First stab at tantivy's codec

Convert SegmentReader, InvertedIndexReader and postinglists to traits.
Add special functions to pushdown certain performance methods to keep
them strictly typed.

We rely on a ObjectSafeCodec contraption to avoid the proliferation of generics.
That object's point is to make sure we can build TermScorer with a concrete
codec specific type before reboxing it. (same thing for PhraseScorer).

fix performance regression: fix incorrect scorer cast for buffered union
bock wand

benches/str_search_and_get.rs

@@ -45,7 +45,7 @@ fn build_shared_indices(num_docs: usize, distribution: &str) -> BenchIndex {
         match distribution {
             "dense_random" => {
                 for _doc_id in 0..num_docs {
-                    let suffix = rng.gen_range(0u64..1000u64);
+                    let suffix = rng.random_range(0u64..1000u64);
                     let str_val = format!("str_{:03}", suffix);
 
                     writer
@@ -71,7 +71,7 @@ fn build_shared_indices(num_docs: usize, distribution: &str) -> BenchIndex {
             }
             "sparse_random" => {
                 for _doc_id in 0..num_docs {
-                    let suffix = rng.gen_range(0u64..1000000u64);
+                    let suffix = rng.random_range(0u64..1000000u64);
                     let str_val = format!("str_{:07}", suffix);
 
                     writer

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`.
@@ -299,6 +297,9 @@ impl BitSet {
             .map(|delta_bucket| bucket + delta_bucket as u32)
     }
 
+    /// Returns the maximum number of elements in the bitset.
+    ///
+    /// Warning: The largest element the bitset can contain is `max_value - 1`.
     #[inline]
     pub fn max_value(&self) -> u32 {
         self.max_value

common/src/writer.rs

@@ -62,7 +62,9 @@ impl<W: TerminatingWrite> TerminatingWrite for CountingWriter<W> {
 pub struct AntiCallToken(());
 
 /// Trait used to indicate when no more write need to be done on a writer
-pub trait TerminatingWrite: Write + Send + Sync {
+///
+/// Thread-safety is enforced at the call sites that require it.
+pub trait TerminatingWrite: Write {
     /// Indicate that the writer will no longer be used. Internally call terminate_ref.
     fn terminate(mut self) -> io::Result<()>
     where Self: Sized {

examples/custom_collector.rs

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

examples/faceted_search_with_tweaked_score.rs

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

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

query-grammar/src/query_grammar.rs

@@ -704,7 +704,11 @@ fn regex(inp: &str) -> IResult<&str, UserInputLeaf> {
                 many1(alt((preceded(char('\\'), char('/')), none_of("/")))),
                 char('/'),
             ),
-            peek(alt((multispace1, eof))),
+            peek(alt((
+                value((), multispace1),
+                value((), char(')')),
+                value((), eof),
+            ))),
         ),
         |elements| UserInputLeaf::Regex {
             field: None,
@@ -721,8 +725,12 @@ fn regex_infallible(inp: &str) -> JResult<&str, UserInputLeaf> {
             opt_i_err(char('/'), "missing delimiter /"),
         ),
         opt_i_err(
-            peek(alt((multispace1, eof))),
-            "expected whitespace or end of input",
+            peek(alt((
+                value((), multispace1),
+                value((), char(')')),
+                value((), eof),
+            ))),
+            "expected whitespace, closing parenthesis, or end of input",
         ),
     )(inp)
     {
@@ -1707,6 +1715,10 @@ mod test {
         test_parse_query_to_ast_helper("foo:(A OR B)", "(?\"foo\":A ?\"foo\":B)");
         test_parse_query_to_ast_helper("foo:(A* OR B*)", "(?\"foo\":A* ?\"foo\":B*)");
         test_parse_query_to_ast_helper("foo:(*A OR *B)", "(?\"foo\":*A ?\"foo\":*B)");
+
+        // Regexes between parentheses
+        test_parse_query_to_ast_helper("foo:(/A.*/)", "\"foo\":/A.*/");
+        test_parse_query_to_ast_helper("foo:(/A.*/ OR /B.*/)", "(?\"foo\":/A.*/ ?\"foo\":/B.*/)");
     }
 
     #[test]

query-grammar/src/user_input_ast.rs

@@ -66,6 +66,7 @@ impl UserInputLeaf {
             }
             UserInputLeaf::Range { field, .. } if field.is_none() => *field = Some(default_field),
             UserInputLeaf::Set { field, .. } if field.is_none() => *field = Some(default_field),
+            UserInputLeaf::Regex { field, .. } if field.is_none() => *field = Some(default_field),
             _ => (), // field was already set, do nothing
         }
     }

src/aggregation/accessor_helpers.rs

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

src/aggregation/agg_data.rs

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

src/aggregation/agg_result.rs

@@ -10,8 +10,7 @@ use serde::{Deserialize, Serialize};
 
 use super::bucket::GetDocCount;
 use super::metric::{
-    AverageMetricResult, CardinalityMetricResult, ExtendedStats, PercentilesMetricResult,
-    SingleMetricResult, Stats, TopHitsMetricResult,
+    ExtendedStats, PercentilesMetricResult, SingleMetricResult, Stats, TopHitsMetricResult,
 };
 use super::{AggregationError, Key};
 use crate::TantivyError;
@@ -82,8 +81,8 @@ impl AggregationResult {
 #[serde(untagged)]
 /// MetricResult
 pub enum MetricResult {
-    /// Average metric result with sum and count for multi-step merging.
-    Average(AverageMetricResult),
+    /// Average metric result.
+    Average(SingleMetricResult),
     /// Count metric result.
     Count(SingleMetricResult),
     /// Max metric result.
@@ -100,8 +99,8 @@ pub enum MetricResult {
     Percentiles(PercentilesMetricResult),
     /// Top hits metric result
     TopHits(TopHitsMetricResult),
-    /// Cardinality metric result with HLL sketch for multi-step merging.
-    Cardinality(CardinalityMetricResult),
+    /// Cardinality metric result
+    Cardinality(SingleMetricResult),
 }
 
 impl MetricResult {
@@ -120,7 +119,7 @@ impl MetricResult {
             MetricResult::TopHits(_) => Err(TantivyError::AggregationError(
                 AggregationError::InvalidRequest("top_hits can't be used to order".to_string()),
             )),
-            MetricResult::Cardinality(card) => Ok(card.value), // CardinalityMetricResult.value
+            MetricResult::Cardinality(card) => Ok(card.value),
         }
     }
 }

src/aggregation/agg_tests.rs

@@ -1359,10 +1359,10 @@ fn test_aggregation_on_json_object_mixed_types() {
         &serde_json::json!({
           "rangeagg": {
             "buckets": [
-              { "average_in_range": { "value": -20.5, "sum": -20.5, "count": 1 }, "doc_count": 1, "key": "*-3", "to": 3.0 },
-              { "average_in_range": { "value": 10.0, "sum": 10.0, "count": 1 }, "doc_count": 1, "from": 3.0, "key": "3-19", "to": 19.0 },
-              { "average_in_range": { "value": null, "sum": 0.0, "count": 0 }, "doc_count": 0, "from": 19.0, "key": "19-20", "to": 20.0 },
-              { "average_in_range": { "value": null, "sum": 0.0, "count": 0 }, "doc_count": 0, "from": 20.0, "key": "20-*" }
+              { "average_in_range": { "value": -20.5 }, "doc_count": 1, "key": "*-3", "to": 3.0 },
+              { "average_in_range": { "value": 10.0 }, "doc_count": 1, "from": 3.0, "key": "3-19", "to": 19.0 },
+              { "average_in_range": { "value": null }, "doc_count": 0, "from": 19.0, "key": "19-20", "to": 20.0 },
+              { "average_in_range": { "value": null }, "doc_count": 0, "from": 20.0, "key": "20-*" }
             ]
           },
           "termagg": {

src/aggregation/bucket/filter.rs

@@ -1,4 +1,5 @@
 use std::fmt::Debug;
+use std::sync::Arc;
 
 use common::BitSet;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
@@ -402,7 +403,7 @@ pub struct FilterAggReqData {
     /// The filter aggregation
     pub req: FilterAggregation,
     /// The segment reader
-    pub segment_reader: SegmentReader,
+    pub segment_reader: Arc<dyn SegmentReader>,
     /// Document evaluator for the filter query (precomputed BitSet)
     /// This is built once when the request data is created
     pub evaluator: DocumentQueryEvaluator,
@@ -416,7 +417,7 @@ impl FilterAggReqData {
     pub(crate) fn get_memory_consumption(&self) -> usize {
         // Estimate: name + segment reader reference + bitset + buffer capacity
         self.name.len()
-        + std::mem::size_of::<SegmentReader>()
+        + std::mem::size_of::<Arc<dyn 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>()
@@ -438,7 +439,7 @@ impl DocumentQueryEvaluator {
     pub(crate) fn new(
         query: Box<dyn Query>,
         schema: Schema,
-        segment_reader: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self> {
         let max_doc = segment_reader.max_doc();
 
@@ -838,7 +839,7 @@ mod tests {
         let expected = json!({
             "electronics": {
                 "doc_count": 2,
-                "avg_price": { "value": 899.0, "sum": 1798.0, "count": 2 }  // (999 + 799) / 2
+                "avg_price": { "value": 899.0 }  // (999 + 799) / 2
             }
         });
 
@@ -868,7 +869,7 @@ mod tests {
         let expected = json!({
             "furniture": {
                 "doc_count": 0,
-                "avg_price": { "value": null, "sum": 0.0, "count": 0 }
+                "avg_price": { "value": null }
             }
         });
 
@@ -904,7 +905,7 @@ mod tests {
         let expected = json!({
             "electronics": {
                 "doc_count": 2,
-                "avg_price": { "value": 899.0, "sum": 1798.0, "count": 2 }
+                "avg_price": { "value": 899.0 }
             },
             "in_stock": {
                 "doc_count": 3,  // apple, samsung, penguin
@@ -1000,7 +1001,7 @@ mod tests {
         let expected = json!({
             "premium_electronics": {
                 "doc_count": 1,  // Only apple (999) is >= 800 in tantivy's range semantics
-                "avg_rating": { "value": 4.5, "sum": 4.5, "count": 1 }
+                "avg_rating": { "value": 4.5 }
             }
         });
 
@@ -1032,7 +1033,7 @@ mod tests {
         let expected = json!({
             "in_stock": {
                 "doc_count": 3,  // apple, samsung, penguin
-                "avg_price": { "value": 607.67, "sum": 1823.0, "count": 3 }  // (999 + 799 + 25) / 3 ≈ 607.67
+                "avg_price": { "value": 607.67 }  // (999 + 799 + 25) / 3 ≈ 607.67
             },
             "out_of_stock": {
                 "doc_count": 1,  // nike
@@ -1183,7 +1184,7 @@ mod tests {
                 "doc_count": 4,
                 "electronics_branch": {
                     "doc_count": 2,
-                    "avg_price": { "value": 899.0, "sum": 1798.0, "count": 2 }
+                    "avg_price": { "value": 899.0 }
                 },
                 "in_stock_branch": {
                     "doc_count": 3,
@@ -1259,7 +1260,7 @@ mod tests {
                     "doc_count": 2,  // apple (999), samsung (799)
                     "electronics": {
                         "doc_count": 2,  // both are electronics
-                        "avg_rating": { "value": 4.35, "sum": 8.7, "count": 2 }  // (4.5 + 4.2) / 2
+                        "avg_rating": { "value": 4.35 }  // (4.5 + 4.2) / 2
                     },
                     "in_stock": {
                         "doc_count": 2,  // both are in stock
@@ -1321,12 +1322,12 @@ mod tests {
                         {
                             "key": "samsung",
                             "doc_count": 1,
-                            "avg_price": { "value": 799.0, "sum": 799.0, "count": 1 }
+                            "avg_price": { "value": 799.0 }
                         },
                         {
                             "key": "apple",
                             "doc_count": 1,
-                            "avg_price": { "value": 999.0, "sum": 999.0, "count": 1 }
+                            "avg_price": { "value": 999.0 }
                         }
                     ],
                     "sum_other_doc_count": 0,
@@ -1370,7 +1371,7 @@ mod tests {
                     "sum": 1798.0,
                     "avg": 899.0
                 },
-                "rating_avg": { "value": 4.35, "sum": 8.7, "count": 2 },
+                "rating_avg": { "value": 4.35 },
                 "count": { "value": 2.0 }
             }
         });
@@ -1411,7 +1412,7 @@ mod tests {
         let expected = json!({
             "electronics": {
                 "doc_count": 0,
-                "avg_price": { "value": null, "sum": 0.0, "count": 0 }
+                "avg_price": { "value": null }
             }
         });
 
@@ -1698,15 +1699,13 @@ mod tests {
         let filter_expected = json!({
             "electronics": {
                 "doc_count": 2,
-                "avg_price": { "value": 899.0, "sum": 1798.0, "count": 2 }
+                "avg_price": { "value": 899.0 }
             }
         });
 
         let separate_expected = json!({
             "result": {
-                "value": 899.0,
-                "sum": 1798.0,
-                "count": 2
+                "value": 899.0
             }
         });
 

src/aggregation/bucket/histogram/histogram.rs

@@ -1222,9 +1222,7 @@ mod tests {
             res["histogram"]["buckets"][0],
             json!({
                 "avg": {
-                    "value": Value::Null,
-                    "sum": 0.0,
-                    "count": 0
+                    "value": Value::Null
                 },
                 "doc_count": 0,
                 "key": 2.0,

src/aggregation/collector.rs

@@ -66,7 +66,7 @@ impl Collector for DistributedAggregationCollector {
     fn for_segment(
         &self,
         segment_local_id: crate::SegmentOrdinal,
-        reader: &crate::SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         AggregationSegmentCollector::from_agg_req_and_reader(
             &self.agg,
@@ -96,7 +96,7 @@ impl Collector for AggregationCollector {
     fn for_segment(
         &self,
         segment_local_id: crate::SegmentOrdinal,
-        reader: &crate::SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         AggregationSegmentCollector::from_agg_req_and_reader(
             &self.agg,
@@ -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: &SegmentReader,
+        reader: &dyn SegmentReader,
         segment_ordinal: SegmentOrdinal,
         context: &AggContextParams,
     ) -> crate::Result<Self> {

src/aggregation/intermediate_agg_result.rs

@@ -19,9 +19,8 @@ use super::bucket::{
     GetDocCount, Order, OrderTarget, RangeAggregation, TermsAggregation,
 };
 use super::metric::{
-    AverageMetricResult, CardinalityMetricResult, IntermediateAverage, IntermediateCount,
-    IntermediateExtendedStats, IntermediateMax, IntermediateMin, IntermediateStats,
-    IntermediateSum, PercentilesCollector, TopHitsTopNComputer,
+    IntermediateAverage, IntermediateCount, IntermediateExtendedStats, IntermediateMax,
+    IntermediateMin, IntermediateStats, IntermediateSum, PercentilesCollector, TopHitsTopNComputer,
 };
 use super::segment_agg_result::AggregationLimitsGuard;
 use super::{format_date, AggregationError, Key, SerializedKey};
@@ -91,6 +90,19 @@ impl From<IntermediateKey> for Key {
 
 impl Eq for IntermediateKey {}
 
+impl std::fmt::Display for IntermediateKey {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            IntermediateKey::Str(val) => f.write_str(val),
+            IntermediateKey::F64(val) => f.write_str(&val.to_string()),
+            IntermediateKey::U64(val) => f.write_str(&val.to_string()),
+            IntermediateKey::I64(val) => f.write_str(&val.to_string()),
+            IntermediateKey::Bool(val) => f.write_str(&val.to_string()),
+            IntermediateKey::IpAddr(val) => f.write_str(&val.to_string()),
+        }
+    }
+}
+
 impl std::hash::Hash for IntermediateKey {
     fn hash<H: std::hash::Hasher>(&self, state: &mut H) {
         core::mem::discriminant(self).hash(state);
@@ -106,6 +118,21 @@ impl std::hash::Hash for IntermediateKey {
 }
 
 impl IntermediateAggregationResults {
+    /// Returns a reference to the intermediate aggregation result for the given key.
+    pub fn get(&self, key: &str) -> Option<&IntermediateAggregationResult> {
+        self.aggs_res.get(key)
+    }
+
+    /// Removes and returns the intermediate aggregation result for the given key.
+    pub fn remove(&mut self, key: &str) -> Option<IntermediateAggregationResult> {
+        self.aggs_res.remove(key)
+    }
+
+    /// Returns an iterator over the keys in the intermediate aggregation results.
+    pub fn keys(&self) -> impl Iterator<Item = &String> {
+        self.aggs_res.keys()
+    }
+
     /// Add a result
     pub fn push(&mut self, key: String, value: IntermediateAggregationResult) -> crate::Result<()> {
         let entry = self.aggs_res.entry(key);
@@ -326,11 +353,7 @@ impl IntermediateMetricResult {
     fn into_final_metric_result(self, req: &Aggregation) -> MetricResult {
         match self {
             IntermediateMetricResult::Average(intermediate_avg) => {
-                MetricResult::Average(AverageMetricResult {
-                    value: intermediate_avg.finalize(),
-                    sum: intermediate_avg.sum(),
-                    count: intermediate_avg.count(),
-                })
+                MetricResult::Average(intermediate_avg.finalize().into())
             }
             IntermediateMetricResult::Count(intermediate_count) => {
                 MetricResult::Count(intermediate_count.finalize().into())
@@ -358,11 +381,7 @@ impl IntermediateMetricResult {
                 MetricResult::TopHits(top_hits.into_final_result())
             }
             IntermediateMetricResult::Cardinality(cardinality) => {
-                let value = cardinality.finalize();
-                MetricResult::Cardinality(CardinalityMetricResult {
-                    value,
-                    sketch: Some(cardinality),
-                })
+                MetricResult::Cardinality(cardinality.finalize().into())
             }
         }
     }
@@ -648,6 +667,21 @@ pub struct IntermediateTermBucketResult {
 }
 
 impl IntermediateTermBucketResult {
+    /// Returns a reference to the map of bucket entries keyed by [`IntermediateKey`].
+    pub fn entries(&self) -> &FxHashMap<IntermediateKey, IntermediateTermBucketEntry> {
+        &self.entries
+    }
+
+    /// Returns the count of documents not included in the returned buckets.
+    pub fn sum_other_doc_count(&self) -> u64 {
+        self.sum_other_doc_count
+    }
+
+    /// Returns the upper bound of the error on document counts in the returned buckets.
+    pub fn doc_count_error_upper_bound(&self) -> u64 {
+        self.doc_count_error_upper_bound
+    }
+
     pub(crate) fn into_final_result(
         self,
         req: &TermsAggregation,

src/aggregation/metric/average.rs

@@ -55,6 +55,12 @@ impl IntermediateAverage {
     pub(crate) fn from_stats(stats: IntermediateStats) -> Self {
         Self { stats }
     }
+
+    /// Returns a reference to the underlying [`IntermediateStats`].
+    pub fn stats(&self) -> &IntermediateStats {
+        &self.stats
+    }
+
     /// Merges the other intermediate result into self.
     pub fn merge_fruits(&mut self, other: IntermediateAverage) {
         self.stats.merge_fruits(other.stats);
@@ -63,16 +69,6 @@ impl IntermediateAverage {
     pub fn finalize(&self) -> Option<f64> {
         self.stats.finalize().avg
     }
-
-    /// Returns the sum of all collected values.
-    pub fn sum(&self) -> f64 {
-        self.stats.sum
-    }
-
-    /// Returns the count of all collected values.
-    pub fn count(&self) -> u64 {
-        self.stats.count
-    }
 }
 
 #[cfg(test)]

src/aggregation/metric/cardinality.rs

@@ -340,7 +340,7 @@ impl PartialEq for CardinalityCollector {
 
 impl CardinalityCollector {
     /// Compute the final cardinality estimate.
-    pub fn finalize(&self) -> Option<f64> {
+    pub fn finalize(self) -> Option<f64> {
         Some(self.sketch.clone().count().trunc())
     }
 

src/aggregation/metric/mod.rs

@@ -93,41 +93,6 @@ impl From<Option<f64>> for SingleMetricResult {
     }
 }
 
-/// Average metric result with intermediate data for merging.
-///
-/// Unlike [`SingleMetricResult`], this struct includes the raw `sum` and `count`
-/// values that can be used for multi-step query merging.
-#[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
-pub struct AverageMetricResult {
-    /// The computed average value. None if no documents matched.
-    pub value: Option<f64>,
-    /// The sum of all values (for multi-step merging).
-    pub sum: f64,
-    /// The count of all values (for multi-step merging).
-    pub count: u64,
-}
-
-/// Cardinality metric result with computed value and raw HLL sketch for multi-step merging.
-///
-/// The `value` field contains the computed cardinality estimate.
-/// The `sketch` field contains the serialized HyperLogLog++ sketch that can be used
-/// for merging results across multiple query steps.
-#[derive(Clone, Debug, Serialize, Deserialize)]
-pub struct CardinalityMetricResult {
-    /// The computed cardinality estimate.
-    pub value: Option<f64>,
-    /// The serialized HyperLogLog++ sketch for multi-step merging.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub sketch: Option<CardinalityCollector>,
-}
-
-impl PartialEq for CardinalityMetricResult {
-    fn eq(&self, other: &Self) -> bool {
-        // Only compare values, not sketch (sketch comparison is complex)
-        self.value == other.value
-    }
-}
-
 /// This is the wrapper of percentile entries, which can be vector or hashmap
 /// depending on if it's keyed or not.
 #[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
@@ -142,30 +107,20 @@ pub enum PercentileValues {
 #[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
 /// The entry when requesting percentiles with keyed: false
 pub struct PercentileValuesVecEntry {
-    key: f64,
-    value: f64,
+    /// Percentile
+    pub key: f64,
+
+    /// Value at the percentile
+    pub value: f64,
 }
 
-/// Percentiles metric result with computed values and raw sketch for multi-step merging.
+/// Single-metric aggregations use this common result structure.
 ///
-/// The `values` field contains the computed percentile values.
-/// The `sketch` field contains the serialized DDSketch that can be used for merging
-/// results across multiple query steps.
-#[derive(Clone, Debug, Serialize, Deserialize)]
+/// Main reason to wrap it in value is to match elasticsearch output structure.
+#[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
 pub struct PercentilesMetricResult {
-    /// The computed percentile values.
+    /// The result of the percentile metric.
     pub values: PercentileValues,
-    /// The serialized DDSketch for multi-step merging.
-    /// This is the raw sketch data that can be deserialized and merged with other sketches.
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub sketch: Option<PercentilesCollector>,
-}
-
-impl PartialEq for PercentilesMetricResult {
-    fn eq(&self, other: &Self) -> bool {
-        // Only compare values, not sketch (sketch comparison is complex)
-        self.values == other.values
-    }
 }
 
 /// The top_hits metric results entry
@@ -246,105 +201,4 @@ mod tests {
         assert_eq!(aggregations_res_json["price_min"]["value"], 0.0);
         assert_eq!(aggregations_res_json["price_sum"]["value"], 15.0);
     }
-
-    #[test]
-    fn test_average_returns_sum_and_count() {
-        let mut schema_builder = Schema::builder();
-        let field_options = NumericOptions::default().set_fast();
-        let field = schema_builder.add_f64_field("price", field_options);
-        let index = Index::create_in_ram(schema_builder.build());
-        let mut index_writer: IndexWriter = index.writer_for_tests().unwrap();
-
-        // Add documents with values 0, 1, 2, 3, 4, 5
-        // sum = 15, count = 6, avg = 2.5
-        for i in 0..6 {
-            index_writer
-                .add_document(doc!(
-                    field => i as f64,
-                ))
-                .unwrap();
-        }
-        index_writer.commit().unwrap();
-
-        let aggregations_json = r#"{ "price_avg": { "avg": { "field": "price" } } }"#;
-        let aggregations: Aggregations = serde_json::from_str(aggregations_json).unwrap();
-        let collector = AggregationCollector::from_aggs(aggregations, Default::default());
-        let reader = index.reader().unwrap();
-        let searcher = reader.searcher();
-        let aggregations_res: AggregationResults = searcher.search(&AllQuery, &collector).unwrap();
-        let aggregations_res_json = serde_json::to_value(aggregations_res).unwrap();
-
-        // Verify all three fields are present and correct
-        assert_eq!(aggregations_res_json["price_avg"]["value"], 2.5);
-        assert_eq!(aggregations_res_json["price_avg"]["sum"], 15.0);
-        assert_eq!(aggregations_res_json["price_avg"]["count"], 6);
-    }
-
-    #[test]
-    fn test_percentiles_returns_sketch() {
-        let mut schema_builder = Schema::builder();
-        let field_options = NumericOptions::default().set_fast();
-        let field = schema_builder.add_f64_field("latency", field_options);
-        let index = Index::create_in_ram(schema_builder.build());
-        let mut index_writer: IndexWriter = index.writer_for_tests().unwrap();
-
-        // Add documents with latency values
-        for i in 0..100 {
-            index_writer
-                .add_document(doc!(
-                    field => i as f64,
-                ))
-                .unwrap();
-        }
-        index_writer.commit().unwrap();
-
-        let aggregations_json =
-            r#"{ "latency_percentiles": { "percentiles": { "field": "latency" } } }"#;
-        let aggregations: Aggregations = serde_json::from_str(aggregations_json).unwrap();
-        let collector = AggregationCollector::from_aggs(aggregations, Default::default());
-        let reader = index.reader().unwrap();
-        let searcher = reader.searcher();
-        let aggregations_res: AggregationResults = searcher.search(&AllQuery, &collector).unwrap();
-        let aggregations_res_json = serde_json::to_value(aggregations_res).unwrap();
-
-        // Verify percentile values are present
-        assert!(aggregations_res_json["latency_percentiles"]["values"].is_object());
-        // Verify sketch is present (serialized DDSketch)
-        assert!(aggregations_res_json["latency_percentiles"]["sketch"].is_object());
-    }
-
-    #[test]
-    fn test_cardinality_returns_sketch() {
-        let mut schema_builder = Schema::builder();
-        let field_options = NumericOptions::default().set_fast();
-        let field = schema_builder.add_u64_field("user_id", field_options);
-        let index = Index::create_in_ram(schema_builder.build());
-        let mut index_writer: IndexWriter = index.writer_for_tests().unwrap();
-
-        // Add documents with some duplicate user_ids
-        for i in 0..50 {
-            index_writer
-                .add_document(doc!(
-                    field => (i % 10) as u64,  // 10 unique values
-                ))
-                .unwrap();
-        }
-        index_writer.commit().unwrap();
-
-        let aggregations_json = r#"{ "unique_users": { "cardinality": { "field": "user_id" } } }"#;
-        let aggregations: Aggregations = serde_json::from_str(aggregations_json).unwrap();
-        let collector = AggregationCollector::from_aggs(aggregations, Default::default());
-        let reader = index.reader().unwrap();
-        let searcher = reader.searcher();
-        let aggregations_res: AggregationResults = searcher.search(&AllQuery, &collector).unwrap();
-        let aggregations_res_json = serde_json::to_value(aggregations_res).unwrap();
-
-        // Verify cardinality value is present and approximately correct
-        let cardinality = aggregations_res_json["unique_users"]["value"]
-            .as_f64()
-            .unwrap();
-        assert!(cardinality >= 9.0 && cardinality <= 11.0); // HLL is approximate
-                                                            // Verify sketch is present (serialized HyperLogLog++)
-        assert!(aggregations_res_json["unique_users"]["sketch"].is_object());
-    }
 }

src/aggregation/metric/percentiles.rs

@@ -178,9 +178,6 @@ fn format_percentile(percentile: f64) -> String {
 impl PercentilesCollector {
     /// Convert result into final result. This will query the quantils from the underlying quantil
     /// collector.
-    ///
-    /// The result includes both the computed percentile values and the raw DDSketch
-    /// for multi-step query merging.
     pub fn into_final_result(self, req: &PercentilesAggregationReq) -> PercentilesMetricResult {
         let percentiles: &[f64] = req
             .percents
@@ -213,15 +210,7 @@ impl PercentilesCollector {
                     .collect(),
             )
         };
-        PercentilesMetricResult {
-            values,
-            sketch: Some(self),
-        }
-    }
-
-    /// Returns a reference to the underlying DDSketch.
-    pub fn sketch(&self) -> &sketches_ddsketch::DDSketch {
-        &self.sketch
+        PercentilesMetricResult { values }
     }
 
     fn new() -> Self {

src/aggregation/metric/stats.rs

@@ -110,6 +110,16 @@ impl Default for IntermediateStats {
 }
 
 impl IntermediateStats {
+    /// Returns the number of values collected.
+    pub fn count(&self) -> u64 {
+        self.count
+    }
+
+    /// Returns the sum of all values collected.
+    pub fn sum(&self) -> f64 {
+        self.sum
+    }
+
     /// Merges the other stats intermediate result into self.
     pub fn merge_fruits(&mut self, other: IntermediateStats) {
         self.count += other.count;

src/codec/mod.rs

@@ -0,0 +1,170 @@
+/// Codec specific to postings data.
+pub mod postings;
+
+/// Standard tantivy codec. This is the codec you use by default.
+pub mod standard;
+
+use std::sync::Arc;
+
+pub use standard::StandardCodec;
+
+use crate::codec::postings::PostingsCodec;
+use crate::directory::Directory;
+use crate::fastfield::AliveBitSet;
+use crate::query::score_combiner::DoNothingCombiner;
+use crate::query::term_query::TermScorer;
+use crate::query::{box_scorer, BufferedUnionScorer, Scorer, SumCombiner};
+use crate::schema::Schema;
+use crate::{DocId, Score, SegmentMeta, SegmentReader, TantivySegmentReader};
+
+/// 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;
+
+    /// ID of the codec. It should be unique to your codec.
+    /// Make it human-readable, descriptive, short and unique.
+    const ID: &'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;
+
+    /// Loads postings using the codec's concrete postings type.
+    fn load_postings_typed(
+        &self,
+        reader: &dyn crate::index::InvertedIndexReader,
+        term_info: &crate::postings::TermInfo,
+        option: crate::schema::IndexRecordOption,
+    ) -> std::io::Result<<Self::PostingsCodec as crate::codec::postings::PostingsCodec>::Postings>
+    {
+        let postings_data = reader.read_raw_postings_data(term_info, option)?;
+        self.postings_codec()
+            .load_postings(term_info.doc_freq, postings_data)
+    }
+
+    /// Opens a segment reader using this codec.
+    ///
+    /// Override this if your codec uses a custom segment reader implementation.
+    fn open_segment_reader(
+        &self,
+        directory: &dyn Directory,
+        segment_meta: &SegmentMeta,
+        schema: Schema,
+        custom_bitset: Option<AliveBitSet>,
+    ) -> crate::Result<Arc<dyn SegmentReader>> {
+        let codec: Arc<dyn ObjectSafeCodec> = Arc::new(self.clone());
+        let reader = TantivySegmentReader::open_with_custom_alive_set_from_directory(
+            directory,
+            segment_meta,
+            schema,
+            codec,
+            custom_bitset,
+        )?;
+        Ok(Arc::new(reader))
+    }
+}
+
+/// 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 {
+    /// 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,
+    );
+
+    /// Builds a union scorer possibly specialized if
+    /// all scorers are `Term<Self::Postings>`.
+    fn build_union_scorer_with_sum_combiner(
+        &self,
+        scorers: Vec<Box<dyn Scorer>>,
+        num_docs: DocId,
+        score_combiner_type: SumOrDoNothingCombiner,
+    ) -> Box<dyn Scorer>;
+}
+
+impl<TCodec: Codec> ObjectSafeCodec for TCodec {
+    fn build_union_scorer_with_sum_combiner(
+        &self,
+        scorers: Vec<Box<dyn Scorer>>,
+        num_docs: DocId,
+        sum_or_do_nothing_combiner: SumOrDoNothingCombiner,
+    ) -> Box<dyn Scorer> {
+        if !scorers.iter().all(|scorer| {
+            scorer.is::<TermScorer<<<Self as Codec>::PostingsCodec as PostingsCodec>::Postings>>()
+        }) {
+            return box_scorer(BufferedUnionScorer::build(
+                scorers,
+                SumCombiner::default,
+                num_docs,
+            ));
+        }
+        let specialized_scorers: Vec<
+            TermScorer<<<Self as Codec>::PostingsCodec as PostingsCodec>::Postings>,
+        > = scorers
+            .into_iter()
+            .map(|scorer| {
+                *scorer.downcast::<TermScorer<_>>().ok().expect(
+                    "Downcast failed despite the fact we already checked the type was correct",
+                )
+            })
+            .collect();
+        match sum_or_do_nothing_combiner {
+            SumOrDoNothingCombiner::Sum => box_scorer(BufferedUnionScorer::build(
+                specialized_scorers,
+                SumCombiner::default,
+                num_docs,
+            )),
+            SumOrDoNothingCombiner::DoNothing => box_scorer(BufferedUnionScorer::build(
+                specialized_scorers,
+                DoNothingCombiner::default,
+                num_docs,
+            )),
+        }
+    }
+
+    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);
+        }
+    }
+}
+
+/// SumCombiner or DoNothingCombiner
+#[derive(Copy, Clone)]
+pub enum SumOrDoNothingCombiner {
+    /// Sum scores together
+    Sum,
+    /// Do not track any score.
+    DoNothing,
+}

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 +1,75 @@
+/// Block-max WAND algorithm.
+pub mod block_wand;
+use std::io;
+
+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 (read path).
+pub trait PostingsCodec: Send + Sync + 'static {
+    /// Postings type for the postings codec.
+    type Postings: Postings + Clone;
+
+    /// Load postings from raw bytes and metadata.
+    fn load_postings(
+        &self,
+        doc_freq: u32,
+        postings_data: RawPostingsData,
+    ) -> 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)
+    }
+}
+
+/// Raw postings bytes and metadata read from storage.
+#[derive(Debug, Clone)]
+pub struct RawPostingsData {
+    /// Raw postings bytes for the term.
+    pub postings_data: OwnedBytes,
+    /// Raw positions bytes for the term, if positions are available.
+    pub positions_data: Option<OwnedBytes>,
+    /// Record option of the indexed field.
+    pub record_option: IndexRecordOption,
+    /// Effective record option after downgrading to the indexed field capability.
+    pub effective_option: IndexRecordOption,
+}
+
+/// 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,
+        fieldnorm_reader: &FieldNormReader,
+        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 ID: &'static str = "tantivy-default";
+
+    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_segment_postings.rs

@@ -1,28 +1,19 @@
 use std::io;
 
-use common::VInt;
+use common::{OwnedBytes, VInt};
 
-use crate::directory::{FileSlice, OwnedBytes};
+use crate::codec::standard::postings::FreqReadingOption;
 use crate::fieldnorm::FieldNormReader;
-use crate::postings::compression::{BlockDecoder, VIntDecoder, COMPRESSION_BLOCK_SIZE};
-use crate::postings::{BlockInfo, FreqReadingOption, SkipReader};
+use crate::postings::compression::{BlockDecoder, VIntDecoder as _, COMPRESSION_BLOCK_SIZE};
+use crate::postings::skip::{BlockInfo, SkipReader};
 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 +79,7 @@ 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 +87,10 @@ 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) => {
@@ -138,6 +128,86 @@ impl BlockSegmentPostings {
         block_segment_postings.load_block();
         Ok(block_segment_postings)
     }
+}
+
+fn max_score<I: Iterator<Item = Score>>(mut it: I) -> Option<Score> {
+    it.next().map(|first| it.fold(first, Score::max))
+}
+
+impl BlockSegmentPostings {
+    /// Returns the overall number of documents in the block postings.
+    /// It does not take in account whether documents are deleted or not.
+    ///
+    /// This `doc_freq` is simply the sum of the length of all of the blocks
+    /// length, and it does not take in account deleted documents.
+    pub fn doc_freq(&self) -> u32 {
+        self.doc_freq
+    }
+
+    /// Returns the array of docs in the current block.
+    ///
+    /// Before the first call to `.advance()`, the block
+    /// returned by `.docs()` is empty.
+    #[inline]
+    pub fn docs(&self) -> &[DocId] {
+        debug_assert!(self.block_loaded);
+        self.doc_decoder.output_array()
+    }
+
+    /// Return the document at index `idx` of the block.
+    #[inline]
+    pub fn doc(&self, idx: usize) -> u32 {
+        self.doc_decoder.output(idx)
+    }
+
+    /// Return the array of `term freq` in the block.
+    #[inline]
+    pub fn freqs(&self) -> &[u32] {
+        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_loaded);
+        self.freq_decoder.output(idx)
+    }
+
+    /// 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_without_loading(target_doc);
+        self.load_block();
+
+        // At this point we are on the block that might contain our document.
+        let doc = self.doc_decoder.seek_within_block(target_doc);
+
+        // The last block is not full and padded with TERMINATED,
+        // so we are guaranteed to have at least one value (real or padding)
+        // that is >= target_doc.
+        debug_assert!(doc < COMPRESSION_BLOCK_SIZE);
+
+        // `doc` is now the first element >= `target_doc`.
+        // If all docs are smaller than target, the current block is incomplete and padded
+        // with TERMINATED. After the search, the cursor points to the first TERMINATED.
+        doc
+    }
+
+    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
@@ -160,7 +230,7 @@ impl BlockSegmentPostings {
         }
         // 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() {
+        if self.block_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)| {
@@ -177,112 +247,25 @@ impl BlockSegmentPostings {
         // 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
-    }
-
-    // Resets the block segment postings on another position
-    // in the postings file.
-    //
-    // This is useful for enumerating through a list of terms,
-    // and consuming the associated posting lists while avoiding
-    // reallocating a `BlockSegmentPostings`.
-    //
-    // # Warning
-    //
-    // This does not reset the positions list.
-    pub(crate) fn reset(&mut self, doc_freq: u32, postings_data: OwnedBytes) -> io::Result<()> {
-        let (skip_data_opt, postings_data) =
-            split_into_skips_and_postings(doc_freq, postings_data)?;
-        self.data = postings_data;
-        self.block_max_score_cache = None;
-        self.block_loaded = false;
-        if let Some(skip_data) = skip_data_opt {
-            self.skip_reader.reset(skip_data, doc_freq);
-        } else {
-            self.skip_reader.reset(OwnedBytes::empty(), doc_freq);
+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),
         }
-        self.doc_freq = doc_freq;
-        self.load_block();
-        Ok(())
     }
 
-    /// Returns the overall number of documents in the block postings.
-    /// It does not take in account whether documents are deleted or not.
-    ///
-    /// This `doc_freq` is simply the sum of the length of all of the blocks
-    /// length, and it does not take in account deleted documents.
-    pub fn doc_freq(&self) -> u32 {
-        self.doc_freq
-    }
-
-    /// Returns the array of docs in the current block.
-    ///
-    /// Before the first call to `.advance()`, the block
-    /// returned by `.docs()` is empty.
-    #[inline]
-    pub fn docs(&self) -> &[DocId] {
-        debug_assert!(self.block_is_loaded());
-        self.doc_decoder.output_array()
-    }
-
-    /// Return the document at index `idx` of the block.
-    #[inline]
-    pub fn doc(&self, idx: usize) -> u32 {
-        self.doc_decoder.output(idx)
-    }
-
-    /// Return the array of `term freq` in the block.
-    #[inline]
-    pub fn freqs(&self) -> &[u32] {
-        debug_assert!(self.block_is_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());
-        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.load_block();
-
-        // At this point we are on the block that might contain our document.
-        let doc = self.doc_decoder.seek_within_block(target_doc);
-
-        // The last block is not full and padded with TERMINATED,
-        // so we are guaranteed to have at least one value (real or padding)
-        // that is >= target_doc.
-        debug_assert!(doc < COMPRESSION_BLOCK_SIZE);
-
-        // `doc` is now the first element >= `target_doc`.
-        // If all docs are smaller than target, the current block is incomplete and padded
-        // with TERMINATED. After the search, the cursor points to the first TERMINATED.
-        doc
-    }
-
-    pub(crate) fn position_offset(&self) -> u64 {
-        self.skip_reader.position_offset()
+    pub(crate) fn skip_reader(&self) -> &SkipReader {
+        &self.skip_reader
     }
 
     /// Dangerous API! This calls seeks the next block on the skip list,
@@ -291,19 +274,15 @@ impl BlockSegmentPostings {
     /// `.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) {
-        if self.block_is_loaded() {
+        if self.block_loaded {
             return;
         }
         let offset = self.skip_reader.byte_offset();
@@ -351,68 +330,39 @@ 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::standard::postings::segment_postings::SegmentPostings;
     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::postings::serializer::PostingsSerializer;
+    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 =
+            PostingsSerializer::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]
@@ -427,7 +377,7 @@ 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);
@@ -452,7 +402,7 @@ 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);
@@ -461,7 +411,7 @@ 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);
@@ -470,7 +420,7 @@ 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);
@@ -479,38 +429,13 @@ 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();
@@ -521,40 +446,4 @@ mod tests {
         assert_eq!(block_postings.doc(COMPRESSION_BLOCK_SIZE - 1), TERMINATED);
         Ok(())
     }
-
-    #[test]
-    fn test_reset_block_segment_postings() -> crate::Result<()> {
-        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()?;
-        // create two postings list, one containing even number,
-        // the other containing odd numbers.
-        for i in 0..6 {
-            let doc = doc!(int_field=> (i % 2) as u64);
-            index_writer.add_document(doc)?;
-        }
-        index_writer.commit()?;
-        let searcher = index.reader()?.searcher();
-        let segment_reader = searcher.segment_reader(0);
-
-        let mut block_segments;
-        {
-            let term = Term::from_field_u64(int_field, 0u64);
-            let inverted_index = segment_reader.inverted_index(int_field)?;
-            let term_info = inverted_index.get_term_info(&term)?.unwrap();
-            block_segments = inverted_index
-                .read_block_postings_from_terminfo(&term_info, IndexRecordOption::Basic)?;
-        }
-        assert_eq!(block_segments.docs(), &[0, 2, 4]);
-        {
-            let term = Term::from_field_u64(int_field, 1u64);
-            let inverted_index = segment_reader.inverted_index(int_field)?;
-            let term_info = inverted_index.get_term_info(&term)?.unwrap();
-            inverted_index.reset_block_postings_from_terminfo(&term_info, &mut block_segments)?;
-        }
-        assert_eq!(block_segments.docs(), &[1, 3, 5]);
-        Ok(())
-    }
 }

src/codec/standard/postings/mod.rs

@@ -0,0 +1,171 @@
+use std::io;
+
+use common::BitSet;
+
+use crate::codec::postings::block_wand::{block_wand, block_wand_single_scorer};
+use crate::codec::postings::{PostingsCodec, RawPostingsData};
+use crate::codec::standard::postings::block_segment_postings::BlockSegmentPostings;
+pub use crate::codec::standard::postings::segment_postings::SegmentPostings;
+use crate::positions::PositionReader;
+use crate::query::term_query::TermScorer;
+use crate::query::{BufferedUnionScorer, Scorer, SumCombiner};
+use crate::{DocSet as _, Score, TERMINATED};
+
+mod block_segment_postings;
+mod segment_postings;
+
+pub use segment_postings::SegmentPostings as StandardPostings;
+
+/// 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 Postings = SegmentPostings;
+
+    fn load_postings(
+        &self,
+        doc_freq: u32,
+        postings_data: RawPostingsData,
+    ) -> io::Result<Self::Postings> {
+        load_postings_from_raw_data(doc_freq, postings_data)
+    }
+
+    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<TermScorer<Self::Postings>, SumCombiner>>()?;
+        let doc = union_scorer.doc();
+        if doc == TERMINATED {
+            return Ok(());
+        }
+        let score = union_scorer.score();
+        if score > threshold {
+            threshold = callback(doc, score);
+        }
+        let scorers: Vec<TermScorer<Self::Postings>> = union_scorer.into_scorers();
+        block_wand(scorers, threshold, callback);
+        Ok(())
+    }
+}
+pub(crate) fn load_postings_from_raw_data(
+    doc_freq: u32,
+    postings_data: RawPostingsData,
+) -> io::Result<SegmentPostings> {
+    let RawPostingsData {
+        postings_data,
+        positions_data: positions_data_opt,
+        record_option,
+        effective_option,
+    } = postings_data;
+    let requested_option = effective_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,
+    ))
+}
+
+pub(crate) fn fill_bitset_from_raw_data(
+    doc_freq: u32,
+    postings_data: RawPostingsData,
+    doc_bitset: &mut BitSet,
+) -> io::Result<()> {
+    let RawPostingsData {
+        postings_data,
+        record_option,
+        effective_option,
+        ..
+    } = postings_data;
+    let mut block_postings =
+        BlockSegmentPostings::open(doc_freq, postings_data, record_option, effective_option)?;
+    loop {
+        let docs = block_postings.docs();
+        if docs.is_empty() {
+            break;
+        }
+        for &doc in docs {
+            doc_bitset.insert(doc);
+        }
+        block_postings.advance();
+    }
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use common::OwnedBytes;
+
+    use super::*;
+    use crate::postings::serializer::PostingsSerializer;
+    use crate::postings::Postings as _;
+    use crate::schema::IndexRecordOption;
+
+    fn test_segment_postings_tf_aux(num_docs: u32, include_term_freq: bool) -> SegmentPostings {
+        let mut postings_serializer =
+            PostingsSerializer::new(1.0f32, IndexRecordOption::WithFreqs, None);
+        let mut buffer = Vec::new();
+        postings_serializer.new_term(num_docs, include_term_freq);
+        for i in 0..num_docs {
+            postings_serializer.write_doc(i, 2);
+        }
+        postings_serializer
+            .close_term(num_docs, &mut buffer)
+            .unwrap();
+        load_postings_from_raw_data(
+            num_docs,
+            RawPostingsData {
+                postings_data: OwnedBytes::new(buffer),
+                positions_data: None,
+                record_option: IndexRecordOption::WithFreqs,
+                effective_option: IndexRecordOption::WithFreqs,
+            },
+        )
+        .unwrap()
+    }
+
+    #[test]
+    fn test_segment_postings_small_block_with_and_without_freq() {
+        let small_block_without_term_freq = test_segment_postings_tf_aux(1, false);
+        assert!(!small_block_without_term_freq.has_freq());
+        assert_eq!(small_block_without_term_freq.doc(), 0);
+        assert_eq!(small_block_without_term_freq.term_freq(), 1);
+
+        let small_block_with_term_freq = test_segment_postings_tf_aux(1, true);
+        assert!(small_block_with_term_freq.has_freq());
+        assert_eq!(small_block_with_term_freq.doc(), 0);
+        assert_eq!(small_block_with_term_freq.term_freq(), 2);
+    }
+
+    #[test]
+    fn test_segment_postings_large_block_with_and_without_freq() {
+        let large_block_without_term_freq = test_segment_postings_tf_aux(128, false);
+        assert!(!large_block_without_term_freq.has_freq());
+        assert_eq!(large_block_without_term_freq.doc(), 0);
+        assert_eq!(large_block_without_term_freq.term_freq(), 1);
+
+        let large_block_with_term_freq = test_segment_postings_tf_aux(128, true);
+        assert!(large_block_with_term_freq.has_freq());
+        assert_eq!(large_block_with_term_freq.doc(), 0);
+        assert_eq!(large_block_with_term_freq.term_freq(), 2);
+    }
+}

src/codec/standard/postings/segment_postings.rs

@@ -1,11 +1,14 @@
-use common::HasLen;
+use common::BitSet;
 
+use super::BlockSegmentPostings;
+use crate::codec::postings::PostingsWithBlockMax;
 use crate::docset::DocSet;
-use crate::fastfield::AliveBitSet;
+use crate::fieldnorm::FieldNormReader;
 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 +32,6 @@ 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.
     ///
@@ -64,11 +42,13 @@ 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::postings::serializer::PostingsSerializer;
+
             let mut postings_serializer =
                 PostingsSerializer::new(0.0, IndexRecordOption::Basic, None);
             postings_serializer.new_term(docs.len() as u32, false);
@@ -81,7 +61,7 @@ impl SegmentPostings {
         }
         let block_segment_postings = BlockSegmentPostings::open(
             docs.len() as u32,
-            FileSlice::from(buffer),
+            OwnedBytes::new(buffer),
             IndexRecordOption::Basic,
             IndexRecordOption::Basic,
         )
@@ -95,7 +75,8 @@ impl SegmentPostings {
         doc_and_tfs: &[(u32, u32)],
         fieldnorms: Option<&[u32]>,
     ) -> SegmentPostings {
-        use crate::directory::FileSlice;
+        use common::OwnedBytes;
+
         use crate::fieldnorm::FieldNormReader;
         use crate::postings::serializer::PostingsSerializer;
         use crate::schema::IndexRecordOption;
@@ -128,7 +109,7 @@ 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 +139,6 @@ 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();
@@ -197,13 +177,31 @@ impl DocSet for SegmentPostings {
     }
 
     fn size_hint(&self) -> u32 {
-        self.len() as u32
+        self.doc_freq().into()
     }
-}
 
-impl HasLen for SegmentPostings {
-    fn len(&self) -> usize {
-        self.block_cursor.doc_freq() as usize
+    fn fill_bitset(&mut self, bitset: &mut BitSet) {
+        let bitset_max_value: DocId = bitset.max_value();
+        loop {
+            let docs = self.block_cursor.docs();
+            let Some(&last_doc) = docs.last() else {
+                break;
+            };
+            if last_doc < bitset_max_value {
+                // All docs are within the range of the bitset
+                for &doc in docs {
+                    bitset.insert(doc);
+                }
+            } else {
+                for &doc in docs {
+                    if doc < bitset_max_value {
+                        bitset.insert(doc);
+                    }
+                }
+                break;
+            }
+            self.block_cursor.advance();
+        }
     }
 }
 
@@ -229,6 +227,13 @@ 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();
@@ -252,24 +257,44 @@ impl Postings for SegmentPostings {
             }
         }
     }
+
+    fn has_freq(&self) -> bool {
+        !self.block_cursor.freqs().is_empty()
+    }
+}
+
+impl PostingsWithBlockMax for SegmentPostings {
+    #[inline]
+    fn seek_block_max(
+        &mut self,
+        target_doc: crate::DocId,
+        fieldnorm_reader: &FieldNormReader,
+        similarity_weight: &Bm25Weight,
+    ) -> Score {
+        self.block_cursor.seek_block_without_loading(target_doc);
+        self.block_cursor
+            .block_max_score(fieldnorm_reader, similarity_weight)
+    }
+
+    #[inline]
+    fn last_doc_in_block(&self) -> crate::DocId {
+        self.block_cursor.skip_reader().last_doc_in_block()
+    }
 }
 
 #[cfg(test)]
 mod tests {
-
-    use common::HasLen;
-
     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.len(), 0);
+        assert_eq!(postings.doc_freq(), crate::postings::DocFreq::Exact(0));
     }
 
     #[test]
@@ -284,15 +309,4 @@ 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/collector/count_collector.rs

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

src/collector/docset_collector.rs

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

src/collector/facet_collector.rs

@@ -265,7 +265,7 @@ impl Collector for FacetCollector {
     fn for_segment(
         &self,
         _: SegmentOrdinal,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<FacetSegmentCollector> {
         let facet_reader = reader.facet_reader(&self.field_name)?;
         let facet_dict = facet_reader.facet_dict();

src/collector/filter_collector_wrapper.rs

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

src/collector/histogram_collector.rs

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

src/collector/mod.rs

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

src/collector/multi_collector.rs

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

src/collector/sort_key/mod.rs

@@ -1,4 +1,5 @@
 mod order;
+mod sort_by_bytes;
 mod sort_by_erased_type;
 mod sort_by_score;
 mod sort_by_static_fast_value;
@@ -6,6 +7,7 @@ mod sort_by_string;
 mod sort_key_computer;
 
 pub use order::*;
+pub use sort_by_bytes::SortByBytes;
 pub use sort_by_erased_type::SortByErasedType;
 pub use sort_by_score::SortBySimilarityScore;
 pub use sort_by_static_fast_value::SortByStaticFastValue;

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};
+use crate::{DocId, Order, Score, SegmentReader};
 
 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: &crate::SegmentReader,
+        segment_reader: &dyn 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: &crate::SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let child = self.0.segment_sort_key_computer(segment_reader)?;
         Ok(SegmentSortKeyComputerWithComparator {

src/collector/sort_key/sort_by_bytes.rs

@@ -0,0 +1,168 @@
+use columnar::BytesColumn;
+
+use crate::collector::sort_key::NaturalComparator;
+use crate::collector::{SegmentSortKeyComputer, SortKeyComputer};
+use crate::termdict::TermOrdinal;
+use crate::{DocId, Score};
+
+/// Sort by the first value of a bytes column.
+///
+/// If the field is multivalued, only the first value is considered.
+///
+/// Documents that do not have this value are still considered.
+/// Their sort key will simply be `None`.
+#[derive(Debug, Clone)]
+pub struct SortByBytes {
+    column_name: String,
+}
+
+impl SortByBytes {
+    /// Creates a new sort by bytes sort key computer.
+    pub fn for_field(column_name: impl ToString) -> Self {
+        SortByBytes {
+            column_name: column_name.to_string(),
+        }
+    }
+}
+
+impl SortKeyComputer for SortByBytes {
+    type SortKey = Option<Vec<u8>>;
+    type Child = ByBytesColumnSegmentSortKeyComputer;
+    type Comparator = NaturalComparator;
+
+    fn segment_sort_key_computer(
+        &self,
+        segment_reader: &dyn crate::SegmentReader,
+    ) -> crate::Result<Self::Child> {
+        let bytes_column_opt = segment_reader.fast_fields().bytes(&self.column_name)?;
+        Ok(ByBytesColumnSegmentSortKeyComputer { bytes_column_opt })
+    }
+}
+
+/// Segment-level sort key computer for bytes columns.
+pub struct ByBytesColumnSegmentSortKeyComputer {
+    bytes_column_opt: Option<BytesColumn>,
+}
+
+impl SegmentSortKeyComputer for ByBytesColumnSegmentSortKeyComputer {
+    type SortKey = Option<Vec<u8>>;
+    type SegmentSortKey = Option<TermOrdinal>;
+    type SegmentComparator = NaturalComparator;
+
+    #[inline(always)]
+    fn segment_sort_key(&mut self, doc: DocId, _score: Score) -> Option<TermOrdinal> {
+        let bytes_column = self.bytes_column_opt.as_ref()?;
+        bytes_column.ords().first(doc)
+    }
+
+    fn convert_segment_sort_key(&self, term_ord_opt: Option<TermOrdinal>) -> Option<Vec<u8>> {
+        // TODO: Individual lookups to the dictionary like this are very likely to repeatedly
+        // decompress the same blocks. See https://github.com/quickwit-oss/tantivy/issues/2776
+        let term_ord = term_ord_opt?;
+        let bytes_column = self.bytes_column_opt.as_ref()?;
+        let mut bytes = Vec::new();
+        bytes_column
+            .dictionary()
+            .ord_to_term(term_ord, &mut bytes)
+            .ok()?;
+        Some(bytes)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::SortByBytes;
+    use crate::collector::TopDocs;
+    use crate::query::AllQuery;
+    use crate::schema::{BytesOptions, Schema, FAST, INDEXED};
+    use crate::{Index, IndexWriter, Order, TantivyDocument};
+
+    #[test]
+    fn test_sort_by_bytes_asc() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let bytes_field = schema_builder
+            .add_bytes_field("data", BytesOptions::default().set_fast().set_indexed());
+        let id_field = schema_builder.add_u64_field("id", FAST | INDEXED);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer: IndexWriter = index.writer_for_tests()?;
+
+        // Insert documents with byte values in non-sorted order
+        let test_data: Vec<(u64, Vec<u8>)> = vec![
+            (1, vec![0x02, 0x00]),
+            (2, vec![0x00, 0x10]),
+            (3, vec![0x01, 0x00]),
+            (4, vec![0x00, 0x20]),
+        ];
+
+        for (id, bytes) in &test_data {
+            let mut doc = TantivyDocument::new();
+            doc.add_u64(id_field, *id);
+            doc.add_bytes(bytes_field, bytes);
+            index_writer.add_document(doc)?;
+        }
+        index_writer.commit()?;
+
+        let reader = index.reader()?;
+        let searcher = reader.searcher();
+
+        // Sort ascending by bytes
+        let top_docs =
+            TopDocs::with_limit(10).order_by((SortByBytes::for_field("data"), Order::Asc));
+        let results: Vec<(Option<Vec<u8>>, _)> = searcher.search(&AllQuery, &top_docs)?;
+
+        // Expected order: [0x00,0x10], [0x00,0x20], [0x01,0x00], [0x02,0x00]
+        let sorted_bytes: Vec<Option<Vec<u8>>> = results.into_iter().map(|(b, _)| b).collect();
+        assert_eq!(
+            sorted_bytes,
+            vec![
+                Some(vec![0x00, 0x10]),
+                Some(vec![0x00, 0x20]),
+                Some(vec![0x01, 0x00]),
+                Some(vec![0x02, 0x00]),
+            ]
+        );
+
+        Ok(())
+    }
+
+    #[test]
+    fn test_sort_by_bytes_desc() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let bytes_field = schema_builder
+            .add_bytes_field("data", BytesOptions::default().set_fast().set_indexed());
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer: IndexWriter = index.writer_for_tests()?;
+
+        let test_data: Vec<Vec<u8>> = vec![vec![0x00, 0x10], vec![0x02, 0x00], vec![0x01, 0x00]];
+
+        for bytes in &test_data {
+            let mut doc = TantivyDocument::new();
+            doc.add_bytes(bytes_field, bytes);
+            index_writer.add_document(doc)?;
+        }
+        index_writer.commit()?;
+
+        let reader = index.reader()?;
+        let searcher = reader.searcher();
+
+        // Sort descending by bytes
+        let top_docs =
+            TopDocs::with_limit(10).order_by((SortByBytes::for_field("data"), Order::Desc));
+        let results: Vec<(Option<Vec<u8>>, _)> = searcher.search(&AllQuery, &top_docs)?;
+
+        // Expected order (descending): [0x02,0x00], [0x01,0x00], [0x00,0x10]
+        let sorted_bytes: Vec<Option<Vec<u8>>> = results.into_iter().map(|(b, _)| b).collect();
+        assert_eq!(
+            sorted_bytes,
+            vec![
+                Some(vec![0x02, 0x00]),
+                Some(vec![0x01, 0x00]),
+                Some(vec![0x00, 0x10]),
+            ]
+        );
+
+        Ok(())
+    }
+}

src/collector/sort_key/sort_by_erased_type.rs

@@ -1,12 +1,12 @@
 use columnar::{ColumnType, MonotonicallyMappableToU64};
 
 use crate::collector::sort_key::{
-    NaturalComparator, SortBySimilarityScore, SortByStaticFastValue, SortByString,
+    NaturalComparator, SortByBytes, SortBySimilarityScore, SortByStaticFastValue, SortByString,
 };
 use crate::collector::{SegmentSortKeyComputer, SortKeyComputer};
 use crate::fastfield::FastFieldNotAvailableError;
 use crate::schema::OwnedValue;
-use crate::{DateTime, DocId, Score};
+use crate::{DateTime, DocId, Score, SegmentReader};
 
 /// 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: &crate::SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let inner: Box<dyn ErasedSegmentSortKeyComputer> = match self {
             Self::Field(column_name) => {
@@ -114,6 +114,16 @@ impl SortKeyComputer for SortByErasedType {
                             },
                         })
                     }
+                    ColumnType::Bytes => {
+                        let computer = SortByBytes::for_field(column_name);
+                        let inner = computer.segment_sort_key_computer(segment_reader)?;
+                        Box::new(ErasedSegmentSortKeyComputerWrapper {
+                            inner,
+                            converter: |val: Option<Vec<u8>>| {
+                                val.map(OwnedValue::Bytes).unwrap_or(OwnedValue::Null)
+                            },
+                        })
+                    }
                     ColumnType::U64 => {
                         let computer = SortByStaticFastValue::<u64>::for_field(column_name);
                         let inner = computer.segment_sort_key_computer(segment_reader)?;
@@ -281,6 +291,65 @@ mod tests {
         );
     }
 
+    #[test]
+    fn test_sort_by_owned_bytes() {
+        let mut schema_builder = Schema::builder();
+        let data_field = schema_builder.add_bytes_field("data", FAST);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut writer = index.writer_for_tests().unwrap();
+        writer
+            .add_document(doc!(data_field => vec![0x03u8, 0x00]))
+            .unwrap();
+        writer
+            .add_document(doc!(data_field => vec![0x01u8, 0x00]))
+            .unwrap();
+        writer
+            .add_document(doc!(data_field => vec![0x02u8, 0x00]))
+            .unwrap();
+        writer.add_document(doc!()).unwrap();
+        writer.commit().unwrap();
+
+        let reader = index.reader().unwrap();
+        let searcher = reader.searcher();
+
+        // Sort descending (Natural - highest first)
+        let collector = TopDocs::with_limit(10)
+            .order_by((SortByErasedType::for_field("data"), ComparatorEnum::Natural));
+        let top_docs = searcher.search(&AllQuery, &collector).unwrap();
+
+        let values: Vec<OwnedValue> = top_docs.into_iter().map(|(key, _)| key).collect();
+
+        assert_eq!(
+            values,
+            vec![
+                OwnedValue::Bytes(vec![0x03, 0x00]),
+                OwnedValue::Bytes(vec![0x02, 0x00]),
+                OwnedValue::Bytes(vec![0x01, 0x00]),
+                OwnedValue::Null
+            ]
+        );
+
+        // Sort ascending (ReverseNoneLower - lowest first, nulls last)
+        let collector = TopDocs::with_limit(10).order_by((
+            SortByErasedType::for_field("data"),
+            ComparatorEnum::ReverseNoneLower,
+        ));
+        let top_docs = searcher.search(&AllQuery, &collector).unwrap();
+
+        let values: Vec<OwnedValue> = top_docs.into_iter().map(|(key, _)| key).collect();
+
+        assert_eq!(
+            values,
+            vec![
+                OwnedValue::Bytes(vec![0x01, 0x00]),
+                OwnedValue::Bytes(vec![0x02, 0x00]),
+                OwnedValue::Bytes(vec![0x03, 0x00]),
+                OwnedValue::Null
+            ]
+        );
+    }
+
     #[test]
     fn test_sort_by_owned_reverse() {
         let mut schema_builder = Schema::builder();

src/collector/sort_key/sort_by_score.rs

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

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: &SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let sort_column_opt = segment_reader.fast_fields().u64_lenient(&self.field)?;
         let (sort_column, _sort_column_type) =

src/collector/sort_key/sort_by_string.rs

@@ -3,7 +3,7 @@ use columnar::StrColumn;
 use crate::collector::sort_key::NaturalComparator;
 use crate::collector::{SegmentSortKeyComputer, SortKeyComputer};
 use crate::termdict::TermOrdinal;
-use crate::{DocId, Score};
+use crate::{DocId, Score, SegmentReader};
 
 /// Sort by the first value of a string column.
 ///
@@ -35,7 +35,7 @@ impl SortKeyComputer for SortByString {
 
     fn segment_sort_key_computer(
         &self,
-        segment_reader: &crate::SegmentReader,
+        segment_reader: &dyn SegmentReader,
     ) -> crate::Result<Self::Child> {
         let str_column_opt = segment_reader.fast_fields().str(&self.column_name)?;
         Ok(ByStringColumnSegmentSortKeyComputer { str_column_opt })

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: &crate::SegmentReader,
+        reader: &dyn 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: &SegmentReader) -> Result<Self::Child>;
+    fn segment_sort_key_computer(&self, segment_reader: &dyn 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: &SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
         Ok((
             self.0.segment_sort_key_computer(segment_reader)?,
             self.1.segment_sort_key_computer(segment_reader)?,
@@ -357,7 +357,7 @@ where
         )
     }
 
-    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
         let sort_key_computer1 = self.0.segment_sort_key_computer(segment_reader)?;
         let sort_key_computer2 = self.1.segment_sort_key_computer(segment_reader)?;
         let sort_key_computer3 = self.2.segment_sort_key_computer(segment_reader)?;
@@ -420,7 +420,7 @@ where
         SortKeyComputer4::Comparator,
     );
 
-    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
         let sort_key_computer1 = self.0.segment_sort_key_computer(segment_reader)?;
         let sort_key_computer2 = self.1.segment_sort_key_computer(segment_reader)?;
         let sort_key_computer3 = self.2.segment_sort_key_computer(segment_reader)?;
@@ -454,7 +454,7 @@ where
 
 impl<F, SegmentF, TSortKey> SortKeyComputer for F
 where
-    F: 'static + Send + Sync + Fn(&SegmentReader) -> SegmentF,
+    F: 'static + Send + Sync + Fn(&dyn SegmentReader) -> SegmentF,
     SegmentF: 'static + FnMut(DocId) -> TSortKey,
     TSortKey: 'static + PartialOrd + Clone + Send + Sync + std::fmt::Debug,
 {
@@ -462,7 +462,7 @@ where
     type Child = SegmentF;
     type Comparator = NaturalComparator;
 
-    fn segment_sort_key_computer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn segment_sort_key_computer(&self, segment_reader: &dyn SegmentReader) -> Result<Self::Child> {
         Ok((self)(segment_reader))
     }
 }
@@ -509,10 +509,10 @@ mod tests {
 
     #[test]
     fn test_lazy_score_computer() {
-        let score_computer_primary = |_segment_reader: &SegmentReader| |_doc: DocId| 200u32;
+        let score_computer_primary = |_segment_reader: &dyn SegmentReader| |_doc: DocId| 200u32;
         let call_count = Arc::new(AtomicUsize::new(0));
         let call_count_clone = call_count.clone();
-        let score_computer_secondary = move |_segment_reader: &SegmentReader| {
+        let score_computer_secondary = move |_segment_reader: &dyn SegmentReader| {
             let call_count_new_clone = call_count_clone.clone();
             move |_doc: DocId| {
                 call_count_new_clone.fetch_add(1, AtomicOrdering::SeqCst);
@@ -572,10 +572,10 @@ mod tests {
 
     #[test]
     fn test_lazy_score_computer_dynamic_ordering() {
-        let score_computer_primary = |_segment_reader: &SegmentReader| |_doc: DocId| 200u32;
+        let score_computer_primary = |_segment_reader: &dyn SegmentReader| |_doc: DocId| 200u32;
         let call_count = Arc::new(AtomicUsize::new(0));
         let call_count_clone = call_count.clone();
-        let score_computer_secondary = move |_segment_reader: &SegmentReader| {
+        let score_computer_secondary = move |_segment_reader: &dyn SegmentReader| {
             let call_count_new_clone = call_count_clone.clone();
             move |_doc: DocId| {
                 call_count_new_clone.fetch_add(1, AtomicOrdering::SeqCst);

src/collector/sort_key_top_collector.rs

@@ -32,7 +32,11 @@ where TSortKeyComputer: SortKeyComputer + Send + Sync + 'static
         self.sort_key_computer.check_schema(schema)
     }
 
-    fn for_segment(&self, segment_ord: u32, segment_reader: &SegmentReader) -> Result<Self::Child> {
+    fn for_segment(
+        &self,
+        segment_ord: u32,
+        segment_reader: &dyn SegmentReader,
+    ) -> Result<Self::Child> {
         let segment_sort_key_computer = self
             .sort_key_computer
             .segment_sort_key_computer(segment_reader)?;
@@ -63,7 +67,7 @@ where TSortKeyComputer: SortKeyComputer + Send + Sync + 'static
         &self,
         weight: &dyn Weight,
         segment_ord: u32,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
     ) -> crate::Result<Vec<(TSortKeyComputer::SortKey, DocAddress)>> {
         let k = self.doc_range.end;
         let docs = self

src/collector/tests.rs

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

src/collector/top_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: &SegmentReader| {
+    ///          .tweak_score(move |segment_reader: &dyn 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(&SegmentReader) -> TTweakScoreSortKeyFn,
+    F: 'static + Send + Sync + Fn(&dyn 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: &SegmentReader,
+        segment_reader: &dyn 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: &SegmentReader| move |doc: DocId| doc);
+            .order_by(move |_segment_reader: &dyn SegmentReader| move |doc: DocId| doc);
         let score_docs: Vec<(u32, DocAddress)> =
             index.reader()?.searcher().search(&text_query, &collector)?;
         assert_eq!(
@@ -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: &SegmentReader| move |doc: DocId| doc);
+            .order_by(move |_segment_reader: &dyn SegmentReader| move |doc: DocId| doc);
         let score_docs: Vec<(u32, DocAddress)> = index
             .reader()
             .unwrap()

src/core/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

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

src/directory/mod.rs

@@ -21,7 +21,7 @@ use std::path::PathBuf;
 pub use common::file_slice::{FileHandle, FileSlice};
 pub use common::{AntiCallToken, OwnedBytes, TerminatingWrite};
 
-pub(crate) use self::composite_file::{CompositeFile, CompositeWrite};
+pub use self::composite_file::{CompositeFile, CompositeWrite};
 pub use self::directory::{Directory, DirectoryClone, DirectoryLock};
 pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
 pub use self::ram_directory::RamDirectory;
@@ -52,7 +52,7 @@ pub use self::mmap_directory::MmapDirectory;
 ///
 /// `WritePtr` are required to implement both Write
 /// and Seek.
-pub type WritePtr = BufWriter<Box<dyn TerminatingWrite>>;
+pub type WritePtr = BufWriter<Box<dyn TerminatingWrite + Send + Sync>>;
 
 #[cfg(test)]
 mod tests;

src/docset.rs

@@ -1,4 +1,7 @@
-use std::borrow::{Borrow, BorrowMut};
+use std::borrow::BorrowMut;
+use std::ops::{Deref as _, DerefMut as _};
+
+use common::BitSet;
 
 use crate::fastfield::AliveBitSet;
 use crate::DocId;
@@ -130,6 +133,19 @@ pub trait DocSet: Send {
         buffer.len()
     }
 
+    /// Fills the given bitset with the documents in the docset.
+    ///
+    /// If the docset max_doc is smaller than the largest doc, this function might not consume the
+    /// docset entirely.
+    fn fill_bitset(&mut self, bitset: &mut BitSet) {
+        let bitset_max_value: u32 = bitset.max_value();
+        let mut doc = self.doc();
+        while doc < bitset_max_value {
+            bitset.insert(doc);
+            doc = self.advance();
+        }
+    }
+
     /// Returns the current document
     /// Right after creating a new `DocSet`, the docset points to the first document.
     ///
@@ -233,51 +249,59 @@ impl DocSet for &mut dyn DocSet {
     fn count_including_deleted(&mut self) -> u32 {
         (**self).count_including_deleted()
     }
+
+    fn fill_bitset(&mut self, bitset: &mut BitSet) {
+        (**self).fill_bitset(bitset);
+    }
 }
 
 impl<TDocSet: DocSet + ?Sized> DocSet for Box<TDocSet> {
+    #[inline]
     fn advance(&mut self) -> DocId {
-        let unboxed: &mut TDocSet = self.borrow_mut();
-        unboxed.advance()
+        self.deref_mut().advance()
     }
 
+    #[inline]
     fn seek(&mut self, target: DocId) -> DocId {
-        let unboxed: &mut TDocSet = self.borrow_mut();
-        unboxed.seek(target)
+        self.deref_mut().seek(target)
     }
 
+    #[inline]
     fn seek_danger(&mut self, target: DocId) -> SeekDangerResult {
         let unboxed: &mut TDocSet = self.borrow_mut();
         unboxed.seek_danger(target)
     }
 
+    #[inline]
     fn fill_buffer(&mut self, buffer: &mut [DocId; COLLECT_BLOCK_BUFFER_LEN]) -> usize {
-        let unboxed: &mut TDocSet = self.borrow_mut();
-        unboxed.fill_buffer(buffer)
+        self.deref_mut().fill_buffer(buffer)
     }
 
+    #[inline]
     fn doc(&self) -> DocId {
-        let unboxed: &TDocSet = self.borrow();
-        unboxed.doc()
+        self.deref().doc()
     }
 
+    #[inline]
     fn size_hint(&self) -> u32 {
-        let unboxed: &TDocSet = self.borrow();
-        unboxed.size_hint()
+        self.deref().size_hint()
     }
 
+    #[inline]
     fn cost(&self) -> u64 {
-        let unboxed: &TDocSet = self.borrow();
-        unboxed.cost()
+        self.deref().cost()
     }
 
+    #[inline]
     fn count(&mut self, alive_bitset: &AliveBitSet) -> u32 {
-        let unboxed: &mut TDocSet = self.borrow_mut();
-        unboxed.count(alive_bitset)
+        self.deref_mut().count(alive_bitset)
     }
 
     fn count_including_deleted(&mut self) -> u32 {
-        let unboxed: &mut TDocSet = self.borrow_mut();
-        unboxed.count_including_deleted()
+        self.deref_mut().count_including_deleted()
+    }
+
+    fn fill_bitset(&mut self, bitset: &mut BitSet) {
+        self.deref_mut().fill_bitset(bitset);
     }
 }

src/fastfield/mod.rs

@@ -96,7 +96,7 @@ mod tests {
     };
     use crate::time::OffsetDateTime;
     use crate::tokenizer::{LowerCaser, RawTokenizer, TextAnalyzer, TokenizerManager};
-    use crate::{Index, IndexWriter, SegmentReader};
+    use crate::{Index, IndexWriter};
 
     pub static SCHEMA: Lazy<Schema> = Lazy::new(|| {
         let mut schema_builder = Schema::builder();
@@ -430,7 +430,7 @@ mod tests {
             .searcher()
             .segment_readers()
             .iter()
-            .map(SegmentReader::segment_id)
+            .map(|segment_reader| segment_reader.segment_id())
             .collect();
         assert_eq!(segment_ids.len(), 2);
         index_writer.merge(&segment_ids[..]).wait().unwrap();

src/index/codec_configuration.rs

@@ -0,0 +1,49 @@
+use std::borrow::Cow;
+
+use serde::{Deserialize, Serialize};
+
+use crate::codec::{Codec, StandardCodec};
+
+/// A Codec configuration is just a serializable object.
+#[derive(Serialize, Deserialize, Clone, Debug)]
+pub struct CodecConfiguration {
+    codec_id: Cow<'static, str>,
+    #[serde(default, skip_serializing_if = "serde_json::Value::is_null")]
+    props: serde_json::Value,
+}
+
+impl CodecConfiguration {
+    /// Returns true if the codec is the standard codec.
+    pub fn is_standard(&self) -> bool {
+        self.codec_id == StandardCodec::ID && self.props.is_null()
+    }
+
+    /// Creates a codec instance from the configuration.
+    ///
+    /// If the codec id does not match the code's name, an error is returned.
+    pub fn to_codec<C: Codec>(&self) -> crate::Result<C> {
+        if self.codec_id != C::ID {
+            return Err(crate::TantivyError::InvalidArgument(format!(
+                "Codec id mismatch: expected {}, got {}",
+                C::ID,
+                self.codec_id
+            )));
+        }
+        C::from_json_props(&self.props)
+    }
+}
+
+impl<'a, C: Codec> From<&'a C> for CodecConfiguration {
+    fn from(codec: &'a C) -> Self {
+        CodecConfiguration {
+            codec_id: Cow::Borrowed(C::ID),
+            props: codec.to_json_props(),
+        }
+    }
+}
+
+impl Default for CodecConfiguration {
+    fn default() -> Self {
+        CodecConfiguration::from(&StandardCodec)
+    }
+}

src/index/index.rs

@@ -8,12 +8,14 @@ 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::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 +26,6 @@ use crate::reader::{IndexReader, IndexReaderBuilder};
 use crate::schema::document::Document;
 use crate::schema::{Field, FieldType, Schema};
 use crate::tokenizer::{TextAnalyzer, TokenizerManager};
-use crate::SegmentReader;
 
 fn load_metas(
     directory: &dyn Directory,
@@ -59,6 +60,7 @@ fn save_new_metas(
     schema: Schema,
     index_settings: IndexSettings,
     directory: &dyn Directory,
+    codec: CodecConfiguration,
 ) -> crate::Result<()> {
     save_metas(
         &IndexMeta {
@@ -67,6 +69,7 @@ fn save_new_metas(
             schema,
             opstamp: 0u64,
             payload: None,
+            codec,
         },
         directory,
     )?;
@@ -101,18 +104,21 @@ 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 +126,21 @@ 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 +175,7 @@ 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 +186,7 @@ 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 +207,7 @@ 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 +223,7 @@ 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 +236,15 @@ 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 +268,25 @@ 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 +295,7 @@ 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 +303,7 @@ pub struct Index {
     tokenizers: TokenizerManager,
     fast_field_tokenizers: TokenizerManager,
     inventory: SegmentMetaInventory,
+    codec: Codec,
 }
 
 impl Index {
@@ -279,41 +311,6 @@ 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 +321,13 @@ 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 +374,108 @@ 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())
+    }
+
+    #[cfg(feature = "mmap")]
+    #[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 +578,15 @@ impl Index {
         let segments = self.searchable_segments()?;
         let fields_metadata: Vec<Vec<FieldMetadata>> = segments
             .into_iter()
-            .map(|segment| SegmentReader::open(&segment)?.fields_metadata())
+            .map(|segment| {
+                let segment_reader = segment.index().codec().open_segment_reader(
+                    segment.index().directory(),
+                    segment.meta(),
+                    segment.schema(),
+                    None,
+                )?;
+                segment_reader.fields_metadata()
+            })
             .collect::<Result<_, _>>()?;
         Ok(merge_field_meta_data(fields_metadata))
     }
@@ -506,16 +600,6 @@ 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 +623,7 @@ 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 +665,7 @@ 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 +679,7 @@ 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 +697,7 @@ 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 +724,7 @@ 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 +733,12 @@ 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);
@@ -708,7 +792,7 @@ impl Index {
 }
 
 impl fmt::Debug for Index {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         write!(f, "Index({:?})", self.directory)
     }
 }

src/index/index_meta.rs

@@ -5,7 +5,8 @@ use std::path::PathBuf;
 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};
@@ -286,8 +287,10 @@ 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.
+    #[serde(skip_serializing_if = "CodecConfiguration::is_standard")]
+    pub codec: CodecConfiguration,
 }
-
 #[derive(Deserialize, Debug)]
 struct UntrackedIndexMeta {
     pub segments: Vec<InnerSegmentMeta>,
@@ -297,6 +300,8 @@ struct UntrackedIndexMeta {
     pub opstamp: Opstamp,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub payload: Option<String>,
+    #[serde(default)]
+    pub codec: CodecConfiguration,
 }
 
 impl UntrackedIndexMeta {
@@ -311,6 +316,7 @@ impl UntrackedIndexMeta {
             schema: self.schema,
             opstamp: self.opstamp,
             payload: self.payload,
+            codec: self.codec,
         }
     }
 }
@@ -321,13 +327,14 @@ 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),
         }
     }
 
@@ -378,14 +385,38 @@ mod tests {
             schema,
             opstamp: 0u64,
             payload: None,
+            codec: Default::default(),
         };
-        let json = serde_json::ser::to_string(&index_metas).expect("serialization failed");
+        let json_value: serde_json::Value =
+            serde_json::to_value(&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}"#
+            &json_value,
+            &serde_json::json!(
+            {
+              "index_settings": {
+                "docstore_compression": "none",
+                "docstore_blocksize": 16384
+              },
+              "segments": [],
+              "schema": [
+                {
+                  "name": "text",
+                  "type": "text",
+                  "options": {
+                    "indexing": {
+                      "record": "position",
+                      "fieldnorms": true,
+                      "tokenizer": "default"
+                    },
+                    "stored": false,
+                    "fast": false
+                  }
+                }
+              ],
+              "opstamp": 0
+            })
         );
-
-        let deser_meta: UntrackedIndexMeta = serde_json::from_str(&json).unwrap();
+        let deser_meta: UntrackedIndexMeta = serde_json::from_value(json_value).unwrap();
         assert_eq!(index_metas.index_settings, deser_meta.index_settings);
         assert_eq!(index_metas.schema, deser_meta.schema);
         assert_eq!(index_metas.opstamp, deser_meta.opstamp);
@@ -411,14 +442,39 @@ mod tests {
             schema,
             opstamp: 0u64,
             payload: None,
+            codec: Default::default(),
         };
-        let json = serde_json::ser::to_string(&index_metas).expect("serialization failed");
+        let json_value = serde_json::to_value(&index_metas).expect("serialization failed");
         assert_eq!(
-            json,
-            r#"{"index_settings":{"docstore_compression":"zstd(compression_level=4)","docstore_blocksize":1000000},"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","fieldnorms":true,"tokenizer":"default"},"stored":false,"fast":false}}],"opstamp":0}"#
+            &json_value,
+            &serde_json::json!(
+                {
+                  "index_settings": {
+                    "docstore_compression": "zstd(compression_level=4)",
+                    "docstore_blocksize": 1000000
+                  },
+                  "segments": [],
+                  "schema": [
+                    {
+                      "name": "text",
+                      "type": "text",
+                      "options": {
+                        "indexing": {
+                          "record": "position",
+                          "fieldnorms": true,
+                          "tokenizer": "default"
+                        },
+                        "stored": false,
+                        "fast": false
+                      }
+                    }
+                  ],
+                  "opstamp": 0
+                }
+            )
         );
 
-        let deser_meta: UntrackedIndexMeta = serde_json::from_str(&json).unwrap();
+        let deser_meta: UntrackedIndexMeta = serde_json::from_value(json_value).unwrap();
         assert_eq!(index_metas.index_settings, deser_meta.index_settings);
         assert_eq!(index_metas.schema, deser_meta.schema);
         assert_eq!(index_metas.opstamp, deser_meta.opstamp);

src/index/inverted_index_reader.rs

@@ -1,7 +1,11 @@
+#[cfg(feature = "quickwit")]
+use std::future::Future;
 use std::io;
+#[cfg(feature = "quickwit")]
+use std::pin::Pin;
 
 use common::json_path_writer::JSON_END_OF_PATH;
-use common::{BinarySerializable, ByteCount};
+use common::{BinarySerializable, BitSet, ByteCount, OwnedBytes};
 #[cfg(feature = "quickwit")]
 use futures_util::{FutureExt, StreamExt, TryStreamExt};
 #[cfg(feature = "quickwit")]
@@ -9,25 +13,126 @@ use itertools::Itertools;
 #[cfg(feature = "quickwit")]
 use tantivy_fst::automaton::{AlwaysMatch, Automaton};
 
+use crate::codec::postings::RawPostingsData;
+use crate::codec::standard::postings::{
+    fill_bitset_from_raw_data, load_postings_from_raw_data, SegmentPostings,
+};
 use crate::directory::FileSlice;
-use crate::positions::PositionReader;
-use crate::postings::{BlockSegmentPostings, SegmentPostings, TermInfo};
+use crate::docset::DocSet;
+use crate::fieldnorm::FieldNormReader;
+use crate::postings::{Postings, TermInfo};
+use crate::query::term_query::TermScorer;
+use crate::query::{box_scorer, Bm25Weight, PhraseScorer, Scorer};
 use crate::schema::{IndexRecordOption, Term, Type};
 use crate::termdict::TermDictionary;
 
+/// Trait defining the contract for inverted index readers.
+pub trait InvertedIndexReader: Send + Sync {
+    /// Returns the term info associated with the term.
+    fn get_term_info(&self, term: &Term) -> io::Result<Option<TermInfo>> {
+        self.terms().get(term.serialized_value_bytes())
+    }
+
+    /// 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**.
+    fn list_encoded_json_fields(&self) -> io::Result<Vec<InvertedIndexFieldSpace>>;
+
+    /// Build a new term scorer.
+    fn new_term_scorer(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        fieldnorm_reader: FieldNormReader,
+        similarity_weight: Bm25Weight,
+    ) -> io::Result<Box<dyn Scorer>>;
+
+    /// 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<Box<dyn Postings>>;
+
+    /// Returns the raw postings bytes and metadata for a term.
+    fn read_raw_postings_data(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+    ) -> io::Result<RawPostingsData>;
+
+    /// Fills a bitset with documents containing the term.
+    ///
+    /// Implementers can override this to avoid boxing postings.
+    fn fill_bitset_for_term(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        doc_bitset: &mut BitSet,
+    ) -> io::Result<()> {
+        let mut postings = self.read_postings_from_terminfo(term_info, option)?;
+        postings.fill_bitset(doc_bitset);
+        Ok(())
+    }
+
+    /// Builds a phrase scorer for the given term infos.
+    fn new_phrase_scorer(
+        &self,
+        term_infos: &[(usize, TermInfo)],
+        similarity_weight: Option<Bm25Weight>,
+        fieldnorm_reader: FieldNormReader,
+        slop: u32,
+    ) -> io::Result<Box<dyn Scorer>>;
+
+    /// 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<Box<dyn Postings>>> {
+        self.get_term_info(term)?
+            .map(move |term_info| self.read_postings_from_terminfo(&term_info, option))
+            .transpose()
+    }
+
+    /// 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,
+    ) -> Pin<Box<dyn Future<Output = io::Result<u32>> + Send + 'a>>;
+}
+
+/// Tantivy's default inverted index reader implementation.
+///
 /// The inverted index reader is in charge of accessing
 /// the inverted index associated with a specific field.
 ///
 /// # Note
 ///
 /// It is safe to delete the segment associated with
-/// an `InvertedIndexReader`. As long as it is open,
+/// an `InvertedIndexReader` implementation. As long as it is open,
 /// the [`FileSlice`] it is relying on should
 /// stay available.
 ///
-/// `InvertedIndexReader` are created by calling
+/// `TantivyInvertedIndexReader` instances are created by calling
 /// [`SegmentReader::inverted_index()`](crate::SegmentReader::inverted_index).
-pub struct InvertedIndexReader {
+pub struct TantivyInvertedIndexReader {
     termdict: TermDictionary,
     postings_file_slice: FileSlice,
     positions_file_slice: FileSlice,
@@ -36,11 +141,16 @@ pub struct InvertedIndexReader {
 }
 
 /// Object that records the amount of space used by a field in an inverted index.
-pub(crate) struct InvertedIndexFieldSpace {
+pub struct InvertedIndexFieldSpace {
+    /// Field name as encoded in the term dictionary.
     pub field_name: String,
+    /// Value type for the encoded field.
     pub field_type: Type,
+    /// Total bytes used by postings for this field.
     pub postings_size: ByteCount,
+    /// Total bytes used by positions for this field.
     pub positions_size: ByteCount,
+    /// Number of terms in the field.
     pub num_terms: u64,
 }
 
@@ -62,16 +172,43 @@ impl InvertedIndexFieldSpace {
     }
 }
 
-impl InvertedIndexReader {
+impl TantivyInvertedIndexReader {
+    pub(crate) fn read_raw_postings_data_inner(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+    ) -> io::Result<RawPostingsData> {
+        let effective_option = option.downgrade(self.record_option);
+        let postings_data = self
+            .postings_file_slice
+            .slice(term_info.postings_range.clone())
+            .read_bytes()?;
+        let positions_data: Option<OwnedBytes> = if effective_option.has_positions() {
+            let positions_data = self
+                .positions_file_slice
+                .slice(term_info.positions_range.clone())
+                .read_bytes()?;
+            Some(positions_data)
+        } else {
+            None
+        };
+        Ok(RawPostingsData {
+            postings_data,
+            positions_data,
+            record_option: self.record_option,
+            effective_option,
+        })
+    }
+
     pub(crate) fn new(
         termdict: TermDictionary,
         postings_file_slice: FileSlice,
         positions_file_slice: FileSlice,
         record_option: IndexRecordOption,
-    ) -> io::Result<InvertedIndexReader> {
+    ) -> io::Result<TantivyInvertedIndexReader> {
         let (total_num_tokens_slice, postings_body) = postings_file_slice.split(8);
         let total_num_tokens = u64::deserialize(&mut total_num_tokens_slice.read_bytes()?)?;
-        Ok(InvertedIndexReader {
+        Ok(TantivyInvertedIndexReader {
             termdict,
             postings_file_slice: postings_body,
             positions_file_slice,
@@ -80,10 +217,10 @@ impl InvertedIndexReader {
         })
     }
 
-    /// Creates an empty `InvertedIndexReader` object, which
+    /// Creates an empty `TantivyInvertedIndexReader` object, which
     /// contains no terms at all.
-    pub fn empty(record_option: IndexRecordOption) -> InvertedIndexReader {
-        InvertedIndexReader {
+    pub fn empty(record_option: IndexRecordOption) -> TantivyInvertedIndexReader {
+        TantivyInvertedIndexReader {
             termdict: TermDictionary::empty(),
             postings_file_slice: FileSlice::empty(),
             positions_file_slice: FileSlice::empty(),
@@ -92,22 +229,22 @@ impl InvertedIndexReader {
         }
     }
 
-    /// Returns the term info associated with the term.
-    pub fn get_term_info(&self, term: &Term) -> io::Result<Option<TermInfo>> {
-        self.termdict.get(term.serialized_value_bytes())
+    fn load_segment_postings(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+    ) -> io::Result<SegmentPostings> {
+        let postings_data = self.read_raw_postings_data_inner(term_info, option)?;
+        load_postings_from_raw_data(term_info.doc_freq, postings_data)
     }
+}
 
-    /// Return the term dictionary datastructure.
-    pub fn terms(&self) -> &TermDictionary {
+impl InvertedIndexReader for TantivyInvertedIndexReader {
+    fn terms(&self) -> &TermDictionary {
         &self.termdict
     }
 
-    /// 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.
-    pub(crate) fn list_encoded_json_fields(&self) -> io::Result<Vec<InvertedIndexFieldSpace>> {
+    fn list_encoded_json_fields(&self) -> io::Result<Vec<InvertedIndexFieldSpace>> {
         let mut stream = self.termdict.stream()?;
         let mut fields: Vec<InvertedIndexFieldSpace> = Vec::new();
 
@@ -160,129 +297,106 @@ impl InvertedIndexReader {
         Ok(fields)
     }
 
-    /// Resets the block segment to another position of the postings
-    /// file.
-    ///
-    /// This is useful for enumerating through a list of terms,
-    /// and consuming the associated posting lists while avoiding
-    /// reallocating a [`BlockSegmentPostings`].
-    ///
-    /// # Warning
-    ///
-    /// This does not reset the positions list.
-    pub fn reset_block_postings_from_terminfo(
+    fn new_term_scorer(
         &self,
         term_info: &TermInfo,
-        block_postings: &mut BlockSegmentPostings,
+        option: IndexRecordOption,
+        fieldnorm_reader: FieldNormReader,
+        similarity_weight: Bm25Weight,
+    ) -> io::Result<Box<dyn Scorer>> {
+        let postings = self.load_segment_postings(term_info, option)?;
+        let term_scorer = TermScorer::new(postings, fieldnorm_reader, similarity_weight);
+        Ok(box_scorer(term_scorer))
+    }
+
+    fn read_postings_from_terminfo(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+    ) -> io::Result<Box<dyn Postings>> {
+        let postings = self.load_segment_postings(term_info, option)?;
+        Ok(Box::new(postings))
+    }
+
+    fn read_raw_postings_data(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+    ) -> io::Result<RawPostingsData> {
+        self.read_raw_postings_data_inner(term_info, option)
+    }
+
+    fn fill_bitset_for_term(
+        &self,
+        term_info: &TermInfo,
+        option: IndexRecordOption,
+        doc_bitset: &mut BitSet,
     ) -> io::Result<()> {
-        let postings_slice = self
-            .postings_file_slice
-            .slice(term_info.postings_range.clone());
-        let postings_bytes = postings_slice.read_bytes()?;
-        block_postings.reset(term_info.doc_freq, postings_bytes)?;
-        Ok(())
+        let postings_data = self.read_raw_postings_data_inner(term_info, option)?;
+        fill_bitset_from_raw_data(term_info.doc_freq, postings_data, doc_bitset)
     }
 
-    /// 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(
+    fn new_phrase_scorer(
         &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()
+        term_infos: &[(usize, TermInfo)],
+        similarity_weight: Option<Bm25Weight>,
+        fieldnorm_reader: FieldNormReader,
+        slop: u32,
+    ) -> io::Result<Box<dyn Scorer>> {
+        let mut offset_and_term_postings: Vec<(usize, SegmentPostings)> =
+            Vec::with_capacity(term_infos.len());
+        for (offset, term_info) in term_infos {
+            let postings =
+                self.load_segment_postings(term_info, IndexRecordOption::WithFreqsAndPositions)?;
+            offset_and_term_postings.push((*offset, postings));
+        }
+        let scorer = PhraseScorer::new(
+            offset_and_term_postings,
+            similarity_weight,
+            fieldnorm_reader,
+            slop,
+        );
+        Ok(box_scorer(scorer))
     }
 
-    /// 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(
-        &self,
-        term_info: &TermInfo,
-        requested_option: IndexRecordOption,
-    ) -> io::Result<BlockSegmentPostings> {
-        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,
-        )
-    }
-
-    /// 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.
-    pub fn read_postings_from_terminfo(
-        &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,
-        ))
-    }
-
-    /// Returns the total number of tokens recorded for all documents
-    /// (including deleted documents).
-    pub fn total_num_tokens(&self) -> u64 {
+    fn total_num_tokens(&self) -> u64 {
         self.total_num_tokens
     }
 
-    /// Returns the segment postings associated with the term, and with the given option,
-    /// or `None` if the term has never been encountered and indexed.
-    ///
-    /// If the field was not indexed with the indexing options that cover
-    /// the requested options, the returned [`SegmentPostings`] the method does not fail
-    /// and returns a `SegmentPostings` with as much information as possible.
-    ///
-    /// For instance, requesting [`IndexRecordOption::WithFreqs`] for a
-    /// [`TextOptions`](crate::schema::TextOptions) that does not index position
-    /// will return a [`SegmentPostings`] with `DocId`s and frequencies.
-    pub fn read_postings(
+    fn read_postings(
         &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()
     }
 
-    /// Returns the number of documents containing the term.
-    pub fn doc_freq(&self, term: &Term) -> io::Result<u32> {
+    fn doc_freq(&self, term: &Term) -> io::Result<u32> {
         Ok(self
             .get_term_info(term)?
             .map(|term_info| term_info.doc_freq)
             .unwrap_or(0u32))
     }
+
+    #[cfg(feature = "quickwit")]
+    fn doc_freq_async<'a>(
+        &'a self,
+        term: &'a Term,
+    ) -> Pin<Box<dyn Future<Output = io::Result<u32>> + Send + 'a>> {
+        Box::pin(async move {
+            Ok(self
+                .get_term_info_async(term)
+                .await?
+                .map(|term_info| term_info.doc_freq)
+                .unwrap_or(0u32))
+        })
+    }
 }
 
 #[cfg(feature = "quickwit")]
-impl InvertedIndexReader {
+impl TantivyInvertedIndexReader {
     pub(crate) async fn get_term_info_async(&self, term: &Term) -> io::Result<Option<TermInfo>> {
         self.termdict.get_async(term.serialized_value_bytes()).await
     }
@@ -482,13 +596,4 @@ impl InvertedIndexReader {
         }
         Ok(())
     }
-
-    /// Returns the number of documents containing the term asynchronously.
-    pub async fn doc_freq_async(&self, term: &Term) -> io::Result<u32> {
-        Ok(self
-            .get_term_info_async(term)
-            .await?
-            .map(|term_info| term_info.doc_freq)
-            .unwrap_or(0u32))
-    }
 }

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;
@@ -10,11 +11,14 @@ 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::InvertedIndexReader;
+pub use self::inverted_index_reader::{
+    InvertedIndexFieldSpace, InvertedIndexReader, TantivyInvertedIndexReader,
+};
 pub use self::segment::Segment;
 pub use self::segment_component::SegmentComponent;
 pub use self::segment_id::SegmentId;
-pub use self::segment_reader::{FieldMetadata, SegmentReader};
+pub use self::segment_reader::{FieldMetadata, SegmentReader, TantivySegmentReader};

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_id.rs

@@ -44,7 +44,7 @@ fn create_uuid() -> Uuid {
 }
 
 impl SegmentId {
-    #[doc(hidden)]
+    /// Generates a new random `SegmentId`.
     pub fn generate_random() -> SegmentId {
         SegmentId(create_uuid())
     }

src/index/segment_reader.rs

@@ -6,17 +6,99 @@ use common::{ByteCount, HasLen};
 use fnv::FnvHashMap;
 use itertools::Itertools;
 
-use crate::directory::{CompositeFile, FileSlice};
+use crate::codec::{ObjectSafeCodec, SumOrDoNothingCombiner};
+use crate::directory::{CompositeFile, Directory, FileSlice};
 use crate::error::DataCorruption;
 use crate::fastfield::{intersect_alive_bitsets, AliveBitSet, FacetReader, FastFieldReaders};
 use crate::fieldnorm::{FieldNormReader, FieldNormReaders};
-use crate::index::{InvertedIndexReader, Segment, SegmentComponent, SegmentId};
+use crate::index::{
+    InvertedIndexReader, Segment, SegmentComponent, SegmentId, SegmentMeta,
+    TantivyInvertedIndexReader,
+};
 use crate::json_utils::json_path_sep_to_dot;
+use crate::query::Scorer;
 use crate::schema::{Field, IndexRecordOption, Schema, Type};
 use crate::space_usage::SegmentSpaceUsage;
 use crate::store::StoreReader;
 use crate::termdict::TermDictionary;
-use crate::{DocId, Opstamp};
+use crate::{DocId, Opstamp, Score};
+
+/// Trait defining the contract for a segment reader.
+pub trait SegmentReader: Send + Sync {
+    /// Returns the highest document id ever attributed in this segment + 1.
+    fn max_doc(&self) -> DocId;
+
+    /// Returns the 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;
+
+    /// Performs a for_each_pruning operation on the given scorer.
+    fn for_each_pruning(
+        &self,
+        threshold: Score,
+        scorer: Box<dyn Scorer>,
+        callback: &mut dyn FnMut(DocId, Score) -> Score,
+    );
+
+    /// Builds a union scorer possibly specialized if all scorers are term scorers.
+    fn build_union_scorer_with_sum_combiner(
+        &self,
+        scorers: Vec<Box<dyn Scorer>>,
+        num_docs: DocId,
+        score_combiner_type: SumOrDoNothingCombiner,
+    ) -> Box<dyn Scorer>;
+
+    /// Return the number of documents that have been deleted in the segment.
+    fn num_deleted_docs(&self) -> DocId;
+
+    /// Returns true if some of the documents of the segment have been deleted.
+    fn has_deletes(&self) -> bool;
+
+    /// Accessor to a segment's fast field reader given a field.
+    fn fast_fields(&self) -> &FastFieldReaders;
+
+    /// Accessor to the `FacetReader` associated with a given `Field`.
+    fn facet_reader(&self, field_name: &str) -> crate::Result<FacetReader>;
+
+    /// Accessor to the segment's `Field norms`'s reader.
+    fn get_fieldnorms_reader(&self, field: Field) -> crate::Result<FieldNormReader>;
+
+    /// Accessor to the segment's field norms readers.
+    #[doc(hidden)]
+    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<Arc<dyn InvertedIndexReader>>;
+
+    /// 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;
+
+    /// Returns an iterator that will iterate over the alive document ids.
+    fn doc_ids_alive(&self) -> Box<dyn Iterator<Item = DocId> + Send + '_>;
+
+    /// Summarize total space usage of this segment.
+    fn space_usage(&self) -> io::Result<SegmentSpaceUsage>;
+
+    /// Clones this reader into a shared trait object.
+    fn clone_arc(&self) -> Arc<dyn SegmentReader>;
+}
 
 /// Entry point to access all of the datastructures of the `Segment`
 ///
@@ -29,8 +111,8 @@ use crate::{DocId, Opstamp};
 /// The segment reader has a very low memory footprint,
 /// as close to all of the memory data is mmapped.
 #[derive(Clone)]
-pub struct SegmentReader {
-    inv_idx_reader_cache: Arc<RwLock<HashMap<Field, Arc<InvertedIndexReader>>>>,
+pub struct TantivySegmentReader {
+    inv_idx_reader_cache: Arc<RwLock<HashMap<Field, Arc<dyn InvertedIndexReader>>>>,
 
     segment_id: SegmentId,
     delete_opstamp: Option<Opstamp>,
@@ -47,75 +129,162 @@ pub struct SegmentReader {
     store_file: FileSlice,
     alive_bitset_opt: Option<AliveBitSet>,
     schema: Schema,
+    codec: Arc<dyn ObjectSafeCodec>,
 }
 
-impl SegmentReader {
-    /// Returns the highest document id ever attributed in
-    /// this segment + 1.
-    pub fn max_doc(&self) -> DocId {
+impl TantivySegmentReader {
+    /// Open a new segment for reading.
+    pub fn open<C: crate::codec::Codec>(
+        segment: &Segment<C>,
+    ) -> crate::Result<Arc<dyn SegmentReader>> {
+        Self::open_with_custom_alive_set(segment, None)
+    }
+
+    /// Open a new segment for reading.
+    pub fn open_with_custom_alive_set<C: crate::codec::Codec>(
+        segment: &Segment<C>,
+        custom_bitset: Option<AliveBitSet>,
+    ) -> crate::Result<Arc<dyn SegmentReader>> {
+        segment.index().codec().open_segment_reader(
+            segment.index().directory(),
+            segment.meta(),
+            segment.schema(),
+            custom_bitset,
+        )
+    }
+
+    pub(crate) fn open_with_custom_alive_set_from_directory(
+        directory: &dyn Directory,
+        segment_meta: &SegmentMeta,
+        schema: Schema,
+        codec: Arc<dyn ObjectSafeCodec>,
+        custom_bitset: Option<AliveBitSet>,
+    ) -> crate::Result<TantivySegmentReader> {
+        let termdict_file =
+            directory.open_read(&segment_meta.relative_path(SegmentComponent::Terms))?;
+        let termdict_composite = CompositeFile::open(&termdict_file)?;
+
+        let store_file =
+            directory.open_read(&segment_meta.relative_path(SegmentComponent::Store))?;
+
+        crate::fail_point!("SegmentReader::open#middle");
+
+        let postings_file =
+            directory.open_read(&segment_meta.relative_path(SegmentComponent::Postings))?;
+        let postings_composite = CompositeFile::open(&postings_file)?;
+
+        let positions_composite = {
+            if let Ok(positions_file) =
+                directory.open_read(&segment_meta.relative_path(SegmentComponent::Positions))
+            {
+                CompositeFile::open(&positions_file)?
+            } else {
+                CompositeFile::empty()
+            }
+        };
+
+        let fast_fields_data =
+            directory.open_read(&segment_meta.relative_path(SegmentComponent::FastFields))?;
+        let fast_fields_readers = FastFieldReaders::open(fast_fields_data, schema.clone())?;
+        let fieldnorm_data =
+            directory.open_read(&segment_meta.relative_path(SegmentComponent::FieldNorms))?;
+        let fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)?;
+
+        let original_bitset = if segment_meta.has_deletes() {
+            let alive_doc_file_slice =
+                directory.open_read(&segment_meta.relative_path(SegmentComponent::Delete))?;
+            let alive_doc_data = alive_doc_file_slice.read_bytes()?;
+            Some(AliveBitSet::open(alive_doc_data))
+        } else {
+            None
+        };
+
+        let alive_bitset_opt = intersect_alive_bitset(original_bitset, custom_bitset);
+
+        let max_doc = segment_meta.max_doc();
+        let num_docs = alive_bitset_opt
+            .as_ref()
+            .map(|alive_bitset| alive_bitset.num_alive_docs() as u32)
+            .unwrap_or(max_doc);
+
+        Ok(TantivySegmentReader {
+            inv_idx_reader_cache: Default::default(),
+            num_docs,
+            max_doc,
+            termdict_composite,
+            postings_composite,
+            fast_fields_readers,
+            fieldnorm_readers,
+            segment_id: segment_meta.id(),
+            delete_opstamp: segment_meta.delete_opstamp(),
+            store_file,
+            alive_bitset_opt,
+            positions_composite,
+            schema,
+            codec,
+        })
+    }
+}
+
+impl SegmentReader for TantivySegmentReader {
+    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 {
+    fn num_docs(&self) -> DocId {
         self.num_docs
     }
 
-    /// Returns the schema of the index this segment belongs to.
-    pub fn schema(&self) -> &Schema {
+    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 {
+    fn for_each_pruning(
+        &self,
+        threshold: Score,
+        scorer: Box<dyn Scorer>,
+        callback: &mut dyn FnMut(DocId, Score) -> Score,
+    ) {
+        self.codec.for_each_pruning(threshold, scorer, callback);
+    }
+
+    fn build_union_scorer_with_sum_combiner(
+        &self,
+        scorers: Vec<Box<dyn Scorer>>,
+        num_docs: DocId,
+        score_combiner_type: SumOrDoNothingCombiner,
+    ) -> Box<dyn Scorer> {
+        self.codec
+            .build_union_scorer_with_sum_combiner(scorers, num_docs, score_combiner_type)
+    }
+
+    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
+    fn has_deletes(&self) -> bool {
+        self.num_docs != self.max_doc
     }
 
-    /// 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 {
+    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);
+    fn facet_reader(&self, field_name: &str) -> crate::Result<FacetReader> {
+        let field = self.schema.get_field(field_name)?;
+        let field_entry = self.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 {
+        let Some(facet_column) = self.fast_fields_readers.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> {
+    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!(
@@ -126,100 +295,15 @@ impl SegmentReader {
         })
     }
 
-    #[doc(hidden)]
-    pub fn fieldnorms_readers(&self) -> &FieldNormReaders {
+    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> {
+    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<SegmentReader> {
-        Self::open_with_custom_alive_set(segment, None)
-    }
-
-    /// Open a new segment for reading.
-    pub fn open_with_custom_alive_set(
-        segment: &Segment,
-        custom_bitset: Option<AliveBitSet>,
-    ) -> crate::Result<SegmentReader> {
-        let termdict_file = segment.open_read(SegmentComponent::Terms)?;
-        let termdict_composite = CompositeFile::open(&termdict_file)?;
-
-        let store_file = segment.open_read(SegmentComponent::Store)?;
-
-        crate::fail_point!("SegmentReader::open#middle");
-
-        let postings_file = segment.open_read(SegmentComponent::Postings)?;
-        let postings_composite = CompositeFile::open(&postings_file)?;
-
-        let positions_composite = {
-            if let Ok(positions_file) = segment.open_read(SegmentComponent::Positions) {
-                CompositeFile::open(&positions_file)?
-            } else {
-                CompositeFile::empty()
-            }
-        };
-
-        let schema = segment.schema();
-
-        let fast_fields_data = segment.open_read(SegmentComponent::FastFields)?;
-        let fast_fields_readers = FastFieldReaders::open(fast_fields_data, schema.clone())?;
-        let fieldnorm_data = segment.open_read(SegmentComponent::FieldNorms)?;
-        let fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)?;
-
-        let original_bitset = if segment.meta().has_deletes() {
-            let alive_doc_file_slice = segment.open_read(SegmentComponent::Delete)?;
-            let alive_doc_data = alive_doc_file_slice.read_bytes()?;
-            Some(AliveBitSet::open(alive_doc_data))
-        } else {
-            None
-        };
-
-        let alive_bitset_opt = intersect_alive_bitset(original_bitset, custom_bitset);
-
-        let max_doc = segment.meta().max_doc();
-        let num_docs = alive_bitset_opt
-            .as_ref()
-            .map(|alive_bitset| alive_bitset.num_alive_docs() as u32)
-            .unwrap_or(max_doc);
-
-        Ok(SegmentReader {
-            inv_idx_reader_cache: Default::default(),
-            num_docs,
-            max_doc,
-            termdict_composite,
-            postings_composite,
-            fast_fields_readers,
-            fieldnorm_readers,
-            segment_id: segment.id(),
-            delete_opstamp: segment.meta().delete_opstamp(),
-            store_file,
-            alive_bitset_opt,
-            positions_composite,
-            schema,
-        })
-    }
-
-    /// Returns a field reader associated with the field given in argument.
-    /// If the field was not present in the index during indexing time,
-    /// the InvertedIndexReader is empty.
-    ///
-    /// The field reader is in charge of iterating through the
-    /// term dictionary associated with a specific field,
-    /// and opening the posting list associated with any term.
-    ///
-    /// If the field is not marked as index, a warning is logged and an empty `InvertedIndexReader`
-    /// is returned.
-    /// Similarly, if the field is marked as indexed but no term has been indexed for the given
-    /// index, an empty `InvertedIndexReader` is returned (but no warning is logged).
-    pub fn inverted_index(&self, field: Field) -> crate::Result<Arc<InvertedIndexReader>> {
+    fn inverted_index(&self, field: Field) -> crate::Result<Arc<dyn InvertedIndexReader>> {
         if let Some(inv_idx_reader) = self
             .inv_idx_reader_cache
             .read()
@@ -244,7 +328,9 @@ impl SegmentReader {
             //
             // Returns an empty inverted index.
             let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);
-            return Ok(Arc::new(InvertedIndexReader::empty(record_option)));
+            let inv_idx_reader: Arc<dyn InvertedIndexReader> =
+                Arc::new(TantivyInvertedIndexReader::empty(record_option));
+            return Ok(inv_idx_reader);
         }
 
         let record_option = record_option_opt.unwrap();
@@ -268,12 +354,13 @@ impl SegmentReader {
             DataCorruption::comment_only(error_msg)
         })?;
 
-        let inv_idx_reader = Arc::new(InvertedIndexReader::new(
-            TermDictionary::open(termdict_file)?,
-            postings_file,
-            positions_file,
-            record_option,
-        )?);
+        let inv_idx_reader: Arc<dyn InvertedIndexReader> =
+            Arc::new(TantivyInvertedIndexReader::new(
+                TermDictionary::open(termdict_file)?,
+                postings_file,
+                positions_file,
+                record_option,
+            )?);
 
         // by releasing the lock in between, we may end up opening the inverting index
         // twice, but this is fine.
@@ -285,23 +372,10 @@ impl SegmentReader {
         Ok(inv_idx_reader)
     }
 
-    /// Returns the list of fields that have been indexed in the segment.
-    /// The field list includes the field defined in the schema as well as the fields
-    /// that have been indexed as a part of a JSON field.
-    /// The returned field name is the full field name, including the name of the JSON field.
-    ///
-    /// The returned field names can be used in queries.
-    ///
-    /// Notice: If your data contains JSON fields this is **very expensive**, as it requires
-    /// browsing through the inverted index term dictionary and the columnar field dictionary.
-    ///
-    /// Disclaimer: Some fields may not be listed here. For instance, if the schema contains a json
-    /// field that is not indexed nor a fast field but is stored, it is possible for the field
-    /// to not be listed.
-    pub fn fields_metadata(&self) -> crate::Result<Vec<FieldMetadata>> {
+    fn fields_metadata(&self) -> crate::Result<Vec<FieldMetadata>> {
         let mut indexed_fields: Vec<FieldMetadata> = Vec::new();
         let mut map_to_canonical = FnvHashMap::default();
-        for (field, field_entry) in self.schema().fields() {
+        for (field, field_entry) in self.schema.fields() {
             let field_name = field_entry.name().to_string();
             let is_indexed = field_entry.is_indexed();
             if is_indexed {
@@ -391,7 +465,7 @@ impl SegmentReader {
             }
         }
         let fast_fields: Vec<FieldMetadata> = self
-            .fast_fields()
+            .fast_fields_readers
             .columnar()
             .iter_columns()?
             .map(|(mut field_name, handle)| {
@@ -419,31 +493,26 @@ impl SegmentReader {
         Ok(merged_field_metadatas)
     }
 
-    /// Returns the segment id
-    pub fn segment_id(&self) -> SegmentId {
+    fn segment_id(&self) -> SegmentId {
         self.segment_id
     }
 
-    /// Returns the delete opstamp
-    pub fn delete_opstamp(&self) -> Option<Opstamp> {
+    fn delete_opstamp(&self) -> Option<Opstamp> {
         self.delete_opstamp
     }
 
-    /// Returns the bitset representing the alive `DocId`s.
-    pub fn alive_bitset(&self) -> Option<&AliveBitSet> {
+    fn alive_bitset(&self) -> Option<&AliveBitSet> {
         self.alive_bitset_opt.as_ref()
     }
 
-    /// Returns true if the `doc` is marked
-    /// as deleted.
-    pub fn is_deleted(&self, doc: DocId) -> bool {
-        self.alive_bitset()
+    fn is_deleted(&self, doc: DocId) -> bool {
+        self.alive_bitset_opt
+            .as_ref()
             .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 + '_> {
+    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 {
@@ -451,22 +520,25 @@ impl SegmentReader {
         }
     }
 
-    /// Summarize total space usage of this segment.
-    pub fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
+    fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
         Ok(SegmentSpaceUsage::new(
-            self.num_docs(),
-            self.termdict_composite.space_usage(self.schema()),
-            self.postings_composite.space_usage(self.schema()),
-            self.positions_composite.space_usage(self.schema()),
+            self.num_docs,
+            self.termdict_composite.space_usage(&self.schema),
+            self.postings_composite.space_usage(&self.schema),
+            self.positions_composite.space_usage(&self.schema),
             self.fast_fields_readers.space_usage()?,
-            self.fieldnorm_readers.space_usage(self.schema()),
-            self.get_store_reader(0)?.space_usage(),
+            self.fieldnorm_readers.space_usage(&self.schema),
+            StoreReader::open(self.store_file.clone(), 0)?.space_usage(),
             self.alive_bitset_opt
                 .as_ref()
                 .map(AliveBitSet::space_usage)
                 .unwrap_or_default(),
         ))
     }
+
+    fn clone_arc(&self) -> Arc<dyn SegmentReader> {
+        Arc::new(self.clone())
+    }
 }
 
 #[derive(Clone, Debug, PartialEq, Eq, PartialOrd, Ord)]
@@ -576,7 +648,7 @@ fn intersect_alive_bitset(
     }
 }
 
-impl fmt::Debug for SegmentReader {
+impl fmt::Debug for TantivySegmentReader {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         write!(f, "SegmentReader({:?})", self.segment_id)
     }

src/indexer/delete_queue.rs

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

src/indexer/index_writer.rs

@@ -9,6 +9,7 @@ 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;
@@ -68,12 +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,
 
@@ -82,7 +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,
 
@@ -94,7 +95,7 @@ pub struct IndexWriter<D: Document = TantivyDocument> {
 
 fn compute_deleted_bitset(
     alive_bitset: &mut BitSet,
-    segment_reader: &SegmentReader,
+    segment_reader: &dyn SegmentReader,
     delete_cursor: &mut DeleteCursor,
     doc_opstamps: &DocToOpstampMapping,
     target_opstamp: Opstamp,
@@ -128,8 +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<()> {
@@ -143,7 +144,12 @@ pub fn advance_deletes(
         return Ok(());
     }
 
-    let segment_reader = SegmentReader::open(&segment)?;
+    let segment_reader = segment.index().codec().open_segment_reader(
+        segment.index().directory(),
+        segment.meta(),
+        segment.schema(),
+        None,
+    )?;
 
     let max_doc = segment_reader.max_doc();
     let mut alive_bitset: BitSet = match segment_entry.alive_bitset() {
@@ -155,7 +161,7 @@ pub fn advance_deletes(
 
     compute_deleted_bitset(
         &mut alive_bitset,
-        &segment_reader,
+        segment_reader.as_ref(),
         segment_entry.delete_cursor(),
         &DocToOpstampMapping::None,
         target_opstamp,
@@ -179,11 +185,11 @@ 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())?;
@@ -226,8 +232,8 @@ 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>> {
@@ -243,14 +249,19 @@ fn apply_deletes(
         .max()
         .expect("Empty DocOpstamp is forbidden");
 
-    let segment_reader = SegmentReader::open(segment)?;
+    let segment_reader = segment.index().codec().open_segment_reader(
+        segment.index().directory(),
+        segment.meta(),
+        segment.schema(),
+        None,
+    )?;
     let doc_to_opstamps = DocToOpstampMapping::WithMap(doc_opstamps);
 
     let max_doc = segment.meta().max_doc();
     let mut deleted_bitset = BitSet::with_max_value_and_full(max_doc);
     let may_have_deletes = compute_deleted_bitset(
         &mut deleted_bitset,
-        &segment_reader,
+        segment_reader.as_ref(),
         delete_cursor,
         &doc_to_opstamps,
         max_doc_opstamp,
@@ -262,7 +273,7 @@ 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
@@ -278,7 +289,7 @@ 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> {
@@ -345,7 +356,7 @@ impl<D: Document> IndexWriter<D> {
     }
 
     /// Accessor to the index.
-    pub fn index(&self) -> &Index {
+    pub fn index(&self) -> &Index<C> {
         &self.index
     }
 
@@ -393,7 +404,7 @@ 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()
     }
 
@@ -615,7 +626,7 @@ 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.
@@ -665,7 +676,7 @@ 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
     }
 
@@ -804,7 +815,7 @@ 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

@@ -3,7 +3,7 @@ mod tests {
     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 +121,32 @@ 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 mut postings = inverted_index
-                .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
-                .unwrap()
-                .unwrap();
-            assert_eq!(postings.doc_freq(), 2);
+            let term_info = inverted_index.get_term_info(&term_a).unwrap().unwrap();
+            let typed_postings = crate::codec::Codec::load_postings_typed(
+                index.codec(),
+                inverted_index.as_ref(),
+                &term_info,
+                IndexRecordOption::WithFreqsAndPositions,
+            )
+            .unwrap();
             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(
+                    &typed_postings,
                     segment_reader.alive_bitset().unwrap_or(&fallback_bitset)
                 ),
                 2
             );
+            let mut postings = inverted_index
+                .read_postings_from_terminfo(&term_info, IndexRecordOption::WithFreqsAndPositions)
+                .unwrap();
+            assert_eq!(postings.doc_freq(), DocFreq::Exact(2));
+            let mut postings = inverted_index
+                .read_postings_from_terminfo(&term_info, IndexRecordOption::WithFreqsAndPositions)
+                .unwrap();
 
             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::io;
+use std::marker::PhantomData;
 use std::sync::Arc;
 
 use columnar::{
@@ -7,6 +9,8 @@ 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;
@@ -15,8 +19,8 @@ use crate::fieldnorm::{FieldNormReader, FieldNormReaders, FieldNormsSerializer,
 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::schema::{value_type_to_column_type, Field, FieldType, Schema};
+use crate::postings::{InvertedIndexSerializer, Postings, TermInfo};
+use crate::schema::{value_type_to_column_type, Field, FieldType, IndexRecordOption, Schema};
 use crate::store::StoreWriter;
 use crate::termdict::{TermMerger, TermOrdinal};
 use crate::{DocAddress, DocId, InvertedIndexReader};
@@ -27,7 +31,7 @@ use crate::{DocAddress, DocId, InvertedIndexReader};
 pub const MAX_DOC_LIMIT: u32 = 1 << 31;
 
 fn estimate_total_num_tokens_in_single_segment(
-    reader: &SegmentReader,
+    reader: &dyn SegmentReader,
     field: Field,
 ) -> crate::Result<u64> {
     // There are no deletes. We can simply use the exact value saved into the posting list.
@@ -68,18 +72,23 @@ fn estimate_total_num_tokens_in_single_segment(
     Ok((segment_num_tokens as f64 * ratio) as u64)
 }
 
-fn estimate_total_num_tokens(readers: &[SegmentReader], field: Field) -> crate::Result<u64> {
+fn estimate_total_num_tokens(
+    readers: &[Arc<dyn 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)?;
+        total_num_tokens += estimate_total_num_tokens_in_single_segment(reader.as_ref(), field)?;
     }
     Ok(total_num_tokens)
 }
 
-pub struct IndexMerger {
+pub struct IndexMerger<C: Codec = StandardCodec> {
     schema: Schema,
-    pub(crate) readers: Vec<SegmentReader>,
+    pub(crate) readers: Vec<Arc<dyn SegmentReader>>,
     max_doc: u32,
+    codec: C,
+    phantom: PhantomData<C>,
 }
 
 struct DeltaComputer {
@@ -144,8 +153,8 @@ 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)
     }
@@ -162,16 +171,24 @@ 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 =
-                    SegmentReader::open_with_custom_alive_set(segment, new_alive_bitset_opt)?;
+                let reader = segment.index().codec().open_segment_reader(
+                    segment.index().directory(),
+                    segment.meta(),
+                    segment.schema(),
+                    new_alive_bitset_opt,
+                )?;
                 readers.push(reader);
             }
         }
@@ -189,6 +206,8 @@ impl IndexMerger {
             schema,
             readers,
             max_doc,
+            codec,
+            phantom: PhantomData,
         })
     }
 
@@ -262,7 +281,7 @@ impl IndexMerger {
                 }),
         );
 
-        let has_deletes: bool = self.readers.iter().any(SegmentReader::has_deletes);
+        let has_deletes: bool = self.readers.iter().any(|reader| reader.has_deletes());
         let mapping_type = if has_deletes {
             MappingType::StackedWithDeletes
         } else {
@@ -297,7 +316,7 @@ impl IndexMerger {
 
         let mut max_term_ords: Vec<TermOrdinal> = Vec::new();
 
-        let field_readers: Vec<Arc<InvertedIndexReader>> = self
+        let field_readers: Vec<Arc<dyn InvertedIndexReader>> = self
             .readers
             .iter()
             .map(|reader| reader.inverted_index(indexed_field))
@@ -355,7 +374,10 @@ 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();
@@ -366,18 +388,16 @@ impl IndexMerger {
             // Let's compute the list of non-empty posting lists
             for (segment_ord, term_info) in merged_terms.current_segment_ords_and_term_infos() {
                 let segment_reader = &self.readers[segment_ord];
-                let inverted_index: &InvertedIndexReader = &field_readers[segment_ord];
-                let segment_postings = inverted_index
-                    .read_postings_from_terminfo(&term_info, segment_postings_option)?;
-                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)
-                } else {
-                    segment_postings.doc_freq()
-                };
-                if doc_freq > 0u32 {
+                let inverted_index = &field_readers[segment_ord];
+                if let Some((doc_freq, postings)) = postings_for_merge::<C>(
+                    inverted_index.as_ref(),
+                    &self.codec,
+                    &term_info,
+                    segment_postings_option,
+                    segment_reader.alive_bitset(),
+                )? {
                     total_doc_freq += doc_freq;
-                    segment_postings_containing_the_term.push((segment_ord, segment_postings));
+                    segment_postings_containing_the_term.push((segment_ord, postings));
                 }
             }
 
@@ -395,11 +415,7 @@ 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
@@ -415,7 +431,7 @@ 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",
                         )
@@ -525,7 +541,7 @@ 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() {
@@ -553,6 +569,77 @@ 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 postings = postings.clone();
+    let mut doc_freq = 0;
+    loop {
+        let doc = postings.doc();
+        if doc == TERMINATED {
+            return doc_freq;
+        }
+        if alive_bitset.is_alive(doc) {
+            doc_freq += 1u32;
+        }
+        postings.advance();
+    }
+}
+
+fn read_postings_for_merge<C: Codec>(
+    inverted_index: &dyn InvertedIndexReader,
+    codec: &C,
+    term_info: &TermInfo,
+    option: IndexRecordOption,
+) -> io::Result<<C::PostingsCodec as PostingsCodec>::Postings> {
+    codec.load_postings_typed(inverted_index, term_info, option)
+}
+
+fn postings_for_merge<C: Codec>(
+    inverted_index: &dyn InvertedIndexReader,
+    codec: &C,
+    term_info: &TermInfo,
+    option: IndexRecordOption,
+    alive_bitset_opt: Option<&AliveBitSet>,
+) -> io::Result<Option<(u32, <C::PostingsCodec as PostingsCodec>::Postings)>> {
+    let postings = read_postings_for_merge(inverted_index, codec, term_info, option)?;
+    let doc_freq = if let Some(alive_bitset) = alive_bitset_opt {
+        doc_freq_given_deletes(&postings, alive_bitset)
+    } else {
+        // We do not need an exact document frequency here.
+        match postings.doc_freq() {
+            crate::postings::DocFreq::Exact(doc_freq) => doc_freq,
+            crate::postings::DocFreq::Approximate(_) => exact_doc_freq(&postings),
+        }
+    };
+
+    if doc_freq == 0u32 {
+        return Ok(None);
+    }
+
+    Ok(Some((doc_freq, postings)))
+}
+
+/// 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 postings = postings.clone();
+    let mut doc_freq = 0;
+    loop {
+        let doc = postings.doc();
+        if doc == TERMINATED {
+            return doc_freq;
+        }
+        doc_freq += 1u32;
+        postings.advance();
+    }
+}
+
 #[cfg(test)]
 mod tests {
 
@@ -561,12 +648,16 @@ 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,
@@ -1518,10 +1609,10 @@ 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"))?;
@@ -1534,13 +1625,13 @@ 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, 1.0)?
+                .term_scorer_for_test(segment_reader.as_ref(), 1.0)
                 .unwrap();
             // the difference compared to before is intrinsic to the bm25 formula. no worries
             // there.
             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();
             }
@@ -1560,12 +1651,12 @@ 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();
         }
@@ -1579,4 +1670,18 @@ 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);
+        let docs =
+            <StandardPostingsCodec as PostingsCodec>::Postings::create_from_docs(&[0, 2, 10]);
+        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,
 }
 
-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)?;
@@ -50,7 +50,7 @@ impl SegmentSerializer {
         self.store_writer.mem_usage()
     }
 
-    pub fn segment(&self) -> &Segment {
+    pub fn segment(&self) -> &Segment<C> {
         &self.segment
     }
 

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;
@@ -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: &SegmentReader, field: &str, typ: ColumnType) {
+        fn assert_type(reader: &dyn 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: &SegmentReader, field: &str) {
+        fn assert_empty(reader: &dyn 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
@@ -225,7 +228,7 @@ pub use crate::core::{json_utils, Executor, Searcher, SearcherGeneration};
 pub use crate::directory::Directory;
 pub use crate::index::{
     Index, IndexBuilder, IndexMeta, IndexSettings, InvertedIndexReader, Order, Segment,
-    SegmentMeta, SegmentReader,
+    SegmentMeta, SegmentReader, TantivyInvertedIndexReader, TantivySegmentReader,
 };
 pub use crate::indexer::{IndexWriter, SingleSegmentIndexWriter};
 pub use crate::schema::{Document, TantivyDocument, Term};
@@ -545,7 +548,7 @@ pub mod tests {
         index_writer.commit()?;
         let reader = index.reader()?;
         let searcher = reader.searcher();
-        let segment_reader: &SegmentReader = searcher.segment_reader(0);
+        let segment_reader: &dyn 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);
@@ -553,7 +556,7 @@ pub mod tests {
         Ok(())
     }
 
-    fn advance_undeleted(docset: &mut dyn DocSet, reader: &SegmentReader) -> bool {
+    fn advance_undeleted(docset: &mut dyn DocSet, reader: &dyn SegmentReader) -> bool {
         let mut doc = docset.advance();
         while doc != TERMINATED {
             if !reader.is_deleted(doc) {
@@ -1070,7 +1073,7 @@ pub mod tests {
         }
         let reader = index.reader()?;
         let searcher = reader.searcher();
-        let segment_reader: &SegmentReader = searcher.segment_reader(0);
+        let segment_reader: &dyn 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/json_postings_writer.rs

@@ -22,12 +22,6 @@ 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(

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 +12,24 @@ mod per_field_postings_writer;
 mod postings;
 mod postings_writer;
 mod recorder;
-mod segment_postings;
-mod serializer;
-mod skip;
+/// Serializer module for the inverted index
+pub mod serializer;
+pub(crate) 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 +37,10 @@ pub(crate) mod tests {
     use super::{InvertedIndexSerializer, Postings};
     use crate::docset::{DocSet, TERMINATED};
     use crate::fieldnorm::FieldNormReader;
-    use crate::index::{Index, SegmentComponent, SegmentReader};
+    use crate::index::{Index, SegmentComponent};
     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,
@@ -258,7 +250,13 @@ pub(crate) mod tests {
             segment_writer.finalize()?;
         }
         {
-            let segment_reader = SegmentReader::open(&segment)?;
+            let segment_reader = crate::codec::Codec::open_segment_reader(
+                segment.index().codec(),
+                segment.index().directory(),
+                segment.meta(),
+                segment.schema(),
+                None,
+            )?;
             {
                 let fieldnorm_reader = segment_reader.get_fieldnorms_reader(text_field)?;
                 assert_eq!(fieldnorm_reader.fieldnorm(0), 8 + 5);
@@ -279,11 +277,11 @@ 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);
@@ -306,7 +304,7 @@ 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);

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

@@ -7,7 +7,10 @@ use stacker::Addr;
 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,
 };
@@ -100,6 +103,141 @@ 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(
+        &self,
+        term_addrs: &[(Field, OrderedPathId, &[u8], Addr)],
+        ordered_id_to_path: &[&str],
+        ctx: &IndexingContext,
+        serializer: &mut FieldSerializer,
+    ) -> 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.
 ///
@@ -171,14 +309,6 @@ 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(

src/postings/recorder.rs

@@ -70,7 +70,7 @@ pub(crate) trait Recorder: Copy + Default + Send + Sync + 'static {
     fn serialize(
         &self,
         arena: &MemoryArena,
-        serializer: &mut FieldSerializer<'_>,
+        serializer: &mut FieldSerializer,
         buffer_lender: &mut BufferLender,
     );
     /// Returns the number of document containing this term.
@@ -113,7 +113,7 @@ impl Recorder for DocIdRecorder {
     fn serialize(
         &self,
         arena: &MemoryArena,
-        serializer: &mut FieldSerializer<'_>,
+        serializer: &mut FieldSerializer,
         buffer_lender: &mut BufferLender,
     ) {
         let buffer = buffer_lender.lend_u8();
@@ -181,7 +181,7 @@ impl Recorder for TermFrequencyRecorder {
     fn serialize(
         &self,
         arena: &MemoryArena,
-        serializer: &mut FieldSerializer<'_>,
+        serializer: &mut FieldSerializer,
         buffer_lender: &mut BufferLender,
     ) {
         let buffer = buffer_lender.lend_u8();
@@ -238,7 +238,7 @@ impl Recorder for TfAndPositionRecorder {
     fn serialize(
         &self,
         arena: &MemoryArena,
-        serializer: &mut FieldSerializer<'_>,
+        serializer: &mut FieldSerializer,
         buffer_lender: &mut BufferLender,
     ) {
         let (buffer_u8, buffer_positions) = buffer_lender.lend_all();

src/postings/serializer.rs

@@ -8,10 +8,10 @@ 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::compression::{BlockEncoder, VIntEncoder as _, COMPRESSION_BLOCK_SIZE};
 use crate::postings::skip::SkipSerializer;
 use crate::query::Bm25Weight;
-use crate::schema::{Field, FieldEntry, FieldType, IndexRecordOption, Schema};
+use crate::schema::{Field, FieldEntry, IndexRecordOption, Schema};
 use crate::termdict::TermDictionaryBuilder;
 use crate::{DocId, Score};
 
@@ -55,7 +55,9 @@ pub struct InvertedIndexSerializer {
 
 impl InvertedIndexSerializer {
     /// Open a new `InvertedIndexSerializer` for the given segment
-    pub fn open(segment: &mut Segment) -> crate::Result<InvertedIndexSerializer> {
+    pub fn open<C: crate::codec::Codec>(
+        segment: &mut Segment<C>,
+    ) -> crate::Result<InvertedIndexSerializer> {
         use crate::index::SegmentComponent::{Positions, Postings, Terms};
         let inv_index_serializer = InvertedIndexSerializer {
             terms_write: CompositeWrite::wrap(segment.open_write(Terms)?),
@@ -80,9 +82,12 @@ impl InvertedIndexSerializer {
         let term_dictionary_write = self.terms_write.for_field(field);
         let postings_write = self.postings_write.for_field(field);
         let positions_write = self.positions_write.for_field(field);
-        let field_type: FieldType = (*field_entry.field_type()).clone();
+        let index_record_option = field_entry
+            .field_type()
+            .index_record_option()
+            .unwrap_or(IndexRecordOption::Basic);
         FieldSerializer::create(
-            &field_type,
+            index_record_option,
             total_num_tokens,
             term_dictionary_write,
             postings_write,
@@ -102,29 +107,27 @@ impl InvertedIndexSerializer {
 
 /// The field serializer is in charge of
 /// the serialization of a specific field.
-pub struct FieldSerializer<'a> {
-    term_dictionary_builder: TermDictionaryBuilder<&'a mut CountingWriter<WritePtr>>,
+pub struct FieldSerializer<'a, W: Write = WritePtr> {
+    term_dictionary_builder: TermDictionaryBuilder<&'a mut CountingWriter<W>>,
     postings_serializer: PostingsSerializer,
-    positions_serializer_opt: Option<PositionSerializer<&'a mut CountingWriter<WritePtr>>>,
+    positions_serializer_opt: Option<PositionSerializer<&'a mut CountingWriter<W>>>,
     current_term_info: TermInfo,
     term_open: bool,
-    postings_write: &'a mut CountingWriter<WritePtr>,
+    postings_write: &'a mut CountingWriter<W>,
     postings_start_offset: u64,
 }
 
-impl<'a> FieldSerializer<'a> {
-    fn create(
-        field_type: &FieldType,
+impl<'a, W: Write> FieldSerializer<'a, W> {
+    /// Creates a new `FieldSerializer` for the given field type.
+    pub fn create(
+        index_record_option: IndexRecordOption,
         total_num_tokens: u64,
-        term_dictionary_write: &'a mut CountingWriter<WritePtr>,
-        postings_write: &'a mut CountingWriter<WritePtr>,
-        positions_write: &'a mut CountingWriter<WritePtr>,
+        term_dictionary_write: &'a mut CountingWriter<W>,
+        postings_write: &'a mut CountingWriter<W>,
+        positions_write: &'a mut CountingWriter<W>,
         fieldnorm_reader: Option<FieldNormReader>,
-    ) -> io::Result<FieldSerializer<'a>> {
+    ) -> io::Result<FieldSerializer<'a, W>> {
         total_num_tokens.serialize(postings_write)?;
-        let index_record_option = field_type
-            .index_record_option()
-            .unwrap_or(IndexRecordOption::Basic);
         let term_dictionary_builder = TermDictionaryBuilder::create(term_dictionary_write)?;
         let average_fieldnorm = fieldnorm_reader
             .as_ref()
@@ -192,6 +195,11 @@ impl<'a> FieldSerializer<'a> {
         Ok(())
     }
 
+    /// Starts the postings for a new term without recording term frequencies.
+    pub fn new_term_without_freq(&mut self, term: &[u8]) -> io::Result<()> {
+        self.new_term(term, 0, false)
+    }
+
     /// Serialize the information that a document contains for the current term:
     /// its term frequency, and the position deltas.
     ///
@@ -297,6 +305,7 @@ impl Block {
     }
 }
 
+/// Serializer for postings lists.
 pub struct PostingsSerializer {
     last_doc_id_encoded: u32,
 
@@ -316,6 +325,9 @@ pub struct PostingsSerializer {
 }
 
 impl PostingsSerializer {
+    /// Creates a new `PostingsSerializer`.
+    /// * avg_fieldnorm - average field norm for the field being serialized.
+    /// * mode - indexing options for the field being serialized.
     pub fn new(
         avg_fieldnorm: Score,
         mode: IndexRecordOption,
@@ -338,6 +350,8 @@ impl PostingsSerializer {
         }
     }
 
+    /// Starts the serialization for a new term.
+    /// * term_doc_freq - the number of documents containing the term.
     pub fn new_term(&mut self, term_doc_freq: u32, record_term_freq: bool) {
         self.bm25_weight = None;
 
@@ -377,6 +391,7 @@ impl PostingsSerializer {
             self.postings_write.extend(block_encoded);
         }
         if self.term_has_freq {
+            // encode the term frequencies
             let (num_bits, block_encoded): (u8, &[u8]) = self
                 .block_encoder
                 .compress_block_unsorted(self.block.term_freqs(), true);
@@ -417,6 +432,9 @@ impl PostingsSerializer {
         self.block.clear();
     }
 
+    /// Register that the given document contains the current term.
+    /// * doc_id - the document id.
+    /// * term_freq - the term frequency within the document.
     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() {
@@ -424,6 +442,7 @@ impl PostingsSerializer {
         }
     }
 
+    /// Finish the serialization for this term.
     pub fn close_term(
         &mut self,
         doc_freq: u32,

src/postings/skip.rs

@@ -14,7 +14,11 @@ use crate::{DocId, Score, TERMINATED};
 //   (requiring a 6th bit), but the biggest doc_id we can want to encode is TERMINATED-1, which can
 //   be represented on 31b without delta encoding.
 fn encode_bitwidth(bitwidth: u8, delta_1: bool) -> u8 {
-    assert!(bitwidth < 32);
+    assert!(
+        bitwidth < 32,
+        "bitwidth needs to be less than 32, but got {}",
+        bitwidth
+    );
     bitwidth | ((delta_1 as u8) << 6)
 }
 
@@ -142,23 +146,6 @@ impl SkipReader {
         skip_reader
     }
 
-    pub fn reset(&mut self, data: OwnedBytes, doc_freq: u32) {
-        self.last_doc_in_block = if doc_freq >= COMPRESSION_BLOCK_SIZE as u32 {
-            0
-        } else {
-            TERMINATED
-        };
-        self.last_doc_in_previous_block = 0u32;
-        self.owned_read = data;
-        self.block_info = BlockInfo::VInt { num_docs: doc_freq };
-        self.byte_offset = 0;
-        self.remaining_docs = doc_freq;
-        self.position_offset = 0u64;
-        if doc_freq >= COMPRESSION_BLOCK_SIZE as u32 {
-            self.read_block_info();
-        }
-    }
-
     // Returns the block max score for this block if available.
     //
     // The block max score is available for all full bitpacked block,

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: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &dyn 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: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &dyn 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: &SegmentReader) -> crate::Result<Vec<TermInfo>> {
+    pub fn get_match_term_infos(&self, reader: &dyn 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: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &dyn 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 +92,18 @@ 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();
-            }
+            inverted_index.fill_bitset_for_term(
+                term_info,
+                IndexRecordOption::Basic,
+                &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: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &dyn 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

@@ -1,24 +1,19 @@
 use std::collections::HashMap;
 
+use crate::codec::SumOrDoNothingCombiner;
 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;
 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, SumCombiner, 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 +27,7 @@ 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,
@@ -44,57 +39,39 @@ fn scorer_union<TScoreCombiner>(
     scorers: Vec<Box<dyn Scorer>>,
     score_combiner_fn: impl Fn() -> TScoreCombiner,
     num_docs: u32,
-) -> SpecializedScorer
+    reader: &dyn SegmentReader,
+) -> 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)
+    match scorers.len() {
+        0 => box_scorer(EmptyScorer),
+        1 => scorers.into_iter().next().unwrap(),
+        _ => {
+            let combiner_opt: Option<SumOrDoNothingCombiner> = if std::any::TypeId::of::<
+                TScoreCombiner,
+            >() == std::any::TypeId::of::<
+                SumCombiner,
+            >() {
+                Some(SumOrDoNothingCombiner::Sum)
+            } else if std::any::TypeId::of::<TScoreCombiner>()
+                == std::any::TypeId::of::<DoNothingCombiner>()
             {
-                // Block wand is only available if we read frequencies.
-                return SpecializedScorer::TermUnion(scorers);
+                Some(SumOrDoNothingCombiner::DoNothing)
             } else {
-                return SpecializedScorer::Other(Box::new(BufferedUnionScorer::build(
+                None
+            };
+            if let Some(combiner) = combiner_opt {
+                reader.build_union_scorer_with_sum_combiner(scorers, num_docs, combiner)
+            } else {
+                box_scorer(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,
-    }
 }
 
 /// Returns the effective MUST scorer, accounting for removed AllScorers.
@@ -110,7 +87,7 @@ 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 +105,26 @@ 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 +135,9 @@ 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 +180,7 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
 
     fn per_occur_scorers(
         &self,
-        reader: &SegmentReader,
+        reader: &dyn 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 +196,10 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
 
     fn complex_scorer<TComplexScoreCombiner: ScoreCombiner>(
         &self,
-        reader: &SegmentReader,
+        reader: &dyn 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 +209,7 @@ 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 +224,7 @@ 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 +236,7 @@ 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,
@@ -269,11 +244,13 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
                     should_scorers,
                     &score_combiner_fn,
                     num_docs,
+                    reader,
                 )),
                 1 => ShouldScorersCombinationMethod::Required(scorer_union(
                     should_scorers,
                     &score_combiner_fn,
                     num_docs,
+                    reader,
                 )),
                 n if num_of_should_scorers == n => {
                     // When num_of_should_scorers equals the number of should clauses,
@@ -281,12 +258,10 @@ 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,
                 )),
             }
         };
@@ -303,8 +278,8 @@ 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.
@@ -329,16 +304,12 @@ 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
                         }
                     }
                 }
@@ -358,12 +329,7 @@ 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)
                     }
                 }
             }
@@ -372,19 +338,18 @@ impl<TScoreCombiner: ScoreCombiner> BooleanWeight<TScoreCombiner> {
             return Ok(include_scorer);
         }
 
-        let include_scorer_boxed = into_box_scorer(include_scorer, &score_combiner_fn, num_docs);
         let scorer: Box<dyn Scorer> = if exclude_scorers.len() == 1 {
             let exclude_scorer = exclude_scorers.pop().unwrap();
             match exclude_scorer.downcast::<TermScorer>() {
                 // Cast to TermScorer succeeded
-                Ok(exclude_scorer) => Box::new(Exclude::new(include_scorer_boxed, *exclude_scorer)),
+                Ok(exclude_scorer) => Box::new(Exclude::new(include_scorer, *exclude_scorer)),
                 // We get back the original Box<dyn Scorer>
-                Err(exclude_scorer) => Box::new(Exclude::new(include_scorer_boxed, exclude_scorer)),
+                Err(exclude_scorer) => Box::new(Exclude::new(include_scorer, exclude_scorer)),
             }
         } else {
-            Box::new(Exclude::new(include_scorer_boxed, exclude_scorers))
+            Box::new(Exclude::new(include_scorer, exclude_scorers))
         };
-        Ok(SpecializedScorer::Other(scorer))
+        Ok(scorer)
     }
 }
 
@@ -413,8 +378,7 @@ fn remove_and_count_all_and_empty_scorers(
 }
 
 impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombiner> {
-    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
-        let num_docs = reader.num_docs();
+    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         if self.weights.is_empty() {
             Ok(Box::new(EmptyScorer))
         } else if self.weights.len() == 1 {
@@ -426,18 +390,12 @@ 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: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &dyn 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));
@@ -459,47 +417,22 @@ impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombin
 
     fn for_each(
         &self,
-        reader: &SegmentReader,
+        reader: &dyn 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)?;
+        scorer.for_each(callback);
         Ok(())
     }
 
     fn for_each_no_score(
         &self,
-        reader: &SegmentReader,
+        reader: &dyn 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(())
     }
 
@@ -516,18 +449,11 @@ impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombin
     fn for_each_pruning(
         &self,
         threshold: Score,
-        reader: &SegmentReader,
+        reader: &dyn 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.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

@@ -67,11 +67,11 @@ impl BoostWeight {
 }
 
 impl Weight for BoostWeight {
-    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         self.weight.scorer(reader, boost * self.boost)
     }
 
-    fn explain(&self, reader: &SegmentReader, doc: u32) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &dyn 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: &SegmentReader) -> crate::Result<u32> {
+    fn count(&self, reader: &dyn SegmentReader) -> crate::Result<u32> {
         self.weight.count(reader)
     }
 }

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: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &dyn 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: &SegmentReader, doc: u32) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &dyn 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: &SegmentReader) -> crate::Result<u32> {
+    fn count(&self, reader: &dyn SegmentReader) -> crate::Result<u32> {
         self.weight.count(reader)
     }
 }

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: &SegmentReader, _boost: Score) -> crate::Result<Box<dyn Scorer>> {
-        Ok(Box::new(EmptyScorer))
+    fn scorer(&self, _reader: &dyn SegmentReader, _boost: Score) -> crate::Result<Box<dyn Scorer>> {
+        Ok(box_scorer(EmptyScorer))
     }
 
-    fn explain(&self, _reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, _reader: &dyn 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: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &dyn 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: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &dyn 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::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,

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

@@ -2,7 +2,7 @@ use crate::docset::{DocSet, SeekDangerResult, 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
     }
 }
 

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, Scorer, Weight};
 use crate::schema::{IndexRecordOption, Term};
-use crate::{DocId, DocSet, Score};
+use crate::Score;
 
 pub struct PhrasePrefixWeight {
     phrase_terms: Vec<(usize, Term)>,
@@ -32,7 +31,7 @@ impl PhrasePrefixWeight {
         }
     }
 
-    fn fieldnorm_reader(&self, reader: &SegmentReader) -> crate::Result<FieldNormReader> {
+    fn fieldnorm_reader(&self, reader: &dyn 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: &SegmentReader,
+        reader: &dyn 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())?
@@ -103,49 +102,32 @@ impl PhrasePrefixWeight {
             }
         }
 
-        Ok(Some(PhrasePrefixScorer::new(
+        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: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &dyn 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: &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)
-    }
 }
 
 #[cfg(test)]
 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 +168,14 @@ 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 +195,15 @@ 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(())
     }

src/query/phrase_query/mod.rs

@@ -5,7 +5,7 @@ pub mod regex_phrase_query;
 mod regex_phrase_weight;
 
 pub use self::phrase_query::PhraseQuery;
-pub(crate) use self::phrase_scorer::intersection_count;
+pub(crate) use self::phrase_scorer::intersection_exists;
 pub use self::phrase_scorer::PhraseScorer;
 pub use self::phrase_weight::PhraseWeight;
 

src/query/phrase_query/phrase_query.rs

@@ -126,7 +126,7 @@ impl PhraseQuery {
         };
         let mut weight = PhraseWeight::new(self.phrase_terms.clone(), bm25_weight_opt);
         if self.slop > 0 {
-            weight.slop(self.slop);
+            weight.set_slop(self.slop);
         }
         Ok(weight)
     }

src/query/phrase_query/phrase_scorer.rs

@@ -1,10 +1,11 @@
 use std::cmp::Ordering;
 
+use crate::codec::standard::postings::StandardPostings;
 use crate::docset::{DocSet, SeekDangerResult, TERMINATED};
 use crate::fieldnorm::FieldNormReader;
 use crate::postings::Postings;
 use crate::query::bm25::Bm25Weight;
-use crate::query::{Intersection, Scorer};
+use crate::query::{Explanation, Intersection, Scorer};
 use crate::{DocId, Score};
 
 struct PostingsWithOffset<TPostings> {
@@ -43,7 +44,7 @@ impl<TPostings: Postings> DocSet for PostingsWithOffset<TPostings> {
     }
 }
 
-pub struct PhraseScorer<TPostings: Postings> {
+pub struct PhraseScorer<TPostings: Postings = StandardPostings> {
     intersection_docset: Intersection<PostingsWithOffset<TPostings>, PostingsWithOffset<TPostings>>,
     num_terms: usize,
     left_positions: Vec<u32>,
@@ -58,7 +59,7 @@ pub struct PhraseScorer<TPostings: Postings> {
 }
 
 /// Returns true if and only if the two sorted arrays contain a common element
-fn intersection_exists(left: &[u32], right: &[u32]) -> bool {
+pub(crate) fn intersection_exists(left: &[u32], right: &[u32]) -> bool {
     let mut left_index = 0;
     let mut right_index = 0;
     while left_index < left.len() && right_index < right.len() {
@@ -79,7 +80,7 @@ fn intersection_exists(left: &[u32], right: &[u32]) -> bool {
     false
 }
 
-pub(crate) fn intersection_count(left: &[u32], right: &[u32]) -> usize {
+fn intersection_count(left: &[u32], right: &[u32]) -> usize {
     let mut left_index = 0;
     let mut right_index = 0;
     let mut count = 0;
@@ -402,6 +403,7 @@ impl<TPostings: Postings> PhraseScorer<TPostings> {
         scorer
     }
 
+    /// Returns the number of phrases identified in the current matching doc.
     pub fn phrase_count(&self) -> u32 {
         self.phrase_count
     }
@@ -584,6 +586,17 @@ impl<TPostings: Postings> Scorer for PhraseScorer<TPostings> {
             1.0f32
         }
     }
+
+    fn explain(&mut self) -> Explanation {
+        let doc = self.doc();
+        let phrase_count = self.phrase_count();
+        let fieldnorm_id = self.fieldnorm_reader.fieldnorm_id(doc);
+        let mut explanation = Explanation::new("Phrase Scorer", self.score());
+        if let Some(similarity_weight) = self.similarity_weight_opt.as_ref() {
+            explanation.add_detail(similarity_weight.explain(fieldnorm_id, phrase_count));
+        }
+        explanation
+    }
 }
 
 #[cfg(test)]

src/query/phrase_query/phrase_weight.rs

@@ -1,11 +1,10 @@
-use super::PhraseScorer;
 use crate::fieldnorm::FieldNormReader;
 use crate::index::SegmentReader;
-use crate::postings::SegmentPostings;
+use crate::postings::TermInfo;
 use crate::query::bm25::Bm25Weight;
 use crate::query::explanation::does_not_match;
-use crate::query::{EmptyScorer, Explanation, Scorer, Weight};
-use crate::schema::{IndexRecordOption, Term};
+use crate::query::{box_scorer, EmptyScorer, Explanation, Scorer, Weight};
+use crate::schema::Term;
 use crate::{DocId, DocSet, Score};
 
 pub struct PhraseWeight {
@@ -21,15 +20,14 @@ impl PhraseWeight {
         phrase_terms: Vec<(usize, Term)>,
         similarity_weight_opt: Option<Bm25Weight>,
     ) -> PhraseWeight {
-        let slop = 0;
         PhraseWeight {
             phrase_terms,
             similarity_weight_opt,
-            slop,
+            slop: 0,
         }
     }
 
-    fn fieldnorm_reader(&self, reader: &SegmentReader) -> crate::Result<FieldNormReader> {
+    fn fieldnorm_reader(&self, reader: &dyn 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)? {
@@ -41,48 +39,67 @@ impl PhraseWeight {
 
     pub(crate) fn phrase_scorer(
         &self,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
         boost: Score,
-    ) -> crate::Result<Option<PhraseScorer<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();
-        for &(offset, ref term) in &self.phrase_terms {
-            if let Some(postings) = reader
-                .inverted_index(term.field())?
-                .read_postings(term, IndexRecordOption::WithFreqsAndPositions)?
-            {
-                term_postings_list.push((offset, postings));
-            } else {
-                return Ok(None);
-            }
+
+        if self.phrase_terms.is_empty() {
+            return Ok(None);
         }
-        Ok(Some(PhraseScorer::new(
-            term_postings_list,
+        let field = self.phrase_terms[0].1.field();
+
+        if !self
+            .phrase_terms
+            .iter()
+            .all(|(_offset, term)| term.field() == field)
+        {
+            return Err(crate::TantivyError::InvalidArgument(
+                "All terms in a phrase query must belong to the same field".to_string(),
+            ));
+        }
+
+        let inverted_index_reader = reader.inverted_index(field)?;
+
+        let mut term_infos: Vec<(usize, TermInfo)> = Vec::with_capacity(self.phrase_terms.len());
+
+        for &(offset, ref term) in &self.phrase_terms {
+            let Some(term_info) = inverted_index_reader.get_term_info(term)? else {
+                return Ok(None);
+            };
+            term_infos.push((offset, term_info));
+        }
+
+        let scorer = inverted_index_reader.new_phrase_scorer(
+            &term_infos[..],
             similarity_weight_opt,
             fieldnorm_reader,
             self.slop,
-        )))
+        )?;
+
+        Ok(Some(scorer))
     }
 
-    pub fn slop(&mut self, slop: u32) {
+    /// Sets the slop for the given PhraseWeight.
+    pub fn set_slop(&mut self, slop: u32) {
         self.slop = slop;
     }
 }
 
 impl Weight for PhraseWeight {
-    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         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: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    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));
@@ -91,14 +108,7 @@ impl Weight for PhraseWeight {
         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 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)
+        Ok(scorer.explain())
     }
 }
 
@@ -106,7 +116,8 @@ impl Weight for PhraseWeight {
 mod tests {
     use super::super::tests::create_index;
     use crate::docset::TERMINATED;
-    use crate::query::{EnableScoring, PhraseQuery};
+    use crate::query::phrase_query::PhraseScorer;
+    use crate::query::{EnableScoring, PhraseQuery, Scorer};
     use crate::{DocSet, Term};
 
     #[test]
@@ -121,9 +132,11 @@ mod tests {
         ]);
         let enable_scoring = EnableScoring::enabled_from_searcher(&searcher);
         let phrase_weight = phrase_query.phrase_weight(enable_scoring).unwrap();
-        let mut phrase_scorer = phrase_weight
+        let phrase_scorer_boxed: Box<dyn Scorer> = phrase_weight
             .phrase_scorer(searcher.segment_reader(0u32), 1.0)?
             .unwrap();
+        let mut phrase_scorer: Box<PhraseScorer> =
+            phrase_scorer_boxed.downcast::<PhraseScorer>().ok().unwrap();
         assert_eq!(phrase_scorer.doc(), 1);
         assert_eq!(phrase_scorer.phrase_count(), 2);
         assert_eq!(phrase_scorer.advance(), 2);

src/query/phrase_query/regex_phrase_weight.rs

@@ -6,11 +6,13 @@ use tantivy_fst::Regex;
 use super::PhraseScorer;
 use crate::fieldnorm::FieldNormReader;
 use crate::index::SegmentReader;
-use crate::postings::{LoadedPostings, Postings, SegmentPostings, TermInfo};
+use crate::postings::{LoadedPostings, Postings, TermInfo};
 use crate::query::bm25::Bm25Weight;
 use crate::query::explanation::does_not_match;
 use crate::query::union::{BitSetPostingUnion, SimpleUnion};
-use crate::query::{AutomatonWeight, BitSetDocSet, EmptyScorer, Explanation, Scorer, Weight};
+use crate::query::{
+    box_scorer, AutomatonWeight, BitSetDocSet, EmptyScorer, Explanation, Scorer, Weight,
+};
 use crate::schema::{Field, IndexRecordOption};
 use crate::{DocId, DocSet, InvertedIndexReader, Score};
 
@@ -45,7 +47,7 @@ impl RegexPhraseWeight {
         }
     }
 
-    fn fieldnorm_reader(&self, reader: &SegmentReader) -> crate::Result<FieldNormReader> {
+    fn fieldnorm_reader(&self, reader: &dyn SegmentReader) -> crate::Result<FieldNormReader> {
         if self.similarity_weight_opt.is_some() {
             if let Some(fieldnorm_reader) = reader.fieldnorms_readers().get_field(self.field)? {
                 return Ok(fieldnorm_reader);
@@ -56,7 +58,7 @@ impl RegexPhraseWeight {
 
     pub(crate) fn phrase_scorer(
         &self,
-        reader: &SegmentReader,
+        reader: &dyn SegmentReader,
         boost: Score,
     ) -> crate::Result<Option<PhraseScorer<UnionType>>> {
         let similarity_weight_opt = self
@@ -84,7 +86,8 @@ impl RegexPhraseWeight {
                     "Phrase query exceeded max expansions {num_terms}"
                 )));
             }
-            let union = Self::get_union_from_term_infos(&term_infos, reader, &inverted_index)?;
+            let union =
+                Self::get_union_from_term_infos(&term_infos, reader, inverted_index.as_ref())?;
 
             posting_lists.push((offset, union));
         }
@@ -99,22 +102,11 @@ impl RegexPhraseWeight {
 
     /// Add all docs of the term to the docset
     fn add_to_bitset(
-        inverted_index: &InvertedIndexReader,
+        inverted_index: &dyn InvertedIndexReader,
         term_info: &TermInfo,
         doc_bitset: &mut BitSet,
     ) -> crate::Result<()> {
-        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();
-        }
+        inverted_index.fill_bitset_for_term(term_info, IndexRecordOption::Basic, doc_bitset)?;
         Ok(())
     }
 
@@ -174,8 +166,8 @@ impl RegexPhraseWeight {
     /// Use Roaring Bitmaps for sparse terms. The full bitvec is main memory consumer currently.
     pub(crate) fn get_union_from_term_infos(
         term_infos: &[TermInfo],
-        reader: &SegmentReader,
-        inverted_index: &InvertedIndexReader,
+        reader: &dyn SegmentReader,
+        inverted_index: &dyn InvertedIndexReader,
     ) -> crate::Result<UnionType> {
         let max_doc = reader.max_doc();
 
@@ -188,7 +180,7 @@ impl RegexPhraseWeight {
         // - Bucket 1: Terms appearing in 0.1% to 1% of documents
         // - Bucket 2: Terms appearing in 1% to 10% of documents
         // - Bucket 3: Terms appearing in more than 10% of documents
-        let mut buckets: Vec<(BitSet, Vec<SegmentPostings>)> = (0..4)
+        let mut buckets: Vec<(BitSet, Vec<Box<dyn Postings>>)> = (0..4)
             .map(|_| (BitSet::with_max_value(max_doc), Vec::new()))
             .collect();
 
@@ -197,7 +189,7 @@ impl RegexPhraseWeight {
         for term_info in term_infos {
             let mut term_posting = inverted_index
                 .read_postings_from_terminfo(term_info, IndexRecordOption::WithFreqsAndPositions)?;
-            let num_docs = term_posting.doc_freq();
+            let num_docs = u32::from(term_posting.doc_freq());
 
             if num_docs < SPARSE_TERM_DOC_THRESHOLD {
                 let current_bucket = &mut sparse_buckets[0];
@@ -269,15 +261,15 @@ impl RegexPhraseWeight {
 }
 
 impl Weight for RegexPhraseWeight {
-    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &dyn SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         if let Some(scorer) = self.phrase_scorer(reader, boost)? {
-            Ok(Box::new(scorer))
+            Ok(box_scorer(scorer))
         } else {
-            Ok(Box::new(EmptyScorer))
+            Ok(box_scorer(EmptyScorer))
         }
     }
 
-    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    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));

src/query/query.rs

@@ -146,7 +146,7 @@ pub trait Query: QueryClone + Send + Sync + downcast_rs::Downcast + fmt::Debug {
         let weight = self.weight(EnableScoring::disabled_from_searcher(searcher))?;
         let mut result = 0;
         for reader in searcher.segment_readers() {
-            result += weight.count(reader)? as usize;
+            result += weight.count(reader.as_ref())? as usize;
         }
         Ok(result)
     }

src/query/query_parser/query_parser.rs

@@ -2068,6 +2068,16 @@ mod test {
             format!("Regex(Field(0), {:#?})", expected_regex).as_str(),
             false,
         );
+        let expected_regex2 = tantivy_fst::Regex::new(r".*a").unwrap();
+        test_parse_query_to_logical_ast_helper(
+            "title:(/.*b/ OR /.*a/)",
+            format!(
+                "(Regex(Field(0), {:#?}) Regex(Field(0), {:#?}))",
+                expected_regex, expected_regex2
+            )
+            .as_str(),
+            false,
+        );
 
         // Invalid field
         let err = parse_query_to_logical_ast("float:/.*b/", false).unwrap_err();

src/query/range_query/mod.rs

@@ -19,7 +19,8 @@ pub(crate) fn is_type_valid_for_fastfield_range_query(typ: Type) -> bool {
         | Type::Bool
         | Type::Date
         | Type::Json
-        | Type::IpAddr => true,
-        Type::Facet | Type::Bytes => false,
+        | Type::IpAddr
+        | Type::Bytes => true,
+        Type::Facet => false,
     }
 }