Removing block postings public accessors

src/docset.rs

@@ -1,5 +1,7 @@
 use std::borrow::{Borrow, BorrowMut};
 
+use common::BitSet;
+
 use crate::fastfield::AliveBitSet;
 use crate::DocId;
 
@@ -106,6 +108,15 @@ pub trait DocSet: Send {
         buffer.len()
     }
 
+    // comment on the size of the bitset
+    fn fill_bitset(&mut self, bitset: &mut BitSet) {
+        let mut doc = self.doc();
+        while doc != TERMINATED {
+            bitset.insert(doc);
+            doc = self.advance();
+        }
+    }
+
     /// Returns the current document
     /// Right after creating a new `DocSet`, the docset points to the first document.
     ///

src/index/inverted_index_reader.rs

@@ -12,7 +12,7 @@ use tantivy_fst::automaton::{AlwaysMatch, Automaton};
 use crate::codec::postings::PostingsReader as _;
 use crate::directory::FileSlice;
 use crate::positions::PositionReader;
-use crate::postings::{BlockSegmentPostings, SegmentPostings, TermInfo};
+use crate::postings::{BlockSegmentPostings, Postings, SegmentPostings, TermInfo};
 use crate::schema::{IndexRecordOption, Term, Type};
 use crate::termdict::TermDictionary;
 

src/postings/segment_postings.rs

@@ -1,4 +1,4 @@
-use common::HasLen;
+use common::{BitSet, HasLen};
 
 use crate::codec::postings::PostingsReader;
 use crate::docset::DocSet;
@@ -201,6 +201,19 @@ impl DocSet for SegmentPostings {
     fn size_hint(&self) -> u32 {
         self.len() as u32
     }
+
+    fn fill_bitset(&mut self, bitset: &mut BitSet) {
+        loop {
+            let docs = self.block_cursor.docs();
+            if docs.is_empty() {
+                break;
+            }
+            for &doc in docs {
+                bitset.insert(doc);
+            }
+            self.block_cursor.advance();
+        }
+    }
 }
 
 impl HasLen for SegmentPostings {

src/query/automaton_weight.rs

@@ -5,13 +5,12 @@ use common::BitSet;
 use tantivy_fst::Automaton;
 
 use super::phrase_prefix_query::prefix_end;
-use crate::codec::postings::PostingsReader as _;
 use crate::index::SegmentReader;
 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> {
@@ -93,18 +92,9 @@ where
         let mut term_stream = self.automaton_stream(term_dict)?;
         while term_stream.advance() {
             let term_info = term_stream.value();
-            let mut block_segment_postings = inverted_index
-                .read_block_postings_from_terminfo(term_info, IndexRecordOption::Basic)?;
-            loop {
-                let docs = block_segment_postings.docs();
-                if docs.is_empty() {
-                    break;
-                }
-                for &doc in docs {
-                    doc_bitset.insert(doc);
-                }
-                block_segment_postings.advance();
-            }
+            let mut block_segment_postings =
+                inverted_index.read_postings_from_terminfo(term_info, IndexRecordOption::Basic)?;
+            block_segment_postings.fill_bitset(&mut doc_bitset);
         }
         let doc_bitset = BitSetDocSet::from(doc_bitset);
         let const_scorer = ConstScorer::new(doc_bitset, boost);

src/query/phrase_query/regex_phrase_weight.rs

@@ -104,18 +104,9 @@ impl RegexPhraseWeight {
         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();
-        }
+        let mut segment_postings =
+            inverted_index.read_postings_from_terminfo(term_info, IndexRecordOption::Basic)?;
+        segment_postings.fill_bitset(doc_bitset);
         Ok(())
     }
 

src/query/range_query/range_query.rs

@@ -12,7 +12,7 @@ use crate::query::range_query::is_type_valid_for_fastfield_range_query;
 use crate::query::{BitSetDocSet, ConstScorer, EnableScoring, Explanation, Query, Scorer, Weight};
 use crate::schema::{Field, IndexRecordOption, Term, Type};
 use crate::termdict::{TermDictionary, TermStreamer};
-use crate::{DocId, Score};
+use crate::{DocId, DocSet, Score};
 
 /// `RangeQuery` matches all documents that have at least one term within a defined range.
 ///
@@ -229,18 +229,9 @@ impl Weight for InvertedIndexRangeWeight {
             }
             processed_count += 1;
             let term_info = term_range.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 block_segment_postings.docs() {
-                    doc_bitset.insert(doc);
-                }
-                block_segment_postings.advance();
-            }
+            let mut postings =
+                inverted_index.read_postings_from_terminfo(term_info, IndexRecordOption::Basic)?;
+            postings.fill_bitset(&mut doc_bitset);
         }
         let doc_bitset = BitSetDocSet::from(doc_bitset);
         Ok(Box::new(ConstScorer::new(doc_bitset, boost)))