Added method to convert named doc to doc

CHANGELOG.md

@@ -2,10 +2,6 @@ Tantivy 0.11.0
 =====================
 
 - Added f64 field. Internally reuse u64 code the same way i64 does (@fdb-hiroshima)
-- Various bugfixes in the query parser.
-    - Better handling of hyphens in query parser. (#609)
-    - Better handling of whitespaces.
-
 
 Tantivy 0.10.1
 =====================

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy"
-version = "0.11.0"
+version = "0.10.1"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
@@ -25,6 +25,7 @@ atomicwrites = {version="0.2.2", optional=true}
 tempfile = "3.0"
 log = "0.4"
 combine = ">=3.6.0,<4.0.0"
+tempdir = "0.3"
 serde = "1.0"
 serde_derive = "1.0"
 serde_json = "1.0"
@@ -35,7 +36,7 @@ levenshtein_automata = {version="0.1", features=["fst_automaton"]}
 notify = {version="4", optional=true}
 bit-set = "0.5"
 uuid = { version = "0.7.2", features = ["v4", "serde"] }
-crossbeam = "0.7"
+crossbeam = "0.5"
 futures = "0.1"
 futures-cpupool = "0.1"
 owning_ref = "0.4"
@@ -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
@@ -75,7 +75,6 @@ overflow-checks = true
 
 [features]
 default = ["mmap"]
-forbench = []
 mmap = ["atomicwrites", "fs2", "memmap", "notify"]
 lz4-compression = ["lz4"]
 failpoints = ["fail/failpoints"]
@@ -88,6 +87,7 @@ travis-ci = { repository = "tantivy-search/tantivy" }
 [dev-dependencies.fail]
 features = ["failpoints"]
 
+
 # Following the "fail" crate best practises, we isolate
 # tests that define specific behavior in fail check points
 # in a different binary.
@@ -98,16 +98,4 @@ features = ["failpoints"]
 [[test]]
 name = "failpoints"
 path = "tests/failpoints/mod.rs"
-required-features = ["fail/failpoints"]
+required-features = ["fail/failpoints"]
-
-[profile.bench]
-lto = true
-
-[[bench]]
-name = "vint"
-harness = false
-
-
-[[bench]]
-name = "fastfield"
-harness = false

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);

examples/basic_search.rs

@@ -19,12 +19,12 @@ use tantivy::query::QueryParser;
 use tantivy::schema::*;
 use tantivy::Index;
 use tantivy::ReloadPolicy;
-use tempfile::TempDir;
+use tempdir::TempDir;
 
 fn main() -> tantivy::Result<()> {
     // Let's create a temporary directory for the
     // sake of this example
-    let index_path = TempDir::new()?;
+    let index_path = TempDir::new("tantivy_example_dir")?;
 
     // # Defining the schema
     //

examples/faceted_search.rs

@@ -18,12 +18,11 @@ use tantivy::collector::FacetCollector;
 use tantivy::query::AllQuery;
 use tantivy::schema::*;
 use tantivy::Index;
-use tempfile::TempDir;
 
 fn main() -> tantivy::Result<()> {
     // Let's create a temporary directory for the
     // sake of this example
-    let index_path = TempDir::new()?;
+    let index_path = TempDir::new("tantivy_facet_example_dir")?;
     let mut schema_builder = Schema::builder();
 
     schema_builder.add_text_field("name", TEXT | STORED);
@@ -75,3 +74,5 @@ fn main() -> tantivy::Result<()> {
 
     Ok(())
 }
+
+use tempdir::TempDir;

examples/snippet.rs

@@ -14,12 +14,12 @@ use tantivy::query::QueryParser;
 use tantivy::schema::*;
 use tantivy::Index;
 use tantivy::{Snippet, SnippetGenerator};
-use tempfile::TempDir;
+use tempdir::TempDir;
 
 fn main() -> tantivy::Result<()> {
     // Let's create a temporary directory for the
     // sake of this example
-    let index_path = TempDir::new()?;
+    let index_path = TempDir::new("tantivy_example_dir")?;
 
     // # Defining the schema
     let mut schema_builder = Schema::builder();

run-bench.rs

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

src/collector/top_score_collector.rs

@@ -591,7 +591,7 @@ mod tests {
         query_field: Field,
         schema: Schema,
         mut doc_adder: impl FnMut(&mut IndexWriter) -> (),
-    ) -> (Index, Box<dyn Query>) {
+    ) -> (Index, Box<Query>) {
         let index = Index::create_in_ram(schema);
 
         let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();

src/common/bitpacker.rs

@@ -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/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};
@@ -124,24 +124,26 @@ pub fn f64_to_u64(val: f64) -> u64 {
 /// Reverse the mapping given by [`i64_to_u64`](./fn.i64_to_u64.html).
 #[inline(always)]
 pub fn u64_to_f64(val: u64) -> f64 {
-    f64::from_bits(if val & HIGHEST_BIT != 0 {
+    f64::from_bits(
-        val ^ HIGHEST_BIT
+        if val & HIGHEST_BIT != 0 {
-    } else {
+            val ^ HIGHEST_BIT
-        !val
+        } else {
-    })
+            !val
+        }
+    )
 }
 
 #[cfg(test)]
 pub(crate) mod test {
 
     pub use super::serialize::test::fixed_size_test;
-    use super::{compute_num_bits, f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
+    use super::{compute_num_bits, i64_to_u64, u64_to_i64, f64_to_u64, u64_to_f64};
     use std::f64;
 
     fn test_i64_converter_helper(val: i64) {
         assert_eq!(u64_to_i64(i64_to_u64(val)), val);
     }
-
+    
     fn test_f64_converter_helper(val: f64) {
         assert_eq!(u64_to_f64(f64_to_u64(val)), val);
     }
@@ -170,8 +172,7 @@ pub(crate) mod test {
 
     #[test]
     fn test_f64_order() {
-        assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY))
+        assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY)).contains(&f64_to_u64(f64::NAN))); //nan is not a number
-            .contains(&f64_to_u64(f64::NAN))); //nan is not a number
         assert!(f64_to_u64(1.5) > f64_to_u64(1.0)); //same exponent, different mantissa
         assert!(f64_to_u64(2.0) > f64_to_u64(1.0)); //same mantissa, different exponent
         assert!(f64_to_u64(2.0) > f64_to_u64(1.5)); //different exponent and mantissa

src/core/index.rs

@@ -459,13 +459,13 @@ mod tests {
 
         use super::*;
         use std::path::PathBuf;
-        use tempfile::TempDir;
+        use tempdir::TempDir;
 
         #[test]
         fn test_index_on_commit_reload_policy_mmap() {
             let schema = throw_away_schema();
             let field = schema.get_field("num_likes").unwrap();
-            let tempdir = TempDir::new().unwrap();
+            let tempdir = TempDir::new("index").unwrap();
             let tempdir_path = PathBuf::from(tempdir.path());
             let index = Index::create_in_dir(&tempdir_path, schema).unwrap();
             let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
@@ -504,7 +504,7 @@ mod tests {
         fn test_index_on_commit_reload_policy_different_directories() {
             let schema = throw_away_schema();
             let field = schema.get_field("num_likes").unwrap();
-            let tempdir = TempDir::new().unwrap();
+            let tempdir = TempDir::new("index").unwrap();
             let tempdir_path = PathBuf::from(tempdir.path());
             let write_index = Index::create_in_dir(&tempdir_path, schema).unwrap();
             let read_index = Index::open_in_dir(&tempdir_path).unwrap();

src/directory/directory.rs

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

src/directory/managed_directory.rs

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

src/directory/mmap_directory.rs

@@ -36,7 +36,7 @@ use std::sync::Mutex;
 use std::sync::RwLock;
 use std::sync::Weak;
 use std::thread;
-use tempfile::TempDir;
+use tempdir::TempDir;
 
 /// Create a default io error given a string.
 pub(crate) fn make_io_err(msg: String) -> io::Error {
@@ -294,7 +294,7 @@ impl MmapDirectory {
     /// This is mostly useful to test the MmapDirectory itself.
     /// For your unit tests, prefer the RAMDirectory.
     pub fn create_from_tempdir() -> Result<MmapDirectory, OpenDirectoryError> {
-        let tempdir = TempDir::new().map_err(OpenDirectoryError::IoError)?;
+        let tempdir = TempDir::new("index").map_err(OpenDirectoryError::IoError)?;
         let tempdir_path = PathBuf::from(tempdir.path());
         MmapDirectory::new(tempdir_path, Some(tempdir))
     }
@@ -642,7 +642,7 @@ mod tests {
     fn test_watch_wrapper() {
         let counter: Arc<AtomicUsize> = Default::default();
         let counter_clone = counter.clone();
-        let tmp_dir = tempfile::TempDir::new().unwrap();
+        let tmp_dir: TempDir = tempdir::TempDir::new("test_watch_wrapper").unwrap();
         let tmp_dirpath = tmp_dir.path().to_owned();
         let mut watch_wrapper = WatcherWrapper::new(&tmp_dirpath).unwrap();
         let tmp_file = tmp_dirpath.join("coucou");

src/directory/ram_directory.rs

@@ -177,7 +177,7 @@ impl Directory for RAMDirectory {
     fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
         fail_point!("RAMDirectory::atomic_write", |msg| Err(io::Error::new(
             io::ErrorKind::Other,
-            msg.unwrap_or_else(|| "Undefined".to_string())
+            msg.unwrap_or("Undefined".to_string())
         )));
         let path_buf = PathBuf::from(path);
 

src/fastfield/mod.rs

@@ -431,3 +431,111 @@ mod tests {
     }
 
 }
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+    use super::tests::FIELD;
+    use super::tests::{generate_permutation, SCHEMA};
+    use super::*;
+    use common::CompositeFile;
+    use directory::{Directory, RAMDirectory, WritePtr};
+    use 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/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

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

src/indexer/index_writer.rs

@@ -761,6 +761,7 @@ mod tests {
     use crate::Index;
     use crate::ReloadPolicy;
     use crate::Term;
+    use fail;
 
     #[test]
     fn test_operations_group() {

src/lib.rs

@@ -1,9 +1,9 @@
 #![doc(html_logo_url = "http://fulmicoton.com/tantivy-logo/tantivy-logo.png")]
-#![recursion_limit = "100"]
 #![cfg_attr(all(feature = "unstable", test), feature(test))]
 #![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))]
 #![doc(test(attr(allow(unused_variables), deny(warnings))))]
 #![warn(missing_docs)]
+#![recursion_limit = "80"]
 
 //! # `tantivy`
 //!
@@ -12,7 +12,7 @@
 //!
 //! ```rust
 
-//! # extern crate tempfile;
+//! # extern crate tempdir;
 //! #
 //! #[macro_use]
 //! extern crate tantivy;
@@ -20,7 +20,7 @@
 //! // ...
 //!
 //! # use std::path::Path;
-//! # use tempfile::TempDir;
+//! # use tempdir::TempDir;
 //! # use tantivy::Index;
 //! # use tantivy::schema::*;
 //! # use tantivy::{Score, DocAddress};
@@ -30,7 +30,7 @@
 //! # fn main() {
 //! #     // Let's create a temporary directory for the
 //! #     // sake of this example
-//! #     if let Ok(dir) = TempDir::new() {
+//! #     if let Ok(dir) = TempDir::new("tantivy_example_dir") {
 //! #         run_example(dir.path()).unwrap();
 //! #         dir.close().unwrap();
 //! #     }
@@ -249,6 +249,7 @@ 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 +895,3 @@ 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/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 +268,78 @@ pub mod tests {
             }
         }
     }
+}
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+
+    use super::*;
+    use rand::SeedableRng;
+    use rand::{Rng, XorShiftRng};
+    use test::Bencher;
+
+    fn generate_array_with_seed(n: usize, ratio: f64, seed_val: u8) -> Vec<u32> {
+        let seed: &[u8; 16] = &[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, seed_val];
+        let mut rng: XorShiftRng = XorShiftRng::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
 ///

src/query/bitset/mod.rs

@@ -218,3 +218,49 @@ mod tests {
     }
 
 }
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+
+    use super::BitSet;
+    use super::BitSetDocSet;
+    use test;
+    use tests;
+    use DocSet;
+
+    #[bench]
+    fn bench_bitset_1pct_insert(b: &mut test::Bencher) {
+        use tests;
+        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) {
+        use tests;
+        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/fuzzy_query.rs

@@ -1,4 +1,3 @@
-use crate::error::TantivyError::InvalidArgument;
 use crate::query::{AutomatonWeight, Query, Weight};
 use crate::schema::Term;
 use crate::Result;
@@ -6,16 +5,11 @@ use crate::Searcher;
 use levenshtein_automata::{LevenshteinAutomatonBuilder, DFA};
 use once_cell::sync::Lazy;
 use std::collections::HashMap;
-use std::ops::Range;
-
-/// A range of Levenshtein distances that we will build DFAs for our terms
-/// The computation is exponential, so best keep it to low single digits
-const VALID_LEVENSHTEIN_DISTANCE_RANGE: Range<u8> = (0..3);
 
 static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Lazy::new(|| {
     let mut lev_builder_cache = HashMap::new();
     // TODO make population lazy on a `(distance, val)` basis
-    for distance in VALID_LEVENSHTEIN_DISTANCE_RANGE {
+    for distance in 0..3 {
         for &transposition in &[false, true] {
             let lev_automaton_builder = LevenshteinAutomatonBuilder::new(distance, transposition);
             lev_builder_cache.insert((distance, transposition), lev_automaton_builder);
@@ -106,18 +100,10 @@ impl FuzzyTermQuery {
     }
 
     fn specialized_weight(&self) -> Result<AutomatonWeight<DFA>> {
-        // LEV_BUILDER is a HashMap, whose `get` method returns an Option
+        let automaton = LEV_BUILDER.get(&(self.distance, false))
-        match LEV_BUILDER.get(&(self.distance, false)) {
+            .unwrap() // TODO return an error
-            // Unwrap the option and build the Ok(AutomatonWeight)
+            .build_dfa(self.term.text());
-            Some(automaton_builder) => {
+        Ok(AutomatonWeight::new(self.term.field(), automaton))
-                let automaton = automaton_builder.build_dfa(self.term.text());
-                Ok(AutomatonWeight::new(self.term.field(), automaton))
-            }
-            None => Err(InvalidArgument(format!(
-                "Levenshtein distance of {} is not allowed. Choose a value in the {:?} range",
-                self.distance, VALID_LEVENSHTEIN_DISTANCE_RANGE
-            ))),
-        }
     }
 }
 

src/query/query_parser/logical_ast.rs

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

src/query/query_parser/query_grammar.rs

@@ -1,3 +1,4 @@
+use super::query_grammar;
 use super::user_input_ast::*;
 use crate::query::occur::Occur;
 use crate::query::query_parser::user_input_ast::UserInputBound;
@@ -12,25 +13,22 @@ parser! {
         (
             letter(),
             many(satisfy(|c: char| c.is_alphanumeric() || c == '_')),
-        ).skip(char(':')).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
+        ).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
     }
 }
 
 parser! {
     fn word[I]()(I) -> String
     where [I: Stream<Item = char>] {
-        (
+        many1(satisfy(|c: char| c.is_alphanumeric() || c=='.'))
-            satisfy(|c: char| !c.is_whitespace() && !['-', '`', ':', '{', '}', '"', '[', ']', '(',')'].contains(&c) ),
+               .and_then(|s: String| {
-            many(satisfy(|c: char| !c.is_whitespace() && ![':', '{', '}', '"', '[', ']', '(',')'].contains(&c)))
+                   match s.as_str() {
-        )
+                     "OR" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
-        .map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
+                     "AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
-        .and_then(|s: String|
+                     "NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
-           match s.as_str() {
+                     _ => Ok(s)
-             "OR" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
+                   }
-             "AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
+               })
-             "NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
-             _ => Ok(s)
-           })
     }
 }
 
@@ -39,13 +37,12 @@ parser! {
     where [I: Stream<Item = char>]
     {
         let term_val = || {
-            let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
+            let phrase = (char('"'), many1(satisfy(|c| c != '"')), char('"')).map(|(_, s, _)| s);
             phrase.or(word())
         };
         let term_val_with_field = negative_number().or(term_val());
         let term_query =
-            (field(), term_val_with_field)
+            (field(), char(':'), term_val_with_field).map(|(field_name, _, phrase)| UserInputLiteral {
-            .map(|(field_name, phrase)| UserInputLiteral {
                 field_name: Some(field_name),
                 phrase,
             });
@@ -63,15 +60,8 @@ parser! {
     fn negative_number[I]()(I) -> String
     where [I: Stream<Item = char>]
     {
-        (char('-'), many1(satisfy(char::is_numeric)),
+            (char('-'), many1(satisfy(char::is_numeric)))
-         optional((char('.'), many1(satisfy(char::is_numeric)))))
+                .map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
-            .map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
-                if let Some(('.', s3)) = s3 {
-                    format!("{}{}.{}", s1, s2, s3)
-                } else {
-                    format!("{}{}", s1, s2)
-                }
-            })
     }
 }
 
@@ -85,23 +75,27 @@ parser! {
 parser! {
     fn range[I]()(I) -> UserInputLeaf
     where [I: Stream<Item = char>] {
-        let range_term_val = || {
+        let term_val = || {
-            word().or(negative_number()).or(char('*').with(value("*".to_string())))
+            word().or(negative_number()).or(char('*').map(|_| "*".to_string()))
+        };
+        let lower_bound = {
+            let excl = (char('{'), term_val()).map(|(_, w)| UserInputBound::Exclusive(w));
+            let incl = (char('['), term_val()).map(|(_, w)| UserInputBound::Inclusive(w));
+            attempt(excl).or(incl)
+        };
+        let upper_bound = {
+            let excl = (term_val(), char('}')).map(|(w, _)| UserInputBound::Exclusive(w));
+            let incl = (term_val(), char(']')).map(|(w, _)| UserInputBound::Inclusive(w));
+            attempt(excl).or(incl)
         };
-        let lower_bound = (one_of("{[".chars()), range_term_val())
-            .map(|(boundary_char, lower_bound): (char, String)|
-                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) }
-                else { UserInputBound::Inclusive(higher_bound) });
         (
-            optional(field()),
+            optional((field(), char(':')).map(|x| x.0)),
-            lower_bound
+            lower_bound,
-            .skip((spaces(), string("TO"), spaces())),
+            spaces(),
+            string("TO"),
+            spaces(),
             upper_bound,
-        ).map(|(field, lower, upper)| UserInputLeaf::Range {
+        ).map(|(field, lower, _, _, _, upper)| UserInputLeaf::Range {
                 field,
                 lower,
                 upper
@@ -109,28 +103,25 @@ parser! {
     }
 }
 
-fn negate(expr: UserInputAST) -> UserInputAST {
-    expr.unary(Occur::MustNot)
-}
-
-fn must(expr: UserInputAST) -> UserInputAST {
-    expr.unary(Occur::Must)
-}
-
 parser! {
     fn leaf[I]()(I) -> UserInputAST
     where [I: Stream<Item = char>] {
-            char('-').with(leaf()).map(negate)
+         (char('-'), leaf()).map(|(_, expr)| expr.unary(Occur::MustNot) )
-        .or(char('+').with(leaf()).map(must))
+        .or((char('+'), leaf()).map(|(_, expr)| expr.unary(Occur::Must) ))
-        .or(char('(').with(ast()).skip(char(')')))
+        .or((char('('), parse_to_ast(), char(')')).map(|(_, expr, _)| expr))
-        .or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All)))
+        .or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All) ))
-        .or(attempt(string("NOT").skip(spaces1()).with(leaf()).map(negate)))
+        .or(attempt(
-        .or(attempt(range().map(UserInputAST::from)))
+            (string("NOT"), spaces1(), leaf()).map(|(_, _, expr)| expr.unary(Occur::MustNot))
-        .or(literal().map(UserInputAST::from))
+            )
+         )
+        .or(attempt(
+            range().map(UserInputAST::from)
+            )
+        )
+        .or(literal().map(|leaf| UserInputAST::Leaf(Box::new(leaf))))
     }
 }
 
-#[derive(Clone, Copy)]
 enum BinaryOperand {
     Or,
     And,
@@ -138,62 +129,84 @@ enum BinaryOperand {
 
 parser! {
     fn binary_operand[I]()(I) -> BinaryOperand
-    where [I: Stream<Item = char>]
+    where [I: Stream<Item = char>] {
-    {
+        (spaces1(),
-       string("AND").with(value(BinaryOperand::And))
+         (
-       .or(string("OR").with(value(BinaryOperand::Or)))
+            string("AND").map(|_| BinaryOperand::And)
+           .or(string("OR").map(|_| BinaryOperand::Or))
+         ),
+         spaces1()).map(|(_, op,_)| op)
     }
 }
 
-fn aggregate_binary_expressions(
+enum Element {
-    left: UserInputAST,
+    SingleEl(UserInputAST),
-    others: Vec<(BinaryOperand, UserInputAST)>,
+    NormalDisjunctive(Vec<Vec<UserInputAST>>),
-) -> UserInputAST {
+}
-    let mut dnf: Vec<Vec<UserInputAST>> = vec![vec![left]];
+
-    for (operator, operand_ast) in others {
+impl Element {
-        match operator {
+    pub fn into_dnf(self) -> Vec<Vec<UserInputAST>> {
-            BinaryOperand::And => {
+        match self {
-                if let Some(last) = dnf.last_mut() {
+            Element::NormalDisjunctive(conjunctions) => conjunctions,
-                    last.push(operand_ast);
+            Element::SingleEl(el) => vec![vec![el]],
-                }
-            }
-            BinaryOperand::Or => {
-                dnf.push(vec![operand_ast]);
-            }
         }
     }
-    if dnf.len() == 1 {
-        UserInputAST::and(dnf.into_iter().next().unwrap()) //< safe
-    } else {
-        let conjunctions = dnf.into_iter().map(UserInputAST::and).collect();
-        UserInputAST::or(conjunctions)
-    }
-}
-
-parser! {
-    pub fn ast[I]()(I) -> UserInputAST
-    where [I: Stream<Item = char>]
-    {
-        let operand_leaf = (binary_operand().skip(spaces()), leaf().skip(spaces()));
-        let boolean_expr = (leaf().skip(spaces().silent()), many1(operand_leaf)).map(
-            |(left, right)| aggregate_binary_expressions(left,right));
-        let whitespace_separated_leaves = many1(leaf().skip(spaces().silent()))
-        .map(|subqueries: Vec<UserInputAST>|
-            if subqueries.len() == 1 {
-                subqueries.into_iter().next().unwrap()
-            } else {
-                UserInputAST::Clause(subqueries.into_iter().collect())
-            });
-        let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
-        spaces().with(expr).skip(spaces())
-    }
 }
 
 parser! {
     pub fn parse_to_ast[I]()(I) -> UserInputAST
     where [I: Stream<Item = char>]
     {
-        spaces().with(optional(ast()).skip(eof())).map(|opt_ast| opt_ast.unwrap_or_else(UserInputAST::empty_query))
+        (
+            attempt(
+                chainl1(
+                    leaf().map(Element::SingleEl),
+                    binary_operand().map(|op: BinaryOperand|
+                        move |left: Element, right: Element| {
+                            let mut dnf = left.into_dnf();
+                            if let Element::SingleEl(el) = right {
+                                match op {
+                                    BinaryOperand::And => {
+                                        if let Some(last) = dnf.last_mut() {
+                                            last.push(el);
+                                        }
+                                    }
+                                    BinaryOperand::Or => {
+                                        dnf.push(vec!(el));
+                                    }
+                                }
+                            } else {
+                                unreachable!("Please report.")
+                            }
+                            Element::NormalDisjunctive(dnf)
+                        }
+                    )
+                )
+                .map(query_grammar::Element::into_dnf)
+                .map(|fnd| {
+                    if fnd.len() == 1 {
+                        UserInputAST::and(fnd.into_iter().next().unwrap()) //< safe
+                    } else {
+                        let conjunctions = fnd
+                        .into_iter()
+                        .map(UserInputAST::and)
+                        .collect();
+                        UserInputAST::or(conjunctions)
+                    }
+                })
+            )
+            .or(
+                sep_by(leaf(), spaces())
+                .map(|subqueries: Vec<UserInputAST>| {
+                    if subqueries.len() == 1 {
+                        subqueries.into_iter().next().unwrap()
+                    } else {
+                        UserInputAST::Clause(subqueries.into_iter().collect())
+                    }
+                })
+            )
+        )
+
     }
 }
 
@@ -212,18 +225,6 @@ mod test {
         assert!(parse_to_ast().parse(query).is_err());
     }
 
-    #[test]
-    fn test_parse_empty_to_ast() {
-        test_parse_query_to_ast_helper("", "<emptyclause>");
-    }
-
-    #[test]
-    fn test_parse_query_to_ast_hyphen() {
-        test_parse_query_to_ast_helper("\"www-form-encoded\"", "\"www-form-encoded\"");
-        test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
-        test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
-    }
-
     #[test]
     fn test_parse_query_to_ast_not_op() {
         assert_eq!(
@@ -258,24 +259,8 @@ mod test {
         );
     }
 
-    #[test]
-    fn test_parse_query_to_triming_spaces() {
-        test_parse_query_to_ast_helper("   abc", "\"abc\"");
-        test_parse_query_to_ast_helper("abc ", "\"abc\"");
-        test_parse_query_to_ast_helper("(  a OR abc)", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("(a  OR abc)", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("(a OR  abc)", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("a OR abc ", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("(a OR abc )", "(?(\"a\") ?(\"abc\"))");
-        test_parse_query_to_ast_helper("(a OR  abc) ", "(?(\"a\") ?(\"abc\"))");
-    }
-
     #[test]
     fn test_parse_query_to_ast() {
-        test_parse_query_to_ast_helper("abc", "\"abc\"");
-        test_parse_query_to_ast_helper("a b", "(\"a\" \"b\")");
-        test_parse_query_to_ast_helper("+(a b)", "+((\"a\" \"b\"))");
-        test_parse_query_to_ast_helper("+d", "+(\"d\")");
         test_parse_query_to_ast_helper("+(a b) +d", "(+((\"a\" \"b\")) +(\"d\"))");
         test_parse_query_to_ast_helper("(+a +b) d", "((+(\"a\") +(\"b\")) \"d\")");
         test_parse_query_to_ast_helper("(+a)", "+(\"a\")");

src/query/query_parser/query_parser.rs

@@ -690,7 +690,7 @@ mod test {
     }
 
     #[test]
-    pub fn test_parse_query_to_ast_single_term() {
+    pub fn test_parse_query_to_ast_disjunction() {
         test_parse_query_to_logical_ast_helper(
             "title:toto",
             "Term([0, 0, 0, 0, 116, 111, 116, 111])",
@@ -714,10 +714,6 @@ mod test {
                 .unwrap(),
             QueryParserError::AllButQueryForbidden
         );
-    }
-
-    #[test]
-    pub fn test_parse_query_to_ast_two_terms() {
         test_parse_query_to_logical_ast_helper(
             "title:a b",
             "(Term([0, 0, 0, 0, 97]) (Term([0, 0, 0, 0, 98]) \
@@ -730,10 +726,6 @@ mod test {
              (1, Term([0, 0, 0, 0, 98]))]\"",
             false,
         );
-    }
-
-    #[test]
-    pub fn test_parse_query_to_ast_ranges() {
         test_parse_query_to_logical_ast_helper(
             "title:[a TO b]",
             "(Included(Term([0, 0, 0, 0, 97])) TO \
@@ -765,19 +757,6 @@ mod test {
             "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO Unbounded)",
             false,
         );
-        test_parse_query_to_logical_ast_helper(
-            "signed:{-5 TO 3}",
-            "(Excluded(Term([0, 0, 0, 2, 127, 255, 255, 255, 255, 255, 255, 251])) TO \
-            Excluded(Term([0, 0, 0, 2, 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([0, 0, 0, 10, 191, 248, 0, 0, 0, 0, 0, 0])))",
-            false,
-        );
-
         test_parse_query_to_logical_ast_helper("*", "*", false);
     }
 
@@ -914,15 +893,4 @@ mod test {
             true,
         );
     }
-
-    #[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])), \
-             (1, Term([0, 0, 0, 0, 102, 111, 114, 109])), \
-             (2, Term([0, 0, 0, 0, 101, 110, 99, 111, 100, 101, 100]))]\"",
-            false,
-        );
-    }
 }

src/query/query_parser/stemmer.rs

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

src/query/query_parser/user_input_ast.rs

@@ -80,6 +80,9 @@ impl UserInputBound {
 pub enum UserInputAST {
     Clause(Vec<UserInputAST>),
     Unary(Occur, Box<UserInputAST>),
+    //    Not(Box<UserInputAST>),
+    //    Should(Box<UserInputAST>),
+    //    Must(Box<UserInputAST>),
     Leaf(Box<UserInputLeaf>),
 }
 
@@ -89,7 +92,7 @@ impl UserInputAST {
     }
 
     fn compose(occur: Occur, asts: Vec<UserInputAST>) -> UserInputAST {
-        assert_ne!(occur, Occur::MustNot);
+        assert!(occur != Occur::MustNot);
         assert!(!asts.is_empty());
         if asts.len() == 1 {
             asts.into_iter().next().unwrap() //< safe
@@ -102,10 +105,6 @@ impl UserInputAST {
         }
     }
 
-    pub fn empty_query() -> UserInputAST {
-        UserInputAST::Clause(Vec::default())
-    }
-
     pub fn and(asts: Vec<UserInputAST>) -> UserInputAST {
         UserInputAST::compose(Occur::Must, asts)
     }
@@ -115,6 +114,42 @@ impl UserInputAST {
     }
 }
 
+/*
+impl UserInputAST {
+
+    fn compose_occur(self, occur: Occur) -> UserInputAST {
+        match self {
+            UserInputAST::Not(other) => {
+                let new_occur = compose_occur(Occur::MustNot, occur);
+                other.simplify()
+            }
+            _ => {
+                self
+            }
+        }
+    }
+
+    pub fn simplify(self) -> UserInputAST {
+        match self {
+            UserInputAST::Clause(els) => {
+                if els.len() == 1 {
+                    return els.into_iter().next().unwrap();
+                } else {
+                    return self;
+                }
+            }
+            UserInputAST::Not(els) => {
+                if els.len() == 1 {
+                    return els.into_iter().next().unwrap();
+                } else {
+                    return self;
+                }
+            }
+        }
+    }
+}
+*/
+
 impl From<UserInputLiteral> for UserInputLeaf {
     fn from(literal: UserInputLiteral) -> UserInputLeaf {
         UserInputLeaf::Literal(literal)

src/query/range_query.rs

@@ -460,10 +460,7 @@ mod tests {
         let count_multiples =
             |range_query: RangeQuery| searcher.search(&range_query, &Count).unwrap();
 
-        assert_eq!(
+        assert_eq!(count_multiples(RangeQuery::new_f64(float_field, 10.0..11.0)), 9);
-            count_multiples(RangeQuery::new_f64(float_field, 10.0..11.0)),
-            9
-        );
         assert_eq!(
             count_multiples(RangeQuery::new_f64_bounds(
                 float_field,

src/query/union.rs

@@ -411,3 +411,52 @@ mod tests {
     }
 
 }
+
+#[cfg(all(test, feature = "unstable"))]
+mod bench {
+
+    use query::score_combiner::DoNothingCombiner;
+    use query::ConstScorer;
+    use query::Union;
+    use query::VecDocSet;
+    use test::Bencher;
+    use tests;
+    use DocId;
+    use DocSet;
+
+    #[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/schema/facet.rs

@@ -120,7 +120,9 @@ impl Facet {
 
     /// Extract path from the `Facet`.
     pub fn to_path(&self) -> Vec<&str> {
-        self.encoded_str().split(|c| c == FACET_SEP_CHAR).collect()
+        self.encoded_str()
+            .split(|c| c == FACET_SEP_CHAR)
+            .collect()
     }
 }
 

src/schema/field_entry.rs

@@ -108,9 +108,7 @@ impl FieldEntry {
     /// Returns true iff the field is a int (signed or unsigned) fast field
     pub fn is_int_fast(&self) -> bool {
         match self.field_type {
-            FieldType::U64(ref options)
+            FieldType::U64(ref options) | FieldType::I64(ref options) | FieldType::F64(ref options) => options.is_fast(),
-            | FieldType::I64(ref options)
-            | FieldType::F64(ref options) => options.is_fast(),
             _ => false,
         }
     }

src/schema/field_type.rs

@@ -83,9 +83,9 @@ impl FieldType {
     pub fn is_indexed(&self) -> bool {
         match *self {
             FieldType::Str(ref text_options) => text_options.get_indexing_options().is_some(),
-            FieldType::U64(ref int_options)
+            FieldType::U64(ref int_options) | FieldType::I64(ref int_options) | FieldType::F64(ref int_options) => {
-            | FieldType::I64(ref int_options)
+                int_options.is_indexed()
-            | FieldType::F64(ref int_options) => int_options.is_indexed(),
+            }
             FieldType::Date(ref date_options) => date_options.is_indexed(),
             FieldType::HierarchicalFacet => true,
             FieldType::Bytes => false,
@@ -125,12 +125,9 @@ impl FieldType {
         match *json {
             JsonValue::String(ref field_text) => match *self {
                 FieldType::Str(_) => Ok(Value::Str(field_text.clone())),
-                FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => {
+                FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => Err(
-                    Err(ValueParsingError::TypeError(format!(
+                    ValueParsingError::TypeError(format!("Expected an integer, got {:?}", json)),
-                        "Expected an integer, got {:?}",
+                ),
-                        json
-                    )))
-                }
                 FieldType::HierarchicalFacet => Ok(Value::Facet(Facet::from(field_text))),
                 FieldType::Bytes => decode(field_text).map(Value::Bytes).map_err(|_| {
                     ValueParsingError::InvalidBase64(format!(
@@ -155,7 +152,7 @@ impl FieldType {
                         let msg = format!("Expected a u64 int, got {:?}", json);
                         Err(ValueParsingError::OverflowError(msg))
                     }
-                }
+                },
                 FieldType::F64(_) => {
                     if let Some(field_val_f64) = field_val_num.as_f64() {
                         Ok(Value::F64(field_val_f64))

src/schema/schema.rs

@@ -261,6 +261,24 @@ impl Schema {
         NamedFieldDocument(field_map)
     }
 
+    /// Converts a named doc into a document.
+    pub fn from_named_doc(
+        &self,
+        named_doc: NamedFieldDocument,
+    ) -> Result<Document, DocParsingError> {
+        let mut doc = Document::default();
+        for (field_name, field_values) in named_doc.0 {
+            if let Some(field) = self.get_field(&field_name) {
+                for field_value in field_values {
+                    doc.add(FieldValue::new(field, field_value));
+                }
+            } else {
+                return Err(DocParsingError::NoSuchFieldInSchema(field_name.clone()));
+            }
+        }
+        Ok(doc)
+    }
+
     /// Encode the schema in JSON.
     ///
     /// Encoding a document cannot fail.
@@ -279,7 +297,6 @@ impl Schema {
                 };
                 DocParsingError::NotJSON(doc_json_sample)
             })?;
-
         let mut doc = Document::default();
         for (field_name, json_value) in json_obj.iter() {
             match self.get_field(field_name) {

src/schema/value.rs

@@ -2,7 +2,7 @@ use crate::schema::Facet;
 use crate::DateTime;
 use serde::de::Visitor;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
-use std::{cmp::Ordering, fmt};
+use std::{fmt, cmp::Ordering};
 
 /// Value represents the value of a any field.
 /// It is an enum over all over all of the possible field type.
@@ -27,7 +27,7 @@ pub enum Value {
 impl Eq for Value {}
 impl Ord for Value {
     fn cmp(&self, other: &Self) -> Ordering {
-        match (self, other) {
+        match (self,other) {
             (Value::Str(l), Value::Str(r)) => l.cmp(r),
             (Value::U64(l), Value::U64(r)) => l.cmp(r),
             (Value::I64(l), Value::I64(r)) => l.cmp(r),
@@ -35,7 +35,7 @@ impl Ord for Value {
             (Value::Facet(l), Value::Facet(r)) => l.cmp(r),
             (Value::Bytes(l), Value::Bytes(r)) => l.cmp(r),
             (Value::F64(l), Value::F64(r)) => {
-                match (l.is_nan(), r.is_nan()) {
+                match (l.is_nan(),r.is_nan()) {
                     (false, false) => l.partial_cmp(r).unwrap(), // only fail on NaN
                     (true, true) => Ordering::Equal,
                     (true, false) => Ordering::Less, // we define NaN as less than -∞
@@ -155,7 +155,7 @@ impl Value {
             Value::F64(ref value) => *value,
             _ => panic!("This is not a f64 field."),
         }
-    }
+    }    
 
     /// Returns the Date-value, provided the value is of the `Date` type.
     ///
@@ -219,7 +219,7 @@ impl From<Vec<u8>> for Value {
 
 mod binary_serialize {
     use super::Value;
-    use crate::common::{f64_to_u64, u64_to_f64, BinarySerializable};
+    use crate::common::{BinarySerializable, f64_to_u64, u64_to_f64};
     use crate::schema::Facet;
     use chrono::{TimeZone, Utc};
     use std::io::{self, Read, Write};

tests/failpoints/mod.rs

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