Added psuedocode for poll implementation

CHANGELOG.md

@@ -1,9 +1,6 @@
 Tantivy 0.12.0
 ======================
 - Removing static dispatch in tokenizers for simplicity. (#762)
-- Added backward iteration for `TermDictionary` stream. (@halvorboe)
-- Fixed a performance issue when searching for the posting lists of a missing term (@audunhalland)
-- Added a configurable maximum number of docs (10M by default) for a segment to be considered for merge (@hntd187, landed by @halvorboe #713) 
 
 ## How to update?
 

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy"
-version = "0.12.0"
+version = "0.11.3"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
@@ -18,7 +18,7 @@ byteorder = "1.0"
 crc32fast = "1.2.0"
 once_cell = "1.0"
 regex ={version = "1.3.0", default-features = false, features = ["std"]}
-tantivy-fst = "0.2.1"
+tantivy-fst = "0.2"
 memmap = {version = "0.7", optional=true}
 lz4 = {version="1.20", optional=true}
 snap = {version="0.2"}
@@ -60,6 +60,7 @@ winapi = "0.3"
 rand = "0.7"
 maplit = "1"
 matches = "0.1.8"
+time = "0.1.42"
 
 [dev-dependencies.fail]
 version = "0.3"

src/collector/count_collector.rs

@@ -1,6 +1,7 @@
 use super::Collector;
 use crate::collector::SegmentCollector;
 use crate::DocId;
+use crate::Result;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
@@ -43,11 +44,7 @@ impl Collector for Count {
 
     type Child = SegmentCountCollector;
 
-    fn for_segment(
+    fn for_segment(&self, _: SegmentLocalId, _: &SegmentReader) -> Result<SegmentCountCollector> {
-        &self,
-        _: SegmentLocalId,
-        _: &SegmentReader,
-    ) -> crate::Result<SegmentCountCollector> {
         Ok(SegmentCountCollector::default())
     }
 
@@ -55,7 +52,7 @@ impl Collector for Count {
         false
     }
 
-    fn merge_fruits(&self, segment_counts: Vec<usize>) -> crate::Result<usize> {
+    fn merge_fruits(&self, segment_counts: Vec<usize>) -> Result<usize> {
         Ok(segment_counts.into_iter().sum())
     }
 }

src/collector/custom_score_top_collector.rs

@@ -1,5 +1,6 @@
 use crate::collector::top_collector::{TopCollector, TopSegmentCollector};
 use crate::collector::{Collector, SegmentCollector};
+use crate::Result;
 use crate::{DocAddress, DocId, Score, SegmentReader};
 
 pub(crate) struct CustomScoreTopCollector<TCustomScorer, TScore = Score> {
@@ -41,7 +42,7 @@ pub trait CustomScorer<TScore>: Sync {
     type Child: CustomSegmentScorer<TScore>;
     /// Builds a child scorer for a specific segment. The child scorer is associated to
     /// a specific segment.
-    fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child>;
+    fn segment_scorer(&self, segment_reader: &SegmentReader) -> Result<Self::Child>;
 }
 
 impl<TCustomScorer, TScore> Collector for CustomScoreTopCollector<TCustomScorer, TScore>
@@ -57,7 +58,7 @@ where
         &self,
         segment_local_id: u32,
         segment_reader: &SegmentReader,
-    ) -> crate::Result<Self::Child> {
+    ) -> Result<Self::Child> {
         let segment_scorer = self.custom_scorer.segment_scorer(segment_reader)?;
         let segment_collector = self
             .collector
@@ -72,7 +73,7 @@ where
         false
     }
 
-    fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
+    fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> Result<Self::Fruit> {
         self.collector.merge_fruits(segment_fruits)
     }
 }
@@ -110,7 +111,7 @@ where
 {
     type Child = T;
 
-    fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child> {
+    fn segment_scorer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
         Ok((self)(segment_reader))
     }
 }

src/collector/facet_collector.rs

@@ -5,6 +5,7 @@ use crate::fastfield::FacetReader;
 use crate::schema::Facet;
 use crate::schema::Field;
 use crate::DocId;
+use crate::Result;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
@@ -83,9 +84,9 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
 /// use tantivy::collector::FacetCollector;
 /// use tantivy::query::AllQuery;
 /// use tantivy::schema::{Facet, Schema, TEXT};
-/// use tantivy::{doc, Index};
+/// use tantivy::{doc, Index, Result};
 ///
-/// fn example() -> tantivy::Result<()> {
+/// fn example() -> Result<()> {
 ///     let mut schema_builder = Schema::builder();
 ///
 ///     // Facet have their own specific type.
@@ -261,7 +262,7 @@ impl Collector for FacetCollector {
         &self,
         _: SegmentLocalId,
         reader: &SegmentReader,
-    ) -> crate::Result<FacetSegmentCollector> {
+    ) -> Result<FacetSegmentCollector> {
         let field_name = reader.schema().get_field_name(self.field);
         let facet_reader = reader.facet_reader(self.field).ok_or_else(|| {
             TantivyError::SchemaError(format!("Field {:?} is not a facet field.", field_name))
@@ -327,7 +328,7 @@ impl Collector for FacetCollector {
         false
     }
 
-    fn merge_fruits(&self, segments_facet_counts: Vec<FacetCounts>) -> crate::Result<FacetCounts> {
+    fn merge_fruits(&self, segments_facet_counts: Vec<FacetCounts>) -> Result<FacetCounts> {
         let mut facet_counts: BTreeMap<Facet, u64> = BTreeMap::new();
         for segment_facet_counts in segments_facet_counts {
             for (facet, count) in segment_facet_counts.facet_counts {

src/collector/mod.rs

@@ -85,6 +85,7 @@ See the `custom_collector` example.
 */
 
 use crate::DocId;
+use crate::Result;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
@@ -146,14 +147,14 @@ pub trait Collector: Sync {
         &self,
         segment_local_id: SegmentLocalId,
         segment: &SegmentReader,
-    ) -> crate::Result<Self::Child>;
+    ) -> Result<Self::Child>;
 
     /// Returns true iff the collector requires to compute scores for documents.
     fn requires_scoring(&self) -> bool;
 
     /// Combines the fruit associated to the collection of each segments
     /// into one fruit.
-    fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> crate::Result<Self::Fruit>;
+    fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> Result<Self::Fruit>;
 }
 
 /// The `SegmentCollector` is the trait in charge of defining the
@@ -184,11 +185,7 @@ where
     type Fruit = (Left::Fruit, Right::Fruit);
     type Child = (Left::Child, Right::Child);
 
-    fn for_segment(
+    fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
-        &self,
-        segment_local_id: u32,
-        segment: &SegmentReader,
-    ) -> crate::Result<Self::Child> {
         let left = self.0.for_segment(segment_local_id, segment)?;
         let right = self.1.for_segment(segment_local_id, segment)?;
         Ok((left, right))
@@ -201,7 +198,7 @@ where
     fn merge_fruits(
         &self,
         children: Vec<(Left::Fruit, Right::Fruit)>,
-    ) -> crate::Result<(Left::Fruit, Right::Fruit)> {
+    ) -> Result<(Left::Fruit, Right::Fruit)> {
         let mut left_fruits = vec![];
         let mut right_fruits = vec![];
         for (left_fruit, right_fruit) in children {
@@ -243,11 +240,7 @@ where
     type Fruit = (One::Fruit, Two::Fruit, Three::Fruit);
     type Child = (One::Child, Two::Child, Three::Child);
 
-    fn for_segment(
+    fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
-        &self,
-        segment_local_id: u32,
-        segment: &SegmentReader,
-    ) -> crate::Result<Self::Child> {
         let one = self.0.for_segment(segment_local_id, segment)?;
         let two = self.1.for_segment(segment_local_id, segment)?;
         let three = self.2.for_segment(segment_local_id, segment)?;
@@ -258,7 +251,7 @@ where
         self.0.requires_scoring() || self.1.requires_scoring() || self.2.requires_scoring()
     }
 
-    fn merge_fruits(&self, children: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
+    fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
         let mut one_fruits = vec![];
         let mut two_fruits = vec![];
         let mut three_fruits = vec![];
@@ -306,11 +299,7 @@ where
     type Fruit = (One::Fruit, Two::Fruit, Three::Fruit, Four::Fruit);
     type Child = (One::Child, Two::Child, Three::Child, Four::Child);
 
-    fn for_segment(
+    fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
-        &self,
-        segment_local_id: u32,
-        segment: &SegmentReader,
-    ) -> crate::Result<Self::Child> {
         let one = self.0.for_segment(segment_local_id, segment)?;
         let two = self.1.for_segment(segment_local_id, segment)?;
         let three = self.2.for_segment(segment_local_id, segment)?;
@@ -325,7 +314,7 @@ where
             || self.3.requires_scoring()
     }
 
-    fn merge_fruits(&self, children: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
+    fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
         let mut one_fruits = vec![];
         let mut two_fruits = vec![];
         let mut three_fruits = vec![];

src/collector/multi_collector.rs

@@ -2,6 +2,7 @@ use super::Collector;
 use super::SegmentCollector;
 use crate::collector::Fruit;
 use crate::DocId;
+use crate::Result;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
@@ -23,7 +24,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
         &self,
         segment_local_id: u32,
         reader: &SegmentReader,
-    ) -> crate::Result<Box<dyn BoxableSegmentCollector>> {
+    ) -> Result<Box<dyn BoxableSegmentCollector>> {
         let child = self.0.for_segment(segment_local_id, reader)?;
         Ok(Box::new(SegmentCollectorWrapper(child)))
     }
@@ -32,10 +33,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
         self.0.requires_scoring()
     }
 
-    fn merge_fruits(
+    fn merge_fruits(&self, children: Vec<<Self as Collector>::Fruit>) -> Result<Box<dyn Fruit>> {
-        &self,
-        children: Vec<<Self as Collector>::Fruit>,
-    ) -> crate::Result<Box<dyn Fruit>> {
         let typed_fruit: Vec<TCollector::Fruit> = children
             .into_iter()
             .map(|untyped_fruit| {
@@ -46,7 +44,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
                         TantivyError::InvalidArgument("Failed to cast child fruit.".to_string())
                     })
             })
-            .collect::<crate::Result<_>>()?;
+            .collect::<Result<_>>()?;
         let merged_fruit = self.0.merge_fruits(typed_fruit)?;
         Ok(Box::new(merged_fruit))
     }
@@ -177,12 +175,12 @@ impl<'a> Collector for MultiCollector<'a> {
         &self,
         segment_local_id: SegmentLocalId,
         segment: &SegmentReader,
-    ) -> crate::Result<MultiCollectorChild> {
+    ) -> Result<MultiCollectorChild> {
         let children = self
             .collector_wrappers
             .iter()
             .map(|collector_wrapper| collector_wrapper.for_segment(segment_local_id, segment))
-            .collect::<crate::Result<Vec<_>>>()?;
+            .collect::<Result<Vec<_>>>()?;
         Ok(MultiCollectorChild { children })
     }
 
@@ -193,7 +191,7 @@ impl<'a> Collector for MultiCollector<'a> {
             .any(Collector::requires_scoring)
     }
 
-    fn merge_fruits(&self, segments_multifruits: Vec<MultiFruit>) -> crate::Result<MultiFruit> {
+    fn merge_fruits(&self, segments_multifruits: Vec<MultiFruit>) -> Result<MultiFruit> {
         let mut segment_fruits_list: Vec<Vec<Box<dyn Fruit>>> = (0..self.collector_wrappers.len())
             .map(|_| Vec::with_capacity(segments_multifruits.len()))
             .collect::<Vec<_>>();
@@ -211,7 +209,7 @@ impl<'a> Collector for MultiCollector<'a> {
             .map(|(child_collector, segment_fruits)| {
                 Ok(Some(child_collector.merge_fruits(segment_fruits)?))
             })
-            .collect::<crate::Result<_>>()?;
+            .collect::<Result<_>>()?;
         Ok(MultiFruit { sub_fruits })
     }
 }

src/collector/tests.rs

@@ -55,7 +55,7 @@ impl Collector for TestCollector {
         &self,
         segment_id: SegmentLocalId,
         _reader: &SegmentReader,
-    ) -> crate::Result<TestSegmentCollector> {
+    ) -> Result<TestSegmentCollector> {
         Ok(TestSegmentCollector {
             segment_id,
             fruit: TestFruit::default(),
@@ -66,7 +66,7 @@ impl Collector for TestCollector {
         self.compute_score
     }
 
-    fn merge_fruits(&self, mut children: Vec<TestFruit>) -> crate::Result<TestFruit> {
+    fn merge_fruits(&self, mut children: Vec<TestFruit>) -> Result<TestFruit> {
         children.sort_by_key(|fruit| {
             if fruit.docs().is_empty() {
                 0
@@ -124,7 +124,7 @@ impl Collector for FastFieldTestCollector {
         &self,
         _: SegmentLocalId,
         segment_reader: &SegmentReader,
-    ) -> crate::Result<FastFieldSegmentCollector> {
+    ) -> Result<FastFieldSegmentCollector> {
         let reader = segment_reader
             .fast_fields()
             .u64(self.field)
@@ -139,7 +139,7 @@ impl Collector for FastFieldTestCollector {
         false
     }
 
-    fn merge_fruits(&self, children: Vec<Vec<u64>>) -> crate::Result<Vec<u64>> {
+    fn merge_fruits(&self, children: Vec<Vec<u64>>) -> Result<Vec<u64>> {
         Ok(children.into_iter().flat_map(|v| v.into_iter()).collect())
     }
 }
@@ -184,7 +184,7 @@ impl Collector for BytesFastFieldTestCollector {
         &self,
         _segment_local_id: u32,
         segment_reader: &SegmentReader,
-    ) -> crate::Result<BytesFastFieldSegmentCollector> {
+    ) -> Result<BytesFastFieldSegmentCollector> {
         Ok(BytesFastFieldSegmentCollector {
             vals: Vec::new(),
             reader: segment_reader
@@ -198,7 +198,7 @@ impl Collector for BytesFastFieldTestCollector {
         false
     }
 
-    fn merge_fruits(&self, children: Vec<Vec<u8>>) -> crate::Result<Vec<u8>> {
+    fn merge_fruits(&self, children: Vec<Vec<u8>>) -> Result<Vec<u8>> {
         Ok(children.into_iter().flat_map(|c| c.into_iter()).collect())
     }
 }

src/collector/top_collector.rs

@@ -1,5 +1,6 @@
 use crate::DocAddress;
 use crate::DocId;
+use crate::Result;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
 use serde::export::PhantomData;
@@ -85,7 +86,7 @@ where
     pub fn merge_fruits(
         &self,
         children: Vec<Vec<(T, DocAddress)>>,
-    ) -> crate::Result<Vec<(T, DocAddress)>> {
+    ) -> Result<Vec<(T, DocAddress)>> {
         if self.limit == 0 {
             return Ok(Vec::new());
         }
@@ -112,7 +113,7 @@ where
         &self,
         segment_id: SegmentLocalId,
         _: &SegmentReader,
-    ) -> crate::Result<TopSegmentCollector<F>> {
+    ) -> Result<TopSegmentCollector<F>> {
         Ok(TopSegmentCollector::new(segment_id, self.limit))
     }
 }

src/collector/top_score_collector.rs

@@ -10,6 +10,7 @@ use crate::fastfield::FastFieldReader;
 use crate::schema::Field;
 use crate::DocAddress;
 use crate::DocId;
+use crate::Result;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
@@ -83,9 +84,7 @@ impl CustomScorer<u64> for ScorerByField {
             .fast_fields()
             .u64(self.field)
             .ok_or_else(|| {
-                crate::TantivyError::SchemaError(format!(
+                crate::Error::SchemaError(format!("Field requested is not a i64/u64 fast field."))
-                    "Field requested is not a i64/u64 fast field."
-                ))
             })?;
         Ok(ScorerByFastFieldReader { ff_reader })
     }
@@ -104,7 +103,7 @@ impl TopDocs {
     ///
     /// ```rust
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{doc, Index, DocAddress};
+    /// # use tantivy::{doc, Index, Result, DocAddress};
     /// # use tantivy::query::{Query, QueryParser};
     /// use tantivy::Searcher;
     /// use tantivy::collector::TopDocs;
@@ -141,7 +140,7 @@ impl TopDocs {
     /// fn docs_sorted_by_rating(searcher: &Searcher,
     ///                          query: &dyn Query,
     ///                          sort_by_field: Field)
-    ///     -> tantivy::Result<Vec<(u64, DocAddress)>> {
+    ///     -> Result<Vec<(u64, DocAddress)>> {
     ///
     ///     // This is where we build our topdocs collector
     ///     //
@@ -407,7 +406,7 @@ impl Collector for TopDocs {
         &self,
         segment_local_id: SegmentLocalId,
         reader: &SegmentReader,
-    ) -> crate::Result<Self::Child> {
+    ) -> Result<Self::Child> {
         let collector = self.0.for_segment(segment_local_id, reader)?;
         Ok(TopScoreSegmentCollector(collector))
     }
@@ -416,10 +415,7 @@ impl Collector for TopDocs {
         true
     }
 
-    fn merge_fruits(
+    fn merge_fruits(&self, child_fruits: Vec<Vec<(Score, DocAddress)>>) -> Result<Self::Fruit> {
-        &self,
-        child_fruits: Vec<Vec<(Score, DocAddress)>>,
-    ) -> crate::Result<Self::Fruit> {
         self.0.merge_fruits(child_fruits)
     }
 }
@@ -613,7 +609,7 @@ mod tests {
         let segment = searcher.segment_reader(0);
         let top_collector = TopDocs::with_limit(4).order_by_u64_field(size);
         let err = top_collector.for_segment(0, segment);
-        if let Err(crate::TantivyError::SchemaError(msg)) = err {
+        if let Err(crate::Error::SchemaError(msg)) = err {
             assert_eq!(msg, "Field requested is not a i64/u64 fast field.");
         } else {
             assert!(false);

src/core/executor.rs

@@ -1,3 +1,4 @@
+use crate::Result;
 use crossbeam::channel;
 use rayon::{ThreadPool, ThreadPoolBuilder};
 
@@ -9,9 +10,7 @@ use rayon::{ThreadPool, ThreadPoolBuilder};
 /// API of a dependency, knowing it might conflict with a different version
 /// used by the client. Second, we may stop using rayon in the future.
 pub enum Executor {
-    /// Single thread variant of an Executor
     SingleThread,
-    /// Thread pool variant of an Executor
     ThreadPool(ThreadPool),
 }
 
@@ -21,8 +20,8 @@ impl Executor {
         Executor::SingleThread
     }
 
-    /// Creates an Executor that dispatches the tasks in a thread pool.
+    // Creates an Executor that dispatches the tasks in a thread pool.
-    pub fn multi_thread(num_threads: usize, prefix: &'static str) -> crate::Result<Executor> {
+    pub fn multi_thread(num_threads: usize, prefix: &'static str) -> Result<Executor> {
         let pool = ThreadPoolBuilder::new()
             .num_threads(num_threads)
             .thread_name(move |num| format!("{}{}", prefix, num))
@@ -30,22 +29,22 @@ impl Executor {
         Ok(Executor::ThreadPool(pool))
     }
 
-    /// Perform a map in the thread pool.
+    // Perform a map in the thread pool.
-    ///
+    //
-    /// Regardless of the executor (`SingleThread` or `ThreadPool`), panics in the task
+    // Regardless of the executor (`SingleThread` or `ThreadPool`), panics in the task
-    /// will propagate to the caller.
+    // will propagate to the caller.
     pub fn map<
         A: Send,
         R: Send,
         AIterator: Iterator<Item = A>,
-        F: Sized + Sync + Fn(A) -> crate::Result<R>,
+        F: Sized + Sync + Fn(A) -> Result<R>,
     >(
         &self,
         f: F,
         args: AIterator,
-    ) -> crate::Result<Vec<R>> {
+    ) -> Result<Vec<R>> {
         match self {
-            Executor::SingleThread => args.map(f).collect::<crate::Result<_>>(),
+            Executor::SingleThread => args.map(f).collect::<Result<_>>(),
             Executor::ThreadPool(pool) => {
                 let args_with_indices: Vec<(usize, A)> = args.enumerate().collect();
                 let num_fruits = args_with_indices.len();

src/core/index.rs

@@ -22,6 +22,7 @@ use crate::schema::FieldType;
 use crate::schema::Schema;
 use crate::tokenizer::{TextAnalyzer, TokenizerManager};
 use crate::IndexWriter;
+use crate::Result;
 use num_cpus;
 use std::borrow::BorrowMut;
 use std::collections::HashSet;
@@ -30,10 +31,7 @@ use std::fmt;
 use std::path::{Path, PathBuf};
 use std::sync::Arc;
 
-fn load_metas(
+fn load_metas(directory: &dyn Directory, inventory: &SegmentMetaInventory) -> Result<IndexMeta> {
-    directory: &dyn Directory,
-    inventory: &SegmentMetaInventory,
-) -> crate::Result<IndexMeta> {
     let meta_data = directory.atomic_read(&META_FILEPATH)?;
     let meta_string = String::from_utf8_lossy(&meta_data);
     IndexMeta::deserialize(&meta_string, &inventory)
@@ -74,14 +72,14 @@ impl Index {
 
     /// Replace the default single thread search executor pool
     /// by a thread pool with a given number of threads.
-    pub fn set_multithread_executor(&mut self, num_threads: usize) -> crate::Result<()> {
+    pub fn set_multithread_executor(&mut self, num_threads: usize) -> Result<()> {
         self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-")?);
         Ok(())
     }
 
     /// Replace the default single thread search executor pool
     /// by a thread pool with a given number of threads.
-    pub fn set_default_multithread_executor(&mut self) -> crate::Result<()> {
+    pub fn set_default_multithread_executor(&mut self) -> Result<()> {
         let default_num_threads = num_cpus::get();
         self.set_multithread_executor(default_num_threads)
     }
@@ -100,10 +98,7 @@ impl Index {
     ///
     /// If a previous index was in this directory, then its meta file will be destroyed.
     #[cfg(feature = "mmap")]
-    pub fn create_in_dir<P: AsRef<Path>>(
+    pub fn create_in_dir<P: AsRef<Path>>(directory_path: P, schema: Schema) -> Result<Index> {
-        directory_path: P,
-        schema: Schema,
-    ) -> crate::Result<Index> {
         let mmap_directory = MmapDirectory::open(directory_path)?;
         if Index::exists(&mmap_directory) {
             return Err(TantivyError::IndexAlreadyExists);
@@ -112,7 +107,7 @@ impl Index {
     }
 
     /// Opens or creates a new index in the provided directory
-    pub fn open_or_create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
+    pub fn open_or_create<Dir: Directory>(dir: Dir, schema: Schema) -> Result<Index> {
         if !Index::exists(&dir) {
             return Index::create(dir, schema);
         }
@@ -135,13 +130,13 @@ impl Index {
     /// The temp directory is only used for testing the `MmapDirectory`.
     /// For other unit tests, prefer the `RAMDirectory`, see: `create_in_ram`.
     #[cfg(feature = "mmap")]
-    pub fn create_from_tempdir(schema: Schema) -> crate::Result<Index> {
+    pub fn create_from_tempdir(schema: Schema) -> Result<Index> {
         let mmap_directory = MmapDirectory::create_from_tempdir()?;
         Index::create(mmap_directory, schema)
     }
 
     /// Creates a new index given an implementation of the trait `Directory`
-    pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
+    pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> Result<Index> {
         let directory = ManagedDirectory::wrap(dir)?;
         Index::from_directory(directory, schema)
     }
@@ -149,7 +144,7 @@ impl Index {
     /// Create a new index from a directory.
     ///
     /// This will overwrite existing meta.json
-    fn from_directory(mut directory: ManagedDirectory, schema: Schema) -> crate::Result<Index> {
+    fn from_directory(mut directory: ManagedDirectory, schema: Schema) -> Result<Index> {
         save_new_metas(schema.clone(), directory.borrow_mut())?;
         let metas = IndexMeta::with_schema(schema);
         Index::create_from_metas(directory, &metas, SegmentMetaInventory::default())
@@ -160,7 +155,7 @@ impl Index {
         directory: ManagedDirectory,
         metas: &IndexMeta,
         inventory: SegmentMetaInventory,
-    ) -> crate::Result<Index> {
+    ) -> Result<Index> {
         let schema = metas.schema.clone();
         Ok(Index {
             directory,
@@ -177,7 +172,7 @@ impl Index {
     }
 
     /// Helper to access the tokenizer associated to a specific field.
-    pub fn tokenizer_for_field(&self, field: Field) -> crate::Result<TextAnalyzer> {
+    pub fn tokenizer_for_field(&self, field: Field) -> Result<TextAnalyzer> {
         let field_entry = self.schema.get_field_entry(field);
         let field_type = field_entry.field_type();
         let tokenizer_manager: &TokenizerManager = self.tokenizers();
@@ -200,7 +195,7 @@ impl Index {
     /// Create a default `IndexReader` for the given index.
     ///
     /// See [`Index.reader_builder()`](#method.reader_builder).
-    pub fn reader(&self) -> crate::Result<IndexReader> {
+    pub fn reader(&self) -> Result<IndexReader> {
         self.reader_builder().try_into()
     }
 
@@ -215,7 +210,7 @@ impl Index {
 
     /// Opens a new directory from an index path.
     #[cfg(feature = "mmap")]
-    pub fn open_in_dir<P: AsRef<Path>>(directory_path: P) -> crate::Result<Index> {
+    pub fn open_in_dir<P: AsRef<Path>>(directory_path: P) -> Result<Index> {
         let mmap_directory = MmapDirectory::open(directory_path)?;
         Index::open(mmap_directory)
     }
@@ -239,7 +234,7 @@ impl Index {
     }
 
     /// Open the index using the provided directory
-    pub fn open<D: Directory>(directory: D) -> crate::Result<Index> {
+    pub fn open<D: Directory>(directory: D) -> Result<Index> {
         let directory = ManagedDirectory::wrap(directory)?;
         let inventory = SegmentMetaInventory::default();
         let metas = load_metas(&directory, &inventory)?;
@@ -247,7 +242,7 @@ impl Index {
     }
 
     /// Reads the index meta file from the directory.
-    pub fn load_metas(&self) -> crate::Result<IndexMeta> {
+    pub fn load_metas(&self) -> Result<IndexMeta> {
         load_metas(self.directory(), &self.inventory)
     }
 
@@ -275,7 +270,7 @@ impl Index {
         &self,
         num_threads: usize,
         overall_heap_size_in_bytes: usize,
-    ) -> crate::Result<IndexWriter> {
+    ) -> Result<IndexWriter> {
         let directory_lock = self
             .directory
             .acquire_lock(&INDEX_WRITER_LOCK)
@@ -310,7 +305,7 @@ impl Index {
     /// If the lockfile already exists, returns `Error::FileAlreadyExists`.
     /// # Panics
     /// If the heap size per thread is too small, panics.
-    pub fn writer(&self, overall_heap_size_in_bytes: usize) -> crate::Result<IndexWriter> {
+    pub fn writer(&self, overall_heap_size_in_bytes: usize) -> Result<IndexWriter> {
         let mut num_threads = num_cpus::get();
         let heap_size_in_bytes_per_thread = overall_heap_size_in_bytes / num_threads;
         if heap_size_in_bytes_per_thread < HEAP_SIZE_MIN {
@@ -327,7 +322,7 @@ impl Index {
     }
 
     /// Returns the list of segments that are searchable
-    pub fn searchable_segments(&self) -> crate::Result<Vec<Segment>> {
+    pub fn searchable_segments(&self) -> Result<Vec<Segment>> {
         Ok(self
             .searchable_segment_metas()?
             .into_iter()
@@ -360,12 +355,12 @@ impl Index {
 
     /// Reads the meta.json and returns the list of
     /// `SegmentMeta` from the last commit.
-    pub fn searchable_segment_metas(&self) -> crate::Result<Vec<SegmentMeta>> {
+    pub fn searchable_segment_metas(&self) -> Result<Vec<SegmentMeta>> {
         Ok(self.load_metas()?.segments)
     }
 
     /// Returns the list of segment ids that are searchable.
-    pub fn searchable_segment_ids(&self) -> crate::Result<Vec<SegmentId>> {
+    pub fn searchable_segment_ids(&self) -> Result<Vec<SegmentId>> {
         Ok(self
             .searchable_segment_metas()?
             .iter()
@@ -374,7 +369,7 @@ impl Index {
     }
 
     /// Returns the set of corrupted files
-    pub fn validate_checksum(&self) -> crate::Result<HashSet<PathBuf>> {
+    pub fn validate_checksum(&self) -> Result<HashSet<PathBuf>> {
         self.directory.list_damaged().map_err(Into::into)
     }
 }

src/core/inverted_index_reader.rs

@@ -60,7 +60,7 @@ impl InvertedIndexReader {
             .get_index_record_option()
             .unwrap_or(IndexRecordOption::Basic);
         InvertedIndexReader {
-            termdict: TermDictionary::empty(),
+            termdict: TermDictionary::empty(&field_type),
             postings_source: ReadOnlySource::empty(),
             positions_source: ReadOnlySource::empty(),
             positions_idx_source: ReadOnlySource::empty(),

src/core/searcher.rs

@@ -14,6 +14,7 @@ use crate::store::StoreReader;
 use crate::termdict::TermMerger;
 use crate::DocAddress;
 use crate::Index;
+use crate::Result;
 use std::fmt;
 use std::sync::Arc;
 
@@ -22,7 +23,7 @@ fn collect_segment<C: Collector>(
     weight: &dyn Weight,
     segment_ord: u32,
     segment_reader: &SegmentReader,
-) -> crate::Result<C::Fruit> {
+) -> Result<C::Fruit> {
     let mut scorer = weight.scorer(segment_reader)?;
     let mut segment_collector = collector.for_segment(segment_ord as u32, segment_reader)?;
     if let Some(delete_bitset) = segment_reader.delete_bitset() {
@@ -77,7 +78,7 @@ impl Searcher {
     ///
     /// The searcher uses the segment ordinal to route the
     /// the request to the right `Segment`.
-    pub fn doc(&self, doc_address: DocAddress) -> crate::Result<Document> {
+    pub fn doc(&self, doc_address: DocAddress) -> Result<Document> {
         let DocAddress(segment_local_id, doc_id) = doc_address;
         let store_reader = &self.store_readers[segment_local_id as usize];
         store_reader.get(doc_id)
@@ -131,11 +132,7 @@ impl Searcher {
     ///
     ///  Finally, the Collector merges each of the child collectors into itself for result usability
     ///  by the caller.
-    pub fn search<C: Collector>(
+    pub fn search<C: Collector>(&self, query: &dyn Query, collector: &C) -> Result<C::Fruit> {
-        &self,
-        query: &dyn Query,
-        collector: &C,
-    ) -> crate::Result<C::Fruit> {
         let executor = self.index.search_executor();
         self.search_with_executor(query, collector, executor)
     }
@@ -157,7 +154,7 @@ impl Searcher {
         query: &dyn Query,
         collector: &C,
         executor: &Executor,
-    ) -> crate::Result<C::Fruit> {
+    ) -> Result<C::Fruit> {
         let scoring_enabled = collector.requires_scoring();
         let weight = query.weight(self, scoring_enabled)?;
         let segment_readers = self.segment_readers();

src/core/segment.rs

@@ -8,8 +8,10 @@ use crate::directory::{ReadOnlySource, WritePtr};
 use crate::indexer::segment_serializer::SegmentSerializer;
 use crate::schema::Schema;
 use crate::Opstamp;
+use crate::Result;
 use std::fmt;
 use std::path::PathBuf;
+use std::result;
 
 /// A segment is a piece of the index.
 #[derive(Clone)]
@@ -81,14 +83,20 @@ impl Segment {
     }
 
     /// Open one of the component file for a *regular* read.
-    pub fn open_read(&self, component: SegmentComponent) -> Result<ReadOnlySource, OpenReadError> {
+    pub fn open_read(
+        &self,
+        component: SegmentComponent,
+    ) -> result::Result<ReadOnlySource, OpenReadError> {
         let path = self.relative_path(component);
         let source = self.index.directory().open_read(&path)?;
         Ok(source)
     }
 
     /// Open one of the component file for *regular* write.
-    pub fn open_write(&mut self, component: SegmentComponent) -> Result<WritePtr, OpenWriteError> {
+    pub fn open_write(
+        &mut self,
+        component: SegmentComponent,
+    ) -> result::Result<WritePtr, OpenWriteError> {
         let path = self.relative_path(component);
         let write = self.index.directory_mut().open_write(&path)?;
         Ok(write)
@@ -101,5 +109,5 @@ pub trait SerializableSegment {
     ///
     /// # Returns
     /// The number of documents in the segment.
-    fn write(&self, serializer: SegmentSerializer) -> crate::Result<u32>;
+    fn write(&self, serializer: SegmentSerializer) -> Result<u32>;
 }

src/core/segment_reader.rs

@@ -16,6 +16,7 @@ use crate::space_usage::SegmentSpaceUsage;
 use crate::store::StoreReader;
 use crate::termdict::TermDictionary;
 use crate::DocId;
+use crate::Result;
 use fail::fail_point;
 use std::collections::HashMap;
 use std::fmt;
@@ -144,7 +145,7 @@ impl SegmentReader {
     }
 
     /// Open a new segment for reading.
-    pub fn open(segment: &Segment) -> crate::Result<SegmentReader> {
+    pub fn open(segment: &Segment) -> Result<SegmentReader> {
         let termdict_source = segment.open_read(SegmentComponent::TERMS)?;
         let termdict_composite = CompositeFile::open(&termdict_source)?;
 

src/directory/managed_directory.rs

@@ -150,7 +150,7 @@ impl ManagedDirectory {
                 }
                 Err(err) => {
                     error!("Failed to acquire lock for GC");
-                    return Err(crate::TantivyError::from(err));
+                    return Err(crate::Error::from(err));
                 }
             }
         }

src/directory/mmap_directory.rs

@@ -141,16 +141,24 @@ impl MmapCache {
     }
 }
 
-struct WatcherWrapper {
+pub enum WatcherMode {
-    _watcher: Mutex<notify::PollWatcher>,
+    Event,
-    watcher_router: Arc<WatchCallbackList>,
+    Poll
 }
 
+struct WatcherWrapper {
+    _watcher: Mutex<notify::RecommendedWatcher>,
+    watcher_router: Arc<WatchCallbackList>,
+    watcher_mode: WatcherMode,
+}
+
+
+
 impl WatcherWrapper {
     pub fn new(path: &Path) -> Result<Self, OpenDirectoryError> {
         let (tx, watcher_recv): (Sender<RawEvent>, Receiver<RawEvent>) = channel();
         // We need to initialize the
-        let watcher = notify::poll::PollWatcher::with_delay_ms(tx, 1)
+        let watcher = notify::raw_watcher(tx)
             .and_then(|mut watcher| {
                 watcher.watch(path, RecursiveMode::Recursive)?;
                 Ok(watcher)
@@ -163,33 +171,57 @@ impl WatcherWrapper {
             })?;
         let watcher_router: Arc<WatchCallbackList> = Default::default();
         let watcher_router_clone = watcher_router.clone();
+        let path_clone = path.clone();
+        let meta_path = path_clone.join(*META_FILEPATH);
         thread::Builder::new()
             .name("meta-file-watch-thread".to_string())
             .spawn(move || {
+                let mut old_content = String::new();
+                let mode = WatcherMode::Event;
                 loop {
-                    match watcher_recv.recv().map(|evt| evt.path) {
+                    match mode {
-                        Ok(Some(changed_path)) => {
+                        WatcherMode::Event => {
-                            // ... Actually subject to false positive.
+                            match watcher_recv.recv().map(|evt| evt.path) {
-                            // We might want to be more accurate than this at one point.
+                                Ok(Some(changed_path)) => {
-                            if let Some(filename) = changed_path.file_name() {
+                                    // ... Actually subject to false positive.
-                                if filename == *META_FILEPATH {
+                                    // We might want to be more accurate than this at one point.
-                                    let _ = watcher_router_clone.broadcast();
+                                    if let Some(filename) = changed_path.file_name() {
+                                        if filename == *META_FILEPATH {
+                                            let _ = watcher_router_clone.broadcast();
+                                        }
+                                    }
+                                }
+                                Ok(None) => {
+                                    // not an event we are interested in.
+                                }
+                                Err(_e) => {
+                                    // the watch send channel was dropped
+                                    break;
                                 }
                             }
                         }
-                        Ok(None) => {
+                        WatcherMode::Poll => {
-                            // not an event we are interested in.
+                            let mut file = match File::open(&meta_path) {
+                                Err(why) => panic!("open: nope"),
+                                Ok(file) => file,
+                            };
+                            let mut new_content = String::new();
+                            match file.read_to_string(&mut new_content) {
+                                Err(why) => panic!("read: nope"),
+                                Ok(_) => {},
+                            }
+                            if old_content != new_content {
+                                let _ = watcher_router_clone.broadcast();
+                                old_content = new_content;
+                            }
                         }
-                        Err(_e) => {
+                    };
-                            // the watch send channel was dropped
-                            break;
-                        }
-                    }
                 }
             })?;
         Ok(WatcherWrapper {
             _watcher: Mutex::new(watcher),
             watcher_router,
+            watcher_mode: WatcherMode::Event,
         })
     }
 

src/fastfield/multivalued/mod.rs

@@ -7,6 +7,9 @@ pub use self::writer::MultiValueIntFastFieldWriter;
 #[cfg(test)]
 mod tests {
 
+    use time;
+
+    use self::time::Duration;
     use crate::collector::TopDocs;
     use crate::query::QueryParser;
     use crate::schema::Cardinality;
@@ -14,7 +17,6 @@ mod tests {
     use crate::schema::IntOptions;
     use crate::schema::Schema;
     use crate::Index;
-    use chrono::Duration;
 
     #[test]
     fn test_multivalued_u64() {

src/fastfield/readers.rs

@@ -4,6 +4,7 @@ use crate::fastfield::MultiValueIntFastFieldReader;
 use crate::fastfield::{FastFieldNotAvailableError, FastFieldReader};
 use crate::schema::{Cardinality, Field, FieldType, Schema};
 use crate::space_usage::PerFieldSpaceUsage;
+use crate::Result;
 use std::collections::HashMap;
 
 /// Provides access to all of the FastFieldReader.
@@ -53,7 +54,7 @@ impl FastFieldReaders {
     pub(crate) fn load_all(
         schema: &Schema,
         fast_fields_composite: &CompositeFile,
-    ) -> crate::Result<FastFieldReaders> {
+    ) -> Result<FastFieldReaders> {
         let mut fast_field_readers = FastFieldReaders {
             fast_field_i64: Default::default(),
             fast_field_u64: Default::default(),

src/indexer/index_writer.rs

@@ -897,7 +897,7 @@ mod tests {
         let index_writer = index.writer(3_000_000).unwrap();
         assert_eq!(
             format!("{:?}", index_writer.get_merge_policy()),
-            "LogMergePolicy { min_merge_size: 8, max_merge_size: 10000000, min_layer_size: 10000, \
+            "LogMergePolicy { min_merge_size: 8, min_layer_size: 10000, \
              level_log_size: 0.75 }"
         );
         let merge_policy = Box::new(NoMergePolicy::default());

src/indexer/log_merge_policy.rs

@@ -6,14 +6,12 @@ use std::f64;
 const DEFAULT_LEVEL_LOG_SIZE: f64 = 0.75;
 const DEFAULT_MIN_LAYER_SIZE: u32 = 10_000;
 const DEFAULT_MIN_MERGE_SIZE: usize = 8;
-const DEFAULT_MAX_MERGE_SIZE: usize = 10_000_000;
 
 /// `LogMergePolicy` tries tries to merge segments that have a similar number of
 /// documents.
 #[derive(Debug, Clone)]
 pub struct LogMergePolicy {
     min_merge_size: usize,
-    max_merge_size: usize,
     min_layer_size: u32,
     level_log_size: f64,
 }
@@ -28,12 +26,6 @@ impl LogMergePolicy {
         self.min_merge_size = min_merge_size;
     }
 
-    /// Set the maximum number docs in a segment for it to be considered for
-    /// merging.
-    pub fn set_max_merge_size(&mut self, max_merge_size: usize) {
-        self.max_merge_size = max_merge_size;
-    }
-
     /// Set the minimum segment size under which all segment belong
     /// to the same level.
     pub fn set_min_layer_size(&mut self, min_layer_size: u32) {
@@ -61,7 +53,6 @@ impl MergePolicy for LogMergePolicy {
         let mut size_sorted_tuples = segments
             .iter()
             .map(SegmentMeta::num_docs)
-            .filter(|s| s <= &(self.max_merge_size as u32))
             .enumerate()
             .collect::<Vec<(usize, u32)>>();
 
@@ -95,7 +86,6 @@ impl Default for LogMergePolicy {
     fn default() -> LogMergePolicy {
         LogMergePolicy {
             min_merge_size: DEFAULT_MIN_MERGE_SIZE,
-            max_merge_size: DEFAULT_MAX_MERGE_SIZE,
             min_layer_size: DEFAULT_MIN_LAYER_SIZE,
             level_log_size: DEFAULT_LEVEL_LOG_SIZE,
         }
@@ -114,7 +104,6 @@ mod tests {
     fn test_merge_policy() -> LogMergePolicy {
         let mut log_merge_policy = LogMergePolicy::default();
         log_merge_policy.set_min_merge_size(3);
-        log_merge_policy.set_max_merge_size(100_000);
         log_merge_policy.set_min_layer_size(2);
         log_merge_policy
     }
@@ -152,11 +141,11 @@ mod tests {
             create_random_segment_meta(10),
             create_random_segment_meta(10),
             create_random_segment_meta(10),
-            create_random_segment_meta(1_000),
+            create_random_segment_meta(1000),
-            create_random_segment_meta(1_000),
+            create_random_segment_meta(1000),
-            create_random_segment_meta(1_000),
+            create_random_segment_meta(1000),
-            create_random_segment_meta(10_000),
+            create_random_segment_meta(10000),
-            create_random_segment_meta(10_000),
+            create_random_segment_meta(10000),
             create_random_segment_meta(10),
             create_random_segment_meta(10),
             create_random_segment_meta(10),
@@ -193,19 +182,4 @@ mod tests {
         let result_list = test_merge_policy().compute_merge_candidates(&test_input);
         assert_eq!(result_list.len(), 1);
     }
-
-    #[test]
-    fn test_large_merge_segments() {
-        let test_input = vec![
-            create_random_segment_meta(1_000_000),
-            create_random_segment_meta(100_001),
-            create_random_segment_meta(100_000),
-            create_random_segment_meta(100_000),
-            create_random_segment_meta(100_000),
-        ];
-        let result_list = test_merge_policy().compute_merge_candidates(&test_input);
-        // Do not include large segments
-        assert_eq!(result_list.len(), 1);
-        assert_eq!(result_list[0].0.len(), 3)
-    }
 }

src/indexer/merger.rs

@@ -21,6 +21,8 @@ use crate::store::StoreWriter;
 use crate::termdict::TermMerger;
 use crate::termdict::TermOrdinal;
 use crate::DocId;
+use crate::Result;
+use crate::TantivyError;
 use itertools::Itertools;
 use std::cmp;
 use std::collections::HashMap;
@@ -141,7 +143,7 @@ impl DeltaComputer {
 }
 
 impl IndexMerger {
-    pub fn open(schema: Schema, segments: &[Segment]) -> crate::Result<IndexMerger> {
+    pub fn open(schema: Schema, segments: &[Segment]) -> Result<IndexMerger> {
         let mut readers = vec![];
         let mut max_doc: u32 = 0u32;
         for segment in segments {
@@ -157,7 +159,7 @@ impl IndexMerger {
                  which exceeds the limit {}.",
                 max_doc, MAX_DOC_LIMIT
             );
-            return Err(crate::TantivyError::InvalidArgument(err_msg));
+            return Err(TantivyError::InvalidArgument(err_msg));
         }
         Ok(IndexMerger {
             schema,
@@ -166,10 +168,7 @@ impl IndexMerger {
         })
     }
 
-    fn write_fieldnorms(
+    fn write_fieldnorms(&self, fieldnorms_serializer: &mut FieldNormsSerializer) -> Result<()> {
-        &self,
-        fieldnorms_serializer: &mut FieldNormsSerializer,
-    ) -> crate::Result<()> {
         let fields = FieldNormsWriter::fields_with_fieldnorm(&self.schema);
         let mut fieldnorms_data = Vec::with_capacity(self.max_doc as usize);
         for field in fields {
@@ -190,7 +189,7 @@ impl IndexMerger {
         &self,
         fast_field_serializer: &mut FastFieldSerializer,
         mut term_ord_mappings: HashMap<Field, TermOrdinalMapping>,
-    ) -> crate::Result<()> {
+    ) -> Result<()> {
         for (field, field_entry) in self.schema.fields() {
             let field_type = field_entry.field_type();
             match *field_type {
@@ -235,7 +234,7 @@ impl IndexMerger {
         &self,
         field: Field,
         fast_field_serializer: &mut FastFieldSerializer,
-    ) -> crate::Result<()> {
+    ) -> Result<()> {
         let mut u64_readers = vec![];
         let mut min_value = u64::max_value();
         let mut max_value = u64::min_value();
@@ -285,7 +284,7 @@ impl IndexMerger {
         &self,
         field: Field,
         fast_field_serializer: &mut FastFieldSerializer,
-    ) -> crate::Result<()> {
+    ) -> Result<()> {
         let mut total_num_vals = 0u64;
         let mut u64s_readers: Vec<MultiValueIntFastFieldReader<u64>> = Vec::new();
 
@@ -332,7 +331,7 @@ impl IndexMerger {
         field: Field,
         term_ordinal_mappings: &TermOrdinalMapping,
         fast_field_serializer: &mut FastFieldSerializer,
-    ) -> crate::Result<()> {
+    ) -> Result<()> {
         // Multifastfield consists in 2 fastfields.
         // The first serves as an index into the second one and is stricly increasing.
         // The second contains the actual values.
@@ -372,7 +371,7 @@ impl IndexMerger {
         &self,
         field: Field,
         fast_field_serializer: &mut FastFieldSerializer,
-    ) -> crate::Result<()> {
+    ) -> Result<()> {
         // Multifastfield consists in 2 fastfields.
         // The first serves as an index into the second one and is stricly increasing.
         // The second contains the actual values.
@@ -437,7 +436,7 @@ impl IndexMerger {
         &self,
         field: Field,
         fast_field_serializer: &mut FastFieldSerializer,
-    ) -> crate::Result<()> {
+    ) -> Result<()> {
         let mut total_num_vals = 0u64;
         let mut bytes_readers: Vec<BytesFastFieldReader> = Vec::new();
 
@@ -493,7 +492,7 @@ impl IndexMerger {
         indexed_field: Field,
         field_type: &FieldType,
         serializer: &mut InvertedIndexSerializer,
-    ) -> crate::Result<Option<TermOrdinalMapping>> {
+    ) -> Result<Option<TermOrdinalMapping>> {
         let mut positions_buffer: Vec<u32> = Vec::with_capacity(1_000);
         let mut delta_computer = DeltaComputer::new();
         let field_readers = self
@@ -647,7 +646,7 @@ impl IndexMerger {
     fn write_postings(
         &self,
         serializer: &mut InvertedIndexSerializer,
-    ) -> crate::Result<HashMap<Field, TermOrdinalMapping>> {
+    ) -> Result<HashMap<Field, TermOrdinalMapping>> {
         let mut term_ordinal_mappings = HashMap::new();
         for (field, field_entry) in self.schema.fields() {
             if field_entry.is_indexed() {
@@ -661,7 +660,7 @@ impl IndexMerger {
         Ok(term_ordinal_mappings)
     }
 
-    fn write_storable_fields(&self, store_writer: &mut StoreWriter) -> crate::Result<()> {
+    fn write_storable_fields(&self, store_writer: &mut StoreWriter) -> Result<()> {
         for reader in &self.readers {
             let store_reader = reader.get_store_reader();
             if reader.num_deleted_docs() > 0 {
@@ -678,7 +677,7 @@ impl IndexMerger {
 }
 
 impl SerializableSegment for IndexMerger {
-    fn write(&self, mut serializer: SegmentSerializer) -> crate::Result<u32> {
+    fn write(&self, mut serializer: SegmentSerializer) -> Result<u32> {
         let term_ord_mappings = self.write_postings(serializer.get_postings_serializer())?;
         self.write_fieldnorms(serializer.get_fieldnorms_serializer())?;
         self.write_fast_fields(serializer.get_fast_field_serializer(), term_ord_mappings)?;

src/indexer/prepared_commit.rs

@@ -1,5 +1,6 @@
 use super::IndexWriter;
 use crate::Opstamp;
+use crate::Result;
 use futures::executor::block_on;
 
 /// A prepared commit
@@ -26,11 +27,11 @@ impl<'a> PreparedCommit<'a> {
         self.payload = Some(payload.to_string())
     }
 
-    pub fn abort(self) -> crate::Result<Opstamp> {
+    pub fn abort(self) -> Result<Opstamp> {
         self.index_writer.rollback()
     }
 
-    pub fn commit(self) -> crate::Result<Opstamp> {
+    pub fn commit(self) -> Result<Opstamp> {
         info!("committing {}", self.opstamp);
         let _ = block_on(
             self.index_writer

src/indexer/segment_manager.rs

@@ -4,6 +4,7 @@ use crate::core::SegmentMeta;
 use crate::error::TantivyError;
 use crate::indexer::delete_queue::DeleteCursor;
 use crate::indexer::SegmentEntry;
+use crate::Result as TantivyResult;
 use std::collections::hash_set::HashSet;
 use std::fmt::{self, Debug, Formatter};
 use std::sync::RwLock;
@@ -48,7 +49,7 @@ pub struct SegmentManager {
 }
 
 impl Debug for SegmentManager {
-    fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
+    fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), fmt::Error> {
         let lock = self.read();
         write!(
             f,
@@ -144,7 +145,7 @@ impl SegmentManager {
     /// Returns an error if some segments are missing, or if
     /// the `segment_ids` are not either all committed or all
     /// uncommitted.
-    pub fn start_merge(&self, segment_ids: &[SegmentId]) -> crate::Result<Vec<SegmentEntry>> {
+    pub fn start_merge(&self, segment_ids: &[SegmentId]) -> TantivyResult<Vec<SegmentEntry>> {
         let registers_lock = self.read();
         let mut segment_entries = vec![];
         if registers_lock.uncommitted.contains_all(segment_ids) {
@@ -187,7 +188,7 @@ impl SegmentManager {
             .segments_status(before_merge_segment_ids)
             .ok_or_else(|| {
                 warn!("couldn't find segment in SegmentManager");
-                crate::TantivyError::InvalidArgument(
+                crate::Error::InvalidArgument(
                     "The segments that were merged could not be found in the SegmentManager. \
                      This is not necessarily a bug, and can happen after a rollback for instance."
                         .to_string(),

src/indexer/segment_serializer.rs

@@ -1,3 +1,5 @@
+use crate::Result;
+
 use crate::core::Segment;
 use crate::core::SegmentComponent;
 use crate::fastfield::FastFieldSerializer;
@@ -16,7 +18,7 @@ pub struct SegmentSerializer {
 
 impl SegmentSerializer {
     /// Creates a new `SegmentSerializer`.
-    pub fn for_segment(segment: &mut Segment) -> crate::Result<SegmentSerializer> {
+    pub fn for_segment(segment: &mut Segment) -> Result<SegmentSerializer> {
         let store_write = segment.open_write(SegmentComponent::STORE)?;
 
         let fast_field_write = segment.open_write(SegmentComponent::FASTFIELDS)?;
@@ -55,7 +57,7 @@ impl SegmentSerializer {
     }
 
     /// Finalize the segment serialization.
-    pub fn close(self) -> crate::Result<()> {
+    pub fn close(self) -> Result<()> {
         self.fast_field_serializer.close()?;
         self.postings_serializer.close()?;
         self.store_writer.close()?;

src/indexer/segment_updater.rs

@@ -173,18 +173,14 @@ impl SegmentUpdater {
             .pool_size(1)
             .create()
             .map_err(|_| {
-                crate::TantivyError::SystemError(
+                crate::Error::SystemError("Failed to spawn segment updater thread".to_string())
-                    "Failed to spawn segment updater thread".to_string(),
-                )
             })?;
         let merge_thread_pool = ThreadPoolBuilder::new()
             .name_prefix("merge_thread")
             .pool_size(NUM_MERGE_THREADS)
             .create()
             .map_err(|_| {
-                crate::TantivyError::SystemError(
+                crate::Error::SystemError("Failed to spawn segment merging thread".to_string())
-                    "Failed to spawn segment merging thread".to_string(),
-                )
             })?;
         let index_meta = index.load_metas()?;
         Ok(SegmentUpdater(Arc::new(InnerSegmentUpdater {
@@ -226,7 +222,7 @@ impl SegmentUpdater {
         receiver.unwrap_or_else(|_| {
             let err_msg =
                 "A segment_updater future did not success. This should never happen.".to_string();
-            Err(crate::TantivyError::SystemError(err_msg))
+            Err(crate::Error::SystemError(err_msg))
         })
     }
 
@@ -423,7 +419,7 @@ impl SegmentUpdater {
         });
 
         Ok(merging_future_recv
-            .unwrap_or_else(|_| Err(crate::TantivyError::SystemError("Merge failed".to_string()))))
+            .unwrap_or_else(|_| Err(crate::Error::SystemError("Merge failed".to_string()))))
     }
 
     async fn consider_merge_options(&self) {

src/indexer/segment_writer.rs

@@ -16,13 +16,15 @@ use crate::tokenizer::{FacetTokenizer, TextAnalyzer};
 use crate::tokenizer::{TokenStreamChain, Tokenizer};
 use crate::DocId;
 use crate::Opstamp;
+use crate::Result;
+use crate::TantivyError;
 use std::io;
 use std::str;
 
 /// Computes the initial size of the hash table.
 ///
 /// Returns a number of bit `b`, such that the recommended initial table size is 2^b.
-fn initial_table_size(per_thread_memory_budget: usize) -> crate::Result<usize> {
+fn initial_table_size(per_thread_memory_budget: usize) -> Result<usize> {
     let table_memory_upper_bound = per_thread_memory_budget / 3;
     if let Some(limit) = (10..)
         .take_while(|num_bits: &usize| compute_table_size(*num_bits) < table_memory_upper_bound)
@@ -30,7 +32,7 @@ fn initial_table_size(per_thread_memory_budget: usize) -> crate::Result<usize> {
     {
         Ok(limit.min(19)) // we cap it at 2^19 = 512K.
     } else {
-        Err(crate::TantivyError::InvalidArgument(
+        Err(TantivyError::InvalidArgument(
             format!("per thread memory budget (={}) is too small. Raise the memory budget or lower the number of threads.", per_thread_memory_budget)))
     }
 }
@@ -64,7 +66,7 @@ impl SegmentWriter {
         memory_budget: usize,
         mut segment: Segment,
         schema: &Schema,
-    ) -> crate::Result<SegmentWriter> {
+    ) -> Result<SegmentWriter> {
         let table_num_bits = initial_table_size(memory_budget)?;
         let segment_serializer = SegmentSerializer::for_segment(&mut segment)?;
         let multifield_postings = MultiFieldPostingsWriter::new(schema, table_num_bits);
@@ -97,7 +99,7 @@ impl SegmentWriter {
     ///
     /// Finalize consumes the `SegmentWriter`, so that it cannot
     /// be used afterwards.
-    pub fn finalize(mut self) -> crate::Result<Vec<u64>> {
+    pub fn finalize(mut self) -> Result<Vec<u64>> {
         self.fieldnorms_writer.fill_up_to_max_doc(self.max_doc);
         write(
             &self.multifield_postings,
@@ -279,7 +281,7 @@ fn write(
     fast_field_writers: &FastFieldsWriter,
     fieldnorms_writer: &FieldNormsWriter,
     mut serializer: SegmentSerializer,
-) -> crate::Result<()> {
+) -> Result<()> {
     let term_ord_map = multifield_postings.serialize(serializer.get_postings_serializer())?;
     fast_field_writers.serialize(serializer.get_fast_field_serializer(), &term_ord_map)?;
     fieldnorms_writer.serialize(serializer.get_fieldnorms_serializer())?;
@@ -288,7 +290,7 @@ fn write(
 }
 
 impl SerializableSegment for SegmentWriter {
-    fn write(&self, serializer: SegmentSerializer) -> crate::Result<u32> {
+    fn write(&self, serializer: SegmentSerializer) -> Result<u32> {
         let max_doc = self.max_doc;
         write(
             &self.multifield_postings,

src/lib.rs

@@ -121,13 +121,13 @@ mod functional_test;
 mod macros;
 
 pub use crate::error::TantivyError;
+
+#[deprecated(since = "0.7.0", note = "please use `tantivy::TantivyError` instead")]
+pub use crate::error::TantivyError as Error;
 pub use chrono;
 
 /// Tantivy result.
-///
+pub type Result<T> = std::result::Result<T, error::TantivyError>;
-/// Within tantivy, please avoid importing `Result` using `use crate::Result`
-/// and instead, refer to this as `crate::Result<T>`.
-pub type Result<T> = std::result::Result<T, TantivyError>;
 
 /// Tantivy DateTime
 pub type DateTime = chrono::DateTime<chrono::Utc>;
@@ -161,7 +161,7 @@ pub use self::snippet::{Snippet, SnippetGenerator};
 mod docset;
 pub use self::docset::{DocSet, SkipResult};
 pub use crate::common::{f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
-pub use crate::core::{Executor, SegmentComponent};
+pub use crate::core::SegmentComponent;
 pub use crate::core::{Index, IndexMeta, Searcher, Segment, SegmentId, SegmentMeta};
 pub use crate::core::{InvertedIndexReader, SegmentReader};
 pub use crate::directory::Directory;

src/postings/postings_writer.rs

@@ -11,6 +11,7 @@ use crate::termdict::TermOrdinal;
 use crate::tokenizer::TokenStream;
 use crate::tokenizer::{Token, MAX_TOKEN_LEN};
 use crate::DocId;
+use crate::Result;
 use fnv::FnvHashMap;
 use std::collections::HashMap;
 use std::io;
@@ -128,7 +129,7 @@ impl MultiFieldPostingsWriter {
     pub fn serialize(
         &self,
         serializer: &mut InvertedIndexSerializer,
-    ) -> crate::Result<HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>> {
+    ) -> Result<HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>> {
         let mut term_offsets: Vec<(&[u8], Addr, UnorderedTermId)> =
             self.term_index.iter().collect();
         term_offsets.sort_unstable_by_key(|&(k, _, _)| k);

src/postings/serializer.rs

@@ -11,6 +11,7 @@ use crate::schema::Schema;
 use crate::schema::{Field, FieldEntry, FieldType};
 use crate::termdict::{TermDictionaryBuilder, TermOrdinal};
 use crate::DocId;
+use crate::Result;
 use std::io::{self, Write};
 
 /// `InvertedIndexSerializer` is in charge of serializing
@@ -60,7 +61,7 @@ impl InvertedIndexSerializer {
         positions_write: CompositeWrite<WritePtr>,
         positionsidx_write: CompositeWrite<WritePtr>,
         schema: Schema,
-    ) -> crate::Result<InvertedIndexSerializer> {
+    ) -> Result<InvertedIndexSerializer> {
         Ok(InvertedIndexSerializer {
             terms_write,
             postings_write,
@@ -71,7 +72,7 @@ impl InvertedIndexSerializer {
     }
 
     /// Open a new `PostingsSerializer` for the given segment
-    pub fn open(segment: &mut Segment) -> crate::Result<InvertedIndexSerializer> {
+    pub fn open(segment: &mut Segment) -> Result<InvertedIndexSerializer> {
         use crate::SegmentComponent::{POSITIONS, POSITIONSSKIP, POSTINGS, TERMS};
         InvertedIndexSerializer::create(
             CompositeWrite::wrap(segment.open_write(TERMS)?),
@@ -147,7 +148,8 @@ impl<'a> FieldSerializer<'a> {
             }
             _ => (false, false),
         };
-        let term_dictionary_builder = TermDictionaryBuilder::create(term_dictionary_write)?;
+        let term_dictionary_builder =
+            TermDictionaryBuilder::create(term_dictionary_write, &field_type)?;
         let postings_serializer =
             PostingsSerializer::new(postings_write, term_freq_enabled, position_enabled);
         let positions_serializer_opt = if position_enabled {

src/query/all_query.rs

@@ -4,6 +4,7 @@ use crate::docset::DocSet;
 use crate::query::explanation::does_not_match;
 use crate::query::{Explanation, Query, Scorer, Weight};
 use crate::DocId;
+use crate::Result;
 use crate::Score;
 
 /// Query that matches all of the documents.
@@ -13,7 +14,7 @@ use crate::Score;
 pub struct AllQuery;
 
 impl Query for AllQuery {
-    fn weight(&self, _: &Searcher, _: bool) -> crate::Result<Box<dyn Weight>> {
+    fn weight(&self, _: &Searcher, _: bool) -> Result<Box<dyn Weight>> {
         Ok(Box::new(AllWeight))
     }
 }
@@ -22,7 +23,7 @@ impl Query for AllQuery {
 pub struct AllWeight;
 
 impl Weight for AllWeight {
-    fn scorer(&self, reader: &SegmentReader) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader) -> Result<Box<dyn Scorer>> {
         Ok(Box::new(AllScorer {
             state: State::NotStarted,
             doc: 0u32,
@@ -30,7 +31,7 @@ impl Weight for AllWeight {
         }))
     }
 
-    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
         if doc >= reader.max_doc() {
             return Err(does_not_match(doc));
         }

src/query/boolean_query/boolean_query.rs

@@ -5,6 +5,7 @@ use crate::query::TermQuery;
 use crate::query::Weight;
 use crate::schema::IndexRecordOption;
 use crate::schema::Term;
+use crate::Result;
 use crate::Searcher;
 use std::collections::BTreeSet;
 
@@ -29,9 +30,9 @@ use std::collections::BTreeSet;
 ///use tantivy::query::{BooleanQuery, Occur, PhraseQuery, Query, TermQuery};
 ///use tantivy::schema::{IndexRecordOption, Schema, TEXT};
 ///use tantivy::Term;
-///use tantivy::Index;
+///use tantivy::{Index, Result};
 ///
-///fn main() -> tantivy::Result<()> {
+///fn main() -> Result<()> {
 ///    let mut schema_builder = Schema::builder();
 ///    let title = schema_builder.add_text_field("title", TEXT);
 ///    let body = schema_builder.add_text_field("body", TEXT);
@@ -148,14 +149,14 @@ impl From<Vec<(Occur, Box<dyn Query>)>> for BooleanQuery {
 }
 
 impl Query for BooleanQuery {
-    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> crate::Result<Box<dyn Weight>> {
+    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> Result<Box<dyn Weight>> {
         let sub_weights = self
             .subqueries
             .iter()
             .map(|&(ref occur, ref subquery)| {
                 Ok((*occur, subquery.weight(searcher, scoring_enabled)?))
             })
-            .collect::<crate::Result<_>>()?;
+            .collect::<Result<_>>()?;
         Ok(Box::new(BooleanWeight::new(sub_weights, scoring_enabled)))
     }
 

src/query/boolean_query/boolean_weight.rs

@@ -10,6 +10,7 @@ use crate::query::Scorer;
 use crate::query::Union;
 use crate::query::Weight;
 use crate::query::{intersect_scorers, Explanation};
+use crate::Result;
 use crate::{DocId, SkipResult};
 use std::collections::HashMap;
 
@@ -55,7 +56,7 @@ impl BooleanWeight {
     fn per_occur_scorers(
         &self,
         reader: &SegmentReader,
-    ) -> crate::Result<HashMap<Occur, Vec<Box<dyn Scorer>>>> {
+    ) -> Result<HashMap<Occur, Vec<Box<dyn Scorer>>>> {
         let mut per_occur_scorers: HashMap<Occur, Vec<Box<dyn Scorer>>> = HashMap::new();
         for &(ref occur, ref subweight) in &self.weights {
             let sub_scorer: Box<dyn Scorer> = subweight.scorer(reader)?;
@@ -70,7 +71,7 @@ impl BooleanWeight {
     fn complex_scorer<TScoreCombiner: ScoreCombiner>(
         &self,
         reader: &SegmentReader,
-    ) -> crate::Result<Box<dyn Scorer>> {
+    ) -> Result<Box<dyn Scorer>> {
         let mut per_occur_scorers = self.per_occur_scorers(reader)?;
 
         let should_scorer_opt: Option<Box<dyn Scorer>> = per_occur_scorers
@@ -112,7 +113,7 @@ impl BooleanWeight {
 }
 
 impl Weight for BooleanWeight {
-    fn scorer(&self, reader: &SegmentReader) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader) -> Result<Box<dyn Scorer>> {
         if self.weights.is_empty() {
             Ok(Box::new(EmptyScorer))
         } else if self.weights.len() == 1 {
@@ -129,7 +130,7 @@ impl Weight for BooleanWeight {
         }
     }
 
-    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
         let mut scorer = self.scorer(reader)?;
         if scorer.skip_next(doc) != SkipResult::Reached {
             return Err(does_not_match(doc));

src/query/empty_query.rs

@@ -4,6 +4,7 @@ use crate::query::Weight;
 use crate::query::{Explanation, Query};
 use crate::DocId;
 use crate::DocSet;
+use crate::Result;
 use crate::Score;
 use crate::Searcher;
 use crate::SegmentReader;
@@ -15,15 +16,11 @@ use crate::SegmentReader;
 pub struct EmptyQuery;
 
 impl Query for EmptyQuery {
-    fn weight(
+    fn weight(&self, _searcher: &Searcher, _scoring_enabled: bool) -> Result<Box<dyn Weight>> {
-        &self,
-        _searcher: &Searcher,
-        _scoring_enabled: bool,
-    ) -> crate::Result<Box<dyn Weight>> {
         Ok(Box::new(EmptyWeight))
     }
 
-    fn count(&self, _searcher: &Searcher) -> crate::Result<usize> {
+    fn count(&self, _searcher: &Searcher) -> Result<usize> {
         Ok(0)
     }
 }
@@ -33,11 +30,11 @@ impl Query for EmptyQuery {
 /// It is useful for tests and handling edge cases.
 pub struct EmptyWeight;
 impl Weight for EmptyWeight {
-    fn scorer(&self, _reader: &SegmentReader) -> crate::Result<Box<dyn Scorer>> {
+    fn scorer(&self, _reader: &SegmentReader) -> Result<Box<dyn Scorer>> {
         Ok(Box::new(EmptyScorer))
     }
 
-    fn explain(&self, _reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
+    fn explain(&self, _reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
         Err(does_not_match(doc))
     }
 }

src/query/fuzzy_query.rs

@@ -1,7 +1,8 @@
+use crate::error::TantivyError::InvalidArgument;
 use crate::query::{AutomatonWeight, Query, Weight};
 use crate::schema::Term;
+use crate::Result;
 use crate::Searcher;
-use crate::TantivyError::InvalidArgument;
 use levenshtein_automata::{LevenshteinAutomatonBuilder, DFA};
 use once_cell::sync::Lazy;
 use std::collections::HashMap;
@@ -30,9 +31,9 @@ static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Laz
 /// use tantivy::collector::{Count, TopDocs};
 /// use tantivy::query::FuzzyTermQuery;
 /// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, Index, Term};
+/// use tantivy::{doc, Index, Result, Term};
 ///
-/// fn example() -> tantivy::Result<()> {
+/// fn example() -> Result<()> {
 ///     let mut schema_builder = Schema::builder();
 ///     let title = schema_builder.add_text_field("title", TEXT);
 ///     let schema = schema_builder.build();
@@ -101,7 +102,7 @@ impl FuzzyTermQuery {
         }
     }
 
-    fn specialized_weight(&self) -> crate::Result<AutomatonWeight<DFA>> {
+    fn specialized_weight(&self) -> Result<AutomatonWeight<DFA>> {
         // LEV_BUILDER is a HashMap, whose `get` method returns an Option
         match LEV_BUILDER.get(&(self.distance, false)) {
             // Unwrap the option and build the Ok(AutomatonWeight)
@@ -118,11 +119,7 @@ impl FuzzyTermQuery {
 }
 
 impl Query for FuzzyTermQuery {
-    fn weight(
+    fn weight(&self, _searcher: &Searcher, _scoring_enabled: bool) -> Result<Box<dyn Weight>> {
-        &self,
-        _searcher: &Searcher,
-        _scoring_enabled: bool,
-    ) -> crate::Result<Box<dyn Weight>> {
         Ok(Box::new(self.specialized_weight()?))
     }
 }

src/query/phrase_query/phrase_query.rs

@@ -1,10 +1,12 @@
 use super::PhraseWeight;
 use crate::core::searcher::Searcher;
+use crate::error::TantivyError;
 use crate::query::bm25::BM25Weight;
 use crate::query::Query;
 use crate::query::Weight;
 use crate::schema::IndexRecordOption;
 use crate::schema::{Field, Term};
+use crate::Result;
 use std::collections::BTreeSet;
 
 /// `PhraseQuery` matches a specific sequence of words.
@@ -79,7 +81,7 @@ impl PhraseQuery {
         &self,
         searcher: &Searcher,
         scoring_enabled: bool,
-    ) -> crate::Result<PhraseWeight> {
+    ) -> Result<PhraseWeight> {
         let schema = searcher.schema();
         let field_entry = schema.get_field_entry(self.field);
         let has_positions = field_entry
@@ -89,7 +91,7 @@ impl PhraseQuery {
             .unwrap_or(false);
         if !has_positions {
             let field_name = field_entry.name();
-            return Err(crate::TantivyError::SchemaError(format!(
+            return Err(TantivyError::SchemaError(format!(
                 "Applied phrase query on field {:?}, which does not have positions indexed",
                 field_name
             )));
@@ -108,7 +110,7 @@ impl Query for PhraseQuery {
     /// Create the weight associated to a query.
     ///
     /// See [`Weight`](./trait.Weight.html).
-    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> crate::Result<Box<dyn Weight>> {
+    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> Result<Box<dyn Weight>> {
         let phrase_weight = self.phrase_weight(searcher, scoring_enabled)?;
         Ok(Box::new(phrase_weight))
     }

src/query/query.rs

@@ -2,6 +2,7 @@ use super::Weight;
 use crate::core::searcher::Searcher;
 use crate::query::Explanation;
 use crate::DocAddress;
+use crate::Result;
 use crate::Term;
 use downcast_rs::impl_downcast;
 use std::collections::BTreeSet;
@@ -47,17 +48,17 @@ pub trait Query: QueryClone + downcast_rs::Downcast + fmt::Debug {
     /// can increase performances.
     ///
     /// See [`Weight`](./trait.Weight.html).
-    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> crate::Result<Box<dyn Weight>>;
+    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> Result<Box<dyn Weight>>;
 
     /// Returns an `Explanation` for the score of the document.
-    fn explain(&self, searcher: &Searcher, doc_address: DocAddress) -> crate::Result<Explanation> {
+    fn explain(&self, searcher: &Searcher, doc_address: DocAddress) -> Result<Explanation> {
         let reader = searcher.segment_reader(doc_address.segment_ord());
         let weight = self.weight(searcher, true)?;
         weight.explain(reader, doc_address.doc())
     }
 
     /// Returns the number of documents matching the query.
-    fn count(&self, searcher: &Searcher) -> crate::Result<usize> {
+    fn count(&self, searcher: &Searcher) -> Result<usize> {
         let weight = self.weight(searcher, false)?;
         let mut result = 0;
         for reader in searcher.segment_readers() {
@@ -85,11 +86,11 @@ where
 }
 
 impl Query for Box<dyn Query> {
-    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> crate::Result<Box<dyn Weight>> {
+    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> Result<Box<dyn Weight>> {
         self.as_ref().weight(searcher, scoring_enabled)
     }
 
-    fn count(&self, searcher: &Searcher) -> crate::Result<usize> {
+    fn count(&self, searcher: &Searcher) -> Result<usize> {
         self.as_ref().count(searcher)
     }
 

src/query/regex_query.rs

@@ -1,6 +1,7 @@
 use crate::error::TantivyError;
 use crate::query::{AutomatonWeight, Query, Weight};
 use crate::schema::Field;
+use crate::Result;
 use crate::Searcher;
 use std::clone::Clone;
 use std::sync::Arc;
@@ -57,7 +58,7 @@ pub struct RegexQuery {
 
 impl RegexQuery {
     /// Creates a new RegexQuery from a given pattern
-    pub fn from_pattern(regex_pattern: &str, field: Field) -> crate::Result<Self> {
+    pub fn from_pattern(regex_pattern: &str, field: Field) -> Result<Self> {
         let regex = Regex::new(&regex_pattern)
             .map_err(|_| TantivyError::InvalidArgument(regex_pattern.to_string()))?;
         Ok(RegexQuery::from_regex(regex, field))
@@ -77,11 +78,7 @@ impl RegexQuery {
 }
 
 impl Query for RegexQuery {
-    fn weight(
+    fn weight(&self, _searcher: &Searcher, _scoring_enabled: bool) -> Result<Box<dyn Weight>> {
-        &self,
-        _searcher: &Searcher,
-        _scoring_enabled: bool,
-    ) -> crate::Result<Box<dyn Weight>> {
         Ok(Box::new(self.specialized_weight()))
     }
 }

src/query/term_query/term_query.rs

@@ -3,6 +3,7 @@ use crate::query::bm25::BM25Weight;
 use crate::query::Query;
 use crate::query::Weight;
 use crate::schema::IndexRecordOption;
+use crate::Result;
 use crate::Searcher;
 use crate::Term;
 use std::collections::BTreeSet;
@@ -100,7 +101,7 @@ impl TermQuery {
 }
 
 impl Query for TermQuery {
-    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> crate::Result<Box<dyn Weight>> {
+    fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> Result<Box<dyn Weight>> {
         Ok(Box::new(self.specialized_weight(searcher, scoring_enabled)))
     }
     fn query_terms(&self, term_set: &mut BTreeSet<Term>) {

src/reader/mod.rs

@@ -7,9 +7,11 @@ use crate::directory::Directory;
 use crate::directory::WatchHandle;
 use crate::directory::META_LOCK;
 use crate::Index;
+use crate::Result;
 use crate::Searcher;
 use crate::SegmentReader;
 use std::sync::Arc;
+use std::thread;
 
 /// Defines when a new version of the index should be reloaded.
 ///
@@ -61,7 +63,7 @@ impl IndexReaderBuilder {
     /// to open different segment readers. It may take hundreds of milliseconds
     /// of time and it may return an error.
     /// TODO(pmasurel) Use the `TryInto` trait once it is available in stable.
-    pub fn try_into(self) -> crate::Result<IndexReader> {
+    pub fn try_into(self) -> Result<IndexReader> {
         let inner_reader = InnerIndexReader {
             index: self.index,
             num_searchers: self.num_searchers,
@@ -120,14 +122,14 @@ struct InnerIndexReader {
 }
 
 impl InnerIndexReader {
-    fn reload(&self) -> crate::Result<()> {
+    fn reload(&self) -> Result<()> {
         let segment_readers: Vec<SegmentReader> = {
             let _meta_lock = self.index.directory().acquire_lock(&META_LOCK)?;
             let searchable_segments = self.searchable_segments()?;
             searchable_segments
                 .iter()
                 .map(SegmentReader::open)
-                .collect::<crate::Result<_>>()?
+                .collect::<Result<_>>()?
         };
         let schema = self.index.schema();
         let searchers = (0..self.num_searchers)
@@ -138,7 +140,7 @@ impl InnerIndexReader {
     }
 
     /// Returns the list of segments that are searchable
-    fn searchable_segments(&self) -> crate::Result<Vec<Segment>> {
+    fn searchable_segments(&self) -> Result<Vec<Segment>> {
         self.index.searchable_segments()
     }
 
@@ -175,7 +177,7 @@ impl IndexReader {
     ///
     /// This automatic reload can take 10s of milliseconds to kick in however, and in unit tests
     /// it can be nice to deterministically force the reload of searchers.
-    pub fn reload(&self) -> crate::Result<()> {
+    pub fn reload(&self) -> Result<()> {
         self.inner.reload()
     }
 

src/schema/facet.rs

@@ -122,11 +122,6 @@ impl Facet {
     pub fn to_path(&self) -> Vec<&str> {
         self.encoded_str().split(|c| c == FACET_SEP_CHAR).collect()
     }
-
-    /// This function is the inverse of Facet::from(&str).
-    pub fn to_path_string(&self) -> String {
-        format!("{}", self.to_string())
-    }
 }
 
 impl Borrow<str> for Facet {
@@ -270,21 +265,4 @@ mod tests {
         let facet = Facet::from_path(v.iter());
         assert_eq!(facet.to_path(), v);
     }
-
-    #[test]
-    fn test_to_path_string() {
-        let v = ["first", "second", "third/not_fourth"];
-        let facet = Facet::from_path(v.iter());
-        assert_eq!(
-            facet.to_path_string(),
-            String::from("/first/second/third\\/not_fourth")
-        );
-    }
-
-    #[test]
-    fn test_to_path_string_empty() {
-        let v: Vec<&str> = vec![];
-        let facet = Facet::from_path(v.iter());
-        assert_eq!(facet.to_path_string(), "/");
-    }
 }

src/snippet/mod.rs

@@ -3,6 +3,7 @@ use crate::schema::Field;
 use crate::schema::Value;
 use crate::tokenizer::{TextAnalyzer, Token};
 use crate::Document;
+use crate::Result;
 use crate::Searcher;
 use htmlescape::encode_minimal;
 use std::cmp::Ordering;
@@ -260,7 +261,7 @@ impl SnippetGenerator {
         searcher: &Searcher,
         query: &dyn Query,
         field: Field,
-    ) -> crate::Result<SnippetGenerator> {
+    ) -> Result<SnippetGenerator> {
         let mut terms = BTreeSet::new();
         query.query_terms(&mut terms);
         let terms_text: BTreeMap<String, f32> = terms

src/store/reader.rs

@@ -1,3 +1,5 @@
+use crate::Result;
+
 use super::decompress;
 use super::skiplist::SkipList;
 use crate::common::BinarySerializable;
@@ -73,7 +75,7 @@ impl StoreReader {
     ///
     /// It should not be called to score documents
     /// for instance.
-    pub fn get(&self, doc_id: DocId) -> crate::Result<Document> {
+    pub fn get(&self, doc_id: DocId) -> Result<Document> {
         let (first_doc_id, block_offset) = self.block_offset(doc_id);
         self.read_block(block_offset as usize)?;
         let current_block_mut = self.current_block.borrow_mut();

src/termdict/mod.rs

@@ -38,7 +38,7 @@ mod tests {
     use crate::core::Index;
     use crate::directory::{Directory, RAMDirectory, ReadOnlySource};
     use crate::postings::TermInfo;
-    use crate::schema::{Document, Schema, TEXT};
+    use crate::schema::{Document, FieldType, Schema, TEXT};
     use std::path::PathBuf;
     use std::str;
 
@@ -52,12 +52,6 @@ mod tests {
         }
     }
 
-    #[test]
-    fn test_empty_term_dictionary() {
-        let empty = TermDictionary::empty();
-        assert!(empty.stream().next().is_none());
-    }
-
     #[test]
     fn test_term_ordinals() {
         const COUNTRIES: [&'static str; 7] = [
@@ -73,7 +67,9 @@ mod tests {
         let path = PathBuf::from("TermDictionary");
         {
             let write = directory.open_write(&path).unwrap();
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(write).unwrap();
+            let field_type = FieldType::Str(TEXT);
+            let mut term_dictionary_builder =
+                TermDictionaryBuilder::create(write, &field_type).unwrap();
             for term in COUNTRIES.iter() {
                 term_dictionary_builder
                     .insert(term.as_bytes(), &make_term_info(0u64))
@@ -97,7 +93,9 @@ mod tests {
         let path = PathBuf::from("TermDictionary");
         {
             let write = directory.open_write(&path).unwrap();
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(write).unwrap();
+            let field_type = FieldType::Str(TEXT);
+            let mut term_dictionary_builder =
+                TermDictionaryBuilder::create(write, &field_type).unwrap();
             term_dictionary_builder
                 .insert("abc".as_bytes(), &make_term_info(34u64))
                 .unwrap();
@@ -181,8 +179,10 @@ mod tests {
         let ids: Vec<_> = (0u32..10_000u32)
             .map(|i| (format!("doc{:0>6}", i), i))
             .collect();
+        let field_type = FieldType::Str(TEXT);
         let buffer: Vec<u8> = {
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(vec![]).unwrap();
+            let mut term_dictionary_builder =
+                TermDictionaryBuilder::create(vec![], &field_type).unwrap();
             for &(ref id, ref i) in &ids {
                 term_dictionary_builder
                     .insert(id.as_bytes(), &make_term_info(*i as u64))
@@ -209,8 +209,10 @@ mod tests {
 
     #[test]
     fn test_stream_high_range_prefix_suffix() {
+        let field_type = FieldType::Str(TEXT);
         let buffer: Vec<u8> = {
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(vec![]).unwrap();
+            let mut term_dictionary_builder =
+                TermDictionaryBuilder::create(vec![], &field_type).unwrap();
             // term requires more than 16bits
             term_dictionary_builder
                 .insert("abcdefghijklmnopqrstuvwxy", &make_term_info(1))
@@ -242,8 +244,10 @@ mod tests {
         let ids: Vec<_> = (0u32..10_000u32)
             .map(|i| (format!("doc{:0>6}", i), i))
             .collect();
+        let field_type = FieldType::Str(TEXT);
         let buffer: Vec<u8> = {
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(vec![]).unwrap();
+            let mut term_dictionary_builder =
+                TermDictionaryBuilder::create(vec![], &field_type).unwrap();
             for &(ref id, ref i) in &ids {
                 term_dictionary_builder
                     .insert(id.as_bytes(), &make_term_info(*i as u64))
@@ -309,8 +313,10 @@ mod tests {
 
     #[test]
     fn test_empty_string() {
+        let field_type = FieldType::Str(TEXT);
         let buffer: Vec<u8> = {
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(vec![]).unwrap();
+            let mut term_dictionary_builder =
+                TermDictionaryBuilder::create(vec![], &field_type).unwrap();
             term_dictionary_builder
                 .insert(&[], &make_term_info(1 as u64))
                 .unwrap();
@@ -331,8 +337,10 @@ mod tests {
 
     #[test]
     fn test_stream_range_boundaries() {
+        let field_type = FieldType::Str(TEXT);
         let buffer: Vec<u8> = {
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(vec![]).unwrap();
+            let mut term_dictionary_builder =
+                TermDictionaryBuilder::create(vec![], &field_type).unwrap();
             for i in 0u8..10u8 {
                 let number_arr = [i; 1];
                 term_dictionary_builder
@@ -344,91 +352,41 @@ mod tests {
         let source = ReadOnlySource::from(buffer);
         let term_dictionary: TermDictionary = TermDictionary::from_source(&source);
 
-        let value_list = |mut streamer: TermStreamer<'_>, backwards: bool| {
+        let value_list = |mut streamer: TermStreamer<'_>| {
             let mut res: Vec<u32> = vec![];
             while let Some((_, ref v)) = streamer.next() {
                 res.push(v.doc_freq);
             }
-            if backwards {
-                res.reverse();
-            }
             res
         };
-        {
-            let range = term_dictionary.range().backward().into_stream();
-            assert_eq!(
-                value_list(range, true),
-                vec![0u32, 1u32, 2u32, 3u32, 4u32, 5u32, 6u32, 7u32, 8u32, 9u32]
-            );
-        }
         {
             let range = term_dictionary.range().ge([2u8]).into_stream();
             assert_eq!(
-                value_list(range, false),
+                value_list(range),
-                vec![2u32, 3u32, 4u32, 5u32, 6u32, 7u32, 8u32, 9u32]
-            );
-        }
-        {
-            let range = term_dictionary.range().ge([2u8]).backward().into_stream();
-            assert_eq!(
-                value_list(range, true),
                 vec![2u32, 3u32, 4u32, 5u32, 6u32, 7u32, 8u32, 9u32]
             );
         }
         {
             let range = term_dictionary.range().gt([2u8]).into_stream();
             assert_eq!(
-                value_list(range, false),
+                value_list(range),
-                vec![3u32, 4u32, 5u32, 6u32, 7u32, 8u32, 9u32]
-            );
-        }
-        {
-            let range = term_dictionary.range().gt([2u8]).backward().into_stream();
-            assert_eq!(
-                value_list(range, true),
                 vec![3u32, 4u32, 5u32, 6u32, 7u32, 8u32, 9u32]
             );
         }
         {
             let range = term_dictionary.range().lt([6u8]).into_stream();
-            assert_eq!(
+            assert_eq!(value_list(range), vec![0u32, 1u32, 2u32, 3u32, 4u32, 5u32]);
-                value_list(range, false),
-                vec![0u32, 1u32, 2u32, 3u32, 4u32, 5u32]
-            );
-        }
-        {
-            let range = term_dictionary.range().lt([6u8]).backward().into_stream();
-            assert_eq!(
-                value_list(range, true),
-                vec![0u32, 1u32, 2u32, 3u32, 4u32, 5u32]
-            );
         }
         {
             let range = term_dictionary.range().le([6u8]).into_stream();
             assert_eq!(
-                value_list(range, false),
+                value_list(range),
-                vec![0u32, 1u32, 2u32, 3u32, 4u32, 5u32, 6u32]
-            );
-        }
-        {
-            let range = term_dictionary.range().le([6u8]).backward().into_stream();
-            assert_eq!(
-                value_list(range, true),
                 vec![0u32, 1u32, 2u32, 3u32, 4u32, 5u32, 6u32]
             );
         }
         {
             let range = term_dictionary.range().ge([0u8]).lt([5u8]).into_stream();
-            assert_eq!(value_list(range, false), vec![0u32, 1u32, 2u32, 3u32, 4u32]);
+            assert_eq!(value_list(range), vec![0u32, 1u32, 2u32, 3u32, 4u32]);
-        }
-        {
-            let range = term_dictionary
-                .range()
-                .ge([0u8])
-                .lt([5u8])
-                .backward()
-                .into_stream();
-            assert_eq!(value_list(range, true), vec![0u32, 1u32, 2u32, 3u32, 4u32]);
         }
     }
 
@@ -450,7 +408,9 @@ mod tests {
         let path = PathBuf::from("TermDictionary");
         {
             let write = directory.open_write(&path).unwrap();
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(write).unwrap();
+            let field_type = FieldType::Str(TEXT);
+            let mut term_dictionary_builder =
+                TermDictionaryBuilder::create(write, &field_type).unwrap();
             for term in COUNTRIES.iter() {
                 term_dictionary_builder
                     .insert(term.as_bytes(), &make_term_info(0u64))

src/termdict/streamer.rs

@@ -51,12 +51,6 @@ where
         self
     }
 
-    /// Iterate over the range backwards.
-    pub fn backward(mut self) -> Self {
-        self.stream_builder = self.stream_builder.backward();
-        self
-    }
-
     /// Creates the stream corresponding to the range
     /// of terms defined using the `TermStreamerBuilder`.
     pub fn into_stream(self) -> TermStreamer<'a, A> {

src/termdict/termdict.rs

@@ -4,8 +4,8 @@ use crate::common::BinarySerializable;
 use crate::common::CountingWriter;
 use crate::directory::ReadOnlySource;
 use crate::postings::TermInfo;
+use crate::schema::FieldType;
 use crate::termdict::TermOrdinal;
-use once_cell::sync::Lazy;
 use std::io::{self, Write};
 use tantivy_fst;
 use tantivy_fst::raw::Fst;
@@ -29,7 +29,7 @@ where
     W: Write,
 {
     /// Creates a new `TermDictionaryBuilder`
-    pub fn create(w: W) -> io::Result<Self> {
+    pub fn create(w: W, _field_type: &FieldType) -> io::Result<Self> {
         let fst_builder = tantivy_fst::MapBuilder::new(w).map_err(convert_fst_error)?;
         Ok(TermDictionaryBuilder {
             fst_builder,
@@ -92,14 +92,6 @@ fn open_fst_index(source: ReadOnlySource) -> tantivy_fst::Map<ReadOnlySource> {
     tantivy_fst::Map::from(fst)
 }
 
-static EMPTY_DATA_SOURCE: Lazy<ReadOnlySource> = Lazy::new(|| {
-    let term_dictionary_data: Vec<u8> = TermDictionaryBuilder::create(Vec::<u8>::new())
-        .expect("Creating a TermDictionaryBuilder in a Vec<u8> should never fail")
-        .finish()
-        .expect("Writing in a Vec<u8> should never fail");
-    ReadOnlySource::from(term_dictionary_data)
-});
-
 /// The term dictionary contains all of the terms in
 /// `tantivy index` in a sorted manner.
 ///
@@ -130,8 +122,14 @@ impl TermDictionary {
     }
 
     /// Creates an empty term dictionary which contains no terms.
-    pub fn empty() -> Self {
+    pub fn empty(field_type: &FieldType) -> Self {
-        TermDictionary::from_source(&*EMPTY_DATA_SOURCE)
+        let term_dictionary_data: Vec<u8> =
+            TermDictionaryBuilder::create(Vec::<u8>::new(), &field_type)
+                .expect("Creating a TermDictionaryBuilder in a Vec<u8> should never fail")
+                .finish()
+                .expect("Writing in a Vec<u8> should never fail");
+        let source = ReadOnlySource::from(term_dictionary_data);
+        Self::from_source(&source)
     }
 
     /// Returns the number of terms in the dictionary.