Raise matching floor: boundary tokenizer, stemming/folding/stopwords, boosts, snippets, engine seam

src/engine.rs

@@ -0,0 +1,67 @@
+use anyhow::Result;
+
+use crate::index::{LocalIndex, SearchHit};
+
+pub struct EngineOutput {
+    pub hits: Vec<SearchHit>,
+    pub total: Option<u64>,
+}
+
+pub trait SearchEngine: Send + Sync {
+    fn search(&self, text: &str, budget: usize, only_shared: bool) -> Result<EngineOutput>;
+    fn doc_count(&self) -> u64;
+}
+
+pub struct TantivyEngine {
+    pub index: LocalIndex,
+    pub min_coverage: f64,
+}
+
+impl SearchEngine for TantivyEngine {
+    fn search(&self, text: &str, budget: usize, only_shared: bool) -> Result<EngineOutput> {
+        let (hits, total) =
+            self.index
+                .search_with_coverage(text, budget, only_shared, self.min_coverage)?;
+        Ok(EngineOutput {
+            hits,
+            total: Some(total),
+        })
+    }
+
+    fn doc_count(&self) -> u64 {
+        self.index.doc_count()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::index::Collection;
+    use crate::message::EXPOSURE_FULL;
+    use std::fs;
+
+    #[test]
+    fn tantivy_engine_reports_hits_and_total() {
+        let temp = tempfile::tempdir().unwrap();
+        let dir = temp.path().join("corpus");
+        fs::create_dir_all(&dir).unwrap();
+        fs::write(dir.join("a.txt"), "rust ownership guide").unwrap();
+        let engine = TantivyEngine {
+            index: LocalIndex::open(&temp.path().join("index")).unwrap(),
+            min_coverage: 0.4,
+        };
+        engine
+            .index
+            .add_collection(&Collection {
+                name: "docs".to_string(),
+                path: dir.display().to_string(),
+                shared: true,
+                exposure: EXPOSURE_FULL.to_string(),
+            })
+            .unwrap();
+        let output = engine.search("rust", 5, false).unwrap();
+        assert_eq!(output.hits.len(), 1);
+        assert_eq!(output.total, Some(1));
+        assert_eq!(engine.doc_count(), 1);
+    }
+}