Closes #896 - Facet reader related

Bugfix. Acquiring a facet reader on a segment that does not contain any
doc with this facet returns `None`.

CHANGELOG.md

@@ -1,3 +1,14 @@
+Tantivy 0.13.2
+===================
+Bugfix. Acquiring a facet reader on a segment that does not contain any 
+doc with this facet returns `None`. (#896)
+
+Tantivy 0.13.1
+======================
+Made `Query` and `Collector` `Send + Sync`.
+Updated misc dependency versions.
+
+
 Tantivy 0.13.0
 ======================
 Tantivy 0.13 introduce a change in the index format that will require

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy"
-version = "0.13.0"
+version = "0.13.2"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
@@ -13,21 +13,21 @@ keywords = ["search", "information", "retrieval"]
 edition = "2018"
 
 [dependencies]
-base64 = "0.12.0"
-byteorder = "1.0"
-crc32fast = "1.2.0"
-once_cell = "1.0"
-regex ={version = "1.3.0", default-features = false, features = ["std"]}
+base64 = "0.12"
+byteorder = "1"
+crc32fast = "1"
+once_cell = "1"
+regex ={version = "1", default-features = false, features = ["std"]}
 tantivy-fst = "0.3"
 memmap = {version = "0.7", optional=true}
-lz4 = {version="1.20", optional=true}
+lz4 = {version="1", optional=true}
 snap = "1"
-atomicwrites = {version="0.2.2", optional=true}
-tempfile = "3.0"
+atomicwrites = {version="0.2", optional=true}
+tempfile = "3"
 log = "0.4"
-serde = {version="1.0", features=["derive"]}
-serde_json = "1.0"
-num_cpus = "1.2"
+serde = {version="1", features=["derive"]}
+serde_json = "1"
+num_cpus = "1"
 fs2={version="0.4", optional=true}
 levenshtein_automata = "0.2"
 notify = {version="4", optional=true}
@@ -35,20 +35,20 @@ uuid = { version = "0.8", features = ["v4", "serde"] }
 crossbeam = "0.7"
 futures = {version = "0.3",  features=["thread-pool"] }
 owning_ref = "0.4"
-stable_deref_trait = "1.0.0"
-rust-stemmers = "1.2"
-downcast-rs = { version="1.0" }
+stable_deref_trait = "1"
+rust-stemmers = "1"
+downcast-rs = "1"
 tantivy-query-grammar = { version="0.13", path="./query-grammar" }
 bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
 census = "0.4"
-fnv = "1.0.6"
+fnv = "1"
 owned-read = "0.4"
 failure = "0.1"
-htmlescape = "0.3.1"
+htmlescape = "0.3"
 fail = "0.4"
 murmurhash32 = "0.2"
 chrono = "0.4"
-smallvec = "1.0"
+smallvec = "1"
 rayon = "1"
 
 [target.'cfg(windows)'.dependencies]

examples/faceted_search_with_tweaked_score.rs

@@ -56,7 +56,7 @@ fn main() -> tantivy::Result<()> {
         );
         let top_docs_by_custom_score =
             TopDocs::with_limit(2).tweak_score(move |segment_reader: &SegmentReader| {
-                let mut ingredient_reader = segment_reader.facet_reader(ingredient).unwrap();
+                let ingredient_reader = segment_reader.facet_reader(ingredient).unwrap();
                 let facet_dict = ingredient_reader.facet_dict();
 
                 let query_ords: HashSet<u64> = facets

src/collector/custom_score_top_collector.rs

@@ -46,7 +46,7 @@ pub trait CustomScorer<TScore>: Sync {
 
 impl<TCustomScorer, TScore> Collector for CustomScoreTopCollector<TCustomScorer, TScore>
 where
-    TCustomScorer: CustomScorer<TScore>,
+    TCustomScorer: CustomScorer<TScore> + Send + Sync,
     TScore: 'static + PartialOrd + Clone + Send + Sync,
 {
     type Fruit = Vec<(TScore, DocAddress)>;

src/collector/mod.rs

@@ -133,7 +133,7 @@ impl<T> Fruit for T where T: Send + downcast_rs::Downcast {}
 /// The collection logic itself is in the `SegmentCollector`.
 ///
 /// Segments are not guaranteed to be visited in any specific order.
-pub trait Collector: Sync {
+pub trait Collector: Sync + Send {
     /// `Fruit` is the type for the result of our collection.
     /// e.g. `usize` for the `Count` collector.
     type Fruit: Fruit;

src/collector/top_score_collector.rs

@@ -324,7 +324,7 @@ impl TopDocs {
     where
         TScore: 'static + Send + Sync + Clone + PartialOrd,
         TScoreSegmentTweaker: ScoreSegmentTweaker<TScore> + 'static,
-        TScoreTweaker: ScoreTweaker<TScore, Child = TScoreSegmentTweaker>,
+        TScoreTweaker: ScoreTweaker<TScore, Child = TScoreSegmentTweaker> + Send + Sync,
     {
         TweakedScoreTopCollector::new(score_tweaker, self.0.into_tscore())
     }
@@ -438,7 +438,7 @@ impl TopDocs {
     where
         TScore: 'static + Send + Sync + Clone + PartialOrd,
         TCustomSegmentScorer: CustomSegmentScorer<TScore> + 'static,
-        TCustomScorer: CustomScorer<TScore, Child = TCustomSegmentScorer>,
+        TCustomScorer: CustomScorer<TScore, Child = TCustomSegmentScorer> + Send + Sync,
     {
         CustomScoreTopCollector::new(custom_score, self.0.into_tscore())
     }

src/collector/tweak_score_top_collector.rs

@@ -49,7 +49,7 @@ pub trait ScoreTweaker<TScore>: Sync {
 
 impl<TScoreTweaker, TScore> Collector for TweakedScoreTopCollector<TScoreTweaker, TScore>
 where
-    TScoreTweaker: ScoreTweaker<TScore>,
+    TScoreTweaker: ScoreTweaker<TScore> + Send + Sync,
     TScore: 'static + PartialOrd + Clone + Send + Sync,
 {
     type Fruit = Vec<(TScore, DocAddress)>;

src/core/segment_reader.rs

@@ -112,8 +112,10 @@ impl SegmentReader {
             return None;
         }
         let term_ords_reader = self.fast_fields().u64s(field)?;
-        let termdict_source = self.termdict_composite.open_read(field)?;
-        let termdict = TermDictionary::from_source(&termdict_source);
+        let termdict = self.termdict_composite
+            .open_read(field)
+            .map(|source| TermDictionary::from_source(&source))
+            .unwrap_or_else(TermDictionary::empty);
         let facet_reader = FacetReader::new(term_ords_reader, termdict);
         Some(facet_reader)
     }

src/fastfield/facet_reader.rs

@@ -73,7 +73,52 @@ impl FacetReader {
     }
 
     /// Return the list of facet ordinals associated to a document.
-    pub fn facet_ords(&mut self, doc: DocId, output: &mut Vec<u64>) {
+    pub fn facet_ords(&self, doc: DocId, output: &mut Vec<u64>) {
         self.term_ords.get_vals(doc, output);
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use crate::{Document, schema::{Facet, SchemaBuilder}};
+    use crate::Index;
+
+    #[test]
+    fn test_facet_not_populated_for_all_docs() -> crate::Result<()> {
+        let mut schema_builder = SchemaBuilder::default();
+        let facet_field = schema_builder.add_facet_field("facet");
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
+        index_writer.add_document(doc!(facet_field=>Facet::from_text("/a/b")));
+        index_writer.add_document(Document::default());
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
+        let facet_reader = searcher.segment_reader(0u32).facet_reader(facet_field).unwrap();
+        let mut facet_ords = Vec::new();
+        facet_reader.facet_ords(0u32, &mut facet_ords);
+        assert_eq!(&facet_ords, &[2u64]);
+        facet_reader.facet_ords(1u32, &mut facet_ords);
+        assert!(facet_ords.is_empty());
+        Ok(())
+    }
+    #[test]
+    fn test_facet_not_populated_for_any_docs() -> crate::Result<()> {
+        let mut schema_builder = SchemaBuilder::default();
+        let facet_field = schema_builder.add_facet_field("facet");
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
+        index_writer.add_document(Document::default());
+        index_writer.add_document(Document::default());
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
+        let facet_reader = searcher.segment_reader(0u32).facet_reader(facet_field).unwrap();
+        let mut facet_ords = Vec::new();
+        facet_reader.facet_ords(0u32, &mut facet_ords);
+        assert!(facet_ords.is_empty());
+        facet_reader.facet_ords(1u32, &mut facet_ords);
+        assert!(facet_ords.is_empty());
+        Ok(())
+    }
+}

src/fastfield/writer.rs

@@ -126,6 +126,7 @@ impl FastFieldsWriter {
         for field_writer in &self.single_value_writers {
             field_writer.serialize(serializer)?;
         }
+        
         for field_writer in &self.multi_values_writers {
             let field = field_writer.field();
             field_writer.serialize(serializer, mapping.get(&field))?;

src/indexer/segment_writer.rs

@@ -151,7 +151,7 @@ impl SegmentWriter {
                         if let Some(unordered_term_id) = unordered_term_id_opt {
                             self.fast_field_writers
                                 .get_multivalue_writer(field)
-                                .expect("multified writer for facet missing")
+                                .expect("writer for facet missing")
                                 .add_val(unordered_term_id);
                         }
                     }

src/query/query.rs

@@ -40,7 +40,7 @@ use std::fmt;
 ///
 /// When implementing a new type of `Query`, it is normal to implement a
 /// dedicated `Query`, `Weight` and `Scorer`.
-pub trait Query: QueryClone + downcast_rs::Downcast + fmt::Debug {
+pub trait Query: QueryClone + Send + Sync + downcast_rs::Downcast + fmt::Debug {
     /// Create the weight associated to a query.
     ///
     /// If scoring is not required, setting `scoring_enabled` to `false`