Address #656

Broke the reference loop to make sure that the watch_router can
be dropped, and the thread exits.

.travis.yml

@@ -47,7 +47,6 @@ matrix:
 before_install:
   - set -e
   - rustup self update
-  - rustup component add rustfmt
 
 install:
   - sh ci/install.sh
@@ -61,7 +60,6 @@ before_script:
 
 script:
   - bash ci/script.sh
-  - cargo fmt --all -- --check
 
 before_deploy:
   - sh ci/before_deploy.sh

CHANGELOG.md

@@ -2,18 +2,12 @@ Tantivy 0.11.0
 =====================
 
 - Added f64 field. Internally reuse u64 code the same way i64 does (@fdb-hiroshima)
-- Various bugfixes in the query parser.
-    - Better handling of hyphens in query parser. (#609)
-    - Better handling of whitespaces.
-- Closes #498 - add support for Elastic-style unbounded range queries for alphanumeric types eg. "title:>hello", "weight:>=70.5", "height:<200" (@petr-tik)
-- API change around `Box<BoxableTokenizer>`. See detail in #629
-- Avoid rebuilding Regex automaton whenever a regex query is reused. #630 (@brainlock)
- 
-## How to update?
 
-- `Box<dyn BoxableTokenizer>` has been replaced by a `BoxedTokenizer` struct.
+
-- Regex are now compiled when the `RegexQuery` instance is built. As a result, it can now return
+Tantivy 0.10.2
-an error and handling the `Result` is required.
+=====================
+
+- Closes #656. Solving memory leak.
 
 Tantivy 0.10.1
 =====================

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy"
-version = "0.11.0"
+version = "0.10.2"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
@@ -15,7 +15,7 @@ edition = "2018"
 [dependencies]
 base64 = "0.10.0"
 byteorder = "1.0"
-once_cell = "1.0"
+once_cell = "0.2"
 regex = "1.0"
 tantivy-fst = "0.1"
 memmap = {version = "0.7", optional=true}
@@ -25,6 +25,7 @@ atomicwrites = {version="0.2.2", optional=true}
 tempfile = "3.0"
 log = "0.4"
 combine = ">=3.6.0,<4.0.0"
+tempdir = "0.3"
 serde = "1.0"
 serde_derive = "1.0"
 serde_json = "1.0"
@@ -35,7 +36,7 @@ levenshtein_automata = {version="0.1", features=["fst_automaton"]}
 notify = {version="4", optional=true}
 bit-set = "0.5"
 uuid = { version = "0.7.2", features = ["v4", "serde"] }
-crossbeam = "0.7"
+crossbeam = "0.5"
 futures = "0.1"
 futures-cpupool = "0.1"
 owning_ref = "0.4"
@@ -54,10 +55,6 @@ murmurhash32 = "0.2"
 chrono = "0.4"
 smallvec = "0.6"
 
-tantivy-schema = {path= "./tantivy-schema"}
-tantivy-tokenizer = {path= "./tantivy-tokenizer"}
-tantivy-common = {path="./tantivy-common"}
-
 [target.'cfg(windows)'.dependencies]
 winapi = "0.3"
 
@@ -90,6 +87,7 @@ travis-ci = { repository = "tantivy-search/tantivy" }
 [dev-dependencies.fail]
 features = ["failpoints"]
 
+
 # Following the "fail" crate best practises, we isolate
 # tests that define specific behavior in fail check points
 # in a different binary.
@@ -101,7 +99,3 @@ features = ["failpoints"]
 name = "failpoints"
 path = "tests/failpoints/mod.rs"
 required-features = ["fail/failpoints"]
-
-
-[workspace]
-members = ["tantivy-schema", "tantivy-common", "tantivy-tokenizer"]

examples/basic_search.rs

@@ -5,23 +5,26 @@
 //
 // We will :
 // - define our schema
-// - create an index in a directory
+// = create an index in a directory
-// - index a few documents into our index
+// - index few documents in our index
-// - search for the best document matching a basic query
+// - search for the best document matchings "sea whale"
-// - retrieve the best document's original content.
+// - retrieve the best document original content.
 
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
-use tantivy::{doc, Index, ReloadPolicy};
+use tantivy::Index;
-use tempfile::TempDir;
+use tantivy::ReloadPolicy;
+use tempdir::TempDir;
 
 fn main() -> tantivy::Result<()> {
     // Let's create a temporary directory for the
     // sake of this example
-    let index_path = TempDir::new()?;
+    let index_path = TempDir::new("tantivy_example_dir")?;
 
     // # Defining the schema
     //
@@ -30,7 +33,7 @@ fn main() -> tantivy::Result<()> {
     // and for each field, its type and "the way it should
     // be indexed".
 
-    // First we need to define a schema ...
+    // first we need to define a schema ...
     let mut schema_builder = Schema::builder();
 
     // Our first field is title.
@@ -45,7 +48,7 @@ fn main() -> tantivy::Result<()> {
     //
     // `STORED` means that the field will also be saved
     // in a compressed, row-oriented key-value store.
-    // This store is useful for reconstructing the
+    // This store is useful to reconstruct the
     // documents that were selected during the search phase.
     schema_builder.add_text_field("title", TEXT | STORED);
 
@@ -54,7 +57,8 @@ fn main() -> tantivy::Result<()> {
     // need to be able to be able to retrieve it
     // for our application.
     //
-    // We can make our index lighter by omitting the `STORED` flag.
+    // We can make our index lighter and
+    // by omitting `STORED` flag.
     schema_builder.add_text_field("body", TEXT);
 
     let schema = schema_builder.build();
@@ -67,7 +71,7 @@ fn main() -> tantivy::Result<()> {
     // with our schema in the directory.
     let index = Index::create_in_dir(&index_path, schema.clone())?;
 
-    // To insert a document we will need an index writer.
+    // To insert document we need an index writer.
     // There must be only one writer at a time.
     // This single `IndexWriter` is already
     // multithreaded.
@@ -145,8 +149,8 @@ fn main() -> tantivy::Result<()> {
     // At this point our documents are not searchable.
     //
     //
-    // We need to call `.commit()` explicitly to force the
+    // We need to call .commit() explicitly to force the
-    // `index_writer` to finish processing the documents in the queue,
+    // index_writer to finish processing the documents in the queue,
     // flush the current index to the disk, and advertise
     // the existence of new documents.
     //
@@ -158,14 +162,14 @@ fn main() -> tantivy::Result<()> {
     // persistently indexed.
     //
     // In the scenario of a crash or a power failure,
-    // tantivy behaves as if it has rolled back to its last
+    // tantivy behaves as if has rolled back to its last
     // commit.
 
     // # Searching
     //
     // ### Searcher
     //
-    // A reader is required first in order to search an index.
+    // A reader is required to get search the index.
     // It acts as a `Searcher` pool that reloads itself,
     // depending on a `ReloadPolicy`.
     //
@@ -181,7 +185,7 @@ fn main() -> tantivy::Result<()> {
 
     // We now need to acquire a searcher.
     //
-    // A searcher points to a snapshotted, immutable version of the index.
+    // A searcher points to snapshotted, immutable version of the index.
     //
     // Some search experience might require more than
     // one query. Using the same searcher ensures that all of these queries will run on the
@@ -201,7 +205,7 @@ fn main() -> tantivy::Result<()> {
     // in both title and body.
     let query_parser = QueryParser::for_index(&index, vec![title, body]);
 
-    // `QueryParser` may fail if the query is not in the right
+    // QueryParser may fail if the query is not in the right
     // format. For user facing applications, this can be a problem.
     // A ticket has been opened regarding this problem.
     let query = query_parser.parse_query("sea whale")?;
@@ -217,7 +221,7 @@ fn main() -> tantivy::Result<()> {
     //
     // We are not interested in all of the documents but
     // only in the top 10. Keeping track of our top 10 best documents
-    // is the role of the `TopDocs` collector.
+    // is the role of the TopDocs.
 
     // We can now perform our query.
     let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;

examples/custom_collector.rs

@@ -9,12 +9,15 @@
 
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::{Collector, SegmentCollector};
 use tantivy::fastfield::FastFieldReader;
 use tantivy::query::QueryParser;
 use tantivy::schema::Field;
 use tantivy::schema::{Schema, FAST, INDEXED, TEXT};
-use tantivy::{doc, Index, SegmentReader, TantivyError};
+use tantivy::SegmentReader;
+use tantivy::{Index, TantivyError};
 
 #[derive(Default)]
 struct Stats {

examples/custom_tokenizer.rs

@@ -2,11 +2,14 @@
 //
 // In this example, we'll see how to define a tokenizer pipeline
 // by aligning a bunch of `TokenFilter`.
+
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
 use tantivy::tokenizer::NgramTokenizer;
-use tantivy::{doc, Index};
+use tantivy::Index;
 
 fn main() -> tantivy::Result<()> {
     // # Defining the schema

examples/deleting_updating_documents.rs

@@ -8,10 +8,13 @@
 //
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::TopDocs;
 use tantivy::query::TermQuery;
 use tantivy::schema::*;
-use tantivy::{doc, Index, IndexReader};
+use tantivy::Index;
+use tantivy::IndexReader;
 
 // A simple helper function to fetch a single document
 // given its id from our index.

examples/faceted_search.rs

@@ -12,16 +12,17 @@
 
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::FacetCollector;
 use tantivy::query::AllQuery;
 use tantivy::schema::*;
-use tantivy::{doc, Index};
+use tantivy::Index;
-use tempfile::TempDir;
 
 fn main() -> tantivy::Result<()> {
     // Let's create a temporary directory for the
     // sake of this example
-    let index_path = TempDir::new()?;
+    let index_path = TempDir::new("tantivy_facet_example_dir")?;
     let mut schema_builder = Schema::builder();
 
     schema_builder.add_text_field("name", TEXT | STORED);
@@ -73,3 +74,5 @@ fn main() -> tantivy::Result<()> {
 
     Ok(())
 }
+
+use tempdir::TempDir;

examples/integer_range_search.rs

@@ -2,10 +2,14 @@
 //
 // Below is an example of creating an indexed integer field in your schema
 // You can use RangeQuery to get a Count of all occurrences in a given range.
+
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::Count;
 use tantivy::query::RangeQuery;
 use tantivy::schema::{Schema, INDEXED};
-use tantivy::{doc, Index, Result};
+use tantivy::Index;
+use tantivy::Result;
 
 fn run() -> Result<()> {
     // For the sake of simplicity, this schema will only have 1 field

examples/iterating_docs_and_positions.rs

@@ -9,8 +9,11 @@
 
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use tantivy::schema::*;
-use tantivy::{doc, DocId, DocSet, Index, Postings};
+use tantivy::Index;
+use tantivy::{DocId, DocSet, Postings};
 
 fn main() -> tantivy::Result<()> {
     // We first create a schema for the sake of the

examples/multiple_producer.rs

@@ -25,11 +25,14 @@
 
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use std::sync::{Arc, RwLock};
 use std::thread;
 use std::time::Duration;
 use tantivy::schema::{Schema, STORED, TEXT};
-use tantivy::{doc, Index, IndexWriter, Opstamp};
+use tantivy::Opstamp;
+use tantivy::{Index, IndexWriter};
 
 fn main() -> tantivy::Result<()> {
     // # Defining the schema

examples/snippet.rs

@@ -7,16 +7,19 @@
 
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
-use tantivy::{doc, Index, Snippet, SnippetGenerator};
+use tantivy::Index;
-use tempfile::TempDir;
+use tantivy::{Snippet, SnippetGenerator};
+use tempdir::TempDir;
 
 fn main() -> tantivy::Result<()> {
     // Let's create a temporary directory for the
     // sake of this example
-    let index_path = TempDir::new()?;
+    let index_path = TempDir::new("tantivy_example_dir")?;
 
     // # Defining the schema
     let mut schema_builder = Schema::builder();

examples/stop_words.rs

@@ -11,11 +11,13 @@
 
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
 use tantivy::tokenizer::*;
-use tantivy::{doc, Index};
+use tantivy::Index;
 
 fn main() -> tantivy::Result<()> {
     // this example assumes you understand the content in `basic_search`

src/collector/count_collector.rs

@@ -10,10 +10,12 @@ use crate::SegmentReader;
 /// documents match the query.
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Schema, TEXT};
+/// use tantivy::{Index, Result};
 /// use tantivy::collector::Count;
 /// use tantivy::query::QueryParser;
-/// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, Index, Result};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {

src/collector/facet_collector.rs

@@ -81,10 +81,12 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
 ///
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Facet, Schema, TEXT};
+/// use tantivy::{Index, Result};
 /// use tantivy::collector::FacetCollector;
 /// use tantivy::query::AllQuery;
-/// use tantivy::schema::{Facet, Schema, TEXT};
-/// use tantivy::{doc, Index, Result};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {

src/collector/mod.rs

@@ -35,6 +35,7 @@ The resulting `Fruit` will then be a typed tuple with each collector's original
 in their respective position.
 
 ```rust
+# extern crate tantivy;
 # use tantivy::schema::*;
 # use tantivy::*;
 # use tantivy::query::*;

src/collector/multi_collector.rs

@@ -105,10 +105,12 @@ impl<TFruit: Fruit> FruitHandle<TFruit> {
 /// [Combining several collectors section of the collector documentation](./index.html#combining-several-collectors).
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Schema, TEXT};
+/// use tantivy::{Index, Result};
 /// use tantivy::collector::{Count, TopDocs, MultiCollector};
 /// use tantivy::query::QueryParser;
-/// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, Index, Result};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {

src/collector/top_score_collector.rs

@@ -13,7 +13,6 @@ use crate::Result;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
-use std::fmt;
 
 /// The Top Score Collector keeps track of the K documents
 /// sorted by their score.
@@ -23,10 +22,13 @@ use std::fmt;
 /// is `O(n log K)`.
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::DocAddress;
+/// use tantivy::schema::{Schema, TEXT};
+/// use tantivy::{Index, Result};
 /// use tantivy::collector::TopDocs;
 /// use tantivy::query::QueryParser;
-/// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, DocAddress, Index, Result};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {
@@ -66,12 +68,6 @@ use std::fmt;
 /// ```
 pub struct TopDocs(TopCollector<Score>);
 
-impl fmt::Debug for TopDocs {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "TopDocs({})", self.0.limit())
-    }
-}
-
 impl TopDocs {
     /// Creates a top score collector, with a number of documents equal to "limit".
     ///
@@ -84,8 +80,10 @@ impl TopDocs {
     /// Set top-K to rank documents by a given fast field.
     ///
     /// ```rust
+    /// #[macro_use]
+    /// extern crate tantivy;
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{doc, Index, Result, DocAddress};
+    /// # use tantivy::{Index, Result, DocAddress};
     /// # use tantivy::query::{Query, QueryParser};
     /// use tantivy::Searcher;
     /// use tantivy::collector::TopDocs;
@@ -123,7 +121,7 @@ impl TopDocs {
     /// ///
     /// /// `field` is required to be a FAST field.
     /// fn docs_sorted_by_rating(searcher: &Searcher,
-    ///                          query: &dyn Query,
+    ///                          query: &Query,
     ///                          sort_by_field: Field)
     ///     -> Result<Vec<(u64, DocAddress)>> {
     ///
@@ -192,8 +190,10 @@ impl TopDocs {
     /// learning-to-rank model over various features
     ///
     /// ```rust
+    /// #[macro_use]
+    /// extern crate tantivy;
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{doc, Index, DocAddress, DocId, Score};
+    /// # use tantivy::{Index, DocAddress, DocId, Score};
     /// # use tantivy::query::QueryParser;
     /// use tantivy::SegmentReader;
     /// use tantivy::collector::TopDocs;
@@ -295,8 +295,10 @@ impl TopDocs {
     /// # Example
     ///
     /// ```rust
+    /// # #[macro_use]
+    /// # extern crate tantivy;
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{doc, Index, DocAddress, DocId};
+    /// # use tantivy::{Index, DocAddress, DocId};
     /// # use tantivy::query::QueryParser;
     /// use tantivy::SegmentReader;
     /// use tantivy::collector::TopDocs;
@@ -582,7 +584,7 @@ mod tests {
         query_field: Field,
         schema: Schema,
         mut doc_adder: impl FnMut(&mut IndexWriter) -> (),
-    ) -> (Index, Box<dyn Query>) {
+    ) -> (Index, Box<Query>) {
         let index = Index::create_in_ram(schema);
 
         let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();

src/common/bitpacker.rs

@@ -2,7 +2,7 @@ use byteorder::{ByteOrder, LittleEndian, WriteBytesExt};
 use std::io;
 use std::ops::Deref;
 
-pub struct BitPacker {
+pub(crate) struct BitPacker {
     mini_buffer: u64,
     mini_buffer_written: usize,
 }

src/common/bitset.rs

@@ -2,7 +2,7 @@ use std::fmt;
 use std::u64;
 
 #[derive(Clone, Copy, Eq, PartialEq)]
-pub struct TinySet(u64);
+pub(crate) struct TinySet(u64);
 
 impl fmt::Debug for TinySet {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
@@ -179,7 +179,7 @@ impl BitSet {
     ///
     /// Reminder: the tiny set with the bucket `bucket`, represents the
     /// elements from `bucket * 64` to `(bucket+1) * 64`.
-    pub fn first_non_empty_bucket(&self, bucket: u32) -> Option<u32> {
+    pub(crate) fn first_non_empty_bucket(&self, bucket: u32) -> Option<u32> {
         self.tinysets[bucket as usize..]
             .iter()
             .cloned()
@@ -194,7 +194,7 @@ impl BitSet {
     /// Returns the tiny bitset representing the
     /// the set restricted to the number range from
     /// `bucket * 64` to `(bucket + 1) * 64`.
-    pub fn tinyset(&self, bucket: u32) -> TinySet {
+    pub(crate) fn tinyset(&self, bucket: u32) -> TinySet {
         self.tinysets[bucket as usize]
     }
 }
@@ -204,7 +204,12 @@ mod tests {
 
     use super::BitSet;
     use super::TinySet;
-    use std::collections::{BTreeSet, HashSet};
+    use crate::docset::DocSet;
+    use crate::query::BitSetDocSet;
+    use crate::tests;
+    use crate::tests::generate_nonunique_unsorted;
+    use std::collections::BTreeSet;
+    use std::collections::HashSet;
 
     #[test]
     fn test_tiny_set() {
@@ -259,19 +264,26 @@ mod tests {
         test_against_hashset(&[62u32, 63u32], 64);
     }
 
-    //    #[test]
+    #[test]
-    //    fn test_bitset_clear() {
+    fn test_bitset_large() {
-    //        let mut bitset = BitSet::with_max_value(1_000);
+        let arr = generate_nonunique_unsorted(100_000, 5_000);
-    //        let els = tests::sample(1_000, 0.01f64);
+        let mut btreeset: BTreeSet<u32> = BTreeSet::new();
-    //        for &el in &els {
+        let mut bitset = BitSet::with_max_value(100_000);
-    //            bitset.insert(el);
+        for el in arr {
-    //        }
+            btreeset.insert(el);
-    //        assert!(els.iter().all(|el| bitset.contains(*el)));
+            bitset.insert(el);
-    //        bitset.clear();
+        }
-    //        for el in 0u32..1000u32 {
+        for i in 0..100_000 {
-    //            assert!(!bitset.contains(el));
+            assert_eq!(btreeset.contains(&i), bitset.contains(i));
-    //        }
+        }
-    //    }
+        assert_eq!(btreeset.len(), bitset.len());
+        let mut bitset_docset = BitSetDocSet::from(bitset);
+        for el in btreeset.into_iter() {
+            bitset_docset.advance();
+            assert_eq!(bitset_docset.doc(), el);
+        }
+        assert!(!bitset_docset.advance());
+    }
 
     #[test]
     fn test_bitset_num_buckets() {
@@ -327,6 +339,19 @@ mod tests {
         assert_eq!(bitset.len(), 3);
     }
 
+    #[test]
+    fn test_bitset_clear() {
+        let mut bitset = BitSet::with_max_value(1_000);
+        let els = tests::sample(1_000, 0.01f64);
+        for &el in &els {
+            bitset.insert(el);
+        }
+        assert!(els.iter().all(|el| bitset.contains(*el)));
+        bitset.clear();
+        for el in 0u32..1000u32 {
+            assert!(!bitset.contains(el));
+        }
+    }
 }
 
 #[cfg(all(test, feature = "unstable"))]

src/common/mod.rs

@@ -1,18 +1,18 @@
 pub mod bitpacker;
 mod bitset;
+mod composite_file;
 mod counting_writer;
 mod serialize;
 mod vint;
 
 pub use self::bitset::BitSet;
-pub use self::bitset::TinySet;
+pub(crate) use self::bitset::TinySet;
+pub(crate) use self::composite_file::{CompositeFile, CompositeWrite};
 pub use self::counting_writer::CountingWriter;
 pub use self::serialize::{BinarySerializable, FixedSize};
 pub use self::vint::{read_u32_vint, serialize_vint_u32, write_u32_vint, VInt};
 pub use byteorder::LittleEndian as Endianness;
 
-pub type DateTime = chrono::DateTime<chrono::Utc>;
-
 /// Segment's max doc must be `< MAX_DOC_LIMIT`.
 ///
 /// We do not allow segments with more than
@@ -42,7 +42,7 @@ pub const MAX_DOC_LIMIT: u32 = 1 << 31;
 /// a very large range of values. Even in this case, it results
 /// in an extra cost of at most 12% compared to the optimal
 /// number of bits.
-pub fn compute_num_bits(n: u64) -> u8 {
+pub(crate) fn compute_num_bits(n: u64) -> u8 {
     let amplitude = (64u32 - n.leading_zeros()) as u8;
     if amplitude <= 64 - 8 {
         amplitude
@@ -51,7 +51,7 @@ pub fn compute_num_bits(n: u64) -> u8 {
     }
 }
 
-pub fn is_power_of_2(n: usize) -> bool {
+pub(crate) fn is_power_of_2(n: usize) -> bool {
     (n > 0) && (n & (n - 1) == 0)
 }
 
@@ -124,26 +124,26 @@ pub fn f64_to_u64(val: f64) -> u64 {
 /// Reverse the mapping given by [`i64_to_u64`](./fn.i64_to_u64.html).
 #[inline(always)]
 pub fn u64_to_f64(val: u64) -> f64 {
-    f64::from_bits(if val & HIGHEST_BIT != 0 {
+    f64::from_bits(
-        val ^ HIGHEST_BIT
+        if val & HIGHEST_BIT != 0 {
-    } else {
+            val ^ HIGHEST_BIT
-        !val
+        } else {
-    })
+            !val
+        }
+    )
 }
 
-pub use self::serialize::fixed_size_test;
-
 #[cfg(test)]
 pub(crate) mod test {
 
-    use super::fixed_size_test;
+    pub use super::serialize::test::fixed_size_test;
-    use super::{compute_num_bits, f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
+    use super::{compute_num_bits, i64_to_u64, u64_to_i64, f64_to_u64, u64_to_f64};
     use std::f64;
 
     fn test_i64_converter_helper(val: i64) {
         assert_eq!(u64_to_i64(i64_to_u64(val)), val);
     }
-
+    
     fn test_f64_converter_helper(val: f64) {
         assert_eq!(u64_to_f64(f64_to_u64(val)), val);
     }
@@ -172,8 +172,7 @@ pub(crate) mod test {
 
     #[test]
     fn test_f64_order() {
-        assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY))
+        assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY)).contains(&f64_to_u64(f64::NAN))); //nan is not a number
-            .contains(&f64_to_u64(f64::NAN))); //nan is not a number
         assert!(f64_to_u64(1.5) > f64_to_u64(1.0)); //same exponent, different mantissa
         assert!(f64_to_u64(2.0) > f64_to_u64(1.0)); //same mantissa, different exponent
         assert!(f64_to_u64(2.0) > f64_to_u64(1.5)); //different exponent and mantissa

src/common/serialize.rs

@@ -1,5 +1,5 @@
-use crate::Endianness;
+use crate::common::Endianness;
-use crate::VInt;
+use crate::common::VInt;
 use byteorder::{ReadBytesExt, WriteBytesExt};
 use std::fmt;
 use std::io;
@@ -145,17 +145,17 @@ impl BinarySerializable for String {
     }
 }
 
-pub fn fixed_size_test<O: BinarySerializable + FixedSize + Default>() {
-    let mut buffer = Vec::new();
-    O::default().serialize(&mut buffer).unwrap();
-    assert_eq!(buffer.len(), O::SIZE_IN_BYTES);
-}
-
 #[cfg(test)]
-mod test {
+pub mod test {
 
     use super::*;
-    use crate::VInt;
+    use crate::common::VInt;
+
+    pub fn fixed_size_test<O: BinarySerializable + FixedSize + Default>() {
+        let mut buffer = Vec::new();
+        O::default().serialize(&mut buffer).unwrap();
+        assert_eq!(buffer.len(), O::SIZE_IN_BYTES);
+    }
 
     fn serialize_test<T: BinarySerializable + Eq>(v: T) -> usize {
         let mut buffer: Vec<u8> = Vec::new();

src/common/vint.rs

@@ -171,7 +171,7 @@ mod tests {
 
     use super::serialize_vint_u32;
     use super::VInt;
-    use crate::BinarySerializable;
+    use crate::common::BinarySerializable;
     use byteorder::{ByteOrder, LittleEndian};
 
     fn aux_test_vint(val: u64) {

src/core/index.rs

@@ -173,11 +173,11 @@ impl Index {
     }
 
     /// Helper to access the tokenizer associated to a specific field.
-    pub fn tokenizer_for_field(&self, field: Field) -> Result<BoxedTokenizer> {
+    pub fn tokenizer_for_field(&self, field: Field) -> Result<Box<dyn BoxedTokenizer>> {
         let field_entry = self.schema.get_field_entry(field);
         let field_type = field_entry.field_type();
         let tokenizer_manager: &TokenizerManager = self.tokenizers();
-        let tokenizer_name_opt: Option<BoxedTokenizer> = match field_type {
+        let tokenizer_name_opt: Option<Box<dyn BoxedTokenizer>> = match field_type {
             FieldType::Str(text_options) => text_options
                 .get_indexing_options()
                 .map(|text_indexing_options| text_indexing_options.tokenizer().to_string())
@@ -216,22 +216,8 @@ impl Index {
         Index::open(mmap_directory)
     }
 
-    /// Returns the list of the segment metas tracked by the index.
+    pub(crate) fn inventory(&self) -> &SegmentMetaInventory {
-    ///
+        &self.inventory
-    /// Such segments can of course be part of the index,
-    /// but also they could be segments being currently built or in the middle of a merge
-    /// operation.
-    pub fn list_all_segment_metas(&self) -> Vec<SegmentMeta> {
-        self.inventory.all()
-    }
-
-    /// Creates a new segment_meta (Advanced user only).
-    ///
-    /// As long as the `SegmentMeta` lives, the files associated with the
-    /// `SegmentMeta` are guaranteed to not be garbage collected, regardless of
-    /// whether the segment is recorded as part of the index or not.
-    pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
-        self.inventory.new_segment_meta(segment_id, max_doc)
     }
 
     /// Open the index using the provided directory
@@ -473,13 +459,13 @@ mod tests {
 
         use super::*;
         use std::path::PathBuf;
-        use tempfile::TempDir;
+        use tempdir::TempDir;
 
         #[test]
         fn test_index_on_commit_reload_policy_mmap() {
             let schema = throw_away_schema();
             let field = schema.get_field("num_likes").unwrap();
-            let tempdir = TempDir::new().unwrap();
+            let tempdir = TempDir::new("index").unwrap();
             let tempdir_path = PathBuf::from(tempdir.path());
             let index = Index::create_in_dir(&tempdir_path, schema).unwrap();
             let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
@@ -518,7 +504,7 @@ mod tests {
         fn test_index_on_commit_reload_policy_different_directories() {
             let schema = throw_away_schema();
             let field = schema.get_field("num_likes").unwrap();
-            let tempdir = TempDir::new().unwrap();
+            let tempdir = TempDir::new("index").unwrap();
             let tempdir_path = PathBuf::from(tempdir.path());
             let write_index = Index::create_in_dir(&tempdir_path, schema).unwrap();
             let read_index = Index::open_in_dir(&tempdir_path).unwrap();

src/core/index_meta.rs

@@ -30,6 +30,7 @@ impl SegmentMetaInventory {
             .collect::<Vec<_>>()
     }
 
+    #[doc(hidden)]
     pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
         let inner = InnerSegmentMeta {
             segment_id,

src/core/segment_id.rs

@@ -4,8 +4,6 @@ use uuid::Uuid;
 
 #[cfg(test)]
 use once_cell::sync::Lazy;
-use std::error::Error;
-use std::str::FromStr;
 #[cfg(test)]
 use std::sync::atomic;
 
@@ -54,51 +52,15 @@ impl SegmentId {
     /// and the rest is random.
     ///
     /// Picking the first 8 chars is ok to identify
-    /// segments in a display message (e.g. a5c4dfcb).
+    /// segments in a display message.
     pub fn short_uuid_string(&self) -> String {
         (&self.0.to_simple_ref().to_string()[..8]).to_string()
     }
 
     /// Returns a segment uuid string.
-    ///
-    /// It consists in 32 lowercase hexadecimal chars
-    /// (e.g. a5c4dfcbdfe645089129e308e26d5523)
     pub fn uuid_string(&self) -> String {
         self.0.to_simple_ref().to_string()
     }
-
-    /// Build a `SegmentId` string from the full uuid string.
-    ///
-    /// E.g. "a5c4dfcbdfe645089129e308e26d5523"
-    pub fn from_uuid_string(uuid_string: &str) -> Result<SegmentId, SegmentIdParseError> {
-        FromStr::from_str(uuid_string)
-    }
-}
-
-/// Error type used when parsing a `SegmentId` from a string fails.
-pub struct SegmentIdParseError(uuid::parser::ParseError);
-
-impl Error for SegmentIdParseError {}
-
-impl fmt::Debug for SegmentIdParseError {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        self.0.fmt(f)
-    }
-}
-
-impl fmt::Display for SegmentIdParseError {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        self.0.fmt(f)
-    }
-}
-
-impl FromStr for SegmentId {
-    type Err = SegmentIdParseError;
-
-    fn from_str(uuid_string: &str) -> Result<Self, SegmentIdParseError> {
-        let uuid = Uuid::parse_str(uuid_string).map_err(SegmentIdParseError)?;
-        Ok(SegmentId(uuid))
-    }
 }
 
 impl fmt::Debug for SegmentId {
@@ -118,18 +80,3 @@ impl Ord for SegmentId {
         self.0.as_bytes().cmp(other.0.as_bytes())
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use super::SegmentId;
-
-    #[test]
-    fn test_to_uuid_string() {
-        let full_uuid = "a5c4dfcbdfe645089129e308e26d5523";
-        let segment_id = SegmentId::from_uuid_string(full_uuid).unwrap();
-        assert_eq!(segment_id.uuid_string(), full_uuid);
-        assert_eq!(segment_id.short_uuid_string(), "a5c4dfcb");
-        // one extra char
-        assert!(SegmentId::from_uuid_string("a5c4dfcbdfe645089129e308e26d5523b").is_err());
-    }
-}

src/core/segment_reader.rs

@@ -1,3 +1,4 @@
+use crate::common::CompositeFile;
 use crate::common::HasLen;
 use crate::core::InvertedIndexReader;
 use crate::core::Segment;
@@ -14,7 +15,6 @@ use crate::schema::Schema;
 use crate::space_usage::SegmentSpaceUsage;
 use crate::store::StoreReader;
 use crate::termdict::TermDictionary;
-use crate::CompositeFile;
 use crate::DocId;
 use crate::Result;
 use fail::fail_point;

src/directory/directory.rs

@@ -48,14 +48,14 @@ impl RetryPolicy {
 ///
 /// It is transparently associated to a lock file, that gets deleted
 /// on `Drop.` The lock is released automatically on `Drop`.
-pub struct DirectoryLock(Box<dyn Send + Sync + 'static>);
+pub struct DirectoryLock(Box<dyn Drop + Send + Sync + 'static>);
 
 struct DirectoryLockGuard {
     directory: Box<dyn Directory>,
     path: PathBuf,
 }
 
-impl<T: Send + Sync + 'static> From<Box<T>> for DirectoryLock {
+impl<T: Drop + Send + Sync + 'static> From<Box<T>> for DirectoryLock {
     fn from(underlying: Box<T>) -> Self {
         DirectoryLock(underlying)
     }

src/directory/managed_directory.rs

@@ -263,11 +263,11 @@ mod tests_mmap_specific {
     use std::collections::HashSet;
     use std::io::Write;
     use std::path::{Path, PathBuf};
-    use tempfile::TempDir;
+    use tempdir::TempDir;
 
     #[test]
     fn test_managed_directory() {
-        let tempdir = TempDir::new().unwrap();
+        let tempdir = TempDir::new("tantivy-test").unwrap();
         let tempdir_path = PathBuf::from(tempdir.path());
 
         let test_path1: &'static Path = Path::new("some_path_for_test");
@@ -304,7 +304,7 @@ mod tests_mmap_specific {
     fn test_managed_directory_gc_while_mmapped() {
         let test_path1: &'static Path = Path::new("some_path_for_test");
 
-        let tempdir = TempDir::new().unwrap();
+        let tempdir = TempDir::new("index").unwrap();
         let tempdir_path = PathBuf::from(tempdir.path());
         let living_files = HashSet::new();
 

src/directory/mmap_directory.rs

@@ -36,7 +36,7 @@ use std::sync::Mutex;
 use std::sync::RwLock;
 use std::sync::Weak;
 use std::thread;
-use tempfile::TempDir;
+use tempdir::TempDir;
 
 /// Create a default io error given a string.
 pub(crate) fn make_io_err(msg: String) -> io::Error {
@@ -141,42 +141,28 @@ impl MmapCache {
     }
 }
 
-struct InnerWatcherWrapper {
-    _watcher: Mutex<notify::RecommendedWatcher>,
-    watcher_router: WatchCallbackList,
-}
-
-impl InnerWatcherWrapper {
-    pub fn new(path: &Path) -> Result<(Self, Receiver<notify::RawEvent>), notify::Error> {
-        let (tx, watcher_recv): (Sender<RawEvent>, Receiver<RawEvent>) = channel();
-        // We need to initialize the
-        let mut watcher = notify::raw_watcher(tx)?;
-        watcher.watch(path, RecursiveMode::Recursive)?;
-        let inner = InnerWatcherWrapper {
-            _watcher: Mutex::new(watcher),
-            watcher_router: Default::default(),
-        };
-        Ok((inner, watcher_recv))
-    }
-}
-
-#[derive(Clone)]
 struct WatcherWrapper {
-    inner: Arc<InnerWatcherWrapper>,
+    _watcher: Mutex<notify::RecommendedWatcher>,
+    watcher_router: Arc<WatchCallbackList>,
 }
 
 impl WatcherWrapper {
     pub fn new(path: &Path) -> Result<Self, OpenDirectoryError> {
-        let (inner, watcher_recv) = InnerWatcherWrapper::new(path).map_err(|err| match err {
+        let (tx, watcher_recv): (Sender<RawEvent>, Receiver<RawEvent>) = channel();
-            notify::Error::PathNotFound => OpenDirectoryError::DoesNotExist(path.to_owned()),
+        // We need to initialize the
-            _ => {
+        let watcher = notify::raw_watcher(tx)
-                panic!("Unknown error while starting watching directory {:?}", path);
+            .and_then(|mut watcher| {
-            }
+                watcher.watch(path, RecursiveMode::Recursive)?;
-        })?;
+                Ok(watcher)
-        let watcher_wrapper = WatcherWrapper {
+            })
-            inner: Arc::new(inner),
+            .map_err(|err| match err {
-        };
+                notify::Error::PathNotFound => OpenDirectoryError::DoesNotExist(path.to_owned()),
-        let watcher_wrapper_clone = watcher_wrapper.clone();
+                _ => {
+                    panic!("Unknown error while starting watching directory {:?}", path);
+                }
+            })?;
+        let watcher_router: Arc<WatchCallbackList> = Default::default();
+        let watcher_router_clone = watcher_router.clone();
         thread::Builder::new()
             .name("meta-file-watch-thread".to_string())
             .spawn(move || {
@@ -187,7 +173,7 @@ impl WatcherWrapper {
                             // We might want to be more accurate than this at one point.
                             if let Some(filename) = changed_path.file_name() {
                                 if filename == *META_FILEPATH {
-                                    watcher_wrapper_clone.inner.watcher_router.broadcast();
+                                    watcher_router_clone.broadcast();
                                 }
                             }
                         }
@@ -200,13 +186,15 @@ impl WatcherWrapper {
                         }
                     }
                 }
-            })
+            })?;
-            .expect("Failed to spawn thread to watch meta.json");
+        Ok(WatcherWrapper {
-        Ok(watcher_wrapper)
+            _watcher: Mutex::new(watcher),
+            watcher_router,
+        })
     }
 
     pub fn watch(&mut self, watch_callback: WatchCallback) -> WatchHandle {
-        self.inner.watcher_router.subscribe(watch_callback)
+        self.watcher_router.subscribe(watch_callback)
     }
 }
 
@@ -294,7 +282,7 @@ 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 = TempDir::new("index").map_err(OpenDirectoryError::IoError)?;
         let tempdir_path = PathBuf::from(tempdir.path());
         MmapDirectory::new(tempdir_path, Some(tempdir))
     }
@@ -539,7 +527,7 @@ impl Directory for MmapDirectory {
 #[cfg(test)]
 mod tests {
 
-    // There are more tests in directory/lib.rs
+    // There are more tests in directory/mod.rs
     // The following tests are specific to the MmapDirectory
 
     use super::*;
@@ -642,7 +630,7 @@ mod tests {
     fn test_watch_wrapper() {
         let counter: Arc<AtomicUsize> = Default::default();
         let counter_clone = counter.clone();
-        let tmp_dir = tempfile::TempDir::new().unwrap();
+        let tmp_dir: TempDir = tempdir::TempDir::new("test_watch_wrapper").unwrap();
         let tmp_dirpath = tmp_dir.path().to_owned();
         let mut watch_wrapper = WatcherWrapper::new(&tmp_dirpath).unwrap();
         let tmp_file = tmp_dirpath.join("coucou");

src/directory/ram_directory.rs

@@ -177,7 +177,7 @@ impl Directory for RAMDirectory {
     fn atomic_write(&mut 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())
+            msg.unwrap_or("Undefined".to_string())
         )));
         let path_buf = PathBuf::from(path);
 

src/fastfield/mod.rs

@@ -148,13 +148,13 @@ fn value_to_u64(value: &Value) -> u64 {
 mod tests {
 
     use super::*;
+    use crate::common::CompositeFile;
     use crate::directory::{Directory, RAMDirectory, WritePtr};
     use crate::fastfield::FastFieldReader;
     use crate::schema::Document;
     use crate::schema::Field;
     use crate::schema::Schema;
     use crate::schema::FAST;
-    use crate::CompositeFile;
     use once_cell::sync::Lazy;
     use rand::prelude::SliceRandom;
     use rand::rngs::StdRng;

src/fastfield/reader.rs

@@ -2,12 +2,12 @@ use super::FastValue;
 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::{Directory, RAMDirectory, WritePtr};
 use crate::fastfield::{FastFieldSerializer, FastFieldsWriter};
 use crate::schema::Schema;
 use crate::schema::FAST;
-use crate::CompositeFile;
 use crate::DocId;
 use owning_ref::OwningRef;
 use std::collections::HashMap;

src/fastfield/readers.rs

@@ -1,9 +1,9 @@
+use crate::common::CompositeFile;
 use crate::fastfield::BytesFastFieldReader;
 use crate::fastfield::MultiValueIntFastFieldReader;
 use crate::fastfield::{FastFieldNotAvailableError, FastFieldReader};
 use crate::schema::{Cardinality, Field, FieldType, Schema};
 use crate::space_usage::PerFieldSpaceUsage;
-use crate::CompositeFile;
 use crate::Result;
 use std::collections::HashMap;
 

src/fastfield/serializer.rs

@@ -1,10 +1,10 @@
 use crate::common::bitpacker::BitPacker;
 use crate::common::compute_num_bits;
 use crate::common::BinarySerializable;
+use crate::common::CompositeWrite;
 use crate::common::CountingWriter;
 use crate::directory::WritePtr;
 use crate::schema::Field;
-use crate::CompositeWrite;
 use std::io::{self, Write};
 
 /// `FastFieldSerializer` is in charge of serializing

src/fastfield/writer.rs

@@ -31,9 +31,7 @@ impl FastFieldsWriter {
                 _ => 0u64,
             };
             match *field_entry.field_type() {
-                FieldType::I64(ref int_options)
+                FieldType::I64(ref int_options) | FieldType::U64(ref int_options) | FieldType::F64(ref int_options) => {
-                | FieldType::U64(ref int_options)
-                | FieldType::F64(ref int_options) => {
                     match int_options.get_fastfield_cardinality() {
                         Some(Cardinality::SingleValue) => {
                             let mut fast_field_writer = IntFastFieldWriter::new(field);

src/fieldnorm/serializer.rs

@@ -1,6 +1,6 @@
+use crate::common::CompositeWrite;
 use crate::directory::WritePtr;
 use crate::schema::Field;
-use crate::CompositeWrite;
 use std::io;
 use std::io::Write;
 

src/indexer/index_writer.rs

@@ -209,7 +209,10 @@ fn index_documents(
     assert!(num_docs > 0);
 
     let doc_opstamps: Vec<Opstamp> = segment_writer.finalize()?;
-    let segment_meta = segment.index().new_segment_meta(segment_id, num_docs);
+    let segment_meta = segment
+        .index()
+        .inventory()
+        .new_segment_meta(segment_id, num_docs);
 
     let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap());
 
@@ -447,10 +450,12 @@ impl IndexWriter {
     /// by clearing and resubmitting necessary documents
     ///
     /// ```rust
-    /// use tantivy::collector::TopDocs;
+    /// #[macro_use]
+    /// extern crate tantivy;
     /// use tantivy::query::QueryParser;
+    /// use tantivy::collector::TopDocs;
     /// use tantivy::schema::*;
-    /// use tantivy::{doc, Index};
+    /// use tantivy::Index;
     ///
     /// fn main() -> tantivy::Result<()> {
     ///     let mut schema_builder = Schema::builder();
@@ -756,6 +761,7 @@ mod tests {
     use crate::Index;
     use crate::ReloadPolicy;
     use crate::Term;
+    use fail;
 
     #[test]
     fn test_operations_group() {

src/indexer/segment_updater.rs

@@ -126,7 +126,9 @@ fn perform_merge(
 
     let num_docs = merger.write(segment_serializer)?;
 
-    let segment_meta = index.new_segment_meta(merged_segment.id(), num_docs);
+    let segment_meta = index
+        .inventory()
+        .new_segment_meta(merged_segment.id(), num_docs);
 
     let after_merge_segment_entry = SegmentEntry::new(segment_meta.clone(), delete_cursor, None);
     Ok(after_merge_segment_entry)
@@ -280,7 +282,7 @@ impl SegmentUpdater {
     fn list_files(&self) -> HashSet<PathBuf> {
         let mut files = HashSet::new();
         files.insert(META_FILEPATH.to_path_buf());
-        for segment_meta in self.0.index.list_all_segment_metas() {
+        for segment_meta in self.0.index.inventory().all() {
             files.extend(segment_meta.list_files());
         }
         files

src/indexer/segment_writer.rs

@@ -49,7 +49,7 @@ pub struct SegmentWriter {
     fast_field_writers: FastFieldsWriter,
     fieldnorms_writer: FieldNormsWriter,
     doc_opstamps: Vec<Opstamp>,
-    tokenizers: Vec<Option<BoxedTokenizer>>,
+    tokenizers: Vec<Option<Box<dyn BoxedTokenizer>>>,
 }
 
 impl SegmentWriter {

src/lib.rs

@@ -1,9 +1,9 @@
 #![doc(html_logo_url = "http://fulmicoton.com/tantivy-logo/tantivy-logo.png")]
-#![recursion_limit = "100"]
 #![cfg_attr(all(feature = "unstable", test), feature(test))]
 #![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))]
 #![doc(test(attr(allow(unused_variables), deny(warnings))))]
 #![warn(missing_docs)]
+#![recursion_limit = "80"]
 
 //! # `tantivy`
 //!
@@ -11,17 +11,26 @@
 //! Think `Lucene`, but in Rust.
 //!
 //! ```rust
+
+//! # extern crate tempdir;
+//! #
+//! #[macro_use]
+//! extern crate tantivy;
+//!
+//! // ...
+//!
 //! # use std::path::Path;
-//! # use tempfile::TempDir;
+//! # use tempdir::TempDir;
+//! # use tantivy::Index;
+//! # use tantivy::schema::*;
+//! # use tantivy::{Score, DocAddress};
 //! # use tantivy::collector::TopDocs;
 //! # use tantivy::query::QueryParser;
-//! # use tantivy::schema::*;
-//! # use tantivy::{doc, DocAddress, Index, Score};
 //! #
 //! # fn main() {
 //! #     // Let's create a temporary directory for the
 //! #     // sake of this example
-//! #     if let Ok(dir) = TempDir::new() {
+//! #     if let Ok(dir) = TempDir::new("tantivy_example_dir") {
 //! #         run_example(dir.path()).unwrap();
 //! #         dir.close().unwrap();
 //! #     }
@@ -102,6 +111,9 @@
 #[macro_use]
 extern crate serde_derive;
 
+#[cfg_attr(test, macro_use)]
+extern crate serde_json;
+
 #[macro_use]
 extern crate log;
 
@@ -118,9 +130,6 @@ mod functional_test;
 #[macro_use]
 mod macros;
 
-mod composite_file;
-pub(crate) use composite_file::{CompositeFile, CompositeWrite};
-
 pub use crate::error::TantivyError;
 
 #[deprecated(since = "0.7.0", note = "please use `tantivy::TantivyError` instead")]
@@ -133,22 +142,22 @@ pub type Result<T> = std::result::Result<T, error::TantivyError>;
 /// Tantivy DateTime
 pub type DateTime = chrono::DateTime<chrono::Utc>;
 
-pub use tantivy_common as common;
+mod common;
-pub use tantivy_schema as schema;
-pub use tantivy_tokenizer as tokenizer;
-
 mod core;
 mod indexer;
 
-pub mod collector;
-pub mod directory;
 #[allow(unused_doc_comments)]
 mod error;
+pub mod tokenizer;
+
+pub mod collector;
+pub mod directory;
 pub mod fastfield;
 pub mod fieldnorm;
 pub(crate) mod positions;
 pub mod postings;
 pub mod query;
+pub mod schema;
 pub mod space_usage;
 pub mod store;
 pub mod termdict;
@@ -162,16 +171,16 @@ pub use self::snippet::{Snippet, SnippetGenerator};
 mod docset;
 pub use self::docset::{DocSet, SkipResult};
 
-pub use crate::common::{f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
 pub use crate::core::SegmentComponent;
 pub use crate::core::{Index, IndexMeta, Searcher, Segment, SegmentId, SegmentMeta};
 pub use crate::core::{InvertedIndexReader, SegmentReader};
 pub use crate::directory::Directory;
 pub use crate::indexer::IndexWriter;
 pub use crate::postings::Postings;
-pub use crate::reader::LeasedItem;
 pub use crate::schema::{Document, Term};
 
+pub use crate::common::{i64_to_u64, u64_to_i64, f64_to_u64, u64_to_f64};
+
 /// Expose the current version of tantivy, as well
 /// whether it was compiled with the simd compression.
 pub fn version() -> &'static str {
@@ -252,6 +261,7 @@ mod tests {
     use crate::Postings;
     use crate::ReloadPolicy;
     use rand::distributions::Bernoulli;
+    use rand::distributions::Uniform;
     use rand::rngs::StdRng;
     use rand::{Rng, SeedableRng};
 
@@ -268,6 +278,14 @@ mod tests {
         (a - b).abs() < 0.0005 * (a + b).abs()
     }
 
+    pub fn generate_nonunique_unsorted(max_value: u32, n_elems: usize) -> Vec<u32> {
+        let seed: [u8; 32] = [1; 32];
+        StdRng::from_seed(seed)
+            .sample_iter(&Uniform::new(0u32, max_value))
+            .take(n_elems)
+            .collect::<Vec<u32>>()
+    }
+
     pub fn sample_with_seed(n: u32, ratio: f64, seed_val: u8) -> Vec<u32> {
         StdRng::from_seed([seed_val; 32])
             .sample_iter(&Bernoulli::new(ratio).unwrap())
@@ -277,6 +295,10 @@ mod tests {
             .collect()
     }
 
+    pub fn sample(n: u32, ratio: f64) -> Vec<u32> {
+        sample_with_seed(n, ratio, 4)
+    }
+
     #[test]
     #[cfg(feature = "mmap")]
     fn test_indexing() {
@@ -827,8 +849,7 @@ mod tests {
         let index = Index::create_in_ram(schema);
         let mut index_writer = index.writer_with_num_threads(1, 50_000_000).unwrap();
         {
-            let document =
+            let document = doc!(fast_field_unsigned => 4u64, fast_field_signed=>4i64, fast_field_float=>4f64);
-                doc!(fast_field_unsigned => 4u64, fast_field_signed=>4i64, fast_field_float=>4f64);
             index_writer.add_document(document);
             index_writer.commit().unwrap();
         }

src/macros.rs

@@ -22,9 +22,11 @@
 ///
 /// # Example
 ///
-/// ```rust
+/// ```
+/// #[macro_use]
+/// extern crate tantivy;
+///
 /// use tantivy::schema::{Schema, TEXT, FAST};
-/// use tantivy::doc;
 ///
 /// //...
 ///

src/postings/serializer.rs

@@ -1,6 +1,6 @@
 use super::TermInfo;
-use crate::common::CountingWriter;
 use crate::common::{BinarySerializable, VInt};
+use crate::common::{CompositeWrite, CountingWriter};
 use crate::core::Segment;
 use crate::directory::WritePtr;
 use crate::positions::PositionSerializer;
@@ -10,7 +10,6 @@ use crate::postings::USE_SKIP_INFO_LIMIT;
 use crate::schema::Schema;
 use crate::schema::{Field, FieldEntry, FieldType};
 use crate::termdict::{TermDictionaryBuilder, TermOrdinal};
-use crate::CompositeWrite;
 use crate::DocId;
 use crate::Result;
 use std::io::{self, Write};

src/postings/term_info.rs

@@ -45,7 +45,7 @@ impl BinarySerializable for TermInfo {
 mod tests {
 
     use super::TermInfo;
-    use crate::common::fixed_size_test;
+    use crate::common::test::fixed_size_test;
 
     #[test]
     fn test_fixed_size() {

src/query/automaton_weight.rs

@@ -8,13 +8,15 @@ use crate::termdict::{TermDictionary, TermStreamer};
 use crate::DocId;
 use crate::TantivyError;
 use crate::{Result, SkipResult};
-use std::sync::Arc;
 use tantivy_fst::Automaton;
 
 /// A weight struct for Fuzzy Term and Regex Queries
-pub struct AutomatonWeight<A> {
+pub struct AutomatonWeight<A>
+where
+    A: Automaton + Send + Sync + 'static,
+{
     field: Field,
-    automaton: Arc<A>,
+    automaton: A,
 }
 
 impl<A> AutomatonWeight<A>
@@ -22,16 +24,12 @@ where
     A: Automaton + Send + Sync + 'static,
 {
     /// Create a new AutomationWeight
-    pub fn new<IntoArcA: Into<Arc<A>>>(field: Field, automaton: IntoArcA) -> AutomatonWeight<A> {
+    pub fn new(field: Field, automaton: A) -> AutomatonWeight<A> {
-        AutomatonWeight {
+        AutomatonWeight { field, automaton }
-            field,
-            automaton: automaton.into(),
-        }
     }
 
     fn automaton_stream<'a>(&'a self, term_dict: &'a TermDictionary) -> TermStreamer<'a, &'a A> {
-        let automaton: &A = &*self.automaton;
+        let term_stream_builder = term_dict.search(&self.automaton);
-        let term_stream_builder = term_dict.search(automaton);
         term_stream_builder.into_stream()
     }
 }

src/query/bitset/mod.rs

@@ -216,6 +216,7 @@ mod tests {
             assert!(!docset.advance());
         }
     }
+
 }
 
 #[cfg(all(test, feature = "unstable"))]

src/query/fuzzy_query.rs

@@ -1,4 +1,3 @@
-use crate::error::TantivyError::InvalidArgument;
 use crate::query::{AutomatonWeight, Query, Weight};
 use crate::schema::Term;
 use crate::Result;
@@ -6,16 +5,11 @@ use crate::Searcher;
 use levenshtein_automata::{LevenshteinAutomatonBuilder, DFA};
 use once_cell::sync::Lazy;
 use std::collections::HashMap;
-use std::ops::Range;
-
-/// A range of Levenshtein distances that we will build DFAs for our terms
-/// The computation is exponential, so best keep it to low single digits
-const VALID_LEVENSHTEIN_DISTANCE_RANGE: Range<u8> = (0..3);
 
 static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Lazy::new(|| {
     let mut lev_builder_cache = HashMap::new();
     // TODO make population lazy on a `(distance, val)` basis
-    for distance in VALID_LEVENSHTEIN_DISTANCE_RANGE {
+    for distance in 0..3 {
         for &transposition in &[false, true] {
             let lev_automaton_builder = LevenshteinAutomatonBuilder::new(distance, transposition);
             lev_builder_cache.insert((distance, transposition), lev_automaton_builder);
@@ -28,10 +22,12 @@ static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Laz
 /// containing a specific term that is within
 /// Levenshtein distance
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Schema, TEXT};
+/// use tantivy::{Index, Result, Term};
 /// use tantivy::collector::{Count, TopDocs};
 /// use tantivy::query::FuzzyTermQuery;
-/// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, Index, Result, Term};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {
@@ -104,18 +100,10 @@ impl FuzzyTermQuery {
     }
 
     fn specialized_weight(&self) -> Result<AutomatonWeight<DFA>> {
-        // LEV_BUILDER is a HashMap, whose `get` method returns an Option
+        let automaton = LEV_BUILDER.get(&(self.distance, false))
-        match LEV_BUILDER.get(&(self.distance, false)) {
+            .unwrap() // TODO return an error
-            // Unwrap the option and build the Ok(AutomatonWeight)
+            .build_dfa(self.term.text());
-            Some(automaton_builder) => {
+        Ok(AutomatonWeight::new(self.term.field(), automaton))
-                let automaton = automaton_builder.build_dfa(self.term.text());
-                Ok(AutomatonWeight::new(self.term.field(), automaton))
-            }
-            None => Err(InvalidArgument(format!(
-                "Levenshtein distance of {} is not allowed. Choose a value in the {:?} range",
-                self.distance, VALID_LEVENSHTEIN_DISTANCE_RANGE
-            ))),
-        }
     }
 }
 

src/query/query_parser/logical_ast.rs

@@ -18,6 +18,7 @@ pub enum LogicalLiteral {
     All,
 }
 
+#[derive(Clone)]
 pub enum LogicalAST {
     Clause(Vec<(Occur, LogicalAST)>),
     Leaf(Box<LogicalLiteral>),

src/query/query_parser/query_grammar.rs

@@ -1,3 +1,4 @@
+use super::query_grammar;
 use super::user_input_ast::*;
 use crate::query::occur::Occur;
 use crate::query::query_parser::user_input_ast::UserInputBound;
@@ -12,25 +13,22 @@ parser! {
         (
             letter(),
             many(satisfy(|c: char| c.is_alphanumeric() || c == '_')),
-        ).skip(char(':')).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
+        ).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
     }
 }
 
 parser! {
     fn word[I]()(I) -> String
     where [I: Stream<Item = char>] {
-        (
+        many1(satisfy(|c: char| c.is_alphanumeric() || c=='.'))
-            satisfy(|c: char| !c.is_whitespace() && !['-', '`', ':', '{', '}', '"', '[', ']', '(',')'].contains(&c) ),
+               .and_then(|s: String| {
-            many(satisfy(|c: char| !c.is_whitespace() && ![':', '{', '}', '"', '[', ']', '(',')'].contains(&c)))
+                   match s.as_str() {
-        )
+                     "OR" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
-        .map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
+                     "AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
-        .and_then(|s: String|
+                     "NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
-           match s.as_str() {
+                     _ => Ok(s)
-             "OR" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
+                   }
-             "AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
+               })
-             "NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
-             _ => Ok(s)
-           })
     }
 }
 
@@ -39,13 +37,12 @@ parser! {
     where [I: Stream<Item = char>]
     {
         let term_val = || {
-            let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
+            let phrase = (char('"'), many1(satisfy(|c| c != '"')), char('"')).map(|(_, s, _)| s);
             phrase.or(word())
         };
         let term_val_with_field = negative_number().or(term_val());
         let term_query =
-            (field(), term_val_with_field)
+            (field(), char(':'), term_val_with_field).map(|(field_name, _, phrase)| UserInputLiteral {
-            .map(|(field_name, phrase)| UserInputLiteral {
                 field_name: Some(field_name),
                 phrase,
             });
@@ -63,15 +60,8 @@ parser! {
     fn negative_number[I]()(I) -> String
     where [I: Stream<Item = char>]
     {
-        (char('-'), many1(satisfy(char::is_numeric)),
+            (char('-'), many1(satisfy(char::is_numeric)))
-         optional((char('.'), many1(satisfy(char::is_numeric)))))
+                .map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
-            .map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
-                if let Some(('.', s3)) = s3 {
-                    format!("{}{}.{}", s1, s2, s3)
-                } else {
-                    format!("{}{}", s1, s2)
-                }
-            })
     }
 }
 
@@ -83,93 +73,55 @@ parser! {
 }
 
 parser! {
-    /// Function that parses a range out of a Stream
-    /// Supports ranges like:
-    /// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
-    /// [a TO *], [a TO c], [abc TO bcd}
     fn range[I]()(I) -> UserInputLeaf
     where [I: Stream<Item = char>] {
-        let range_term_val = || {
+        let term_val = || {
-            word().or(negative_number()).or(char('*').with(value("*".to_string())))
+            word().or(negative_number()).or(char('*').map(|_| "*".to_string()))
         };
-
+        let lower_bound = {
-        // check for unbounded range in the form of <5, <=10, >5, >=5
+            let excl = (char('{'), term_val()).map(|(_, w)| UserInputBound::Exclusive(w));
-        let elastic_unbounded_range = (choice([attempt(string(">=")),
+            let incl = (char('['), term_val()).map(|(_, w)| UserInputBound::Inclusive(w));
-                                               attempt(string("<=")),
+            attempt(excl).or(incl)
-                                               attempt(string("<")),
+        };
-                                               attempt(string(">"))])
+        let upper_bound = {
-                                       .skip(spaces()),
+            let excl = (term_val(), char('}')).map(|(w, _)| UserInputBound::Exclusive(w));
-                                       range_term_val()).
+            let incl = (term_val(), char(']')).map(|(w, _)| UserInputBound::Inclusive(w));
-            map(|(comparison_sign, bound): (&str, String)|
+            attempt(excl).or(incl)
-                match comparison_sign {
+        };
-                    ">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
+        (
-                    "<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
+            optional((field(), char(':')).map(|x| x.0)),
-                    "<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
+            lower_bound,
-                    ">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
+            spaces(),
-                    // default case
+            string("TO"),
-                    _ => (UserInputBound::Unbounded, UserInputBound::Unbounded)
+            spaces(),
-                });
+            upper_bound,
-        let lower_bound = (one_of("{[".chars()), range_term_val())
+        ).map(|(field, lower, _, _, _, upper)| UserInputLeaf::Range {
-            .map(|(boundary_char, lower_bound): (char, String)|
+                field,
-                 if lower_bound == "*" {
+                lower,
-                     UserInputBound::Unbounded
+                upper
-                 } else if boundary_char == '{' {
-                         UserInputBound::Exclusive(lower_bound)
-                 } else {
-                     UserInputBound::Inclusive(lower_bound)
-                 });
-        let upper_bound = (range_term_val(), one_of("}]".chars()))
-            .map(|(higher_bound, boundary_char): (String, char)|
-                 if higher_bound == "*" {
-                     UserInputBound::Unbounded
-                 } else if boundary_char == '}' {
-                     UserInputBound::Exclusive(higher_bound)
-                 } else {
-                     UserInputBound::Inclusive(higher_bound)
-                 });
-         // return only lower and upper
-        let lower_to_upper = (lower_bound.
-                                    skip((spaces(),
-                                          string("TO"),
-                                          spaces())),
-                                    upper_bound);
-
-        (optional(field()).skip(spaces()),
-         // try elastic first, if it matches, the range is unbounded
-         attempt(elastic_unbounded_range).or(lower_to_upper))
-            .map(|(field, (lower, upper))|
-                 // Construct the leaf from extracted field (optional)
-                 // and bounds
-                 UserInputLeaf::Range {
-                     field,
-                     lower,
-                     upper
         })
     }
 }
 
-fn negate(expr: UserInputAST) -> UserInputAST {
-    expr.unary(Occur::MustNot)
-}
-
-fn must(expr: UserInputAST) -> UserInputAST {
-    expr.unary(Occur::Must)
-}
-
 parser! {
     fn leaf[I]()(I) -> UserInputAST
     where [I: Stream<Item = char>] {
-            char('-').with(leaf()).map(negate)
+         (char('-'), leaf()).map(|(_, expr)| expr.unary(Occur::MustNot) )
-        .or(char('+').with(leaf()).map(must))
+        .or((char('+'), leaf()).map(|(_, expr)| expr.unary(Occur::Must) ))
-        .or(char('(').with(ast()).skip(char(')')))
+        .or((char('('), parse_to_ast(), char(')')).map(|(_, expr, _)| expr))
-        .or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All)))
+        .or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All) ))
-        .or(attempt(string("NOT").skip(spaces1()).with(leaf()).map(negate)))
+        .or(attempt(
-        .or(attempt(range().map(UserInputAST::from)))
+            (string("NOT"), spaces1(), leaf()).map(|(_, _, expr)| expr.unary(Occur::MustNot))
-        .or(literal().map(UserInputAST::from))
+            )
+         )
+        .or(attempt(
+            range().map(UserInputAST::from)
+            )
+        )
+        .or(literal().map(|leaf| UserInputAST::Leaf(Box::new(leaf))))
     }
 }
 
-#[derive(Clone, Copy)]
 enum BinaryOperand {
     Or,
     And,
@@ -177,62 +129,84 @@ enum BinaryOperand {
 
 parser! {
     fn binary_operand[I]()(I) -> BinaryOperand
-    where [I: Stream<Item = char>]
+    where [I: Stream<Item = char>] {
-    {
+        (spaces1(),
-       string("AND").with(value(BinaryOperand::And))
+         (
-       .or(string("OR").with(value(BinaryOperand::Or)))
+            string("AND").map(|_| BinaryOperand::And)
+           .or(string("OR").map(|_| BinaryOperand::Or))
+         ),
+         spaces1()).map(|(_, op,_)| op)
     }
 }
 
-fn aggregate_binary_expressions(
+enum Element {
-    left: UserInputAST,
+    SingleEl(UserInputAST),
-    others: Vec<(BinaryOperand, UserInputAST)>,
+    NormalDisjunctive(Vec<Vec<UserInputAST>>),
-) -> UserInputAST {
+}
-    let mut dnf: Vec<Vec<UserInputAST>> = vec![vec![left]];
+
-    for (operator, operand_ast) in others {
+impl Element {
-        match operator {
+    pub fn into_dnf(self) -> Vec<Vec<UserInputAST>> {
-            BinaryOperand::And => {
+        match self {
-                if let Some(last) = dnf.last_mut() {
+            Element::NormalDisjunctive(conjunctions) => conjunctions,
-                    last.push(operand_ast);
+            Element::SingleEl(el) => vec![vec![el]],
-                }
-            }
-            BinaryOperand::Or => {
-                dnf.push(vec![operand_ast]);
-            }
         }
     }
-    if dnf.len() == 1 {
-        UserInputAST::and(dnf.into_iter().next().unwrap()) //< safe
-    } else {
-        let conjunctions = dnf.into_iter().map(UserInputAST::and).collect();
-        UserInputAST::or(conjunctions)
-    }
-}
-
-parser! {
-    pub fn ast[I]()(I) -> UserInputAST
-    where [I: Stream<Item = char>]
-    {
-        let operand_leaf = (binary_operand().skip(spaces()), leaf().skip(spaces()));
-        let boolean_expr = (leaf().skip(spaces().silent()), many1(operand_leaf)).map(
-            |(left, right)| aggregate_binary_expressions(left,right));
-        let whitespace_separated_leaves = many1(leaf().skip(spaces().silent()))
-        .map(|subqueries: Vec<UserInputAST>|
-            if subqueries.len() == 1 {
-                subqueries.into_iter().next().unwrap()
-            } else {
-                UserInputAST::Clause(subqueries.into_iter().collect())
-            });
-        let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
-        spaces().with(expr).skip(spaces())
-    }
 }
 
 parser! {
     pub fn parse_to_ast[I]()(I) -> UserInputAST
     where [I: Stream<Item = char>]
     {
-        spaces().with(optional(ast()).skip(eof())).map(|opt_ast| opt_ast.unwrap_or_else(UserInputAST::empty_query))
+        (
+            attempt(
+                chainl1(
+                    leaf().map(Element::SingleEl),
+                    binary_operand().map(|op: BinaryOperand|
+                        move |left: Element, right: Element| {
+                            let mut dnf = left.into_dnf();
+                            if let Element::SingleEl(el) = right {
+                                match op {
+                                    BinaryOperand::And => {
+                                        if let Some(last) = dnf.last_mut() {
+                                            last.push(el);
+                                        }
+                                    }
+                                    BinaryOperand::Or => {
+                                        dnf.push(vec!(el));
+                                    }
+                                }
+                            } else {
+                                unreachable!("Please report.")
+                            }
+                            Element::NormalDisjunctive(dnf)
+                        }
+                    )
+                )
+                .map(query_grammar::Element::into_dnf)
+                .map(|fnd| {
+                    if fnd.len() == 1 {
+                        UserInputAST::and(fnd.into_iter().next().unwrap()) //< safe
+                    } else {
+                        let conjunctions = fnd
+                        .into_iter()
+                        .map(UserInputAST::and)
+                        .collect();
+                        UserInputAST::or(conjunctions)
+                    }
+                })
+            )
+            .or(
+                sep_by(leaf(), spaces())
+                .map(|subqueries: Vec<UserInputAST>| {
+                    if subqueries.len() == 1 {
+                        subqueries.into_iter().next().unwrap()
+                    } else {
+                        UserInputAST::Clause(subqueries.into_iter().collect())
+                    }
+                })
+            )
+        )
+
     }
 }
 
@@ -251,18 +225,6 @@ mod test {
         assert!(parse_to_ast().parse(query).is_err());
     }
 
-    #[test]
-    fn test_parse_empty_to_ast() {
-        test_parse_query_to_ast_helper("", "<emptyclause>");
-    }
-
-    #[test]
-    fn test_parse_query_to_ast_hyphen() {
-        test_parse_query_to_ast_helper("\"www-form-encoded\"", "\"www-form-encoded\"");
-        test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
-        test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
-    }
-
     #[test]
     fn test_parse_query_to_ast_not_op() {
         assert_eq!(
@@ -297,67 +259,8 @@ mod test {
         );
     }
 
-    #[test]
-    fn test_parse_elastic_query_ranges() {
-        test_parse_query_to_ast_helper("title: >a", "title:{\"a\" TO \"*\"}");
-        test_parse_query_to_ast_helper("title:>=a", "title:[\"a\" TO \"*\"}");
-        test_parse_query_to_ast_helper("title: <a", "title:{\"*\" TO \"a\"}");
-        test_parse_query_to_ast_helper("title:<=a", "title:{\"*\" TO \"a\"]");
-        test_parse_query_to_ast_helper("title:<=bsd", "title:{\"*\" TO \"bsd\"]");
-
-        test_parse_query_to_ast_helper("weight: >70", "weight:{\"70\" TO \"*\"}");
-        test_parse_query_to_ast_helper("weight:>=70", "weight:[\"70\" TO \"*\"}");
-        test_parse_query_to_ast_helper("weight: <70", "weight:{\"*\" TO \"70\"}");
-        test_parse_query_to_ast_helper("weight:<=70", "weight:{\"*\" TO \"70\"]");
-        test_parse_query_to_ast_helper("weight: >60.7", "weight:{\"60.7\" TO \"*\"}");
-
-        test_parse_query_to_ast_helper("weight: <= 70", "weight:{\"*\" TO \"70\"]");
-
-        test_parse_query_to_ast_helper("weight: <= 70.5", "weight:{\"*\" TO \"70.5\"]");
-    }
-
-    #[test]
-    fn test_range_parser() {
-        // testing the range() parser separately
-        let res = range().parse("title: <hello").unwrap().0;
-        let expected = UserInputLeaf::Range {
-            field: Some("title".to_string()),
-            lower: UserInputBound::Unbounded,
-            upper: UserInputBound::Exclusive("hello".to_string()),
-        };
-        let res2 = range().parse("title:{* TO hello}").unwrap().0;
-        assert_eq!(res, expected);
-        assert_eq!(res2, expected);
-        let expected_weight = UserInputLeaf::Range {
-            field: Some("weight".to_string()),
-            lower: UserInputBound::Inclusive("71.2".to_string()),
-            upper: UserInputBound::Unbounded,
-        };
-
-        let res3 = range().parse("weight: >=71.2").unwrap().0;
-        let res4 = range().parse("weight:[71.2 TO *}").unwrap().0;
-        assert_eq!(res3, expected_weight);
-        assert_eq!(res4, expected_weight);
-    }
-
-    #[test]
-    fn test_parse_query_to_triming_spaces() {
-        test_parse_query_to_ast_helper("   abc", "\"abc\"");
-        test_parse_query_to_ast_helper("abc ", "\"abc\"");
-        test_parse_query_to_ast_helper("(  a OR abc)", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("(a  OR abc)", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("(a OR  abc)", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("a OR abc ", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("(a OR abc )", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("(a OR  abc) ", "(?(\"a\") ?(\"abc\"))");
-    }
-
     #[test]
     fn test_parse_query_to_ast() {
-        test_parse_query_to_ast_helper("abc", "\"abc\"");
-        test_parse_query_to_ast_helper("a b", "(\"a\" \"b\")");
-        test_parse_query_to_ast_helper("+(a b)", "+((\"a\" \"b\"))");
-        test_parse_query_to_ast_helper("+d", "+(\"d\")");
         test_parse_query_to_ast_helper("+(a b) +d", "(+((\"a\" \"b\")) +(\"d\"))");
         test_parse_query_to_ast_helper("(+a +b) d", "((+(\"a\") +(\"b\")) \"d\")");
         test_parse_query_to_ast_helper("(+a)", "+(\"a\")");
@@ -373,7 +276,7 @@ mod test {
         test_parse_query_to_ast_helper("[1 TO 5]", "[\"1\" TO \"5\"]");
         test_parse_query_to_ast_helper("foo:{a TO z}", "foo:{\"a\" TO \"z\"}");
         test_parse_query_to_ast_helper("foo:[1 TO toto}", "foo:[\"1\" TO \"toto\"}");
-        test_parse_query_to_ast_helper("foo:[* TO toto}", "foo:{\"*\" TO \"toto\"}");
+        test_parse_query_to_ast_helper("foo:[* TO toto}", "foo:[\"*\" TO \"toto\"}");
         test_parse_query_to_ast_helper("foo:[1 TO *}", "foo:[\"1\" TO \"*\"}");
         test_parse_query_to_ast_helper("foo:[1.1 TO *}", "foo:[\"1.1\" TO \"*\"}");
         test_is_parse_err("abc +    ");

src/query/query_parser/query_parser.rs

@@ -18,56 +18,42 @@ use crate::schema::{FieldType, Term};
 use crate::tokenizer::TokenizerManager;
 use combine::Parser;
 use std::borrow::Cow;
-use std::num::{ParseFloatError, ParseIntError};
+use std::num::{ParseIntError, ParseFloatError};
 use std::ops::Bound;
 use std::str::FromStr;
 
 /// Possible error that may happen when parsing a query.
-#[derive(Debug, PartialEq, Eq, Fail)]
+#[derive(Debug, PartialEq, Eq)]
 pub enum QueryParserError {
     /// Error in the query syntax
-    #[fail(display = "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)]
     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)]
     ExpectedInt(ParseIntError),
     /// The query contains a term for a `f64`-field, but the value
     /// is not a f64.
-    #[fail(display = "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")]
     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")]
     NoDefaultFieldDeclared,
     /// The field searched for is not declared
     /// as indexed in the schema.
-    #[fail(display = "The field '{:?}' is not declared as indexed", _0)]
     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)]
     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
-    )]
     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")]
     RangeMustNotHavePhrase,
     /// The format for the date field is not RFC 3339 compliant.
-    #[fail(display = "The date field has an invalid format")]
     DateFormatError(chrono::ParseError),
 }
 
@@ -369,7 +355,6 @@ impl QueryParser {
         match *bound {
             UserInputBound::Inclusive(_) => Ok(Bound::Included(term)),
             UserInputBound::Exclusive(_) => Ok(Bound::Excluded(term)),
-            UserInputBound::Unbounded => Ok(Bound::Unbounded),
         }
     }
 
@@ -629,7 +614,7 @@ mod test {
     pub fn test_parse_query_untokenized() {
         test_parse_query_to_logical_ast_helper(
             "nottokenized:\"wordone wordtwo\"",
-            "Term(field=7,bytes=[119, 111, 114, 100, 111, 110, \
+            "Term([0, 0, 0, 7, 119, 111, 114, 100, 111, 110, \
              101, 32, 119, 111, 114, 100, 116, 119, 111])",
             false,
         );
@@ -673,7 +658,7 @@ mod test {
             .is_ok());
         test_parse_query_to_logical_ast_helper(
             "unsigned:2324",
-            "Term(field=3,bytes=[0, 0, 0, 0, 0, 0, 9, 20])",
+            "Term([0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 9, 20])",
             false,
         );
 
@@ -691,22 +676,22 @@ mod test {
     }
 
     #[test]
-    pub fn test_parse_query_to_ast_single_term() {
+    pub fn test_parse_query_to_ast_disjunction() {
         test_parse_query_to_logical_ast_helper(
             "title:toto",
-            "Term(field=0,bytes=[116, 111, 116, 111])",
+            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto",
-            "Term(field=0,bytes=[116, 111, 116, 111])",
+            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto -titi",
-            "(+Term(field=0,bytes=[116, 111, 116, 111]) \
+            "(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
-             -(Term(field=0,bytes=[116, 105, 116, 105]) \
+             -(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
-             Term(field=1,bytes=[116, 105, 116, 105])))",
+             Term([0, 0, 0, 1, 116, 105, 116, 105])))",
             false,
         );
         assert_eq!(
@@ -715,67 +700,49 @@ mod test {
                 .unwrap(),
             QueryParserError::AllButQueryForbidden
         );
-    }
-
-    #[test]
-    pub fn test_parse_query_to_ast_two_terms() {
         test_parse_query_to_logical_ast_helper(
             "title:a b",
-            "(Term(field=0,bytes=[97]) (Term(field=0,bytes=[98]) Term(field=1,bytes=[98])))",
+            "(Term([0, 0, 0, 0, 97]) (Term([0, 0, 0, 0, 98]) \
+             Term([0, 0, 0, 1, 98])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:\"a b\"",
-            "\"[(0, Term(field=0,bytes=[97])), \
+            "\"[(0, Term([0, 0, 0, 0, 97])), \
-             (1, Term(field=0,bytes=[98]))]\"",
+             (1, Term([0, 0, 0, 0, 98]))]\"",
             false,
         );
-    }
-
-    #[test]
-    pub fn test_parse_query_to_ast_ranges() {
         test_parse_query_to_logical_ast_helper(
             "title:[a TO b]",
-            "(Included(Term(field=0,bytes=[97])) TO Included(Term(field=0,bytes=[98])))",
+            "(Included(Term([0, 0, 0, 0, 97])) TO \
+             Included(Term([0, 0, 0, 0, 98])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "[a TO b]",
-            "((Included(Term(field=0,bytes=[97])) TO \
+            "((Included(Term([0, 0, 0, 0, 97])) TO \
-             Included(Term(field=0,bytes=[98]))) \
+             Included(Term([0, 0, 0, 0, 98]))) \
-             (Included(Term(field=1,bytes=[97])) TO \
+             (Included(Term([0, 0, 0, 1, 97])) TO \
-             Included(Term(field=1,bytes=[98]))))",
+             Included(Term([0, 0, 0, 1, 98]))))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:{titi TO toto}",
-            "(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO \
+            "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO \
-             Excluded(Term(field=0,bytes=[116, 111, 116, 111])))",
+             Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:{* TO toto}",
-            "(Unbounded TO Excluded(Term(field=0,bytes=[116, 111, 116, 111])))",
+            "(Unbounded TO \
+             Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:{titi TO *}",
-            "(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO Unbounded)",
+            "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO Unbounded)",
             false,
         );
-        test_parse_query_to_logical_ast_helper(
-            "signed:{-5 TO 3}",
-            "(Excluded(Term(field=2,bytes=[127, 255, 255, 255, 255, 255, 255, 251])) TO \
-             Excluded(Term(field=2,bytes=[128, 0, 0, 0, 0, 0, 0, 3])))",
-            false,
-        );
-        test_parse_query_to_logical_ast_helper(
-            "float:{-1.5 TO 1.5}",
-            "(Excluded(Term(field=10,bytes=[64, 7, 255, 255, 255, 255, 255, 255])) TO \
-             Excluded(Term(field=10,bytes=[191, 248, 0, 0, 0, 0, 0, 0])))",
-            false,
-        );
-
         test_parse_query_to_logical_ast_helper("*", "*", false);
     }
 
@@ -877,19 +844,19 @@ mod test {
     pub fn test_parse_query_to_ast_conjunction() {
         test_parse_query_to_logical_ast_helper(
             "title:toto",
-            "Term(field=0,bytes=[116, 111, 116, 111])",
+            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto",
-            "Term(field=0,bytes=[116, 111, 116, 111])",
+            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto -titi",
-            "(+Term(field=0,bytes=[116, 111, 116, 111]) \
+            "(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
-             -(Term(field=0,bytes=[116, 105, 116, 105]) \
+             -(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
-             Term(field=1,bytes=[116, 105, 116, 105])))",
+             Term([0, 0, 0, 1, 116, 105, 116, 105])))",
             true,
         );
         assert_eq!(
@@ -900,25 +867,16 @@ mod test {
         );
         test_parse_query_to_logical_ast_helper(
             "title:a b",
-            "(+Term(field=0,bytes=[97]) \
+            "(+Term([0, 0, 0, 0, 97]) \
-             +(Term(field=0,bytes=[98]) \
+             +(Term([0, 0, 0, 0, 98]) \
-             Term(field=1,bytes=[98])))",
+             Term([0, 0, 0, 1, 98])))",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "title:\"a b\"",
-            "\"[(0, Term(field=0,bytes=[97])), \
+            "\"[(0, Term([0, 0, 0, 0, 97])), \
-             (1, Term(field=0,bytes=[98]))]\"",
+             (1, Term([0, 0, 0, 0, 98]))]\"",
             true,
         );
     }
-
-    #[test]
-    pub fn test_query_parser_hyphen() {
-        test_parse_query_to_logical_ast_helper(
-            "title:www-form-encoded",
-            "\"[(0, Term(field=0,bytes=[119, 119, 119])), (1, Term(field=0,bytes=[102, 111, 114, 109])), (2, Term(field=0,bytes=[101, 110, 99, 111, 100, 101, 100]))]\"",
-            false
-        );
-    }
 }

src/query/query_parser/stemmer.rs

@@ -0,0 +1,44 @@
+use std::sync::Arc;
+use stemmer;
+
+
+pub struct StemmerTokenStream<TailTokenStream> 
+    where TailTokenStream: TokenStream {
+    tail: TailTokenStream,
+    stemmer: Arc<stemmer::Stemmer>,
+}
+
+impl<TailTokenStream> TokenStream for StemmerTokenStream<TailTokenStream>
+    where TailTokenStream: TokenStream {
+
+    fn token(&self) -> &Token {
+        self.tail.token()
+    }
+    
+    fn token_mut(&mut self) -> &mut Token {
+        self.tail.token_mut()
+    }
+
+    fn advance(&mut self) -> bool {
+        if self.tail.advance() {
+            // self.tail.token_mut().term.make_ascii_lowercase();
+            let new_str = self.stemmer.stem_str(&self.token().term);
+            true
+        }
+        else {
+            false
+        }
+    }
+
+}
+
+impl<TailTokenStream> StemmerTokenStream<TailTokenStream>
+    where TailTokenStream: TokenStream {
+    
+    fn wrap(stemmer: Arc<stemmer::Stemmer>, tail: TailTokenStream) -> StemmerTokenStream<TailTokenStream> {
+        StemmerTokenStream {
+            tail,
+            stemmer,
+        }
+    } 
+}

src/query/query_parser/user_input_ast.rs

@@ -3,7 +3,6 @@ use std::fmt::{Debug, Formatter};
 
 use crate::query::Occur;
 
-#[derive(PartialEq)]
 pub enum UserInputLeaf {
     Literal(UserInputLiteral),
     All,
@@ -36,7 +35,6 @@ impl Debug for UserInputLeaf {
     }
 }
 
-#[derive(PartialEq)]
 pub struct UserInputLiteral {
     pub field_name: Option<String>,
     pub phrase: String,
@@ -51,11 +49,9 @@ impl fmt::Debug for UserInputLiteral {
     }
 }
 
-#[derive(PartialEq)]
 pub enum UserInputBound {
     Inclusive(String),
     Exclusive(String),
-    Unbounded,
 }
 
 impl UserInputBound {
@@ -63,7 +59,6 @@ impl UserInputBound {
         match *self {
             UserInputBound::Inclusive(ref word) => write!(formatter, "[\"{}\"", word),
             UserInputBound::Exclusive(ref word) => write!(formatter, "{{\"{}\"", word),
-            UserInputBound::Unbounded => write!(formatter, "{{\"*\""),
         }
     }
 
@@ -71,7 +66,6 @@ impl UserInputBound {
         match *self {
             UserInputBound::Inclusive(ref word) => write!(formatter, "\"{}\"]", word),
             UserInputBound::Exclusive(ref word) => write!(formatter, "\"{}\"}}", word),
-            UserInputBound::Unbounded => write!(formatter, "\"*\"}}"),
         }
     }
 
@@ -79,7 +73,6 @@ impl UserInputBound {
         match *self {
             UserInputBound::Inclusive(ref contents) => contents,
             UserInputBound::Exclusive(ref contents) => contents,
-            UserInputBound::Unbounded => &"*",
         }
     }
 }
@@ -87,6 +80,9 @@ impl UserInputBound {
 pub enum UserInputAST {
     Clause(Vec<UserInputAST>),
     Unary(Occur, Box<UserInputAST>),
+    //    Not(Box<UserInputAST>),
+    //    Should(Box<UserInputAST>),
+    //    Must(Box<UserInputAST>),
     Leaf(Box<UserInputLeaf>),
 }
 
@@ -96,7 +92,7 @@ impl UserInputAST {
     }
 
     fn compose(occur: Occur, asts: Vec<UserInputAST>) -> UserInputAST {
-        assert_ne!(occur, Occur::MustNot);
+        assert!(occur != Occur::MustNot);
         assert!(!asts.is_empty());
         if asts.len() == 1 {
             asts.into_iter().next().unwrap() //< safe
@@ -109,10 +105,6 @@ impl UserInputAST {
         }
     }
 
-    pub fn empty_query() -> UserInputAST {
-        UserInputAST::Clause(Vec::default())
-    }
-
     pub fn and(asts: Vec<UserInputAST>) -> UserInputAST {
         UserInputAST::compose(Occur::Must, asts)
     }
@@ -122,6 +114,42 @@ impl UserInputAST {
     }
 }
 
+/*
+impl UserInputAST {
+
+    fn compose_occur(self, occur: Occur) -> UserInputAST {
+        match self {
+            UserInputAST::Not(other) => {
+                let new_occur = compose_occur(Occur::MustNot, occur);
+                other.simplify()
+            }
+            _ => {
+                self
+            }
+        }
+    }
+
+    pub fn simplify(self) -> UserInputAST {
+        match self {
+            UserInputAST::Clause(els) => {
+                if els.len() == 1 {
+                    return els.into_iter().next().unwrap();
+                } else {
+                    return self;
+                }
+            }
+            UserInputAST::Not(els) => {
+                if els.len() == 1 {
+                    return els.into_iter().next().unwrap();
+                } else {
+                    return self;
+                }
+            }
+        }
+    }
+}
+*/
+
 impl From<UserInputLiteral> for UserInputLeaf {
     fn from(literal: UserInputLiteral) -> UserInputLeaf {
         UserInputLeaf::Literal(literal)

src/query/range_query.rs

@@ -38,10 +38,14 @@ fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
 /// # Example
 ///
 /// ```rust
-/// # use tantivy::collector::Count;
+///
-/// # use tantivy::query::RangeQuery;
+/// # #[macro_use]
+/// # extern crate tantivy;
+/// # use tantivy::Index;
 /// # use tantivy::schema::{Schema, INDEXED};
-/// # use tantivy::{doc, Index, Result};
+/// # use tantivy::collector::Count;
+/// # use tantivy::Result;
+/// # use tantivy::query::RangeQuery;
 /// #
 /// # fn run() -> Result<()> {
 /// #     let mut schema_builder = Schema::builder();
@@ -334,33 +338,39 @@ mod tests {
     use crate::collector::Count;
     use crate::schema::{Document, Field, Schema, INDEXED};
     use crate::Index;
+    use crate::Result;
     use std::collections::Bound;
 
     #[test]
     fn test_range_query_simple() {
-        let mut schema_builder = Schema::builder();
+        fn run() -> Result<()> {
-        let year_field = schema_builder.add_u64_field("year", INDEXED);
+            let mut schema_builder = Schema::builder();
-        let schema = schema_builder.build();
+            let year_field = schema_builder.add_u64_field("year", INDEXED);
+            let schema = schema_builder.build();
 
-        let index = Index::create_in_ram(schema);
+            let index = Index::create_in_ram(schema);
-        {
+            {
-            let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
+                let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
-            for year in 1950u64..2017u64 {
+                for year in 1950u64..2017u64 {
-                let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
+                    let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
-                for _ in 0..num_docs_within_year {
+                    for _ in 0..num_docs_within_year {
-                    index_writer.add_document(doc!(year_field => year));
+                        index_writer.add_document(doc!(year_field => year));
+                    }
                 }
+                index_writer.commit().unwrap();
             }
-            index_writer.commit().unwrap();
+            let reader = index.reader().unwrap();
+            let searcher = reader.searcher();
+
+            let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960u64..1970u64);
+
+            // ... or `1960..=1969` if inclusive range is enabled.
+            let count = searcher.search(&docs_in_the_sixties, &Count)?;
+            assert_eq!(count, 2285);
+            Ok(())
         }
-        let reader = index.reader().unwrap();
-        let searcher = reader.searcher();
 
-        let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960u64..1970u64);
+        run().unwrap();
-
-        // ... or `1960..=1969` if inclusive range is enabled.
-        let count = searcher.search(&docs_in_the_sixties, &Count).unwrap();
-        assert_eq!(count, 2285);
     }
 
     #[test]
@@ -450,10 +460,7 @@ mod tests {
         let count_multiples =
             |range_query: RangeQuery| searcher.search(&range_query, &Count).unwrap();
 
-        assert_eq!(
+        assert_eq!(count_multiples(RangeQuery::new_f64(float_field, 10.0..11.0)), 9);
-            count_multiples(RangeQuery::new_f64(float_field, 10.0..11.0)),
-            9
-        );
         assert_eq!(
             count_multiples(RangeQuery::new_f64_bounds(
                 float_field,

src/query/regex_query.rs

@@ -4,18 +4,22 @@ use crate::schema::Field;
 use crate::Result;
 use crate::Searcher;
 use std::clone::Clone;
-use std::sync::Arc;
 use tantivy_fst::Regex;
 
-/// A Regex Query matches all of the documents
+// A Regex Query matches all of the documents
 /// containing a specific term that matches
-/// a regex pattern.
+/// a regex pattern
+/// A Fuzzy Query matches all of the documents
+/// containing a specific term that is within
+/// Levenshtein distance
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Schema, TEXT};
+/// use tantivy::{Index, Result, Term};
 /// use tantivy::collector::Count;
 /// use tantivy::query::RegexQuery;
-/// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, Index, Result, Term};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {
@@ -44,7 +48,7 @@ use tantivy_fst::Regex;
 ///     let searcher = reader.searcher();
 ///
 ///     let term = Term::from_field_text(title, "Diary");
-///     let query = RegexQuery::from_pattern("d[ai]{2}ry", title)?;
+///     let query = RegexQuery::new("d[ai]{2}ry".to_string(), title);
 ///     let count = searcher.search(&query, &Count)?;
 ///     assert_eq!(count, 3);
 ///     Ok(())
@@ -52,34 +56,30 @@ use tantivy_fst::Regex;
 /// ```
 #[derive(Debug, Clone)]
 pub struct RegexQuery {
-    regex: Arc<Regex>,
+    regex_pattern: String,
     field: Field,
 }
 
 impl RegexQuery {
-    /// Creates a new RegexQuery from a given pattern
+    /// Creates a new Fuzzy Query
-    pub fn from_pattern(regex_pattern: &str, field: Field) -> Result<Self> {
+    pub fn new(regex_pattern: String, field: Field) -> RegexQuery {
-        let regex = Regex::new(&regex_pattern)
-            .map_err(|_| TantivyError::InvalidArgument(regex_pattern.to_string()))?;
-        Ok(RegexQuery::from_regex(regex, field))
-    }
-
-    /// Creates a new RegexQuery from a fully built Regex
-    pub fn from_regex<T: Into<Arc<Regex>>>(regex: T, field: Field) -> Self {
         RegexQuery {
-            regex: regex.into(),
+            regex_pattern,
             field,
         }
     }
 
-    fn specialized_weight(&self) -> AutomatonWeight<Regex> {
+    fn specialized_weight(&self) -> Result<AutomatonWeight<Regex>> {
-        AutomatonWeight::new(self.field, self.regex.clone())
+        let automaton = Regex::new(&self.regex_pattern)
+            .map_err(|_| TantivyError::InvalidArgument(self.regex_pattern.clone()))?;
+
+        Ok(AutomatonWeight::new(self.field, automaton))
     }
 }
 
 impl Query for RegexQuery {
     fn weight(&self, _searcher: &Searcher, _scoring_enabled: bool) -> Result<Box<dyn Weight>> {
-        Ok(Box::new(self.specialized_weight()))
+        Ok(Box::new(self.specialized_weight()?))
     }
 }
 
@@ -87,14 +87,13 @@ impl Query for RegexQuery {
 mod test {
     use super::RegexQuery;
     use crate::collector::TopDocs;
+    use crate::schema::Schema;
     use crate::schema::TEXT;
-    use crate::schema::{Field, Schema};
     use crate::tests::assert_nearly_equals;
-    use crate::{Index, IndexReader};
+    use crate::Index;
-    use std::sync::Arc;
-    use tantivy_fst::Regex;
 
-    fn build_test_index() -> (IndexReader, Field) {
+    #[test]
+    pub fn test_regex_query() {
         let mut schema_builder = Schema::builder();
         let country_field = schema_builder.add_text_field("country", TEXT);
         let schema = schema_builder.build();
@@ -110,65 +109,20 @@ mod test {
             index_writer.commit().unwrap();
         }
         let reader = index.reader().unwrap();
-
-        (reader, country_field)
-    }
-
-    fn verify_regex_query(
-        query_matching_one: RegexQuery,
-        query_matching_zero: RegexQuery,
-        reader: IndexReader,
-    ) {
         let searcher = reader.searcher();
         {
+            let regex_query = RegexQuery::new("jap[ao]n".to_string(), country_field);
             let scored_docs = searcher
-                .search(&query_matching_one, &TopDocs::with_limit(2))
+                .search(&regex_query, &TopDocs::with_limit(2))
                 .unwrap();
             assert_eq!(scored_docs.len(), 1, "Expected only 1 document");
             let (score, _) = scored_docs[0];
             assert_nearly_equals(1f32, score);
         }
+        let regex_query = RegexQuery::new("jap[A-Z]n".to_string(), country_field);
         let top_docs = searcher
-            .search(&query_matching_zero, &TopDocs::with_limit(2))
+            .search(&regex_query, &TopDocs::with_limit(2))
             .unwrap();
         assert!(top_docs.is_empty(), "Expected ZERO document");
     }
-
-    #[test]
-    pub fn test_regex_query() {
-        let (reader, field) = build_test_index();
-
-        let matching_one = RegexQuery::from_pattern("jap[ao]n", field).unwrap();
-        let matching_zero = RegexQuery::from_pattern("jap[A-Z]n", field).unwrap();
-
-        verify_regex_query(matching_one, matching_zero, reader);
-    }
-
-    #[test]
-    pub fn test_construct_from_regex() {
-        let (reader, field) = build_test_index();
-
-        let matching_one = RegexQuery::from_regex(Regex::new("jap[ao]n").unwrap(), field);
-        let matching_zero = RegexQuery::from_regex(Regex::new("jap[A-Z]n").unwrap(), field);
-
-        verify_regex_query(matching_one, matching_zero, reader);
-    }
-
-    #[test]
-    pub fn test_construct_from_reused_regex() {
-        let r1 = Arc::new(Regex::new("jap[ao]n").unwrap());
-        let r2 = Arc::new(Regex::new("jap[A-Z]n").unwrap());
-
-        let (reader, field) = build_test_index();
-
-        let matching_one = RegexQuery::from_regex(r1.clone(), field);
-        let matching_zero = RegexQuery::from_regex(r2.clone(), field);
-
-        verify_regex_query(matching_one, matching_zero, reader.clone());
-
-        let matching_one = RegexQuery::from_regex(r1.clone(), field);
-        let matching_zero = RegexQuery::from_regex(r2.clone(), field);
-
-        verify_regex_query(matching_one, matching_zero, reader.clone());
-    }
 }

src/query/term_query/mod.rs

@@ -12,7 +12,7 @@ mod tests {
     use crate::collector::TopDocs;
     use crate::docset::DocSet;
     use crate::query::{Query, QueryParser, Scorer, TermQuery};
-    use crate::schema::{Field, IndexRecordOption, Schema, STRING, TEXT};
+    use crate::schema::{IndexRecordOption, Schema, STRING, TEXT};
     use crate::tests::assert_nearly_equals;
     use crate::Index;
     use crate::Term;
@@ -114,16 +114,4 @@ mod tests {
         let reader = index.reader().unwrap();
         assert_eq!(term_query.count(&*reader.searcher()).unwrap(), 1);
     }
-
-    #[test]
-    fn test_term_query_debug() {
-        let term_query = TermQuery::new(
-            Term::from_field_text(Field(1), "hello"),
-            IndexRecordOption::WithFreqs,
-        );
-        assert_eq!(
-            format!("{:?}", term_query),
-            "TermQuery(Term(field=1,bytes=[104, 101, 108, 108, 111]))"
-        );
-    }
 }

src/query/term_query/term_query.rs

@@ -7,7 +7,6 @@ use crate::Result;
 use crate::Searcher;
 use crate::Term;
 use std::collections::BTreeSet;
-use std::fmt;
 
 /// A Term query matches all of the documents
 /// containing a specific term.
@@ -20,10 +19,12 @@ use std::fmt;
 /// * `field norm` - number of tokens in the field.
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Schema, TEXT, IndexRecordOption};
+/// use tantivy::{Index, Result, Term};
 /// use tantivy::collector::{Count, TopDocs};
 /// use tantivy::query::TermQuery;
-/// use tantivy::schema::{Schema, TEXT, IndexRecordOption};
-/// use tantivy::{doc, Index, Result, Term};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {
@@ -60,18 +61,12 @@ use std::fmt;
 ///     Ok(())
 /// }
 /// ```
-#[derive(Clone)]
+#[derive(Clone, Debug)]
 pub struct TermQuery {
     term: Term,
     index_record_option: IndexRecordOption,
 }
 
-impl fmt::Debug for TermQuery {
-    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "TermQuery({:?})", self.term)
-    }
-}
-
 impl TermQuery {
     /// Creates a new term query.
     pub fn new(term: Term, segment_postings_options: IndexRecordOption) -> TermQuery {

src/reader/mod.rs

@@ -1,7 +1,6 @@
 mod pool;
 
-pub use self::pool::LeasedItem;
+use self::pool::{LeasedItem, Pool};
-use self::pool::Pool;
 use crate::core::Segment;
 use crate::directory::Directory;
 use crate::directory::WatchHandle;

src/reader/pool.rs

@@ -123,10 +123,6 @@ impl<T> Pool<T> {
     }
 }
 
-/// A LeasedItem holds an object borrowed from a Pool.
-///
-/// Upon drop, the object is automatically returned
-/// into the pool.
 pub struct LeasedItem<T> {
     gen_item: Option<GenerationItem<T>>,
     recycle_queue: Arc<Queue<GenerationItem<T>>>,

src/schema/document.rs

@@ -1,10 +1,9 @@
 use super::*;
+use crate::common::BinarySerializable;
+use crate::common::VInt;
+use crate::DateTime;
 use itertools::Itertools;
-use serde_derive::{Deserialize, Serialize};
 use std::io::{self, Read, Write};
-use tantivy_common::BinarySerializable;
-use tantivy_common::DateTime;
-use tantivy_common::VInt;
 
 /// Tantivy's Document is the object that can
 /// be indexed and then searched for.
@@ -169,7 +168,7 @@ impl BinarySerializable for Document {
 #[cfg(test)]
 mod tests {
 
-    use crate::*;
+    use crate::schema::*;
 
     #[test]
     fn test_doc() {

src/schema/facet.rs

@@ -1,3 +1,4 @@
+use crate::common::BinarySerializable;
 use once_cell::sync::Lazy;
 use regex::Regex;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
@@ -7,7 +8,6 @@ use std::fmt::{self, Debug, Display, Formatter};
 use std::io::{self, Read, Write};
 use std::str;
 use std::string::FromUtf8Error;
-use tantivy_common::BinarySerializable;
 
 const SLASH_BYTE: u8 = b'/';
 const ESCAPE_BYTE: u8 = b'\\';
@@ -59,7 +59,7 @@ impl Facet {
         &self.0
     }
 
-    pub fn from_encoded_string(facet_string: String) -> Facet {
+    pub(crate) fn from_encoded_string(facet_string: String) -> Facet {
         Facet(facet_string)
     }
 
@@ -104,7 +104,7 @@ impl Facet {
     }
 
     /// Accessor for the inner buffer of the `Facet`.
-    pub fn set_facet_str(&mut self, facet_str: &str) {
+    pub(crate) fn set_facet_str(&mut self, facet_str: &str) {
         self.0.clear();
         self.0.push_str(facet_str);
     }
@@ -120,7 +120,9 @@ impl Facet {
 
     /// Extract path from the `Facet`.
     pub fn to_path(&self) -> Vec<&str> {
-        self.encoded_str().split(|c| c == FACET_SEP_CHAR).collect()
+        self.encoded_str()
+            .split(|c| c == FACET_SEP_CHAR)
+            .collect()
     }
 }
 

src/schema/field.rs

@@ -1,8 +1,7 @@
-use serde_derive::{Deserialize, Serialize};
+use crate::common::BinarySerializable;
 use std::io;
 use std::io::Read;
 use std::io::Write;
-use tantivy_common::BinarySerializable;
 
 /// `Field` is actually a `u8` identifying a `Field`
 /// The schema is in charge of holding mapping between field names

src/schema/field_entry.rs

@@ -1,8 +1,7 @@
-use serde_derive::*;
+use crate::schema::IntOptions;
+use crate::schema::TextOptions;
 
-use crate::FieldType;
+use crate::schema::FieldType;
-use crate::IntOptions;
-use crate::TextOptions;
 use serde::de::{self, MapAccess, Visitor};
 use serde::ser::SerializeStruct;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
@@ -109,9 +108,7 @@ impl FieldEntry {
     /// Returns true iff the field is a int (signed or unsigned) fast field
     pub fn is_int_fast(&self) -> bool {
         match self.field_type {
-            FieldType::U64(ref options)
+            FieldType::U64(ref options) | FieldType::I64(ref options) | FieldType::F64(ref options) => options.is_fast(),
-            | FieldType::I64(ref options)
-            | FieldType::F64(ref options) => options.is_fast(),
             _ => false,
         }
     }
@@ -266,7 +263,7 @@ impl<'de> Deserialize<'de> for FieldEntry {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::TEXT;
+    use crate::schema::TEXT;
     use serde_json;
 
     #[test]

src/schema/field_type.rs

@@ -1,15 +1,16 @@
 use base64::decode;
 
-use crate::Facet;
+use crate::schema::{IntOptions, TextOptions};
-use crate::IndexRecordOption;
+
-use crate::TextFieldIndexing;
+use crate::schema::Facet;
-use crate::Value;
+use crate::schema::IndexRecordOption;
-use crate::{IntOptions, TextOptions};
+use crate::schema::TextFieldIndexing;
+use crate::schema::Value;
 use serde_json::Value as JsonValue;
 
 /// Possible error that may occur while parsing a field value
 /// At this point the JSON is known to be valid.
-#[derive(Debug, PartialEq)]
+#[derive(Debug)]
 pub enum ValueParsingError {
     /// Encountered a numerical value that overflows or underflow its integer type.
     OverflowError(String),
@@ -82,9 +83,9 @@ impl FieldType {
     pub fn is_indexed(&self) -> bool {
         match *self {
             FieldType::Str(ref text_options) => text_options.get_indexing_options().is_some(),
-            FieldType::U64(ref int_options)
+            FieldType::U64(ref int_options) | FieldType::I64(ref int_options) | FieldType::F64(ref int_options) => {
-            | FieldType::I64(ref int_options)
+                int_options.is_indexed()
-            | FieldType::F64(ref int_options) => int_options.is_indexed(),
+            }
             FieldType::Date(ref date_options) => date_options.is_indexed(),
             FieldType::HierarchicalFacet => true,
             FieldType::Bytes => false,
@@ -124,12 +125,9 @@ impl FieldType {
         match *json {
             JsonValue::String(ref field_text) => match *self {
                 FieldType::Str(_) => Ok(Value::Str(field_text.clone())),
-                FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => {
+                FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => Err(
-                    Err(ValueParsingError::TypeError(format!(
+                    ValueParsingError::TypeError(format!("Expected an integer, got {:?}", json)),
-                        "Expected an integer, got {:?}",
+                ),
-                        json
-                    )))
-                }
                 FieldType::HierarchicalFacet => Ok(Value::Facet(Facet::from(field_text))),
                 FieldType::Bytes => decode(field_text).map(Value::Bytes).map_err(|_| {
                     ValueParsingError::InvalidBase64(format!(
@@ -154,7 +152,7 @@ impl FieldType {
                         let msg = format!("Expected a u64 int, got {:?}", json);
                         Err(ValueParsingError::OverflowError(msg))
                     }
-                }
+                },
                 FieldType::F64(_) => {
                     if let Some(field_val_f64) = field_val_num.as_f64() {
                         Ok(Value::F64(field_val_f64))
@@ -182,9 +180,8 @@ impl FieldType {
 #[cfg(test)]
 mod tests {
     use super::FieldType;
-    use crate::field_type::ValueParsingError;
+    use crate::schema::field_type::ValueParsingError;
-    use crate::Value;
+    use crate::schema::Value;
-    use serde_json::json;
 
     #[test]
     fn test_bytes_value_from_json() {

src/schema/field_value.rs

@@ -1,11 +1,9 @@
-use crate::Field;
+use crate::common::BinarySerializable;
-use crate::Value;
+use crate::schema::Field;
-//use serde::Deserialize;
+use crate::schema::Value;
-use serde_derive::{Deserialize, Serialize};
 use std::io;
 use std::io::Read;
 use std::io::Write;
-use tantivy_common::BinarySerializable;
 
 /// `FieldValue` holds together a `Field` and its `Value`.
 #[derive(Debug, Clone, Ord, PartialEq, Eq, PartialOrd, Serialize, Deserialize)]

src/schema/flags.rs

@@ -1,5 +1,5 @@
-use crate::IntOptions;
+use crate::schema::IntOptions;
-use crate::TextOptions;
+use crate::schema::TextOptions;
 use std::ops::BitOr;
 
 #[derive(Clone)]

src/schema/index_record_option.rs

@@ -1,5 +1,3 @@
-use serde_derive::{Deserialize, Serialize};
-
 /// `IndexRecordOption` describes an amount information associated
 /// to a given indexed field.
 ///

src/schema/int_options.rs

@@ -1,5 +1,4 @@
-use crate::flags::{FastFlag, IndexedFlag, SchemaFlagList, StoredFlag};
+use crate::schema::flags::{FastFlag, IndexedFlag, SchemaFlagList, StoredFlag};
-use serde_derive::{Deserialize, Serialize};
 use std::ops::BitOr;
 
 /// Express whether a field is single-value or multi-valued.

src/schema/mod.rs

@@ -26,7 +26,7 @@ directory.
 ### Example
 
 ```
-use tantivy_schema::*;
+use tantivy::schema::*;
 let mut schema_builder = Schema::builder();
 let title_options = TextOptions::default()
     .set_stored()
@@ -59,7 +59,7 @@ when [`searcher.doc(doc_address)`](../struct.Searcher.html#method.doc) is called
 ### Example
 
 ```
-use tantivy_schema::*;
+use tantivy::schema::*;
 let mut schema_builder = Schema::builder();
 let num_stars_options = IntOptions::default()
     .set_stored()
@@ -93,7 +93,7 @@ using the  `|` operator.
 For instance, a schema containing the two fields defined in the example above could be rewritten :
 
 ```
-use tantivy_schema::*;
+use tantivy::schema::*;
 let mut schema_builder = Schema::builder();
 schema_builder.add_u64_field("num_stars", INDEXED | STORED);
 schema_builder.add_text_field("title", TEXT | STORED);
@@ -126,6 +126,7 @@ pub use self::schema::{Schema, SchemaBuilder};
 pub use self::value::Value;
 
 pub use self::facet::Facet;
+pub(crate) use self::facet::FACET_SEP_BYTE;
 
 pub use self::document::Document;
 pub use self::field::Field;

src/schema/named_field_document.rs

@@ -1,5 +1,4 @@
-use crate::Value;
+use crate::schema::Value;
-use serde_derive::Serialize;
 use std::collections::BTreeMap;
 
 /// Internal representation of a document used for JSON

src/schema/schema.rs

@@ -1,14 +1,14 @@
-use super::*;
 use crate::schema::field_type::ValueParsingError;
-use failure::Fail;
+use std::collections::BTreeMap;
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use super::*;
 use serde::de::{SeqAccess, Visitor};
 use serde::ser::SerializeSeq;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
 use serde_json::{self, Map as JsonObject, Value as JsonValue};
-use std::collections::BTreeMap;
-use std::collections::HashMap;
 use std::fmt;
-use std::sync::Arc;
 
 /// Tantivy has a very strict schema.
 /// You need to specify in advance whether a field is indexed or not,
@@ -21,7 +21,7 @@ use std::sync::Arc;
 /// # Examples
 ///
 /// ```
-/// use tantivy_schema::*;
+/// use tantivy::schema::*;
 ///
 /// let mut schema_builder = Schema::builder();
 /// let id_field = schema_builder.add_text_field("id", STRING);
@@ -208,7 +208,7 @@ impl Eq for InnerSchema {}
 /// # Examples
 ///
 /// ```
-/// use tantivy_schema::*;
+/// use tantivy::schema::*;
 ///
 /// let mut schema_builder = Schema::builder();
 /// let id_field = schema_builder.add_text_field("id", STRING);
@@ -246,25 +246,6 @@ impl Schema {
         self.0.fields_map.get(field_name).cloned()
     }
 
-    /// Create a named document off the doc.
-    pub fn convert_named_doc(
-        &self,
-        named_doc: NamedFieldDocument,
-    ) -> Result<Document, DocParsingError> {
-        let mut document = Document::new();
-        for (field_name, values) in named_doc.0 {
-            if let Some(field) = self.get_field(&field_name) {
-                for value in values {
-                    let field_value = FieldValue::new(field, value);
-                    document.add(field_value);
-                }
-            } else {
-                return Err(DocParsingError::NoSuchFieldInSchema(field_name));
-            }
-        }
-        Ok(document)
-    }
-
     /// Create a named document off the doc.
     pub fn to_named_doc(&self, doc: &Document) -> NamedFieldDocument {
         let mut field_map = BTreeMap::new();
@@ -301,26 +282,28 @@ impl Schema {
 
         let mut doc = Document::default();
         for (field_name, json_value) in json_obj.iter() {
-            let field = self
+            match self.get_field(field_name) {
-                .get_field(field_name)
+                Some(field) => {
-                .ok_or_else(|| DocParsingError::NoSuchFieldInSchema(field_name.clone()))?;
+                    let field_entry = self.get_field_entry(field);
-            let field_entry = self.get_field_entry(field);
+                    let field_type = field_entry.field_type();
-            let field_type = field_entry.field_type();
+                    match *json_value {
-            match *json_value {
+                        JsonValue::Array(ref json_items) => {
-                JsonValue::Array(ref json_items) => {
+                            for json_item in json_items {
-                    for json_item in json_items {
+                                let value = field_type.value_from_json(json_item).map_err(|e| {
-                        let value = field_type
+                                    DocParsingError::ValueError(field_name.clone(), e)
-                            .value_from_json(json_item)
+                                })?;
-                            .map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
+                                doc.add(FieldValue::new(field, value));
-                        doc.add(FieldValue::new(field, value));
+                            }
+                        }
+                        _ => {
+                            let value = field_type
+                                .value_from_json(json_value)
+                                .map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
+                            doc.add(FieldValue::new(field, value));
+                        }
                     }
                 }
-                _ => {
+                None => return Err(DocParsingError::NoSuchFieldInSchema(field_name.clone())),
-                    let value = field_type
-                        .value_from_json(json_value)
-                        .map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
-                    doc.add(FieldValue::new(field, value));
-                }
             }
         }
         Ok(doc)
@@ -377,19 +360,13 @@ impl<'de> Deserialize<'de> for Schema {
 
 /// Error that may happen when deserializing
 /// a document from JSON.
-#[derive(Debug, Fail, PartialEq)]
+#[derive(Debug)]
 pub enum DocParsingError {
     /// The payload given is not valid JSON.
-    #[fail(display = "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)]
     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
-    )]
     NoSuchFieldInSchema(String),
 }
 
@@ -401,7 +378,6 @@ mod tests {
     use crate::schema::*;
     use matches::{assert_matches, matches};
     use serde_json;
-    use std::collections::BTreeMap;
 
     #[test]
     pub fn is_indexed_test() {
@@ -516,54 +492,6 @@ mod tests {
         assert_eq!(doc, doc_serdeser);
     }
 
-    #[test]
-    pub fn test_document_from_nameddoc() {
-        let mut schema_builder = Schema::builder();
-        let title = schema_builder.add_text_field("title", TEXT);
-        let val = schema_builder.add_i64_field("val", INDEXED);
-        let schema = schema_builder.build();
-        let mut named_doc_map = BTreeMap::default();
-        named_doc_map.insert(
-            "title".to_string(),
-            vec![Value::from("title1"), Value::from("title2")],
-        );
-        named_doc_map.insert(
-            "val".to_string(),
-            vec![Value::from(14u64), Value::from(-1i64)],
-        );
-        let doc = schema
-            .convert_named_doc(NamedFieldDocument(named_doc_map))
-            .unwrap();
-        assert_eq!(
-            doc.get_all(title),
-            vec![
-                &Value::from("title1".to_string()),
-                &Value::from("title2".to_string())
-            ]
-        );
-        assert_eq!(
-            doc.get_all(val),
-            vec![&Value::from(14u64), &Value::from(-1i64)]
-        );
-    }
-
-    #[test]
-    pub fn test_document_from_nameddoc_error() {
-        let schema = Schema::builder().build();
-        let mut named_doc_map = BTreeMap::default();
-        named_doc_map.insert(
-            "title".to_string(),
-            vec![Value::from("title1"), Value::from("title2")],
-        );
-        let err = schema
-            .convert_named_doc(NamedFieldDocument(named_doc_map))
-            .unwrap_err();
-        assert_eq!(
-            err,
-            DocParsingError::NoSuchFieldInSchema("title".to_string())
-        );
-    }
-
     #[test]
     pub fn test_parse_document() {
         let mut schema_builder = Schema::builder();

src/schema/term.rs

@@ -1,11 +1,11 @@
 use std::fmt;
 
-use crate::Facet;
+use super::Field;
-use crate::Field;
+use crate::common;
+use crate::schema::Facet;
+use crate::DateTime;
 use byteorder::{BigEndian, ByteOrder};
 use std::str;
-use tantivy_common as common;
-use tantivy_common::DateTime;
 
 /// Size (in bytes) of the buffer of a int field.
 const INT_TERM_LEN: usize = 4 + 8;
@@ -94,7 +94,7 @@ impl Term {
     }
 
     /// Creates a new Term for a given field.
-    pub fn for_field(field: Field) -> Term {
+    pub(crate) fn for_field(field: Field) -> Term {
         let mut term = Term(Vec::with_capacity(100));
         term.set_field(field);
         term
@@ -134,7 +134,7 @@ impl Term {
         self.0.extend(bytes);
     }
 
-    pub fn from_field_bytes(field: Field, bytes: &[u8]) -> Term {
+    pub(crate) fn from_field_bytes(field: Field, bytes: &[u8]) -> Term {
         let mut term = Term::for_field(field);
         term.set_bytes(bytes);
         term
@@ -224,19 +224,14 @@ where
 
 impl fmt::Debug for Term {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(
+        write!(f, "Term({:?})", &self.0[..])
-            f,
-            "Term(field={},bytes={:?})",
-            self.field().0,
-            self.value_bytes()
-        )
     }
 }
 
 #[cfg(test)]
 mod tests {
 
-    use crate::{Schema, Term, STRING};
+    use crate::schema::*;
 
     #[test]
     pub fn test_term() {

src/schema/text_options.rs

@@ -1,7 +1,6 @@
-use crate::flags::SchemaFlagList;
+use crate::schema::flags::SchemaFlagList;
-use crate::flags::StoredFlag;
+use crate::schema::flags::StoredFlag;
-use crate::IndexRecordOption;
+use crate::schema::IndexRecordOption;
-use serde_derive::{Deserialize, Serialize};
 use std::borrow::Cow;
 use std::ops::BitOr;
 
@@ -152,7 +151,7 @@ where
 
 #[cfg(test)]
 mod tests {
-    use crate::{FieldType, IndexRecordOption, Schema, STORED, TEXT};
+    use crate::schema::*;
 
     #[test]
     fn test_field_options() {

src/schema/value.rs

@@ -1,10 +1,8 @@
-use crate::Facet;
+use crate::schema::Facet;
-use chrono;
+use crate::DateTime;
 use serde::de::Visitor;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
-use std::{cmp::Ordering, fmt};
+use std::{fmt, cmp::Ordering};
-
-pub(crate) type DateTime = chrono::DateTime<chrono::Utc>;
 
 /// Value represents the value of a any field.
 /// It is an enum over all over all of the possible field type.
@@ -29,7 +27,7 @@ pub enum Value {
 impl Eq for Value {}
 impl Ord for Value {
     fn cmp(&self, other: &Self) -> Ordering {
-        match (self, other) {
+        match (self,other) {
             (Value::Str(l), Value::Str(r)) => l.cmp(r),
             (Value::U64(l), Value::U64(r)) => l.cmp(r),
             (Value::I64(l), Value::I64(r)) => l.cmp(r),
@@ -37,7 +35,7 @@ impl Ord for Value {
             (Value::Facet(l), Value::Facet(r)) => l.cmp(r),
             (Value::Bytes(l), Value::Bytes(r)) => l.cmp(r),
             (Value::F64(l), Value::F64(r)) => {
-                match (l.is_nan(), r.is_nan()) {
+                match (l.is_nan(),r.is_nan()) {
                     (false, false) => l.partial_cmp(r).unwrap(), // only fail on NaN
                     (true, true) => Ordering::Equal,
                     (true, false) => Ordering::Less, // we define NaN as less than -∞
@@ -157,7 +155,7 @@ impl Value {
             Value::F64(ref value) => *value,
             _ => panic!("This is not a f64 field."),
         }
-    }
+    }    
 
     /// Returns the Date-value, provided the value is of the `Date` type.
     ///
@@ -220,11 +218,11 @@ impl From<Vec<u8>> for Value {
 }
 
 mod binary_serialize {
-    use crate::Facet;
+    use super::Value;
-    use crate::Value;
+    use crate::common::{BinarySerializable, f64_to_u64, u64_to_f64};
+    use crate::schema::Facet;
     use chrono::{TimeZone, Utc};
     use std::io::{self, Read, Write};
-    use tantivy_common::{f64_to_u64, u64_to_f64, BinarySerializable};
 
     const TEXT_CODE: u8 = 0;
     const U64_CODE: u8 = 1;

src/snippet/mod.rs

@@ -63,7 +63,7 @@ impl FragmentCandidate {
     fn try_add_token(&mut self, token: &Token, terms: &BTreeMap<String, f32>) {
         self.stop_offset = token.offset_to;
 
-        if let Some(&score) = terms.get(&token.text.to_lowercase()) {
+        if let Some(score) = terms.get(&token.text.to_lowercase()) {
             self.score += score;
             self.highlighted
                 .push(HighlightSection::new(token.offset_from, token.offset_to));
@@ -142,7 +142,7 @@ impl Snippet {
 /// Fragments must be valid in the sense that `&text[fragment.start..fragment.stop]`\
 /// has to be a valid string.
 fn search_fragments<'a>(
-    tokenizer: &BoxedTokenizer,
+    tokenizer: &dyn BoxedTokenizer,
     text: &'a str,
     terms: &BTreeMap<String, f32>,
     max_num_chars: usize,
@@ -150,6 +150,7 @@ fn search_fragments<'a>(
     let mut token_stream = tokenizer.token_stream(text);
     let mut fragment = FragmentCandidate::new(0);
     let mut fragments: Vec<FragmentCandidate> = vec![];
+
     while let Some(next) = token_stream.next() {
         if (next.offset_to - fragment.start_offset) > max_num_chars {
             if fragment.score > 0.0 {
@@ -213,9 +214,11 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
 /// # Example
 ///
 /// ```rust
-/// # use tantivy::query::QueryParser;
+/// # #[macro_use]
+/// # extern crate tantivy;
+/// # use tantivy::Index;
 /// # use tantivy::schema::{Schema, TEXT};
-/// # use tantivy::{doc, Index};
+/// # use tantivy::query::QueryParser;
 /// use tantivy::SnippetGenerator;
 ///
 /// # fn main() -> tantivy::Result<()> {
@@ -251,7 +254,7 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
 /// ```
 pub struct SnippetGenerator {
     terms_text: BTreeMap<String, f32>,
-    tokenizer: BoxedTokenizer,
+    tokenizer: Box<dyn BoxedTokenizer>,
     field: Field,
     max_num_chars: usize,
 }
@@ -313,8 +316,12 @@ impl SnippetGenerator {
 
     /// Generates a snippet for the given text.
     pub fn snippet(&self, text: &str) -> Snippet {
-        let fragment_candidates =
+        let fragment_candidates = search_fragments(
-            search_fragments(&self.tokenizer, &text, &self.terms_text, self.max_num_chars);
+            &*self.tokenizer,
+            &text,
+            &self.terms_text,
+            self.max_num_chars,
+        );
         select_best_fragment_combination(&fragment_candidates[..], &text)
     }
 }
@@ -324,7 +331,7 @@ mod tests {
     use super::{search_fragments, select_best_fragment_combination};
     use crate::query::QueryParser;
     use crate::schema::{IndexRecordOption, Schema, TextFieldIndexing, TextOptions, TEXT};
-    use crate::tokenizer::SimpleTokenizer;
+    use crate::tokenizer::{box_tokenizer, SimpleTokenizer};
     use crate::Index;
     use crate::SnippetGenerator;
     use maplit::btreemap;
@@ -348,12 +355,12 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet() {
-        let boxed_tokenizer = SimpleTokenizer.into();
+        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
         let terms = btreemap! {
             String::from("rust") => 1.0,
             String::from("language") => 0.9
         };
-        let fragments = search_fragments(&boxed_tokenizer, TEST_TEXT, &terms, 100);
+        let fragments = search_fragments(&*boxed_tokenizer, TEST_TEXT, &terms, 100);
         assert_eq!(fragments.len(), 7);
         {
             let first = &fragments[0];
@@ -375,13 +382,13 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_scored_fragment() {
-        let boxed_tokenizer = SimpleTokenizer.into();
+        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
         {
             let terms = btreemap! {
                 String::from("rust") =>1.0f32,
                 String::from("language") => 0.9f32
             };
-            let fragments = search_fragments(&boxed_tokenizer, TEST_TEXT, &terms, 20);
+            let fragments = search_fragments(&*boxed_tokenizer, TEST_TEXT, &terms, 20);
             {
                 let first = &fragments[0];
                 assert_eq!(first.score, 1.0);
@@ -390,13 +397,13 @@ Survey in 2016, 2017, and 2018."#;
             let snippet = select_best_fragment_combination(&fragments[..], &TEST_TEXT);
             assert_eq!(snippet.to_html(), "<b>Rust</b> is a systems")
         }
-        let boxed_tokenizer = SimpleTokenizer.into();
+        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
         {
             let terms = btreemap! {
                 String::from("rust") =>0.9f32,
                 String::from("language") => 1.0f32
             };
-            let fragments = search_fragments(&boxed_tokenizer, TEST_TEXT, &terms, 20);
+            let fragments = search_fragments(&*boxed_tokenizer, TEST_TEXT, &terms, 20);
             //assert_eq!(fragments.len(), 7);
             {
                 let first = &fragments[0];
@@ -410,14 +417,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_in_second_fragment() {
-        let boxed_tokenizer = SimpleTokenizer.into();
+        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
 
         let text = "a b c d e f g";
 
         let mut terms = BTreeMap::new();
         terms.insert(String::from("c"), 1.0);
 
-        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 3);
+        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 3);
 
         assert_eq!(fragments.len(), 1);
         {
@@ -434,14 +441,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_term_at_the_end_of_fragment() {
-        let boxed_tokenizer = SimpleTokenizer.into();
+        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
 
         let text = "a b c d e f f g";
 
         let mut terms = BTreeMap::new();
         terms.insert(String::from("f"), 1.0);
 
-        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 3);
+        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 3);
 
         assert_eq!(fragments.len(), 2);
         {
@@ -458,7 +465,7 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_second_fragment_has_the_highest_score() {
-        let boxed_tokenizer = SimpleTokenizer.into();
+        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
 
         let text = "a b c d e f g";
 
@@ -466,7 +473,7 @@ Survey in 2016, 2017, and 2018."#;
         terms.insert(String::from("f"), 1.0);
         terms.insert(String::from("a"), 0.9);
 
-        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 7);
+        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 7);
 
         assert_eq!(fragments.len(), 2);
         {
@@ -483,14 +490,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_term_not_in_text() {
-        let boxed_tokenizer = SimpleTokenizer.into();
+        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
 
         let text = "a b c d";
 
         let mut terms = BTreeMap::new();
         terms.insert(String::from("z"), 1.0);
 
-        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 3);
+        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 3);
 
         assert_eq!(fragments.len(), 0);
 
@@ -501,12 +508,12 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_no_terms() {
-        let boxed_tokenizer = SimpleTokenizer.into();
+        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
 
         let text = "a b c d";
 
         let terms = BTreeMap::new();
-        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 3);
+        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 3);
         assert_eq!(fragments.len(), 0);
 
         let snippet = select_best_fragment_combination(&fragments[..], &text);

src/termdict/term_info_store.rs

@@ -268,7 +268,7 @@ mod tests {
 
     #[test]
     fn test_term_info_block() {
-        common::fixed_size_test::<TermInfoBlockMeta>();
+        common::test::fixed_size_test::<TermInfoBlockMeta>();
     }
 
     #[test]

src/tokenizer/alphanum_only.rs

@@ -1,6 +1,7 @@
 //! # Example
-//! ```rust
+//! ```
-//! use tantivy_tokenizer::*;
+//! extern crate tantivy;
+//! use tantivy::tokenizer::*;
 //!
 //! # fn main() {
 //!
@@ -64,6 +65,14 @@ impl<TailTokenStream> TokenStream for AlphaNumOnlyFilterStream<TailTokenStream>
 where
     TailTokenStream: TokenStream,
 {
+    fn token(&self) -> &Token {
+        self.tail.token()
+    }
+
+    fn token_mut(&mut self) -> &mut Token {
+        self.tail.token_mut()
+    }
+
     fn advance(&mut self) -> bool {
         while self.tail.advance() {
             if self.predicate(self.tail.token()) {
@@ -73,12 +82,4 @@ where
 
         false
     }
-
-    fn token(&self) -> &Token {
-        self.tail.token()
-    }
-
-    fn token_mut(&mut self) -> &mut Token {
-        self.tail.token_mut()
-    }
 }

src/tokenizer/ascii_folding_filter.rs

@@ -1558,11 +1558,11 @@ fn to_ascii(text: &mut String, output: &mut String) {
 #[cfg(test)]
 mod tests {
     use super::to_ascii;
-    use crate::AsciiFoldingFilter;
+    use crate::tokenizer::AsciiFoldingFilter;
-    use crate::RawTokenizer;
+    use crate::tokenizer::RawTokenizer;
-    use crate::SimpleTokenizer;
+    use crate::tokenizer::SimpleTokenizer;
-    use crate::TokenStream;
+    use crate::tokenizer::TokenStream;
-    use crate::Tokenizer;
+    use crate::tokenizer::Tokenizer;
     use std::iter;
 
     #[test]

src/tokenizer/facet_tokenizer.rs

@@ -1,5 +1,5 @@
 use super::{Token, TokenStream, Tokenizer};
-use crate::FACET_SEP_BYTE;
+use crate::schema::FACET_SEP_BYTE;
 
 /// The `FacetTokenizer` process a `Facet` binary representation
 /// and emits a token for all of its parent.
@@ -83,8 +83,8 @@ impl<'a> TokenStream for FacetTokenStream<'a> {
 mod tests {
 
     use super::FacetTokenizer;
+    use crate::schema::Facet;
     use crate::tokenizer::{Token, TokenStream, Tokenizer};
-    use tantivy_schema::Facet;
 
     #[test]
     fn test_facet_tokenizer() {

src/tokenizer/lower_caser.rs

@@ -72,10 +72,10 @@ where
 
 #[cfg(test)]
 mod tests {
-    use crate::LowerCaser;
+    use crate::tokenizer::LowerCaser;
-    use crate::SimpleTokenizer;
+    use crate::tokenizer::SimpleTokenizer;
-    use crate::TokenStream;
+    use crate::tokenizer::TokenStream;
-    use crate::Tokenizer;
+    use crate::tokenizer::Tokenizer;
 
     #[test]
     fn test_to_lower_case() {

src/tokenizer/mod.rs

@@ -4,8 +4,9 @@
 //! You must define in your schema which tokenizer should be used for
 //! each of your fields :
 //!
-//! ```rust
+//! ```
-//! use tantivy_schema::*;
+//! extern crate tantivy;
+//! use tantivy::schema::*;
 //!
 //! # fn main() {
 //! let mut schema_builder = Schema::builder();
@@ -64,7 +65,9 @@
 //! For instance, the `en_stem` is defined as follows.
 //!
 //! ```rust
-//! use tantivy_tokenizer::*;
+//! # extern crate tantivy;
+//!
+//! use tantivy::tokenizer::*;
 //!
 //! # fn main() {
 //! let en_stem = SimpleTokenizer
@@ -77,9 +80,10 @@
 //! Once your tokenizer is defined, you need to
 //! register it with a name in your index's [`TokenizerManager`](./struct.TokenizerManager.html).
 //!
-//! ```rust
+//! ```
-//! # use tantivy_schema::Schema;
+//! # extern crate tantivy;
-//! # use tantivy_tokenizer::*;
+//! # use tantivy::schema::Schema;
+//! # use tantivy::tokenizer::*;
 //! # use tantivy::Index;
 //! # fn main() {
 //! # let custom_en_tokenizer = SimpleTokenizer;
@@ -97,9 +101,10 @@
 //!
 //! # Example
 //!
-//! ```rust
+//! ```
-//! use tantivy_schema::{Schema, IndexRecordOption, TextOptions, TextFieldIndexing};
+//! extern crate tantivy;
-//! use tantivy_tokenizer::*;
+//! use tantivy::schema::{Schema, IndexRecordOption, TextOptions, TextFieldIndexing};
+//! use tantivy::tokenizer::*;
 //! use tantivy::Index;
 //!
 //! # fn main() {
@@ -150,10 +155,9 @@ pub use self::simple_tokenizer::SimpleTokenizer;
 pub use self::stemmer::{Language, Stemmer};
 pub use self::stop_word_filter::StopWordFilter;
 pub(crate) use self::token_stream_chain::TokenStreamChain;
-
+pub(crate) use self::tokenizer::box_tokenizer;
 pub use self::tokenizer::BoxedTokenizer;
 
-pub(crate) const FACET_SEP_BYTE: u8 = 0u8;
 pub use self::tokenizer::{Token, TokenFilter, TokenStream, Tokenizer};
 pub use self::tokenizer_manager::TokenizerManager;
 

src/tokenizer/ngram_tokenizer.rs

@@ -29,8 +29,9 @@ use super::{Token, TokenStream, Tokenizer};
 ///
 /// # Example
 ///
-/// ```rust
+/// ```
-/// use tantivy_tokenizer::*;
+/// # extern crate tantivy;
+/// use tantivy::tokenizer::*;
 /// # fn main() {
 /// let tokenizer = NgramTokenizer::new(2, 3, false);
 /// let mut stream = tokenizer.token_stream("hello");
@@ -308,9 +309,9 @@ mod tests {
     use super::CodepointFrontiers;
     use super::NgramTokenizer;
     use super::StutteringIterator;
-    use crate::tests::assert_token;
+    use crate::tokenizer::tests::assert_token;
-    use crate::tokenizer::{TokenStream, Tokenizer};
+    use crate::tokenizer::tokenizer::{TokenStream, Tokenizer};
-    use crate::Token;
+    use crate::tokenizer::Token;
 
     fn test_helper<T: TokenStream>(mut tokenizer: T) -> Vec<Token> {
         let mut tokens: Vec<Token> = vec![];

src/tokenizer/remove_long.rs

@@ -1,6 +1,7 @@
 //! # Example
-//! ```rust
+//! ```
-//! use tantivy_tokenizer::*;
+//! extern crate tantivy;
+//! use tantivy::tokenizer::*;
 //!
 //! # fn main() {
 //!

src/tokenizer/stemmer.rs

@@ -1,6 +1,5 @@
 use super::{Token, TokenFilter, TokenStream};
 use rust_stemmers::{self, Algorithm};
-use serde_derive::{Deserialize, Serialize};
 
 /// Available stemmer languages.
 #[derive(Debug, Serialize, Deserialize, Eq, PartialEq, Copy, Clone)]

src/tokenizer/stop_word_filter.rs

@@ -1,6 +1,7 @@
 //! # Example
-//! ```rust
+//! ```
-//! use tantivy_tokenizer::*;
+//! extern crate tantivy;
+//! use tantivy::tokenizer::*;
 //!
 //! # fn main() {
 //! let tokenizer = SimpleTokenizer

src/tokenizer/token_stream_chain.rs

@@ -1,4 +1,4 @@
-use crate::{Token, TokenStream};
+use crate::tokenizer::{Token, TokenStream};
 
 const POSITION_GAP: usize = 2;
 

src/tokenizer/tokenizer.rs

@@ -1,4 +1,4 @@
-use crate::TokenStreamChain;
+use crate::tokenizer::TokenStreamChain;
 /// The tokenizer module contains all of the tools used to process
 /// text in `tantivy`.
 use std::borrow::{Borrow, BorrowMut};
@@ -56,7 +56,9 @@ pub trait Tokenizer<'a>: Sized + Clone {
     /// # Example
     ///
     /// ```rust
-    /// use tantivy_tokenizer::*;
+    /// # extern crate tantivy;
+    ///
+    /// use tantivy::tokenizer::*;
     ///
     /// # fn main() {
     /// let en_stem = SimpleTokenizer
@@ -78,7 +80,7 @@ pub trait Tokenizer<'a>: Sized + Clone {
 }
 
 /// A boxed tokenizer
-trait BoxedTokenizerTrait: Send + Sync {
+pub trait BoxedTokenizer: Send + Sync {
     /// Tokenize a `&str`
     fn token_stream<'a>(&self, text: &'a str) -> Box<dyn TokenStream + 'a>;
 
@@ -90,41 +92,7 @@ trait BoxedTokenizerTrait: Send + Sync {
     fn token_stream_texts<'b>(&self, texts: &'b [&'b str]) -> Box<dyn TokenStream + 'b>;
 
     /// Return a boxed clone of the tokenizer
-    fn boxed_clone(&self) -> BoxedTokenizer;
+    fn boxed_clone(&self) -> Box<dyn BoxedTokenizer>;
-}
-
-/// A boxed tokenizer
-pub struct BoxedTokenizer(Box<dyn BoxedTokenizerTrait>);
-
-impl<T> From<T> for BoxedTokenizer
-where
-    T: 'static + Send + Sync + for<'a> Tokenizer<'a>,
-{
-    fn from(tokenizer: T) -> BoxedTokenizer {
-        BoxedTokenizer(Box::new(BoxableTokenizer(tokenizer)))
-    }
-}
-
-impl BoxedTokenizer {
-    /// Tokenize a `&str`
-    pub fn token_stream<'a>(&self, text: &'a str) -> Box<dyn TokenStream + 'a> {
-        self.0.token_stream(text)
-    }
-
-    /// Tokenize an array`&str`
-    ///
-    /// The resulting `TokenStream` is equivalent to what would be obtained if the &str were
-    /// one concatenated `&str`, with an artificial position gap of `2` between the different fields
-    /// to prevent accidental `PhraseQuery` to match accross two terms.
-    pub fn token_stream_texts<'b>(&self, texts: &'b [&'b str]) -> Box<dyn TokenStream + 'b> {
-        self.0.token_stream_texts(texts)
-    }
-}
-
-impl Clone for BoxedTokenizer {
-    fn clone(&self) -> BoxedTokenizer {
-        self.0.boxed_clone()
-    }
 }
 
 #[derive(Clone)]
@@ -132,7 +100,7 @@ struct BoxableTokenizer<A>(A)
 where
     A: for<'a> Tokenizer<'a> + Send + Sync;
 
-impl<A> BoxedTokenizerTrait for BoxableTokenizer<A>
+impl<A> BoxedTokenizer for BoxableTokenizer<A>
 where
     A: 'static + Send + Sync + for<'a> Tokenizer<'a>,
 {
@@ -157,11 +125,18 @@ where
         }
     }
 
-    fn boxed_clone(&self) -> BoxedTokenizer {
+    fn boxed_clone(&self) -> Box<dyn BoxedTokenizer> {
-        self.0.clone().into()
+        Box::new(self.clone())
     }
 }
 
+pub(crate) fn box_tokenizer<A>(a: A) -> Box<dyn BoxedTokenizer>
+where
+    A: 'static + Send + Sync + for<'a> Tokenizer<'a>,
+{
+    Box::new(BoxableTokenizer(a))
+}
+
 impl<'b> TokenStream for Box<dyn TokenStream + 'b> {
     fn advance(&mut self) -> bool {
         let token_stream: &mut dyn TokenStream = self.borrow_mut();
@@ -186,7 +161,8 @@ impl<'b> TokenStream for Box<dyn TokenStream + 'b> {
 /// # Example
 ///
 /// ```
-/// use tantivy_tokenizer::*;
+/// extern crate tantivy;
+/// use tantivy::tokenizer::*;
 ///
 /// # fn main() {
 /// let tokenizer = SimpleTokenizer
@@ -227,7 +203,8 @@ pub trait TokenStream {
     /// and `.token()`.
     ///
     /// ```
-    /// # use tantivy_tokenizer::*;
+    /// # extern crate tantivy;
+    /// # use tantivy::tokenizer::*;
     /// #
     /// # fn main() {
     /// # let tokenizer = SimpleTokenizer

src/tokenizer/tokenizer_manager.rs

@@ -1,12 +1,14 @@
-use crate::stemmer::Language;
+use crate::tokenizer::box_tokenizer;
-use crate::BoxedTokenizer;
+use crate::tokenizer::stemmer::Language;
-use crate::LowerCaser;
+use crate::tokenizer::BoxedTokenizer;
-use crate::RawTokenizer;
+use crate::tokenizer::LowerCaser;
-use crate::RemoveLongFilter;
+use crate::tokenizer::RawTokenizer;
-use crate::SimpleTokenizer;
+use crate::tokenizer::RemoveLongFilter;
-use crate::Stemmer;
+use crate::tokenizer::SimpleTokenizer;
-use crate::Tokenizer;
+use crate::tokenizer::Stemmer;
+use crate::tokenizer::Tokenizer;
 use std::collections::HashMap;
+use std::ops::Deref;
 use std::sync::{Arc, RwLock};
 
 /// The tokenizer manager serves as a store for
@@ -23,28 +25,30 @@ use std::sync::{Arc, RwLock};
 ///  search engine.
 #[derive(Clone)]
 pub struct TokenizerManager {
-    tokenizers: Arc<RwLock<HashMap<String, BoxedTokenizer>>>,
+    tokenizers: Arc<RwLock<HashMap<String, Box<dyn BoxedTokenizer>>>>,
 }
 
 impl TokenizerManager {
     /// Registers a new tokenizer associated with a given name.
     pub fn register<A>(&self, tokenizer_name: &str, tokenizer: A)
     where
-        A: Into<BoxedTokenizer>,
+        A: 'static + Send + Sync + for<'a> Tokenizer<'a>,
     {
+        let boxed_tokenizer = box_tokenizer(tokenizer);
         self.tokenizers
             .write()
             .expect("Acquiring the lock should never fail")
-            .insert(tokenizer_name.to_string(), tokenizer.into());
+            .insert(tokenizer_name.to_string(), boxed_tokenizer);
     }
 
     /// Accessing a tokenizer given its name.
-    pub fn get(&self, tokenizer_name: &str) -> Option<BoxedTokenizer> {
+    pub fn get(&self, tokenizer_name: &str) -> Option<Box<dyn BoxedTokenizer>> {
         self.tokenizers
             .read()
             .expect("Acquiring the lock should never fail")
             .get(tokenizer_name)
-            .cloned()
+            .map(Deref::deref)
+            .map(BoxedTokenizer::boxed_clone)
     }
 }
 

tantivy-common/Cargo.toml

@@ -1,10 +0,0 @@
-[package]
-name = "tantivy-common"
-version = "0.1.0"
-authors = ["Paul Masurel <paul.masurel@gmail.com>"]
-edition = "2018"
-workspace = ".."
-
-[dependencies]
-byteorder = "*"
-chrono = "*"

tantivy-common/src/composite_file.rs

@@ -1,235 +0,0 @@
-use crate::common::BinarySerializable;
-use crate::common::CountingWriter;
-use crate::common::VInt;
-use crate::directory::ReadOnlySource;
-use crate::directory::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};
-
-#[derive(Eq, PartialEq, Hash, Copy, Ord, PartialOrd, Clone, Debug)]
-pub struct FileAddr {
-    field: Field,
-    idx: usize,
-}
-
-impl FileAddr {
-    fn new(field: Field, idx: usize) -> FileAddr {
-        FileAddr { field, idx }
-    }
-}
-
-impl BinarySerializable for FileAddr {
-    fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
-        self.field.serialize(writer)?;
-        VInt(self.idx as u64).serialize(writer)?;
-        Ok(())
-    }
-
-    fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
-        let field = Field::deserialize(reader)?;
-        let idx = VInt::deserialize(reader)?.0 as usize;
-        Ok(FileAddr { field, idx })
-    }
-}
-
-/// A `CompositeWrite` is used to write a `CompositeFile`.
-pub struct CompositeWrite<W = WritePtr> {
-    write: CountingWriter<W>,
-    offsets: HashMap<FileAddr, u64>,
-}
-
-impl<W: Write> CompositeWrite<W> {
-    /// Crate a new API writer that writes a composite file
-    /// in a given write.
-    pub fn wrap(w: W) -> CompositeWrite<W> {
-        CompositeWrite {
-            write: CountingWriter::wrap(w),
-            offsets: HashMap::new(),
-        }
-    }
-
-    /// Start writing a new field.
-    pub fn for_field(&mut self, field: Field) -> &mut CountingWriter<W> {
-        self.for_field_with_idx(field, 0)
-    }
-
-    /// Start writing a new field.
-    pub fn for_field_with_idx(&mut self, field: Field, idx: usize) -> &mut CountingWriter<W> {
-        let offset = self.write.written_bytes();
-        let file_addr = FileAddr::new(field, idx);
-        assert!(!self.offsets.contains_key(&file_addr));
-        self.offsets.insert(file_addr, offset);
-        &mut self.write
-    }
-
-    /// Close the composite file
-    ///
-    /// An index of the different field offsets
-    /// will be written as a footer.
-    pub fn close(mut self) -> io::Result<()> {
-        let footer_offset = self.write.written_bytes();
-        VInt(self.offsets.len() as u64).serialize(&mut self.write)?;
-
-        let mut offset_fields: Vec<_> = self
-            .offsets
-            .iter()
-            .map(|(file_addr, offset)| (*offset, *file_addr))
-            .collect();
-
-        offset_fields.sort();
-
-        let mut prev_offset = 0;
-        for (offset, file_addr) in offset_fields {
-            VInt((offset - prev_offset) as u64).serialize(&mut self.write)?;
-            file_addr.serialize(&mut self.write)?;
-            prev_offset = offset;
-        }
-
-        let footer_len = (self.write.written_bytes() - footer_offset) as u32;
-        footer_len.serialize(&mut self.write)?;
-        self.write.flush()?;
-        Ok(())
-    }
-}
-
-/// A composite file is an abstraction to store a
-/// file partitioned by field.
-///
-/// The file needs to be written field by field.
-/// A footer describes the start and stop offsets
-/// for each field.
-#[derive(Clone)]
-pub struct CompositeFile {
-    data: ReadOnlySource,
-    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> {
-        let end = data.len();
-        let footer_len_data = data.slice_from(end - 4);
-        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 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;
-        for _ in 0..num_fields {
-            offset += VInt::deserialize(&mut footer_buffer)?.0 as usize;
-            let file_addr = FileAddr::deserialize(&mut footer_buffer)?;
-            offsets.push(offset);
-            file_addrs.push(file_addr);
-        }
-        offsets.push(footer_start);
-        for i in 0..num_fields {
-            let file_addr = file_addrs[i];
-            let start_offset = offsets[i];
-            let end_offset = offsets[i + 1];
-            field_index.insert(file_addr, (start_offset, end_offset));
-        }
-
-        Ok(CompositeFile {
-            data: data.slice_to(footer_start),
-            offsets_index: field_index,
-        })
-    }
-
-    /// Returns a composite file that stores
-    /// no fields.
-    pub fn empty() -> CompositeFile {
-        CompositeFile {
-            offsets_index: HashMap::new(),
-            data: ReadOnlySource::empty(),
-        }
-    }
-
-    /// Returns the `ReadOnlySource` associated
-    /// to a given `Field` and stored in a `CompositeFile`.
-    pub fn open_read(&self, field: Field) -> Option<ReadOnlySource> {
-        self.open_read_with_idx(field, 0)
-    }
-
-    /// Returns the `ReadOnlySource` associated
-    /// to a given `Field` and stored in a `CompositeFile`.
-    pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<ReadOnlySource> {
-        self.offsets_index
-            .get(&FileAddr { field, idx })
-            .map(|&(from, to)| self.data.slice(from, to))
-    }
-
-    pub fn space_usage(&self) -> PerFieldSpaceUsage {
-        let mut fields = HashMap::new();
-        for (&field_addr, &(start, end)) in self.offsets_index.iter() {
-            fields
-                .entry(field_addr.field)
-                .or_insert_with(|| FieldUsage::empty(field_addr.field))
-                .add_field_idx(field_addr.idx, end - start);
-        }
-        PerFieldSpaceUsage::new(fields)
-    }
-}
-
-#[cfg(test)]
-mod test {
-
-    use super::{CompositeFile, CompositeWrite};
-    use crate::common::BinarySerializable;
-    use crate::common::VInt;
-    use crate::directory::{Directory, RAMDirectory};
-    use crate::schema::Field;
-    use std::io::Write;
-    use std::path::Path;
-
-    #[test]
-    fn test_composite_file() {
-        let path = Path::new("test_path");
-        let mut 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(0u32));
-                VInt(32431123u64).serialize(&mut write_0).unwrap();
-                write_0.flush().unwrap();
-            }
-
-            {
-                let mut write_4 = composite_write.for_field(Field(4u32));
-                VInt(2).serialize(&mut write_4).unwrap();
-                write_4.flush().unwrap();
-            }
-            composite_write.close().unwrap();
-        }
-        {
-            let r = directory.open_read(path).unwrap();
-            let composite_file = CompositeFile::open(&r).unwrap();
-            {
-                let file0 = composite_file.open_read(Field(0u32)).unwrap();
-                let mut file0_buf = file0.as_slice();
-                let payload_0 = VInt::deserialize(&mut file0_buf).unwrap().0;
-                assert_eq!(file0_buf.len(), 0);
-                assert_eq!(payload_0, 32431123u64);
-            }
-            {
-                let file4 = composite_file.open_read(Field(4u32)).unwrap();
-                let mut file4_buf = file4.as_slice();
-                let payload_4 = VInt::deserialize(&mut file4_buf).unwrap().0;
-                assert_eq!(file4_buf.len(), 0);
-                assert_eq!(payload_4, 2u64);
-            }
-        }
-    }
-
-}

tantivy-schema/Cargo.toml

@@ -1,33 +0,0 @@
-[package]
-name = "tantivy-schema"
-version = "0.1.0"
-authors = ["Paul Masurel <paul.masurel@gmail.com>"]
-edition = "2018"
-workspace = ".."
-
-
-[dependencies]
-base64 = "0.10.0"
-byteorder = "1.0"
-once_cell = "0.2"
-regex = "1.0"
-serde = "1.0"
-serde_derive = "1.0"
-serde_json = "1.0"
-num_cpus = "1.2"
-itertools = "0.8"
-notify = {version="4", optional=true}
-crossbeam = "0.7"
-owning_ref = "0.4"
-stable_deref_trait = "1.0.0"
-downcast-rs = { version="1.0" }
-census = "0.2"
-failure = "0.1"
-fail = "0.3"
-scoped-pool = "1.0"
-tantivy-common = {path="../tantivy-common"}
-chrono = "*"
-
-
-[dev-dependencies]
-matches = "0.1.8"

tantivy-tokenizer/Cargo.toml

@@ -1,13 +0,0 @@
-[package]
-name = "tantivy-tokenizer"
-version = "0.1.0"
-authors = ["Paul Masurel <paul.masurel@gmail.com>"]
-edition = "2018"
-workspace = ".."
-
-[dependencies]
-fnv = "*"
-rust-stemmers = "*"
-serde = "*"
-serde_derive = "*"
-tantivy-schema = {path="../tantivy-schema"}

tests/failpoints/mod.rs

@@ -8,7 +8,7 @@ use tantivy::{Index, Term};
 
 #[test]
 fn test_failpoints_managed_directory_gc_if_delete_fails() {
-    let _scenario = fail::FailScenario::setup();
+    let scenario = fail::FailScenario::setup();
 
     let test_path: &'static Path = Path::new("some_path_for_test");