Add an option to opt out fieldnorms for indexed fields.

Closes #922

CHANGELOG.md

@@ -1,6 +1,18 @@
 Tantivy 0.14.0
 =========================
 - Remove dependency to atomicwrites #833 .Implemented by @pmasurel upon suggestion and research from @asafigan). 
+- 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. 
+- Large API Change in the Directory API. Tantivy used to assume that all files could be somehow memory mapped. After this change, Directory return a `FileSlice` that can be reduced and eventually read into an `OwnedBytes` object. Long and blocking io operation are still required by they do not span over the entire file.
+- Added support for Brotli compression in the DocStore. (@ppodolsky)
+- Added helper for building intersections and unions in BooleanQuery (@guilload)
+- Bugfix in `Query::explain`
+- Making it possible to opt out the generation of fieldnorms information for indexed fields. This change breaks compatibility as the meta.json file format is slightly changed. (#922, @pmasurel)
+
+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
 ===================

Cargo.toml

@@ -13,7 +13,7 @@ keywords = ["search", "information", "retrieval"]
 edition = "2018"
 
 [dependencies]
-base64 = "0.12"
+base64 = "0.13"
 byteorder = "1"
 crc32fast = "1"
 once_cell = "1"
@@ -21,6 +21,7 @@ regex ={version = "1", default-features = false, features = ["std"]}
 tantivy-fst = "0.3"
 memmap = {version = "0.7", optional=true}
 lz4 = {version="1", optional=true}
+brotli = {version="3.3.0", optional=true}
 snap = "1"
 tempfile = {version="3", optional=true}
 log = "0.4"
@@ -31,9 +32,8 @@ fs2={version="0.4", optional=true}
 levenshtein_automata = "0.2"
 notify = {version="4", optional=true}
 uuid = { version = "0.8", features = ["v4", "serde"] }
-crossbeam = "0.7"
+crossbeam = "0.8"
 futures = {version = "0.3",  features=["thread-pool"] }
-owning_ref = "0.4"
 tantivy-query-grammar = { version="0.14.0-dev", path="./query-grammar" }
 stable_deref_trait = "1"
 rust-stemmers = "1"
@@ -41,8 +41,7 @@ downcast-rs = "1"
 bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
 census = "0.4"
 fnv = "1"
-owned-read = "0.4"
-failure = "0.1"
+thiserror = "1.0"
 htmlescape = "0.3"
 fail = "0.4"
 murmurhash32 = "0.2"
@@ -75,6 +74,7 @@ overflow-checks = true
 [features]
 default = ["mmap"]
 mmap = ["fs2", "tempfile", "memmap", "notify"]
+brotli-compression = ["brotli"]
 lz4-compression = ["lz4"]
 failpoints = ["fail/failpoints"]
 unstable = [] # useful for benches.

README.md

@@ -5,7 +5,6 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Build status](https://ci.appveyor.com/api/projects/status/r7nb13kj23u8m9pj/branch/master?svg=true)](https://ci.appveyor.com/project/fulmicoton/tantivy/branch/master)
 [![Crates.io](https://img.shields.io/crates/v/tantivy.svg)](https://crates.io/crates/tantivy)
-[![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/fulmicoton)
 
 ![Tantivy](https://tantivy-search.github.io/logo/tantivy-logo.png)
 
@@ -85,7 +84,7 @@ There are many ways to support this project.
 - Help with documentation by asking questions or submitting PRs
 - Contribute code (you can join [our Gitter](https://gitter.im/tantivy-search/tantivy))
 - Talk about Tantivy around you
-- Drop a word on on [![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/fulmicoton) or even [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
+- [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
 
 # Contributing code
 

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

examples/iterating_docs_and_positions.rs

@@ -45,7 +45,7 @@ fn main() -> tantivy::Result<()> {
         // Inverted index stands for the combination of
         // - the term dictionary
         // - the inverted lists associated to each terms and their positions
-        let inverted_index = segment_reader.inverted_index(title);
+        let inverted_index = segment_reader.inverted_index(title)?;
 
         // A `Term` is a text token associated with a field.
         // Let's go through all docs containing the term `title:the` and access their position
@@ -58,7 +58,7 @@ fn main() -> tantivy::Result<()> {
         // If you don't need all this information, you may get better performance by decompressing less
         // information.
         if let Some(mut segment_postings) =
-            inverted_index.read_postings(&term_the, IndexRecordOption::WithFreqsAndPositions)
+            inverted_index.read_postings(&term_the, IndexRecordOption::WithFreqsAndPositions)?
         {
             // this buffer will be used to request for positions
             let mut positions: Vec<u32> = Vec::with_capacity(100);
@@ -106,7 +106,7 @@ fn main() -> tantivy::Result<()> {
         // Inverted index stands for the combination of
         // - the term dictionary
         // - the inverted lists associated to each terms and their positions
-        let inverted_index = segment_reader.inverted_index(title);
+        let inverted_index = segment_reader.inverted_index(title)?;
 
         // This segment posting object is like a cursor over the documents matching the term.
         // The `IndexRecordOption` arguments tells tantivy we will be interested in both term frequencies
@@ -115,7 +115,7 @@ fn main() -> tantivy::Result<()> {
         // If you don't need all this information, you may get better performance by decompressing less
         // information.
         if let Some(mut block_segment_postings) =
-            inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)
+            inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)?
         {
             loop {
                 let docs = block_segment_postings.docs();

src/collector/custom_score_top_collector.rs

@@ -58,10 +58,10 @@ where
         segment_local_id: u32,
         segment_reader: &SegmentReader,
     ) -> crate::Result<Self::Child> {
-        let segment_scorer = self.custom_scorer.segment_scorer(segment_reader)?;
         let segment_collector = self
             .collector
             .for_segment(segment_local_id, segment_reader)?;
+        let segment_scorer = self.custom_scorer.segment_scorer(segment_reader)?;
         Ok(CustomScoreTopSegmentCollector {
             segment_collector,
             segment_scorer,

src/collector/docset_collector.rs

@@ -0,0 +1,61 @@
+use std::collections::HashSet;
+
+use crate::{DocAddress, DocId, Score};
+
+use super::{Collector, SegmentCollector};
+
+/// Collectors that returns the set of DocAddress that matches the query.
+///
+/// This collector is mostly useful for tests.
+pub struct DocSetCollector;
+
+impl Collector for DocSetCollector {
+    type Fruit = HashSet<DocAddress>;
+    type Child = DocSetChildCollector;
+
+    fn for_segment(
+        &self,
+        segment_local_id: crate::SegmentLocalId,
+        _segment: &crate::SegmentReader,
+    ) -> crate::Result<Self::Child> {
+        Ok(DocSetChildCollector {
+            segment_local_id,
+            docs: HashSet::new(),
+        })
+    }
+
+    fn requires_scoring(&self) -> bool {
+        false
+    }
+
+    fn merge_fruits(
+        &self,
+        segment_fruits: Vec<(u32, HashSet<DocId>)>,
+    ) -> crate::Result<Self::Fruit> {
+        let len: usize = segment_fruits.iter().map(|(_, docset)| docset.len()).sum();
+        let mut result = HashSet::with_capacity(len);
+        for (segment_local_id, docs) in segment_fruits {
+            for doc in docs {
+                result.insert(DocAddress(segment_local_id, doc));
+            }
+        }
+        Ok(result)
+    }
+}
+
+pub struct DocSetChildCollector {
+    segment_local_id: u32,
+    docs: HashSet<DocId>,
+}
+
+impl SegmentCollector for DocSetChildCollector {
+    type Fruit = (u32, HashSet<DocId>);
+
+    fn collect(&mut self, doc: crate::DocId, _score: Score) {
+        self.docs.insert(doc);
+    }
+
+    fn harvest(self) -> (u32, HashSet<DocId>) {
+        (self.segment_local_id, self.docs)
+    }
+}

src/collector/facet_collector.rs

@@ -7,7 +7,6 @@ use crate::DocId;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
-use crate::TantivyError;
 use std::cmp::Ordering;
 use std::collections::btree_map;
 use std::collections::BTreeMap;
@@ -266,10 +265,7 @@ impl Collector for FacetCollector {
         _: SegmentLocalId,
         reader: &SegmentReader,
     ) -> crate::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))
-        })?;
+        let facet_reader = reader.facet_reader(self.field)?;
 
         let mut collapse_mapping = Vec::new();
         let mut counts = Vec::new();

src/collector/int_facet_collector.rs

@@ -1,127 +0,0 @@
-use std::cmp::Eq;
-use std::collections::HashMap;
-use std::hash::Hash;
-
-use collector::Collector;
-use fastfield::FastFieldReader;
-use schema::Field;
-
-use DocId;
-use Result;
-use Score;
-use SegmentReader;
-use SegmentLocalId;
-
-
-/// Facet collector  for i64/u64 fast field
-pub struct IntFacetCollector<T>
-where
-    T: FastFieldReader,
-    T::ValueType: Eq + Hash,
-{
-    counters: HashMap<T::ValueType, u64>,
-    field: Field,
-    ff_reader: Option<T>,
-}
-
-
-impl<T> IntFacetCollector<T>
-where
-    T: FastFieldReader,
-    T::ValueType: Eq + Hash,
-{
-    /// Creates a new facet collector for aggregating a given field.
-    pub fn new(field: Field) -> IntFacetCollector<T> {
-        IntFacetCollector {
-            counters: HashMap::new(),
-            field: field,
-            ff_reader: None,
-        }
-    }
-}
-
-
-impl<T> Collector for IntFacetCollector<T>
-where
-    T: FastFieldReader,
-    T::ValueType: Eq + Hash,
-{
-    fn set_segment(&mut self, _: SegmentLocalId, reader: &SegmentReader) -> Result<()> {
-        self.ff_reader = Some(reader.get_fast_field_reader(self.field)?);
-        Ok(())
-    }
-
-    fn collect(&mut self, doc: DocId, _: Score) {
-        let val = self.ff_reader
-            .as_ref()
-            .expect(
-                "collect() was called before set_segment. \
-                This should never happen.",
-            )
-            .get(doc);
-        *(self.counters.entry(val).or_insert(0)) += 1;
-    }
-}
-
-
-
-#[cfg(test)]
-mod tests {
-
-    use collector::{chain, IntFacetCollector};
-    use query::QueryParser;
-    use fastfield::{I64FastFieldReader, U64FastFieldReader};
-    use schema::{self, FAST, STRING};
-    use Index;
-
-    #[test]
-    // create 10 documents, set num field value to 0 or 1 for even/odd ones
-    // make sure we have facet counters correctly filled
-    fn test_facet_collector_results() {
-
-        let mut schema_builder = schema::Schema::builder();
-        let num_field_i64 = schema_builder.add_i64_field("num_i64", FAST);
-        let num_field_u64 = schema_builder.add_u64_field("num_u64", FAST);
-        let num_field_f64 = schema_builder.add_f64_field("num_f64", FAST);
-        let text_field = schema_builder.add_text_field("text", STRING);
-        let schema = schema_builder.build();
-
-        let index = Index::create_in_ram(schema.clone());
-
-        {
-            let mut index_writer = index.writer_for_tests().unwrap();
-            {
-                for i in 0u64..10u64 {
-                    index_writer.add_document(doc!(
-                        num_field_i64 => ((i as i64) % 3i64) as i64,
-                        num_field_u64 => (i % 2u64) as u64,
-                        num_field_f64 => (i % 4u64) as f64,
-                        text_field => "text"
-                    ));
-                }
-            }
-            assert_eq!(index_writer.commit().unwrap(), 10u64);
-        }
-
-        let searcher = index.reader().searcher();
-        let mut ffvf_i64: IntFacetCollector<I64FastFieldReader> = IntFacetCollector::new(num_field_i64);
-        let mut ffvf_u64: IntFacetCollector<U64FastFieldReader> = IntFacetCollector::new(num_field_u64);
-        let mut ffvf_f64: IntFacetCollector<F64FastFieldReader> = IntFacetCollector::new(num_field_f64);
-
-        {
-            // perform the query
-            let mut facet_collectors = chain().push(&mut ffvf_i64).push(&mut ffvf_u64).push(&mut ffvf_f64);
-            let mut query_parser = QueryParser::for_index(index, vec![text_field]);
-            let query = query_parser.parse_query("text:text").unwrap();
-            query.search(&searcher, &mut facet_collectors).unwrap();
-        }
-
-        assert_eq!(ffvf_u64.counters[&0], 5);
-        assert_eq!(ffvf_u64.counters[&1], 5);
-        assert_eq!(ffvf_i64.counters[&0], 4);
-        assert_eq!(ffvf_i64.counters[&1], 3);
-        assert_eq!(ffvf_f64.counters[&0.0], 3);
-        assert_eq!(ffvf_f64.counters[&2.0], 2);
-
-    }
-}

src/collector/mod.rs

@@ -111,6 +111,9 @@ mod facet_collector;
 pub use self::facet_collector::FacetCollector;
 use crate::query::Weight;
 
+mod docset_collector;
+pub use self::docset_collector::DocSetCollector;
+
 /// `Fruit` is the type for the result of our collection.
 /// e.g. `usize` for the `Count` collector.
 pub trait Fruit: Send + downcast_rs::Downcast {}
@@ -139,7 +142,7 @@ pub trait Collector: Sync + Send {
     type Fruit: Fruit;
 
     /// Type of the `SegmentCollector` associated to this collector.
-    type Child: SegmentCollector<Fruit = Self::Fruit>;
+    type Child: SegmentCollector;
 
     /// `set_segment` is called before beginning to enumerate
     /// on this segment.
@@ -154,7 +157,10 @@ pub trait Collector: Sync + Send {
 
     /// 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::Child as SegmentCollector>::Fruit>,
+    ) -> crate::Result<Self::Fruit>;
 
     /// Created a segment collector and
     fn collect_segment(
@@ -224,11 +230,11 @@ where
 
     fn merge_fruits(
         &self,
-        children: Vec<(Left::Fruit, Right::Fruit)>,
+        segment_fruits: Vec<<Self::Child as SegmentCollector>::Fruit>,
     ) -> crate::Result<(Left::Fruit, Right::Fruit)> {
         let mut left_fruits = vec![];
         let mut right_fruits = vec![];
-        for (left_fruit, right_fruit) in children {
+        for (left_fruit, right_fruit) in segment_fruits {
             left_fruits.push(left_fruit);
             right_fruits.push(right_fruit);
         }
@@ -282,7 +288,10 @@ 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::Child as SegmentCollector>::Fruit>,
+    ) -> crate::Result<Self::Fruit> {
         let mut one_fruits = vec![];
         let mut two_fruits = vec![];
         let mut three_fruits = vec![];
@@ -349,7 +358,10 @@ where
             || self.3.requires_scoring()
     }
 
-    fn merge_fruits(&self, children: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
+    fn merge_fruits(
+        &self,
+        children: Vec<<Self::Child as SegmentCollector>::Fruit>,
+    ) -> crate::Result<Self::Fruit> {
         let mut one_fruits = vec![];
         let mut two_fruits = vec![];
         let mut three_fruits = vec![];

src/collector/multi_collector.rs

@@ -34,13 +34,13 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
 
     fn merge_fruits(
         &self,
-        children: Vec<<Self as Collector>::Fruit>,
+        children: Vec<<Self::Child as SegmentCollector>::Fruit>,
     ) -> crate::Result<Box<dyn Fruit>> {
-        let typed_fruit: Vec<TCollector::Fruit> = children
+        let typed_fruit: Vec<<TCollector::Child as SegmentCollector>::Fruit> = children
             .into_iter()
             .map(|untyped_fruit| {
                 untyped_fruit
-                    .downcast::<TCollector::Fruit>()
+                    .downcast::<<TCollector::Child as SegmentCollector>::Fruit>()
                     .map(|boxed_but_typed| *boxed_but_typed)
                     .map_err(|_| {
                         TantivyError::InvalidArgument("Failed to cast child fruit.".to_string())

src/collector/tests.rs

@@ -185,12 +185,15 @@ impl Collector for BytesFastFieldTestCollector {
         _segment_local_id: u32,
         segment_reader: &SegmentReader,
     ) -> crate::Result<BytesFastFieldSegmentCollector> {
+        let reader = segment_reader
+            .fast_fields()
+            .bytes(self.field)
+            .ok_or_else(|| {
+                crate::TantivyError::InvalidArgument("Field is not a bytes fast field.".to_string())
+            })?;
         Ok(BytesFastFieldSegmentCollector {
             vals: Vec::new(),
-            reader: segment_reader
-                .fast_fields()
-                .bytes(self.field)
-                .expect("Field is not a bytes fast field."),
+            reader,
         })
     }
 

src/collector/top_score_collector.rs

@@ -1,6 +1,4 @@
 use super::Collector;
-use crate::collector::custom_score_top_collector::CustomScoreTopCollector;
-use crate::collector::top_collector::TopSegmentCollector;
 use crate::collector::top_collector::{ComparableDoc, TopCollector};
 use crate::collector::tweak_score_top_collector::TweakedScoreTopCollector;
 use crate::collector::{
@@ -14,8 +12,71 @@ use crate::DocId;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
-use std::collections::BinaryHeap;
+use crate::{collector::custom_score_top_collector::CustomScoreTopCollector, fastfield::FastValue};
+use crate::{collector::top_collector::TopSegmentCollector, TantivyError};
 use std::fmt;
+use std::{collections::BinaryHeap, marker::PhantomData};
+
+struct FastFieldConvertCollector<
+    TCollector: Collector<Fruit = Vec<(u64, DocAddress)>>,
+    TFastValue: FastValue,
+> {
+    pub collector: TCollector,
+    pub field: Field,
+    pub fast_value: std::marker::PhantomData<TFastValue>,
+}
+
+impl<TCollector, TFastValue> Collector for FastFieldConvertCollector<TCollector, TFastValue>
+where
+    TCollector: Collector<Fruit = Vec<(u64, DocAddress)>>,
+    TFastValue: FastValue + 'static,
+{
+    type Fruit = Vec<(TFastValue, DocAddress)>;
+
+    type Child = TCollector::Child;
+
+    fn for_segment(
+        &self,
+        segment_local_id: crate::SegmentLocalId,
+        segment: &SegmentReader,
+    ) -> crate::Result<Self::Child> {
+        let schema = segment.schema();
+        let field_entry = schema.get_field_entry(self.field);
+        if !field_entry.is_fast() {
+            return Err(TantivyError::SchemaError(format!(
+                "Field {:?} is not a fast field.",
+                field_entry.name()
+            )));
+        }
+        let schema_type = TFastValue::to_type();
+        let requested_type = field_entry.field_type().value_type();
+        if schema_type != requested_type {
+            return Err(TantivyError::SchemaError(format!(
+                "Field {:?} is of type {:?}!={:?}",
+                field_entry.name(),
+                schema_type,
+                requested_type
+            )));
+        }
+        self.collector.for_segment(segment_local_id, segment)
+    }
+
+    fn requires_scoring(&self) -> bool {
+        self.collector.requires_scoring()
+    }
+
+    fn merge_fruits(
+        &self,
+        segment_fruits: Vec<<Self::Child as SegmentCollector>::Fruit>,
+    ) -> crate::Result<Self::Fruit> {
+        let raw_result = self.collector.merge_fruits(segment_fruits)?;
+        let transformed_result = raw_result
+            .into_iter()
+            .map(|(score, doc_address)| (TFastValue::from_u64(score), doc_address))
+            .collect::<Vec<_>>();
+        Ok(transformed_result)
+    }
+}
 
 /// The `TopDocs` collector keeps track of the top `K` documents
 /// sorted by their score.
@@ -73,7 +134,7 @@ struct ScorerByFastFieldReader {
 
 impl CustomSegmentScorer<u64> for ScorerByFastFieldReader {
     fn score(&mut self, doc: DocId) -> u64 {
-        self.ff_reader.get_u64(u64::from(doc))
+        self.ff_reader.get(doc)
     }
 }
 
@@ -87,10 +148,10 @@ impl CustomScorer<u64> for ScorerByField {
     fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child> {
         let ff_reader = segment_reader
             .fast_fields()
-            .u64(self.field)
+            .u64_lenient(self.field)
             .ok_or_else(|| {
                 crate::TantivyError::SchemaError(format!(
-                    "Field requested ({:?}) is not a i64/u64 fast field.",
+                    "Field requested ({:?}) is not a fast field.",
                     self.field
                 ))
             })?;
@@ -112,6 +173,8 @@ impl TopDocs {
     /// This is equivalent to `OFFSET` in MySQL or PostgreSQL and `start` in
     /// Lucene's TopDocsCollector.
     ///
+    /// # Example
+    ///
     /// ```rust
     /// use tantivy::collector::TopDocs;
     /// use tantivy::query::QueryParser;
@@ -148,6 +211,14 @@ impl TopDocs {
 
     /// Set top-K to rank documents by a given fast field.
     ///
+    /// If the field is not a fast or does not exist, this method returns successfully (it is not aware of any schema).
+    /// An error will be returned at the moment of search.
+    ///
+    /// If the field is a FAST field but not a u64 field, search will return successfully but it will return
+    /// returns a monotonic u64-representation (ie. the order is still correct) of the requested field type.
+    ///
+    /// # Example
+    ///
     /// ```rust
     /// # use tantivy::schema::{Schema, FAST, TEXT};
     /// # use tantivy::{doc, Index, DocAddress};
@@ -169,7 +240,7 @@ impl TopDocs {
     /// #   index_writer.add_document(doc!(title => "A Dairy Cow", rating => 63u64));
     /// #   index_writer.add_document(doc!(title => "The Diary of a Young Girl", rating => 80u64));
     /// #   assert!(index_writer.commit().is_ok());
-    /// #   let reader = index.reader().unwrap();
+    /// #   let reader = index.reader()?;
     /// #   let query = QueryParser::for_index(&index, vec![title]).parse_query("diary")?;
     /// #   let top_docs = docs_sorted_by_rating(&reader.searcher(), &query, rating)?;
     /// #   assert_eq!(top_docs,
@@ -177,25 +248,20 @@ impl TopDocs {
     /// #                 (80u64, DocAddress(0u32, 3))]);
     /// #   Ok(())
     /// # }
-    ///
-    ///
     /// /// Searches the document matching the given query, and
     /// /// collects the top 10 documents, order by the u64-`field`
     /// /// given in argument.
-    /// ///
-    /// /// `field` is required to be a FAST field.
     /// fn docs_sorted_by_rating(searcher: &Searcher,
     ///                          query: &dyn Query,
-    ///                          sort_by_field: Field)
+    ///                          rating_field: Field)
     ///     -> tantivy::Result<Vec<(u64, DocAddress)>> {
     ///
     ///     // This is where we build our topdocs collector
     ///     //
-    ///     // Note the generics parameter that needs to match the
-    ///     // type `sort_by_field`.
-    ///     let top_docs_by_rating = TopDocs
+    ///     // Note the `rating_field` needs to be a FAST field here.
+    ///     let top_books_by_rating = TopDocs
     ///                 ::with_limit(10)
-    ///                  .order_by_u64_field(sort_by_field);
+    ///                  .order_by_u64_field(rating_field);
     ///     
     ///     // ... and here are our documents. Note this is a simple vec.
     ///     // The `u64` in the pair is the value of our fast field for
@@ -205,21 +271,105 @@ impl TopDocs {
     ///     // length of 10, or less if not enough documents matched the
     ///     // query.
     ///     let resulting_docs: Vec<(u64, DocAddress)> =
-    ///          searcher.search(query, &top_docs_by_rating)?;
+    ///          searcher.search(query, &top_books_by_rating)?;
     ///     
     ///     Ok(resulting_docs)
     /// }
     /// ```
     ///
-    /// # Panics
-    ///
-    /// May panic if the field requested is not a fast field.
-    ///
+    /// # See also
+    ///  
+    /// To confortably work with `u64`s, `i64`s, `f64`s, or `date`s, please refer to
+    /// [.order_by_fast_field(...)](#method.order_by_fast_field) method.
     pub fn order_by_u64_field(
         self,
         field: Field,
     ) -> impl Collector<Fruit = Vec<(u64, DocAddress)>> {
-        self.custom_score(ScorerByField { field })
+        CustomScoreTopCollector::new(ScorerByField { field }, self.0.into_tscore())
+    }
+
+    /// Set top-K to rank documents by a given fast field.
+    ///
+    /// If the field is not a fast field, or its field type does not match the generic type, this method does not panic,  
+    /// but an explicit error will be returned at the moment of collection.
+    ///
+    /// Note that this method is a generic. The requested fast field type will be often
+    /// inferred in your code by the rust compiler.
+    ///
+    /// Implementation-wise, for performance reason, tantivy will manipulate the u64 representation of your fast
+    /// field until the last moment.
+    ///
+    /// # Example
+    ///
+    /// ```rust
+    /// # use tantivy::schema::{Schema, FAST, TEXT};
+    /// # use tantivy::{doc, Index, DocAddress};
+    /// # use tantivy::query::{Query, AllQuery};
+    /// use tantivy::Searcher;
+    /// use tantivy::collector::TopDocs;
+    /// use tantivy::schema::Field;
+    ///
+    /// # fn main() -> tantivy::Result<()> {
+    /// #   let mut schema_builder = Schema::builder();
+    /// #   let title = schema_builder.add_text_field("company", TEXT);
+    /// #   let rating = schema_builder.add_i64_field("revenue", FAST);
+    /// #   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!(title => "MadCow Inc.", rating => 92_000_000i64));
+    /// #   index_writer.add_document(doc!(title => "Zozo Cow KKK", rating => 119_000_000i64));
+    /// #   index_writer.add_document(doc!(title => "Declining Cow", rating => -63_000_000i64));
+    /// #   assert!(index_writer.commit().is_ok());
+    /// #   let reader = index.reader()?;
+    /// #   let top_docs = docs_sorted_by_revenue(&reader.searcher(), &AllQuery, rating)?;
+    /// #   assert_eq!(top_docs,
+    /// #            vec![(119_000_000i64, DocAddress(0, 1)),
+    /// #                 (92_000_000i64, DocAddress(0, 0))]);
+    /// #   Ok(())
+    /// # }
+    /// /// Searches the document matching the given query, and
+    /// /// collects the top 10 documents, order by the u64-`field`
+    /// /// given in argument.
+    /// fn docs_sorted_by_revenue(searcher: &Searcher,
+    ///                          query: &dyn Query,
+    ///                          revenue_field: Field)
+    ///     -> tantivy::Result<Vec<(i64, DocAddress)>> {
+    ///
+    ///     // This is where we build our topdocs collector
+    ///     //
+    ///     // Note the generics parameter that needs to match the
+    ///     // type `sort_by_field`. revenue_field here is a FAST i64 field.
+    ///     let top_company_by_revenue = TopDocs
+    ///                 ::with_limit(2)
+    ///                  .order_by_fast_field(revenue_field);
+    ///     
+    ///     // ... and here are our documents. Note this is a simple vec.
+    ///     // The `i64` in the pair is the value of our fast field for
+    ///     // each documents.
+    ///     //
+    ///     // The vec is sorted decreasingly by `sort_by_field`, and has a
+    ///     // length of 10, or less if not enough documents matched the
+    ///     // query.
+    ///     let resulting_docs: Vec<(i64, DocAddress)> =
+    ///          searcher.search(query, &top_company_by_revenue)?;
+    ///     
+    ///     Ok(resulting_docs)
+    /// }
+    /// ```
+    pub fn order_by_fast_field<TFastValue>(
+        self,
+        fast_field: Field,
+    ) -> impl Collector<Fruit = Vec<(TFastValue, DocAddress)>>
+    where
+        TFastValue: FastValue + 'static,
+    {
+        let u64_collector = self.order_by_u64_field(fast_field);
+        FastFieldConvertCollector {
+            collector: u64_collector,
+            field: fast_field,
+            fast_value: PhantomData,
+        }
     }
 
     /// Ranks the documents using a custom score.
@@ -722,6 +872,94 @@ mod tests {
         );
     }
 
+    #[test]
+    fn test_top_field_collector_datetime() -> crate::Result<()> {
+        use std::str::FromStr;
+        let mut schema_builder = Schema::builder();
+        let name = schema_builder.add_text_field("name", TEXT);
+        let birthday = schema_builder.add_date_field("birthday", FAST);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests()?;
+        let pr_birthday = crate::DateTime::from_str("1898-04-09T00:00:00+00:00")?;
+        index_writer.add_document(doc!(
+            name => "Paul Robeson",
+            birthday => pr_birthday
+        ));
+        let mr_birthday = crate::DateTime::from_str("1947-11-08T00:00:00+00:00")?;
+        index_writer.add_document(doc!(
+            name => "Minnie Riperton",
+            birthday => mr_birthday
+        ));
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
+        let top_collector = TopDocs::with_limit(3).order_by_fast_field(birthday);
+        let top_docs: Vec<(crate::DateTime, DocAddress)> =
+            searcher.search(&AllQuery, &top_collector)?;
+        assert_eq!(
+            &top_docs[..],
+            &[
+                (mr_birthday, DocAddress(0, 1)),
+                (pr_birthday, DocAddress(0, 0)),
+            ]
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn test_top_field_collector_i64() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let city = schema_builder.add_text_field("city", TEXT);
+        let altitude = schema_builder.add_i64_field("altitude", FAST);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(
+                city => "georgetown",
+                altitude =>  -1i64,
+        ));
+        index_writer.add_document(doc!(
+            city => "tokyo",
+            altitude =>  40i64,
+        ));
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
+        let top_collector = TopDocs::with_limit(3).order_by_fast_field(altitude);
+        let top_docs: Vec<(i64, DocAddress)> = searcher.search(&AllQuery, &top_collector)?;
+        assert_eq!(
+            &top_docs[..],
+            &[(40i64, DocAddress(0, 1)), (-1i64, DocAddress(0, 0)),]
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn test_top_field_collector_f64() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let city = schema_builder.add_text_field("city", TEXT);
+        let altitude = schema_builder.add_f64_field("altitude", FAST);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(
+                city => "georgetown",
+                altitude =>  -1.0f64,
+        ));
+        index_writer.add_document(doc!(
+            city => "tokyo",
+            altitude =>  40f64,
+        ));
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
+        let top_collector = TopDocs::with_limit(3).order_by_fast_field(altitude);
+        let top_docs: Vec<(f64, DocAddress)> = searcher.search(&AllQuery, &top_collector)?;
+        assert_eq!(
+            &top_docs[..],
+            &[(40f64, DocAddress(0, 1)), (-1.0f64, DocAddress(0, 0)),]
+        );
+        Ok(())
+    }
+
     #[test]
     #[should_panic]
     fn test_field_does_not_exist() {
@@ -744,29 +982,41 @@ mod tests {
     }
 
     #[test]
-    fn test_field_not_fast_field() {
+    fn test_field_not_fast_field() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
-        let title = schema_builder.add_text_field(TITLE, TEXT);
         let size = schema_builder.add_u64_field(SIZE, STORED);
         let schema = schema_builder.build();
-        let (index, _) = index("beer", title, schema, |index_writer| {
-            index_writer.add_document(doc!(
-                title => "bottle of beer",
-                size => 12u64,
-            ));
-        });
-        let searcher = index.reader().unwrap().searcher();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(size=>1u64));
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
         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 {
-            assert_eq!(
-                msg,
-                "Field requested (Field(1)) is not a i64/u64 fast field."
-            );
-        } else {
-            assert!(false);
-        }
+        let err = top_collector.for_segment(0, segment).err().unwrap();
+        assert!(
+            matches!(err, crate::TantivyError::SchemaError(msg) if msg == "Field requested (Field(0)) is not a fast field.")
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn test_field_wrong_type() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let size = schema_builder.add_u64_field(SIZE, STORED);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(size=>1u64));
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
+        let segment = searcher.segment_reader(0);
+        let top_collector = TopDocs::with_limit(4).order_by_fast_field::<i64>(size);
+        let err = top_collector.for_segment(0, segment).err().unwrap();
+        assert!(
+            matches!(err, crate::TantivyError::SchemaError(msg) if msg == "Field \"size\" is not a fast field.")
+        );
+        Ok(())
     }
 
     #[test]
@@ -820,7 +1070,6 @@ mod tests {
         mut doc_adder: impl FnMut(&mut IndexWriter) -> (),
     ) -> (Index, Box<dyn Query>) {
         let index = Index::create_in_ram(schema);
-
         let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
         doc_adder(&mut index_writer);
         index_writer.commit().unwrap();

src/common/bitpacker.rs

@@ -1,6 +1,7 @@
 use byteorder::{ByteOrder, LittleEndian, WriteBytesExt};
 use std::io;
-use std::ops::Deref;
+
+use crate::directory::OwnedBytes;
 
 pub(crate) struct BitPacker {
     mini_buffer: u64,
@@ -60,20 +61,14 @@ impl BitPacker {
 }
 
 #[derive(Clone)]
-pub struct BitUnpacker<Data>
-where
-    Data: Deref<Target = [u8]>,
-{
+pub struct BitUnpacker {
     num_bits: u64,
     mask: u64,
-    data: Data,
+    data: OwnedBytes,
 }
 
-impl<Data> BitUnpacker<Data>
-where
-    Data: Deref<Target = [u8]>,
-{
-    pub fn new(data: Data, num_bits: u8) -> BitUnpacker<Data> {
+impl BitUnpacker {
+    pub fn new(data: OwnedBytes, num_bits: u8) -> BitUnpacker {
         let mask: u64 = if num_bits == 64 {
             !0u64
         } else {
@@ -90,7 +85,7 @@ where
         if self.num_bits == 0 {
             return 0u64;
         }
-        let data: &[u8] = &*self.data;
+        let data: &[u8] = self.data.as_slice();
         let num_bits = self.num_bits;
         let mask = self.mask;
         let addr_in_bits = idx * num_bits;
@@ -109,8 +104,9 @@ where
 #[cfg(test)]
 mod test {
     use super::{BitPacker, BitUnpacker};
+    use crate::directory::OwnedBytes;
 
-    fn create_fastfield_bitpacker(len: usize, num_bits: u8) -> (BitUnpacker<Vec<u8>>, Vec<u64>) {
+    fn create_fastfield_bitpacker(len: usize, num_bits: u8) -> (BitUnpacker, Vec<u64>) {
         let mut data = Vec::new();
         let mut bitpacker = BitPacker::new();
         let max_val: u64 = (1u64 << num_bits as u64) - 1u64;
@@ -122,7 +118,7 @@ mod test {
         }
         bitpacker.close(&mut data).unwrap();
         assert_eq!(data.len(), ((num_bits as usize) * len + 7) / 8 + 7);
-        let bitunpacker = BitUnpacker::new(data, num_bits);
+        let bitunpacker = BitUnpacker::new(OwnedBytes::new(data), num_bits);
         (bitunpacker, vals)
     }
 

src/common/composite_file.rs

@@ -1,14 +1,15 @@
 use crate::common::BinarySerializable;
 use crate::common::CountingWriter;
 use crate::common::VInt;
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
 use crate::directory::{TerminatingWrite, WritePtr};
 use crate::schema::Field;
 use crate::space_usage::FieldUsage;
 use crate::space_usage::PerFieldSpaceUsage;
 use std::collections::HashMap;
-use std::io::Write;
-use std::io::{self, Read};
+use std::io::{self, Read, Write};
+
+use super::HasLen;
 
 #[derive(Eq, PartialEq, Hash, Copy, Ord, PartialOrd, Clone, Debug)]
 pub struct FileAddr {
@@ -103,25 +104,26 @@ impl<W: TerminatingWrite + Write> CompositeWrite<W> {
 /// for each field.
 #[derive(Clone)]
 pub struct CompositeFile {
-    data: ReadOnlySource,
+    data: FileSlice,
     offsets_index: HashMap<FileAddr, (usize, usize)>,
 }
 
 impl CompositeFile {
     /// Opens a composite file stored in a given
-    /// `ReadOnlySource`.
-    pub fn open(data: &ReadOnlySource) -> io::Result<CompositeFile> {
+    /// `FileSlice`.
+    pub fn open(data: &FileSlice) -> io::Result<CompositeFile> {
         let end = data.len();
-        let footer_len_data = data.slice_from(end - 4);
+        let footer_len_data = data.slice_from(end - 4).read_bytes()?;
         let footer_len = u32::deserialize(&mut footer_len_data.as_slice())? as usize;
         let footer_start = end - 4 - footer_len;
-        let footer_data = data.slice(footer_start, footer_start + footer_len);
+        let footer_data = data
+            .slice(footer_start, footer_start + footer_len)
+            .read_bytes()?;
         let mut footer_buffer = footer_data.as_slice();
         let num_fields = VInt::deserialize(&mut footer_buffer)?.0 as usize;
 
         let mut file_addrs = vec![];
         let mut offsets = vec![];
-
         let mut field_index = HashMap::new();
 
         let mut offset = 0;
@@ -150,19 +152,19 @@ impl CompositeFile {
     pub fn empty() -> CompositeFile {
         CompositeFile {
             offsets_index: HashMap::new(),
-            data: ReadOnlySource::empty(),
+            data: FileSlice::empty(),
         }
     }
 
-    /// Returns the `ReadOnlySource` associated
+    /// Returns the `FileSlice` associated
     /// to a given `Field` and stored in a `CompositeFile`.
-    pub fn open_read(&self, field: Field) -> Option<ReadOnlySource> {
+    pub fn open_read(&self, field: Field) -> Option<FileSlice> {
         self.open_read_with_idx(field, 0)
     }
 
-    /// Returns the `ReadOnlySource` associated
+    /// Returns the `FileSlice` associated
     /// to a given `Field` and stored in a `CompositeFile`.
-    pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<ReadOnlySource> {
+    pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<FileSlice> {
         self.offsets_index
             .get(&FileAddr { field, idx })
             .map(|&(from, to)| self.data.slice(from, to))
@@ -192,46 +194,44 @@ mod test {
     use std::path::Path;
 
     #[test]
-    fn test_composite_file() {
+    fn test_composite_file() -> crate::Result<()> {
         let path = Path::new("test_path");
-        let mut directory = RAMDirectory::create();
+        let directory = RAMDirectory::create();
         {
             let w = directory.open_write(path).unwrap();
             let mut composite_write = CompositeWrite::wrap(w);
-            {
-                let mut write_0 = composite_write.for_field(Field::from_field_id(0u32));
-                VInt(32431123u64).serialize(&mut write_0).unwrap();
-                write_0.flush().unwrap();
-            }
-
-            {
-                let mut write_4 = composite_write.for_field(Field::from_field_id(4u32));
-                VInt(2).serialize(&mut write_4).unwrap();
-                write_4.flush().unwrap();
-            }
-            composite_write.close().unwrap();
+            let mut write_0 = composite_write.for_field(Field::from_field_id(0u32));
+            VInt(32431123u64).serialize(&mut write_0)?;
+            write_0.flush()?;
+            let mut write_4 = composite_write.for_field(Field::from_field_id(4u32));
+            VInt(2).serialize(&mut write_4)?;
+            write_4.flush()?;
+            composite_write.close()?;
         }
         {
-            let r = directory.open_read(path).unwrap();
-            let composite_file = CompositeFile::open(&r).unwrap();
+            let r = directory.open_read(path)?;
+            let composite_file = CompositeFile::open(&r)?;
             {
                 let file0 = composite_file
                     .open_read(Field::from_field_id(0u32))
-                    .unwrap();
+                    .unwrap()
+                    .read_bytes()?;
                 let mut file0_buf = file0.as_slice();
-                let payload_0 = VInt::deserialize(&mut file0_buf).unwrap().0;
+                let payload_0 = VInt::deserialize(&mut file0_buf)?.0;
                 assert_eq!(file0_buf.len(), 0);
                 assert_eq!(payload_0, 32431123u64);
             }
             {
                 let file4 = composite_file
                     .open_read(Field::from_field_id(4u32))
-                    .unwrap();
+                    .unwrap()
+                    .read_bytes()?;
                 let mut file4_buf = file4.as_slice();
-                let payload_4 = VInt::deserialize(&mut file4_buf).unwrap().0;
+                let payload_4 = VInt::deserialize(&mut file4_buf)?.0;
                 assert_eq!(file4_buf.len(), 0);
                 assert_eq!(payload_4, 2u64);
             }
         }
+        Ok(())
     }
 }

src/core/index.rs

@@ -21,7 +21,6 @@ use crate::schema::FieldType;
 use crate::schema::Schema;
 use crate::tokenizer::{TextAnalyzer, TokenizerManager};
 use crate::IndexWriter;
-use std::borrow::BorrowMut;
 use std::collections::HashSet;
 use std::fmt;
 
@@ -57,7 +56,9 @@ pub struct Index {
 }
 
 impl Index {
-    /// Examines the director to see if it contains an index
+    /// Examines the directory to see if it contains an index.
+    ///
+    /// Effectively, it only checks for the presence of the `meta.json` file.
     pub fn exists<Dir: Directory>(dir: &Dir) -> bool {
         dir.exists(&META_FILEPATH)
     }
@@ -140,7 +141,9 @@ impl Index {
         Index::create(mmap_directory, schema)
     }
 
-    /// Creates a new index given an implementation of the trait `Directory`
+    /// Creates a new index given an implementation of the trait `Directory`.
+    ///
+    /// If a directory previously existed, it will be erased.
     pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
         let directory = ManagedDirectory::wrap(dir)?;
         Index::from_directory(directory, schema)
@@ -149,8 +152,8 @@ 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> {
-        save_new_metas(schema.clone(), directory.borrow_mut())?;
+    fn from_directory(directory: ManagedDirectory, schema: Schema) -> crate::Result<Index> {
+        save_new_metas(schema.clone(), &directory)?;
         let metas = IndexMeta::with_schema(schema);
         Index::create_from_metas(directory, &metas, SegmentMetaInventory::default())
     }

src/core/index_meta.rs

@@ -301,7 +301,7 @@ mod tests {
         let json = serde_json::ser::to_string(&index_metas).expect("serialization failed");
         assert_eq!(
             json,
-            r#"{"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","tokenizer":"default"},"stored":false}}],"opstamp":0}"#
+            r#"{"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","tokenizer":"default","fieldnorms":true},"stored":false}}],"opstamp":0}"#
         );
     }
 }

src/core/inverted_index_reader.rs

@@ -1,5 +1,7 @@
+use std::io;
+
 use crate::common::BinarySerializable;
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
 use crate::positions::PositionReader;
 use crate::postings::TermInfo;
 use crate::postings::{BlockSegmentPostings, SegmentPostings};
@@ -14,7 +16,7 @@ use crate::termdict::TermDictionary;
 ///
 /// It is safe to delete the segment associated to
 /// an `InvertedIndexReader`. As long as it is open,
-/// the `ReadOnlySource` it is relying on should
+/// the `FileSlice` it is relying on should
 /// stay available.
 ///
 ///
@@ -22,9 +24,9 @@ use crate::termdict::TermDictionary;
 /// the `SegmentReader`'s [`.inverted_index(...)`] method
 pub struct InvertedIndexReader {
     termdict: TermDictionary,
-    postings_source: ReadOnlySource,
-    positions_source: ReadOnlySource,
-    positions_idx_source: ReadOnlySource,
+    postings_file_slice: FileSlice,
+    positions_file_slice: FileSlice,
+    positions_idx_file_slice: FileSlice,
     record_option: IndexRecordOption,
     total_num_tokens: u64,
 }
@@ -33,22 +35,21 @@ impl InvertedIndexReader {
     #[cfg_attr(feature = "cargo-clippy", allow(clippy::needless_pass_by_value))] // for symmetry
     pub(crate) fn new(
         termdict: TermDictionary,
-        postings_source: ReadOnlySource,
-        positions_source: ReadOnlySource,
-        positions_idx_source: ReadOnlySource,
+        postings_file_slice: FileSlice,
+        positions_file_slice: FileSlice,
+        positions_idx_file_slice: FileSlice,
         record_option: IndexRecordOption,
-    ) -> InvertedIndexReader {
-        let total_num_tokens_data = postings_source.slice(0, 8);
-        let mut total_num_tokens_cursor = total_num_tokens_data.as_slice();
-        let total_num_tokens = u64::deserialize(&mut total_num_tokens_cursor).unwrap_or(0u64);
-        InvertedIndexReader {
+    ) -> io::Result<InvertedIndexReader> {
+        let (total_num_tokens_slice, postings_body) = postings_file_slice.split(8);
+        let total_num_tokens = u64::deserialize(&mut total_num_tokens_slice.read_bytes()?)?;
+        Ok(InvertedIndexReader {
             termdict,
-            postings_source: postings_source.slice_from(8),
-            positions_source,
-            positions_idx_source,
+            postings_file_slice: postings_body,
+            positions_file_slice,
+            positions_idx_file_slice,
             record_option,
             total_num_tokens,
-        }
+        })
     }
 
     /// Creates an empty `InvertedIndexReader` object, which
@@ -56,9 +57,9 @@ impl InvertedIndexReader {
     pub fn empty(record_option: IndexRecordOption) -> InvertedIndexReader {
         InvertedIndexReader {
             termdict: TermDictionary::empty(),
-            postings_source: ReadOnlySource::empty(),
-            positions_source: ReadOnlySource::empty(),
-            positions_idx_source: ReadOnlySource::empty(),
+            postings_file_slice: FileSlice::empty(),
+            positions_file_slice: FileSlice::empty(),
+            positions_idx_file_slice: FileSlice::empty(),
             record_option,
             total_num_tokens: 0u64,
         }
@@ -88,11 +89,12 @@ impl InvertedIndexReader {
         &self,
         term_info: &TermInfo,
         block_postings: &mut BlockSegmentPostings,
-    ) {
-        let offset = term_info.postings_offset as usize;
-        let end_source = self.postings_source.len();
-        let postings_slice = self.postings_source.slice(offset, end_source);
-        block_postings.reset(term_info.doc_freq, postings_slice);
+    ) -> io::Result<()> {
+        let postings_slice = self
+            .postings_file_slice
+            .slice_from(term_info.postings_offset as usize);
+        block_postings.reset(term_info.doc_freq, postings_slice.read_bytes()?);
+        Ok(())
     }
 
     /// Returns a block postings given a `Term`.
@@ -103,9 +105,11 @@ impl InvertedIndexReader {
         &self,
         term: &Term,
         option: IndexRecordOption,
-    ) -> Option<BlockSegmentPostings> {
-        self.get_term_info(term)
+    ) -> io::Result<Option<BlockSegmentPostings>> {
+        Ok(self
+            .get_term_info(term)
             .map(move |term_info| self.read_block_postings_from_terminfo(&term_info, option))
+            .transpose()?)
     }
 
     /// Returns a block postings given a `term_info`.
@@ -116,10 +120,10 @@ impl InvertedIndexReader {
         &self,
         term_info: &TermInfo,
         requested_option: IndexRecordOption,
-    ) -> BlockSegmentPostings {
+    ) -> io::Result<BlockSegmentPostings> {
         let offset = term_info.postings_offset as usize;
-        let postings_data = self.postings_source.slice_from(offset);
-        BlockSegmentPostings::from_data(
+        let postings_data = self.postings_file_slice.slice_from(offset);
+        BlockSegmentPostings::open(
             term_info.doc_freq,
             postings_data,
             self.record_option,
@@ -135,20 +139,23 @@ impl InvertedIndexReader {
         &self,
         term_info: &TermInfo,
         option: IndexRecordOption,
-    ) -> SegmentPostings {
-        let block_postings = self.read_block_postings_from_terminfo(term_info, option);
+    ) -> io::Result<SegmentPostings> {
+        let block_postings = self.read_block_postings_from_terminfo(term_info, option)?;
         let position_stream = {
             if option.has_positions() {
-                let position_reader = self.positions_source.clone();
-                let skip_reader = self.positions_idx_source.clone();
+                let position_reader = self.positions_file_slice.clone();
+                let skip_reader = self.positions_idx_file_slice.clone();
                 let position_reader =
-                    PositionReader::new(position_reader, skip_reader, term_info.positions_idx);
+                    PositionReader::new(position_reader, skip_reader, term_info.positions_idx)?;
                 Some(position_reader)
             } else {
                 None
             }
         };
-        SegmentPostings::from_block_postings(block_postings, position_stream)
+        Ok(SegmentPostings::from_block_postings(
+            block_postings,
+            position_stream,
+        ))
     }
 
     /// Returns the total number of tokens recorded for all documents
@@ -167,24 +174,31 @@ impl InvertedIndexReader {
     /// For instance, requesting `IndexRecordOption::Freq` for a
     /// `TextIndexingOptions` that does not index position will return a `SegmentPostings`
     /// with `DocId`s and frequencies.
-    pub fn read_postings(&self, term: &Term, option: IndexRecordOption) -> Option<SegmentPostings> {
+    pub fn read_postings(
+        &self,
+        term: &Term,
+        option: IndexRecordOption,
+    ) -> io::Result<Option<SegmentPostings>> {
         self.get_term_info(term)
             .map(move |term_info| self.read_postings_from_terminfo(&term_info, option))
+            .transpose()
     }
 
     pub(crate) fn read_postings_no_deletes(
         &self,
         term: &Term,
         option: IndexRecordOption,
-    ) -> Option<SegmentPostings> {
+    ) -> io::Result<Option<SegmentPostings>> {
         self.get_term_info(term)
             .map(|term_info| self.read_postings_from_terminfo(&term_info, option))
+            .transpose()
     }
 
     /// Returns the number of documents containing the term.
-    pub fn doc_freq(&self, term: &Term) -> u32 {
-        self.get_term_info(term)
+    pub fn doc_freq(&self, term: &Term) -> io::Result<u32> {
+        Ok(self
+            .get_term_info(term)
             .map(|term_info| term_info.doc_freq)
-            .unwrap_or(0u32)
+            .unwrap_or(0u32))
     }
 }

src/core/searcher.rs

@@ -11,8 +11,8 @@ use crate::store::StoreReader;
 use crate::termdict::TermMerger;
 use crate::DocAddress;
 use crate::Index;
-use std::fmt;
 use std::sync::Arc;
+use std::{fmt, io};
 
 /// Holds a list of `SegmentReader`s ready for search.
 ///
@@ -32,17 +32,17 @@ impl Searcher {
         schema: Schema,
         index: Index,
         segment_readers: Vec<SegmentReader>,
-    ) -> Searcher {
-        let store_readers = segment_readers
+    ) -> io::Result<Searcher> {
+        let store_readers: Vec<StoreReader> = segment_readers
             .iter()
             .map(SegmentReader::get_store_reader)
-            .collect();
-        Searcher {
+            .collect::<io::Result<Vec<_>>>()?;
+        Ok(Searcher {
             schema,
             index,
             segment_readers,
             store_readers,
-        }
+        })
     }
 
     /// Returns the `Index` associated to the `Searcher`
@@ -75,13 +75,14 @@ impl Searcher {
 
     /// Return the overall number of documents containing
     /// the given term.
-    pub fn doc_freq(&self, term: &Term) -> u64 {
-        self.segment_readers
-            .iter()
-            .map(|segment_reader| {
-                u64::from(segment_reader.inverted_index(term.field()).doc_freq(term))
-            })
-            .sum::<u64>()
+    pub fn doc_freq(&self, term: &Term) -> crate::Result<u64> {
+        let mut total_doc_freq = 0;
+        for segment_reader in &self.segment_readers {
+            let inverted_index = segment_reader.inverted_index(term.field())?;
+            let doc_freq = inverted_index.doc_freq(term)?;
+            total_doc_freq += u64::from(doc_freq);
+        }
+        Ok(total_doc_freq)
     }
 
     /// Return the list of segment readers
@@ -148,22 +149,22 @@ impl Searcher {
     }
 
     /// Return the field searcher associated to a `Field`.
-    pub fn field(&self, field: Field) -> FieldSearcher {
-        let inv_index_readers = self
+    pub fn field(&self, field: Field) -> crate::Result<FieldSearcher> {
+        let inv_index_readers: Vec<Arc<InvertedIndexReader>> = self
             .segment_readers
             .iter()
             .map(|segment_reader| segment_reader.inverted_index(field))
-            .collect::<Vec<_>>();
-        FieldSearcher::new(inv_index_readers)
+            .collect::<crate::Result<Vec<_>>>()?;
+        Ok(FieldSearcher::new(inv_index_readers))
     }
 
     /// Summarize total space usage of this searcher.
-    pub fn space_usage(&self) -> SearcherSpaceUsage {
+    pub fn space_usage(&self) -> io::Result<SearcherSpaceUsage> {
         let mut space_usage = SearcherSpaceUsage::new();
-        for segment_reader in self.segment_readers.iter() {
-            space_usage.add_segment(segment_reader.space_usage());
+        for segment_reader in &self.segment_readers {
+            space_usage.add_segment(segment_reader.space_usage()?);
         }
-        space_usage
+        Ok(space_usage)
     }
 }
 

src/core/segment.rs

@@ -4,7 +4,7 @@ use crate::core::SegmentId;
 use crate::core::SegmentMeta;
 use crate::directory::error::{OpenReadError, OpenWriteError};
 use crate::directory::Directory;
-use crate::directory::{ReadOnlySource, WritePtr};
+use crate::directory::{FileSlice, WritePtr};
 use crate::indexer::segment_serializer::SegmentSerializer;
 use crate::schema::Schema;
 use crate::Opstamp;
@@ -78,10 +78,9 @@ 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<FileSlice, OpenReadError> {
         let path = self.relative_path(component);
-        let source = self.index.directory().open_read(&path)?;
-        Ok(source)
+        self.index.directory().open_read(&path)
     }
 
     /// Open one of the component file for *regular* write.

src/core/segment_component.rs

@@ -20,7 +20,7 @@ pub enum SegmentComponent {
     /// Dictionary associating `Term`s to `TermInfo`s which is
     /// simply an address into the `postings` file and the `positions` file.
     TERMS,
-    /// Row-oriented, LZ4-compressed storage of the documents.
+    /// Row-oriented, compressed storage of the documents.
     /// Accessing a document from the store is relatively slow, as it
     /// requires to decompress the entire block it belongs to.
     STORE,

src/core/segment_reader.rs

@@ -1,10 +1,9 @@
-use crate::common::CompositeFile;
 use crate::common::HasLen;
 use crate::core::InvertedIndexReader;
 use crate::core::Segment;
 use crate::core::SegmentComponent;
 use crate::core::SegmentId;
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
 use crate::fastfield::DeleteBitSet;
 use crate::fastfield::FacetReader;
 use crate::fastfield::FastFieldReaders;
@@ -16,11 +15,12 @@ use crate::space_usage::SegmentSpaceUsage;
 use crate::store::StoreReader;
 use crate::termdict::TermDictionary;
 use crate::DocId;
+use crate::{common::CompositeFile, error::DataCorruption};
 use fail::fail_point;
-use std::collections::HashMap;
 use std::fmt;
 use std::sync::Arc;
 use std::sync::RwLock;
+use std::{collections::HashMap, io};
 
 /// Entry point to access all of the datastructures of the `Segment`
 ///
@@ -50,7 +50,7 @@ pub struct SegmentReader {
     fast_fields_readers: Arc<FastFieldReaders>,
     fieldnorm_readers: FieldNormReaders,
 
-    store_source: ReadOnlySource,
+    store_file: FileSlice,
     delete_bitset_opt: Option<DeleteBitSet>,
     schema: Schema,
 }
@@ -106,16 +106,26 @@ impl SegmentReader {
     }
 
     /// Accessor to the `FacetReader` associated to a given `Field`.
-    pub fn facet_reader(&self, field: Field) -> Option<FacetReader> {
+    pub fn facet_reader(&self, field: Field) -> crate::Result<FacetReader> {
         let field_entry = self.schema.get_field_entry(field);
         if field_entry.field_type() != &FieldType::HierarchicalFacet {
-            return None;
+            return Err(crate::TantivyError::InvalidArgument(format!(
+                "Field {:?} is not a facet field.",
+                field_entry.name()
+            )));
         }
-        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 facet_reader = FacetReader::new(term_ords_reader, termdict);
-        Some(facet_reader)
+        let term_ords_reader = self.fast_fields().u64s(field).ok_or_else(|| {
+            DataCorruption::comment_only(format!(
+                "Cannot find data for hierarchical facet {:?}",
+                field_entry.name()
+            ))
+        })?;
+        let termdict = self
+            .termdict_composite
+            .open_read(field)
+            .map(TermDictionary::open)
+            .unwrap_or_else(|| Ok(TermDictionary::empty()))?;
+        Ok(FacetReader::new(term_ords_reader, termdict))
     }
 
     /// Accessor to the segment's `Field norms`'s reader.
@@ -126,10 +136,10 @@ impl SegmentReader {
     /// They are simply stored as a fast field, serialized in
     /// the `.fieldnorm` file of the segment.
     pub fn get_fieldnorms_reader(&self, field: Field) -> crate::Result<FieldNormReader> {
-        self.fieldnorm_readers.get_field(field).ok_or_else(|| {
+        self.fieldnorm_readers.get_field(field)?.ok_or_else(|| {
             let field_name = self.schema.get_field_name(field);
             let err_msg = format!(
-                "Field norm not found for field {:?}. Was it market as indexed during indexing.",
+                "Field norm not found for field {:?}. Was it marked as indexed during indexing?",
                 field_name
             );
             crate::TantivyError::SchemaError(err_msg)
@@ -137,33 +147,33 @@ impl SegmentReader {
     }
 
     /// Accessor to the segment's `StoreReader`.
-    pub fn get_store_reader(&self) -> StoreReader {
-        StoreReader::from_source(self.store_source.clone())
+    pub fn get_store_reader(&self) -> io::Result<StoreReader> {
+        StoreReader::open(self.store_file.clone())
     }
 
     /// Open a new segment for reading.
     pub fn open(segment: &Segment) -> crate::Result<SegmentReader> {
-        let termdict_source = segment.open_read(SegmentComponent::TERMS)?;
-        let termdict_composite = CompositeFile::open(&termdict_source)?;
+        let termdict_file = segment.open_read(SegmentComponent::TERMS)?;
+        let termdict_composite = CompositeFile::open(&termdict_file)?;
 
-        let store_source = segment.open_read(SegmentComponent::STORE)?;
+        let store_file = segment.open_read(SegmentComponent::STORE)?;
 
         fail_point!("SegmentReader::open#middle");
 
-        let postings_source = segment.open_read(SegmentComponent::POSTINGS)?;
-        let postings_composite = CompositeFile::open(&postings_source)?;
+        let postings_file = segment.open_read(SegmentComponent::POSTINGS)?;
+        let postings_composite = CompositeFile::open(&postings_file)?;
 
         let positions_composite = {
-            if let Ok(source) = segment.open_read(SegmentComponent::POSITIONS) {
-                CompositeFile::open(&source)?
+            if let Ok(positions_file) = segment.open_read(SegmentComponent::POSITIONS) {
+                CompositeFile::open(&positions_file)?
             } else {
                 CompositeFile::empty()
             }
         };
 
         let positions_idx_composite = {
-            if let Ok(source) = segment.open_read(SegmentComponent::POSITIONSSKIP) {
-                CompositeFile::open(&source)?
+            if let Ok(positions_skip_file) = segment.open_read(SegmentComponent::POSITIONSSKIP) {
+                CompositeFile::open(&positions_skip_file)?
             } else {
                 CompositeFile::empty()
             }
@@ -181,13 +191,14 @@ impl SegmentReader {
 
         let delete_bitset_opt = if segment.meta().has_deletes() {
             let delete_data = segment.open_read(SegmentComponent::DELETE)?;
-            Some(DeleteBitSet::open(delete_data))
+            let delete_bitset = DeleteBitSet::open(delete_data)?;
+            Some(delete_bitset)
         } else {
             None
         };
 
         Ok(SegmentReader {
-            inv_idx_reader_cache: Arc::new(RwLock::new(HashMap::new())),
+            inv_idx_reader_cache: Default::default(),
             max_doc: segment.meta().max_doc(),
             num_docs: segment.meta().num_docs(),
             termdict_composite,
@@ -195,7 +206,7 @@ impl SegmentReader {
             fast_fields_readers: fast_field_readers,
             fieldnorm_readers,
             segment_id: segment.id(),
-            store_source,
+            store_file,
             delete_bitset_opt,
             positions_composite,
             positions_idx_composite,
@@ -215,14 +226,14 @@ impl SegmentReader {
     /// is returned.
     /// Similarly if the field is marked as indexed but no term has been indexed for the given
     /// index. an empty `InvertedIndexReader` is returned (but no warning is logged).
-    pub fn inverted_index(&self, field: Field) -> Arc<InvertedIndexReader> {
+    pub fn inverted_index(&self, field: Field) -> crate::Result<Arc<InvertedIndexReader>> {
         if let Some(inv_idx_reader) = self
             .inv_idx_reader_cache
             .read()
             .expect("Lock poisoned. This should never happen")
             .get(&field)
         {
-            return Arc::clone(inv_idx_reader);
+            return Ok(Arc::clone(inv_idx_reader));
         }
         let field_entry = self.schema.get_field_entry(field);
         let field_type = field_entry.field_type();
@@ -232,41 +243,42 @@ impl SegmentReader {
             warn!("Field {:?} does not seem indexed.", field_entry.name());
         }
 
-        let postings_source_opt = self.postings_composite.open_read(field);
+        let postings_file_opt = self.postings_composite.open_read(field);
 
-        if postings_source_opt.is_none() || record_option_opt.is_none() {
+        if postings_file_opt.is_none() || record_option_opt.is_none() {
             // no documents in the segment contained this field.
             // As a result, no data is associated to the inverted index.
             //
             // Returns an empty inverted index.
             let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);
-            return Arc::new(InvertedIndexReader::empty(record_option));
+            return Ok(Arc::new(InvertedIndexReader::empty(record_option)));
         }
 
         let record_option = record_option_opt.unwrap();
-        let postings_source = postings_source_opt.unwrap();
+        let postings_file = postings_file_opt.unwrap();
 
-        let termdict_source = self.termdict_composite.open_read(field).expect(
-            "Failed to open field term dictionary in composite file. Is the field indexed?",
-        );
+        let termdict_file: FileSlice = self.termdict_composite.open_read(field)
+            .ok_or_else(||
+               DataCorruption::comment_only(format!("Failed to open field {:?}'s term dictionary in the composite file. Has the schema been modified?", field_entry.name()))
+            )?;
 
-        let positions_source = self
+        let positions_file = self
             .positions_composite
             .open_read(field)
             .expect("Index corrupted. Failed to open field positions in composite file.");
 
-        let positions_idx_source = self
+        let positions_idx_file = self
             .positions_idx_composite
             .open_read(field)
             .expect("Index corrupted. Failed to open field positions in composite file.");
 
         let inv_idx_reader = Arc::new(InvertedIndexReader::new(
-            TermDictionary::from_source(&termdict_source),
-            postings_source,
-            positions_source,
-            positions_idx_source,
+            TermDictionary::open(termdict_file)?,
+            postings_file,
+            positions_file,
+            positions_idx_file,
             record_option,
-        ));
+        )?);
 
         // by releasing the lock in between, we may end up opening the inverting index
         // twice, but this is fine.
@@ -275,7 +287,7 @@ impl SegmentReader {
             .expect("Field reader cache lock poisoned. This should never happen.")
             .insert(field, Arc::clone(&inv_idx_reader));
 
-        inv_idx_reader
+        Ok(inv_idx_reader)
     }
 
     /// Returns the segment id
@@ -303,8 +315,8 @@ impl SegmentReader {
     }
 
     /// Summarize total space usage of this segment.
-    pub fn space_usage(&self) -> SegmentSpaceUsage {
-        SegmentSpaceUsage::new(
+    pub fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
+        Ok(SegmentSpaceUsage::new(
             self.num_docs(),
             self.termdict_composite.space_usage(),
             self.postings_composite.space_usage(),
@@ -312,12 +324,12 @@ impl SegmentReader {
             self.positions_idx_composite.space_usage(),
             self.fast_fields_readers.space_usage(),
             self.fieldnorm_readers.space_usage(),
-            self.get_store_reader().space_usage(),
+            self.get_store_reader()?.space_usage(),
             self.delete_bitset_opt
                 .as_ref()
                 .map(DeleteBitSet::space_usage)
                 .unwrap_or(0),
-        )
+        ))
     }
 }
 
@@ -334,7 +346,7 @@ mod test {
     use crate::DocId;
 
     #[test]
-    fn test_alive_docs_iterator() {
+    fn test_alive_docs_iterator() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         schema_builder.add_text_field("name", TEXT | STORED);
         let schema = schema_builder.build();
@@ -342,26 +354,26 @@ mod test {
         let name = schema.get_field("name").unwrap();
 
         {
-            let mut index_writer = index.writer_for_tests().unwrap();
+            let mut index_writer = index.writer_for_tests()?;
             index_writer.add_document(doc!(name => "tantivy"));
             index_writer.add_document(doc!(name => "horse"));
             index_writer.add_document(doc!(name => "jockey"));
             index_writer.add_document(doc!(name => "cap"));
-
             // we should now have one segment with two docs
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
         }
 
         {
-            let mut index_writer2 = index.writer(50_000_000).unwrap();
+            let mut index_writer2 = index.writer(50_000_000)?;
             index_writer2.delete_term(Term::from_field_text(name, "horse"));
             index_writer2.delete_term(Term::from_field_text(name, "cap"));
 
             // ok, now we should have a deleted doc
-            index_writer2.commit().unwrap();
+            index_writer2.commit()?;
         }
-        let searcher = index.reader().unwrap().searcher();
+        let searcher = index.reader()?.searcher();
         let docs: Vec<DocId> = searcher.segment_reader(0).doc_ids_alive().collect();
         assert_eq!(vec![0u32, 2u32], docs);
+        Ok(())
     }
 }

src/directory/directory.rs

@@ -3,7 +3,7 @@ use crate::directory::error::LockError;
 use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
 use crate::directory::WatchCallback;
 use crate::directory::WatchHandle;
-use crate::directory::{ReadOnlySource, WritePtr};
+use crate::directory::{FileSlice, WritePtr};
 use std::fmt;
 use std::io;
 use std::io::Write;
@@ -11,7 +11,6 @@ use std::marker::Send;
 use std::marker::Sync;
 use std::path::Path;
 use std::path::PathBuf;
-use std::result;
 use std::thread;
 use std::time::Duration;
 
@@ -80,7 +79,7 @@ fn try_acquire_lock(
 ) -> Result<DirectoryLock, TryAcquireLockError> {
     let mut write = directory.open_write(filepath).map_err(|e| match e {
         OpenWriteError::FileAlreadyExists(_) => TryAcquireLockError::FileExists,
-        OpenWriteError::IOError(io_error) => TryAcquireLockError::IOError(io_error.into()),
+        OpenWriteError::IOError { io_error, .. } => TryAcquireLockError::IOError(io_error),
     })?;
     write.flush().map_err(TryAcquireLockError::IOError)?;
     Ok(DirectoryLock::from(Box::new(DirectoryLockGuard {
@@ -117,19 +116,19 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
     /// change.
     ///
     /// Specifically, subsequent writes or flushes should
-    /// have no effect on the returned `ReadOnlySource` object.
+    /// have no effect on the returned `FileSlice` object.
     ///
     /// You should only use this to read files create with [Directory::open_write].
-    fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>;
+    fn open_read(&self, path: &Path) -> Result<FileSlice, OpenReadError>;
 
     /// Removes a file
     ///
     /// Removing a file will not affect an eventual
-    /// existing ReadOnlySource pointing to it.
+    /// existing FileSlice pointing to it.
     ///
     /// Removing a nonexistent file, yields a
     /// `DeleteError::DoesNotExist`.
-    fn delete(&self, path: &Path) -> result::Result<(), DeleteError>;
+    fn delete(&self, path: &Path) -> Result<(), DeleteError>;
 
     /// Returns true iff the file exists
     fn exists(&self, path: &Path) -> bool;
@@ -139,7 +138,7 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
     ///
     /// Right after this call, the file should be created
     /// and any subsequent call to `open_read` for the
-    /// same path should return a `ReadOnlySource`.
+    /// same path should return a `FileSlice`.
     ///
     /// Write operations may be aggressively buffered.
     /// The client of this trait is responsible for calling flush
@@ -153,7 +152,7 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
     /// was not called.
     ///
     /// The file may not previously exist.
-    fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError>;
+    fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError>;
 
     /// Reads the full content file that has been written using
     /// atomic_write.
@@ -169,7 +168,7 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
     /// a partially written file.
     ///
     /// The file may or may not previously exist.
-    fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()>;
+    fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()>;
 
     /// Acquire a lock in the given directory.
     ///

src/directory/error.rs

@@ -1,162 +1,67 @@
 use crate::Version;
-use std::error::Error as StdError;
 use std::fmt;
 use std::io;
 use std::path::PathBuf;
 
 /// Error while trying to acquire a directory lock.
-#[derive(Debug, Fail)]
+#[derive(Debug, Error)]
 pub enum LockError {
     /// Failed to acquired a lock as it is already held by another
     /// client.
     /// - In the context of a blocking lock, this means the lock was not released within some `timeout` period.
     /// - In the context of a non-blocking lock, this means the lock was busy at the moment of the call.
-    #[fail(
-        display = "Could not acquire lock as it is already held, possibly by a different process."
-    )]
+    #[error("Could not acquire lock as it is already held, possibly by a different process.")]
     LockBusy,
     /// Trying to acquire a lock failed with an `IOError`
-    #[fail(display = "Failed to acquire the lock due to an io:Error.")]
+    #[error("Failed to acquire the lock due to an io:Error.")]
     IOError(io::Error),
 }
 
-/// General IO error with an optional path to the offending file.
-#[derive(Debug)]
-pub struct IOError {
-    path: Option<PathBuf>,
-    err: io::Error,
-}
-
-impl Into<io::Error> for IOError {
-    fn into(self) -> io::Error {
-        self.err
-    }
-}
-
-impl fmt::Display for IOError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match self.path {
-            Some(ref path) => write!(f, "io error occurred on path '{:?}': '{}'", path, self.err),
-            None => write!(f, "io error occurred: '{}'", self.err),
-        }
-    }
-}
-
-impl StdError for IOError {
-    fn description(&self) -> &str {
-        "io error occurred"
-    }
-
-    fn cause(&self) -> Option<&dyn StdError> {
-        Some(&self.err)
-    }
-}
-
-impl IOError {
-    pub(crate) fn with_path(path: PathBuf, err: io::Error) -> Self {
-        IOError {
-            path: Some(path),
-            err,
-        }
-    }
-}
-
-impl From<io::Error> for IOError {
-    fn from(err: io::Error) -> IOError {
-        IOError { path: None, err }
-    }
-}
-
 /// Error that may occur when opening a directory
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum OpenDirectoryError {
     /// The underlying directory does not exists.
+    #[error("Directory does not exist: '{0}'.")]
     DoesNotExist(PathBuf),
     /// The path exists but is not a directory.
+    #[error("Path exists but is not a directory: '{0}'.")]
     NotADirectory(PathBuf),
+    /// Failed to create a temp directory.
+    #[error("Failed to create a temporary directory: '{0}'.")]
+    FailedToCreateTempDir(io::Error),
     /// IoError
-    IoError(io::Error),
-}
-
-impl From<io::Error> for OpenDirectoryError {
-    fn from(io_err: io::Error) -> Self {
-        OpenDirectoryError::IoError(io_err)
-    }
-}
-
-impl fmt::Display for OpenDirectoryError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match *self {
-            OpenDirectoryError::DoesNotExist(ref path) => {
-                write!(f, "the underlying directory '{:?}' does not exist", path)
-            }
-            OpenDirectoryError::NotADirectory(ref path) => {
-                write!(f, "the path '{:?}' exists but is not a directory", path)
-            }
-            OpenDirectoryError::IoError(ref err) => write!(
-                f,
-                "IOError while trying to open/create the directory. {:?}",
-                err
-            ),
-        }
-    }
-}
-
-impl StdError for OpenDirectoryError {
-    fn description(&self) -> &str {
-        "error occurred while opening a directory"
-    }
-
-    fn cause(&self) -> Option<&dyn StdError> {
-        None
-    }
+    #[error("IOError '{io_error:?}' while create directory in: '{directory_path:?}'.")]
+    IoError {
+        /// underlying io Error.
+        io_error: io::Error,
+        /// directory we tried to open.
+        directory_path: PathBuf,
+    },
 }
 
 /// Error that may occur when starting to write in a file
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum OpenWriteError {
     /// Our directory is WORM, writing an existing file is forbidden.
     /// Checkout the `Directory` documentation.
+    #[error("File already exists: '{0}'")]
     FileAlreadyExists(PathBuf),
     /// Any kind of IO error that happens when
     /// writing in the underlying IO device.
-    IOError(IOError),
+    #[error("IOError '{io_error:?}' while opening file for write: '{filepath}'.")]
+    IOError {
+        /// The underlying `io::Error`.
+        io_error: io::Error,
+        /// File path of the file that tantivy failed to open for write.
+        filepath: PathBuf,
+    },
 }
 
-impl From<IOError> for OpenWriteError {
-    fn from(err: IOError) -> OpenWriteError {
-        OpenWriteError::IOError(err)
+impl OpenWriteError {
+    pub(crate) fn wrap_io_error(io_error: io::Error, filepath: PathBuf) -> Self {
+        Self::IOError { io_error, filepath }
     }
 }
-
-impl fmt::Display for OpenWriteError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match *self {
-            OpenWriteError::FileAlreadyExists(ref path) => {
-                write!(f, "the file '{:?}' already exists", path)
-            }
-            OpenWriteError::IOError(ref err) => write!(
-                f,
-                "an io error occurred while opening a file for writing: '{}'",
-                err
-            ),
-        }
-    }
-}
-
-impl StdError for OpenWriteError {
-    fn description(&self) -> &str {
-        "error occurred while opening a file for writing"
-    }
-
-    fn cause(&self) -> Option<&dyn StdError> {
-        match *self {
-            OpenWriteError::FileAlreadyExists(_) => None,
-            OpenWriteError::IOError(ref err) => Some(err),
-        }
-    }
-}
-
 /// Type of index incompatibility between the library and the index found on disk
 /// Used to catch and provide a hint to solve this incompatibility issue
 pub enum Incompatibility {
@@ -217,55 +122,46 @@ impl fmt::Debug for Incompatibility {
 }
 
 /// Error that may occur when accessing a file read
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum OpenReadError {
     /// The file does not exists.
+    #[error("Files does not exists: {0:?}")]
     FileDoesNotExist(PathBuf),
-    /// Any kind of IO error that happens when
-    /// interacting with the underlying IO device.
-    IOError(IOError),
-    /// This library doesn't support the index version found on disk
+    /// Any kind of io::Error.
+    #[error(
+        "IOError: '{io_error:?}' happened while opening the following file for Read: {filepath}."
+    )]
+    IOError {
+        /// The underlying `io::Error`.
+        io_error: io::Error,
+        /// File path of the file that tantivy failed to open for read.
+        filepath: PathBuf,
+    },
+    /// This library does not support the index version found in file footer.
+    #[error("Index version unsupported: {0:?}")]
     IncompatibleIndex(Incompatibility),
 }
 
-impl From<IOError> for OpenReadError {
-    fn from(err: IOError) -> OpenReadError {
-        OpenReadError::IOError(err)
+impl OpenReadError {
+    pub(crate) fn wrap_io_error(io_error: io::Error, filepath: PathBuf) -> Self {
+        Self::IOError { io_error, filepath }
     }
 }
-
-impl fmt::Display for OpenReadError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match *self {
-            OpenReadError::FileDoesNotExist(ref path) => {
-                write!(f, "the file '{:?}' does not exist", path)
-            }
-            OpenReadError::IOError(ref err) => write!(
-                f,
-                "an io error occurred while opening a file for reading: '{}'",
-                err
-            ),
-            OpenReadError::IncompatibleIndex(ref footer) => {
-                write!(f, "Incompatible index format: {:?}", footer)
-            }
-        }
-    }
-}
-
 /// Error that may occur when trying to delete a file
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum DeleteError {
     /// The file does not exists.
+    #[error("File does not exists: '{0}'.")]
     FileDoesNotExist(PathBuf),
     /// Any kind of IO error that happens when
     /// interacting with the underlying IO device.
-    IOError(IOError),
-}
-
-impl From<IOError> for DeleteError {
-    fn from(err: IOError) -> DeleteError {
-        DeleteError::IOError(err)
-    }
+    #[error("The following IO error happened while deleting file '{filepath}': '{io_error:?}'.")]
+    IOError {
+        /// The underlying `io::Error`.
+        io_error: io::Error,
+        /// File path of the file that tantivy failed to delete.
+        filepath: PathBuf,
+    },
 }
 
 impl From<Incompatibility> for OpenReadError {
@@ -273,29 +169,3 @@ impl From<Incompatibility> for OpenReadError {
         OpenReadError::IncompatibleIndex(incompatibility)
     }
 }
-
-impl fmt::Display for DeleteError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match *self {
-            DeleteError::FileDoesNotExist(ref path) => {
-                write!(f, "the file '{:?}' does not exist", path)
-            }
-            DeleteError::IOError(ref err) => {
-                write!(f, "an io error occurred while deleting a file: '{}'", err)
-            }
-        }
-    }
-}
-
-impl StdError for DeleteError {
-    fn description(&self) -> &str {
-        "error occurred while deleting a file"
-    }
-
-    fn cause(&self) -> Option<&dyn StdError> {
-        match *self {
-            DeleteError::FileDoesNotExist(_) => None,
-            DeleteError::IOError(ref err) => Some(err),
-        }
-    }
-}

src/directory/file_slice.rs

@@ -0,0 +1,237 @@
+use stable_deref_trait::StableDeref;
+
+use crate::common::HasLen;
+use crate::directory::OwnedBytes;
+use std::sync::Arc;
+use std::{io, ops::Deref};
+
+pub type BoxedData = Box<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
+
+/// Objects that represents files sections in tantivy.
+///
+/// By contract, whatever happens to the directory file, as long as a FileHandle
+/// is alive, the data associated with it cannot be altered or destroyed.
+///
+/// The underlying behavior is therefore specific to the `Directory` that created it.
+/// Despite its name, a `FileSlice` may or may not directly map to an actual file
+/// on the filesystem.
+pub trait FileHandle: 'static + Send + Sync + HasLen {
+    /// Reads a slice of bytes.
+    ///
+    /// This method may panic if the range requested is invalid.
+    fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes>;
+}
+
+impl FileHandle for &'static [u8] {
+    fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
+        let bytes = &self[from..to];
+        Ok(OwnedBytes::new(bytes))
+    }
+}
+
+impl<T: Deref<Target = [u8]>> HasLen for T {
+    fn len(&self) -> usize {
+        self.as_ref().len()
+    }
+}
+
+impl<B> From<B> for FileSlice
+where
+    B: StableDeref + Deref<Target = [u8]> + 'static + Send + Sync,
+{
+    fn from(bytes: B) -> FileSlice {
+        FileSlice::new(OwnedBytes::new(bytes))
+    }
+}
+
+/// Logical slice of read only file in tantivy.
+//
+/// It can be cloned and sliced cheaply.
+///
+#[derive(Clone)]
+pub struct FileSlice {
+    data: Arc<Box<dyn FileHandle>>,
+    start: usize,
+    stop: usize,
+}
+
+impl FileSlice {
+    /// Wraps a FileHandle.
+    pub fn new<D>(data: D) -> Self
+    where
+        D: FileHandle,
+    {
+        let len = data.len();
+        FileSlice {
+            data: Arc::new(Box::new(data)),
+            start: 0,
+            stop: len,
+        }
+    }
+
+    /// Creates a fileslice that is just a view over a slice of the data.
+    ///
+    /// # Panics
+    ///
+    /// Panics if `to < from` or if `to` exceeds the filesize.
+    pub fn slice(&self, from: usize, to: usize) -> FileSlice {
+        assert!(to <= self.len());
+        assert!(to >= from);
+        FileSlice {
+            data: self.data.clone(),
+            start: self.start + from,
+            stop: self.start + to,
+        }
+    }
+
+    /// Creates an empty FileSlice
+    pub fn empty() -> FileSlice {
+        const EMPTY_SLICE: &[u8] = &[];
+        FileSlice::from(EMPTY_SLICE)
+    }
+
+    /// Returns a `OwnedBytes` with all of the data in the `FileSlice`.
+    ///
+    /// The behavior is strongly dependant on the implementation of the underlying
+    /// `Directory` and the `FileSliceTrait` it creates.
+    /// In particular, it is  up to the `Directory` implementation
+    /// to handle caching if needed.
+    pub fn read_bytes(&self) -> io::Result<OwnedBytes> {
+        self.data.read_bytes(self.start, self.stop)
+    }
+
+    /// Reads a specific slice of data.
+    ///
+    /// This is equivalent to running `file_slice.slice(from, to).read_bytes()`.
+    pub fn read_bytes_slice(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
+        assert!(from <= to);
+        assert!(
+            self.start + to <= self.stop,
+            "`to` exceeds the fileslice length"
+        );
+        self.data.read_bytes(self.start + from, self.start + to)
+    }
+
+    /// Splits the FileSlice at the given offset and return two file slices.
+    /// `file_slice[..split_offset]` and `file_slice[split_offset..]`.
+    ///
+    /// This operation is cheap and must not copy any underlying data.
+    pub fn split(self, left_len: usize) -> (FileSlice, FileSlice) {
+        let left = self.slice_to(left_len);
+        let right = self.slice_from(left_len);
+        (left, right)
+    }
+
+    /// Splits the file slice at the given offset and return two file slices.
+    /// `file_slice[..split_offset]` and `file_slice[split_offset..]`.
+    pub fn split_from_end(self, right_len: usize) -> (FileSlice, FileSlice) {
+        let left_len = self.len() - right_len;
+        self.split(left_len)
+    }
+
+    /// Like `.slice(...)` but enforcing only the `from`
+    /// boundary.
+    ///
+    /// Equivalent to `.slice(from_offset, self.len())`
+    pub fn slice_from(&self, from_offset: usize) -> FileSlice {
+        self.slice(from_offset, self.len())
+    }
+
+    /// Like `.slice(...)` but enforcing only the `to`
+    /// boundary.
+    ///
+    /// Equivalent to `.slice(0, to_offset)`
+    pub fn slice_to(&self, to_offset: usize) -> FileSlice {
+        self.slice(0, to_offset)
+    }
+}
+
+impl HasLen for FileSlice {
+    fn len(&self) -> usize {
+        self.stop - self.start
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{FileHandle, FileSlice};
+    use crate::common::HasLen;
+    use std::io;
+
+    #[test]
+    fn test_file_slice() -> io::Result<()> {
+        let file_slice = FileSlice::new(b"abcdef".as_ref());
+        assert_eq!(file_slice.len(), 6);
+        assert_eq!(file_slice.slice_from(2).read_bytes()?.as_slice(), b"cdef");
+        assert_eq!(file_slice.slice_to(2).read_bytes()?.as_slice(), b"ab");
+        assert_eq!(
+            file_slice
+                .slice_from(1)
+                .slice_to(2)
+                .read_bytes()?
+                .as_slice(),
+            b"bc"
+        );
+        {
+            let (left, right) = file_slice.clone().split(0);
+            assert_eq!(left.read_bytes()?.as_slice(), b"");
+            assert_eq!(right.read_bytes()?.as_slice(), b"abcdef");
+        }
+        {
+            let (left, right) = file_slice.clone().split(2);
+            assert_eq!(left.read_bytes()?.as_slice(), b"ab");
+            assert_eq!(right.read_bytes()?.as_slice(), b"cdef");
+        }
+        {
+            let (left, right) = file_slice.clone().split_from_end(0);
+            assert_eq!(left.read_bytes()?.as_slice(), b"abcdef");
+            assert_eq!(right.read_bytes()?.as_slice(), b"");
+        }
+        {
+            let (left, right) = file_slice.clone().split_from_end(2);
+            assert_eq!(left.read_bytes()?.as_slice(), b"abcd");
+            assert_eq!(right.read_bytes()?.as_slice(), b"ef");
+        }
+        Ok(())
+    }
+
+    #[test]
+    fn test_file_slice_trait_slice_len() {
+        let blop: &'static [u8] = b"abc";
+        let owned_bytes: Box<dyn FileHandle> = Box::new(blop);
+        assert_eq!(owned_bytes.len(), 3);
+    }
+
+    #[test]
+    fn test_slice_simple_read() -> io::Result<()> {
+        let slice = FileSlice::new(&b"abcdef"[..]);
+        assert_eq!(slice.len(), 6);
+        assert_eq!(slice.read_bytes()?.as_ref(), b"abcdef");
+        assert_eq!(slice.slice(1, 4).read_bytes()?.as_ref(), b"bcd");
+        Ok(())
+    }
+
+    #[test]
+    fn test_slice_read_slice() -> io::Result<()> {
+        let slice_deref = FileSlice::new(&b"abcdef"[..]);
+        assert_eq!(slice_deref.read_bytes_slice(1, 4)?.as_ref(), b"bcd");
+        Ok(())
+    }
+
+    #[test]
+    #[should_panic(expected = "assertion failed: from <= to")]
+    fn test_slice_read_slice_invalid_range() {
+        let slice_deref = FileSlice::new(&b"abcdef"[..]);
+        assert_eq!(slice_deref.read_bytes_slice(1, 0).unwrap().as_ref(), b"bcd");
+    }
+
+    #[test]
+    #[should_panic(expected = "`to` exceeds the fileslice length")]
+    fn test_slice_read_slice_invalid_range_exceeds() {
+        let slice_deref = FileSlice::new(&b"abcdef"[..]);
+        assert_eq!(
+            slice_deref.read_bytes_slice(0, 10).unwrap().as_ref(),
+            b"bcd"
+        );
+    }
+}

src/directory/footer.rs

@@ -1,9 +1,8 @@
-use crate::common::{BinarySerializable, CountingWriter, FixedSize, VInt};
+use crate::common::{BinarySerializable, CountingWriter, FixedSize, HasLen, VInt};
 use crate::directory::error::Incompatibility;
-use crate::directory::read_only_source::ReadOnlySource;
+use crate::directory::FileSlice;
 use crate::directory::{AntiCallToken, TerminatingWrite};
 use crate::Version;
-use byteorder::{ByteOrder, LittleEndian, WriteBytesExt};
 use crc32fast::Hasher;
 use std::io;
 use std::io::Write;
@@ -64,26 +63,26 @@ impl Footer {
         let mut counting_write = CountingWriter::wrap(&mut write);
         self.serialize(&mut counting_write)?;
         let written_len = counting_write.written_bytes();
-        write.write_u32::<LittleEndian>(written_len as u32)?;
+        (written_len as u32).serialize(write)?;
         Ok(())
     }
 
-    pub fn extract_footer(source: ReadOnlySource) -> Result<(Footer, ReadOnlySource), io::Error> {
-        if source.len() < 4 {
+    pub fn extract_footer(file: FileSlice) -> io::Result<(Footer, FileSlice)> {
+        if file.len() < 4 {
             return Err(io::Error::new(
                 io::ErrorKind::UnexpectedEof,
                 format!(
                     "File corrupted. The file is smaller than 4 bytes (len={}).",
-                    source.len()
+                    file.len()
                 ),
             ));
         }
-        let (body_footer, footer_len_bytes) = source.split_from_end(u32::SIZE_IN_BYTES);
-        let footer_len = LittleEndian::read_u32(footer_len_bytes.as_slice()) as usize;
-        let body_len = body_footer.len() - footer_len;
-        let (body, footer_data) = body_footer.split(body_len);
-        let mut cursor = footer_data.as_slice();
-        let footer = Footer::deserialize(&mut cursor)?;
+        let (body_footer, footer_len_file) = file.split_from_end(u32::SIZE_IN_BYTES);
+        let mut footer_len_bytes = footer_len_file.read_bytes()?;
+        let footer_len = u32::deserialize(&mut footer_len_bytes)? as usize;
+        let (body, footer) = body_footer.split_from_end(footer_len);
+        let mut footer_bytes = footer.read_bytes()?;
+        let footer = Footer::deserialize(&mut footer_bytes)?;
         Ok((footer, body))
     }
 

src/directory/managed_directory.rs

@@ -1,11 +1,11 @@
 use crate::core::{MANAGED_FILEPATH, META_FILEPATH};
-use crate::directory::error::{DeleteError, IOError, LockError, OpenReadError, OpenWriteError};
+use crate::directory::error::{DeleteError, LockError, OpenReadError, OpenWriteError};
 use crate::directory::footer::{Footer, FooterProxy};
 use crate::directory::DirectoryLock;
 use crate::directory::GarbageCollectionResult;
 use crate::directory::Lock;
 use crate::directory::META_LOCK;
-use crate::directory::{ReadOnlySource, WritePtr};
+use crate::directory::{FileSlice, WritePtr};
 use crate::directory::{WatchCallback, WatchHandle};
 use crate::error::DataCorruption;
 use crate::Directory;
@@ -53,7 +53,7 @@ struct MetaInformation {
 /// Saves the file containing the list of existing files
 /// that were created by tantivy.
 fn save_managed_paths(
-    directory: &mut dyn Directory,
+    directory: &dyn Directory,
     wlock: &RwLockWriteGuard<'_, MetaInformation>,
 ) -> io::Result<()> {
     let mut w = serde_json::to_vec(&wlock.managed_paths)?;
@@ -86,7 +86,7 @@ impl ManagedDirectory {
                 directory: Box::new(directory),
                 meta_informations: Arc::default(),
             }),
-            Err(OpenReadError::IOError(e)) => Err(From::from(e)),
+            io_err @ Err(OpenReadError::IOError { .. }) => Err(io_err.err().unwrap().into()),
             Err(OpenReadError::IncompatibleIndex(incompatibility)) => {
                 // For the moment, this should never happen  `meta.json`
                 // do not have any footer and cannot detect incompatibility.
@@ -168,7 +168,7 @@ impl ManagedDirectory {
                         DeleteError::FileDoesNotExist(_) => {
                             deleted_files.push(file_to_delete.clone());
                         }
-                        DeleteError::IOError(_) => {
+                        DeleteError::IOError { .. } => {
                             failed_to_delete_files.push(file_to_delete.clone());
                             if !cfg!(target_os = "windows") {
                                 // On windows, delete is expected to fail if the file
@@ -212,7 +212,7 @@ impl ManagedDirectory {
     /// File starting by "." are reserved to locks.
     /// They are not managed and cannot be subjected
     /// to garbage collection.
-    fn register_file_as_managed(&mut self, filepath: &Path) -> io::Result<()> {
+    fn register_file_as_managed(&self, filepath: &Path) -> io::Result<()> {
         // Files starting by "." (e.g. lock files) are not managed.
         if !is_managed(filepath) {
             return Ok(());
@@ -223,7 +223,7 @@ impl ManagedDirectory {
             .expect("Managed file lock poisoned");
         let has_changed = meta_wlock.managed_paths.insert(filepath.to_owned());
         if has_changed {
-            save_managed_paths(self.directory.as_mut(), &meta_wlock)?;
+            save_managed_paths(self.directory.as_ref(), &meta_wlock)?;
         }
         Ok(())
     }
@@ -231,10 +231,19 @@ impl ManagedDirectory {
     /// Verify checksum of a managed file
     pub fn validate_checksum(&self, path: &Path) -> result::Result<bool, OpenReadError> {
         let reader = self.directory.open_read(path)?;
-        let (footer, data) = Footer::extract_footer(reader)
-            .map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
+        let (footer, data) =
+            Footer::extract_footer(reader).map_err(|io_error| OpenReadError::IOError {
+                io_error,
+                filepath: path.to_path_buf(),
+            })?;
+        let bytes = data
+            .read_bytes()
+            .map_err(|io_error| OpenReadError::IOError {
+                filepath: path.to_path_buf(),
+                io_error,
+            })?;
         let mut hasher = Hasher::new();
-        hasher.update(data.as_slice());
+        hasher.update(bytes.as_slice());
         let crc = hasher.finalize();
         Ok(footer
             .versioned_footer
@@ -245,7 +254,6 @@ impl ManagedDirectory {
 
     /// List files for which checksum does not match content
     pub fn list_damaged(&self) -> result::Result<HashSet<PathBuf>, OpenReadError> {
-        let mut hashset = HashSet::new();
         let mut managed_paths = self
             .meta_informations
             .read()
@@ -255,27 +263,28 @@ impl ManagedDirectory {
 
         managed_paths.remove(*META_FILEPATH);
 
-        for path in managed_paths.into_iter() {
+        let mut damaged_files = HashSet::new();
+        for path in managed_paths {
             if !self.validate_checksum(&path)? {
-                hashset.insert(path);
+                damaged_files.insert(path);
             }
         }
-        Ok(hashset)
+        Ok(damaged_files)
     }
 }
 
 impl Directory for ManagedDirectory {
-    fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
-        let read_only_source = self.directory.open_read(path)?;
-        let (footer, reader) = Footer::extract_footer(read_only_source)
-            .map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
+    fn open_read(&self, path: &Path) -> result::Result<FileSlice, OpenReadError> {
+        let file_slice = self.directory.open_read(path)?;
+        let (footer, reader) = Footer::extract_footer(file_slice)
+            .map_err(|io_error| OpenReadError::wrap_io_error(io_error, path.to_path_buf()))?;
         footer.is_compatible()?;
         Ok(reader)
     }
 
-    fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
+    fn open_write(&self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
         self.register_file_as_managed(path)
-            .map_err(|e| IOError::with_path(path.to_owned(), e))?;
+            .map_err(|io_error| OpenWriteError::wrap_io_error(io_error, path.to_path_buf()))?;
         Ok(io::BufWriter::new(Box::new(FooterProxy::new(
             self.directory
                 .open_write(path)?
@@ -285,7 +294,7 @@ impl Directory for ManagedDirectory {
         ))))
     }
 
-    fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
+    fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()> {
         self.register_file_as_managed(path)?;
         self.directory.atomic_write(path, data)
     }
@@ -399,39 +408,37 @@ mod tests_mmap_specific {
     }
 
     #[test]
-    fn test_checksum() {
+    fn test_checksum() -> crate::Result<()> {
         let test_path1: &'static Path = Path::new("some_path_for_test");
         let test_path2: &'static Path = Path::new("other_test_path");
 
         let tempdir = TempDir::new().unwrap();
         let tempdir_path = PathBuf::from(tempdir.path());
 
-        let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
-        let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
-        let mut write = managed_directory.open_write(test_path1).unwrap();
-        write.write_all(&[0u8, 1u8]).unwrap();
-        write.terminate().unwrap();
+        let mmap_directory = MmapDirectory::open(&tempdir_path)?;
+        let managed_directory = ManagedDirectory::wrap(mmap_directory)?;
+        let mut write = managed_directory.open_write(test_path1)?;
+        write.write_all(&[0u8, 1u8])?;
+        write.terminate()?;
 
-        let mut write = managed_directory.open_write(test_path2).unwrap();
-        write.write_all(&[3u8, 4u8, 5u8]).unwrap();
-        write.terminate().unwrap();
+        let mut write = managed_directory.open_write(test_path2)?;
+        write.write_all(&[3u8, 4u8, 5u8])?;
+        write.terminate()?;
 
-        let read_source = managed_directory.open_read(test_path2).unwrap();
-        assert_eq!(read_source.as_slice(), &[3u8, 4u8, 5u8]);
+        let read_file = managed_directory.open_read(test_path2)?.read_bytes()?;
+        assert_eq!(read_file.as_slice(), &[3u8, 4u8, 5u8]);
         assert!(managed_directory.list_damaged().unwrap().is_empty());
 
         let mut corrupted_path = tempdir_path.clone();
         corrupted_path.push(test_path2);
-        let mut file = OpenOptions::new()
-            .write(true)
-            .open(&corrupted_path)
-            .unwrap();
-        file.write_all(&[255u8]).unwrap();
-        file.flush().unwrap();
+        let mut file = OpenOptions::new().write(true).open(&corrupted_path)?;
+        file.write_all(&[255u8])?;
+        file.flush()?;
         drop(file);
 
-        let damaged = managed_directory.list_damaged().unwrap();
+        let damaged = managed_directory.list_damaged()?;
         assert_eq!(damaged.len(), 1);
         assert!(damaged.contains(test_path2));
+        Ok(())
     }
 }

src/directory/mmap_directory.rs

@@ -1,14 +1,12 @@
 use crate::core::META_FILEPATH;
 use crate::directory::error::LockError;
-use crate::directory::error::{
-    DeleteError, IOError, OpenDirectoryError, OpenReadError, OpenWriteError,
-};
-use crate::directory::read_only_source::BoxedData;
+use crate::directory::error::{DeleteError, OpenDirectoryError, OpenReadError, OpenWriteError};
 use crate::directory::AntiCallToken;
+use crate::directory::BoxedData;
 use crate::directory::Directory;
 use crate::directory::DirectoryLock;
+use crate::directory::FileSlice;
 use crate::directory::Lock;
-use crate::directory::ReadOnlySource;
 use crate::directory::WatchCallback;
 use crate::directory::WatchCallbackList;
 use crate::directory::WatchHandle;
@@ -19,7 +17,7 @@ use notify::RawEvent;
 use notify::RecursiveMode;
 use notify::Watcher;
 use serde::{Deserialize, Serialize};
-use std::collections::HashMap;
+use stable_deref_trait::StableDeref;
 use std::convert::From;
 use std::fmt;
 use std::fs::OpenOptions;
@@ -34,6 +32,7 @@ use std::sync::Mutex;
 use std::sync::RwLock;
 use std::sync::Weak;
 use std::thread;
+use std::{collections::HashMap, ops::Deref};
 use tempfile::TempDir;
 
 /// Create a default io error given a string.
@@ -44,17 +43,17 @@ pub(crate) fn make_io_err(msg: String) -> io::Error {
 /// Returns None iff the file exists, can be read, but is empty (and hence
 /// cannot be mmapped)
 fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
-    let file = File::open(full_path).map_err(|e| {
-        if e.kind() == io::ErrorKind::NotFound {
-            OpenReadError::FileDoesNotExist(full_path.to_owned())
+    let file = File::open(full_path).map_err(|io_err| {
+        if io_err.kind() == io::ErrorKind::NotFound {
+            OpenReadError::FileDoesNotExist(full_path.to_path_buf())
         } else {
-            OpenReadError::IOError(IOError::with_path(full_path.to_owned(), e))
+            OpenReadError::wrap_io_error(io_err, full_path.to_path_buf())
         }
     })?;
 
     let meta_data = file
         .metadata()
-        .map_err(|e| IOError::with_path(full_path.to_owned(), e))?;
+        .map_err(|io_err| OpenReadError::wrap_io_error(io_err, full_path.to_owned()))?;
     if meta_data.len() == 0 {
         // if the file size is 0, it will not be possible
         // to mmap the file, so we return None
@@ -64,7 +63,7 @@ fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
     unsafe {
         memmap::Mmap::map(&file)
             .map(Some)
-            .map_err(|e| From::from(IOError::with_path(full_path.to_owned(), e)))
+            .map_err(|io_err| OpenReadError::wrap_io_error(io_err, full_path.to_path_buf()))
     }
 }
 
@@ -183,6 +182,10 @@ impl WatcherWrapper {
                         }
                     }
                 }
+            })
+            .map_err(|io_error| OpenDirectoryError::IoError {
+                io_error,
+                directory_path: path.to_path_buf(),
             })?;
         Ok(WatcherWrapper {
             _watcher: Mutex::new(watcher),
@@ -272,9 +275,11 @@ impl MmapDirectory {
     /// This is mostly useful to test the MmapDirectory itself.
     /// For your unit tests, prefer the RAMDirectory.
     pub fn create_from_tempdir() -> Result<MmapDirectory, OpenDirectoryError> {
-        let tempdir = TempDir::new().map_err(OpenDirectoryError::IoError)?;
-        let tempdir_path = PathBuf::from(tempdir.path());
-        Ok(MmapDirectory::new(tempdir_path, Some(tempdir)))
+        let tempdir = TempDir::new().map_err(OpenDirectoryError::FailedToCreateTempDir)?;
+        Ok(MmapDirectory::new(
+            tempdir.path().to_path_buf(),
+            Some(tempdir),
+        ))
     }
 
     /// Opens a MmapDirectory in a directory.
@@ -396,8 +401,20 @@ impl TerminatingWrite for SafeFileWriter {
     }
 }
 
+#[derive(Clone)]
+struct MmapArc(Arc<Box<dyn Deref<Target = [u8]> + Send + Sync>>);
+
+impl Deref for MmapArc {
+    type Target = [u8];
+
+    fn deref(&self) -> &[u8] {
+        self.0.deref()
+    }
+}
+unsafe impl StableDeref for MmapArc {}
+
 impl Directory for MmapDirectory {
-    fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
+    fn open_read(&self, path: &Path) -> result::Result<FileSlice, OpenReadError> {
         debug!("Open Read {:?}", path);
         let full_path = self.resolve_path(path);
 
@@ -407,12 +424,14 @@ impl Directory for MmapDirectory {
                  on mmap cache while reading {:?}",
                 path
             );
-            IOError::with_path(path.to_owned(), make_io_err(msg))
+            let io_err = make_io_err(msg);
+            OpenReadError::wrap_io_error(io_err, path.to_path_buf())
         })?;
-        Ok(mmap_cache
-            .get_mmap(&full_path)?
-            .map(ReadOnlySource::from)
-            .unwrap_or_else(ReadOnlySource::empty))
+        if let Some(mmap_arc) = mmap_cache.get_mmap(&full_path)? {
+            Ok(FileSlice::from(MmapArc(mmap_arc)))
+        } else {
+            Ok(FileSlice::empty())
+        }
     }
 
     /// Any entry associated to the path in the mmap will be
@@ -420,14 +439,18 @@ impl Directory for MmapDirectory {
     fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
         let full_path = self.resolve_path(path);
         match fs::remove_file(&full_path) {
-            Ok(_) => self
-                .sync_directory()
-                .map_err(|e| IOError::with_path(path.to_owned(), e).into()),
+            Ok(_) => self.sync_directory().map_err(|e| DeleteError::IOError {
+                io_error: e,
+                filepath: path.to_path_buf(),
+            }),
             Err(e) => {
                 if e.kind() == io::ErrorKind::NotFound {
                     Err(DeleteError::FileDoesNotExist(path.to_owned()))
                 } else {
-                    Err(IOError::with_path(path.to_owned(), e).into())
+                    Err(DeleteError::IOError {
+                        io_error: e,
+                        filepath: path.to_path_buf(),
+                    })
                 }
             }
         }
@@ -438,7 +461,7 @@ impl Directory for MmapDirectory {
         full_path.exists()
     }
 
-    fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
+    fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError> {
         debug!("Open Write {:?}", path);
         let full_path = self.resolve_path(path);
 
@@ -447,22 +470,22 @@ impl Directory for MmapDirectory {
             .create_new(true)
             .open(full_path);
 
-        let mut file = open_res.map_err(|err| {
-            if err.kind() == io::ErrorKind::AlreadyExists {
-                OpenWriteError::FileAlreadyExists(path.to_owned())
+        let mut file = open_res.map_err(|io_err| {
+            if io_err.kind() == io::ErrorKind::AlreadyExists {
+                OpenWriteError::FileAlreadyExists(path.to_path_buf())
             } else {
-                IOError::with_path(path.to_owned(), err).into()
+                OpenWriteError::wrap_io_error(io_err, path.to_path_buf())
             }
         })?;
 
         // making sure the file is created.
         file.flush()
-            .map_err(|e| IOError::with_path(path.to_owned(), e))?;
+            .map_err(|io_error| OpenWriteError::wrap_io_error(io_error, path.to_path_buf()))?;
 
         // Apparetntly, on some filesystem syncing the parent
         // directory is required.
         self.sync_directory()
-            .map_err(|e| IOError::with_path(path.to_owned(), e))?;
+            .map_err(|io_err| OpenWriteError::wrap_io_error(io_err, path.to_path_buf()))?;
 
         let writer = SafeFileWriter::new(file);
         Ok(BufWriter::new(Box::new(writer)))
@@ -473,21 +496,22 @@ impl Directory for MmapDirectory {
         let mut buffer = Vec::new();
         match File::open(&full_path) {
             Ok(mut file) => {
-                file.read_to_end(&mut buffer)
-                    .map_err(|e| IOError::with_path(path.to_owned(), e))?;
+                file.read_to_end(&mut buffer).map_err(|io_error| {
+                    OpenReadError::wrap_io_error(io_error, path.to_path_buf())
+                })?;
                 Ok(buffer)
             }
-            Err(e) => {
-                if e.kind() == io::ErrorKind::NotFound {
+            Err(io_error) => {
+                if io_error.kind() == io::ErrorKind::NotFound {
                     Err(OpenReadError::FileDoesNotExist(path.to_owned()))
                 } else {
-                    Err(IOError::with_path(path.to_owned(), e).into())
+                    Err(OpenReadError::wrap_io_error(io_error, path.to_path_buf()))
                 }
             }
         }
     }
 
-    fn atomic_write(&mut self, path: &Path, content: &[u8]) -> io::Result<()> {
+    fn atomic_write(&self, path: &Path, content: &[u8]) -> io::Result<()> {
         debug!("Atomic Write {:?}", path);
         let mut tempfile = tempfile::Builder::new().tempfile_in(&self.inner.root_path)?;
         tempfile.write_all(content)?;
@@ -529,10 +553,10 @@ mod tests {
     // The following tests are specific to the MmapDirectory
 
     use super::*;
-    use crate::indexer::LogMergePolicy;
     use crate::schema::{Schema, SchemaBuilder, TEXT};
     use crate::Index;
     use crate::ReloadPolicy;
+    use crate::{common::HasLen, indexer::LogMergePolicy};
     use std::fs;
     use std::sync::atomic::{AtomicUsize, Ordering};
 
@@ -547,7 +571,7 @@ mod tests {
         // cannot be mmapped.
         //
         // In that case the directory returns a SharedVecSlice.
-        let mut mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
+        let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
         let path = PathBuf::from("test");
         {
             let mut w = mmap_directory.open_write(&path).unwrap();
@@ -563,7 +587,7 @@ mod tests {
 
         // here we test if the cache releases
         // mmaps correctly.
-        let mut mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
+        let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
         let num_paths = 10;
         let paths: Vec<PathBuf> = (0..num_paths)
             .map(|i| PathBuf::from(&*format!("file_{}", i)))

src/directory/mod.rs

@@ -9,10 +9,11 @@ mod mmap_directory;
 
 mod directory;
 mod directory_lock;
+mod file_slice;
 mod footer;
 mod managed_directory;
+mod owned_bytes;
 mod ram_directory;
-mod read_only_source;
 mod watch_event_router;
 
 /// Errors specific to the directory module.
@@ -21,11 +22,14 @@ pub mod error;
 pub use self::directory::DirectoryLock;
 pub use self::directory::{Directory, DirectoryClone};
 pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
+pub(crate) use self::file_slice::BoxedData;
+pub use self::file_slice::{FileHandle, FileSlice};
+pub use self::owned_bytes::OwnedBytes;
 pub use self::ram_directory::RAMDirectory;
-pub use self::read_only_source::ReadOnlySource;
 pub use self::watch_event_router::{WatchCallback, WatchCallbackList, WatchHandle};
 use std::io::{self, BufWriter, Write};
 use std::path::PathBuf;
+
 /// Outcome of the Garbage collection
 pub struct GarbageCollectionResult {
     /// List of files that were deleted in this cycle

src/directory/owned_bytes.rs

@@ -0,0 +1,255 @@
+use crate::directory::FileHandle;
+use stable_deref_trait::StableDeref;
+use std::mem;
+use std::ops::Deref;
+use std::sync::Arc;
+use std::{fmt, io};
+
+/// An OwnedBytes simply wraps an object that owns a slice of data and exposes
+/// this data as a static slice.
+///
+/// The backing object is required to be `StableDeref`.
+#[derive(Clone)]
+pub struct OwnedBytes {
+    data: &'static [u8],
+    box_stable_deref: Arc<dyn Deref<Target = [u8]> + Sync + Send>,
+}
+
+impl FileHandle for OwnedBytes {
+    fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
+        Ok(self.slice(from, to))
+    }
+}
+
+impl OwnedBytes {
+    /// Creates an empty `OwnedBytes`.
+    pub fn empty() -> OwnedBytes {
+        OwnedBytes::new(&[][..])
+    }
+
+    /// Creates an `OwnedBytes` intance given a `StableDeref` object.
+    pub fn new<T: StableDeref + Deref<Target = [u8]> + 'static + Send + Sync>(
+        data_holder: T,
+    ) -> OwnedBytes {
+        let box_stable_deref = Arc::new(data_holder);
+        let bytes: &[u8] = box_stable_deref.as_ref();
+        let data = unsafe { mem::transmute::<_, &'static [u8]>(bytes.deref()) };
+        OwnedBytes {
+            box_stable_deref,
+            data,
+        }
+    }
+
+    /// creates a fileslice that is just a view over a slice of the data.
+    pub fn slice(&self, from: usize, to: usize) -> Self {
+        OwnedBytes {
+            data: &self.data[from..to],
+            box_stable_deref: self.box_stable_deref.clone(),
+        }
+    }
+
+    /// Returns the underlying slice of data.
+    /// `Deref` and `AsRef` are also available.
+    #[inline(always)]
+    pub fn as_slice(&self) -> &[u8] {
+        self.data
+    }
+
+    /// Returns the len of the slice.
+    #[inline(always)]
+    pub fn len(&self) -> usize {
+        self.data.len()
+    }
+
+    /// Splits the OwnedBytes into two OwnedBytes `(left, right)`.
+    ///
+    /// Left will hold `split_len` bytes.
+    ///
+    /// This operation is cheap and does not require to copy any memory.
+    /// On the other hand, both `left` and `right` retain a handle over
+    /// the entire slice of memory. In other words, the memory will only
+    /// be released when both left and right are dropped.
+    pub fn split(self, split_len: usize) -> (OwnedBytes, OwnedBytes) {
+        let right_box_stable_deref = self.box_stable_deref.clone();
+        let left = OwnedBytes {
+            data: &self.data[..split_len],
+            box_stable_deref: self.box_stable_deref,
+        };
+        let right = OwnedBytes {
+            data: &self.data[split_len..],
+            box_stable_deref: right_box_stable_deref,
+        };
+        (left, right)
+    }
+
+    /// Returns true iff this `OwnedBytes` is empty.
+    #[inline(always)]
+    pub fn is_empty(&self) -> bool {
+        self.as_slice().is_empty()
+    }
+
+    /// Drops the left most `advance_len` bytes.
+    ///
+    /// See also [.clip(clip_len: usize))](#method.clip).
+    #[inline(always)]
+    pub fn advance(&mut self, advance_len: usize) {
+        self.data = &self.data[advance_len..]
+    }
+}
+
+impl fmt::Debug for OwnedBytes {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        // We truncate the bytes in order to make sure the debug string
+        // is not too long.
+        let bytes_truncated: &[u8] = if self.len() > 8 {
+            &self.as_slice()[..10]
+        } else {
+            self.as_slice()
+        };
+        write!(f, "OwnedBytes({:?}, len={})", bytes_truncated, self.len())
+    }
+}
+
+impl Deref for OwnedBytes {
+    type Target = [u8];
+
+    fn deref(&self) -> &Self::Target {
+        self.as_slice()
+    }
+}
+
+impl io::Read for OwnedBytes {
+    fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> {
+        let read_len = {
+            let data = self.as_slice();
+            if data.len() >= buf.len() {
+                let buf_len = buf.len();
+                buf.copy_from_slice(&data[..buf_len]);
+                buf.len()
+            } else {
+                let data_len = data.len();
+                buf[..data_len].copy_from_slice(data);
+                data_len
+            }
+        };
+        self.advance(read_len);
+        Ok(read_len)
+    }
+    fn read_to_end(&mut self, buf: &mut Vec<u8>) -> io::Result<usize> {
+        let read_len = {
+            let data = self.as_slice();
+            buf.extend(data);
+            data.len()
+        };
+        self.advance(read_len);
+        Ok(read_len)
+    }
+    fn read_exact(&mut self, buf: &mut [u8]) -> io::Result<()> {
+        let read_len = self.read(buf)?;
+        if read_len != buf.len() {
+            return Err(io::Error::new(
+                io::ErrorKind::UnexpectedEof,
+                "failed to fill whole buffer",
+            ));
+        }
+        Ok(())
+    }
+}
+
+impl AsRef<[u8]> for OwnedBytes {
+    fn as_ref(&self) -> &[u8] {
+        self.as_slice()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use std::io::{self, Read};
+
+    use super::OwnedBytes;
+
+    #[test]
+    fn test_owned_bytes_debug() {
+        let short_bytes = OwnedBytes::new(b"abcd".as_ref());
+        assert_eq!(
+            format!("{:?}", short_bytes),
+            "OwnedBytes([97, 98, 99, 100], len=4)"
+        );
+        let long_bytes = OwnedBytes::new(b"abcdefghijklmnopq".as_ref());
+        assert_eq!(
+            format!("{:?}", long_bytes),
+            "OwnedBytes([97, 98, 99, 100, 101, 102, 103, 104, 105, 106], len=17)"
+        );
+    }
+
+    #[test]
+    fn test_owned_bytes_read() -> io::Result<()> {
+        let mut bytes = OwnedBytes::new(b"abcdefghiklmnopqrstuvwxyz".as_ref());
+        {
+            let mut buf = [0u8; 5];
+            bytes.read_exact(&mut buf[..]).unwrap();
+            assert_eq!(&buf, b"abcde");
+            assert_eq!(bytes.as_slice(), b"fghiklmnopqrstuvwxyz")
+        }
+        {
+            let mut buf = [0u8; 2];
+            bytes.read_exact(&mut buf[..]).unwrap();
+            assert_eq!(&buf, b"fg");
+            assert_eq!(bytes.as_slice(), b"hiklmnopqrstuvwxyz")
+        }
+        Ok(())
+    }
+
+    #[test]
+    fn test_owned_bytes_read_right_at_the_end() -> io::Result<()> {
+        let mut bytes = OwnedBytes::new(b"abcde".as_ref());
+        let mut buf = [0u8; 5];
+        assert_eq!(bytes.read(&mut buf[..]).unwrap(), 5);
+        assert_eq!(&buf, b"abcde");
+        assert_eq!(bytes.as_slice(), b"");
+        assert_eq!(bytes.read(&mut buf[..]).unwrap(), 0);
+        assert_eq!(&buf, b"abcde");
+        Ok(())
+    }
+    #[test]
+    fn test_owned_bytes_read_incomplete() -> io::Result<()> {
+        let mut bytes = OwnedBytes::new(b"abcde".as_ref());
+        let mut buf = [0u8; 7];
+        assert_eq!(bytes.read(&mut buf[..]).unwrap(), 5);
+        assert_eq!(&buf[..5], b"abcde");
+        assert_eq!(bytes.read(&mut buf[..]).unwrap(), 0);
+        Ok(())
+    }
+
+    #[test]
+    fn test_owned_bytes_read_to_end() -> io::Result<()> {
+        let mut bytes = OwnedBytes::new(b"abcde".as_ref());
+        let mut buf = Vec::new();
+        bytes.read_to_end(&mut buf)?;
+        assert_eq!(buf.as_slice(), b"abcde".as_ref());
+        Ok(())
+    }
+
+    #[test]
+    fn test_owned_bytes_split() {
+        let bytes = OwnedBytes::new(b"abcdefghi".as_ref());
+        let (left, right) = bytes.split(3);
+        assert_eq!(left.as_slice(), b"abc");
+        assert_eq!(right.as_slice(), b"defghi");
+    }
+
+    #[test]
+    fn test_owned_bytes_split_boundary() {
+        let bytes = OwnedBytes::new(b"abcdefghi".as_ref());
+        {
+            let (left, right) = bytes.clone().split(0);
+            assert_eq!(left.as_slice(), b"");
+            assert_eq!(right.as_slice(), b"abcdefghi");
+        }
+        {
+            let (left, right) = bytes.split(9);
+            assert_eq!(left.as_slice(), b"abcdefghi");
+            assert_eq!(right.as_slice(), b"");
+        }
+    }
+}

src/directory/ram_directory.rs

@@ -1,9 +1,9 @@
-use crate::core::META_FILEPATH;
 use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
 use crate::directory::AntiCallToken;
 use crate::directory::WatchCallbackList;
-use crate::directory::{Directory, ReadOnlySource, WatchCallback, WatchHandle};
+use crate::directory::{Directory, FileSlice, WatchCallback, WatchHandle};
 use crate::directory::{TerminatingWrite, WritePtr};
+use crate::{common::HasLen, core::META_FILEPATH};
 use fail::fail_point;
 use std::collections::HashMap;
 use std::fmt;
@@ -80,17 +80,17 @@ impl TerminatingWrite for VecWriter {
 
 #[derive(Default)]
 struct InnerDirectory {
-    fs: HashMap<PathBuf, ReadOnlySource>,
+    fs: HashMap<PathBuf, FileSlice>,
     watch_router: WatchCallbackList,
 }
 
 impl InnerDirectory {
     fn write(&mut self, path: PathBuf, data: &[u8]) -> bool {
-        let data = ReadOnlySource::new(Vec::from(data));
+        let data = FileSlice::from(data.to_vec());
         self.fs.insert(path, data).is_some()
     }
 
-    fn open_read(&self, path: &Path) -> Result<ReadOnlySource, OpenReadError> {
+    fn open_read(&self, path: &Path) -> Result<FileSlice, OpenReadError> {
         self.fs
             .get(path)
             .ok_or_else(|| OpenReadError::FileDoesNotExist(PathBuf::from(path)))
@@ -151,11 +151,11 @@ impl RAMDirectory {
     /// written using the `atomic_write` api.
     ///
     /// If an error is encounterred, files may be persisted partially.
-    pub fn persist(&self, dest: &mut dyn Directory) -> crate::Result<()> {
+    pub fn persist(&self, dest: &dyn Directory) -> crate::Result<()> {
         let wlock = self.fs.write().unwrap();
-        for (path, source) in wlock.fs.iter() {
+        for (path, file) in wlock.fs.iter() {
             let mut dest_wrt = dest.open_write(path)?;
-            dest_wrt.write_all(source.as_slice())?;
+            dest_wrt.write_all(file.read_bytes()?.as_slice())?;
             dest_wrt.terminate()?;
         }
         Ok(())
@@ -163,15 +163,16 @@ impl RAMDirectory {
 }
 
 impl Directory for RAMDirectory {
-    fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
+    fn open_read(&self, path: &Path) -> result::Result<FileSlice, OpenReadError> {
         self.fs.read().unwrap().open_read(path)
     }
 
     fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
         fail_point!("RAMDirectory::delete", |_| {
-            use crate::directory::error::IOError;
-            let io_error = IOError::from(io::Error::from(io::ErrorKind::Other));
-            Err(DeleteError::from(io_error))
+            Err(DeleteError::IOError {
+                io_error: io::Error::from(io::ErrorKind::Other),
+                filepath: path.to_path_buf(),
+            })
         });
         self.fs.write().unwrap().delete(path)
     }
@@ -180,7 +181,7 @@ impl Directory for RAMDirectory {
         self.fs.read().unwrap().exists(path)
     }
 
-    fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
+    fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError> {
         let mut fs = self.fs.write().unwrap();
         let path_buf = PathBuf::from(path);
         let vec_writer = VecWriter::new(path_buf.clone(), self.clone());
@@ -194,10 +195,17 @@ impl Directory for RAMDirectory {
     }
 
     fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError> {
-        Ok(self.open_read(path)?.as_slice().to_owned())
+        let bytes =
+            self.open_read(path)?
+                .read_bytes()
+                .map_err(|io_error| OpenReadError::IOError {
+                    io_error,
+                    filepath: path.to_path_buf(),
+                })?;
+        Ok(bytes.as_slice().to_owned())
     }
 
-    fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
+    fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()> {
         fail_point!("RAMDirectory::atomic_write", |msg| Err(io::Error::new(
             io::ErrorKind::Other,
             msg.unwrap_or_else(|| "Undefined".to_string())
@@ -234,13 +242,13 @@ mod tests {
         let msg_seq: &'static [u8] = b"sequential is the way";
         let path_atomic: &'static Path = Path::new("atomic");
         let path_seq: &'static Path = Path::new("seq");
-        let mut directory = RAMDirectory::create();
+        let directory = RAMDirectory::create();
         assert!(directory.atomic_write(path_atomic, msg_atomic).is_ok());
         let mut wrt = directory.open_write(path_seq).unwrap();
         assert!(wrt.write_all(msg_seq).is_ok());
         assert!(wrt.flush().is_ok());
-        let mut directory_copy = RAMDirectory::create();
-        assert!(directory.persist(&mut directory_copy).is_ok());
+        let directory_copy = RAMDirectory::create();
+        assert!(directory.persist(&directory_copy).is_ok());
         assert_eq!(directory_copy.atomic_read(path_atomic).unwrap(), msg_atomic);
         assert_eq!(directory_copy.atomic_read(path_seq).unwrap(), msg_seq);
     }

src/directory/read_only_source.rs

@@ -1,137 +0,0 @@
-use crate::common::HasLen;
-use stable_deref_trait::{CloneStableDeref, StableDeref};
-use std::ops::Deref;
-use std::sync::Arc;
-
-pub type BoxedData = Box<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
-
-/// Read object that represents files in tantivy.
-///
-/// These read objects are only in charge to deliver
-/// the data in the form of a constant read-only `&[u8]`.
-/// Whatever happens to the directory file, the data
-/// hold by this object should never be altered or destroyed.
-pub struct ReadOnlySource {
-    data: Arc<BoxedData>,
-    start: usize,
-    stop: usize,
-}
-
-unsafe impl StableDeref for ReadOnlySource {}
-unsafe impl CloneStableDeref for ReadOnlySource {}
-
-impl Deref for ReadOnlySource {
-    type Target = [u8];
-
-    fn deref(&self) -> &[u8] {
-        self.as_slice()
-    }
-}
-
-impl From<Arc<BoxedData>> for ReadOnlySource {
-    fn from(data: Arc<BoxedData>) -> Self {
-        let len = data.len();
-        ReadOnlySource {
-            data,
-            start: 0,
-            stop: len,
-        }
-    }
-}
-
-impl ReadOnlySource {
-    pub(crate) fn new<D>(data: D) -> ReadOnlySource
-    where
-        D: Deref<Target = [u8]> + Send + Sync + 'static,
-    {
-        let len = data.len();
-        ReadOnlySource {
-            data: Arc::new(Box::new(data)),
-            start: 0,
-            stop: len,
-        }
-    }
-
-    /// Creates an empty ReadOnlySource
-    pub fn empty() -> ReadOnlySource {
-        ReadOnlySource::new(&[][..])
-    }
-
-    /// Returns the data underlying the ReadOnlySource object.
-    pub fn as_slice(&self) -> &[u8] {
-        &self.data[self.start..self.stop]
-    }
-
-    /// Splits into 2 `ReadOnlySource`, at the offset given
-    /// as an argument.
-    pub fn split(self, addr: usize) -> (ReadOnlySource, ReadOnlySource) {
-        let left = self.slice(0, addr);
-        let right = self.slice_from(addr);
-        (left, right)
-    }
-
-    /// Splits into 2 `ReadOnlySource`, at the offset `end - right_len`.
-    pub fn split_from_end(self, right_len: usize) -> (ReadOnlySource, ReadOnlySource) {
-        let left_len = self.len() - right_len;
-        self.split(left_len)
-    }
-
-    /// Creates a ReadOnlySource that is just a
-    /// view over a slice of the data.
-    ///
-    /// Keep in mind that any living slice extends
-    /// the lifetime of the original ReadOnlySource,
-    ///
-    /// For instance, if `ReadOnlySource` wraps 500MB
-    /// worth of data in anonymous memory, and only a
-    /// 1KB slice is remaining, the whole `500MBs`
-    /// are retained in memory.
-    pub fn slice(&self, start: usize, stop: usize) -> ReadOnlySource {
-        assert!(
-            start <= stop,
-            "Requested negative slice [{}..{}]",
-            start,
-            stop
-        );
-        assert!(stop <= self.len());
-        ReadOnlySource {
-            data: self.data.clone(),
-            start: self.start + start,
-            stop: self.start + stop,
-        }
-    }
-
-    /// Like `.slice(...)` but enforcing only the `from`
-    /// boundary.
-    ///
-    /// Equivalent to `.slice(from_offset, self.len())`
-    pub fn slice_from(&self, from_offset: usize) -> ReadOnlySource {
-        self.slice(from_offset, self.len())
-    }
-
-    /// Like `.slice(...)` but enforcing only the `to`
-    /// boundary.
-    ///
-    /// Equivalent to `.slice(0, to_offset)`
-    pub fn slice_to(&self, to_offset: usize) -> ReadOnlySource {
-        self.slice(0, to_offset)
-    }
-}
-
-impl HasLen for ReadOnlySource {
-    fn len(&self) -> usize {
-        self.stop - self.start
-    }
-}
-
-impl Clone for ReadOnlySource {
-    fn clone(&self) -> Self {
-        self.slice_from(0)
-    }
-}
-
-impl From<Vec<u8>> for ReadOnlySource {
-    fn from(data: Vec<u8>) -> ReadOnlySource {
-        ReadOnlySource::new(data)
-    }
-}

src/directory/tests.rs

@@ -20,45 +20,47 @@ mod mmap_directory_tests {
     }
 
     #[test]
-    fn test_simple() {
-        let mut directory = make_directory();
-        super::test_simple(&mut directory);
+    fn test_simple() -> crate::Result<()> {
+        let directory = make_directory();
+        super::test_simple(&directory)
     }
 
     #[test]
     fn test_write_create_the_file() {
-        let mut directory = make_directory();
-        super::test_write_create_the_file(&mut directory);
+        let directory = make_directory();
+        super::test_write_create_the_file(&directory);
     }
 
     #[test]
-    fn test_rewrite_forbidden() {
-        let mut directory = make_directory();
-        super::test_rewrite_forbidden(&mut directory);
+    fn test_rewrite_forbidden() -> crate::Result<()> {
+        let directory = make_directory();
+        super::test_rewrite_forbidden(&directory)?;
+        Ok(())
     }
 
     #[test]
-    fn test_directory_delete() {
-        let mut directory = make_directory();
-        super::test_directory_delete(&mut directory);
+    fn test_directory_delete() -> crate::Result<()> {
+        let directory = make_directory();
+        super::test_directory_delete(&directory)?;
+        Ok(())
     }
 
     #[test]
     fn test_lock_non_blocking() {
-        let mut directory = make_directory();
-        super::test_lock_non_blocking(&mut directory);
+        let directory = make_directory();
+        super::test_lock_non_blocking(&directory);
     }
 
     #[test]
     fn test_lock_blocking() {
-        let mut directory = make_directory();
-        super::test_lock_blocking(&mut directory);
+        let directory = make_directory();
+        super::test_lock_blocking(&directory);
     }
 
     #[test]
     fn test_watch() {
-        let mut directory = make_directory();
-        super::test_watch(&mut directory);
+        let directory = make_directory();
+        super::test_watch(&directory);
     }
 }
 
@@ -72,45 +74,47 @@ mod ram_directory_tests {
     }
 
     #[test]
-    fn test_simple() {
-        let mut directory = make_directory();
-        super::test_simple(&mut directory);
+    fn test_simple() -> crate::Result<()> {
+        let directory = make_directory();
+        super::test_simple(&directory)
     }
 
     #[test]
     fn test_write_create_the_file() {
-        let mut directory = make_directory();
-        super::test_write_create_the_file(&mut directory);
+        let directory = make_directory();
+        super::test_write_create_the_file(&directory);
     }
 
     #[test]
-    fn test_rewrite_forbidden() {
-        let mut directory = make_directory();
-        super::test_rewrite_forbidden(&mut directory);
+    fn test_rewrite_forbidden() -> crate::Result<()> {
+        let directory = make_directory();
+        super::test_rewrite_forbidden(&directory)?;
+        Ok(())
     }
 
     #[test]
-    fn test_directory_delete() {
-        let mut directory = make_directory();
-        super::test_directory_delete(&mut directory);
+    fn test_directory_delete() -> crate::Result<()> {
+        let directory = make_directory();
+        super::test_directory_delete(&directory)?;
+        Ok(())
     }
 
     #[test]
     fn test_lock_non_blocking() {
-        let mut directory = make_directory();
-        super::test_lock_non_blocking(&mut directory);
+        let directory = make_directory();
+        super::test_lock_non_blocking(&directory);
     }
 
     #[test]
     fn test_lock_blocking() {
-        let mut directory = make_directory();
-        super::test_lock_blocking(&mut directory);
+        let directory = make_directory();
+        super::test_lock_blocking(&directory);
     }
 
     #[test]
     fn test_watch() {
-        let mut directory = make_directory();
-        super::test_watch(&mut directory);
+        let directory = make_directory();
+        super::test_watch(&directory);
     }
 }
 
@@ -118,43 +122,37 @@ mod ram_directory_tests {
 #[should_panic]
 fn ram_directory_panics_if_flush_forgotten() {
     let test_path: &'static Path = Path::new("some_path_for_test");
-    let mut ram_directory = RAMDirectory::create();
+    let ram_directory = RAMDirectory::create();
     let mut write_file = ram_directory.open_write(test_path).unwrap();
     assert!(write_file.write_all(&[4]).is_ok());
 }
 
-fn test_simple(directory: &mut dyn Directory) {
+fn test_simple(directory: &dyn Directory) -> crate::Result<()> {
     let test_path: &'static Path = Path::new("some_path_for_test");
-    {
-        let mut write_file = directory.open_write(test_path).unwrap();
-        assert!(directory.exists(test_path));
-        write_file.write_all(&[4]).unwrap();
-        write_file.write_all(&[3]).unwrap();
-        write_file.write_all(&[7, 3, 5]).unwrap();
-        write_file.flush().unwrap();
-    }
-    {
-        let read_file = directory.open_read(test_path).unwrap();
-        let data: &[u8] = &*read_file;
-        assert_eq!(data, &[4u8, 3u8, 7u8, 3u8, 5u8]);
-    }
+    let mut write_file = directory.open_write(test_path)?;
+    assert!(directory.exists(test_path));
+    write_file.write_all(&[4])?;
+    write_file.write_all(&[3])?;
+    write_file.write_all(&[7, 3, 5])?;
+    write_file.flush()?;
+    let read_file = directory.open_read(test_path)?.read_bytes()?;
+    assert_eq!(read_file.as_slice(), &[4u8, 3u8, 7u8, 3u8, 5u8]);
+    mem::drop(read_file);
     assert!(directory.delete(test_path).is_ok());
     assert!(!directory.exists(test_path));
+    Ok(())
 }
 
-fn test_rewrite_forbidden(directory: &mut dyn Directory) {
+fn test_rewrite_forbidden(directory: &dyn Directory) -> crate::Result<()> {
     let test_path: &'static Path = Path::new("some_path_for_test");
-    {
-        directory.open_write(test_path).unwrap();
-        assert!(directory.exists(test_path));
-    }
-    {
-        assert!(directory.open_write(test_path).is_err());
-    }
+    directory.open_write(test_path)?;
+    assert!(directory.exists(test_path));
+    assert!(directory.open_write(test_path).is_err());
     assert!(directory.delete(test_path).is_ok());
+    Ok(())
 }
 
-fn test_write_create_the_file(directory: &mut dyn Directory) {
+fn test_write_create_the_file(directory: &dyn Directory) {
     let test_path: &'static Path = Path::new("some_path_for_test");
     {
         assert!(directory.open_read(test_path).is_err());
@@ -165,21 +163,20 @@ fn test_write_create_the_file(directory: &mut dyn Directory) {
     }
 }
 
-fn test_directory_delete(directory: &mut dyn Directory) {
+fn test_directory_delete(directory: &dyn Directory) -> crate::Result<()> {
     let test_path: &'static Path = Path::new("some_path_for_test");
     assert!(directory.open_read(test_path).is_err());
-    let mut write_file = directory.open_write(&test_path).unwrap();
-    write_file.write_all(&[1, 2, 3, 4]).unwrap();
-    write_file.flush().unwrap();
+    let mut write_file = directory.open_write(&test_path)?;
+    write_file.write_all(&[1, 2, 3, 4])?;
+    write_file.flush()?;
     {
-        let read_handle = directory.open_read(&test_path).unwrap();
-        assert_eq!(&*read_handle, &[1u8, 2u8, 3u8, 4u8]);
+        let read_handle = directory.open_read(&test_path)?.read_bytes()?;
+        assert_eq!(read_handle.as_slice(), &[1u8, 2u8, 3u8, 4u8]);
         // Mapped files can't be deleted on Windows
         if !cfg!(windows) {
             assert!(directory.delete(&test_path).is_ok());
-            assert_eq!(&*read_handle, &[1u8, 2u8, 3u8, 4u8]);
+            assert_eq!(read_handle.as_slice(), &[1u8, 2u8, 3u8, 4u8]);
         }
-
         assert!(directory.delete(Path::new("SomeOtherPath")).is_err());
     }
 
@@ -189,9 +186,10 @@ fn test_directory_delete(directory: &mut dyn Directory) {
 
     assert!(directory.open_read(&test_path).is_err());
     assert!(directory.delete(&test_path).is_err());
+    Ok(())
 }
 
-fn test_watch(directory: &mut dyn Directory) {
+fn test_watch(directory: &dyn Directory) {
     let num_progress: Arc<AtomicUsize> = Default::default();
     let counter: Arc<AtomicUsize> = Default::default();
     let counter_clone = counter.clone();
@@ -226,7 +224,7 @@ fn test_watch(directory: &mut dyn Directory) {
     assert!(10 <= counter.load(SeqCst));
 }
 
-fn test_lock_non_blocking(directory: &mut dyn Directory) {
+fn test_lock_non_blocking(directory: &dyn Directory) {
     {
         let lock_a_res = directory.acquire_lock(&Lock {
             filepath: PathBuf::from("a.lock"),
@@ -251,7 +249,7 @@ fn test_lock_non_blocking(directory: &mut dyn Directory) {
     assert!(lock_a_res.is_ok());
 }
 
-fn test_lock_blocking(directory: &mut dyn Directory) {
+fn test_lock_blocking(directory: &dyn Directory) {
     let lock_a_res = directory.acquire_lock(&Lock {
         filepath: PathBuf::from("a.lock"),
         is_blocking: true,

src/directory/watch_event_router.rs

@@ -29,6 +29,13 @@ impl WatchHandle {
     pub fn new(watch_callback: Arc<WatchCallback>) -> WatchHandle {
         WatchHandle(watch_callback)
     }
+
+    /// Returns an empty watch handle.
+    ///
+    /// This function is only useful when implementing a readonly directory.
+    pub fn empty() -> WatchHandle {
+        WatchHandle::new(Arc::new(Box::new(|| {})))
+    }
 }
 
 impl WatchCallbackList {

src/error.rs

@@ -2,21 +2,27 @@
 
 use std::io;
 
-use crate::directory::error::{IOError, OpenDirectoryError, OpenReadError, OpenWriteError};
 use crate::directory::error::{Incompatibility, LockError};
 use crate::fastfield::FastFieldNotAvailableError;
 use crate::query;
-use crate::schema;
+use crate::{
+    directory::error::{OpenDirectoryError, OpenReadError, OpenWriteError},
+    schema,
+};
 use std::fmt;
 use std::path::PathBuf;
 use std::sync::PoisonError;
 
+/// Represents a `DataCorruption` error.
+///
+/// When facing data corruption, tantivy  actually panic or return this error.
 pub struct DataCorruption {
     filepath: Option<PathBuf>,
     comment: String,
 }
 
 impl DataCorruption {
+    /// Creates a `DataCorruption` Error.
     pub fn new(filepath: PathBuf, comment: String) -> DataCorruption {
         DataCorruption {
             filepath: Some(filepath),
@@ -24,10 +30,11 @@ impl DataCorruption {
         }
     }
 
-    pub fn comment_only(comment: String) -> DataCorruption {
+    /// Creates a `DataCorruption` Error, when the filepath is irrelevant.
+    pub fn comment_only<TStr: ToString>(comment: TStr) -> DataCorruption {
         DataCorruption {
             filepath: None,
-            comment,
+            comment: comment.to_string(),
         }
     }
 }
@@ -43,44 +50,47 @@ impl fmt::Debug for DataCorruption {
     }
 }
 
-/// The library's failure based error enum
-#[derive(Debug, Fail)]
+/// The library's error enum
+#[derive(Debug, Error)]
 pub enum TantivyError {
-    /// Path does not exist.
-    #[fail(display = "Path does not exist: '{:?}'", _0)]
-    PathDoesNotExist(PathBuf),
-    /// File already exists, this is a problem when we try to write into a new file.
-    #[fail(display = "File already exists: '{:?}'", _0)]
-    FileAlreadyExists(PathBuf),
+    /// Failed to open the directory.
+    #[error("Failed to open the directory: '{0:?}'")]
+    OpenDirectoryError(#[from] OpenDirectoryError),
+    /// Failed to open a file for read.
+    #[error("Failed to open file for read: '{0:?}'")]
+    OpenReadError(#[from] OpenReadError),
+    /// Failed to open a file for write.
+    #[error("Failed to open file for write: '{0:?}'")]
+    OpenWriteError(#[from] OpenWriteError),
     /// Index already exists in this directory
-    #[fail(display = "Index already exists")]
+    #[error("Index already exists")]
     IndexAlreadyExists,
     /// Failed to acquire file lock
-    #[fail(display = "Failed to acquire Lockfile: {:?}. {:?}", _0, _1)]
+    #[error("Failed to acquire Lockfile: {0:?}. {1:?}")]
     LockFailure(LockError, Option<String>),
     /// IO Error.
-    #[fail(display = "An IO error occurred: '{}'", _0)]
-    IOError(#[cause] IOError),
+    #[error("An IO error occurred: '{0}'")]
+    IOError(#[from] io::Error),
     /// Data corruption.
-    #[fail(display = "{:?}", _0)]
+    #[error("Data corrupted: '{0:?}'")]
     DataCorruption(DataCorruption),
     /// A thread holding the locked panicked and poisoned the lock.
-    #[fail(display = "A thread holding the locked panicked and poisoned the lock")]
+    #[error("A thread holding the locked panicked and poisoned the lock")]
     Poisoned,
     /// Invalid argument was passed by the user.
-    #[fail(display = "An invalid argument was passed: '{}'", _0)]
+    #[error("An invalid argument was passed: '{0}'")]
     InvalidArgument(String),
     /// An Error happened in one of the thread.
-    #[fail(display = "An error occurred in a thread: '{}'", _0)]
+    #[error("An error occurred in a thread: '{0}'")]
     ErrorInThread(String),
     /// An Error appeared related to the schema.
-    #[fail(display = "Schema error: '{}'", _0)]
+    #[error("Schema error: '{0}'")]
     SchemaError(String),
     /// System error. (e.g.: We failed spawning a new thread)
-    #[fail(display = "System error.'{}'", _0)]
+    #[error("System error.'{0}'")]
     SystemError(String),
     /// Index incompatible with current version of tantivy
-    #[fail(display = "{:?}", _0)]
+    #[error("{0:?}")]
     IncompatibleIndex(Incompatibility),
 }
 
@@ -89,31 +99,17 @@ impl From<DataCorruption> for TantivyError {
         TantivyError::DataCorruption(data_corruption)
     }
 }
-
 impl From<FastFieldNotAvailableError> for TantivyError {
     fn from(fastfield_error: FastFieldNotAvailableError) -> TantivyError {
         TantivyError::SchemaError(format!("{}", fastfield_error))
     }
 }
-
 impl From<LockError> for TantivyError {
     fn from(lock_error: LockError) -> TantivyError {
         TantivyError::LockFailure(lock_error, None)
     }
 }
 
-impl From<IOError> for TantivyError {
-    fn from(io_error: IOError) -> TantivyError {
-        TantivyError::IOError(io_error)
-    }
-}
-
-impl From<io::Error> for TantivyError {
-    fn from(io_error: io::Error) -> TantivyError {
-        TantivyError::IOError(io_error.into())
-    }
-}
-
 impl From<query::QueryParserError> for TantivyError {
     fn from(parsing_error: query::QueryParserError) -> TantivyError {
         TantivyError::InvalidArgument(format!("Query is invalid. {:?}", parsing_error))
@@ -126,15 +122,9 @@ impl<Guard> From<PoisonError<Guard>> for TantivyError {
     }
 }
 
-impl From<OpenReadError> for TantivyError {
-    fn from(error: OpenReadError) -> TantivyError {
-        match error {
-            OpenReadError::FileDoesNotExist(filepath) => TantivyError::PathDoesNotExist(filepath),
-            OpenReadError::IOError(io_error) => TantivyError::IOError(io_error),
-            OpenReadError::IncompatibleIndex(incompatibility) => {
-                TantivyError::IncompatibleIndex(incompatibility)
-            }
-        }
+impl From<chrono::ParseError> for TantivyError {
+    fn from(err: chrono::ParseError) -> TantivyError {
+        TantivyError::InvalidArgument(err.to_string())
     }
 }
 
@@ -144,35 +134,9 @@ impl From<schema::DocParsingError> for TantivyError {
     }
 }
 
-impl From<OpenWriteError> for TantivyError {
-    fn from(error: OpenWriteError) -> TantivyError {
-        match error {
-            OpenWriteError::FileAlreadyExists(filepath) => {
-                TantivyError::FileAlreadyExists(filepath)
-            }
-            OpenWriteError::IOError(io_error) => TantivyError::IOError(io_error),
-        }
-    }
-}
-
-impl From<OpenDirectoryError> for TantivyError {
-    fn from(error: OpenDirectoryError) -> TantivyError {
-        match error {
-            OpenDirectoryError::DoesNotExist(directory_path) => {
-                TantivyError::PathDoesNotExist(directory_path)
-            }
-            OpenDirectoryError::NotADirectory(directory_path) => {
-                TantivyError::InvalidArgument(format!("{:?} is not a directory", directory_path))
-            }
-            OpenDirectoryError::IoError(err) => TantivyError::IOError(IOError::from(err)),
-        }
-    }
-}
-
 impl From<serde_json::Error> for TantivyError {
     fn from(error: serde_json::Error) -> TantivyError {
-        let io_err = io::Error::from(error);
-        TantivyError::IOError(io_err.into())
+        TantivyError::IOError(error.into())
     }
 }
 

src/fastfield/bytes/mod.rs

@@ -6,31 +6,114 @@ pub use self::writer::BytesFastFieldWriter;
 
 #[cfg(test)]
 mod tests {
-    use crate::schema::Schema;
-    use crate::Index;
+    use crate::schema::{BytesOptions, IndexRecordOption, Schema, Value};
+    use crate::{query::TermQuery, schema::FAST, schema::INDEXED, schema::STORED};
+    use crate::{DocAddress, DocSet, Index, Searcher, Term};
+    use std::ops::Deref;
 
     #[test]
-    fn test_bytes() {
+    fn test_bytes() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
-        let field = schema_builder.add_bytes_field("bytesfield");
+        let bytes_field = schema_builder.add_bytes_field("bytesfield", FAST);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_for_tests().unwrap();
-        index_writer.add_document(doc!(field=>vec![0u8, 1, 2, 3]));
-        index_writer.add_document(doc!(field=>vec![]));
-        index_writer.add_document(doc!(field=>vec![255u8]));
-        index_writer.add_document(doc!(field=>vec![1u8, 3, 5, 7, 9]));
-        index_writer.add_document(doc!(field=>vec![0u8; 1000]));
-        assert!(index_writer.commit().is_ok());
-        let searcher = index.reader().unwrap().searcher();
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(bytes_field=>vec![0u8, 1, 2, 3]));
+        index_writer.add_document(doc!(bytes_field=>vec![]));
+        index_writer.add_document(doc!(bytes_field=>vec![255u8]));
+        index_writer.add_document(doc!(bytes_field=>vec![1u8, 3, 5, 7, 9]));
+        index_writer.add_document(doc!(bytes_field=>vec![0u8; 1000]));
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
         let segment_reader = searcher.segment_reader(0);
-        let bytes_reader = segment_reader.fast_fields().bytes(field).unwrap();
-
+        let bytes_reader = segment_reader.fast_fields().bytes(bytes_field).unwrap();
         assert_eq!(bytes_reader.get_bytes(0), &[0u8, 1, 2, 3]);
         assert!(bytes_reader.get_bytes(1).is_empty());
         assert_eq!(bytes_reader.get_bytes(2), &[255u8]);
         assert_eq!(bytes_reader.get_bytes(3), &[1u8, 3, 5, 7, 9]);
         let long = vec![0u8; 1000];
         assert_eq!(bytes_reader.get_bytes(4), long.as_slice());
+        Ok(())
+    }
+
+    fn create_index_for_test<T: Into<BytesOptions>>(
+        byte_options: T,
+    ) -> crate::Result<impl Deref<Target = Searcher>> {
+        let mut schema_builder = Schema::builder();
+        let field = schema_builder.add_bytes_field("string_bytes", byte_options.into());
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(
+                field => b"tantivy".as_ref(),
+                field => b"lucene".as_ref()
+        ));
+        index_writer.commit()?;
+        Ok(index.reader()?.searcher())
+    }
+
+    #[test]
+    fn test_stored_bytes() -> crate::Result<()> {
+        let searcher = create_index_for_test(STORED)?;
+        assert_eq!(searcher.num_docs(), 1);
+        let retrieved_doc = searcher.doc(DocAddress(0u32, 0u32))?;
+        let field = searcher.schema().get_field("string_bytes").unwrap();
+        let values: Vec<&Value> = retrieved_doc.get_all(field).collect();
+        assert_eq!(values.len(), 2);
+        let values_bytes: Vec<&[u8]> = values
+            .into_iter()
+            .flat_map(|value| value.bytes_value())
+            .collect();
+        assert_eq!(values_bytes, &[&b"tantivy"[..], &b"lucene"[..]]);
+        Ok(())
+    }
+
+    #[test]
+    fn test_non_stored_bytes() -> crate::Result<()> {
+        let searcher = create_index_for_test(INDEXED)?;
+        assert_eq!(searcher.num_docs(), 1);
+        let retrieved_doc = searcher.doc(DocAddress(0u32, 0u32))?;
+        let field = searcher.schema().get_field("string_bytes").unwrap();
+        assert!(retrieved_doc.get_first(field).is_none());
+        Ok(())
+    }
+
+    #[test]
+    fn test_index_bytes() -> crate::Result<()> {
+        let searcher = create_index_for_test(INDEXED)?;
+        assert_eq!(searcher.num_docs(), 1);
+        let field = searcher.schema().get_field("string_bytes").unwrap();
+        let term = Term::from_field_bytes(field, b"lucene".as_ref());
+        let term_query = TermQuery::new(term, IndexRecordOption::Basic);
+        let term_weight = term_query.specialized_weight(&searcher, true)?;
+        let term_scorer = term_weight.specialized_scorer(searcher.segment_reader(0), 1.0f32)?;
+        assert_eq!(term_scorer.doc(), 0u32);
+        Ok(())
+    }
+
+    #[test]
+    fn test_non_index_bytes() -> crate::Result<()> {
+        let searcher = create_index_for_test(STORED)?;
+        assert_eq!(searcher.num_docs(), 1);
+        let field = searcher.schema().get_field("string_bytes").unwrap();
+        let term = Term::from_field_bytes(field, b"lucene".as_ref());
+        let term_query = TermQuery::new(term, IndexRecordOption::Basic);
+        let term_weight_res = term_query.specialized_weight(&searcher, false);
+        assert!(matches!(
+            term_weight_res,
+            Err(crate::TantivyError::SchemaError(_))
+        ));
+        Ok(())
+    }
+
+    #[test]
+    fn test_fast_bytes_multivalue_value() -> crate::Result<()> {
+        let searcher = create_index_for_test(FAST)?;
+        assert_eq!(searcher.num_docs(), 1);
+        let fast_fields = searcher.segment_reader(0u32).fast_fields();
+        let field = searcher.schema().get_field("string_bytes").unwrap();
+        let fast_field_reader = fast_fields.bytes(field).unwrap();
+        assert_eq!(fast_field_reader.get_bytes(0u32), b"tantivy");
+        Ok(())
     }
 }

src/fastfield/bytes/reader.rs

@@ -1,6 +1,5 @@
-use owning_ref::OwningRef;
-
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
+use crate::directory::OwnedBytes;
 use crate::fastfield::FastFieldReader;
 use crate::DocId;
 
@@ -17,16 +16,16 @@ use crate::DocId;
 #[derive(Clone)]
 pub struct BytesFastFieldReader {
     idx_reader: FastFieldReader<u64>,
-    values: OwningRef<ReadOnlySource, [u8]>,
+    values: OwnedBytes,
 }
 
 impl BytesFastFieldReader {
     pub(crate) fn open(
         idx_reader: FastFieldReader<u64>,
-        values_source: ReadOnlySource,
-    ) -> BytesFastFieldReader {
-        let values = OwningRef::new(values_source).map(|source| &source[..]);
-        BytesFastFieldReader { idx_reader, values }
+        values_file: FileSlice,
+    ) -> crate::Result<BytesFastFieldReader> {
+        let values = values_file.read_bytes()?;
+        Ok(BytesFastFieldReader { idx_reader, values })
     }
 
     fn range(&self, doc: DocId) -> (usize, usize) {
@@ -38,7 +37,7 @@ impl BytesFastFieldReader {
     /// Returns the bytes associated to the given `doc`
     pub fn get_bytes(&self, doc: DocId) -> &[u8] {
         let (start, stop) = self.range(doc);
-        &self.values[start..stop]
+        &self.values.as_slice()[start..stop]
     }
 
     /// Returns the overall number of bytes in this bytes fast field.

src/fastfield/bytes/writer.rs

@@ -49,16 +49,10 @@ impl BytesFastFieldWriter {
     /// matching field values present in the document.
     pub fn add_document(&mut self, doc: &Document) {
         self.next_doc();
-        for field_value in doc.field_values() {
-            if field_value.field() == self.field {
-                if let Value::Bytes(ref bytes) = *field_value.value() {
-                    self.vals.extend_from_slice(bytes);
-                } else {
-                    panic!(
-                        "Bytes field contained non-Bytes Value!. Field {:?} = {:?}",
-                        self.field, field_value
-                    );
-                }
+        for field_value in doc.get_all(self.field) {
+            if let Value::Bytes(ref bytes) = field_value {
+                self.vals.extend_from_slice(bytes);
+                return;
             }
         }
     }
@@ -76,21 +70,18 @@ impl BytesFastFieldWriter {
 
     /// Serializes the fast field values by pushing them to the `FastFieldSerializer`.
     pub fn serialize(&self, serializer: &mut FastFieldSerializer) -> io::Result<()> {
-        {
-            // writing the offset index
-            let mut doc_index_serializer =
-                serializer.new_u64_fast_field_with_idx(self.field, 0, self.vals.len() as u64, 0)?;
-            for &offset in &self.doc_index {
-                doc_index_serializer.add_val(offset)?;
-            }
-            doc_index_serializer.add_val(self.vals.len() as u64)?;
-            doc_index_serializer.close_field()?;
-        }
-        {
-            // writing the values themselves
-            let mut value_serializer = serializer.new_bytes_fast_field_with_idx(self.field, 1)?;
-            value_serializer.write_all(&self.vals)?;
+        // writing the offset index
+        let mut doc_index_serializer =
+            serializer.new_u64_fast_field_with_idx(self.field, 0, self.vals.len() as u64, 0)?;
+        for &offset in &self.doc_index {
+            doc_index_serializer.add_val(offset)?;
         }
+        doc_index_serializer.add_val(self.vals.len() as u64)?;
+        doc_index_serializer.close_field()?;
+        // writing the values themselves
+        serializer
+            .new_bytes_fast_field_with_idx(self.field, 1)?
+            .write_all(&self.vals)?;
         Ok(())
     }
 }

src/fastfield/delete.rs

@@ -1,5 +1,6 @@
 use crate::common::{BitSet, HasLen};
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
+use crate::directory::OwnedBytes;
 use crate::directory::WritePtr;
 use crate::space_usage::ByteCount;
 use crate::DocId;
@@ -39,7 +40,7 @@ pub fn write_delete_bitset(
 /// Set of deleted `DocId`s.
 #[derive(Clone)]
 pub struct DeleteBitSet {
-    data: ReadOnlySource,
+    data: OwnedBytes,
     len: usize,
 }
 
@@ -53,26 +54,27 @@ impl DeleteBitSet {
         for &doc in docs {
             bitset.insert(doc);
         }
-        let mut directory = RAMDirectory::create();
+        let directory = RAMDirectory::create();
         let path = Path::new("dummydeletebitset");
         let mut wrt = directory.open_write(path).unwrap();
         write_delete_bitset(&bitset, max_doc, &mut wrt).unwrap();
         wrt.terminate().unwrap();
-        let source = directory.open_read(path).unwrap();
-        Self::open(source)
+        let file = directory.open_read(path).unwrap();
+        Self::open(file).unwrap()
     }
 
-    /// Opens a delete bitset given its data source.
-    pub fn open(data: ReadOnlySource) -> DeleteBitSet {
-        let num_deleted: usize = data
+    /// Opens a delete bitset given its file.
+    pub fn open(file: FileSlice) -> crate::Result<DeleteBitSet> {
+        let bytes = file.read_bytes()?;
+        let num_deleted: usize = bytes
             .as_slice()
             .iter()
             .map(|b| b.count_ones() as usize)
             .sum();
-        DeleteBitSet {
-            data,
+        Ok(DeleteBitSet {
+            data: bytes,
             len: num_deleted,
-        }
+        })
     }
 
     /// Returns true iff the document is still "alive". In other words, if it has not been deleted.
@@ -84,7 +86,7 @@ impl DeleteBitSet {
     #[inline(always)]
     pub fn is_deleted(&self, doc: DocId) -> bool {
         let byte_offset = doc / 8u32;
-        let b: u8 = (*self.data)[byte_offset as usize];
+        let b: u8 = self.data.as_slice()[byte_offset as usize];
         let shift = (doc & 7u32) as u8;
         b & (1u8 << shift) != 0
     }

src/fastfield/error.rs

@@ -4,8 +4,8 @@ use std::result;
 /// `FastFieldNotAvailableError` is returned when the
 /// user requested for a fast field reader, and the field was not
 /// defined in the schema as a fast field.
-#[derive(Debug, Fail)]
-#[fail(display = "Fast field not available: '{:?}'", field_name)]
+#[derive(Debug, Error)]
+#[error("Fast field not available: '{field_name:?}'")]
 pub struct FastFieldNotAvailableError {
     field_name: String,
 }

src/fastfield/facet_reader.rs

@@ -73,7 +73,61 @@ 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::Index;
+    use crate::{
+        schema::{Facet, SchemaBuilder},
+        Document,
+    };
+
+    #[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_for_tests()?;
+        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_for_tests()?;
+        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/mod.rs

@@ -33,11 +33,14 @@ pub use self::reader::FastFieldReader;
 pub use self::readers::FastFieldReaders;
 pub use self::serializer::FastFieldSerializer;
 pub use self::writer::{FastFieldsWriter, IntFastFieldWriter};
-use crate::chrono::{NaiveDateTime, Utc};
 use crate::common;
 use crate::schema::Cardinality;
 use crate::schema::FieldType;
 use crate::schema::Value;
+use crate::{
+    chrono::{NaiveDateTime, Utc},
+    schema::Type,
+};
 
 mod bytes;
 mod delete;
@@ -76,6 +79,9 @@ pub trait FastValue: Clone + Copy + Send + Sync + PartialOrd {
     fn make_zero() -> Self {
         Self::from_u64(0i64.to_u64())
     }
+
+    /// Returns the `schema::Type` for this FastValue.
+    fn to_type() -> Type;
 }
 
 impl FastValue for u64 {
@@ -98,6 +104,10 @@ impl FastValue for u64 {
     fn as_u64(&self) -> u64 {
         *self
     }
+
+    fn to_type() -> Type {
+        Type::U64
+    }
 }
 
 impl FastValue for i64 {
@@ -119,6 +129,10 @@ impl FastValue for i64 {
     fn as_u64(&self) -> u64 {
         *self as u64
     }
+
+    fn to_type() -> Type {
+        Type::I64
+    }
 }
 
 impl FastValue for f64 {
@@ -140,6 +154,10 @@ impl FastValue for f64 {
     fn as_u64(&self) -> u64 {
         self.to_bits()
     }
+
+    fn to_type() -> Type {
+        Type::F64
+    }
 }
 
 impl FastValue for crate::DateTime {
@@ -162,6 +180,10 @@ impl FastValue for crate::DateTime {
     fn as_u64(&self) -> u64 {
         self.timestamp().as_u64()
     }
+
+    fn to_type() -> Type {
+        Type::Date
+    }
 }
 
 fn value_to_u64(value: &Value) -> u64 {
@@ -187,6 +209,7 @@ mod tests {
     use crate::schema::FAST;
     use crate::schema::{Document, IntOptions};
     use crate::{Index, SegmentId, SegmentReader};
+    use common::HasLen;
     use once_cell::sync::Lazy;
     use rand::prelude::SliceRandom;
     use rand::rngs::StdRng;
@@ -217,9 +240,9 @@ mod tests {
     }
 
     #[test]
-    fn test_intfastfield_small() {
+    fn test_intfastfield_small() -> crate::Result<()> {
         let path = Path::new("test");
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
         {
             let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
             let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -232,27 +255,24 @@ mod tests {
                 .unwrap();
             serializer.close().unwrap();
         }
-        let source = directory.open_read(&path).unwrap();
-        {
-            assert_eq!(source.len(), 36 as usize);
-        }
-        {
-            let composite_file = CompositeFile::open(&source).unwrap();
-            let field_source = composite_file.open_read(*FIELD).unwrap();
-            let fast_field_reader = FastFieldReader::<u64>::open(field_source);
-            assert_eq!(fast_field_reader.get(0), 13u64);
-            assert_eq!(fast_field_reader.get(1), 14u64);
-            assert_eq!(fast_field_reader.get(2), 2u64);
-        }
+        let file = directory.open_read(&path).unwrap();
+        assert_eq!(file.len(), 36 as usize);
+        let composite_file = CompositeFile::open(&file)?;
+        let file = composite_file.open_read(*FIELD).unwrap();
+        let fast_field_reader = FastFieldReader::<u64>::open(file)?;
+        assert_eq!(fast_field_reader.get(0), 13u64);
+        assert_eq!(fast_field_reader.get(1), 14u64);
+        assert_eq!(fast_field_reader.get(2), 2u64);
+        Ok(())
     }
 
     #[test]
-    fn test_intfastfield_large() {
+    fn test_intfastfield_large() -> crate::Result<()> {
         let path = Path::new("test");
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
         {
-            let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
-            let mut serializer = FastFieldSerializer::from_write(write).unwrap();
+            let write: WritePtr = directory.open_write(Path::new("test"))?;
+            let mut serializer = FastFieldSerializer::from_write(write)?;
             let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
             fast_field_writers.add_document(&doc!(*FIELD=>4u64));
             fast_field_writers.add_document(&doc!(*FIELD=>14_082_001u64));
@@ -263,19 +283,15 @@ mod tests {
             fast_field_writers.add_document(&doc!(*FIELD=>1_002u64));
             fast_field_writers.add_document(&doc!(*FIELD=>1_501u64));
             fast_field_writers.add_document(&doc!(*FIELD=>215u64));
-            fast_field_writers
-                .serialize(&mut serializer, &HashMap::new())
-                .unwrap();
-            serializer.close().unwrap();
+            fast_field_writers.serialize(&mut serializer, &HashMap::new())?;
+            serializer.close()?;
         }
-        let source = directory.open_read(&path).unwrap();
+        let file = directory.open_read(&path)?;
+        assert_eq!(file.len(), 61 as usize);
         {
-            assert_eq!(source.len(), 61 as usize);
-        }
-        {
-            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let fast_fields_composite = CompositeFile::open(&file)?;
             let data = fast_fields_composite.open_read(*FIELD).unwrap();
-            let fast_field_reader = FastFieldReader::<u64>::open(data);
+            let fast_field_reader = FastFieldReader::<u64>::open(data)?;
             assert_eq!(fast_field_reader.get(0), 4u64);
             assert_eq!(fast_field_reader.get(1), 14_082_001u64);
             assert_eq!(fast_field_reader.get(2), 3_052u64);
@@ -286,12 +302,13 @@ mod tests {
             assert_eq!(fast_field_reader.get(7), 1_501u64);
             assert_eq!(fast_field_reader.get(8), 215u64);
         }
+        Ok(())
     }
 
     #[test]
-    fn test_intfastfield_null_amplitude() {
+    fn test_intfastfield_null_amplitude() -> crate::Result<()> {
         let path = Path::new("test");
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
 
         {
             let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
@@ -305,24 +322,23 @@ mod tests {
                 .unwrap();
             serializer.close().unwrap();
         }
-        let source = directory.open_read(&path).unwrap();
+        let file = directory.open_read(&path).unwrap();
+        assert_eq!(file.len(), 34 as usize);
         {
-            assert_eq!(source.len(), 34 as usize);
-        }
-        {
-            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let fast_fields_composite = CompositeFile::open(&file).unwrap();
             let data = fast_fields_composite.open_read(*FIELD).unwrap();
-            let fast_field_reader = FastFieldReader::<u64>::open(data);
+            let fast_field_reader = FastFieldReader::<u64>::open(data)?;
             for doc in 0..10_000 {
                 assert_eq!(fast_field_reader.get(doc), 100_000u64);
             }
         }
+        Ok(())
     }
 
     #[test]
-    fn test_intfastfield_large_numbers() {
+    fn test_intfastfield_large_numbers() -> crate::Result<()> {
         let path = Path::new("test");
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
 
         {
             let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
@@ -338,14 +354,12 @@ mod tests {
                 .unwrap();
             serializer.close().unwrap();
         }
-        let source = directory.open_read(&path).unwrap();
+        let file = directory.open_read(&path).unwrap();
+        assert_eq!(file.len(), 80042 as usize);
         {
-            assert_eq!(source.len(), 80042 as usize);
-        }
-        {
-            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let fast_fields_composite = CompositeFile::open(&file)?;
             let data = fast_fields_composite.open_read(*FIELD).unwrap();
-            let fast_field_reader = FastFieldReader::<u64>::open(data);
+            let fast_field_reader = FastFieldReader::<u64>::open(data)?;
             assert_eq!(fast_field_reader.get(0), 0u64);
             for doc in 1..10_001 {
                 assert_eq!(
@@ -354,12 +368,13 @@ mod tests {
                 );
             }
         }
+        Ok(())
     }
 
     #[test]
-    fn test_signed_intfastfield() {
+    fn test_signed_intfastfield() -> crate::Result<()> {
         let path = Path::new("test");
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
         let mut schema_builder = Schema::builder();
 
         let i64_field = schema_builder.add_i64_field("field", FAST);
@@ -378,14 +393,12 @@ mod tests {
                 .unwrap();
             serializer.close().unwrap();
         }
-        let source = directory.open_read(&path).unwrap();
+        let file = directory.open_read(&path).unwrap();
+        assert_eq!(file.len(), 17709 as usize);
         {
-            assert_eq!(source.len(), 17709 as usize);
-        }
-        {
-            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let fast_fields_composite = CompositeFile::open(&file)?;
             let data = fast_fields_composite.open_read(i64_field).unwrap();
-            let fast_field_reader = FastFieldReader::<i64>::open(data);
+            let fast_field_reader = FastFieldReader::<i64>::open(data)?;
 
             assert_eq!(fast_field_reader.min_value(), -100i64);
             assert_eq!(fast_field_reader.max_value(), 9_999i64);
@@ -398,12 +411,13 @@ mod tests {
                 assert_eq!(buffer[i], -100i64 + 53i64 + i as i64);
             }
         }
+        Ok(())
     }
 
     #[test]
-    fn test_signed_intfastfield_default_val() {
+    fn test_signed_intfastfield_default_val() -> crate::Result<()> {
         let path = Path::new("test");
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
         let mut schema_builder = Schema::builder();
         let i64_field = schema_builder.add_i64_field("field", FAST);
         let schema = schema_builder.build();
@@ -420,13 +434,14 @@ mod tests {
             serializer.close().unwrap();
         }
 
-        let source = directory.open_read(&path).unwrap();
+        let file = directory.open_read(&path).unwrap();
         {
-            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let fast_fields_composite = CompositeFile::open(&file).unwrap();
             let data = fast_fields_composite.open_read(i64_field).unwrap();
-            let fast_field_reader = FastFieldReader::<i64>::open(data);
+            let fast_field_reader = FastFieldReader::<i64>::open(data)?;
             assert_eq!(fast_field_reader.get(0u32), 0i64);
         }
+        Ok(())
     }
 
     // Warning: this generates the same permutation at each call
@@ -437,28 +452,26 @@ mod tests {
     }
 
     #[test]
-    fn test_intfastfield_permutation() {
+    fn test_intfastfield_permutation() -> crate::Result<()> {
         let path = Path::new("test");
         let permutation = generate_permutation();
         let n = permutation.len();
-        let mut directory = RAMDirectory::create();
+        let directory = RAMDirectory::create();
         {
-            let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
-            let mut serializer = FastFieldSerializer::from_write(write).unwrap();
+            let write: WritePtr = directory.open_write(Path::new("test"))?;
+            let mut serializer = FastFieldSerializer::from_write(write)?;
             let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
             for &x in &permutation {
                 fast_field_writers.add_document(&doc!(*FIELD=>x));
             }
-            fast_field_writers
-                .serialize(&mut serializer, &HashMap::new())
-                .unwrap();
-            serializer.close().unwrap();
+            fast_field_writers.serialize(&mut serializer, &HashMap::new())?;
+            serializer.close()?;
         }
-        let source = directory.open_read(&path).unwrap();
+        let file = directory.open_read(&path)?;
         {
-            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let fast_fields_composite = CompositeFile::open(&file)?;
             let data = fast_fields_composite.open_read(*FIELD).unwrap();
-            let fast_field_reader = FastFieldReader::<u64>::open(data);
+            let fast_field_reader = FastFieldReader::<u64>::open(data)?;
 
             let mut a = 0u64;
             for _ in 0..n {
@@ -466,6 +479,7 @@ mod tests {
                 a = fast_field_reader.get(a as u32);
             }
         }
+        Ok(())
     }
 
     #[test]
@@ -598,7 +612,7 @@ mod bench {
     fn bench_intfastfield_linear_fflookup(b: &mut Bencher) {
         let path = Path::new("test");
         let permutation = generate_permutation();
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
         {
             let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
             let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -611,9 +625,9 @@ mod bench {
                 .unwrap();
             serializer.close().unwrap();
         }
-        let source = directory.open_read(&path).unwrap();
+        let file = directory.open_read(&path).unwrap();
         {
-            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let fast_fields_composite = CompositeFile::open(&file).unwrap();
             let data = fast_fields_composite.open_read(*FIELD).unwrap();
             let fast_field_reader = FastFieldReader::<u64>::open(data);
 
@@ -632,7 +646,7 @@ mod bench {
     fn bench_intfastfield_fflookup(b: &mut Bencher) {
         let path = Path::new("test");
         let permutation = generate_permutation();
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
         {
             let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
             let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -645,9 +659,9 @@ mod bench {
                 .unwrap();
             serializer.close().unwrap();
         }
-        let source = directory.open_read(&path).unwrap();
+        let file = directory.open_read(&path).unwrap();
         {
-            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let fast_fields_composite = CompositeFile::open(&file).unwrap();
             let data = fast_fields_composite.open_read(*FIELD).unwrap();
             let fast_field_reader = FastFieldReader::<u64>::open(data);
 

src/fastfield/multivalued/mod.rs

@@ -100,6 +100,7 @@ mod tests {
                         .get_first(date_field)
                         .expect("cannot find value")
                         .date_value()
+                        .unwrap()
                         .timestamp(),
                     first_time_stamp.timestamp()
                 );
@@ -108,7 +109,7 @@ mod tests {
                         .get_first(time_i)
                         .expect("cannot find value")
                         .i64_value(),
-                    1i64
+                    Some(1i64)
                 );
             }
         }
@@ -131,6 +132,7 @@ mod tests {
                         .get_first(date_field)
                         .expect("cannot find value")
                         .date_value()
+                        .unwrap()
                         .timestamp(),
                     two_secs_ahead.timestamp()
                 );
@@ -139,7 +141,7 @@ mod tests {
                         .get_first(time_i)
                         .expect("cannot find value")
                         .i64_value(),
-                    3i64
+                    Some(3i64)
                 );
             }
         }
@@ -197,22 +199,14 @@ mod tests {
         let segment_reader = searcher.segment_reader(0);
         let mut vals = Vec::new();
         let multi_value_reader = segment_reader.fast_fields().i64s(field).unwrap();
-        {
-            multi_value_reader.get_vals(2, &mut vals);
-            assert_eq!(&vals, &[-4i64]);
-        }
-        {
-            multi_value_reader.get_vals(0, &mut vals);
-            assert_eq!(&vals, &[1i64, 3i64]);
-        }
-        {
-            multi_value_reader.get_vals(1, &mut vals);
-            assert!(vals.is_empty());
-        }
-        {
-            multi_value_reader.get_vals(3, &mut vals);
-            assert_eq!(&vals, &[-5i64, -20i64, 1i64]);
-        }
+        multi_value_reader.get_vals(2, &mut vals);
+        assert_eq!(&vals, &[-4i64]);
+        multi_value_reader.get_vals(0, &mut vals);
+        assert_eq!(&vals, &[1i64, 3i64]);
+        multi_value_reader.get_vals(1, &mut vals);
+        assert!(vals.is_empty());
+        multi_value_reader.get_vals(3, &mut vals);
+        assert_eq!(&vals, &[-5i64, -20i64, 1i64]);
     }
     #[test]
     #[ignore]

src/fastfield/multivalued/writer.rs

@@ -143,7 +143,7 @@ impl MultiValueIntFastFieldWriter {
                             .iter()
                             .map(|val| *mapping.get(val).expect("Missing term ordinal"));
                         doc_vals.extend(remapped_vals);
-                        doc_vals.sort();
+                        doc_vals.sort_unstable();
                         for &val in &doc_vals {
                             value_serializer.add_val(val)?;
                         }

src/fastfield/reader.rs

@@ -3,13 +3,12 @@ use crate::common::bitpacker::BitUnpacker;
 use crate::common::compute_num_bits;
 use crate::common::BinarySerializable;
 use crate::common::CompositeFile;
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
 use crate::directory::{Directory, RAMDirectory, WritePtr};
 use crate::fastfield::{FastFieldSerializer, FastFieldsWriter};
 use crate::schema::Schema;
 use crate::schema::FAST;
 use crate::DocId;
-use owning_ref::OwningRef;
 use std::collections::HashMap;
 use std::marker::PhantomData;
 use std::path::Path;
@@ -20,34 +19,27 @@ use std::path::Path;
 /// fast field is required.
 #[derive(Clone)]
 pub struct FastFieldReader<Item: FastValue> {
-    bit_unpacker: BitUnpacker<OwningRef<ReadOnlySource, [u8]>>,
+    bit_unpacker: BitUnpacker,
     min_value_u64: u64,
     max_value_u64: u64,
     _phantom: PhantomData<Item>,
 }
 
 impl<Item: FastValue> FastFieldReader<Item> {
-    /// Opens a fast field given a source.
-    pub fn open(data: ReadOnlySource) -> Self {
-        let min_value: u64;
-        let amplitude: u64;
-        {
-            let mut cursor = data.as_slice();
-            min_value =
-                u64::deserialize(&mut cursor).expect("Failed to read the min_value of fast field.");
-            amplitude =
-                u64::deserialize(&mut cursor).expect("Failed to read the amplitude of fast field.");
-        }
+    /// Opens a fast field given a file.
+    pub fn open(file: FileSlice) -> crate::Result<Self> {
+        let mut bytes = file.read_bytes()?;
+        let min_value = u64::deserialize(&mut bytes)?;
+        let amplitude = u64::deserialize(&mut bytes)?;
         let max_value = min_value + amplitude;
         let num_bits = compute_num_bits(amplitude);
-        let owning_ref = OwningRef::new(data).map(|data| &data[16..]);
-        let bit_unpacker = BitUnpacker::new(owning_ref, num_bits);
-        FastFieldReader {
+        let bit_unpacker = BitUnpacker::new(bytes, num_bits);
+        Ok(FastFieldReader {
             min_value_u64: min_value,
             max_value_u64: max_value,
             bit_unpacker,
             _phantom: PhantomData,
-        }
+        })
     }
 
     pub(crate) fn into_u64_reader(self) -> FastFieldReader<u64> {
@@ -135,7 +127,7 @@ impl<Item: FastValue> From<Vec<Item>> for FastFieldReader<Item> {
         let field = schema_builder.add_u64_field("field", FAST);
         let schema = schema_builder.build();
         let path = Path::new("__dummy__");
-        let mut directory: RAMDirectory = RAMDirectory::create();
+        let directory: RAMDirectory = RAMDirectory::create();
         {
             let write: WritePtr = directory
                 .open_write(path)
@@ -157,12 +149,11 @@ impl<Item: FastValue> From<Vec<Item>> for FastFieldReader<Item> {
             serializer.close().unwrap();
         }
 
-        let source = directory.open_read(path).expect("Failed to open the file");
-        let composite_file =
-            CompositeFile::open(&source).expect("Failed to read the composite file");
-        let field_source = composite_file
+        let file = directory.open_read(path).expect("Failed to open the file");
+        let composite_file = CompositeFile::open(&file).expect("Failed to read the composite file");
+        let field_file = composite_file
             .open_read(field)
             .expect("File component not found");
-        FastFieldReader::open(field_source)
+        FastFieldReader::open(field_file).unwrap()
     }
 }

src/fastfield/readers.rs

@@ -68,45 +68,52 @@ impl FastFieldReaders {
         };
         for (field, field_entry) in schema.fields() {
             let field_type = field_entry.field_type();
-            if field_type == &FieldType::Bytes {
-                let idx_reader = fast_fields_composite
+            if let FieldType::Bytes(bytes_option) = field_type {
+                if !bytes_option.is_fast() {
+                    continue;
+                }
+                let fast_field_idx_file = fast_fields_composite
                     .open_read_with_idx(field, 0)
-                    .ok_or_else(|| FastFieldNotAvailableError::new(field_entry))
-                    .map(FastFieldReader::open)?;
+                    .ok_or_else(|| FastFieldNotAvailableError::new(field_entry))?;
+                let idx_reader = FastFieldReader::open(fast_field_idx_file)?;
                 let data = fast_fields_composite
                     .open_read_with_idx(field, 1)
                     .ok_or_else(|| FastFieldNotAvailableError::new(field_entry))?;
+                let bytes_fast_field_reader = BytesFastFieldReader::open(idx_reader, data)?;
                 fast_field_readers
                     .fast_bytes
-                    .insert(field, BytesFastFieldReader::open(idx_reader, data));
+                    .insert(field, bytes_fast_field_reader);
             } else if let Some((fast_type, cardinality)) = type_and_cardinality(field_type) {
                 match cardinality {
                     Cardinality::SingleValue => {
                         if let Some(fast_field_data) = fast_fields_composite.open_read(field) {
                             match fast_type {
                                 FastType::U64 => {
-                                    let fast_field_reader = FastFieldReader::open(fast_field_data);
+                                    let fast_field_reader = FastFieldReader::open(fast_field_data)?;
                                     fast_field_readers
                                         .fast_field_u64
                                         .insert(field, fast_field_reader);
                                 }
                                 FastType::I64 => {
-                                    fast_field_readers.fast_field_i64.insert(
-                                        field,
-                                        FastFieldReader::open(fast_field_data.clone()),
-                                    );
+                                    let fast_field_reader =
+                                        FastFieldReader::open(fast_field_data.clone())?;
+                                    fast_field_readers
+                                        .fast_field_i64
+                                        .insert(field, fast_field_reader);
                                 }
                                 FastType::F64 => {
-                                    fast_field_readers.fast_field_f64.insert(
-                                        field,
-                                        FastFieldReader::open(fast_field_data.clone()),
-                                    );
+                                    let fast_field_reader =
+                                        FastFieldReader::open(fast_field_data.clone())?;
+                                    fast_field_readers
+                                        .fast_field_f64
+                                        .insert(field, fast_field_reader);
                                 }
                                 FastType::Date => {
-                                    fast_field_readers.fast_field_date.insert(
-                                        field,
-                                        FastFieldReader::open(fast_field_data.clone()),
-                                    );
+                                    let fast_field_reader =
+                                        FastFieldReader::open(fast_field_data.clone())?;
+                                    fast_field_readers
+                                        .fast_field_date
+                                        .insert(field, fast_field_reader);
                                 }
                             }
                         } else {
@@ -117,10 +124,10 @@ impl FastFieldReaders {
                         let idx_opt = fast_fields_composite.open_read_with_idx(field, 0);
                         let data_opt = fast_fields_composite.open_read_with_idx(field, 1);
                         if let (Some(fast_field_idx), Some(fast_field_data)) = (idx_opt, data_opt) {
-                            let idx_reader = FastFieldReader::open(fast_field_idx);
+                            let idx_reader = FastFieldReader::open(fast_field_idx)?;
                             match fast_type {
                                 FastType::I64 => {
-                                    let vals_reader = FastFieldReader::open(fast_field_data);
+                                    let vals_reader = FastFieldReader::open(fast_field_data)?;
                                     let multivalued_int_fast_field =
                                         MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
                                     fast_field_readers
@@ -128,7 +135,7 @@ impl FastFieldReaders {
                                         .insert(field, multivalued_int_fast_field);
                                 }
                                 FastType::U64 => {
-                                    let vals_reader = FastFieldReader::open(fast_field_data);
+                                    let vals_reader = FastFieldReader::open(fast_field_data)?;
                                     let multivalued_int_fast_field =
                                         MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
                                     fast_field_readers
@@ -136,7 +143,7 @@ impl FastFieldReaders {
                                         .insert(field, multivalued_int_fast_field);
                                 }
                                 FastType::F64 => {
-                                    let vals_reader = FastFieldReader::open(fast_field_data);
+                                    let vals_reader = FastFieldReader::open(fast_field_data)?;
                                     let multivalued_int_fast_field =
                                         MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
                                     fast_field_readers
@@ -144,7 +151,7 @@ impl FastFieldReaders {
                                         .insert(field, multivalued_int_fast_field);
                                 }
                                 FastType::Date => {
-                                    let vals_reader = FastFieldReader::open(fast_field_data);
+                                    let vals_reader = FastFieldReader::open(fast_field_data)?;
                                     let multivalued_int_fast_field =
                                         MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
                                     fast_field_readers

src/fastfield/writer.rs

@@ -33,7 +33,7 @@ impl FastFieldsWriter {
         let mut bytes_value_writers = Vec::new();
 
         for (field, field_entry) in schema.fields() {
-            match *field_entry.field_type() {
+            match field_entry.field_type() {
                 FieldType::I64(ref int_options)
                 | FieldType::U64(ref int_options)
                 | FieldType::F64(ref int_options)
@@ -56,9 +56,11 @@ impl FastFieldsWriter {
                     let fast_field_writer = MultiValueIntFastFieldWriter::new(field, true);
                     multi_values_writers.push(fast_field_writer);
                 }
-                FieldType::Bytes => {
-                    let fast_field_writer = BytesFastFieldWriter::new(field);
-                    bytes_value_writers.push(fast_field_writer);
+                FieldType::Bytes(bytes_option) => {
+                    if bytes_option.is_fast() {
+                        let fast_field_writer = BytesFastFieldWriter::new(field);
+                        bytes_value_writers.push(fast_field_writer);
+                    }
                 }
                 _ => {}
             }
@@ -126,6 +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/fieldnorm/reader.rs

@@ -1,6 +1,7 @@
 use super::{fieldnorm_to_id, id_to_fieldnorm};
 use crate::common::CompositeFile;
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
+use crate::directory::OwnedBytes;
 use crate::schema::Field;
 use crate::space_usage::PerFieldSpaceUsage;
 use crate::DocId;
@@ -19,16 +20,21 @@ pub struct FieldNormReaders {
 
 impl FieldNormReaders {
     /// Creates a field norm reader.
-    pub fn open(source: ReadOnlySource) -> crate::Result<FieldNormReaders> {
-        let data = CompositeFile::open(&source)?;
+    pub fn open(file: FileSlice) -> crate::Result<FieldNormReaders> {
+        let data = CompositeFile::open(&file)?;
         Ok(FieldNormReaders {
             data: Arc::new(data),
         })
     }
 
     /// Returns the FieldNormReader for a specific field.
-    pub fn get_field(&self, field: Field) -> Option<FieldNormReader> {
-        self.data.open_read(field).map(FieldNormReader::open)
+    pub fn get_field(&self, field: Field) -> crate::Result<Option<FieldNormReader>> {
+        if let Some(file) = self.data.open_read(field) {
+            let fieldnorm_reader = FieldNormReader::open(file)?;
+            Ok(Some(fieldnorm_reader))
+        } else {
+            Ok(None)
+        }
     }
 
     /// Return a break down of the space usage per field.
@@ -43,7 +49,7 @@ impl FieldNormReaders {
 ///
 /// This metric is important to compute the score of a
 /// document : a document having a query word in one its short fields
-/// (e.g. title)  is likely to be more relevant than in one of its longer field
+/// (e.g. title)is likely to be more relevant than in one of its longer field
 /// (e.g. body).
 ///
 /// tantivy encodes `fieldnorm` on one byte with some precision loss,
@@ -55,19 +61,31 @@ impl FieldNormReaders {
 /// precompute computationally expensive functions of the fieldnorm
 /// in a very short array.
 #[derive(Clone)]
-pub struct FieldNormReader {
-    data: ReadOnlySource,
+pub enum FieldNormReader {
+    ConstFieldNorm { fieldnorm_id: u8, num_docs: u32 },
+    OneByte(OwnedBytes),
 }
 
 impl FieldNormReader {
-    /// Opens a field norm reader given its data source.
-    pub fn open(data: ReadOnlySource) -> Self {
-        FieldNormReader { data }
+    pub fn const_fieldnorm_id(fieldnorm_id: u8, num_docs: u32) -> FieldNormReader {
+        FieldNormReader::ConstFieldNorm {
+            fieldnorm_id,
+            num_docs,
+        }
+    }
+
+    /// Opens a field norm reader given its file.
+    pub fn open(fieldnorm_file: FileSlice) -> crate::Result<Self> {
+        let data = fieldnorm_file.read_bytes()?;
+        Ok(FieldNormReader::OneByte(data))
     }
 
     /// Returns the number of documents in this segment.
     pub fn num_docs(&self) -> u32 {
-        self.data.len() as u32
+        match self {
+            Self::ConstFieldNorm { num_docs, .. } => *num_docs,
+            FieldNormReader::OneByte(vals) => vals.len() as u32,
+        }
     }
 
     /// Returns the `fieldnorm` associated to a doc id.
@@ -79,6 +97,7 @@ impl FieldNormReader {
     ///
     /// The fieldnorm is effectively decoded from the
     /// `fieldnorm_id` by doing a simple table lookup.
+    #[inline(always)]
     pub fn fieldnorm(&self, doc_id: DocId) -> u32 {
         let fieldnorm_id = self.fieldnorm_id(doc_id);
         id_to_fieldnorm(fieldnorm_id)
@@ -87,8 +106,11 @@ impl FieldNormReader {
     /// Returns the `fieldnorm_id` associated to a document.
     #[inline(always)]
     pub fn fieldnorm_id(&self, doc_id: DocId) -> u8 {
-        let fielnorms_data = self.data.as_slice();
-        fielnorms_data[doc_id as usize]
+        match self {
+            FieldNormReader::ConstFieldNorm { fieldnorm_id, .. } => *fieldnorm_id,
+
+            FieldNormReader::OneByte(data) => data.as_slice()[doc_id as usize],
+        }
     }
 
     /// Converts a `fieldnorm_id` into a fieldnorm.
@@ -111,10 +133,8 @@ impl FieldNormReader {
             .cloned()
             .map(FieldNormReader::fieldnorm_to_id)
             .collect::<Vec<u8>>();
-        let field_norms_data = ReadOnlySource::from(field_norms_id);
-        FieldNormReader {
-            data: field_norms_data,
-        }
+        let field_norms_data = OwnedBytes::new(field_norms_id);
+        FieldNormReader::OneByte(field_norms_data)
     }
 }
 

src/fieldnorm/writer.rs

@@ -13,7 +13,7 @@ use std::io;
 /// byte per document per field.
 pub struct FieldNormsWriter {
     fields: Vec<Field>,
-    fieldnorms_buffer: Vec<Vec<u8>>,
+    fieldnorms_buffer: Vec<Option<Vec<u8>>>,
 }
 
 impl FieldNormsWriter {
@@ -23,7 +23,7 @@ impl FieldNormsWriter {
         schema
             .fields()
             .filter_map(|(field, field_entry)| {
-                if field_entry.is_indexed() {
+                if field_entry.has_fieldnorms() {
                     Some(field)
                 } else {
                     None
@@ -36,15 +36,14 @@ impl FieldNormsWriter {
     /// specified in the schema.
     pub fn for_schema(schema: &Schema) -> FieldNormsWriter {
         let fields = FieldNormsWriter::fields_with_fieldnorm(schema);
-        let max_field = fields
-            .iter()
-            .map(Field::field_id)
-            .max()
-            .map(|max_field_id| max_field_id as usize + 1)
-            .unwrap_or(0);
+        let num_fields = schema.num_fields();
+        let mut fieldnorms_buffer: Vec<Option<Vec<u8>>> = vec![None; num_fields];
+        for field in &fields {
+            fieldnorms_buffer[field.field_id() as usize] = Some(Vec::new());
+        }
         FieldNormsWriter {
             fields,
-            fieldnorms_buffer: (0..max_field).map(|_| Vec::new()).collect::<Vec<_>>(),
+            fieldnorms_buffer,
         }
     }
 
@@ -53,8 +52,10 @@ impl FieldNormsWriter {
     ///
     /// Will extend with 0-bytes for documents that have not been seen.
     pub fn fill_up_to_max_doc(&mut self, max_doc: DocId) {
-        for field in self.fields.iter() {
-            self.fieldnorms_buffer[field.field_id() as usize].resize(max_doc as usize, 0u8);
+        for buffer_opt in self.fieldnorms_buffer.iter_mut() {
+            if let Some(buffer) = buffer_opt {
+                buffer.resize(max_doc as usize, 0u8);
+            }
         }
     }
 
@@ -67,21 +68,22 @@ impl FieldNormsWriter {
     /// * field     - the field being set
     /// * fieldnorm - the number of terms present in document `doc` in field `field`
     pub fn record(&mut self, doc: DocId, field: Field, fieldnorm: u32) {
-        let fieldnorm_buffer: &mut Vec<u8> = &mut self.fieldnorms_buffer[field.field_id() as usize];
-        assert!(
-            fieldnorm_buffer.len() <= doc as usize,
-            "Cannot register a given fieldnorm twice"
-        );
-        // we fill intermediary `DocId` as  having a fieldnorm of 0.
-        fieldnorm_buffer.resize(doc as usize + 1, 0u8);
-        fieldnorm_buffer[doc as usize] = fieldnorm_to_id(fieldnorm);
+        if let Some(fieldnorm_buffer) = self.fieldnorms_buffer[field.field_id() as usize].as_mut() {
+            assert!(
+                fieldnorm_buffer.len() <= doc as usize,
+                "Cannot register a given fieldnorm twice" // we fill intermediary `DocId` as  having a fieldnorm of 0.
+            );
+            fieldnorm_buffer.resize(doc as usize + 1, 0u8);
+            fieldnorm_buffer[doc as usize] = fieldnorm_to_id(fieldnorm);
+        }
     }
 
     /// Serialize the seen fieldnorm values to the serializer for all fields.
     pub fn serialize(&self, mut fieldnorms_serializer: FieldNormsSerializer) -> io::Result<()> {
         for &field in self.fields.iter() {
-            let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.field_id() as usize][..];
-            fieldnorms_serializer.serialize_field(field, fieldnorm_values)?;
+            if let Some(buffer) = self.fieldnorms_buffer[field.field_id() as usize].as_ref() {
+                fieldnorms_serializer.serialize_field(field, &buffer[..])?;
+            }
         }
         fieldnorms_serializer.close()?;
         Ok(())

src/indexer/index_writer.rs

@@ -108,9 +108,9 @@ fn compute_deleted_bitset(
         // Limit doc helps identify the first document
         // that may be affected by the delete operation.
         let limit_doc = doc_opstamps.compute_doc_limit(delete_op.opstamp);
-        let inverted_index = segment_reader.inverted_index(delete_op.term.field());
+        let inverted_index = segment_reader.inverted_index(delete_op.term.field())?;
         if let Some(mut docset) =
-            inverted_index.read_postings(&delete_op.term, IndexRecordOption::Basic)
+            inverted_index.read_postings(&delete_op.term, IndexRecordOption::Basic)?
         {
             let mut deleted_doc = docset.doc();
             while deleted_doc != TERMINATED {
@@ -979,7 +979,7 @@ mod tests {
         let num_docs_containing = |s: &str| {
             let searcher = reader.searcher();
             let term = Term::from_field_text(text_field, s);
-            searcher.doc_freq(&term)
+            searcher.doc_freq(&term).unwrap()
         };
 
         {
@@ -1015,7 +1015,7 @@ mod tests {
             .unwrap();
         let num_docs_containing = |s: &str| {
             let term_a = Term::from_field_text(text_field, s);
-            reader.searcher().doc_freq(&term_a)
+            reader.searcher().doc_freq(&term_a).unwrap()
         };
         {
             // writing the segment
@@ -1110,6 +1110,7 @@ mod tests {
                 .unwrap()
                 .searcher()
                 .doc_freq(&term_a)
+                .unwrap()
         };
         assert_eq!(num_docs_containing("a"), 0);
         assert_eq!(num_docs_containing("b"), 100);
@@ -1129,7 +1130,7 @@ mod tests {
             reader.reload().unwrap();
             let searcher = reader.searcher();
             let term = Term::from_field_text(text_field, s);
-            searcher.doc_freq(&term)
+            searcher.doc_freq(&term).unwrap()
         };
         let mut index_writer = index.writer_with_num_threads(4, 12_000_000).unwrap();
 
@@ -1180,7 +1181,15 @@ mod tests {
 
         // working with an empty index == no documents
         let term_b = Term::from_field_text(text_field, "b");
-        assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_b), 0);
+        assert_eq!(
+            index
+                .reader()
+                .unwrap()
+                .searcher()
+                .doc_freq(&term_b)
+                .unwrap(),
+            0
+        );
     }
 
     #[test]
@@ -1200,7 +1209,15 @@ mod tests {
 
         let term_a = Term::from_field_text(text_field, "a");
         // expect the document with that term to be in the index
-        assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_a), 1);
+        assert_eq!(
+            index
+                .reader()
+                .unwrap()
+                .searcher()
+                .doc_freq(&term_a)
+                .unwrap(),
+            1
+        );
     }
 
     #[test]
@@ -1226,7 +1243,15 @@ mod tests {
         // Find original docs in the index
         let term_a = Term::from_field_text(text_field, "a");
         // expect the document with that term to be in the index
-        assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_a), 1);
+        assert_eq!(
+            index
+                .reader()
+                .unwrap()
+                .searcher()
+                .doc_freq(&term_a)
+                .unwrap(),
+            1
+        );
     }
 
     #[test]

src/indexer/merger.rs

@@ -38,7 +38,7 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> crate::R
                 count[fieldnorm_id as usize] += 1;
             }
         } else {
-            total_tokens += reader.inverted_index(field).total_num_tokens();
+            total_tokens += reader.inverted_index(field)?.total_num_tokens();
         }
     }
     Ok(total_tokens
@@ -194,7 +194,7 @@ impl IndexMerger {
     ) -> crate::Result<()> {
         for (field, field_entry) in self.schema.fields() {
             let field_type = field_entry.field_type();
-            match *field_type {
+            match field_type {
                 FieldType::HierarchicalFacet => {
                     let term_ordinal_mapping = term_ord_mappings
                         .remove(&field)
@@ -223,8 +223,10 @@ impl IndexMerger {
                     // They can be implemented using what is done
                     // for facets in the future.
                 }
-                FieldType::Bytes => {
-                    self.write_bytes_fast_field(field, fast_field_serializer)?;
+                FieldType::Bytes(byte_options) => {
+                    if byte_options.is_fast() {
+                        self.write_bytes_fast_field(field, fast_field_serializer)?;
+                    }
                 }
             }
         }
@@ -443,9 +445,11 @@ impl IndexMerger {
         let mut bytes_readers: Vec<BytesFastFieldReader> = Vec::new();
 
         for reader in &self.readers {
-            let bytes_reader = reader.fast_fields().bytes(field).expect(
-                "Failed to find bytes fast field reader. This is a bug in tantivy, please report.",
-            );
+            let bytes_reader = reader.fast_fields().bytes(field).ok_or_else(|| {
+                crate::TantivyError::InvalidArgument(
+                    "Bytes fast field {:?} not found in segment.".to_string(),
+                )
+            })?;
             if let Some(delete_bitset) = reader.delete_bitset() {
                 for doc in 0u32..reader.max_doc() {
                     if delete_bitset.is_alive(doc) {
@@ -498,14 +502,15 @@ impl IndexMerger {
     ) -> crate::Result<Option<TermOrdinalMapping>> {
         let mut positions_buffer: Vec<u32> = Vec::with_capacity(1_000);
         let mut delta_computer = DeltaComputer::new();
+
+        let mut field_term_streams = Vec::new();
+        let mut max_term_ords: Vec<TermOrdinal> = Vec::new();
+
         let field_readers: Vec<Arc<InvertedIndexReader>> = self
             .readers
             .iter()
             .map(|reader| reader.inverted_index(indexed_field))
-            .collect::<Vec<_>>();
-
-        let mut field_term_streams = Vec::new();
-        let mut max_term_ords: Vec<TermOrdinal> = Vec::new();
+            .collect::<crate::Result<Vec<_>>>()?;
 
         for field_reader in &field_readers {
             let terms = field_reader.terms();
@@ -578,8 +583,8 @@ impl IndexMerger {
                 let term_info = heap_item.streamer.value();
                 let segment_reader = &self.readers[heap_item.segment_ord];
                 let inverted_index: &InvertedIndexReader = &*field_readers[segment_ord];
-                let segment_postings =
-                    inverted_index.read_postings_from_terminfo(term_info, segment_postings_option);
+                let segment_postings = inverted_index
+                    .read_postings_from_terminfo(term_info, segment_postings_option)?;
                 let delete_bitset_opt = segment_reader.delete_bitset();
                 let doc_freq = if let Some(delete_bitset) = delete_bitset_opt {
                     segment_postings.doc_freq_given_deletes(delete_bitset)
@@ -648,7 +653,7 @@ impl IndexMerger {
     ) -> crate::Result<HashMap<Field, TermOrdinalMapping>> {
         let mut term_ordinal_mappings = HashMap::new();
         for (field, field_entry) in self.schema.fields() {
-            let fieldnorm_reader = fieldnorm_readers.get_field(field);
+            let fieldnorm_reader = fieldnorm_readers.get_field(field)?;
             if field_entry.is_indexed() {
                 if let Some(term_ordinal_mapping) = self.write_postings_for_field(
                     field,
@@ -665,7 +670,7 @@ impl IndexMerger {
 
     fn write_storable_fields(&self, store_writer: &mut StoreWriter) -> crate::Result<()> {
         for reader in &self.readers {
-            let store_reader = reader.get_store_reader();
+            let store_reader = reader.get_store_reader()?;
             if reader.num_deleted_docs() > 0 {
                 for doc_id in reader.doc_ids_alive() {
                     let doc = store_reader.get(doc_id)?;
@@ -720,12 +725,12 @@ mod tests {
     use crate::IndexWriter;
     use crate::Searcher;
     use crate::{schema, DocSet, SegmentId};
-    use byteorder::{BigEndian, ReadBytesExt, WriteBytesExt};
+    use byteorder::{BigEndian, ReadBytesExt};
     use futures::executor::block_on;
-    use std::io::Cursor;
+    use schema::FAST;
 
     #[test]
-    fn test_index_merger_no_deletes() {
+    fn test_index_merger_no_deletes() -> crate::Result<()> {
         let mut schema_builder = schema::Schema::builder();
         let text_fieldtype = schema::TextOptions::default()
             .set_indexing_options(
@@ -738,98 +743,77 @@ mod tests {
         let date_field = schema_builder.add_date_field("date", INDEXED);
         let score_fieldtype = schema::IntOptions::default().set_fast(Cardinality::SingleValue);
         let score_field = schema_builder.add_u64_field("score", score_fieldtype);
-        let bytes_score_field = schema_builder.add_bytes_field("score_bytes");
+        let bytes_score_field = schema_builder.add_bytes_field("score_bytes", FAST);
         let index = Index::create_in_ram(schema_builder.build());
-        let reader = index.reader().unwrap();
+        let reader = index.reader()?;
         let curr_time = chrono::Utc::now();
-        let add_score_bytes = |doc: &mut Document, score: u32| {
-            let mut bytes = Vec::new();
-            bytes
-                .write_u32::<BigEndian>(score)
-                .expect("failed to write u32 bytes to Vec...");
-            doc.add_bytes(bytes_score_field, bytes);
-        };
-
         {
-            let mut index_writer = index.writer_for_tests().unwrap();
-            {
-                // writing the segment
-                {
-                    let mut doc = Document::default();
-                    doc.add_text(text_field, "af b");
-                    doc.add_u64(score_field, 3);
-                    doc.add_date(date_field, &curr_time);
-                    add_score_bytes(&mut doc, 3);
-                    index_writer.add_document(doc);
-                }
-                {
-                    let mut doc = Document::default();
-                    doc.add_text(text_field, "a b c");
-                    doc.add_u64(score_field, 5);
-                    add_score_bytes(&mut doc, 5);
-                    index_writer.add_document(doc);
-                }
-                {
-                    let mut doc = Document::default();
-                    doc.add_text(text_field, "a b c d");
-                    doc.add_u64(score_field, 7);
-                    add_score_bytes(&mut doc, 7);
-                    index_writer.add_document(doc);
-                }
-                index_writer.commit().expect("committed");
-            }
+            let mut index_writer = index.writer_for_tests()?;
+            // writing the segment
+            index_writer.add_document(doc!(
+                text_field => "af b",
+                score_field => 3u64,
+                date_field => curr_time,
+                bytes_score_field => 3u32.to_be_bytes().as_ref()
+            ));
 
-            {
-                // writing the segment
-                {
-                    let mut doc = Document::default();
-                    doc.add_text(text_field, "af b");
-                    doc.add_date(date_field, &curr_time);
-                    doc.add_u64(score_field, 11);
-                    add_score_bytes(&mut doc, 11);
-                    index_writer.add_document(doc);
-                }
-                {
-                    let mut doc = Document::default();
-                    doc.add_text(text_field, "a b c g");
-                    doc.add_u64(score_field, 13);
-                    add_score_bytes(&mut doc, 13);
-                    index_writer.add_document(doc);
-                }
-                index_writer.commit().expect("Commit failed");
-            }
+            index_writer.add_document(doc!(
+                text_field => "a b c",
+                score_field => 5u64,
+                bytes_score_field => 5u32.to_be_bytes().as_ref()
+            ));
+            index_writer.add_document(doc!(
+                text_field => "a b c d",
+                score_field => 7u64,
+                bytes_score_field => 7u32.to_be_bytes().as_ref()
+            ));
+            index_writer.commit()?;
+            // writing the segment
+            index_writer.add_document(doc!(
+                text_field => "af b",
+                date_field => curr_time,
+                score_field => 11u64,
+                bytes_score_field => 11u32.to_be_bytes().as_ref()
+            ));
+            index_writer.add_document(doc!(
+                text_field => "a b c g",
+                score_field => 13u64,
+                bytes_score_field => 13u32.to_be_bytes().as_ref()
+            ));
+            index_writer.commit()?;
         }
         {
             let segment_ids = index
                 .searchable_segment_ids()
                 .expect("Searchable segments failed.");
-            let mut index_writer = index.writer_for_tests().unwrap();
-            block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
-            index_writer.wait_merging_threads().unwrap();
+            let mut index_writer = index.writer_for_tests()?;
+            block_on(index_writer.merge(&segment_ids))?;
+            index_writer.wait_merging_threads()?;
         }
         {
-            reader.reload().unwrap();
+            reader.reload()?;
             let searcher = reader.searcher();
             let get_doc_ids = |terms: Vec<Term>| {
                 let query = BooleanQuery::new_multiterms_query(terms);
-                let top_docs = searcher.search(&query, &TEST_COLLECTOR_WITH_SCORE).unwrap();
-                top_docs.docs().to_vec()
+                searcher
+                    .search(&query, &TEST_COLLECTOR_WITH_SCORE)
+                    .map(|top_docs| top_docs.docs().to_vec())
             };
             {
                 assert_eq!(
-                    get_doc_ids(vec![Term::from_field_text(text_field, "a")]),
+                    get_doc_ids(vec![Term::from_field_text(text_field, "a")])?,
                     vec![DocAddress(0, 1), DocAddress(0, 2), DocAddress(0, 4)]
                 );
                 assert_eq!(
-                    get_doc_ids(vec![Term::from_field_text(text_field, "af")]),
+                    get_doc_ids(vec![Term::from_field_text(text_field, "af")])?,
                     vec![DocAddress(0, 0), DocAddress(0, 3)]
                 );
                 assert_eq!(
-                    get_doc_ids(vec![Term::from_field_text(text_field, "g")]),
+                    get_doc_ids(vec![Term::from_field_text(text_field, "g")])?,
                     vec![DocAddress(0, 4)]
                 );
                 assert_eq!(
-                    get_doc_ids(vec![Term::from_field_text(text_field, "b")]),
+                    get_doc_ids(vec![Term::from_field_text(text_field, "b")])?,
                     vec![
                         DocAddress(0, 0),
                         DocAddress(0, 1),
@@ -839,60 +823,57 @@ mod tests {
                     ]
                 );
                 assert_eq!(
-                    get_doc_ids(vec![Term::from_field_date(date_field, &curr_time)]),
+                    get_doc_ids(vec![Term::from_field_date(date_field, &curr_time)])?,
                     vec![DocAddress(0, 0), DocAddress(0, 3)]
                 );
             }
             {
-                let doc = searcher.doc(DocAddress(0, 0)).unwrap();
+                let doc = searcher.doc(DocAddress(0, 0))?;
                 assert_eq!(doc.get_first(text_field).unwrap().text(), Some("af b"));
             }
             {
-                let doc = searcher.doc(DocAddress(0, 1)).unwrap();
+                let doc = searcher.doc(DocAddress(0, 1))?;
                 assert_eq!(doc.get_first(text_field).unwrap().text(), Some("a b c"));
             }
             {
-                let doc = searcher.doc(DocAddress(0, 2)).unwrap();
+                let doc = searcher.doc(DocAddress(0, 2))?;
                 assert_eq!(doc.get_first(text_field).unwrap().text(), Some("a b c d"));
             }
             {
-                let doc = searcher.doc(DocAddress(0, 3)).unwrap();
+                let doc = searcher.doc(DocAddress(0, 3))?;
                 assert_eq!(doc.get_first(text_field).unwrap().text(), Some("af b"));
             }
             {
-                let doc = searcher.doc(DocAddress(0, 4)).unwrap();
+                let doc = searcher.doc(DocAddress(0, 4))?;
                 assert_eq!(doc.get_first(text_field).unwrap().text(), Some("a b c g"));
             }
             {
                 let get_fast_vals = |terms: Vec<Term>| {
                     let query = BooleanQuery::new_multiterms_query(terms);
-                    searcher
-                        .search(&query, &FastFieldTestCollector::for_field(score_field))
-                        .unwrap()
+                    searcher.search(&query, &FastFieldTestCollector::for_field(score_field))
                 };
                 let get_fast_vals_bytes = |terms: Vec<Term>| {
                     let query = BooleanQuery::new_multiterms_query(terms);
-                    searcher
-                        .search(
-                            &query,
-                            &BytesFastFieldTestCollector::for_field(bytes_score_field),
-                        )
-                        .expect("failed to search")
+                    searcher.search(
+                        &query,
+                        &BytesFastFieldTestCollector::for_field(bytes_score_field),
+                    )
                 };
                 assert_eq!(
-                    get_fast_vals(vec![Term::from_field_text(text_field, "a")]),
+                    get_fast_vals(vec![Term::from_field_text(text_field, "a")])?,
                     vec![5, 7, 13]
                 );
                 assert_eq!(
-                    get_fast_vals_bytes(vec![Term::from_field_text(text_field, "a")]),
+                    get_fast_vals_bytes(vec![Term::from_field_text(text_field, "a")])?,
                     vec![0, 0, 0, 5, 0, 0, 0, 7, 0, 0, 0, 13]
                 );
             }
         }
+        Ok(())
     }
 
     #[test]
-    fn test_index_merger_with_deletes() {
+    fn test_index_merger_with_deletes() -> crate::Result<()> {
         let mut schema_builder = schema::Schema::builder();
         let text_fieldtype = schema::TextOptions::default()
             .set_indexing_options(
@@ -902,27 +883,26 @@ mod tests {
         let text_field = schema_builder.add_text_field("text", text_fieldtype);
         let score_fieldtype = schema::IntOptions::default().set_fast(Cardinality::SingleValue);
         let score_field = schema_builder.add_u64_field("score", score_fieldtype);
-        let bytes_score_field = schema_builder.add_bytes_field("score_bytes");
+        let bytes_score_field = schema_builder.add_bytes_field("score_bytes", FAST);
         let index = Index::create_in_ram(schema_builder.build());
-        let mut index_writer = index.writer_for_tests().unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         let reader = index.reader().unwrap();
         let search_term = |searcher: &Searcher, term: Term| {
             let collector = FastFieldTestCollector::for_field(score_field);
             let bytes_collector = BytesFastFieldTestCollector::for_field(bytes_score_field);
             let term_query = TermQuery::new(term, IndexRecordOption::Basic);
-            let (scores, bytes) = searcher
+            searcher
                 .search(&term_query, &(collector, bytes_collector))
-                .unwrap();
-            let mut score_bytes = Cursor::new(bytes);
-            for &score in &scores {
-                assert_eq!(score as u32, score_bytes.read_u32::<BigEndian>().unwrap());
-            }
-
-            scores
+                .map(|(scores, bytes)| {
+                    let mut score_bytes = &bytes[..];
+                    for &score in &scores {
+                        assert_eq!(score as u32, score_bytes.read_u32::<BigEndian>().unwrap());
+                    }
+                    scores
+                })
         };
 
         let empty_vec = Vec::<u64>::new();
-
         {
             // a first commit
             index_writer.add_document(doc!(
@@ -941,26 +921,26 @@ mod tests {
                 score_field => 3u64,
                 bytes_score_field => vec![0u8, 0, 0, 3],
             ));
-            index_writer.commit().expect("committed");
-            reader.reload().unwrap();
+            index_writer.commit()?;
+            reader.reload()?;
             let searcher = reader.searcher();
             assert_eq!(searcher.num_docs(), 2);
             assert_eq!(searcher.segment_readers()[0].num_docs(), 2);
             assert_eq!(searcher.segment_readers()[0].max_doc(), 3);
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "a")),
+                search_term(&searcher, Term::from_field_text(text_field, "a"))?,
                 vec![1]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "b")),
+                search_term(&searcher, Term::from_field_text(text_field, "b"))?,
                 vec![1]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "c")),
+                search_term(&searcher, Term::from_field_text(text_field, "c"))?,
                 vec![3]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "d")),
+                search_term(&searcher, Term::from_field_text(text_field, "d"))?,
                 vec![1, 3]
             );
         }
@@ -988,8 +968,8 @@ mod tests {
                 score_field => 7_000u64,
                 bytes_score_field => vec![0u8, 0, 27, 88],
             ));
-            index_writer.commit().expect("committed");
-            reader.reload().unwrap();
+            index_writer.commit()?;
+            reader.reload()?;
             let searcher = reader.searcher();
 
             assert_eq!(searcher.segment_readers().len(), 2);
@@ -999,31 +979,31 @@ mod tests {
             assert_eq!(searcher.segment_readers()[1].num_docs(), 1);
             assert_eq!(searcher.segment_readers()[1].max_doc(), 3);
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "a")),
+                search_term(&searcher, Term::from_field_text(text_field, "a"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "b")),
+                search_term(&searcher, Term::from_field_text(text_field, "b"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "c")),
+                search_term(&searcher, Term::from_field_text(text_field, "c"))?,
                 vec![3]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "d")),
+                search_term(&searcher, Term::from_field_text(text_field, "d"))?,
                 vec![3]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "e")),
+                search_term(&searcher, Term::from_field_text(text_field, "e"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "f")),
+                search_term(&searcher, Term::from_field_text(text_field, "f"))?,
                 vec![6_000]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "g")),
+                search_term(&searcher, Term::from_field_text(text_field, "g"))?,
                 vec![6_000, 7_000]
             );
 
@@ -1045,42 +1025,40 @@ mod tests {
         }
         {
             // merging the segments
-            let segment_ids = index
-                .searchable_segment_ids()
-                .expect("Searchable segments failed.");
-            block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
-            reader.reload().unwrap();
+            let segment_ids = index.searchable_segment_ids()?;
+            block_on(index_writer.merge(&segment_ids))?;
+            reader.reload()?;
             let searcher = reader.searcher();
             assert_eq!(searcher.segment_readers().len(), 1);
             assert_eq!(searcher.num_docs(), 3);
             assert_eq!(searcher.segment_readers()[0].num_docs(), 3);
             assert_eq!(searcher.segment_readers()[0].max_doc(), 3);
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "a")),
+                search_term(&searcher, Term::from_field_text(text_field, "a"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "b")),
+                search_term(&searcher, Term::from_field_text(text_field, "b"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "c")),
+                search_term(&searcher, Term::from_field_text(text_field, "c"))?,
                 vec![3]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "d")),
+                search_term(&searcher, Term::from_field_text(text_field, "d"))?,
                 vec![3]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "e")),
+                search_term(&searcher, Term::from_field_text(text_field, "e"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "f")),
+                search_term(&searcher, Term::from_field_text(text_field, "f"))?,
                 vec![6_000]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "g")),
+                search_term(&searcher, Term::from_field_text(text_field, "g"))?,
                 vec![6_000, 7_000]
             );
             let score_field_reader = searcher
@@ -1094,40 +1072,40 @@ mod tests {
         {
             // test a commit with only deletes
             index_writer.delete_term(Term::from_field_text(text_field, "c"));
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
 
-            reader.reload().unwrap();
+            reader.reload()?;
             let searcher = reader.searcher();
             assert_eq!(searcher.segment_readers().len(), 1);
             assert_eq!(searcher.num_docs(), 2);
             assert_eq!(searcher.segment_readers()[0].num_docs(), 2);
             assert_eq!(searcher.segment_readers()[0].max_doc(), 3);
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "a")),
+                search_term(&searcher, Term::from_field_text(text_field, "a"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "b")),
+                search_term(&searcher, Term::from_field_text(text_field, "b"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "c")),
+                search_term(&searcher, Term::from_field_text(text_field, "c"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "d")),
+                search_term(&searcher, Term::from_field_text(text_field, "d"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "e")),
+                search_term(&searcher, Term::from_field_text(text_field, "e"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "f")),
+                search_term(&searcher, Term::from_field_text(text_field, "f"))?,
                 vec![6_000]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "g")),
+                search_term(&searcher, Term::from_field_text(text_field, "g"))?,
                 vec![6_000, 7_000]
             );
             let score_field_reader = searcher
@@ -1140,11 +1118,9 @@ mod tests {
         }
         {
             // Test merging a single segment in order to remove deletes.
-            let segment_ids = index
-                .searchable_segment_ids()
-                .expect("Searchable segments failed.");
-            block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
-            reader.reload().unwrap();
+            let segment_ids = index.searchable_segment_ids()?;
+            block_on(index_writer.merge(&segment_ids))?;
+            reader.reload()?;
 
             let searcher = reader.searcher();
             assert_eq!(searcher.segment_readers().len(), 1);
@@ -1152,31 +1128,31 @@ mod tests {
             assert_eq!(searcher.segment_readers()[0].num_docs(), 2);
             assert_eq!(searcher.segment_readers()[0].max_doc(), 2);
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "a")),
+                search_term(&searcher, Term::from_field_text(text_field, "a"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "b")),
+                search_term(&searcher, Term::from_field_text(text_field, "b"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "c")),
+                search_term(&searcher, Term::from_field_text(text_field, "c"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "d")),
+                search_term(&searcher, Term::from_field_text(text_field, "d"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "e")),
+                search_term(&searcher, Term::from_field_text(text_field, "e"))?,
                 empty_vec
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "f")),
+                search_term(&searcher, Term::from_field_text(text_field, "f"))?,
                 vec![6_000]
             );
             assert_eq!(
-                search_term(&searcher, Term::from_field_text(text_field, "g")),
+                search_term(&searcher, Term::from_field_text(text_field, "g"))?,
                 vec![6_000, 7_000]
             );
             let score_field_reader = searcher
@@ -1191,17 +1167,16 @@ mod tests {
         {
             // Test removing all docs
             index_writer.delete_term(Term::from_field_text(text_field, "g"));
-            index_writer.commit().unwrap();
-            let segment_ids = index
-                .searchable_segment_ids()
-                .expect("Searchable segments failed.");
-            reader.reload().unwrap();
+            index_writer.commit()?;
+            let segment_ids = index.searchable_segment_ids()?;
+            reader.reload()?;
 
             let searcher = reader.searcher();
             assert!(segment_ids.is_empty());
             assert!(searcher.segment_readers().is_empty());
             assert_eq!(searcher.num_docs(), 0);
         }
+        Ok(())
     }
 
     #[test]
@@ -1558,7 +1533,7 @@ mod tests {
         let reader = index.reader()?;
         let searcher = reader.searcher();
         let mut term_scorer = term_query
-            .specialized_weight(&searcher, true)
+            .specialized_weight(&searcher, true)?
             .specialized_scorer(searcher.segment_reader(0u32), 1.0)?;
         assert_eq!(term_scorer.doc(), 0);
         assert_nearly_equals!(term_scorer.block_max_score(), 0.0079681855);
@@ -1573,7 +1548,7 @@ mod tests {
         assert_eq!(searcher.segment_readers().len(), 2);
         for segment_reader in searcher.segment_readers() {
             let mut term_scorer = term_query
-                .specialized_weight(&searcher, true)
+                .specialized_weight(&searcher, true)?
                 .specialized_scorer(segment_reader, 1.0)?;
             // the difference compared to before is instrinsic to the bm25 formula. no worries there.
             for doc in segment_reader.doc_ids_alive() {
@@ -1597,7 +1572,7 @@ mod tests {
 
         let segment_reader = searcher.segment_reader(0u32);
         let mut term_scorer = term_query
-            .specialized_weight(&searcher, true)
+            .specialized_weight(&searcher, true)?
             .specialized_scorer(segment_reader, 1.0)?;
         // the difference compared to before is instrinsic to the bm25 formula. no worries there.
         for doc in segment_reader.doc_ids_alive() {

src/indexer/segment_updater.rs

@@ -43,7 +43,7 @@ const NUM_MERGE_THREADS: usize = 4;
 /// and flushed.
 ///
 /// This method is not part of tantivy's public API
-pub fn save_new_metas(schema: Schema, directory: &mut dyn Directory) -> crate::Result<()> {
+pub fn save_new_metas(schema: Schema, directory: &dyn Directory) -> crate::Result<()> {
     save_metas(
         &IndexMeta {
             segments: Vec::new(),
@@ -64,7 +64,7 @@ pub fn save_new_metas(schema: Schema, directory: &mut dyn Directory) -> crate::R
 /// and flushed.
 ///
 /// This method is not part of tantivy's public API
-fn save_metas(metas: &IndexMeta, directory: &mut dyn Directory) -> crate::Result<()> {
+fn save_metas(metas: &IndexMeta, directory: &dyn Directory) -> crate::Result<()> {
     info!("save metas");
     let mut buffer = serde_json::to_vec_pretty(metas)?;
     // Just adding a new line at the end of the buffer.
@@ -450,9 +450,8 @@ impl SegmentUpdater {
             .into_iter()
             .map(|merge_candidate: MergeCandidate| {
                 MergeOperation::new(&self.merge_operations, commit_opstamp, merge_candidate.0)
-            })
-            .collect::<Vec<_>>();
-        merge_candidates.extend(committed_merge_candidates.into_iter());
+            });
+        merge_candidates.extend(committed_merge_candidates);
 
         for merge_operation in merge_candidates {
             if let Err(err) = self.start_merge(merge_operation) {

src/indexer/segment_writer.rs

@@ -16,7 +16,6 @@ use crate::tokenizer::{FacetTokenizer, TextAnalyzer};
 use crate::tokenizer::{TokenStreamChain, Tokenizer};
 use crate::Opstamp;
 use crate::{DocId, SegmentComponent};
-use std::io;
 
 /// Computes the initial size of the hash table.
 ///
@@ -117,7 +116,11 @@ impl SegmentWriter {
     /// Indexes a new document
     ///
     /// As a user, you should rather use `IndexWriter`'s add_document.
-    pub fn add_document(&mut self, add_operation: AddOperation, schema: &Schema) -> io::Result<()> {
+    pub fn add_document(
+        &mut self,
+        add_operation: AddOperation,
+        schema: &Schema,
+    ) -> crate::Result<()> {
         let doc_id = self.max_doc;
         let mut doc = add_operation.document;
         self.doc_opstamps.push(add_operation.opstamp);
@@ -125,13 +128,20 @@ impl SegmentWriter {
         self.fast_field_writers.add_document(&doc);
 
         for (field, field_values) in doc.get_sorted_field_values() {
-            let field_options = schema.get_field_entry(field);
-            if !field_options.is_indexed() {
+            let field_entry = schema.get_field_entry(field);
+            let make_schema_error = || {
+                crate::TantivyError::SchemaError(format!(
+                    "Expected a {:?} for field {:?}",
+                    field_entry.field_type().value_type(),
+                    field_entry.name()
+                ))
+            };
+            if !field_entry.is_indexed() {
                 continue;
             }
             let (term_buffer, multifield_postings) =
                 (&mut self.term_buffer, &mut self.multifield_postings);
-            match *field_options.field_type() {
+            match *field_entry.field_type() {
                 FieldType::HierarchicalFacet => {
                     term_buffer.set_field(field);
                     let facets =
@@ -143,18 +153,20 @@ impl SegmentWriter {
                                     panic!("Expected hierarchical facet");
                                 }
                             });
-                    for fake_str in facets {
+                    for facet_str in facets {
                         let mut unordered_term_id_opt = None;
-                        FacetTokenizer.token_stream(fake_str).process(&mut |token| {
-                            term_buffer.set_text(&token.text);
-                            let unordered_term_id =
-                                multifield_postings.subscribe(doc_id, &term_buffer);
-                            unordered_term_id_opt = Some(unordered_term_id);
-                        });
+                        FacetTokenizer
+                            .token_stream(facet_str)
+                            .process(&mut |token| {
+                                term_buffer.set_text(&token.text);
+                                let unordered_term_id =
+                                    multifield_postings.subscribe(doc_id, &term_buffer);
+                                unordered_term_id_opt = Some(unordered_term_id);
+                            });
                         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);
                         }
                     }
@@ -205,7 +217,11 @@ impl SegmentWriter {
                     if int_option.is_indexed() {
                         for field_value in field_values {
                             term_buffer.set_field(field_value.field());
-                            term_buffer.set_u64(field_value.value().u64_value());
+                            let u64_val = field_value
+                                .value()
+                                .u64_value()
+                                .ok_or_else(make_schema_error)?;
+                            term_buffer.set_u64(u64_val);
                             multifield_postings.subscribe(doc_id, &term_buffer);
                         }
                     }
@@ -214,7 +230,11 @@ impl SegmentWriter {
                     if int_option.is_indexed() {
                         for field_value in field_values {
                             term_buffer.set_field(field_value.field());
-                            term_buffer.set_i64(field_value.value().date_value().timestamp());
+                            let date_val = field_value
+                                .value()
+                                .date_value()
+                                .ok_or_else(make_schema_error)?;
+                            term_buffer.set_i64(date_val.timestamp());
                             multifield_postings.subscribe(doc_id, &term_buffer);
                         }
                     }
@@ -223,7 +243,11 @@ impl SegmentWriter {
                     if int_option.is_indexed() {
                         for field_value in field_values {
                             term_buffer.set_field(field_value.field());
-                            term_buffer.set_i64(field_value.value().i64_value());
+                            let i64_val = field_value
+                                .value()
+                                .i64_value()
+                                .ok_or_else(make_schema_error)?;
+                            term_buffer.set_i64(i64_val);
                             multifield_postings.subscribe(doc_id, &term_buffer);
                         }
                     }
@@ -232,13 +256,27 @@ impl SegmentWriter {
                     if int_option.is_indexed() {
                         for field_value in field_values {
                             term_buffer.set_field(field_value.field());
-                            term_buffer.set_f64(field_value.value().f64_value());
+                            let f64_val = field_value
+                                .value()
+                                .f64_value()
+                                .ok_or_else(make_schema_error)?;
+                            term_buffer.set_f64(f64_val);
                             multifield_postings.subscribe(doc_id, &term_buffer);
                         }
                     }
                 }
-                FieldType::Bytes => {
-                    // Do nothing. Bytes only supports fast fields.
+                FieldType::Bytes(ref option) => {
+                    if option.is_indexed() {
+                        for field_value in field_values {
+                            term_buffer.set_field(field_value.field());
+                            let bytes = field_value
+                                .value()
+                                .bytes_value()
+                                .ok_or_else(make_schema_error)?;
+                            term_buffer.set_bytes(bytes);
+                            self.multifield_postings.subscribe(doc_id, &term_buffer);
+                        }
+                    }
                 }
             }
         }

src/lib.rs

@@ -105,7 +105,7 @@ extern crate serde_json;
 extern crate log;
 
 #[macro_use]
-extern crate failure;
+extern crate thiserror;
 
 #[cfg(all(test, feature = "unstable"))]
 extern crate test;
@@ -134,7 +134,7 @@ mod core;
 mod indexer;
 
 #[allow(unused_doc_comments)]
-mod error;
+pub mod error;
 pub mod tokenizer;
 
 pub mod collector;
@@ -157,6 +157,7 @@ pub use self::snippet::{Snippet, SnippetGenerator};
 
 mod docset;
 pub use self::docset::{DocSet, TERMINATED};
+pub use crate::common::HasLen;
 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::{Index, IndexMeta, Searcher, Segment, SegmentId, SegmentMeta};
@@ -276,7 +277,7 @@ impl DocAddress {
 ///
 /// The id used for the segment is actually an ordinal
 /// in the list of `Segment`s held by a `Searcher`.
-#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
+#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
 pub struct DocAddress(pub SegmentLocalId, pub DocId);
 
 #[cfg(test)]
@@ -383,31 +384,23 @@ mod tests {
         let text_field = schema_builder.add_text_field("text", TEXT);
         let index = Index::create_in_ram(schema_builder.build());
         let mut index_writer = index.writer_for_tests()?;
-        {
-            index_writer.add_document(doc!(text_field=>"a b c"));
-            index_writer.commit()?;
-        }
-        {
-            index_writer.add_document(doc!(text_field=>"a"));
-            index_writer.add_document(doc!(text_field=>"a a"));
-            index_writer.commit()?;
-        }
-        {
-            index_writer.add_document(doc!(text_field=>"c"));
-            index_writer.commit()?;
-        }
-        {
-            let reader = index.reader()?;
-            let searcher = reader.searcher();
-            let term_a = Term::from_field_text(text_field, "a");
-            assert_eq!(searcher.doc_freq(&term_a), 3);
-            let term_b = Term::from_field_text(text_field, "b");
-            assert_eq!(searcher.doc_freq(&term_b), 1);
-            let term_c = Term::from_field_text(text_field, "c");
-            assert_eq!(searcher.doc_freq(&term_c), 2);
-            let term_d = Term::from_field_text(text_field, "d");
-            assert_eq!(searcher.doc_freq(&term_d), 0);
-        }
+        index_writer.add_document(doc!(text_field=>"a b c"));
+        index_writer.commit()?;
+        index_writer.add_document(doc!(text_field=>"a"));
+        index_writer.add_document(doc!(text_field=>"a a"));
+        index_writer.commit()?;
+        index_writer.add_document(doc!(text_field=>"c"));
+        index_writer.commit()?;
+        let reader = index.reader()?;
+        let searcher = reader.searcher();
+        let term_a = Term::from_field_text(text_field, "a");
+        assert_eq!(searcher.doc_freq(&term_a)?, 3);
+        let term_b = Term::from_field_text(text_field, "b");
+        assert_eq!(searcher.doc_freq(&term_b)?, 1);
+        let term_c = Term::from_field_text(text_field, "c");
+        assert_eq!(searcher.doc_freq(&term_c)?, 2);
+        let term_d = Term::from_field_text(text_field, "d");
+        assert_eq!(searcher.doc_freq(&term_d)?, 0);
         Ok(())
     }
 
@@ -504,13 +497,13 @@ mod tests {
             reader.reload()?;
             let searcher = reader.searcher();
             let segment_reader = searcher.segment_reader(0);
-            let inverted_index = segment_reader.inverted_index(text_field);
+            let inverted_index = segment_reader.inverted_index(text_field)?;
             assert!(inverted_index
-                .read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)?
                 .is_none());
             {
                 let mut postings = inverted_index
-                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
+                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert!(advance_undeleted(&mut postings, segment_reader));
                 assert_eq!(postings.doc(), 5);
@@ -518,7 +511,7 @@ mod tests {
             }
             {
                 let mut postings = inverted_index
-                    .read_postings(&term_b, IndexRecordOption::WithFreqsAndPositions)
+                    .read_postings(&term_b, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert!(advance_undeleted(&mut postings, segment_reader));
                 assert_eq!(postings.doc(), 3);
@@ -540,14 +533,14 @@ mod tests {
             reader.reload()?;
             let searcher = reader.searcher();
             let seg_reader = searcher.segment_reader(0);
-            let inverted_index = seg_reader.inverted_index(term_abcd.field());
+            let inverted_index = seg_reader.inverted_index(term_abcd.field())?;
 
             assert!(inverted_index
-                .read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)?
                 .is_none());
             {
                 let mut postings = inverted_index
-                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
+                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert!(advance_undeleted(&mut postings, seg_reader));
                 assert_eq!(postings.doc(), 5);
@@ -555,7 +548,7 @@ mod tests {
             }
             {
                 let mut postings = inverted_index
-                    .read_postings(&term_b, IndexRecordOption::WithFreqsAndPositions)
+                    .read_postings(&term_b, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert!(advance_undeleted(&mut postings, seg_reader));
                 assert_eq!(postings.doc(), 3);
@@ -577,19 +570,19 @@ mod tests {
             reader.reload()?;
             let searcher = reader.searcher();
             let segment_reader = searcher.segment_reader(0);
-            let inverted_index = segment_reader.inverted_index(term_abcd.field());
+            let inverted_index = segment_reader.inverted_index(term_abcd.field())?;
             assert!(inverted_index
-                .read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)?
                 .is_none());
             {
                 let mut postings = inverted_index
-                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
+                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert!(!advance_undeleted(&mut postings, segment_reader));
             }
             {
                 let mut postings = inverted_index
-                    .read_postings(&term_b, IndexRecordOption::WithFreqsAndPositions)
+                    .read_postings(&term_b, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert!(advance_undeleted(&mut postings, segment_reader));
                 assert_eq!(postings.doc(), 3);
@@ -599,7 +592,7 @@ mod tests {
             }
             {
                 let mut postings = inverted_index
-                    .read_postings(&term_c, IndexRecordOption::WithFreqsAndPositions)
+                    .read_postings(&term_c, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert!(advance_undeleted(&mut postings, segment_reader));
                 assert_eq!(postings.doc(), 4);
@@ -624,8 +617,8 @@ mod tests {
         let term = Term::from_field_u64(field, 1u64);
         let mut postings = searcher
             .segment_reader(0)
-            .inverted_index(term.field())
-            .read_postings(&term, IndexRecordOption::Basic)
+            .inverted_index(term.field())?
+            .read_postings(&term, IndexRecordOption::Basic)?
             .unwrap();
         assert_eq!(postings.doc(), 0);
         assert_eq!(postings.advance(), TERMINATED);
@@ -648,8 +641,8 @@ mod tests {
         let term = Term::from_field_i64(value_field, negative_val);
         let mut postings = searcher
             .segment_reader(0)
-            .inverted_index(term.field())
-            .read_postings(&term, IndexRecordOption::Basic)
+            .inverted_index(term.field())?
+            .read_postings(&term, IndexRecordOption::Basic)?
             .unwrap();
         assert_eq!(postings.doc(), 0);
         assert_eq!(postings.advance(), TERMINATED);
@@ -672,8 +665,8 @@ mod tests {
         let term = Term::from_field_f64(value_field, val);
         let mut postings = searcher
             .segment_reader(0)
-            .inverted_index(term.field())
-            .read_postings(&term, IndexRecordOption::Basic)
+            .inverted_index(term.field())?
+            .read_postings(&term, IndexRecordOption::Basic)?
             .unwrap();
         assert_eq!(postings.doc(), 0);
         assert_eq!(postings.advance(), TERMINATED);
@@ -693,7 +686,7 @@ mod tests {
         let reader = index.reader()?;
         let searcher = reader.searcher();
         let segment_reader = searcher.segment_reader(0);
-        let inverted_index = segment_reader.inverted_index(absent_field); //< should not panic
+        let inverted_index = segment_reader.inverted_index(absent_field)?;
         assert_eq!(inverted_index.terms().num_terms(), 0);
         Ok(())
     }
@@ -743,14 +736,14 @@ mod tests {
             let index_reader = index.reader()?;
             let searcher = index_reader.searcher();
             let reader = searcher.segment_reader(0);
-            let inverted_index = reader.inverted_index(text_field);
+            let inverted_index = reader.inverted_index(text_field)?;
             let term_abcd = Term::from_field_text(text_field, "abcd");
             assert!(inverted_index
-                .read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)?
                 .is_none());
             let term_af = Term::from_field_text(text_field, "af");
             let mut postings = inverted_index
-                .read_postings(&term_af, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term_af, IndexRecordOption::WithFreqsAndPositions)?
                 .unwrap();
             assert_eq!(postings.doc(), 0);
             assert_eq!(postings.term_freq(), 3);
@@ -842,11 +835,11 @@ mod tests {
                             text_field => "some other value",
                             other_text_field => "short");
         assert_eq!(document.len(), 3);
-        let values = document.get_all(text_field);
+        let values: Vec<&Value> = document.get_all(text_field).collect();
         assert_eq!(values.len(), 2);
         assert_eq!(values[0].text(), Some("tantivy"));
         assert_eq!(values[1].text(), Some("some other value"));
-        let values = document.get_all(other_text_field);
+        let values: Vec<&Value> = document.get_all(other_text_field).collect();
         assert_eq!(values.len(), 1);
         assert_eq!(values[0].text(), Some("short"));
     }

src/positions/mod.rs

@@ -38,11 +38,11 @@ const LONG_SKIP_INTERVAL: u64 = (LONG_SKIP_IN_BLOCKS * COMPRESSION_BLOCK_SIZE) a
 pub mod tests {
 
     use super::PositionSerializer;
-    use crate::directory::ReadOnlySource;
     use crate::positions::reader::PositionReader;
+    use crate::{common::HasLen, directory::FileSlice};
     use std::iter;
 
-    fn create_stream_buffer(vals: &[u32]) -> (ReadOnlySource, ReadOnlySource) {
+    fn create_stream_buffer(vals: &[u32]) -> (FileSlice, FileSlice) {
         let mut skip_buffer = vec![];
         let mut stream_buffer = vec![];
         {
@@ -53,10 +53,7 @@ pub mod tests {
             }
             serializer.close().unwrap();
         }
-        (
-            ReadOnlySource::from(stream_buffer),
-            ReadOnlySource::from(skip_buffer),
-        )
+        (FileSlice::from(stream_buffer), FileSlice::from(skip_buffer))
     }
 
     #[test]
@@ -65,7 +62,7 @@ pub mod tests {
         let (stream, skip) = create_stream_buffer(&v[..]);
         assert_eq!(skip.len(), 12);
         assert_eq!(stream.len(), 1168);
-        let mut position_reader = PositionReader::new(stream, skip, 0u64);
+        let mut position_reader = PositionReader::new(stream, skip, 0u64).unwrap();
         for &n in &[1, 10, 127, 128, 130, 312] {
             let mut v = vec![0u32; n];
             position_reader.read(0, &mut v[..]);
@@ -81,7 +78,7 @@ pub mod tests {
         let (stream, skip) = create_stream_buffer(&v[..]);
         assert_eq!(skip.len(), 12);
         assert_eq!(stream.len(), 1168);
-        let mut position_reader = PositionReader::new(stream, skip, 0u64);
+        let mut position_reader = PositionReader::new(stream, skip, 0u64).unwrap();
         for &offset in &[1u64, 10u64, 127u64, 128u64, 130u64, 312u64] {
             for &len in &[1, 10, 130, 500] {
                 let mut v = vec![0u32; len];
@@ -100,7 +97,7 @@ pub mod tests {
         assert_eq!(skip.len(), 12);
         assert_eq!(stream.len(), 1168);
 
-        let mut position_reader = PositionReader::new(stream, skip, 0u64);
+        let mut position_reader = PositionReader::new(stream, skip, 0u64).unwrap();
         let mut buf = [0u32; 7];
         let mut c = 0;
 
@@ -122,7 +119,7 @@ pub mod tests {
         let (stream, skip) = create_stream_buffer(&v[..]);
         assert_eq!(skip.len(), 15_749);
         assert_eq!(stream.len(), 4_987_872);
-        let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), 0);
+        let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), 0).unwrap();
         let mut buf = [0u32; 256];
         position_reader.read(128, &mut buf);
         for i in 0..256 {
@@ -142,7 +139,8 @@ pub mod tests {
         assert_eq!(skip.len(), 15_749);
         assert_eq!(stream.len(), 4_987_872);
         let mut buf = [0u32; 1];
-        let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), 200_000);
+        let mut position_reader =
+            PositionReader::new(stream.clone(), skip.clone(), 200_000).unwrap();
         position_reader.read(230, &mut buf);
         position_reader.read(9, &mut buf);
     }
@@ -157,7 +155,7 @@ pub mod tests {
         }
         let (stream, skip) = create_stream_buffer(&v[..]);
         let mut buf = Vec::new();
-        let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), 0);
+        let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), 0).unwrap();
         let mut offset = 0;
         for i in 1..24 {
             buf.resize(i, 0);
@@ -175,7 +173,7 @@ pub mod tests {
         let (stream, skip) = create_stream_buffer(&v[..]);
         assert_eq!(skip.len(), 15_749);
         assert_eq!(stream.len(), 1_000_000);
-        let mut position_reader = PositionReader::new(stream, skip, 128 * 1024);
+        let mut position_reader = PositionReader::new(stream, skip, 128 * 1024).unwrap();
         let mut buf = [0u32; 1];
         position_reader.read(0, &mut buf);
         assert_eq!(buf[0], CONST_VAL);
@@ -194,7 +192,8 @@ pub mod tests {
             128 * 1024 + 7,
             128 * 10 * 1024 + 10,
         ] {
-            let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), offset);
+            let mut position_reader =
+                PositionReader::new(stream.clone(), skip.clone(), offset).unwrap();
             let mut buf = [0u32; 1];
             position_reader.read(0, &mut buf);
             assert_eq!(buf[0], offset as u32);

src/positions/reader.rs

@@ -1,8 +1,13 @@
+use std::io;
+
 use crate::common::{BinarySerializable, FixedSize};
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
+use crate::directory::OwnedBytes;
 use crate::positions::COMPRESSION_BLOCK_SIZE;
 use crate::positions::LONG_SKIP_INTERVAL;
 use crate::positions::LONG_SKIP_IN_BLOCKS;
+use bitpacking::{BitPacker, BitPacker4x};
+
 /// Positions works as a long sequence of compressed block.
 /// All terms are chained one after the other.
 ///
@@ -23,28 +28,28 @@ use crate::positions::LONG_SKIP_IN_BLOCKS;
 /// A given block obviously takes `(128 x  num_bit_for_the_block / num_bits_in_a_byte)`,
 /// so skipping a block without decompressing it is just a matter of advancing that many
 /// bytes.
-use bitpacking::{BitPacker, BitPacker4x};
-use owned_read::OwnedRead;
 
 struct Positions {
     bit_packer: BitPacker4x,
-    skip_source: ReadOnlySource,
-    position_source: ReadOnlySource,
-    long_skip_source: ReadOnlySource,
+    skip_file: FileSlice,
+    position_file: FileSlice,
+    long_skip_data: OwnedBytes,
 }
 
 impl Positions {
-    pub fn new(position_source: ReadOnlySource, skip_source: ReadOnlySource) -> Positions {
-        let (body, footer) = skip_source.split_from_end(u32::SIZE_IN_BYTES);
-        let num_long_skips = u32::deserialize(&mut footer.as_slice()).expect("Index corrupted");
-        let (skip_source, long_skip_source) =
+    pub fn new(position_file: FileSlice, skip_file: FileSlice) -> io::Result<Positions> {
+        let (body, footer) = skip_file.split_from_end(u32::SIZE_IN_BYTES);
+        let footer_data = footer.read_bytes()?;
+        let num_long_skips = u32::deserialize(&mut footer_data.as_slice())?;
+        let (skip_file, long_skip_file) =
             body.split_from_end(u64::SIZE_IN_BYTES * (num_long_skips as usize));
-        Positions {
+        let long_skip_data = long_skip_file.read_bytes()?;
+        Ok(Positions {
             bit_packer: BitPacker4x::new(),
-            skip_source,
-            long_skip_source,
-            position_source,
-        }
+            skip_file,
+            long_skip_data,
+            position_file,
+        })
     }
 
     /// Returns the offset of the block associated to the given `long_skip_id`.
@@ -54,19 +59,23 @@ impl Positions {
         if long_skip_id == 0 {
             return 0;
         }
-        let long_skip_slice = self.long_skip_source.as_slice();
+        let long_skip_slice = self.long_skip_data.as_slice();
         let mut long_skip_blocks: &[u8] = &long_skip_slice[(long_skip_id - 1) * 8..][..8];
         u64::deserialize(&mut long_skip_blocks).expect("Index corrupted")
     }
 
-    fn reader(&self, offset: u64) -> PositionReader {
+    fn reader(&self, offset: u64) -> io::Result<PositionReader> {
         let long_skip_id = (offset / LONG_SKIP_INTERVAL) as usize;
         let offset_num_bytes: u64 = self.long_skip(long_skip_id);
-        let mut position_read = OwnedRead::new(self.position_source.clone());
-        position_read.advance(offset_num_bytes as usize);
-        let mut skip_read = OwnedRead::new(self.skip_source.clone());
-        skip_read.advance(long_skip_id * LONG_SKIP_IN_BLOCKS);
-        PositionReader {
+        let position_read = self
+            .position_file
+            .slice_from(offset_num_bytes as usize)
+            .read_bytes()?;
+        let skip_read = self
+            .skip_file
+            .slice_from(long_skip_id * LONG_SKIP_IN_BLOCKS)
+            .read_bytes()?;
+        Ok(PositionReader {
             bit_packer: self.bit_packer,
             skip_read,
             position_read,
@@ -74,14 +83,14 @@ impl Positions {
             block_offset: std::i64::MAX as u64,
             anchor_offset: (long_skip_id as u64) * LONG_SKIP_INTERVAL,
             abs_offset: offset,
-        }
+        })
     }
 }
 
 #[derive(Clone)]
 pub struct PositionReader {
-    skip_read: OwnedRead,
-    position_read: OwnedRead,
+    skip_read: OwnedBytes,
+    position_read: OwnedBytes,
     bit_packer: BitPacker4x,
     buffer: Box<[u32; COMPRESSION_BLOCK_SIZE]>,
 
@@ -93,11 +102,12 @@ pub struct PositionReader {
 
 impl PositionReader {
     pub fn new(
-        position_source: ReadOnlySource,
-        skip_source: ReadOnlySource,
+        position_file: FileSlice,
+        skip_file: FileSlice,
         offset: u64,
-    ) -> PositionReader {
-        Positions::new(position_source, skip_source).reader(offset)
+    ) -> io::Result<PositionReader> {
+        let positions = Positions::new(position_file, skip_file)?;
+        positions.reader(offset)
     }
 
     fn advance_num_blocks(&mut self, num_blocks: usize) {
@@ -131,7 +141,7 @@ impl PositionReader {
             self.advance_num_blocks(num_blocks_to_skip);
             self.anchor_offset = offset - (offset % COMPRESSION_BLOCK_SIZE as u64);
             self.block_offset = self.anchor_offset;
-            let num_bits = self.skip_read.get(0);
+            let num_bits = self.skip_read.as_slice()[0];
             self.bit_packer
                 .decompress(self.position_read.as_ref(), self.buffer.as_mut(), num_bits);
         } else {
@@ -141,7 +151,7 @@ impl PositionReader {
             self.anchor_offset = self.block_offset;
         }
 
-        let mut num_bits = self.skip_read.get(0);
+        let mut num_bits = self.skip_read.as_slice()[0];
         let mut position_data = self.position_read.as_ref();
 
         for i in 1.. {
@@ -155,7 +165,7 @@ impl PositionReader {
             output = &mut output[remaining_in_block..];
             offset += remaining_in_block as u64;
             position_data = &position_data[(num_bits as usize * COMPRESSION_BLOCK_SIZE / 8)..];
-            num_bits = self.skip_read.get(i);
+            num_bits = self.skip_read.as_slice()[i];
             self.bit_packer
                 .decompress(position_data, self.buffer.as_mut(), num_bits);
             self.block_offset += COMPRESSION_BLOCK_SIZE as u64;

src/postings/block_segment_postings.rs

@@ -1,5 +1,8 @@
+use std::io;
+
 use crate::common::{BinarySerializable, VInt};
-use crate::directory::ReadOnlySource;
+use crate::directory::FileSlice;
+use crate::directory::OwnedBytes;
 use crate::fieldnorm::FieldNormReader;
 use crate::postings::compression::{
     AlignedBuffer, BlockDecoder, VIntDecoder, COMPRESSION_BLOCK_SIZE,
@@ -34,7 +37,7 @@ pub struct BlockSegmentPostings {
 
     doc_freq: u32,
 
-    data: ReadOnlySource,
+    data: OwnedBytes,
     pub(crate) skip_reader: SkipReader,
 }
 
@@ -72,37 +75,34 @@ fn decode_vint_block(
 
 fn split_into_skips_and_postings(
     doc_freq: u32,
-    data: ReadOnlySource,
-) -> (Option<ReadOnlySource>, ReadOnlySource) {
+    mut bytes: OwnedBytes,
+) -> (Option<OwnedBytes>, OwnedBytes) {
     if doc_freq < COMPRESSION_BLOCK_SIZE as u32 {
-        return (None, data);
+        return (None, bytes);
     }
-    let mut data_byte_arr = data.as_slice();
-    let skip_len = VInt::deserialize(&mut data_byte_arr)
-        .expect("Data corrupted")
-        .0 as usize;
-    let vint_len = data.len() - data_byte_arr.len();
-    let (skip_data, postings_data) = data.slice_from(vint_len).split(skip_len);
+    let skip_len = VInt::deserialize(&mut bytes).expect("Data corrupted").0 as usize;
+    let (skip_data, postings_data) = bytes.split(skip_len);
     (Some(skip_data), postings_data)
 }
 
 impl BlockSegmentPostings {
-    pub(crate) fn from_data(
+    pub(crate) fn open(
         doc_freq: u32,
-        data: ReadOnlySource,
+        data: FileSlice,
         record_option: IndexRecordOption,
         requested_option: IndexRecordOption,
-    ) -> BlockSegmentPostings {
+    ) -> io::Result<BlockSegmentPostings> {
         let freq_reading_option = match (record_option, requested_option) {
             (IndexRecordOption::Basic, _) => FreqReadingOption::NoFreq,
             (_, IndexRecordOption::Basic) => FreqReadingOption::SkipFreq,
             (_, _) => FreqReadingOption::ReadFreq,
         };
 
-        let (skip_data_opt, postings_data) = split_into_skips_and_postings(doc_freq, data);
+        let (skip_data_opt, postings_data) =
+            split_into_skips_and_postings(doc_freq, data.read_bytes()?);
         let skip_reader = match skip_data_opt {
             Some(skip_data) => SkipReader::new(skip_data, doc_freq, record_option),
-            None => SkipReader::new(ReadOnlySource::empty(), doc_freq, record_option),
+            None => SkipReader::new(OwnedBytes::empty(), doc_freq, record_option),
         };
 
         let mut block_segment_postings = BlockSegmentPostings {
@@ -116,7 +116,7 @@ impl BlockSegmentPostings {
             skip_reader,
         };
         block_segment_postings.load_block();
-        block_segment_postings
+        Ok(block_segment_postings)
     }
 
     /// Returns the block_max_score for the current block.
@@ -172,15 +172,15 @@ impl BlockSegmentPostings {
     // # Warning
     //
     // This does not reset the positions list.
-    pub(crate) fn reset(&mut self, doc_freq: u32, postings_data: ReadOnlySource) {
+    pub(crate) fn reset(&mut self, doc_freq: u32, postings_data: OwnedBytes) {
         let (skip_data_opt, postings_data) = split_into_skips_and_postings(doc_freq, postings_data);
-        self.data = ReadOnlySource::new(postings_data);
+        self.data = postings_data;
         self.block_max_score_cache = None;
         self.loaded_offset = std::usize::MAX;
         if let Some(skip_data) = skip_data_opt {
             self.skip_reader.reset(skip_data, doc_freq);
         } else {
-            self.skip_reader.reset(ReadOnlySource::empty(), doc_freq);
+            self.skip_reader.reset(OwnedBytes::empty(), doc_freq);
         }
         self.doc_freq = doc_freq;
         self.load_block();
@@ -344,8 +344,8 @@ impl BlockSegmentPostings {
             freq_reading_option: FreqReadingOption::NoFreq,
             block_max_score_cache: None,
             doc_freq: 0,
-            data: ReadOnlySource::new(vec![]),
-            skip_reader: SkipReader::new(ReadOnlySource::new(vec![]), 0, IndexRecordOption::Basic),
+            data: OwnedBytes::empty(),
+            skip_reader: SkipReader::new(OwnedBytes::empty(), 0, IndexRecordOption::Basic),
         }
     }
 }
@@ -467,10 +467,12 @@ mod tests {
         index_writer.commit().unwrap();
         let searcher = index.reader().unwrap().searcher();
         let segment_reader = searcher.segment_reader(0);
-        let inverted_index = segment_reader.inverted_index(int_field);
+        let inverted_index = segment_reader.inverted_index(int_field).unwrap();
         let term = Term::from_field_u64(int_field, 0u64);
         let term_info = inverted_index.get_term_info(&term).unwrap();
-        inverted_index.read_block_postings_from_terminfo(&term_info, IndexRecordOption::Basic)
+        inverted_index
+            .read_block_postings_from_terminfo(&term_info, IndexRecordOption::Basic)
+            .unwrap()
     }
 
     #[test]
@@ -491,37 +493,38 @@ mod tests {
     }
 
     #[test]
-    fn test_reset_block_segment_postings() {
+    fn test_reset_block_segment_postings() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let int_field = schema_builder.add_u64_field("id", INDEXED);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_for_tests().unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         // create two postings list, one containg even number,
         // the other containing odd numbers.
         for i in 0..6 {
             let doc = doc!(int_field=> (i % 2) as u64);
             index_writer.add_document(doc);
         }
-        index_writer.commit().unwrap();
-        let searcher = index.reader().unwrap().searcher();
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
         let segment_reader = searcher.segment_reader(0);
 
         let mut block_segments;
         {
             let term = Term::from_field_u64(int_field, 0u64);
-            let inverted_index = segment_reader.inverted_index(int_field);
+            let inverted_index = segment_reader.inverted_index(int_field)?;
             let term_info = inverted_index.get_term_info(&term).unwrap();
             block_segments = inverted_index
-                .read_block_postings_from_terminfo(&term_info, IndexRecordOption::Basic);
+                .read_block_postings_from_terminfo(&term_info, IndexRecordOption::Basic)?;
         }
         assert_eq!(block_segments.docs(), &[0, 2, 4]);
         {
             let term = Term::from_field_u64(int_field, 1u64);
-            let inverted_index = segment_reader.inverted_index(int_field);
+            let inverted_index = segment_reader.inverted_index(int_field)?;
             let term_info = inverted_index.get_term_info(&term).unwrap();
-            inverted_index.reset_block_postings_from_terminfo(&term_info, &mut block_segments);
+            inverted_index.reset_block_postings_from_terminfo(&term_info, &mut block_segments)?;
         }
         assert_eq!(block_segments.docs(), &[1, 3, 5]);
+        Ok(())
     }
 }

src/postings/mod.rs

@@ -28,8 +28,6 @@ pub use self::segment_postings::SegmentPostings;
 
 pub(crate) use self::stacker::compute_table_size;
 
-pub use crate::common::HasLen;
-
 pub(crate) type UnorderedTermId = u64;
 
 #[cfg_attr(feature = "cargo-clippy", allow(clippy::enum_variant_names))]
@@ -42,8 +40,8 @@ pub(crate) enum FreqReadingOption {
 
 #[cfg(test)]
 pub mod tests {
-
-    use super::*;
+    use super::InvertedIndexSerializer;
+    use super::Postings;
     use crate::core::Index;
     use crate::core::SegmentComponent;
     use crate::core::SegmentReader;
@@ -58,6 +56,7 @@ pub mod tests {
     use crate::schema::{IndexRecordOption, TextFieldIndexing};
     use crate::tokenizer::{SimpleTokenizer, MAX_TOKEN_LEN};
     use crate::DocId;
+    use crate::HasLen;
     use crate::Score;
     use once_cell::sync::Lazy;
     use rand::rngs::StdRng;
@@ -101,12 +100,12 @@ pub mod tests {
         index_writer.commit()?;
 
         let searcher = index.reader()?.searcher();
-        let inverted_index = searcher.segment_reader(0u32).inverted_index(title);
+        let inverted_index = searcher.segment_reader(0u32).inverted_index(title)?;
         let term = Term::from_field_text(title, "abc");
         let mut positions = Vec::new();
         {
             let mut postings = inverted_index
-                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)?
                 .unwrap();
             assert_eq!(postings.doc(), 0);
             postings.positions(&mut positions);
@@ -120,7 +119,7 @@ pub mod tests {
         }
         {
             let mut postings = inverted_index
-                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)?
                 .unwrap();
             assert_eq!(postings.doc(), 0);
             assert_eq!(postings.advance(), 1);
@@ -129,7 +128,7 @@ pub mod tests {
         }
         {
             let mut postings = inverted_index
-                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)?
                 .unwrap();
             assert_eq!(postings.seek(1), 1);
             assert_eq!(postings.doc(), 1);
@@ -138,7 +137,7 @@ pub mod tests {
         }
         {
             let mut postings = inverted_index
-                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)?
                 .unwrap();
             assert_eq!(postings.seek(1002), 1002);
             assert_eq!(postings.doc(), 1002);
@@ -147,7 +146,7 @@ pub mod tests {
         }
         {
             let mut postings = inverted_index
-                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
+                .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)?
                 .unwrap();
             assert_eq!(postings.seek(100), 100);
             assert_eq!(postings.seek(1002), 1002);
@@ -159,7 +158,7 @@ pub mod tests {
     }
 
     #[test]
-    pub fn test_drop_token_that_are_too_long() {
+    pub fn test_drop_token_that_are_too_long() -> crate::Result<()> {
         let ok_token_text: String = iter::repeat('A').take(MAX_TOKEN_LEN).collect();
         let mut exceeding_token_text: String = iter::repeat('A').take(MAX_TOKEN_LEN + 1).collect();
         exceeding_token_text.push_str(" hello");
@@ -184,7 +183,7 @@ pub mod tests {
             reader.reload().unwrap();
             let searcher = reader.searcher();
             let segment_reader = searcher.segment_reader(0u32);
-            let inverted_index = segment_reader.inverted_index(text_field);
+            let inverted_index = segment_reader.inverted_index(text_field)?;
             assert_eq!(inverted_index.terms().num_terms(), 1);
             let mut bytes = vec![];
             assert!(inverted_index.terms().ord_to_term(0, &mut bytes));
@@ -196,12 +195,13 @@ pub mod tests {
             reader.reload().unwrap();
             let searcher = reader.searcher();
             let segment_reader = searcher.segment_reader(1u32);
-            let inverted_index = segment_reader.inverted_index(text_field);
+            let inverted_index = segment_reader.inverted_index(text_field)?;
             assert_eq!(inverted_index.terms().num_terms(), 1);
             let mut bytes = vec![];
             assert!(inverted_index.terms().ord_to_term(0, &mut bytes));
             assert_eq!(&bytes[..], ok_token_text.as_bytes());
         }
+        Ok(())
     }
 
     #[test]
@@ -261,15 +261,15 @@ pub mod tests {
             {
                 let term_a = Term::from_field_text(text_field, "abcdef");
                 assert!(segment_reader
-                    .inverted_index(term_a.field())
-                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
+                    .inverted_index(term_a.field())?
+                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)?
                     .is_none());
             }
             {
                 let term_a = Term::from_field_text(text_field, "a");
                 let mut postings_a = segment_reader
-                    .inverted_index(term_a.field())
-                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
+                    .inverted_index(term_a.field())?
+                    .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert_eq!(postings_a.len(), 1000);
                 assert_eq!(postings_a.doc(), 0);
@@ -291,8 +291,8 @@ pub mod tests {
             {
                 let term_e = Term::from_field_text(text_field, "e");
                 let mut postings_e = segment_reader
-                    .inverted_index(term_e.field())
-                    .read_postings(&term_e, IndexRecordOption::WithFreqsAndPositions)
+                    .inverted_index(term_e.field())?
+                    .read_postings(&term_e, IndexRecordOption::WithFreqsAndPositions)?
                     .unwrap();
                 assert_eq!(postings_e.len(), 1000 - 2);
                 for i in 2u32..1000u32 {
@@ -312,7 +312,7 @@ pub mod tests {
     }
 
     #[test]
-    pub fn test_position_and_fieldnorm2() {
+    pub fn test_position_and_fieldnorm2() -> crate::Result<()> {
         let mut positions: Vec<u32> = Vec::new();
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
@@ -328,16 +328,17 @@ pub mod tests {
         let searcher = index.reader().unwrap().searcher();
         let segment_reader = searcher.segment_reader(0);
         let mut postings = segment_reader
-            .inverted_index(text_field)
-            .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
+            .inverted_index(text_field)?
+            .read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)?
             .unwrap();
         assert_eq!(postings.doc(), 1u32);
         postings.positions(&mut positions);
         assert_eq!(&positions[..], &[1u32, 4]);
+        Ok(())
     }
 
     #[test]
-    fn test_skip_next() {
+    fn test_skip_next() -> crate::Result<()> {
         let term_0 = Term::from_field_u64(Field::from_field_id(0), 0);
         let term_1 = Term::from_field_u64(Field::from_field_id(0), 1);
         let term_2 = Term::from_field_u64(Field::from_field_id(0), 2);
@@ -348,10 +349,9 @@ pub mod tests {
             let mut schema_builder = Schema::builder();
             let value_field = schema_builder.add_u64_field("value", INDEXED);
             let schema = schema_builder.build();
-
             let index = Index::create_in_ram(schema);
             {
-                let mut index_writer = index.writer_for_tests().unwrap();
+                let mut index_writer = index.writer_for_tests()?;
                 for i in 0u64..num_docs as u64 {
                     let doc = doc!(value_field => 2u64, value_field => i % 2u64);
                     index_writer.add_document(doc);
@@ -360,15 +360,15 @@ pub mod tests {
             }
             index
         };
-        let searcher = index.reader().unwrap().searcher();
+        let searcher = index.reader()?.searcher();
         let segment_reader = searcher.segment_reader(0);
 
         // check that the basic usage works
         for i in 0..num_docs - 1 {
             for j in i + 1..num_docs {
                 let mut segment_postings = segment_reader
-                    .inverted_index(term_2.field())
-                    .read_postings(&term_2, IndexRecordOption::Basic)
+                    .inverted_index(term_2.field())?
+                    .read_postings(&term_2, IndexRecordOption::Basic)?
                     .unwrap();
                 assert_eq!(segment_postings.seek(i), i);
                 assert_eq!(segment_postings.doc(), i);
@@ -380,8 +380,8 @@ pub mod tests {
 
         {
             let mut segment_postings = segment_reader
-                .inverted_index(term_2.field())
-                .read_postings(&term_2, IndexRecordOption::Basic)
+                .inverted_index(term_2.field())?
+                .read_postings(&term_2, IndexRecordOption::Basic)?
                 .unwrap();
 
             // check that `skip_next` advances the iterator
@@ -400,8 +400,8 @@ pub mod tests {
         // check that filtering works
         {
             let mut segment_postings = segment_reader
-                .inverted_index(term_0.field())
-                .read_postings(&term_0, IndexRecordOption::Basic)
+                .inverted_index(term_0.field())?
+                .read_postings(&term_0, IndexRecordOption::Basic)?
                 .unwrap();
 
             for i in 0..num_docs / 2 {
@@ -410,8 +410,8 @@ pub mod tests {
             }
 
             let mut segment_postings = segment_reader
-                .inverted_index(term_0.field())
-                .read_postings(&term_0, IndexRecordOption::Basic)
+                .inverted_index(term_0.field())?
+                .read_postings(&term_0, IndexRecordOption::Basic)?
                 .unwrap();
 
             for i in 0..num_docs / 2 - 1 {
@@ -422,19 +422,19 @@ pub mod tests {
 
         // delete some of the documents
         {
-            let mut index_writer = index.writer_for_tests().unwrap();
+            let mut index_writer = index.writer_for_tests()?;
             index_writer.delete_term(term_0);
             assert!(index_writer.commit().is_ok());
         }
-        let searcher = index.reader().unwrap().searcher();
+        let searcher = index.reader()?.searcher();
         assert_eq!(searcher.segment_readers().len(), 1);
         let segment_reader = searcher.segment_reader(0);
 
         // make sure seeking still works
         for i in 0..num_docs {
             let mut segment_postings = segment_reader
-                .inverted_index(term_2.field())
-                .read_postings(&term_2, IndexRecordOption::Basic)
+                .inverted_index(term_2.field())?
+                .read_postings(&term_2, IndexRecordOption::Basic)?
                 .unwrap();
 
             if i % 2 == 0 {
@@ -450,8 +450,8 @@ pub mod tests {
         // now try with a longer sequence
         {
             let mut segment_postings = segment_reader
-                .inverted_index(term_2.field())
-                .read_postings(&term_2, IndexRecordOption::Basic)
+                .inverted_index(term_2.field())?
+                .read_postings(&term_2, IndexRecordOption::Basic)?
                 .unwrap();
 
             let mut last = 2; // start from 5 to avoid seeking to 3 twice
@@ -476,20 +476,19 @@ pub mod tests {
 
         // delete everything else
         {
-            let mut index_writer = index.writer_for_tests().unwrap();
+            let mut index_writer = index.writer_for_tests()?;
             index_writer.delete_term(term_1);
             assert!(index_writer.commit().is_ok());
         }
-        let searcher = index.reader().unwrap().searcher();
+        let searcher = index.reader()?.searcher();
 
         // finally, check that it's empty
         {
-            let searchable_segment_ids = index
-                .searchable_segment_ids()
-                .expect("could not get index segment ids");
+            let searchable_segment_ids = index.searchable_segment_ids()?;
             assert!(searchable_segment_ids.is_empty());
             assert_eq!(searcher.num_docs(), 0);
         }
+        Ok(())
     }
 
     pub static TERM_A: Lazy<Term> = Lazy::new(|| {
@@ -621,7 +620,7 @@ mod bench {
         b.iter(|| {
             let mut segment_postings = segment_reader
                 .inverted_index(TERM_A.field())
-                .read_postings(&*TERM_A, IndexRecordOption::Basic)
+                .read_postings(&*TERM_A, IndexRecordOption::Basic)?
                 .unwrap();
             while segment_postings.advance() != TERMINATED {}
         });
@@ -636,18 +635,22 @@ mod bench {
             let segment_postings_a = segment_reader
                 .inverted_index(TERM_A.field())
                 .read_postings(&*TERM_A, IndexRecordOption::Basic)
+                .unwrap()
                 .unwrap();
             let segment_postings_b = segment_reader
                 .inverted_index(TERM_B.field())
                 .read_postings(&*TERM_B, IndexRecordOption::Basic)
+                .unwrap()
                 .unwrap();
             let segment_postings_c = segment_reader
                 .inverted_index(TERM_C.field())
                 .read_postings(&*TERM_C, IndexRecordOption::Basic)
+                .unwrap()
                 .unwrap();
             let segment_postings_d = segment_reader
                 .inverted_index(TERM_D.field())
                 .read_postings(&*TERM_D, IndexRecordOption::Basic)
+                .unwrap()
                 .unwrap();
             let mut intersection = Intersection::new(vec![
                 segment_postings_a,
@@ -668,6 +671,7 @@ mod bench {
         let mut segment_postings = segment_reader
             .inverted_index(TERM_A.field())
             .read_postings(&*TERM_A, IndexRecordOption::Basic)
+            .unwrap()
             .unwrap();
 
         let mut existing_docs = Vec::new();

src/postings/postings_writer.rs

@@ -38,12 +38,8 @@ fn posting_from_field_entry(field_entry: &FieldEntry) -> Box<dyn PostingsWriter>
         | FieldType::I64(_)
         | FieldType::F64(_)
         | FieldType::Date(_)
+        | FieldType::Bytes(_)
         | FieldType::HierarchicalFacet => SpecializedPostingsWriter::<NothingRecorder>::new_boxed(),
-        FieldType::Bytes => {
-            // FieldType::Bytes cannot actually be indexed.
-            // TODO fix during the indexer refactoring described in #276
-            SpecializedPostingsWriter::<NothingRecorder>::new_boxed()
-        }
     }
 }
 
@@ -161,11 +157,12 @@ impl MultiFieldPostingsWriter {
                     unordered_term_mappings.insert(field, mapping);
                 }
                 FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => {}
-                FieldType::Bytes => {}
+                FieldType::Bytes(_) => {}
             }
 
-            let postings_writer = &self.per_field_postings_writers[field.field_id() as usize];
-            let fieldnorm_reader = fieldnorm_readers.get_field(field);
+            let postings_writer =
+                self.per_field_postings_writers[field.field_id() as usize].as_ref();
+            let fieldnorm_reader = fieldnorm_readers.get_field(field)?;
             let mut field_serializer = serializer.new_field(
                 field,
                 postings_writer.total_num_tokens(),

src/postings/segment_postings.rs

@@ -1,21 +1,16 @@
 use crate::common::HasLen;
-
+use crate::directory::FileSlice;
 use crate::docset::DocSet;
+use crate::fastfield::DeleteBitSet;
 use crate::positions::PositionReader;
-
 use crate::postings::compression::COMPRESSION_BLOCK_SIZE;
 use crate::postings::serializer::PostingsSerializer;
 use crate::postings::BlockSearcher;
-
+use crate::postings::BlockSegmentPostings;
 use crate::postings::Postings;
-
 use crate::schema::IndexRecordOption;
 use crate::{DocId, TERMINATED};
 
-use crate::directory::ReadOnlySource;
-use crate::fastfield::DeleteBitSet;
-use crate::postings::BlockSegmentPostings;
-
 /// `SegmentPostings` represents the inverted list or postings associated to
 /// a term in a `Segment`.
 ///
@@ -77,7 +72,7 @@ impl SegmentPostings {
         let mut buffer = Vec::new();
         {
             let mut postings_serializer =
-                PostingsSerializer::new(&mut buffer, 0.0, false, false, None);
+                PostingsSerializer::new(&mut buffer, 0.0, IndexRecordOption::Basic, None);
             postings_serializer.new_term(docs.len() as u32);
             for &doc in docs {
                 postings_serializer.write_doc(doc, 1u32);
@@ -86,12 +81,13 @@ impl SegmentPostings {
                 .close_term(docs.len() as u32)
                 .expect("In memory Serialization should never fail.");
         }
-        let block_segment_postings = BlockSegmentPostings::from_data(
+        let block_segment_postings = BlockSegmentPostings::open(
             docs.len() as u32,
-            ReadOnlySource::from(buffer),
+            FileSlice::from(buffer),
             IndexRecordOption::Basic,
             IndexRecordOption::Basic,
-        );
+        )
+        .unwrap();
         SegmentPostings::from_block_postings(block_segment_postings, None)
     }
 
@@ -120,8 +116,7 @@ impl SegmentPostings {
         let mut postings_serializer = PostingsSerializer::new(
             &mut buffer,
             average_field_norm,
-            true,
-            false,
+            IndexRecordOption::WithFreqs,
             fieldnorm_reader,
         );
         postings_serializer.new_term(doc_and_tfs.len() as u32);
@@ -131,12 +126,13 @@ impl SegmentPostings {
         postings_serializer
             .close_term(doc_and_tfs.len() as u32)
             .unwrap();
-        let block_segment_postings = BlockSegmentPostings::from_data(
+        let block_segment_postings = BlockSegmentPostings::open(
             doc_and_tfs.len() as u32,
-            ReadOnlySource::from(buffer),
+            FileSlice::from(buffer),
             IndexRecordOption::WithFreqs,
             IndexRecordOption::WithFreqs,
-        );
+        )
+        .unwrap();
         SegmentPostings::from_block_postings(block_segment_postings, None)
     }
 
@@ -204,7 +200,7 @@ impl DocSet for SegmentPostings {
     }
 
     /// Return the current document's `DocId`.
-    #[inline]
+    #[inline(always)]
     fn doc(&self) -> DocId {
         self.block_cursor.doc(self.cur)
     }

src/postings/serializer.rs

@@ -8,8 +8,8 @@ use crate::positions::PositionSerializer;
 use crate::postings::compression::{BlockEncoder, VIntEncoder, COMPRESSION_BLOCK_SIZE};
 use crate::postings::skip::SkipSerializer;
 use crate::query::BM25Weight;
-use crate::schema::Schema;
 use crate::schema::{Field, FieldEntry, FieldType};
+use crate::schema::{IndexRecordOption, Schema};
 use crate::termdict::{TermDictionaryBuilder, TermOrdinal};
 use crate::{DocId, Score};
 use std::cmp::Ordering;
@@ -143,30 +143,24 @@ impl<'a> FieldSerializer<'a> {
         fieldnorm_reader: Option<FieldNormReader>,
     ) -> io::Result<FieldSerializer<'a>> {
         total_num_tokens.serialize(postings_write)?;
-        let (term_freq_enabled, position_enabled): (bool, bool) = match field_type {
+        let mode = match field_type {
             FieldType::Str(ref text_options) => {
                 if let Some(text_indexing_options) = text_options.get_indexing_options() {
-                    let index_option = text_indexing_options.index_option();
-                    (index_option.has_freq(), index_option.has_positions())
+                    text_indexing_options.index_option()
                 } else {
-                    (false, false)
+                    IndexRecordOption::Basic
                 }
             }
-            _ => (false, false),
+            _ => IndexRecordOption::Basic,
         };
         let term_dictionary_builder = TermDictionaryBuilder::create(term_dictionary_write)?;
         let average_fieldnorm = fieldnorm_reader
             .as_ref()
             .map(|ff_reader| (total_num_tokens as Score / ff_reader.num_docs() as Score))
             .unwrap_or(0.0);
-        let postings_serializer = PostingsSerializer::new(
-            postings_write,
-            average_fieldnorm,
-            term_freq_enabled,
-            position_enabled,
-            fieldnorm_reader,
-        );
-        let positions_serializer_opt = if position_enabled {
+        let postings_serializer =
+            PostingsSerializer::new(postings_write, average_fieldnorm, mode, fieldnorm_reader);
+        let positions_serializer_opt = if mode.has_positions() {
             Some(PositionSerializer::new(positions_write, positionsidx_write))
         } else {
             None
@@ -323,29 +317,22 @@ pub struct PostingsSerializer<W: Write> {
     postings_write: Vec<u8>,
     skip_write: SkipSerializer,
 
-    termfreq_enabled: bool,
-    termfreq_sum_enabled: bool,
+    mode: IndexRecordOption,
     fieldnorm_reader: Option<FieldNormReader>,
 
     bm25_weight: Option<BM25Weight>,
 
-    num_docs: u32, // Number of docs in the segment
     avg_fieldnorm: Score, // Average number of term in the field for that segment.
-                   // this value is used to compute the block wand information.
+                          // this value is used to compute the block wand information.
 }
 
 impl<W: Write> PostingsSerializer<W> {
     pub fn new(
         write: W,
         avg_fieldnorm: Score,
-        termfreq_enabled: bool,
-        termfreq_sum_enabled: bool,
+        mode: IndexRecordOption,
         fieldnorm_reader: Option<FieldNormReader>,
     ) -> PostingsSerializer<W> {
-        let num_docs = fieldnorm_reader
-            .as_ref()
-            .map(|fieldnorm_reader| fieldnorm_reader.num_docs())
-            .unwrap_or(0u32);
         PostingsSerializer {
             output_write: CountingWriter::wrap(write),
 
@@ -356,26 +343,30 @@ impl<W: Write> PostingsSerializer<W> {
             skip_write: SkipSerializer::new(),
 
             last_doc_id_encoded: 0u32,
-            termfreq_enabled,
-            termfreq_sum_enabled,
+            mode,
 
             fieldnorm_reader,
             bm25_weight: None,
 
-            num_docs,
             avg_fieldnorm,
         }
     }
 
+    /// Returns the number of documents in the segment currently being serialized.
+    /// This function may return `None` if there are no fieldnorm for that field.
+    fn num_docs_in_segment(&self) -> Option<u32> {
+        self.fieldnorm_reader
+            .as_ref()
+            .map(|reader| reader.num_docs())
+    }
+
     pub fn new_term(&mut self, term_doc_freq: u32) {
-        if self.termfreq_enabled && self.num_docs > 0 {
-            let bm25_weight = BM25Weight::for_one_term(
-                term_doc_freq as u64,
-                self.num_docs as u64,
-                self.avg_fieldnorm,
-            );
-            self.bm25_weight = Some(bm25_weight);
+        if self.mode.has_freq() {
+            return;
         }
+        self.bm25_weight = self.num_docs_in_segment().map(|num_docs| {
+            BM25Weight::for_one_term(term_doc_freq as u64, num_docs as u64, self.avg_fieldnorm)
+        });
     }
 
     fn write_block(&mut self) {
@@ -390,13 +381,15 @@ impl<W: Write> PostingsSerializer<W> {
             // last el block 0, offset block 1,
             self.postings_write.extend(block_encoded);
         }
-        if self.termfreq_enabled {
+        if self.mode.has_freq() {
             let (num_bits, block_encoded): (u8, &[u8]) = self
                 .block_encoder
                 .compress_block_unsorted(&self.block.term_freqs());
             self.postings_write.extend(block_encoded);
             self.skip_write.write_term_freq(num_bits);
-            if self.termfreq_sum_enabled {
+            if self.mode.has_positions() {
+                // We serialize the sum of term freqs within the skip information
+                // in order to navigate through positions.
                 let sum_freq = self.block.term_freqs().iter().cloned().sum();
                 self.skip_write.write_total_term_freq(sum_freq);
             }
@@ -455,7 +448,7 @@ impl<W: Write> PostingsSerializer<W> {
                 self.postings_write.write_all(block_encoded)?;
             }
             // ... Idem for term frequencies
-            if self.termfreq_enabled {
+            if self.mode.has_freq() {
                 let block_encoded = self
                     .block_encoder
                     .compress_vint_unsorted(self.block.term_freqs());

src/postings/skip.rs

@@ -1,10 +1,9 @@
-use crate::common::{read_u32_vint_no_advance, serialize_vint_u32, BinarySerializable, VInt};
-use crate::directory::ReadOnlySource;
+use crate::common::{read_u32_vint_no_advance, serialize_vint_u32, BinarySerializable};
+use crate::directory::OwnedBytes;
 use crate::postings::compression::{compressed_block_size, COMPRESSION_BLOCK_SIZE};
 use crate::query::BM25Weight;
 use crate::schema::IndexRecordOption;
 use crate::{DocId, Score, TERMINATED};
-use owned_read::OwnedRead;
 
 pub struct SkipSerializer {
     buffer: Vec<u8>,
@@ -62,7 +61,7 @@ impl SkipSerializer {
 pub(crate) struct SkipReader {
     last_doc_in_block: DocId,
     pub(crate) last_doc_in_previous_block: DocId,
-    owned_read: OwnedRead,
+    owned_read: OwnedBytes,
     skip_info: IndexRecordOption,
     byte_offset: usize,
     remaining_docs: u32, // number of docs remaining, including the
@@ -93,7 +92,7 @@ impl Default for BlockInfo {
 }
 
 impl SkipReader {
-    pub fn new(data: ReadOnlySource, doc_freq: u32, skip_info: IndexRecordOption) -> SkipReader {
+    pub fn new(data: OwnedBytes, doc_freq: u32, skip_info: IndexRecordOption) -> SkipReader {
         let mut skip_reader = SkipReader {
             last_doc_in_block: if doc_freq >= COMPRESSION_BLOCK_SIZE as u32 {
                 0
@@ -101,7 +100,7 @@ impl SkipReader {
                 TERMINATED
             },
             last_doc_in_previous_block: 0u32,
-            owned_read: OwnedRead::new(data),
+            owned_read: data,
             skip_info,
             block_info: BlockInfo::VInt { num_docs: doc_freq },
             byte_offset: 0,
@@ -114,14 +113,14 @@ impl SkipReader {
         skip_reader
     }
 
-    pub fn reset(&mut self, data: ReadOnlySource, doc_freq: u32) {
+    pub fn reset(&mut self, data: OwnedBytes, doc_freq: u32) {
         self.last_doc_in_block = if doc_freq >= COMPRESSION_BLOCK_SIZE as u32 {
             0
         } else {
             TERMINATED
         };
         self.last_doc_in_previous_block = 0u32;
-        self.owned_read = OwnedRead::new(data);
+        self.owned_read = data;
         self.block_info = BlockInfo::VInt { num_docs: doc_freq };
         self.byte_offset = 0;
         self.remaining_docs = doc_freq;
@@ -154,17 +153,24 @@ impl SkipReader {
         self.position_offset
     }
 
+    #[inline(always)]
     pub fn byte_offset(&self) -> usize {
         self.byte_offset
     }
 
     fn read_block_info(&mut self) {
-        let doc_delta = u32::deserialize(&mut self.owned_read).expect("Skip data corrupted");
+        let doc_delta = {
+            let bytes = self.owned_read.as_slice();
+            let mut buf = [0; 4];
+            buf.copy_from_slice(&bytes[..4]);
+            u32::from_le_bytes(buf)
+        };
         self.last_doc_in_block += doc_delta as DocId;
-        let doc_num_bits = self.owned_read.get(0);
+        let doc_num_bits = self.owned_read.as_slice()[4];
+
         match self.skip_info {
             IndexRecordOption::Basic => {
-                self.owned_read.advance(1);
+                self.owned_read.advance(5);
                 self.block_info = BlockInfo::BitPacked {
                     doc_num_bits,
                     tf_num_bits: 0,
@@ -174,11 +180,11 @@ impl SkipReader {
                 };
             }
             IndexRecordOption::WithFreqs => {
-                let tf_num_bits = self.owned_read.get(1);
-                let block_wand_fieldnorm_id = self.owned_read.get(2);
-                let data = &self.owned_read.as_ref()[3..];
-                let (block_wand_term_freq, num_bytes) = read_u32_vint_no_advance(data);
-                self.owned_read.advance(3 + num_bytes);
+                let bytes = self.owned_read.as_slice();
+                let tf_num_bits = bytes[5];
+                let block_wand_fieldnorm_id = bytes[6];
+                let (block_wand_term_freq, num_bytes) = read_u32_vint_no_advance(&bytes[7..]);
+                self.owned_read.advance(7 + num_bytes);
                 self.block_info = BlockInfo::BitPacked {
                     doc_num_bits,
                     tf_num_bits,
@@ -188,13 +194,16 @@ impl SkipReader {
                 };
             }
             IndexRecordOption::WithFreqsAndPositions => {
-                let tf_num_bits = self.owned_read.get(1);
-                self.owned_read.advance(2);
-                let tf_sum = u32::deserialize(&mut self.owned_read).expect("Failed reading tf_sum");
-                let block_wand_fieldnorm_id = self.owned_read.get(0);
-                self.owned_read.advance(1);
-                let block_wand_term_freq =
-                    VInt::deserialize_u64(&mut self.owned_read).unwrap() as u32;
+                let bytes = self.owned_read.as_slice();
+                let tf_num_bits = bytes[5];
+                let tf_sum = {
+                    let mut buf = [0; 4];
+                    buf.copy_from_slice(&bytes[6..10]);
+                    u32::from_le_bytes(buf)
+                };
+                let block_wand_fieldnorm_id = bytes[10];
+                let (block_wand_term_freq, num_bytes) = read_u32_vint_no_advance(&bytes[11..]);
+                self.owned_read.advance(11 + num_bytes);
                 self.block_info = BlockInfo::BitPacked {
                     doc_num_bits,
                     tf_num_bits,
@@ -262,7 +271,7 @@ mod tests {
     use super::BlockInfo;
     use super::IndexRecordOption;
     use super::{SkipReader, SkipSerializer};
-    use crate::directory::ReadOnlySource;
+    use crate::directory::OwnedBytes;
     use crate::postings::compression::COMPRESSION_BLOCK_SIZE;
 
     #[test]
@@ -278,11 +287,8 @@ mod tests {
             skip_serializer.data().to_owned()
         };
         let doc_freq = 3u32 + (COMPRESSION_BLOCK_SIZE * 2) as u32;
-        let mut skip_reader = SkipReader::new(
-            ReadOnlySource::new(buf),
-            doc_freq,
-            IndexRecordOption::WithFreqs,
-        );
+        let mut skip_reader =
+            SkipReader::new(OwnedBytes::new(buf), doc_freq, IndexRecordOption::WithFreqs);
         assert_eq!(skip_reader.last_doc_in_block(), 1u32);
         assert_eq!(
             skip_reader.block_info,
@@ -323,11 +329,8 @@ mod tests {
             skip_serializer.data().to_owned()
         };
         let doc_freq = 3u32 + (COMPRESSION_BLOCK_SIZE * 2) as u32;
-        let mut skip_reader = SkipReader::new(
-            ReadOnlySource::from(buf),
-            doc_freq,
-            IndexRecordOption::Basic,
-        );
+        let mut skip_reader =
+            SkipReader::new(OwnedBytes::new(buf), doc_freq, IndexRecordOption::Basic);
         assert_eq!(skip_reader.last_doc_in_block(), 1u32);
         assert_eq!(
             skip_reader.block_info(),
@@ -367,11 +370,8 @@ mod tests {
             skip_serializer.data().to_owned()
         };
         let doc_freq = COMPRESSION_BLOCK_SIZE as u32;
-        let mut skip_reader = SkipReader::new(
-            ReadOnlySource::from(buf),
-            doc_freq,
-            IndexRecordOption::Basic,
-        );
+        let mut skip_reader =
+            SkipReader::new(OwnedBytes::new(buf), doc_freq, IndexRecordOption::Basic);
         assert_eq!(skip_reader.last_doc_in_block(), 1u32);
         assert_eq!(
             skip_reader.block_info(),

src/postings/stacker/expull.rs

@@ -206,8 +206,8 @@ mod tests {
     fn test_stack_long() {
         let mut heap = MemoryArena::new();
         let mut stack = ExpUnrolledLinkedList::new();
-        let source: Vec<u32> = (0..100).collect();
-        for &el in &source {
+        let data: Vec<u32> = (0..100).collect();
+        for &el in &data {
             assert!(stack
                 .writer(&mut heap)
                 .write_u32::<LittleEndian>(el)
@@ -221,7 +221,7 @@ mod tests {
             result.push(LittleEndian::read_u32(&remaining[..4]));
             remaining = &remaining[4..];
         }
-        assert_eq!(&result[..], &source[..]);
+        assert_eq!(&result[..], &data[..]);
     }
 
     #[test]

src/query/automaton_weight.rs

@@ -42,13 +42,13 @@ where
     fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         let max_doc = reader.max_doc();
         let mut doc_bitset = BitSet::with_max_value(max_doc);
-        let inverted_index = reader.inverted_index(self.field);
+        let inverted_index = reader.inverted_index(self.field)?;
         let term_dict = inverted_index.terms();
         let mut term_stream = self.automaton_stream(term_dict);
         while term_stream.advance() {
             let term_info = term_stream.value();
             let mut block_segment_postings = inverted_index
-                .read_block_postings_from_terminfo(term_info, IndexRecordOption::Basic);
+                .read_block_postings_from_terminfo(term_info, IndexRecordOption::Basic)?;
             loop {
                 let docs = block_segment_postings.docs();
                 if docs.is_empty() {

src/query/bm25.rs

@@ -52,7 +52,7 @@ impl BM25Weight {
         }
     }
 
-    pub fn for_terms(searcher: &Searcher, terms: &[Term]) -> BM25Weight {
+    pub fn for_terms(searcher: &Searcher, terms: &[Term]) -> crate::Result<BM25Weight> {
         assert!(!terms.is_empty(), "BM25 requires at least one term");
         let field = terms[0].field();
         for term in &terms[1..] {
@@ -66,25 +66,27 @@ impl BM25Weight {
         let mut total_num_tokens = 0u64;
         let mut total_num_docs = 0u64;
         for segment_reader in searcher.segment_readers() {
-            let inverted_index = segment_reader.inverted_index(field);
+            let inverted_index = segment_reader.inverted_index(field)?;
             total_num_tokens += inverted_index.total_num_tokens();
             total_num_docs += u64::from(segment_reader.max_doc());
         }
         let average_fieldnorm = total_num_tokens as Score / total_num_docs as Score;
 
         if terms.len() == 1 {
-            let term_doc_freq = searcher.doc_freq(&terms[0]);
-            BM25Weight::for_one_term(term_doc_freq, total_num_docs, average_fieldnorm)
+            let term_doc_freq = searcher.doc_freq(&terms[0])?;
+            Ok(BM25Weight::for_one_term(
+                term_doc_freq,
+                total_num_docs,
+                average_fieldnorm,
+            ))
         } else {
-            let idf = terms
-                .iter()
-                .map(|term| {
-                    let term_doc_freq = searcher.doc_freq(term);
-                    idf(term_doc_freq, total_num_docs)
-                })
-                .sum::<Score>();
-            let idf_explain = Explanation::new("idf", idf);
-            BM25Weight::new(idf_explain, average_fieldnorm)
+            let mut idf_sum: Score = 0.0;
+            for term in terms {
+                let term_doc_freq = searcher.doc_freq(term)?;
+                idf_sum += idf(term_doc_freq, total_num_docs);
+            }
+            let idf_explain = Explanation::new("idf", idf_sum);
+            Ok(BM25Weight::new(idf_explain, average_fieldnorm))
         }
     }
 

src/query/boolean_query/boolean_query.rs

@@ -83,7 +83,7 @@ use std::collections::BTreeSet;
 ///    ];
 ///    // Make a BooleanQuery equivalent to
 ///    // title:+diary title:-girl
-///    let diary_must_and_girl_mustnot = BooleanQuery::from(queries_with_occurs1);
+///    let diary_must_and_girl_mustnot = BooleanQuery::new(queries_with_occurs1);
 ///    let count1 = searcher.search(&diary_must_and_girl_mustnot, &Count)?;
 ///    assert_eq!(count1, 1);
 ///
@@ -93,7 +93,7 @@ use std::collections::BTreeSet;
 ///        IndexRecordOption::Basic,
 ///    ));
 ///    // "title:diary OR title:cow"
-///    let title_diary_or_cow = BooleanQuery::from(vec![
+///    let title_diary_or_cow = BooleanQuery::new(vec![
 ///        (Occur::Should, diary_term_query.box_clone()),
 ///        (Occur::Should, cow_term_query),
 ///    ]);
@@ -108,7 +108,7 @@ use std::collections::BTreeSet;
 ///    // You can combine subqueries of different types into 1 BooleanQuery:
 ///    // `TermQuery` and `PhraseQuery`
 ///    // "title:diary OR "dairy cow"
-///    let term_of_phrase_query = BooleanQuery::from(vec![
+///    let term_of_phrase_query = BooleanQuery::new(vec![
 ///        (Occur::Should, diary_term_query.box_clone()),
 ///        (Occur::Should, phrase_query.box_clone()),
 ///    ]);
@@ -117,7 +117,7 @@ use std::collections::BTreeSet;
 ///
 ///    // You can nest one BooleanQuery inside another
 ///    // body:found AND ("title:diary OR "dairy cow")
-///    let nested_query = BooleanQuery::from(vec![
+///    let nested_query = BooleanQuery::new(vec![
 ///        (Occur::Must, body_term_query),
 ///        (Occur::Must, Box::new(term_of_phrase_query))
 ///    ]);
@@ -143,7 +143,7 @@ impl Clone for BooleanQuery {
 
 impl From<Vec<(Occur, Box<dyn Query>)>> for BooleanQuery {
     fn from(subqueries: Vec<(Occur, Box<dyn Query>)>) -> BooleanQuery {
-        BooleanQuery { subqueries }
+        BooleanQuery::new(subqueries)
     }
 }
 
@@ -167,6 +167,23 @@ impl Query for BooleanQuery {
 }
 
 impl BooleanQuery {
+    /// Creates a new boolean query.
+    pub fn new(subqueries: Vec<(Occur, Box<dyn Query>)>) -> BooleanQuery {
+        BooleanQuery { subqueries }
+    }
+
+    /// Returns the intersection of the queries.
+    pub fn intersection(queries: Vec<Box<dyn Query>>) -> BooleanQuery {
+        let subqueries = queries.into_iter().map(|s| (Occur::Must, s)).collect();
+        BooleanQuery::new(subqueries)
+    }
+
+    /// Returns the union of the queries.
+    pub fn union(queries: Vec<Box<dyn Query>>) -> BooleanQuery {
+        let subqueries = queries.into_iter().map(|s| (Occur::Should, s)).collect();
+        BooleanQuery::new(subqueries)
+    }
+
     /// Helper method to create a boolean query matching a given list of terms.
     /// The resulting query is a disjunction of the terms.
     pub fn new_multiterms_query(terms: Vec<Term>) -> BooleanQuery {
@@ -178,7 +195,7 @@ impl BooleanQuery {
                 (Occur::Should, term_query)
             })
             .collect();
-        BooleanQuery::from(occur_term_queries)
+        BooleanQuery::new(occur_term_queries)
     }
 
     /// Deconstructed view of the clauses making up this query.
@@ -186,3 +203,77 @@ impl BooleanQuery {
         &self.subqueries[..]
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::BooleanQuery;
+    use crate::collector::DocSetCollector;
+    use crate::query::{QueryClone, TermQuery};
+    use crate::schema::{IndexRecordOption, Schema, TEXT};
+    use crate::{DocAddress, Index, Term};
+
+    fn create_test_index() -> crate::Result<Index> {
+        let mut schema_builder = Schema::builder();
+        let text = schema_builder.add_text_field("text", TEXT);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut writer = index.writer_for_tests().unwrap();
+        writer.add_document(doc!(text=>"b c"));
+        writer.add_document(doc!(text=>"a c"));
+        writer.add_document(doc!(text=>"a b"));
+        writer.add_document(doc!(text=>"a d"));
+        writer.commit()?;
+        Ok(index)
+    }
+
+    #[test]
+    fn test_union() -> crate::Result<()> {
+        let index = create_test_index()?;
+        let searcher = index.reader()?.searcher();
+        let text = index.schema().get_field("text").unwrap();
+        let term_a = TermQuery::new(Term::from_field_text(text, "a"), IndexRecordOption::Basic);
+        let term_d = TermQuery::new(Term::from_field_text(text, "d"), IndexRecordOption::Basic);
+        let union_ad = BooleanQuery::union(vec![term_a.box_clone(), term_d.box_clone()]);
+        let docs = searcher.search(&union_ad, &DocSetCollector)?;
+        assert_eq!(
+            docs,
+            vec![
+                DocAddress(0u32, 1u32),
+                DocAddress(0u32, 2u32),
+                DocAddress(0u32, 3u32)
+            ]
+            .into_iter()
+            .collect()
+        );
+        Ok(())
+    }
+
+    #[test]
+    fn test_intersection() -> crate::Result<()> {
+        let index = create_test_index()?;
+        let searcher = index.reader()?.searcher();
+        let text = index.schema().get_field("text").unwrap();
+        let term_a = TermQuery::new(Term::from_field_text(text, "a"), IndexRecordOption::Basic);
+        let term_b = TermQuery::new(Term::from_field_text(text, "b"), IndexRecordOption::Basic);
+        let term_c = TermQuery::new(Term::from_field_text(text, "c"), IndexRecordOption::Basic);
+        let intersection_ab =
+            BooleanQuery::intersection(vec![term_a.box_clone(), term_b.box_clone()]);
+        let intersection_ac =
+            BooleanQuery::intersection(vec![term_a.box_clone(), term_c.box_clone()]);
+        let intersection_bc =
+            BooleanQuery::intersection(vec![term_b.box_clone(), term_c.box_clone()]);
+        {
+            let docs = searcher.search(&intersection_ab, &DocSetCollector)?;
+            assert_eq!(docs, vec![DocAddress(0u32, 2u32)].into_iter().collect());
+        }
+        {
+            let docs = searcher.search(&intersection_ac, &DocSetCollector)?;
+            assert_eq!(docs, vec![DocAddress(0u32, 1u32)].into_iter().collect());
+        }
+        {
+            let docs = searcher.search(&intersection_bc, &DocSetCollector)?;
+            assert_eq!(docs, vec![DocAddress(0u32, 0u32)].into_iter().collect());
+        }
+        Ok(())
+    }
+}

src/query/boolean_query/mod.rs

@@ -33,13 +33,11 @@ mod tests {
         {
             // writing the segment
             let mut index_writer = index.writer_for_tests().unwrap();
-            {
-                index_writer.add_document(doc!(text_field => "a b c"));
-                index_writer.add_document(doc!(text_field => "a c"));
-                index_writer.add_document(doc!(text_field => "b c"));
-                index_writer.add_document(doc!(text_field => "a b c d"));
-                index_writer.add_document(doc!(text_field => "d"));
-            }
+            index_writer.add_document(doc!(text_field => "a b c"));
+            index_writer.add_document(doc!(text_field => "a c"));
+            index_writer.add_document(doc!(text_field => "b c"));
+            index_writer.add_document(doc!(text_field => "a b c d"));
+            index_writer.add_document(doc!(text_field => "d"));
             assert!(index_writer.commit().is_ok());
         }
         (index, text_field)
@@ -134,29 +132,29 @@ mod tests {
                 .collect::<Vec<DocId>>()
         };
         {
-            let boolean_query = BooleanQuery::from(vec![(Occur::Must, make_term_query("a"))]);
+            let boolean_query = BooleanQuery::new(vec![(Occur::Must, make_term_query("a"))]);
             assert_eq!(matching_docs(&boolean_query), vec![0, 1, 3]);
         }
         {
-            let boolean_query = BooleanQuery::from(vec![(Occur::Should, make_term_query("a"))]);
+            let boolean_query = BooleanQuery::new(vec![(Occur::Should, make_term_query("a"))]);
             assert_eq!(matching_docs(&boolean_query), vec![0, 1, 3]);
         }
         {
-            let boolean_query = BooleanQuery::from(vec![
+            let boolean_query = BooleanQuery::new(vec![
                 (Occur::Should, make_term_query("a")),
                 (Occur::Should, make_term_query("b")),
             ]);
             assert_eq!(matching_docs(&boolean_query), vec![0, 1, 2, 3]);
         }
         {
-            let boolean_query = BooleanQuery::from(vec![
+            let boolean_query = BooleanQuery::new(vec![
                 (Occur::Must, make_term_query("a")),
                 (Occur::Should, make_term_query("b")),
             ]);
             assert_eq!(matching_docs(&boolean_query), vec![0, 1, 3]);
         }
         {
-            let boolean_query = BooleanQuery::from(vec![
+            let boolean_query = BooleanQuery::new(vec![
                 (Occur::Must, make_term_query("a")),
                 (Occur::Should, make_term_query("b")),
                 (Occur::MustNot, make_term_query("d")),
@@ -164,7 +162,7 @@ mod tests {
             assert_eq!(matching_docs(&boolean_query), vec![0, 1]);
         }
         {
-            let boolean_query = BooleanQuery::from(vec![(Occur::MustNot, make_term_query("d"))]);
+            let boolean_query = BooleanQuery::new(vec![(Occur::MustNot, make_term_query("d"))]);
             assert_eq!(matching_docs(&boolean_query), Vec::<u32>::new());
         }
     }
@@ -194,7 +192,7 @@ mod tests {
         let score_doc_4: Score; // score of doc 4 should not be influenced by exclusion
         {
             let boolean_query_no_excluded =
-                BooleanQuery::from(vec![(Occur::Must, make_term_query("d"))]);
+                BooleanQuery::new(vec![(Occur::Must, make_term_query("d"))]);
             let topdocs_no_excluded = matching_topdocs(&boolean_query_no_excluded);
             assert_eq!(topdocs_no_excluded.len(), 2);
             let (top_score, top_doc) = topdocs_no_excluded[0];
@@ -204,7 +202,7 @@ mod tests {
         }
 
         {
-            let boolean_query_two_excluded = BooleanQuery::from(vec![
+            let boolean_query_two_excluded = BooleanQuery::new(vec![
                 (Occur::Must, make_term_query("d")),
                 (Occur::MustNot, make_term_query("a")),
                 (Occur::MustNot, make_term_query("b")),
@@ -241,7 +239,7 @@ mod tests {
         let reader = index.reader().unwrap();
         let searcher = reader.searcher();
         let boolean_query =
-            BooleanQuery::from(vec![(Occur::Should, term_a), (Occur::Should, term_b)]);
+            BooleanQuery::new(vec![(Occur::Should, term_a), (Occur::Should, term_b)]);
         let boolean_weight = boolean_query.weight(&searcher, true).unwrap();
         {
             let mut boolean_scorer = boolean_weight
@@ -281,7 +279,7 @@ mod tests {
         };
 
         {
-            let boolean_query = BooleanQuery::from(vec![
+            let boolean_query = BooleanQuery::new(vec![
                 (Occur::Must, make_term_query("a")),
                 (Occur::Must, make_term_query("b")),
             ]);
@@ -290,4 +288,29 @@ mod tests {
             assert_nearly_equals!(scores[1], 0.84699446);
         }
     }
+
+    #[test]
+    pub fn test_explain() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let text = schema_builder.add_text_field("text", STRING);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_with_num_threads(1, 5_000_000)?;
+        index_writer.add_document(doc!(text=>"a"));
+        index_writer.add_document(doc!(text=>"b"));
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
+        let term_a: Box<dyn Query> = Box::new(TermQuery::new(
+            Term::from_field_text(text, "a"),
+            IndexRecordOption::Basic,
+        ));
+        let term_b: Box<dyn Query> = Box::new(TermQuery::new(
+            Term::from_field_text(text, "b"),
+            IndexRecordOption::Basic,
+        ));
+        let query = BooleanQuery::from(vec![(Occur::Should, term_a), (Occur::Should, term_b)]);
+        let explanation = query.explain(&searcher, DocAddress(0, 0u32))?;
+        assert_nearly_equals!(explanation.value(), 0.6931472f32);
+        Ok(())
+    }
 }

src/query/boost_query.rs

@@ -153,7 +153,7 @@ mod tests {
         let explanation = query.explain(&searcher, DocAddress(0, 0u32)).unwrap();
         assert_eq!(
             explanation.to_pretty_json(),
-            "{\n  \"value\": 0.2,\n  \"description\": \"Boost x0.2 of ...\",\n  \"details\": [\n    {\n      \"value\": 1.0,\n      \"description\": \"AllQuery\"\n    }\n  ]\n}"
+            "{\n  \"value\": 0.2,\n  \"description\": \"Boost x0.2 of ...\",\n  \"details\": [\n    {\n      \"value\": 1.0,\n      \"description\": \"AllQuery\",\n      \"context\": []\n    }\n  ],\n  \"context\": []\n}"
         )
     }
 }

src/query/explanation.rs

@@ -17,6 +17,7 @@ pub struct Explanation {
     description: String,
     #[serde(skip_serializing_if = "Vec::is_empty")]
     details: Vec<Explanation>,
+    context: Vec<String>,
 }
 
 impl fmt::Debug for Explanation {
@@ -32,6 +33,7 @@ impl Explanation {
             value,
             description: description.to_string(),
             details: vec![],
+            context: vec![],
         }
     }
 
@@ -47,6 +49,11 @@ impl Explanation {
         self.details.push(child_explanation);
     }
 
+    /// Adds some extra context to the explanation.
+    pub fn add_context(&mut self, context: String) {
+        self.context.push(context);
+    }
+
     /// Shortcut for `self.details.push(Explanation::new(name, value));`
     pub fn add_const<T: ToString>(&mut self, name: T, value: Score) {
         self.details.push(Explanation::new(name, value));

src/query/mod.rs

@@ -46,7 +46,7 @@ pub(crate) use self::fuzzy_query::DFAWrapper;
 pub use self::fuzzy_query::FuzzyTermQuery;
 pub use self::intersection::intersect_scorers;
 pub use self::phrase_query::PhraseQuery;
-pub use self::query::Query;
+pub use self::query::{Query, QueryClone};
 pub use self::query_parser::QueryParser;
 pub use self::query_parser::QueryParserError;
 pub use self::range_query::RangeQuery;

src/query/phrase_query/phrase_query.rs

@@ -95,7 +95,7 @@ impl PhraseQuery {
             )));
         }
         let terms = self.phrase_terms();
-        let bm25_weight = BM25Weight::for_terms(searcher, &terms);
+        let bm25_weight = BM25Weight::for_terms(searcher, &terms)?;
         Ok(PhraseWeight::new(
             self.phrase_terms.clone(),
             bm25_weight,

src/query/phrase_query/phrase_weight.rs

@@ -48,8 +48,8 @@ impl PhraseWeight {
             let mut term_postings_list = Vec::new();
             for &(offset, ref term) in &self.phrase_terms {
                 if let Some(postings) = reader
-                    .inverted_index(term.field())
-                    .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
+                    .inverted_index(term.field())?
+                    .read_postings(&term, IndexRecordOption::WithFreqsAndPositions)?
                 {
                     term_postings_list.push((offset, postings));
                 } else {
@@ -66,8 +66,8 @@ impl PhraseWeight {
             let mut term_postings_list = Vec::new();
             for &(offset, ref term) in &self.phrase_terms {
                 if let Some(postings) = reader
-                    .inverted_index(term.field())
-                    .read_postings_no_deletes(&term, IndexRecordOption::WithFreqsAndPositions)
+                    .inverted_index(term.field())?
+                    .read_postings_no_deletes(&term, IndexRecordOption::WithFreqsAndPositions)?
                 {
                     term_postings_list.push((offset, postings));
                 } else {

src/query/query.rs

@@ -71,7 +71,9 @@ pub trait Query: QueryClone + Send + Sync + downcast_rs::Downcast + fmt::Debug {
     fn query_terms(&self, _term_set: &mut BTreeSet<Term>) {}
 }
 
+/// Implements `box_clone`.
 pub trait QueryClone {
+    /// Returns a boxed clone of `self`.
     fn box_clone(&self) -> Box<dyn Query>;
 }
 

src/query/query_parser/query_parser.rs

@@ -21,51 +21,52 @@ use std::str::FromStr;
 use tantivy_query_grammar::{UserInputAST, UserInputBound, UserInputLeaf};
 
 /// Possible error that may happen when parsing a query.
-#[derive(Debug, PartialEq, Eq, Fail)]
+#[derive(Debug, PartialEq, Eq, Error)]
 pub enum QueryParserError {
     /// Error in the query syntax
-    #[fail(display = "Syntax Error")]
+    #[error("Syntax Error")]
     SyntaxError,
     /// `FieldDoesNotExist(field_name: String)`
     /// The query references a field that is not in the schema
-    #[fail(display = "File does not exists: '{:?}'", _0)]
+    #[error("File does not exists: '{0:?}'")]
     FieldDoesNotExist(String),
     /// The query contains a term for a `u64` or `i64`-field, but the value
     /// is neither.
-    #[fail(display = "Expected a valid integer: '{:?}'", _0)]
+    #[error("Expected a valid integer: '{0:?}'")]
     ExpectedInt(ParseIntError),
+    /// The query contains a term for a bytes field, but the value is not valid
+    /// base64.
+    #[error("Expected base64: '{0:?}'")]
+    ExpectedBase64(base64::DecodeError),
     /// The query contains a term for a `f64`-field, but the value
     /// is not a f64.
-    #[fail(display = "Invalid query: Only excluding terms given")]
+    #[error("Invalid query: Only excluding terms given")]
     ExpectedFloat(ParseFloatError),
     /// It is forbidden queries that are only "excluding". (e.g. -title:pop)
-    #[fail(display = "Invalid query: Only excluding terms given")]
+    #[error("Invalid query: Only excluding terms given")]
     AllButQueryForbidden,
     /// If no default field is declared, running a query without any
     /// field specified is forbbidden.
-    #[fail(display = "No default field declared and no field specified in query")]
+    #[error("No default field declared and no field specified in query")]
     NoDefaultFieldDeclared,
     /// The field searched for is not declared
     /// as indexed in the schema.
-    #[fail(display = "The field '{:?}' is not declared as indexed", _0)]
+    #[error("The field '{0:?}' is not declared as indexed")]
     FieldNotIndexed(String),
     /// A phrase query was requested for a field that does not
     /// have any positions indexed.
-    #[fail(display = "The field '{:?}' does not have positions indexed", _0)]
+    #[error("The field '{0:?}' does not have positions indexed")]
     FieldDoesNotHavePositionsIndexed(String),
     /// The tokenizer for the given field is unknown
     /// The two argument strings are the name of the field, the name of the tokenizer
-    #[fail(
-        display = "The tokenizer '{:?}' for the field '{:?}' is unknown",
-        _0, _1
-    )]
+    #[error("The tokenizer '{0:?}' for the field '{1:?}' is unknown")]
     UnknownTokenizer(String, String),
     /// The query contains a range query with a phrase as one of the bounds.
     /// Only terms can be used as bounds.
-    #[fail(display = "A range query cannot have a phrase as one of the bounds")]
+    #[error("A range query cannot have a phrase as one of the bounds")]
     RangeMustNotHavePhrase,
     /// The format for the date field is not RFC 3339 compliant.
-    #[fail(display = "The date field has an invalid format")]
+    #[error("The date field has an invalid format")]
     DateFormatError(chrono::ParseError),
 }
 
@@ -360,9 +361,10 @@ impl QueryParser {
                 let facet = Facet::from_text(phrase);
                 Ok(vec![(0, Term::from_field_text(field, facet.encoded_str()))])
             }
-            FieldType::Bytes => {
-                let field_name = self.schema.get_field_name(field).to_string();
-                Err(QueryParserError::FieldNotIndexed(field_name))
+            FieldType::Bytes(_) => {
+                let bytes = base64::decode(phrase).map_err(QueryParserError::ExpectedBase64)?;
+                let term = Term::from_field_bytes(field, &bytes);
+                Ok(vec![(0, term)])
             }
         }
     }
@@ -555,7 +557,7 @@ fn convert_to_query(logical_ast: LogicalAST) -> Box<dyn Query> {
                 !occur_subqueries.is_empty(),
                 "Should not be empty after trimming"
             );
-            Box::new(BooleanQuery::from(occur_subqueries))
+            Box::new(BooleanQuery::new(occur_subqueries))
         }
         Some(LogicalAST::Leaf(trimmed_logical_literal)) => {
             convert_literal_to_query(*trimmed_logical_literal)
@@ -604,6 +606,8 @@ mod test {
         schema_builder.add_date_field("date", INDEXED);
         schema_builder.add_f64_field("float", INDEXED);
         schema_builder.add_facet_field("facet");
+        schema_builder.add_bytes_field("bytes", INDEXED);
+        schema_builder.add_bytes_field("bytes_not_indexed", STORED);
         schema_builder.build()
     }
 
@@ -791,6 +795,37 @@ mod test {
         );
     }
 
+    #[test]
+    fn test_parse_bytes() {
+        test_parse_query_to_logical_ast_helper(
+            "bytes:YnVidQ==",
+            "Term(field=12,bytes=[98, 117, 98, 117])",
+            false,
+        );
+    }
+
+    #[test]
+    fn test_parse_bytes_not_indexed() {
+        let error = parse_query_to_logical_ast("bytes_not_indexed:aaa", false).unwrap_err();
+        assert!(matches!(error, QueryParserError::FieldNotIndexed(_)));
+    }
+
+    #[test]
+    fn test_parse_bytes_phrase() {
+        test_parse_query_to_logical_ast_helper(
+            "bytes:\"YnVidQ==\"",
+            "Term(field=12,bytes=[98, 117, 98, 117])",
+            false,
+        );
+    }
+
+    #[test]
+    fn test_parse_bytes_invalid_base64() {
+        let base64_err: QueryParserError =
+            parse_query_to_logical_ast("bytes:aa", false).unwrap_err();
+        assert!(matches!(base64_err, QueryParserError::ExpectedBase64(_)));
+    }
+
     #[test]
     fn test_parse_query_to_ast_ab_c() {
         test_parse_query_to_logical_ast_helper(

src/query/range_query.rs

@@ -296,13 +296,13 @@ impl Weight for RangeWeight {
         let max_doc = reader.max_doc();
         let mut doc_bitset = BitSet::with_max_value(max_doc);
 
-        let inverted_index = reader.inverted_index(self.field);
+        let inverted_index = reader.inverted_index(self.field)?;
         let term_dict = inverted_index.terms();
         let mut term_range = self.term_range(term_dict);
         while term_range.advance() {
             let term_info = term_range.value();
             let mut block_segment_postings = inverted_index
-                .read_block_postings_from_terminfo(term_info, IndexRecordOption::Basic);
+                .read_block_postings_from_terminfo(term_info, IndexRecordOption::Basic)?;
             loop {
                 let docs = block_segment_postings.docs();
                 if docs.is_empty() {

src/query/term_query/mod.rs

@@ -9,12 +9,12 @@ pub use self::term_weight::TermWeight;
 #[cfg(test)]
 mod tests {
 
-    use crate::assert_nearly_equals;
     use crate::collector::TopDocs;
     use crate::docset::DocSet;
     use crate::postings::compression::COMPRESSION_BLOCK_SIZE;
     use crate::query::{Query, QueryParser, Scorer, TermQuery};
     use crate::schema::{Field, IndexRecordOption, Schema, STRING, TEXT};
+    use crate::{assert_nearly_equals, DocAddress};
     use crate::{Index, Term, TERMINATED};
 
     #[test]
@@ -179,4 +179,40 @@ mod tests {
             "TermQuery(Term(field=1,bytes=[104, 101, 108, 108, 111]))"
         );
     }
+
+    #[test]
+    fn test_term_query_explain() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let text_field = schema_builder.add_text_field("text", TEXT);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests().unwrap();
+        index_writer.add_document(doc!(text_field=>"b"));
+        index_writer.add_document(doc!(text_field=>"a"));
+        index_writer.add_document(doc!(text_field=>"a"));
+        index_writer.add_document(doc!(text_field=>"b"));
+        index_writer.commit()?;
+        let term_a = Term::from_field_text(text_field, "a");
+        let term_query = TermQuery::new(term_a, IndexRecordOption::Basic);
+        let searcher = index.reader()?.searcher();
+        {
+            let explanation = term_query.explain(&searcher, DocAddress(0u32, 1u32))?;
+            assert_nearly_equals!(explanation.value(), 0.6931472f32);
+        }
+        {
+            let explanation_err = term_query.explain(&searcher, DocAddress(0u32, 0u32));
+            assert!(matches!(
+                explanation_err,
+                Err(crate::TantivyError::InvalidArgument(_msg))
+            ));
+        }
+        {
+            let explanation_err = term_query.explain(&searcher, DocAddress(0u32, 3u32));
+            assert!(matches!(
+                explanation_err,
+                Err(crate::TantivyError::InvalidArgument(_msg))
+            ));
+        }
+        Ok(())
+    }
 }

src/query/term_query/term_query.rs

@@ -87,21 +87,43 @@ impl TermQuery {
     /// While `.weight(...)` returns a boxed trait object,
     /// this method return a specific implementation.
     /// This is useful for optimization purpose.
-    pub fn specialized_weight(&self, searcher: &Searcher, scoring_enabled: bool) -> TermWeight {
+    pub fn specialized_weight(
+        &self,
+        searcher: &Searcher,
+        scoring_enabled: bool,
+    ) -> crate::Result<TermWeight> {
+        let field_entry = searcher
+            .schema()
+            .get_field_entry(self.term.field());
+        if !field_entry.is_indexed() {
+            let error_msg = format!("Field {:?} is not indexed.", field_entry.name());
+            return Err(crate::TantivyError::SchemaError(error_msg));
+        }
+        let has_fieldnorms = searcher
+            .schema()
+            .get_field_entry(self.term.field())
+            .has_fieldnorms();
         let term = self.term.clone();
-        let bm25_weight = BM25Weight::for_terms(searcher, &[term]);
+        let bm25_weight = BM25Weight::for_terms(searcher, &[term])?;
         let index_record_option = if scoring_enabled {
             self.index_record_option
         } else {
             IndexRecordOption::Basic
         };
-        TermWeight::new(self.term.clone(), index_record_option, bm25_weight)
+        Ok(TermWeight::new(
+            self.term.clone(),
+            index_record_option,
+            bm25_weight,
+            has_fieldnorms,
+        ))
     }
 }
 
 impl Query for TermQuery {
     fn weight(&self, searcher: &Searcher, scoring_enabled: bool) -> crate::Result<Box<dyn Weight>> {
-        Ok(Box::new(self.specialized_weight(searcher, scoring_enabled)))
+        Ok(Box::new(
+            self.specialized_weight(searcher, scoring_enabled)?,
+        ))
     }
     fn query_terms(&self, term_set: &mut BTreeSet<Term>) {
         term_set.insert(self.term.clone());

src/query/term_query/term_scorer.rs

@@ -253,7 +253,7 @@ mod tests {
     }
 
     fn test_block_wand_aux(term_query: &TermQuery, searcher: &Searcher) -> crate::Result<()> {
-        let term_weight = term_query.specialized_weight(&searcher, true);
+        let term_weight = term_query.specialized_weight(&searcher, true)?;
         for reader in searcher.segment_readers() {
             let mut block_max_scores = vec![];
             let mut block_max_scores_b = vec![];

src/query/term_query/term_weight.rs

@@ -1,6 +1,7 @@
 use super::term_scorer::TermScorer;
 use crate::core::SegmentReader;
 use crate::docset::DocSet;
+use crate::fieldnorm::FieldNormReader;
 use crate::postings::SegmentPostings;
 use crate::query::bm25::BM25Weight;
 use crate::query::explanation::does_not_match;
@@ -15,6 +16,7 @@ pub struct TermWeight {
     term: Term,
     index_record_option: IndexRecordOption,
     similarity_weight: BM25Weight,
+    has_fieldnorms: bool,
 }
 
 impl Weight for TermWeight {
@@ -25,10 +27,16 @@ impl Weight for TermWeight {
 
     fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         let mut scorer = self.specialized_scorer(reader, 1.0)?;
-        if scorer.seek(doc) != doc {
+        if scorer.doc() > doc || scorer.seek(doc) != doc {
             return Err(does_not_match(doc));
         }
-        Ok(scorer.explain())
+        let mut explanation = scorer.explain();
+        explanation.add_context(format!(
+            "Term ={:?}:{:?}",
+            self.term.field(),
+            self.term.value_bytes()
+        ));
+        Ok(explanation)
     }
 
     fn count(&self, reader: &SegmentReader) -> crate::Result<u32> {
@@ -36,11 +44,9 @@ impl Weight for TermWeight {
             Ok(self.scorer(reader, 1.0)?.count(delete_bitset))
         } else {
             let field = self.term.field();
-            Ok(reader
-                .inverted_index(field)
-                .get_term_info(&self.term)
-                .map(|term_info| term_info.doc_freq)
-                .unwrap_or(0))
+            let inv_index = reader.inverted_index(field)?;
+            let term_info = inv_index.get_term_info(&self.term);
+            Ok(term_info.map(|term_info| term_info.doc_freq).unwrap_or(0))
         }
     }
 
@@ -83,11 +89,13 @@ impl TermWeight {
         term: Term,
         index_record_option: IndexRecordOption,
         similarity_weight: BM25Weight,
+        has_fieldnorms: bool,
     ) -> TermWeight {
         TermWeight {
             term,
             index_record_option,
             similarity_weight,
+            has_fieldnorms,
         }
     }
 
@@ -97,11 +105,15 @@ impl TermWeight {
         boost: Score,
     ) -> crate::Result<TermScorer> {
         let field = self.term.field();
-        let inverted_index = reader.inverted_index(field);
-        let fieldnorm_reader = reader.get_fieldnorms_reader(field)?;
+        let inverted_index = reader.inverted_index(field)?;
+        let fieldnorm_reader = if self.has_fieldnorms {
+            reader.get_fieldnorms_reader(field)?
+        } else {
+            FieldNormReader::const_fieldnorm_id(1u8, reader.num_docs())
+        };
         let similarity_weight = self.similarity_weight.boost_by(boost);
         let postings_opt: Option<SegmentPostings> =
-            inverted_index.read_postings(&self.term, self.index_record_option);
+            inverted_index.read_postings(&self.term, self.index_record_option)?;
         if let Some(segment_postings) = postings_opt {
             Ok(TermScorer::new(
                 segment_postings,

src/reader/mod.rs

@@ -9,8 +9,8 @@ use crate::directory::META_LOCK;
 use crate::Index;
 use crate::Searcher;
 use crate::SegmentReader;
-use std::convert::TryInto;
 use std::sync::Arc;
+use std::{convert::TryInto, io};
 
 /// Defines when a new version of the index should be reloaded.
 ///
@@ -138,11 +138,11 @@ impl InnerIndexReader {
                 .collect::<crate::Result<_>>()?
         };
         let schema = self.index.schema();
-        let searchers = std::iter::repeat_with(|| {
+        let searchers: Vec<Searcher> = std::iter::repeat_with(|| {
             Searcher::new(schema.clone(), self.index.clone(), segment_readers.clone())
         })
         .take(self.num_searchers)
-        .collect();
+        .collect::<io::Result<_>>()?;
         self.searcher_pool.publish_new_generation(searchers);
         Ok(())
     }

src/reader/pool.rs

@@ -1,5 +1,5 @@
-use crossbeam::crossbeam_channel::unbounded;
-use crossbeam::{Receiver, RecvError, Sender};
+use crossbeam::channel::unbounded;
+use crossbeam::channel::{Receiver, RecvError, Sender};
 use std::ops::{Deref, DerefMut};
 use std::sync::atomic::AtomicUsize;
 use std::sync::atomic::Ordering;
@@ -186,6 +186,7 @@ mod tests {
 
     use super::Pool;
     use super::Queue;
+    use crossbeam::channel;
     use std::{iter, mem};
 
     #[test]
@@ -230,11 +231,11 @@ mod tests {
         let mut threads = vec![];
         // spawn one more thread than there are elements in the pool
 
-        let (start_1_send, start_1_recv) = crossbeam::bounded(0);
-        let (start_2_send, start_2_recv) = crossbeam::bounded(0);
-        let (start_3_send, start_3_recv) = crossbeam::bounded(0);
+        let (start_1_send, start_1_recv) = channel::bounded(0);
+        let (start_2_send, start_2_recv) = channel::bounded(0);
+        let (start_3_send, start_3_recv) = channel::bounded(0);
 
-        let (event_send1, event_recv) = crossbeam::unbounded();
+        let (event_send1, event_recv) = channel::unbounded();
         let event_send2 = event_send1.clone();
         let event_send3 = event_send1.clone();
 

src/schema/bytes_options.rs

@@ -0,0 +1,164 @@
+use serde::{Deserialize, Serialize};
+use std::ops::BitOr;
+
+use super::flags::{FastFlag, IndexedFlag, SchemaFlagList, StoredFlag};
+/// Define how an a bytes field should be handled by tantivy.
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
+pub struct BytesOptions {
+    indexed: bool,
+    fast: bool,
+    stored: bool,
+}
+
+impl BytesOptions {
+    /// Returns true iff the value is indexed.
+    pub fn is_indexed(&self) -> bool {
+        self.indexed
+    }
+
+    /// Returns true iff the value is a fast field.
+    pub fn is_fast(&self) -> bool {
+        self.fast
+    }
+
+    /// Returns true iff the value is stored.
+    pub fn is_stored(&self) -> bool {
+        self.stored
+    }
+
+    /// Set the field as indexed.
+    ///
+    /// Setting an integer as indexed will generate
+    /// a posting list for each value taken by the integer.
+    pub fn set_indexed(mut self) -> BytesOptions {
+        self.indexed = true;
+        self
+    }
+
+    /// Set the field as a single-valued fast field.
+    ///
+    /// Fast fields are designed for random access.
+    /// Access time are similar to a random lookup in an array.
+    /// If more than one value is associated to a fast field, only the last one is
+    /// kept.
+    pub fn set_fast(mut self) -> BytesOptions {
+        self.fast = true;
+        self
+    }
+
+    /// Set the field as stored.
+    ///
+    /// Only the fields that are set as *stored* are
+    /// persisted into the Tantivy's store.
+    pub fn set_stored(mut self) -> BytesOptions {
+        self.stored = true;
+        self
+    }
+}
+
+impl Default for BytesOptions {
+    fn default() -> BytesOptions {
+        BytesOptions {
+            indexed: false,
+            fast: false,
+            stored: false,
+        }
+    }
+}
+
+impl<T: Into<BytesOptions>> BitOr<T> for BytesOptions {
+    type Output = BytesOptions;
+
+    fn bitor(self, other: T) -> BytesOptions {
+        let other = other.into();
+        BytesOptions {
+            indexed: self.indexed | other.indexed,
+            stored: self.stored | other.stored,
+            fast: self.fast | other.fast,
+        }
+    }
+}
+
+impl From<()> for BytesOptions {
+    fn from(_: ()) -> Self {
+        Self::default()
+    }
+}
+
+impl From<FastFlag> for BytesOptions {
+    fn from(_: FastFlag) -> Self {
+        BytesOptions {
+            indexed: false,
+            stored: false,
+            fast: true,
+        }
+    }
+}
+
+impl From<StoredFlag> for BytesOptions {
+    fn from(_: StoredFlag) -> Self {
+        BytesOptions {
+            indexed: false,
+            stored: true,
+            fast: false,
+        }
+    }
+}
+
+impl From<IndexedFlag> for BytesOptions {
+    fn from(_: IndexedFlag) -> Self {
+        BytesOptions {
+            indexed: true,
+            stored: false,
+            fast: false,
+        }
+    }
+}
+
+impl<Head, Tail> From<SchemaFlagList<Head, Tail>> for BytesOptions
+where
+    Head: Clone,
+    Tail: Clone,
+    Self: BitOr<Output = Self> + From<Head> + From<Tail>,
+{
+    fn from(head_tail: SchemaFlagList<Head, Tail>) -> Self {
+        Self::from(head_tail.head) | Self::from(head_tail.tail)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::schema::{BytesOptions, FAST, INDEXED, STORED};
+
+    #[test]
+    fn test_bytes_option_fast_flag() {
+        assert_eq!(BytesOptions::default().set_fast(), FAST.into());
+        assert_eq!(BytesOptions::default().set_indexed(), INDEXED.into());
+        assert_eq!(BytesOptions::default().set_stored(), STORED.into());
+    }
+    #[test]
+    fn test_bytes_option_fast_flag_composition() {
+        assert_eq!(
+            BytesOptions::default().set_fast().set_stored(),
+            (FAST | STORED).into()
+        );
+        assert_eq!(
+            BytesOptions::default().set_indexed().set_fast(),
+            (INDEXED | FAST).into()
+        );
+        assert_eq!(
+            BytesOptions::default().set_stored().set_indexed(),
+            (STORED | INDEXED).into()
+        );
+    }
+
+    #[test]
+    fn test_bytes_option_fast_() {
+        assert!(!BytesOptions::default().is_stored());
+        assert!(!BytesOptions::default().is_fast());
+        assert!(!BytesOptions::default().is_indexed());
+        assert!(BytesOptions::default().set_stored().is_stored());
+        assert!(BytesOptions::default().set_fast().is_fast());
+        assert!(BytesOptions::default().set_indexed().is_indexed());
+    }
+}

src/schema/document.rs

@@ -161,20 +161,16 @@ impl Document {
     }
 
     /// Returns all of the `FieldValue`s associated the given field
-    pub fn get_all(&self, field: Field) -> Vec<&Value> {
+    pub fn get_all(&self, field: Field) -> impl Iterator<Item = &Value> {
         self.field_values
             .iter()
-            .filter(|field_value| field_value.field() == field)
+            .filter(move |field_value| field_value.field() == field)
             .map(FieldValue::value)
-            .collect()
     }
 
     /// Returns the first `FieldValue` associated the given field
     pub fn get_first(&self, field: Field) -> Option<&Value> {
-        self.field_values
-            .iter()
-            .find(|field_value| field_value.field() == field)
-            .map(FieldValue::value)
+        self.get_all(field).next()
     }
 
     /// Prepares Document for being stored in the document store

src/schema/field_entry.rs

@@ -1,6 +1,7 @@
 use crate::schema::TextOptions;
 use crate::schema::{is_valid_field_name, IntOptions};
 
+use crate::schema::bytes_options::BytesOptions;
 use crate::schema::FieldType;
 use serde::de::{self, MapAccess, Visitor};
 use serde::ser::SerializeStruct;
@@ -81,11 +82,10 @@ impl FieldEntry {
     }
 
     /// Creates a field entry for a bytes field
-    pub fn new_bytes(field_name: String) -> FieldEntry {
-        assert!(is_valid_field_name(&field_name));
+    pub fn new_bytes(field_name: String, bytes_type: BytesOptions) -> FieldEntry {
         FieldEntry {
             name: field_name,
-            field_type: FieldType::Bytes,
+            field_type: FieldType::Bytes(bytes_type),
         }
     }
 
@@ -108,15 +108,31 @@ impl FieldEntry {
             | FieldType::F64(ref options)
             | FieldType::Date(ref options) => options.is_indexed(),
             FieldType::HierarchicalFacet => true,
-            FieldType::Bytes => false,
+            FieldType::Bytes(ref options) => options.is_indexed(),
+        }
+    }
+
+    pub fn has_fieldnorms(&self) -> bool {
+        match self.field_type {
+            FieldType::Str(ref options) => options
+                .get_indexing_options()
+                .map(|options| options.fieldnorms())
+                .unwrap_or(false),
+            FieldType::U64(ref options)
+            | FieldType::I64(ref options)
+            | FieldType::F64(ref options)
+            | FieldType::Date(ref options) => options.index_option().has_fieldnorms(),
+            FieldType::HierarchicalFacet => false,
+            FieldType::Bytes(ref _options) => false,
         }
     }
 
     /// Returns true iff the field is a int (signed or unsigned) fast field
-    pub fn is_int_fast(&self) -> bool {
+    pub fn is_fast(&self) -> bool {
         match self.field_type {
             FieldType::U64(ref options)
             | FieldType::I64(ref options)
+            | FieldType::Date(ref options)
             | FieldType::F64(ref options) => options.is_fast(),
             _ => false,
         }
@@ -132,7 +148,7 @@ impl FieldEntry {
             FieldType::Str(ref options) => options.is_stored(),
             // TODO make stored hierarchical facet optional
             FieldType::HierarchicalFacet => true,
-            FieldType::Bytes => false,
+            FieldType::Bytes(ref options) => options.is_stored(),
         }
     }
 }
@@ -169,8 +185,9 @@ impl Serialize for FieldEntry {
             FieldType::HierarchicalFacet => {
                 s.serialize_field("type", "hierarchical_facet")?;
             }
-            FieldType::Bytes => {
+            FieldType::Bytes(ref options) => {
                 s.serialize_field("type", "bytes")?;
+                s.serialize_field("options", options)?;
             }
         }
 
@@ -221,15 +238,12 @@ impl<'de> Deserialize<'de> for FieldEntry {
                             if ty.is_some() {
                                 return Err(de::Error::duplicate_field("type"));
                             }
-                            let type_string = map.next_value()?;
-                            match type_string {
+                            let type_string = map.next_value::<String>()?;
+                            match type_string.as_str() {
                                 "hierarchical_facet" => {
                                     field_type = Some(FieldType::HierarchicalFacet);
                                 }
-                                "bytes" => {
-                                    field_type = Some(FieldType::Bytes);
-                                }
-                                "text" | "u64" | "i64" | "f64" | "date" => {
+                                "text" | "u64" | "i64" | "f64" | "date" | "bytes" => {
                                     // These types require additional options to create a field_type
                                 }
                                 _ => panic!("unhandled type"),
@@ -242,12 +256,13 @@ impl<'de> Deserialize<'de> for FieldEntry {
                                            specified before `options`";
                                 return Err(de::Error::custom(msg));
                             }
-                            Some(ty) => match ty {
+                            Some(ref ty) => match ty.as_str() {
                                 "text" => field_type = Some(FieldType::Str(map.next_value()?)),
                                 "u64" => field_type = Some(FieldType::U64(map.next_value()?)),
                                 "i64" => field_type = Some(FieldType::I64(map.next_value()?)),
                                 "f64" => field_type = Some(FieldType::F64(map.next_value()?)),
                                 "date" => field_type = Some(FieldType::Date(map.next_value()?)),
+                                "bytes" => field_type = Some(FieldType::Bytes(map.next_value()?)),
                                 _ => {
                                     let msg = format!("Unrecognised type {}", ty);
                                     return Err(de::Error::custom(msg));
@@ -272,7 +287,8 @@ impl<'de> Deserialize<'de> for FieldEntry {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::schema::TEXT;
+    use crate::schema::{Schema, STRING, TEXT};
+    use crate::Index;
     use serde_json;
 
     #[test]
@@ -291,7 +307,8 @@ mod tests {
   "options": {
     "indexing": {
       "record": "position",
-      "tokenizer": "default"
+      "tokenizer": "default",
+      "fieldnorms": true
     },
     "stored": false
   }
@@ -309,4 +326,19 @@ mod tests {
             _ => panic!("expected FieldType::Str"),
         }
     }
+
+    #[test]
+    fn test_fieldnorms() -> crate::Result<()> {
+        let mut schema_builder = Schema::builder();
+        let text = schema_builder.add_text_field("text", STRING);
+        let schema = schema_builder.build();
+        let index = Index::create_in_ram(schema);
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(text=>"abc"));
+        index_writer.commit()?;
+        let searcher = index.reader()?.searcher();
+        let err = searcher.segment_reader(0u32).get_fieldnorms_reader(text);
+        assert!(matches!(err, Err(crate::TantivyError::SchemaError(_))));
+        Ok(())
+    }
 }

src/schema/field_type.rs

@@ -1,5 +1,4 @@
-use base64::decode;
-
+use crate::schema::bytes_options::BytesOptions;
 use crate::schema::Facet;
 use crate::schema::IndexRecordOption;
 use crate::schema::TextFieldIndexing;
@@ -63,7 +62,7 @@ pub enum FieldType {
     /// Hierachical Facet
     HierarchicalFacet,
     /// Bytes (one per document)
-    Bytes,
+    Bytes(BytesOptions),
 }
 
 impl FieldType {
@@ -76,7 +75,7 @@ impl FieldType {
             FieldType::F64(_) => Type::F64,
             FieldType::Date(_) => Type::Date,
             FieldType::HierarchicalFacet => Type::HierarchicalFacet,
-            FieldType::Bytes => Type::Bytes,
+            FieldType::Bytes(_) => Type::Bytes,
         }
     }
 
@@ -89,7 +88,7 @@ impl FieldType {
             | FieldType::F64(ref int_options) => int_options.is_indexed(),
             FieldType::Date(ref date_options) => date_options.is_indexed(),
             FieldType::HierarchicalFacet => true,
-            FieldType::Bytes => false,
+            FieldType::Bytes(ref bytes_options) => bytes_options.is_indexed(),
         }
     }
 
@@ -113,7 +112,13 @@ impl FieldType {
                 }
             }
             FieldType::HierarchicalFacet => Some(IndexRecordOption::Basic),
-            FieldType::Bytes => None,
+            FieldType::Bytes(ref bytes_options) => {
+                if bytes_options.is_indexed() {
+                    Some(IndexRecordOption::Basic)
+                } else {
+                    None
+                }
+            }
         }
     }
 
@@ -140,7 +145,7 @@ impl FieldType {
                     ValueParsingError::TypeError(format!("Expected an integer, got {:?}", json)),
                 ),
                 FieldType::HierarchicalFacet => Ok(Value::Facet(Facet::from(field_text))),
-                FieldType::Bytes => decode(field_text).map(Value::Bytes).map_err(|_| {
+                FieldType::Bytes(_) => base64::decode(field_text).map(Value::Bytes).map_err(|_| {
                     ValueParsingError::InvalidBase64(format!(
                         "Expected base64 string, got {:?}",
                         field_text
@@ -172,7 +177,7 @@ impl FieldType {
                         Err(ValueParsingError::OverflowError(msg))
                     }
                 }
-                FieldType::Str(_) | FieldType::HierarchicalFacet | FieldType::Bytes => {
+                FieldType::Str(_) | FieldType::HierarchicalFacet | FieldType::Bytes(_) => {
                     let msg = format!("Expected a string, got {:?}", json);
                     Err(ValueParsingError::TypeError(msg))
                 }
@@ -248,18 +253,18 @@ mod tests {
 
     #[test]
     fn test_bytes_value_from_json() {
-        let result = FieldType::Bytes
+        let result = FieldType::Bytes(Default::default())
             .value_from_json(&json!("dGhpcyBpcyBhIHRlc3Q="))
             .unwrap();
         assert_eq!(result, Value::Bytes("this is a test".as_bytes().to_vec()));
 
-        let result = FieldType::Bytes.value_from_json(&json!(521));
+        let result = FieldType::Bytes(Default::default()).value_from_json(&json!(521));
         match result {
             Err(ValueParsingError::TypeError(_)) => {}
             _ => panic!("Expected parse failure for wrong type"),
         }
 
-        let result = FieldType::Bytes.value_from_json(&json!("-"));
+        let result = FieldType::Bytes(Default::default()).value_from_json(&json!("-"));
         match result {
             Err(ValueParsingError::InvalidBase64(_)) => {}
             _ => panic!("Expected parse failure for invalid base64"),

src/schema/flags.rs

@@ -8,7 +8,7 @@ pub struct StoredFlag;
 /// This flag can apply to any kind of field.
 ///
 /// A stored fields of a document can be retrieved given its `DocId`.
-/// Stored field are stored together and LZ4 compressed.
+/// Stored field are stored together and compressed.
 /// Reading the stored fields of a document is relatively slow.
 /// (~ 100 microsecs)
 ///

src/schema/int_options.rs

@@ -14,10 +14,50 @@ pub enum Cardinality {
     MultiValues,
 }
 
-/// Define how an int field should be handled by tantivy.
+#[derive(Copy, Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
+pub enum IntOptionIndex {
+    #[serde(rename = "no_index")]
+    NoIndex,
+    #[serde(rename = "index_no_fieldnorms")]
+    IndexNoFieldnorms,
+    #[serde(rename = "index_with_fieldnorms")]
+    IndexWithFieldnorms,
+}
+
+impl BitOr<IntOptionIndex> for IntOptionIndex {
+    type Output = IntOptionIndex;
+
+    fn bitor(self, other: IntOptionIndex) -> IntOptionIndex {
+        match (self, other) {
+            (_, Self::IndexWithFieldnorms) | (Self::IndexWithFieldnorms, _) => {
+                Self::IndexWithFieldnorms
+            }
+            (_, Self::IndexNoFieldnorms) | (Self::IndexNoFieldnorms, _) => Self::IndexNoFieldnorms,
+            (Self::NoIndex, Self::NoIndex) => Self::NoIndex,
+        }
+    }
+}
+
+impl IntOptionIndex {
+    pub fn is_indexed(&self) -> bool {
+        match *self {
+            Self::NoIndex => false,
+            Self::IndexNoFieldnorms | Self::IndexWithFieldnorms => true,
+        }
+    }
+
+    pub fn has_fieldnorms(&self) -> bool {
+        match *self {
+            Self::NoIndex | Self::IndexNoFieldnorms => false,
+            Self::IndexWithFieldnorms => true,
+        }
+    }
+}
+
+/// Define how an u64, i64, of f64 field should be handled by tantivy.
 #[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
 pub struct IntOptions {
-    indexed: bool,
+    indexed: IntOptionIndex,
     #[serde(skip_serializing_if = "Option::is_none")]
     fast: Option<Cardinality>,
     stored: bool,
@@ -31,7 +71,7 @@ impl IntOptions {
 
     /// Returns true iff the value is indexed.
     pub fn is_indexed(&self) -> bool {
-        self.indexed
+        self.indexed.is_indexed()
     }
 
     /// Returns true iff the value is a fast field.
@@ -39,7 +79,7 @@ impl IntOptions {
         self.fast.is_some()
     }
 
-    /// Set the u64 options as stored.
+    /// Set the field as stored.
     ///
     /// Only the fields that are set as *stored* are
     /// persisted into the Tantivy's store.
@@ -48,16 +88,25 @@ impl IntOptions {
         self
     }
 
-    /// Set the u64 options as indexed.
-    ///
-    /// Setting an integer as indexed will generate
-    /// a posting list for each value taken by the integer.
+    pub fn index_option(&self) -> &IntOptionIndex {
+        &self.indexed
+    }
+
     pub fn set_indexed(mut self) -> IntOptions {
-        self.indexed = true;
+        self.indexed = IntOptionIndex::IndexWithFieldnorms;
         self
     }
 
-    /// Set the u64 options as a single-valued fast field.
+    /// Set the field as indexed.
+    ///
+    /// Setting an integer as indexed will generate
+    /// a posting list for each value taken by the integer.
+    pub fn set_index_option(mut self, int_option_index: IntOptionIndex) -> IntOptions {
+        self.indexed = int_option_index;
+        self
+    }
+
+    /// Set the field as a single-valued fast field.
     ///
     /// Fast fields are designed for random access.
     /// Access time are similar to a random lookup in an array.
@@ -80,7 +129,7 @@ impl IntOptions {
 impl Default for IntOptions {
     fn default() -> IntOptions {
         IntOptions {
-            indexed: false,
+            indexed: IntOptionIndex::NoIndex,
             stored: false,
             fast: None,
         }
@@ -96,7 +145,7 @@ impl From<()> for IntOptions {
 impl From<FastFlag> for IntOptions {
     fn from(_: FastFlag) -> Self {
         IntOptions {
-            indexed: false,
+            indexed: IntOptionIndex::NoIndex,
             stored: false,
             fast: Some(Cardinality::SingleValue),
         }
@@ -106,7 +155,7 @@ impl From<FastFlag> for IntOptions {
 impl From<StoredFlag> for IntOptions {
     fn from(_: StoredFlag) -> Self {
         IntOptions {
-            indexed: false,
+            indexed: IntOptionIndex::NoIndex,
             stored: true,
             fast: None,
         }
@@ -116,7 +165,7 @@ impl From<StoredFlag> for IntOptions {
 impl From<IndexedFlag> for IntOptions {
     fn from(_: IndexedFlag) -> Self {
         IntOptions {
-            indexed: true,
+            indexed: IntOptionIndex::IndexWithFieldnorms,
             stored: false,
             fast: None,
         }
@@ -127,12 +176,12 @@ impl<T: Into<IntOptions>> BitOr<T> for IntOptions {
     type Output = IntOptions;
 
     fn bitor(self, other: T) -> IntOptions {
-        let mut res = IntOptions::default();
         let other = other.into();
-        res.indexed = self.indexed | other.indexed;
-        res.stored = self.stored | other.stored;
-        res.fast = self.fast.or(other.fast);
-        res
+        IntOptions {
+            indexed: self.indexed | other.indexed,
+            stored: self.stored | other.stored,
+            fast: self.fast.or(other.fast),
+        }
     }
 }
 

src/schema/mod.rs

@@ -111,6 +111,7 @@ mod field_entry;
 mod field_type;
 mod field_value;
 
+mod bytes_options;
 mod field;
 mod index_record_option;
 mod int_options;
@@ -142,6 +143,7 @@ pub use self::text_options::TextOptions;
 pub use self::text_options::STRING;
 pub use self::text_options::TEXT;
 
+pub use self::bytes_options::BytesOptions;
 pub use self::flags::{FAST, INDEXED, STORED};
 pub use self::int_options::Cardinality;
 pub use self::int_options::IntOptions;

src/schema/schema.rs

@@ -4,6 +4,7 @@ use std::collections::HashMap;
 use std::sync::Arc;
 
 use super::*;
+use crate::schema::bytes_options::BytesOptions;
 use serde::de::{SeqAccess, Visitor};
 use serde::ser::SerializeSeq;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
@@ -160,8 +161,12 @@ impl SchemaBuilder {
     /// some document features at scoring time.
     /// These can be serializing and stored as a bytes field to
     /// get access rapidly when scoring each document.
-    pub fn add_bytes_field(&mut self, field_name: &str) -> Field {
-        let field_entry = FieldEntry::new_bytes(field_name.to_string());
+    pub fn add_bytes_field<T: Into<BytesOptions>>(
+        &mut self,
+        field_name: &str,
+        field_options: T,
+    ) -> Field {
+        let field_entry = FieldEntry::new_bytes(field_name.to_string(), field_options.into());
         self.add_field(field_entry)
     }
 
@@ -226,6 +231,10 @@ impl Schema {
         &self.0.fields[field.field_id() as usize]
     }
 
+    pub fn num_fields(&self) -> usize {
+        self.0.fields.len()
+    }
+
     /// Return the field name for a given `Field`.
     pub fn get_field_name(&self, field: Field) -> &str {
         self.get_field_entry(field).name()
@@ -381,19 +390,16 @@ impl<'de> Deserialize<'de> for Schema {
 
 /// Error that may happen when deserializing
 /// a document from JSON.
-#[derive(Debug, Fail, PartialEq)]
+#[derive(Debug, Error, PartialEq)]
 pub enum DocParsingError {
     /// The payload given is not valid JSON.
-    #[fail(display = "The provided string is not valid JSON")]
+    #[error("The provided string is not valid JSON")]
     NotJSON(String),
     /// One of the value node could not be parsed.
-    #[fail(display = "The field '{:?}' could not be parsed: {:?}", _0, _1)]
+    #[error("The field '{0:?}' could not be parsed: {1:?}")]
     ValueError(String, ValueParsingError),
     /// The json-document contains a field that is not declared in the schema.
-    #[fail(
-        display = "The document contains a field that is not declared in the schema: {:?}",
-        _0
-    )]
+    #[error("The document contains a field that is not declared in the schema: {0:?}")]
     NoSuchFieldInSchema(String),
 }
 
@@ -442,7 +448,8 @@ mod tests {
     "options": {
       "indexing": {
         "record": "position",
-        "tokenizer": "default"
+        "tokenizer": "default",
+        "fieldnorms": true
       },
       "stored": false
     }
@@ -453,7 +460,8 @@ mod tests {
     "options": {
       "indexing": {
         "record": "basic",
-        "tokenizer": "raw"
+        "tokenizer": "raw",
+        "fieldnorms": false
       },
       "stored": false
     }
@@ -462,7 +470,7 @@ mod tests {
     "name": "count",
     "type": "u64",
     "options": {
-      "indexed": false,
+      "indexed": "no_index",
       "fast": "single",
       "stored": true
     }
@@ -471,7 +479,7 @@ mod tests {
     "name": "popularity",
     "type": "i64",
     "options": {
-      "indexed": false,
+      "indexed": "no_index",
       "fast": "single",
       "stored": true
     }
@@ -480,7 +488,7 @@ mod tests {
     "name": "score",
     "type": "f64",
     "options": {
-      "indexed": true,
+      "indexed": "index_with_fieldnorms",
       "fast": "single",
       "stored": false
     }
@@ -559,14 +567,14 @@ mod tests {
             .convert_named_doc(NamedFieldDocument(named_doc_map))
             .unwrap();
         assert_eq!(
-            doc.get_all(title),
+            doc.get_all(title).collect::<Vec<_>>(),
             vec![
                 &Value::from("title1".to_string()),
                 &Value::from("title2".to_string())
             ]
         );
         assert_eq!(
-            doc.get_all(val),
+            doc.get_all(val).collect::<Vec<_>>(),
             vec![&Value::from(14u64), &Value::from(-1i64)]
         );
     }
@@ -627,9 +635,15 @@ mod tests {
                 doc.get_first(author_field).unwrap().text(),
                 Some("fulmicoton")
             );
-            assert_eq!(doc.get_first(count_field).unwrap().u64_value(), 4);
-            assert_eq!(doc.get_first(popularity_field).unwrap().i64_value(), 10);
-            assert_eq!(doc.get_first(score_field).unwrap().f64_value(), 80.5);
+            assert_eq!(doc.get_first(count_field).unwrap().u64_value(), Some(4));
+            assert_eq!(
+                doc.get_first(popularity_field).unwrap().i64_value(),
+                Some(10)
+            );
+            assert_eq!(
+                doc.get_first(score_field).unwrap().f64_value(),
+                Some(80.5f64)
+            );
         }
         {
             let json_err = schema.parse_document(
@@ -739,7 +753,8 @@ mod tests {
     "options": {
       "indexing": {
         "record": "position",
-        "tokenizer": "default"
+        "tokenizer": "default",
+        "fieldnorms": true
       },
       "stored": false
     }
@@ -748,7 +763,7 @@ mod tests {
     "name": "popularity",
     "type": "i64",
     "options": {
-      "indexed": false,
+      "indexed": "no_index",
       "fast": "single",
       "stored": true
     }
@@ -769,7 +784,8 @@ mod tests {
     "options": {
       "indexing": {
         "record": "basic",
-        "tokenizer": "raw"
+        "tokenizer": "raw",
+        "fieldnorms": false
       },
       "stored": true
     }
@@ -778,7 +794,7 @@ mod tests {
     "name": "_timestamp",
     "type": "date",
     "options": {
-      "indexed": true,
+      "indexed": "index_with_fieldnorms",
       "fast": "single",
       "stored": true
     }
@@ -789,7 +805,8 @@ mod tests {
     "options": {
       "indexing": {
         "record": "position",
-        "tokenizer": "default"
+        "tokenizer": "default",
+        "fieldnorms": true
       },
       "stored": false
     }
@@ -798,7 +815,7 @@ mod tests {
     "name": "popularity",
     "type": "i64",
     "options": {
-      "indexed": false,
+      "indexed": "no_index",
       "fast": "single",
       "stored": true
     }

src/schema/term.rs

@@ -96,7 +96,8 @@ impl Term {
         term
     }
 
-    pub(crate) fn from_field_bytes(field: Field, bytes: &[u8]) -> Term {
+    /// Builds a term bytes.
+    pub fn from_field_bytes(field: Field, bytes: &[u8]) -> Term {
         let mut term = Term::for_field(field);
         term.set_bytes(bytes);
         term
@@ -112,7 +113,7 @@ impl Term {
     pub(crate) fn set_field(&mut self, field: Field) {
         self.0.clear();
         self.0
-            .extend_from_slice(&field.field_id().to_be_bytes()[..]);
+            .extend_from_slice(field.field_id().to_be_bytes().as_ref());
     }
 
     /// Sets a u64 value in the term.
@@ -123,7 +124,7 @@ impl Term {
     /// the natural order of the values.
     pub fn set_u64(&mut self, val: u64) {
         self.0.resize(INT_TERM_LEN, 0u8);
-        self.0[4..12].copy_from_slice(val.to_be_bytes().as_ref());
+        self.set_bytes(val.to_be_bytes().as_ref());
     }
 
     /// Sets a `i64` value in the term.
@@ -136,7 +137,8 @@ impl Term {
         self.set_u64(common::f64_to_u64(val));
     }
 
-    fn set_bytes(&mut self, bytes: &[u8]) {
+    /// Sets the value of a `Bytes` field.
+    pub fn set_bytes(&mut self, bytes: &[u8]) {
         self.0.resize(4, 0u8);
         self.0.extend(bytes);
     }
@@ -151,7 +153,7 @@ impl<B> Term<B>
 where
     B: AsRef<[u8]>,
 {
-    /// Wraps a source of data
+    /// Wraps a object holding bytes
     pub fn wrap(data: B) -> Term<B> {
         Term(data)
     }

src/schema/text_options.rs

@@ -55,6 +55,7 @@ impl Default for TextOptions {
 pub struct TextFieldIndexing {
     record: IndexRecordOption,
     tokenizer: Cow<'static, str>,
+    fieldnorms: bool,
 }
 
 impl Default for TextFieldIndexing {
@@ -62,6 +63,7 @@ impl Default for TextFieldIndexing {
         TextFieldIndexing {
             tokenizer: Cow::Borrowed("default"),
             record: IndexRecordOption::Basic,
+            fieldnorms: false,
         }
     }
 }
@@ -78,6 +80,15 @@ impl TextFieldIndexing {
         &self.tokenizer
     }
 
+    pub fn set_fieldnorms(mut self, fieldnorms: bool) -> TextFieldIndexing {
+        self.fieldnorms = fieldnorms;
+        self
+    }
+
+    pub fn fieldnorms(&self) -> bool {
+        self.fieldnorms
+    }
+
     /// Sets which information should be indexed with the tokens.
     ///
     /// See [IndexRecordOption](./enum.IndexRecordOption.html) for more detail.
@@ -99,6 +110,7 @@ pub const STRING: TextOptions = TextOptions {
     indexing: Some(TextFieldIndexing {
         tokenizer: Cow::Borrowed("raw"),
         record: IndexRecordOption::Basic,
+        fieldnorms: false,
     }),
     stored: false,
 };
@@ -108,6 +120,7 @@ pub const TEXT: TextOptions = TextOptions {
     indexing: Some(TextFieldIndexing {
         tokenizer: Cow::Borrowed("default"),
         record: IndexRecordOption::WithFreqsAndPositions,
+        fieldnorms: true,
     }),
     stored: false,
 };
@@ -117,10 +130,10 @@ impl<T: Into<TextOptions>> BitOr<T> for TextOptions {
 
     fn bitor(self, other: T) -> TextOptions {
         let other = other.into();
-        let mut res = TextOptions::default();
-        res.indexing = self.indexing.or(other.indexing);
-        res.stored = self.stored | other.stored;
-        res
+        TextOptions {
+            indexing: self.indexing.or(other.indexing),
+            stored: self.stored | other.stored,
+        }
     }
 }
 

src/schema/value.rs

@@ -7,7 +7,7 @@ use std::{cmp::Ordering, fmt};
 
 /// Value represents the value of a any field.
 /// It is an enum over all over all of the possible field type.
-#[derive(Debug, Clone, PartialEq, PartialOrd)]
+#[derive(Debug, Clone, PartialEq)]
 pub enum Value {
     /// The str type is used for any text information.
     Str(String),
@@ -28,6 +28,11 @@ pub enum Value {
 }
 
 impl Eq for Value {}
+impl PartialOrd for Value {
+    fn partial_cmp(&self, other: &Value) -> Option<Ordering> {
+        Some(self.cmp(other))
+    }
+}
 impl Ord for Value {
     fn cmp(&self, other: &Self) -> Ordering {
         match (self, other) {
@@ -125,62 +130,76 @@ impl Value {
     /// Returns the text value, provided the value is of the `Str` type.
     /// (Returns None if the value is not of the `Str` type).
     pub fn text(&self) -> Option<&str> {
-        match *self {
-            Value::Str(ref text) => Some(text),
-            _ => None,
+        if let Value::Str(text) = self {
+            Some(text)
+        } else {
+            None
         }
     }
 
     /// Returns the tokenized text, provided the value is of the `PreTokStr` type.
-    /// (Returns None if the value is not of the `PreTokStr` type).
+    ///
+    /// Returns None if the value is not of the `PreTokStr` type.
     pub fn tokenized_text(&self) -> Option<&PreTokenizedString> {
-        match *self {
-            Value::PreTokStr(ref tok_text) => Some(tok_text),
-            _ => None,
+        if let Value::PreTokStr(tokenized_text) = self {
+            Some(tokenized_text)
+        } else {
+            None
         }
     }
 
     /// Returns the u64-value, provided the value is of the `U64` type.
     ///
-    /// # Panics
-    /// If the value is not of type `U64`
-    pub fn u64_value(&self) -> u64 {
-        match *self {
-            Value::U64(ref value) => *value,
-            _ => panic!("This is not a u64 field."),
+    /// Returns None if the value is not of the `U64` type.
+    pub fn u64_value(&self) -> Option<u64> {
+        if let Value::U64(val) = self {
+            Some(*val)
+        } else {
+            None
         }
     }
 
     /// Returns the i64-value, provided the value is of the `I64` type.
     ///
-    /// # Panics
-    /// If the value is not of type `I64`
-    pub fn i64_value(&self) -> i64 {
-        match *self {
-            Value::I64(ref value) => *value,
-            _ => panic!("This is not a i64 field."),
+    /// Return None if the value is not of type `I64`.
+    pub fn i64_value(&self) -> Option<i64> {
+        if let Value::I64(val) = self {
+            Some(*val)
+        } else {
+            None
         }
     }
 
     /// Returns the f64-value, provided the value is of the `F64` type.
     ///
-    /// # Panics
-    /// If the value is not of type `F64`
-    pub fn f64_value(&self) -> f64 {
-        match *self {
-            Value::F64(ref value) => *value,
-            _ => panic!("This is not a f64 field."),
+    /// Return None if the value is not of type `F64`.
+    pub fn f64_value(&self) -> Option<f64> {
+        if let Value::F64(value) = self {
+            Some(*value)
+        } else {
+            None
         }
     }
 
     /// Returns the Date-value, provided the value is of the `Date` type.
     ///
-    /// # Panics
-    /// If the value is not of type `Date`
-    pub fn date_value(&self) -> &DateTime {
-        match *self {
-            Value::Date(ref value) => value,
-            _ => panic!("This is not a date field."),
+    /// Returns None if the value is not of type `Date`.
+    pub fn date_value(&self) -> Option<&DateTime> {
+        if let Value::Date(date) = self {
+            Some(date)
+        } else {
+            None
+        }
+    }
+
+    /// Returns the Bytes-value, provided the value is of the `Bytes` type.
+    ///
+    /// Returns None if the value is not of type `Bytes`.
+    pub fn bytes_value(&self) -> Option<&[u8]> {
+        if let Value::Bytes(bytes) = self {
+            Some(bytes)
+        } else {
+            None
         }
     }
 }

src/snippet/mod.rs

@@ -263,19 +263,17 @@ impl SnippetGenerator {
     ) -> crate::Result<SnippetGenerator> {
         let mut terms = BTreeSet::new();
         query.query_terms(&mut terms);
-        let terms_text: BTreeMap<String, Score> = terms
-            .into_iter()
-            .filter(|term| term.field() == field)
-            .flat_map(|term| {
-                let doc_freq = searcher.doc_freq(&term);
+        let mut terms_text: BTreeMap<String, Score> = Default::default();
+        for term in terms {
+            if term.field() != field {
+                continue;
+            }
+            let doc_freq = searcher.doc_freq(&term)?;
+            if doc_freq > 0 {
                 let score = 1.0 / (1.0 + doc_freq as Score);
-                if doc_freq > 0 {
-                    Some((term.text().to_string(), score))
-                } else {
-                    None
-                }
-            })
-            .collect();
+                terms_text.insert(term.text().to_string(), score);
+            }
+        }
         let tokenizer = searcher.index().tokenizer_for_field(field)?;
         Ok(SnippetGenerator {
             terms_text,
@@ -302,7 +300,6 @@ impl SnippetGenerator {
     pub fn snippet_from_doc(&self, doc: &Document) -> Snippet {
         let text: String = doc
             .get_all(self.field)
-            .into_iter()
             .flat_map(Value::text)
             .collect::<Vec<&str>>()
             .join(" ");

src/space_usage/mod.rs

@@ -307,7 +307,7 @@ mod test {
         let index = Index::create_in_ram(schema.clone());
         let reader = index.reader().unwrap();
         let searcher = reader.searcher();
-        let searcher_space_usage = searcher.space_usage();
+        let searcher_space_usage = searcher.space_usage().unwrap();
         assert_eq!(0, searcher_space_usage.total());
     }
 
@@ -346,7 +346,7 @@ mod test {
 
         let reader = index.reader().unwrap();
         let searcher = reader.searcher();
-        let searcher_space_usage = searcher.space_usage();
+        let searcher_space_usage = searcher.space_usage().unwrap();
         assert!(searcher_space_usage.total() > 0);
         assert_eq!(1, searcher_space_usage.segments().len());
 
@@ -386,7 +386,7 @@ mod test {
 
         let reader = index.reader().unwrap();
         let searcher = reader.searcher();
-        let searcher_space_usage = searcher.space_usage();
+        let searcher_space_usage = searcher.space_usage().unwrap();
         assert!(searcher_space_usage.total() > 0);
         assert_eq!(1, searcher_space_usage.segments().len());
 
@@ -425,7 +425,7 @@ mod test {
         }
         let reader = index.reader().unwrap();
         let searcher = reader.searcher();
-        let searcher_space_usage = searcher.space_usage();
+        let searcher_space_usage = searcher.space_usage().unwrap();
         assert!(searcher_space_usage.total() > 0);
         assert_eq!(1, searcher_space_usage.segments().len());
 
@@ -446,49 +446,47 @@ mod test {
     }
 
     #[test]
-    fn test_deletes() {
+    fn test_deletes() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let name = schema_builder.add_u64_field("name", INDEXED);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema.clone());
 
         {
-            let mut index_writer = index.writer_for_tests().unwrap();
+            let mut index_writer = index.writer_for_tests()?;
             index_writer.add_document(doc!(name => 1u64));
             index_writer.add_document(doc!(name => 2u64));
             index_writer.add_document(doc!(name => 3u64));
             index_writer.add_document(doc!(name => 4u64));
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
         }
 
         {
-            let mut index_writer2 = index.writer(50_000_000).unwrap();
+            let mut index_writer2 = index.writer(50_000_000)?;
             index_writer2.delete_term(Term::from_field_u64(name, 2u64));
             index_writer2.delete_term(Term::from_field_u64(name, 3u64));
-
             // ok, now we should have a deleted doc
-            index_writer2.commit().unwrap();
+            index_writer2.commit()?;
         }
 
-        let reader = index.reader().unwrap();
+        let reader = index.reader()?;
         let searcher = reader.searcher();
-        let searcher_space_usage = searcher.space_usage();
+        let searcher_space_usage = searcher.space_usage()?;
         assert!(searcher_space_usage.total() > 0);
         assert_eq!(1, searcher_space_usage.segments().len());
 
-        let segment = &searcher_space_usage.segments()[0];
-        assert!(segment.total() > 0);
+        let segment_space_usage = &searcher_space_usage.segments()[0];
+        assert!(segment_space_usage.total() > 0);
 
-        assert_eq!(2, segment.num_docs());
+        assert_eq!(2, segment_space_usage.num_docs());
 
-        expect_single_field(segment.termdict(), &name, 1, 512);
-        expect_single_field(segment.postings(), &name, 1, 512);
-        assert_eq!(0, segment.positions().total());
-        assert_eq!(0, segment.positions_skip_idx().total());
-        assert_eq!(0, segment.fast_fields().total());
-        expect_single_field(segment.fieldnorms(), &name, 1, 512);
-        // TODO: understand why the following fails
-        //        assert_eq!(0, segment.store().total());
-        assert!(segment.deletes() > 0);
+        expect_single_field(segment_space_usage.termdict(), &name, 1, 512);
+        expect_single_field(segment_space_usage.postings(), &name, 1, 512);
+        assert_eq!(0, segment_space_usage.positions().total());
+        assert_eq!(0, segment_space_usage.positions_skip_idx().total());
+        assert_eq!(0, segment_space_usage.fast_fields().total());
+        expect_single_field(segment_space_usage.fieldnorms(), &name, 1, 512);
+        assert!(segment_space_usage.deletes() > 0);
+        Ok(())
     }
 }

src/store/compression_brotli.rs

@@ -0,0 +1,20 @@
+use std::io;
+
+/// Name of the compression scheme used in the doc store.
+///
+/// This name is appended to the version string of tantivy.
+pub const COMPRESSION: &'static str = "brotli";
+
+pub fn compress(mut uncompressed: &[u8], compressed: &mut Vec<u8>) -> io::Result<()> {
+    let mut params = brotli::enc::BrotliEncoderParams::default();
+    params.quality = 5;
+    compressed.clear();
+    brotli::BrotliCompress(&mut uncompressed, compressed, &params)?;
+    Ok(())
+}
+
+pub fn decompress(mut compressed: &[u8], decompressed: &mut Vec<u8>) -> io::Result<()> {
+    decompressed.clear();
+    brotli::BrotliDecompress(&mut compressed, decompressed)?;
+    Ok(())
+}

src/store/mod.rs

@@ -5,7 +5,7 @@ A field needs to be marked as stored in the schema in
 order to be handled in the `Store`.
 
 Internally, documents (or rather their stored fields) are serialized to a buffer.
-When the buffer exceeds 16K, the buffer is compressed using `LZ4`
+When the buffer exceeds 16K, the buffer is compressed using `brotli`, `LZ4` or `snappy`
 and the resulting block is written to disk.
 
 One can then request for a specific `DocId`.
@@ -39,6 +39,9 @@ mod writer;
 pub use self::reader::StoreReader;
 pub use self::writer::StoreWriter;
 
+#[cfg(all(feature = "lz4", feature = "brotli"))]
+compile_error!("feature `lz4` or `brotli` must not be enabled together.");
+
 #[cfg(feature = "lz4")]
 mod compression_lz4;
 #[cfg(feature = "lz4")]
@@ -46,11 +49,18 @@ pub use self::compression_lz4::COMPRESSION;
 #[cfg(feature = "lz4")]
 use self::compression_lz4::{compress, decompress};
 
-#[cfg(not(feature = "lz4"))]
+#[cfg(feature = "brotli")]
+mod compression_brotli;
+#[cfg(feature = "brotli")]
+pub use self::compression_brotli::COMPRESSION;
+#[cfg(feature = "brotli")]
+use self::compression_brotli::{compress, decompress};
+
+#[cfg(not(any(feature = "lz4", feature = "brotli")))]
 mod compression_snap;
-#[cfg(not(feature = "lz4"))]
+#[cfg(not(any(feature = "lz4", feature = "brotli")))]
 pub use self::compression_snap::COMPRESSION;
-#[cfg(not(feature = "lz4"))]
+#[cfg(not(any(feature = "lz4", feature = "brotli")))]
 use self::compression_snap::{compress, decompress};
 
 #[cfg(test)]
@@ -103,19 +113,18 @@ pub mod tests {
     }
 
     #[test]
-    fn test_store() {
+    fn test_store() -> crate::Result<()> {
         let path = Path::new("store");
-        let mut directory = RAMDirectory::create();
-        let store_file = directory.open_write(path).unwrap();
-        let schema = write_lorem_ipsum_store(store_file, 1_000);
+        let directory = RAMDirectory::create();
+        let store_wrt = directory.open_write(path)?;
+        let schema = write_lorem_ipsum_store(store_wrt, 1_000);
         let field_title = schema.get_field("title").unwrap();
-        let store_source = directory.open_read(path).unwrap();
-        let store = StoreReader::from_source(store_source);
+        let store_file = directory.open_read(path)?;
+        let store = StoreReader::open(store_file)?;
         for i in 0..1_000 {
             assert_eq!(
                 *store
-                    .get(i)
-                    .unwrap()
+                    .get(i)?
                     .get_first(field_title)
                     .unwrap()
                     .text()
@@ -123,6 +132,7 @@ pub mod tests {
                 format!("Doc {}", i)
             );
         }
+        Ok(())
     }
 }
 
@@ -139,7 +149,7 @@ mod bench {
     #[bench]
     #[cfg(feature = "mmap")]
     fn bench_store_encode(b: &mut Bencher) {
-        let mut directory = RAMDirectory::create();
+        let directory = RAMDirectory::create();
         let path = Path::new("store");
         b.iter(|| {
             write_lorem_ipsum_store(directory.open_write(path).unwrap(), 1_000);
@@ -149,11 +159,11 @@ mod bench {
 
     #[bench]
     fn bench_store_decode(b: &mut Bencher) {
-        let mut directory = RAMDirectory::create();
+        let directory = RAMDirectory::create();
         let path = Path::new("store");
         write_lorem_ipsum_store(directory.open_write(path).unwrap(), 1_000);
-        let store_source = directory.open_read(path).unwrap();
-        let store = StoreReader::from_source(store_source);
+        let store_file = directory.open_read(path).unwrap();
+        let store = StoreReader::open(store_file).unwrap();
         b.iter(|| {
             store.get(12).unwrap();
         });

src/store/reader.rs

@@ -1,8 +1,8 @@
 use super::decompress;
 use super::skiplist::SkipList;
-use crate::common::BinarySerializable;
 use crate::common::VInt;
-use crate::directory::ReadOnlySource;
+use crate::common::{BinarySerializable, HasLen};
+use crate::directory::{FileSlice, OwnedBytes};
 use crate::schema::Document;
 use crate::space_usage::StoreSpaceUsage;
 use crate::DocId;
@@ -13,8 +13,8 @@ use std::mem::size_of;
 /// Reads document off tantivy's [`Store`](./index.html)
 #[derive(Clone)]
 pub struct StoreReader {
-    data: ReadOnlySource,
-    offset_index_source: ReadOnlySource,
+    data: FileSlice,
+    offset_index_file: OwnedBytes,
     current_block_offset: RefCell<usize>,
     current_block: RefCell<Vec<u8>>,
     max_doc: DocId,
@@ -22,19 +22,20 @@ pub struct StoreReader {
 
 impl StoreReader {
     /// Opens a store reader
-    pub fn from_source(data: ReadOnlySource) -> StoreReader {
-        let (data_source, offset_index_source, max_doc) = split_source(data);
-        StoreReader {
-            data: data_source,
-            offset_index_source,
+    // TODO rename open
+    pub fn open(store_file: FileSlice) -> io::Result<StoreReader> {
+        let (data_file, offset_index_file, max_doc) = split_file(store_file)?;
+        Ok(StoreReader {
+            data: data_file,
+            offset_index_file: offset_index_file.read_bytes()?,
             current_block_offset: RefCell::new(usize::max_value()),
             current_block: RefCell::new(Vec::new()),
             max_doc,
-        }
+        })
     }
 
     pub(crate) fn block_index(&self) -> SkipList<'_, u64> {
-        SkipList::from(self.offset_index_source.as_slice())
+        SkipList::from(self.offset_index_file.as_slice())
     }
 
     fn block_offset(&self, doc_id: DocId) -> (DocId, u64) {
@@ -44,23 +45,22 @@ impl StoreReader {
             .unwrap_or((0u32, 0u64))
     }
 
-    pub(crate) fn block_data(&self) -> &[u8] {
-        self.data.as_slice()
+    pub(crate) fn block_data(&self) -> io::Result<OwnedBytes> {
+        self.data.read_bytes()
     }
 
-    fn compressed_block(&self, addr: usize) -> &[u8] {
-        let total_buffer = self.data.as_slice();
-        let mut buffer = &total_buffer[addr..];
-        let block_len = u32::deserialize(&mut buffer).expect("") as usize;
-        &buffer[..block_len]
+    fn compressed_block(&self, addr: usize) -> io::Result<OwnedBytes> {
+        let (block_len_bytes, block_body) = self.data.slice_from(addr).split(4);
+        let block_len = u32::deserialize(&mut block_len_bytes.read_bytes()?)?;
+        block_body.slice_to(block_len as usize).read_bytes()
     }
 
     fn read_block(&self, block_offset: usize) -> io::Result<()> {
         if block_offset != *self.current_block_offset.borrow() {
             let mut current_block_mut = self.current_block.borrow_mut();
             current_block_mut.clear();
-            let compressed_block = self.compressed_block(block_offset);
-            decompress(compressed_block, &mut current_block_mut)?;
+            let compressed_block = self.compressed_block(block_offset)?;
+            decompress(compressed_block.as_slice(), &mut current_block_mut)?;
             *self.current_block_offset.borrow_mut() = block_offset;
         }
         Ok(())
@@ -69,7 +69,7 @@ impl StoreReader {
     /// Reads a given document.
     ///
     /// Calling `.get(doc)` is relatively costly as it requires
-    /// decompressing a LZ4-compressed block.
+    /// decompressing a compressed block.
     ///
     /// It should not be called to score documents
     /// for instance.
@@ -89,21 +89,21 @@ impl StoreReader {
 
     /// Summarize total space usage of this store reader.
     pub fn space_usage(&self) -> StoreSpaceUsage {
-        StoreSpaceUsage::new(self.data.len(), self.offset_index_source.len())
+        StoreSpaceUsage::new(self.data.len(), self.offset_index_file.len())
     }
 }
 
-fn split_source(data: ReadOnlySource) -> (ReadOnlySource, ReadOnlySource, DocId) {
+fn split_file(data: FileSlice) -> io::Result<(FileSlice, FileSlice, DocId)> {
     let data_len = data.len();
     let footer_offset = data_len - size_of::<u64>() - size_of::<u32>();
-    let serialized_offset: ReadOnlySource = data.slice(footer_offset, data_len);
+    let serialized_offset: OwnedBytes = data.slice(footer_offset, data_len).read_bytes()?;
     let mut serialized_offset_buf = serialized_offset.as_slice();
-    let offset = u64::deserialize(&mut serialized_offset_buf).unwrap();
+    let offset = u64::deserialize(&mut serialized_offset_buf)?;
     let offset = offset as usize;
-    let max_doc = u32::deserialize(&mut serialized_offset_buf).unwrap();
-    (
+    let max_doc = u32::deserialize(&mut serialized_offset_buf)?;
+    Ok((
         data.slice(0, offset),
         data.slice(offset, footer_offset),
         max_doc,
-    )
+    ))
 }

src/store/skiplist/skiplist_builder.rs

@@ -68,19 +68,17 @@ impl<T: BinarySerializable> SkipListBuilder<T> {
     }
 
     pub fn insert(&mut self, key: u64, dest: &T) -> io::Result<()> {
-        let mut layer_id = 0;
         let mut skip_pointer = self.data_layer.insert(key, dest)?;
-        loop {
-            skip_pointer = match skip_pointer {
-                Some((skip_doc_id, skip_offset)) => self
+        for layer_id in 0.. {
+            if let Some((skip_doc_id, skip_offset)) = skip_pointer {
+                skip_pointer = self
                     .get_skip_layer(layer_id)
-                    .insert(skip_doc_id, &skip_offset)?,
-                None => {
-                    return Ok(());
-                }
-            };
-            layer_id += 1;
+                    .insert(skip_doc_id, &skip_offset)?;
+            } else {
+                break;
+            }
         }
+        Ok(())
     }
 
     pub fn write<W: Write>(self, output: &mut W) -> io::Result<()> {

src/store/writer.rs

@@ -75,7 +75,8 @@ impl StoreWriter {
         let start_offset = self.writer.written_bytes() as u64;
 
         // just bulk write all of the block of the given reader.
-        self.writer.write_all(store_reader.block_data())?;
+        self.writer
+            .write_all(store_reader.block_data()?.as_slice())?;
 
         // concatenate the index of the `store_reader`, after translating
         // its start doc id and its start file offset.

src/termdict/mod.rs

@@ -36,9 +36,9 @@ pub use self::termdict::{TermDictionary, TermDictionaryBuilder};
 mod tests {
     use super::{TermDictionary, TermDictionaryBuilder, TermStreamer};
     use crate::core::Index;
-    use crate::directory::{Directory, RAMDirectory, ReadOnlySource};
+    use crate::directory::{Directory, FileSlice, RAMDirectory};
     use crate::postings::TermInfo;
-    use crate::schema::{Document, Schema, TEXT};
+    use crate::schema::{Schema, TEXT};
     use std::path::PathBuf;
     use std::str;
 
@@ -59,7 +59,7 @@ mod tests {
     }
 
     #[test]
-    fn test_term_ordinals() {
+    fn test_term_ordinals() -> crate::Result<()> {
         const COUNTRIES: [&'static str; 7] = [
             "San Marino",
             "Serbia",
@@ -69,45 +69,40 @@ mod tests {
             "Sweden",
             "Switzerland",
         ];
-        let mut directory = RAMDirectory::create();
+        let directory = RAMDirectory::create();
         let path = PathBuf::from("TermDictionary");
         {
-            let write = directory.open_write(&path).unwrap();
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(write).unwrap();
+            let write = directory.open_write(&path)?;
+            let mut term_dictionary_builder = TermDictionaryBuilder::create(write)?;
             for term in COUNTRIES.iter() {
-                term_dictionary_builder
-                    .insert(term.as_bytes(), &make_term_info(0u64))
-                    .unwrap();
+                term_dictionary_builder.insert(term.as_bytes(), &make_term_info(0u64))?;
             }
-            term_dictionary_builder.finish().unwrap();
+            term_dictionary_builder.finish()?;
         }
-        let source = directory.open_read(&path).unwrap();
-        let term_dict: TermDictionary = TermDictionary::from_source(&source);
+        let term_file = directory.open_read(&path)?;
+        let term_dict: TermDictionary = TermDictionary::open(term_file)?;
         for (term_ord, term) in COUNTRIES.iter().enumerate() {
             assert_eq!(term_dict.term_ord(term).unwrap(), term_ord as u64);
             let mut bytes = vec![];
             assert!(term_dict.ord_to_term(term_ord as u64, &mut bytes));
             assert_eq!(bytes, term.as_bytes());
         }
+        Ok(())
     }
 
     #[test]
-    fn test_term_dictionary_simple() {
-        let mut directory = RAMDirectory::create();
+    fn test_term_dictionary_simple() -> crate::Result<()> {
+        let directory = RAMDirectory::create();
         let path = PathBuf::from("TermDictionary");
         {
-            let write = directory.open_write(&path).unwrap();
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(write).unwrap();
-            term_dictionary_builder
-                .insert("abc".as_bytes(), &make_term_info(34u64))
-                .unwrap();
-            term_dictionary_builder
-                .insert("abcd".as_bytes(), &make_term_info(346u64))
-                .unwrap();
-            term_dictionary_builder.finish().unwrap();
+            let write = directory.open_write(&path)?;
+            let mut term_dictionary_builder = TermDictionaryBuilder::create(write)?;
+            term_dictionary_builder.insert("abc".as_bytes(), &make_term_info(34u64))?;
+            term_dictionary_builder.insert("abcd".as_bytes(), &make_term_info(346u64))?;
+            term_dictionary_builder.finish()?;
         }
-        let source = directory.open_read(&path).unwrap();
-        let term_dict: TermDictionary = TermDictionary::from_source(&source);
+        let file = directory.open_read(&path)?;
+        let term_dict: TermDictionary = TermDictionary::open(file)?;
         assert_eq!(term_dict.get("abc").unwrap().doc_freq, 34u32);
         assert_eq!(term_dict.get("abcd").unwrap().doc_freq, 346u32);
         let mut stream = term_dict.stream();
@@ -130,43 +125,26 @@ mod tests {
             assert_eq!(stream.value().doc_freq, 346u32);
         }
         assert!(!stream.advance());
+        Ok(())
     }
 
     #[test]
-    fn test_term_iterator() {
+    fn test_term_iterator() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let index = Index::create_in_ram(schema_builder.build());
         {
-            let mut index_writer = index.writer_for_tests().unwrap();
-            {
-                {
-                    let mut doc = Document::default();
-                    doc.add_text(text_field, "a b d f");
-                    index_writer.add_document(doc);
-                }
-                index_writer.commit().unwrap();
-            }
-            {
-                {
-                    let mut doc = Document::default();
-                    doc.add_text(text_field, "a b c d f");
-                    index_writer.add_document(doc);
-                }
-                index_writer.commit().unwrap();
-            }
-            {
-                {
-                    let mut doc = Document::default();
-                    doc.add_text(text_field, "e f");
-                    index_writer.add_document(doc);
-                }
-                index_writer.commit().unwrap();
-            }
+            let mut index_writer = index.writer_for_tests()?;
+            index_writer.add_document(doc!(text_field=>"a b d f"));
+            index_writer.commit()?;
+            index_writer.add_document(doc!(text_field=>"a b c d f"));
+            index_writer.commit()?;
+            index_writer.add_document(doc!(text_field => "e f"));
+            index_writer.commit()?;
         }
-        let searcher = index.reader().unwrap().searcher();
+        let searcher = index.reader()?.searcher();
 
-        let field_searcher = searcher.field(text_field);
+        let field_searcher = searcher.field(text_field)?;
         let mut term_it = field_searcher.terms();
         let mut term_string = String::new();
         while term_it.advance() {
@@ -174,10 +152,11 @@ mod tests {
             term_string.push_str(str::from_utf8(term_it.key()).expect("test"));
         }
         assert_eq!(&*term_string, "abcdef");
+        Ok(())
     }
 
     #[test]
-    fn test_term_dictionary_stream() {
+    fn test_term_dictionary_stream() -> crate::Result<()> {
         let ids: Vec<_> = (0u32..10_000u32)
             .map(|i| (format!("doc{:0>6}", i), i))
             .collect();
@@ -190,8 +169,8 @@ mod tests {
             }
             term_dictionary_builder.finish().unwrap()
         };
-        let source = ReadOnlySource::from(buffer);
-        let term_dictionary: TermDictionary = TermDictionary::from_source(&source);
+        let term_file = FileSlice::from(buffer);
+        let term_dictionary: TermDictionary = TermDictionary::open(term_file)?;
         {
             let mut streamer = term_dictionary.stream();
             let mut i = 0;
@@ -203,28 +182,26 @@ mod tests {
             }
         }
 
-        let &(ref key, ref _v) = &ids[2047];
-        term_dictionary.get(key.as_bytes());
+        let &(ref key, ref val) = &ids[2047];
+        assert_eq!(
+            term_dictionary.get(key.as_bytes()),
+            Some(make_term_info(*val as u64))
+        );
+        Ok(())
     }
 
     #[test]
-    fn test_stream_high_range_prefix_suffix() {
+    fn test_stream_high_range_prefix_suffix() -> crate::Result<()> {
         let buffer: Vec<u8> = {
             let mut term_dictionary_builder = TermDictionaryBuilder::create(vec![]).unwrap();
             // term requires more than 16bits
-            term_dictionary_builder
-                .insert("abcdefghijklmnopqrstuvwxy", &make_term_info(1))
-                .unwrap();
-            term_dictionary_builder
-                .insert("abcdefghijklmnopqrstuvwxyz", &make_term_info(2))
-                .unwrap();
-            term_dictionary_builder
-                .insert("abr", &make_term_info(2))
-                .unwrap();
-            term_dictionary_builder.finish().unwrap()
+            term_dictionary_builder.insert("abcdefghijklmnopqrstuvwxy", &make_term_info(1))?;
+            term_dictionary_builder.insert("abcdefghijklmnopqrstuvwxyz", &make_term_info(2))?;
+            term_dictionary_builder.insert("abr", &make_term_info(2))?;
+            term_dictionary_builder.finish()?
         };
-        let source = ReadOnlySource::from(buffer);
-        let term_dictionary: TermDictionary = TermDictionary::from_source(&source);
+        let term_dict_file = FileSlice::from(buffer);
+        let term_dictionary: TermDictionary = TermDictionary::open(term_dict_file)?;
         let mut kv_stream = term_dictionary.stream();
         assert!(kv_stream.advance());
         assert_eq!(kv_stream.key(), "abcdefghijklmnopqrstuvwxy".as_bytes());
@@ -235,10 +212,11 @@ mod tests {
         assert!(kv_stream.advance());
         assert_eq!(kv_stream.key(), "abr".as_bytes());
         assert!(!kv_stream.advance());
+        Ok(())
     }
 
     #[test]
-    fn test_stream_range() {
+    fn test_stream_range() -> crate::Result<()> {
         let ids: Vec<_> = (0u32..10_000u32)
             .map(|i| (format!("doc{:0>6}", i), i))
             .collect();
@@ -252,9 +230,9 @@ mod tests {
             term_dictionary_builder.finish().unwrap()
         };
 
-        let source = ReadOnlySource::from(buffer);
+        let file = FileSlice::from(buffer);
 
-        let term_dictionary: TermDictionary = TermDictionary::from_source(&source);
+        let term_dictionary: TermDictionary = TermDictionary::open(file)?;
         {
             for i in (0..20).chain(6000..8_000) {
                 let &(ref target_key, _) = &ids[i];
@@ -305,10 +283,11 @@ mod tests {
                 }
             }
         }
+        Ok(())
     }
 
     #[test]
-    fn test_empty_string() {
+    fn test_empty_string() -> crate::Result<()> {
         let buffer: Vec<u8> = {
             let mut term_dictionary_builder = TermDictionaryBuilder::create(vec![]).unwrap();
             term_dictionary_builder
@@ -319,30 +298,29 @@ mod tests {
                 .unwrap();
             term_dictionary_builder.finish().unwrap()
         };
-        let source = ReadOnlySource::from(buffer);
-        let term_dictionary: TermDictionary = TermDictionary::from_source(&source);
+        let file = FileSlice::from(buffer);
+        let term_dictionary: TermDictionary = TermDictionary::open(file)?;
         let mut stream = term_dictionary.stream();
         assert!(stream.advance());
         assert!(stream.key().is_empty());
         assert!(stream.advance());
         assert_eq!(stream.key(), &[1u8]);
         assert!(!stream.advance());
+        Ok(())
     }
 
     #[test]
-    fn test_stream_range_boundaries() {
+    fn test_stream_range_boundaries() -> crate::Result<()> {
         let buffer: Vec<u8> = {
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(vec![]).unwrap();
+            let mut term_dictionary_builder = TermDictionaryBuilder::create(Vec::new())?;
             for i in 0u8..10u8 {
                 let number_arr = [i; 1];
-                term_dictionary_builder
-                    .insert(&number_arr, &make_term_info(i as u64))
-                    .unwrap();
+                term_dictionary_builder.insert(&number_arr, &make_term_info(i as u64))?;
             }
-            term_dictionary_builder.finish().unwrap()
+            term_dictionary_builder.finish()?
         };
-        let source = ReadOnlySource::from(buffer);
-        let term_dictionary: TermDictionary = TermDictionary::from_source(&source);
+        let file = FileSlice::from(buffer);
+        let term_dictionary: TermDictionary = TermDictionary::open(file)?;
 
         let value_list = |mut streamer: TermStreamer<'_>, backwards: bool| {
             let mut res: Vec<u32> = vec![];
@@ -430,10 +408,11 @@ mod tests {
                 .into_stream();
             assert_eq!(value_list(range, true), vec![0u32, 1u32, 2u32, 3u32, 4u32]);
         }
+        Ok(())
     }
 
     #[test]
-    fn test_automaton_search() {
+    fn test_automaton_search() -> crate::Result<()> {
         use crate::query::DFAWrapper;
         use levenshtein_automata::LevenshteinAutomatonBuilder;
 
@@ -447,20 +426,18 @@ mod tests {
             "Switzerland",
         ];
 
-        let mut directory = RAMDirectory::create();
+        let directory = RAMDirectory::create();
         let path = PathBuf::from("TermDictionary");
         {
-            let write = directory.open_write(&path).unwrap();
-            let mut term_dictionary_builder = TermDictionaryBuilder::create(write).unwrap();
+            let write = directory.open_write(&path)?;
+            let mut term_dictionary_builder = TermDictionaryBuilder::create(write)?;
             for term in COUNTRIES.iter() {
-                term_dictionary_builder
-                    .insert(term.as_bytes(), &make_term_info(0u64))
-                    .unwrap();
+                term_dictionary_builder.insert(term.as_bytes(), &make_term_info(0u64))?;
             }
-            term_dictionary_builder.finish().unwrap();
+            term_dictionary_builder.finish()?;
         }
-        let source = directory.open_read(&path).unwrap();
-        let term_dict: TermDictionary = TermDictionary::from_source(&source);
+        let file = directory.open_read(&path)?;
+        let term_dict: TermDictionary = TermDictionary::open(file)?;
 
         // We can now build an entire dfa.
         let lev_automaton_builder = LevenshteinAutomatonBuilder::new(2, true);
@@ -472,5 +449,6 @@ mod tests {
         assert!(range.advance());
         assert_eq!("Spain".as_bytes(), range.key());
         assert!(!range.advance());
+        Ok(())
     }
 }