introducing tantivy codec

Removes the Write generics argument in PostingsSerializer.
This removes useless generic.
Prepares the path for codecs.
Removes one useless CountingWrite layer.
etc.

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 = "0.12", default-features = false, optional = true }
+lz4_flex = { version = "0.11", 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"
@@ -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 = "0.16.3"
+lru = "0.12.0"
 fastdivide = "0.4.0"
 itertools = "0.14.0"
 measure_time = "0.9.0"
@@ -76,7 +76,7 @@ winapi = "0.3.9"
 
 [dev-dependencies]
 binggan = "0.14.2"
-rand = "0.9"
+rand = "0.8.5"
 maplit = "1.0.2"
 matches = "0.1.9"
 pretty_assertions = "1.2.1"
@@ -85,7 +85,7 @@ test-log = "0.2.10"
 futures = "0.3.21"
 paste = "1.0.11"
 more-asserts = "0.3.1"
-rand_distr = "0.5"
+rand_distr = "0.4.3"
 time = { version = "0.3.10", features = ["serde-well-known", "macros"] }
 postcard = { version = "1.0.4", features = [
     "use-std",
@@ -189,7 +189,3 @@ harness = false
 [[bench]]
 name = "bool_queries_with_range"
 harness = false
-
-[[bench]]
-name = "str_search_and_get"
-harness = false

benches/agg_bench.rs

@@ -1,8 +1,8 @@
 use binggan::plugins::PeakMemAllocPlugin;
 use binggan::{black_box, InputGroup, PeakMemAlloc, INSTRUMENTED_SYSTEM};
-use rand::distr::weighted::WeightedIndex;
+use rand::distributions::WeightedIndex;
+use rand::prelude::SliceRandom;
 use rand::rngs::StdRng;
-use rand::seq::IndexedRandom;
 use rand::{Rng, SeedableRng};
 use rand_distr::Distribution;
 use serde_json::json;
@@ -532,7 +532,7 @@ fn get_test_index_bench(cardinality: Cardinality) -> tantivy::Result<Index> {
     // 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 zipf_1000 = rand_distr::Zipf::new(1000, 1.1f64).unwrap();
 
     {
         let mut rng = StdRng::from_seed([1u8; 32]);
@@ -576,8 +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.random_range(0.0..1_000_000.0);
-            let json = if rng.random_bool(0.1) {
+            let val: f64 = rng.gen_range(0.0..1_000_000.0);
+            let json = if rng.gen_bool(0.1) {
                 // 10% are numeric values
                 json!({ "mixed_type": val })
             } else {
@@ -586,7 +586,7 @@ 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_all_unique_terms => format!("unique_term_{}", rng.gen::<u64>()),
                 text_field_many_terms => many_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(),

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.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 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 mut title_tokens: Vec<&str> = Vec::new();
             let mut body_tokens: Vec<&str> = Vec::new();
             if has_a {
-                if rng.random_bool(0.1) {
+                if rng.gen_bool(0.1) {
                     title_tokens.push("a");
                 } else {
                     body_tokens.push("a");
                 }
             }
             if has_b {
-                if rng.random_bool(0.1) {
+                if rng.gen_bool(0.1) {
                     title_tokens.push("b");
                 } else {
                     body_tokens.push("b");
                 }
             }
             if has_c {
-                if rng.random_bool(0.1) {
+                if rng.gen_bool(0.1) {
                     title_tokens.push("c");
                 } else {
                     body_tokens.push("c");

benches/bool_queries_with_range.rs

@@ -36,13 +36,13 @@ fn build_shared_indices(num_docs: usize, p_title_a: f32, distribution: &str) ->
             "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) {
+                    let title_token = if rng.gen_bool(p_title_a as f64) {
                         "a"
                     } else {
                         "b"
                     };
 
-                    let num_rand = rng.random_range(0u64..1000u64);
+                    let num_rand = rng.gen_range(0u64..1000u64);
 
                     let num_asc = (doc_id / 10000) as u64;
 
@@ -60,13 +60,13 @@ fn build_shared_indices(num_docs: usize, p_title_a: f32, distribution: &str) ->
             "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) {
+                    let title_token = if rng.gen_bool(p_title_a as f64) {
                         "a"
                     } else {
                         "b"
                     };
 
-                    let num_rand = rng.random_range(0u64..10000000u64);
+                    let num_rand = rng.gen_range(0u64..10000000u64);
 
                     let num_asc = doc_id as u64;
 

benches/range_queries.rs

@@ -33,7 +33,7 @@ fn build_shared_indices(num_docs: usize, distribution: &str) -> BenchIndex {
         match distribution {
             "dense" => {
                 for doc_id in 0..num_docs {
-                    let num_rand = rng.random_range(0u64..1000u64);
+                    let num_rand = rng.gen_range(0u64..1000u64);
                     let num_asc = (doc_id / 10000) as u64;
 
                     writer
@@ -46,7 +46,7 @@ fn build_shared_indices(num_docs: usize, distribution: &str) -> BenchIndex {
             }
             "sparse" => {
                 for doc_id in 0..num_docs {
-                    let num_rand = rng.random_range(0u64..10000000u64);
+                    let num_rand = rng.gen_range(0u64..10000000u64);
                     let num_asc = doc_id as u64;
 
                     writer

benches/range_query.rs

@@ -97,20 +97,20 @@ fn get_index_0_to_100() -> Index {
     let num_vals = 100_000;
     let docs: Vec<_> = (0..num_vals)
         .map(|_i| {
-            let id_name = if rng.random_bool(0.01) {
+            let id_name = if rng.gen_bool(0.01) {
                 "veryfew".to_string() // 1%
-            } else if rng.random_bool(0.1) {
+            } else if rng.gen_bool(0.1) {
                 "few".to_string() // 9%
             } else {
                 "most".to_string() // 90%
             };
             Doc {
                 id_name,
-                id: rng.random_range(0..100),
+                id: rng.gen_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),
+                ip: Ipv6Addr::from_u128(rng.gen_range(0..100) * 1000),
             }
         })
         .collect();

benches/str_search_and_get.rs

@@ -1,421 +0,0 @@
-// 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 = "0.9"
+rand = "0.8"
 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 rng(), 100_000);
+        let idxs: Vec<u32> = (0..num_els).choose_multiple(&mut thread_rng(), 100_000);
         b.iter(|| {
             let mut out = 0u64;
             for &idx in &idxs {

columnar/Cargo.toml

@@ -22,7 +22,7 @@ downcast-rs = "2.0.1"
 [dev-dependencies]
 proptest = "1"
 more-asserts = "0.3.1"
-rand = "0.9"
+rand = "0.8"
 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.random::<u8>() as u64)
+        .map(|num| num + rng.r#gen::<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.random::<u8>() as u64)
+        .map(|num| num + rng.r#gen::<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.random_bool(fill_ratio))
+        .map(|_| rng.gen_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.random_range(avg_step_size - avg_deviation..=avg_step_size + avg_deviation);
+        current += rng.gen_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.random_range(1..=100);
+        let val = rng.gen_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.random_range(1..=100);
+        let val = rng.gen_range(1..=100);
         data.push(val);
     }
     data.push(SINGLE_ITEM);

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::rng();
+        let mut rng = rand::thread_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::rng().random_range(0..=vals.len() - 1);
+        let test_rand_idx = rand::thread_rng().gen_range(0..=vals.len() - 1);
         let expected_positions: Vec<u32> = vals
             .iter()
             .enumerate()

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 = "0.9"
+rand = "0.8.4"
 

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 rng(), 100_000);
+    let vals: Vec<u32> = (0..20_000).choose_multiple(&mut thread_rng(), 100_000);
     runner.bench_function("bench_vint_rand", move |_| {
         let mut out = 0u64;
         for val in vals.iter().cloned() {

common/src/bitset.rs

@@ -178,13 +178,11 @@ impl TinySet {
 #[derive(Clone)]
 pub struct BitSet {
     tinysets: Box<[TinySet]>,
-    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()
     }
@@ -212,7 +210,6 @@ impl BitSet {
         let tinybitsets = vec![TinySet::empty(); num_buckets as usize].into_boxed_slice();
         BitSet {
             tinysets: tinybitsets,
-            len: 0,
             max_value,
         }
     }
@@ -230,7 +227,6 @@ impl BitSet {
         }
         BitSet {
             tinysets: tinybitsets,
-            len: max_value as u64,
             max_value,
         }
     }
@@ -249,17 +245,19 @@ impl BitSet {
 
     /// Intersect with tinysets
     fn intersect_update_with_iter(&mut self, other: impl Iterator<Item = TinySet>) {
-        self.len = 0;
         for (left, right) in self.tinysets.iter_mut().zip(other) {
             *left = left.intersect(right);
-            self.len += left.len() as u64;
         }
     }
 
     /// Returns the number of elements in the `BitSet`.
     #[inline]
     pub fn len(&self) -> usize {
-        self.len as usize
+        self.tinysets
+            .iter()
+            .copied()
+            .map(|tinyset| tinyset.len())
+            .sum::<u32>() as usize
     }
 
     /// Inserts an element in the `BitSet`
@@ -268,7 +266,7 @@ impl BitSet {
         // we do not check saturated els.
         let higher = el / 64u32;
         let lower = el % 64u32;
-        self.len += u64::from(self.tinysets[higher as usize].insert_mut(lower));
+        self.tinysets[higher as usize].insert_mut(lower);
     }
 
     /// Inserts an element in the `BitSet`
@@ -277,7 +275,7 @@ impl BitSet {
         // we do not check saturated els.
         let higher = el / 64u32;
         let lower = el % 64u32;
-        self.len -= u64::from(self.tinysets[higher as usize].remove_mut(lower));
+        self.tinysets[higher as usize].remove_mut(lower);
     }
 
     /// Returns true iff the elements is in the `BitSet`.
@@ -416,7 +414,7 @@ mod tests {
     use std::collections::HashSet;
 
     use ownedbytes::OwnedBytes;
-    use rand::distr::Bernoulli;
+    use rand::distributions::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: &dyn SegmentReader,
+        segment_reader: &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: &dyn SegmentReader| {
+            TopDocs::with_limit(2).tweak_score(move |segment_reader: &SegmentReader| {
                 let ingredient_reader = segment_reader.facet_reader("ingredient").unwrap();
                 let facet_dict = ingredient_reader.facet_dict();
 

examples/iterating_docs_and_positions.rs

@@ -91,46 +91,10 @@ fn main() -> tantivy::Result<()> {
         }
     }
 
-    // A `Term` is a text token associated with a field.
-    // Let's go through all docs containing the term `title:the` and access their position
-    let term_the = Term::from_field_text(title, "the");
-
-    // Some other powerful operations (especially `.skip_to`) may be useful to consume these
+    // Some other powerful operations (especially `.seek`) may be useful to consume these
     // posting lists rapidly.
     // You can check for them in the [`DocSet`](https://docs.rs/tantivy/~0/tantivy/trait.DocSet.html) trait
     // and the [`Postings`](https://docs.rs/tantivy/~0/tantivy/trait.Postings.html) trait
 
-    // Also, for some VERY specific high performance use case like an OLAP analysis of logs,
-    // you can get better performance by accessing directly the blocks of doc ids.
-    for segment_reader in searcher.segment_readers() {
-        // A segment contains different data structure.
-        // Inverted index stands for the combination of
-        // - the term dictionary
-        // - the inverted lists associated with each terms and their positions
-        let inverted_index = segment_reader.inverted_index(title)?;
-
-        // This segment posting object is like a cursor over the documents matching the term.
-        // The `IndexRecordOption` arguments tells tantivy we will be interested in both term
-        // frequencies and positions.
-        //
-        // If you don't need all this information, you may get better performance by decompressing
-        // less information.
-        if let Some(mut block_segment_postings) =
-            inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)?
-        {
-            loop {
-                let docs = block_segment_postings.docs();
-                if docs.is_empty() {
-                    break;
-                }
-                // Once again these docs MAY contains deleted documents as well.
-                let docs = block_segment_postings.docs();
-                // Prints `Docs [0, 2].`
-                println!("Docs {docs:?}");
-                block_segment_postings.advance();
-            }
-        }
-    }
-
     Ok(())
 }

examples/warmer.rs

@@ -43,7 +43,7 @@ impl DynamicPriceColumn {
         }
     }
 
-    pub fn price_for_segment(&self, segment_reader: &dyn SegmentReader) -> Option<Arc<Vec<Price>>> {
+    pub fn price_for_segment(&self, segment_reader: &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: &dyn SegmentReader| {
+    let score_by_price = move |segment_reader: &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: &dyn SegmentReader,
+    reader: &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: &dyn SegmentReader,
+    reader: &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: &dyn SegmentReader,
+    reader: &SegmentReader,
     field_name: &str,
     allowed_column_types: Option<&[ColumnType]>,
     fallback_type: ColumnType,

src/aggregation/agg_data.rs

@@ -469,7 +469,7 @@ impl AggKind {
 /// Build AggregationsData by walking the request tree.
 pub(crate) fn build_aggregations_data_from_req(
     aggs: &Aggregations,
-    reader: &dyn SegmentReader,
+    reader: &SegmentReader,
     segment_ordinal: SegmentOrdinal,
     context: AggContextParams,
 ) -> crate::Result<AggregationsSegmentCtx> {
@@ -489,7 +489,7 @@ pub(crate) fn build_aggregations_data_from_req(
 fn build_nodes(
     agg_name: &str,
     req: &Aggregation,
-    reader: &dyn SegmentReader,
+    reader: &SegmentReader,
     segment_ordinal: SegmentOrdinal,
     data: &mut AggregationsSegmentCtx,
     is_top_level: bool,
@@ -728,6 +728,7 @@ 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,
@@ -744,7 +745,7 @@ fn build_nodes(
 
 fn build_children(
     aggs: &Aggregations,
-    reader: &dyn SegmentReader,
+    reader: &SegmentReader,
     segment_ordinal: SegmentOrdinal,
     data: &mut AggregationsSegmentCtx,
 ) -> crate::Result<Vec<AggRefNode>> {
@@ -763,7 +764,7 @@ fn build_children(
 }
 
 fn get_term_agg_accessors(
-    reader: &dyn SegmentReader,
+    reader: &SegmentReader,
     field_name: &str,
     missing: &Option<Key>,
 ) -> crate::Result<Vec<(Column<u64>, ColumnType)>> {
@@ -816,7 +817,7 @@ fn build_terms_or_cardinality_nodes(
     agg_name: &str,
     field_name: &str,
     missing: &Option<Key>,
-    reader: &dyn SegmentReader,
+    reader: &SegmentReader,
     segment_ordinal: SegmentOrdinal,
     data: &mut AggregationsSegmentCtx,
     sub_aggs: &Aggregations,

src/aggregation/bucket/filter.rs

@@ -401,6 +401,8 @@ 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,
@@ -412,8 +414,9 @@ pub struct FilterAggReqData {
 
 impl FilterAggReqData {
     pub(crate) fn get_memory_consumption(&self) -> usize {
-        // Estimate: name + bitset + buffer capacity
+        // Estimate: name + segment reader reference + 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>()
         + std::mem::size_of::<bool>()
@@ -435,7 +438,7 @@ impl DocumentQueryEvaluator {
     pub(crate) fn new(
         query: Box<dyn Query>,
         schema: Schema,
-        segment_reader: &dyn SegmentReader,
+        segment_reader: &SegmentReader,
     ) -> crate::Result<Self> {
         let max_doc = segment_reader.max_doc();
 

src/aggregation/collector.rs

@@ -66,7 +66,7 @@ impl Collector for DistributedAggregationCollector {
     fn for_segment(
         &self,
         segment_local_id: crate::SegmentOrdinal,
-        reader: &dyn SegmentReader,
+        reader: &crate::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: &dyn SegmentReader,
+        reader: &crate::SegmentReader,
     ) -> crate::Result<Self::Child> {
         AggregationSegmentCollector::from_agg_req_and_reader(
             &self.agg,
@@ -145,7 +145,7 @@ impl AggregationSegmentCollector {
     /// reader. Also includes validation, e.g. checking field types and existence.
     pub fn from_agg_req_and_reader(
         agg: &Aggregations,
-        reader: &dyn SegmentReader,
+        reader: &SegmentReader,
         segment_ordinal: SegmentOrdinal,
         context: &AggContextParams,
     ) -> crate::Result<Self> {

src/codec/mod.rs

@@ -0,0 +1,169 @@
+/// Codec specific to postings data.
+pub mod postings;
+
+/// Standard tantivy codec. This is the codec you use by default.
+pub mod standard;
+
+use std::io;
+
+pub use standard::StandardCodec;
+
+use crate::codec::postings::PostingsCodec;
+use crate::fieldnorm::FieldNormReader;
+use crate::postings::{Postings, TermInfo};
+use crate::query::{box_scorer, Bm25Weight, Scorer};
+use crate::schema::IndexRecordOption;
+use crate::{DocId, InvertedIndexReader, Score};
+
+/// Codecs describes how data is layed out on disk.
+///
+/// For the moment, only postings codec can be custom.
+pub trait Codec: Clone + std::fmt::Debug + Send + Sync + 'static {
+    /// The specific postings type used by this codec.
+    type PostingsCodec: PostingsCodec;
+
+    /// Name of the codec. It should be unique to your codec.
+    const NAME: &'static str;
+
+    /// Load codec based on the codec configuration.
+    fn from_json_props(json_value: &serde_json::Value) -> crate::Result<Self>;
+
+    /// Get codec configuration.
+    fn to_json_props(&self) -> serde_json::Value;
+
+    /// Returns the postings codec.
+    fn postings_codec(&self) -> &Self::PostingsCodec;
+}
+
+/// Object-safe codec is a Codec that can be used in a trait object.
+///
+/// The point of it is to offer a way to use a codec without a proliferation of generics.
+pub trait ObjectSafeCodec: 'static + Send + Sync {
+    /// Loads a type-erased Postings object for the given term.
+    ///
+    /// If the schema used to build the index did not provide enough
+    /// information to match the requested `option`, a Postings is still
+    /// returned in a best-effort manner.
+    fn load_postings_type_erased(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        inverted_index_reader: &InvertedIndexReader,
+    ) -> io::Result<Box<dyn Postings>>;
+
+    /// Loads a type-erased TermScorer object for the given term.
+    ///
+    /// If the schema used to build the index did not provide enough
+    /// information to match the requested `option`, a TermScorer is still
+    /// returned in a best-effort manner.
+    ///
+    /// The point of this contraption is that the return TermScorer is backed,
+    /// not by Box<dyn Postings> but by the codec's concrete Postings type.
+    fn load_term_scorer_type_erased(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        inverted_index_reader: &InvertedIndexReader,
+        fieldnorm_reader: FieldNormReader,
+        similarity_weight: Bm25Weight,
+    ) -> io::Result<Box<dyn Scorer>>;
+
+    /// Loads a type-erased PhraseScorer object for the given term.
+    ///
+    /// If the schema used to build the index did not provide enough
+    /// information to match the requested `option`, a TermScorer is still
+    /// returned in a best-effort manner.
+    ///
+    /// The point of this contraption is that the return PhraseScorer is backed,
+    /// not by Box<dyn Postings> but by the codec's concrete Postings type.
+    fn new_phrase_scorer_type_erased(
+        &self,
+        term_infos: &[(usize, TermInfo)],
+        similarity_weight: Option<Bm25Weight>,
+        fieldnorm_reader: FieldNormReader,
+        slop: u32,
+        inverted_index_reader: &InvertedIndexReader,
+    ) -> io::Result<Box<dyn Scorer>>;
+
+    /// Performs a for_each_pruning operation on the given scorer.
+    ///
+    /// The function will go through matching documents and call the callback
+    /// function for all docs with a score exceeding the threshold.
+    ///
+    /// The function itself will return a larger threshold value,
+    /// meant to update the threshold value.
+    ///
+    /// If the codec and the scorer allow it, this function can rely on
+    /// optimizations like the block-max wand.
+    fn for_each_pruning(
+        &self,
+        threshold: Score,
+        scorer: Box<dyn Scorer>,
+        callback: &mut dyn FnMut(DocId, Score) -> Score,
+    );
+}
+
+impl<TCodec: Codec> ObjectSafeCodec for TCodec {
+    fn load_postings_type_erased(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        inverted_index_reader: &InvertedIndexReader,
+    ) -> io::Result<Box<dyn Postings>> {
+        let postings = inverted_index_reader
+            .read_postings_from_terminfo_specialized(term_info, option, self)?;
+        Ok(Box::new(postings))
+    }
+
+    fn load_term_scorer_type_erased(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        inverted_index_reader: &InvertedIndexReader,
+        fieldnorm_reader: FieldNormReader,
+        similarity_weight: Bm25Weight,
+    ) -> io::Result<Box<dyn Scorer>> {
+        let scorer = inverted_index_reader.new_term_scorer_specialized(
+            term_info,
+            option,
+            fieldnorm_reader,
+            similarity_weight,
+            self,
+        )?;
+        Ok(box_scorer(scorer))
+    }
+
+    fn new_phrase_scorer_type_erased(
+        &self,
+        term_infos: &[(usize, TermInfo)],
+        similarity_weight: Option<Bm25Weight>,
+        fieldnorm_reader: FieldNormReader,
+        slop: u32,
+        inverted_index_reader: &InvertedIndexReader,
+    ) -> io::Result<Box<dyn Scorer>> {
+        let scorer = inverted_index_reader.new_phrase_scorer_type_specialized(
+            term_infos,
+            similarity_weight,
+            fieldnorm_reader,
+            slop,
+            self,
+        )?;
+        Ok(box_scorer(scorer))
+    }
+
+    fn for_each_pruning(
+        &self,
+        threshold: Score,
+        scorer: Box<dyn Scorer>,
+        callback: &mut dyn FnMut(DocId, Score) -> Score,
+    ) {
+        let accerelerated_foreach_pruning_res =
+            <TCodec as Codec>::PostingsCodec::try_accelerated_for_each_pruning(
+                threshold, scorer, callback,
+            );
+        if let Err(mut scorer) = accerelerated_foreach_pruning_res {
+            // No acceleration available. We need to do things manually.
+            scorer.for_each_pruning(threshold, callback);
+        }
+    }
+}

src/codec/postings/block_wand.rs

@@ -1,5 +1,6 @@
 use std::ops::{Deref, DerefMut};
 
+use crate::codec::postings::PostingsWithBlockMax;
 use crate::query::term_query::TermScorer;
 use crate::query::Scorer;
 use crate::{DocId, DocSet, Score, TERMINATED};
@@ -13,8 +14,8 @@ use crate::{DocId, DocSet, Score, TERMINATED};
 /// We always have `before_pivot_len` < `pivot_len`.
 ///
 /// `None` is returned if we establish that no document can exceed the threshold.
-fn find_pivot_doc(
-    term_scorers: &[TermScorerWithMaxScore],
+fn find_pivot_doc<TPostings: PostingsWithBlockMax>(
+    term_scorers: &[TermScorerWithMaxScore<TPostings>],
     threshold: Score,
 ) -> Option<(usize, usize, DocId)> {
     let mut max_score = 0.0;
@@ -46,8 +47,8 @@ fn find_pivot_doc(
 /// the next doc candidate defined by the min of `last_doc_in_block + 1` for
 /// scorer in scorers[..pivot_len] and `scorer.doc()` for scorer in scorers[pivot_len..].
 /// Note: before and after calling this method, scorers need to be sorted by their `.doc()`.
-fn block_max_was_too_low_advance_one_scorer(
-    scorers: &mut [TermScorerWithMaxScore],
+fn block_max_was_too_low_advance_one_scorer<TPostings: PostingsWithBlockMax>(
+    scorers: &mut [TermScorerWithMaxScore<TPostings>],
     pivot_len: usize,
 ) {
     debug_assert!(is_sorted(scorers.iter().map(|scorer| scorer.doc())));
@@ -82,7 +83,10 @@ fn block_max_was_too_low_advance_one_scorer(
 // Given a list of term_scorers and a `ord` and assuming that `term_scorers[ord]` is sorted
 // except term_scorers[ord] that might be in advance compared to its ranks,
 // bubble up term_scorers[ord] in order to restore the ordering.
-fn restore_ordering(term_scorers: &mut [TermScorerWithMaxScore], ord: usize) {
+fn restore_ordering<TPostings: PostingsWithBlockMax>(
+    term_scorers: &mut [TermScorerWithMaxScore<TPostings>],
+    ord: usize,
+) {
     let doc = term_scorers[ord].doc();
     for i in ord + 1..term_scorers.len() {
         if term_scorers[i].doc() >= doc {
@@ -97,9 +101,10 @@ fn restore_ordering(term_scorers: &mut [TermScorerWithMaxScore], ord: usize) {
 // If this works, return true.
 // If this fails (ie: one of the term_scorer does not contain `pivot_doc` and seek goes past the
 // pivot), reorder the term_scorers to ensure the list is still sorted and returns `false`.
-// If a term_scorer reach TERMINATED in the process return false remove the term_scorer and return.
-fn align_scorers(
-    term_scorers: &mut Vec<TermScorerWithMaxScore>,
+// If a term_scorer reach TERMINATED in the process return false remove the term_scorer and
+// return.
+fn align_scorers<TPostings: PostingsWithBlockMax>(
+    term_scorers: &mut Vec<TermScorerWithMaxScore<TPostings>>,
     pivot_doc: DocId,
     before_pivot_len: usize,
 ) -> bool {
@@ -126,7 +131,10 @@ fn align_scorers(
 // Assumes terms_scorers[..pivot_len] are positioned on the same doc (pivot_doc).
 // Advance term_scorers[..pivot_len] and out of these removes the terminated scores.
 // Restores the ordering of term_scorers.
-fn advance_all_scorers_on_pivot(term_scorers: &mut Vec<TermScorerWithMaxScore>, pivot_len: usize) {
+fn advance_all_scorers_on_pivot<TPostings: PostingsWithBlockMax>(
+    term_scorers: &mut Vec<TermScorerWithMaxScore<TPostings>>,
+    pivot_len: usize,
+) {
     for term_scorer in &mut term_scorers[..pivot_len] {
         term_scorer.advance();
     }
@@ -145,12 +153,12 @@ fn advance_all_scorers_on_pivot(term_scorers: &mut Vec<TermScorerWithMaxScore>,
 /// Implements the WAND (Weak AND) algorithm for dynamic pruning
 /// described in the paper "Faster Top-k Document Retrieval Using Block-Max Indexes".
 /// Link: <http://engineering.nyu.edu/~suel/papers/bmw.pdf>
-pub fn block_wand(
-    mut scorers: Vec<TermScorer>,
+pub fn block_wand<TPostings: PostingsWithBlockMax>(
+    mut scorers: Vec<TermScorer<TPostings>>,
     mut threshold: Score,
     callback: &mut dyn FnMut(u32, Score) -> Score,
 ) {
-    let mut scorers: Vec<TermScorerWithMaxScore> = scorers
+    let mut scorers: Vec<TermScorerWithMaxScore<TPostings>> = scorers
         .iter_mut()
         .map(TermScorerWithMaxScore::from)
         .collect();
@@ -166,10 +174,7 @@ pub fn block_wand(
 
         let block_max_score_upperbound: Score = scorers[..pivot_len]
             .iter_mut()
-            .map(|scorer| {
-                scorer.seek_block(pivot_doc);
-                scorer.block_max_score()
-            })
+            .map(|scorer| scorer.seek_block_max(pivot_doc))
             .sum();
 
         // Beware after shallow advance, skip readers can be in advance compared to
@@ -220,21 +225,22 @@ pub fn block_wand(
 ///   - On a block, advance until the end and execute `callback` when the doc score is greater or
 ///     equal to the `threshold`.
 pub fn block_wand_single_scorer(
-    mut scorer: TermScorer,
+    mut scorer: TermScorer<impl PostingsWithBlockMax>,
     mut threshold: Score,
     callback: &mut dyn FnMut(u32, Score) -> Score,
 ) {
     let mut doc = scorer.doc();
+    let mut block_max_score = scorer.seek_block_max(doc);
     loop {
         // We position the scorer on a block that can reach
         // the threshold.
-        while scorer.block_max_score() < threshold {
+        while block_max_score < threshold {
             let last_doc_in_block = scorer.last_doc_in_block();
             if last_doc_in_block == TERMINATED {
                 return;
             }
             doc = last_doc_in_block + 1;
-            scorer.seek_block(doc);
+            block_max_score = scorer.seek_block_max(doc);
         }
         // Seek will effectively load that block.
         doc = scorer.seek(doc);
@@ -256,31 +262,33 @@ pub fn block_wand_single_scorer(
             }
         }
         doc += 1;
-        scorer.seek_block(doc);
+        block_max_score = scorer.seek_block_max(doc);
     }
 }
 
-struct TermScorerWithMaxScore<'a> {
-    scorer: &'a mut TermScorer,
+struct TermScorerWithMaxScore<'a, TPostings: PostingsWithBlockMax> {
+    scorer: &'a mut TermScorer<TPostings>,
     max_score: Score,
 }
 
-impl<'a> From<&'a mut TermScorer> for TermScorerWithMaxScore<'a> {
-    fn from(scorer: &'a mut TermScorer) -> Self {
+impl<'a, TPostings: PostingsWithBlockMax> From<&'a mut TermScorer<TPostings>>
+    for TermScorerWithMaxScore<'a, TPostings>
+{
+    fn from(scorer: &'a mut TermScorer<TPostings>) -> Self {
         let max_score = scorer.max_score();
         TermScorerWithMaxScore { scorer, max_score }
     }
 }
 
-impl Deref for TermScorerWithMaxScore<'_> {
-    type Target = TermScorer;
+impl<TPostings: PostingsWithBlockMax> Deref for TermScorerWithMaxScore<'_, TPostings> {
+    type Target = TermScorer<TPostings>;
 
     fn deref(&self) -> &Self::Target {
         self.scorer
     }
 }
 
-impl DerefMut for TermScorerWithMaxScore<'_> {
+impl<TPostings: PostingsWithBlockMax> DerefMut for TermScorerWithMaxScore<'_, TPostings> {
     fn deref_mut(&mut self) -> &mut Self::Target {
         self.scorer
     }

src/codec/postings/mod.rs

@@ -0,0 +1,119 @@
+use std::io;
+
+/// Block-max WAND algorithm.
+pub mod block_wand;
+use common::OwnedBytes;
+
+use crate::fieldnorm::FieldNormReader;
+use crate::postings::Postings;
+use crate::query::{Bm25Weight, Scorer};
+use crate::schema::IndexRecordOption;
+use crate::{DocId, Score};
+
+/// Postings codec.
+pub trait PostingsCodec: Send + Sync + 'static {
+    /// Serializer type for the postings codec.
+    type PostingsSerializer: PostingsSerializer;
+    /// Postings type for the postings codec.
+    type Postings: Postings + Clone;
+    /// Creates a new postings serializer.
+    fn new_serializer(
+        &self,
+        avg_fieldnorm: Score,
+        mode: IndexRecordOption,
+        fieldnorm_reader: Option<FieldNormReader>,
+    ) -> Self::PostingsSerializer;
+
+    /// Loads postings
+    ///
+    /// Record option is the option that was passed at indexing time.
+    /// Requested option is the option that is requested.
+    ///
+    /// For instance, we may have term_freq in the posting list
+    /// but we can skip decompressing as we read the posting list.
+    ///
+    /// If record option does not support the requested option,
+    /// this method does NOT return an error and will in fact restrict
+    /// requested_option to what is available.
+    fn load_postings(
+        &self,
+        doc_freq: u32,
+        postings_data: OwnedBytes,
+        record_option: IndexRecordOption,
+        requested_option: IndexRecordOption,
+        positions_data: Option<OwnedBytes>,
+    ) -> io::Result<Self::Postings>;
+
+    /// If your codec supports different ways to accelerate `for_each_pruning` that's
+    /// where you should implement it.
+    ///
+    /// Returning `Err(scorer)` without mutating the scorer nor calling the callback function,
+    /// is never "wrong". It just leaves the responsability to the caller to call a fallback
+    /// implementation on the scorer.
+    ///
+    /// If your codec supports BlockMax-Wand, you just need to have your
+    /// postings implement `PostingsWithBlockMax` and copy what is done in the StandardPostings
+    /// codec to enable it.
+    fn try_accelerated_for_each_pruning(
+        _threshold: Score,
+        scorer: Box<dyn Scorer>,
+        _callback: &mut dyn FnMut(DocId, Score) -> Score,
+    ) -> Result<(), Box<dyn Scorer>> {
+        Err(scorer)
+    }
+}
+
+/// A postings serializer is a listener that is in charge of serializing postings
+///
+/// IO is done only once per postings, once all of the data has been received.
+/// A serializer will therefore contain internal buffers.
+///
+/// A serializer is created once and recycled for all postings.
+///
+/// Clients should use PostingsSerializer as follows.
+/// ```
+/// // First postings list
+/// serializer.new_term(2, true);
+/// serializer.write_doc(2, 1);
+/// serializer.write_doc(6, 2);
+/// serializer.close_term(3);
+/// serializer.clear();
+/// // Second postings list
+/// serializer.new_term(1, true);
+/// serializer.write_doc(3, 1);
+/// serializer.close_term(3);
+/// ```
+pub trait PostingsSerializer {
+    /// The term_doc_freq here is the number of documents
+    /// in the postings lists.
+    ///
+    /// It can be used to compute the idf that will be used for the
+    /// blockmax parameters.
+    ///
+    /// If not available (e.g. if we do not collect `term_frequencies`
+    /// blockwand is disabled), the term_doc_freq passed will be set 0.
+    fn new_term(&mut self, term_doc_freq: u32, record_term_freq: bool);
+
+    /// Records a new document id for the current term.
+    /// The serializer may ignore it.
+    fn write_doc(&mut self, doc_id: DocId, term_freq: u32);
+
+    /// Closes the current term and writes the postings list associated.
+    fn close_term(&mut self, doc_freq: u32, wrt: &mut impl io::Write) -> io::Result<()>;
+}
+
+/// A light complement interface to Postings to allow block-max wand acceleration.
+pub trait PostingsWithBlockMax: Postings {
+    /// Moves the postings to the block containign `target_doc` and returns
+    /// an upperbound of the score for documents in the block.
+    ///
+    /// `Warning`: Calling this method may leave the postings in an invalid state.
+    /// callers are required to call seek before calling any other of the
+    /// `Postings` method (like doc / advance etc.).
+    fn seek_block_max(&mut self, target_doc: crate::DocId, similarity_weight: &Bm25Weight)
+        -> Score;
+
+    /// Returns the last document in the current block (or Terminated if this
+    /// is the last block).
+    fn last_doc_in_block(&self) -> crate::DocId;
+}

src/codec/standard/mod.rs

@@ -0,0 +1,35 @@
+use serde::{Deserialize, Serialize};
+
+use crate::codec::standard::postings::StandardPostingsCodec;
+use crate::codec::Codec;
+
+/// Tantivy's default postings codec.
+pub mod postings;
+
+/// Tantivy's default codec.
+#[derive(Debug, Default, Clone, Serialize, Deserialize)]
+pub struct StandardCodec;
+
+impl Codec for StandardCodec {
+    type PostingsCodec = StandardPostingsCodec;
+
+    const NAME: &'static str = "standard";
+
+    fn from_json_props(json_value: &serde_json::Value) -> crate::Result<Self> {
+        if !json_value.is_null() {
+            return Err(crate::TantivyError::InvalidArgument(format!(
+                "Codec property for the StandardCodec are unexpected. expected null, got {}",
+                json_value.as_str().unwrap_or("null")
+            )));
+        }
+        Ok(StandardCodec)
+    }
+
+    fn to_json_props(&self) -> serde_json::Value {
+        serde_json::Value::Null
+    }
+
+    fn postings_codec(&self) -> &Self::PostingsCodec {
+        &StandardPostingsCodec
+    }
+}

src/codec/standard/postings/block.rs

@@ -0,0 +1,50 @@
+use crate::postings::compression::COMPRESSION_BLOCK_SIZE;
+use crate::DocId;
+
+pub struct Block {
+    doc_ids: [DocId; COMPRESSION_BLOCK_SIZE],
+    term_freqs: [u32; COMPRESSION_BLOCK_SIZE],
+    len: usize,
+}
+
+impl Block {
+    pub fn new() -> Self {
+        Block {
+            doc_ids: [0u32; COMPRESSION_BLOCK_SIZE],
+            term_freqs: [0u32; COMPRESSION_BLOCK_SIZE],
+            len: 0,
+        }
+    }
+
+    pub fn doc_ids(&self) -> &[DocId] {
+        &self.doc_ids[..self.len]
+    }
+
+    pub fn term_freqs(&self) -> &[u32] {
+        &self.term_freqs[..self.len]
+    }
+
+    pub fn clear(&mut self) {
+        self.len = 0;
+    }
+
+    pub fn append_doc(&mut self, doc: DocId, term_freq: u32) {
+        let len = self.len;
+        self.doc_ids[len] = doc;
+        self.term_freqs[len] = term_freq;
+        self.len = len + 1;
+    }
+
+    pub fn is_full(&self) -> bool {
+        self.len == COMPRESSION_BLOCK_SIZE
+    }
+
+    pub fn is_empty(&self) -> bool {
+        self.len == 0
+    }
+
+    pub fn last_doc(&self) -> DocId {
+        assert_eq!(self.len, COMPRESSION_BLOCK_SIZE);
+        self.doc_ids[COMPRESSION_BLOCK_SIZE - 1]
+    }
+}

src/codec/standard/postings/block_segment_postings.rs

@@ -1,28 +1,18 @@
 use std::io;
 
-use common::VInt;
+use common::{OwnedBytes, VInt};
 
-use crate::directory::{FileSlice, OwnedBytes};
-use crate::fieldnorm::FieldNormReader;
-use crate::postings::compression::{BlockDecoder, VIntDecoder, COMPRESSION_BLOCK_SIZE};
-use crate::postings::{BlockInfo, FreqReadingOption, SkipReader};
+use crate::codec::standard::postings::skip::{BlockInfo, SkipReader};
+use crate::codec::standard::postings::FreqReadingOption;
+use crate::postings::compression::{BlockDecoder, VIntDecoder as _, COMPRESSION_BLOCK_SIZE};
 use crate::query::Bm25Weight;
 use crate::schema::IndexRecordOption;
 use crate::{DocId, Score, TERMINATED};
 
-fn max_score<I: Iterator<Item = Score>>(mut it: I) -> Option<Score> {
-    it.next().map(|first| it.fold(first, Score::max))
-}
-
 /// `BlockSegmentPostings` is a cursor iterating over blocks
 /// of documents.
-///
-/// # Warning
-///
-/// While it is useful for some very specific high-performance
-/// use cases, you should prefer using `SegmentPostings` for most usage.
 #[derive(Clone)]
-pub struct BlockSegmentPostings {
+pub(crate) struct BlockSegmentPostings {
     pub(crate) doc_decoder: BlockDecoder,
     block_loaded: bool,
     freq_decoder: BlockDecoder,
@@ -88,7 +78,7 @@ fn split_into_skips_and_postings(
 }
 
 impl BlockSegmentPostings {
-    /// Opens a `BlockSegmentPostings`.
+    /// Opens a `StandardPostingsReader`.
     /// `doc_freq` is the number of documents in the posting list.
     /// `record_option` represents the amount of data available according to the schema.
     /// `requested_option` is the amount of data requested by the user.
@@ -96,11 +86,10 @@ impl BlockSegmentPostings {
     /// term frequency blocks.
     pub(crate) fn open(
         doc_freq: u32,
-        data: FileSlice,
+        bytes: OwnedBytes,
         mut record_option: IndexRecordOption,
         requested_option: IndexRecordOption,
     ) -> io::Result<BlockSegmentPostings> {
-        let bytes = data.read_bytes()?;
         let (skip_data_opt, postings_data) = split_into_skips_and_postings(doc_freq, bytes)?;
         let skip_reader = match skip_data_opt {
             Some(skip_data) => {
@@ -138,50 +127,9 @@ impl BlockSegmentPostings {
         block_segment_postings.load_block();
         Ok(block_segment_postings)
     }
+}
 
-    /// Returns the block_max_score for the current block.
-    /// It does not require the block to be loaded. For instance, it is ok to call this method
-    /// after having called `.shallow_advance(..)`.
-    ///
-    /// See `TermScorer::block_max_score(..)` for more information.
-    pub fn block_max_score(
-        &mut self,
-        fieldnorm_reader: &FieldNormReader,
-        bm25_weight: &Bm25Weight,
-    ) -> Score {
-        if let Some(score) = self.block_max_score_cache {
-            return score;
-        }
-        if let Some(skip_reader_max_score) = self.skip_reader.block_max_score(bm25_weight) {
-            // if we are on a full block, the skip reader should have the block max information
-            // for us
-            self.block_max_score_cache = Some(skip_reader_max_score);
-            return skip_reader_max_score;
-        }
-        // this is the last block of the segment posting list.
-        // If it is actually loaded, we can compute block max manually.
-        if self.block_is_loaded() {
-            let docs = self.doc_decoder.output_array().iter().cloned();
-            let freqs = self.freq_decoder.output_array().iter().cloned();
-            let bm25_scores = docs.zip(freqs).map(|(doc, term_freq)| {
-                let fieldnorm_id = fieldnorm_reader.fieldnorm_id(doc);
-                bm25_weight.score(fieldnorm_id, term_freq)
-            });
-            let block_max_score = max_score(bm25_scores).unwrap_or(0.0);
-            self.block_max_score_cache = Some(block_max_score);
-            return block_max_score;
-        }
-        // We do not have access to any good block max value. We return bm25_weight.max_score()
-        // as it is a valid upperbound.
-        //
-        // We do not cache it however, so that it gets computed when once block is loaded.
-        bm25_weight.max_score()
-    }
-
-    pub(crate) fn freq_reading_option(&self) -> FreqReadingOption {
-        self.freq_reading_option
-    }
-
+impl BlockSegmentPostings {
     /// Returns the overall number of documents in the block postings.
     /// It does not take in account whether documents are deleted or not.
     ///
@@ -197,7 +145,7 @@ impl BlockSegmentPostings {
     /// returned by `.docs()` is empty.
     #[inline]
     pub fn docs(&self) -> &[DocId] {
-        debug_assert!(self.block_is_loaded());
+        debug_assert!(self.block_loaded);
         self.doc_decoder.output_array()
     }
 
@@ -210,35 +158,24 @@ impl BlockSegmentPostings {
     /// Return the array of `term freq` in the block.
     #[inline]
     pub fn freqs(&self) -> &[u32] {
-        debug_assert!(self.block_is_loaded());
+        debug_assert!(self.block_loaded);
         self.freq_decoder.output_array()
     }
 
     /// Return the frequency at index `idx` of the block.
     #[inline]
     pub fn freq(&self, idx: usize) -> u32 {
-        debug_assert!(self.block_is_loaded());
+        debug_assert!(self.block_loaded);
         self.freq_decoder.output(idx)
     }
 
-    /// Returns the length of the current block.
-    ///
-    /// All blocks have a length of `NUM_DOCS_PER_BLOCK`,
-    /// except the last block that may have a length
-    /// of any number between 1 and `NUM_DOCS_PER_BLOCK - 1`
-    #[inline]
-    pub fn block_len(&self) -> usize {
-        debug_assert!(self.block_is_loaded());
-        self.doc_decoder.output_len
-    }
-
     /// Position on a block that may contains `target_doc`.
     ///
     /// If all docs are smaller than target, the block loaded may be empty,
     /// or be the last an incomplete VInt block.
     pub fn seek(&mut self, target_doc: DocId) -> usize {
         // Move to the block that might contain our document.
-        self.seek_block(target_doc);
+        self.seek_block_without_loading(target_doc);
         self.load_block();
 
         // At this point we are on the block that might contain our document.
@@ -255,32 +192,79 @@ impl BlockSegmentPostings {
         doc
     }
 
-    pub(crate) fn position_offset(&self) -> u64 {
+    pub fn position_offset(&self) -> u64 {
         self.skip_reader.position_offset()
     }
 
+    /// Advance to the next block.
+    pub fn advance(&mut self) {
+        self.skip_reader.advance();
+        self.block_loaded = false;
+        self.block_max_score_cache = None;
+        self.load_block();
+    }
+
+    /// Returns the block_max_score for the current block.
+    /// It does not require the block to be loaded. For instance, it is ok to call this method
+    /// after having called `.shallow_advance(..)`.
+    ///
+    /// See `TermScorer::block_max_score(..)` for more information.
+    pub fn block_max_score(&mut self, bm25_weight: &Bm25Weight) -> Score {
+        if let Some(score) = self.block_max_score_cache {
+            return score;
+        }
+        if let Some(skip_reader_max_score) = self.skip_reader.block_max_score(bm25_weight) {
+            // if we are on a full block, the skip reader should have the block max information
+            // for us
+            self.block_max_score_cache = Some(skip_reader_max_score);
+            return skip_reader_max_score;
+        }
+        // We do not have access to any good block max value.
+        // It happens if this is the last block.
+        // We return bm25_weight.max_score() as it is a valid upperbound.
+        //
+        // We do not cache it however, so that it gets computed when once block is loaded.
+        bm25_weight.max_score()
+    }
+}
+
+impl BlockSegmentPostings {
+    /// Returns an empty segment postings object
+    pub fn empty() -> BlockSegmentPostings {
+        BlockSegmentPostings {
+            doc_decoder: BlockDecoder::with_val(TERMINATED),
+            block_loaded: true,
+            freq_decoder: BlockDecoder::with_val(1),
+            freq_reading_option: FreqReadingOption::NoFreq,
+            block_max_score_cache: None,
+            doc_freq: 0,
+            data: OwnedBytes::empty(),
+            skip_reader: SkipReader::new(OwnedBytes::empty(), 0, IndexRecordOption::Basic),
+        }
+    }
+
+    pub(crate) fn skip_reader(&self) -> &SkipReader {
+        &self.skip_reader
+    }
+
     /// Dangerous API! This calls seeks the next block on the skip list,
     /// but does not `.load_block()` afterwards.
     ///
     /// `.load_block()` needs to be called manually afterwards.
     /// If all docs are smaller than target, the block loaded may be empty,
     /// or be the last an incomplete VInt block.
-    pub(crate) fn seek_block(&mut self, target_doc: DocId) {
+    pub(crate) fn seek_block_without_loading(&mut self, target_doc: DocId) {
         if self.skip_reader.seek(target_doc) {
             self.block_max_score_cache = None;
             self.block_loaded = false;
         }
     }
 
-    pub(crate) fn block_is_loaded(&self) -> bool {
-        self.block_loaded
-    }
-
     pub(crate) fn load_block(&mut self) {
-        let offset = self.skip_reader.byte_offset();
-        if self.block_is_loaded() {
+        if self.block_loaded {
             return;
         }
+        let offset = self.skip_reader.byte_offset();
         match self.skip_reader.block_info() {
             BlockInfo::BitPacked {
                 doc_num_bits,
@@ -325,68 +309,40 @@ impl BlockSegmentPostings {
         }
         self.block_loaded = true;
     }
-
-    /// Advance to the next block.
-    pub fn advance(&mut self) {
-        self.skip_reader.advance();
-        self.block_loaded = false;
-        self.block_max_score_cache = None;
-        self.load_block();
-    }
-
-    /// Returns an empty segment postings object
-    pub fn empty() -> BlockSegmentPostings {
-        BlockSegmentPostings {
-            doc_decoder: BlockDecoder::with_val(TERMINATED),
-            block_loaded: true,
-            freq_decoder: BlockDecoder::with_val(1),
-            freq_reading_option: FreqReadingOption::NoFreq,
-            block_max_score_cache: None,
-            doc_freq: 0,
-            data: OwnedBytes::empty(),
-            skip_reader: SkipReader::new(OwnedBytes::empty(), 0, IndexRecordOption::Basic),
-        }
-    }
-
-    pub(crate) fn skip_reader(&self) -> &SkipReader {
-        &self.skip_reader
-    }
 }
 
 #[cfg(test)]
 mod tests {
-    use common::HasLen;
+    use common::OwnedBytes;
 
     use super::BlockSegmentPostings;
+    use crate::codec::postings::PostingsSerializer;
+    use crate::codec::standard::postings::segment_postings::SegmentPostings;
+    use crate::codec::standard::postings::StandardPostingsSerializer;
     use crate::docset::{DocSet, TERMINATED};
-    use crate::index::Index;
     use crate::postings::compression::COMPRESSION_BLOCK_SIZE;
-    use crate::postings::postings::Postings;
-    use crate::postings::SegmentPostings;
-    use crate::schema::{IndexRecordOption, Schema, Term, INDEXED};
-    use crate::DocId;
+    use crate::schema::IndexRecordOption;
 
-    #[test]
-    fn test_empty_segment_postings() {
-        let mut postings = SegmentPostings::empty();
-        assert_eq!(postings.doc(), TERMINATED);
-        assert_eq!(postings.advance(), TERMINATED);
-        assert_eq!(postings.advance(), TERMINATED);
-        assert_eq!(postings.doc_freq(), 0);
-        assert_eq!(postings.len(), 0);
-    }
-
-    #[test]
-    fn test_empty_postings_doc_returns_terminated() {
-        let mut postings = SegmentPostings::empty();
-        assert_eq!(postings.doc(), TERMINATED);
-        assert_eq!(postings.advance(), TERMINATED);
-    }
-
-    #[test]
-    fn test_empty_postings_doc_term_freq_returns_0() {
-        let postings = SegmentPostings::empty();
-        assert_eq!(postings.term_freq(), 1);
+    #[cfg(test)]
+    fn build_block_postings(docs: &[u32]) -> BlockSegmentPostings {
+        let doc_freq = docs.len() as u32;
+        let mut postings_serializer =
+            StandardPostingsSerializer::new(1.0f32, IndexRecordOption::Basic, None);
+        postings_serializer.new_term(docs.len() as u32, false);
+        for doc in docs {
+            postings_serializer.write_doc(*doc, 1u32);
+        }
+        let mut buffer: Vec<u8> = Vec::new();
+        postings_serializer
+            .close_term(doc_freq, &mut buffer)
+            .unwrap();
+        BlockSegmentPostings::open(
+            doc_freq,
+            OwnedBytes::new(buffer),
+            IndexRecordOption::Basic,
+            IndexRecordOption::Basic,
+        )
+        .unwrap()
     }
 
     #[test]
@@ -401,7 +357,7 @@ mod tests {
 
     #[test]
     fn test_block_segment_postings() -> crate::Result<()> {
-        let mut block_segments = build_block_postings(&(0..100_000).collect::<Vec<u32>>())?;
+        let mut block_segments = build_block_postings(&(0..100_000).collect::<Vec<u32>>());
         let mut offset: u32 = 0u32;
         // checking that the `doc_freq` is correct
         assert_eq!(block_segments.doc_freq(), 100_000);
@@ -426,7 +382,7 @@ mod tests {
         doc_ids.push(129);
         doc_ids.push(130);
         {
-            let block_segments = build_block_postings(&doc_ids)?;
+            let block_segments = build_block_postings(&doc_ids);
             let mut docset = SegmentPostings::from_block_postings(block_segments, None);
             assert_eq!(docset.seek(128), 129);
             assert_eq!(docset.doc(), 129);
@@ -435,7 +391,7 @@ mod tests {
             assert_eq!(docset.advance(), TERMINATED);
         }
         {
-            let block_segments = build_block_postings(&doc_ids).unwrap();
+            let block_segments = build_block_postings(&doc_ids);
             let mut docset = SegmentPostings::from_block_postings(block_segments, None);
             assert_eq!(docset.seek(129), 129);
             assert_eq!(docset.doc(), 129);
@@ -444,7 +400,7 @@ mod tests {
             assert_eq!(docset.advance(), TERMINATED);
         }
         {
-            let block_segments = build_block_postings(&doc_ids)?;
+            let block_segments = build_block_postings(&doc_ids);
             let mut docset = SegmentPostings::from_block_postings(block_segments, None);
             assert_eq!(docset.doc(), 0);
             assert_eq!(docset.seek(131), TERMINATED);
@@ -453,38 +409,13 @@ mod tests {
         Ok(())
     }
 
-    fn build_block_postings(docs: &[DocId]) -> crate::Result<BlockSegmentPostings> {
-        let mut schema_builder = Schema::builder();
-        let int_field = schema_builder.add_u64_field("id", INDEXED);
-        let schema = schema_builder.build();
-        let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_for_tests()?;
-        let mut last_doc = 0u32;
-        for &doc in docs {
-            for _ in last_doc..doc {
-                index_writer.add_document(doc!(int_field=>1u64))?;
-            }
-            index_writer.add_document(doc!(int_field=>0u64))?;
-            last_doc = doc + 1;
-        }
-        index_writer.commit()?;
-        let searcher = index.reader()?.searcher();
-        let segment_reader = searcher.segment_reader(0);
-        let inverted_index = segment_reader.inverted_index(int_field).unwrap();
-        let term = Term::from_field_u64(int_field, 0u64);
-        let term_info = inverted_index.get_term_info(&term)?.unwrap();
-        let block_postings = inverted_index
-            .read_block_postings_from_terminfo(&term_info, IndexRecordOption::Basic)?;
-        Ok(block_postings)
-    }
-
     #[test]
     fn test_block_segment_postings_seek() -> crate::Result<()> {
-        let mut docs = vec![0];
+        let mut docs = Vec::new();
         for i in 0..1300 {
             docs.push((i * i / 100) + i);
         }
-        let mut block_postings = build_block_postings(&docs[..])?;
+        let mut block_postings = build_block_postings(&docs[..]);
         for i in &[0, 424, 10000] {
             block_postings.seek(*i);
             let docs = block_postings.docs();

src/codec/standard/postings/mod.rs

@@ -0,0 +1,107 @@
+use std::io;
+
+use crate::codec::postings::block_wand::{block_wand, block_wand_single_scorer};
+use crate::codec::postings::PostingsCodec;
+use crate::codec::standard::postings::block_segment_postings::BlockSegmentPostings;
+use crate::codec::standard::postings::segment_postings::SegmentPostings;
+use crate::fieldnorm::FieldNormReader;
+use crate::positions::PositionReader;
+use crate::query::term_query::TermScorer;
+use crate::query::{BufferedUnionScorer, Scorer, SumCombiner};
+use crate::schema::IndexRecordOption;
+use crate::{DocSet as _, Score, TERMINATED};
+
+mod block;
+mod block_segment_postings;
+mod segment_postings;
+mod skip;
+mod standard_postings_serializer;
+
+pub use segment_postings::SegmentPostings as StandardPostings;
+pub use standard_postings_serializer::StandardPostingsSerializer;
+
+/// The default postings codec for tantivy.
+pub struct StandardPostingsCodec;
+
+#[expect(clippy::enum_variant_names)]
+#[derive(Debug, PartialEq, Clone, Copy, Eq)]
+pub(crate) enum FreqReadingOption {
+    NoFreq,
+    SkipFreq,
+    ReadFreq,
+}
+
+impl PostingsCodec for StandardPostingsCodec {
+    type PostingsSerializer = StandardPostingsSerializer;
+    type Postings = SegmentPostings;
+
+    fn new_serializer(
+        &self,
+        avg_fieldnorm: Score,
+        mode: IndexRecordOption,
+        fieldnorm_reader: Option<FieldNormReader>,
+    ) -> Self::PostingsSerializer {
+        StandardPostingsSerializer::new(avg_fieldnorm, mode, fieldnorm_reader)
+    }
+
+    fn load_postings(
+        &self,
+        doc_freq: u32,
+        postings_data: common::OwnedBytes,
+        record_option: IndexRecordOption,
+        requested_option: IndexRecordOption,
+        positions_data_opt: Option<common::OwnedBytes>,
+    ) -> io::Result<Self::Postings> {
+        // Rationalize record_option/requested_option.
+        let requested_option = requested_option.downgrade(record_option);
+        let block_segment_postings =
+            BlockSegmentPostings::open(doc_freq, postings_data, record_option, requested_option)?;
+        let position_reader = positions_data_opt.map(PositionReader::open).transpose()?;
+        Ok(SegmentPostings::from_block_postings(
+            block_segment_postings,
+            position_reader,
+        ))
+    }
+
+    fn try_accelerated_for_each_pruning(
+        mut threshold: Score,
+        mut scorer: Box<dyn Scorer>,
+        callback: &mut dyn FnMut(crate::DocId, Score) -> Score,
+    ) -> Result<(), Box<dyn Scorer>> {
+        scorer = match scorer.downcast::<TermScorer<Self::Postings>>() {
+            Ok(term_scorer) => {
+                block_wand_single_scorer(*term_scorer, threshold, callback);
+                return Ok(());
+            }
+            Err(scorer) => scorer,
+        };
+        let mut union_scorer =
+            scorer.downcast::<BufferedUnionScorer<Box<dyn Scorer>, SumCombiner>>()?;
+        if !union_scorer
+            .scorers()
+            .iter()
+            .all(|scorer| scorer.is::<TermScorer<Self::Postings>>())
+        {
+            return Err(union_scorer);
+        }
+        let doc = union_scorer.doc();
+        if doc == TERMINATED {
+            return Ok(());
+        }
+        let score = union_scorer.score();
+        if score > threshold {
+            threshold = callback(doc, score);
+        }
+        let boxed_scorers: Vec<Box<dyn Scorer>> = union_scorer.into_scorers();
+        let scorers: Vec<TermScorer<Self::Postings>> = boxed_scorers
+            .into_iter()
+            .map(|scorer| {
+                *scorer.downcast::<TermScorer<Self::Postings>>().ok().expect(
+                    "Downcast failed despite the fact we already checked the type was correct",
+                )
+            })
+            .collect();
+        block_wand(scorers, threshold, callback);
+        Ok(())
+    }
+}

src/codec/standard/postings/segment_postings.rs

@@ -1,11 +1,13 @@
-use common::HasLen;
+use common::{BitSet, HasLen};
 
+use super::BlockSegmentPostings;
+use crate::codec::postings::PostingsWithBlockMax;
 use crate::docset::DocSet;
-use crate::fastfield::AliveBitSet;
 use crate::positions::PositionReader;
 use crate::postings::compression::COMPRESSION_BLOCK_SIZE;
-use crate::postings::{BlockSegmentPostings, Postings};
-use crate::{DocId, TERMINATED};
+use crate::postings::{DocFreq, Postings};
+use crate::query::Bm25Weight;
+use crate::{DocId, Score};
 
 /// `SegmentPostings` represents the inverted list or postings associated with
 /// a term in a `Segment`.
@@ -29,31 +31,6 @@ impl SegmentPostings {
         }
     }
 
-    /// Compute the number of non-deleted documents.
-    ///
-    /// This method will clone and scan through the posting lists.
-    /// (this is a rather expensive operation).
-    pub fn doc_freq_given_deletes(&self, alive_bitset: &AliveBitSet) -> u32 {
-        let mut docset = self.clone();
-        let mut doc_freq = 0;
-        loop {
-            let doc = docset.doc();
-            if doc == TERMINATED {
-                return doc_freq;
-            }
-            if alive_bitset.is_alive(doc) {
-                doc_freq += 1u32;
-            }
-            docset.advance();
-        }
-    }
-
-    /// Returns the overall number of documents in the block postings.
-    /// It does not take in account whether documents are deleted or not.
-    pub fn doc_freq(&self) -> u32 {
-        self.block_cursor.doc_freq()
-    }
-
     /// Creates a segment postings object with the given documents
     /// and no frequency encoded.
     ///
@@ -64,13 +41,19 @@ impl SegmentPostings {
     /// buffer with the serialized data.
     #[cfg(test)]
     pub fn create_from_docs(docs: &[u32]) -> SegmentPostings {
-        use crate::directory::FileSlice;
-        use crate::postings::serializer::PostingsSerializer;
+        use common::OwnedBytes;
+
         use crate::schema::IndexRecordOption;
         let mut buffer = Vec::new();
         {
+            use crate::codec::postings::PostingsSerializer;
+
             let mut postings_serializer =
-                PostingsSerializer::new(0.0, IndexRecordOption::Basic, None);
+                crate::codec::standard::postings::StandardPostingsSerializer::new(
+                    0.0,
+                    IndexRecordOption::Basic,
+                    None,
+                );
             postings_serializer.new_term(docs.len() as u32, false);
             for &doc in docs {
                 postings_serializer.write_doc(doc, 1u32);
@@ -81,7 +64,7 @@ impl SegmentPostings {
         }
         let block_segment_postings = BlockSegmentPostings::open(
             docs.len() as u32,
-            FileSlice::from(buffer),
+            OwnedBytes::new(buffer),
             IndexRecordOption::Basic,
             IndexRecordOption::Basic,
         )
@@ -95,9 +78,11 @@ impl SegmentPostings {
         doc_and_tfs: &[(u32, u32)],
         fieldnorms: Option<&[u32]>,
     ) -> SegmentPostings {
-        use crate::directory::FileSlice;
+        use common::OwnedBytes;
+
+        use crate::codec::postings::PostingsSerializer as _;
+        use crate::codec::standard::postings::StandardPostingsSerializer;
         use crate::fieldnorm::FieldNormReader;
-        use crate::postings::serializer::PostingsSerializer;
         use crate::schema::IndexRecordOption;
         use crate::Score;
         let mut buffer: Vec<u8> = Vec::new();
@@ -114,7 +99,7 @@ impl SegmentPostings {
                 total_num_tokens as Score / fieldnorms.len() as Score
             })
             .unwrap_or(0.0);
-        let mut postings_serializer = PostingsSerializer::new(
+        let mut postings_serializer = StandardPostingsSerializer::new(
             average_field_norm,
             IndexRecordOption::WithFreqs,
             fieldnorm_reader,
@@ -128,7 +113,7 @@ impl SegmentPostings {
             .unwrap();
         let block_segment_postings = BlockSegmentPostings::open(
             doc_and_tfs.len() as u32,
-            FileSlice::from(buffer),
+            OwnedBytes::new(buffer),
             IndexRecordOption::WithFreqs,
             IndexRecordOption::WithFreqs,
         )
@@ -158,7 +143,6 @@ impl DocSet for SegmentPostings {
     // next needs to be called a first time to point to the correct element.
     #[inline]
     fn advance(&mut self) -> DocId {
-        debug_assert!(self.block_cursor.block_is_loaded());
         if self.cur == COMPRESSION_BLOCK_SIZE - 1 {
             self.cur = 0;
             self.block_cursor.advance();
@@ -191,6 +175,19 @@ impl DocSet for SegmentPostings {
     fn size_hint(&self) -> u32 {
         self.len() as u32
     }
+
+    fn fill_bitset(&mut self, bitset: &mut BitSet) {
+        loop {
+            let docs = self.block_cursor.docs();
+            if docs.is_empty() {
+                break;
+            }
+            for &doc in docs {
+                bitset.insert(doc);
+            }
+            self.block_cursor.advance();
+        }
+    }
 }
 
 impl HasLen for SegmentPostings {
@@ -206,7 +203,7 @@ impl Postings for SegmentPostings {
     ///
     /// # Panics
     ///
-    /// Will panics if called without having called advance before.
+    /// Will panics if called without having cagled advance before.
     fn term_freq(&self) -> u32 {
         debug_assert!(
             // Here we do not use the len of `freqs()`
@@ -221,6 +218,13 @@ impl Postings for SegmentPostings {
         self.block_cursor.freq(self.cur)
     }
 
+    /// Returns the overall number of documents in the block postings.
+    /// It does not take in account whether documents are deleted or not.
+    #[inline(always)]
+    fn doc_freq(&self) -> DocFreq {
+        DocFreq::Exact(self.block_cursor.doc_freq())
+    }
+
     fn append_positions_with_offset(&mut self, offset: u32, output: &mut Vec<u32>) {
         let term_freq = self.term_freq();
         let prev_len = output.len();
@@ -244,6 +248,25 @@ impl Postings for SegmentPostings {
             }
         }
     }
+
+    fn has_freq(&self) -> bool {
+        !self.block_cursor.freqs().is_empty()
+    }
+}
+
+impl PostingsWithBlockMax for SegmentPostings {
+    fn seek_block_max(
+        &mut self,
+        target_doc: crate::DocId,
+        similarity_weight: &Bm25Weight,
+    ) -> Score {
+        self.block_cursor.seek_block_without_loading(target_doc);
+        self.block_cursor.block_max_score(similarity_weight)
+    }
+
+    fn last_doc_in_block(&self) -> crate::DocId {
+        self.block_cursor.skip_reader().last_doc_in_block()
+    }
 }
 
 #[cfg(test)]
@@ -253,14 +276,15 @@ mod tests {
 
     use super::SegmentPostings;
     use crate::docset::{DocSet, TERMINATED};
-    use crate::fastfield::AliveBitSet;
-    use crate::postings::postings::Postings;
+    use crate::postings::Postings;
 
     #[test]
     fn test_empty_segment_postings() {
         let mut postings = SegmentPostings::empty();
+        assert_eq!(postings.doc(), TERMINATED);
         assert_eq!(postings.advance(), TERMINATED);
         assert_eq!(postings.advance(), TERMINATED);
+        assert_eq!(postings.doc_freq(), crate::postings::DocFreq::Exact(0));
         assert_eq!(postings.len(), 0);
     }
 
@@ -276,15 +300,4 @@ mod tests {
         let postings = SegmentPostings::empty();
         assert_eq!(postings.term_freq(), 1);
     }
-
-    #[test]
-    fn test_doc_freq() {
-        let docs = SegmentPostings::create_from_docs(&[0, 2, 10]);
-        assert_eq!(docs.doc_freq(), 3);
-        let alive_bitset = AliveBitSet::for_test_from_deleted_docs(&[2], 12);
-        assert_eq!(docs.doc_freq_given_deletes(&alive_bitset), 2);
-        let all_deleted =
-            AliveBitSet::for_test_from_deleted_docs(&[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11], 12);
-        assert_eq!(docs.doc_freq_given_deletes(&all_deleted), 0);
-    }
 }

src/codec/standard/postings/standard_postings_serializer.rs

@@ -0,0 +1,185 @@
+use std::cmp::Ordering;
+use std::io::{self, Write as _};
+
+use common::{BinarySerializable as _, VInt};
+
+use crate::codec::postings::PostingsSerializer;
+use crate::codec::standard::postings::block::Block;
+use crate::codec::standard::postings::skip::SkipSerializer;
+use crate::fieldnorm::FieldNormReader;
+use crate::postings::compression::{BlockEncoder, VIntEncoder as _, COMPRESSION_BLOCK_SIZE};
+use crate::query::Bm25Weight;
+use crate::schema::IndexRecordOption;
+use crate::{DocId, Score};
+
+/// Default tantivy postings codec serializer.
+pub struct StandardPostingsSerializer {
+    last_doc_id_encoded: u32,
+
+    block_encoder: BlockEncoder,
+    block: Box<Block>,
+
+    postings_write: Vec<u8>,
+    skip_write: SkipSerializer,
+
+    mode: IndexRecordOption,
+    fieldnorm_reader: Option<FieldNormReader>,
+
+    bm25_weight: Option<Bm25Weight>,
+    avg_fieldnorm: Score, /* Average number of term in the field for that segment.
+                           * this value is used to compute the block wand information. */
+    term_has_freq: bool,
+}
+
+impl StandardPostingsSerializer {
+    /// Creates a new instance of `StandardPostingsSerializer`.
+    pub fn new(
+        avg_fieldnorm: Score,
+        mode: IndexRecordOption,
+        fieldnorm_reader: Option<FieldNormReader>,
+    ) -> StandardPostingsSerializer {
+        Self {
+            last_doc_id_encoded: 0,
+            block_encoder: BlockEncoder::new(),
+            block: Box::new(Block::new()),
+            postings_write: Vec::new(),
+            skip_write: SkipSerializer::new(),
+            mode,
+            fieldnorm_reader,
+            bm25_weight: None,
+            avg_fieldnorm,
+            term_has_freq: false,
+        }
+    }
+}
+
+impl PostingsSerializer for StandardPostingsSerializer {
+    fn new_term(&mut self, term_doc_freq: u32, record_term_freq: bool) {
+        self.clear();
+
+        self.term_has_freq = self.mode.has_freq() && record_term_freq;
+        if !self.term_has_freq {
+            return;
+        }
+
+        let num_docs_in_segment: u64 =
+            if let Some(fieldnorm_reader) = self.fieldnorm_reader.as_ref() {
+                fieldnorm_reader.num_docs() as u64
+            } else {
+                return;
+            };
+
+        if num_docs_in_segment == 0 {
+            return;
+        }
+
+        self.bm25_weight = Some(Bm25Weight::for_one_term_without_explain(
+            term_doc_freq as u64,
+            num_docs_in_segment,
+            self.avg_fieldnorm,
+        ));
+    }
+
+    fn write_doc(&mut self, doc_id: DocId, term_freq: u32) {
+        self.block.append_doc(doc_id, term_freq);
+        if self.block.is_full() {
+            self.write_block();
+        }
+    }
+
+    fn close_term(&mut self, doc_freq: u32, output_write: &mut impl io::Write) -> io::Result<()> {
+        if !self.block.is_empty() {
+            // we have doc ids waiting to be written
+            // this happens when the number of doc ids is
+            // not a perfect multiple of our block size.
+            //
+            // In that case, the remaining part is encoded
+            // using variable int encoding.
+            {
+                let block_encoded = self
+                    .block_encoder
+                    .compress_vint_sorted(self.block.doc_ids(), self.last_doc_id_encoded);
+                self.postings_write.write_all(block_encoded)?;
+            }
+            // ... Idem for term frequencies
+            if self.term_has_freq {
+                let block_encoded = self
+                    .block_encoder
+                    .compress_vint_unsorted(self.block.term_freqs());
+                self.postings_write.write_all(block_encoded)?;
+            }
+            self.block.clear();
+        }
+        if doc_freq >= COMPRESSION_BLOCK_SIZE as u32 {
+            let skip_data = self.skip_write.data();
+            VInt(skip_data.len() as u64).serialize(output_write)?;
+            output_write.write_all(skip_data)?;
+        }
+        output_write.write_all(&self.postings_write[..])?;
+        self.skip_write.clear();
+        self.postings_write.clear();
+        self.bm25_weight = None;
+        Ok(())
+    }
+}
+
+impl StandardPostingsSerializer {
+    fn clear(&mut self) {
+        self.bm25_weight = None;
+        self.block.clear();
+        self.last_doc_id_encoded = 0;
+    }
+
+    fn write_block(&mut self) {
+        {
+            // encode the doc ids
+            let (num_bits, block_encoded): (u8, &[u8]) = self
+                .block_encoder
+                .compress_block_sorted(self.block.doc_ids(), self.last_doc_id_encoded);
+            self.last_doc_id_encoded = self.block.last_doc();
+            self.skip_write
+                .write_doc(self.last_doc_id_encoded, num_bits);
+            // last el block 0, offset block 1,
+            self.postings_write.extend(block_encoded);
+        }
+        if self.term_has_freq {
+            let (num_bits, block_encoded): (u8, &[u8]) = self
+                .block_encoder
+                .compress_block_unsorted(self.block.term_freqs(), true);
+            self.postings_write.extend(block_encoded);
+            self.skip_write.write_term_freq(num_bits);
+            if self.mode.has_positions() {
+                // We serialize the sum of term freqs within the skip information
+                // in order to navigate through positions.
+                let sum_freq = self.block.term_freqs().iter().cloned().sum();
+                self.skip_write.write_total_term_freq(sum_freq);
+            }
+            let mut blockwand_params = (0u8, 0u32);
+            if let Some(bm25_weight) = self.bm25_weight.as_ref() {
+                if let Some(fieldnorm_reader) = self.fieldnorm_reader.as_ref() {
+                    let docs = self.block.doc_ids().iter().cloned();
+                    let term_freqs = self.block.term_freqs().iter().cloned();
+                    let fieldnorms = docs.map(|doc| fieldnorm_reader.fieldnorm_id(doc));
+                    blockwand_params = fieldnorms
+                        .zip(term_freqs)
+                        .max_by(
+                            |(left_fieldnorm_id, left_term_freq),
+                             (right_fieldnorm_id, right_term_freq)| {
+                                let left_score =
+                                    bm25_weight.tf_factor(*left_fieldnorm_id, *left_term_freq);
+                                let right_score =
+                                    bm25_weight.tf_factor(*right_fieldnorm_id, *right_term_freq);
+                                left_score
+                                    .partial_cmp(&right_score)
+                                    .unwrap_or(Ordering::Equal)
+                            },
+                        )
+                        .unwrap();
+                }
+            }
+            let (fieldnorm_id, term_freq) = blockwand_params;
+            self.skip_write.write_blockwand_max(fieldnorm_id, term_freq);
+        }
+        self.block.clear();
+    }
+}

src/collector/count_collector.rs

@@ -43,7 +43,7 @@ impl Collector for Count {
     fn for_segment(
         &self,
         _: SegmentOrdinal,
-        _: &dyn SegmentReader,
+        _: &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, SegmentReader};
+use crate::{DocAddress, DocId, Score};
 
 /// 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: &dyn SegmentReader,
+        _segment: &crate::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: &dyn SegmentReader,
+        reader: &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::distr::Uniform;
+    use rand::distributions::Uniform;
     use rand::prelude::SliceRandom;
-    use rand::{rng, Rng};
+    use rand::{thread_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).unwrap();
+        let uniform = Uniform::new_inclusive(1, 100_000);
         let mut docs: Vec<TantivyDocument> =
             vec![("a", 10), ("b", 100), ("c", 7), ("d", 12), ("e", 21)]
                 .into_iter()
@@ -741,11 +741,14 @@ mod tests {
                     std::iter::repeat_n(doc, count)
                 })
                 .map(|mut doc| {
-                    doc.add_facet(facet_field, &format!("/facet/{}", rng().sample(uniform)));
+                    doc.add_facet(
+                        facet_field,
+                        &format!("/facet/{}", thread_rng().sample(uniform)),
+                    );
                     doc
                 })
                 .collect();
-        docs[..].shuffle(&mut rng());
+        docs[..].shuffle(&mut thread_rng());
 
         let mut index_writer: IndexWriter = index.writer_for_tests().unwrap();
         for doc in docs {
@@ -819,8 +822,8 @@ 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;
@@ -843,7 +846,7 @@ mod bench {
             }
         }
         // 40425 docs
-        docs[..].shuffle(&mut rng());
+        docs[..].shuffle(&mut thread_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: &dyn SegmentReader,
+        segment_reader: &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: &dyn SegmentReader,
+        segment_reader: &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, SegmentReader};
+use crate::{DocId, Score};
 
 /// 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: &dyn SegmentReader,
+        segment: &crate::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: &dyn SegmentReader,
+        segment: &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: &dyn SegmentReader,
+        reader: &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: &dyn SegmentReader,
+    reader: &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: &dyn SegmentReader,
+        segment: &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: &dyn SegmentReader,
+        segment: &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: &dyn SegmentReader,
+        segment: &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: &dyn SegmentReader,
+        segment: &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: &dyn SegmentReader,
+        reader: &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: &dyn SegmentReader,
+        segment: &SegmentReader,
     ) -> crate::Result<MultiCollectorChild> {
         let children = self
             .collector_wrappers

src/collector/sort_key/order.rs

@@ -5,7 +5,7 @@ use serde::{Deserialize, Serialize};
 
 use crate::collector::{SegmentSortKeyComputer, SortKeyComputer};
 use crate::schema::{OwnedValue, Schema};
-use crate::{DocId, Order, Score, SegmentReader};
+use crate::{DocId, Order, Score};
 
 fn compare_owned_value<const NULLS_FIRST: bool>(lhs: &OwnedValue, rhs: &OwnedValue) -> Ordering {
     match (lhs, rhs) {
@@ -430,7 +430,7 @@ where
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &dyn SegmentReader,
+        segment_reader: &crate::SegmentReader,
     ) -> crate::Result<Self::Child> {
         let child = self.0.segment_sort_key_computer(segment_reader)?;
         Ok(SegmentSortKeyComputerWithComparator {
@@ -468,7 +468,7 @@ where
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &dyn SegmentReader,
+        segment_reader: &crate::SegmentReader,
     ) -> crate::Result<Self::Child> {
         let child = self.0.segment_sort_key_computer(segment_reader)?;
         Ok(SegmentSortKeyComputerWithComparator {

src/collector/sort_key/sort_by_erased_type.rs

@@ -6,7 +6,7 @@ use crate::collector::sort_key::{
 use crate::collector::{SegmentSortKeyComputer, SortKeyComputer};
 use crate::fastfield::FastFieldNotAvailableError;
 use crate::schema::OwnedValue;
-use crate::{DateTime, DocId, Score, SegmentReader};
+use crate::{DateTime, DocId, Score};
 
 /// Sort by the boxed / OwnedValue representation of either a fast field, or of the score.
 ///
@@ -86,7 +86,7 @@ impl SortKeyComputer for SortByErasedType {
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &dyn SegmentReader,
+        segment_reader: &crate::SegmentReader,
     ) -> crate::Result<Self::Child> {
         let inner: Box<dyn ErasedSegmentSortKeyComputer> = match self {
             Self::Field(column_name) => {

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

src/collector/sort_key/sort_by_static_fast_value.rs

@@ -61,7 +61,7 @@ impl<T: FastValue> SortKeyComputer for SortByStaticFastValue<T> {
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &dyn SegmentReader,
+        segment_reader: &SegmentReader,
     ) -> crate::Result<Self::Child> {
         let sort_column_opt = segment_reader.fast_fields().u64_lenient(&self.field)?;
         let (sort_column, _sort_column_type) =

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, SegmentReader};
+use crate::{DocId, Score};
 
 /// Sort by the first value of a string column.
 ///
@@ -35,7 +35,7 @@ impl SortKeyComputer for SortByString {
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &dyn SegmentReader,
+        segment_reader: &crate::SegmentReader,
     ) -> crate::Result<Self::Child> {
         let str_column_opt = segment_reader.fast_fields().str(&self.column_name)?;
         Ok(ByStringColumnSegmentSortKeyComputer { str_column_opt })

src/collector/sort_key/sort_key_computer.rs

@@ -119,7 +119,7 @@ pub trait SortKeyComputer: Sync {
         &self,
         k: usize,
         weight: &dyn crate::query::Weight,
-        reader: &dyn SegmentReader,
+        reader: &crate::SegmentReader,
         segment_ord: u32,
     ) -> crate::Result<Vec<(Self::SortKey, DocAddress)>> {
         let with_scoring = self.requires_scoring();
@@ -135,7 +135,7 @@ pub trait SortKeyComputer: Sync {
     }
 
     /// Builds a child sort key computer for a specific segment.
-    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child>;
+    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child>;
 }
 
 impl<HeadSortKeyComputer, TailSortKeyComputer> SortKeyComputer
@@ -156,7 +156,7 @@ where
         (self.0.comparator(), self.1.comparator())
     }
 
-    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
         Ok((
             self.0.segment_sort_key_computer(segment_reader)?,
             self.1.segment_sort_key_computer(segment_reader)?,
@@ -357,7 +357,7 @@ where
         )
     }
 
-    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &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)?;
@@ -420,7 +420,7 @@ where
         SortKeyComputer4::Comparator,
     );
 
-    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &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)?;
@@ -454,7 +454,7 @@ where
 
 impl<F, SegmentF, TSortKey> SortKeyComputer for F
 where
-    F: 'static + Send + Sync + Fn(&dyn SegmentReader) -> SegmentF,
+    F: 'static + Send + Sync + Fn(&SegmentReader) -> SegmentF,
     SegmentF: 'static + FnMut(DocId) -> TSortKey,
     TSortKey: 'static + PartialOrd + Clone + Send + Sync + std::fmt::Debug,
 {
@@ -462,7 +462,7 @@ where
     type Child = SegmentF;
     type Comparator = NaturalComparator;
 
-    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
         Ok((self)(segment_reader))
     }
 }
@@ -509,10 +509,10 @@ mod tests {
 
     #[test]
     fn test_lazy_score_computer() {
-        let score_computer_primary = |_segment_reader: &dyn SegmentReader| |_doc: DocId| 200u32;
+        let score_computer_primary = |_segment_reader: &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: &dyn SegmentReader| {
+        let score_computer_secondary = move |_segment_reader: &SegmentReader| {
             let call_count_new_clone = call_count_clone.clone();
             move |_doc: DocId| {
                 call_count_new_clone.fetch_add(1, AtomicOrdering::SeqCst);
@@ -572,10 +572,10 @@ mod tests {
 
     #[test]
     fn test_lazy_score_computer_dynamic_ordering() {
-        let score_computer_primary = |_segment_reader: &dyn SegmentReader| |_doc: DocId| 200u32;
+        let score_computer_primary = |_segment_reader: &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: &dyn SegmentReader| {
+        let score_computer_secondary = move |_segment_reader: &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

@@ -32,11 +32,7 @@ where TSortKeyComputer: SortKeyComputer + Send + Sync + 'static
         self.sort_key_computer.check_schema(schema)
     }
 
-    fn for_segment(
-        &self,
-        segment_ord: u32,
-        segment_reader: &dyn SegmentReader,
-    ) -> Result<Self::Child> {
+    fn for_segment(&self, segment_ord: u32, segment_reader: &SegmentReader) -> Result<Self::Child> {
         let segment_sort_key_computer = self
             .sort_key_computer
             .segment_sort_key_computer(segment_reader)?;
@@ -67,7 +63,7 @@ where TSortKeyComputer: SortKeyComputer + Send + Sync + 'static
         &self,
         weight: &dyn Weight,
         segment_ord: u32,
-        reader: &dyn SegmentReader,
+        reader: &SegmentReader,
     ) -> crate::Result<Vec<(TSortKeyComputer::SortKey, DocAddress)>> {
         let k = self.doc_range.end;
         let docs = self
@@ -164,7 +160,7 @@ 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::rng());
+        vals.shuffle(&mut rand::thread_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, SegmentReader, TantivyDocument};
+use crate::{DateTime, DocAddress, Index, Searcher, 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: &dyn SegmentReader,
+        _reader: &SegmentReader,
     ) -> crate::Result<TestSegmentCollector> {
         Ok(TestSegmentCollector {
             segment_id,
@@ -180,7 +180,7 @@ impl Collector for FastFieldTestCollector {
     fn for_segment(
         &self,
         _: SegmentOrdinal,
-        segment_reader: &dyn SegmentReader,
+        segment_reader: &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: &dyn SegmentReader,
+        segment_reader: &SegmentReader,
     ) -> crate::Result<BytesFastFieldSegmentCollector> {
         let column_opt = segment_reader.fast_fields().bytes(&self.field)?;
         Ok(BytesFastFieldSegmentCollector {

src/collector/top_score_collector.rs

@@ -393,7 +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: &dyn SegmentReader| {
+    ///          .tweak_score(move |segment_reader: &SegmentReader| {
     ///             // The argument is a function that returns our scoring
     ///             // function.
     ///             //
@@ -442,7 +442,7 @@ pub struct TweakScoreFn<F>(F);
 
 impl<F, TTweakScoreSortKeyFn, TSortKey> SortKeyComputer for TweakScoreFn<F>
 where
-    F: 'static + Send + Sync + Fn(&dyn SegmentReader) -> TTweakScoreSortKeyFn,
+    F: 'static + Send + Sync + Fn(&SegmentReader) -> TTweakScoreSortKeyFn,
     TTweakScoreSortKeyFn: 'static + Fn(DocId, Score) -> TSortKey,
     TweakScoreSegmentSortKeyComputer<TTweakScoreSortKeyFn>:
         SegmentSortKeyComputer<SortKey = TSortKey, SegmentSortKey = TSortKey>,
@@ -458,7 +458,7 @@ where
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &dyn SegmentReader,
+        segment_reader: &SegmentReader,
     ) -> crate::Result<Self::Child> {
         Ok({
             TweakScoreSegmentSortKeyComputer {
@@ -1525,7 +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: &dyn SegmentReader| move |doc: DocId| doc);
+            .order_by(move |_segment_reader: &SegmentReader| move |doc: DocId| doc);
         let score_docs: Vec<(u32, DocAddress)> =
             index.reader()?.searcher().search(&text_query, &collector)?;
         assert_eq!(
@@ -1543,7 +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: &dyn SegmentReader| move |doc: DocId| doc);
+            .order_by(move |_segment_reader: &SegmentReader| move |doc: DocId| doc);
         let score_docs: Vec<(u32, DocAddress)> = index
             .reader()
             .unwrap()

src/core/json_utils.rs

@@ -4,7 +4,7 @@ use common::{replace_in_place, JsonPathWriter};
 use rustc_hash::FxHashMap;
 
 use crate::indexer::indexing_term::IndexingTerm;
-use crate::postings::{IndexingContext, IndexingPosition, PostingsWriter};
+use crate::postings::{IndexingContext, IndexingPosition, PostingsWriter as _, PostingsWriterEnum};
 use crate::schema::document::{ReferenceValue, ReferenceValueLeaf, Value};
 use crate::schema::{Type, DATE_TIME_PRECISION_INDEXED};
 use crate::time::format_description::well_known::Rfc3339;
@@ -80,7 +80,7 @@ fn index_json_object<'a, V: Value<'a>>(
     text_analyzer: &mut TextAnalyzer,
     term_buffer: &mut IndexingTerm,
     json_path_writer: &mut JsonPathWriter,
-    postings_writer: &mut dyn PostingsWriter,
+    postings_writer: &mut PostingsWriterEnum,
     ctx: &mut IndexingContext,
     positions_per_path: &mut IndexingPositionsPerPath,
 ) {
@@ -110,7 +110,7 @@ pub(crate) fn index_json_value<'a, V: Value<'a>>(
     text_analyzer: &mut TextAnalyzer,
     term_buffer: &mut IndexingTerm,
     json_path_writer: &mut JsonPathWriter,
-    postings_writer: &mut dyn PostingsWriter,
+    postings_writer: &mut PostingsWriterEnum,
     ctx: &mut IndexingContext,
     positions_per_path: &mut IndexingPositionsPerPath,
 ) {

src/core/searcher.rs

@@ -4,7 +4,7 @@ use std::{fmt, io};
 
 use crate::collector::Collector;
 use crate::core::Executor;
-use crate::index::{ArcSegmentReader, SegmentId, SegmentReader};
+use crate::index::{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: &[ArcSegmentReader],
+        segment_readers: &[SegmentReader],
         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.as_ref().inverted_index(term.field())?;
+            let inverted_index = segment_reader.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.as_ref().inverted_index(term.field())?;
+            let inverted_index = segment_reader.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) -> &[ArcSegmentReader] {
+    pub fn segment_readers(&self) -> &[SegmentReader] {
         &self.inner.segment_readers
     }
 
     /// Returns the segment_reader associated with the given segment_ord
-    pub fn segment_reader(&self, segment_ord: u32) -> &dyn SegmentReader {
-        self.inner.segment_readers[segment_ord as usize].as_ref()
+    pub fn segment_reader(&self, segment_ord: u32) -> &SegmentReader {
+        &self.inner.segment_readers[segment_ord as usize]
     }
 
     /// Runs a query on the segment readers wrapped by the searcher.
@@ -229,11 +229,7 @@ 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.as_ref(),
-                )
+                collector.collect_segment(weight.as_ref(), segment_ord as u32, segment_reader)
             },
             segment_readers.iter().enumerate(),
         )?;
@@ -263,7 +259,7 @@ impl From<Arc<SearcherInner>> for Searcher {
 pub(crate) struct SearcherInner {
     schema: Schema,
     index: Index,
-    segment_readers: Vec<ArcSegmentReader>,
+    segment_readers: Vec<SegmentReader>,
     store_readers: Vec<StoreReader>,
     generation: TrackedObject<SearcherGeneration>,
 }
@@ -273,7 +269,7 @@ impl SearcherInner {
     pub(crate) fn new(
         schema: Schema,
         index: Index,
-        segment_readers: Vec<ArcSegmentReader>,
+        segment_readers: Vec<SegmentReader>,
         generation: TrackedObject<SearcherGeneration>,
         doc_store_cache_num_blocks: usize,
     ) -> io::Result<SearcherInner> {
@@ -305,7 +301,7 @@ impl fmt::Debug for Searcher {
         let segment_ids = self
             .segment_readers()
             .iter()
-            .map(|segment_reader| segment_reader.segment_id())
+            .map(SegmentReader::segment_id)
             .collect::<Vec<_>>();
         write!(f, "Searcher({segment_ids:?})")
     }

src/docset.rs

@@ -1,5 +1,7 @@
 use std::borrow::{Borrow, BorrowMut};
 
+use common::BitSet;
+
 use crate::fastfield::AliveBitSet;
 use crate::DocId;
 
@@ -51,55 +53,31 @@ 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.
+    /// Seeks to the target if possible and returns true if the target is in the DocSet.
     ///
     /// DocSets that already have an efficient `seek` method don't need to implement
-    /// `seek_danger`.
+    /// `seek_into_the_danger_zone`. All wrapper DocSets should forward
+    /// `seek_into_the_danger_zone` to the underlying DocSet.
     ///
-    /// 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())
+    /// ## API Behaviour
+    /// If `seek_into_the_danger_zone` is returning true, a call to `doc()` has to return target.
+    /// If `seek_into_the_danger_zone` is returning false, a call to `doc()` may return any doc
+    /// between the last doc that matched and target or a doc that is a valid next hit after
+    /// target. The DocSet is considered to be in an invalid state until
+    /// `seek_into_the_danger_zone` returns true again.
+    ///
+    /// `target` needs to be equal or larger than `doc` when in a valid state.
+    ///
+    /// Consecutive calls are not allowed to have decreasing `target` values.
+    ///
+    /// # Warning
+    /// This is an advanced API used by intersection. The API contract is tricky, avoid using it.
+    fn seek_into_the_danger_zone(&mut self, target: DocId) -> bool {
+        let current_doc = self.doc();
+        if current_doc < target {
+            self.seek(target);
         }
+        self.doc() == target
     }
 
     /// Fills a given mutable buffer with the next doc ids from the
@@ -130,6 +108,15 @@ pub trait DocSet: Send {
         buffer.len()
     }
 
+    /// TODO comment on the size of the bitset
+    fn fill_bitset(&mut self, bitset: &mut BitSet) {
+        let mut doc = self.doc();
+        while doc != TERMINATED {
+            bitset.insert(doc);
+            doc = self.advance();
+        }
+    }
+
     /// Returns the current document
     /// Right after creating a new `DocSet`, the docset points to the first document.
     ///
@@ -190,17 +177,6 @@ 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()
@@ -210,8 +186,8 @@ impl DocSet for &mut dyn DocSet {
         (**self).seek(target)
     }
 
-    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
-        (**self).seek_danger(target)
+    fn seek_into_the_danger_zone(&mut self, target: DocId) -> bool {
+        (**self).seek_into_the_danger_zone(target)
     }
 
     fn doc(&self) -> u32 {
@@ -246,9 +222,9 @@ impl<TDocSet: DocSet + ?Sized> DocSet for Box<TDocSet> {
         unboxed.seek(target)
     }
 
-    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
+    fn seek_into_the_danger_zone(&mut self, target: DocId) -> bool {
         let unboxed: &mut TDocSet = self.borrow_mut();
-        unboxed.seek_danger(target)
+        unboxed.seek_into_the_danger_zone(target)
     }
 
     fn fill_buffer(&mut self, buffer: &mut [DocId; COLLECT_BLOCK_BUFFER_LEN]) -> usize {

src/fastfield/alive_bitset.rs

@@ -162,7 +162,7 @@ mod tests {
 mod bench {
 
     use rand::prelude::IteratorRandom;
-    use rand::rng;
+    use rand::thread_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 rng()).unwrap();
+        let i = (0..raw.len()).choose(&mut thread_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};
+    use crate::{Index, IndexWriter, SegmentReader};
 
     pub static SCHEMA: Lazy<Schema> = Lazy::new(|| {
         let mut schema_builder = Schema::builder();
@@ -430,7 +430,7 @@ mod tests {
             .searcher()
             .segment_readers()
             .iter()
-            .map(|segment_reader| segment_reader.segment_id())
+            .map(SegmentReader::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.random_range(-ONE_HOUR_IN_MICROSECS..ONE_HOUR_IN_MICROSECS);
+            let t = T0 + rng.gen_range(-ONE_HOUR_IN_MICROSECS..ONE_HOUR_IN_MICROSECS);
             DateTime::from_timestamp_micros(t)
         })
         .take(1_000)

src/functional_test.rs

@@ -1,6 +1,6 @@
 use std::collections::HashSet;
 
-use rand::{rng, Rng};
+use rand::{thread_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 = rng();
+    let mut rng = thread_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.random_range(0..4);
+        let num_docs: usize = rng.gen_range(0..4);
         if !doc_set.is_empty() {
-            let doc_to_remove_id = rng.random_range(0..doc_set.len());
+            let doc_to_remove_id = rng.gen_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::IndexedRandom;
-    let mut rng = rng();
+    use rand::seq::SliceRandom;
+    let mut rng = thread_rng();
     let tokens: Vec<_> = LOREM.split(' ').collect();
-    let random_val = rng.random_range(0..20);
+    let random_val = rng.gen_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 = rng();
+    let mut rng = thread_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.random_range(0..20);
+        let random_val = rng.gen_range(0..20);
         if random_val == 0 {
             index_writer.commit()?;
             committed_docs.extend(&uncommitted_docs);

src/index/codec_configuration.rs

@@ -0,0 +1,46 @@
+use std::borrow::Cow;
+
+use serde::{Deserialize, Serialize};
+
+use crate::codec::{Codec, StandardCodec};
+
+/// A small struct representing a codec configuration.
+/// It is meant to be serialized in the index metadata file.
+#[derive(Serialize, Deserialize, Clone, Debug)]
+pub struct CodecConfiguration {
+    name: Cow<'static, str>,
+    #[serde(default, skip_serializing_if = "serde_json::Value::is_null")]
+    props: serde_json::Value,
+}
+
+impl CodecConfiguration {
+    /// Builds the codec given a codec_configuration.
+    ///
+    /// If the configuration codec name does not match the type C,
+    /// a tantivy error is returned.
+    pub fn to_codec<C: Codec>(&self) -> crate::Result<C> {
+        if self.name != C::NAME {
+            return Err(crate::TantivyError::InvalidArgument(format!(
+                "Codec name mismatch: expected {}, got {}",
+                C::NAME,
+                self.name
+            )));
+        }
+        C::from_json_props(&self.props)
+    }
+}
+
+impl<'a, C: Codec> From<&'a C> for CodecConfiguration {
+    fn from(codec: &'a C) -> Self {
+        CodecConfiguration {
+            name: Cow::Borrowed(C::NAME),
+            props: codec.to_json_props(),
+        }
+    }
+}
+
+impl Default for CodecConfiguration {
+    fn default() -> Self {
+        CodecConfiguration::from(&StandardCodec)
+    }
+}

src/index/index.rs

@@ -8,13 +8,15 @@ use std::thread::available_parallelism;
 use super::segment::Segment;
 use super::segment_reader::merge_field_meta_data;
 use super::{FieldMetadata, IndexSettings};
+use crate::codec::StandardCodec;
 use crate::core::{Executor, META_FILEPATH};
 use crate::directory::error::OpenReadError;
 #[cfg(feature = "mmap")]
 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, SegmentReader};
+use crate::index::codec_configuration::CodecConfiguration;
+use crate::index::{IndexMeta, SegmentId, SegmentMeta, SegmentMetaInventory};
 use crate::indexer::index_writer::{
     IndexWriterOptions, MAX_NUM_THREAD, MEMORY_BUDGET_NUM_BYTES_MIN,
 };
@@ -24,7 +26,7 @@ use crate::reader::{IndexReader, IndexReaderBuilder};
 use crate::schema::document::Document;
 use crate::schema::{Field, FieldType, Schema};
 use crate::tokenizer::{TextAnalyzer, TokenizerManager};
-use crate::TantivySegmentReader;
+use crate::SegmentReader;
 
 fn load_metas(
     directory: &dyn Directory,
@@ -59,6 +61,7 @@ fn save_new_metas(
     schema: Schema,
     index_settings: IndexSettings,
     directory: &dyn Directory,
+    codec: CodecConfiguration,
 ) -> crate::Result<()> {
     save_metas(
         &IndexMeta {
@@ -67,6 +70,7 @@ fn save_new_metas(
             schema,
             opstamp: 0u64,
             payload: None,
+            codec,
         },
         directory,
     )?;
@@ -101,18 +105,21 @@ fn save_new_metas(
 /// };
 /// let index = Index::builder().schema(schema).settings(settings).create_in_ram();
 /// ```
-pub struct IndexBuilder {
+pub struct IndexBuilder<Codec: crate::codec::Codec = StandardCodec> {
     schema: Option<Schema>,
     index_settings: IndexSettings,
     tokenizer_manager: TokenizerManager,
     fast_field_tokenizer_manager: TokenizerManager,
+    codec: Codec,
 }
-impl Default for IndexBuilder {
+
+impl Default for IndexBuilder<StandardCodec> {
     fn default() -> Self {
         IndexBuilder::new()
     }
 }
-impl IndexBuilder {
+
+impl IndexBuilder<StandardCodec> {
     /// Creates a new `IndexBuilder`
     pub fn new() -> Self {
         Self {
@@ -120,6 +127,21 @@ impl IndexBuilder {
             index_settings: IndexSettings::default(),
             tokenizer_manager: TokenizerManager::default(),
             fast_field_tokenizer_manager: TokenizerManager::default(),
+            codec: StandardCodec,
+        }
+    }
+}
+
+impl<Codec: crate::codec::Codec> IndexBuilder<Codec> {
+    /// Set the codec
+    #[must_use]
+    pub fn codec<NewCodec: crate::codec::Codec>(self, codec: NewCodec) -> IndexBuilder<NewCodec> {
+        IndexBuilder {
+            schema: self.schema,
+            index_settings: self.index_settings,
+            tokenizer_manager: self.tokenizer_manager,
+            fast_field_tokenizer_manager: self.fast_field_tokenizer_manager,
+            codec,
         }
     }
 
@@ -154,7 +176,7 @@ impl IndexBuilder {
     /// The index will be allocated in anonymous memory.
     /// This is useful for indexing small set of documents
     /// for instances like unit test or temporary in memory index.
-    pub fn create_in_ram(self) -> Result<Index, TantivyError> {
+    pub fn create_in_ram(self) -> Result<Index<Codec>, TantivyError> {
         let ram_directory = RamDirectory::create();
         self.create(ram_directory)
     }
@@ -165,7 +187,7 @@ impl IndexBuilder {
     /// If a previous index was in this directory, it returns an
     /// [`TantivyError::IndexAlreadyExists`] error.
     #[cfg(feature = "mmap")]
-    pub fn create_in_dir<P: AsRef<Path>>(self, directory_path: P) -> crate::Result<Index> {
+    pub fn create_in_dir<P: AsRef<Path>>(self, directory_path: P) -> crate::Result<Index<Codec>> {
         let mmap_directory: Box<dyn Directory> = Box::new(MmapDirectory::open(directory_path)?);
         if Index::exists(&*mmap_directory)? {
             return Err(TantivyError::IndexAlreadyExists);
@@ -186,7 +208,7 @@ impl IndexBuilder {
         self,
         dir: impl Into<Box<dyn Directory>>,
         mem_budget: usize,
-    ) -> crate::Result<SingleSegmentIndexWriter<D>> {
+    ) -> crate::Result<SingleSegmentIndexWriter<Codec, D>> {
         let index = self.create(dir)?;
         let index_simple_writer = SingleSegmentIndexWriter::new(index, mem_budget)?;
         Ok(index_simple_writer)
@@ -202,7 +224,7 @@ impl IndexBuilder {
     /// For other unit tests, prefer the [`RamDirectory`], see:
     /// [`IndexBuilder::create_in_ram()`].
     #[cfg(feature = "mmap")]
-    pub fn create_from_tempdir(self) -> crate::Result<Index> {
+    pub fn create_from_tempdir(self) -> crate::Result<Index<Codec>> {
         let mmap_directory: Box<dyn Directory> = Box::new(MmapDirectory::create_from_tempdir()?);
         self.create(mmap_directory)
     }
@@ -215,12 +237,15 @@ impl IndexBuilder {
     }
 
     /// Opens or creates a new index in the provided directory
-    pub fn open_or_create<T: Into<Box<dyn Directory>>>(self, dir: T) -> crate::Result<Index> {
+    pub fn open_or_create<T: Into<Box<dyn Directory>>>(
+        self,
+        dir: T,
+    ) -> crate::Result<Index<Codec>> {
         let dir: Box<dyn Directory> = dir.into();
         if !Index::exists(&*dir)? {
             return self.create(dir);
         }
-        let mut index = Index::open(dir)?;
+        let mut index: Index<Codec> = Index::<Codec>::open_with_codec(dir)?;
         index.set_tokenizers(self.tokenizer_manager.clone());
         if index.schema() == self.get_expect_schema()? {
             Ok(index)
@@ -244,18 +269,25 @@ impl IndexBuilder {
     /// Creates a new index given an implementation of the trait `Directory`.
     ///
     /// If a directory previously existed, it will be erased.
-    fn create<T: Into<Box<dyn Directory>>>(self, dir: T) -> crate::Result<Index> {
+    pub fn create<T: Into<Box<dyn Directory>>>(self, dir: T) -> crate::Result<Index<Codec>> {
+        self.create_avoid_monomorphization(dir.into())
+    }
+
+    fn create_avoid_monomorphization(self, dir: Box<dyn Directory>) -> crate::Result<Index<Codec>> {
         self.validate()?;
-        let dir = dir.into();
         let directory = ManagedDirectory::wrap(dir)?;
+        let codec: CodecConfiguration = CodecConfiguration::from(&self.codec);
         save_new_metas(
             self.get_expect_schema()?,
             self.index_settings.clone(),
             &directory,
+            codec,
         )?;
-        let mut metas = IndexMeta::with_schema(self.get_expect_schema()?);
+        let schema = self.get_expect_schema()?;
+        let mut metas = IndexMeta::with_schema_and_codec(schema, &self.codec);
         metas.index_settings = self.index_settings;
-        let mut index = Index::open_from_metas(directory, &metas, SegmentMetaInventory::default());
+        let mut index: Index<Codec> =
+            Index::<Codec>::open_from_metas(directory, &metas, SegmentMetaInventory::default())?;
         index.set_tokenizers(self.tokenizer_manager);
         index.set_fast_field_tokenizers(self.fast_field_tokenizer_manager);
         Ok(index)
@@ -264,7 +296,7 @@ impl IndexBuilder {
 
 /// Search Index
 #[derive(Clone)]
-pub struct Index {
+pub struct Index<Codec: crate::codec::Codec = crate::codec::StandardCodec> {
     directory: ManagedDirectory,
     schema: Schema,
     settings: IndexSettings,
@@ -272,6 +304,7 @@ pub struct Index {
     tokenizers: TokenizerManager,
     fast_field_tokenizers: TokenizerManager,
     inventory: SegmentMetaInventory,
+    codec: Codec,
 }
 
 impl Index {
@@ -279,41 +312,6 @@ impl Index {
     pub fn builder() -> IndexBuilder {
         IndexBuilder::new()
     }
-    /// Examines the directory to see if it contains an index.
-    ///
-    /// Effectively, it only checks for the presence of the `meta.json` file.
-    pub fn exists(dir: &dyn Directory) -> Result<bool, OpenReadError> {
-        dir.exists(&META_FILEPATH)
-    }
-
-    /// Accessor to the search executor.
-    ///
-    /// This pool is used by default when calling `searcher.search(...)`
-    /// to perform search on the individual segments.
-    ///
-    /// By default the executor is single thread, and simply runs in the calling thread.
-    pub fn search_executor(&self) -> &Executor {
-        &self.executor
-    }
-
-    /// Replace the default single thread search executor pool
-    /// by a thread pool with a given number of threads.
-    pub fn set_multithread_executor(&mut self, num_threads: usize) -> crate::Result<()> {
-        self.executor = Executor::multi_thread(num_threads, "tantivy-search-")?;
-        Ok(())
-    }
-
-    /// Custom thread pool by a outer thread pool.
-    pub fn set_executor(&mut self, executor: Executor) {
-        self.executor = executor;
-    }
-
-    /// Replace the default single thread search executor pool
-    /// by a thread pool with as many threads as there are CPUs on the system.
-    pub fn set_default_multithread_executor(&mut self) -> crate::Result<()> {
-        let default_num_threads = available_parallelism()?.get();
-        self.set_multithread_executor(default_num_threads)
-    }
 
     /// Creates a new index using the [`RamDirectory`].
     ///
@@ -324,6 +322,13 @@ impl Index {
         IndexBuilder::new().schema(schema).create_in_ram().unwrap()
     }
 
+    /// Examines the directory to see if it contains an index.
+    ///
+    /// Effectively, it only checks for the presence of the `meta.json` file.
+    pub fn exists(directory: &dyn Directory) -> Result<bool, OpenReadError> {
+        directory.exists(&META_FILEPATH)
+    }
+
     /// Creates a new index in a given filepath.
     /// The index will use the [`MmapDirectory`].
     ///
@@ -370,20 +375,107 @@ impl Index {
         schema: Schema,
         settings: IndexSettings,
     ) -> crate::Result<Index> {
-        let dir: Box<dyn Directory> = dir.into();
+        Self::create_to_avoid_monomorphization(dir.into(), schema, settings)
+    }
+
+    fn create_to_avoid_monomorphization(
+        dir: Box<dyn Directory>,
+        schema: Schema,
+        settings: IndexSettings,
+    ) -> crate::Result<Index> {
         let mut builder = IndexBuilder::new().schema(schema);
         builder = builder.settings(settings);
         builder.create(dir)
     }
 
+    /// Opens a new directory from an index path.
+    #[cfg(feature = "mmap")]
+    pub fn open_in_dir<P: AsRef<Path>>(directory_path: P) -> crate::Result<Index> {
+        Self::open_in_dir_to_avoid_monomorphization(directory_path.as_ref())
+    }
+
+    #[inline(never)]
+    fn open_in_dir_to_avoid_monomorphization(directory_path: &Path) -> crate::Result<Index> {
+        let mmap_directory = MmapDirectory::open(directory_path)?;
+        Index::open(mmap_directory)
+    }
+
+    /// Open the index using the provided directory
+    pub fn open<T: Into<Box<dyn Directory>>>(directory: T) -> crate::Result<Index> {
+        Index::<StandardCodec>::open_with_codec(directory.into())
+    }
+}
+
+impl<Codec: crate::codec::Codec> Index<Codec> {
+    /// Returns a version of this index with the standard codec.
+    /// This is useful when you need to pass the index to APIs that
+    /// don't care about the codec (e.g., for reading).
+    pub(crate) fn with_standard_codec(&self) -> Index<StandardCodec> {
+        Index {
+            directory: self.directory.clone(),
+            schema: self.schema.clone(),
+            settings: self.settings.clone(),
+            executor: self.executor.clone(),
+            tokenizers: self.tokenizers.clone(),
+            fast_field_tokenizers: self.fast_field_tokenizers.clone(),
+            inventory: self.inventory.clone(),
+            codec: StandardCodec,
+        }
+    }
+
+    /// Open the index using the provided directory
+    #[inline(never)]
+    pub fn open_with_codec(directory: Box<dyn Directory>) -> crate::Result<Index<Codec>> {
+        let directory = ManagedDirectory::wrap(directory)?;
+        let inventory = SegmentMetaInventory::default();
+        let metas = load_metas(&directory, &inventory)?;
+        let index: Index<Codec> = Index::<Codec>::open_from_metas(directory, &metas, inventory)?;
+        Ok(index)
+    }
+
+    /// Accessor to the codec.
+    pub fn codec(&self) -> &Codec {
+        &self.codec
+    }
+
+    /// Accessor to the search executor.
+    ///
+    /// This pool is used by default when calling `searcher.search(...)`
+    /// to perform search on the individual segments.
+    ///
+    /// By default the executor is single thread, and simply runs in the calling thread.
+    pub fn search_executor(&self) -> &Executor {
+        &self.executor
+    }
+
+    /// Replace the default single thread search executor pool
+    /// by a thread pool with a given number of threads.
+    pub fn set_multithread_executor(&mut self, num_threads: usize) -> crate::Result<()> {
+        self.executor = Executor::multi_thread(num_threads, "tantivy-search-")?;
+        Ok(())
+    }
+
+    /// Custom thread pool by a outer thread pool.
+    pub fn set_executor(&mut self, executor: Executor) {
+        self.executor = executor;
+    }
+
+    /// Replace the default single thread search executor pool
+    /// by a thread pool with as many threads as there are CPUs on the system.
+    pub fn set_default_multithread_executor(&mut self) -> crate::Result<()> {
+        let default_num_threads = available_parallelism()?.get();
+        self.set_multithread_executor(default_num_threads)
+    }
+
     /// Creates a new index given a directory and an [`IndexMeta`].
-    fn open_from_metas(
+    fn open_from_metas<C: crate::codec::Codec>(
         directory: ManagedDirectory,
         metas: &IndexMeta,
         inventory: SegmentMetaInventory,
-    ) -> Index {
+    ) -> crate::Result<Index<C>> {
         let schema = metas.schema.clone();
-        Index {
+        let codec = metas.codec.to_codec::<C>()?;
+        Ok(Index {
             settings: metas.index_settings.clone(),
             directory,
             schema,
@@ -391,7 +483,8 @@ impl Index {
             fast_field_tokenizers: TokenizerManager::default(),
             executor: Executor::single_thread(),
             inventory,
-        }
+            codec,
+        })
     }
 
     /// Setter for the tokenizer manager.
@@ -447,7 +540,7 @@ impl Index {
     /// Create a default [`IndexReader`] for the given index.
     ///
     /// See [`Index.reader_builder()`].
-    pub fn reader(&self) -> crate::Result<IndexReader> {
+    pub fn reader(&self) -> crate::Result<IndexReader<Codec>> {
         self.reader_builder().try_into()
     }
 
@@ -455,17 +548,10 @@ impl Index {
     ///
     /// Most project should create at most one reader for a given index.
     /// This method is typically called only once per `Index` instance.
-    pub fn reader_builder(&self) -> IndexReaderBuilder {
+    pub fn reader_builder(&self) -> IndexReaderBuilder<Codec> {
         IndexReaderBuilder::new(self.clone())
     }
 
-    /// Opens a new directory from an index path.
-    #[cfg(feature = "mmap")]
-    pub fn open_in_dir<P: AsRef<Path>>(directory_path: P) -> crate::Result<Index> {
-        let mmap_directory = MmapDirectory::open(directory_path)?;
-        Index::open(mmap_directory)
-    }
-
     /// Returns the list of the segment metas tracked by the index.
     ///
     /// Such segments can of course be part of the index,
@@ -492,7 +578,7 @@ impl Index {
         let segments = self.searchable_segments()?;
         let fields_metadata: Vec<Vec<FieldMetadata>> = segments
             .into_iter()
-            .map(|segment| TantivySegmentReader::open(&segment)?.fields_metadata())
+            .map(|segment| SegmentReader::open(&segment)?.fields_metadata())
             .collect::<Result<_, _>>()?;
         Ok(merge_field_meta_data(fields_metadata))
     }
@@ -506,16 +592,6 @@ impl Index {
         self.inventory.new_segment_meta(segment_id, max_doc)
     }
 
-    /// Open the index using the provided directory
-    pub fn open<T: Into<Box<dyn Directory>>>(directory: T) -> crate::Result<Index> {
-        let directory = directory.into();
-        let directory = ManagedDirectory::wrap(directory)?;
-        let inventory = SegmentMetaInventory::default();
-        let metas = load_metas(&directory, &inventory)?;
-        let index = Index::open_from_metas(directory, &metas, inventory);
-        Ok(index)
-    }
-
     /// Reads the index meta file from the directory.
     pub fn load_metas(&self) -> crate::Result<IndexMeta> {
         load_metas(self.directory(), &self.inventory)
@@ -539,7 +615,7 @@ impl Index {
     pub fn writer_with_options<D: Document>(
         &self,
         options: IndexWriterOptions,
-    ) -> crate::Result<IndexWriter<D>> {
+    ) -> crate::Result<IndexWriter<Codec, D>> {
         let directory_lock = self
             .directory
             .acquire_lock(&INDEX_WRITER_LOCK)
@@ -581,7 +657,7 @@ impl Index {
         &self,
         num_threads: usize,
         overall_memory_budget_in_bytes: usize,
-    ) -> crate::Result<IndexWriter<D>> {
+    ) -> crate::Result<IndexWriter<Codec, D>> {
         let memory_arena_in_bytes_per_thread = overall_memory_budget_in_bytes / num_threads;
         let options = IndexWriterOptions::builder()
             .num_worker_threads(num_threads)
@@ -595,7 +671,7 @@ impl Index {
     /// That index writer only simply has a single thread and a memory budget of 15 MB.
     /// Using a single thread gives us a deterministic allocation of DocId.
     #[cfg(test)]
-    pub fn writer_for_tests<D: Document>(&self) -> crate::Result<IndexWriter<D>> {
+    pub fn writer_for_tests<D: Document>(&self) -> crate::Result<IndexWriter<Codec, D>> {
         self.writer_with_num_threads(1, MEMORY_BUDGET_NUM_BYTES_MIN)
     }
 
@@ -613,7 +689,7 @@ impl Index {
     pub fn writer<D: Document>(
         &self,
         memory_budget_in_bytes: usize,
-    ) -> crate::Result<IndexWriter<D>> {
+    ) -> crate::Result<IndexWriter<Codec, D>> {
         let mut num_threads = std::cmp::min(available_parallelism()?.get(), MAX_NUM_THREAD);
         let memory_budget_num_bytes_per_thread = memory_budget_in_bytes / num_threads;
         if memory_budget_num_bytes_per_thread < MEMORY_BUDGET_NUM_BYTES_MIN {
@@ -640,7 +716,7 @@ impl Index {
     }
 
     /// Returns the list of segments that are searchable
-    pub fn searchable_segments(&self) -> crate::Result<Vec<Segment>> {
+    pub fn searchable_segments(&self) -> crate::Result<Vec<Segment<Codec>>> {
         Ok(self
             .searchable_segment_metas()?
             .into_iter()
@@ -649,12 +725,12 @@ impl Index {
     }
 
     #[doc(hidden)]
-    pub fn segment(&self, segment_meta: SegmentMeta) -> Segment {
+    pub fn segment(&self, segment_meta: SegmentMeta) -> Segment<Codec> {
         Segment::for_index(self.clone(), segment_meta)
     }
 
     /// Creates a new segment.
-    pub fn new_segment(&self) -> Segment {
+    pub fn new_segment(&self) -> Segment<Codec> {
         let segment_meta = self
             .inventory
             .new_segment_meta(SegmentId::generate_random(), 0);

src/index/index_meta.rs

@@ -7,7 +7,8 @@ use std::sync::Arc;
 use serde::{Deserialize, Serialize};
 
 use super::SegmentComponent;
-use crate::index::SegmentId;
+use crate::codec::Codec;
+use crate::index::{CodecConfiguration, SegmentId};
 use crate::schema::Schema;
 use crate::store::Compressor;
 use crate::{Inventory, Opstamp, TrackedObject};
@@ -320,6 +321,8 @@ pub struct IndexMeta {
     /// This payload is entirely unused by tantivy.
     #[serde(skip_serializing_if = "Option::is_none")]
     pub payload: Option<String>,
+    /// Codec configuration for the index.
+    pub codec: CodecConfiguration,
 }
 
 #[derive(Deserialize, Debug)]
@@ -331,6 +334,8 @@ struct UntrackedIndexMeta {
     pub opstamp: Opstamp,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub payload: Option<String>,
+    #[serde(default)]
+    pub codec: CodecConfiguration,
 }
 
 impl UntrackedIndexMeta {
@@ -345,6 +350,7 @@ impl UntrackedIndexMeta {
             schema: self.schema,
             opstamp: self.opstamp,
             payload: self.payload,
+            codec: self.codec,
         }
     }
 }
@@ -355,13 +361,14 @@ impl IndexMeta {
     ///
     /// This new index does not contains any segments.
     /// Opstamp will the value `0u64`.
-    pub fn with_schema(schema: Schema) -> IndexMeta {
+    pub fn with_schema_and_codec<C: Codec>(schema: Schema, codec: &C) -> IndexMeta {
         IndexMeta {
             index_settings: IndexSettings::default(),
             segments: vec![],
             schema,
             opstamp: 0u64,
             payload: None,
+            codec: CodecConfiguration::from(codec),
         }
     }
 
@@ -412,11 +419,12 @@ mod tests {
             schema,
             opstamp: 0u64,
             payload: None,
+            codec: Default::default(),
         };
         let json = serde_json::ser::to_string(&index_metas).expect("serialization failed");
         assert_eq!(
             json,
-            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}"#
+            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,"codec":{"name":"standard"}}"#
         );
 
         let deser_meta: UntrackedIndexMeta = serde_json::from_str(&json).unwrap();

src/index/inverted_index_reader.rs

@@ -1,12 +1,8 @@
-#[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};
+use common::{BinarySerializable, ByteCount, OwnedBytes};
 #[cfg(feature = "quickwit")]
 use futures_util::{FutureExt, StreamExt, TryStreamExt};
 #[cfg(feature = "quickwit")]
@@ -14,9 +10,13 @@ use itertools::Itertools;
 #[cfg(feature = "quickwit")]
 use tantivy_fst::automaton::{AlwaysMatch, Automaton};
 
+use crate::codec::postings::PostingsCodec;
+use crate::codec::{Codec, ObjectSafeCodec, StandardCodec};
 use crate::directory::FileSlice;
-use crate::positions::PositionReader;
-use crate::postings::{BlockSegmentPostings, SegmentPostings, TermInfo};
+use crate::fieldnorm::FieldNormReader;
+use crate::postings::{Postings, TermInfo};
+use crate::query::term_query::TermScorer;
+use crate::query::{Bm25Weight, PhraseScorer, Scorer};
 use crate::schema::{IndexRecordOption, Term, Type};
 use crate::termdict::TermDictionary;
 
@@ -32,120 +32,21 @@ use crate::termdict::TermDictionary;
 ///
 /// `InvertedIndexReader` are created by calling
 /// [`SegmentReader::inverted_index()`](crate::SegmentReader::inverted_index).
-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 {
+pub struct InvertedIndexReader {
     termdict: TermDictionary,
     postings_file_slice: FileSlice,
     positions_file_slice: FileSlice,
     record_option: IndexRecordOption,
     total_num_tokens: u64,
+    codec: Arc<dyn ObjectSafeCodec>,
 }
 
 /// Object that records the amount of space used by a field in an inverted index.
-pub struct InvertedIndexFieldSpace {
-    /// The JSON field name (without the parent field).
+pub(crate) struct InvertedIndexFieldSpace {
     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,
 }
 
@@ -167,33 +68,36 @@ impl InvertedIndexFieldSpace {
     }
 }
 
-impl TantivyInvertedIndexReader {
+impl InvertedIndexReader {
     pub(crate) fn new(
         termdict: TermDictionary,
         postings_file_slice: FileSlice,
         positions_file_slice: FileSlice,
         record_option: IndexRecordOption,
-    ) -> io::Result<TantivyInvertedIndexReader> {
+        codec: Arc<dyn ObjectSafeCodec>,
+    ) -> io::Result<InvertedIndexReader> {
         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(TantivyInvertedIndexReader {
+        Ok(InvertedIndexReader {
             termdict,
             postings_file_slice: postings_body,
             positions_file_slice,
             record_option,
             total_num_tokens,
+            codec,
         })
     }
 
     /// Creates an empty `InvertedIndexReader` object, which
     /// contains no terms at all.
-    pub fn empty(record_option: IndexRecordOption) -> TantivyInvertedIndexReader {
-        TantivyInvertedIndexReader {
+    pub fn empty(record_option: IndexRecordOption) -> InvertedIndexReader {
+        InvertedIndexReader {
             termdict: TermDictionary::empty(),
             postings_file_slice: FileSlice::empty(),
             positions_file_slice: FileSlice::empty(),
             record_option,
             total_num_tokens: 0u64,
+            codec: Arc::new(StandardCodec),
         }
     }
 
@@ -265,38 +169,98 @@ impl TantivyInvertedIndexReader {
         Ok(fields)
     }
 
-    /// Returns a block postings given a `Term`.
-    /// This method is for an advanced usage only.
-    ///
-    /// Most users should prefer using [`Self::read_postings()`] instead.
-    pub fn read_block_postings(
-        &self,
-        term: &Term,
-        option: IndexRecordOption,
-    ) -> io::Result<Option<BlockSegmentPostings>> {
-        self.get_term_info(term)?
-            .map(move |term_info| self.read_block_postings_from_terminfo(&term_info, option))
-            .transpose()
-    }
-
-    /// 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.
-    pub fn read_block_postings_from_terminfo(
+    pub(crate) fn new_term_scorer_specialized<C: Codec>(
         &self,
         term_info: &TermInfo,
-        requested_option: IndexRecordOption,
-    ) -> io::Result<BlockSegmentPostings> {
+        option: IndexRecordOption,
+        fieldnorm_reader: FieldNormReader,
+        similarity_weight: Bm25Weight,
+        codec: &C,
+    ) -> io::Result<TermScorer<<<C as Codec>::PostingsCodec as PostingsCodec>::Postings>> {
+        let postings = self.read_postings_from_terminfo_specialized(term_info, option, codec)?;
+        let term_scorer = TermScorer::new(postings, fieldnorm_reader, similarity_weight);
+        Ok(term_scorer)
+    }
+
+    pub(crate) fn new_phrase_scorer_type_specialized<C: Codec>(
+        &self,
+        term_infos: &[(usize, TermInfo)],
+        similarity_weight_opt: Option<Bm25Weight>,
+        fieldnorm_reader: FieldNormReader,
+        slop: u32,
+        codec: &C,
+    ) -> io::Result<PhraseScorer<<<C as Codec>::PostingsCodec as PostingsCodec>::Postings>> {
+        let mut offset_and_term_postings: Vec<(
+            usize,
+            <<C as Codec>::PostingsCodec as PostingsCodec>::Postings,
+        )> = Vec::with_capacity(term_infos.len());
+        for (offset, term_info) in term_infos {
+            let postings = self.read_postings_from_terminfo_specialized(
+                term_info,
+                IndexRecordOption::WithFreqsAndPositions,
+                codec,
+            )?;
+            offset_and_term_postings.push((*offset, postings));
+        }
+        let phrase_scorer = PhraseScorer::new(
+            offset_and_term_postings,
+            similarity_weight_opt,
+            fieldnorm_reader,
+            slop,
+        );
+        Ok(phrase_scorer)
+    }
+
+    /// Build a new term scorer.
+    pub fn new_term_scorer(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        fieldnorm_reader: FieldNormReader,
+        similarity_weight: Bm25Weight,
+    ) -> io::Result<Box<dyn Scorer>> {
+        let term_scorer = self.codec.load_term_scorer_type_erased(
+            term_info,
+            option,
+            self,
+            fieldnorm_reader,
+            similarity_weight,
+        )?;
+        Ok(term_scorer)
+    }
+
+    /// Returns a postings object specific with a concrete type.
+    ///
+    /// This requires you to provied the actual codec.
+    pub fn read_postings_from_terminfo_specialized<C: Codec>(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        codec: &C,
+    ) -> io::Result<<<C as Codec>::PostingsCodec as PostingsCodec>::Postings> {
+        let option = option.downgrade(self.record_option);
         let postings_data = self
             .postings_file_slice
-            .slice(term_info.postings_range.clone());
-        BlockSegmentPostings::open(
-            term_info.doc_freq,
-            postings_data,
-            self.record_option,
-            requested_option,
-        )
+            .slice(term_info.postings_range.clone())
+            .read_bytes()?;
+        let positions_data: Option<OwnedBytes> = if option.has_positions() {
+            let positions_data = self
+                .positions_file_slice
+                .slice(term_info.positions_range.clone())
+                .read_bytes()?;
+            Some(positions_data)
+        } else {
+            None
+        };
+        let postings: <<C as Codec>::PostingsCodec as PostingsCodec>::Postings =
+            codec.postings_codec().load_postings(
+                term_info.doc_freq,
+                postings_data,
+                self.record_option,
+                option,
+                positions_data,
+            )?;
+        Ok(postings)
     }
 
     /// Returns a posting object given a `term_info`.
@@ -307,25 +271,9 @@ impl TantivyInvertedIndexReader {
         &self,
         term_info: &TermInfo,
         option: IndexRecordOption,
-    ) -> io::Result<SegmentPostings> {
-        let option = option.downgrade(self.record_option);
-
-        let block_postings = self.read_block_postings_from_terminfo(term_info, option)?;
-        let position_reader = {
-            if option.has_positions() {
-                let positions_data = self
-                    .positions_file_slice
-                    .read_bytes_slice(term_info.positions_range.clone())?;
-                let position_reader = PositionReader::open(positions_data)?;
-                Some(position_reader)
-            } else {
-                None
-            }
-        };
-        Ok(SegmentPostings::from_block_postings(
-            block_postings,
-            position_reader,
-        ))
+    ) -> io::Result<Box<dyn Postings>> {
+        self.codec
+            .load_postings_type_erased(term_info, option, self)
     }
 
     /// Returns the total number of tokens recorded for all documents
@@ -348,7 +296,7 @@ impl TantivyInvertedIndexReader {
         &self,
         term: &Term,
         option: IndexRecordOption,
-    ) -> io::Result<Option<SegmentPostings>> {
+    ) -> io::Result<Option<Box<dyn Postings>>> {
         self.get_term_info(term)?
             .map(move |term_info| self.read_postings_from_terminfo(&term_info, option))
             .transpose()
@@ -364,7 +312,7 @@ impl TantivyInvertedIndexReader {
 }
 
 #[cfg(feature = "quickwit")]
-impl TantivyInvertedIndexReader {
+impl InvertedIndexReader {
     pub(crate) async fn get_term_info_async(&self, term: &Term) -> io::Result<Option<TermInfo>> {
         self.termdict.get_async(term.serialized_value_bytes()).await
     }
@@ -574,84 +522,3 @@ impl TantivyInvertedIndexReader {
             .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

@@ -2,6 +2,7 @@
 //!
 //! It contains `Index` and `Segment`, where a `Index` consists of one or more `Segment`s.
 
+mod codec_configuration;
 mod index;
 mod index_meta;
 mod inverted_index_reader;
@@ -10,16 +11,12 @@ mod segment_component;
 mod segment_id;
 mod segment_reader;
 
+pub use self::codec_configuration::CodecConfiguration;
 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::{
-    ArcInvertedIndexReader, InvertedIndexFieldSpace, InvertedIndexReader,
-    TantivyInvertedIndexReader,
-};
+pub use self::inverted_index_reader::InvertedIndexReader;
 pub use self::segment::Segment;
 pub use self::segment_component::SegmentComponent;
 pub use self::segment_id::SegmentId;
-pub use self::segment_reader::{
-    ArcSegmentReader, FieldMetadata, SegmentReader, TantivySegmentReader,
-};
+pub use self::segment_reader::{FieldMetadata, SegmentReader};

src/index/segment.rs

@@ -2,6 +2,7 @@ use std::fmt;
 use std::path::PathBuf;
 
 use super::SegmentComponent;
+use crate::codec::StandardCodec;
 use crate::directory::error::{OpenReadError, OpenWriteError};
 use crate::directory::{Directory, FileSlice, WritePtr};
 use crate::index::{Index, SegmentId, SegmentMeta};
@@ -10,25 +11,25 @@ use crate::Opstamp;
 
 /// A segment is a piece of the index.
 #[derive(Clone)]
-pub struct Segment {
-    index: Index,
+pub struct Segment<C: crate::codec::Codec = StandardCodec> {
+    index: Index<C>,
     meta: SegmentMeta,
 }
 
-impl fmt::Debug for Segment {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+impl<C: crate::codec::Codec> fmt::Debug for Segment<C> {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         write!(f, "Segment({:?})", self.id().uuid_string())
     }
 }
 
-impl Segment {
+impl<C: crate::codec::Codec> Segment<C> {
     /// Creates a new segment given an `Index` and a `SegmentId`
-    pub(crate) fn for_index(index: Index, meta: SegmentMeta) -> Segment {
+    pub(crate) fn for_index(index: Index<C>, meta: SegmentMeta) -> Segment<C> {
         Segment { index, meta }
     }
 
     /// Returns the index the segment belongs to.
-    pub fn index(&self) -> &Index {
+    pub fn index(&self) -> &Index<C> {
         &self.index
     }
 
@@ -46,7 +47,7 @@ impl Segment {
     ///
     /// This method is only used when updating `max_doc` from 0
     /// as we finalize a fresh new segment.
-    pub fn with_max_doc(self, max_doc: u32) -> Segment {
+    pub fn with_max_doc(self, max_doc: u32) -> Segment<C> {
         Segment {
             index: self.index,
             meta: self.meta.with_max_doc(max_doc),
@@ -55,7 +56,7 @@ impl Segment {
 
     #[doc(hidden)]
     #[must_use]
-    pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> Segment {
+    pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> Segment<C> {
         Segment {
             index: self.index,
             meta: self.meta.with_delete_meta(num_deleted_docs, opstamp),

src/index/segment_reader.rs

@@ -6,13 +6,12 @@ use common::{ByteCount, HasLen};
 use fnv::FnvHashMap;
 use itertools::Itertools;
 
+use crate::codec::ObjectSafeCodec;
 use crate::directory::{CompositeFile, FileSlice};
 use crate::error::DataCorruption;
 use crate::fastfield::{intersect_alive_bitsets, AliveBitSet, FacetReader, FastFieldReaders};
-use crate::fieldnorm::FieldNormReaders;
-use crate::index::{
-    ArcInvertedIndexReader, Segment, SegmentComponent, SegmentId, TantivyInvertedIndexReader,
-};
+use crate::fieldnorm::{FieldNormReader, FieldNormReaders};
+use crate::index::{InvertedIndexReader, Segment, SegmentComponent, SegmentId};
 use crate::json_utils::json_path_sep_to_dot;
 use crate::schema::{Field, IndexRecordOption, Schema, Type};
 use crate::space_usage::SegmentSpaceUsage;
@@ -20,93 +19,6 @@ 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
@@ -118,8 +30,8 @@ pub type ArcSegmentReader = Arc<dyn SegmentReader>;
 /// The segment reader has a very low memory footprint,
 /// as close to all of the memory data is mmapped.
 #[derive(Clone)]
-pub struct TantivySegmentReader {
-    inv_idx_reader_cache: Arc<RwLock<HashMap<Field, ArcInvertedIndexReader>>>,
+pub struct SegmentReader {
+    inv_idx_reader_cache: Arc<RwLock<HashMap<Field, Arc<InvertedIndexReader>>>>,
 
     segment_id: SegmentId,
     delete_opstamp: Option<Opstamp>,
@@ -136,19 +48,111 @@ pub struct TantivySegmentReader {
     store_file: FileSlice,
     alive_bitset_opt: Option<AliveBitSet>,
     schema: Schema,
+
+    pub(crate) codec: Arc<dyn ObjectSafeCodec>,
 }
 
-impl TantivySegmentReader {
+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)
+    }
+
     /// Open a new segment for reading.
-    pub fn open(segment: &Segment) -> crate::Result<TantivySegmentReader> {
+    pub fn open<C: crate::codec::Codec>(segment: &Segment<C>) -> crate::Result<SegmentReader> {
         Self::open_with_custom_alive_set(segment, None)
     }
 
     /// Open a new segment for reading.
-    pub fn open_with_custom_alive_set(
-        segment: &Segment,
+    pub fn open_with_custom_alive_set<C: crate::codec::Codec>(
+        segment: &Segment<C>,
         custom_bitset: Option<AliveBitSet>,
-    ) -> crate::Result<TantivySegmentReader> {
+    ) -> crate::Result<SegmentReader> {
+        let codec: Arc<dyn ObjectSafeCodec> = Arc::new(segment.index().codec().clone());
         let termdict_file = segment.open_read(SegmentComponent::Terms)?;
         let termdict_composite = CompositeFile::open(&termdict_file)?;
 
@@ -190,7 +194,7 @@ impl TantivySegmentReader {
             .map(|alive_bitset| alive_bitset.num_alive_docs() as u32)
             .unwrap_or(max_doc);
 
-        Ok(TantivySegmentReader {
+        Ok(SegmentReader {
             inv_idx_reader_cache: Default::default(),
             num_docs,
             max_doc,
@@ -204,54 +208,9 @@ impl TantivySegmentReader {
             alive_bitset_opt,
             positions_composite,
             schema,
+            codec,
         })
     }
-}
-
-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,
@@ -265,7 +224,7 @@ impl SegmentReader for TantivySegmentReader {
     /// 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).
-    fn inverted_index(&self, field: Field) -> crate::Result<ArcInvertedIndexReader> {
+    pub fn inverted_index(&self, field: Field) -> crate::Result<Arc<InvertedIndexReader>> {
         if let Some(inv_idx_reader) = self
             .inv_idx_reader_cache
             .read()
@@ -290,7 +249,7 @@ impl SegmentReader for TantivySegmentReader {
             //
             // Returns an empty inverted index.
             let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);
-            return Ok(Arc::new(TantivyInvertedIndexReader::empty(record_option)));
+            return Ok(Arc::new(InvertedIndexReader::empty(record_option)));
         }
 
         let record_option = record_option_opt.unwrap();
@@ -314,11 +273,12 @@ impl SegmentReader for TantivySegmentReader {
             DataCorruption::comment_only(error_msg)
         })?;
 
-        let inv_idx_reader: ArcInvertedIndexReader = Arc::new(TantivyInvertedIndexReader::new(
+        let inv_idx_reader = Arc::new(InvertedIndexReader::new(
             TermDictionary::open(termdict_file)?,
             postings_file,
             positions_file,
             record_option,
+            self.codec.clone(),
         )?);
 
         // by releasing the lock in between, we may end up opening the inverting index
@@ -344,7 +304,7 @@ impl SegmentReader for TantivySegmentReader {
     /// 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.
-    fn fields_metadata(&self) -> crate::Result<Vec<FieldMetadata>> {
+    pub 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() {
@@ -466,22 +426,39 @@ impl SegmentReader for TantivySegmentReader {
     }
 
     /// Returns the segment id
-    fn segment_id(&self) -> SegmentId {
+    pub fn segment_id(&self) -> SegmentId {
         self.segment_id
     }
 
     /// Returns the delete opstamp
-    fn delete_opstamp(&self) -> Option<Opstamp> {
+    pub fn delete_opstamp(&self) -> Option<Opstamp> {
         self.delete_opstamp
     }
 
     /// Returns the bitset representing the alive `DocId`s.
-    fn alive_bitset(&self) -> Option<&AliveBitSet> {
+    pub 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.
-    fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
+    pub fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
         Ok(SegmentSpaceUsage::new(
             self.num_docs(),
             self.termdict_composite.space_usage(self.schema()),
@@ -605,7 +582,7 @@ fn intersect_alive_bitset(
     }
 }
 
-impl fmt::Debug for TantivySegmentReader {
+impl fmt::Debug for SegmentReader {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         write!(f, "SegmentReader({:?})", self.segment_id)
     }

src/indexer/delete_queue.rs

@@ -250,15 +250,11 @@ mod tests {
 
     struct DummyWeight;
     impl Weight for DummyWeight {
-        fn scorer(
-            &self,
-            _reader: &dyn SegmentReader,
-            _boost: Score,
-        ) -> crate::Result<Box<dyn Scorer>> {
+        fn scorer(&self, _reader: &SegmentReader, _boost: Score) -> crate::Result<Box<dyn Scorer>> {
             Err(crate::TantivyError::InternalError("dummy impl".to_owned()))
         }
 
-        fn explain(&self, _reader: &dyn SegmentReader, _doc: DocId) -> crate::Result<Explanation> {
+        fn explain(&self, _reader: &SegmentReader, _doc: DocId) -> crate::Result<Explanation> {
             Err(crate::TantivyError::InternalError("dummy impl".to_owned()))
         }
     }

src/indexer/index_writer.rs

@@ -9,12 +9,11 @@ use smallvec::smallvec;
 use super::operation::{AddOperation, UserOperation};
 use super::segment_updater::SegmentUpdater;
 use super::{AddBatch, AddBatchReceiver, AddBatchSender, PreparedCommit};
+use crate::codec::{Codec, StandardCodec};
 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, TantivySegmentReader,
-};
+use crate::index::{Index, Segment, SegmentComponent, SegmentId, SegmentMeta, SegmentReader};
 use crate::indexer::delete_queue::{DeleteCursor, DeleteQueue};
 use crate::indexer::doc_opstamp_mapping::DocToOpstampMapping;
 use crate::indexer::index_writer_status::IndexWriterStatus;
@@ -70,12 +69,12 @@ pub struct IndexWriterOptions {
 /// indexing queue.
 /// Each indexing thread builds its own independent [`Segment`], via
 /// a `SegmentWriter` object.
-pub struct IndexWriter<D: Document = TantivyDocument> {
+pub struct IndexWriter<C: Codec = StandardCodec, D: Document = TantivyDocument> {
     // the lock is just used to bind the
     // lifetime of the lock with that of the IndexWriter.
     _directory_lock: Option<DirectoryLock>,
 
-    index: Index,
+    index: Index<C>,
 
     options: IndexWriterOptions,
 
@@ -84,7 +83,7 @@ pub struct IndexWriter<D: Document = TantivyDocument> {
     index_writer_status: IndexWriterStatus<D>,
     operation_sender: AddBatchSender<D>,
 
-    segment_updater: SegmentUpdater,
+    segment_updater: SegmentUpdater<C>,
 
     worker_id: usize,
 
@@ -96,7 +95,7 @@ pub struct IndexWriter<D: Document = TantivyDocument> {
 
 fn compute_deleted_bitset(
     alive_bitset: &mut BitSet,
-    segment_reader: &dyn SegmentReader,
+    segment_reader: &SegmentReader,
     delete_cursor: &mut DeleteCursor,
     doc_opstamps: &DocToOpstampMapping,
     target_opstamp: Opstamp,
@@ -130,8 +129,8 @@ 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 fn advance_deletes(
-    mut segment: Segment,
+pub fn advance_deletes<C: Codec>(
+    mut segment: Segment<C>,
     segment_entry: &mut SegmentEntry,
     target_opstamp: Opstamp,
 ) -> crate::Result<()> {
@@ -145,7 +144,7 @@ pub fn advance_deletes(
         return Ok(());
     }
 
-    let segment_reader = TantivySegmentReader::open(&segment)?;
+    let segment_reader = SegmentReader::open(&segment)?;
 
     let max_doc = segment_reader.max_doc();
     let mut alive_bitset: BitSet = match segment_entry.alive_bitset() {
@@ -181,11 +180,11 @@ pub fn advance_deletes(
     Ok(())
 }
 
-fn index_documents<D: Document>(
+fn index_documents<C: crate::codec::Codec, D: Document>(
     memory_budget: usize,
-    segment: Segment,
+    segment: Segment<C>,
     grouped_document_iterator: &mut dyn Iterator<Item = AddBatch<D>>,
-    segment_updater: &SegmentUpdater,
+    segment_updater: &SegmentUpdater<C>,
     mut delete_cursor: DeleteCursor,
 ) -> crate::Result<()> {
     let mut segment_writer = SegmentWriter::for_segment(memory_budget, segment.clone())?;
@@ -228,8 +227,8 @@ fn index_documents<D: Document>(
 }
 
 /// `doc_opstamps` is required to be non-empty.
-fn apply_deletes(
-    segment: &Segment,
+fn apply_deletes<C: crate::codec::Codec>(
+    segment: &Segment<C>,
     delete_cursor: &mut DeleteCursor,
     doc_opstamps: &[Opstamp],
 ) -> crate::Result<Option<BitSet>> {
@@ -245,7 +244,7 @@ fn apply_deletes(
         .max()
         .expect("Empty DocOpstamp is forbidden");
 
-    let segment_reader = TantivySegmentReader::open(segment)?;
+    let segment_reader = SegmentReader::open(segment)?;
     let doc_to_opstamps = DocToOpstampMapping::WithMap(doc_opstamps);
 
     let max_doc = segment.meta().max_doc();
@@ -264,7 +263,7 @@ fn apply_deletes(
     })
 }
 
-impl<D: Document> IndexWriter<D> {
+impl<C: Codec, D: Document> IndexWriter<C, D> {
     /// Create a new index writer. Attempts to acquire a lockfile.
     ///
     /// The lockfile should be deleted on drop, but it is possible
@@ -280,7 +279,7 @@ impl<D: Document> IndexWriter<D> {
     /// If the memory arena per thread is too small or too big, returns
     /// `TantivyError::InvalidArgument`
     pub(crate) fn new(
-        index: &Index,
+        index: &Index<C>,
         options: IndexWriterOptions,
         directory_lock: DirectoryLock,
     ) -> crate::Result<Self> {
@@ -347,7 +346,7 @@ impl<D: Document> IndexWriter<D> {
     }
 
     /// Accessor to the index.
-    pub fn index(&self) -> &Index {
+    pub fn index(&self) -> &Index<C> {
         &self.index
     }
 
@@ -395,7 +394,7 @@ impl<D: Document> IndexWriter<D> {
     /// It is safe to start writing file associated with the new `Segment`.
     /// These will not be garbage collected as long as an instance object of
     /// `SegmentMeta` object associated with the new `Segment` is "alive".
-    pub fn new_segment(&self) -> Segment {
+    pub fn new_segment(&self) -> Segment<C> {
         self.index.new_segment()
     }
 
@@ -617,7 +616,7 @@ impl<D: Document> IndexWriter<D> {
     /// It is also possible to add a payload to the `commit`
     /// using this API.
     /// See [`PreparedCommit::set_payload()`].
-    pub fn prepare_commit(&mut self) -> crate::Result<PreparedCommit<'_, D>> {
+    pub fn prepare_commit(&mut self) -> crate::Result<PreparedCommit<'_, C, D>> {
         // Here, because we join all of the worker threads,
         // all of the segment update for this commit have been
         // sent.
@@ -667,7 +666,7 @@ impl<D: Document> IndexWriter<D> {
         self.prepare_commit()?.commit()
     }
 
-    pub(crate) fn segment_updater(&self) -> &SegmentUpdater {
+    pub(crate) fn segment_updater(&self) -> &SegmentUpdater<C> {
         &self.segment_updater
     }
 
@@ -806,7 +805,7 @@ impl<D: Document> IndexWriter<D> {
     }
 }
 
-impl<D: Document> Drop for IndexWriter<D> {
+impl<C: Codec, D: Document> Drop for IndexWriter<C, D> {
     fn drop(&mut self) {
         self.segment_updater.kill();
         self.drop_sender();

src/indexer/merge_index_test.rs

@@ -1,9 +1,10 @@
 #[cfg(test)]
 mod tests {
+    use crate::codec::StandardCodec;
     use crate::collector::TopDocs;
     use crate::fastfield::AliveBitSet;
     use crate::index::Index;
-    use crate::postings::Postings;
+    use crate::postings::{DocFreq, Postings};
     use crate::query::QueryParser;
     use crate::schema::{
         self, BytesOptions, Facet, FacetOptions, IndexRecordOption, NumericOptions,
@@ -121,21 +122,26 @@ mod tests {
             let my_text_field = index.schema().get_field("text_field").unwrap();
             let term_a = Term::from_field_text(my_text_field, "text");
             let inverted_index = segment_reader.inverted_index(my_text_field).unwrap();
+            let term_info = inverted_index.get_term_info(&term_a).unwrap().unwrap();
             let mut postings = inverted_index
-                .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
-                .unwrap()
+                .read_postings_from_terminfo_specialized(
+                    &term_info,
+                    IndexRecordOption::WithFreqsAndPositions,
+                    &StandardCodec,
+                )
                 .unwrap();
-            assert_eq!(postings.doc_freq(), 2);
+            assert_eq!(postings.doc_freq(), DocFreq::Exact(2));
             let fallback_bitset = AliveBitSet::for_test_from_deleted_docs(&[0], 100);
             assert_eq!(
-                postings.doc_freq_given_deletes(
+                crate::indexer::merger::doc_freq_given_deletes(
+                    &postings,
                     segment_reader.alive_bitset().unwrap_or(&fallback_bitset)
                 ),
                 2
             );
 
             assert_eq!(postings.term_freq(), 1);
-            let mut output = vec![];
+            let mut output = Vec::new();
             postings.positions(&mut output);
             assert_eq!(output, vec![1]);
             postings.advance();

src/indexer/merger.rs

@@ -1,3 +1,5 @@
+use std::sync::Arc;
+
 use columnar::{
     ColumnType, ColumnarReader, MergeRowOrder, RowAddr, ShuffleMergeOrder, StackMergeOrder,
 };
@@ -5,19 +7,21 @@ use common::ReadOnlyBitSet;
 use itertools::Itertools;
 use measure_time::debug_time;
 
+use crate::codec::postings::PostingsCodec;
+use crate::codec::{Codec, StandardCodec};
 use crate::directory::WritePtr;
 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, TantivySegmentReader};
+use crate::index::{Segment, SegmentComponent, SegmentReader};
 use crate::indexer::doc_id_mapping::{MappingType, SegmentDocIdMapping};
 use crate::indexer::SegmentSerializer;
-use crate::postings::{InvertedIndexSerializer, Postings, SegmentPostings};
+use crate::postings::{InvertedIndexSerializer, Postings};
 use crate::schema::{value_type_to_column_type, Field, FieldType, Schema};
 use crate::store::StoreWriter;
 use crate::termdict::{TermMerger, TermOrdinal};
-use crate::{ArcInvertedIndexReader, DocAddress, DocId};
+use crate::{DocAddress, DocId, InvertedIndexReader};
 
 /// Segment's max doc must be `< MAX_DOC_LIMIT`.
 ///
@@ -25,7 +29,7 @@ use crate::{ArcInvertedIndexReader, DocAddress, DocId};
 pub const MAX_DOC_LIMIT: u32 = 1 << 31;
 
 fn estimate_total_num_tokens_in_single_segment(
-    reader: &dyn SegmentReader,
+    reader: &SegmentReader,
     field: Field,
 ) -> crate::Result<u64> {
     // There are no deletes. We can simply use the exact value saved into the posting list.
@@ -66,7 +70,7 @@ fn estimate_total_num_tokens_in_single_segment(
     Ok((segment_num_tokens as f64 * ratio) as u64)
 }
 
-fn estimate_total_num_tokens(readers: &[TantivySegmentReader], field: Field) -> crate::Result<u64> {
+fn estimate_total_num_tokens(readers: &[SegmentReader], 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)?;
@@ -74,10 +78,11 @@ fn estimate_total_num_tokens(readers: &[TantivySegmentReader], field: Field) ->
     Ok(total_num_tokens)
 }
 
-pub struct IndexMerger {
+pub struct IndexMerger<C: Codec = StandardCodec> {
     schema: Schema,
-    pub(crate) readers: Vec<TantivySegmentReader>,
+    pub(crate) readers: Vec<SegmentReader>,
     max_doc: u32,
+    codec: C,
 }
 
 struct DeltaComputer {
@@ -142,8 +147,8 @@ fn extract_fast_field_required_columns(schema: &Schema) -> Vec<(String, ColumnTy
         .collect()
 }
 
-impl IndexMerger {
-    pub fn open(schema: Schema, segments: &[Segment]) -> crate::Result<IndexMerger> {
+impl<C: Codec> IndexMerger<C> {
+    pub fn open(schema: Schema, segments: &[Segment<C>]) -> crate::Result<IndexMerger<C>> {
         let alive_bitset = segments.iter().map(|_| None).collect_vec();
         Self::open_with_custom_alive_set(schema, segments, alive_bitset)
     }
@@ -160,18 +165,20 @@ impl IndexMerger {
     // This can be used to merge but also apply an additional filter.
     // One use case is demux, which is basically taking a list of
     // segments and partitions them e.g. by a value in a field.
+    //
+    // # Panics if segments is empty.
     pub fn open_with_custom_alive_set(
         schema: Schema,
-        segments: &[Segment],
+        segments: &[Segment<C>],
         alive_bitset_opt: Vec<Option<AliveBitSet>>,
-    ) -> crate::Result<IndexMerger> {
+    ) -> crate::Result<IndexMerger<C>> {
+        assert!(!segments.is_empty());
+        let codec = segments[0].index().codec().clone();
         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 = TantivySegmentReader::open_with_custom_alive_set(
-                    segment,
-                    new_alive_bitset_opt,
-                )?;
+                let reader =
+                    SegmentReader::open_with_custom_alive_set(segment, new_alive_bitset_opt)?;
                 readers.push(reader);
             }
         }
@@ -189,6 +196,7 @@ impl IndexMerger {
             schema,
             readers,
             max_doc,
+            codec,
         })
     }
 
@@ -204,20 +212,8 @@ impl IndexMerger {
             let fieldnorms_readers: Vec<FieldNormReader> = self
                 .readers
                 .iter()
-                .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<_>>()?;
+                .map(|reader| reader.get_fieldnorms_reader(field))
+                .collect::<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);
@@ -274,7 +270,7 @@ impl IndexMerger {
                 }),
         );
 
-        let has_deletes: bool = self.readers.iter().any(|reader| reader.has_deletes());
+        let has_deletes: bool = self.readers.iter().any(SegmentReader::has_deletes);
         let mapping_type = if has_deletes {
             MappingType::StackedWithDeletes
         } else {
@@ -299,7 +295,7 @@ impl IndexMerger {
         &self,
         indexed_field: Field,
         _field_type: &FieldType,
-        serializer: &mut InvertedIndexSerializer,
+        serializer: &mut InvertedIndexSerializer<C>,
         fieldnorm_reader: Option<FieldNormReader>,
         doc_id_mapping: &SegmentDocIdMapping,
     ) -> crate::Result<()> {
@@ -309,7 +305,7 @@ impl IndexMerger {
 
         let mut max_term_ords: Vec<TermOrdinal> = Vec::new();
 
-        let field_readers: Vec<ArcInvertedIndexReader> = self
+        let field_readers: Vec<Arc<InvertedIndexReader>> = self
             .readers
             .iter()
             .map(|reader| reader.inverted_index(indexed_field))
@@ -367,7 +363,10 @@ impl IndexMerger {
                          indexed. Have you modified the schema?",
         );
 
-        let mut segment_postings_containing_the_term: Vec<(usize, SegmentPostings)> = vec![];
+        let mut segment_postings_containing_the_term: Vec<(
+            usize,
+            <C::PostingsCodec as PostingsCodec>::Postings,
+        )> = Vec::with_capacity(self.readers.len());
 
         while merged_terms.advance() {
             segment_postings_containing_the_term.clear();
@@ -378,18 +377,25 @@ 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 = field_readers[segment_ord].as_ref();
-                let segment_postings = inverted_index
-                    .read_postings_from_terminfo(&term_info, segment_postings_option)?;
+                let inverted_index: &InvertedIndexReader = &field_readers[segment_ord];
+                let postings = inverted_index.read_postings_from_terminfo_specialized(
+                    &term_info,
+                    segment_postings_option,
+                    &self.codec,
+                )?;
                 let alive_bitset_opt = segment_reader.alive_bitset();
                 let doc_freq = if let Some(alive_bitset) = alive_bitset_opt {
-                    segment_postings.doc_freq_given_deletes(alive_bitset)
+                    doc_freq_given_deletes(&postings, alive_bitset)
                 } else {
-                    segment_postings.doc_freq()
+                    // We do not an exact document frequency here.
+                    match postings.doc_freq() {
+                        crate::postings::DocFreq::Approximate(_) => exact_doc_freq(&postings),
+                        crate::postings::DocFreq::Exact(doc_freq) => doc_freq,
+                    }
                 };
                 if doc_freq > 0u32 {
                     total_doc_freq += doc_freq;
-                    segment_postings_containing_the_term.push((segment_ord, segment_postings));
+                    segment_postings_containing_the_term.push((segment_ord, postings));
                 }
             }
 
@@ -407,11 +413,7 @@ impl IndexMerger {
             assert!(!segment_postings_containing_the_term.is_empty());
 
             let has_term_freq = {
-                let has_term_freq = !segment_postings_containing_the_term[0]
-                    .1
-                    .block_cursor
-                    .freqs()
-                    .is_empty();
+                let has_term_freq = segment_postings_containing_the_term[0].1.has_freq();
                 for (_, postings) in &segment_postings_containing_the_term[1..] {
                     // This may look at a strange way to test whether we have term freq or not.
                     // With JSON object, the schema is not sufficient to know whether a term
@@ -427,7 +429,7 @@ impl IndexMerger {
                     //
                     // Overall the reliable way to know if we have actual frequencies loaded or not
                     // is to check whether the actual decoded array is empty or not.
-                    if has_term_freq == postings.block_cursor.freqs().is_empty() {
+                    if postings.has_freq() != has_term_freq {
                         return Err(DataCorruption::comment_only(
                             "Term freqs are inconsistent across segments",
                         )
@@ -479,7 +481,7 @@ impl IndexMerger {
 
     fn write_postings(
         &self,
-        serializer: &mut InvertedIndexSerializer,
+        serializer: &mut InvertedIndexSerializer<C>,
         fieldnorm_readers: FieldNormReaders,
         doc_id_mapping: &SegmentDocIdMapping,
     ) -> crate::Result<()> {
@@ -537,7 +539,7 @@ impl IndexMerger {
     ///
     /// # Returns
     /// The number of documents in the resulting segment.
-    pub fn write(&self, mut serializer: SegmentSerializer) -> crate::Result<u32> {
+    pub fn write(&self, mut serializer: SegmentSerializer<C>) -> crate::Result<u32> {
         let doc_id_mapping = self.get_doc_id_from_concatenated_data()?;
         debug!("write-fieldnorms");
         if let Some(fieldnorms_serializer) = serializer.extract_fieldnorms_serializer() {
@@ -565,6 +567,43 @@ impl IndexMerger {
     }
 }
 
+/// Compute the number of non-deleted documents.
+///
+/// This method will clone and scan through the posting lists.
+/// (this is a rather expensive operation).
+pub(crate) fn doc_freq_given_deletes<P: Postings + Clone>(
+    postings: &P,
+    alive_bitset: &AliveBitSet,
+) -> u32 {
+    let mut docset = postings.clone();
+    let mut doc_freq = 0;
+    loop {
+        let doc = docset.doc();
+        if doc == TERMINATED {
+            return doc_freq;
+        }
+        if alive_bitset.is_alive(doc) {
+            doc_freq += 1u32;
+        }
+        docset.advance();
+    }
+}
+
+/// If the postings is not able to inform us of the document frequency,
+/// we just scan through it.
+pub(crate) fn exact_doc_freq<P: Postings + Clone>(postings: &P) -> u32 {
+    let mut docset = postings.clone();
+    let mut doc_freq = 0;
+    loop {
+        let doc = docset.doc();
+        if doc == TERMINATED {
+            return doc_freq;
+        }
+        doc_freq += 1u32;
+        docset.advance();
+    }
+}
+
 #[cfg(test)]
 mod tests {
 
@@ -573,12 +612,16 @@ mod tests {
     use proptest::strategy::Strategy;
     use schema::FAST;
 
+    use crate::codec::postings::PostingsCodec;
+    use crate::codec::standard::postings::StandardPostingsCodec;
     use crate::collector::tests::{
         BytesFastFieldTestCollector, FastFieldTestCollector, TEST_COLLECTOR_WITH_SCORE,
     };
     use crate::collector::{Count, FacetCollector};
+    use crate::fastfield::AliveBitSet;
     use crate::index::{Index, SegmentId};
     use crate::indexer::NoMergePolicy;
+    use crate::postings::{DocFreq, Postings as _};
     use crate::query::{AllQuery, BooleanQuery, EnableScoring, Scorer, TermQuery};
     use crate::schema::{
         Facet, FacetOptions, IndexRecordOption, NumericOptions, TantivyDocument, Term,
@@ -1530,10 +1573,10 @@ mod tests {
         let searcher = reader.searcher();
         let mut term_scorer = term_query
             .specialized_weight(EnableScoring::enabled_from_searcher(&searcher))?
-            .term_scorer_for_test(searcher.segment_reader(0u32), 1.0)?
+            .term_scorer_for_test(searcher.segment_reader(0u32), 1.0)
             .unwrap();
         assert_eq!(term_scorer.doc(), 0);
-        assert_nearly_equals!(term_scorer.block_max_score(), 0.0079681855);
+        assert_nearly_equals!(term_scorer.seek_block_max(0), 0.0079681855);
         assert_nearly_equals!(term_scorer.score(), 0.0079681855);
         for _ in 0..81 {
             writer.add_document(doc!(text=>"hello happy tax payer"))?;
@@ -1546,13 +1589,13 @@ 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.as_ref(), 1.0)?
+                .term_scorer_for_test(segment_reader, 1.0)
                 .unwrap();
             // the difference compared to before is intrinsic to the bm25 formula. no worries
             // there.
             for doc in segment_reader.doc_ids_alive() {
                 assert_eq!(term_scorer.doc(), doc);
-                assert_nearly_equals!(term_scorer.block_max_score(), 0.003478312);
+                assert_nearly_equals!(term_scorer.seek_block_max(doc), 0.003478312);
                 assert_nearly_equals!(term_scorer.score(), 0.003478312);
                 term_scorer.advance();
             }
@@ -1572,12 +1615,12 @@ mod tests {
         let segment_reader = searcher.segment_reader(0u32);
         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, 1.0)
             .unwrap();
         // the difference compared to before is intrinsic to the bm25 formula. no worries there.
         for doc in segment_reader.doc_ids_alive() {
             assert_eq!(term_scorer.doc(), doc);
-            assert_nearly_equals!(term_scorer.block_max_score(), 0.003478312);
+            assert_nearly_equals!(term_scorer.seek_block_max(doc), 0.003478312);
             assert_nearly_equals!(term_scorer.score(), 0.003478312);
             term_scorer.advance();
         }
@@ -1591,4 +1634,16 @@ mod tests {
         assert!(((super::MAX_DOC_LIMIT - 1) as i32) >= 0);
         assert!((super::MAX_DOC_LIMIT as i32) < 0);
     }
+
+    #[test]
+    fn test_doc_freq_given_delete() {
+        let docs =
+            <StandardPostingsCodec as PostingsCodec>::Postings::create_from_docs(&[0, 2, 10]);
+        assert_eq!(docs.doc_freq(), DocFreq::Exact(3));
+        let alive_bitset = AliveBitSet::for_test_from_deleted_docs(&[2], 12);
+        assert_eq!(super::doc_freq_given_deletes(&docs, &alive_bitset), 2);
+        let all_deleted =
+            AliveBitSet::for_test_from_deleted_docs(&[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11], 12);
+        assert_eq!(super::doc_freq_given_deletes(&docs, &all_deleted), 0);
+    }
 }

src/indexer/prepared_commit.rs

@@ -1,16 +1,17 @@
 use super::IndexWriter;
+use crate::codec::Codec;
 use crate::schema::document::Document;
 use crate::{FutureResult, Opstamp, TantivyDocument};
 
 /// A prepared commit
-pub struct PreparedCommit<'a, D: Document = TantivyDocument> {
-    index_writer: &'a mut IndexWriter<D>,
+pub struct PreparedCommit<'a, C: Codec, D: Document = TantivyDocument> {
+    index_writer: &'a mut IndexWriter<C, D>,
     payload: Option<String>,
     opstamp: Opstamp,
 }
 
-impl<'a, D: Document> PreparedCommit<'a, D> {
-    pub(crate) fn new(index_writer: &'a mut IndexWriter<D>, opstamp: Opstamp) -> Self {
+impl<'a, C: Codec, D: Document> PreparedCommit<'a, C, D> {
+    pub(crate) fn new(index_writer: &'a mut IndexWriter<C, D>, opstamp: Opstamp) -> Self {
         Self {
             index_writer,
             payload: None,

src/indexer/segment_serializer.rs

@@ -8,17 +8,17 @@ use crate::store::StoreWriter;
 
 /// Segment serializer is in charge of laying out on disk
 /// the data accumulated and sorted by the `SegmentWriter`.
-pub struct SegmentSerializer {
-    segment: Segment,
+pub struct SegmentSerializer<C: crate::codec::Codec> {
+    segment: Segment<C>,
     pub(crate) store_writer: StoreWriter,
     fast_field_write: WritePtr,
     fieldnorms_serializer: Option<FieldNormsSerializer>,
-    postings_serializer: InvertedIndexSerializer,
+    postings_serializer: InvertedIndexSerializer<C>,
 }
 
-impl SegmentSerializer {
+impl<C: crate::codec::Codec> SegmentSerializer<C> {
     /// Creates a new `SegmentSerializer`.
-    pub fn for_segment(mut segment: Segment) -> crate::Result<SegmentSerializer> {
+    pub fn for_segment(mut segment: Segment<C>) -> crate::Result<SegmentSerializer<C>> {
         let settings = segment.index().settings().clone();
         let store_writer = {
             let store_write = segment.open_write(SegmentComponent::Store)?;
@@ -50,12 +50,12 @@ impl SegmentSerializer {
         self.store_writer.mem_usage()
     }
 
-    pub fn segment(&self) -> &Segment {
+    pub fn segment(&self) -> &Segment<C> {
         &self.segment
     }
 
     /// Accessor to the `PostingsSerializer`.
-    pub fn get_postings_serializer(&mut self) -> &mut InvertedIndexSerializer {
+    pub fn get_postings_serializer(&mut self) -> &mut InvertedIndexSerializer<C> {
         &mut self.postings_serializer
     }
 

src/indexer/segment_updater.rs

@@ -10,10 +10,13 @@ use std::sync::{Arc, RwLock};
 use rayon::{ThreadPool, ThreadPoolBuilder};
 
 use super::segment_manager::SegmentManager;
+use crate::codec::Codec;
 use crate::core::META_FILEPATH;
 use crate::directory::{Directory, DirectoryClone, GarbageCollectionResult};
 use crate::fastfield::AliveBitSet;
-use crate::index::{Index, IndexMeta, IndexSettings, Segment, SegmentId, SegmentMeta};
+use crate::index::{
+    CodecConfiguration, Index, IndexMeta, IndexSettings, Segment, SegmentId, SegmentMeta,
+};
 use crate::indexer::delete_queue::DeleteCursor;
 use crate::indexer::index_writer::advance_deletes;
 use crate::indexer::merge_operation::MergeOperationInventory;
@@ -61,10 +64,10 @@ pub(crate) fn save_metas(metas: &IndexMeta, directory: &dyn Directory) -> crate:
 // We voluntarily pass a merge_operation ref to guarantee that
 // the merge_operation is alive during the process
 #[derive(Clone)]
-pub(crate) struct SegmentUpdater(Arc<InnerSegmentUpdater>);
+pub(crate) struct SegmentUpdater<C: Codec>(Arc<InnerSegmentUpdater<C>>);
 
-impl Deref for SegmentUpdater {
-    type Target = InnerSegmentUpdater;
+impl<C: Codec> Deref for SegmentUpdater<C> {
+    type Target = InnerSegmentUpdater<C>;
 
     #[inline]
     fn deref(&self) -> &Self::Target {
@@ -72,8 +75,8 @@ impl Deref for SegmentUpdater {
     }
 }
 
-fn garbage_collect_files(
-    segment_updater: SegmentUpdater,
+fn garbage_collect_files<C: Codec>(
+    segment_updater: SegmentUpdater<C>,
 ) -> crate::Result<GarbageCollectionResult> {
     info!("Running garbage collection");
     let mut index = segment_updater.index.clone();
@@ -84,8 +87,8 @@ fn garbage_collect_files(
 
 /// Merges a list of segments the list of segment givens in the `segment_entries`.
 /// This function happens in the calling thread and is computationally expensive.
-fn merge(
-    index: &Index,
+fn merge<Codec: crate::codec::Codec>(
+    index: &Index<Codec>,
     mut segment_entries: Vec<SegmentEntry>,
     target_opstamp: Opstamp,
 ) -> crate::Result<Option<SegmentEntry>> {
@@ -108,13 +111,13 @@ fn merge(
 
     let delete_cursor = segment_entries[0].delete_cursor().clone();
 
-    let segments: Vec<Segment> = segment_entries
+    let segments: Vec<Segment<Codec>> = segment_entries
         .iter()
         .map(|segment_entry| index.segment(segment_entry.meta().clone()))
         .collect();
 
     // An IndexMerger is like a "view" of our merged segments.
-    let merger: IndexMerger = IndexMerger::open(index.schema(), &segments[..])?;
+    let merger: IndexMerger<Codec> = IndexMerger::open(index.schema(), &segments[..])?;
 
     // ... we just serialize this index merger in our new segment to merge the segments.
     let segment_serializer = SegmentSerializer::for_segment(merged_segment.clone())?;
@@ -139,10 +142,10 @@ fn merge(
 /// meant to work if you have an `IndexWriter` running for the origin indices, or
 /// the destination `Index`.
 #[doc(hidden)]
-pub fn merge_indices<T: Into<Box<dyn Directory>>>(
-    indices: &[Index],
-    output_directory: T,
-) -> crate::Result<Index> {
+pub fn merge_indices<Codec: crate::codec::Codec>(
+    indices: &[Index<Codec>],
+    output_directory: Box<dyn Directory>,
+) -> crate::Result<Index<Codec>> {
     if indices.is_empty() {
         // If there are no indices to merge, there is no need to do anything.
         return Err(crate::TantivyError::InvalidArgument(
@@ -163,7 +166,7 @@ pub fn merge_indices<T: Into<Box<dyn Directory>>>(
         ));
     }
 
-    let mut segments: Vec<Segment> = Vec::new();
+    let mut segments: Vec<Segment<Codec>> = Vec::new();
     for index in indices {
         segments.extend(index.searchable_segments()?);
     }
@@ -185,12 +188,12 @@ pub fn merge_indices<T: Into<Box<dyn Directory>>>(
 /// meant to work if you have an `IndexWriter` running for the origin indices, or
 /// the destination `Index`.
 #[doc(hidden)]
-pub fn merge_filtered_segments<T: Into<Box<dyn Directory>>>(
-    segments: &[Segment],
+pub fn merge_filtered_segments<C: crate::codec::Codec, T: Into<Box<dyn Directory>>>(
+    segments: &[Segment<C>],
     target_settings: IndexSettings,
     filter_doc_ids: Vec<Option<AliveBitSet>>,
     output_directory: T,
-) -> crate::Result<Index> {
+) -> crate::Result<Index<C>> {
     if segments.is_empty() {
         // If there are no indices to merge, there is no need to do anything.
         return Err(crate::TantivyError::InvalidArgument(
@@ -211,14 +214,15 @@ pub fn merge_filtered_segments<T: Into<Box<dyn Directory>>>(
         ));
     }
 
-    let mut merged_index = Index::create(
-        output_directory,
-        target_schema.clone(),
-        target_settings.clone(),
-    )?;
+    let mut merged_index: Index<C> = Index::builder()
+        .schema(target_schema.clone())
+        .codec(segments[0].index().codec().clone())
+        .settings(target_settings.clone())
+        .create(output_directory.into())?;
+
     let merged_segment = merged_index.new_segment();
     let merged_segment_id = merged_segment.id();
-    let merger: IndexMerger =
+    let merger: IndexMerger<C> =
         IndexMerger::open_with_custom_alive_set(merged_index.schema(), segments, filter_doc_ids)?;
     let segment_serializer = SegmentSerializer::for_segment(merged_segment)?;
     let num_docs = merger.write(segment_serializer)?;
@@ -235,6 +239,7 @@ pub fn merge_filtered_segments<T: Into<Box<dyn Directory>>>(
             ))
             .trim_end()
     );
+    let codec_configuration = CodecConfiguration::from(segments[0].index().codec());
 
     let index_meta = IndexMeta {
         index_settings: target_settings, // index_settings of all segments should be the same
@@ -242,6 +247,7 @@ pub fn merge_filtered_segments<T: Into<Box<dyn Directory>>>(
         schema: target_schema,
         opstamp: 0u64,
         payload: Some(stats),
+        codec: codec_configuration,
     };
 
     // save the meta.json
@@ -250,7 +256,7 @@ pub fn merge_filtered_segments<T: Into<Box<dyn Directory>>>(
     Ok(merged_index)
 }
 
-pub(crate) struct InnerSegmentUpdater {
+pub(crate) struct InnerSegmentUpdater<C: Codec> {
     // we keep a copy of the current active IndexMeta to
     // avoid loading the file every time we need it in the
     // `SegmentUpdater`.
@@ -261,7 +267,7 @@ pub(crate) struct InnerSegmentUpdater {
     pool: ThreadPool,
     merge_thread_pool: ThreadPool,
 
-    index: Index,
+    index: Index<C>,
     segment_manager: SegmentManager,
     merge_policy: RwLock<Arc<dyn MergePolicy>>,
     killed: AtomicBool,
@@ -269,13 +275,13 @@ pub(crate) struct InnerSegmentUpdater {
     merge_operations: MergeOperationInventory,
 }
 
-impl SegmentUpdater {
+impl<Codec: crate::codec::Codec> SegmentUpdater<Codec> {
     pub fn create(
-        index: Index,
+        index: Index<Codec>,
         stamper: Stamper,
         delete_cursor: &DeleteCursor,
         num_merge_threads: usize,
-    ) -> crate::Result<SegmentUpdater> {
+    ) -> crate::Result<Self> {
         let segments = index.searchable_segment_metas()?;
         let segment_manager = SegmentManager::from_segments(segments, delete_cursor);
         let pool = ThreadPoolBuilder::new()
@@ -404,12 +410,14 @@ impl SegmentUpdater {
             //
             // Segment 1 from disk 1, Segment 1 from disk 2, etc.
             committed_segment_metas.sort_by_key(|segment_meta| -(segment_meta.max_doc() as i32));
+            let codec = CodecConfiguration::from(index.codec());
             let index_meta = IndexMeta {
                 index_settings: index.settings().clone(),
                 segments: committed_segment_metas,
                 schema: index.schema(),
                 opstamp,
                 payload: commit_message,
+                codec,
             };
             // TODO add context to the error.
             save_metas(&index_meta, directory.box_clone().borrow_mut())?;
@@ -443,7 +451,7 @@ impl SegmentUpdater {
         opstamp: Opstamp,
         payload: Option<String>,
     ) -> FutureResult<Opstamp> {
-        let segment_updater: SegmentUpdater = self.clone();
+        let segment_updater: SegmentUpdater<Codec> = self.clone();
         self.schedule_task(move || {
             let segment_entries = segment_updater.purge_deletes(opstamp)?;
             segment_updater.segment_manager.commit(segment_entries);
@@ -702,6 +710,7 @@ impl SegmentUpdater {
 #[cfg(test)]
 mod tests {
     use super::merge_indices;
+    use crate::codec::StandardCodec;
     use crate::collector::TopDocs;
     use crate::directory::RamDirectory;
     use crate::fastfield::AliveBitSet;
@@ -710,7 +719,7 @@ mod tests {
     use crate::indexer::segment_updater::merge_filtered_segments;
     use crate::query::QueryParser;
     use crate::schema::*;
-    use crate::{Directory, DocAddress, Index, Segment, SegmentReader};
+    use crate::{Directory, DocAddress, Index, Segment};
 
     #[test]
     fn test_delete_during_merge() -> crate::Result<()> {
@@ -915,7 +924,7 @@ mod tests {
 
     #[test]
     fn test_merge_empty_indices_array() {
-        let merge_result = merge_indices(&[], RamDirectory::default());
+        let merge_result = merge_indices::<StandardCodec>(&[], Box::new(RamDirectory::default()));
         assert!(merge_result.is_err());
     }
 
@@ -942,7 +951,10 @@ mod tests {
         };
 
         // mismatched schema index list
-        let result = merge_indices(&[first_index, second_index], RamDirectory::default());
+        let result = merge_indices(
+            &[first_index, second_index],
+            Box::new(RamDirectory::default()),
+        );
         assert!(result.is_err());
 
         Ok(())

src/indexer/segment_writer.rs

@@ -4,6 +4,7 @@ use itertools::Itertools;
 use tokenizer_api::BoxTokenStream;
 
 use super::operation::AddOperation;
+use crate::codec::Codec;
 use crate::fastfield::FastFieldsWriter;
 use crate::fieldnorm::{FieldNormReaders, FieldNormsWriter};
 use crate::index::{Segment, SegmentComponent};
@@ -12,7 +13,7 @@ use crate::indexer::segment_serializer::SegmentSerializer;
 use crate::json_utils::{index_json_value, IndexingPositionsPerPath};
 use crate::postings::{
     compute_table_memory_size, serialize_postings, IndexingContext, IndexingPosition,
-    PerFieldPostingsWriter, PostingsWriter,
+    PerFieldPostingsWriter, PostingsWriter, PostingsWriterEnum,
 };
 use crate::schema::document::{Document, Value};
 use crate::schema::{FieldEntry, FieldType, Schema, DATE_TIME_PRECISION_INDEXED};
@@ -45,11 +46,11 @@ fn compute_initial_table_size(per_thread_memory_budget: usize) -> crate::Result<
 ///
 /// They creates the postings list in anonymous memory.
 /// The segment is laid on disk when the segment gets `finalized`.
-pub struct SegmentWriter {
+pub struct SegmentWriter<Codec: crate::codec::Codec> {
     pub(crate) max_doc: DocId,
     pub(crate) ctx: IndexingContext,
     pub(crate) per_field_postings_writers: PerFieldPostingsWriter,
-    pub(crate) segment_serializer: SegmentSerializer,
+    pub(crate) segment_serializer: SegmentSerializer<Codec>,
     pub(crate) fast_field_writers: FastFieldsWriter,
     pub(crate) fieldnorms_writer: FieldNormsWriter,
     pub(crate) json_path_writer: JsonPathWriter,
@@ -60,7 +61,7 @@ pub struct SegmentWriter {
     schema: Schema,
 }
 
-impl SegmentWriter {
+impl<Codec: crate::codec::Codec> SegmentWriter<Codec> {
     /// Creates a new `SegmentWriter`
     ///
     /// The arguments are defined as follows
@@ -70,7 +71,10 @@ impl SegmentWriter {
     ///   behavior as a memory limit.
     /// - segment: The segment being written
     /// - schema
-    pub fn for_segment(memory_budget_in_bytes: usize, segment: Segment) -> crate::Result<Self> {
+    pub fn for_segment(
+        memory_budget_in_bytes: usize,
+        segment: Segment<Codec>,
+    ) -> crate::Result<Self> {
         let schema = segment.schema();
         let tokenizer_manager = segment.index().tokenizers().clone();
         let tokenizer_manager_fast_field = segment.index().fast_field_tokenizer().clone();
@@ -169,7 +173,7 @@ impl SegmentWriter {
             }
 
             let (term_buffer, ctx) = (&mut self.term_buffer, &mut self.ctx);
-            let postings_writer: &mut dyn PostingsWriter =
+            let postings_writer: &mut PostingsWriterEnum =
                 self.per_field_postings_writers.get_for_field_mut(field);
             term_buffer.clear_with_field(field);
 
@@ -386,13 +390,13 @@ impl SegmentWriter {
 /// to the `SegmentSerializer`.
 ///
 /// `doc_id_map` is used to map to the new doc_id order.
-fn remap_and_write(
+fn remap_and_write<C: Codec>(
     schema: Schema,
     per_field_postings_writers: &PerFieldPostingsWriter,
     ctx: IndexingContext,
     fast_field_writers: FastFieldsWriter,
     fieldnorms_writer: &FieldNormsWriter,
-    mut serializer: SegmentSerializer,
+    mut serializer: SegmentSerializer<C>,
 ) -> crate::Result<()> {
     debug!("remap-and-write");
     if let Some(fieldnorms_serializer) = serializer.extract_fieldnorms_serializer() {
@@ -871,7 +875,7 @@ mod tests {
         let searcher = reader.searcher();
         let segment_reader = searcher.segment_reader(0u32);
 
-        fn assert_type(reader: &dyn SegmentReader, field: &str, typ: ColumnType) {
+        fn assert_type(reader: &SegmentReader, field: &str, typ: ColumnType) {
             let cols = reader.fast_fields().dynamic_column_handles(field).unwrap();
             assert_eq!(cols.len(), 1, "{field}");
             assert_eq!(cols[0].column_type(), typ, "{field}");
@@ -890,7 +894,7 @@ mod tests {
         assert_type(segment_reader, "json.my_arr", ColumnType::I64);
         assert_type(segment_reader, "json.my_arr.my_key", ColumnType::Str);
 
-        fn assert_empty(reader: &dyn SegmentReader, field: &str) {
+        fn assert_empty(reader: &SegmentReader, field: &str) {
             let cols = reader.fast_fields().dynamic_column_handles(field).unwrap();
             assert_eq!(cols.len(), 0);
         }

src/indexer/single_segment_index_writer.rs

@@ -1,5 +1,7 @@
 use std::marker::PhantomData;
 
+use crate::codec::StandardCodec;
+use crate::index::CodecConfiguration;
 use crate::indexer::operation::AddOperation;
 use crate::indexer::segment_updater::save_metas;
 use crate::indexer::SegmentWriter;
@@ -7,22 +9,25 @@ use crate::schema::document::Document;
 use crate::{Directory, Index, IndexMeta, Opstamp, Segment, TantivyDocument};
 
 #[doc(hidden)]
-pub struct SingleSegmentIndexWriter<D: Document = TantivyDocument> {
-    segment_writer: SegmentWriter,
-    segment: Segment,
+pub struct SingleSegmentIndexWriter<
+    Codec: crate::codec::Codec = StandardCodec,
+    D: Document = TantivyDocument,
+> {
+    segment_writer: SegmentWriter<Codec>,
+    segment: Segment<Codec>,
     opstamp: Opstamp,
-    _phantom: PhantomData<D>,
+    _doc: PhantomData<D>,
 }
 
-impl<D: Document> SingleSegmentIndexWriter<D> {
-    pub fn new(index: Index, mem_budget: usize) -> crate::Result<Self> {
+impl<Codec: crate::codec::Codec, D: Document> SingleSegmentIndexWriter<Codec, D> {
+    pub fn new(index: Index<Codec>, mem_budget: usize) -> crate::Result<Self> {
         let segment = index.new_segment();
         let segment_writer = SegmentWriter::for_segment(mem_budget, segment.clone())?;
         Ok(Self {
             segment_writer,
             segment,
             opstamp: 0,
-            _phantom: PhantomData,
+            _doc: PhantomData,
         })
     }
 
@@ -37,10 +42,10 @@ impl<D: Document> SingleSegmentIndexWriter<D> {
             .add_document(AddOperation { opstamp, document })
     }
 
-    pub fn finalize(self) -> crate::Result<Index> {
+    pub fn finalize(self) -> crate::Result<Index<Codec>> {
         let max_doc = self.segment_writer.max_doc();
         self.segment_writer.finalize()?;
-        let segment: Segment = self.segment.with_max_doc(max_doc);
+        let segment: Segment<Codec> = self.segment.with_max_doc(max_doc);
         let index = segment.index();
         let index_meta = IndexMeta {
             index_settings: index.settings().clone(),
@@ -48,6 +53,7 @@ impl<D: Document> SingleSegmentIndexWriter<D> {
             schema: index.schema(),
             opstamp: 0,
             payload: None,
+            codec: CodecConfiguration::from(index.codec()),
         };
         save_metas(&index_meta, index.directory())?;
         index.directory().sync_directory()?;

src/lib.rs

@@ -166,6 +166,9 @@ mod functional_test;
 
 #[macro_use]
 mod macros;
+
+/// Tantivy codecs describes how data is layed out on disk.
+pub mod codec;
 mod future_result;
 
 // Re-exports
@@ -224,9 +227,8 @@ pub use self::docset::{DocSet, COLLECT_BLOCK_BUFFER_LEN, TERMINATED};
 pub use crate::core::{json_utils, Executor, Searcher, SearcherGeneration};
 pub use crate::directory::Directory;
 pub use crate::index::{
-    ArcInvertedIndexReader, ArcSegmentReader, Index, IndexBuilder, IndexMeta, IndexSettings,
-    InvertedIndexReader, Order, Segment, SegmentMeta, SegmentReader, TantivyInvertedIndexReader,
-    TantivySegmentReader,
+    Index, IndexBuilder, IndexMeta, IndexSettings, InvertedIndexReader, Order, Segment,
+    SegmentMeta, SegmentReader,
 };
 pub use crate::indexer::{IndexWriter, SingleSegmentIndexWriter};
 pub use crate::schema::{Document, TantivyDocument, Term};
@@ -378,7 +380,7 @@ pub mod tests {
 
     use common::{BinarySerializable, FixedSize};
     use query_grammar::{UserInputAst, UserInputLeaf, UserInputLiteral};
-    use rand::distr::{Bernoulli, Uniform};
+    use rand::distributions::{Bernoulli, Uniform};
     use rand::rngs::StdRng;
     use rand::{Rng, SeedableRng};
     use time::OffsetDateTime;
@@ -429,7 +431,7 @@ pub mod tests {
     pub fn generate_nonunique_unsorted(max_value: u32, n_elems: usize) -> Vec<u32> {
         let seed: [u8; 32] = [1; 32];
         StdRng::from_seed(seed)
-            .sample_iter(&Uniform::new(0u32, max_value).unwrap())
+            .sample_iter(&Uniform::new(0u32, max_value))
             .take(n_elems)
             .collect::<Vec<u32>>()
     }
@@ -524,11 +526,11 @@ pub mod tests {
         let searcher = index_reader.searcher();
         let reader = searcher.segment_reader(0);
         {
-            let fieldnorm_reader = reader.fieldnorms_readers().get_field(text_field)?.unwrap();
+            let fieldnorm_reader = reader.get_fieldnorms_reader(text_field)?;
             assert_eq!(fieldnorm_reader.fieldnorm(0), 3);
         }
         {
-            let fieldnorm_reader = reader.fieldnorms_readers().get_field(title_field)?.unwrap();
+            let fieldnorm_reader = reader.get_fieldnorms_reader(title_field)?;
             assert_eq!(fieldnorm_reader.fieldnorm_id(0), 0);
         }
         Ok(())
@@ -546,18 +548,15 @@ pub mod tests {
         index_writer.commit()?;
         let reader = index.reader()?;
         let searcher = reader.searcher();
-        let segment_reader: &dyn SegmentReader = searcher.segment_reader(0);
-        let fieldnorms_reader = segment_reader
-            .fieldnorms_readers()
-            .get_field(text_field)?
-            .unwrap();
+        let segment_reader: &SegmentReader = searcher.segment_reader(0);
+        let fieldnorms_reader = segment_reader.get_fieldnorms_reader(text_field)?;
         assert_eq!(fieldnorms_reader.fieldnorm(0), 3);
         assert_eq!(fieldnorms_reader.fieldnorm(1), 0);
         assert_eq!(fieldnorms_reader.fieldnorm(2), 2);
         Ok(())
     }
 
-    fn advance_undeleted(docset: &mut dyn DocSet, reader: &dyn SegmentReader) -> bool {
+    fn advance_undeleted(docset: &mut dyn DocSet, reader: &SegmentReader) -> bool {
         let mut doc = docset.advance();
         while doc != TERMINATED {
             if !reader.is_deleted(doc) {
@@ -1074,7 +1073,7 @@ pub mod tests {
         }
         let reader = index.reader()?;
         let searcher = reader.searcher();
-        let segment_reader: &dyn SegmentReader = searcher.segment_reader(0);
+        let segment_reader: &SegmentReader = searcher.segment_reader(0);
         {
             let fast_field_reader_res = segment_reader.fast_fields().u64("text");
             assert!(fast_field_reader_res.is_err());

src/postings/compression/mod.rs

@@ -397,10 +397,7 @@ mod bench {
         let mut seed: [u8; 32] = [0; 32];
         seed[31] = seed_val;
         let mut rng = StdRng::from_seed(seed);
-        (0u32..)
-            .filter(|_| rng.random_bool(ratio))
-            .take(n)
-            .collect()
+        (0u32..).filter(|_| rng.gen_bool(ratio)).take(n).collect()
     }
 
     pub fn generate_array(n: usize, ratio: f64) -> Vec<u32> {

src/postings/json_postings_writer.rs

@@ -3,6 +3,7 @@ use std::io;
 use common::json_path_writer::JSON_END_OF_PATH;
 use stacker::Addr;
 
+use crate::codec::Codec;
 use crate::indexer::indexing_term::IndexingTerm;
 use crate::indexer::path_to_unordered_id::OrderedPathId;
 use crate::postings::postings_writer::SpecializedPostingsWriter;
@@ -22,12 +23,6 @@ pub(crate) struct JsonPostingsWriter<Rec: Recorder> {
     non_str_posting_writer: SpecializedPostingsWriter<DocIdRecorder>,
 }
 
-impl<Rec: Recorder> From<JsonPostingsWriter<Rec>> for Box<dyn PostingsWriter> {
-    fn from(json_postings_writer: JsonPostingsWriter<Rec>) -> Box<dyn PostingsWriter> {
-        Box::new(json_postings_writer)
-    }
-}
-
 impl<Rec: Recorder> PostingsWriter for JsonPostingsWriter<Rec> {
     #[inline]
     fn subscribe(
@@ -58,12 +53,12 @@ impl<Rec: Recorder> PostingsWriter for JsonPostingsWriter<Rec> {
     }
 
     /// The actual serialization format is handled by the `PostingsSerializer`.
-    fn serialize(
+    fn serialize<C: Codec>(
         &self,
         ordered_term_addrs: &[(Field, OrderedPathId, &[u8], Addr)],
         ordered_id_to_path: &[&str],
         ctx: &IndexingContext,
-        serializer: &mut FieldSerializer,
+        serializer: &mut FieldSerializer<C>,
     ) -> io::Result<()> {
         let mut term_buffer = JsonTermSerializer(Vec::with_capacity(48));
         let mut buffer_lender = BufferLender::default();

src/postings/loaded_postings.rs

@@ -1,5 +1,5 @@
 use crate::docset::{DocSet, TERMINATED};
-use crate::postings::{Postings, SegmentPostings};
+use crate::postings::{DocFreq, Postings};
 use crate::DocId;
 
 /// `LoadedPostings` is a `DocSet` and `Postings` implementation.
@@ -25,16 +25,16 @@ impl LoadedPostings {
     /// Creates a new `LoadedPostings` from a `SegmentPostings`.
     ///
     /// It will also preload positions, if positions are available in the SegmentPostings.
-    pub fn load(segment_postings: &mut SegmentPostings) -> LoadedPostings {
-        let num_docs = segment_postings.doc_freq() as usize;
+    pub fn load(postings: &mut Box<dyn Postings>) -> LoadedPostings {
+        let num_docs: usize = u32::from(postings.doc_freq()) as usize;
         let mut doc_ids = Vec::with_capacity(num_docs);
         let mut positions = Vec::with_capacity(num_docs);
         let mut position_offsets = Vec::with_capacity(num_docs);
-        while segment_postings.doc() != TERMINATED {
+        while postings.doc() != TERMINATED {
             position_offsets.push(positions.len() as u32);
-            doc_ids.push(segment_postings.doc());
-            segment_postings.append_positions_with_offset(0, &mut positions);
-            segment_postings.advance();
+            doc_ids.push(postings.doc());
+            postings.append_positions_with_offset(0, &mut positions);
+            postings.advance();
         }
         position_offsets.push(positions.len() as u32);
         LoadedPostings {
@@ -101,6 +101,14 @@ impl Postings for LoadedPostings {
             output.push(*pos + offset);
         }
     }
+
+    fn has_freq(&self) -> bool {
+        true
+    }
+
+    fn doc_freq(&self) -> DocFreq {
+        DocFreq::Exact(self.doc_ids.len() as u32)
+    }
 }
 
 #[cfg(test)]

src/postings/mod.rs

@@ -4,7 +4,6 @@ mod block_search;
 
 pub(crate) use self::block_search::branchless_binary_search;
 
-mod block_segment_postings;
 pub(crate) mod compression;
 mod indexing_context;
 mod json_postings_writer;
@@ -13,32 +12,22 @@ mod per_field_postings_writer;
 mod postings;
 mod postings_writer;
 mod recorder;
-mod segment_postings;
 mod serializer;
-mod skip;
 mod term_info;
 
 pub(crate) use loaded_postings::LoadedPostings;
+pub use postings::DocFreq;
 pub(crate) use stacker::compute_table_memory_size;
 
-pub use self::block_segment_postings::BlockSegmentPostings;
 pub(crate) use self::indexing_context::IndexingContext;
 pub(crate) use self::per_field_postings_writer::PerFieldPostingsWriter;
 pub use self::postings::Postings;
-pub(crate) use self::postings_writer::{serialize_postings, IndexingPosition, PostingsWriter};
-pub use self::segment_postings::SegmentPostings;
+pub(crate) use self::postings_writer::{
+    serialize_postings, IndexingPosition, PostingsWriter, PostingsWriterEnum,
+};
 pub use self::serializer::{FieldSerializer, InvertedIndexSerializer};
-pub(crate) use self::skip::{BlockInfo, SkipReader};
 pub use self::term_info::TermInfo;
 
-#[expect(clippy::enum_variant_names)]
-#[derive(Debug, PartialEq, Clone, Copy, Eq)]
-pub(crate) enum FreqReadingOption {
-    NoFreq,
-    SkipFreq,
-    ReadFreq,
-}
-
 #[cfg(test)]
 pub(crate) mod tests {
     use std::mem;
@@ -46,9 +35,10 @@ pub(crate) mod tests {
     use super::{InvertedIndexSerializer, Postings};
     use crate::docset::{DocSet, TERMINATED};
     use crate::fieldnorm::FieldNormReader;
-    use crate::index::{Index, SegmentComponent, SegmentReader, TantivySegmentReader};
+    use crate::index::{Index, SegmentComponent, SegmentReader};
     use crate::indexer::operation::AddOperation;
     use crate::indexer::SegmentWriter;
+    use crate::postings::DocFreq;
     use crate::query::Scorer;
     use crate::schema::{
         Field, IndexRecordOption, Schema, Term, TextFieldIndexing, TextOptions, INDEXED, TEXT,
@@ -258,12 +248,9 @@ pub(crate) mod tests {
             segment_writer.finalize()?;
         }
         {
-            let segment_reader = TantivySegmentReader::open(&segment)?;
+            let segment_reader = SegmentReader::open(&segment)?;
             {
-                let fieldnorm_reader = segment_reader
-                    .fieldnorms_readers()
-                    .get_field(text_field)?
-                    .unwrap();
+                let fieldnorm_reader = segment_reader.get_fieldnorms_reader(text_field)?;
                 assert_eq!(fieldnorm_reader.fieldnorm(0), 8 + 5);
                 assert_eq!(fieldnorm_reader.fieldnorm(1), 2);
                 for i in 2..1000 {
@@ -282,11 +269,11 @@ pub(crate) mod tests {
             }
             {
                 let term_a = Term::from_field_text(text_field, "a");
-                let mut postings_a = segment_reader
+                let mut postings_a: Box<dyn Postings> = segment_reader
                     .inverted_index(term_a.field())?
                     .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
-                assert_eq!(postings_a.len(), 1000);
+                assert_eq!(postings_a.doc_freq(), DocFreq::Exact(1000));
                 assert_eq!(postings_a.doc(), 0);
                 assert_eq!(postings_a.term_freq(), 6);
                 postings_a.positions(&mut positions);
@@ -309,7 +296,7 @@ pub(crate) mod tests {
                     .inverted_index(term_e.field())?
                     .read_postings(&term_e, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
-                assert_eq!(postings_e.len(), 1000 - 2);
+                assert_eq!(postings_e.doc_freq(), DocFreq::Exact(1000 - 2));
                 for i in 2u32..1000u32 {
                     assert_eq!(postings_e.term_freq(), i);
                     postings_e.positions(&mut positions);
@@ -607,13 +594,13 @@ mod bench {
             let mut index_writer: IndexWriter = index.writer_for_tests().unwrap();
             for _ in 0..posting_list_size {
                 let mut doc = TantivyDocument::default();
-                if rng.random_bool(1f64 / 15f64) {
+                if rng.gen_bool(1f64 / 15f64) {
                     doc.add_text(text_field, "a");
                 }
-                if rng.random_bool(1f64 / 10f64) {
+                if rng.gen_bool(1f64 / 10f64) {
                     doc.add_text(text_field, "b");
                 }
-                if rng.random_bool(1f64 / 5f64) {
+                if rng.gen_bool(1f64 / 5f64) {
                     doc.add_text(text_field, "c");
                 }
                 doc.add_text(text_field, "d");

src/postings/per_field_postings_writer.rs

@@ -1,16 +1,15 @@
 use crate::postings::json_postings_writer::JsonPostingsWriter;
-use crate::postings::postings_writer::SpecializedPostingsWriter;
+use crate::postings::postings_writer::{PostingsWriterEnum, SpecializedPostingsWriter};
 use crate::postings::recorder::{DocIdRecorder, TermFrequencyRecorder, TfAndPositionRecorder};
-use crate::postings::PostingsWriter;
 use crate::schema::{Field, FieldEntry, FieldType, IndexRecordOption, Schema};
 
 pub(crate) struct PerFieldPostingsWriter {
-    per_field_postings_writers: Vec<Box<dyn PostingsWriter>>,
+    per_field_postings_writers: Vec<PostingsWriterEnum>,
 }
 
 impl PerFieldPostingsWriter {
     pub fn for_schema(schema: &Schema) -> Self {
-        let per_field_postings_writers = schema
+        let per_field_postings_writers: Vec<PostingsWriterEnum> = schema
             .fields()
             .map(|(_, field_entry)| posting_writer_from_field_entry(field_entry))
             .collect();
@@ -19,16 +18,16 @@ impl PerFieldPostingsWriter {
         }
     }
 
-    pub(crate) fn get_for_field(&self, field: Field) -> &dyn PostingsWriter {
-        self.per_field_postings_writers[field.field_id() as usize].as_ref()
+    pub(crate) fn get_for_field(&self, field: Field) -> &PostingsWriterEnum {
+        &self.per_field_postings_writers[field.field_id() as usize]
     }
 
-    pub(crate) fn get_for_field_mut(&mut self, field: Field) -> &mut dyn PostingsWriter {
-        self.per_field_postings_writers[field.field_id() as usize].as_mut()
+    pub(crate) fn get_for_field_mut(&mut self, field: Field) -> &mut PostingsWriterEnum {
+        &mut self.per_field_postings_writers[field.field_id() as usize]
     }
 }
 
-fn posting_writer_from_field_entry(field_entry: &FieldEntry) -> Box<dyn PostingsWriter> {
+fn posting_writer_from_field_entry(field_entry: &FieldEntry) -> PostingsWriterEnum {
     match *field_entry.field_type() {
         FieldType::Str(ref text_options) => text_options
             .get_indexing_options()
@@ -51,7 +50,7 @@ fn posting_writer_from_field_entry(field_entry: &FieldEntry) -> Box<dyn Postings
         | FieldType::Date(_)
         | FieldType::Bytes(_)
         | FieldType::IpAddr(_)
-        | FieldType::Facet(_) => Box::<SpecializedPostingsWriter<DocIdRecorder>>::default(),
+        | FieldType::Facet(_) => <SpecializedPostingsWriter<DocIdRecorder>>::default().into(),
         FieldType::JsonObject(ref json_object_options) => {
             if let Some(text_indexing_option) = json_object_options.get_text_indexing_options() {
                 match text_indexing_option.index_option() {

src/postings/postings.rs

@@ -1,5 +1,25 @@
 use crate::docset::DocSet;
 
+/// Result of the doc_freq method.
+///
+/// Postings can inform us that the document frequency is approximate.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum DocFreq {
+    /// The document frequency is approximate.
+    Approximate(u32),
+    /// The document frequency is exact.
+    Exact(u32),
+}
+
+impl From<DocFreq> for u32 {
+    fn from(doc_freq: DocFreq) -> Self {
+        match doc_freq {
+            DocFreq::Approximate(approximate_doc_freq) => approximate_doc_freq,
+            DocFreq::Exact(doc_freq) => doc_freq,
+        }
+    }
+}
+
 /// Postings (also called inverted list)
 ///
 /// For a given term, it is the list of doc ids of the doc
@@ -14,6 +34,9 @@ pub trait Postings: DocSet + 'static {
     /// The number of times the term appears in the document.
     fn term_freq(&self) -> u32;
 
+    /// Returns the number of documents containing the term in the segment.
+    fn doc_freq(&self) -> DocFreq;
+
     /// Returns the positions offsetted with a given value.
     /// It is not necessary to clear the `output` before calling this method.
     /// The output vector will be resized to the `term_freq`.
@@ -31,6 +54,16 @@ pub trait Postings: DocSet + 'static {
     fn positions(&mut self, output: &mut Vec<u32>) {
         self.positions_with_offset(0u32, output);
     }
+
+    /// Returns true if the term_frequency is available.
+    ///
+    /// This is a tricky question, because on JSON fields, it is possible
+    /// for a text term to have term freq, whereas a number term in the field has none.
+    ///
+    /// This function returns whether the actual term has term frequencies or not.
+    /// In this above JSON field example, `has_freq` should return true for the
+    /// earlier and false for the latter.
+    fn has_freq(&self) -> bool;
 }
 
 impl Postings for Box<dyn Postings> {
@@ -41,4 +74,12 @@ impl Postings for Box<dyn Postings> {
     fn append_positions_with_offset(&mut self, offset: u32, output: &mut Vec<u32>) {
         (**self).append_positions_with_offset(offset, output);
     }
+
+    fn has_freq(&self) -> bool {
+        (**self).has_freq()
+    }
+
+    fn doc_freq(&self) -> DocFreq {
+        (**self).doc_freq()
+    }
 }

src/postings/postings_writer.rs

@@ -4,10 +4,14 @@ use std::ops::Range;
 
 use stacker::Addr;
 
+use crate::codec::Codec;
 use crate::fieldnorm::FieldNormReaders;
 use crate::indexer::indexing_term::IndexingTerm;
 use crate::indexer::path_to_unordered_id::OrderedPathId;
-use crate::postings::recorder::{BufferLender, Recorder};
+use crate::postings::json_postings_writer::JsonPostingsWriter;
+use crate::postings::recorder::{
+    BufferLender, DocIdRecorder, Recorder, TermFrequencyRecorder, TfAndPositionRecorder,
+};
 use crate::postings::{
     FieldSerializer, IndexingContext, InvertedIndexSerializer, PerFieldPostingsWriter,
 };
@@ -45,12 +49,12 @@ fn make_field_partition(
 /// Serialize the inverted index.
 /// It pushes all term, one field at a time, towards the
 /// postings serializer.
-pub(crate) fn serialize_postings(
+pub(crate) fn serialize_postings<C: Codec>(
     ctx: IndexingContext,
     schema: Schema,
     per_field_postings_writers: &PerFieldPostingsWriter,
     fieldnorm_readers: FieldNormReaders,
-    serializer: &mut InvertedIndexSerializer,
+    serializer: &mut InvertedIndexSerializer<C>,
 ) -> crate::Result<()> {
     // Replace unordered ids by ordered ids to be able to sort
     let unordered_id_to_ordered_id: Vec<OrderedPathId> =
@@ -100,6 +104,141 @@ pub(crate) struct IndexingPosition {
     pub end_position: u32,
 }
 
+pub enum PostingsWriterEnum {
+    DocId(SpecializedPostingsWriter<DocIdRecorder>),
+    DocIdTf(SpecializedPostingsWriter<TermFrequencyRecorder>),
+    DocTfAndPosition(SpecializedPostingsWriter<TfAndPositionRecorder>),
+    JsonDocId(JsonPostingsWriter<DocIdRecorder>),
+    JsonDocIdTf(JsonPostingsWriter<TermFrequencyRecorder>),
+    JsonDocTfAndPosition(JsonPostingsWriter<TfAndPositionRecorder>),
+}
+
+impl From<SpecializedPostingsWriter<DocIdRecorder>> for PostingsWriterEnum {
+    fn from(doc_id_recorder_writer: SpecializedPostingsWriter<DocIdRecorder>) -> Self {
+        PostingsWriterEnum::DocId(doc_id_recorder_writer)
+    }
+}
+
+impl From<SpecializedPostingsWriter<TermFrequencyRecorder>> for PostingsWriterEnum {
+    fn from(doc_id_tf_recorder_writer: SpecializedPostingsWriter<TermFrequencyRecorder>) -> Self {
+        PostingsWriterEnum::DocIdTf(doc_id_tf_recorder_writer)
+    }
+}
+
+impl From<SpecializedPostingsWriter<TfAndPositionRecorder>> for PostingsWriterEnum {
+    fn from(
+        doc_id_tf_and_positions_recorder_writer: SpecializedPostingsWriter<TfAndPositionRecorder>,
+    ) -> Self {
+        PostingsWriterEnum::DocTfAndPosition(doc_id_tf_and_positions_recorder_writer)
+    }
+}
+
+impl From<JsonPostingsWriter<DocIdRecorder>> for PostingsWriterEnum {
+    fn from(doc_id_recorder_writer: JsonPostingsWriter<DocIdRecorder>) -> Self {
+        PostingsWriterEnum::JsonDocId(doc_id_recorder_writer)
+    }
+}
+
+impl From<JsonPostingsWriter<TermFrequencyRecorder>> for PostingsWriterEnum {
+    fn from(doc_id_tf_recorder_writer: JsonPostingsWriter<TermFrequencyRecorder>) -> Self {
+        PostingsWriterEnum::JsonDocIdTf(doc_id_tf_recorder_writer)
+    }
+}
+
+impl From<JsonPostingsWriter<TfAndPositionRecorder>> for PostingsWriterEnum {
+    fn from(
+        doc_id_tf_and_positions_recorder_writer: JsonPostingsWriter<TfAndPositionRecorder>,
+    ) -> Self {
+        PostingsWriterEnum::JsonDocTfAndPosition(doc_id_tf_and_positions_recorder_writer)
+    }
+}
+
+impl PostingsWriter for PostingsWriterEnum {
+    fn subscribe(&mut self, doc: DocId, pos: u32, term: &IndexingTerm, ctx: &mut IndexingContext) {
+        match self {
+            PostingsWriterEnum::DocId(writer) => writer.subscribe(doc, pos, term, ctx),
+            PostingsWriterEnum::DocIdTf(writer) => writer.subscribe(doc, pos, term, ctx),
+            PostingsWriterEnum::DocTfAndPosition(writer) => writer.subscribe(doc, pos, term, ctx),
+            PostingsWriterEnum::JsonDocId(writer) => writer.subscribe(doc, pos, term, ctx),
+            PostingsWriterEnum::JsonDocIdTf(writer) => writer.subscribe(doc, pos, term, ctx),
+            PostingsWriterEnum::JsonDocTfAndPosition(writer) => {
+                writer.subscribe(doc, pos, term, ctx)
+            }
+        }
+    }
+
+    fn serialize<C: Codec>(
+        &self,
+        term_addrs: &[(Field, OrderedPathId, &[u8], Addr)],
+        ordered_id_to_path: &[&str],
+        ctx: &IndexingContext,
+        serializer: &mut FieldSerializer<C>,
+    ) -> io::Result<()> {
+        match self {
+            PostingsWriterEnum::DocId(writer) => {
+                writer.serialize(term_addrs, ordered_id_to_path, ctx, serializer)
+            }
+            PostingsWriterEnum::DocIdTf(writer) => {
+                writer.serialize(term_addrs, ordered_id_to_path, ctx, serializer)
+            }
+            PostingsWriterEnum::DocTfAndPosition(writer) => {
+                writer.serialize(term_addrs, ordered_id_to_path, ctx, serializer)
+            }
+            PostingsWriterEnum::JsonDocId(writer) => {
+                writer.serialize(term_addrs, ordered_id_to_path, ctx, serializer)
+            }
+            PostingsWriterEnum::JsonDocIdTf(writer) => {
+                writer.serialize(term_addrs, ordered_id_to_path, ctx, serializer)
+            }
+            PostingsWriterEnum::JsonDocTfAndPosition(writer) => {
+                writer.serialize(term_addrs, ordered_id_to_path, ctx, serializer)
+            }
+        }
+    }
+
+    /// Tokenize a text and subscribe all of its token.
+    fn index_text(
+        &mut self,
+        doc_id: DocId,
+        token_stream: &mut dyn TokenStream,
+        term_buffer: &mut IndexingTerm,
+        ctx: &mut IndexingContext,
+        indexing_position: &mut IndexingPosition,
+    ) {
+        match self {
+            PostingsWriterEnum::DocId(writer) => {
+                writer.index_text(doc_id, token_stream, term_buffer, ctx, indexing_position)
+            }
+            PostingsWriterEnum::DocIdTf(writer) => {
+                writer.index_text(doc_id, token_stream, term_buffer, ctx, indexing_position)
+            }
+            PostingsWriterEnum::DocTfAndPosition(writer) => {
+                writer.index_text(doc_id, token_stream, term_buffer, ctx, indexing_position)
+            }
+            PostingsWriterEnum::JsonDocId(writer) => {
+                writer.index_text(doc_id, token_stream, term_buffer, ctx, indexing_position)
+            }
+            PostingsWriterEnum::JsonDocIdTf(writer) => {
+                writer.index_text(doc_id, token_stream, term_buffer, ctx, indexing_position)
+            }
+            PostingsWriterEnum::JsonDocTfAndPosition(writer) => {
+                writer.index_text(doc_id, token_stream, term_buffer, ctx, indexing_position)
+            }
+        }
+    }
+
+    fn total_num_tokens(&self) -> u64 {
+        match self {
+            PostingsWriterEnum::DocId(writer) => writer.total_num_tokens(),
+            PostingsWriterEnum::DocIdTf(writer) => writer.total_num_tokens(),
+            PostingsWriterEnum::DocTfAndPosition(writer) => writer.total_num_tokens(),
+            PostingsWriterEnum::JsonDocId(writer) => writer.total_num_tokens(),
+            PostingsWriterEnum::JsonDocIdTf(writer) => writer.total_num_tokens(),
+            PostingsWriterEnum::JsonDocTfAndPosition(writer) => writer.total_num_tokens(),
+        }
+    }
+}
+
 /// The `PostingsWriter` is in charge of receiving documenting
 /// and building a `Segment` in anonymous memory.
 ///
@@ -116,12 +255,12 @@ pub(crate) trait PostingsWriter: Send + Sync {
 
     /// Serializes the postings on disk.
     /// The actual serialization format is handled by the `PostingsSerializer`.
-    fn serialize(
+    fn serialize<C: Codec>(
         &self,
         term_addrs: &[(Field, OrderedPathId, &[u8], Addr)],
         ordered_id_to_path: &[&str],
         ctx: &IndexingContext,
-        serializer: &mut FieldSerializer,
+        serializer: &mut FieldSerializer<C>,
     ) -> io::Result<()>;
 
     /// Tokenize a text and subscribe all of its token.
@@ -171,22 +310,14 @@ pub(crate) struct SpecializedPostingsWriter<Rec: Recorder> {
     _recorder_type: PhantomData<Rec>,
 }
 
-impl<Rec: Recorder> From<SpecializedPostingsWriter<Rec>> for Box<dyn PostingsWriter> {
-    fn from(
-        specialized_postings_writer: SpecializedPostingsWriter<Rec>,
-    ) -> Box<dyn PostingsWriter> {
-        Box::new(specialized_postings_writer)
-    }
-}
-
 impl<Rec: Recorder> SpecializedPostingsWriter<Rec> {
     #[inline]
-    pub(crate) fn serialize_one_term(
+    pub(crate) fn serialize_one_term<C: Codec>(
         term: &[u8],
         addr: Addr,
         buffer_lender: &mut BufferLender,
         ctx: &IndexingContext,
-        serializer: &mut FieldSerializer,
+        serializer: &mut FieldSerializer<C>,
     ) -> io::Result<()> {
         let recorder: Rec = ctx.term_index.read(addr);
         let term_doc_freq = recorder.term_doc_freq().unwrap_or(0u32);
@@ -227,12 +358,12 @@ impl<Rec: Recorder> PostingsWriter for SpecializedPostingsWriter<Rec> {
         });
     }
 
-    fn serialize(
+    fn serialize<C: Codec>(
         &self,
         term_addrs: &[(Field, OrderedPathId, &[u8], Addr)],
         _ordered_id_to_path: &[&str],
         ctx: &IndexingContext,
-        serializer: &mut FieldSerializer,
+        serializer: &mut FieldSerializer<C>,
     ) -> io::Result<()> {
         let mut buffer_lender = BufferLender::default();
         for (_field, _path_id, term, addr) in term_addrs {

src/postings/recorder.rs

@@ -1,6 +1,7 @@
 use common::read_u32_vint;
 use stacker::{ExpUnrolledLinkedList, MemoryArena};
 
+use crate::codec::Codec;
 use crate::postings::FieldSerializer;
 use crate::DocId;
 
@@ -67,10 +68,10 @@ pub(crate) trait Recorder: Copy + Default + Send + Sync + 'static {
     /// Close the document. It will help record the term frequency.
     fn close_doc(&mut self, arena: &mut MemoryArena);
     /// Pushes the postings information to the serializer.
-    fn serialize(
+    fn serialize<C: Codec>(
         &self,
         arena: &MemoryArena,
-        serializer: &mut FieldSerializer<'_>,
+        serializer: &mut FieldSerializer<C>,
         buffer_lender: &mut BufferLender,
     );
     /// Returns the number of document containing this term.
@@ -110,10 +111,10 @@ impl Recorder for DocIdRecorder {
     #[inline]
     fn close_doc(&mut self, _arena: &mut MemoryArena) {}
 
-    fn serialize(
+    fn serialize<C: Codec>(
         &self,
         arena: &MemoryArena,
-        serializer: &mut FieldSerializer<'_>,
+        serializer: &mut FieldSerializer<C>,
         buffer_lender: &mut BufferLender,
     ) {
         let buffer = buffer_lender.lend_u8();
@@ -178,10 +179,10 @@ impl Recorder for TermFrequencyRecorder {
         self.current_tf = 0;
     }
 
-    fn serialize(
+    fn serialize<C: Codec>(
         &self,
         arena: &MemoryArena,
-        serializer: &mut FieldSerializer<'_>,
+        serializer: &mut FieldSerializer<C>,
         buffer_lender: &mut BufferLender,
     ) {
         let buffer = buffer_lender.lend_u8();
@@ -235,10 +236,10 @@ impl Recorder for TfAndPositionRecorder {
         self.stack.writer(arena).write_u32_vint(POSITION_END);
     }
 
-    fn serialize(
+    fn serialize<C: Codec>(
         &self,
         arena: &MemoryArena,
-        serializer: &mut FieldSerializer<'_>,
+        serializer: &mut FieldSerializer<C>,
         buffer_lender: &mut BufferLender,
     ) {
         let (buffer_u8, buffer_positions) = buffer_lender.lend_all();

src/postings/serializer.rs

@@ -1,16 +1,14 @@
-use std::cmp::Ordering;
 use std::io::{self, Write};
 
-use common::{BinarySerializable, CountingWriter, VInt};
+use common::{BinarySerializable, CountingWriter};
 
 use super::TermInfo;
+use crate::codec::postings::PostingsSerializer;
+use crate::codec::Codec;
 use crate::directory::{CompositeWrite, WritePtr};
 use crate::fieldnorm::FieldNormReader;
 use crate::index::Segment;
 use crate::positions::PositionSerializer;
-use crate::postings::compression::{BlockEncoder, VIntEncoder, COMPRESSION_BLOCK_SIZE};
-use crate::postings::skip::SkipSerializer;
-use crate::query::Bm25Weight;
 use crate::schema::{Field, FieldEntry, FieldType, IndexRecordOption, Schema};
 use crate::termdict::TermDictionaryBuilder;
 use crate::{DocId, Score};
@@ -46,22 +44,27 @@ use crate::{DocId, Score};
 ///
 /// A description of the serialization format is
 /// [available here](https://fulmicoton.gitbooks.io/tantivy-doc/content/inverted-index.html).
-pub struct InvertedIndexSerializer {
+pub struct InvertedIndexSerializer<C: Codec> {
     terms_write: CompositeWrite<WritePtr>,
     postings_write: CompositeWrite<WritePtr>,
     positions_write: CompositeWrite<WritePtr>,
     schema: Schema,
+    codec: C,
 }
 
-impl InvertedIndexSerializer {
+use crate::codec::postings::PostingsCodec;
+
+impl<C: Codec> InvertedIndexSerializer<C> {
     /// Open a new `InvertedIndexSerializer` for the given segment
-    pub fn open(segment: &mut Segment) -> crate::Result<InvertedIndexSerializer> {
+    pub fn open(segment: &mut Segment<C>) -> crate::Result<InvertedIndexSerializer<C>> {
         use crate::index::SegmentComponent::{Positions, Postings, Terms};
+        let codec = segment.index().codec().clone();
         let inv_index_serializer = InvertedIndexSerializer {
             terms_write: CompositeWrite::wrap(segment.open_write(Terms)?),
             postings_write: CompositeWrite::wrap(segment.open_write(Postings)?),
             positions_write: CompositeWrite::wrap(segment.open_write(Positions)?),
             schema: segment.schema(),
+            codec,
         };
         Ok(inv_index_serializer)
     }
@@ -75,7 +78,7 @@ impl InvertedIndexSerializer {
         field: Field,
         total_num_tokens: u64,
         fieldnorm_reader: Option<FieldNormReader>,
-    ) -> io::Result<FieldSerializer<'_>> {
+    ) -> io::Result<FieldSerializer<'_, C>> {
         let field_entry: &FieldEntry = self.schema.get_field_entry(field);
         let term_dictionary_write = self.terms_write.for_field(field);
         let postings_write = self.postings_write.for_field(field);
@@ -88,6 +91,7 @@ impl InvertedIndexSerializer {
             postings_write,
             positions_write,
             fieldnorm_reader,
+            &self.codec,
         )
     }
 
@@ -102,9 +106,9 @@ impl InvertedIndexSerializer {
 
 /// The field serializer is in charge of
 /// the serialization of a specific field.
-pub struct FieldSerializer<'a> {
+pub struct FieldSerializer<'a, C: Codec> {
     term_dictionary_builder: TermDictionaryBuilder<&'a mut CountingWriter<WritePtr>>,
-    postings_serializer: PostingsSerializer,
+    postings_serializer: <C::PostingsCodec as PostingsCodec>::PostingsSerializer,
     positions_serializer_opt: Option<PositionSerializer<&'a mut CountingWriter<WritePtr>>>,
     current_term_info: TermInfo,
     term_open: bool,
@@ -112,7 +116,7 @@ pub struct FieldSerializer<'a> {
     postings_start_offset: u64,
 }
 
-impl<'a> FieldSerializer<'a> {
+impl<'a, C: Codec> FieldSerializer<'a, C> {
     fn create(
         field_type: &FieldType,
         total_num_tokens: u64,
@@ -120,7 +124,8 @@ impl<'a> FieldSerializer<'a> {
         postings_write: &'a mut CountingWriter<WritePtr>,
         positions_write: &'a mut CountingWriter<WritePtr>,
         fieldnorm_reader: Option<FieldNormReader>,
-    ) -> io::Result<FieldSerializer<'a>> {
+        codec: &C,
+    ) -> io::Result<FieldSerializer<'a, C>> {
         total_num_tokens.serialize(postings_write)?;
         let index_record_option = field_type
             .index_record_option()
@@ -130,8 +135,11 @@ impl<'a> FieldSerializer<'a> {
             .as_ref()
             .map(|ff_reader| total_num_tokens as Score / ff_reader.num_docs() as Score)
             .unwrap_or(0.0);
-        let postings_serializer =
-            PostingsSerializer::new(average_fieldnorm, index_record_option, fieldnorm_reader);
+        let postings_serializer = codec.postings_codec().new_serializer(
+            average_fieldnorm,
+            index_record_option,
+            fieldnorm_reader,
+        );
         let positions_serializer_opt = if index_record_option.has_positions() {
             Some(PositionSerializer::new(positions_write))
         } else {
@@ -184,7 +192,6 @@ impl<'a> FieldSerializer<'a> {
             "Called new_term, while the previous term was not closed."
         );
         self.term_open = true;
-        self.postings_serializer.clear();
         self.current_term_info = self.current_term_info();
         self.term_dictionary_builder.insert_key(term)?;
         self.postings_serializer
@@ -248,223 +255,3 @@ impl<'a> FieldSerializer<'a> {
         Ok(())
     }
 }
-
-struct Block {
-    doc_ids: [DocId; COMPRESSION_BLOCK_SIZE],
-    term_freqs: [u32; COMPRESSION_BLOCK_SIZE],
-    len: usize,
-}
-
-impl Block {
-    fn new() -> Self {
-        Block {
-            doc_ids: [0u32; COMPRESSION_BLOCK_SIZE],
-            term_freqs: [0u32; COMPRESSION_BLOCK_SIZE],
-            len: 0,
-        }
-    }
-
-    fn doc_ids(&self) -> &[DocId] {
-        &self.doc_ids[..self.len]
-    }
-
-    fn term_freqs(&self) -> &[u32] {
-        &self.term_freqs[..self.len]
-    }
-
-    fn clear(&mut self) {
-        self.len = 0;
-    }
-
-    fn append_doc(&mut self, doc: DocId, term_freq: u32) {
-        let len = self.len;
-        self.doc_ids[len] = doc;
-        self.term_freqs[len] = term_freq;
-        self.len = len + 1;
-    }
-
-    fn is_full(&self) -> bool {
-        self.len == COMPRESSION_BLOCK_SIZE
-    }
-
-    fn is_empty(&self) -> bool {
-        self.len == 0
-    }
-
-    fn last_doc(&self) -> DocId {
-        assert_eq!(self.len, COMPRESSION_BLOCK_SIZE);
-        self.doc_ids[COMPRESSION_BLOCK_SIZE - 1]
-    }
-}
-
-pub struct PostingsSerializer {
-    last_doc_id_encoded: u32,
-
-    block_encoder: BlockEncoder,
-    block: Box<Block>,
-
-    postings_write: Vec<u8>,
-    skip_write: SkipSerializer,
-
-    mode: IndexRecordOption,
-    fieldnorm_reader: Option<FieldNormReader>,
-
-    bm25_weight: Option<Bm25Weight>,
-    avg_fieldnorm: Score, /* Average number of term in the field for that segment.
-                           * this value is used to compute the block wand information. */
-    term_has_freq: bool,
-}
-
-impl PostingsSerializer {
-    pub fn new(
-        avg_fieldnorm: Score,
-        mode: IndexRecordOption,
-        fieldnorm_reader: Option<FieldNormReader>,
-    ) -> PostingsSerializer {
-        PostingsSerializer {
-            block_encoder: BlockEncoder::new(),
-            block: Box::new(Block::new()),
-
-            postings_write: Vec::new(),
-            skip_write: SkipSerializer::new(),
-
-            last_doc_id_encoded: 0u32,
-            mode,
-
-            fieldnorm_reader,
-            bm25_weight: None,
-            avg_fieldnorm,
-            term_has_freq: false,
-        }
-    }
-
-    pub fn new_term(&mut self, term_doc_freq: u32, record_term_freq: bool) {
-        self.bm25_weight = None;
-
-        self.term_has_freq = self.mode.has_freq() && record_term_freq;
-        if !self.term_has_freq {
-            return;
-        }
-
-        let num_docs_in_segment: u64 =
-            if let Some(fieldnorm_reader) = self.fieldnorm_reader.as_ref() {
-                fieldnorm_reader.num_docs() as u64
-            } else {
-                return;
-            };
-
-        if num_docs_in_segment == 0 {
-            return;
-        }
-
-        self.bm25_weight = Some(Bm25Weight::for_one_term_without_explain(
-            term_doc_freq as u64,
-            num_docs_in_segment,
-            self.avg_fieldnorm,
-        ));
-    }
-
-    fn write_block(&mut self) {
-        {
-            // encode the doc ids
-            let (num_bits, block_encoded): (u8, &[u8]) = self
-                .block_encoder
-                .compress_block_sorted(self.block.doc_ids(), self.last_doc_id_encoded);
-            self.last_doc_id_encoded = self.block.last_doc();
-            self.skip_write
-                .write_doc(self.last_doc_id_encoded, num_bits);
-            // last el block 0, offset block 1,
-            self.postings_write.extend(block_encoded);
-        }
-        if self.term_has_freq {
-            let (num_bits, block_encoded): (u8, &[u8]) = self
-                .block_encoder
-                .compress_block_unsorted(self.block.term_freqs(), true);
-            self.postings_write.extend(block_encoded);
-            self.skip_write.write_term_freq(num_bits);
-            if self.mode.has_positions() {
-                // We serialize the sum of term freqs within the skip information
-                // in order to navigate through positions.
-                let sum_freq = self.block.term_freqs().iter().cloned().sum();
-                self.skip_write.write_total_term_freq(sum_freq);
-            }
-            let mut blockwand_params = (0u8, 0u32);
-            if let Some(bm25_weight) = self.bm25_weight.as_ref() {
-                if let Some(fieldnorm_reader) = self.fieldnorm_reader.as_ref() {
-                    let docs = self.block.doc_ids().iter().cloned();
-                    let term_freqs = self.block.term_freqs().iter().cloned();
-                    let fieldnorms = docs.map(|doc| fieldnorm_reader.fieldnorm_id(doc));
-                    blockwand_params = fieldnorms
-                        .zip(term_freqs)
-                        .max_by(
-                            |(left_fieldnorm_id, left_term_freq),
-                             (right_fieldnorm_id, right_term_freq)| {
-                                let left_score =
-                                    bm25_weight.tf_factor(*left_fieldnorm_id, *left_term_freq);
-                                let right_score =
-                                    bm25_weight.tf_factor(*right_fieldnorm_id, *right_term_freq);
-                                left_score
-                                    .partial_cmp(&right_score)
-                                    .unwrap_or(Ordering::Equal)
-                            },
-                        )
-                        .unwrap();
-                }
-            }
-            let (fieldnorm_id, term_freq) = blockwand_params;
-            self.skip_write.write_blockwand_max(fieldnorm_id, term_freq);
-        }
-        self.block.clear();
-    }
-
-    pub fn write_doc(&mut self, doc_id: DocId, term_freq: u32) {
-        self.block.append_doc(doc_id, term_freq);
-        if self.block.is_full() {
-            self.write_block();
-        }
-    }
-
-    pub fn close_term(
-        &mut self,
-        doc_freq: u32,
-        output_write: &mut impl std::io::Write,
-    ) -> io::Result<()> {
-        if !self.block.is_empty() {
-            // we have doc ids waiting to be written
-            // this happens when the number of doc ids is
-            // not a perfect multiple of our block size.
-            //
-            // In that case, the remaining part is encoded
-            // using variable int encoding.
-            {
-                let block_encoded = self
-                    .block_encoder
-                    .compress_vint_sorted(self.block.doc_ids(), self.last_doc_id_encoded);
-                self.postings_write.write_all(block_encoded)?;
-            }
-            // ... Idem for term frequencies
-            if self.term_has_freq {
-                let block_encoded = self
-                    .block_encoder
-                    .compress_vint_unsorted(self.block.term_freqs());
-                self.postings_write.write_all(block_encoded)?;
-            }
-            self.block.clear();
-        }
-        if doc_freq >= COMPRESSION_BLOCK_SIZE as u32 {
-            let skip_data = self.skip_write.data();
-            VInt(skip_data.len() as u64).serialize(output_write)?;
-            output_write.write_all(skip_data)?;
-        }
-        output_write.write_all(&self.postings_write[..])?;
-        self.skip_write.clear();
-        self.postings_write.clear();
-        self.bm25_weight = None;
-        Ok(())
-    }
-
-    fn clear(&mut self) {
-        self.block.clear();
-        self.last_doc_id_encoded = 0;
-    }
-}

src/query/all_query.rs

@@ -2,7 +2,7 @@ use crate::docset::{DocSet, COLLECT_BLOCK_BUFFER_LEN, TERMINATED};
 use crate::index::SegmentReader;
 use crate::query::boost_query::BoostScorer;
 use crate::query::explanation::does_not_match;
-use crate::query::{EnableScoring, Explanation, Query, Scorer, Weight};
+use crate::query::{box_scorer, EnableScoring, Explanation, Query, Scorer, Weight};
 use crate::{DocId, Score};
 
 /// Query that matches all of the documents.
@@ -21,16 +21,16 @@ impl Query for AllQuery {
 pub struct AllWeight;
 
 impl Weight for AllWeight {
-    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         let all_scorer = AllScorer::new(reader.max_doc());
         if boost != 1.0 {
-            Ok(Box::new(BoostScorer::new(all_scorer, boost)))
+            Ok(box_scorer(BoostScorer::new(all_scorer, boost)))
         } else {
-            Ok(Box::new(all_scorer))
+            Ok(box_scorer(all_scorer))
         }
     }
 
-    fn explain(&self, reader: &dyn SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         if doc >= reader.max_doc() {
             return Err(does_not_match(doc));
         }

src/query/automaton_weight.rs

@@ -10,7 +10,7 @@ use crate::postings::TermInfo;
 use crate::query::{BitSetDocSet, ConstScorer, Explanation, Scorer, Weight};
 use crate::schema::{Field, IndexRecordOption};
 use crate::termdict::{TermDictionary, TermStreamer};
-use crate::{DocId, Score, TantivyError};
+use crate::{DocId, DocSet, Score, TantivyError};
 
 /// A weight struct for Fuzzy Term and Regex Queries
 pub struct AutomatonWeight<A> {
@@ -67,7 +67,7 @@ where
     }
 
     /// Returns the term infos that match the automaton
-    pub fn get_match_term_infos(&self, reader: &dyn SegmentReader) -> crate::Result<Vec<TermInfo>> {
+    pub fn get_match_term_infos(&self, reader: &SegmentReader) -> crate::Result<Vec<TermInfo>> {
         let inverted_index = reader.inverted_index(self.field)?;
         let term_dict = inverted_index.terms();
         let mut term_stream = self.automaton_stream(term_dict)?;
@@ -84,7 +84,7 @@ where
     A: Automaton + Send + Sync + 'static,
     A::State: Clone,
 {
-    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         let max_doc = reader.max_doc();
         let mut doc_bitset = BitSet::with_max_value(max_doc);
         let inverted_index = reader.inverted_index(self.field)?;
@@ -92,25 +92,16 @@ where
         let mut term_stream = self.automaton_stream(term_dict)?;
         while term_stream.advance() {
             let term_info = term_stream.value();
-            let mut block_segment_postings = inverted_index
-                .read_block_postings_from_terminfo(term_info, IndexRecordOption::Basic)?;
-            loop {
-                let docs = block_segment_postings.docs();
-                if docs.is_empty() {
-                    break;
-                }
-                for &doc in docs {
-                    doc_bitset.insert(doc);
-                }
-                block_segment_postings.advance();
-            }
+            let mut block_segment_postings =
+                inverted_index.read_postings_from_terminfo(term_info, IndexRecordOption::Basic)?;
+            block_segment_postings.fill_bitset(&mut doc_bitset);
         }
         let doc_bitset = BitSetDocSet::from(doc_bitset);
         let const_scorer = ConstScorer::new(doc_bitset, boost);
         Ok(Box::new(const_scorer))
     }
 
-    fn explain(&self, reader: &dyn SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         let mut scorer = self.scorer(reader, 1.0)?;
         if scorer.seek(doc) == doc {
             Ok(Explanation::new("AutomatonScorer", 1.0))

src/query/bitset/mod.rs

@@ -24,6 +24,13 @@ impl BitSetDocSet {
         self.cursor_bucket = bucket_addr;
         self.cursor_tinybitset = self.docs.tinyset(bucket_addr);
     }
+
+    /// Returns the number of documents in the bitset.
+    ///
+    /// This call is not free: it will bitcount the number of bits in the bitset.
+    pub fn doc_freq(&self) -> u32 {
+        self.docs.len() as u32
+    }
 }
 
 impl From<BitSet> for BitSetDocSet {

src/query/boolean_query/boolean_weight.rs

@@ -2,23 +2,16 @@ use std::collections::HashMap;
 
 use crate::docset::COLLECT_BLOCK_BUFFER_LEN;
 use crate::index::SegmentReader;
-use crate::postings::FreqReadingOption;
 use crate::query::disjunction::Disjunction;
 use crate::query::explanation::does_not_match;
 use crate::query::score_combiner::{DoNothingCombiner, ScoreCombiner};
-use crate::query::term_query::TermScorer;
-use crate::query::weight::{for_each_docset_buffered, for_each_pruning_scorer, for_each_scorer};
+use crate::query::weight::{for_each_docset_buffered, for_each_scorer};
 use crate::query::{
-    intersect_scorers, AllScorer, BufferedUnionScorer, EmptyScorer, Exclude, Explanation, Occur,
-    RequiredOptionalScorer, Scorer, Weight,
+    box_scorer, intersect_scorers, AllScorer, BufferedUnionScorer, EmptyScorer, Exclude,
+    Explanation, Occur, RequiredOptionalScorer, Scorer, Weight,
 };
 use crate::{DocId, Score};
 
-enum SpecializedScorer {
-    TermUnion(Vec<TermScorer>),
-    Other(Box<dyn Scorer>),
-}
-
 fn scorer_disjunction<TScoreCombiner>(
     scorers: Vec<Box<dyn Scorer>>,
     score_combiner: TScoreCombiner,
@@ -32,7 +25,7 @@ where
     if scorers.len() == 1 {
         return scorers.into_iter().next().unwrap(); // Safe unwrap.
     }
-    Box::new(Disjunction::new(
+    box_scorer(Disjunction::new(
         scorers,
         score_combiner,
         minimum_match_required,
@@ -44,56 +37,18 @@ fn scorer_union<TScoreCombiner>(
     scorers: Vec<Box<dyn Scorer>>,
     score_combiner_fn: impl Fn() -> TScoreCombiner,
     num_docs: u32,
-) -> SpecializedScorer
+) -> Box<dyn Scorer>
 where
     TScoreCombiner: ScoreCombiner,
 {
-    assert!(!scorers.is_empty());
-    if scorers.len() == 1 {
-        return SpecializedScorer::Other(scorers.into_iter().next().unwrap()); //< we checked the size beforehand
-    }
-
-    {
-        let is_all_term_queries = scorers.iter().all(|scorer| scorer.is::<TermScorer>());
-        if is_all_term_queries {
-            let scorers: Vec<TermScorer> = scorers
-                .into_iter()
-                .map(|scorer| *(scorer.downcast::<TermScorer>().map_err(|_| ()).unwrap()))
-                .collect();
-            if scorers
-                .iter()
-                .all(|scorer| scorer.freq_reading_option() == FreqReadingOption::ReadFreq)
-            {
-                // Block wand is only available if we read frequencies.
-                return SpecializedScorer::TermUnion(scorers);
-            } else {
-                return SpecializedScorer::Other(Box::new(BufferedUnionScorer::build(
-                    scorers,
-                    score_combiner_fn,
-                    num_docs,
-                )));
-            }
-        }
-    }
-    SpecializedScorer::Other(Box::new(BufferedUnionScorer::build(
-        scorers,
-        score_combiner_fn,
-        num_docs,
-    )))
-}
-
-fn into_box_scorer<TScoreCombiner: ScoreCombiner>(
-    scorer: SpecializedScorer,
-    score_combiner_fn: impl Fn() -> TScoreCombiner,
-    num_docs: u32,
-) -> Box<dyn Scorer> {
-    match scorer {
-        SpecializedScorer::TermUnion(term_scorers) => {
-            let union_scorer =
-                BufferedUnionScorer::build(term_scorers, score_combiner_fn, num_docs);
-            Box::new(union_scorer)
-        }
-        SpecializedScorer::Other(scorer) => scorer,
+    match scorers.len() {
+        0 => box_scorer(EmptyScorer),
+        1 => scorers.into_iter().next().unwrap(),
+        _ => box_scorer(BufferedUnionScorer::build(
+            scorers,
+            score_combiner_fn,
+            num_docs,
+        )),
     }
 }
 
@@ -110,7 +65,7 @@ fn effective_must_scorer(
     if must_scorers.is_empty() {
         if removed_all_scorer_count > 0 {
             // Had AllScorer(s) only - all docs match
-            Some(Box::new(AllScorer::new(max_doc)))
+            Some(box_scorer(AllScorer::new(max_doc)))
         } else {
             // No MUST constraint at all
             None
@@ -128,28 +83,26 @@ fn effective_must_scorer(
 /// When `scoring_enabled` is false, we can just return AllScorer alone since
 /// we don't need score contributions from the should_scorer.
 fn effective_should_scorer_for_union<TScoreCombiner: ScoreCombiner>(
-    should_scorer: SpecializedScorer,
+    should_scorer: Box<dyn Scorer>,
     removed_all_scorer_count: usize,
     max_doc: DocId,
     num_docs: u32,
     score_combiner_fn: impl Fn() -> TScoreCombiner,
     scoring_enabled: bool,
-) -> SpecializedScorer {
+) -> Box<dyn Scorer> {
     if removed_all_scorer_count > 0 {
         if scoring_enabled {
             // Need to union to get score contributions from both
-            let all_scorers: Vec<Box<dyn Scorer>> = vec![
-                into_box_scorer(should_scorer, &score_combiner_fn, num_docs),
-                Box::new(AllScorer::new(max_doc)),
-            ];
-            SpecializedScorer::Other(Box::new(BufferedUnionScorer::build(
+            let all_scorers: Vec<Box<dyn Scorer>> =
+                vec![should_scorer, box_scorer(AllScorer::new(max_doc))];
+            box_scorer(BufferedUnionScorer::build(
                 all_scorers,
                 score_combiner_fn,
                 num_docs,
-            )))
+            ))
         } else {
             // Scoring disabled - AllScorer alone is sufficient
-            SpecializedScorer::Other(Box::new(AllScorer::new(max_doc)))
+            box_scorer(AllScorer::new(max_doc))
         }
     } else {
         should_scorer
@@ -160,9 +113,9 @@ enum ShouldScorersCombinationMethod {
     // Should scorers are irrelevant.
     Ignored,
     // Only contributes to final score.
-    Optional(SpecializedScorer),
+    Optional(Box<dyn Scorer>),
     // Regardless of score, the should scorers may impact whether a document is matching or not.
-    Required(SpecializedScorer),
+    Required(Box<dyn Scorer>),
 }
 
 /// Weight associated to the `BoolQuery`.
@@ -205,7 +158,7 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
 
     fn per_occur_scorers(
         &self,
-        reader: &dyn SegmentReader,
+        reader: &SegmentReader,
         boost: Score,
     ) -> crate::Result<HashMap<Occur, Vec<Box<dyn Scorer>>>> {
         let mut per_occur_scorers: HashMap<Occur, Vec<Box<dyn Scorer>>> = HashMap::new();
@@ -221,10 +174,10 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
 
     fn complex_scorer<TComplexScoreCombiner: ScoreCombiner>(
         &self,
-        reader: &dyn SegmentReader,
+        reader: &SegmentReader,
         boost: Score,
         score_combiner_fn: impl Fn() -> TComplexScoreCombiner,
-    ) -> crate::Result<SpecializedScorer> {
+    ) -> crate::Result<Box<dyn Scorer>> {
         let num_docs = reader.num_docs();
         let mut per_occur_scorers = self.per_occur_scorers(reader, boost)?;
 
@@ -234,7 +187,7 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
         let must_special_scorer_counts = remove_and_count_all_and_empty_scorers(&mut must_scorers);
 
         if must_special_scorer_counts.num_empty_scorers > 0 {
-            return Ok(SpecializedScorer::Other(Box::new(EmptyScorer)));
+            return Ok(box_scorer(EmptyScorer));
         }
 
         let mut should_scorers = per_occur_scorers.remove(&Occur::Should).unwrap_or_default();
@@ -249,7 +202,7 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
 
         if exclude_special_scorer_counts.num_all_scorers > 0 {
             // We exclude all documents at one point.
-            return Ok(SpecializedScorer::Other(Box::new(EmptyScorer)));
+            return Ok(box_scorer(EmptyScorer));
         }
 
         let effective_minimum_number_should_match = self
@@ -261,7 +214,7 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
             if effective_minimum_number_should_match > num_of_should_scorers {
                 // We don't have enough scorers to satisfy the minimum number of should matches.
                 // The request will match no documents.
-                return Ok(SpecializedScorer::Other(Box::new(EmptyScorer)));
+                return Ok(box_scorer(EmptyScorer));
             }
             match effective_minimum_number_should_match {
                 0 if num_of_should_scorers == 0 => ShouldScorersCombinationMethod::Ignored,
@@ -281,12 +234,10 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
                     must_scorers.append(&mut should_scorers);
                     ShouldScorersCombinationMethod::Ignored
                 }
-                _ => ShouldScorersCombinationMethod::Required(SpecializedScorer::Other(
-                    scorer_disjunction(
-                        should_scorers,
-                        score_combiner_fn(),
-                        effective_minimum_number_should_match,
-                    ),
+                _ => ShouldScorersCombinationMethod::Required(scorer_disjunction(
+                    should_scorers,
+                    score_combiner_fn(),
+                    effective_minimum_number_should_match,
                 )),
             }
         };
@@ -294,13 +245,9 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
         let exclude_scorer_opt: Option<Box<dyn Scorer>> = if exclude_scorers.is_empty() {
             None
         } else {
-            let exclude_specialized_scorer: SpecializedScorer =
+            let exclude_scorers_union: Box<dyn Scorer> =
                 scorer_union(exclude_scorers, DoNothingCombiner::default, num_docs);
-            Some(into_box_scorer(
-                exclude_specialized_scorer,
-                DoNothingCombiner::default,
-                num_docs,
-            ))
+            Some(exclude_scorers_union)
         };
 
         let include_scorer = match (should_scorers, must_scorers) {
@@ -315,8 +262,8 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
                     reader.max_doc(),
                     num_docs,
                 )
-                .unwrap_or_else(|| Box::new(EmptyScorer));
-                SpecializedScorer::Other(boxed_scorer)
+                .unwrap_or_else(|| box_scorer(EmptyScorer));
+                boxed_scorer
             }
             (ShouldScorersCombinationMethod::Optional(should_scorer), must_scorers) => {
                 // Optional SHOULD: contributes to scoring but not required for matching.
@@ -341,16 +288,12 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
                     Some(must_scorer) => {
                         // Has MUST constraint: SHOULD only affects scoring.
                         if self.scoring_enabled {
-                            SpecializedScorer::Other(Box::new(RequiredOptionalScorer::<
-                                _,
-                                _,
-                                TScoreCombiner,
-                            >::new(
+                            box_scorer(RequiredOptionalScorer::<_, _, TScoreCombiner>::new(
                                 must_scorer,
-                                into_box_scorer(should_scorer, &score_combiner_fn, num_docs),
-                            )))
+                                should_scorer,
+                            ))
                         } else {
-                            SpecializedScorer::Other(must_scorer)
+                            must_scorer
                         }
                     }
                 }
@@ -370,23 +313,13 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
                     }
                     Some(must_scorer) => {
                         // Has MUST constraint: intersect MUST with SHOULD.
-                        let should_boxed =
-                            into_box_scorer(should_scorer, &score_combiner_fn, num_docs);
-                        SpecializedScorer::Other(intersect_scorers(
-                            vec![must_scorer, should_boxed],
-                            num_docs,
-                        ))
+                        intersect_scorers(vec![must_scorer, should_scorer], num_docs)
                     }
                 }
             }
         };
         if let Some(exclude_scorer) = exclude_scorer_opt {
-            let include_scorer_boxed =
-                into_box_scorer(include_scorer, &score_combiner_fn, num_docs);
-            Ok(SpecializedScorer::Other(Box::new(Exclude::new(
-                include_scorer_boxed,
-                exclude_scorer,
-            ))))
+            Ok(box_scorer(Exclude::new(include_scorer, exclude_scorer)))
         } else {
             Ok(include_scorer)
         }
@@ -418,8 +351,7 @@ fn remove_and_count_all_and_empty_scorers(
 }
 
 impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombiner> {
-    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
-        let num_docs = reader.num_docs();
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         if self.weights.is_empty() {
             Ok(Box::new(EmptyScorer))
         } else if self.weights.len() == 1 {
@@ -431,18 +363,12 @@ impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombin
             }
         } else if self.scoring_enabled {
             self.complex_scorer(reader, boost, &self.score_combiner_fn)
-                .map(|specialized_scorer| {
-                    into_box_scorer(specialized_scorer, &self.score_combiner_fn, num_docs)
-                })
         } else {
             self.complex_scorer(reader, boost, DoNothingCombiner::default)
-                .map(|specialized_scorer| {
-                    into_box_scorer(specialized_scorer, DoNothingCombiner::default, num_docs)
-                })
         }
     }
 
-    fn explain(&self, reader: &dyn SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         let mut scorer = self.scorer(reader, 1.0)?;
         if scorer.seek(doc) != doc {
             return Err(does_not_match(doc));
@@ -464,47 +390,22 @@ impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombin
 
     fn for_each(
         &self,
-        reader: &dyn SegmentReader,
+        reader: &SegmentReader,
         callback: &mut dyn FnMut(DocId, Score),
     ) -> crate::Result<()> {
-        let scorer = self.complex_scorer(reader, 1.0, &self.score_combiner_fn)?;
-        match scorer {
-            SpecializedScorer::TermUnion(term_scorers) => {
-                let mut union_scorer = BufferedUnionScorer::build(
-                    term_scorers,
-                    &self.score_combiner_fn,
-                    reader.num_docs(),
-                );
-                for_each_scorer(&mut union_scorer, callback);
-            }
-            SpecializedScorer::Other(mut scorer) => {
-                for_each_scorer(scorer.as_mut(), callback);
-            }
-        }
+        let mut scorer = self.complex_scorer(reader, 1.0, &self.score_combiner_fn)?;
+        for_each_scorer(scorer.as_mut(), callback);
         Ok(())
     }
 
     fn for_each_no_score(
         &self,
-        reader: &dyn SegmentReader,
+        reader: &SegmentReader,
         callback: &mut dyn FnMut(&[DocId]),
     ) -> crate::Result<()> {
-        let scorer = self.complex_scorer(reader, 1.0, || DoNothingCombiner)?;
+        let mut scorer = self.complex_scorer(reader, 1.0, || DoNothingCombiner)?;
         let mut buffer = [0u32; COLLECT_BLOCK_BUFFER_LEN];
-
-        match scorer {
-            SpecializedScorer::TermUnion(term_scorers) => {
-                let mut union_scorer = BufferedUnionScorer::build(
-                    term_scorers,
-                    &self.score_combiner_fn,
-                    reader.num_docs(),
-                );
-                for_each_docset_buffered(&mut union_scorer, &mut buffer, callback);
-            }
-            SpecializedScorer::Other(mut scorer) => {
-                for_each_docset_buffered(scorer.as_mut(), &mut buffer, callback);
-            }
-        }
+        for_each_docset_buffered(scorer.as_mut(), &mut buffer, callback);
         Ok(())
     }
 
@@ -521,18 +422,11 @@ impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombin
     fn for_each_pruning(
         &self,
         threshold: Score,
-        reader: &dyn SegmentReader,
+        reader: &SegmentReader,
         callback: &mut dyn FnMut(DocId, Score) -> Score,
     ) -> crate::Result<()> {
         let scorer = self.complex_scorer(reader, 1.0, &self.score_combiner_fn)?;
-        match scorer {
-            SpecializedScorer::TermUnion(term_scorers) => {
-                super::block_wand(term_scorers, threshold, callback);
-            }
-            SpecializedScorer::Other(mut scorer) => {
-                for_each_pruning_scorer(scorer.as_mut(), threshold, callback);
-            }
-        }
+        reader.codec.for_each_pruning(threshold, scorer, callback);
         Ok(())
     }
 }

src/query/boolean_query/mod.rs

@@ -1,8 +1,6 @@
-mod block_wand;
 mod boolean_query;
 mod boolean_weight;
 
-pub(crate) use self::block_wand::{block_wand, block_wand_single_scorer};
 pub use self::boolean_query::BooleanQuery;
 pub use self::boolean_weight::BooleanWeight;
 

src/query/boost_query.rs

@@ -1,6 +1,6 @@
 use std::fmt;
 
-use crate::docset::{SeekDangerResult, COLLECT_BLOCK_BUFFER_LEN};
+use crate::docset::COLLECT_BLOCK_BUFFER_LEN;
 use crate::fastfield::AliveBitSet;
 use crate::query::{EnableScoring, Explanation, Query, Scorer, Weight};
 use crate::{DocId, DocSet, Score, SegmentReader, Term};
@@ -67,11 +67,11 @@ impl BoostWeight {
 }
 
 impl Weight for BoostWeight {
-    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         self.weight.scorer(reader, boost * self.boost)
     }
 
-    fn explain(&self, reader: &dyn SegmentReader, doc: u32) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: u32) -> crate::Result<Explanation> {
         let underlying_explanation = self.weight.explain(reader, doc)?;
         let score = underlying_explanation.value() * self.boost;
         let mut explanation =
@@ -80,7 +80,7 @@ impl Weight for BoostWeight {
         Ok(explanation)
     }
 
-    fn count(&self, reader: &dyn SegmentReader) -> crate::Result<u32> {
+    fn count(&self, reader: &SegmentReader) -> crate::Result<u32> {
         self.weight.count(reader)
     }
 }
@@ -104,8 +104,8 @@ impl<S: Scorer> DocSet for BoostScorer<S> {
     fn seek(&mut self, target: DocId) -> DocId {
         self.underlying.seek(target)
     }
-    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
-        self.underlying.seek_danger(target)
+    fn seek_into_the_danger_zone(&mut self, target: DocId) -> bool {
+        self.underlying.seek_into_the_danger_zone(target)
     }
 
     fn fill_buffer(&mut self, buffer: &mut [DocId; COLLECT_BLOCK_BUFFER_LEN]) -> usize {

src/query/const_score_query.rs

@@ -1,7 +1,7 @@
 use std::fmt;
 
 use crate::docset::COLLECT_BLOCK_BUFFER_LEN;
-use crate::query::{EnableScoring, Explanation, Query, Scorer, Weight};
+use crate::query::{box_scorer, EnableScoring, Explanation, Query, Scorer, Weight};
 use crate::{DocId, DocSet, Score, SegmentReader, TantivyError, Term};
 
 /// `ConstScoreQuery` is a wrapper over a query to provide a constant score.
@@ -63,12 +63,15 @@ impl ConstWeight {
 }
 
 impl Weight for ConstWeight {
-    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         let inner_scorer = self.weight.scorer(reader, boost)?;
-        Ok(Box::new(ConstScorer::new(inner_scorer, boost * self.score)))
+        Ok(box_scorer(ConstScorer::new(
+            inner_scorer,
+            boost * self.score,
+        )))
     }
 
-    fn explain(&self, reader: &dyn SegmentReader, doc: u32) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: u32) -> crate::Result<Explanation> {
         let mut scorer = self.scorer(reader, 1.0)?;
         if scorer.seek(doc) != doc {
             return Err(TantivyError::InvalidArgument(format!(
@@ -81,7 +84,7 @@ impl Weight for ConstWeight {
         Ok(explanation)
     }
 
-    fn count(&self, reader: &dyn SegmentReader) -> crate::Result<u32> {
+    fn count(&self, reader: &SegmentReader) -> crate::Result<u32> {
         self.weight.count(reader)
     }
 }

src/query/disjunction.rs

@@ -1,7 +1,6 @@
 use std::cmp::Ordering;
 use std::collections::BinaryHeap;
 
-use crate::docset::SeekDangerResult;
 use crate::query::score_combiner::DoNothingCombiner;
 use crate::query::{ScoreCombiner, Scorer};
 use crate::{DocId, DocSet, Score, TERMINATED};
@@ -68,12 +67,10 @@ impl<T: Scorer> DocSet for ScorerWrapper<T> {
         self.current_doc = doc_id;
         doc_id
     }
-    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
-        let result = self.scorer.seek_danger(target);
-        if result == SeekDangerResult::Found {
-            self.current_doc = target;
-        }
-        result
+    fn seek_into_the_danger_zone(&mut self, target: DocId) -> bool {
+        let found = self.scorer.seek_into_the_danger_zone(target);
+        self.current_doc = self.scorer.doc();
+        found
     }
 
     fn doc(&self) -> DocId {

src/query/empty_query.rs

@@ -2,7 +2,7 @@ use super::Scorer;
 use crate::docset::TERMINATED;
 use crate::index::SegmentReader;
 use crate::query::explanation::does_not_match;
-use crate::query::{EnableScoring, Explanation, Query, Weight};
+use crate::query::{box_scorer, EnableScoring, Explanation, Query, Weight};
 use crate::{DocId, DocSet, Score, Searcher};
 
 /// `EmptyQuery` is a dummy `Query` in which no document matches.
@@ -26,11 +26,11 @@ impl Query for EmptyQuery {
 /// It is useful for tests and handling edge cases.
 pub struct EmptyWeight;
 impl Weight for EmptyWeight {
-    fn scorer(&self, _reader: &dyn SegmentReader, _boost: Score) -> crate::Result<Box<dyn Scorer>> {
-        Ok(Box::new(EmptyScorer))
+    fn scorer(&self, _reader: &SegmentReader, _boost: Score) -> crate::Result<Box<dyn Scorer>> {
+        Ok(box_scorer(EmptyScorer))
     }
 
-    fn explain(&self, _reader: &dyn SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, _reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         Err(does_not_match(doc))
     }
 }

src/query/exist_query.rs

@@ -3,7 +3,7 @@ use core::fmt::Debug;
 use columnar::{ColumnIndex, DynamicColumn};
 use common::BitSet;
 
-use super::{ConstScorer, EmptyScorer};
+use super::{box_scorer, ConstScorer, EmptyScorer};
 use crate::docset::{DocSet, TERMINATED};
 use crate::index::SegmentReader;
 use crate::query::all_query::AllScorer;
@@ -98,7 +98,7 @@ pub struct ExistsWeight {
 }
 
 impl Weight for ExistsWeight {
-    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         let fast_field_reader = reader.fast_fields();
         let mut column_handles = fast_field_reader.dynamic_column_handles(&self.field_name)?;
         if self.field_type == Type::Json && self.json_subpaths {
@@ -117,7 +117,7 @@ impl Weight for ExistsWeight {
             }
         }
         if non_empty_columns.is_empty() {
-            return Ok(Box::new(EmptyScorer));
+            return Ok(box_scorer(EmptyScorer));
         }
 
         // If any column is full, all docs match.
@@ -128,9 +128,9 @@ impl Weight for ExistsWeight {
         {
             let all_scorer = AllScorer::new(max_doc);
             if boost != 1.0f32 {
-                return Ok(Box::new(BoostScorer::new(all_scorer, boost)));
+                return Ok(box_scorer(BoostScorer::new(all_scorer, boost)));
             } else {
-                return Ok(Box::new(all_scorer));
+                return Ok(box_scorer(all_scorer));
             }
         }
 
@@ -138,7 +138,7 @@ impl Weight for ExistsWeight {
         // NOTE: A lower number may be better for very sparse columns
         if non_empty_columns.len() < 4 {
             let docset = ExistsDocSet::new(non_empty_columns, reader.max_doc());
-            return Ok(Box::new(ConstScorer::new(docset, boost)));
+            return Ok(box_scorer(ConstScorer::new(docset, boost)));
         }
 
         // If we have many dynamic columns, precompute a bitset of matching docs
@@ -162,10 +162,10 @@ impl Weight for ExistsWeight {
             }
         }
         let docset = BitSetDocSet::from(doc_bitset);
-        Ok(Box::new(ConstScorer::new(docset, boost)))
+        Ok(box_scorer(ConstScorer::new(docset, boost)))
     }
 
-    fn explain(&self, reader: &dyn SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         let mut scorer = self.scorer(reader, 1.0)?;
         if scorer.seek(doc) != doc {
             return Err(does_not_match(doc));

src/query/intersection.rs

@@ -1,7 +1,7 @@
 use super::size_hint::estimate_intersection;
-use crate::docset::{DocSet, SeekDangerResult, TERMINATED};
+use crate::docset::{DocSet, TERMINATED};
 use crate::query::term_query::TermScorer;
-use crate::query::{EmptyScorer, Scorer};
+use crate::query::{box_scorer, EmptyScorer, Scorer};
 use crate::{DocId, Score};
 
 /// Returns the intersection scorer.
@@ -20,7 +20,7 @@ pub fn intersect_scorers(
     num_docs_segment: u32,
 ) -> Box<dyn Scorer> {
     if scorers.is_empty() {
-        return Box::new(EmptyScorer);
+        return box_scorer(EmptyScorer);
     }
     if scorers.len() == 1 {
         return scorers.pop().unwrap();
@@ -29,7 +29,7 @@ pub fn intersect_scorers(
     scorers.sort_by_key(|scorer| scorer.cost());
     let doc = go_to_first_doc(&mut scorers[..]);
     if doc == TERMINATED {
-        return Box::new(EmptyScorer);
+        return box_scorer(EmptyScorer);
     }
     // We know that we have at least 2 elements.
     let left = scorers.remove(0);
@@ -38,14 +38,14 @@ pub fn intersect_scorers(
         .iter()
         .all(|&scorer| scorer.is::<TermScorer>());
     if all_term_scorers {
-        return Box::new(Intersection {
+        return box_scorer(Intersection {
             left: *(left.downcast::<TermScorer>().map_err(|_| ()).unwrap()),
             right: *(right.downcast::<TermScorer>().map_err(|_| ()).unwrap()),
             others: scorers,
             num_docs: num_docs_segment,
         });
     }
-    Box::new(Intersection {
+    box_scorer(Intersection {
         left,
         right,
         others: scorers,
@@ -108,63 +108,46 @@ impl<TDocSet: DocSet, TOtherDocSet: DocSet> DocSet for Intersection<TDocSet, TOt
     #[inline]
     fn advance(&mut self) -> DocId {
         let (left, right) = (&mut self.left, &mut self.right);
+        let mut candidate = left.advance();
+        if candidate == TERMINATED {
+            return TERMINATED;
+        }
 
-        // Invariant:
-        // - candidate is always <= to the next document in the intersection.
-        // - candidate strictly increases at every occurence of the loop.
-        let mut candidate = 0;
+        loop {
+            // In the first part we look for a document in the intersection
+            // of the two rarest `DocSet` in the intersection.
 
-        // Termination: candidate strictly increases.
-        'outer: while candidate < TERMINATED {
-            // As we enter the loop, we should always have candidate < next_doc.
-
-            // This step always increases candidate.
-            //
-            // TODO: Think about which value would make sense here
-            // It depends on the DocSet implementation, when a seek would outweigh an advance.
-            candidate = if candidate > left.doc().wrapping_add(100) {
-                left.seek(candidate)
-            } else {
-                left.advance()
-            };
-
-            // Left is positionned on `candidate`.
-            debug_assert_eq!(left.doc(), candidate);
-
-            if let SeekDangerResult::SeekLowerBound(seek_lower_bound) = right.seek_danger(candidate)
-            {
-                // The max is technically useless but it makes the invariant
-                // easier to proofread.
-                debug_assert!(seek_lower_bound >= candidate);
-                candidate = seek_lower_bound;
-                continue;
-            }
-
-            // Left and right are positionned on `candidate`.
-            debug_assert_eq!(right.doc(), candidate);
-
-            for other in &mut self.others {
-                if let SeekDangerResult::SeekLowerBound(seek_lower_bound) =
-                    other.seek_danger(candidate)
-                {
-                    // One of the scorer does not match, let's restart at the top of the loop.
-                    debug_assert!(seek_lower_bound >= candidate);
-                    candidate = seek_lower_bound;
-                    continue 'outer;
+            loop {
+                if right.seek_into_the_danger_zone(candidate) {
+                    break;
+                }
+                let right_doc = right.doc();
+                // TODO: Think about which value would make sense here
+                // It depends on the DocSet implementation, when a seek would outweigh an advance.
+                if right_doc > candidate.wrapping_add(100) {
+                    candidate = left.seek(right_doc);
+                } else {
+                    candidate = left.advance();
+                }
+                if candidate == TERMINATED {
+                    return TERMINATED;
                 }
             }
 
-            // At this point all scorers are in a valid state, aligned on the next document in the
-            // intersection.
-            debug_assert!(self.others.iter().all(|docset| docset.doc() == candidate));
-            return candidate;
+            debug_assert_eq!(left.doc(), right.doc());
+            // test the remaining scorers
+            if self
+                .others
+                .iter_mut()
+                .all(|docset| docset.seek_into_the_danger_zone(candidate))
+            {
+                debug_assert_eq!(candidate, self.left.doc());
+                debug_assert_eq!(candidate, self.right.doc());
+                debug_assert!(self.others.iter().all(|docset| docset.doc() == candidate));
+                return candidate;
+            }
+            candidate = left.advance();
         }
-
-        // We make sure our docset is in a valid state.
-        // In particular, we want .doc() to return TERMINATED.
-        left.seek(TERMINATED);
-
-        TERMINATED
     }
 
     fn seek(&mut self, target: DocId) -> DocId {
@@ -183,19 +166,13 @@ impl<TDocSet: DocSet, TOtherDocSet: DocSet> DocSet for Intersection<TDocSet, TOt
     ///
     /// Some implementations may choose to advance past the target if beneficial for performance.
     /// The return value is `true` if the target is in the docset, and `false` otherwise.
-    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
-        if let SeekDangerResult::SeekLowerBound(new_target) = self.left.seek_danger(target) {
-            return SeekDangerResult::SeekLowerBound(new_target);
-        }
-        if let SeekDangerResult::SeekLowerBound(new_target) = self.right.seek_danger(target) {
-            return SeekDangerResult::SeekLowerBound(new_target);
-        }
-        for docset in &mut self.others {
-            if let SeekDangerResult::SeekLowerBound(new_target) = docset.seek_danger(target) {
-                return SeekDangerResult::SeekLowerBound(new_target);
-            }
-        }
-        SeekDangerResult::Found
+    fn seek_into_the_danger_zone(&mut self, target: DocId) -> bool {
+        self.left.seek_into_the_danger_zone(target)
+            && self.right.seek_into_the_danger_zone(target)
+            && self
+                .others
+                .iter_mut()
+                .all(|docset| docset.seek_into_the_danger_zone(target))
     }
 
     #[inline]
@@ -327,58 +304,6 @@ mod tests {
         assert_eq!(intersection.doc(), TERMINATED);
     }
 
-    #[test]
-    fn test_intersection_abc() {
-        let a = VecDocSet::from(vec![2, 3, 6]);
-        let b = VecDocSet::from(vec![1, 3, 5]);
-        let c = VecDocSet::from(vec![1, 3, 5]);
-        let mut intersection = Intersection::new(vec![c, b, a], 10);
-        let mut docs = Vec::new();
-        use crate::DocSet;
-        while intersection.doc() != TERMINATED {
-            docs.push(intersection.doc());
-            intersection.advance();
-        }
-        assert_eq!(&docs, &[3]);
-    }
-
-    #[test]
-    fn test_intersection_termination() {
-        use crate::query::score_combiner::DoNothingCombiner;
-        use crate::query::{BufferedUnionScorer, ConstScorer, VecDocSet};
-
-        let a1 = ConstScorer::new(VecDocSet::from(vec![0u32, 10000]), 1.0);
-        let a2 = ConstScorer::new(VecDocSet::from(vec![0u32, 10000]), 1.0);
-
-        let mut b_scorers = vec![];
-        for _ in 0..2 {
-            // Union matches 0 and 10000.
-            b_scorers.push(ConstScorer::new(VecDocSet::from(vec![0, 10000]), 1.0));
-        }
-        // That's the union of two scores matching 0, and 10_000.
-        let union = BufferedUnionScorer::build(b_scorers, DoNothingCombiner::default, 30000);
-
-        // Mismatching scorer: matches 0 and 20000. We then append more docs at the end to ensure it
-        // is last.
-        let mut m_docs = vec![0, 20000];
-        for i in 30000..30100 {
-            m_docs.push(i);
-        }
-        let m = ConstScorer::new(VecDocSet::from(m_docs), 1.0);
-
-        // Costs: A1=2, A2=2, Union=4, M=102.
-        // Sorted: A1, A2, Union, M.
-        // Left=A1, Right=A2, Others=[Union, M].
-        let mut intersection = crate::query::intersect_scorers(
-            vec![Box::new(a1), Box::new(a2), Box::new(union), Box::new(m)],
-            40000,
-        );
-
-        while intersection.doc() != TERMINATED {
-            intersection.advance();
-        }
-    }
-
     // Strategy to generate sorted and deduplicated vectors of u32 document IDs
     fn sorted_deduped_vec(max_val: u32, max_size: usize) -> impl Strategy<Value = Vec<u32>> {
         prop::collection::vec(0..max_val, 0..max_size).prop_map(|mut vec| {
@@ -410,5 +335,6 @@ mod tests {
             }
             assert_eq!(intersection.doc(), TERMINATED);
         }
+
     }
 }

src/query/mod.rs

@@ -24,7 +24,7 @@ mod reqopt_scorer;
 mod scorer;
 mod set_query;
 mod size_hint;
-mod term_query;
+pub(crate) mod term_query;
 mod union;
 mod weight;
 
@@ -54,13 +54,14 @@ pub use self::more_like_this::{MoreLikeThisQuery, MoreLikeThisQueryBuilder};
 pub use self::phrase_prefix_query::PhrasePrefixQuery;
 pub use self::phrase_query::regex_phrase_query::{wildcard_query_to_regex_str, RegexPhraseQuery};
 pub use self::phrase_query::PhraseQuery;
+pub(crate) use self::phrase_query::PhraseScorer;
 pub use self::query::{EnableScoring, Query, QueryClone};
 pub use self::query_parser::{QueryParser, QueryParserError};
 pub use self::range_query::*;
 pub use self::regex_query::RegexQuery;
 pub use self::reqopt_scorer::RequiredOptionalScorer;
 pub use self::score_combiner::{DisjunctionMaxCombiner, ScoreCombiner, SumCombiner};
-pub use self::scorer::Scorer;
+pub use self::scorer::{box_scorer, Scorer};
 pub use self::set_query::TermSetQuery;
 pub use self::term_query::TermQuery;
 pub use self::union::BufferedUnionScorer;

src/query/phrase_prefix_query/phrase_prefix_scorer.rs

@@ -1,8 +1,8 @@
-use crate::docset::{DocSet, SeekDangerResult, TERMINATED};
+use crate::docset::{DocSet, TERMINATED};
 use crate::fieldnorm::FieldNormReader;
 use crate::postings::Postings;
 use crate::query::bm25::Bm25Weight;
-use crate::query::phrase_query::{intersection_count, PhraseScorer};
+use crate::query::phrase_query::{intersection_exists, PhraseScorer};
 use crate::query::Scorer;
 use crate::{DocId, Score};
 
@@ -100,7 +100,6 @@ pub struct PhrasePrefixScorer<TPostings: Postings> {
     phrase_scorer: PhraseKind<TPostings>,
     suffixes: Vec<TPostings>,
     suffix_offset: u32,
-    phrase_count: u32,
     suffix_position_buffer: Vec<u32>,
 }
 
@@ -144,7 +143,6 @@ impl<TPostings: Postings> PhrasePrefixScorer<TPostings> {
             phrase_scorer,
             suffixes,
             suffix_offset: (max_offset - suffix_pos) as u32,
-            phrase_count: 0,
             suffix_position_buffer: Vec::with_capacity(100),
         };
         if phrase_prefix_scorer.doc() != TERMINATED && !phrase_prefix_scorer.matches_prefix() {
@@ -153,12 +151,7 @@ impl<TPostings: Postings> PhrasePrefixScorer<TPostings> {
         phrase_prefix_scorer
     }
 
-    pub fn phrase_count(&self) -> u32 {
-        self.phrase_count
-    }
-
     fn matches_prefix(&mut self) -> bool {
-        let mut count = 0;
         let current_doc = self.doc();
         let pos_matching = self.phrase_scorer.get_intersection();
         for suffix in &mut self.suffixes {
@@ -168,11 +161,12 @@ impl<TPostings: Postings> PhrasePrefixScorer<TPostings> {
             let doc = suffix.seek(current_doc);
             if doc == current_doc {
                 suffix.positions_with_offset(self.suffix_offset, &mut self.suffix_position_buffer);
-                count += intersection_count(pos_matching, &self.suffix_position_buffer);
+                if intersection_exists(pos_matching, &self.suffix_position_buffer) {
+                    return true;
+                }
             }
         }
-        self.phrase_count = count as u32;
-        count != 0
+        false
     }
 }
 
@@ -194,16 +188,11 @@ impl<TPostings: Postings> DocSet for PhrasePrefixScorer<TPostings> {
         self.advance()
     }
 
-    fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
-        let seek_res = self.phrase_scorer.seek_danger(target);
-        if seek_res != SeekDangerResult::Found {
-            return seek_res;
-        }
-        // The intersection matched. Now let's see if we match the prefix.
-        if self.matches_prefix() {
-            SeekDangerResult::Found
+    fn seek_into_the_danger_zone(&mut self, target: DocId) -> bool {
+        if self.phrase_scorer.seek_into_the_danger_zone(target) {
+            self.matches_prefix()
         } else {
-            SeekDangerResult::SeekLowerBound(target + 1)
+            false
         }
     }
 

src/query/phrase_prefix_query/phrase_prefix_weight.rs

@@ -1,12 +1,11 @@
 use super::{prefix_end, PhrasePrefixScorer};
 use crate::fieldnorm::FieldNormReader;
 use crate::index::SegmentReader;
-use crate::postings::SegmentPostings;
+use crate::postings::Postings;
 use crate::query::bm25::Bm25Weight;
-use crate::query::explanation::does_not_match;
-use crate::query::{EmptyScorer, Explanation, Scorer, Weight};
+use crate::query::{box_scorer, EmptyScorer, Explanation, Scorer, Weight};
 use crate::schema::{IndexRecordOption, Term};
-use crate::{DocId, DocSet, Score};
+use crate::{DocId, Score};
 
 pub struct PhrasePrefixWeight {
     phrase_terms: Vec<(usize, Term)>,
@@ -32,7 +31,7 @@ impl PhrasePrefixWeight {
         }
     }
 
-    fn fieldnorm_reader(&self, reader: &dyn SegmentReader) -> crate::Result<FieldNormReader> {
+    fn fieldnorm_reader(&self, reader: &SegmentReader) -> crate::Result<FieldNormReader> {
         let field = self.phrase_terms[0].1.field();
         if self.similarity_weight_opt.is_some() {
             if let Some(fieldnorm_reader) = reader.fieldnorms_readers().get_field(field)? {
@@ -44,15 +43,15 @@ impl PhrasePrefixWeight {
 
     pub(crate) fn phrase_scorer(
         &self,
-        reader: &dyn SegmentReader,
+        reader: &SegmentReader,
         boost: Score,
-    ) -> crate::Result<Option<PhrasePrefixScorer<SegmentPostings>>> {
+    ) -> crate::Result<Option<Box<dyn Scorer>>> {
         let similarity_weight_opt = self
             .similarity_weight_opt
             .as_ref()
             .map(|similarity_weight| similarity_weight.boost_by(boost));
         let fieldnorm_reader = self.fieldnorm_reader(reader)?;
-        let mut term_postings_list = Vec::new();
+        let mut term_postings_list: Vec<(usize, Box<dyn Postings>)> = Vec::new();
         for &(offset, ref term) in &self.phrase_terms {
             if let Some(postings) = reader
                 .inverted_index(term.field())?
@@ -103,42 +102,44 @@ impl PhrasePrefixWeight {
             }
         }
 
-        Ok(Some(PhrasePrefixScorer::new(
+        // TODO make this specialized.
+        Ok(Some(box_scorer(PhrasePrefixScorer::new(
             term_postings_list,
             similarity_weight_opt,
             fieldnorm_reader,
             suffixes,
             self.prefix.0,
-        )))
+        ))))
     }
 }
 
 impl Weight for PhrasePrefixWeight {
-    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         if let Some(scorer) = self.phrase_scorer(reader, boost)? {
-            Ok(Box::new(scorer))
+            Ok(scorer)
         } else {
-            Ok(Box::new(EmptyScorer))
+            Ok(box_scorer(EmptyScorer))
         }
     }
 
-    fn explain(&self, reader: &dyn SegmentReader, doc: DocId) -> crate::Result<Explanation> {
-        let scorer_opt = self.phrase_scorer(reader, 1.0)?;
-        if scorer_opt.is_none() {
-            return Err(does_not_match(doc));
-        }
-        let mut scorer = scorer_opt.unwrap();
-        if scorer.seek(doc) != doc {
-            return Err(does_not_match(doc));
-        }
-        let fieldnorm_reader = self.fieldnorm_reader(reader)?;
-        let fieldnorm_id = fieldnorm_reader.fieldnorm_id(doc);
-        let phrase_count = scorer.phrase_count();
-        let mut explanation = Explanation::new("Phrase Prefix Scorer", scorer.score());
-        if let Some(similarity_weight) = self.similarity_weight_opt.as_ref() {
-            explanation.add_detail(similarity_weight.explain(fieldnorm_id, phrase_count));
-        }
-        Ok(explanation)
+    fn explain(&self, _reader: &SegmentReader, _doc: DocId) -> crate::Result<Explanation> {
+        todo!();
+        // let scorer_opt = self.phrase_scorer(reader, 1.0)?;
+        // if scorer_opt.is_none() {
+        //     return Err(does_not_match(doc));
+        // }
+        // let mut scorer = scorer_opt.unwrap();
+        // if scorer.seek(doc) != doc {
+        //     return Err(does_not_match(doc));
+        // }
+        // let fieldnorm_reader = self.fieldnorm_reader(reader)?;
+        // let fieldnorm_id = fieldnorm_reader.fieldnorm_id(doc);
+        // let phrase_count = scorer.phrase_count();
+        // let mut explanation = Explanation::new("Phrase Prefix Scorer", scorer.score());
+        // if let Some(similarity_weight) = self.similarity_weight_opt.as_ref() {
+        //     explanation.add_detail(similarity_weight.explain(fieldnorm_id, phrase_count));
+        // }
+        // Ok(explanation)
     }
 }
 
@@ -146,6 +147,8 @@ impl Weight for PhrasePrefixWeight {
 mod tests {
     use crate::docset::TERMINATED;
     use crate::index::Index;
+    use crate::postings::Postings;
+    use crate::query::phrase_prefix_query::PhrasePrefixScorer;
     use crate::query::{EnableScoring, PhrasePrefixQuery, Query};
     use crate::schema::{Schema, TEXT};
     use crate::{DocSet, IndexWriter, Term};
@@ -186,14 +189,14 @@ mod tests {
             .phrase_prefix_query_weight(enable_scoring)
             .unwrap()
             .unwrap();
-        let mut phrase_scorer = phrase_weight
+        let mut phrase_scorer_boxed = phrase_weight
             .phrase_scorer(searcher.segment_reader(0u32), 1.0)?
             .unwrap();
+        let phrase_scorer: &mut PhrasePrefixScorer<Box<dyn Postings>> =
+            phrase_scorer_boxed.as_any_mut().downcast_mut().unwrap();
         assert_eq!(phrase_scorer.doc(), 1);
-        assert_eq!(phrase_scorer.phrase_count(), 2);
         assert_eq!(phrase_scorer.advance(), 2);
         assert_eq!(phrase_scorer.doc(), 2);
-        assert_eq!(phrase_scorer.phrase_count(), 1);
         assert_eq!(phrase_scorer.advance(), TERMINATED);
         Ok(())
     }
@@ -213,14 +216,15 @@ mod tests {
             .phrase_prefix_query_weight(enable_scoring)
             .unwrap()
             .unwrap();
-        let mut phrase_scorer = phrase_weight
+        let mut phrase_scorer_boxed = phrase_weight
             .phrase_scorer(searcher.segment_reader(0u32), 1.0)?
             .unwrap();
+        let phrase_scorer = phrase_scorer_boxed
+            .downcast_mut::<PhrasePrefixScorer<Box<dyn Postings>>>()
+            .unwrap();
         assert_eq!(phrase_scorer.doc(), 1);
-        assert_eq!(phrase_scorer.phrase_count(), 2);
         assert_eq!(phrase_scorer.advance(), 2);
         assert_eq!(phrase_scorer.doc(), 2);
-        assert_eq!(phrase_scorer.phrase_count(), 1);
         assert_eq!(phrase_scorer.advance(), TERMINATED);
         Ok(())
     }