Merge branch 'issue/896' into main

CHANGELOG.md

@@ -4,6 +4,11 @@ Tantivy 0.14.0
 - Migrated tantivy error from the now deprecated `failure` crate to `thiserror` #760. (@hirevo)
 - API Change. Accessing the typed value off a `Schema::Value` now returns an Option instead of panicking if the type does not match. 
 
+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`.

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/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

@@ -128,6 +128,7 @@ 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

@@ -166,7 +166,7 @@ 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);
                         }
                     }