chore: make more things public

In implementing custom queries that are similar to tantivy's built-in
PhraseQuery and RegexPhraseQuery queries I've found a number of things
that can benefit from being `pub` so they can be reused externally.

Author: Eric B. Ridge

.gitignore

@@ -17,3 +17,4 @@ variable
 
 # for `sample record -p`
 profile.json
+profile.json.gz

src/postings/loaded_postings.rs

@@ -15,10 +15,10 @@ use crate::DocId;
 /// terms.
 /// E.g. 100_000 terms would need 184MB due to SegmentPostings.
 pub struct LoadedPostings {
-    doc_ids: Box<[DocId]>,
-    position_offsets: Box<[u32]>,
-    positions: Box<[u32]>,
-    cursor: usize,
+    pub doc_ids: Box<[DocId]>,
+    pub position_offsets: Box<[u32]>,
+    pub positions: Box<[u32]>,
+    pub cursor: usize,
 }
 
 impl LoadedPostings {

src/postings/mod.rs

@@ -21,7 +21,7 @@ mod serializer;
 pub(crate) mod skip;
 mod term_info;
 
-pub(crate) use loaded_postings::LoadedPostings;
+pub use loaded_postings::LoadedPostings;
 pub(crate) use stacker::compute_table_memory_size;
 
 pub use self::block_segment_postings::BlockSegmentPostings;

src/query/explanation.rs

@@ -5,7 +5,7 @@ use serde::Serialize;
 
 use crate::{DocId, Score, TantivyError};
 
-pub(crate) fn does_not_match(doc: DocId) -> TantivyError {
+pub fn does_not_match(doc: DocId) -> TantivyError {
     TantivyError::InvalidArgument(format!("Document #({doc}) does not match"))
 }
 

src/query/intersection.rs

@@ -66,7 +66,7 @@ fn go_to_first_doc<TDocSet: DocSet>(docsets: &mut [TDocSet]) -> DocId {
 }
 
 impl<TDocSet: DocSet> Intersection<TDocSet, TDocSet> {
-    pub(crate) fn new(mut docsets: Vec<TDocSet>) -> Intersection<TDocSet, TDocSet> {
+    pub fn new(mut docsets: Vec<TDocSet>) -> Intersection<TDocSet, TDocSet> {
         let num_docsets = docsets.len();
         assert!(num_docsets >= 2);
         docsets.sort_by_key(|docset| docset.size_hint());
@@ -79,10 +79,22 @@ impl<TDocSet: DocSet> Intersection<TDocSet, TDocSet> {
             others: docsets,
         }
     }
+
+    pub fn with_two_sets(left: TDocSet, right: TDocSet) -> Intersection<TDocSet, TDocSet> {
+        let mut docsets = vec![left, right];
+        go_to_first_doc(&mut docsets);
+        let left = docsets.remove(0);
+        let right = docsets.remove(0);
+        Intersection {
+            left,
+            right,
+            others: docsets,
+        }
+    }
 }
 
 impl<TDocSet: DocSet> Intersection<TDocSet, TDocSet> {
-    pub(crate) fn docset_mut_specialized(&mut self, ord: usize) -> &mut TDocSet {
+    pub fn docset_mut_specialized(&mut self, ord: usize) -> &mut TDocSet {
         match ord {
             0 => &mut self.left,
             1 => &mut self.right,

src/query/mod.rs

@@ -44,7 +44,7 @@ pub use self::disjunction_max_query::DisjunctionMaxQuery;
 pub use self::empty_query::{EmptyQuery, EmptyScorer, EmptyWeight};
 pub use self::exclude::Exclude;
 pub use self::exist_query::ExistsQuery;
-pub use self::explanation::Explanation;
+pub use self::explanation::{does_not_match, Explanation};
 #[cfg(test)]
 pub(crate) use self::fuzzy_query::DfaWrapper;
 pub use self::fuzzy_query::FuzzyTermQuery;
@@ -54,6 +54,7 @@ pub use self::more_like_this::{
 };
 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::regex_phrase_weight::RegexPhraseWeight;
 pub use self::phrase_query::PhraseQuery;
 pub use self::query::{EnableScoring, Query, QueryClone};
 pub use self::query_parser::{QueryParser, QueryParserError};
@@ -64,7 +65,7 @@ pub use self::score_combiner::{DisjunctionMaxCombiner, ScoreCombiner, SumCombine
 pub use self::scorer::Scorer;
 pub use self::set_query::TermSetQuery;
 pub use self::term_query::TermQuery;
-pub use self::union::BufferedUnionScorer;
+pub use self::union::{BufferedUnionScorer, SimpleUnion};
 #[cfg(test)]
 pub use self::vec_docset::VecDocSet;
 pub use self::weight::Weight;

src/query/phrase_query/mod.rs

@@ -2,7 +2,7 @@ mod phrase_query;
 mod phrase_scorer;
 mod phrase_weight;
 pub mod regex_phrase_query;
-mod regex_phrase_weight;
+pub mod regex_phrase_weight;
 
 pub use self::phrase_query::PhraseQuery;
 pub(crate) use self::phrase_scorer::intersection_count;

src/query/phrase_query/regex_phrase_query.rs

@@ -1,4 +1,4 @@
-use super::regex_phrase_weight::RegexPhraseWeight;
+pub(crate) use super::regex_phrase_weight::RegexPhraseWeight;
 use crate::query::bm25::Bm25Weight;
 use crate::query::{EnableScoring, Query, Weight};
 use crate::schema::{Field, IndexRecordOption, Term, Type};

src/query/phrase_query/regex_phrase_weight.rs

@@ -173,7 +173,7 @@ impl RegexPhraseWeight {
     /// docs. For higher cardinality buckets this is irrelevant as they are in most blocks.
     ///
     /// Use Roaring Bitmaps for sparse terms. The full bitvec is main memory consumer currently.
-    pub(crate) fn get_union_from_term_infos(
+    pub fn get_union_from_term_infos(
         term_infos: &[TermInfo],
         reader: &SegmentReader,
         inverted_index: &InvertedIndexReader,

src/query/union/simple_union.rs

@@ -12,7 +12,7 @@ pub struct SimpleUnion<TDocSet> {
 }
 
 impl<TDocSet: DocSet> SimpleUnion<TDocSet> {
-    pub(crate) fn build(mut docsets: Vec<TDocSet>) -> SimpleUnion<TDocSet> {
+    pub fn build(mut docsets: Vec<TDocSet>) -> SimpleUnion<TDocSet> {
         docsets.retain(|docset| docset.doc() != TERMINATED);
         let mut docset = SimpleUnion { docsets, doc: 0 };