prealloc vec in postinglist

src/indexer/merger.rs

@@ -70,7 +70,7 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> crate::R
 pub struct IndexMerger {
     index_settings: IndexSettings,
     schema: Schema,
-    readers: Vec<SegmentReader>,
+    pub(crate) readers: Vec<SegmentReader>,
     max_doc: u32,
 }
 

src/indexer/merger_sorted_index_test.rs

@@ -546,8 +546,9 @@ mod bench_sorted_index_merge {
         let doc_id_mapping = merger.generate_doc_id_mapping(&sort_by_field).unwrap();
         b.iter(|| {
 
-            let sorted_doc_ids = doc_id_mapping.iter().map(|(doc_id, reader)|{
-            let u64_reader: DynamicFastFieldReader<u64> = reader.reader
+            let sorted_doc_ids = doc_id_mapping.iter().map(|(doc_id, ordinal)|{
+            let reader = &merger.readers[*ordinal as usize];
+            let u64_reader: DynamicFastFieldReader<u64> = reader
                 .fast_fields()
                 .typed_fast_field_reader(field)
                 .expect("Failed to find a reader for single fast field. This is a tantivy bug and it should never happen.");

src/postings/postings_writer.rs

@@ -133,7 +133,8 @@ impl MultiFieldPostingsWriter {
         doc_id_map: Option<&DocIdMapping>,
     ) -> crate::Result<HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>> {
         let mut term_offsets: Vec<(&[u8], Addr, UnorderedTermId)> =
-            self.term_index.iter().collect();
+            Vec::with_capacity(self.term_index.len());
+        term_offsets.extend(self.term_index.iter());
         term_offsets.sort_unstable_by_key(|&(k, _, _)| k);
 
         let mut unordered_term_mappings: HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>> =

src/postings/stacker/term_hashmap.rs

@@ -148,6 +148,10 @@ impl TermHashMap {
         unordered_term_id
     }
 
+    pub fn len(&self) -> usize {
+        self.len
+    }
+
     pub fn iter(&self) -> Iter<'_> {
         Iter {
             inner: self.occupied.iter(),