Fixing bench compilation

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

.travis.yml

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

CHANGELOG.md

@@ -5,7 +5,22 @@ Tantivy 0.11.0
 - 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. #639 (@brainlock)
+- Add footer with some metadata to index files. #605 (@fdb-hiroshima)
+ 
+## 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` has been replaced by a `BoxedTokenizer` struct.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
+an error and handling the `Result` is required.
+
+
+Tantivy 0.10.2
+=====================
+
+- Closes #656. Solving memory leak.
 
 Tantivy 0.10.1
 =====================

Cargo.toml

@@ -15,8 +15,9 @@ edition = "2018"
 [dependencies]
 base64 = "0.10.0"
 byteorder = "1.0"
-once_cell = "0.2"
+crc32fast = "1.2.0"
-regex = "1.0"
+once_cell = "1.0"
+regex ={version = "1.3.0", default-features = false, features = ["std"]}
 tantivy-fst = "0.1"
 memmap = {version = "0.7", optional=true}
 lz4 = {version="1.20", optional=true}
@@ -24,7 +25,6 @@ snap = {version="0.2"}
 atomicwrites = {version="0.2.2", optional=true}
 tempfile = "3.0"
 log = "0.4"
-combine = ">=3.6.0,<4.0.0"
 serde = "1.0"
 serde_derive = "1.0"
 serde_json = "1.0"
@@ -42,6 +42,7 @@ owning_ref = "0.4"
 stable_deref_trait = "1.0.0"
 rust-stemmers = "1.1"
 downcast-rs = { version="1.0" }
+tantivy-query-grammar = { path="./query-grammar" }
 bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
 census = "0.2"
 fnv = "1.0.6"
@@ -62,7 +63,6 @@ rand = "0.7"
 maplit = "1"
 matches = "0.1.8"
 time = "0.1.42"
-criterion = "0.2"
 
 [profile.release]
 opt-level = 3
@@ -75,17 +75,20 @@ overflow-checks = true
 
 [features]
 default = ["mmap"]
-forbench = []
 mmap = ["atomicwrites", "fs2", "memmap", "notify"]
 lz4-compression = ["lz4"]
 failpoints = ["fail/failpoints"]
 unstable = [] # useful for benches.
 wasm-bindgen = ["uuid/wasm-bindgen"]
 
+[workspace]
+members = ["query-grammar"]
+
 [badges]
 travis-ci = { repository = "tantivy-search/tantivy" }
 
 [dev-dependencies.fail]
+version = "0.3"
 features = ["failpoints"]
 
 # Following the "fail" crate best practises, we isolate
@@ -99,15 +102,3 @@ features = ["failpoints"]
 name = "failpoints"
 path = "tests/failpoints/mod.rs"
 required-features = ["fail/failpoints"]
-
-[profile.bench]
-lto = true
-
-[[bench]]
-name = "vint"
-harness = false
-
-
-[[bench]]
-name = "fastfield"
-harness = false

Makefile

@@ -0,0 +1,3 @@
+test:
+	echo "Run test only... No examples."
+	cargo test --tests --lib

benches/bitset.rs

@@ -1,73 +0,0 @@
-use criterion::{criterion_group, criterion_main, Criterion};
-use rand::distributions::{Bernoulli, Uniform};
-use rand::rngs::StdRng;
-use rand::{Rng, SeedableRng};
-use tantivy::forbench::bitset::{BitSet, TinySet};
-use tantivy::query::BitSetDocSet;
-use tantivy::DocSet;
-
-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())
-        .take(n as usize)
-        .enumerate()
-        .filter_map(|(val, keep)| if keep { Some(val as u32) } else { None })
-        .collect()
-}
-
-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>>()
-}
-
-fn bench_tinyset_pop(criterion: &mut Criterion) {
-    criterion.bench_function("pop_lowest", |b| {
-        b.iter(|| {
-            let mut tinyset = TinySet::singleton(criterion::black_box(31u32));
-            tinyset.pop_lowest();
-            tinyset.pop_lowest();
-            tinyset.pop_lowest();
-            tinyset.pop_lowest();
-            tinyset.pop_lowest();
-            tinyset.pop_lowest();
-        })
-    });
-}
-
-fn bench_bitset_insert(criterion: &mut Criterion) {
-    criterion.bench_function_over_inputs(
-        "bitset_insert",
-        |bench, (max_value, n_elems)| {
-            let els = generate_nonunique_unsorted(*max_value, *n_elems);
-            bench.iter(move || {
-                let mut bitset = BitSet::with_max_value(1_000_000);
-                for el in els.iter().cloned() {
-                    bitset.insert(el);
-                }
-            });
-        },
-        vec![(1_000_000u32, 10_000)],
-    );
-}
-
-fn bench_bitsetdocset_iterate(b: &mut test::Bencher) {
-    let mut bitset = BitSet::with_max_value(1_000_000);
-    for el in sample_with_seed(1_000_000u32, 0.01, 0u8) {
-        bitset.insert(el);
-    }
-    b.iter(|| {
-        let mut docset = BitSetDocSet::from(bitset.clone());
-        while docset.advance() {}
-    });
-}
-
-criterion_group!(
-    benches,
-    bench_tinyset_pop,
-    bench_bitset_insert,
-    bench_bitsetdocset_iterate
-);
-criterion_main!(benches);

benches/fastfield.rs

@@ -1,107 +0,0 @@
-use criterion::criterion_group;
-use criterion::criterion_main;
-use criterion::Criterion;
-use criterion::ParameterizedBenchmark;
-use rand::rngs::StdRng;
-use rand::seq::SliceRandom;
-use rand::SeedableRng;
-use tantivy::schema::{Schema, FAST};
-use tantivy::{doc, DocId, Index};
-
-const NUM_LOOKUPS: usize = 1_000;
-
-fn generate_permutation(stride: usize, bit_width: u8) -> Vec<u64> {
-    let mut permutation: Vec<u64> = (0u64..(NUM_LOOKUPS * stride) as u64).collect();
-    permutation.shuffle(&mut StdRng::from_seed([1u8; 32]));
-    permutation.push(1u64 << (bit_width as u64)); //< just to force the bit_width
-    permutation
-}
-
-fn bench_linear_lookup(c: &mut Criterion) {
-    c.bench(
-        "lookup_stride",
-        ParameterizedBenchmark::new(
-            "baseline_vec",
-            |bench, (stride, num_bits)| {
-                let arr = generate_permutation(*stride, *num_bits);
-                bench.iter(move || {
-                    let mut a = 0u64;
-                    for i in (0..NUM_LOOKUPS / stride).map(|v| v * 7) {
-                        a ^= arr[i as usize];
-                    }
-                    a
-                })
-            },
-            vec![(7, 1), (7, 5), (7, 20)],
-        )
-        .with_function("fastfield", |bench, (stride, num_bits)| {
-            let mut schema_builder = Schema::builder();
-            let val_field = schema_builder.add_u64_field("val", FAST);
-            let schema = schema_builder.build();
-
-            let index = Index::create_in_ram(schema);
-            let mut index_writer = index.writer_with_num_threads(1, 80_000_000).unwrap();
-            for el in generate_permutation(*stride, *num_bits) {
-                index_writer.add_document(doc!(val_field=>el));
-            }
-            index_writer.commit().unwrap();
-            let reader = index.reader().unwrap();
-            let searcher = reader.searcher();
-            let segment_reader = searcher.segment_reader(0u32);
-            let fast_field_reader = segment_reader.fast_fields().u64(val_field).unwrap();
-            bench.iter(move || {
-                let mut a = 0u64;
-                for i in (0..NUM_LOOKUPS / stride).map(|v| v * 7) {
-                    a ^= fast_field_reader.get(i as DocId);
-                }
-                a
-            })
-        }),
-    );
-}
-
-fn bench_jumpy_lookup(c: &mut Criterion) {
-    c.bench(
-        "lookup_jumpy",
-        ParameterizedBenchmark::new(
-            "baseline_vec",
-            |bench, (stride, num_bits)| {
-                let arr = generate_permutation(*stride, *num_bits);
-                bench.iter(move || {
-                    let mut a = 0u64;
-                    for _ in 0..NUM_LOOKUPS {
-                        a = arr[a as usize];
-                    }
-                    a
-                })
-            },
-            vec![(7, 1), (7, 5), (7, 20)],
-        )
-        .with_function("fastfield", |bench, (stride, num_bits)| {
-            let mut schema_builder = Schema::builder();
-            let val_field = schema_builder.add_u64_field("val", FAST);
-            let schema = schema_builder.build();
-
-            let index = Index::create_in_ram(schema);
-            let mut index_writer = index.writer_with_num_threads(1, 80_000_000).unwrap();
-            for el in generate_permutation(*stride, *num_bits) {
-                index_writer.add_document(doc!(val_field=>el));
-            }
-            index_writer.commit().unwrap();
-            let reader = index.reader().unwrap();
-            let searcher = reader.searcher();
-            let segment_reader = searcher.segment_reader(0u32);
-            let fast_field_reader = segment_reader.fast_fields().u64(val_field).unwrap();
-            bench.iter(move || {
-                let mut a = 0u64;
-                for _ in 0..NUM_LOOKUPS {
-                    a = fast_field_reader.get(a as DocId);
-                }
-                a
-            })
-        }),
-    );
-}
-
-criterion_group!(benches, bench_linear_lookup, bench_jumpy_lookup);
-criterion_main!(benches);

benches/union.rs

@@ -1,50 +0,0 @@
-use criterion::{criterion_group, criterion_main, Criterion};
-use rand::rngs::StdRng;
-use rand::{Rng, SeedableRng};
-use tantivy::query::QueryParser;
-use tantivy::schema::{Schema, STRING};
-use tantivy::{Document, Index};
-
-fn bench_union(criterion: &mut Criterion) {
-    criterion.bench_function_over_inputs(
-        "union_docset_fulladvance",
-        |bench, (ratio_left, ratio_right)| {
-            let mut schema_builder = Schema::builder();
-            let field = schema_builder.add_text_field("val", STRING);
-            let schema = schema_builder.build();
-            let index = Index::create_in_ram(schema);
-            let mut index_writer = index.writer_with_num_threads(1, 80_000_000).unwrap();
-            let mut stdrng = StdRng::from_seed([0u8; 32]);
-            for _ in 0u32..100_000u32 {
-                let mut doc = Document::default();
-                if stdrng.gen_bool(*ratio_left) {
-                    doc.add_text(field, "left");
-                }
-                if stdrng.gen_bool(*ratio_right) {
-                    doc.add_text(field, "right");
-                }
-                index_writer.add_document(doc);
-            }
-            index_writer.commit().unwrap();
-            let reader = index.reader().unwrap();
-            let searcher = reader.searcher();
-
-            let query = QueryParser::for_index(&index, vec![field])
-                .parse_query("left right")
-                .unwrap();
-
-            bench.iter(move || {
-                let weight = query.weight(&searcher, false).unwrap();
-                let mut scorer = weight.scorer(searcher.segment_reader(0u32)).unwrap();
-                let mut sum_docs = 0u64;
-                scorer.for_each(&mut |doc_id, _score| {
-                    sum_docs += doc_id as u64;
-                });
-            });
-        },
-        vec![(0.2, 0.1), (0.2, 0.02)],
-    );
-}
-
-criterion_group!(benches, bench_union);
-criterion_main!(benches);

benches/vint.rs

@@ -1,72 +0,0 @@
-use criterion::{criterion_group, criterion_main, Criterion, ParameterizedBenchmark};
-use rand::rngs::StdRng;
-use rand::Rng;
-use rand::SeedableRng;
-use tantivy::forbench::compression::{compressed_block_size, BlockDecoder};
-use tantivy::forbench::compression::{BlockEncoder, VIntEncoder};
-use tantivy::forbench::compression::{VIntDecoder, COMPRESSION_BLOCK_SIZE};
-
-fn generate_array_with_seed(n: usize, ratio: f64, seed_val: u8) -> Vec<u32> {
-    let seed: [u8; 32] = [seed_val; 32];
-    let mut rng = StdRng::from_seed(seed);
-    (0u32..).filter(|_| rng.gen_bool(ratio)).take(n).collect()
-}
-
-pub fn generate_array(n: usize, ratio: f64) -> Vec<u32> {
-    generate_array_with_seed(n, ratio, 4)
-}
-
-fn bench_compress(criterion: &mut Criterion) {
-    criterion.bench(
-        "compress_sorted",
-        ParameterizedBenchmark::new(
-            "bitpack",
-            |bench, ratio| {
-                let mut encoder = BlockEncoder::new();
-                let data = generate_array(COMPRESSION_BLOCK_SIZE, *ratio);
-                bench.iter(|| {
-                    encoder.compress_block_sorted(&data, 0u32);
-                });
-            },
-            vec![0.1],
-        )
-        .with_function("vint", |bench, ratio| {
-            let mut encoder = BlockEncoder::new();
-            let data = generate_array(COMPRESSION_BLOCK_SIZE, *ratio);
-            bench.iter(|| {
-                encoder.compress_vint_sorted(&data, 0u32);
-            });
-        }),
-    );
-}
-
-fn bench_uncompress(criterion: &mut Criterion) {
-    criterion.bench(
-        "uncompress_sorted",
-        ParameterizedBenchmark::new(
-            "bitpack",
-            |bench, ratio| {
-                let mut encoder = BlockEncoder::new();
-                let data = generate_array(COMPRESSION_BLOCK_SIZE, *ratio);
-                let (num_bits, compressed) = encoder.compress_block_sorted(&data, 0u32);
-                let mut decoder = BlockDecoder::new();
-                bench.iter(|| {
-                    decoder.uncompress_block_sorted(compressed, 0u32, num_bits);
-                });
-            },
-            vec![0.1],
-        )
-        .with_function("vint", |bench, ratio| {
-            let mut encoder = BlockEncoder::new();
-            let data = generate_array(COMPRESSION_BLOCK_SIZE, *ratio);
-            let compressed = encoder.compress_vint_sorted(&data, 0u32);
-            let mut decoder = BlockDecoder::new();
-            bench.iter(move || {
-                decoder.uncompress_vint_sorted(compressed, 0u32, COMPRESSION_BLOCK_SIZE);
-            });
-        }),
-    );
-}
-
-criterion_group!(benches, bench_compress, bench_uncompress);
-criterion_main!(benches);

ci/script.sh

@@ -7,7 +7,7 @@ set -ex
 main() {
     if [ ! -z $CODECOV ]; then
         echo "Codecov"
-        cargo build --verbose && cargo coverage --verbose && bash <(curl -s https://codecov.io/bash) -s target/kcov
+        cargo build --verbose && cargo coverage --verbose --all && bash <(curl -s https://codecov.io/bash) -s target/kcov
     else
         echo "Build"
         cross build --target $TARGET
@@ -15,7 +15,8 @@ main() {
             return
         fi
         echo "Test"
-        cross test --target $TARGET --no-default-features --features mmap -- --test-threads 1
+        cross test --target $TARGET --no-default-features --features mmap
+        cross test --target $TARGET --no-default-features --features mmap query-grammar
     fi
     for example in $(ls examples/*.rs)
     do

examples/basic_search.rs

@@ -5,20 +5,17 @@
 //
 // We will :
 // - define our schema
-// = create an index in a directory
+// - create an index in a directory
-// - index few documents in our index
+// - index a few documents into our index
-// - search for the best document matchings "sea whale"
+// - search for the best document matching a basic query
-// - retrieve the best document original content.
+// - retrieve the best document's original content.
 
 // ---
 // Importing tantivy...
-#[macro_use]
-extern crate tantivy;
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
-use tantivy::Index;
+use tantivy::{doc, Index, ReloadPolicy};
-use tantivy::ReloadPolicy;
 use tempfile::TempDir;
 
 fn main() -> tantivy::Result<()> {
@@ -33,7 +30,7 @@ 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.
@@ -48,7 +45,7 @@ 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 to reconstruct the
+    // This store is useful for reconstructing the
     // documents that were selected during the search phase.
     schema_builder.add_text_field("title", TEXT | STORED);
 
@@ -57,8 +54,7 @@ fn main() -> tantivy::Result<()> {
     // need to be able to be able to retrieve it
     // for our application.
     //
-    // We can make our index lighter and
+    // We can make our index lighter by omitting the `STORED` flag.
-    // by omitting `STORED` flag.
     schema_builder.add_text_field("body", TEXT);
 
     let schema = schema_builder.build();
@@ -71,7 +67,7 @@ fn main() -> tantivy::Result<()> {
     // with our schema in the directory.
     let index = Index::create_in_dir(&index_path, schema.clone())?;
 
-    // To insert document we need an index writer.
+    // To insert a document we will need an index writer.
     // There must be only one writer at a time.
     // This single `IndexWriter` is already
     // multithreaded.
@@ -149,8 +145,8 @@ 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.
     //
@@ -162,14 +158,14 @@ fn main() -> tantivy::Result<()> {
     // persistently indexed.
     //
     // In the scenario of a crash or a power failure,
-    // tantivy behaves as if has rolled back to its last
+    // tantivy behaves as if it has rolled back to its last
     // commit.
 
     // # Searching
     //
     // ### Searcher
     //
-    // A reader is required to get search the index.
+    // A reader is required first in order to search an index.
     // It acts as a `Searcher` pool that reloads itself,
     // depending on a `ReloadPolicy`.
     //
@@ -185,7 +181,7 @@ fn main() -> tantivy::Result<()> {
 
     // We now need to acquire a searcher.
     //
-    // A searcher points to snapshotted, immutable version of the index.
+    // A searcher points to a 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
@@ -205,7 +201,7 @@ 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")?;
@@ -221,7 +217,7 @@ 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.
+    // is the role of the `TopDocs` collector.
 
     // We can now perform our query.
     let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;

examples/custom_collector.rs

@@ -9,15 +9,12 @@
 
 // ---
 // 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::SegmentReader;
+use tantivy::{doc, Index, SegmentReader, TantivyError};
-use tantivy::{Index, TantivyError};
 
 #[derive(Default)]
 struct Stats {

examples/custom_tokenizer.rs

@@ -2,14 +2,11 @@
 //
 // 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::Index;
+use tantivy::{doc, Index};
 
 fn main() -> tantivy::Result<()> {
     // # Defining the schema

examples/deleting_updating_documents.rs

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

examples/faceted_search.rs

@@ -12,12 +12,10 @@
 
 // ---
 // Importing tantivy...
-#[macro_use]
-extern crate tantivy;
 use tantivy::collector::FacetCollector;
 use tantivy::query::AllQuery;
 use tantivy::schema::*;
-use tantivy::Index;
+use tantivy::{doc, Index};
 use tempfile::TempDir;
 
 fn main() -> tantivy::Result<()> {

examples/integer_range_search.rs

@@ -2,14 +2,10 @@
 //
 // 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::Index;
+use tantivy::{doc, Index, Result};
-use tantivy::Result;
 
 fn run() -> Result<()> {
     // For the sake of simplicity, this schema will only have 1 field

examples/iterating_docs_and_positions.rs

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

examples/multiple_producer.rs

@@ -25,14 +25,11 @@
 
 // ---
 // 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::Opstamp;
+use tantivy::{doc, Index, IndexWriter, Opstamp};
-use tantivy::{Index, IndexWriter};
 
 fn main() -> tantivy::Result<()> {
     // # Defining the schema
@@ -49,10 +46,9 @@ fn main() -> tantivy::Result<()> {
     thread::spawn(move || {
         // we index 100 times the document... for the sake of the example.
         for i in 0..100 {
-            let opstamp = {
+            let opstamp = index_writer_clone_1
-                // A read lock is sufficient here.
+                .read().unwrap() //< A read lock is sufficient here.
-                let index_writer_rlock = index_writer_clone_1.read().unwrap();
+                .add_document(
-                index_writer_rlock.add_document(
                     doc!(
                         title => "Of Mice and Men",
                         body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
@@ -63,8 +59,7 @@ fn main() -> tantivy::Result<()> {
                         fresh and green with every spring, carrying in their lower leaf junctures the \
                         debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
                         limbs and branches that arch over the pool"
-                    ))
+                    ));
-            };
             println!("add doc {} from thread 1 - opstamp {}", i, opstamp);
             thread::sleep(Duration::from_millis(20));
         }

examples/snippet.rs

@@ -7,13 +7,10 @@
 
 // ---
 // Importing tantivy...
-#[macro_use]
-extern crate tantivy;
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
-use tantivy::Index;
+use tantivy::{doc, Index, Snippet, SnippetGenerator};
-use tantivy::{Snippet, SnippetGenerator};
 use tempfile::TempDir;
 
 fn main() -> tantivy::Result<()> {

examples/stop_words.rs

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

query-grammar/Cargo.toml

@@ -0,0 +1,16 @@
+[package]
+name = "tantivy-query-grammar"
+version = "0.11.0"
+authors = ["Paul Masurel <paul.masurel@gmail.com>"]
+license = "MIT"
+categories = ["database-implementations", "data-structures"]
+description = """Search engine library"""
+documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
+homepage = "https://github.com/tantivy-search/tantivy"
+repository = "https://github.com/tantivy-search/tantivy"
+readme = "README.md"
+keywords = ["search", "information", "retrieval"]
+edition = "2018"
+
+[dependencies]
+combine = ">=3.6.0,<4.0.0"

query-grammar/src/lib.rs

@@ -0,0 +1,17 @@
+#![recursion_limit = "100"]
+
+mod occur;
+mod query_grammar;
+mod user_input_ast;
+use combine::parser::Parser;
+
+pub use crate::occur::Occur;
+use crate::query_grammar::parse_to_ast;
+pub use crate::user_input_ast::{UserInputAST, UserInputBound, UserInputLeaf, UserInputLiteral};
+
+pub struct Error;
+
+pub fn parse_query(query: &str) -> Result<UserInputAST, Error> {
+    let (user_input_ast, _remaining) = parse_to_ast().parse(query).map_err(|_| Error)?;
+    Ok(user_input_ast)
+}

query-grammar/src/occur.rs

@@ -1,3 +1,6 @@
+use std::fmt;
+use std::fmt::Write;
+
 /// Defines whether a term in a query must be present,
 /// should be present or must not be present.
 #[derive(Debug, Clone, Hash, Copy, Eq, PartialEq)]
@@ -18,32 +21,38 @@ impl Occur {
     /// - `Should` => '?',
     /// - `Must` => '+'
     /// - `Not` => '-'
-    pub fn to_char(self) -> char {
+    fn to_char(self) -> char {
         match self {
             Occur::Should => '?',
             Occur::Must => '+',
             Occur::MustNot => '-',
         }
     }
-}
 
-/// Compose two occur values.
+    /// Compose two occur values.
-pub fn compose_occur(left: Occur, right: Occur) -> Occur {
+    pub fn compose(left: Occur, right: Occur) -> Occur {
-    match left {
+        match left {
-        Occur::Should => right,
+            Occur::Should => right,
-        Occur::Must => {
+            Occur::Must => {
-            if right == Occur::MustNot {
+                if right == Occur::MustNot {
-                Occur::MustNot
+                    Occur::MustNot
-            } else {
+                } else {
-                Occur::Must
+                    Occur::Must
+                }
             }
-        }
+            Occur::MustNot => {
-        Occur::MustNot => {
+                if right == Occur::MustNot {
-            if right == Occur::MustNot {
+                    Occur::Must
-                Occur::Must
+                } else {
-            } else {
+                    Occur::MustNot
-                Occur::MustNot
+                }
             }
         }
     }
 }
+
+impl fmt::Display for Occur {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        f.write_char(self.to_char())
+    }
+}

query-grammar/src/query_grammar.rs

@@ -1,6 +1,5 @@
 use super::user_input_ast::*;
-use crate::query::occur::Occur;
+use crate::Occur;
-use crate::query::query_parser::user_input_ast::UserInputBound;
 use combine::char::*;
 use combine::error::StreamError;
 use combine::stream::StreamErrorFor;
@@ -83,28 +82,67 @@ 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 = || {
             word().or(negative_number()).or(char('*').with(value("*".to_string())))
         };
+
+        // check for unbounded range in the form of <5, <=10, >5, >=5
+        let elastic_unbounded_range = (choice([attempt(string(">=")),
+                                               attempt(string("<=")),
+                                               attempt(string("<")),
+                                               attempt(string(">"))])
+                                       .skip(spaces()),
+                                       range_term_val()).
+            map(|(comparison_sign, bound): (&str, String)|
+                match comparison_sign {
+                    ">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
+                    "<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
+                    "<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
+                    ">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
+                    // default case
+                    _ => (UserInputBound::Unbounded, UserInputBound::Unbounded)
+                });
         let lower_bound = (one_of("{[".chars()), range_term_val())
             .map(|(boundary_char, lower_bound): (char, String)|
-                if boundary_char == '{' { UserInputBound::Exclusive(lower_bound) }
+                 if lower_bound == "*" {
-                else { UserInputBound::Inclusive(lower_bound) });
+                     UserInputBound::Unbounded
+                 } 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 boundary_char == '}' { UserInputBound::Exclusive(higher_bound) }
+                 if higher_bound == "*" {
-                else { UserInputBound::Inclusive(higher_bound) });
+                     UserInputBound::Unbounded
-        (
+                 } else if boundary_char == '}' {
-            optional(field()),
+                     UserInputBound::Exclusive(higher_bound)
-            lower_bound
+                 } else {
-            .skip((spaces(), string("TO"), spaces())),
+                     UserInputBound::Inclusive(higher_bound)
-            upper_bound,
+                 });
-        ).map(|(field, lower, upper)| UserInputLeaf::Range {
+         // return only lower and upper
-                field,
+        let lower_to_upper = (lower_bound.
-                lower,
+                                    skip((spaces(),
-                upper
+                                          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
         })
     }
 }
@@ -258,6 +296,49 @@ 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\"");
@@ -291,7 +372,7 @@ 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 +    ");

query-grammar/src/user_input_ast.rs

@@ -1,8 +1,9 @@
 use std::fmt;
 use std::fmt::{Debug, Formatter};
 
-use crate::query::Occur;
+use crate::Occur;
 
+#[derive(PartialEq)]
 pub enum UserInputLeaf {
     Literal(UserInputLiteral),
     All,
@@ -35,6 +36,7 @@ impl Debug for UserInputLeaf {
     }
 }
 
+#[derive(PartialEq)]
 pub struct UserInputLiteral {
     pub field_name: Option<String>,
     pub phrase: String,
@@ -49,9 +51,11 @@ impl fmt::Debug for UserInputLiteral {
     }
 }
 
+#[derive(PartialEq)]
 pub enum UserInputBound {
     Inclusive(String),
     Exclusive(String),
+    Unbounded,
 }
 
 impl UserInputBound {
@@ -59,6 +63,7 @@ impl UserInputBound {
         match *self {
             UserInputBound::Inclusive(ref word) => write!(formatter, "[\"{}\"", word),
             UserInputBound::Exclusive(ref word) => write!(formatter, "{{\"{}\"", word),
+            UserInputBound::Unbounded => write!(formatter, "{{\"*\""),
         }
     }
 
@@ -66,6 +71,7 @@ impl UserInputBound {
         match *self {
             UserInputBound::Inclusive(ref word) => write!(formatter, "\"{}\"]", word),
             UserInputBound::Exclusive(ref word) => write!(formatter, "\"{}\"}}", word),
+            UserInputBound::Unbounded => write!(formatter, "\"*\"}}"),
         }
     }
 
@@ -73,6 +79,7 @@ impl UserInputBound {
         match *self {
             UserInputBound::Inclusive(ref contents) => contents,
             UserInputBound::Exclusive(ref contents) => contents,
+            UserInputBound::Unbounded => &"*",
         }
     }
 }
@@ -144,7 +151,7 @@ impl fmt::Debug for UserInputAST {
                 Ok(())
             }
             UserInputAST::Unary(ref occur, ref subquery) => {
-                write!(formatter, "{}({:?})", occur.to_char(), subquery)
+                write!(formatter, "{}({:?})", occur, subquery)
             }
             UserInputAST::Leaf(ref subquery) => write!(formatter, "{:?}", subquery),
         }

run-bench.rs

@@ -1,2 +0,0 @@
-#!/usr/bin/env bash
-cargo bench --features forbench 

src/collector/count_collector.rs

@@ -10,12 +10,10 @@ 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<()> {
@@ -125,5 +123,4 @@ mod tests {
             assert_eq!(count_collector.harvest(), 2);
         }
     }
-
 }

src/collector/facet_collector.rs

@@ -81,12 +81,10 @@ 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<()> {
@@ -601,19 +599,18 @@ mod tests {
             );
         }
     }
-
 }
 
 #[cfg(all(test, feature = "unstable"))]
 mod bench {
 
-    use collector::FacetCollector;
+    use crate::collector::FacetCollector;
-    use query::AllQuery;
+    use crate::query::AllQuery;
-    use rand::{thread_rng, Rng};
+    use crate::schema::{Facet, Schema};
-    use schema::Facet;
+    use crate::Index;
-    use schema::Schema;
+    use rand::seq::SliceRandom;
+    use rand::thread_rng;
     use test::Bencher;
-    use Index;
 
     #[bench]
     fn bench_facet_collector(b: &mut Bencher) {
@@ -630,7 +627,7 @@ mod bench {
             }
         }
         // 40425 docs
-        thread_rng().shuffle(&mut docs[..]);
+        docs[..].shuffle(&mut thread_rng());
 
         let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
         for doc in docs {
@@ -639,7 +636,7 @@ mod bench {
         index_writer.commit().unwrap();
         let reader = index.reader().unwrap();
         b.iter(|| {
-            let searcher = index.searcher();
+            let searcher = reader.searcher();
             let facet_collector = FacetCollector::for_field(facet_field);
             searcher.search(&AllQuery, &facet_collector).unwrap();
         });

src/collector/mod.rs

@@ -35,7 +35,6 @@ 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

@@ -105,12 +105,10 @@ 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

@@ -23,13 +23,10 @@ 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<()> {
@@ -87,10 +84,8 @@ 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::{Index, Result, DocAddress};
+    /// # use tantivy::{doc, Index, Result, DocAddress};
     /// # use tantivy::query::{Query, QueryParser};
     /// use tantivy::Searcher;
     /// use tantivy::collector::TopDocs;
@@ -128,7 +123,7 @@ impl TopDocs {
     /// ///
     /// /// `field` is required to be a FAST field.
     /// fn docs_sorted_by_rating(searcher: &Searcher,
-    ///                          query: &Query,
+    ///                          query: &dyn Query,
     ///                          sort_by_field: Field)
     ///     -> Result<Vec<(u64, DocAddress)>> {
     ///
@@ -197,10 +192,8 @@ impl TopDocs {
     /// learning-to-rank model over various features
     ///
     /// ```rust
-    /// #[macro_use]
-    /// extern crate tantivy;
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{Index, DocAddress, DocId, Score};
+    /// # use tantivy::{doc, Index, DocAddress, DocId, Score};
     /// # use tantivy::query::QueryParser;
     /// use tantivy::SegmentReader;
     /// use tantivy::collector::TopDocs;
@@ -302,10 +295,8 @@ impl TopDocs {
     /// # Example
     ///
     /// ```rust
-    /// # #[macro_use]
-    /// # extern crate tantivy;
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{Index, DocAddress, DocId};
+    /// # use tantivy::{doc, Index, DocAddress, DocId};
     /// # use tantivy::query::QueryParser;
     /// use tantivy::SegmentReader;
     /// use tantivy::collector::TopDocs;
@@ -601,5 +592,4 @@ mod tests {
         let query = query_parser.parse_query(query).unwrap();
         (index, query)
     }
-
 }

src/common/bitpacker.rs

@@ -86,7 +86,6 @@ where
         }
     }
 
-    #[inline(always)]
     pub fn get(&self, idx: u64) -> u64 {
         if self.num_bits == 0 {
             return 0u64;

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 {
@@ -353,3 +353,43 @@ mod tests {
         }
     }
 }
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+
+    use super::BitSet;
+    use super::TinySet;
+    use test;
+
+    #[bench]
+    fn bench_tinyset_pop(b: &mut test::Bencher) {
+        b.iter(|| {
+            let mut tinyset = TinySet::singleton(test::black_box(31u32));
+            tinyset.pop_lowest();
+            tinyset.pop_lowest();
+            tinyset.pop_lowest();
+            tinyset.pop_lowest();
+            tinyset.pop_lowest();
+            tinyset.pop_lowest();
+        });
+    }
+
+    #[bench]
+    fn bench_tinyset_sum(b: &mut test::Bencher) {
+        let tiny_set = TinySet::empty().insert(10u32).insert(14u32).insert(21u32);
+        b.iter(|| {
+            assert_eq!(test::black_box(tiny_set).into_iter().sum::<u32>(), 45u32);
+        });
+    }
+
+    #[bench]
+    fn bench_tinyarr_sum(b: &mut test::Bencher) {
+        let v = [10u32, 14u32, 21u32];
+        b.iter(|| test::black_box(v).iter().cloned().sum::<u32>());
+    }
+
+    #[bench]
+    fn bench_bitset_initialize(b: &mut test::Bencher) {
+        b.iter(|| BitSet::with_max_value(1_000_000));
+    }
+}

src/common/composite_file.rs

@@ -2,7 +2,7 @@ use crate::common::BinarySerializable;
 use crate::common::CountingWriter;
 use crate::common::VInt;
 use crate::directory::ReadOnlySource;
-use crate::directory::WritePtr;
+use crate::directory::{TerminatingWrite, WritePtr};
 use crate::schema::Field;
 use crate::space_usage::FieldUsage;
 use crate::space_usage::PerFieldSpaceUsage;
@@ -42,7 +42,7 @@ pub struct CompositeWrite<W = WritePtr> {
     offsets: HashMap<FileAddr, u64>,
 }
 
-impl<W: Write> CompositeWrite<W> {
+impl<W: TerminatingWrite + Write> CompositeWrite<W> {
     /// Crate a new API writer that writes a composite file
     /// in a given write.
     pub fn wrap(w: W) -> CompositeWrite<W> {
@@ -91,8 +91,7 @@ impl<W: Write> CompositeWrite<W> {
 
         let footer_len = (self.write.written_bytes() - footer_offset) as u32;
         footer_len.serialize(&mut self.write)?;
-        self.write.flush()?;
+        self.write.terminate()
-        Ok(())
     }
 }
 
@@ -231,5 +230,4 @@ mod test {
             }
         }
     }
-
 }

src/common/counting_writer.rs

@@ -1,3 +1,5 @@
+use crate::directory::AntiCallToken;
+use crate::directory::TerminatingWrite;
 use std::io;
 use std::io::Write;
 
@@ -42,6 +44,13 @@ impl<W: Write> Write for CountingWriter<W> {
     }
 }
 
+impl<W: TerminatingWrite> TerminatingWrite for CountingWriter<W> {
+    fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
+        self.flush()?;
+        self.underlying.terminate_ref(token)
+    }
+}
+
 #[cfg(test)]
 mod test {
 

src/common/mod.rs

@@ -6,7 +6,7 @@ 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};

src/common/serialize.rs

@@ -199,10 +199,7 @@ pub mod test {
     fn test_serialize_string() {
         assert_eq!(serialize_test(String::from("")), 1);
         assert_eq!(serialize_test(String::from("ぽよぽよ")), 1 + 3 * 4);
-        assert_eq!(
+        assert_eq!(serialize_test(String::from("富士さん見える。")), 1 + 3 * 8);
-            serialize_test(String::from("富士さん見える。")),
-            1 + 3 * 8
-        );
     }
 
     #[test]

src/core/index.rs

@@ -26,9 +26,10 @@ use crate::IndexWriter;
 use crate::Result;
 use num_cpus;
 use std::borrow::BorrowMut;
+use std::collections::HashSet;
 use std::fmt;
 #[cfg(feature = "mmap")]
-use std::path::Path;
+use std::path::{Path, PathBuf};
 use std::sync::Arc;
 
 fn load_metas(directory: &dyn Directory, inventory: &SegmentMetaInventory) -> Result<IndexMeta> {
@@ -173,11 +174,11 @@ impl Index {
     }
 
     /// Helper to access the tokenizer associated to a specific field.
-    pub fn tokenizer_for_field(&self, field: Field) -> Result<Box<dyn BoxedTokenizer>> {
+    pub fn tokenizer_for_field(&self, field: Field) -> Result<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<Box<dyn BoxedTokenizer>> = match field_type {
+        let tokenizer_name_opt: Option<BoxedTokenizer> = match field_type {
             FieldType::Str(text_options) => text_options
                 .get_indexing_options()
                 .map(|text_indexing_options| text_indexing_options.tokenizer().to_string())
@@ -216,8 +217,22 @@ impl Index {
         Index::open(mmap_directory)
     }
 
-    pub(crate) fn inventory(&self) -> &SegmentMetaInventory {
+    /// Returns the list of the segment metas tracked by the index.
-        &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
@@ -354,6 +369,11 @@ impl Index {
             .map(SegmentMeta::id)
             .collect())
     }
+
+    /// Returns the set of corrupted files
+    pub fn validate_checksum(&self) -> Result<HashSet<PathBuf>> {
+        self.directory.list_damaged().map_err(Into::into)
+    }
 }
 
 impl fmt::Debug for Index {
@@ -581,5 +601,4 @@ mod tests {
         assert_eq!(searcher.num_docs(), 8_000);
         assert!(mem_right_after_merge_finished < mem_right_after_commit);
     }
-
 }

src/core/index_meta.rs

@@ -30,7 +30,6 @@ 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

@@ -4,6 +4,8 @@ use uuid::Uuid;
 
 #[cfg(test)]
 use once_cell::sync::Lazy;
+use std::error::Error;
+use std::str::FromStr;
 #[cfg(test)]
 use std::sync::atomic;
 
@@ -52,15 +54,51 @@ impl SegmentId {
     /// and the rest is random.
     ///
     /// Picking the first 8 chars is ok to identify
-    /// segments in a display message.
+    /// segments in a display message (e.g. a5c4dfcb).
     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 {
@@ -80,3 +118,18 @@ 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/directory/directory.rs

@@ -118,6 +118,8 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
     ///
     /// Specifically, subsequent writes or flushes should
     /// have no effect on the returned `ReadOnlySource` object.
+    ///
+    /// You should only use this to read files create with [`open_write`]
     fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>;
 
     /// Removes a file
@@ -157,6 +159,8 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
     /// atomic_write.
     ///
     /// This should only be used for small files.
+    ///
+    /// You should only use this to read files create with [`atomic_write`]
     fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError>;
 
     /// Atomically replace the content of a file with data.

src/directory/footer.rs

@@ -0,0 +1,213 @@
+use crate::directory::read_only_source::ReadOnlySource;
+use crate::directory::{AntiCallToken, TerminatingWrite};
+use byteorder::{ByteOrder, LittleEndian};
+use crc32fast::Hasher;
+use std::io;
+use std::io::Write;
+
+const COMMON_FOOTER_SIZE: usize = 4 * 5;
+
+#[derive(Debug, Clone, PartialEq)]
+pub struct Footer {
+    pub tantivy_version: (u32, u32, u32),
+    pub meta: String,
+    pub versioned_footer: VersionedFooter,
+}
+
+impl Footer {
+    pub fn new(versioned_footer: VersionedFooter) -> Self {
+        let tantivy_version = (
+            env!("CARGO_PKG_VERSION_MAJOR").parse().unwrap(),
+            env!("CARGO_PKG_VERSION_MINOR").parse().unwrap(),
+            env!("CARGO_PKG_VERSION_PATCH").parse().unwrap(),
+        );
+        Footer {
+            tantivy_version,
+            meta: format!(
+                "tantivy {}.{}.{}, index v{}",
+                tantivy_version.0,
+                tantivy_version.1,
+                tantivy_version.2,
+                versioned_footer.version()
+            ),
+            versioned_footer,
+        }
+    }
+
+    pub fn to_bytes(&self) -> Vec<u8> {
+        let mut res = self.versioned_footer.to_bytes();
+        res.extend_from_slice(self.meta.as_bytes());
+        let len = res.len();
+        res.resize(len + COMMON_FOOTER_SIZE, 0);
+        let mut common_footer = &mut res[len..];
+        LittleEndian::write_u32(&mut common_footer, self.meta.len() as u32);
+        LittleEndian::write_u32(&mut common_footer[4..], self.tantivy_version.0);
+        LittleEndian::write_u32(&mut common_footer[8..], self.tantivy_version.1);
+        LittleEndian::write_u32(&mut common_footer[12..], self.tantivy_version.2);
+        LittleEndian::write_u32(&mut common_footer[16..], (len + COMMON_FOOTER_SIZE) as u32);
+        res
+    }
+
+    pub fn from_bytes(data: &[u8]) -> Result<Self, io::Error> {
+        let len = data.len();
+        if len < COMMON_FOOTER_SIZE + 4 {
+            // 4 bytes for index version, stored in versioned footer
+            return Err(io::Error::new(
+                    io::ErrorKind::UnexpectedEof,
+                    format!("File corrupted. The footer len must be over 24, while the entire file len is {}", len)
+                    )
+            );
+        }
+
+        let size = LittleEndian::read_u32(&data[len - 4..]) as usize;
+        if len < size as usize {
+            return Err(io::Error::new(
+                io::ErrorKind::UnexpectedEof,
+                format!(
+                    "File corrupted. The footer len is {}, while the entire file len is {}",
+                    size, len
+                ),
+            ));
+        }
+        let footer = &data[len - size as usize..];
+        let meta_len = LittleEndian::read_u32(&footer[size - 20..]) as usize;
+        let tantivy_major = LittleEndian::read_u32(&footer[size - 16..]);
+        let tantivy_minor = LittleEndian::read_u32(&footer[size - 12..]);
+        let tantivy_patch = LittleEndian::read_u32(&footer[size - 8..]);
+        Ok(Footer {
+            tantivy_version: (tantivy_major, tantivy_minor, tantivy_patch),
+            meta: String::from_utf8_lossy(&footer[size - meta_len - 20..size - 20]).into_owned(),
+            versioned_footer: VersionedFooter::from_bytes(&footer[..size - meta_len - 20])?,
+        })
+    }
+
+    pub fn extract_footer(source: ReadOnlySource) -> Result<(Footer, ReadOnlySource), io::Error> {
+        let footer = Footer::from_bytes(source.as_slice())?;
+        let reader = source.slice_to(source.as_slice().len() - footer.size());
+        Ok((footer, reader))
+    }
+
+    pub fn size(&self) -> usize {
+        self.versioned_footer.size() as usize + self.meta.len() + 20
+    }
+}
+
+#[derive(Debug, Clone, PartialEq)]
+pub enum VersionedFooter {
+    UnknownVersion { version: u32, size: u32 },
+    V0(u32), // crc
+}
+
+impl VersionedFooter {
+    pub fn to_bytes(&self) -> Vec<u8> {
+        match self {
+            VersionedFooter::V0(crc) => {
+                let mut res = vec![0; 8];
+                LittleEndian::write_u32(&mut res, 0);
+                LittleEndian::write_u32(&mut res[4..], *crc);
+                res
+            }
+            VersionedFooter::UnknownVersion { .. } => {
+                panic!("Unsupported index should never get serialized");
+            }
+        }
+    }
+
+    pub fn from_bytes(footer: &[u8]) -> Result<Self, io::Error> {
+        assert!(footer.len() >= 4);
+        let version = LittleEndian::read_u32(footer);
+        match version {
+            0 => {
+                if footer.len() == 8 {
+                    Ok(VersionedFooter::V0(LittleEndian::read_u32(&footer[4..])))
+                } else {
+                    Err(io::Error::new(
+                        io::ErrorKind::UnexpectedEof,
+                        format!(
+                            "File corrupted. The versioned footer len is {}, while it should be 8",
+                            footer.len()
+                        ),
+                    ))
+                }
+            }
+            version => Ok(VersionedFooter::UnknownVersion {
+                version,
+                size: footer.len() as u32,
+            }),
+        }
+    }
+
+    pub fn size(&self) -> u32 {
+        match self {
+            VersionedFooter::V0(_) => 8,
+            VersionedFooter::UnknownVersion { size, .. } => *size,
+        }
+    }
+
+    pub fn version(&self) -> u32 {
+        match self {
+            VersionedFooter::V0(_) => 0,
+            VersionedFooter::UnknownVersion { version, .. } => *version,
+        }
+    }
+
+    pub fn crc(&self) -> Option<u32> {
+        match self {
+            VersionedFooter::V0(crc) => Some(*crc),
+            VersionedFooter::UnknownVersion { .. } => None,
+        }
+    }
+}
+
+pub(crate) struct FooterProxy<W: TerminatingWrite> {
+    /// always Some except after terminate call
+    hasher: Option<Hasher>,
+    /// always Some except after terminate call
+    writer: Option<W>,
+}
+
+impl<W: TerminatingWrite> FooterProxy<W> {
+    pub fn new(writer: W) -> Self {
+        FooterProxy {
+            hasher: Some(Hasher::new()),
+            writer: Some(writer),
+        }
+    }
+}
+
+impl<W: TerminatingWrite> Write for FooterProxy<W> {
+    fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
+        let count = self.writer.as_mut().unwrap().write(buf)?;
+        self.hasher.as_mut().unwrap().update(&buf[..count]);
+        Ok(count)
+    }
+
+    fn flush(&mut self) -> io::Result<()> {
+        self.writer.as_mut().unwrap().flush()
+    }
+}
+
+impl<W: TerminatingWrite> TerminatingWrite for FooterProxy<W> {
+    fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
+        let crc = self.hasher.take().unwrap().finalize();
+
+        let footer = Footer::new(VersionedFooter::V0(crc)).to_bytes();
+        let mut writer = self.writer.take().unwrap();
+        writer.write_all(&footer)?;
+        writer.terminate()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::directory::footer::{Footer, VersionedFooter};
+
+    #[test]
+    fn test_serialize_deserialize_footer() {
+        let crc = 123456;
+        let footer = Footer::new(VersionedFooter::V0(crc));
+        let footer_bytes = footer.to_bytes();
+
+        assert_eq!(Footer::from_bytes(&footer_bytes).unwrap(), footer);
+    }
+}

src/directory/managed_directory.rs

@@ -1,5 +1,6 @@
 use crate::core::MANAGED_FILEPATH;
 use crate::directory::error::{DeleteError, IOError, LockError, OpenReadError, OpenWriteError};
+use crate::directory::footer::{Footer, FooterProxy};
 use crate::directory::DirectoryLock;
 use crate::directory::Lock;
 use crate::directory::META_LOCK;
@@ -8,6 +9,7 @@ use crate::directory::{WatchCallback, WatchHandle};
 use crate::error::DataCorruption;
 use crate::Directory;
 use crate::Result;
+use crc32fast::Hasher;
 use serde_json;
 use std::collections::HashSet;
 use std::io;
@@ -207,17 +209,59 @@ impl ManagedDirectory {
         }
         Ok(())
     }
+
+    /// Verify checksum of a managed file
+    pub fn validate_checksum(&self, path: &Path) -> result::Result<bool, OpenReadError> {
+        let reader = self.directory.open_read(path)?;
+        let (footer, data) = Footer::extract_footer(reader)
+            .map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
+        let mut hasher = Hasher::new();
+        hasher.update(data.as_slice());
+        let crc = hasher.finalize();
+        Ok(footer
+            .versioned_footer
+            .crc()
+            .map(|v| v == crc)
+            .unwrap_or(false))
+    }
+
+    /// List files for which checksum does not match content
+    pub fn list_damaged(&self) -> result::Result<HashSet<PathBuf>, OpenReadError> {
+        let mut hashset = HashSet::new();
+        let managed_paths = self
+            .meta_informations
+            .read()
+            .expect("Managed directory rlock poisoned in list damaged.")
+            .managed_paths
+            .clone();
+
+        for path in managed_paths.into_iter() {
+            if !self.validate_checksum(&path)? {
+                hashset.insert(path);
+            }
+        }
+        Ok(hashset)
+    }
 }
 
 impl Directory for ManagedDirectory {
     fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
-        self.directory.open_read(path)
+        let read_only_source = self.directory.open_read(path)?;
+        let (_footer, reader) = Footer::extract_footer(read_only_source)
+            .map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
+        Ok(reader)
     }
 
     fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
         self.register_file_as_managed(path)
             .map_err(|e| IOError::with_path(path.to_owned(), e))?;
-        self.directory.open_write(path)
+        Ok(io::BufWriter::new(Box::new(FooterProxy::new(
+            self.directory
+                .open_write(path)?
+                .into_inner()
+                .map_err(|_| ())
+                .expect("buffer should be empty"),
+        ))))
     }
 
     fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
@@ -259,8 +303,9 @@ impl Clone for ManagedDirectory {
 #[cfg(test)]
 mod tests_mmap_specific {
 
-    use crate::directory::{Directory, ManagedDirectory, MmapDirectory};
+    use crate::directory::{Directory, ManagedDirectory, MmapDirectory, TerminatingWrite};
     use std::collections::HashSet;
+    use std::fs::OpenOptions;
     use std::io::Write;
     use std::path::{Path, PathBuf};
     use tempfile::TempDir;
@@ -275,8 +320,8 @@ mod tests_mmap_specific {
         {
             let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
             let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
-            let mut write_file = managed_directory.open_write(test_path1).unwrap();
+            let write_file = managed_directory.open_write(test_path1).unwrap();
-            write_file.flush().unwrap();
+            write_file.terminate().unwrap();
             managed_directory
                 .atomic_write(test_path2, &[0u8, 1u8])
                 .unwrap();
@@ -310,9 +355,9 @@ mod tests_mmap_specific {
 
         let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
         let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
-        managed_directory
+        let mut write = managed_directory.open_write(test_path1).unwrap();
-            .atomic_write(test_path1, &vec![0u8, 1u8])
+        write.write_all(&[0u8, 1u8]).unwrap();
-            .unwrap();
+        write.terminate().unwrap();
         assert!(managed_directory.exists(test_path1));
 
         let _mmap_read = managed_directory.open_read(test_path1).unwrap();
@@ -331,4 +376,38 @@ mod tests_mmap_specific {
         }
     }
 
+    #[test]
+    fn test_checksum() {
+        let test_path1: &'static Path = Path::new("some_path_for_test");
+        let test_path2: &'static Path = Path::new("other_test_path");
+
+        let tempdir = TempDir::new().unwrap();
+        let tempdir_path = PathBuf::from(tempdir.path());
+
+        let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
+        let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
+        let mut write = managed_directory.open_write(test_path1).unwrap();
+        write.write_all(&[0u8, 1u8]).unwrap();
+        write.terminate().unwrap();
+
+        let mut write = managed_directory.open_write(test_path2).unwrap();
+        write.write_all(&[3u8, 4u8, 5u8]).unwrap();
+        write.terminate().unwrap();
+
+        assert!(managed_directory.list_damaged().unwrap().is_empty());
+
+        let mut corrupted_path = tempdir_path.clone();
+        corrupted_path.push(test_path2);
+        let mut file = OpenOptions::new()
+            .write(true)
+            .open(&corrupted_path)
+            .unwrap();
+        file.write_all(&[255u8]).unwrap();
+        file.flush().unwrap();
+        drop(file);
+
+        let damaged = managed_directory.list_damaged().unwrap();
+        assert_eq!(damaged.len(), 1);
+        assert!(damaged.contains(test_path2));
+    }
 }

src/directory/mmap_directory.rs

@@ -11,6 +11,7 @@ use crate::directory::error::{
     DeleteError, IOError, OpenDirectoryError, OpenReadError, OpenWriteError,
 };
 use crate::directory::read_only_source::BoxedData;
+use crate::directory::AntiCallToken;
 use crate::directory::Directory;
 use crate::directory::DirectoryLock;
 use crate::directory::Lock;
@@ -18,7 +19,7 @@ use crate::directory::ReadOnlySource;
 use crate::directory::WatchCallback;
 use crate::directory::WatchCallbackList;
 use crate::directory::WatchHandle;
-use crate::directory::WritePtr;
+use crate::directory::{TerminatingWrite, WritePtr};
 use atomicwrites;
 use memmap::Mmap;
 use std::collections::HashMap;
@@ -141,42 +142,28 @@ 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 +174,7 @@ 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 +187,15 @@ 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)
     }
 }
 
@@ -265,7 +254,7 @@ impl MmapDirectoryInner {
             }
         }
         if let Some(watch_wrapper) = self.watcher.write().unwrap().as_mut() {
-            return Ok(watch_wrapper.watch(watch_callback));
+            Ok(watch_wrapper.watch(watch_callback))
         } else {
             unreachable!("At this point, watch wrapper is supposed to be initialized");
         }
@@ -412,6 +401,12 @@ impl Seek for SafeFileWriter {
     }
 }
 
+impl TerminatingWrite for SafeFileWriter {
+    fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
+        self.flush()
+    }
+}
+
 impl Directory for MmapDirectory {
     fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
         debug!("Open Read {:?}", path);

src/directory/mod.rs

@@ -9,6 +9,7 @@ mod mmap_directory;
 
 mod directory;
 mod directory_lock;
+mod footer;
 mod managed_directory;
 mod ram_directory;
 mod read_only_source;
@@ -24,18 +25,49 @@ pub use self::ram_directory::RAMDirectory;
 pub use self::read_only_source::ReadOnlySource;
 pub(crate) use self::watch_event_router::WatchCallbackList;
 pub use self::watch_event_router::{WatchCallback, WatchHandle};
-use std::io::{BufWriter, Write};
+use std::io::{self, BufWriter, Write};
 
 #[cfg(feature = "mmap")]
 pub use self::mmap_directory::MmapDirectory;
 
 pub use self::managed_directory::ManagedDirectory;
 
+/// Struct used to prevent from calling [`terminate_ref`](trait.TerminatingWrite#method.terminate_ref) directly
+pub struct AntiCallToken(());
+
+/// Trait used to indicate when no more write need to be done on a writer
+pub trait TerminatingWrite: Write {
+    /// Indicate that the writer will no longer be used. Internally call terminate_ref.
+    fn terminate(mut self) -> io::Result<()>
+    where
+        Self: Sized,
+    {
+        self.terminate_ref(AntiCallToken(()))
+    }
+
+    /// You should implement this function to define custom behavior.
+    /// This function should flush any buffer it may hold.
+    fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()>;
+}
+
+impl<W: TerminatingWrite + ?Sized> TerminatingWrite for Box<W> {
+    fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
+        self.as_mut().terminate_ref(token)
+    }
+}
+
+impl<W: TerminatingWrite> TerminatingWrite for BufWriter<W> {
+    fn terminate_ref(&mut self, a: AntiCallToken) -> io::Result<()> {
+        self.flush()?;
+        self.get_mut().terminate_ref(a)
+    }
+}
+
 /// Write object for Directory.
 ///
 /// `WritePtr` are required to implement both Write
 /// and Seek.
-pub type WritePtr = BufWriter<Box<dyn Write>>;
+pub type WritePtr = BufWriter<Box<dyn TerminatingWrite>>;
 
 #[cfg(test)]
 mod tests;

src/directory/ram_directory.rs

@@ -1,8 +1,9 @@
 use crate::core::META_FILEPATH;
 use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
+use crate::directory::AntiCallToken;
 use crate::directory::WatchCallbackList;
-use crate::directory::WritePtr;
 use crate::directory::{Directory, ReadOnlySource, WatchCallback, WatchHandle};
+use crate::directory::{TerminatingWrite, WritePtr};
 use fail::fail_point;
 use std::collections::HashMap;
 use std::fmt;
@@ -71,6 +72,12 @@ impl Write for VecWriter {
     }
 }
 
+impl TerminatingWrite for VecWriter {
+    fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
+        self.flush()
+    }
+}
+
 #[derive(Default)]
 struct InnerDirectory {
     fs: HashMap<PathBuf, ReadOnlySource>,

src/directory/tests.rs

@@ -127,7 +127,7 @@ fn test_watch(directory: &mut dyn Directory) {
         assert!(directory
             .atomic_write(Path::new("meta.json"), b"random_test_data_2")
             .is_ok());
-        for _ in 0..100 {
+        for _ in 0..1_000 {
             if counter.load(Ordering::SeqCst) > i {
                 break;
             }

src/directory/watch_event_router.rs

@@ -152,5 +152,4 @@ mod tests {
         thread::sleep(Duration::from_millis(WAIT_TIME));
         assert_eq!(2, counter.load(Ordering::SeqCst));
     }
-
 }

src/fastfield/mod.rs

@@ -429,5 +429,111 @@ mod tests {
             }
         }
     }
-
+}
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+    use super::tests::FIELD;
+    use super::tests::{generate_permutation, SCHEMA};
+    use super::*;
+    use crate::common::CompositeFile;
+    use crate::directory::{Directory, RAMDirectory, WritePtr};
+    use crate::fastfield::FastFieldReader;
+    use std::collections::HashMap;
+    use std::path::Path;
+    use test::{self, Bencher};
+
+    #[bench]
+    fn bench_intfastfield_linear_veclookup(b: &mut Bencher) {
+        let permutation = generate_permutation();
+        b.iter(|| {
+            let n = test::black_box(7000u32);
+            let mut a = 0u64;
+            for i in (0u32..n / 7).map(|v| v * 7) {
+                a ^= permutation[i as usize];
+            }
+            a
+        });
+    }
+
+    #[bench]
+    fn bench_intfastfield_veclookup(b: &mut Bencher) {
+        let permutation = generate_permutation();
+        b.iter(|| {
+            let n = test::black_box(1000u32);
+            let mut a = 0u64;
+            for _ in 0u32..n {
+                a = permutation[a as usize];
+            }
+            a
+        });
+    }
+
+    #[bench]
+    fn bench_intfastfield_linear_fflookup(b: &mut Bencher) {
+        let path = Path::new("test");
+        let permutation = generate_permutation();
+        let mut directory: RAMDirectory = RAMDirectory::create();
+        {
+            let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
+            let mut serializer = FastFieldSerializer::from_write(write).unwrap();
+            let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
+            for &x in &permutation {
+                fast_field_writers.add_document(&doc!(*FIELD=>x));
+            }
+            fast_field_writers
+                .serialize(&mut serializer, &HashMap::new())
+                .unwrap();
+            serializer.close().unwrap();
+        }
+        let source = directory.open_read(&path).unwrap();
+        {
+            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let data = fast_fields_composite.open_read(*FIELD).unwrap();
+            let fast_field_reader = FastFieldReader::<u64>::open(data);
+
+            b.iter(|| {
+                let n = test::black_box(7000u32);
+                let mut a = 0u64;
+                for i in (0u32..n / 7).map(|val| val * 7) {
+                    a ^= fast_field_reader.get(i);
+                }
+                a
+            });
+        }
+    }
+
+    #[bench]
+    fn bench_intfastfield_fflookup(b: &mut Bencher) {
+        let path = Path::new("test");
+        let permutation = generate_permutation();
+        let mut directory: RAMDirectory = RAMDirectory::create();
+        {
+            let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
+            let mut serializer = FastFieldSerializer::from_write(write).unwrap();
+            let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
+            for &x in &permutation {
+                fast_field_writers.add_document(&doc!(*FIELD=>x));
+            }
+            fast_field_writers
+                .serialize(&mut serializer, &HashMap::new())
+                .unwrap();
+            serializer.close().unwrap();
+        }
+        let source = directory.open_read(&path).unwrap();
+        {
+            let fast_fields_composite = CompositeFile::open(&source).unwrap();
+            let data = fast_fields_composite.open_read(*FIELD).unwrap();
+            let fast_field_reader = FastFieldReader::<u64>::open(data);
+
+            b.iter(|| {
+                let n = test::black_box(1000u32);
+                let mut a = 0u32;
+                for _ in 0u32..n {
+                    a = fast_field_reader.get(a) as u32;
+                }
+                a
+            });
+        }
+    }
 }

src/fastfield/multivalued/writer.rs

@@ -5,8 +5,8 @@ use crate::postings::UnorderedTermId;
 use crate::schema::{Document, Field};
 use crate::termdict::TermOrdinal;
 use crate::DocId;
+use fnv::FnvHashMap;
 use itertools::Itertools;
-use std::collections::HashMap;
 use std::io;
 
 /// Writer for multi-valued (as in, more than one value per document)
@@ -102,7 +102,7 @@ impl MultiValueIntFastFieldWriter {
     pub fn serialize(
         &self,
         serializer: &mut FastFieldSerializer,
-        mapping_opt: Option<&HashMap<UnorderedTermId, TermOrdinal>>,
+        mapping_opt: Option<&FnvHashMap<UnorderedTermId, TermOrdinal>>,
     ) -> io::Result<()> {
         {
             // writing the offset index

src/fastfield/reader.rs

@@ -67,12 +67,10 @@ impl<Item: FastValue> FastFieldReader<Item> {
     ///
     /// May panic if `doc` is greater than the segment
     // `maxdoc`.
-    #[inline(always)]
     pub fn get(&self, doc: DocId) -> Item {
         self.get_u64(u64::from(doc))
     }
 
-    #[inline(always)]
     pub(crate) fn get_u64(&self, doc: u64) -> Item {
         Item::from_u64(self.min_value_u64 + self.bit_unpacker.get(doc))
     }

src/fastfield/writer.rs

@@ -6,6 +6,7 @@ use crate::fastfield::{BytesFastFieldWriter, FastFieldSerializer};
 use crate::postings::UnorderedTermId;
 use crate::schema::{Cardinality, Document, Field, FieldType, Schema};
 use crate::termdict::TermOrdinal;
+use fnv::FnvHashMap;
 use std::collections::HashMap;
 use std::io;
 
@@ -116,7 +117,7 @@ impl FastFieldsWriter {
     pub fn serialize(
         &self,
         serializer: &mut FastFieldSerializer,
-        mapping: &HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>>,
+        mapping: &HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>,
     ) -> io::Result<()> {
         for field_writer in &self.single_value_writers {
             field_writer.serialize(serializer)?;

src/indexer/index_writer.rs

@@ -8,6 +8,7 @@ use crate::core::SegmentId;
 use crate::core::SegmentMeta;
 use crate::core::SegmentReader;
 use crate::directory::DirectoryLock;
+use crate::directory::TerminatingWrite;
 use crate::docset::DocSet;
 use crate::error::TantivyError;
 use crate::fastfield::write_delete_bitset;
@@ -168,6 +169,7 @@ pub(crate) fn advance_deletes(
             segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
             let mut delete_file = segment.open_write(SegmentComponent::DELETE)?;
             write_delete_bitset(&delete_bitset, &mut delete_file)?;
+            delete_file.terminate()?;
         }
     }
     segment_entry.set_meta(segment.meta().clone());
@@ -209,10 +211,7 @@ fn index_documents(
     assert!(num_docs > 0);
 
     let doc_opstamps: Vec<Opstamp> = segment_writer.finalize()?;
-    let segment_meta = segment
+    let segment_meta = segment.index().new_segment_meta(segment_id, num_docs);
-        .index()
-        .inventory()
-        .new_segment_meta(segment_id, num_docs);
 
     let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap());
 
@@ -450,12 +449,10 @@ impl IndexWriter {
     /// by clearing and resubmitting necessary documents
     ///
     /// ```rust
-    /// #[macro_use]
-    /// extern crate tantivy;
-    /// use tantivy::query::QueryParser;
     /// use tantivy::collector::TopDocs;
+    /// use tantivy::query::QueryParser;
     /// use tantivy::schema::*;
-    /// use tantivy::Index;
+    /// use tantivy::{doc, Index};
     ///
     /// fn main() -> tantivy::Result<()> {
     ///     let mut schema_builder = Schema::builder();
@@ -1182,5 +1179,4 @@ mod tests {
         assert!(clear_again.is_ok());
         assert!(commit_again.is_ok());
     }
-
 }

src/indexer/segment_register.rs

@@ -134,5 +134,4 @@ mod tests {
         }
         assert_eq!(segment_ids(&segment_register), vec![segment_id_merged]);
     }
-
 }

src/indexer/segment_updater.rs

@@ -126,9 +126,7 @@ fn perform_merge(
 
     let num_docs = merger.write(segment_serializer)?;
 
-    let segment_meta = index
+    let segment_meta = index.new_segment_meta(merged_segment.id(), num_docs);
-        .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)
@@ -282,7 +280,7 @@ 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.inventory().all() {
+        for segment_meta in self.0.index.list_all_segment_metas() {
             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<Box<dyn BoxedTokenizer>>>,
+    tokenizers: Vec<Option<BoxedTokenizer>>,
 }
 
 impl SegmentWriter {
@@ -296,5 +296,4 @@ mod tests {
         assert_eq!(initial_table_size(10_000_000).unwrap(), 17);
         assert_eq!(initial_table_size(1_000_000_000).unwrap(), 19);
     }
-
 }

src/lib.rs

@@ -1,5 +1,4 @@
 #![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))))]
@@ -11,21 +10,12 @@
 //! Think `Lucene`, but in Rust.
 //!
 //! ```rust
-
-//! # extern crate tempfile;
-//! #
-//! #[macro_use]
-//! extern crate tantivy;
-//!
-//! // ...
-//!
 //! # use std::path::Path;
 //! # use tempfile::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
@@ -249,6 +239,7 @@ pub struct DocAddress(pub SegmentLocalId, pub DocId);
 
 #[cfg(test)]
 mod tests {
+
     use crate::collector::tests::TEST_COLLECTOR_WITH_SCORE;
     use crate::core::SegmentReader;
     use crate::docset::DocSet;
@@ -894,15 +885,3 @@ mod tests {
         }
     }
 }
-
-#[cfg(feature = "forbench")]
-pub mod forbench {
-    pub mod compression {
-        pub use crate::postings::compression::*;
-    }
-
-    pub mod bitset {
-        pub use crate::common::BitSet;
-        pub use crate::common::TinySet;
-    }
-}

src/macros.rs

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

src/postings/compression/mod.rs

@@ -160,9 +160,9 @@ impl VIntEncoder for BlockEncoder {
 }
 
 impl VIntDecoder for BlockDecoder {
-    fn uncompress_vint_sorted(
+    fn uncompress_vint_sorted<'a>(
         &mut self,
-        compressed_data: &[u8],
+        compressed_data: &'a [u8],
         offset: u32,
         num_els: usize,
     ) -> usize {
@@ -170,7 +170,7 @@ impl VIntDecoder for BlockDecoder {
         vint::uncompress_sorted(compressed_data, &mut self.output.0[..num_els], offset)
     }
 
-    fn uncompress_vint_unsorted(&mut self, compressed_data: &[u8], num_els: usize) -> usize {
+    fn uncompress_vint_unsorted<'a>(&mut self, compressed_data: &'a [u8], num_els: usize) -> usize {
         self.output_len = num_els;
         vint::uncompress_unsorted(compressed_data, &mut self.output.0[..num_els])
     }
@@ -268,17 +268,80 @@ pub mod tests {
             }
         }
     }
+}
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+
+    use super::*;
+    use rand::rngs::StdRng;
+    use rand::Rng;
+    use rand::SeedableRng;
+    use test::Bencher;
+
+    fn generate_array_with_seed(n: usize, ratio: f64, seed_val: u8) -> Vec<u32> {
+        let mut seed: [u8; 32] = [0; 32];
+        seed[31] = seed_val;
+        let mut rng = StdRng::from_seed(seed);
+        (0u32..).filter(|_| rng.gen_bool(ratio)).take(n).collect()
+    }
+
+    pub fn generate_array(n: usize, ratio: f64) -> Vec<u32> {
+        generate_array_with_seed(n, ratio, 4)
+    }
+
+    #[bench]
+    fn bench_compress(b: &mut Bencher) {
+        let mut encoder = BlockEncoder::new();
+        let data = generate_array(COMPRESSION_BLOCK_SIZE, 0.1);
+        b.iter(|| {
+            encoder.compress_block_sorted(&data, 0u32);
+        });
+    }
+
+    #[bench]
+    fn bench_uncompress(b: &mut Bencher) {
+        let mut encoder = BlockEncoder::new();
+        let data = generate_array(COMPRESSION_BLOCK_SIZE, 0.1);
+        let (num_bits, compressed) = encoder.compress_block_sorted(&data, 0u32);
+        let mut decoder = BlockDecoder::new();
+        b.iter(|| {
+            decoder.uncompress_block_sorted(compressed, 0u32, num_bits);
+        });
+    }
 
     #[test]
     fn test_all_docs_compression_numbits() {
-        for expected_num_bits in 0u8..33u8 {
+        for expected_num_bits in 0u8.. {
             let mut data = [0u32; 128];
             if expected_num_bits > 0 {
-                data[0] = (1u64 << (expected_num_bits as u64) - 1u64) as u32;
+                data[0] = (1u64 << (expected_num_bits as usize) - 1) as u32;
             }
             let mut encoder = BlockEncoder::new();
             let (num_bits, compressed) = encoder.compress_block_unsorted(&data);
             assert_eq!(compressed.len(), compressed_block_size(num_bits));
         }
     }
+
+    const NUM_INTS_BENCH_VINT: usize = 10;
+
+    #[bench]
+    fn bench_compress_vint(b: &mut Bencher) {
+        let mut encoder = BlockEncoder::new();
+        let data = generate_array(NUM_INTS_BENCH_VINT, 0.001);
+        b.iter(|| {
+            encoder.compress_vint_sorted(&data, 0u32);
+        });
+    }
+
+    #[bench]
+    fn bench_uncompress_vint(b: &mut Bencher) {
+        let mut encoder = BlockEncoder::new();
+        let data = generate_array(NUM_INTS_BENCH_VINT, 0.001);
+        let compressed = encoder.compress_vint_sorted(&data, 0u32);
+        let mut decoder = BlockDecoder::new();
+        b.iter(|| {
+            decoder.uncompress_vint_sorted(compressed, 0u32, NUM_INTS_BENCH_VINT);
+        });
+    }
 }

src/postings/mod.rs

@@ -3,7 +3,6 @@ Postings module (also called inverted index)
 */
 
 mod block_search;
-
 pub(crate) mod compression;
 /// Postings module
 ///
@@ -623,23 +622,23 @@ pub mod tests {
             assert!(!postings_unopt.advance());
         }
     }
-
 }
 
 #[cfg(all(test, feature = "unstable"))]
 mod bench {
 
     use super::tests::*;
-    use docset::SkipResult;
+    use crate::docset::SkipResult;
-    use query::Intersection;
+    use crate::query::Intersection;
-    use schema::IndexRecordOption;
+    use crate::schema::IndexRecordOption;
+    use crate::tests;
+    use crate::DocSet;
     use test::{self, Bencher};
-    use tests;
-    use DocSet;
 
     #[bench]
     fn bench_segment_postings(b: &mut Bencher) {
-        let searcher = INDEX.searcher();
+        let reader = INDEX.reader().unwrap();
+        let searcher = reader.searcher();
         let segment_reader = searcher.segment_reader(0);
 
         b.iter(|| {
@@ -653,7 +652,8 @@ mod bench {
 
     #[bench]
     fn bench_segment_intersection(b: &mut Bencher) {
-        let searcher = INDEX.searcher();
+        let reader = INDEX.reader().unwrap();
+        let searcher = reader.searcher();
         let segment_reader = searcher.segment_reader(0);
         b.iter(|| {
             let segment_postings_a = segment_reader
@@ -683,7 +683,8 @@ mod bench {
     }
 
     fn bench_skip_next(p: f64, b: &mut Bencher) {
-        let searcher = INDEX.searcher();
+        let reader = INDEX.reader().unwrap();
+        let searcher = reader.searcher();
         let segment_reader = searcher.segment_reader(0);
         let docs = tests::sample(segment_reader.num_docs(), p);
 
@@ -738,7 +739,8 @@ mod bench {
 
     #[bench]
     fn bench_iterate_segment_postings(b: &mut Bencher) {
-        let searcher = INDEX.searcher();
+        let reader = INDEX.reader().unwrap();
+        let searcher = reader.searcher();
         let segment_reader = searcher.segment_reader(0);
         b.iter(|| {
             let n: u32 = test::black_box(17);

src/postings/postings_writer.rs

@@ -12,6 +12,7 @@ use crate::tokenizer::TokenStream;
 use crate::tokenizer::{Token, MAX_TOKEN_LEN};
 use crate::DocId;
 use crate::Result;
+use fnv::FnvHashMap;
 use std::collections::HashMap;
 use std::io;
 use std::marker::PhantomData;
@@ -127,12 +128,12 @@ impl MultiFieldPostingsWriter {
     pub fn serialize(
         &self,
         serializer: &mut InvertedIndexSerializer,
-    ) -> Result<HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>>> {
+    ) -> Result<HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>> {
         let mut term_offsets: Vec<(&[u8], Addr, UnorderedTermId)> =
             self.term_index.iter().collect();
         term_offsets.sort_unstable_by_key(|&(k, _, _)| k);
 
-        let mut unordered_term_mappings: HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>> =
+        let mut unordered_term_mappings: HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>> =
             HashMap::new();
 
         let field_offsets = make_field_partition(&term_offsets);
@@ -147,7 +148,7 @@ impl MultiFieldPostingsWriter {
                     let unordered_term_ids = term_offsets[start..stop]
                         .iter()
                         .map(|&(_, _, bucket)| bucket);
-                    let mapping: HashMap<UnorderedTermId, TermOrdinal> = unordered_term_ids
+                    let mapping: FnvHashMap<UnorderedTermId, TermOrdinal> = unordered_term_ids
                         .enumerate()
                         .map(|(term_ord, unord_term_id)| {
                             (unord_term_id as UnorderedTermId, term_ord as TermOrdinal)

src/postings/serializer.rs

@@ -141,10 +141,7 @@ impl<'a> FieldSerializer<'a> {
             FieldType::Str(ref text_options) => {
                 if let Some(text_indexing_options) = text_options.get_indexing_options() {
                     let index_option = text_indexing_options.index_option();
-                    (
+                    (index_option.has_freq(), index_option.has_positions())
-                        index_option.is_termfreq_enabled(),
-                        index_option.is_position_enabled(),
-                    )
                 } else {
                     (false, false)
                 }

src/postings/stacker/expull.rs

@@ -310,6 +310,7 @@ mod bench {
     use super::super::MemoryArena;
     use super::ExpUnrolledLinkedList;
     use byteorder::{NativeEndian, WriteBytesExt};
+    use std::iter;
     use test::Bencher;
 
     const NUM_STACK: usize = 10_000;
@@ -335,11 +336,10 @@ mod bench {
     fn bench_push_stack(bench: &mut Bencher) {
         bench.iter(|| {
             let mut heap = MemoryArena::new();
-            let mut stacks = Vec::with_capacity(100);
+            let mut stacks: Vec<ExpUnrolledLinkedList> =
-            for _ in 0..NUM_STACK {
+                iter::repeat_with(ExpUnrolledLinkedList::new)
-                let mut stack = ExpUnrolledLinkedList::new();
+                    .take(NUM_STACK)
-                stacks.push(stack);
+                    .collect();
-            }
             for s in 0..NUM_STACK {
                 for i in 0u32..STACK_SIZE {
                     let t = s * 392017 % NUM_STACK;

src/query/all_query.rs

@@ -130,5 +130,4 @@ mod tests {
             assert!(!scorer.advance());
         }
     }
-
 }

src/query/automaton_weight.rs

@@ -8,15 +8,13 @@ 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: A,
+    automaton: Arc<A>,
 }
 
 impl<A> AutomatonWeight<A>
@@ -24,12 +22,16 @@ where
     A: Automaton + Send + Sync + 'static,
 {
     /// Create a new AutomationWeight
-    pub fn new(field: Field, automaton: A) -> AutomatonWeight<A> {
+    pub fn new<IntoArcA: Into<Arc<A>>>(field: Field, automaton: IntoArcA) -> AutomatonWeight<A> {
-        AutomatonWeight { field, automaton }
+        AutomatonWeight {
+            field,
+            automaton: automaton.into(),
+        }
     }
 
     fn automaton_stream<'a>(&'a self, term_dict: &'a TermDictionary) -> TermStreamer<'a, &'a A> {
-        let term_stream_builder = term_dict.search(&self.automaton);
+        let automaton: &A = &*self.automaton;
+        let term_stream_builder = term_dict.search(automaton);
         term_stream_builder.into_stream()
     }
 }

src/query/bitset/mod.rs

@@ -216,5 +216,48 @@ mod tests {
             assert!(!docset.advance());
         }
     }
-
+}
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+
+    use super::BitSet;
+    use super::BitSetDocSet;
+    use crate::test;
+    use crate::tests;
+    use crate::DocSet;
+
+    #[bench]
+    fn bench_bitset_1pct_insert(b: &mut test::Bencher) {
+        let els = tests::generate_nonunique_unsorted(1_000_000u32, 10_000);
+        b.iter(|| {
+            let mut bitset = BitSet::with_max_value(1_000_000);
+            for el in els.iter().cloned() {
+                bitset.insert(el);
+            }
+        });
+    }
+
+    #[bench]
+    fn bench_bitset_1pct_clone(b: &mut test::Bencher) {
+        let els = tests::generate_nonunique_unsorted(1_000_000u32, 10_000);
+        let mut bitset = BitSet::with_max_value(1_000_000);
+        for el in els {
+            bitset.insert(el);
+        }
+        b.iter(|| bitset.clone());
+    }
+
+    #[bench]
+    fn bench_bitset_1pct_clone_iterate(b: &mut test::Bencher) {
+        let els = tests::sample(1_000_000u32, 0.01);
+        let mut bitset = BitSet::with_max_value(1_000_000);
+        for el in els {
+            bitset.insert(el);
+        }
+        b.iter(|| {
+            let mut docset = BitSetDocSet::from(bitset.clone());
+            while docset.advance() {}
+        });
+    }
 }

src/query/bm25.rs

@@ -137,5 +137,4 @@ mod tests {
     fn test_idf() {
         assert_nearly_equals(idf(1, 2), 0.6931472);
     }
-
 }

src/query/boolean_query/mod.rs

@@ -247,9 +247,7 @@ mod tests {
         let reader = index.reader().unwrap();
         let searcher = reader.searcher();
         let query_parser = QueryParser::for_index(&index, vec![title, text]);
-        let query = query_parser
+        let query = query_parser.parse_query("Оксана Лифенко").unwrap();
-            .parse_query("Оксана Лифенко")
-            .unwrap();
         let weight = query.weight(&searcher, true).unwrap();
         let mut scorer = weight.scorer(searcher.segment_reader(0u32)).unwrap();
         scorer.advance();

src/query/exclude.rs

@@ -175,5 +175,4 @@ mod tests {
             sample_skip,
         );
     }
-
 }

src/query/fuzzy_query.rs

@@ -28,12 +28,10 @@ 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<()> {

src/query/intersection.rs

@@ -45,7 +45,7 @@ pub fn intersect_scorers(mut scorers: Vec<Box<dyn Scorer>>) -> Box<dyn Scorer> {
     })
 }
 
-/// Creates a `DocSet` that iterator through the intersection of two `DocSet`s.
+/// Creates a `DocSet` that iterate through the intersection of two or more `DocSet`s.
 pub struct Intersection<TDocSet: DocSet, TOtherDocSet: DocSet = Box<dyn Scorer>> {
     left: TDocSet,
     right: TDocSet,

src/query/intersection_two.rs

@@ -5,7 +5,7 @@ use Score;
 use SkipResult;
 
 
-/// Creates a `DocSet` that iterator through the intersection of two `DocSet`s.
+/// Creates a `DocSet` that iterate through the intersection of two `DocSet`s.
 pub struct IntersectionTwoTerms<TDocSet> {
     left: TDocSet,
     right: TDocSet

src/query/mod.rs

@@ -12,7 +12,6 @@ mod exclude;
 mod explanation;
 mod fuzzy_query;
 mod intersection;
-mod occur;
 mod phrase_query;
 mod query;
 mod query_parser;
@@ -43,7 +42,6 @@ pub use self::exclude::Exclude;
 pub use self::explanation::Explanation;
 pub use self::fuzzy_query::FuzzyTermQuery;
 pub use self::intersection::intersect_scorers;
-pub use self::occur::Occur;
 pub use self::phrase_query::PhraseQuery;
 pub use self::query::Query;
 pub use self::query_parser::QueryParser;
@@ -55,6 +53,7 @@ pub use self::scorer::ConstScorer;
 pub use self::scorer::Scorer;
 pub use self::term_query::TermQuery;
 pub use self::weight::Weight;
+pub use tantivy_query_grammar::Occur;
 
 #[cfg(test)]
 mod tests {

src/query/query_parser/mod.rs

@@ -1,6 +1,4 @@
-mod query_grammar;
 mod query_parser;
-mod user_input_ast;
 
 pub mod logical_ast;
 pub use self::query_parser::QueryParser;

src/query/query_parser/query_parser.rs

@@ -1,9 +1,5 @@
 use super::logical_ast::*;
-use super::query_grammar::parse_to_ast;
-use super::user_input_ast::*;
 use crate::core::Index;
-use crate::query::occur::compose_occur;
-use crate::query::query_parser::logical_ast::LogicalAST;
 use crate::query::AllQuery;
 use crate::query::BooleanQuery;
 use crate::query::EmptyQuery;
@@ -16,11 +12,11 @@ use crate::schema::IndexRecordOption;
 use crate::schema::{Field, Schema};
 use crate::schema::{FieldType, Term};
 use crate::tokenizer::TokenizerManager;
-use combine::Parser;
 use std::borrow::Cow;
 use std::num::{ParseFloatError, ParseIntError};
 use std::ops::Bound;
 use std::str::FromStr;
+use tantivy_query_grammar::{UserInputAST, UserInputBound, UserInputLeaf};
 
 /// Possible error that may happen when parsing a query.
 #[derive(Debug, PartialEq, Eq, Fail)]
@@ -222,9 +218,8 @@ impl QueryParser {
 
     /// Parse the user query into an AST.
     fn parse_query_to_logical_ast(&self, query: &str) -> Result<LogicalAST, QueryParserError> {
-        let (user_input_ast, _remaining) = parse_to_ast()
+        let user_input_ast =
-            .parse(query)
+            tantivy_query_grammar::parse_query(query).map_err(|_| QueryParserError::SyntaxError)?;
-            .map_err(|_| QueryParserError::SyntaxError)?;
         self.compute_logical_ast(user_input_ast)
     }
 
@@ -369,6 +364,7 @@ impl QueryParser {
         match *bound {
             UserInputBound::Inclusive(_) => Ok(Bound::Included(term)),
             UserInputBound::Exclusive(_) => Ok(Bound::Excluded(term)),
+            UserInputBound::Unbounded => Ok(Bound::Unbounded),
         }
     }
 
@@ -398,7 +394,7 @@ impl QueryParser {
                 let mut logical_sub_queries: Vec<(Occur, LogicalAST)> = Vec::new();
                 for sub_query in sub_queries {
                     let (occur, sub_ast) = self.compute_logical_ast_with_occur(sub_query)?;
-                    let new_occur = compose_occur(default_occur, occur);
+                    let new_occur = Occur::compose(default_occur, occur);
                     logical_sub_queries.push((new_occur, sub_ast));
                 }
                 Ok((Occur::Should, LogicalAST::Clause(logical_sub_queries)))
@@ -406,7 +402,7 @@ impl QueryParser {
             UserInputAST::Unary(left_occur, subquery) => {
                 let (right_occur, logical_sub_queries) =
                     self.compute_logical_ast_with_occur(*subquery)?;
-                Ok((compose_occur(left_occur, right_occur), logical_sub_queries))
+                Ok((Occur::compose(left_occur, right_occur), logical_sub_queries))
             }
             UserInputAST::Leaf(leaf) => {
                 let result_ast = self.compute_logical_ast_from_leaf(*leaf)?;
@@ -628,7 +624,7 @@ mod test {
     pub fn test_parse_query_untokenized() {
         test_parse_query_to_logical_ast_helper(
             "nottokenized:\"wordone wordtwo\"",
-            "Term([0, 0, 0, 7, 119, 111, 114, 100, 111, 110, \
+            "Term(field=7,bytes=[119, 111, 114, 100, 111, 110, \
              101, 32, 119, 111, 114, 100, 116, 119, 111])",
             false,
         );
@@ -672,7 +668,7 @@ mod test {
             .is_ok());
         test_parse_query_to_logical_ast_helper(
             "unsigned:2324",
-            "Term([0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 9, 20])",
+            "Term(field=3,bytes=[0, 0, 0, 0, 0, 0, 9, 20])",
             false,
         );
 
@@ -693,19 +689,19 @@ mod test {
     pub fn test_parse_query_to_ast_single_term() {
         test_parse_query_to_logical_ast_helper(
             "title:toto",
-            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
+            "Term(field=0,bytes=[116, 111, 116, 111])",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto",
-            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
+            "Term(field=0,bytes=[116, 111, 116, 111])",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto -titi",
-            "(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
+            "(+Term(field=0,bytes=[116, 111, 116, 111]) \
-             -(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
+             -(Term(field=0,bytes=[116, 105, 116, 105]) \
-             Term([0, 0, 0, 1, 116, 105, 116, 105])))",
+             Term(field=1,bytes=[116, 105, 116, 105])))",
             false,
         );
         assert_eq!(
@@ -720,14 +716,13 @@ mod test {
     pub fn test_parse_query_to_ast_two_terms() {
         test_parse_query_to_logical_ast_helper(
             "title:a b",
-            "(Term([0, 0, 0, 0, 97]) (Term([0, 0, 0, 0, 98]) \
+            "(Term(field=0,bytes=[97]) (Term(field=0,bytes=[98]) Term(field=1,bytes=[98])))",
-             Term([0, 0, 0, 1, 98])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:\"a b\"",
-            "\"[(0, Term([0, 0, 0, 0, 97])), \
+            "\"[(0, Term(field=0,bytes=[97])), \
-             (1, Term([0, 0, 0, 0, 98]))]\"",
+             (1, Term(field=0,bytes=[98]))]\"",
             false,
         );
     }
@@ -736,45 +731,43 @@ mod test {
     pub fn test_parse_query_to_ast_ranges() {
         test_parse_query_to_logical_ast_helper(
             "title:[a TO b]",
-            "(Included(Term([0, 0, 0, 0, 97])) TO \
+            "(Included(Term(field=0,bytes=[97])) TO Included(Term(field=0,bytes=[98])))",
-             Included(Term([0, 0, 0, 0, 98])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "[a TO b]",
-            "((Included(Term([0, 0, 0, 0, 97])) TO \
+            "((Included(Term(field=0,bytes=[97])) TO \
-             Included(Term([0, 0, 0, 0, 98]))) \
+             Included(Term(field=0,bytes=[98]))) \
-             (Included(Term([0, 0, 0, 1, 97])) TO \
+             (Included(Term(field=1,bytes=[97])) TO \
-             Included(Term([0, 0, 0, 1, 98]))))",
+             Included(Term(field=1,bytes=[98]))))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:{titi TO toto}",
-            "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO \
+            "(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO \
-             Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
+             Excluded(Term(field=0,bytes=[116, 111, 116, 111])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:{* TO toto}",
-            "(Unbounded TO \
+            "(Unbounded 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:{titi TO *}",
-            "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO Unbounded)",
+            "(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO Unbounded)",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "signed:{-5 TO 3}",
-            "(Excluded(Term([0, 0, 0, 2, 127, 255, 255, 255, 255, 255, 255, 251])) TO \
+            "(Excluded(Term(field=2,bytes=[127, 255, 255, 255, 255, 255, 255, 251])) TO \
-            Excluded(Term([0, 0, 0, 2, 128, 0, 0, 0, 0, 0, 0, 3])))",
+             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([0, 0, 0, 10, 64, 7, 255, 255, 255, 255, 255, 255])) TO \
+            "(Excluded(Term(field=10,bytes=[64, 7, 255, 255, 255, 255, 255, 255])) TO \
-            Excluded(Term([0, 0, 0, 10, 191, 248, 0, 0, 0, 0, 0, 0])))",
+             Excluded(Term(field=10,bytes=[191, 248, 0, 0, 0, 0, 0, 0])))",
             false,
         );
 
@@ -879,19 +872,19 @@ mod test {
     pub fn test_parse_query_to_ast_conjunction() {
         test_parse_query_to_logical_ast_helper(
             "title:toto",
-            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
+            "Term(field=0,bytes=[116, 111, 116, 111])",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto",
-            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
+            "Term(field=0,bytes=[116, 111, 116, 111])",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto -titi",
-            "(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
+            "(+Term(field=0,bytes=[116, 111, 116, 111]) \
-             -(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
+             -(Term(field=0,bytes=[116, 105, 116, 105]) \
-             Term([0, 0, 0, 1, 116, 105, 116, 105])))",
+             Term(field=1,bytes=[116, 105, 116, 105])))",
             true,
         );
         assert_eq!(
@@ -902,15 +895,15 @@ mod test {
         );
         test_parse_query_to_logical_ast_helper(
             "title:a b",
-            "(+Term([0, 0, 0, 0, 97]) \
+            "(+Term(field=0,bytes=[97]) \
-             +(Term([0, 0, 0, 0, 98]) \
+             +(Term(field=0,bytes=[98]) \
-             Term([0, 0, 0, 1, 98])))",
+             Term(field=1,bytes=[98])))",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "title:\"a b\"",
-            "\"[(0, Term([0, 0, 0, 0, 97])), \
+            "\"[(0, Term(field=0,bytes=[97])), \
-             (1, Term([0, 0, 0, 0, 98]))]\"",
+             (1, Term(field=0,bytes=[98]))]\"",
             true,
         );
     }
@@ -919,10 +912,8 @@ mod test {
     pub fn test_query_parser_hyphen() {
         test_parse_query_to_logical_ast_helper(
             "title:www-form-encoded",
-            "\"[(0, Term([0, 0, 0, 0, 119, 119, 119])), \
+            "\"[(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]))]\"",
-             (1, Term([0, 0, 0, 0, 102, 111, 114, 109])), \
+            false
-             (2, Term([0, 0, 0, 0, 101, 110, 99, 111, 100, 101, 100]))]\"",
-            false,
         );
     }
 }

src/query/range_query.rs

@@ -38,14 +38,10 @@ fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
 /// # Example
 ///
 /// ```rust
-///
-/// # #[macro_use]
-/// # extern crate tantivy;
-/// # use tantivy::Index;
-/// # use tantivy::schema::{Schema, INDEXED};
 /// # use tantivy::collector::Count;
-/// # use tantivy::Result;
 /// # use tantivy::query::RangeQuery;
+/// # use tantivy::schema::{Schema, INDEXED};
+/// # use tantivy::{doc, Index, Result};
 /// #
 /// # fn run() -> Result<()> {
 /// #     let mut schema_builder = Schema::builder();
@@ -338,39 +334,33 @@ 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() {
-        fn run() -> Result<()> {
+        let mut schema_builder = Schema::builder();
-            let mut schema_builder = Schema::builder();
+        let year_field = schema_builder.add_u64_field("year", INDEXED);
-            let year_field = schema_builder.add_u64_field("year", INDEXED);
+        let schema = schema_builder.build();
-            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();
             }
-            let reader = index.reader().unwrap();
+            index_writer.commit().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();
 
-        run().unwrap();
+        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).unwrap();
+        assert_eq!(count, 2285);
     }
 
     #[test]
@@ -489,5 +479,4 @@ mod tests {
             91
         );
     }
-
 }

src/query/regex_query.rs

@@ -4,22 +4,18 @@ 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<()> {
@@ -48,7 +44,7 @@ use tantivy_fst::Regex;
 ///     let searcher = reader.searcher();
 ///
 ///     let term = Term::from_field_text(title, "Diary");
-///     let query = RegexQuery::new("d[ai]{2}ry".to_string(), title);
+///     let query = RegexQuery::from_pattern("d[ai]{2}ry", title)?;
 ///     let count = searcher.search(&query, &Count)?;
 ///     assert_eq!(count, 3);
 ///     Ok(())
@@ -56,30 +52,34 @@ use tantivy_fst::Regex;
 /// ```
 #[derive(Debug, Clone)]
 pub struct RegexQuery {
-    regex_pattern: String,
+    regex: Arc<Regex>,
     field: Field,
 }
 
 impl RegexQuery {
-    /// Creates a new Fuzzy Query
+    /// Creates a new RegexQuery from a given pattern
-    pub fn new(regex_pattern: String, field: Field) -> RegexQuery {
+    pub fn from_pattern(regex_pattern: &str, field: Field) -> Result<Self> {
+        let regex = Regex::new(&regex_pattern)
+            .map_err(|_| TantivyError::InvalidArgument(regex_pattern.to_string()))?;
+        Ok(RegexQuery::from_regex(regex, field))
+    }
+
+    /// Creates a new RegexQuery from a fully built Regex
+    pub fn from_regex<T: Into<Arc<Regex>>>(regex: T, field: Field) -> Self {
         RegexQuery {
-            regex_pattern,
+            regex: regex.into(),
             field,
         }
     }
 
-    fn specialized_weight(&self) -> Result<AutomatonWeight<Regex>> {
+    fn specialized_weight(&self) -> AutomatonWeight<Regex> {
-        let automaton = Regex::new(&self.regex_pattern)
+        AutomatonWeight::new(self.field, self.regex.clone())
-            .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()))
     }
 }
 
@@ -87,13 +87,14 @@ 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;
+    use crate::{Index, IndexReader};
+    use std::sync::Arc;
+    use tantivy_fst::Regex;
 
-    #[test]
+    fn build_test_index() -> (IndexReader, Field) {
-    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();
@@ -109,20 +110,65 @@ 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(&regex_query, &TopDocs::with_limit(2))
+                .search(&query_matching_one, &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(&regex_query, &TopDocs::with_limit(2))
+            .search(&query_matching_zero, &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/reqopt_scorer.rs

@@ -190,5 +190,4 @@ mod tests {
             skip_docs,
         );
     }
-
 }

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::{IndexRecordOption, Schema, STRING, TEXT};
+    use crate::schema::{Field, IndexRecordOption, Schema, STRING, TEXT};
     use crate::tests::assert_nearly_equals;
     use crate::Index;
     use crate::Term;
@@ -114,4 +114,16 @@ 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

@@ -7,6 +7,7 @@ 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.
@@ -19,12 +20,10 @@ use std::collections::BTreeSet;
 /// * `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<()> {
@@ -61,12 +60,18 @@ use std::collections::BTreeSet;
 ///     Ok(())
 /// }
 /// ```
-#[derive(Clone, Debug)]
+#[derive(Clone)]
 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/query/union.rs

@@ -28,7 +28,7 @@ where
     }
 }
 
-/// Creates a `DocSet` that iterator through the intersection of two `DocSet`s.
+/// Creates a `DocSet` that iterate through the union of two or more `DocSet`s.
 pub struct Union<TScorer, TScoreCombiner = DoNothingCombiner> {
     docsets: Vec<TScorer>,
     bitsets: Box<[TinySet; HORIZON_NUM_TINYBITSETS]>,
@@ -409,5 +409,51 @@ mod tests {
             vec![1, 2, 3, 7, 8, 9, 99, 100, 101, 500, 20000],
         );
     }
-
+}
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+
+    use crate::query::score_combiner::DoNothingCombiner;
+    use crate::query::{ConstScorer, Union, VecDocSet};
+    use crate::tests;
+    use crate::DocId;
+    use crate::DocSet;
+    use test::Bencher;
+
+    #[bench]
+    fn bench_union_3_high(bench: &mut Bencher) {
+        let union_docset: Vec<Vec<DocId>> = vec![
+            tests::sample_with_seed(100_000, 0.1, 0),
+            tests::sample_with_seed(100_000, 0.2, 1),
+        ];
+        bench.iter(|| {
+            let mut v = Union::<_, DoNothingCombiner>::from(
+                union_docset
+                    .iter()
+                    .map(|doc_ids| VecDocSet::from(doc_ids.clone()))
+                    .map(ConstScorer::new)
+                    .collect::<Vec<_>>(),
+            );
+            while v.advance() {}
+        });
+    }
+    #[bench]
+    fn bench_union_3_low(bench: &mut Bencher) {
+        let union_docset: Vec<Vec<DocId>> = vec![
+            tests::sample_with_seed(100_000, 0.01, 0),
+            tests::sample_with_seed(100_000, 0.05, 1),
+            tests::sample_with_seed(100_000, 0.001, 2),
+        ];
+        bench.iter(|| {
+            let mut v = Union::<_, DoNothingCombiner>::from(
+                union_docset
+                    .iter()
+                    .map(|doc_ids| VecDocSet::from(doc_ids.clone()))
+                    .map(ConstScorer::new)
+                    .collect::<Vec<_>>(),
+            );
+            while v.advance() {}
+        });
+    }
 }

src/query/vec_docset.rs

@@ -82,5 +82,4 @@ pub mod tests {
         }
         assert_eq!(postings.fill_buffer(&mut buffer[..]), 9);
     }
-
 }

src/schema/document.rs

@@ -178,5 +178,4 @@ mod tests {
         doc.add_text(text_field, "My title");
         assert_eq!(doc.field_values().len(), 1);
     }
-
 }

src/schema/field_type.rs

@@ -10,7 +10,7 @@ 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)]
+#[derive(Debug, PartialEq)]
 pub enum ValueParsingError {
     /// Encountered a numerical value that overflows or underflow its integer type.
     OverflowError(String),

src/schema/index_record_option.rs

@@ -29,22 +29,6 @@ pub enum IndexRecordOption {
 }
 
 impl IndexRecordOption {
-    /// Returns true iff the term frequency will be encoded.
-    pub fn is_termfreq_enabled(self) -> bool {
-        match self {
-            IndexRecordOption::WithFreqsAndPositions | IndexRecordOption::WithFreqs => true,
-            _ => false,
-        }
-    }
-
-    /// Returns true iff the term positions within the document are stored as well.
-    pub fn is_position_enabled(self) -> bool {
-        match self {
-            IndexRecordOption::WithFreqsAndPositions => true,
-            _ => false,
-        }
-    }
-
     /// Returns true iff this option includes encoding
     /// term frequencies.
     pub fn has_freq(self) -> bool {

src/schema/mod.rs

@@ -174,5 +174,4 @@ mod tests {
         assert!(!is_valid_field_name("シャボン玉"));
         assert!(is_valid_field_name("my_text_field"));
     }
-
 }

src/schema/schema.rs

@@ -246,6 +246,25 @@ 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();
@@ -282,28 +301,26 @@ impl Schema {
 
         let mut doc = Document::default();
         for (field_name, json_value) in json_obj.iter() {
-            match self.get_field(field_name) {
+            let field = self
-                Some(field) => {
+                .get_field(field_name)
-                    let field_entry = self.get_field_entry(field);
+                .ok_or_else(|| DocParsingError::NoSuchFieldInSchema(field_name.clone()))?;
-                    let field_type = field_entry.field_type();
+            let field_entry = self.get_field_entry(field);
-                    match *json_value {
+            let field_type = field_entry.field_type();
-                        JsonValue::Array(ref json_items) => {
+            match *json_value {
-                            for json_item in json_items {
+                JsonValue::Array(ref json_items) => {
-                                let value = field_type.value_from_json(json_item).map_err(|e| {
+                    for json_item in json_items {
-                                    DocParsingError::ValueError(field_name.clone(), e)
+                        let value = field_type
-                                })?;
+                            .value_from_json(json_item)
-                                doc.add(FieldValue::new(field, value));
+                            .map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
-                            }
+                        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)
@@ -360,7 +377,7 @@ impl<'de> Deserialize<'de> for Schema {
 
 /// Error that may happen when deserializing
 /// a document from JSON.
-#[derive(Debug, Fail)]
+#[derive(Debug, Fail, PartialEq)]
 pub enum DocParsingError {
     /// The payload given is not valid JSON.
     #[fail(display = "The provided string is not valid JSON")]
@@ -369,7 +386,10 @@ pub enum DocParsingError {
     #[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 json-document contains an unknown field: {:?}", _0)]
+    #[fail(
+        display = "The document contains a field that is not declared in the schema: {:?}",
+        _0
+    )]
     NoSuchFieldInSchema(String),
 }
 
@@ -381,6 +401,7 @@ mod tests {
     use crate::schema::*;
     use matches::{assert_matches, matches};
     use serde_json;
+    use std::collections::BTreeMap;
 
     #[test]
     pub fn is_indexed_test() {
@@ -495,6 +516,54 @@ 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

@@ -22,10 +22,10 @@ impl Term {
     /// Builds a term given a field, and a i64-value
     ///
     /// Assuming the term has a field id of 1, and a i64 value of 3234,
-    /// the Term will have 8 bytes.
+    /// the Term will have 12 bytes.
     ///
     /// The first four byte are dedicated to storing the field id as a u64.
-    /// The 4 following bytes are encoding the u64 value.
+    /// The 8 following bytes are encoding the u64 value.
     pub fn from_field_i64(field: Field, val: i64) -> Term {
         let val_u64: u64 = common::i64_to_u64(val);
         Term::from_field_u64(field, val_u64)
@@ -33,11 +33,11 @@ impl Term {
 
     /// Builds a term given a field, and a f64-value
     ///
-    /// Assuming the term has a field id of 1, and a u64 value of 3234,
+    /// Assuming the term has a field id of 1, and a f64 value of 1.5,
-    /// the Term will have 8 bytes. <= this is wrong
+    /// the Term will have 12 bytes.
     ///
     /// The first four byte are dedicated to storing the field id as a u64.
-    /// The 4 following bytes are encoding the u64 value.
+    /// The 8 following bytes are encoding the f64 as a u64 value.
     pub fn from_field_f64(field: Field, val: f64) -> Term {
         let val_u64: u64 = common::f64_to_u64(val);
         Term::from_field_u64(field, val_u64)
@@ -46,10 +46,10 @@ impl Term {
     /// Builds a term given a field, and a DateTime value
     ///
     /// Assuming the term has a field id of 1, and a timestamp i64 value of 3234,
-    /// the Term will have 8 bytes.
+    /// the Term will have 12 bytes.
     ///
     /// The first four byte are dedicated to storing the field id as a u64.
-    /// The 4 following bytes are encoding the DateTime as i64 timestamp value.
+    /// The 8 following bytes are encoding the DateTime as i64 timestamp value.
     pub fn from_field_date(field: Field, val: &DateTime) -> Term {
         let val_timestamp = val.timestamp();
         Term::from_field_i64(field, val_timestamp)
@@ -82,10 +82,10 @@ impl Term {
     /// Builds a term given a field, and a u64-value
     ///
     /// Assuming the term has a field id of 1, and a u64 value of 3234,
-    /// the Term will have 8 bytes.
+    /// the Term will have 12 bytes.
     ///
     /// The first four byte are dedicated to storing the field id as a u64.
-    /// The 4 following bytes are encoding the u64 value.
+    /// The 8 following bytes are encoding the u64 value.
     pub fn from_field_u64(field: Field, val: u64) -> Term {
         let mut term = Term(vec![0u8; INT_TERM_LEN]);
         term.set_field(field);
@@ -182,7 +182,7 @@ where
     ///
     /// # Panics
     /// ... or returns an invalid value
-    /// if the term is not a `i64` field.
+    /// if the term is not a `f64` field.
     pub fn get_f64(&self) -> f64 {
         common::u64_to_f64(BigEndian::read_u64(&self.0.as_ref()[4..]))
     }
@@ -224,7 +224,12 @@ where
 
 impl fmt::Debug for Term {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(f, "Term({:?})", &self.0[..])
+        write!(
+            f,
+            "Term(field={},bytes={:?})",
+            self.field().0,
+            self.value_bytes()
+        )
     }
 }
 

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: &dyn BoxedTokenizer,
+    tokenizer: &BoxedTokenizer,
     text: &'a str,
     terms: &BTreeMap<String, f32>,
     max_num_chars: usize,
@@ -150,7 +150,6 @@ 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 {
@@ -214,11 +213,9 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
 /// # Example
 ///
 /// ```rust
-/// # #[macro_use]
-/// # extern crate tantivy;
-/// # use tantivy::Index;
-/// # use tantivy::schema::{Schema, TEXT};
 /// # use tantivy::query::QueryParser;
+/// # use tantivy::schema::{Schema, TEXT};
+/// # use tantivy::{doc, Index};
 /// use tantivy::SnippetGenerator;
 ///
 /// # fn main() -> tantivy::Result<()> {
@@ -254,7 +251,7 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
 /// ```
 pub struct SnippetGenerator {
     terms_text: BTreeMap<String, f32>,
-    tokenizer: Box<dyn BoxedTokenizer>,
+    tokenizer: BoxedTokenizer,
     field: Field,
     max_num_chars: usize,
 }
@@ -316,12 +313,8 @@ impl SnippetGenerator {
 
     /// Generates a snippet for the given text.
     pub fn snippet(&self, text: &str) -> Snippet {
-        let fragment_candidates = search_fragments(
+        let fragment_candidates =
-            &*self.tokenizer,
+            search_fragments(&self.tokenizer, &text, &self.terms_text, self.max_num_chars);
-            &text,
-            &self.terms_text,
-            self.max_num_chars,
-        );
         select_best_fragment_combination(&fragment_candidates[..], &text)
     }
 }
@@ -331,7 +324,7 @@ 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::{box_tokenizer, SimpleTokenizer};
+    use crate::tokenizer::SimpleTokenizer;
     use crate::Index;
     use crate::SnippetGenerator;
     use maplit::btreemap;
@@ -355,12 +348,12 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
         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];
@@ -382,13 +375,13 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_scored_fragment() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
         {
             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);
@@ -397,13 +390,13 @@ 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 = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
         {
             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];
@@ -417,14 +410,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_in_second_fragment() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         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);
         {
@@ -441,14 +434,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_term_at_the_end_of_fragment() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         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);
         {
@@ -465,7 +458,7 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_second_fragment_has_the_highest_score() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         let text = "a b c d e f g";
 
@@ -473,7 +466,7 @@ 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);
         {
@@ -490,14 +483,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_term_not_in_text() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         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);
 
@@ -508,12 +501,12 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_no_terms() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         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/store/mod.rs

@@ -120,17 +120,16 @@ pub mod tests {
             );
         }
     }
-
 }
 
 #[cfg(all(test, feature = "unstable"))]
 mod bench {
 
     use super::tests::write_lorem_ipsum_store;
-    use directory::Directory;
+    use crate::directory::Directory;
-    use directory::RAMDirectory;
+    use crate::directory::RAMDirectory;
+    use crate::store::StoreReader;
     use std::path::Path;
-    use store::StoreReader;
     use test::Bencher;
 
     #[bench]

src/store/skiplist/mod.rs

@@ -165,5 +165,4 @@ mod tests {
         assert_eq!(output.len(), 65);
         assert_eq!(output[0], 128u8 + 3u8);
     }
-
 }

src/store/writer.rs

@@ -3,6 +3,7 @@ use super::skiplist::SkipListBuilder;
 use super::StoreReader;
 use crate::common::CountingWriter;
 use crate::common::{BinarySerializable, VInt};
+use crate::directory::TerminatingWrite;
 use crate::directory::WritePtr;
 use crate::schema::Document;
 use crate::DocId;
@@ -109,6 +110,6 @@ impl StoreWriter {
         self.offset_index_writer.write(&mut self.writer)?;
         header_offset.serialize(&mut self.writer)?;
         self.doc.serialize(&mut self.writer)?;
-        self.writer.flush()
+        self.writer.terminate()
     }
 }

src/termdict/term_info_store.rs

@@ -328,5 +328,4 @@ mod tests {
             assert_eq!(term_info_store.get(i as u64), term_infos[i]);
         }
     }
-
 }

src/tokenizer/alphanum_only.rs

@@ -1,6 +1,5 @@
 //! # Example
-//! ```
+//! ```rust
-//! extern crate tantivy;
 //! use tantivy::tokenizer::*;
 //!
 //! # fn main() {

src/tokenizer/lower_caser.rs

@@ -98,10 +98,6 @@ mod tests {
     #[test]
     fn test_lowercaser() {
         assert_eq!(lowercase_helper("Tree"), vec!["tree".to_string()]);
-        assert_eq!(
+        assert_eq!(lowercase_helper("Русский"), vec!["русский".to_string()]);
-            lowercase_helper("Русский"),
-            vec!["русский".to_string()]
-        );
     }
-
 }

src/tokenizer/mod.rs

@@ -4,8 +4,7 @@
 //! You must define in your schema which tokenizer should be used for
 //! each of your fields :
 //!
-//! ```
+//! ```rust
-//! extern crate tantivy;
 //! use tantivy::schema::*;
 //!
 //! # fn main() {
@@ -65,8 +64,6 @@
 //! For instance, the `en_stem` is defined as follows.
 //!
 //! ```rust
-//! # extern crate tantivy;
-//!
 //! use tantivy::tokenizer::*;
 //!
 //! # fn main() {
@@ -80,8 +77,7 @@
 //! Once your tokenizer is defined, you need to
 //! register it with a name in your index's [`TokenizerManager`](./struct.TokenizerManager.html).
 //!
-//! ```
+//! ```rust
-//! # extern crate tantivy;
 //! # use tantivy::schema::Schema;
 //! # use tantivy::tokenizer::*;
 //! # use tantivy::Index;
@@ -101,8 +97,7 @@
 //!
 //! # Example
 //!
-//! ```
+//! ```rust
-//! extern crate tantivy;
 //! use tantivy::schema::{Schema, IndexRecordOption, TextOptions, TextFieldIndexing};
 //! use tantivy::tokenizer::*;
 //! use tantivy::Index;
@@ -155,7 +150,6 @@ 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 use self::tokenizer::{Token, TokenFilter, TokenStream, Tokenizer};
@@ -287,5 +281,4 @@ pub mod tests {
             assert!(tokens.is_empty());
         }
     }
-
 }

src/tokenizer/ngram_tokenizer.rs

@@ -29,8 +29,7 @@ use super::{Token, TokenStream, Tokenizer};
 ///
 /// # Example
 ///
-/// ```
+/// ```rust
-/// # extern crate tantivy;
 /// use tantivy::tokenizer::*;
 /// # fn main() {
 /// let tokenizer = NgramTokenizer::new(2, 3, false);
@@ -461,5 +460,4 @@ mod tests {
         assert_eq!(it.next(), Some((8, 9)));
         assert_eq!(it.next(), None);
     }
-
 }

src/tokenizer/remove_long.rs

@@ -1,6 +1,5 @@
 //! # Example
-//! ```
+//! ```rust
-//! extern crate tantivy;
 //! use tantivy::tokenizer::*;
 //!
 //! # fn main() {

src/tokenizer/stop_word_filter.rs

@@ -1,6 +1,5 @@
 //! # Example
-//! ```
+//! ```rust
-//! extern crate tantivy;
 //! use tantivy::tokenizer::*;
 //!
 //! # fn main() {

src/tokenizer/token_stream_chain.rs

@@ -97,5 +97,4 @@ mod tests {
 
         assert!(!token_chain.advance());
     }
-
 }

src/tokenizer/tokenizer.rs

@@ -56,8 +56,6 @@ pub trait Tokenizer<'a>: Sized + Clone {
     /// # Example
     ///
     /// ```rust
-    /// # extern crate tantivy;
-    ///
     /// use tantivy::tokenizer::*;
     ///
     /// # fn main() {
@@ -80,7 +78,7 @@ pub trait Tokenizer<'a>: Sized + Clone {
 }
 
 /// A boxed tokenizer
-pub trait BoxedTokenizer: Send + Sync {
+trait BoxedTokenizerTrait: Send + Sync {
     /// Tokenize a `&str`
     fn token_stream<'a>(&self, text: &'a str) -> Box<dyn TokenStream + 'a>;
 
@@ -92,7 +90,41 @@ pub trait BoxedTokenizer: 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) -> Box<dyn BoxedTokenizer>;
+    fn boxed_clone(&self) -> 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)]
@@ -100,7 +132,7 @@ struct BoxableTokenizer<A>(A)
 where
     A: for<'a> Tokenizer<'a> + Send + Sync;
 
-impl<A> BoxedTokenizer for BoxableTokenizer<A>
+impl<A> BoxedTokenizerTrait for BoxableTokenizer<A>
 where
     A: 'static + Send + Sync + for<'a> Tokenizer<'a>,
 {
@@ -125,18 +157,11 @@ where
         }
     }
 
-    fn boxed_clone(&self) -> Box<dyn BoxedTokenizer> {
+    fn boxed_clone(&self) -> BoxedTokenizer {
-        Box::new(self.clone())
+        self.0.clone().into()
     }
 }
 
-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();
@@ -161,7 +186,6 @@ impl<'b> TokenStream for Box<dyn TokenStream + 'b> {
 /// # Example
 ///
 /// ```
-/// extern crate tantivy;
 /// use tantivy::tokenizer::*;
 ///
 /// # fn main() {
@@ -203,7 +227,6 @@ pub trait TokenStream {
     /// and `.token()`.
     ///
     /// ```
-    /// # extern crate tantivy;
     /// # use tantivy::tokenizer::*;
     /// #
     /// # fn main() {