more: Aggregations = serde_json::from_value(json!({
+        "parent_terms": {
+            "terms": {"field": "text"},
+            "aggs": {
+                "child_hist": {"histogram": {"field": "score", "interval": 10.0}}
+            }
+        }
+    }))
+    .unwrap();
+    let res = crate::aggregation::tests::exec_request(agg_child_more, &index)?;
+    assert_eq!(
+        res["parent_terms"],
+        json!({
+            "buckets": [
+                {
+                    "key": "cool",
+                    "doc_count": 7,
+                    "child_hist": {
+                        "buckets": [
+                            {"key": 0.0, "doc_count": 4},
+                            {"key": 10.0, "doc_count": 2},
+                            {"key": 20.0, "doc_count": 0},
+                            {"key": 30.0, "doc_count": 0},
+                            {"key": 40.0, "doc_count": 1}
+                        ]
+                    }
+                },
+                {
+                    "key": "nohit",
+                    "doc_count": 2,
+                    "child_hist": {
+                        "buckets": [
+                            {"key": 0.0, "doc_count": 1},
+                            {"key": 10.0, "doc_count": 0},
+                            {"key": 20.0, "doc_count": 0},
+                            {"key": 30.0, "doc_count": 0},
+                            {"key": 40.0, "doc_count": 1}
+                        ]
+                    }
+                }
+            ],
+            "doc_count_error_upper_bound": 0,
+            "sum_other_doc_count": 0
+        })
+    );
+
+    Ok(())
+}
+
+#[test]
+fn test_date_histogram_as_subagg_parent_more_vs_child_more() -> crate::Result<()> {
+    let index = get_test_index_2_segments(false)?;
+
+    // Case A: parent has more buckets than child
+    // Parent: range with several buckets
+    // Child: date_histogram with 30d -> single bucket per parent
+    let agg_parent_more: Aggregations = serde_json::from_value(json!({
+        "parent_range": {
+            "range": {
+                "field": "score",
+                "ranges": [
+                    {"to": 3.0},
+                    {"from": 3.0, "to": 7.0},
+                    {"from": 7.0, "to": 11.0},
+                    {"from": 11.0, "to": 20.0},
+                    {"from": 20.0}
+                ]
+            },
+            "aggs": {
+                "child_date_hist": {"date_histogram": {"field": "date", "fixed_interval": "30d"}}
+            }
+        }
+    }))
+    .unwrap();
+    let res = crate::aggregation::tests::exec_request(agg_parent_more, &index)?;
+    let buckets = res["parent_range"]["buckets"].as_array().unwrap();
+    // Verify each parent bucket has exactly one child date bucket with matching doc_count
+    for bucket in buckets {
+        let parent_count = bucket["doc_count"].as_u64().unwrap();
+        let child_buckets = bucket["child_date_hist"]["buckets"].as_array().unwrap();
+        assert_eq!(child_buckets.len(), 1);
+        assert_eq!(child_buckets[0]["doc_count"], parent_count);
+    }
+
+    // Case B: child has more buckets than parent
+    // Parent: terms on text (2 buckets)
+    // Child: date_histogram with 1d -> multiple buckets
+    let agg_child_more: Aggregations = serde_json::from_value(json!({
+        "parent_terms": {
+            "terms": {"field": "text"},
+            "aggs": {
+                "child_date_hist": {"date_histogram": {"field": "date", "fixed_interval": "1d"}}
+            }
+        }
+    }))
+    .unwrap();
+    let res = crate::aggregation::tests::exec_request(agg_child_more, &index)?;
+    let buckets = res["parent_terms"]["buckets"].as_array().unwrap();
+
+    // cool bucket
+    assert_eq!(buckets[0]["key"], "cool");
+    let cool_buckets = buckets[0]["child_date_hist"]["buckets"].as_array().unwrap();
+    assert_eq!(cool_buckets.len(), 3);
+    assert_eq!(cool_buckets[0]["doc_count"], 1); // day 0
+    assert_eq!(cool_buckets[1]["doc_count"], 4); // day 1
+    assert_eq!(cool_buckets[2]["doc_count"], 2); // day 2
+
+    // nohit bucket
+    assert_eq!(buckets[1]["key"], "nohit");
+    let nohit_buckets = buckets[1]["child_date_hist"]["buckets"].as_array().unwrap();
+    assert_eq!(nohit_buckets.len(), 2);
+    assert_eq!(nohit_buckets[0]["doc_count"], 1); // day 1
+    assert_eq!(nohit_buckets[1]["doc_count"], 1); // day 2
+
+    Ok(())
+}
+
 fn get_avg_req(field_name: &str) -> Aggregation {
     serde_json::from_value(json!({
         "avg": {
@@ -25,6 +451,10 @@ fn get_collector(agg_req: Aggregations) -> AggregationCollector {
 }
 
 // *** EVERY BUCKET-TYPE SHOULD BE TESTED HERE ***
+// Note: The flushng part of these  tests are outdated, since the buffering change after converting
+// the collection into one collector per request instead of per bucket.
+//
+// However they are useful as they test a complex aggregation requests.
 fn test_aggregation_flushing(
     merge_segments: bool,
     use_distributed_collector: bool,
@@ -37,8 +467,9 @@ fn test_aggregation_flushing(
 
     let reader = index.reader()?;
 
-    assert_eq!(DOC_BLOCK_SIZE, 64);
-    // In the tree we cache Documents of DOC_BLOCK_SIZE, before passing them down as one block.
+    assert_eq!(COLLECT_BLOCK_BUFFER_LEN, 64);
+    // In the tree we cache documents of COLLECT_BLOCK_BUFFER_LEN before passing them down as one
+    // block.
     //
     // Build a request so that on the first level we have one full cache, which is then flushed.
     // The same cache should have some residue docs at the end, which are flushed (Range 0-70)

src/aggregation/bucket/filter.rs

@@ -6,10 +6,14 @@ use serde::{Deserialize, Deserializer, Serialize, Serializer};
 use crate::aggregation::agg_data::{
     build_segment_agg_collectors, AggRefNode, AggregationsSegmentCtx,
 };
+use crate::aggregation::cached_sub_aggs::{
+    CachedSubAggs, HighCardSubAggCache, LowCardSubAggCache, SubAggCache,
+};
 use crate::aggregation::intermediate_agg_result::{
     IntermediateAggregationResult, IntermediateAggregationResults, IntermediateBucketResult,
 };
-use crate::aggregation::segment_agg_result::{CollectorClone, SegmentAggregationCollector};
+use crate::aggregation::segment_agg_result::{BucketIdProvider, SegmentAggregationCollector};
+use crate::aggregation::BucketId;
 use crate::docset::DocSet;
 use crate::query::{AllQuery, EnableScoring, Query, QueryParser};
 use crate::schema::Schema;
@@ -397,22 +401,22 @@ pub struct FilterAggReqData {
     pub name: String,
     /// The filter aggregation
     pub req: FilterAggregation,
-    /// The segment reader
-    pub segment_reader: SegmentReader,
     /// Document evaluator for the filter query (precomputed BitSet)
     /// This is built once when the request data is created
     pub evaluator: DocumentQueryEvaluator,
     /// Reusable buffer for matching documents to minimize allocations during collection
     pub matching_docs_buffer: Vec<DocId>,
+    /// True if this filter aggregation is at the top level of the aggregation tree (not nested).
+    pub is_top_level: bool,
 }
 
 impl FilterAggReqData {
     pub(crate) fn get_memory_consumption(&self) -> usize {
-        // Estimate: name + segment reader reference + bitset + buffer capacity
+        // Estimate: name + bitset + buffer capacity
         self.name.len()
-            + std::mem::size_of::<SegmentReader>()
-            + self.evaluator.bitset.len() / 8 // BitSet memory (bits to bytes)
-            + self.matching_docs_buffer.capacity() * std::mem::size_of::<DocId>()
+        + self.evaluator.bitset.len() / 8 // BitSet memory (bits to bytes)
+        + self.matching_docs_buffer.capacity() * std::mem::size_of::<DocId>()
+        + std::mem::size_of::<bool>()
     }
 }
 
@@ -431,7 +435,7 @@ impl DocumentQueryEvaluator {
     pub(crate) fn new(
         query: Box<dyn Query>,
         schema: Schema,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self> {
         let max_doc = segment_reader.max_doc();
 
@@ -489,17 +493,24 @@ impl Debug for DocumentQueryEvaluator {
     }
 }
 
-/// Segment collector for filter aggregation
-pub struct SegmentFilterCollector {
-    /// Document count in this bucket
+#[derive(Debug, Clone, PartialEq, Copy)]
+struct DocCount {
     doc_count: u64,
+    bucket_id: BucketId,
+}
+
+/// Segment collector for filter aggregation
+pub struct SegmentFilterCollector<C: SubAggCache> {
+    /// Document counts per parent bucket
+    parent_buckets: Vec<DocCount>,
     /// Sub-aggregation collectors
-    sub_aggregations: Option<Box<dyn SegmentAggregationCollector>>,
+    sub_aggregations: Option<CachedSubAggs<C>>,
+    bucket_id_provider: BucketIdProvider,
     /// Accessor index for this filter aggregation (to access FilterAggReqData)
     accessor_idx: usize,
 }
 
-impl SegmentFilterCollector {
+impl<C: SubAggCache> SegmentFilterCollector<C> {
     /// Create a new filter segment collector following the new agg_data pattern
     pub(crate) fn from_req_and_validate(
         req: &mut AggregationsSegmentCtx,
@@ -511,47 +522,75 @@ impl SegmentFilterCollector {
         } else {
             None
         };
+        let sub_agg_collector = sub_agg_collector.map(CachedSubAggs::new);
 
         Ok(SegmentFilterCollector {
-            doc_count: 0,
+            parent_buckets: Vec::new(),
             sub_aggregations: sub_agg_collector,
             accessor_idx: node.idx_in_req_data,
+            bucket_id_provider: BucketIdProvider::default(),
         })
     }
 }
 
-impl Debug for SegmentFilterCollector {
+pub(crate) fn build_segment_filter_collector(
+    req: &mut AggregationsSegmentCtx,
+    node: &AggRefNode,
+) -> crate::Result<Box<dyn SegmentAggregationCollector>> {
+    let is_top_level = req.per_request.filter_req_data[node.idx_in_req_data]
+        .as_ref()
+        .expect("filter_req_data slot is empty")
+        .is_top_level;
+
+    if is_top_level {
+        Ok(Box::new(
+            SegmentFilterCollector::<LowCardSubAggCache>::from_req_and_validate(req, node)?,
+        ))
+    } else {
+        Ok(Box::new(
+            SegmentFilterCollector::<HighCardSubAggCache>::from_req_and_validate(req, node)?,
+        ))
+    }
+}
+
+impl<C: SubAggCache> Debug for SegmentFilterCollector<C> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         f.debug_struct("SegmentFilterCollector")
-            .field("doc_count", &self.doc_count)
+            .field("buckets", &self.parent_buckets)
             .field("has_sub_aggs", &self.sub_aggregations.is_some())
             .field("accessor_idx", &self.accessor_idx)
             .finish()
     }
 }
 
-impl CollectorClone for SegmentFilterCollector {
-    fn clone_box(&self) -> Box<dyn SegmentAggregationCollector> {
-        // For now, panic - this needs proper implementation with weight recreation
-        panic!("SegmentFilterCollector cloning not yet implemented - requires weight recreation")
-    }
-}
-
-impl SegmentAggregationCollector for SegmentFilterCollector {
+impl<C: SubAggCache> SegmentAggregationCollector for SegmentFilterCollector<C> {
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
         let mut sub_results = IntermediateAggregationResults::default();
+        let bucket_opt = self.parent_buckets.get(parent_bucket_id as usize);
 
-        if let Some(sub_aggs) = self.sub_aggregations {
-            sub_aggs.add_intermediate_aggregation_result(agg_data, &mut sub_results)?;
+        if let Some(sub_aggs) = &mut self.sub_aggregations {
+            sub_aggs
+                .get_sub_agg_collector()
+                .add_intermediate_aggregation_result(
+                    agg_data,
+                    &mut sub_results,
+                    // Here we create a new bucket ID for sub-aggregations if the bucket doesn't
+                    // exist, so that sub-aggregations can still produce results (e.g., zero doc
+                    // count)
+                    bucket_opt
+                        .map(|bucket| bucket.bucket_id)
+                        .unwrap_or(self.bucket_id_provider.next_bucket_id()),
+                )?;
         }
 
         // Create the filter bucket result
         let filter_bucket_result = IntermediateBucketResult::Filter {
-            doc_count: self.doc_count,
+            doc_count: bucket_opt.map(|b| b.doc_count).unwrap_or(0),
             sub_aggregations: sub_results,
         };
 
@@ -570,32 +609,17 @@ impl SegmentAggregationCollector for SegmentFilterCollector {
         Ok(())
     }
 
-    fn collect(&mut self, doc: DocId, agg_data: &mut AggregationsSegmentCtx) -> crate::Result<()> {
-        // Access the evaluator from FilterAggReqData
-        let req_data = agg_data.get_filter_req_data(self.accessor_idx);
-
-        // O(1) BitSet lookup to check if document matches filter
-        if req_data.evaluator.matches_document(doc) {
-            self.doc_count += 1;
-
-            // If we have sub-aggregations, collect on them for this filtered document
-            if let Some(sub_aggs) = &mut self.sub_aggregations {
-                sub_aggs.collect(doc, agg_data)?;
-            }
-        }
-        Ok(())
-    }
-
-    #[inline]
-    fn collect_block(
+    fn collect(
         &mut self,
-        docs: &[DocId],
+        parent_bucket_id: BucketId,
+        docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
         if docs.is_empty() {
             return Ok(());
         }
 
+        let mut bucket = self.parent_buckets[parent_bucket_id as usize];
         // Take the request data to avoid borrow checker issues with sub-aggregations
         let mut req = agg_data.take_filter_req_data(self.accessor_idx);
 
@@ -604,18 +628,24 @@ impl SegmentAggregationCollector for SegmentFilterCollector {
         req.evaluator
             .filter_batch(docs, &mut req.matching_docs_buffer);
 
-        self.doc_count += req.matching_docs_buffer.len() as u64;
+        bucket.doc_count += req.matching_docs_buffer.len() as u64;
 
         // Batch process sub-aggregations if we have matches
         if !req.matching_docs_buffer.is_empty() {
             if let Some(sub_aggs) = &mut self.sub_aggregations {
-                // Use collect_block for better sub-aggregation performance
-                sub_aggs.collect_block(&req.matching_docs_buffer, agg_data)?;
+                for &doc_id in &req.matching_docs_buffer {
+                    sub_aggs.push(bucket.bucket_id, doc_id);
+                }
             }
         }
 
         // Put the request data back
         agg_data.put_back_filter_req_data(self.accessor_idx, req);
+        if let Some(sub_aggs) = &mut self.sub_aggregations {
+            sub_aggs.check_flush_local(agg_data)?;
+        }
+        // put back bucket
+        self.parent_buckets[parent_bucket_id as usize] = bucket;
 
         Ok(())
     }
@@ -626,6 +656,21 @@ impl SegmentAggregationCollector for SegmentFilterCollector {
         }
         Ok(())
     }
+
+    fn prepare_max_bucket(
+        &mut self,
+        max_bucket: BucketId,
+        _agg_data: &AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        while self.parent_buckets.len() <= max_bucket as usize {
+            let bucket_id = self.bucket_id_provider.next_bucket_id();
+            self.parent_buckets.push(DocCount {
+                doc_count: 0,
+                bucket_id,
+            });
+        }
+        Ok(())
+    }
 }
 
 /// Intermediate result for filter aggregation
@@ -1519,9 +1564,9 @@ mod tests {
         let searcher = reader.searcher();
 
         let agg = json!({
-            "test": {
-                "filter": deserialized,
-                "aggs": { "count": { "value_count": { "field": "brand" } } }
+                "test": {
+                    "filter": deserialized,
+                    "aggs": { "count": { "value_count": { "field": "brand" } } }
             }
         });
 

src/aggregation/bucket/histogram/histogram.rs

@@ -1,6 +1,6 @@
 use std::cmp::Ordering;
 
-use columnar::{Column, ColumnBlockAccessor, ColumnType};
+use columnar::{Column, ColumnType};
 use rustc_hash::FxHashMap;
 use serde::{Deserialize, Serialize};
 use tantivy_bitpacker::minmax;
@@ -8,14 +8,14 @@ use tantivy_bitpacker::minmax;
 use crate::aggregation::agg_data::{
     build_segment_agg_collectors, AggRefNode, AggregationsSegmentCtx,
 };
-use crate::aggregation::agg_limits::MemoryConsumption;
 use crate::aggregation::agg_req::Aggregations;
 use crate::aggregation::agg_result::BucketEntry;
+use crate::aggregation::cached_sub_aggs::{CachedSubAggs, HighCardCachedSubAggs};
 use crate::aggregation::intermediate_agg_result::{
     IntermediateAggregationResult, IntermediateAggregationResults, IntermediateBucketResult,
     IntermediateHistogramBucketEntry,
 };
-use crate::aggregation::segment_agg_result::SegmentAggregationCollector;
+use crate::aggregation::segment_agg_result::{BucketIdProvider, SegmentAggregationCollector};
 use crate::aggregation::*;
 use crate::TantivyError;
 
@@ -26,13 +26,8 @@ pub struct HistogramAggReqData {
     pub accessor: Column<u64>,
     /// The field type of the fast field.
     pub field_type: ColumnType,
-    /// The column block accessor to access the fast field values.
-    pub column_block_accessor: ColumnBlockAccessor<u64>,
     /// The name of the aggregation.
     pub name: String,
-    /// The sub aggregation blueprint, used to create sub aggregations for each bucket.
-    /// Will be filled during initialization of the collector.
-    pub sub_aggregation_blueprint: Option<Box<dyn SegmentAggregationCollector>>,
     /// The histogram aggregation request.
     pub req: HistogramAggregation,
     /// True if this is a date_histogram aggregation.
@@ -257,18 +252,24 @@ impl HistogramBounds {
 pub(crate) struct SegmentHistogramBucketEntry {
     pub key: f64,
     pub doc_count: u64,
+    pub bucket_id: BucketId,
 }
 
 impl SegmentHistogramBucketEntry {
     pub(crate) fn into_intermediate_bucket_entry(
         self,
-        sub_aggregation: Option<Box<dyn SegmentAggregationCollector>>,
+        sub_aggregation: &mut Option<HighCardCachedSubAggs>,
         agg_data: &AggregationsSegmentCtx,
     ) -> crate::Result<IntermediateHistogramBucketEntry> {
         let mut sub_aggregation_res = IntermediateAggregationResults::default();
         if let Some(sub_aggregation) = sub_aggregation {
             sub_aggregation
-                .add_intermediate_aggregation_result(agg_data, &mut sub_aggregation_res)?;
+                .get_sub_agg_collector()
+                .add_intermediate_aggregation_result(
+                    agg_data,
+                    &mut sub_aggregation_res,
+                    self.bucket_id,
+                )?;
         }
         Ok(IntermediateHistogramBucketEntry {
             key: self.key,
@@ -278,27 +279,38 @@ impl SegmentHistogramBucketEntry {
     }
 }
 
+#[derive(Clone, Debug, Default)]
+struct HistogramBuckets {
+    pub buckets: FxHashMap<i64, SegmentHistogramBucketEntry>,
+}
+
 /// The collector puts values from the fast field into the correct buckets and does a conversion to
 /// the correct datatype.
-#[derive(Clone, Debug)]
+#[derive(Debug)]
 pub struct SegmentHistogramCollector {
     /// The buckets containing the aggregation data.
-    buckets: FxHashMap<i64, SegmentHistogramBucketEntry>,
-    sub_aggregations: FxHashMap<i64, Box<dyn SegmentAggregationCollector>>,
+    /// One Histogram bucket per parent bucket id.
+    parent_buckets: Vec<HistogramBuckets>,
+    sub_agg: Option<HighCardCachedSubAggs>,
     accessor_idx: usize,
+    bucket_id_provider: BucketIdProvider,
 }
 
 impl SegmentAggregationCollector for SegmentHistogramCollector {
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
         let name = agg_data
             .get_histogram_req_data(self.accessor_idx)
             .name
             .clone();
-        let bucket = self.into_intermediate_bucket_result(agg_data)?;
+        // TODO: avoid prepare_max_bucket here and handle empty buckets.
+        self.prepare_max_bucket(parent_bucket_id, agg_data)?;
+        let histogram = std::mem::take(&mut self.parent_buckets[parent_bucket_id as usize]);
+        let bucket = self.add_intermediate_bucket_result(agg_data, histogram)?;
         results.push(name, IntermediateAggregationResult::Bucket(bucket))?;
 
         Ok(())
@@ -307,44 +319,40 @@ impl SegmentAggregationCollector for SegmentHistogramCollector {
     #[inline]
     fn collect(
         &mut self,
-        doc: crate::DocId,
-        agg_data: &mut AggregationsSegmentCtx,
-    ) -> crate::Result<()> {
-        self.collect_block(&[doc], agg_data)
-    }
-
-    #[inline]
-    fn collect_block(
-        &mut self,
+        parent_bucket_id: BucketId,
         docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        let mut req = agg_data.take_histogram_req_data(self.accessor_idx);
+        let req = agg_data.take_histogram_req_data(self.accessor_idx);
         let mem_pre = self.get_memory_consumption();
+        let buckets = &mut self.parent_buckets[parent_bucket_id as usize].buckets;
 
         let bounds = req.bounds;
         let interval = req.req.interval;
         let offset = req.offset;
         let get_bucket_pos = |val| get_bucket_pos_f64(val, interval, offset) as i64;
 
-        req.column_block_accessor.fetch_block(docs, &req.accessor);
-        for (doc, val) in req
+        agg_data
+            .column_block_accessor
+            .fetch_block(docs, &req.accessor);
+        for (doc, val) in agg_data
             .column_block_accessor
             .iter_docid_vals(docs, &req.accessor)
         {
-            let val = f64_from_fastfield_u64(val, &req.field_type);
+            let val = f64_from_fastfield_u64(val, req.field_type);
             let bucket_pos = get_bucket_pos(val);
             if bounds.contains(val) {
-                let bucket = self.buckets.entry(bucket_pos).or_insert_with(|| {
+                let bucket = buckets.entry(bucket_pos).or_insert_with(|| {
                     let key = get_bucket_key_from_pos(bucket_pos as f64, interval, offset);
-                    SegmentHistogramBucketEntry { key, doc_count: 0 }
+                    SegmentHistogramBucketEntry {
+                        key,
+                        doc_count: 0,
+                        bucket_id: self.bucket_id_provider.next_bucket_id(),
+                    }
                 });
                 bucket.doc_count += 1;
-                if let Some(sub_aggregation_blueprint) = req.sub_aggregation_blueprint.as_ref() {
-                    self.sub_aggregations
-                        .entry(bucket_pos)
-                        .or_insert_with(|| sub_aggregation_blueprint.clone())
-                        .collect(doc, agg_data)?;
+                if let Some(sub_agg) = &mut self.sub_agg {
+                    sub_agg.push(bucket.bucket_id, doc);
                 }
             }
         }
@@ -358,14 +366,30 @@ impl SegmentAggregationCollector for SegmentHistogramCollector {
                 .add_memory_consumed(mem_delta as u64)?;
         }
 
+        if let Some(sub_agg) = &mut self.sub_agg {
+            sub_agg.check_flush_local(agg_data)?;
+        }
+
         Ok(())
     }
 
     fn flush(&mut self, agg_data: &mut AggregationsSegmentCtx) -> crate::Result<()> {
-        for sub_aggregation in self.sub_aggregations.values_mut() {
+        if let Some(sub_aggregation) = &mut self.sub_agg {
             sub_aggregation.flush(agg_data)?;
         }
+        Ok(())
+    }
 
+    fn prepare_max_bucket(
+        &mut self,
+        max_bucket: BucketId,
+        _agg_data: &AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        while self.parent_buckets.len() <= max_bucket as usize {
+            self.parent_buckets.push(HistogramBuckets {
+                buckets: FxHashMap::default(),
+            });
+        }
         Ok(())
     }
 }
@@ -373,22 +397,19 @@ impl SegmentAggregationCollector for SegmentHistogramCollector {
 impl SegmentHistogramCollector {
     fn get_memory_consumption(&self) -> usize {
         let self_mem = std::mem::size_of::<Self>();
-        let sub_aggs_mem = self.sub_aggregations.memory_consumption();
-        let buckets_mem = self.buckets.memory_consumption();
-        self_mem + sub_aggs_mem + buckets_mem
+        let buckets_mem = self.parent_buckets.len() * std::mem::size_of::<HistogramBuckets>();
+        self_mem + buckets_mem
     }
     /// Converts the collector result into a intermediate bucket result.
-    pub fn into_intermediate_bucket_result(
-        self,
+    fn add_intermediate_bucket_result(
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
+        histogram: HistogramBuckets,
     ) -> crate::Result<IntermediateBucketResult> {
-        let mut buckets = Vec::with_capacity(self.buckets.len());
+        let mut buckets = Vec::with_capacity(histogram.buckets.len());
 
-        for (bucket_pos, bucket) in self.buckets {
-            let bucket_res = bucket.into_intermediate_bucket_entry(
-                self.sub_aggregations.get(&bucket_pos).cloned(),
-                agg_data,
-            );
+        for bucket in histogram.buckets.into_values() {
+            let bucket_res = bucket.into_intermediate_bucket_entry(&mut self.sub_agg, agg_data);
 
             buckets.push(bucket_res?);
         }
@@ -408,7 +429,7 @@ impl SegmentHistogramCollector {
         agg_data: &mut AggregationsSegmentCtx,
         node: &AggRefNode,
     ) -> crate::Result<Self> {
-        let blueprint = if !node.children.is_empty() {
+        let sub_agg = if !node.children.is_empty() {
             Some(build_segment_agg_collectors(agg_data, &node.children)?)
         } else {
             None
@@ -423,13 +444,13 @@ impl SegmentHistogramCollector {
             max: f64::MAX,
         });
         req_data.offset = req_data.req.offset.unwrap_or(0.0);
-
-        req_data.sub_aggregation_blueprint = blueprint;
+        let sub_agg = sub_agg.map(CachedSubAggs::new);
 
         Ok(Self {
-            buckets: Default::default(),
-            sub_aggregations: Default::default(),
+            parent_buckets: Default::default(),
+            sub_agg,
             accessor_idx: node.idx_in_req_data,
+            bucket_id_provider: BucketIdProvider::default(),
         })
     }
 }

src/aggregation/bucket/range.rs

@@ -1,18 +1,22 @@
 use std::fmt::Debug;
 use std::ops::Range;
 
-use columnar::{Column, ColumnBlockAccessor, ColumnType};
+use columnar::{Column, ColumnType};
 use rustc_hash::FxHashMap;
 use serde::{Deserialize, Serialize};
 
 use crate::aggregation::agg_data::{
     build_segment_agg_collectors, AggRefNode, AggregationsSegmentCtx,
 };
+use crate::aggregation::agg_limits::AggregationLimitsGuard;
+use crate::aggregation::cached_sub_aggs::{
+    CachedSubAggs, HighCardSubAggCache, LowCardCachedSubAggs, LowCardSubAggCache, SubAggCache,
+};
 use crate::aggregation::intermediate_agg_result::{
     IntermediateAggregationResult, IntermediateAggregationResults, IntermediateBucketResult,
     IntermediateRangeBucketEntry, IntermediateRangeBucketResult,
 };
-use crate::aggregation::segment_agg_result::SegmentAggregationCollector;
+use crate::aggregation::segment_agg_result::{BucketIdProvider, SegmentAggregationCollector};
 use crate::aggregation::*;
 use crate::TantivyError;
 
@@ -23,12 +27,12 @@ pub struct RangeAggReqData {
     pub accessor: Column<u64>,
     /// The type of the fast field.
     pub field_type: ColumnType,
-    /// The column block accessor to access the fast field values.
-    pub column_block_accessor: ColumnBlockAccessor<u64>,
     /// The range aggregation request.
     pub req: RangeAggregation,
     /// The name of the aggregation.
     pub name: String,
+    /// Whether this is a top-level aggregation.
+    pub is_top_level: bool,
 }
 
 impl RangeAggReqData {
@@ -151,19 +155,47 @@ pub(crate) struct SegmentRangeAndBucketEntry {
 
 /// The collector puts values from the fast field into the correct buckets and does a conversion to
 /// the correct datatype.
-#[derive(Clone, Debug)]
-pub struct SegmentRangeCollector {
+pub struct SegmentRangeCollector<C: SubAggCache> {
     /// The buckets containing the aggregation data.
-    buckets: Vec<SegmentRangeAndBucketEntry>,
+    /// One for each ParentBucketId
+    parent_buckets: Vec<Vec<SegmentRangeAndBucketEntry>>,
     column_type: ColumnType,
     pub(crate) accessor_idx: usize,
+    sub_agg: Option<CachedSubAggs<C>>,
+    /// Here things get a bit weird. We need to assign unique bucket ids across all
+    /// parent buckets. So we keep track of the next available bucket id here.
+    /// This allows a kind of flattening of the bucket ids across all parent buckets.
+    /// E.g. in nested aggregations:
+    /// Term Agg -> Range aggregation -> Stats aggregation
+    /// E.g. the Term Agg creates 3 buckets ["INFO", "ERROR", "WARN"], each of these has a Range
+    /// aggregation with 4 buckets. The Range aggregation will create buckets with ids:
+    /// - INFO: 0,1,2,3
+    /// - ERROR: 4,5,6,7
+    /// - WARN: 8,9,10,11
+    ///
+    /// This allows the Stats aggregation to have unique bucket ids to refer to.
+    bucket_id_provider: BucketIdProvider,
+    limits: AggregationLimitsGuard,
 }
 
+impl<C: SubAggCache> Debug for SegmentRangeCollector<C> {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("SegmentRangeCollector")
+            .field("parent_buckets_len", &self.parent_buckets.len())
+            .field("column_type", &self.column_type)
+            .field("accessor_idx", &self.accessor_idx)
+            .field("has_sub_agg", &self.sub_agg.is_some())
+            .finish()
+    }
+}
+
+/// TODO: Bad naming, there's also SegmentRangeAndBucketEntry
 #[derive(Clone)]
 pub(crate) struct SegmentRangeBucketEntry {
     pub key: Key,
     pub doc_count: u64,
-    pub sub_aggregation: Option<Box<dyn SegmentAggregationCollector>>,
+    // pub sub_aggregation: Option<Box<dyn SegmentAggregationCollector>>,
+    pub bucket_id: BucketId,
     /// The from range of the bucket. Equals `f64::MIN` when `None`.
     pub from: Option<f64>,
     /// The to range of the bucket. Equals `f64::MAX` when `None`. Open interval, `to` is not
@@ -184,48 +216,50 @@ impl Debug for SegmentRangeBucketEntry {
 impl SegmentRangeBucketEntry {
     pub(crate) fn into_intermediate_bucket_entry(
         self,
-        agg_data: &AggregationsSegmentCtx,
     ) -> crate::Result<IntermediateRangeBucketEntry> {
-        let mut sub_aggregation_res = IntermediateAggregationResults::default();
-        if let Some(sub_aggregation) = self.sub_aggregation {
-            sub_aggregation
-                .add_intermediate_aggregation_result(agg_data, &mut sub_aggregation_res)?
-        } else {
-            Default::default()
-        };
+        let sub_aggregation = IntermediateAggregationResults::default();
 
         Ok(IntermediateRangeBucketEntry {
             key: self.key.into(),
             doc_count: self.doc_count,
-            sub_aggregation: sub_aggregation_res,
+            sub_aggregation_res: sub_aggregation,
             from: self.from,
             to: self.to,
         })
     }
 }
 
-impl SegmentAggregationCollector for SegmentRangeCollector {
+impl<C: SubAggCache> SegmentAggregationCollector for SegmentRangeCollector<C> {
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
+        self.prepare_max_bucket(parent_bucket_id, agg_data)?;
         let field_type = self.column_type;
         let name = agg_data
             .get_range_req_data(self.accessor_idx)
             .name
             .to_string();
 
-        let buckets: FxHashMap<SerializedKey, IntermediateRangeBucketEntry> = self
-            .buckets
+        let buckets = std::mem::take(&mut self.parent_buckets[parent_bucket_id as usize]);
+
+        let buckets: FxHashMap<SerializedKey, IntermediateRangeBucketEntry> = buckets
             .into_iter()
-            .map(move |range_bucket| {
-                Ok((
-                    range_to_string(&range_bucket.range, &field_type)?,
-                    range_bucket
-                        .bucket
-                        .into_intermediate_bucket_entry(agg_data)?,
-                ))
+            .map(|range_bucket| {
+                let bucket_id = range_bucket.bucket.bucket_id;
+                let mut agg = range_bucket.bucket.into_intermediate_bucket_entry()?;
+                if let Some(sub_aggregation) = &mut self.sub_agg {
+                    sub_aggregation
+                        .get_sub_agg_collector()
+                        .add_intermediate_aggregation_result(
+                            agg_data,
+                            &mut agg.sub_aggregation_res,
+                            bucket_id,
+                        )?;
+                }
+                Ok((range_to_string(&range_bucket.range, &field_type)?, agg))
             })
             .collect::<crate::Result<_>>()?;
 
@@ -242,73 +276,114 @@ impl SegmentAggregationCollector for SegmentRangeCollector {
     #[inline]
     fn collect(
         &mut self,
-        doc: crate::DocId,
-        agg_data: &mut AggregationsSegmentCtx,
-    ) -> crate::Result<()> {
-        self.collect_block(&[doc], agg_data)
-    }
-
-    #[inline]
-    fn collect_block(
-        &mut self,
+        parent_bucket_id: BucketId,
         docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        // Take request data to avoid borrow conflicts during sub-aggregation
-        let mut req = agg_data.take_range_req_data(self.accessor_idx);
+        let req = agg_data.take_range_req_data(self.accessor_idx);
 
-        req.column_block_accessor.fetch_block(docs, &req.accessor);
+        agg_data
+            .column_block_accessor
+            .fetch_block(docs, &req.accessor);
 
-        for (doc, val) in req
+        let buckets = &mut self.parent_buckets[parent_bucket_id as usize];
+
+        for (doc, val) in agg_data
             .column_block_accessor
             .iter_docid_vals(docs, &req.accessor)
         {
-            let bucket_pos = self.get_bucket_pos(val);
-            let bucket = &mut self.buckets[bucket_pos];
+            let bucket_pos = get_bucket_pos(val, buckets);
+            let bucket = &mut buckets[bucket_pos];
             bucket.bucket.doc_count += 1;
-            if let Some(sub_agg) = bucket.bucket.sub_aggregation.as_mut() {
-                sub_agg.collect(doc, agg_data)?;
+            if let Some(sub_agg) = self.sub_agg.as_mut() {
+                sub_agg.push(bucket.bucket.bucket_id, doc);
             }
         }
 
         agg_data.put_back_range_req_data(self.accessor_idx, req);
+        if let Some(sub_agg) = self.sub_agg.as_mut() {
+            sub_agg.check_flush_local(agg_data)?;
+        }
 
         Ok(())
     }
 
     fn flush(&mut self, agg_data: &mut AggregationsSegmentCtx) -> crate::Result<()> {
-        for bucket in self.buckets.iter_mut() {
-            if let Some(sub_agg) = bucket.bucket.sub_aggregation.as_mut() {
-                sub_agg.flush(agg_data)?;
-            }
+        if let Some(sub_agg) = self.sub_agg.as_mut() {
+            sub_agg.flush(agg_data)?;
         }
         Ok(())
     }
+
+    fn prepare_max_bucket(
+        &mut self,
+        max_bucket: BucketId,
+        agg_data: &AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        while self.parent_buckets.len() <= max_bucket as usize {
+            let new_buckets = self.create_new_buckets(agg_data)?;
+            self.parent_buckets.push(new_buckets);
+        }
+
+        Ok(())
+    }
+}
+/// Build a concrete `SegmentRangeCollector` with either a Vec- or HashMap-backed
+/// bucket storage, depending on the column type and aggregation level.
+pub(crate) fn build_segment_range_collector(
+    agg_data: &mut AggregationsSegmentCtx,
+    node: &AggRefNode,
+) -> crate::Result<Box<dyn SegmentAggregationCollector>> {
+    let accessor_idx = node.idx_in_req_data;
+    let req_data = agg_data.get_range_req_data(node.idx_in_req_data);
+    let field_type = req_data.field_type;
+
+    // TODO: A better metric instead of is_top_level would be the number of buckets expected.
+    // E.g. If range agg is not top level, but the parent is a bucket agg with less than 10 buckets,
+    // we can are still in low cardinality territory.
+    let is_low_card = req_data.is_top_level && req_data.req.ranges.len() <= 64;
+
+    let sub_agg = if !node.children.is_empty() {
+        Some(build_segment_agg_collectors(agg_data, &node.children)?)
+    } else {
+        None
+    };
+
+    if is_low_card {
+        Ok(Box::new(SegmentRangeCollector::<LowCardSubAggCache> {
+            sub_agg: sub_agg.map(LowCardCachedSubAggs::new),
+            column_type: field_type,
+            accessor_idx,
+            parent_buckets: Vec::new(),
+            bucket_id_provider: BucketIdProvider::default(),
+            limits: agg_data.context.limits.clone(),
+        }))
+    } else {
+        Ok(Box::new(SegmentRangeCollector::<HighCardSubAggCache> {
+            sub_agg: sub_agg.map(CachedSubAggs::new),
+            column_type: field_type,
+            accessor_idx,
+            parent_buckets: Vec::new(),
+            bucket_id_provider: BucketIdProvider::default(),
+            limits: agg_data.context.limits.clone(),
+        }))
+    }
 }
 
-impl SegmentRangeCollector {
-    pub(crate) fn from_req_and_validate(
-        req_data: &mut AggregationsSegmentCtx,
-        node: &AggRefNode,
-    ) -> crate::Result<Self> {
-        let accessor_idx = node.idx_in_req_data;
-        let (field_type, ranges) = {
-            let req_view = req_data.get_range_req_data(node.idx_in_req_data);
-            (req_view.field_type, req_view.req.ranges.clone())
-        };
-
+impl<C: SubAggCache> SegmentRangeCollector<C> {
+    pub(crate) fn create_new_buckets(
+        &mut self,
+        agg_data: &AggregationsSegmentCtx,
+    ) -> crate::Result<Vec<SegmentRangeAndBucketEntry>> {
+        let field_type = self.column_type;
+        let req_data = agg_data.get_range_req_data(self.accessor_idx);
         // The range input on the request is f64.
         // We need to convert to u64 ranges, because we read the values as u64.
         // The mapping from the conversion is monotonic so ordering is preserved.
-        let sub_agg_prototype = if !node.children.is_empty() {
-            Some(build_segment_agg_collectors(req_data, &node.children)?)
-        } else {
-            None
-        };
-
-        let buckets: Vec<_> = extend_validate_ranges(&ranges, &field_type)?
+        let buckets: Vec<_> = extend_validate_ranges(&req_data.req.ranges, &field_type)?
             .iter()
             .map(|range| {
+                let bucket_id = self.bucket_id_provider.next_bucket_id();
                 let key = range
                     .key
                     .clone()
@@ -317,20 +392,20 @@ impl SegmentRangeCollector {
                 let to = if range.range.end == u64::MAX {
                     None
                 } else {
-                    Some(f64_from_fastfield_u64(range.range.end, &field_type))
+                    Some(f64_from_fastfield_u64(range.range.end, field_type))
                 };
                 let from = if range.range.start == u64::MIN {
                     None
                 } else {
-                    Some(f64_from_fastfield_u64(range.range.start, &field_type))
+                    Some(f64_from_fastfield_u64(range.range.start, field_type))
                 };
-                let sub_aggregation = sub_agg_prototype.clone();
+                // let sub_aggregation = sub_agg_prototype.clone();
 
                 Ok(SegmentRangeAndBucketEntry {
                     range: range.range.clone(),
                     bucket: SegmentRangeBucketEntry {
                         doc_count: 0,
-                        sub_aggregation,
+                        bucket_id,
                         key,
                         from,
                         to,
@@ -339,27 +414,20 @@ impl SegmentRangeCollector {
             })
             .collect::<crate::Result<_>>()?;
 
-        req_data.context.limits.add_memory_consumed(
+        self.limits.add_memory_consumed(
             buckets.len() as u64 * std::mem::size_of::<SegmentRangeAndBucketEntry>() as u64,
         )?;
-
-        Ok(SegmentRangeCollector {
-            buckets,
-            column_type: field_type,
-            accessor_idx,
-        })
-    }
-
-    #[inline]
-    fn get_bucket_pos(&self, val: u64) -> usize {
-        let pos = self
-            .buckets
-            .binary_search_by_key(&val, |probe| probe.range.start)
-            .unwrap_or_else(|pos| pos - 1);
-        debug_assert!(self.buckets[pos].range.contains(&val));
-        pos
+        Ok(buckets)
     }
 }
+#[inline]
+fn get_bucket_pos(val: u64, buckets: &[SegmentRangeAndBucketEntry]) -> usize {
+    let pos = buckets
+        .binary_search_by_key(&val, |probe| probe.range.start)
+        .unwrap_or_else(|pos| pos - 1);
+    debug_assert!(buckets[pos].range.contains(&val));
+    pos
+}
 
 /// Converts the user provided f64 range value to fast field value space.
 ///
@@ -456,7 +524,7 @@ pub(crate) fn range_to_string(
             let val = i64::from_u64(val);
             format_date(val)
         } else {
-            Ok(f64_from_fastfield_u64(val, field_type).to_string())
+            Ok(f64_from_fastfield_u64(val, *field_type).to_string())
         }
     };
 
@@ -486,7 +554,7 @@ mod tests {
     pub fn get_collector_from_ranges(
         ranges: Vec<RangeAggregationRange>,
         field_type: ColumnType,
-    ) -> SegmentRangeCollector {
+    ) -> SegmentRangeCollector<HighCardSubAggCache> {
         let req = RangeAggregation {
             field: "dummy".to_string(),
             ranges,
@@ -506,30 +574,33 @@ mod tests {
                 let to = if range.range.end == u64::MAX {
                     None
                 } else {
-                    Some(f64_from_fastfield_u64(range.range.end, &field_type))
+                    Some(f64_from_fastfield_u64(range.range.end, field_type))
                 };
                 let from = if range.range.start == u64::MIN {
                     None
                 } else {
-                    Some(f64_from_fastfield_u64(range.range.start, &field_type))
+                    Some(f64_from_fastfield_u64(range.range.start, field_type))
                 };
                 SegmentRangeAndBucketEntry {
                     range: range.range.clone(),
                     bucket: SegmentRangeBucketEntry {
                         doc_count: 0,
-                        sub_aggregation: None,
                         key,
                         from,
                         to,
+                        bucket_id: 0,
                     },
                 }
             })
             .collect();
 
         SegmentRangeCollector {
-            buckets,
+            parent_buckets: vec![buckets],
             column_type: field_type,
             accessor_idx: 0,
+            sub_agg: None,
+            bucket_id_provider: Default::default(),
+            limits: AggregationLimitsGuard::default(),
         }
     }
 
@@ -776,7 +847,7 @@ mod tests {
         let buckets = vec![(10f64..20f64).into(), (30f64..40f64).into()];
         let collector = get_collector_from_ranges(buckets, ColumnType::F64);
 
-        let buckets = collector.buckets;
+        let buckets = collector.parent_buckets[0].clone();
         assert_eq!(buckets[0].range.start, u64::MIN);
         assert_eq!(buckets[0].range.end, 10f64.to_u64());
         assert_eq!(buckets[1].range.start, 10f64.to_u64());
@@ -799,7 +870,7 @@ mod tests {
         ];
         let collector = get_collector_from_ranges(buckets, ColumnType::F64);
 
-        let buckets = collector.buckets;
+        let buckets = collector.parent_buckets[0].clone();
         assert_eq!(buckets[0].range.start, u64::MIN);
         assert_eq!(buckets[0].range.end, 10f64.to_u64());
         assert_eq!(buckets[1].range.start, 10f64.to_u64());
@@ -814,7 +885,7 @@ mod tests {
         let buckets = vec![(-10f64..-1f64).into()];
         let collector = get_collector_from_ranges(buckets, ColumnType::F64);
 
-        let buckets = collector.buckets;
+        let buckets = collector.parent_buckets[0].clone();
         assert_eq!(&buckets[0].bucket.key.to_string(), "*--10");
         assert_eq!(&buckets[buckets.len() - 1].bucket.key.to_string(), "-1-*");
     }
@@ -823,7 +894,7 @@ mod tests {
         let buckets = vec![(0f64..10f64).into()];
         let collector = get_collector_from_ranges(buckets, ColumnType::F64);
 
-        let buckets = collector.buckets;
+        let buckets = collector.parent_buckets[0].clone();
         assert_eq!(&buckets[0].bucket.key.to_string(), "*-0");
         assert_eq!(&buckets[buckets.len() - 1].bucket.key.to_string(), "10-*");
     }
@@ -832,7 +903,7 @@ mod tests {
     fn range_binary_search_test_u64() {
         let check_ranges = |ranges: Vec<RangeAggregationRange>| {
             let collector = get_collector_from_ranges(ranges, ColumnType::U64);
-            let search = |val: u64| collector.get_bucket_pos(val);
+            let search = |val: u64| get_bucket_pos(val, &collector.parent_buckets[0]);
 
             assert_eq!(search(u64::MIN), 0);
             assert_eq!(search(9), 0);
@@ -878,7 +949,7 @@ mod tests {
         let ranges = vec![(10.0..100.0).into()];
 
         let collector = get_collector_from_ranges(ranges, ColumnType::F64);
-        let search = |val: u64| collector.get_bucket_pos(val);
+        let search = |val: u64| get_bucket_pos(val, &collector.parent_buckets[0]);
 
         assert_eq!(search(u64::MIN), 0);
         assert_eq!(search(9f64.to_u64()), 0);
@@ -890,63 +961,3 @@ mod tests {
                                              // the max value
     }
 }
-
-#[cfg(all(test, feature = "unstable"))]
-mod bench {
-
-    use itertools::Itertools;
-    use rand::seq::SliceRandom;
-    use rand::thread_rng;
-
-    use super::*;
-    use crate::aggregation::bucket::range::tests::get_collector_from_ranges;
-
-    const TOTAL_DOCS: u64 = 1_000_000u64;
-    const NUM_DOCS: u64 = 50_000u64;
-
-    fn get_collector_with_buckets(num_buckets: u64, num_docs: u64) -> SegmentRangeCollector {
-        let bucket_size = num_docs / num_buckets;
-        let mut buckets: Vec<RangeAggregationRange> = vec![];
-        for i in 0..num_buckets {
-            let bucket_start = (i * bucket_size) as f64;
-            buckets.push((bucket_start..bucket_start + bucket_size as f64).into())
-        }
-
-        get_collector_from_ranges(buckets, ColumnType::U64)
-    }
-
-    fn get_rand_docs(total_docs: u64, num_docs_returned: u64) -> Vec<u64> {
-        let mut rng = thread_rng();
-
-        let all_docs = (0..total_docs - 1).collect_vec();
-        let mut vals = all_docs
-            .as_slice()
-            .choose_multiple(&mut rng, num_docs_returned as usize)
-            .cloned()
-            .collect_vec();
-        vals.sort();
-        vals
-    }
-
-    fn bench_range_binary_search(b: &mut test::Bencher, num_buckets: u64) {
-        let collector = get_collector_with_buckets(num_buckets, TOTAL_DOCS);
-        let vals = get_rand_docs(TOTAL_DOCS, NUM_DOCS);
-        b.iter(|| {
-            let mut bucket_pos = 0;
-            for val in &vals {
-                bucket_pos = collector.get_bucket_pos(*val);
-            }
-            bucket_pos
-        })
-    }
-
-    #[bench]
-    fn bench_range_100_buckets(b: &mut test::Bencher) {
-        bench_range_binary_search(b, 100)
-    }
-
-    #[bench]
-    fn bench_range_10_buckets(b: &mut test::Bencher) {
-        bench_range_binary_search(b, 10)
-    }
-}

src/aggregation/bucket/term_missing_agg.rs

@@ -5,11 +5,13 @@ use crate::aggregation::agg_data::{
     build_segment_agg_collectors, AggRefNode, AggregationsSegmentCtx,
 };
 use crate::aggregation::bucket::term_agg::TermsAggregation;
+use crate::aggregation::cached_sub_aggs::{CachedSubAggs, HighCardCachedSubAggs};
 use crate::aggregation::intermediate_agg_result::{
     IntermediateAggregationResult, IntermediateAggregationResults, IntermediateBucketResult,
     IntermediateKey, IntermediateTermBucketEntry, IntermediateTermBucketResult,
 };
-use crate::aggregation::segment_agg_result::SegmentAggregationCollector;
+use crate::aggregation::segment_agg_result::{BucketIdProvider, SegmentAggregationCollector};
+use crate::aggregation::BucketId;
 
 /// Special aggregation to handle missing values for term aggregations.
 /// This missing aggregation will check multiple columns for existence.
@@ -35,41 +37,55 @@ impl MissingTermAggReqData {
     }
 }
 
-/// The specialized missing term aggregation.
 #[derive(Default, Debug, Clone)]
-pub struct TermMissingAgg {
+struct MissingCount {
     missing_count: u32,
+    bucket_id: BucketId,
+}
+
+/// The specialized missing term aggregation.
+#[derive(Default, Debug)]
+pub struct TermMissingAgg {
     accessor_idx: usize,
-    sub_agg: Option<Box<dyn SegmentAggregationCollector>>,
+    sub_agg: Option<HighCardCachedSubAggs>,
+    /// Idx = parent bucket id, Value = missing count for that bucket
+    missing_count_per_bucket: Vec<MissingCount>,
+    bucket_id_provider: BucketIdProvider,
 }
 impl TermMissingAgg {
     pub(crate) fn new(
-        req_data: &mut AggregationsSegmentCtx,
+        agg_data: &mut AggregationsSegmentCtx,
         node: &AggRefNode,
     ) -> crate::Result<Self> {
         let has_sub_aggregations = !node.children.is_empty();
         let accessor_idx = node.idx_in_req_data;
         let sub_agg = if has_sub_aggregations {
-            let sub_aggregation = build_segment_agg_collectors(req_data, &node.children)?;
+            let sub_aggregation = build_segment_agg_collectors(agg_data, &node.children)?;
             Some(sub_aggregation)
         } else {
             None
         };
 
+        let sub_agg = sub_agg.map(CachedSubAggs::new);
+        let bucket_id_provider = BucketIdProvider::default();
+
         Ok(Self {
             accessor_idx,
             sub_agg,
-            ..Default::default()
+            missing_count_per_bucket: Vec::new(),
+            bucket_id_provider,
         })
     }
 }
 
 impl SegmentAggregationCollector for TermMissingAgg {
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
+        self.prepare_max_bucket(parent_bucket_id, agg_data)?;
         let req_data = agg_data.get_missing_term_req_data(self.accessor_idx);
         let term_agg = &req_data.req;
         let missing = term_agg
@@ -80,13 +96,16 @@ impl SegmentAggregationCollector for TermMissingAgg {
         let mut entries: FxHashMap<IntermediateKey, IntermediateTermBucketEntry> =
             Default::default();
 
+        let missing_count = &self.missing_count_per_bucket[parent_bucket_id as usize];
         let mut missing_entry = IntermediateTermBucketEntry {
-            doc_count: self.missing_count,
+            doc_count: missing_count.missing_count,
             sub_aggregation: Default::default(),
         };
-        if let Some(sub_agg) = self.sub_agg {
+        if let Some(sub_agg) = &mut self.sub_agg {
             let mut res = IntermediateAggregationResults::default();
-            sub_agg.add_intermediate_aggregation_result(agg_data, &mut res)?;
+            sub_agg
+                .get_sub_agg_collector()
+                .add_intermediate_aggregation_result(agg_data, &mut res, missing_count.bucket_id)?;
             missing_entry.sub_aggregation = res;
         }
         entries.insert(missing.into(), missing_entry);
@@ -109,30 +128,52 @@ impl SegmentAggregationCollector for TermMissingAgg {
 
     fn collect(
         &mut self,
-        doc: crate::DocId,
+        parent_bucket_id: BucketId,
+        docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
+        let bucket = &mut self.missing_count_per_bucket[parent_bucket_id as usize];
         let req_data = agg_data.get_missing_term_req_data(self.accessor_idx);
-        let has_value = req_data
-            .accessors
-            .iter()
-            .any(|(acc, _)| acc.index.has_value(doc));
-        if !has_value {
-            self.missing_count += 1;
-            if let Some(sub_agg) = self.sub_agg.as_mut() {
-                sub_agg.collect(doc, agg_data)?;
+
+        for doc in docs {
+            let doc = *doc;
+            let has_value = req_data
+                .accessors
+                .iter()
+                .any(|(acc, _)| acc.index.has_value(doc));
+            if !has_value {
+                bucket.missing_count += 1;
+
+                if let Some(sub_agg) = self.sub_agg.as_mut() {
+                    sub_agg.push(bucket.bucket_id, doc);
+                }
             }
         }
+
+        if let Some(sub_agg) = self.sub_agg.as_mut() {
+            sub_agg.check_flush_local(agg_data)?;
+        }
         Ok(())
     }
 
-    fn collect_block(
+    fn prepare_max_bucket(
         &mut self,
-        docs: &[crate::DocId],
-        agg_data: &mut AggregationsSegmentCtx,
+        max_bucket: BucketId,
+        _agg_data: &AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        for doc in docs {
-            self.collect(*doc, agg_data)?;
+        while self.missing_count_per_bucket.len() <= max_bucket as usize {
+            let bucket_id = self.bucket_id_provider.next_bucket_id();
+            self.missing_count_per_bucket.push(MissingCount {
+                missing_count: 0,
+                bucket_id,
+            });
+        }
+        Ok(())
+    }
+
+    fn flush(&mut self, agg_data: &mut AggregationsSegmentCtx) -> crate::Result<()> {
+        if let Some(sub_agg) = self.sub_agg.as_mut() {
+            sub_agg.flush(agg_data)?;
         }
         Ok(())
     }

src/aggregation/buf_collector.rs

@@ -1,87 +0,0 @@
-use super::intermediate_agg_result::IntermediateAggregationResults;
-use super::segment_agg_result::SegmentAggregationCollector;
-use crate::aggregation::agg_data::AggregationsSegmentCtx;
-use crate::DocId;
-
-#[cfg(test)]
-pub(crate) const DOC_BLOCK_SIZE: usize = 64;
-
-#[cfg(not(test))]
-pub(crate) const DOC_BLOCK_SIZE: usize = 256;
-
-pub(crate) type DocBlock = [DocId; DOC_BLOCK_SIZE];
-
-/// BufAggregationCollector buffers documents before calling collect_block().
-#[derive(Clone)]
-pub(crate) struct BufAggregationCollector {
-    pub(crate) collector: Box<dyn SegmentAggregationCollector>,
-    staged_docs: DocBlock,
-    num_staged_docs: usize,
-}
-
-impl std::fmt::Debug for BufAggregationCollector {
-    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
-        f.debug_struct("SegmentAggregationResultsCollector")
-            .field("staged_docs", &&self.staged_docs[..self.num_staged_docs])
-            .field("num_staged_docs", &self.num_staged_docs)
-            .finish()
-    }
-}
-
-impl BufAggregationCollector {
-    pub fn new(collector: Box<dyn SegmentAggregationCollector>) -> Self {
-        Self {
-            collector,
-            num_staged_docs: 0,
-            staged_docs: [0; DOC_BLOCK_SIZE],
-        }
-    }
-}
-
-impl SegmentAggregationCollector for BufAggregationCollector {
-    #[inline]
-    fn add_intermediate_aggregation_result(
-        self: Box<Self>,
-        agg_data: &AggregationsSegmentCtx,
-        results: &mut IntermediateAggregationResults,
-    ) -> crate::Result<()> {
-        Box::new(self.collector).add_intermediate_aggregation_result(agg_data, results)
-    }
-
-    #[inline]
-    fn collect(
-        &mut self,
-        doc: crate::DocId,
-        agg_data: &mut AggregationsSegmentCtx,
-    ) -> crate::Result<()> {
-        self.staged_docs[self.num_staged_docs] = doc;
-        self.num_staged_docs += 1;
-        if self.num_staged_docs == self.staged_docs.len() {
-            self.collector
-                .collect_block(&self.staged_docs[..self.num_staged_docs], agg_data)?;
-            self.num_staged_docs = 0;
-        }
-        Ok(())
-    }
-
-    #[inline]
-    fn collect_block(
-        &mut self,
-        docs: &[crate::DocId],
-        agg_data: &mut AggregationsSegmentCtx,
-    ) -> crate::Result<()> {
-        self.collector.collect_block(docs, agg_data)?;
-        Ok(())
-    }
-
-    #[inline]
-    fn flush(&mut self, agg_data: &mut AggregationsSegmentCtx) -> crate::Result<()> {
-        self.collector
-            .collect_block(&self.staged_docs[..self.num_staged_docs], agg_data)?;
-        self.num_staged_docs = 0;
-
-        self.collector.flush(agg_data)?;
-
-        Ok(())
-    }
-}

src/aggregation/cached_sub_aggs.rs

@@ -0,0 +1,245 @@
+use std::fmt::Debug;
+
+use super::segment_agg_result::SegmentAggregationCollector;
+use crate::aggregation::agg_data::AggregationsSegmentCtx;
+use crate::aggregation::bucket::MAX_NUM_TERMS_FOR_VEC;
+use crate::aggregation::BucketId;
+use crate::DocId;
+
+/// A cache for sub-aggregations, storing doc ids per bucket id.
+/// Depending on the cardinality of the parent aggregation, we use different
+/// storage strategies.
+///
+/// ## Low Cardinality
+/// Cardinality here refers to the number of unique flattened buckets that can be created
+/// by the parent aggregation.
+/// Flattened buckets are the result of combining all buckets per collector
+/// into a single list of buckets, where each bucket is identified by its BucketId.
+///
+/// ## Usage
+/// Since this is caching for sub-aggregations, it is only used by bucket
+/// aggregations.
+///
+/// TODO: consider using a more advanced data structure for high cardinality
+/// aggregations.
+/// What this datastructure does in general is to group docs by bucket id.
+#[derive(Debug)]
+pub(crate) struct CachedSubAggs<C: SubAggCache> {
+    cache: C,
+    sub_agg_collector: Box<dyn SegmentAggregationCollector>,
+    num_docs: usize,
+}
+
+pub type LowCardCachedSubAggs = CachedSubAggs<LowCardSubAggCache>;
+pub type HighCardCachedSubAggs = CachedSubAggs<HighCardSubAggCache>;
+
+const FLUSH_THRESHOLD: usize = 2048;
+
+/// A trait for caching sub-aggregation doc ids per bucket id.
+/// Different implementations can be used depending on the cardinality
+/// of the parent aggregation.
+pub trait SubAggCache: Debug {
+    fn new() -> Self;
+    fn push(&mut self, bucket_id: BucketId, doc_id: DocId);
+    fn flush_local(
+        &mut self,
+        sub_agg: &mut Box<dyn SegmentAggregationCollector>,
+        agg_data: &mut AggregationsSegmentCtx,
+        force: bool,
+    ) -> crate::Result<()>;
+}
+
+impl<Backend: SubAggCache + Debug> CachedSubAggs<Backend> {
+    pub fn new(sub_agg: Box<dyn SegmentAggregationCollector>) -> Self {
+        Self {
+            cache: Backend::new(),
+            sub_agg_collector: sub_agg,
+            num_docs: 0,
+        }
+    }
+
+    pub fn get_sub_agg_collector(&mut self) -> &mut Box<dyn SegmentAggregationCollector> {
+        &mut self.sub_agg_collector
+    }
+
+    #[inline]
+    pub fn push(&mut self, bucket_id: BucketId, doc_id: DocId) {
+        self.cache.push(bucket_id, doc_id);
+        self.num_docs += 1;
+    }
+
+    /// Check if we need to flush based on the number of documents cached.
+    /// If so, flushes the cache to the provided aggregation collector.
+    pub fn check_flush_local(
+        &mut self,
+        agg_data: &mut AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        if self.num_docs >= FLUSH_THRESHOLD {
+            self.cache
+                .flush_local(&mut self.sub_agg_collector, agg_data, false)?;
+            self.num_docs = 0;
+        }
+        Ok(())
+    }
+
+    /// Note: this _does_ flush the sub aggregations.
+    pub fn flush(&mut self, agg_data: &mut AggregationsSegmentCtx) -> crate::Result<()> {
+        if self.num_docs != 0 {
+            self.cache
+                .flush_local(&mut self.sub_agg_collector, agg_data, true)?;
+            self.num_docs = 0;
+        }
+        self.sub_agg_collector.flush(agg_data)?;
+        Ok(())
+    }
+}
+
+/// Number of partitions for high cardinality sub-aggregation cache.
+const NUM_PARTITIONS: usize = 16;
+
+#[derive(Debug)]
+pub(crate) struct HighCardSubAggCache {
+    /// This weird partitioning is used to do some cheap grouping on the bucket ids.
+    /// bucket ids are dense, e.g. when we don't detect the cardinality as low cardinality,
+    /// but there are just 16 bucket ids, each bucket id will go to its own partition.
+    ///
+    /// We want to keep this cheap, because high cardinality aggregations can have a lot of
+    /// buckets, and there may be nothing to group.
+    partitions: Box<[PartitionEntry; NUM_PARTITIONS]>,
+}
+
+impl HighCardSubAggCache {
+    #[inline]
+    fn clear(&mut self) {
+        for partition in self.partitions.iter_mut() {
+            partition.clear();
+        }
+    }
+}
+
+#[derive(Debug, Clone, Default)]
+struct PartitionEntry {
+    bucket_ids: Vec<BucketId>,
+    docs: Vec<DocId>,
+}
+
+impl PartitionEntry {
+    #[inline]
+    fn clear(&mut self) {
+        self.bucket_ids.clear();
+        self.docs.clear();
+    }
+}
+
+impl SubAggCache for HighCardSubAggCache {
+    fn new() -> Self {
+        Self {
+            partitions: Box::new(core::array::from_fn(|_| PartitionEntry::default())),
+        }
+    }
+
+    fn push(&mut self, bucket_id: BucketId, doc_id: DocId) {
+        let idx = bucket_id % NUM_PARTITIONS as u32;
+        let slot = &mut self.partitions[idx as usize];
+        slot.bucket_ids.push(bucket_id);
+        slot.docs.push(doc_id);
+    }
+
+    fn flush_local(
+        &mut self,
+        sub_agg: &mut Box<dyn SegmentAggregationCollector>,
+        agg_data: &mut AggregationsSegmentCtx,
+        _force: bool,
+    ) -> crate::Result<()> {
+        let mut max_bucket = 0u32;
+        for partition in self.partitions.iter() {
+            if let Some(&local_max) = partition.bucket_ids.iter().max() {
+                max_bucket = max_bucket.max(local_max);
+            }
+        }
+
+        sub_agg.prepare_max_bucket(max_bucket, agg_data)?;
+
+        for slot in self.partitions.iter() {
+            if !slot.bucket_ids.is_empty() {
+                // Reduce dynamic dispatch overhead by collecting a full partition in one call.
+                sub_agg.collect_multiple(&slot.bucket_ids, &slot.docs, agg_data)?;
+            }
+        }
+
+        self.clear();
+        Ok(())
+    }
+}
+
+#[derive(Debug)]
+pub(crate) struct LowCardSubAggCache {
+    /// Cache doc ids per bucket for sub-aggregations.
+    ///
+    /// The outer Vec is indexed by BucketId.
+    per_bucket_docs: Vec<Vec<DocId>>,
+}
+
+impl LowCardSubAggCache {
+    #[inline]
+    fn clear(&mut self) {
+        for v in &mut self.per_bucket_docs {
+            v.clear();
+        }
+    }
+}
+
+impl SubAggCache for LowCardSubAggCache {
+    fn new() -> Self {
+        Self {
+            per_bucket_docs: Vec::new(),
+        }
+    }
+
+    fn push(&mut self, bucket_id: BucketId, doc_id: DocId) {
+        let idx = bucket_id as usize;
+        if self.per_bucket_docs.len() <= idx {
+            self.per_bucket_docs.resize_with(idx + 1, Vec::new);
+        }
+        self.per_bucket_docs[idx].push(doc_id);
+    }
+
+    fn flush_local(
+        &mut self,
+        sub_agg: &mut Box<dyn SegmentAggregationCollector>,
+        agg_data: &mut AggregationsSegmentCtx,
+        force: bool,
+    ) -> crate::Result<()> {
+        // Pre-aggregated: call collect per bucket.
+        let max_bucket = (self.per_bucket_docs.len() as BucketId).saturating_sub(1);
+        sub_agg.prepare_max_bucket(max_bucket, agg_data)?;
+        // The threshold above which we flush buckets individually.
+        // Note: We need to make sure that we don't lock ourselves into a situation where we hit
+        // the FLUSH_THRESHOLD, but never flush any buckets. (except the final flush)
+        let mut bucket_treshold = FLUSH_THRESHOLD / (self.per_bucket_docs.len().max(1) * 2);
+        const _: () = {
+            // MAX_NUM_TERMS_FOR_VEC threshold is used for term aggregations
+            // Note: There may be other flexible values, for other aggregations, but we can use the
+            // const value here as a upper bound. (better than nothing)
+            let bucket_treshold_limit = FLUSH_THRESHOLD / (MAX_NUM_TERMS_FOR_VEC as usize * 2);
+            assert!(
+                bucket_treshold_limit > 0,
+                "Bucket threshold must be greater than 0"
+            );
+        };
+        if force {
+            bucket_treshold = 0;
+        }
+        for (bucket_id, docs) in self
+            .per_bucket_docs
+            .iter()
+            .enumerate()
+            .filter(|(_, docs)| docs.len() > bucket_treshold)
+        {
+            sub_agg.collect(bucket_id as BucketId, docs, agg_data)?;
+        }
+
+        self.clear();
+        Ok(())
+    }
+}

src/aggregation/collector.rs

@@ -1,9 +1,9 @@
 use super::agg_req::Aggregations;
 use super::agg_result::AggregationResults;
-use super::buf_collector::BufAggregationCollector;
+use super::cached_sub_aggs::LowCardCachedSubAggs;
 use super::intermediate_agg_result::IntermediateAggregationResults;
-use super::segment_agg_result::SegmentAggregationCollector;
 use super::AggContextParams;
+// group buffering strategy is chosen explicitly by callers; no need to hash-group on the fly.
 use crate::aggregation::agg_data::{
     build_aggregations_data_from_req, build_segment_agg_collectors_root, AggregationsSegmentCtx,
 };
@@ -66,7 +66,7 @@ impl Collector for DistributedAggregationCollector {
     fn for_segment(
         &self,
         segment_local_id: crate::SegmentOrdinal,
-        reader: &crate::SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         AggregationSegmentCollector::from_agg_req_and_reader(
             &self.agg,
@@ -96,7 +96,7 @@ impl Collector for AggregationCollector {
     fn for_segment(
         &self,
         segment_local_id: crate::SegmentOrdinal,
-        reader: &crate::SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         AggregationSegmentCollector::from_agg_req_and_reader(
             &self.agg,
@@ -136,7 +136,7 @@ fn merge_fruits(
 /// `AggregationSegmentCollector` does the aggregation collection on a segment.
 pub struct AggregationSegmentCollector {
     aggs_with_accessor: AggregationsSegmentCtx,
-    agg_collector: BufAggregationCollector,
+    agg_collector: LowCardCachedSubAggs,
     error: Option<TantivyError>,
 }
 
@@ -145,14 +145,17 @@ impl AggregationSegmentCollector {
     /// reader. Also includes validation, e.g. checking field types and existence.
     pub fn from_agg_req_and_reader(
         agg: &Aggregations,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
         segment_ordinal: SegmentOrdinal,
         context: &AggContextParams,
     ) -> crate::Result<Self> {
         let mut agg_data =
             build_aggregations_data_from_req(agg, reader, segment_ordinal, context.clone())?;
-        let result =
-            BufAggregationCollector::new(build_segment_agg_collectors_root(&mut agg_data)?);
+        let mut result =
+            LowCardCachedSubAggs::new(build_segment_agg_collectors_root(&mut agg_data)?);
+        result
+            .get_sub_agg_collector()
+            .prepare_max_bucket(0, &agg_data)?; // prepare for bucket zero
 
         Ok(AggregationSegmentCollector {
             aggs_with_accessor: agg_data,
@@ -170,26 +173,31 @@ impl SegmentCollector for AggregationSegmentCollector {
         if self.error.is_some() {
             return;
         }
-        if let Err(err) = self
+        self.agg_collector.push(0, doc);
+        match self
             .agg_collector
-            .collect(doc, &mut self.aggs_with_accessor)
+            .check_flush_local(&mut self.aggs_with_accessor)
         {
-            self.error = Some(err);
+            Ok(_) => {}
+            Err(e) => {
+                self.error = Some(e);
+            }
         }
     }
-
-    /// The query pushes the documents to the collector via this method.
-    ///
-    /// Only valid for Collectors that ignore docs
     fn collect_block(&mut self, docs: &[DocId]) {
         if self.error.is_some() {
             return;
         }
-        if let Err(err) = self
-            .agg_collector
-            .collect_block(docs, &mut self.aggs_with_accessor)
-        {
-            self.error = Some(err);
+
+        match self.agg_collector.get_sub_agg_collector().collect(
+            0,
+            docs,
+            &mut self.aggs_with_accessor,
+        ) {
+            Ok(_) => {}
+            Err(e) => {
+                self.error = Some(e);
+            }
         }
     }
 
@@ -200,10 +208,13 @@ impl SegmentCollector for AggregationSegmentCollector {
         self.agg_collector.flush(&mut self.aggs_with_accessor)?;
 
         let mut sub_aggregation_res = IntermediateAggregationResults::default();
-        Box::new(self.agg_collector).add_intermediate_aggregation_result(
-            &self.aggs_with_accessor,
-            &mut sub_aggregation_res,
-        )?;
+        self.agg_collector
+            .get_sub_agg_collector()
+            .add_intermediate_aggregation_result(
+                &self.aggs_with_accessor,
+                &mut sub_aggregation_res,
+                0,
+            )?;
 
         Ok(sub_aggregation_res)
     }

src/aggregation/intermediate_agg_result.rs

@@ -792,7 +792,7 @@ pub struct IntermediateRangeBucketEntry {
     /// The number of documents in the bucket.
     pub doc_count: u64,
     /// The sub_aggregation in this bucket.
-    pub sub_aggregation: IntermediateAggregationResults,
+    pub sub_aggregation_res: IntermediateAggregationResults,
     /// The from range of the bucket. Equals `f64::MIN` when `None`.
     pub from: Option<f64>,
     /// The to range of the bucket. Equals `f64::MAX` when `None`.
@@ -811,7 +811,7 @@ impl IntermediateRangeBucketEntry {
             key: self.key.into(),
             doc_count: self.doc_count,
             sub_aggregation: self
-                .sub_aggregation
+                .sub_aggregation_res
                 .into_final_result_internal(req, limits)?,
             to: self.to,
             from: self.from,
@@ -857,7 +857,8 @@ impl MergeFruits for IntermediateTermBucketEntry {
 impl MergeFruits for IntermediateRangeBucketEntry {
     fn merge_fruits(&mut self, other: IntermediateRangeBucketEntry) -> crate::Result<()> {
         self.doc_count += other.doc_count;
-        self.sub_aggregation.merge_fruits(other.sub_aggregation)?;
+        self.sub_aggregation_res
+            .merge_fruits(other.sub_aggregation_res)?;
         Ok(())
     }
 }
@@ -887,7 +888,7 @@ mod tests {
                 IntermediateRangeBucketEntry {
                     key: IntermediateKey::Str(key.to_string()),
                     doc_count: *doc_count,
-                    sub_aggregation: Default::default(),
+                    sub_aggregation_res: Default::default(),
                     from: None,
                     to: None,
                 },
@@ -920,7 +921,7 @@ mod tests {
                     doc_count: *doc_count,
                     from: None,
                     to: None,
-                    sub_aggregation: get_sub_test_tree(&[(
+                    sub_aggregation_res: get_sub_test_tree(&[(
                         sub_aggregation_key.to_string(),
                         *sub_aggregation_count,
                     )]),

src/aggregation/metric/average.rs

@@ -52,10 +52,8 @@ pub struct IntermediateAverage {
 
 impl IntermediateAverage {
     /// Creates a new [`IntermediateAverage`] instance from a [`SegmentStatsCollector`].
-    pub(crate) fn from_collector(collector: SegmentStatsCollector) -> Self {
-        Self {
-            stats: collector.stats,
-        }
+    pub(crate) fn from_stats(stats: IntermediateStats) -> Self {
+        Self { stats }
     }
     /// Merges the other intermediate result into self.
     pub fn merge_fruits(&mut self, other: IntermediateAverage) {

src/aggregation/metric/cardinality.rs

@@ -2,7 +2,7 @@ use std::collections::hash_map::DefaultHasher;
 use std::hash::{BuildHasher, Hasher};
 
 use columnar::column_values::CompactSpaceU64Accessor;
-use columnar::{Column, ColumnBlockAccessor, ColumnType, Dictionary, StrColumn};
+use columnar::{Column, ColumnType, Dictionary, StrColumn};
 use common::f64_to_u64;
 use hyperloglogplus::{HyperLogLog, HyperLogLogPlus};
 use rustc_hash::FxHashSet;
@@ -106,8 +106,6 @@ pub struct CardinalityAggReqData {
     pub str_dict_column: Option<StrColumn>,
     /// The missing value normalized to the internal u64 representation of the field type.
     pub missing_value_for_accessor: Option<u64>,
-    /// The column block accessor to access the fast field values.
-    pub(crate) column_block_accessor: ColumnBlockAccessor<u64>,
     /// The name of the aggregation.
     pub name: String,
     /// The aggregation request.
@@ -135,45 +133,34 @@ impl CardinalityAggregationReq {
     }
 }
 
-#[derive(Clone, Debug, PartialEq)]
+#[derive(Clone, Debug)]
 pub(crate) struct SegmentCardinalityCollector {
-    cardinality: CardinalityCollector,
-    entries: FxHashSet<u64>,
+    buckets: Vec<SegmentCardinalityCollectorBucket>,
     accessor_idx: usize,
+    /// The column accessor to access the fast field values.
+    accessor: Column<u64>,
+    /// The column_type of the field.
+    column_type: ColumnType,
+    /// The missing value normalized to the internal u64 representation of the field type.
+    missing_value_for_accessor: Option<u64>,
 }
 
-impl SegmentCardinalityCollector {
-    pub fn from_req(column_type: ColumnType, accessor_idx: usize) -> Self {
+#[derive(Clone, Debug, PartialEq, Default)]
+pub(crate) struct SegmentCardinalityCollectorBucket {
+    cardinality: CardinalityCollector,
+    entries: FxHashSet<u64>,
+}
+impl SegmentCardinalityCollectorBucket {
+    pub fn new(column_type: ColumnType) -> Self {
         Self {
             cardinality: CardinalityCollector::new(column_type as u8),
-            entries: Default::default(),
-            accessor_idx,
+            entries: FxHashSet::default(),
         }
     }
-
-    fn fetch_block_with_field(
-        &mut self,
-        docs: &[crate::DocId],
-        agg_data: &mut CardinalityAggReqData,
-    ) {
-        if let Some(missing) = agg_data.missing_value_for_accessor {
-            agg_data.column_block_accessor.fetch_block_with_missing(
-                docs,
-                &agg_data.accessor,
-                missing,
-            );
-        } else {
-            agg_data
-                .column_block_accessor
-                .fetch_block(docs, &agg_data.accessor);
-        }
-    }
-
     fn into_intermediate_metric_result(
         mut self,
-        agg_data: &AggregationsSegmentCtx,
+        req_data: &CardinalityAggReqData,
     ) -> crate::Result<IntermediateMetricResult> {
-        let req_data = &agg_data.get_cardinality_req_data(self.accessor_idx);
         if req_data.column_type == ColumnType::Str {
             let fallback_dict = Dictionary::empty();
             let dict = req_data
@@ -194,6 +181,7 @@ impl SegmentCardinalityCollector {
                     term_ids.push(term_ord as u32);
                 }
             }
+
             term_ids.sort_unstable();
             dict.sorted_ords_to_term_cb(term_ids.iter().map(|term| *term as u64), |term| {
                 self.cardinality.sketch.insert_any(&term);
@@ -227,16 +215,49 @@ impl SegmentCardinalityCollector {
     }
 }
 
+impl SegmentCardinalityCollector {
+    pub fn from_req(
+        column_type: ColumnType,
+        accessor_idx: usize,
+        accessor: Column<u64>,
+        missing_value_for_accessor: Option<u64>,
+    ) -> Self {
+        Self {
+            buckets: vec![SegmentCardinalityCollectorBucket::new(column_type); 1],
+            column_type,
+            accessor_idx,
+            accessor,
+            missing_value_for_accessor,
+        }
+    }
+
+    fn fetch_block_with_field(
+        &mut self,
+        docs: &[crate::DocId],
+        agg_data: &mut AggregationsSegmentCtx,
+    ) {
+        agg_data.column_block_accessor.fetch_block_with_missing(
+            docs,
+            &self.accessor,
+            self.missing_value_for_accessor,
+        );
+    }
+}
+
 impl SegmentAggregationCollector for SegmentCardinalityCollector {
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
+        self.prepare_max_bucket(parent_bucket_id, agg_data)?;
         let req_data = &agg_data.get_cardinality_req_data(self.accessor_idx);
         let name = req_data.name.to_string();
+        // take the bucket in buckets and replace it with a new empty one
+        let bucket = std::mem::take(&mut self.buckets[parent_bucket_id as usize]);
 
-        let intermediate_result = self.into_intermediate_metric_result(agg_data)?;
+        let intermediate_result = bucket.into_intermediate_metric_result(req_data)?;
         results.push(
             name,
             IntermediateAggregationResult::Metric(intermediate_result),
@@ -247,27 +268,20 @@ impl SegmentAggregationCollector for SegmentCardinalityCollector {
 
     fn collect(
         &mut self,
-        doc: crate::DocId,
-        agg_data: &mut AggregationsSegmentCtx,
-    ) -> crate::Result<()> {
-        self.collect_block(&[doc], agg_data)
-    }
-
-    fn collect_block(
-        &mut self,
+        parent_bucket_id: BucketId,
         docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        let req_data = agg_data.get_cardinality_req_data_mut(self.accessor_idx);
-        self.fetch_block_with_field(docs, req_data);
+        self.fetch_block_with_field(docs, agg_data);
+        let bucket = &mut self.buckets[parent_bucket_id as usize];
 
-        let col_block_accessor = &req_data.column_block_accessor;
-        if req_data.column_type == ColumnType::Str {
+        let col_block_accessor = &agg_data.column_block_accessor;
+        if self.column_type == ColumnType::Str {
             for term_ord in col_block_accessor.iter_vals() {
-                self.entries.insert(term_ord);
+                bucket.entries.insert(term_ord);
             }
-        } else if req_data.column_type == ColumnType::IpAddr {
-            let compact_space_accessor = req_data
+        } else if self.column_type == ColumnType::IpAddr {
+            let compact_space_accessor = self
                 .accessor
                 .values
                 .clone()
@@ -282,16 +296,29 @@ impl SegmentAggregationCollector for SegmentCardinalityCollector {
                 })?;
             for val in col_block_accessor.iter_vals() {
                 let val: u128 = compact_space_accessor.compact_to_u128(val as u32);
-                self.cardinality.sketch.insert_any(&val);
+                bucket.cardinality.sketch.insert_any(&val);
             }
         } else {
             for val in col_block_accessor.iter_vals() {
-                self.cardinality.sketch.insert_any(&val);
+                bucket.cardinality.sketch.insert_any(&val);
             }
         }
 
         Ok(())
     }
+
+    fn prepare_max_bucket(
+        &mut self,
+        max_bucket: BucketId,
+        _agg_data: &AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        if max_bucket as usize >= self.buckets.len() {
+            self.buckets.resize_with(max_bucket as usize + 1, || {
+                SegmentCardinalityCollectorBucket::new(self.column_type)
+            });
+        }
+        Ok(())
+    }
 }
 
 #[derive(Clone, Debug, Serialize, Deserialize)]

src/aggregation/metric/count.rs

@@ -52,10 +52,8 @@ pub struct IntermediateCount {
 
 impl IntermediateCount {
     /// Creates a new [`IntermediateCount`] instance from a [`SegmentStatsCollector`].
-    pub(crate) fn from_collector(collector: SegmentStatsCollector) -> Self {
-        Self {
-            stats: collector.stats,
-        }
+    pub(crate) fn from_stats(stats: IntermediateStats) -> Self {
+        Self { stats }
     }
     /// Merges the other intermediate result into self.
     pub fn merge_fruits(&mut self, other: IntermediateCount) {

src/aggregation/metric/extended_stats.rs

@@ -8,10 +8,9 @@ use crate::aggregation::agg_data::AggregationsSegmentCtx;
 use crate::aggregation::intermediate_agg_result::{
     IntermediateAggregationResult, IntermediateAggregationResults, IntermediateMetricResult,
 };
-use crate::aggregation::metric::MetricAggReqData;
 use crate::aggregation::segment_agg_result::SegmentAggregationCollector;
 use crate::aggregation::*;
-use crate::{DocId, TantivyError};
+use crate::TantivyError;
 
 /// A multi-value metric aggregation that computes a collection of extended statistics
 /// on numeric values that are extracted
@@ -318,51 +317,28 @@ impl IntermediateExtendedStats {
     }
 }
 
-#[derive(Clone, Debug, PartialEq)]
+#[derive(Clone, Debug)]
 pub(crate) struct SegmentExtendedStatsCollector {
+    name: String,
     missing: Option<u64>,
     field_type: ColumnType,
-    pub(crate) extended_stats: IntermediateExtendedStats,
-    pub(crate) accessor_idx: usize,
-    val_cache: Vec<u64>,
+    accessor: columnar::Column<u64>,
+    buckets: Vec<IntermediateExtendedStats>,
+    sigma: Option<f64>,
 }
 
 impl SegmentExtendedStatsCollector {
-    pub fn from_req(
-        field_type: ColumnType,
-        sigma: Option<f64>,
-        accessor_idx: usize,
-        missing: Option<f64>,
-    ) -> Self {
-        let missing = missing.and_then(|val| f64_to_fastfield_u64(val, &field_type));
+    pub fn from_req(req: &MetricAggReqData, sigma: Option<f64>) -> Self {
+        let missing = req
+            .missing
+            .and_then(|val| f64_to_fastfield_u64(val, &req.field_type));
         Self {
-            field_type,
-            extended_stats: IntermediateExtendedStats::with_sigma(sigma),
-            accessor_idx,
+            name: req.name.clone(),
+            field_type: req.field_type,
+            accessor: req.accessor.clone(),
             missing,
-            val_cache: Default::default(),
-        }
-    }
-    #[inline]
-    pub(crate) fn collect_block_with_field(
-        &mut self,
-        docs: &[DocId],
-        req_data: &mut MetricAggReqData,
-    ) {
-        if let Some(missing) = self.missing.as_ref() {
-            req_data.column_block_accessor.fetch_block_with_missing(
-                docs,
-                &req_data.accessor,
-                *missing,
-            );
-        } else {
-            req_data
-                .column_block_accessor
-                .fetch_block(docs, &req_data.accessor);
-        }
-        for val in req_data.column_block_accessor.iter_vals() {
-            let val1 = f64_from_fastfield_u64(val, &self.field_type);
-            self.extended_stats.collect(val1);
+            buckets: vec![IntermediateExtendedStats::with_sigma(sigma); 16],
+            sigma,
         }
     }
 }
@@ -370,15 +346,18 @@ impl SegmentExtendedStatsCollector {
 impl SegmentAggregationCollector for SegmentExtendedStatsCollector {
     #[inline]
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
-        let name = agg_data.get_metric_req_data(self.accessor_idx).name.clone();
+        let name = self.name.clone();
+        self.prepare_max_bucket(parent_bucket_id, agg_data)?;
+        let extended_stats = std::mem::take(&mut self.buckets[parent_bucket_id as usize]);
         results.push(
             name,
             IntermediateAggregationResult::Metric(IntermediateMetricResult::ExtendedStats(
-                self.extended_stats,
+                extended_stats,
             )),
         )?;
 
@@ -388,39 +367,36 @@ impl SegmentAggregationCollector for SegmentExtendedStatsCollector {
     #[inline]
     fn collect(
         &mut self,
-        doc: crate::DocId,
+        parent_bucket_id: BucketId,
+        docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        let req_data = agg_data.get_metric_req_data(self.accessor_idx);
-        if let Some(missing) = self.missing {
-            let mut has_val = false;
-            for val in req_data.accessor.values_for_doc(doc) {
-                let val1 = f64_from_fastfield_u64(val, &self.field_type);
-                self.extended_stats.collect(val1);
-                has_val = true;
-            }
-            if !has_val {
-                self.extended_stats
-                    .collect(f64_from_fastfield_u64(missing, &self.field_type));
-            }
-        } else {
-            for val in req_data.accessor.values_for_doc(doc) {
-                let val1 = f64_from_fastfield_u64(val, &self.field_type);
-                self.extended_stats.collect(val1);
-            }
+        let mut extended_stats = self.buckets[parent_bucket_id as usize].clone();
+
+        agg_data
+            .column_block_accessor
+            .fetch_block_with_missing(docs, &self.accessor, self.missing);
+        for val in agg_data.column_block_accessor.iter_vals() {
+            let val1 = f64_from_fastfield_u64(val, self.field_type);
+            extended_stats.collect(val1);
         }
 
+        // store back
+        self.buckets[parent_bucket_id as usize] = extended_stats;
+
         Ok(())
     }
 
-    #[inline]
-    fn collect_block(
+    fn prepare_max_bucket(
         &mut self,
-        docs: &[crate::DocId],
-        agg_data: &mut AggregationsSegmentCtx,
+        max_bucket: BucketId,
+        _agg_data: &AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        let req_data = agg_data.get_metric_req_data_mut(self.accessor_idx);
-        self.collect_block_with_field(docs, req_data);
+        if self.buckets.len() <= max_bucket as usize {
+            self.buckets.resize_with(max_bucket as usize + 1, || {
+                IntermediateExtendedStats::with_sigma(self.sigma)
+            });
+        }
         Ok(())
     }
 }

src/aggregation/metric/max.rs

@@ -52,10 +52,8 @@ pub struct IntermediateMax {
 
 impl IntermediateMax {
     /// Creates a new [`IntermediateMax`] instance from a [`SegmentStatsCollector`].
-    pub(crate) fn from_collector(collector: SegmentStatsCollector) -> Self {
-        Self {
-            stats: collector.stats,
-        }
+    pub(crate) fn from_stats(stats: IntermediateStats) -> Self {
+        Self { stats }
     }
     /// Merges the other intermediate result into self.
     pub fn merge_fruits(&mut self, other: IntermediateMax) {

src/aggregation/metric/min.rs

@@ -52,10 +52,8 @@ pub struct IntermediateMin {
 
 impl IntermediateMin {
     /// Creates a new [`IntermediateMin`] instance from a [`SegmentStatsCollector`].
-    pub(crate) fn from_collector(collector: SegmentStatsCollector) -> Self {
-        Self {
-            stats: collector.stats,
-        }
+    pub(crate) fn from_stats(stats: IntermediateStats) -> Self {
+        Self { stats }
     }
     /// Merges the other intermediate result into self.
     pub fn merge_fruits(&mut self, other: IntermediateMin) {

src/aggregation/metric/mod.rs

@@ -31,7 +31,7 @@ use std::collections::HashMap;
 
 pub use average::*;
 pub use cardinality::*;
-use columnar::{Column, ColumnBlockAccessor, ColumnType};
+use columnar::{Column, ColumnType};
 pub use count::*;
 pub use extended_stats::*;
 pub use max::*;
@@ -55,8 +55,6 @@ pub struct MetricAggReqData {
     pub field_type: ColumnType,
     /// The missing value normalized to the internal u64 representation of the field type.
     pub missing_u64: Option<u64>,
-    /// The column block accessor to access the fast field values.
-    pub column_block_accessor: ColumnBlockAccessor<u64>,
     /// The column accessor to access the fast field values.
     pub accessor: Column<u64>,
     /// Used when converting to intermediate result

src/aggregation/metric/percentiles.rs

@@ -7,10 +7,9 @@ use crate::aggregation::agg_data::AggregationsSegmentCtx;
 use crate::aggregation::intermediate_agg_result::{
     IntermediateAggregationResult, IntermediateAggregationResults, IntermediateMetricResult,
 };
-use crate::aggregation::metric::MetricAggReqData;
 use crate::aggregation::segment_agg_result::SegmentAggregationCollector;
 use crate::aggregation::*;
-use crate::{DocId, TantivyError};
+use crate::TantivyError;
 
 /// # Percentiles
 ///
@@ -131,10 +130,16 @@ impl PercentilesAggregationReq {
     }
 }
 
-#[derive(Clone, Debug, PartialEq)]
+#[derive(Clone, Debug)]
 pub(crate) struct SegmentPercentilesCollector {
-    pub(crate) percentiles: PercentilesCollector,
+    pub(crate) buckets: Vec<PercentilesCollector>,
     pub(crate) accessor_idx: usize,
+    /// The type of the field.
+    pub field_type: ColumnType,
+    /// The missing value normalized to the internal u64 representation of the field type.
+    pub missing_u64: Option<u64>,
+    /// The column accessor to access the fast field values.
+    pub accessor: Column<u64>,
 }
 
 #[derive(Clone, Serialize, Deserialize)]
@@ -229,33 +234,18 @@ impl PercentilesCollector {
 }
 
 impl SegmentPercentilesCollector {
-    pub fn from_req_and_validate(accessor_idx: usize) -> crate::Result<Self> {
-        Ok(Self {
-            percentiles: PercentilesCollector::new(),
+    pub fn from_req_and_validate(
+        field_type: ColumnType,
+        missing_u64: Option<u64>,
+        accessor: Column<u64>,
+        accessor_idx: usize,
+    ) -> Self {
+        Self {
+            buckets: Vec::with_capacity(64),
+            field_type,
+            missing_u64,
+            accessor,
             accessor_idx,
-        })
-    }
-    #[inline]
-    pub(crate) fn collect_block_with_field(
-        &mut self,
-        docs: &[DocId],
-        req_data: &mut MetricAggReqData,
-    ) {
-        if let Some(missing) = req_data.missing_u64.as_ref() {
-            req_data.column_block_accessor.fetch_block_with_missing(
-                docs,
-                &req_data.accessor,
-                *missing,
-            );
-        } else {
-            req_data
-                .column_block_accessor
-                .fetch_block(docs, &req_data.accessor);
-        }
-
-        for val in req_data.column_block_accessor.iter_vals() {
-            let val1 = f64_from_fastfield_u64(val, &req_data.field_type);
-            self.percentiles.collect(val1);
         }
     }
 }
@@ -263,12 +253,18 @@ impl SegmentPercentilesCollector {
 impl SegmentAggregationCollector for SegmentPercentilesCollector {
     #[inline]
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
         let name = agg_data.get_metric_req_data(self.accessor_idx).name.clone();
-        let intermediate_metric_result = IntermediateMetricResult::Percentiles(self.percentiles);
+        self.prepare_max_bucket(parent_bucket_id, agg_data)?;
+        // Swap collector with an empty one to avoid cloning
+        let percentiles_collector = std::mem::take(&mut self.buckets[parent_bucket_id as usize]);
+
+        let intermediate_metric_result =
+            IntermediateMetricResult::Percentiles(percentiles_collector);
 
         results.push(
             name,
@@ -281,40 +277,33 @@ impl SegmentAggregationCollector for SegmentPercentilesCollector {
     #[inline]
     fn collect(
         &mut self,
-        doc: crate::DocId,
+        parent_bucket_id: BucketId,
+        docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        let req_data = agg_data.get_metric_req_data(self.accessor_idx);
+        let percentiles = &mut self.buckets[parent_bucket_id as usize];
+        agg_data.column_block_accessor.fetch_block_with_missing(
+            docs,
+            &self.accessor,
+            self.missing_u64,
+        );
 
-        if let Some(missing) = req_data.missing_u64 {
-            let mut has_val = false;
-            for val in req_data.accessor.values_for_doc(doc) {
-                let val1 = f64_from_fastfield_u64(val, &req_data.field_type);
-                self.percentiles.collect(val1);
-                has_val = true;
-            }
-            if !has_val {
-                self.percentiles
-                    .collect(f64_from_fastfield_u64(missing, &req_data.field_type));
-            }
-        } else {
-            for val in req_data.accessor.values_for_doc(doc) {
-                let val1 = f64_from_fastfield_u64(val, &req_data.field_type);
-                self.percentiles.collect(val1);
-            }
+        for val in agg_data.column_block_accessor.iter_vals() {
+            let val1 = f64_from_fastfield_u64(val, self.field_type);
+            percentiles.collect(val1);
         }
 
         Ok(())
     }
 
-    #[inline]
-    fn collect_block(
+    fn prepare_max_bucket(
         &mut self,
-        docs: &[crate::DocId],
-        agg_data: &mut AggregationsSegmentCtx,
+        max_bucket: BucketId,
+        _agg_data: &AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        let req_data = agg_data.get_metric_req_data_mut(self.accessor_idx);
-        self.collect_block_with_field(docs, req_data);
+        while self.buckets.len() <= max_bucket as usize {
+            self.buckets.push(PercentilesCollector::new());
+        }
         Ok(())
     }
 }

src/aggregation/metric/stats.rs

@@ -1,5 +1,6 @@
 use std::fmt::Debug;
 
+use columnar::{Column, ColumnType};
 use serde::{Deserialize, Serialize};
 
 use super::*;
@@ -7,10 +8,9 @@ use crate::aggregation::agg_data::AggregationsSegmentCtx;
 use crate::aggregation::intermediate_agg_result::{
     IntermediateAggregationResult, IntermediateAggregationResults, IntermediateMetricResult,
 };
-use crate::aggregation::metric::MetricAggReqData;
 use crate::aggregation::segment_agg_result::SegmentAggregationCollector;
 use crate::aggregation::*;
-use crate::{DocId, TantivyError};
+use crate::TantivyError;
 
 /// A multi-value metric aggregation that computes a collection of statistics on numeric values that
 /// are extracted from the aggregated documents.
@@ -83,7 +83,7 @@ impl Stats {
 
 /// Intermediate result of the stats aggregation that can be combined with other intermediate
 /// results.
-#[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
+#[derive(Clone, Copy, Debug, PartialEq, Serialize, Deserialize)]
 pub struct IntermediateStats {
     /// The number of extracted values.
     pub(crate) count: u64,
@@ -187,75 +187,75 @@ pub enum StatsType {
     Percentiles,
 }
 
+fn create_collector<const TYPE_ID: u8>(
+    req: &MetricAggReqData,
+) -> Box<dyn SegmentAggregationCollector> {
+    Box::new(SegmentStatsCollector::<TYPE_ID> {
+        name: req.name.clone(),
+        collecting_for: req.collecting_for,
+        is_number_or_date_type: req.is_number_or_date_type,
+        missing_u64: req.missing_u64,
+        accessor: req.accessor.clone(),
+        buckets: vec![IntermediateStats::default()],
+    })
+}
+
+/// Build a concrete `SegmentStatsCollector` depending on the column type.
+pub(crate) fn build_segment_stats_collector(
+    req: &MetricAggReqData,
+) -> crate::Result<Box<dyn SegmentAggregationCollector>> {
+    match req.field_type {
+        ColumnType::I64 => Ok(create_collector::<{ ColumnType::I64 as u8 }>(req)),
+        ColumnType::U64 => Ok(create_collector::<{ ColumnType::U64 as u8 }>(req)),
+        ColumnType::F64 => Ok(create_collector::<{ ColumnType::F64 as u8 }>(req)),
+        ColumnType::Bool => Ok(create_collector::<{ ColumnType::Bool as u8 }>(req)),
+        ColumnType::DateTime => Ok(create_collector::<{ ColumnType::DateTime as u8 }>(req)),
+        ColumnType::Bytes => Ok(create_collector::<{ ColumnType::Bytes as u8 }>(req)),
+        ColumnType::Str => Ok(create_collector::<{ ColumnType::Str as u8 }>(req)),
+        ColumnType::IpAddr => Ok(create_collector::<{ ColumnType::IpAddr as u8 }>(req)),
+    }
+}
+
+#[repr(C)]
 #[derive(Clone, Debug)]
-pub(crate) struct SegmentStatsCollector {
-    pub(crate) stats: IntermediateStats,
-    pub(crate) accessor_idx: usize,
+pub(crate) struct SegmentStatsCollector<const COLUMN_TYPE_ID: u8> {
+    pub(crate) missing_u64: Option<u64>,
+    pub(crate) accessor: Column<u64>,
+    pub(crate) is_number_or_date_type: bool,
+    pub(crate) buckets: Vec<IntermediateStats>,
+    pub(crate) name: String,
+    pub(crate) collecting_for: StatsType,
 }
 
-impl SegmentStatsCollector {
-    pub fn from_req(accessor_idx: usize) -> Self {
-        Self {
-            stats: IntermediateStats::default(),
-            accessor_idx,
-        }
-    }
-    #[inline]
-    pub(crate) fn collect_block_with_field(
-        &mut self,
-        docs: &[DocId],
-        req_data: &mut MetricAggReqData,
-    ) {
-        if let Some(missing) = req_data.missing_u64.as_ref() {
-            req_data.column_block_accessor.fetch_block_with_missing(
-                docs,
-                &req_data.accessor,
-                *missing,
-            );
-        } else {
-            req_data
-                .column_block_accessor
-                .fetch_block(docs, &req_data.accessor);
-        }
-        if req_data.is_number_or_date_type {
-            for val in req_data.column_block_accessor.iter_vals() {
-                let val1 = f64_from_fastfield_u64(val, &req_data.field_type);
-                self.stats.collect(val1);
-            }
-        } else {
-            for _val in req_data.column_block_accessor.iter_vals() {
-                // we ignore the value and simply record that we got something
-                self.stats.collect(0.0);
-            }
-        }
-    }
-}
-
-impl SegmentAggregationCollector for SegmentStatsCollector {
+impl<const COLUMN_TYPE_ID: u8> SegmentAggregationCollector
+    for SegmentStatsCollector<COLUMN_TYPE_ID>
+{
     #[inline]
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
-        let req = agg_data.get_metric_req_data(self.accessor_idx);
-        let name = req.name.clone();
+        let name = self.name.clone();
 
-        let intermediate_metric_result = match req.collecting_for {
+        self.prepare_max_bucket(parent_bucket_id, agg_data)?;
+        let stats = self.buckets[parent_bucket_id as usize];
+        let intermediate_metric_result = match self.collecting_for {
             StatsType::Average => {
-                IntermediateMetricResult::Average(IntermediateAverage::from_collector(*self))
+                IntermediateMetricResult::Average(IntermediateAverage::from_stats(stats))
             }
             StatsType::Count => {
-                IntermediateMetricResult::Count(IntermediateCount::from_collector(*self))
+                IntermediateMetricResult::Count(IntermediateCount::from_stats(stats))
             }
-            StatsType::Max => IntermediateMetricResult::Max(IntermediateMax::from_collector(*self)),
-            StatsType::Min => IntermediateMetricResult::Min(IntermediateMin::from_collector(*self)),
-            StatsType::Stats => IntermediateMetricResult::Stats(self.stats),
-            StatsType::Sum => IntermediateMetricResult::Sum(IntermediateSum::from_collector(*self)),
+            StatsType::Max => IntermediateMetricResult::Max(IntermediateMax::from_stats(stats)),
+            StatsType::Min => IntermediateMetricResult::Min(IntermediateMin::from_stats(stats)),
+            StatsType::Stats => IntermediateMetricResult::Stats(stats),
+            StatsType::Sum => IntermediateMetricResult::Sum(IntermediateSum::from_stats(stats)),
             _ => {
                 return Err(TantivyError::InvalidArgument(format!(
                     "Unsupported stats type for stats aggregation: {:?}",
-                    req.collecting_for
+                    self.collecting_for
                 )))
             }
         };
@@ -271,41 +271,67 @@ impl SegmentAggregationCollector for SegmentStatsCollector {
     #[inline]
     fn collect(
         &mut self,
-        doc: crate::DocId,
-        agg_data: &mut AggregationsSegmentCtx,
-    ) -> crate::Result<()> {
-        let req_data = agg_data.get_metric_req_data(self.accessor_idx);
-        if let Some(missing) = req_data.missing_u64 {
-            let mut has_val = false;
-            for val in req_data.accessor.values_for_doc(doc) {
-                let val1 = f64_from_fastfield_u64(val, &req_data.field_type);
-                self.stats.collect(val1);
-                has_val = true;
-            }
-            if !has_val {
-                self.stats
-                    .collect(f64_from_fastfield_u64(missing, &req_data.field_type));
-            }
-        } else {
-            for val in req_data.accessor.values_for_doc(doc) {
-                let val1 = f64_from_fastfield_u64(val, &req_data.field_type);
-                self.stats.collect(val1);
-            }
-        }
-
-        Ok(())
-    }
-
-    #[inline]
-    fn collect_block(
-        &mut self,
+        parent_bucket_id: BucketId,
         docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
-        let req_data = agg_data.get_metric_req_data_mut(self.accessor_idx);
-        self.collect_block_with_field(docs, req_data);
+        // TODO: remove once we fetch all values for all bucket ids in one go
+        if docs.len() == 1 && self.missing_u64.is_none() {
+            collect_stats::<COLUMN_TYPE_ID>(
+                &mut self.buckets[parent_bucket_id as usize],
+                self.accessor.values_for_doc(docs[0]),
+                self.is_number_or_date_type,
+            )?;
+
+            return Ok(());
+        }
+        agg_data.column_block_accessor.fetch_block_with_missing(
+            docs,
+            &self.accessor,
+            self.missing_u64,
+        );
+        collect_stats::<COLUMN_TYPE_ID>(
+            &mut self.buckets[parent_bucket_id as usize],
+            agg_data.column_block_accessor.iter_vals(),
+            self.is_number_or_date_type,
+        )?;
+
         Ok(())
     }
+
+    fn prepare_max_bucket(
+        &mut self,
+        max_bucket: BucketId,
+        _agg_data: &AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        let required_buckets = (max_bucket as usize) + 1;
+        if self.buckets.len() < required_buckets {
+            self.buckets
+                .resize_with(required_buckets, IntermediateStats::default);
+        }
+        Ok(())
+    }
+}
+
+#[inline]
+fn collect_stats<const COLUMN_TYPE_ID: u8>(
+    stats: &mut IntermediateStats,
+    vals: impl Iterator<Item = u64>,
+    is_number_or_date_type: bool,
+) -> crate::Result<()> {
+    if is_number_or_date_type {
+        for val in vals {
+            let val1 = convert_to_f64::<COLUMN_TYPE_ID>(val);
+            stats.collect(val1);
+        }
+    } else {
+        for _val in vals {
+            // we ignore the value and simply record that we got something
+            stats.collect(0.0);
+        }
+    }
+
+    Ok(())
 }
 
 #[cfg(test)]

src/aggregation/metric/sum.rs

@@ -52,10 +52,8 @@ pub struct IntermediateSum {
 
 impl IntermediateSum {
     /// Creates a new [`IntermediateSum`] instance from a [`SegmentStatsCollector`].
-    pub(crate) fn from_collector(collector: SegmentStatsCollector) -> Self {
-        Self {
-            stats: collector.stats,
-        }
+    pub(crate) fn from_stats(stats: IntermediateStats) -> Self {
+        Self { stats }
     }
     /// Merges the other intermediate result into self.
     pub fn merge_fruits(&mut self, other: IntermediateSum) {

src/aggregation/metric/top_hits.rs

@@ -15,12 +15,11 @@ use crate::aggregation::intermediate_agg_result::{
     IntermediateAggregationResult, IntermediateMetricResult,
 };
 use crate::aggregation::segment_agg_result::SegmentAggregationCollector;
-use crate::aggregation::AggregationError;
+use crate::aggregation::{AggregationError, BucketId};
 use crate::collector::sort_key::ReverseComparator;
 use crate::collector::TopNComputer;
 use crate::schema::OwnedValue;
 use crate::{DocAddress, DocId, SegmentOrdinal};
-// duplicate import removed; already imported above
 
 /// Contains all information required by the TopHitsSegmentCollector to perform the
 /// top_hits aggregation on a segment.
@@ -472,7 +471,10 @@ impl TopHitsTopNComputer {
     /// Create a new TopHitsCollector
     pub fn new(req: &TopHitsAggregationReq) -> Self {
         Self {
-            top_n: TopNComputer::new(req.size + req.from.unwrap_or(0)),
+            top_n: TopNComputer::new_with_comparator(
+                req.size + req.from.unwrap_or(0),
+                ReverseComparator,
+            ),
             req: req.clone(),
         }
     }
@@ -518,7 +520,8 @@ impl TopHitsTopNComputer {
 pub(crate) struct TopHitsSegmentCollector {
     segment_ordinal: SegmentOrdinal,
     accessor_idx: usize,
-    top_n: TopNComputer<Vec<DocValueAndOrder>, DocAddress, ReverseComparator>,
+    buckets: Vec<TopNComputer<Vec<DocValueAndOrder>, DocAddress, ReverseComparator>>,
+    num_hits: usize,
 }
 
 impl TopHitsSegmentCollector {
@@ -527,19 +530,29 @@ impl TopHitsSegmentCollector {
         accessor_idx: usize,
         segment_ordinal: SegmentOrdinal,
     ) -> Self {
+        let num_hits = req.size + req.from.unwrap_or(0);
         Self {
-            top_n: TopNComputer::new(req.size + req.from.unwrap_or(0)),
+            num_hits,
             segment_ordinal,
             accessor_idx,
+            buckets: vec![TopNComputer::new_with_comparator(num_hits, ReverseComparator); 1],
         }
     }
-    fn into_top_hits_collector(
-        self,
+    fn get_top_hits_computer(
+        &mut self,
+        parent_bucket_id: BucketId,
         value_accessors: &HashMap<String, Vec<DynamicColumn>>,
         req: &TopHitsAggregationReq,
     ) -> TopHitsTopNComputer {
+        if parent_bucket_id as usize >= self.buckets.len() {
+            return TopHitsTopNComputer::new(req);
+        }
+        let top_n = std::mem::replace(
+            &mut self.buckets[parent_bucket_id as usize],
+            TopNComputer::new(0),
+        );
         let mut top_hits_computer = TopHitsTopNComputer::new(req);
-        let top_results = self.top_n.into_vec();
+        let top_results = top_n.into_vec();
 
         for res in top_results {
             let doc_value_fields = req.get_document_field_data(value_accessors, res.doc.doc_id);
@@ -554,54 +567,24 @@ impl TopHitsSegmentCollector {
 
         top_hits_computer
     }
-
-    /// TODO add a specialized variant for a single sort field
-    fn collect_with(
-        &mut self,
-        doc_id: crate::DocId,
-        req: &TopHitsAggregationReq,
-        accessors: &[(Column<u64>, ColumnType)],
-    ) -> crate::Result<()> {
-        let sorts: Vec<DocValueAndOrder> = req
-            .sort
-            .iter()
-            .enumerate()
-            .map(|(idx, KeyOrder { order, .. })| {
-                let order = *order;
-                let value = accessors
-                    .get(idx)
-                    .expect("could not find field in accessors")
-                    .0
-                    .values_for_doc(doc_id)
-                    .next();
-                DocValueAndOrder { value, order }
-            })
-            .collect();
-
-        self.top_n.push(
-            sorts,
-            DocAddress {
-                segment_ord: self.segment_ordinal,
-                doc_id,
-            },
-        );
-        Ok(())
-    }
 }
 
 impl SegmentAggregationCollector for TopHitsSegmentCollector {
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut crate::aggregation::intermediate_agg_result::IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
         let req_data = agg_data.get_top_hits_req_data(self.accessor_idx);
 
         let value_accessors = &req_data.value_accessors;
 
-        let intermediate_result = IntermediateMetricResult::TopHits(
-            self.into_top_hits_collector(value_accessors, &req_data.req),
-        );
+        let intermediate_result = IntermediateMetricResult::TopHits(self.get_top_hits_computer(
+            parent_bucket_id,
+            value_accessors,
+            &req_data.req,
+        ));
         results.push(
             req_data.name.to_string(),
             IntermediateAggregationResult::Metric(intermediate_result),
@@ -611,26 +594,56 @@ impl SegmentAggregationCollector for TopHitsSegmentCollector {
     /// TODO: Consider a caching layer to reduce the call overhead
     fn collect(
         &mut self,
-        doc_id: crate::DocId,
-        agg_data: &mut AggregationsSegmentCtx,
-    ) -> crate::Result<()> {
-        let req_data = agg_data.get_top_hits_req_data(self.accessor_idx);
-        self.collect_with(doc_id, &req_data.req, &req_data.accessors)?;
-        Ok(())
-    }
-
-    fn collect_block(
-        &mut self,
+        parent_bucket_id: BucketId,
         docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
+        let top_n = &mut self.buckets[parent_bucket_id as usize];
         let req_data = agg_data.get_top_hits_req_data(self.accessor_idx);
-        // TODO: Consider getting fields with the column block accessor.
-        for doc in docs {
-            self.collect_with(*doc, &req_data.req, &req_data.accessors)?;
+        let req = &req_data.req;
+        let accessors = &req_data.accessors;
+        for &doc_id in docs {
+            // TODO: this is terrible, a new vec is allocated for every doc
+            // We can fetch blocks instead
+            // We don't need to store the order for every value
+            let sorts: Vec<DocValueAndOrder> = req
+                .sort
+                .iter()
+                .enumerate()
+                .map(|(idx, KeyOrder { order, .. })| {
+                    let order = *order;
+                    let value = accessors
+                        .get(idx)
+                        .expect("could not find field in accessors")
+                        .0
+                        .values_for_doc(doc_id)
+                        .next();
+                    DocValueAndOrder { value, order }
+                })
+                .collect();
+
+            top_n.push(
+                sorts,
+                DocAddress {
+                    segment_ord: self.segment_ordinal,
+                    doc_id,
+                },
+            );
         }
         Ok(())
     }
+
+    fn prepare_max_bucket(
+        &mut self,
+        max_bucket: BucketId,
+        _agg_data: &AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        self.buckets.resize(
+            (max_bucket as usize) + 1,
+            TopNComputer::new_with_comparator(self.num_hits, ReverseComparator),
+        );
+        Ok(())
+    }
 }
 
 #[cfg(test)]
@@ -746,7 +759,7 @@ mod tests {
                     ],
                     "from": 0,
                 }
-        }
+            }
         }))
         .unwrap();
 
@@ -875,7 +888,7 @@ mod tests {
                         "mixed.*",
                     ],
                 }
-        }
+            }
         }))?;
 
         let collector = AggregationCollector::from_aggs(d, Default::default());

src/aggregation/mod.rs

@@ -133,7 +133,7 @@ mod agg_limits;
 pub mod agg_req;
 pub mod agg_result;
 pub mod bucket;
-mod buf_collector;
+pub(crate) mod cached_sub_aggs;
 mod collector;
 mod date;
 mod error;
@@ -162,6 +162,19 @@ use serde::{Deserialize, Deserializer, Serialize};
 
 use crate::tokenizer::TokenizerManager;
 
+/// A bucket id is a dense identifier for a bucket within an aggregation.
+/// It is used to index into a Vec that hold per-bucket data.
+///
+/// For example, in a terms aggregation, each unique term will be assigned a incremental BucketId.
+/// This BucketId will be forwarded to sub-aggregations to identify the parent bucket.
+///
+/// This allows to have a single AggregationCollector instance per aggregation,
+/// that can handle multiple buckets efficiently.
+///
+/// The API to call sub-aggregations is therefore a &[(BucketId, &[DocId])].
+/// For that we'll need a buffer. One Vec per bucket aggregation is needed.
+pub type BucketId = u32;
+
 /// Context parameters for aggregation execution
 ///
 /// This struct holds shared resources needed during aggregation execution:
@@ -335,19 +348,37 @@ impl Display for Key {
     }
 }
 
+pub(crate) fn convert_to_f64<const COLUMN_TYPE_ID: u8>(val: u64) -> f64 {
+    if COLUMN_TYPE_ID == ColumnType::U64 as u8 {
+        val as f64
+    } else if COLUMN_TYPE_ID == ColumnType::I64 as u8
+        || COLUMN_TYPE_ID == ColumnType::DateTime as u8
+    {
+        i64::from_u64(val) as f64
+    } else if COLUMN_TYPE_ID == ColumnType::F64 as u8 {
+        f64::from_u64(val)
+    } else if COLUMN_TYPE_ID == ColumnType::Bool as u8 {
+        val as f64
+    } else {
+        panic!(
+            "ColumnType ID {} cannot be converted to f64 metric",
+            COLUMN_TYPE_ID
+        )
+    }
+}
+
 /// Inverse of `to_fastfield_u64`. Used to convert to `f64` for metrics.
 ///
 /// # Panics
 /// Only `u64`, `f64`, `date`, and `i64` are supported.
-pub(crate) fn f64_from_fastfield_u64(val: u64, field_type: &ColumnType) -> f64 {
+pub(crate) fn f64_from_fastfield_u64(val: u64, field_type: ColumnType) -> f64 {
     match field_type {
-        ColumnType::U64 => val as f64,
-        ColumnType::I64 | ColumnType::DateTime => i64::from_u64(val) as f64,
-        ColumnType::F64 => f64::from_u64(val),
-        ColumnType::Bool => val as f64,
-        _ => {
-            panic!("unexpected type {field_type:?}. This should not happen")
-        }
+        ColumnType::U64 => convert_to_f64::<{ ColumnType::U64 as u8 }>(val),
+        ColumnType::I64 => convert_to_f64::<{ ColumnType::I64 as u8 }>(val),
+        ColumnType::F64 => convert_to_f64::<{ ColumnType::F64 as u8 }>(val),
+        ColumnType::Bool => convert_to_f64::<{ ColumnType::Bool as u8 }>(val),
+        ColumnType::DateTime => convert_to_f64::<{ ColumnType::DateTime as u8 }>(val),
+        _ => panic!("unexpected type {field_type:?}. This should not happen"),
     }
 }
 

src/aggregation/segment_agg_result.rs

@@ -8,25 +8,67 @@ use std::fmt::Debug;
 pub(crate) use super::agg_limits::AggregationLimitsGuard;
 use super::intermediate_agg_result::IntermediateAggregationResults;
 use crate::aggregation::agg_data::AggregationsSegmentCtx;
+use crate::aggregation::BucketId;
+
+/// Monotonically increasing provider of BucketIds.
+#[derive(Debug, Clone, Default)]
+pub struct BucketIdProvider(u32);
+impl BucketIdProvider {
+    /// Get the next BucketId.
+    pub fn next_bucket_id(&mut self) -> BucketId {
+        let bucket_id = self.0;
+        self.0 += 1;
+        bucket_id
+    }
+}
 
 /// A SegmentAggregationCollector is used to collect aggregation results.
-pub trait SegmentAggregationCollector: CollectorClone + Debug {
+pub trait SegmentAggregationCollector: Debug {
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()>;
 
+    /// Note: The caller needs to call `prepare_max_bucket` before calling `collect`.
     fn collect(
         &mut self,
-        doc: crate::DocId,
+        parent_bucket_id: BucketId,
+        docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()>;
 
-    fn collect_block(
+    /// Collect docs for multiple buckets in one call.
+    /// Minimizes dynamic dispatch overhead when collecting many buckets.
+    ///
+    /// Note: The caller needs to call `prepare_max_bucket` before calling `collect`.
+    fn collect_multiple(
         &mut self,
+        bucket_ids: &[BucketId],
         docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        debug_assert_eq!(bucket_ids.len(), docs.len());
+        let mut start = 0;
+        while start < bucket_ids.len() {
+            let bucket_id = bucket_ids[start];
+            let mut end = start + 1;
+            while end < bucket_ids.len() && bucket_ids[end] == bucket_id {
+                end += 1;
+            }
+            self.collect(bucket_id, &docs[start..end], agg_data)?;
+            start = end;
+        }
+        Ok(())
+    }
+
+    /// Prepare the collector for collecting up to BucketId `max_bucket`.
+    /// This is useful so we can split allocation ahead of time of collecting.
+    fn prepare_max_bucket(
+        &mut self,
+        max_bucket: BucketId,
+        agg_data: &AggregationsSegmentCtx,
     ) -> crate::Result<()>;
 
     /// Finalize method. Some Aggregator collect blocks of docs before calling `collect_block`.
@@ -36,26 +78,7 @@ pub trait SegmentAggregationCollector: CollectorClone + Debug {
     }
 }
 
-/// A helper trait to enable cloning of Box<dyn SegmentAggregationCollector>
-pub trait CollectorClone {
-    fn clone_box(&self) -> Box<dyn SegmentAggregationCollector>;
-}
-
-impl<T> CollectorClone for T
-where T: 'static + SegmentAggregationCollector + Clone
-{
-    fn clone_box(&self) -> Box<dyn SegmentAggregationCollector> {
-        Box::new(self.clone())
-    }
-}
-
-impl Clone for Box<dyn SegmentAggregationCollector> {
-    fn clone(&self) -> Box<dyn SegmentAggregationCollector> {
-        self.clone_box()
-    }
-}
-
-#[derive(Clone, Default)]
+#[derive(Default)]
 /// The GenericSegmentAggregationResultsCollector is the generic version of the collector, which
 /// can handle arbitrary complexity of  sub-aggregations. Ideally we never have to pick this one
 /// and can provide specialized versions instead, that remove some of its overhead.
@@ -73,12 +96,13 @@ impl Debug for GenericSegmentAggregationResultsCollector {
 
 impl SegmentAggregationCollector for GenericSegmentAggregationResultsCollector {
     fn add_intermediate_aggregation_result(
-        self: Box<Self>,
+        &mut self,
         agg_data: &AggregationsSegmentCtx,
         results: &mut IntermediateAggregationResults,
+        parent_bucket_id: BucketId,
     ) -> crate::Result<()> {
-        for agg in self.aggs {
-            agg.add_intermediate_aggregation_result(agg_data, results)?;
+        for agg in &mut self.aggs {
+            agg.add_intermediate_aggregation_result(agg_data, results, parent_bucket_id)?;
         }
 
         Ok(())
@@ -86,23 +110,13 @@ impl SegmentAggregationCollector for GenericSegmentAggregationResultsCollector {
 
     fn collect(
         &mut self,
-        doc: crate::DocId,
-        agg_data: &mut AggregationsSegmentCtx,
-    ) -> crate::Result<()> {
-        self.collect_block(&[doc], agg_data)?;
-
-        Ok(())
-    }
-
-    fn collect_block(
-        &mut self,
+        parent_bucket_id: BucketId,
         docs: &[crate::DocId],
         agg_data: &mut AggregationsSegmentCtx,
     ) -> crate::Result<()> {
         for collector in &mut self.aggs {
-            collector.collect_block(docs, agg_data)?;
+            collector.collect(parent_bucket_id, docs, agg_data)?;
         }
-
         Ok(())
     }
 
@@ -112,4 +126,15 @@ impl SegmentAggregationCollector for GenericSegmentAggregationResultsCollector {
         }
         Ok(())
     }
+
+    fn prepare_max_bucket(
+        &mut self,
+        max_bucket: BucketId,
+        agg_data: &AggregationsSegmentCtx,
+    ) -> crate::Result<()> {
+        for collector in &mut self.aggs {
+            collector.prepare_max_bucket(max_bucket, agg_data)?;
+        }
+        Ok(())
+    }
 }

src/collector/count_collector.rs

@@ -43,7 +43,7 @@ impl Collector for Count {
     fn for_segment(
         &self,
         _: SegmentOrdinal,
-        _: &SegmentReader,
+        _: &dyn SegmentReader,
     ) -> crate::Result<SegmentCountCollector> {
         Ok(SegmentCountCollector::default())
     }

src/collector/docset_collector.rs

@@ -1,7 +1,7 @@
 use std::collections::HashSet;
 
 use super::{Collector, SegmentCollector};
-use crate::{DocAddress, DocId, Score};
+use crate::{DocAddress, DocId, Score, SegmentReader};
 
 /// Collectors that returns the set of DocAddress that matches the query.
 ///
@@ -15,7 +15,7 @@ impl Collector for DocSetCollector {
     fn for_segment(
         &self,
         segment_local_id: crate::SegmentOrdinal,
-        _segment: &crate::SegmentReader,
+        _segment: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         Ok(DocSetChildCollector {
             segment_local_id,

src/collector/facet_collector.rs

@@ -265,7 +265,7 @@ impl Collector for FacetCollector {
     fn for_segment(
         &self,
         _: SegmentOrdinal,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<FacetSegmentCollector> {
         let facet_reader = reader.facet_reader(&self.field_name)?;
         let facet_dict = facet_reader.facet_dict();
@@ -486,9 +486,9 @@ mod tests {
     use std::collections::BTreeSet;
 
     use columnar::Dictionary;
-    use rand::distributions::Uniform;
+    use rand::distr::Uniform;
     use rand::prelude::SliceRandom;
-    use rand::{thread_rng, Rng};
+    use rand::{rng, Rng};
 
     use super::{FacetCollector, FacetCounts};
     use crate::collector::facet_collector::compress_mapping;
@@ -731,7 +731,7 @@ mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
 
-        let uniform = Uniform::new_inclusive(1, 100_000);
+        let uniform = Uniform::new_inclusive(1, 100_000).unwrap();
         let mut docs: Vec<TantivyDocument> =
             vec![("a", 10), ("b", 100), ("c", 7), ("d", 12), ("e", 21)]
                 .into_iter()
@@ -741,14 +741,11 @@ mod tests {
                     std::iter::repeat_n(doc, count)
                 })
                 .map(|mut doc| {
-                    doc.add_facet(
-                        facet_field,
-                        &format!("/facet/{}", thread_rng().sample(uniform)),
-                    );
+                    doc.add_facet(facet_field, &format!("/facet/{}", rng().sample(uniform)));
                     doc
                 })
                 .collect();
-        docs[..].shuffle(&mut thread_rng());
+        docs[..].shuffle(&mut rng());
 
         let mut index_writer: IndexWriter = index.writer_for_tests().unwrap();
         for doc in docs {
@@ -822,8 +819,8 @@ mod tests {
 #[cfg(all(test, feature = "unstable"))]
 mod bench {
 
+    use rand::rng;
     use rand::seq::SliceRandom;
-    use rand::thread_rng;
     use test::Bencher;
 
     use crate::collector::FacetCollector;
@@ -846,7 +843,7 @@ mod bench {
             }
         }
         // 40425 docs
-        docs[..].shuffle(&mut thread_rng());
+        docs[..].shuffle(&mut rng());
 
         let mut index_writer: IndexWriter = index.writer_for_tests().unwrap();
         for doc in docs {

src/collector/filter_collector_wrapper.rs

@@ -113,7 +113,7 @@ where
     fn for_segment(
         &self,
         segment_local_id: u32,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let column_opt = segment_reader.fast_fields().column_opt(&self.field)?;
 
@@ -287,7 +287,7 @@ where
     fn for_segment(
         &self,
         segment_local_id: u32,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let column_opt = segment_reader.fast_fields().bytes(&self.field)?;
 

src/collector/histogram_collector.rs

@@ -6,7 +6,7 @@ use fastdivide::DividerU64;
 use crate::collector::{Collector, SegmentCollector};
 use crate::fastfield::{FastFieldNotAvailableError, FastValue};
 use crate::schema::Type;
-use crate::{DocId, Score};
+use crate::{DocId, Score, SegmentReader};
 
 /// Histogram builds an histogram of the values of a fastfield for the
 /// collected DocSet.
@@ -110,7 +110,7 @@ impl Collector for HistogramCollector {
     fn for_segment(
         &self,
         _segment_local_id: crate::SegmentOrdinal,
-        segment: &crate::SegmentReader,
+        segment: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let column_opt = segment.fast_fields().u64_lenient(&self.field)?;
         let (column, _column_type) = column_opt.ok_or_else(|| FastFieldNotAvailableError {

src/collector/mod.rs

@@ -156,7 +156,7 @@ pub trait Collector: Sync + Send {
     fn for_segment(
         &self,
         segment_local_id: SegmentOrdinal,
-        segment: &SegmentReader,
+        segment: &dyn SegmentReader,
     ) -> crate::Result<Self::Child>;
 
     /// Returns true iff the collector requires to compute scores for documents.
@@ -174,7 +174,7 @@ pub trait Collector: Sync + Send {
         &self,
         weight: &dyn Weight,
         segment_ord: u32,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<<Self::Child as SegmentCollector>::Fruit> {
         let with_scoring = self.requires_scoring();
         let mut segment_collector = self.for_segment(segment_ord, reader)?;
@@ -186,7 +186,7 @@ pub trait Collector: Sync + Send {
 pub(crate) fn default_collect_segment_impl<TSegmentCollector: SegmentCollector>(
     segment_collector: &mut TSegmentCollector,
     weight: &dyn Weight,
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     with_scoring: bool,
 ) -> crate::Result<()> {
     match (reader.alive_bitset(), with_scoring) {
@@ -255,7 +255,7 @@ impl<TCollector: Collector> Collector for Option<TCollector> {
     fn for_segment(
         &self,
         segment_local_id: SegmentOrdinal,
-        segment: &SegmentReader,
+        segment: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         Ok(if let Some(inner) = self {
             let inner_segment_collector = inner.for_segment(segment_local_id, segment)?;
@@ -336,7 +336,7 @@ where
     fn for_segment(
         &self,
         segment_local_id: u32,
-        segment: &SegmentReader,
+        segment: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let left = self.0.for_segment(segment_local_id, segment)?;
         let right = self.1.for_segment(segment_local_id, segment)?;
@@ -407,7 +407,7 @@ where
     fn for_segment(
         &self,
         segment_local_id: u32,
-        segment: &SegmentReader,
+        segment: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let one = self.0.for_segment(segment_local_id, segment)?;
         let two = self.1.for_segment(segment_local_id, segment)?;
@@ -487,7 +487,7 @@ where
     fn for_segment(
         &self,
         segment_local_id: u32,
-        segment: &SegmentReader,
+        segment: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let one = self.0.for_segment(segment_local_id, segment)?;
         let two = self.1.for_segment(segment_local_id, segment)?;

src/collector/multi_collector.rs

@@ -24,7 +24,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
     fn for_segment(
         &self,
         segment_local_id: u32,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<Box<dyn BoxableSegmentCollector>> {
         let child = self.0.for_segment(segment_local_id, reader)?;
         Ok(Box::new(SegmentCollectorWrapper(child)))
@@ -209,7 +209,7 @@ impl Collector for MultiCollector<'_> {
     fn for_segment(
         &self,
         segment_local_id: SegmentOrdinal,
-        segment: &SegmentReader,
+        segment: &dyn SegmentReader,
     ) -> crate::Result<MultiCollectorChild> {
         let children = self
             .collector_wrappers

src/collector/sort_key/mod.rs

@@ -1,25 +1,48 @@
 mod order;
+mod sort_by_erased_type;
 mod sort_by_score;
 mod sort_by_static_fast_value;
 mod sort_by_string;
 mod sort_key_computer;
 
 pub use order::*;
+pub use sort_by_erased_type::SortByErasedType;
 pub use sort_by_score::SortBySimilarityScore;
 pub use sort_by_static_fast_value::SortByStaticFastValue;
 pub use sort_by_string::SortByString;
 pub use sort_key_computer::{SegmentSortKeyComputer, SortKeyComputer};
 
 #[cfg(test)]
-mod tests {
+pub(crate) mod tests {
+
+    // By spec, regardless of whether ascending or descending order was requested, in presence of a
+    // tie, we sort by ascending doc id/doc address.
+    pub(crate) fn sort_hits<TSortKey: Ord, D: Ord>(
+        hits: &mut [ComparableDoc<TSortKey, D>],
+        order: Order,
+    ) {
+        if order.is_asc() {
+            hits.sort_by(|l, r| l.sort_key.cmp(&r.sort_key).then(l.doc.cmp(&r.doc)));
+        } else {
+            hits.sort_by(|l, r| {
+                l.sort_key
+                    .cmp(&r.sort_key)
+                    .reverse() // This is descending
+                    .then(l.doc.cmp(&r.doc))
+            });
+        }
+    }
+
     use std::collections::HashMap;
     use std::ops::Range;
 
-    use crate::collector::sort_key::{SortBySimilarityScore, SortByStaticFastValue, SortByString};
+    use crate::collector::sort_key::{
+        SortByErasedType, SortBySimilarityScore, SortByStaticFastValue, SortByString,
+    };
     use crate::collector::{ComparableDoc, DocSetCollector, TopDocs};
     use crate::indexer::NoMergePolicy;
     use crate::query::{AllQuery, QueryParser};
-    use crate::schema::{Schema, FAST, TEXT};
+    use crate::schema::{OwnedValue, Schema, FAST, TEXT};
     use crate::{DocAddress, Document, Index, Order, Score, Searcher};
 
     fn make_index() -> crate::Result<Index> {
@@ -294,11 +317,9 @@ mod tests {
                 (SortBySimilarityScore, score_order),
                 (SortByString::for_field("city"), city_order),
             ));
-            Ok(searcher
-                .search(&AllQuery, &top_collector)?
-                .into_iter()
-                .map(|(f, doc)| (f, ids[&doc]))
-                .collect())
+            let results: Vec<((Score, Option<String>), DocAddress)> =
+                searcher.search(&AllQuery, &top_collector)?;
+            Ok(results.into_iter().map(|(f, doc)| (f, ids[&doc])).collect())
         }
 
         assert_eq!(
@@ -323,6 +344,51 @@ mod tests {
         Ok(())
     }
 
+    #[test]
+    fn test_order_by_score_then_owned_value() -> crate::Result<()> {
+        let index = make_index()?;
+
+        type SortKey = (Score, OwnedValue);
+
+        fn query(
+            index: &Index,
+            score_order: Order,
+            city_order: Order,
+        ) -> crate::Result<Vec<(SortKey, u64)>> {
+            let searcher = index.reader()?.searcher();
+            let ids = id_mapping(&searcher);
+
+            let top_collector = TopDocs::with_limit(4).order_by::<(Score, OwnedValue)>((
+                (SortBySimilarityScore, score_order),
+                (SortByErasedType::for_field("city"), city_order),
+            ));
+            let results: Vec<((Score, OwnedValue), DocAddress)> =
+                searcher.search(&AllQuery, &top_collector)?;
+            Ok(results.into_iter().map(|(f, doc)| (f, ids[&doc])).collect())
+        }
+
+        assert_eq!(
+            &query(&index, Order::Asc, Order::Asc)?,
+            &[
+                ((1.0, OwnedValue::Str("austin".to_owned())), 0),
+                ((1.0, OwnedValue::Str("greenville".to_owned())), 1),
+                ((1.0, OwnedValue::Str("tokyo".to_owned())), 2),
+                ((1.0, OwnedValue::Null), 3),
+            ]
+        );
+
+        assert_eq!(
+            &query(&index, Order::Asc, Order::Desc)?,
+            &[
+                ((1.0, OwnedValue::Str("tokyo".to_owned())), 2),
+                ((1.0, OwnedValue::Str("greenville".to_owned())), 1),
+                ((1.0, OwnedValue::Str("austin".to_owned())), 0),
+                ((1.0, OwnedValue::Null), 3),
+            ]
+        );
+        Ok(())
+    }
+
     use proptest::prelude::*;
 
     proptest! {
@@ -372,15 +438,10 @@ mod tests {
 
             // 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>> =
+            let sorted_docs: Vec<_> = {
+                let mut comparable_docs: Vec<ComparableDoc<_, _>> =
                     all_results.into_iter().map(|(sort_key, doc)| ComparableDoc { sort_key, doc}).collect();
-                comparable_docs.sort();
-                comparable_docs.into_iter().map(|cd| (cd.sort_key, cd.doc)).collect()
-            } else {
-                let mut comparable_docs: Vec<ComparableDoc<_, _, false>> =
-                    all_results.into_iter().map(|(sort_key, doc)| ComparableDoc { sort_key, doc}).collect();
-                comparable_docs.sort();
+                sort_hits(&mut comparable_docs, order);
                 comparable_docs.into_iter().map(|cd| (cd.sort_key, cd.doc)).collect()
             };
             let expected_docs = sorted_docs.into_iter().skip(offset).take(limit).collect::<Vec<_>>();

src/collector/sort_key/order.rs

@@ -1,10 +1,69 @@
 use std::cmp::Ordering;
 
+use columnar::MonotonicallyMappableToU64;
 use serde::{Deserialize, Serialize};
 
 use crate::collector::{SegmentSortKeyComputer, SortKeyComputer};
-use crate::schema::Schema;
-use crate::{DocId, Order, Score};
+use crate::schema::{OwnedValue, Schema};
+use crate::{DocId, Order, Score, SegmentReader};
+
+fn compare_owned_value<const NULLS_FIRST: bool>(lhs: &OwnedValue, rhs: &OwnedValue) -> Ordering {
+    match (lhs, rhs) {
+        (OwnedValue::Null, OwnedValue::Null) => Ordering::Equal,
+        (OwnedValue::Null, _) => {
+            if NULLS_FIRST {
+                Ordering::Less
+            } else {
+                Ordering::Greater
+            }
+        }
+        (_, OwnedValue::Null) => {
+            if NULLS_FIRST {
+                Ordering::Greater
+            } else {
+                Ordering::Less
+            }
+        }
+        (OwnedValue::Str(a), OwnedValue::Str(b)) => a.cmp(b),
+        (OwnedValue::PreTokStr(a), OwnedValue::PreTokStr(b)) => a.cmp(b),
+        (OwnedValue::U64(a), OwnedValue::U64(b)) => a.cmp(b),
+        (OwnedValue::I64(a), OwnedValue::I64(b)) => a.cmp(b),
+        (OwnedValue::F64(a), OwnedValue::F64(b)) => a.to_u64().cmp(&b.to_u64()),
+        (OwnedValue::Bool(a), OwnedValue::Bool(b)) => a.cmp(b),
+        (OwnedValue::Date(a), OwnedValue::Date(b)) => a.cmp(b),
+        (OwnedValue::Facet(a), OwnedValue::Facet(b)) => a.cmp(b),
+        (OwnedValue::Bytes(a), OwnedValue::Bytes(b)) => a.cmp(b),
+        (OwnedValue::IpAddr(a), OwnedValue::IpAddr(b)) => a.cmp(b),
+        (OwnedValue::U64(a), OwnedValue::I64(b)) => {
+            if *b < 0 {
+                Ordering::Greater
+            } else {
+                a.cmp(&(*b as u64))
+            }
+        }
+        (OwnedValue::I64(a), OwnedValue::U64(b)) => {
+            if *a < 0 {
+                Ordering::Less
+            } else {
+                (*a as u64).cmp(b)
+            }
+        }
+        (OwnedValue::U64(a), OwnedValue::F64(b)) => (*a as f64).to_u64().cmp(&b.to_u64()),
+        (OwnedValue::F64(a), OwnedValue::U64(b)) => a.to_u64().cmp(&(*b as f64).to_u64()),
+        (OwnedValue::I64(a), OwnedValue::F64(b)) => (*a as f64).to_u64().cmp(&b.to_u64()),
+        (OwnedValue::F64(a), OwnedValue::I64(b)) => a.to_u64().cmp(&(*b as f64).to_u64()),
+        (a, b) => {
+            let ord = a.discriminant_value().cmp(&b.discriminant_value());
+            // If the discriminant is equal, it's because a new type was added, but hasn't been
+            // included in this `match` statement.
+            assert!(
+                ord != Ordering::Equal,
+                "Unimplemented comparison for type of {a:?}, {b:?}"
+            );
+            ord
+        }
+    }
+}
 
 /// Comparator trait defining the order in which documents should be ordered.
 pub trait Comparator<T>: Send + Sync + std::fmt::Debug + Default {
@@ -12,25 +71,46 @@ pub trait Comparator<T>: Send + Sync + std::fmt::Debug + Default {
     fn compare(&self, lhs: &T, rhs: &T) -> Ordering;
 }
 
-/// With the natural comparator, the top k collector will return
-/// the top documents in decreasing order.
+/// Compare values naturally (e.g. 1 < 2).
+///
+/// When used with `TopDocs`, which reverses the order, this results in a
+/// "Descending" sort (Greatest values first).
+///
+/// `None` (or Null for `OwnedValue`) values are considered to be smaller than any other value,
+/// and will therefore appear last in a descending sort (e.g. `[Some(20), Some(10), None]`).
 #[derive(Debug, Copy, Clone, Default, Serialize, Deserialize)]
 pub struct NaturalComparator;
 
 impl<T: PartialOrd> Comparator<T> for NaturalComparator {
     #[inline(always)]
     fn compare(&self, lhs: &T, rhs: &T) -> Ordering {
-        lhs.partial_cmp(rhs).unwrap()
+        lhs.partial_cmp(rhs).unwrap_or(Ordering::Equal)
     }
 }
 
-/// Sorts document in reverse order.
+/// A (partial) implementation of comparison for OwnedValue.
 ///
-/// If the sort key is None, it will considered as the lowest value, and will therefore appear
-/// first.
+/// Intended for use within columns of homogenous types, and so will panic for OwnedValues with
+/// mismatched types. The one exception is Null, for which we do define all comparisons.
+impl Comparator<OwnedValue> for NaturalComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &OwnedValue, rhs: &OwnedValue) -> Ordering {
+        compare_owned_value::</* NULLS_FIRST= */ true>(lhs, rhs)
+    }
+}
+
+/// Compare values in reverse (e.g. 2 < 1).
+///
+/// When used with `TopDocs`, which reverses the order, this results in an
+/// "Ascending" sort (Smallest values first).
+///
+/// `None` is considered smaller than `Some` in the underlying comparator, but because the
+/// comparison is reversed, `None` is effectively treated as the lowest value in the resulting
+/// Ascending sort (e.g. `[None, Some(10), Some(20)]`).
 ///
 /// The ReverseComparator does not necessarily imply that the sort order is reversed compared
-/// to the NaturalComparator. In presence of a tie, both version will retain the higher doc ids.
+/// to the NaturalComparator. In presence of a tie on the sort key, documents will always be
+/// sorted by ascending `DocId`/`DocAddress` in TopN results, regardless of the sort key's order.
 #[derive(Debug, Copy, Clone, Default, Serialize, Deserialize)]
 pub struct ReverseComparator;
 
@@ -43,11 +123,15 @@ where NaturalComparator: Comparator<T>
     }
 }
 
-/// Sorts document in reverse order, but considers None as having the lowest value.
+/// Compare values in reverse, but treating `None` as lower than `Some`.
+///
+/// When used with `TopDocs`, which reverses the order, this results in an
+/// "Ascending" sort (Smallest values first), but with `None` values appearing last
+/// (e.g. `[Some(10), Some(20), None]`).
 ///
 /// This is usually what is wanted when sorting by a field in an ascending order.
-/// For instance, in a e-commerce website, if I sort by price ascending, I most likely want the
-/// cheapest items first, and the items without a price at last.
+/// For instance, in an e-commerce website, if sorting by price ascending,
+/// the cheapest items would appear first, and items without a price would appear last.
 #[derive(Debug, Copy, Clone, Default)]
 pub struct ReverseNoneIsLowerComparator;
 
@@ -107,6 +191,84 @@ impl Comparator<String> for ReverseNoneIsLowerComparator {
     }
 }
 
+impl Comparator<OwnedValue> for ReverseNoneIsLowerComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &OwnedValue, rhs: &OwnedValue) -> Ordering {
+        compare_owned_value::</* NULLS_FIRST= */ false>(rhs, lhs)
+    }
+}
+
+/// Compare values naturally, but treating `None` as higher than `Some`.
+///
+/// When used with `TopDocs`, which reverses the order, this results in a
+/// "Descending" sort (Greatest values first), but with `None` values appearing first
+/// (e.g. `[None, Some(20), Some(10)]`).
+#[derive(Debug, Copy, Clone, Default, Serialize, Deserialize)]
+pub struct NaturalNoneIsHigherComparator;
+
+impl<T> Comparator<Option<T>> for NaturalNoneIsHigherComparator
+where NaturalComparator: Comparator<T>
+{
+    #[inline(always)]
+    fn compare(&self, lhs_opt: &Option<T>, rhs_opt: &Option<T>) -> Ordering {
+        match (lhs_opt, rhs_opt) {
+            (None, None) => Ordering::Equal,
+            (None, Some(_)) => Ordering::Greater,
+            (Some(_), None) => Ordering::Less,
+            (Some(lhs), Some(rhs)) => NaturalComparator.compare(lhs, rhs),
+        }
+    }
+}
+
+impl Comparator<u32> for NaturalNoneIsHigherComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &u32, rhs: &u32) -> Ordering {
+        NaturalComparator.compare(lhs, rhs)
+    }
+}
+
+impl Comparator<u64> for NaturalNoneIsHigherComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &u64, rhs: &u64) -> Ordering {
+        NaturalComparator.compare(lhs, rhs)
+    }
+}
+
+impl Comparator<f64> for NaturalNoneIsHigherComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &f64, rhs: &f64) -> Ordering {
+        NaturalComparator.compare(lhs, rhs)
+    }
+}
+
+impl Comparator<f32> for NaturalNoneIsHigherComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &f32, rhs: &f32) -> Ordering {
+        NaturalComparator.compare(lhs, rhs)
+    }
+}
+
+impl Comparator<i64> for NaturalNoneIsHigherComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &i64, rhs: &i64) -> Ordering {
+        NaturalComparator.compare(lhs, rhs)
+    }
+}
+
+impl Comparator<String> for NaturalNoneIsHigherComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &String, rhs: &String) -> Ordering {
+        NaturalComparator.compare(lhs, rhs)
+    }
+}
+
+impl Comparator<OwnedValue> for NaturalNoneIsHigherComparator {
+    #[inline(always)]
+    fn compare(&self, lhs: &OwnedValue, rhs: &OwnedValue) -> Ordering {
+        compare_owned_value::</* NULLS_FIRST= */ false>(lhs, rhs)
+    }
+}
+
 /// An enum representing the different sort orders.
 #[derive(Debug, Clone, Copy, Eq, PartialEq, Default)]
 pub enum ComparatorEnum {
@@ -115,8 +277,10 @@ pub enum ComparatorEnum {
     Natural,
     /// Reverse order (See [ReverseComparator])
     Reverse,
-    /// Reverse order by treating None as the lowest value.(See [ReverseNoneLowerComparator])
+    /// Reverse order by treating None as the lowest value. (See [ReverseNoneLowerComparator])
     ReverseNoneLower,
+    /// Natural order but treating None as the highest value. (See [NaturalNoneIsHigherComparator])
+    NaturalNoneHigher,
 }
 
 impl From<Order> for ComparatorEnum {
@@ -133,6 +297,7 @@ where
     ReverseNoneIsLowerComparator: Comparator<T>,
     NaturalComparator: Comparator<T>,
     ReverseComparator: Comparator<T>,
+    NaturalNoneIsHigherComparator: Comparator<T>,
 {
     #[inline(always)]
     fn compare(&self, lhs: &T, rhs: &T) -> Ordering {
@@ -140,6 +305,7 @@ where
             ComparatorEnum::Natural => NaturalComparator.compare(lhs, rhs),
             ComparatorEnum::Reverse => ReverseComparator.compare(lhs, rhs),
             ComparatorEnum::ReverseNoneLower => ReverseNoneIsLowerComparator.compare(lhs, rhs),
+            ComparatorEnum::NaturalNoneHigher => NaturalNoneIsHigherComparator.compare(lhs, rhs),
         }
     }
 }
@@ -264,7 +430,7 @@ where
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &crate::SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let child = self.0.segment_sort_key_computer(segment_reader)?;
         Ok(SegmentSortKeyComputerWithComparator {
@@ -302,7 +468,7 @@ where
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &crate::SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let child = self.0.segment_sort_key_computer(segment_reader)?;
         Ok(SegmentSortKeyComputerWithComparator {
@@ -322,11 +488,12 @@ impl<TSegmentSortKeyComputer, TSegmentSortKey, TComparator> SegmentSortKeyComput
     for SegmentSortKeyComputerWithComparator<TSegmentSortKeyComputer, TComparator>
 where
     TSegmentSortKeyComputer: SegmentSortKeyComputer<SegmentSortKey = TSegmentSortKey>,
-    TSegmentSortKey: PartialOrd + Clone + 'static + Sync + Send,
+    TSegmentSortKey: Clone + 'static + Sync + Send,
     TComparator: Comparator<TSegmentSortKey> + 'static + Sync + Send,
 {
     type SortKey = TSegmentSortKeyComputer::SortKey;
     type SegmentSortKey = TSegmentSortKey;
+    type SegmentComparator = TComparator;
 
     fn segment_sort_key(&mut self, doc: DocId, score: Score) -> Self::SegmentSortKey {
         self.segment_sort_key_computer.segment_sort_key(doc, score)
@@ -346,3 +513,55 @@ where
             .convert_segment_sort_key(sort_key)
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::schema::OwnedValue;
+
+    #[test]
+    fn test_natural_none_is_higher() {
+        let comp = NaturalNoneIsHigherComparator;
+        let null = None;
+        let v1 = Some(1_u64);
+        let v2 = Some(2_u64);
+
+        // NaturalNoneIsGreaterComparator logic:
+        // 1. Delegates to NaturalComparator for non-nulls.
+        // NaturalComparator compare(2, 1) -> 2.cmp(1) -> Greater.
+        assert_eq!(comp.compare(&v2, &v1), Ordering::Greater);
+
+        // 2. Treats None (Null) as Greater than any value.
+        // compare(None, Some(2)) should be Greater.
+        assert_eq!(comp.compare(&null, &v2), Ordering::Greater);
+
+        // compare(Some(1), None) should be Less.
+        assert_eq!(comp.compare(&v1, &null), Ordering::Less);
+
+        // compare(None, None) should be Equal.
+        assert_eq!(comp.compare(&null, &null), Ordering::Equal);
+    }
+
+    #[test]
+    fn test_mixed_ownedvalue_compare() {
+        let u = OwnedValue::U64(10);
+        let i = OwnedValue::I64(10);
+        let f = OwnedValue::F64(10.0);
+
+        let nc = NaturalComparator;
+        assert_eq!(nc.compare(&u, &i), Ordering::Equal);
+        assert_eq!(nc.compare(&u, &f), Ordering::Equal);
+        assert_eq!(nc.compare(&i, &f), Ordering::Equal);
+
+        let u2 = OwnedValue::U64(11);
+        assert_eq!(nc.compare(&u2, &f), Ordering::Greater);
+
+        let s = OwnedValue::Str("a".to_string());
+        // Str < U64
+        assert_eq!(nc.compare(&s, &u), Ordering::Less);
+        // Str < I64
+        assert_eq!(nc.compare(&s, &i), Ordering::Less);
+        // Str < F64
+        assert_eq!(nc.compare(&s, &f), Ordering::Less);
+    }
+}

src/collector/sort_key/sort_by_erased_type.rs

@@ -0,0 +1,361 @@
+use columnar::{ColumnType, MonotonicallyMappableToU64};
+
+use crate::collector::sort_key::{
+    NaturalComparator, SortBySimilarityScore, SortByStaticFastValue, SortByString,
+};
+use crate::collector::{SegmentSortKeyComputer, SortKeyComputer};
+use crate::fastfield::FastFieldNotAvailableError;
+use crate::schema::OwnedValue;
+use crate::{DateTime, DocId, Score, SegmentReader};
+
+/// Sort by the boxed / OwnedValue representation of either a fast field, or of the score.
+///
+/// Using the OwnedValue representation allows for type erasure, and can be useful when sort orders
+/// are not known until runtime. But it comes with a performance cost: wherever possible, prefer to
+/// use a SortKeyComputer implementation with a known-type at compile time.
+#[derive(Debug, Clone)]
+pub enum SortByErasedType {
+    /// Sort by a fast field
+    Field(String),
+    /// Sort by score
+    Score,
+}
+
+impl SortByErasedType {
+    /// Creates a new sort key computer which will sort by the given fast field column, with type
+    /// erasure.
+    pub fn for_field(column_name: impl ToString) -> Self {
+        Self::Field(column_name.to_string())
+    }
+
+    /// Creates a new sort key computer which will sort by score, with type erasure.
+    pub fn for_score() -> Self {
+        Self::Score
+    }
+}
+
+trait ErasedSegmentSortKeyComputer: Send + Sync {
+    fn segment_sort_key(&mut self, doc: DocId, score: Score) -> Option<u64>;
+    fn convert_segment_sort_key(&self, sort_key: Option<u64>) -> OwnedValue;
+}
+
+struct ErasedSegmentSortKeyComputerWrapper<C, F> {
+    inner: C,
+    converter: F,
+}
+
+impl<C, F> ErasedSegmentSortKeyComputer for ErasedSegmentSortKeyComputerWrapper<C, F>
+where
+    C: SegmentSortKeyComputer<SegmentSortKey = Option<u64>> + Send + Sync,
+    F: Fn(C::SortKey) -> OwnedValue + Send + Sync + 'static,
+{
+    fn segment_sort_key(&mut self, doc: DocId, score: Score) -> Option<u64> {
+        self.inner.segment_sort_key(doc, score)
+    }
+
+    fn convert_segment_sort_key(&self, sort_key: Option<u64>) -> OwnedValue {
+        let val = self.inner.convert_segment_sort_key(sort_key);
+        (self.converter)(val)
+    }
+}
+
+struct ScoreSegmentSortKeyComputer {
+    segment_computer: SortBySimilarityScore,
+}
+
+impl ErasedSegmentSortKeyComputer for ScoreSegmentSortKeyComputer {
+    fn segment_sort_key(&mut self, doc: DocId, score: Score) -> Option<u64> {
+        let score_value: f64 = self.segment_computer.segment_sort_key(doc, score).into();
+        Some(score_value.to_u64())
+    }
+
+    fn convert_segment_sort_key(&self, sort_key: Option<u64>) -> OwnedValue {
+        let score_value: u64 = sort_key.expect("This implementation always produces a score.");
+        OwnedValue::F64(f64::from_u64(score_value))
+    }
+}
+
+impl SortKeyComputer for SortByErasedType {
+    type SortKey = OwnedValue;
+    type Child = ErasedColumnSegmentSortKeyComputer;
+    type Comparator = NaturalComparator;
+
+    fn requires_scoring(&self) -> bool {
+        matches!(self, Self::Score)
+    }
+
+    fn segment_sort_key_computer(
+        &self,
+        segment_reader: &dyn SegmentReader,
+    ) -> crate::Result<Self::Child> {
+        let inner: Box<dyn ErasedSegmentSortKeyComputer> = match self {
+            Self::Field(column_name) => {
+                let fast_fields = segment_reader.fast_fields();
+                // TODO: We currently double-open the column to avoid relying on the implementation
+                // details of `SortByString` or `SortByStaticFastValue`. Once
+                // https://github.com/quickwit-oss/tantivy/issues/2776 is resolved, we should
+                // consider directly constructing the appropriate `SegmentSortKeyComputer` type for
+                // the column that we open here.
+                let (_column, column_type) =
+                    fast_fields.u64_lenient(column_name)?.ok_or_else(|| {
+                        FastFieldNotAvailableError {
+                            field_name: column_name.to_owned(),
+                        }
+                    })?;
+
+                match column_type {
+                    ColumnType::Str => {
+                        let computer = SortByString::for_field(column_name);
+                        let inner = computer.segment_sort_key_computer(segment_reader)?;
+                        Box::new(ErasedSegmentSortKeyComputerWrapper {
+                            inner,
+                            converter: |val: Option<String>| {
+                                val.map(OwnedValue::Str).unwrap_or(OwnedValue::Null)
+                            },
+                        })
+                    }
+                    ColumnType::U64 => {
+                        let computer = SortByStaticFastValue::<u64>::for_field(column_name);
+                        let inner = computer.segment_sort_key_computer(segment_reader)?;
+                        Box::new(ErasedSegmentSortKeyComputerWrapper {
+                            inner,
+                            converter: |val: Option<u64>| {
+                                val.map(OwnedValue::U64).unwrap_or(OwnedValue::Null)
+                            },
+                        })
+                    }
+                    ColumnType::I64 => {
+                        let computer = SortByStaticFastValue::<i64>::for_field(column_name);
+                        let inner = computer.segment_sort_key_computer(segment_reader)?;
+                        Box::new(ErasedSegmentSortKeyComputerWrapper {
+                            inner,
+                            converter: |val: Option<i64>| {
+                                val.map(OwnedValue::I64).unwrap_or(OwnedValue::Null)
+                            },
+                        })
+                    }
+                    ColumnType::F64 => {
+                        let computer = SortByStaticFastValue::<f64>::for_field(column_name);
+                        let inner = computer.segment_sort_key_computer(segment_reader)?;
+                        Box::new(ErasedSegmentSortKeyComputerWrapper {
+                            inner,
+                            converter: |val: Option<f64>| {
+                                val.map(OwnedValue::F64).unwrap_or(OwnedValue::Null)
+                            },
+                        })
+                    }
+                    ColumnType::Bool => {
+                        let computer = SortByStaticFastValue::<bool>::for_field(column_name);
+                        let inner = computer.segment_sort_key_computer(segment_reader)?;
+                        Box::new(ErasedSegmentSortKeyComputerWrapper {
+                            inner,
+                            converter: |val: Option<bool>| {
+                                val.map(OwnedValue::Bool).unwrap_or(OwnedValue::Null)
+                            },
+                        })
+                    }
+                    ColumnType::DateTime => {
+                        let computer = SortByStaticFastValue::<DateTime>::for_field(column_name);
+                        let inner = computer.segment_sort_key_computer(segment_reader)?;
+                        Box::new(ErasedSegmentSortKeyComputerWrapper {
+                            inner,
+                            converter: |val: Option<DateTime>| {
+                                val.map(OwnedValue::Date).unwrap_or(OwnedValue::Null)
+                            },
+                        })
+                    }
+                    column_type => {
+                        return Err(crate::TantivyError::SchemaError(format!(
+                            "Field `{}` is of type {column_type:?}, which is not supported for \
+                             sorting by owned value yet.",
+                            column_name
+                        )))
+                    }
+                }
+            }
+            Self::Score => Box::new(ScoreSegmentSortKeyComputer {
+                segment_computer: SortBySimilarityScore,
+            }),
+        };
+        Ok(ErasedColumnSegmentSortKeyComputer { inner })
+    }
+}
+
+pub struct ErasedColumnSegmentSortKeyComputer {
+    inner: Box<dyn ErasedSegmentSortKeyComputer>,
+}
+
+impl SegmentSortKeyComputer for ErasedColumnSegmentSortKeyComputer {
+    type SortKey = OwnedValue;
+    type SegmentSortKey = Option<u64>;
+    type SegmentComparator = NaturalComparator;
+
+    #[inline(always)]
+    fn segment_sort_key(&mut self, doc: DocId, score: Score) -> Option<u64> {
+        self.inner.segment_sort_key(doc, score)
+    }
+
+    fn convert_segment_sort_key(&self, segment_sort_key: Self::SegmentSortKey) -> OwnedValue {
+        self.inner.convert_segment_sort_key(segment_sort_key)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::collector::sort_key::{ComparatorEnum, SortByErasedType};
+    use crate::collector::TopDocs;
+    use crate::query::AllQuery;
+    use crate::schema::{OwnedValue, Schema, FAST, TEXT};
+    use crate::Index;
+
+    #[test]
+    fn test_sort_by_owned_u64() {
+        let mut schema_builder = Schema::builder();
+        let id_field = schema_builder.add_u64_field("id", FAST);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut writer = index.writer_for_tests().unwrap();
+        writer.add_document(doc!(id_field => 10u64)).unwrap();
+        writer.add_document(doc!(id_field => 2u64)).unwrap();
+        writer.add_document(doc!()).unwrap();
+        writer.commit().unwrap();
+
+        let reader = index.reader().unwrap();
+        let searcher = reader.searcher();
+
+        let collector = TopDocs::with_limit(10)
+            .order_by((SortByErasedType::for_field("id"), ComparatorEnum::Natural));
+        let top_docs = searcher.search(&AllQuery, &collector).unwrap();
+
+        let values: Vec<OwnedValue> = top_docs.into_iter().map(|(key, _)| key).collect();
+
+        assert_eq!(
+            values,
+            vec![OwnedValue::U64(10), OwnedValue::U64(2), OwnedValue::Null]
+        );
+
+        let collector = TopDocs::with_limit(10).order_by((
+            SortByErasedType::for_field("id"),
+            ComparatorEnum::ReverseNoneLower,
+        ));
+        let top_docs = searcher.search(&AllQuery, &collector).unwrap();
+
+        let values: Vec<OwnedValue> = top_docs.into_iter().map(|(key, _)| key).collect();
+
+        assert_eq!(
+            values,
+            vec![OwnedValue::U64(2), OwnedValue::U64(10), OwnedValue::Null]
+        );
+    }
+
+    #[test]
+    fn test_sort_by_owned_string() {
+        let mut schema_builder = Schema::builder();
+        let city_field = schema_builder.add_text_field("city", FAST | TEXT);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut writer = index.writer_for_tests().unwrap();
+        writer.add_document(doc!(city_field => "tokyo")).unwrap();
+        writer.add_document(doc!(city_field => "austin")).unwrap();
+        writer.add_document(doc!()).unwrap();
+        writer.commit().unwrap();
+
+        let reader = index.reader().unwrap();
+        let searcher = reader.searcher();
+
+        let collector = TopDocs::with_limit(10).order_by((
+            SortByErasedType::for_field("city"),
+            ComparatorEnum::ReverseNoneLower,
+        ));
+        let top_docs = searcher.search(&AllQuery, &collector).unwrap();
+
+        let values: Vec<OwnedValue> = top_docs.into_iter().map(|(key, _)| key).collect();
+
+        assert_eq!(
+            values,
+            vec![
+                OwnedValue::Str("austin".to_string()),
+                OwnedValue::Str("tokyo".to_string()),
+                OwnedValue::Null
+            ]
+        );
+    }
+
+    #[test]
+    fn test_sort_by_owned_reverse() {
+        let mut schema_builder = Schema::builder();
+        let id_field = schema_builder.add_u64_field("id", FAST);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut writer = index.writer_for_tests().unwrap();
+        writer.add_document(doc!(id_field => 10u64)).unwrap();
+        writer.add_document(doc!(id_field => 2u64)).unwrap();
+        writer.add_document(doc!()).unwrap();
+        writer.commit().unwrap();
+
+        let reader = index.reader().unwrap();
+        let searcher = reader.searcher();
+
+        let collector = TopDocs::with_limit(10)
+            .order_by((SortByErasedType::for_field("id"), ComparatorEnum::Reverse));
+        let top_docs = searcher.search(&AllQuery, &collector).unwrap();
+
+        let values: Vec<OwnedValue> = top_docs.into_iter().map(|(key, _)| key).collect();
+
+        assert_eq!(
+            values,
+            vec![OwnedValue::Null, OwnedValue::U64(2), OwnedValue::U64(10)]
+        );
+    }
+
+    #[test]
+    fn test_sort_by_owned_score() {
+        let mut schema_builder = Schema::builder();
+        let body_field = schema_builder.add_text_field("body", TEXT);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut writer = index.writer_for_tests().unwrap();
+        writer.add_document(doc!(body_field => "a a")).unwrap();
+        writer.add_document(doc!(body_field => "a")).unwrap();
+        writer.commit().unwrap();
+
+        let reader = index.reader().unwrap();
+        let searcher = reader.searcher();
+        let query_parser = crate::query::QueryParser::for_index(&index, vec![body_field]);
+        let query = query_parser.parse_query("a").unwrap();
+
+        // Sort by score descending (Natural)
+        let collector = TopDocs::with_limit(10)
+            .order_by((SortByErasedType::for_score(), ComparatorEnum::Natural));
+        let top_docs = searcher.search(&query, &collector).unwrap();
+
+        let values: Vec<f64> = top_docs
+            .into_iter()
+            .map(|(key, _)| match key {
+                OwnedValue::F64(val) => val,
+                _ => panic!("Wrong type {key:?}"),
+            })
+            .collect();
+
+        assert_eq!(values.len(), 2);
+        assert!(values[0] > values[1]);
+
+        // Sort by score ascending (ReverseNoneLower)
+        let collector = TopDocs::with_limit(10).order_by((
+            SortByErasedType::for_score(),
+            ComparatorEnum::ReverseNoneLower,
+        ));
+        let top_docs = searcher.search(&query, &collector).unwrap();
+
+        let values: Vec<f64> = top_docs
+            .into_iter()
+            .map(|(key, _)| match key {
+                OwnedValue::F64(val) => val,
+                _ => panic!("Wrong type {key:?}"),
+            })
+            .collect();
+
+        assert_eq!(values.len(), 2);
+        assert!(values[0] < values[1]);
+    }
+}

src/collector/sort_key/sort_by_score.rs

@@ -1,6 +1,6 @@
 use crate::collector::sort_key::NaturalComparator;
 use crate::collector::{SegmentSortKeyComputer, SortKeyComputer, TopNComputer};
-use crate::{DocAddress, DocId, Score};
+use crate::{DocAddress, DocId, Score, SegmentReader};
 
 /// Sort by similarity score.
 #[derive(Clone, Debug, Copy)]
@@ -19,7 +19,7 @@ impl SortKeyComputer for SortBySimilarityScore {
 
     fn segment_sort_key_computer(
         &self,
-        _segment_reader: &crate::SegmentReader,
+        _segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         Ok(SortBySimilarityScore)
     }
@@ -29,7 +29,7 @@ impl SortKeyComputer for SortBySimilarityScore {
         &self,
         k: usize,
         weight: &dyn crate::query::Weight,
-        reader: &crate::SegmentReader,
+        reader: &dyn SegmentReader,
         segment_ord: u32,
     ) -> crate::Result<Vec<(Self::SortKey, DocAddress)>> {
         let mut top_n: TopNComputer<Score, DocId, Self::Comparator> =
@@ -63,8 +63,8 @@ impl SortKeyComputer for SortBySimilarityScore {
 
 impl SegmentSortKeyComputer for SortBySimilarityScore {
     type SortKey = Score;
-
     type SegmentSortKey = Score;
+    type SegmentComparator = NaturalComparator;
 
     #[inline(always)]
     fn segment_sort_key(&mut self, _doc: DocId, score: Score) -> Score {

src/collector/sort_key/sort_by_static_fast_value.rs

@@ -34,9 +34,7 @@ impl<T: FastValue> SortByStaticFastValue<T> {
 
 impl<T: FastValue> SortKeyComputer for SortByStaticFastValue<T> {
     type Child = SortByFastValueSegmentSortKeyComputer<T>;
-
     type SortKey = Option<T>;
-
     type Comparator = NaturalComparator;
 
     fn check_schema(&self, schema: &crate::schema::Schema) -> crate::Result<()> {
@@ -63,7 +61,7 @@ impl<T: FastValue> SortKeyComputer for SortByStaticFastValue<T> {
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let sort_column_opt = segment_reader.fast_fields().u64_lenient(&self.field)?;
         let (sort_column, _sort_column_type) =
@@ -84,8 +82,8 @@ pub struct SortByFastValueSegmentSortKeyComputer<T> {
 
 impl<T: FastValue> SegmentSortKeyComputer for SortByFastValueSegmentSortKeyComputer<T> {
     type SortKey = Option<T>;
-
     type SegmentSortKey = Option<u64>;
+    type SegmentComparator = NaturalComparator;
 
     #[inline(always)]
     fn segment_sort_key(&mut self, doc: DocId, _score: Score) -> Self::SegmentSortKey {

src/collector/sort_key/sort_by_string.rs

@@ -3,7 +3,7 @@ use columnar::StrColumn;
 use crate::collector::sort_key::NaturalComparator;
 use crate::collector::{SegmentSortKeyComputer, SortKeyComputer};
 use crate::termdict::TermOrdinal;
-use crate::{DocId, Score};
+use crate::{DocId, Score, SegmentReader};
 
 /// Sort by the first value of a string column.
 ///
@@ -30,14 +30,12 @@ impl SortByString {
 
 impl SortKeyComputer for SortByString {
     type SortKey = Option<String>;
-
     type Child = ByStringColumnSegmentSortKeyComputer;
-
     type Comparator = NaturalComparator;
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &crate::SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let str_column_opt = segment_reader.fast_fields().str(&self.column_name)?;
         Ok(ByStringColumnSegmentSortKeyComputer { str_column_opt })
@@ -50,8 +48,8 @@ pub struct ByStringColumnSegmentSortKeyComputer {
 
 impl SegmentSortKeyComputer for ByStringColumnSegmentSortKeyComputer {
     type SortKey = Option<String>;
-
     type SegmentSortKey = Option<TermOrdinal>;
+    type SegmentComparator = NaturalComparator;
 
     #[inline(always)]
     fn segment_sort_key(&mut self, doc: DocId, _score: Score) -> Option<TermOrdinal> {
@@ -60,6 +58,8 @@ impl SegmentSortKeyComputer for ByStringColumnSegmentSortKeyComputer {
     }
 
     fn convert_segment_sort_key(&self, term_ord_opt: Option<TermOrdinal>) -> Option<String> {
+        // TODO: Individual lookups to the dictionary like this are very likely to repeatedly
+        // decompress the same blocks. See https://github.com/quickwit-oss/tantivy/issues/2776
         let term_ord = term_ord_opt?;
         let str_column = self.str_column_opt.as_ref()?;
         let mut bytes = Vec::new();

src/collector/sort_key/sort_key_computer.rs

@@ -12,13 +12,21 @@ use crate::{DocAddress, DocId, Result, Score, SegmentReader};
 /// It is the segment local version of the [`SortKeyComputer`].
 pub trait SegmentSortKeyComputer: 'static {
     /// The final score being emitted.
-    type SortKey: 'static + PartialOrd + Send + Sync + Clone;
+    type SortKey: 'static + Send + Sync + Clone;
 
     /// Sort key used by at the segment level by the `SegmentSortKeyComputer`.
     ///
     /// It is typically small like a `u64`, and is meant to be converted
     /// to the final score at the end of the collection of the segment.
-    type SegmentSortKey: 'static + PartialOrd + Clone + Send + Sync + Clone;
+    type SegmentSortKey: 'static + Clone + Send + Sync + Clone;
+
+    /// Comparator type.
+    type SegmentComparator: Comparator<Self::SegmentSortKey> + 'static;
+
+    /// Returns the segment sort key comparator.
+    fn segment_comparator(&self) -> Self::SegmentComparator {
+        Self::SegmentComparator::default()
+    }
 
     /// Computes the sort key for the given document and score.
     fn segment_sort_key(&mut self, doc: DocId, score: Score) -> Self::SegmentSortKey;
@@ -47,7 +55,7 @@ pub trait SegmentSortKeyComputer: 'static {
         left: &Self::SegmentSortKey,
         right: &Self::SegmentSortKey,
     ) -> Ordering {
-        NaturalComparator.compare(left, right)
+        self.segment_comparator().compare(left, right)
     }
 
     /// Implementing this method makes it possible to avoid computing
@@ -81,7 +89,7 @@ pub trait SegmentSortKeyComputer: 'static {
 /// the sort key at a segment scale.
 pub trait SortKeyComputer: Sync {
     /// The sort key type.
-    type SortKey: 'static + Send + Sync + PartialOrd + Clone + std::fmt::Debug;
+    type SortKey: 'static + Send + Sync + Clone + std::fmt::Debug;
     /// Type of the associated [`SegmentSortKeyComputer`].
     type Child: SegmentSortKeyComputer<SortKey = Self::SortKey>;
     /// Comparator type.
@@ -111,7 +119,7 @@ pub trait SortKeyComputer: Sync {
         &self,
         k: usize,
         weight: &dyn crate::query::Weight,
-        reader: &crate::SegmentReader,
+        reader: &dyn SegmentReader,
         segment_ord: u32,
     ) -> crate::Result<Vec<(Self::SortKey, DocAddress)>> {
         let with_scoring = self.requires_scoring();
@@ -127,7 +135,7 @@ pub trait SortKeyComputer: Sync {
     }
 
     /// Builds a child sort key computer for a specific segment.
-    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child>;
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child>;
 }
 
 impl<HeadSortKeyComputer, TailSortKeyComputer> SortKeyComputer
@@ -136,10 +144,7 @@ where
     HeadSortKeyComputer: SortKeyComputer,
     TailSortKeyComputer: SortKeyComputer,
 {
-    type SortKey = (
-        <HeadSortKeyComputer::Child as SegmentSortKeyComputer>::SortKey,
-        <TailSortKeyComputer::Child as SegmentSortKeyComputer>::SortKey,
-    );
+    type SortKey = (HeadSortKeyComputer::SortKey, TailSortKeyComputer::SortKey);
     type Child = (HeadSortKeyComputer::Child, TailSortKeyComputer::Child);
 
     type Comparator = (
@@ -151,7 +156,7 @@ where
         (self.0.comparator(), self.1.comparator())
     }
 
-    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
         Ok((
             self.0.segment_sort_key_computer(segment_reader)?,
             self.1.segment_sort_key_computer(segment_reader)?,
@@ -188,6 +193,11 @@ where
         TailSegmentSortKeyComputer::SegmentSortKey,
     );
 
+    type SegmentComparator = (
+        HeadSegmentSortKeyComputer::SegmentComparator,
+        TailSegmentSortKeyComputer::SegmentComparator,
+    );
+
     /// A SegmentSortKeyComputer maps to a SegmentSortKey, but it can also decide on
     /// its ordering.
     ///
@@ -269,11 +279,12 @@ impl<T, PreviousScore, NewScore> SegmentSortKeyComputer
     for MappedSegmentSortKeyComputer<T, PreviousScore, NewScore>
 where
     T: SegmentSortKeyComputer<SortKey = PreviousScore>,
-    PreviousScore: 'static + Clone + Send + Sync + PartialOrd,
-    NewScore: 'static + Clone + Send + Sync + PartialOrd,
+    PreviousScore: 'static + Clone + Send + Sync,
+    NewScore: 'static + Clone + Send + Sync,
 {
     type SortKey = NewScore;
     type SegmentSortKey = T::SegmentSortKey;
+    type SegmentComparator = T::SegmentComparator;
 
     fn segment_sort_key(&mut self, doc: DocId, score: Score) -> Self::SegmentSortKey {
         self.sort_key_computer.segment_sort_key(doc, score)
@@ -346,7 +357,7 @@ where
         )
     }
 
-    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
         let sort_key_computer1 = self.0.segment_sort_key_computer(segment_reader)?;
         let sort_key_computer2 = self.1.segment_sort_key_computer(segment_reader)?;
         let sort_key_computer3 = self.2.segment_sort_key_computer(segment_reader)?;
@@ -409,7 +420,7 @@ where
         SortKeyComputer4::Comparator,
     );
 
-    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
         let sort_key_computer1 = self.0.segment_sort_key_computer(segment_reader)?;
         let sort_key_computer2 = self.1.segment_sort_key_computer(segment_reader)?;
         let sort_key_computer3 = self.2.segment_sort_key_computer(segment_reader)?;
@@ -443,7 +454,7 @@ where
 
 impl<F, SegmentF, TSortKey> SortKeyComputer for F
 where
-    F: 'static + Send + Sync + Fn(&SegmentReader) -> SegmentF,
+    F: 'static + Send + Sync + Fn(&dyn SegmentReader) -> SegmentF,
     SegmentF: 'static + FnMut(DocId) -> TSortKey,
     TSortKey: 'static + PartialOrd + Clone + Send + Sync + std::fmt::Debug,
 {
@@ -451,7 +462,7 @@ where
     type Child = SegmentF;
     type Comparator = NaturalComparator;
 
-    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
         Ok((self)(segment_reader))
     }
 }
@@ -463,6 +474,7 @@ where
 {
     type SortKey = TSortKey;
     type SegmentSortKey = TSortKey;
+    type SegmentComparator = NaturalComparator;
 
     fn segment_sort_key(&mut self, doc: DocId, _score: Score) -> TSortKey {
         (self)(doc)
@@ -497,10 +509,10 @@ mod tests {
 
     #[test]
     fn test_lazy_score_computer() {
-        let score_computer_primary = |_segment_reader: &SegmentReader| |_doc: DocId| 200u32;
+        let score_computer_primary = |_segment_reader: &dyn SegmentReader| |_doc: DocId| 200u32;
         let call_count = Arc::new(AtomicUsize::new(0));
         let call_count_clone = call_count.clone();
-        let score_computer_secondary = move |_segment_reader: &SegmentReader| {
+        let score_computer_secondary = move |_segment_reader: &dyn SegmentReader| {
             let call_count_new_clone = call_count_clone.clone();
             move |_doc: DocId| {
                 call_count_new_clone.fetch_add(1, AtomicOrdering::SeqCst);
@@ -560,10 +572,10 @@ mod tests {
 
     #[test]
     fn test_lazy_score_computer_dynamic_ordering() {
-        let score_computer_primary = |_segment_reader: &SegmentReader| |_doc: DocId| 200u32;
+        let score_computer_primary = |_segment_reader: &dyn SegmentReader| |_doc: DocId| 200u32;
         let call_count = Arc::new(AtomicUsize::new(0));
         let call_count_clone = call_count.clone();
-        let score_computer_secondary = move |_segment_reader: &SegmentReader| {
+        let score_computer_secondary = move |_segment_reader: &dyn SegmentReader| {
             let call_count_new_clone = call_count_clone.clone();
             move |_doc: DocId| {
                 call_count_new_clone.fetch_add(1, AtomicOrdering::SeqCst);

src/collector/sort_key_top_collector.rs

@@ -32,7 +32,11 @@ where TSortKeyComputer: SortKeyComputer + Send + Sync + 'static
         self.sort_key_computer.check_schema(schema)
     }
 
-    fn for_segment(&self, segment_ord: u32, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn for_segment(
+        &self,
+        segment_ord: u32,
+        segment_reader: &dyn SegmentReader,
+    ) -> Result<Self::Child> {
         let segment_sort_key_computer = self
             .sort_key_computer
             .segment_sort_key_computer(segment_reader)?;
@@ -63,7 +67,7 @@ where TSortKeyComputer: SortKeyComputer + Send + Sync + 'static
         &self,
         weight: &dyn Weight,
         segment_ord: u32,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<Vec<(TSortKeyComputer::SortKey, DocAddress)>> {
         let k = self.doc_range.end;
         let docs = self
@@ -160,7 +164,7 @@ mod tests {
         expected: &[(crate::Score, usize)],
     ) {
         let mut vals: Vec<(crate::Score, usize)> = (0..10).map(|val| (val as f32, val)).collect();
-        vals.shuffle(&mut rand::thread_rng());
+        vals.shuffle(&mut rand::rng());
         let vals_merged = merge_top_k(vals.into_iter(), doc_range, ComparatorEnum::from(order));
         assert_eq!(&vals_merged, expected);
     }

src/collector/tests.rs

@@ -5,7 +5,7 @@ use crate::query::{AllQuery, QueryParser};
 use crate::schema::{Schema, FAST, TEXT};
 use crate::time::format_description::well_known::Rfc3339;
 use crate::time::OffsetDateTime;
-use crate::{DateTime, DocAddress, Index, Searcher, TantivyDocument};
+use crate::{DateTime, DocAddress, Index, Searcher, SegmentReader, TantivyDocument};
 
 pub const TEST_COLLECTOR_WITH_SCORE: TestCollector = TestCollector {
     compute_score: true,
@@ -109,7 +109,7 @@ impl Collector for TestCollector {
     fn for_segment(
         &self,
         segment_id: SegmentOrdinal,
-        _reader: &SegmentReader,
+        _reader: &dyn SegmentReader,
     ) -> crate::Result<TestSegmentCollector> {
         Ok(TestSegmentCollector {
             segment_id,
@@ -180,7 +180,7 @@ impl Collector for FastFieldTestCollector {
     fn for_segment(
         &self,
         _: SegmentOrdinal,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<FastFieldSegmentCollector> {
         let reader = segment_reader
             .fast_fields()
@@ -243,7 +243,7 @@ impl Collector for BytesFastFieldTestCollector {
     fn for_segment(
         &self,
         _segment_local_id: u32,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<BytesFastFieldSegmentCollector> {
         let column_opt = segment_reader.fast_fields().bytes(&self.field)?;
         Ok(BytesFastFieldSegmentCollector {

src/collector/top_collector.rs

@@ -1,64 +1,22 @@
-use std::cmp::Ordering;
-
 use serde::{Deserialize, Serialize};
 
 /// Contains a feature (field, score, etc.) of a document along with the document address.
 ///
-/// It guarantees stable sorting: in case of a tie on the feature, the document
-/// address is used.
-///
-/// The REVERSE_ORDER generic parameter controls whether the by-feature order
-/// should be reversed, which is useful for achieving for example largest-first
-/// semantics without having to wrap the feature in a `Reverse`.
-#[derive(Clone, Default, Serialize, Deserialize)]
-pub struct ComparableDoc<T, D, const REVERSE_ORDER: bool = false> {
+/// Used only by TopNComputer, which implements the actual comparison via a `Comparator`.
+#[derive(Clone, Default, Eq, PartialEq, Serialize, Deserialize)]
+pub struct ComparableDoc<T, D> {
     /// The feature of the document. In practice, this is
-    /// is any type that implements `PartialOrd`.
+    /// is a type which can be compared with a `Comparator<T>`.
     pub sort_key: T,
-    /// The document address. In practice, this is any
-    /// type that implements `PartialOrd`, and is guaranteed
-    /// to be unique for each document.
+    /// The document address. In practice, this is either a `DocId` or `DocAddress`.
     pub doc: D,
 }
-impl<T: std::fmt::Debug, D: std::fmt::Debug, const R: bool> std::fmt::Debug
-    for ComparableDoc<T, D, R>
-{
+
+impl<T: std::fmt::Debug, D: std::fmt::Debug> std::fmt::Debug for ComparableDoc<T, D> {
     fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
-        f.debug_struct(format!("ComparableDoc<_, _ {R}").as_str())
+        f.debug_struct("ComparableDoc")
             .field("feature", &self.sort_key)
             .field("doc", &self.doc)
             .finish()
     }
 }
-
-impl<T: PartialOrd, D: PartialOrd, const R: bool> PartialOrd for ComparableDoc<T, D, R> {
-    fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
-        Some(self.cmp(other))
-    }
-}
-
-impl<T: PartialOrd, D: PartialOrd, const R: bool> Ord for ComparableDoc<T, D, R> {
-    #[inline]
-    fn cmp(&self, other: &Self) -> Ordering {
-        let by_feature = self
-            .sort_key
-            .partial_cmp(&other.sort_key)
-            .map(|ord| if R { ord.reverse() } else { ord })
-            .unwrap_or(Ordering::Equal);
-
-        let lazy_by_doc_address = || self.doc.partial_cmp(&other.doc).unwrap_or(Ordering::Equal);
-
-        // In case of a tie on the feature, we sort by ascending
-        // `DocAddress` in order to ensure a stable sorting of the
-        // documents.
-        by_feature.then_with(lazy_by_doc_address)
-    }
-}
-
-impl<T: PartialOrd, D: PartialOrd, const R: bool> PartialEq for ComparableDoc<T, D, R> {
-    fn eq(&self, other: &Self) -> bool {
-        self.cmp(other) == Ordering::Equal
-    }
-}
-
-impl<T: PartialOrd, D: PartialOrd, const R: bool> Eq for ComparableDoc<T, D, R> {}

src/collector/top_score_collector.rs

@@ -23,10 +23,9 @@ use crate::{DocAddress, DocId, Order, Score, SegmentReader};
 /// The theoretical complexity for collecting the top `K` out of `N` documents
 /// is `O(N + K)`.
 ///
-/// This collector does not guarantee a stable sorting in case of a tie on the
-/// document score, for stable sorting `PartialOrd` needs to resolve on other fields
-/// like docid in case of score equality.
-/// Only then, it is suitable for pagination.
+/// This collector guarantees a stable sorting in case of a tie on the
+/// document score/sort key: The document address (`DocAddress`) is used as a tie breaker.
+/// In case of a tie on the sort key, documents are always sorted by ascending `DocAddress`.
 ///
 /// ```rust
 /// use tantivy::collector::TopDocs;
@@ -325,7 +324,7 @@ impl TopDocs {
         sort_key_computer: impl SortKeyComputer<SortKey = TSortKey> + Send + 'static,
     ) -> impl Collector<Fruit = Vec<(TSortKey, DocAddress)>>
     where
-        TSortKey: 'static + Clone + Send + Sync + PartialOrd + std::fmt::Debug,
+        TSortKey: 'static + Clone + Send + Sync + std::fmt::Debug,
     {
         TopBySortKeyCollector::new(sort_key_computer, self.doc_range())
     }
@@ -394,7 +393,7 @@ impl TopDocs {
     /// // This is where we build our collector with our custom score.
     /// let top_docs_by_custom_score = TopDocs
     ///         ::with_limit(10)
-    ///          .tweak_score(move |segment_reader: &SegmentReader| {
+    ///          .tweak_score(move |segment_reader: &dyn SegmentReader| {
     ///             // The argument is a function that returns our scoring
     ///             // function.
     ///             //
@@ -443,10 +442,10 @@ pub struct TweakScoreFn<F>(F);
 
 impl<F, TTweakScoreSortKeyFn, TSortKey> SortKeyComputer for TweakScoreFn<F>
 where
-    F: 'static + Send + Sync + Fn(&SegmentReader) -> TTweakScoreSortKeyFn,
+    F: 'static + Send + Sync + Fn(&dyn SegmentReader) -> TTweakScoreSortKeyFn,
     TTweakScoreSortKeyFn: 'static + Fn(DocId, Score) -> TSortKey,
     TweakScoreSegmentSortKeyComputer<TTweakScoreSortKeyFn>:
-        SegmentSortKeyComputer<SortKey = TSortKey>,
+        SegmentSortKeyComputer<SortKey = TSortKey, SegmentSortKey = TSortKey>,
     TSortKey: 'static + PartialOrd + Clone + Send + Sync + std::fmt::Debug,
 {
     type SortKey = TSortKey;
@@ -459,7 +458,7 @@ where
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         Ok({
             TweakScoreSegmentSortKeyComputer {
@@ -481,6 +480,7 @@ where
 {
     type SortKey = TSortKey;
     type SegmentSortKey = TSortKey;
+    type SegmentComparator = NaturalComparator;
 
     fn segment_sort_key(&mut self, doc: DocId, score: Score) -> TSortKey {
         (self.sort_key_fn)(doc, score)
@@ -500,8 +500,13 @@ where
 ///
 /// For TopN == 0, it will be relative expensive.
 ///
-/// When using the natural comparator, the top N computer returns the top N elements in
-/// descending order, as expected for a top N.
+/// The TopNComputer will tiebreak by using ascending `D` (DocId or DocAddress):
+/// i.e., in case of a tie on the sort key, the `DocId|DocAddress` are always sorted in
+/// ascending order, regardless of the `Comparator` used for the `Score` type.
+///
+/// NOTE: Items must be `push`ed to the TopNComputer in ascending `DocId|DocAddress` order, as the
+/// threshold used to eliminate docs does not include the `DocId` or `DocAddress`: this provides
+/// the ascending `DocId|DocAddress` tie-breaking behavior without additional comparisons.
 #[derive(Serialize, Deserialize)]
 #[serde(from = "TopNComputerDeser<Score, D, C>")]
 pub struct TopNComputer<Score, D, C> {
@@ -580,6 +585,18 @@ where
     }
 }
 
+#[inline(always)]
+fn compare_for_top_k<TSortKey, D: Ord, C: Comparator<TSortKey>>(
+    c: &C,
+    lhs: &ComparableDoc<TSortKey, D>,
+    rhs: &ComparableDoc<TSortKey, D>,
+) -> std::cmp::Ordering {
+    c.compare(&lhs.sort_key, &rhs.sort_key)
+        .reverse() // Reverse here because we want top K.
+        .then_with(|| lhs.doc.cmp(&rhs.doc)) // Regardless of asc/desc, in presence of a tie, we
+                                             // sort by doc id
+}
+
 impl<TSortKey, D, C> TopNComputer<TSortKey, D, C>
 where
     D: Ord,
@@ -600,10 +617,13 @@ where
 
     /// Push a new document to the top n.
     /// If the document is below the current threshold, it will be ignored.
+    ///
+    /// NOTE: `push` must be called in ascending `DocId`/`DocAddress` order.
     #[inline]
     pub fn push(&mut self, sort_key: TSortKey, doc: D) {
         if let Some(last_median) = &self.threshold {
-            if self.comparator.compare(&sort_key, last_median) == Ordering::Less {
+            // See the struct docs for an explanation of why this comparison is strict.
+            if self.comparator.compare(&sort_key, last_median) != Ordering::Greater {
                 return;
             }
         }
@@ -629,9 +649,7 @@ where
     fn truncate_top_n(&mut self) -> TSortKey {
         // Use select_nth_unstable to find the top nth score
         let (_, median_el, _) = self.buffer.select_nth_unstable_by(self.top_n, |lhs, rhs| {
-            self.comparator
-                .compare(&rhs.sort_key, &lhs.sort_key)
-                .then_with(|| lhs.doc.cmp(&rhs.doc))
+            compare_for_top_k(&self.comparator, lhs, rhs)
         });
 
         let median_score = median_el.sort_key.clone();
@@ -646,11 +664,8 @@ where
         if self.buffer.len() > self.top_n {
             self.truncate_top_n();
         }
-        self.buffer.sort_unstable_by(|left, right| {
-            self.comparator
-                .compare(&right.sort_key, &left.sort_key)
-                .then_with(|| left.doc.cmp(&right.doc))
-        });
+        self.buffer
+            .sort_unstable_by(|lhs, rhs| compare_for_top_k(&self.comparator, lhs, rhs));
         self.buffer
     }
 
@@ -755,6 +770,33 @@ mod tests {
         );
     }
 
+    #[test]
+    fn test_topn_computer_duplicates() {
+        let mut computer: TopNComputer<u32, u32, NaturalComparator> =
+            TopNComputer::new_with_comparator(2, NaturalComparator);
+
+        computer.push(1u32, 1u32);
+        computer.push(1u32, 2u32);
+        computer.push(1u32, 3u32);
+        computer.push(1u32, 4u32);
+        computer.push(1u32, 5u32);
+
+        // In the presence of duplicates, DocIds are always ascending order.
+        assert_eq!(
+            computer.into_sorted_vec(),
+            &[
+                ComparableDoc {
+                    sort_key: 1u32,
+                    doc: 1u32,
+                },
+                ComparableDoc {
+                    sort_key: 1u32,
+                    doc: 2u32,
+                }
+            ]
+        );
+    }
+
     #[test]
     fn test_topn_computer_no_panic() {
         for top_n in 0..10 {
@@ -772,14 +814,17 @@ mod tests {
         #[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),
+          mut docs in proptest::collection::vec((0..100_u64, 0..100_u64), 0..100_usize),
         ) {
+            // NB: TopNComputer must receive inputs in ascending DocId order.
+            docs.sort_by_key(|(_, doc_id)| *doc_id);
             let mut computer: TopNComputer<_, _, ReverseComparator> = TopNComputer::new_with_comparator(limit, ReverseComparator);
             for (feature, doc) in &docs {
                 computer.push(*feature, *doc);
             }
-            let mut comparable_docs: Vec<ComparableDoc<u64, u64>> = docs.into_iter().map(|(sort_key, doc)| ComparableDoc { sort_key, doc }).collect::<Vec<_>>();
-            comparable_docs.sort();
+            let mut comparable_docs: Vec<ComparableDoc<u64, u64>> =
+                docs.into_iter().map(|(sort_key, doc)| ComparableDoc { sort_key, doc }).collect();
+            crate::collector::sort_key::tests::sort_hits(&mut comparable_docs, Order::Asc);
             comparable_docs.truncate(limit);
             prop_assert_eq!(
                 computer.into_sorted_vec(),
@@ -1406,15 +1451,10 @@ mod tests {
 
             // 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>> =
+            let sorted_docs: Vec<_> = {
+                let mut comparable_docs: Vec<ComparableDoc<_, _>> =
                     all_results.into_iter().map(|(sort_key, doc)| ComparableDoc { sort_key, doc}).collect();
-                comparable_docs.sort();
-                comparable_docs.into_iter().map(|cd| (cd.sort_key, cd.doc)).collect()
-            } else {
-                let mut comparable_docs: Vec<ComparableDoc<_, _, false>> =
-                    all_results.into_iter().map(|(sort_key, doc)| ComparableDoc { sort_key, doc}).collect();
-                comparable_docs.sort();
+                crate::collector::sort_key::tests::sort_hits(&mut comparable_docs, order);
                 comparable_docs.into_iter().map(|cd| (cd.sort_key, cd.doc)).collect()
             };
             let expected_docs = sorted_docs.into_iter().skip(offset).take(limit).collect::<Vec<_>>();
@@ -1485,7 +1525,7 @@ mod tests {
         let text_query = query_parser.parse_query("droopy tax")?;
         let collector = TopDocs::with_limit(2)
             .and_offset(1)
-            .order_by(move |_segment_reader: &SegmentReader| move |doc: DocId| doc);
+            .order_by(move |_segment_reader: &dyn SegmentReader| move |doc: DocId| doc);
         let score_docs: Vec<(u32, DocAddress)> =
             index.reader()?.searcher().search(&text_query, &collector)?;
         assert_eq!(
@@ -1503,7 +1543,7 @@ mod tests {
         let text_query = query_parser.parse_query("droopy tax").unwrap();
         let collector = TopDocs::with_limit(2)
             .and_offset(1)
-            .order_by(move |_segment_reader: &SegmentReader| move |doc: DocId| doc);
+            .order_by(move |_segment_reader: &dyn SegmentReader| move |doc: DocId| doc);
         let score_docs: Vec<(u32, DocAddress)> = index
             .reader()
             .unwrap()

src/core/executor.rs

@@ -48,7 +48,15 @@ impl Executor {
         F: Sized + Sync + Fn(A) -> crate::Result<R>,
     {
         match self {
-            Executor::SingleThread => args.map(f).collect::<crate::Result<_>>(),
+            Executor::SingleThread => {
+                // Avoid `collect`, since the stacktrace is blown up by it, which makes profiling
+                // harder.
+                let mut result = Vec::with_capacity(args.size_hint().0);
+                for arg in args {
+                    result.push(f(arg)?);
+                }
+                Ok(result)
+            }
             Executor::ThreadPool(pool) => {
                 let args: Vec<A> = args.collect();
                 let num_fruits = args.len();

src/core/json_utils.rs

@@ -406,7 +406,7 @@ mod tests {
         let mut term = Term::from_field_json_path(field, "color", false);
         term.append_type_and_str("red");
 
-        assert_eq!(term.serialized_term(), b"\x00\x00\x00\x01jcolor\x00sred")
+        assert_eq!(term.serialized_value_bytes(), b"color\x00sred".to_vec())
     }
 
     #[test]
@@ -416,8 +416,8 @@ mod tests {
         term.append_type_and_fast_value(-4i64);
 
         assert_eq!(
-            term.serialized_term(),
-            b"\x00\x00\x00\x01jcolor\x00i\x7f\xff\xff\xff\xff\xff\xff\xfc"
+            term.serialized_value_bytes(),
+            b"color\x00i\x7f\xff\xff\xff\xff\xff\xff\xfc".to_vec()
         )
     }
 
@@ -428,8 +428,8 @@ mod tests {
         term.append_type_and_fast_value(4u64);
 
         assert_eq!(
-            term.serialized_term(),
-            b"\x00\x00\x00\x01jcolor\x00u\x00\x00\x00\x00\x00\x00\x00\x04"
+            term.serialized_value_bytes(),
+            b"color\x00u\x00\x00\x00\x00\x00\x00\x00\x04".to_vec()
         )
     }
 
@@ -439,8 +439,8 @@ mod tests {
         let mut term = Term::from_field_json_path(field, "color", false);
         term.append_type_and_fast_value(4.0f64);
         assert_eq!(
-            term.serialized_term(),
-            b"\x00\x00\x00\x01jcolor\x00f\xc0\x10\x00\x00\x00\x00\x00\x00"
+            term.serialized_value_bytes(),
+            b"color\x00f\xc0\x10\x00\x00\x00\x00\x00\x00".to_vec()
         )
     }
 
@@ -450,8 +450,8 @@ mod tests {
         let mut term = Term::from_field_json_path(field, "color", false);
         term.append_type_and_fast_value(true);
         assert_eq!(
-            term.serialized_term(),
-            b"\x00\x00\x00\x01jcolor\x00o\x00\x00\x00\x00\x00\x00\x00\x01"
+            term.serialized_value_bytes(),
+            b"color\x00o\x00\x00\x00\x00\x00\x00\x00\x01".to_vec()
         )
     }
 

src/core/searcher.rs

@@ -4,7 +4,7 @@ use std::{fmt, io};
 
 use crate::collector::Collector;
 use crate::core::Executor;
-use crate::index::{SegmentId, SegmentReader};
+use crate::index::{ArcSegmentReader, SegmentId, SegmentReader};
 use crate::query::{Bm25StatisticsProvider, EnableScoring, Query};
 use crate::schema::document::DocumentDeserialize;
 use crate::schema::{Schema, Term};
@@ -36,7 +36,7 @@ pub struct SearcherGeneration {
 
 impl SearcherGeneration {
     pub(crate) fn from_segment_readers(
-        segment_readers: &[SegmentReader],
+        segment_readers: &[ArcSegmentReader],
         generation_id: u64,
     ) -> Self {
         let mut segment_id_to_del_opstamp = BTreeMap::new();
@@ -133,7 +133,7 @@ impl Searcher {
     pub fn doc_freq(&self, term: &Term) -> crate::Result<u64> {
         let mut total_doc_freq = 0;
         for segment_reader in &self.inner.segment_readers {
-            let inverted_index = segment_reader.inverted_index(term.field())?;
+            let inverted_index = segment_reader.as_ref().inverted_index(term.field())?;
             let doc_freq = inverted_index.doc_freq(term)?;
             total_doc_freq += u64::from(doc_freq);
         }
@@ -146,7 +146,7 @@ impl Searcher {
     pub async fn doc_freq_async(&self, term: &Term) -> crate::Result<u64> {
         let mut total_doc_freq = 0;
         for segment_reader in &self.inner.segment_readers {
-            let inverted_index = segment_reader.inverted_index(term.field())?;
+            let inverted_index = segment_reader.as_ref().inverted_index(term.field())?;
             let doc_freq = inverted_index.doc_freq_async(term).await?;
             total_doc_freq += u64::from(doc_freq);
         }
@@ -154,13 +154,13 @@ impl Searcher {
     }
 
     /// Return the list of segment readers
-    pub fn segment_readers(&self) -> &[SegmentReader] {
+    pub fn segment_readers(&self) -> &[ArcSegmentReader] {
         &self.inner.segment_readers
     }
 
     /// Returns the segment_reader associated with the given segment_ord
-    pub fn segment_reader(&self, segment_ord: u32) -> &SegmentReader {
-        &self.inner.segment_readers[segment_ord as usize]
+    pub fn segment_reader(&self, segment_ord: u32) -> &dyn SegmentReader {
+        self.inner.segment_readers[segment_ord as usize].as_ref()
     }
 
     /// Runs a query on the segment readers wrapped by the searcher.
@@ -229,7 +229,11 @@ impl Searcher {
         let segment_readers = self.segment_readers();
         let fruits = executor.map(
             |(segment_ord, segment_reader)| {
-                collector.collect_segment(weight.as_ref(), segment_ord as u32, segment_reader)
+                collector.collect_segment(
+                    weight.as_ref(),
+                    segment_ord as u32,
+                    segment_reader.as_ref(),
+                )
             },
             segment_readers.iter().enumerate(),
         )?;
@@ -259,7 +263,7 @@ impl From<Arc<SearcherInner>> for Searcher {
 pub(crate) struct SearcherInner {
     schema: Schema,
     index: Index,
-    segment_readers: Vec<SegmentReader>,
+    segment_readers: Vec<ArcSegmentReader>,
     store_readers: Vec<StoreReader>,
     generation: TrackedObject<SearcherGeneration>,
 }
@@ -269,7 +273,7 @@ impl SearcherInner {
     pub(crate) fn new(
         schema: Schema,
         index: Index,
-        segment_readers: Vec<SegmentReader>,
+        segment_readers: Vec<ArcSegmentReader>,
         generation: TrackedObject<SearcherGeneration>,
         doc_store_cache_num_blocks: usize,
     ) -> io::Result<SearcherInner> {
@@ -301,7 +305,7 @@ impl fmt::Debug for Searcher {
         let segment_ids = self
             .segment_readers()
             .iter()
-            .map(SegmentReader::segment_id)
+            .map(|segment_reader| segment_reader.segment_id())
             .collect::<Vec<_>>();
         write!(f, "Searcher({segment_ids:?})")
     }

src/directory/composite_file.rs

@@ -5,7 +5,7 @@ use std::ops::Range;
 use common::{BinarySerializable, CountingWriter, HasLen, VInt};
 
 use crate::directory::{FileSlice, TerminatingWrite, WritePtr};
-use crate::schema::Field;
+use crate::schema::{Field, Schema};
 use crate::space_usage::{FieldUsage, PerFieldSpaceUsage};
 
 #[derive(Eq, PartialEq, Hash, Copy, Ord, PartialOrd, Clone, Debug)]
@@ -167,10 +167,11 @@ impl CompositeFile {
             .map(|byte_range| self.data.slice(byte_range.clone()))
     }
 
-    pub fn space_usage(&self) -> PerFieldSpaceUsage {
+    pub fn space_usage(&self, schema: &Schema) -> PerFieldSpaceUsage {
         let mut fields = Vec::new();
         for (&field_addr, byte_range) in &self.offsets_index {
-            let mut field_usage = FieldUsage::empty(field_addr.field);
+            let field_name = schema.get_field_name(field_addr.field).to_string();
+            let mut field_usage = FieldUsage::empty(field_name);
             field_usage.add_field_idx(field_addr.idx, byte_range.len().into());
             fields.push(field_usage);
         }

src/directory/mmap_directory/mod.rs

@@ -1,3 +1,5 @@
+mod file_watcher;
+
 use std::collections::HashMap;
 use std::fmt;
 use std::fs::{self, File, OpenOptions};
@@ -7,6 +9,7 @@ use std::path::{Path, PathBuf};
 use std::sync::{Arc, RwLock, Weak};
 
 use common::StableDeref;
+use file_watcher::FileWatcher;
 use fs4::fs_std::FileExt;
 #[cfg(all(feature = "mmap", unix))]
 pub use memmap2::Advice;
@@ -18,7 +21,6 @@ use crate::core::META_FILEPATH;
 use crate::directory::error::{
     DeleteError, LockError, OpenDirectoryError, OpenReadError, OpenWriteError,
 };
-use crate::directory::file_watcher::FileWatcher;
 use crate::directory::{
     AntiCallToken, Directory, DirectoryLock, FileHandle, Lock, OwnedBytes, TerminatingWrite,
     WatchCallback, WatchHandle, WritePtr,

src/directory/mod.rs

@@ -5,7 +5,6 @@ mod mmap_directory;
 
 mod directory;
 mod directory_lock;
-mod file_watcher;
 pub mod footer;
 mod managed_directory;
 mod ram_directory;

src/docset.rs

@@ -40,6 +40,8 @@ pub trait DocSet: Send {
     /// of `DocSet` should support it.
     ///
     /// Calling `seek(TERMINATED)` is also legal and is the normal way to consume a `DocSet`.
+    ///
+    /// `target` has to be larger or equal to `.doc()` when calling `seek`.
     fn seek(&mut self, target: DocId) -> DocId {
         let mut doc = self.doc();
         debug_assert!(doc <= target);
@@ -49,6 +51,57 @@ pub trait DocSet: Send {
         doc
     }
 
+    /// !!!Dragons ahead!!!
+    /// In spirit, this is an approximate and dangerous version of `seek`.
+    ///
+    /// It can leave the DocSet in an `invalid` state and might return a
+    /// lower bound of what the result of Seek would have been.
+    ///
+    ///
+    /// More accurately it returns either:
+    /// - Found if the target is in the docset. In that case, the DocSet is left in a valid state.
+    /// - SeekLowerBound(seek_lower_bound) if the target is not in the docset. In that case, The
+    ///   DocSet can be the left in a invalid state. The DocSet should then only receives call to
+    ///   `seek_danger(..)` until it returns `Found`, and get back to a valid state.
+    ///
+    /// `seek_lower_bound` can be any `DocId` (in the docset or not) as long as it is in
+    /// `(target .. seek_result]` where `seek_result` is the first document in the docset greater
+    /// than to `target`.
+    ///
+    /// `seek_danger` may return `SeekLowerBound(TERMINATED)`.
+    ///
+    /// Calling `seek_danger` with TERMINATED as a target is allowed,
+    /// and should always return NewTarget(TERMINATED) or anything larger as TERMINATED is NOT in
+    /// the DocSet.
+    ///
+    /// DocSets that already have an efficient `seek` method don't need to implement
+    /// `seek_danger`.
+    ///
+    /// Consecutive calls to seek_danger are guaranteed to have strictly increasing `target`
+    /// values.
+    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
+        if target >= TERMINATED {
+            debug_assert!(target == TERMINATED);
+            // No need to advance.
+            return SeekDangerResult::SeekLowerBound(target);
+        }
+
+        // The default implementation does not include any
+        // `danger zone` behavior.
+        //
+        // It does not leave the scorer in an invalid state.
+        // For this reason, we can safely call `self.doc()`.
+        let mut doc = self.doc();
+        if doc < target {
+            doc = self.seek(target);
+        }
+        if doc == target {
+            SeekDangerResult::Found
+        } else {
+            SeekDangerResult::SeekLowerBound(self.doc())
+        }
+    }
+
     /// Fills a given mutable buffer with the next doc ids from the
     /// `DocSet`
     ///
@@ -94,6 +147,15 @@ pub trait DocSet: Send {
     /// which would be the number of documents in the DocSet.
     ///
     /// By default this returns `size_hint()`.
+    ///
+    /// DocSets may have vastly different cost depending on their type,
+    /// e.g. an intersection with 10 hits is much cheaper than
+    /// a phrase search with 10 hits, since it needs to load positions.
+    ///
+    /// ### Future Work
+    /// We may want to differentiate `DocSet` costs more more granular, e.g.
+    /// creation_cost, advance_cost, seek_cost on to get a good estimation
+    /// what query types to choose.
     fn cost(&self) -> u64 {
         self.size_hint() as u64
     }
@@ -128,6 +190,17 @@ pub trait DocSet: Send {
     }
 }
 
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum SeekDangerResult {
+    /// The target was found in the DocSet.
+    Found,
+    /// The target was not found in the DocSet.
+    /// We return a range in which the value could be.
+    /// The given target can be any DocId, that is <= than the first document
+    /// in the docset after the target.
+    SeekLowerBound(DocId),
+}
+
 impl DocSet for &mut dyn DocSet {
     fn advance(&mut self) -> u32 {
         (**self).advance()
@@ -137,6 +210,10 @@ impl DocSet for &mut dyn DocSet {
         (**self).seek(target)
     }
 
+    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
+        (**self).seek_danger(target)
+    }
+
     fn doc(&self) -> u32 {
         (**self).doc()
     }
@@ -169,6 +246,11 @@ impl<TDocSet: DocSet + ?Sized> DocSet for Box<TDocSet> {
         unboxed.seek(target)
     }
 
+    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
+        let unboxed: &mut TDocSet = self.borrow_mut();
+        unboxed.seek_danger(target)
+    }
+
     fn fill_buffer(&mut self, buffer: &mut [DocId; COLLECT_BLOCK_BUFFER_LEN]) -> usize {
         let unboxed: &mut TDocSet = self.borrow_mut();
         unboxed.fill_buffer(buffer)

src/fastfield/alive_bitset.rs

@@ -162,7 +162,7 @@ mod tests {
 mod bench {
 
     use rand::prelude::IteratorRandom;
-    use rand::thread_rng;
+    use rand::rng;
     use test::Bencher;
 
     use super::AliveBitSet;
@@ -176,7 +176,7 @@ mod bench {
     }
 
     fn remove_rand(raw: &mut Vec<u32>) {
-        let i = (0..raw.len()).choose(&mut thread_rng()).unwrap();
+        let i = (0..raw.len()).choose(&mut rng()).unwrap();
         raw.remove(i);
     }
 

src/fastfield/mod.rs

@@ -96,7 +96,7 @@ mod tests {
     };
     use crate::time::OffsetDateTime;
     use crate::tokenizer::{LowerCaser, RawTokenizer, TextAnalyzer, TokenizerManager};
-    use crate::{Index, IndexWriter, SegmentReader};
+    use crate::{Index, IndexWriter};
 
     pub static SCHEMA: Lazy<Schema> = Lazy::new(|| {
         let mut schema_builder = Schema::builder();
@@ -430,7 +430,7 @@ mod tests {
             .searcher()
             .segment_readers()
             .iter()
-            .map(SegmentReader::segment_id)
+            .map(|segment_reader| segment_reader.segment_id())
             .collect();
         assert_eq!(segment_ids.len(), 2);
         index_writer.merge(&segment_ids[..]).wait().unwrap();
@@ -879,7 +879,7 @@ mod tests {
         const ONE_HOUR_IN_MICROSECS: i64 = 3_600 * 1_000_000;
         let times: Vec<DateTime> = std::iter::repeat_with(|| {
             // +- One hour.
-            let t = T0 + rng.gen_range(-ONE_HOUR_IN_MICROSECS..ONE_HOUR_IN_MICROSECS);
+            let t = T0 + rng.random_range(-ONE_HOUR_IN_MICROSECS..ONE_HOUR_IN_MICROSECS);
             DateTime::from_timestamp_micros(t)
         })
         .take(1_000)

src/fastfield/readers.rs

@@ -8,7 +8,7 @@ use columnar::{
 };
 use common::ByteCount;
 
-use crate::core::json_utils::encode_column_name;
+use crate::core::json_utils::{encode_column_name, json_path_sep_to_dot};
 use crate::directory::FileSlice;
 use crate::schema::{Field, FieldEntry, FieldType, Schema};
 use crate::space_usage::{FieldUsage, PerFieldSpaceUsage};
@@ -39,19 +39,15 @@ impl FastFieldReaders {
         self.resolve_column_name_given_default_field(column_name, default_field_opt)
     }
 
-    pub(crate) fn space_usage(&self, schema: &Schema) -> io::Result<PerFieldSpaceUsage> {
+    pub(crate) fn space_usage(&self) -> io::Result<PerFieldSpaceUsage> {
         let mut per_field_usages: Vec<FieldUsage> = Default::default();
-        for (field, field_entry) in schema.fields() {
-            let column_handles = self.columnar.read_columns(field_entry.name())?;
-            let num_bytes: ByteCount = column_handles
-                .iter()
-                .map(|column_handle| column_handle.num_bytes())
-                .sum();
-            let mut field_usage = FieldUsage::empty(field);
-            field_usage.add_field_idx(0, num_bytes);
+        for (mut field_name, column_handle) in self.columnar.iter_columns()? {
+            json_path_sep_to_dot(&mut field_name);
+            let space_usage = column_handle.space_usage()?;
+            let mut field_usage = FieldUsage::empty(field_name);
+            field_usage.set_column_usage(space_usage);
             per_field_usages.push(field_usage);
         }
-        // TODO fix space usage for JSON fields.
         Ok(PerFieldSpaceUsage::new(per_field_usages))
     }
 

src/fieldnorm/reader.rs

@@ -2,7 +2,7 @@ use std::sync::Arc;
 
 use super::{fieldnorm_to_id, id_to_fieldnorm};
 use crate::directory::{CompositeFile, FileSlice, OwnedBytes};
-use crate::schema::Field;
+use crate::schema::{Field, Schema};
 use crate::space_usage::PerFieldSpaceUsage;
 use crate::DocId;
 
@@ -37,8 +37,8 @@ impl FieldNormReaders {
     }
 
     /// Return a break down of the space usage per field.
-    pub fn space_usage(&self) -> PerFieldSpaceUsage {
-        self.data.space_usage()
+    pub fn space_usage(&self, schema: &Schema) -> PerFieldSpaceUsage {
+        self.data.space_usage(schema)
     }
 
     /// Returns a handle to inner file

src/functional_test.rs

@@ -1,6 +1,6 @@
 use std::collections::HashSet;
 
-use rand::{thread_rng, Rng};
+use rand::{rng, Rng};
 
 use crate::indexer::index_writer::MEMORY_BUDGET_NUM_BYTES_MIN;
 use crate::schema::*;
@@ -29,7 +29,7 @@ fn test_functional_store() -> crate::Result<()> {
     let index = Index::create_in_ram(schema);
     let reader = index.reader()?;
 
-    let mut rng = thread_rng();
+    let mut rng = rng();
 
     let mut index_writer: IndexWriter =
         index.writer_with_num_threads(3, 3 * MEMORY_BUDGET_NUM_BYTES_MIN)?;
@@ -38,9 +38,9 @@ fn test_functional_store() -> crate::Result<()> {
 
     let mut doc_id = 0u64;
     for _iteration in 0..get_num_iterations() {
-        let num_docs: usize = rng.gen_range(0..4);
+        let num_docs: usize = rng.random_range(0..4);
         if !doc_set.is_empty() {
-            let doc_to_remove_id = rng.gen_range(0..doc_set.len());
+            let doc_to_remove_id = rng.random_range(0..doc_set.len());
             let removed_doc_id = doc_set.swap_remove(doc_to_remove_id);
             index_writer.delete_term(Term::from_field_u64(id_field, removed_doc_id));
         }
@@ -70,10 +70,10 @@ const LOREM: &str = "Doc Lorem ipsum dolor sit amet, consectetur adipiscing elit
                      cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat \
                      non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.";
 fn get_text() -> String {
-    use rand::seq::SliceRandom;
-    let mut rng = thread_rng();
+    use rand::seq::IndexedRandom;
+    let mut rng = rng();
     let tokens: Vec<_> = LOREM.split(' ').collect();
-    let random_val = rng.gen_range(0..20);
+    let random_val = rng.random_range(0..20);
 
     (0..random_val)
         .map(|_| tokens.choose(&mut rng).unwrap())
@@ -101,7 +101,7 @@ fn test_functional_indexing_unsorted() -> crate::Result<()> {
     let index = Index::create_from_tempdir(schema)?;
     let reader = index.reader()?;
 
-    let mut rng = thread_rng();
+    let mut rng = rng();
 
     let mut index_writer: IndexWriter =
         index.writer_with_num_threads(3, 3 * MEMORY_BUDGET_NUM_BYTES_MIN)?;
@@ -110,7 +110,7 @@ fn test_functional_indexing_unsorted() -> crate::Result<()> {
     let mut uncommitted_docs: HashSet<u64> = HashSet::new();
 
     for _ in 0..get_num_iterations() {
-        let random_val = rng.gen_range(0..20);
+        let random_val = rng.random_range(0..20);
         if random_val == 0 {
             index_writer.commit()?;
             committed_docs.extend(&uncommitted_docs);

src/index/index.rs

@@ -14,7 +14,7 @@ use crate::directory::error::OpenReadError;
 use crate::directory::MmapDirectory;
 use crate::directory::{Directory, ManagedDirectory, RamDirectory, INDEX_WRITER_LOCK};
 use crate::error::{DataCorruption, TantivyError};
-use crate::index::{IndexMeta, SegmentId, SegmentMeta, SegmentMetaInventory};
+use crate::index::{IndexMeta, SegmentId, SegmentMeta, SegmentMetaInventory, SegmentReader};
 use crate::indexer::index_writer::{
     IndexWriterOptions, MAX_NUM_THREAD, MEMORY_BUDGET_NUM_BYTES_MIN,
 };
@@ -24,7 +24,7 @@ use crate::reader::{IndexReader, IndexReaderBuilder};
 use crate::schema::document::Document;
 use crate::schema::{Field, FieldType, Schema};
 use crate::tokenizer::{TextAnalyzer, TokenizerManager};
-use crate::SegmentReader;
+use crate::TantivySegmentReader;
 
 fn load_metas(
     directory: &dyn Directory,
@@ -492,7 +492,7 @@ impl Index {
         let segments = self.searchable_segments()?;
         let fields_metadata: Vec<Vec<FieldMetadata>> = segments
             .into_iter()
-            .map(|segment| SegmentReader::open(&segment)?.fields_metadata())
+            .map(|segment| TantivySegmentReader::open(&segment)?.fields_metadata())
             .collect::<Result<_, _>>()?;
         Ok(merge_field_meta_data(fields_metadata))
     }

src/index/index_meta.rs

@@ -13,9 +13,9 @@ use crate::store::Compressor;
 use crate::{Inventory, Opstamp, TrackedObject};
 
 #[derive(Clone, Debug, Serialize, Deserialize)]
-struct DeleteMeta {
+pub struct DeleteMeta {
     num_deleted_docs: u32,
-    opstamp: Opstamp,
+    pub opstamp: Opstamp,
 }
 
 #[derive(Clone, Default)]
@@ -213,7 +213,7 @@ impl SegmentMeta {
 struct InnerSegmentMeta {
     segment_id: SegmentId,
     max_doc: u32,
-    deletes: Option<DeleteMeta>,
+    pub deletes: Option<DeleteMeta>,
     /// If you want to avoid the SegmentComponent::TempStore file to be covered by
     /// garbage collection and deleted, set this to true. This is used during merge.
     #[serde(skip)]
@@ -404,7 +404,10 @@ mod tests {
             schema_builder.build()
         };
         let index_metas = IndexMeta {
-            index_settings: IndexSettings::default(),
+            index_settings: IndexSettings {
+                docstore_compression: Compressor::None,
+                ..Default::default()
+            },
             segments: Vec::new(),
             schema,
             opstamp: 0u64,
@@ -413,7 +416,7 @@ mod tests {
         let json = serde_json::ser::to_string(&index_metas).expect("serialization failed");
         assert_eq!(
             json,
-            r#"{"index_settings":{"docstore_compression":"lz4","docstore_blocksize":16384},"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","fieldnorms":true,"tokenizer":"default"},"stored":false,"fast":false}}],"opstamp":0}"#
+            r#"{"index_settings":{"docstore_compression":"none","docstore_blocksize":16384},"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","fieldnorms":true,"tokenizer":"default"},"stored":false,"fast":false}}],"opstamp":0}"#
         );
 
         let deser_meta: UntrackedIndexMeta = serde_json::from_str(&json).unwrap();
@@ -494,6 +497,8 @@ mod tests {
     #[test]
     #[cfg(feature = "lz4-compression")]
     fn test_index_settings_default() {
+        use crate::store::Compressor;
+
         let mut index_settings = IndexSettings::default();
         assert_eq!(
             index_settings,

src/index/inverted_index_reader.rs

@@ -1,4 +1,9 @@
+#[cfg(feature = "quickwit")]
+use std::future::Future;
 use std::io;
+#[cfg(feature = "quickwit")]
+use std::pin::Pin;
+use std::sync::Arc;
 
 use common::json_path_writer::JSON_END_OF_PATH;
 use common::{BinarySerializable, ByteCount};
@@ -27,7 +32,102 @@ use crate::termdict::TermDictionary;
 ///
 /// `InvertedIndexReader` are created by calling
 /// [`SegmentReader::inverted_index()`](crate::SegmentReader::inverted_index).
-pub struct InvertedIndexReader {
+pub trait InvertedIndexReader: Send + Sync {
+    /// Returns the term info associated with the term.
+    fn get_term_info(&self, term: &Term) -> io::Result<Option<TermInfo>>;
+
+    /// Return the term dictionary datastructure.
+    fn terms(&self) -> &TermDictionary;
+
+    /// Return the fields and types encoded in the dictionary in lexicographic order.
+    /// Only valid on JSON fields.
+    ///
+    /// Notice: This requires a full scan and therefore **very expensive**.
+    /// TODO: Move to sstable to use the index.
+    #[doc(hidden)]
+    fn list_encoded_json_fields(&self) -> io::Result<Vec<InvertedIndexFieldSpace>>;
+
+    /// Returns a block postings given a `Term`.
+    /// This method is for an advanced usage only.
+    ///
+    /// Most users should prefer using [`Self::read_postings()`] instead.
+    fn read_block_postings(
+        &self,
+        term: &Term,
+        option: IndexRecordOption,
+    ) -> io::Result<Option<BlockSegmentPostings>>;
+
+    /// Returns a block postings given a `term_info`.
+    /// This method is for an advanced usage only.
+    ///
+    /// Most users should prefer using [`Self::read_postings()`] instead.
+    fn read_block_postings_from_terminfo(
+        &self,
+        term_info: &TermInfo,
+        requested_option: IndexRecordOption,
+    ) -> io::Result<BlockSegmentPostings>;
+
+    /// Returns a posting object given a `term_info`.
+    /// This method is for an advanced usage only.
+    ///
+    /// Most users should prefer using [`Self::read_postings()`] instead.
+    fn read_postings_from_terminfo(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+    ) -> io::Result<SegmentPostings>;
+
+    /// Returns the total number of tokens recorded for all documents
+    /// (including deleted documents).
+    fn total_num_tokens(&self) -> u64;
+
+    /// Returns the segment postings associated with the term, and with the given option,
+    /// or `None` if the term has never been encountered and indexed.
+    fn read_postings(
+        &self,
+        term: &Term,
+        option: IndexRecordOption,
+    ) -> io::Result<Option<SegmentPostings>>;
+
+    /// Returns the number of documents containing the term.
+    fn doc_freq(&self, term: &Term) -> io::Result<u32>;
+
+    /// Returns the number of documents containing the term asynchronously.
+    #[cfg(feature = "quickwit")]
+    fn doc_freq_async<'a>(&'a self, term: &'a Term) -> BoxFuture<'a, io::Result<u32>>;
+
+    /// Warmup a block postings given a `Term`.
+    /// This method is for an advanced usage only.
+    ///
+    /// returns a boolean, whether the term was found in the dictionary
+    #[cfg(feature = "quickwit")]
+    fn warm_postings<'a>(
+        &'a self,
+        term: &'a Term,
+        with_positions: bool,
+    ) -> BoxFuture<'a, io::Result<bool>>;
+
+    /// Warmup the block postings for all terms.
+    /// This method is for an advanced usage only.
+    ///
+    /// If you know which terms to pre-load, prefer using [`Self::warm_postings`] or
+    /// [`Self::warm_postings`] instead.
+    #[cfg(feature = "quickwit")]
+    fn warm_postings_full<'a>(&'a self, with_positions: bool) -> BoxFuture<'a, io::Result<()>>;
+}
+
+/// Convenient alias for an atomically reference counted inverted index reader handle.
+pub type ArcInvertedIndexReader = Arc<dyn InvertedIndexReader>;
+
+#[cfg(feature = "quickwit")]
+/// Boxed future used by async inverted index reader methods.
+pub type BoxFuture<'a, T> = Pin<Box<dyn Future<Output = T> + Send + 'a>>;
+
+/// The tantivy inverted index reader is in charge of accessing
+/// the inverted index associated with a specific field.
+///
+/// This is the default implementation of [`InvertedIndexReader`].
+pub struct TantivyInvertedIndexReader {
     termdict: TermDictionary,
     postings_file_slice: FileSlice,
     positions_file_slice: FileSlice,
@@ -36,11 +136,16 @@ pub struct InvertedIndexReader {
 }
 
 /// Object that records the amount of space used by a field in an inverted index.
-pub(crate) struct InvertedIndexFieldSpace {
+pub struct InvertedIndexFieldSpace {
+    /// The JSON field name (without the parent field).
     pub field_name: String,
+    /// The field type encoded in the term dictionary.
     pub field_type: Type,
+    /// Total postings size for this field.
     pub postings_size: ByteCount,
+    /// Total positions size for this field.
     pub positions_size: ByteCount,
+    /// Number of terms for this field.
     pub num_terms: u64,
 }
 
@@ -62,16 +167,16 @@ impl InvertedIndexFieldSpace {
     }
 }
 
-impl InvertedIndexReader {
+impl TantivyInvertedIndexReader {
     pub(crate) fn new(
         termdict: TermDictionary,
         postings_file_slice: FileSlice,
         positions_file_slice: FileSlice,
         record_option: IndexRecordOption,
-    ) -> io::Result<InvertedIndexReader> {
+    ) -> io::Result<TantivyInvertedIndexReader> {
         let (total_num_tokens_slice, postings_body) = postings_file_slice.split(8);
         let total_num_tokens = u64::deserialize(&mut total_num_tokens_slice.read_bytes()?)?;
-        Ok(InvertedIndexReader {
+        Ok(TantivyInvertedIndexReader {
             termdict,
             postings_file_slice: postings_body,
             positions_file_slice,
@@ -82,8 +187,8 @@ impl InvertedIndexReader {
 
     /// Creates an empty `InvertedIndexReader` object, which
     /// contains no terms at all.
-    pub fn empty(record_option: IndexRecordOption) -> InvertedIndexReader {
-        InvertedIndexReader {
+    pub fn empty(record_option: IndexRecordOption) -> TantivyInvertedIndexReader {
+        TantivyInvertedIndexReader {
             termdict: TermDictionary::empty(),
             postings_file_slice: FileSlice::empty(),
             positions_file_slice: FileSlice::empty(),
@@ -160,29 +265,6 @@ impl InvertedIndexReader {
         Ok(fields)
     }
 
-    /// Resets the block segment to another position of the postings
-    /// file.
-    ///
-    /// This is useful for enumerating through a list of terms,
-    /// and consuming the associated posting lists while avoiding
-    /// reallocating a [`BlockSegmentPostings`].
-    ///
-    /// # Warning
-    ///
-    /// This does not reset the positions list.
-    pub fn reset_block_postings_from_terminfo(
-        &self,
-        term_info: &TermInfo,
-        block_postings: &mut BlockSegmentPostings,
-    ) -> io::Result<()> {
-        let postings_slice = self
-            .postings_file_slice
-            .slice(term_info.postings_range.clone());
-        let postings_bytes = postings_slice.read_bytes()?;
-        block_postings.reset(term_info.doc_freq, postings_bytes)?;
-        Ok(())
-    }
-
     /// Returns a block postings given a `Term`.
     /// This method is for an advanced usage only.
     ///
@@ -282,7 +364,7 @@ impl InvertedIndexReader {
 }
 
 #[cfg(feature = "quickwit")]
-impl InvertedIndexReader {
+impl TantivyInvertedIndexReader {
     pub(crate) async fn get_term_info_async(&self, term: &Term) -> io::Result<Option<TermInfo>> {
         self.termdict.get_async(term.serialized_value_bytes()).await
     }
@@ -492,3 +574,84 @@ impl InvertedIndexReader {
             .unwrap_or(0u32))
     }
 }
+
+impl InvertedIndexReader for TantivyInvertedIndexReader {
+    fn get_term_info(&self, term: &Term) -> io::Result<Option<TermInfo>> {
+        TantivyInvertedIndexReader::get_term_info(self, term)
+    }
+
+    fn terms(&self) -> &TermDictionary {
+        TantivyInvertedIndexReader::terms(self)
+    }
+
+    fn list_encoded_json_fields(&self) -> io::Result<Vec<InvertedIndexFieldSpace>> {
+        TantivyInvertedIndexReader::list_encoded_json_fields(self)
+    }
+
+    fn read_block_postings(
+        &self,
+        term: &Term,
+        option: IndexRecordOption,
+    ) -> io::Result<Option<BlockSegmentPostings>> {
+        TantivyInvertedIndexReader::read_block_postings(self, term, option)
+    }
+
+    fn read_block_postings_from_terminfo(
+        &self,
+        term_info: &TermInfo,
+        requested_option: IndexRecordOption,
+    ) -> io::Result<BlockSegmentPostings> {
+        TantivyInvertedIndexReader::read_block_postings_from_terminfo(
+            self,
+            term_info,
+            requested_option,
+        )
+    }
+
+    fn read_postings_from_terminfo(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+    ) -> io::Result<SegmentPostings> {
+        TantivyInvertedIndexReader::read_postings_from_terminfo(self, term_info, option)
+    }
+
+    fn total_num_tokens(&self) -> u64 {
+        TantivyInvertedIndexReader::total_num_tokens(self)
+    }
+
+    fn read_postings(
+        &self,
+        term: &Term,
+        option: IndexRecordOption,
+    ) -> io::Result<Option<SegmentPostings>> {
+        TantivyInvertedIndexReader::read_postings(self, term, option)
+    }
+
+    fn doc_freq(&self, term: &Term) -> io::Result<u32> {
+        TantivyInvertedIndexReader::doc_freq(self, term)
+    }
+
+    #[cfg(feature = "quickwit")]
+    fn doc_freq_async<'a>(&'a self, term: &'a Term) -> BoxFuture<'a, io::Result<u32>> {
+        Box::pin(async move { TantivyInvertedIndexReader::doc_freq_async(self, term).await })
+    }
+
+    #[cfg(feature = "quickwit")]
+    fn warm_postings<'a>(
+        &'a self,
+        term: &'a Term,
+        with_positions: bool,
+    ) -> BoxFuture<'a, io::Result<bool>> {
+        Box::pin(async move {
+            TantivyInvertedIndexReader::warm_postings(self, term, with_positions).await
+        })
+    }
+
+    #[cfg(feature = "quickwit")]
+    fn warm_postings_full<'a>(&'a self, with_positions: bool) -> BoxFuture<'a, io::Result<()>> {
+        Box::pin(async move {
+            TantivyInvertedIndexReader::warm_postings_full(self, with_positions).await
+        })
+    }
+}

src/index/mod.rs

@@ -13,8 +13,13 @@ mod segment_reader;
 pub use self::index::{Index, IndexBuilder};
 pub(crate) use self::index_meta::SegmentMetaInventory;
 pub use self::index_meta::{IndexMeta, IndexSettings, Order, SegmentMeta};
-pub use self::inverted_index_reader::InvertedIndexReader;
+pub use self::inverted_index_reader::{
+    ArcInvertedIndexReader, InvertedIndexFieldSpace, InvertedIndexReader,
+    TantivyInvertedIndexReader,
+};
 pub use self::segment::Segment;
 pub use self::segment_component::SegmentComponent;
 pub use self::segment_id::SegmentId;
-pub use self::segment_reader::{FieldMetadata, SegmentReader};
+pub use self::segment_reader::{
+    ArcSegmentReader, FieldMetadata, SegmentReader, TantivySegmentReader,
+};

src/index/segment.rs

@@ -46,7 +46,7 @@ impl Segment {
     ///
     /// This method is only used when updating `max_doc` from 0
     /// as we finalize a fresh new segment.
-    pub(crate) fn with_max_doc(self, max_doc: u32) -> Segment {
+    pub fn with_max_doc(self, max_doc: u32) -> Segment {
         Segment {
             index: self.index,
             meta: self.meta.with_max_doc(max_doc),

src/index/segment_reader.rs

@@ -9,8 +9,10 @@ use itertools::Itertools;
 use crate::directory::{CompositeFile, FileSlice};
 use crate::error::DataCorruption;
 use crate::fastfield::{intersect_alive_bitsets, AliveBitSet, FacetReader, FastFieldReaders};
-use crate::fieldnorm::{FieldNormReader, FieldNormReaders};
-use crate::index::{InvertedIndexReader, Segment, SegmentComponent, SegmentId};
+use crate::fieldnorm::FieldNormReaders;
+use crate::index::{
+    ArcInvertedIndexReader, Segment, SegmentComponent, SegmentId, TantivyInvertedIndexReader,
+};
 use crate::json_utils::json_path_sep_to_dot;
 use crate::schema::{Field, IndexRecordOption, Schema, Type};
 use crate::space_usage::SegmentSpaceUsage;
@@ -18,6 +20,93 @@ use crate::store::StoreReader;
 use crate::termdict::TermDictionary;
 use crate::{DocId, Opstamp};
 
+/// Abstraction over a segment reader for accessing all data structures of a segment.
+///
+/// This trait exists to decouple the query layer from the concrete on-disk layout. Alternative
+/// codecs can implement it to expose their own segment representation.
+pub trait SegmentReader: Send + Sync {
+    /// Highest document id ever attributed in this segment + 1.
+    fn max_doc(&self) -> DocId;
+
+    /// Number of alive documents. Deleted documents are not counted.
+    fn num_docs(&self) -> DocId;
+
+    /// Returns the schema of the index this segment belongs to.
+    fn schema(&self) -> &Schema;
+
+    /// Return the number of documents that have been deleted in the segment.
+    fn num_deleted_docs(&self) -> DocId {
+        self.max_doc() - self.num_docs()
+    }
+
+    /// Returns true if some of the documents of the segment have been deleted.
+    fn has_deletes(&self) -> bool {
+        self.num_deleted_docs() > 0
+    }
+
+    /// Accessor to a segment's fast field reader.
+    fn fast_fields(&self) -> &FastFieldReaders;
+
+    /// Accessor to the `FacetReader` associated with a given `Field`.
+    fn facet_reader(&self, field_name: &str) -> crate::Result<FacetReader> {
+        let schema = self.schema();
+        let field = schema.get_field(field_name)?;
+        let field_entry = schema.get_field_entry(field);
+        if field_entry.field_type().value_type() != Type::Facet {
+            return Err(crate::TantivyError::SchemaError(format!(
+                "`{field_name}` is not a facet field.`"
+            )));
+        }
+        let Some(facet_column) = self.fast_fields().str(field_name)? else {
+            panic!("Facet Field `{field_name}` is missing. This should not happen");
+        };
+        Ok(FacetReader::new(facet_column))
+    }
+
+    /// Accessor to the segment's field norms readers container.
+    fn fieldnorms_readers(&self) -> &FieldNormReaders;
+
+    /// Accessor to the segment's [`StoreReader`](crate::store::StoreReader).
+    fn get_store_reader(&self, cache_num_blocks: usize) -> io::Result<StoreReader>;
+
+    /// Returns a field reader associated with the field given in argument.
+    fn inverted_index(&self, field: Field) -> crate::Result<ArcInvertedIndexReader>;
+
+    /// Returns the list of fields that have been indexed in the segment.
+    fn fields_metadata(&self) -> crate::Result<Vec<FieldMetadata>>;
+
+    /// Returns the segment id
+    fn segment_id(&self) -> SegmentId;
+
+    /// Returns the delete opstamp
+    fn delete_opstamp(&self) -> Option<Opstamp>;
+
+    /// Returns the bitset representing the alive `DocId`s.
+    fn alive_bitset(&self) -> Option<&AliveBitSet>;
+
+    /// Returns true if the `doc` is marked as deleted.
+    fn is_deleted(&self, doc: DocId) -> bool {
+        self.alive_bitset()
+            .map(|alive_bitset| alive_bitset.is_deleted(doc))
+            .unwrap_or(false)
+    }
+
+    /// Returns an iterator that will iterate over the alive document ids
+    fn doc_ids_alive(&self) -> Box<dyn Iterator<Item = DocId> + Send + '_> {
+        if let Some(alive_bitset) = &self.alive_bitset() {
+            Box::new(alive_bitset.iter_alive())
+        } else {
+            Box::new(0u32..self.max_doc())
+        }
+    }
+
+    /// Summarize total space usage of this segment.
+    fn space_usage(&self) -> io::Result<SegmentSpaceUsage>;
+}
+
+/// Convenient alias for an atomically reference counted segment reader handle.
+pub type ArcSegmentReader = Arc<dyn SegmentReader>;
+
 /// Entry point to access all of the datastructures of the `Segment`
 ///
 /// - term dictionary
@@ -29,8 +118,8 @@ use crate::{DocId, Opstamp};
 /// The segment reader has a very low memory footprint,
 /// as close to all of the memory data is mmapped.
 #[derive(Clone)]
-pub struct SegmentReader {
-    inv_idx_reader_cache: Arc<RwLock<HashMap<Field, Arc<InvertedIndexReader>>>>,
+pub struct TantivySegmentReader {
+    inv_idx_reader_cache: Arc<RwLock<HashMap<Field, ArcInvertedIndexReader>>>,
 
     segment_id: SegmentId,
     delete_opstamp: Option<Opstamp>,
@@ -49,98 +138,9 @@ pub struct SegmentReader {
     schema: Schema,
 }
 
-impl SegmentReader {
-    /// Returns the highest document id ever attributed in
-    /// this segment + 1.
-    pub fn max_doc(&self) -> DocId {
-        self.max_doc
-    }
-
-    /// Returns the number of alive documents.
-    /// Deleted documents are not counted.
-    pub fn num_docs(&self) -> DocId {
-        self.num_docs
-    }
-
-    /// Returns the schema of the index this segment belongs to.
-    pub fn schema(&self) -> &Schema {
-        &self.schema
-    }
-
-    /// Return the number of documents that have been
-    /// deleted in the segment.
-    pub fn num_deleted_docs(&self) -> DocId {
-        self.max_doc - self.num_docs
-    }
-
-    /// Returns true if some of the documents of the segment have been deleted.
-    pub fn has_deletes(&self) -> bool {
-        self.num_deleted_docs() > 0
-    }
-
-    /// Accessor to a segment's fast field reader given a field.
-    ///
-    /// Returns the u64 fast value reader if the field
-    /// is a u64 field indexed as "fast".
-    ///
-    /// Return a FastFieldNotAvailableError if the field is not
-    /// declared as a fast field in the schema.
-    ///
-    /// # Panics
-    /// May panic if the index is corrupted.
-    pub fn fast_fields(&self) -> &FastFieldReaders {
-        &self.fast_fields_readers
-    }
-
-    /// Accessor to the `FacetReader` associated with a given `Field`.
-    pub fn facet_reader(&self, field_name: &str) -> crate::Result<FacetReader> {
-        let schema = self.schema();
-        let field = schema.get_field(field_name)?;
-        let field_entry = schema.get_field_entry(field);
-        if field_entry.field_type().value_type() != Type::Facet {
-            return Err(crate::TantivyError::SchemaError(format!(
-                "`{field_name}` is not a facet field.`"
-            )));
-        }
-        let Some(facet_column) = self.fast_fields().str(field_name)? else {
-            panic!("Facet Field `{field_name}` is missing. This should not happen");
-        };
-        Ok(FacetReader::new(facet_column))
-    }
-
-    /// Accessor to the segment's `Field norms`'s reader.
-    ///
-    /// Field norms are the length (in tokens) of the fields.
-    /// It is used in the computation of the [TfIdf](https://fulmicoton.gitbooks.io/tantivy-doc/content/tfidf.html).
-    ///
-    /// They are simply stored as a fast field, serialized in
-    /// the `.fieldnorm` file of the segment.
-    pub fn get_fieldnorms_reader(&self, field: Field) -> crate::Result<FieldNormReader> {
-        self.fieldnorm_readers.get_field(field)?.ok_or_else(|| {
-            let field_name = self.schema.get_field_name(field);
-            let err_msg = format!(
-                "Field norm not found for field {field_name:?}. Was the field set to record norm \
-                 during indexing?"
-            );
-            crate::TantivyError::SchemaError(err_msg)
-        })
-    }
-
-    #[doc(hidden)]
-    pub fn fieldnorms_readers(&self) -> &FieldNormReaders {
-        &self.fieldnorm_readers
-    }
-
-    /// Accessor to the segment's [`StoreReader`](crate::store::StoreReader).
-    ///
-    /// `cache_num_blocks` sets the number of decompressed blocks to be cached in an LRU.
-    /// The size of blocks is configurable, this should be reflexted in the
-    pub fn get_store_reader(&self, cache_num_blocks: usize) -> io::Result<StoreReader> {
-        StoreReader::open(self.store_file.clone(), cache_num_blocks)
-    }
-
+impl TantivySegmentReader {
     /// Open a new segment for reading.
-    pub fn open(segment: &Segment) -> crate::Result<SegmentReader> {
+    pub fn open(segment: &Segment) -> crate::Result<TantivySegmentReader> {
         Self::open_with_custom_alive_set(segment, None)
     }
 
@@ -148,7 +148,7 @@ impl SegmentReader {
     pub fn open_with_custom_alive_set(
         segment: &Segment,
         custom_bitset: Option<AliveBitSet>,
-    ) -> crate::Result<SegmentReader> {
+    ) -> crate::Result<TantivySegmentReader> {
         let termdict_file = segment.open_read(SegmentComponent::Terms)?;
         let termdict_composite = CompositeFile::open(&termdict_file)?;
 
@@ -190,7 +190,7 @@ impl SegmentReader {
             .map(|alive_bitset| alive_bitset.num_alive_docs() as u32)
             .unwrap_or(max_doc);
 
-        Ok(SegmentReader {
+        Ok(TantivySegmentReader {
             inv_idx_reader_cache: Default::default(),
             num_docs,
             max_doc,
@@ -206,6 +206,52 @@ impl SegmentReader {
             schema,
         })
     }
+}
+
+impl SegmentReader for TantivySegmentReader {
+    /// Returns the highest document id ever attributed in
+    /// this segment + 1.
+    fn max_doc(&self) -> DocId {
+        self.max_doc
+    }
+
+    /// Returns the number of alive documents.
+    /// Deleted documents are not counted.
+    fn num_docs(&self) -> DocId {
+        self.num_docs
+    }
+
+    /// Returns the schema of the index this segment belongs to.
+    fn schema(&self) -> &Schema {
+        &self.schema
+    }
+
+    /// Accessor to a segment's fast field reader given a field.
+    ///
+    /// Returns the u64 fast value reader if the field
+    /// is a u64 field indexed as "fast".
+    ///
+    /// Return a FastFieldNotAvailableError if the field is not
+    /// declared as a fast field in the schema.
+    ///
+    /// # Panics
+    /// May panic if the index is corrupted.
+    fn fast_fields(&self) -> &FastFieldReaders {
+        &self.fast_fields_readers
+    }
+
+    #[doc(hidden)]
+    fn fieldnorms_readers(&self) -> &FieldNormReaders {
+        &self.fieldnorm_readers
+    }
+
+    /// Accessor to the segment's [`StoreReader`](crate::store::StoreReader).
+    ///
+    /// `cache_num_blocks` sets the number of decompressed blocks to be cached in an LRU.
+    /// The size of blocks is configurable, this should be reflexted in the
+    fn get_store_reader(&self, cache_num_blocks: usize) -> io::Result<StoreReader> {
+        StoreReader::open(self.store_file.clone(), cache_num_blocks)
+    }
 
     /// Returns a field reader associated with the field given in argument.
     /// If the field was not present in the index during indexing time,
@@ -219,7 +265,7 @@ impl SegmentReader {
     /// is returned.
     /// Similarly, if the field is marked as indexed but no term has been indexed for the given
     /// index, an empty `InvertedIndexReader` is returned (but no warning is logged).
-    pub fn inverted_index(&self, field: Field) -> crate::Result<Arc<InvertedIndexReader>> {
+    fn inverted_index(&self, field: Field) -> crate::Result<ArcInvertedIndexReader> {
         if let Some(inv_idx_reader) = self
             .inv_idx_reader_cache
             .read()
@@ -244,7 +290,7 @@ impl SegmentReader {
             //
             // Returns an empty inverted index.
             let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);
-            return Ok(Arc::new(InvertedIndexReader::empty(record_option)));
+            return Ok(Arc::new(TantivyInvertedIndexReader::empty(record_option)));
         }
 
         let record_option = record_option_opt.unwrap();
@@ -268,7 +314,7 @@ impl SegmentReader {
             DataCorruption::comment_only(error_msg)
         })?;
 
-        let inv_idx_reader = Arc::new(InvertedIndexReader::new(
+        let inv_idx_reader: ArcInvertedIndexReader = Arc::new(TantivyInvertedIndexReader::new(
             TermDictionary::open(termdict_file)?,
             postings_file,
             positions_file,
@@ -298,7 +344,7 @@ impl SegmentReader {
     /// Disclaimer: Some fields may not be listed here. For instance, if the schema contains a json
     /// field that is not indexed nor a fast field but is stored, it is possible for the field
     /// to not be listed.
-    pub fn fields_metadata(&self) -> crate::Result<Vec<FieldMetadata>> {
+    fn fields_metadata(&self) -> crate::Result<Vec<FieldMetadata>> {
         let mut indexed_fields: Vec<FieldMetadata> = Vec::new();
         let mut map_to_canonical = FnvHashMap::default();
         for (field, field_entry) in self.schema().fields() {
@@ -420,46 +466,29 @@ impl SegmentReader {
     }
 
     /// Returns the segment id
-    pub fn segment_id(&self) -> SegmentId {
+    fn segment_id(&self) -> SegmentId {
         self.segment_id
     }
 
     /// Returns the delete opstamp
-    pub fn delete_opstamp(&self) -> Option<Opstamp> {
+    fn delete_opstamp(&self) -> Option<Opstamp> {
         self.delete_opstamp
     }
 
     /// Returns the bitset representing the alive `DocId`s.
-    pub fn alive_bitset(&self) -> Option<&AliveBitSet> {
+    fn alive_bitset(&self) -> Option<&AliveBitSet> {
         self.alive_bitset_opt.as_ref()
     }
 
-    /// Returns true if the `doc` is marked
-    /// as deleted.
-    pub fn is_deleted(&self, doc: DocId) -> bool {
-        self.alive_bitset()
-            .map(|alive_bitset| alive_bitset.is_deleted(doc))
-            .unwrap_or(false)
-    }
-
-    /// Returns an iterator that will iterate over the alive document ids
-    pub fn doc_ids_alive(&self) -> Box<dyn Iterator<Item = DocId> + Send + '_> {
-        if let Some(alive_bitset) = &self.alive_bitset_opt {
-            Box::new(alive_bitset.iter_alive())
-        } else {
-            Box::new(0u32..self.max_doc)
-        }
-    }
-
     /// Summarize total space usage of this segment.
-    pub fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
+    fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
         Ok(SegmentSpaceUsage::new(
             self.num_docs(),
-            self.termdict_composite.space_usage(),
-            self.postings_composite.space_usage(),
-            self.positions_composite.space_usage(),
-            self.fast_fields_readers.space_usage(self.schema())?,
-            self.fieldnorm_readers.space_usage(),
+            self.termdict_composite.space_usage(self.schema()),
+            self.postings_composite.space_usage(self.schema()),
+            self.positions_composite.space_usage(self.schema()),
+            self.fast_fields_readers.space_usage()?,
+            self.fieldnorm_readers.space_usage(self.schema()),
             self.get_store_reader(0)?.space_usage(),
             self.alive_bitset_opt
                 .as_ref()
@@ -576,7 +605,7 @@ fn intersect_alive_bitset(
     }
 }
 
-impl fmt::Debug for SegmentReader {
+impl fmt::Debug for TantivySegmentReader {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         write!(f, "SegmentReader({:?})", self.segment_id)
     }

src/indexer/delete_queue.rs

@@ -4,38 +4,37 @@ use std::sync::{Arc, RwLock, Weak};
 use super::operation::DeleteOperation;
 use crate::Opstamp;
 
-// The DeleteQueue is similar in conceptually to a multiple
-// consumer single producer broadcast channel.
-//
-// All consumer will receive all messages.
-//
-// Consumer of the delete queue are holding a `DeleteCursor`,
-// which points to a specific place of the `DeleteQueue`.
-//
-// New consumer can be created in two ways
-// - calling `delete_queue.cursor()` returns a cursor, that will include all future delete operation
-//   (and some or none of the past operations... The client is in charge of checking the opstamps.).
-// - cloning an existing cursor returns a new cursor, that is at the exact same position, and can
-//   now advance independently from the original cursor.
+/// The DeleteQueue is similar in conceptually to a multiple
+/// consumer single producer broadcast channel.
+///
+/// All consumer will receive all messages.
+///
+/// Consumer of the delete queue are holding a `DeleteCursor`,
+/// which points to a specific place of the `DeleteQueue`.
+///
+/// New consumer can be created in two ways
+/// - calling `delete_queue.cursor()` returns a cursor, that will include all future delete
+///   operation (and some or none of the past operations... The client is in charge of checking the
+///   opstamps.).
+/// - cloning an existing cursor returns a new cursor, that is at the exact same position, and can
+///   now advance independently from the original cursor.
 #[derive(Default)]
 struct InnerDeleteQueue {
     writer: Vec<DeleteOperation>,
     last_block: Weak<Block>,
 }
 
-#[derive(Clone)]
+/// The delete queue is a linked list storing delete operations.
+///
+/// Several consumers can hold a reference to it. Delete operations
+/// get dropped/gc'ed when no more consumers are holding a reference
+/// to them.
+#[derive(Clone, Default)]
 pub struct DeleteQueue {
     inner: Arc<RwLock<InnerDeleteQueue>>,
 }
 
 impl DeleteQueue {
-    // Creates a new delete queue.
-    pub fn new() -> DeleteQueue {
-        DeleteQueue {
-            inner: Arc::default(),
-        }
-    }
-
     fn get_last_block(&self) -> Arc<Block> {
         {
             // try get the last block with simply acquiring the read lock.
@@ -58,10 +57,10 @@ impl DeleteQueue {
         block
     }
 
-    // Creates a new cursor that makes it possible to
-    // consume future delete operations.
-    //
-    // Past delete operations are not accessible.
+    /// Creates a new cursor that makes it possible to
+    /// consume future delete operations.
+    ///
+    /// Past delete operations are not accessible.
     pub fn cursor(&self) -> DeleteCursor {
         let last_block = self.get_last_block();
         let operations_len = last_block.operations.len();
@@ -71,7 +70,7 @@ impl DeleteQueue {
         }
     }
 
-    // Appends a new delete operations.
+    /// Appends a new delete operations.
     pub fn push(&self, delete_operation: DeleteOperation) {
         self.inner
             .write()
@@ -169,6 +168,7 @@ struct Block {
     next: NextBlock,
 }
 
+/// As we process delete operations, keeps track of our position.
 #[derive(Clone)]
 pub struct DeleteCursor {
     block: Arc<Block>,
@@ -250,18 +250,22 @@ mod tests {
 
     struct DummyWeight;
     impl Weight for DummyWeight {
-        fn scorer(&self, _reader: &SegmentReader, _boost: Score) -> crate::Result<Box<dyn Scorer>> {
+        fn scorer(
+            &self,
+            _reader: &dyn SegmentReader,
+            _boost: Score,
+        ) -> crate::Result<Box<dyn Scorer>> {
             Err(crate::TantivyError::InternalError("dummy impl".to_owned()))
         }
 
-        fn explain(&self, _reader: &SegmentReader, _doc: DocId) -> crate::Result<Explanation> {
+        fn explain(&self, _reader: &dyn SegmentReader, _doc: DocId) -> crate::Result<Explanation> {
             Err(crate::TantivyError::InternalError("dummy impl".to_owned()))
         }
     }
 
     #[test]
     fn test_deletequeue() {
-        let delete_queue = DeleteQueue::new();
+        let delete_queue = DeleteQueue::default();
 
         let make_op = |i: usize| DeleteOperation {
             opstamp: i as u64,

src/indexer/index_writer.rs

@@ -12,7 +12,9 @@ use super::{AddBatch, AddBatchReceiver, AddBatchSender, PreparedCommit};
 use crate::directory::{DirectoryLock, GarbageCollectionResult, TerminatingWrite};
 use crate::error::TantivyError;
 use crate::fastfield::write_alive_bitset;
-use crate::index::{Index, Segment, SegmentComponent, SegmentId, SegmentMeta, SegmentReader};
+use crate::index::{
+    Index, Segment, SegmentComponent, SegmentId, SegmentMeta, SegmentReader, TantivySegmentReader,
+};
 use crate::indexer::delete_queue::{DeleteCursor, DeleteQueue};
 use crate::indexer::doc_opstamp_mapping::DocToOpstampMapping;
 use crate::indexer::index_writer_status::IndexWriterStatus;
@@ -94,7 +96,7 @@ pub struct IndexWriter<D: Document = TantivyDocument> {
 
 fn compute_deleted_bitset(
     alive_bitset: &mut BitSet,
-    segment_reader: &SegmentReader,
+    segment_reader: &dyn SegmentReader,
     delete_cursor: &mut DeleteCursor,
     doc_opstamps: &DocToOpstampMapping,
     target_opstamp: Opstamp,
@@ -128,7 +130,7 @@ fn compute_deleted_bitset(
 /// is `==` target_opstamp.
 /// For instance, there was no delete operation between the state of the `segment_entry` and
 /// the `target_opstamp`, `segment_entry` is not updated.
-pub(crate) fn advance_deletes(
+pub fn advance_deletes(
     mut segment: Segment,
     segment_entry: &mut SegmentEntry,
     target_opstamp: Opstamp,
@@ -143,7 +145,7 @@ pub(crate) fn advance_deletes(
         return Ok(());
     }
 
-    let segment_reader = SegmentReader::open(&segment)?;
+    let segment_reader = TantivySegmentReader::open(&segment)?;
 
     let max_doc = segment_reader.max_doc();
     let mut alive_bitset: BitSet = match segment_entry.alive_bitset() {
@@ -243,7 +245,7 @@ fn apply_deletes(
         .max()
         .expect("Empty DocOpstamp is forbidden");
 
-    let segment_reader = SegmentReader::open(segment)?;
+    let segment_reader = TantivySegmentReader::open(segment)?;
     let doc_to_opstamps = DocToOpstampMapping::WithMap(doc_opstamps);
 
     let max_doc = segment.meta().max_doc();
@@ -303,7 +305,7 @@ impl<D: Document> IndexWriter<D> {
         let (document_sender, document_receiver) =
             crossbeam_channel::bounded(PIPELINE_MAX_SIZE_IN_DOCS);
 
-        let delete_queue = DeleteQueue::new();
+        let delete_queue = DeleteQueue::default();
 
         let current_opstamp = index.load_metas()?.opstamp;
 

src/indexer/indexing_term.rs

@@ -3,21 +3,21 @@ use std::net::Ipv6Addr;
 use columnar::MonotonicallyMappableToU128;
 
 use crate::fastfield::FastValue;
-use crate::schema::{Field, Type};
+use crate::schema::Field;
 
-/// Term represents the value that the token can take.
-/// It's a serialized representation over different types.
+/// IndexingTerm is used to represent a term during indexing.
+/// It's a serialized representation over field and value.
 ///
-/// It actually wraps a `Vec<u8>`. The first 5 bytes are metadata.
-/// 4 bytes are the field id, and the last byte is the type.
+/// It actually wraps a `Vec<u8>`. The first 4 bytes are the field.
 ///
-/// The serialized value `ValueBytes` is considered everything after the 4 first bytes (term id).
+/// We serialize the field, because we index everything in a single
+/// global term dictionary during indexing.
 #[derive(Clone)]
 pub(crate) struct IndexingTerm<B = Vec<u8>>(B)
 where B: AsRef<[u8]>;
 
 /// The number of bytes used as metadata by `Term`.
-const TERM_METADATA_LENGTH: usize = 5;
+const TERM_METADATA_LENGTH: usize = 4;
 
 impl IndexingTerm {
     /// Create a new Term with a buffer with a given capacity.
@@ -31,10 +31,9 @@ impl IndexingTerm {
     /// Use `clear_with_field_and_type` in that case.
     ///
     /// Sets field and the type.
-    pub(crate) fn set_field_and_type(&mut self, field: Field, typ: Type) {
+    pub(crate) fn set_field(&mut self, field: Field) {
         assert!(self.is_empty());
         self.0[0..4].clone_from_slice(field.field_id().to_be_bytes().as_ref());
-        self.0[4] = typ.to_code();
     }
 
     /// Is empty if there are no value bytes.
@@ -42,10 +41,10 @@ impl IndexingTerm {
         self.0.len() == TERM_METADATA_LENGTH
     }
 
-    /// Removes the value_bytes and set the field and type code.
-    pub(crate) fn clear_with_field_and_type(&mut self, typ: Type, field: Field) {
+    /// Removes the value_bytes and set the field
+    pub(crate) fn clear_with_field(&mut self, field: Field) {
         self.truncate_value_bytes(0);
-        self.set_field_and_type(field, typ);
+        self.set_field(field);
     }
 
     /// Sets a u64 value in the term.
@@ -122,6 +121,23 @@ impl IndexingTerm {
 impl<B> IndexingTerm<B>
 where B: AsRef<[u8]>
 {
+    /// Wraps serialized term bytes.
+    ///
+    /// The input buffer is expected to be the concatenation of the big endian encoded field id
+    /// followed by the serialized value bytes (type tag + payload).
+    #[inline]
+    pub fn wrap(serialized_term: B) -> IndexingTerm<B> {
+        debug_assert!(serialized_term.as_ref().len() >= TERM_METADATA_LENGTH);
+        IndexingTerm(serialized_term)
+    }
+
+    /// Returns the field this term belongs to.
+    #[inline]
+    pub fn field(&self) -> Field {
+        let field_id_bytes: [u8; 4] = self.0.as_ref()[..4].try_into().unwrap();
+        Field::from_field_id(u32::from_be_bytes(field_id_bytes))
+    }
+
     /// Returns the serialized representation of Term.
     /// This includes field_id, value type and value.
     ///
@@ -136,6 +152,7 @@ where B: AsRef<[u8]>
 #[cfg(test)]
 mod tests {
 
+    use super::IndexingTerm;
     use crate::schema::*;
 
     #[test]
@@ -143,42 +160,55 @@ mod tests {
         let mut schema_builder = Schema::builder();
         schema_builder.add_text_field("text", STRING);
         let title_field = schema_builder.add_text_field("title", STRING);
-        let term = Term::from_field_text(title_field, "test");
+        let mut term = IndexingTerm::with_capacity(0);
+        term.set_field(title_field);
+        term.set_bytes(b"test");
         assert_eq!(term.field(), title_field);
-        assert_eq!(term.typ(), Type::Str);
-        assert_eq!(term.value().as_str(), Some("test"))
+        assert_eq!(term.serialized_term(), b"\x00\x00\x00\x01test".to_vec())
     }
 
     /// Size (in bytes) of the buffer of a fast value (u64, i64, f64, or date) term.
     /// <field> + <type byte> + <value len>
     ///
     /// - <field> is a big endian encoded u32 field id
-    /// - <type_byte>'s most significant bit expresses whether the term is a json term or not The
-    ///   remaining 7 bits are used to encode the type of the value. If this is a JSON term, the
-    ///   type is the type of the leaf of the json.
     /// - <value> is,  if this is not the json term, a binary representation specific to the type.
     ///   If it is a JSON Term, then it is prepended with the path that leads to this leaf value.
-    const FAST_VALUE_TERM_LEN: usize = 4 + 1 + 8;
+    const FAST_VALUE_TERM_LEN: usize = 4 + 8;
 
     #[test]
     pub fn test_term_u64() {
         let mut schema_builder = Schema::builder();
         let count_field = schema_builder.add_u64_field("count", INDEXED);
-        let term = Term::from_field_u64(count_field, 983u64);
+        let mut term = IndexingTerm::with_capacity(0);
+        term.set_field(count_field);
+        term.set_u64(983u64);
         assert_eq!(term.field(), count_field);
-        assert_eq!(term.typ(), Type::U64);
         assert_eq!(term.serialized_term().len(), FAST_VALUE_TERM_LEN);
-        assert_eq!(term.value().as_u64(), Some(983u64))
     }
 
     #[test]
     pub fn test_term_bool() {
         let mut schema_builder = Schema::builder();
         let bool_field = schema_builder.add_bool_field("bool", INDEXED);
-        let term = Term::from_field_bool(bool_field, true);
+        let term = {
+            let mut term = IndexingTerm::with_capacity(0);
+            term.set_field(bool_field);
+            term.set_bool(true);
+            term
+        };
         assert_eq!(term.field(), bool_field);
-        assert_eq!(term.typ(), Type::Bool);
         assert_eq!(term.serialized_term().len(), FAST_VALUE_TERM_LEN);
-        assert_eq!(term.value().as_bool(), Some(true))
+    }
+
+    #[test]
+    pub fn indexing_term_wrap_extracts_field() {
+        let field = Field::from_field_id(7u32);
+        let mut term = IndexingTerm::with_capacity(0);
+        term.set_field(field);
+        term.append_bytes(b"abc");
+
+        let wrapped = IndexingTerm::wrap(term.serialized_term());
+        assert_eq!(wrapped.field(), field);
+        assert_eq!(wrapped.serialized_term(), term.serialized_term());
     }
 }

src/indexer/merger.rs

@@ -1,5 +1,3 @@
-use std::sync::Arc;
-
 use columnar::{
     ColumnType, ColumnarReader, MergeRowOrder, RowAddr, ShuffleMergeOrder, StackMergeOrder,
 };
@@ -12,14 +10,14 @@ use crate::docset::{DocSet, TERMINATED};
 use crate::error::DataCorruption;
 use crate::fastfield::AliveBitSet;
 use crate::fieldnorm::{FieldNormReader, FieldNormReaders, FieldNormsSerializer, FieldNormsWriter};
-use crate::index::{Segment, SegmentComponent, SegmentReader};
+use crate::index::{Segment, SegmentComponent, SegmentReader, TantivySegmentReader};
 use crate::indexer::doc_id_mapping::{MappingType, SegmentDocIdMapping};
 use crate::indexer::SegmentSerializer;
 use crate::postings::{InvertedIndexSerializer, Postings, SegmentPostings};
 use crate::schema::{value_type_to_column_type, Field, FieldType, Schema};
 use crate::store::StoreWriter;
 use crate::termdict::{TermMerger, TermOrdinal};
-use crate::{DocAddress, DocId, InvertedIndexReader};
+use crate::{ArcInvertedIndexReader, DocAddress, DocId};
 
 /// Segment's max doc must be `< MAX_DOC_LIMIT`.
 ///
@@ -27,7 +25,7 @@ use crate::{DocAddress, DocId, InvertedIndexReader};
 pub const MAX_DOC_LIMIT: u32 = 1 << 31;
 
 fn estimate_total_num_tokens_in_single_segment(
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     field: Field,
 ) -> crate::Result<u64> {
     // There are no deletes. We can simply use the exact value saved into the posting list.
@@ -68,7 +66,7 @@ fn estimate_total_num_tokens_in_single_segment(
     Ok((segment_num_tokens as f64 * ratio) as u64)
 }
 
-fn estimate_total_num_tokens(readers: &[SegmentReader], field: Field) -> crate::Result<u64> {
+fn estimate_total_num_tokens(readers: &[TantivySegmentReader], field: Field) -> crate::Result<u64> {
     let mut total_num_tokens: u64 = 0;
     for reader in readers {
         total_num_tokens += estimate_total_num_tokens_in_single_segment(reader, field)?;
@@ -78,7 +76,7 @@ fn estimate_total_num_tokens(readers: &[SegmentReader], field: Field) -> crate::
 
 pub struct IndexMerger {
     schema: Schema,
-    pub(crate) readers: Vec<SegmentReader>,
+    pub(crate) readers: Vec<TantivySegmentReader>,
     max_doc: u32,
 }
 
@@ -170,8 +168,10 @@ impl IndexMerger {
         let mut readers = vec![];
         for (segment, new_alive_bitset_opt) in segments.iter().zip(alive_bitset_opt) {
             if segment.meta().num_docs() > 0 {
-                let reader =
-                    SegmentReader::open_with_custom_alive_set(segment, new_alive_bitset_opt)?;
+                let reader = TantivySegmentReader::open_with_custom_alive_set(
+                    segment,
+                    new_alive_bitset_opt,
+                )?;
                 readers.push(reader);
             }
         }
@@ -204,8 +204,20 @@ impl IndexMerger {
             let fieldnorms_readers: Vec<FieldNormReader> = self
                 .readers
                 .iter()
-                .map(|reader| reader.get_fieldnorms_reader(field))
-                .collect::<Result<_, _>>()?;
+                .map(|reader| {
+                    reader
+                        .fieldnorms_readers()
+                        .get_field(field)?
+                        .ok_or_else(|| {
+                            let field_name = self.schema.get_field_name(field);
+                            let err_msg = format!(
+                                "Field norm not found for field {field_name:?}. Was the field set \
+                                 to record norm during indexing?"
+                            );
+                            crate::TantivyError::SchemaError(err_msg)
+                        })
+                })
+                .collect::<crate::Result<_>>()?;
             for old_doc_addr in doc_id_mapping.iter_old_doc_addrs() {
                 let fieldnorms_reader = &fieldnorms_readers[old_doc_addr.segment_ord as usize];
                 let fieldnorm_id = fieldnorms_reader.fieldnorm_id(old_doc_addr.doc_id);
@@ -262,7 +274,7 @@ impl IndexMerger {
                 }),
         );
 
-        let has_deletes: bool = self.readers.iter().any(SegmentReader::has_deletes);
+        let has_deletes: bool = self.readers.iter().any(|reader| reader.has_deletes());
         let mapping_type = if has_deletes {
             MappingType::StackedWithDeletes
         } else {
@@ -297,7 +309,7 @@ impl IndexMerger {
 
         let mut max_term_ords: Vec<TermOrdinal> = Vec::new();
 
-        let field_readers: Vec<Arc<InvertedIndexReader>> = self
+        let field_readers: Vec<ArcInvertedIndexReader> = self
             .readers
             .iter()
             .map(|reader| reader.inverted_index(indexed_field))
@@ -366,7 +378,7 @@ impl IndexMerger {
             // Let's compute the list of non-empty posting lists
             for (segment_ord, term_info) in merged_terms.current_segment_ords_and_term_infos() {
                 let segment_reader = &self.readers[segment_ord];
-                let inverted_index: &InvertedIndexReader = &field_readers[segment_ord];
+                let inverted_index = field_readers[segment_ord].as_ref();
                 let segment_postings = inverted_index
                     .read_postings_from_terminfo(&term_info, segment_postings_option)?;
                 let alive_bitset_opt = segment_reader.alive_bitset();
@@ -1534,7 +1546,7 @@ mod tests {
         for segment_reader in searcher.segment_readers() {
             let mut term_scorer = term_query
                 .specialized_weight(EnableScoring::enabled_from_searcher(&searcher))?
-                .term_scorer_for_test(segment_reader, 1.0)?
+                .term_scorer_for_test(segment_reader.as_ref(), 1.0)?
                 .unwrap();
             // the difference compared to before is intrinsic to the bm25 formula. no worries
             // there.

src/indexer/mod.rs

@@ -4,6 +4,7 @@
 //! `IndexWriter` is the main entry point for that, which created from
 //! [`Index::writer`](crate::Index::writer).
 
+/// Delete queue implementation for broadcasting delete operations to consumers.
 pub(crate) mod delete_queue;
 pub(crate) mod path_to_unordered_id;
 
@@ -32,12 +33,11 @@ mod stamper;
 use crossbeam_channel as channel;
 use smallvec::SmallVec;
 
-pub use self::index_writer::{IndexWriter, IndexWriterOptions};
+pub use self::index_writer::{advance_deletes, IndexWriter, IndexWriterOptions};
 pub use self::log_merge_policy::LogMergePolicy;
 pub use self::merge_operation::MergeOperation;
 pub use self::merge_policy::{MergeCandidate, MergePolicy, NoMergePolicy};
-use self::operation::AddOperation;
-pub use self::operation::UserOperation;
+pub use self::operation::{AddOperation, DeleteOperation, UserOperation};
 pub use self::prepared_commit::PreparedCommit;
 pub use self::segment_entry::SegmentEntry;
 pub(crate) use self::segment_serializer::SegmentSerializer;