macos ci

u64-based fields are actually 4+8=12 bytes long

.travis.yml

@@ -41,8 +41,8 @@ matrix:
     - env: TARGET=x86_64-unknown-linux-gnu CODECOV=1 #UPLOAD_DOCS=1
     # - env: TARGET=x86_64-unknown-linux-musl CODECOV=1
     # OSX
-    #- env: TARGET=x86_64-apple-darwin
-    #  os: osx
+    - env: TARGET=x86_64-apple-darwin
+      os: osx
 
 before_install:
   - set -e

Cargo.toml

@@ -16,7 +16,7 @@ edition = "2018"
 base64 = "0.10.0"
 byteorder = "1.0"
 once_cell = "1.0"
-regex = "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 +24,6 @@ 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 +41,7 @@ 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"
@@ -54,10 +54,6 @@ murmurhash32 = "0.2"
 chrono = "0.4"
 smallvec = "0.6"
 
-tantivy-schema = {path= "./tantivy-schema"}
-tantivy-tokenizer = {path= "./tantivy-tokenizer"}
-tantivy-common = {path="./tantivy-common"}
-
 [target.'cfg(windows)'.dependencies]
 winapi = "0.3"
 
@@ -84,10 +80,14 @@ 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
@@ -101,7 +101,3 @@ features = ["failpoints"]
 name = "failpoints"
 path = "tests/failpoints/mod.rs"
 required-features = ["fail/failpoints"]
-
-
-[workspace]
-members = ["tantivy-schema", "tantivy-common", "tantivy-tokenizer"]

Makefile

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

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/multiple_producer.rs

@@ -46,10 +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 = {
-                // A read lock is sufficient here.
-                let index_writer_rlock = index_writer_clone_1.read().unwrap();
-                index_writer_rlock.add_document(
+            let opstamp = index_writer_clone_1
+                .read().unwrap() //< A read lock is sufficient here.
+                .add_document(
                     doc!(
                         title => "Of Mice and Men",
                         body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
@@ -60,8 +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));
         }

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.
-pub fn compose_occur(left: Occur, right: Occur) -> Occur {
-    match left {
-        Occur::Should => right,
-        Occur::Must => {
-            if right == Occur::MustNot {
-                Occur::MustNot
-            } else {
-                Occur::Must
+    /// Compose two occur values.
+    pub fn compose(left: Occur, right: Occur) -> Occur {
+        match left {
+            Occur::Should => right,
+            Occur::Must => {
+                if right == Occur::MustNot {
+                    Occur::MustNot
+                } else {
+                    Occur::Must
+                }
             }
-        }
-        Occur::MustNot => {
-            if right == Occur::MustNot {
-                Occur::Must
-            } else {
-                Occur::MustNot
+            Occur::MustNot => {
+                if right == Occur::MustNot {
+                    Occur::Must
+                } else {
+                    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::query::query_parser::user_input_ast::UserInputBound;
+use crate::Occur;
 use combine::char::*;
 use combine::error::StreamError;
 use combine::stream::StreamErrorFor;

query-grammar/src/user_input_ast.rs

@@ -1,7 +1,7 @@
 use std::fmt;
 use std::fmt::{Debug, Formatter};
 
-use crate::query::Occur;
+use crate::Occur;
 
 #[derive(PartialEq)]
 pub enum UserInputLeaf {
@@ -151,7 +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),
         }

src/common/bitpacker.rs

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

src/common/bitset.rs

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

src/common/mod.rs

@@ -1,18 +1,18 @@
 pub mod bitpacker;
 mod bitset;
+mod composite_file;
 mod counting_writer;
 mod serialize;
 mod vint;
 
 pub use self::bitset::BitSet;
-pub use self::bitset::TinySet;
+pub(crate) use self::bitset::TinySet;
+pub(crate) use self::composite_file::{CompositeFile, CompositeWrite};
 pub use self::counting_writer::CountingWriter;
 pub use self::serialize::{BinarySerializable, FixedSize};
 pub use self::vint::{read_u32_vint, serialize_vint_u32, write_u32_vint, VInt};
 pub use byteorder::LittleEndian as Endianness;
 
-pub type DateTime = chrono::DateTime<chrono::Utc>;
-
 /// Segment's max doc must be `< MAX_DOC_LIMIT`.
 ///
 /// We do not allow segments with more than
@@ -42,7 +42,7 @@ pub const MAX_DOC_LIMIT: u32 = 1 << 31;
 /// a very large range of values. Even in this case, it results
 /// in an extra cost of at most 12% compared to the optimal
 /// number of bits.
-pub fn compute_num_bits(n: u64) -> u8 {
+pub(crate) fn compute_num_bits(n: u64) -> u8 {
     let amplitude = (64u32 - n.leading_zeros()) as u8;
     if amplitude <= 64 - 8 {
         amplitude
@@ -51,7 +51,7 @@ pub fn compute_num_bits(n: u64) -> u8 {
     }
 }
 
-pub fn is_power_of_2(n: usize) -> bool {
+pub(crate) fn is_power_of_2(n: usize) -> bool {
     (n > 0) && (n & (n - 1) == 0)
 }
 
@@ -131,12 +131,10 @@ pub fn u64_to_f64(val: u64) -> f64 {
     })
 }
 
-pub use self::serialize::fixed_size_test;
-
 #[cfg(test)]
 pub(crate) mod test {
 
-    use super::fixed_size_test;
+    pub use super::serialize::test::fixed_size_test;
     use super::{compute_num_bits, f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
     use std::f64;
 

src/common/serialize.rs

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

src/common/vint.rs

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

src/core/segment_reader.rs

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

src/directory/mmap_directory.rs

@@ -265,7 +265,7 @@ 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");
         }
@@ -539,7 +539,7 @@ impl Directory for MmapDirectory {
 #[cfg(test)]
 mod tests {
 
-    // There are more tests in directory/lib.rs
+    // There are more tests in directory/mod.rs
     // The following tests are specific to the MmapDirectory
 
     use super::*;

src/fastfield/mod.rs

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

src/fastfield/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

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

src/fastfield/readers.rs

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

src/fastfield/serializer.rs

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

src/fastfield/writer.rs

@@ -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/fieldnorm/serializer.rs

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

src/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))))]
@@ -102,6 +101,9 @@
 #[macro_use]
 extern crate serde_derive;
 
+#[cfg_attr(test, macro_use)]
+extern crate serde_json;
+
 #[macro_use]
 extern crate log;
 
@@ -118,9 +120,6 @@ mod functional_test;
 #[macro_use]
 mod macros;
 
-mod composite_file;
-pub(crate) use composite_file::{CompositeFile, CompositeWrite};
-
 pub use crate::error::TantivyError;
 
 #[deprecated(since = "0.7.0", note = "please use `tantivy::TantivyError` instead")]
@@ -133,22 +132,22 @@ pub type Result<T> = std::result::Result<T, error::TantivyError>;
 /// Tantivy DateTime
 pub type DateTime = chrono::DateTime<chrono::Utc>;
 
-pub use tantivy_common as common;
-pub use tantivy_schema as schema;
-pub use tantivy_tokenizer as tokenizer;
-
+mod common;
 mod core;
 mod indexer;
 
-pub mod collector;
-pub mod directory;
 #[allow(unused_doc_comments)]
 mod error;
+pub mod tokenizer;
+
+pub mod collector;
+pub mod directory;
 pub mod fastfield;
 pub mod fieldnorm;
 pub(crate) mod positions;
 pub mod postings;
 pub mod query;
+pub mod schema;
 pub mod space_usage;
 pub mod store;
 pub mod termdict;
@@ -252,6 +251,7 @@ mod tests {
     use crate::Postings;
     use crate::ReloadPolicy;
     use rand::distributions::Bernoulli;
+    use rand::distributions::Uniform;
     use rand::rngs::StdRng;
     use rand::{Rng, SeedableRng};
 
@@ -268,6 +268,14 @@ mod tests {
         (a - b).abs() < 0.0005 * (a + b).abs()
     }
 
+    pub fn generate_nonunique_unsorted(max_value: u32, n_elems: usize) -> Vec<u32> {
+        let seed: [u8; 32] = [1; 32];
+        StdRng::from_seed(seed)
+            .sample_iter(&Uniform::new(0u32, max_value))
+            .take(n_elems)
+            .collect::<Vec<u32>>()
+    }
+
     pub fn sample_with_seed(n: u32, ratio: f64, seed_val: u8) -> Vec<u32> {
         StdRng::from_seed([seed_val; 32])
             .sample_iter(&Bernoulli::new(ratio).unwrap())
@@ -277,6 +285,10 @@ mod tests {
             .collect()
     }
 
+    pub fn sample(n: u32, ratio: f64) -> Vec<u32> {
+        sample_with_seed(n, ratio, 4)
+    }
+
     #[test]
     #[cfg(feature = "mmap")]
     fn test_indexing() {

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

@@ -1,6 +1,6 @@
 use super::TermInfo;
-use crate::common::CountingWriter;
 use crate::common::{BinarySerializable, VInt};
+use crate::common::{CompositeWrite, CountingWriter};
 use crate::core::Segment;
 use crate::directory::WritePtr;
 use crate::positions::PositionSerializer;
@@ -10,7 +10,6 @@ use crate::postings::USE_SKIP_INFO_LIMIT;
 use crate::schema::Schema;
 use crate::schema::{Field, FieldEntry, FieldType};
 use crate::termdict::{TermDictionaryBuilder, TermOrdinal};
-use crate::CompositeWrite;
 use crate::DocId;
 use crate::Result;
 use std::io::{self, Write};
@@ -142,10 +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.is_termfreq_enabled(),
-                        index_option.is_position_enabled(),
-                    )
+                    (index_option.has_freq(), index_option.has_positions())
                 } else {
                     (false, false)
                 }

src/postings/term_info.rs

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

src/query/bitset/mod.rs

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

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()
-            .parse(query)
-            .map_err(|_| QueryParserError::SyntaxError)?;
+        let user_input_ast =
+            tantivy_query_grammar::parse_query(query).map_err(|_| QueryParserError::SyntaxError)?;
         self.compute_logical_ast(user_input_ast)
     }
 
@@ -399,7 +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)))
@@ -407,7 +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)?;

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]>,

src/schema/document.rs

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

src/schema/facet.rs

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

src/schema/field.rs

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

src/schema/field_entry.rs

@@ -1,8 +1,7 @@
-use serde_derive::*;
+use crate::schema::IntOptions;
+use crate::schema::TextOptions;
 
-use crate::FieldType;
-use crate::IntOptions;
-use crate::TextOptions;
+use crate::schema::FieldType;
 use serde::de::{self, MapAccess, Visitor};
 use serde::ser::SerializeStruct;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
@@ -266,7 +265,7 @@ impl<'de> Deserialize<'de> for FieldEntry {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::TEXT;
+    use crate::schema::TEXT;
     use serde_json;
 
     #[test]

src/schema/field_type.rs

@@ -1,10 +1,11 @@
 use base64::decode;
 
-use crate::Facet;
-use crate::IndexRecordOption;
-use crate::TextFieldIndexing;
-use crate::Value;
-use crate::{IntOptions, TextOptions};
+use crate::schema::{IntOptions, TextOptions};
+
+use crate::schema::Facet;
+use crate::schema::IndexRecordOption;
+use crate::schema::TextFieldIndexing;
+use crate::schema::Value;
 use serde_json::Value as JsonValue;
 
 /// Possible error that may occur while parsing a field value
@@ -182,9 +183,8 @@ impl FieldType {
 #[cfg(test)]
 mod tests {
     use super::FieldType;
-    use crate::field_type::ValueParsingError;
-    use crate::Value;
-    use serde_json::json;
+    use crate::schema::field_type::ValueParsingError;
+    use crate::schema::Value;
 
     #[test]
     fn test_bytes_value_from_json() {

src/schema/field_value.rs

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

src/schema/flags.rs

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

src/schema/index_record_option.rs

@@ -1,5 +1,3 @@
-use serde_derive::{Deserialize, Serialize};
-
 /// `IndexRecordOption` describes an amount information associated
 /// to a given indexed field.
 ///
@@ -31,22 +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/int_options.rs

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

src/schema/mod.rs

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

src/schema/named_field_document.rs

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

src/schema/schema.rs

@@ -1,14 +1,14 @@
-use super::*;
 use crate::schema::field_type::ValueParsingError;
-use failure::Fail;
+use std::collections::BTreeMap;
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use super::*;
 use serde::de::{SeqAccess, Visitor};
 use serde::ser::SerializeSeq;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
 use serde_json::{self, Map as JsonObject, Value as JsonValue};
-use std::collections::BTreeMap;
-use std::collections::HashMap;
 use std::fmt;
-use std::sync::Arc;
 
 /// Tantivy has a very strict schema.
 /// You need to specify in advance whether a field is indexed or not,
@@ -21,7 +21,7 @@ use std::sync::Arc;
 /// # Examples
 ///
 /// ```
-/// use tantivy_schema::*;
+/// use tantivy::schema::*;
 ///
 /// let mut schema_builder = Schema::builder();
 /// let id_field = schema_builder.add_text_field("id", STRING);
@@ -208,7 +208,7 @@ impl Eq for InnerSchema {}
 /// # Examples
 ///
 /// ```
-/// use tantivy_schema::*;
+/// use tantivy::schema::*;
 ///
 /// let mut schema_builder = Schema::builder();
 /// let id_field = schema_builder.add_text_field("id", STRING);

src/schema/term.rs

@@ -1,11 +1,11 @@
 use std::fmt;
 
-use crate::Facet;
-use crate::Field;
+use super::Field;
+use crate::common;
+use crate::schema::Facet;
+use crate::DateTime;
 use byteorder::{BigEndian, ByteOrder};
 use std::str;
-use tantivy_common as common;
-use tantivy_common::DateTime;
 
 /// Size (in bytes) of the buffer of a int field.
 const INT_TERM_LEN: usize = 4 + 8;
@@ -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,
-    /// the Term will have 8 bytes. <= this is wrong
+    /// Assuming the term has a field id of 1, and a f64 value of 1.5,
+    /// 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);
@@ -94,7 +94,7 @@ impl Term {
     }
 
     /// Creates a new Term for a given field.
-    pub fn for_field(field: Field) -> Term {
+    pub(crate) fn for_field(field: Field) -> Term {
         let mut term = Term(Vec::with_capacity(100));
         term.set_field(field);
         term
@@ -134,7 +134,7 @@ impl Term {
         self.0.extend(bytes);
     }
 
-    pub fn from_field_bytes(field: Field, bytes: &[u8]) -> Term {
+    pub(crate) fn from_field_bytes(field: Field, bytes: &[u8]) -> Term {
         let mut term = Term::for_field(field);
         term.set_bytes(bytes);
         term
@@ -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..]))
     }
@@ -236,7 +236,7 @@ impl fmt::Debug for Term {
 #[cfg(test)]
 mod tests {
 
-    use crate::{Schema, Term, STRING};
+    use crate::schema::*;
 
     #[test]
     pub fn test_term() {

src/schema/text_options.rs

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

src/schema/value.rs

@@ -1,11 +1,9 @@
-use crate::Facet;
-use chrono;
+use crate::schema::Facet;
+use crate::DateTime;
 use serde::de::Visitor;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
 use std::{cmp::Ordering, fmt};
 
-pub(crate) type DateTime = chrono::DateTime<chrono::Utc>;
-
 /// Value represents the value of a any field.
 /// It is an enum over all over all of the possible field type.
 #[derive(Debug, Clone, PartialEq, PartialOrd)]
@@ -220,11 +218,11 @@ impl From<Vec<u8>> for Value {
 }
 
 mod binary_serialize {
-    use crate::Facet;
-    use crate::Value;
+    use super::Value;
+    use crate::common::{f64_to_u64, u64_to_f64, BinarySerializable};
+    use crate::schema::Facet;
     use chrono::{TimeZone, Utc};
     use std::io::{self, Read, Write};
-    use tantivy_common::{f64_to_u64, u64_to_f64, BinarySerializable};
 
     const TEXT_CODE: u8 = 0;
     const U64_CODE: u8 = 1;

src/termdict/term_info_store.rs

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

src/tokenizer/alphanum_only.rs

@@ -1,6 +1,6 @@
 //! # Example
 //! ```rust
-//! use tantivy_tokenizer::*;
+//! use tantivy::tokenizer::*;
 //!
 //! # fn main() {
 //!
@@ -64,6 +64,14 @@ impl<TailTokenStream> TokenStream for AlphaNumOnlyFilterStream<TailTokenStream>
 where
     TailTokenStream: TokenStream,
 {
+    fn token(&self) -> &Token {
+        self.tail.token()
+    }
+
+    fn token_mut(&mut self) -> &mut Token {
+        self.tail.token_mut()
+    }
+
     fn advance(&mut self) -> bool {
         while self.tail.advance() {
             if self.predicate(self.tail.token()) {
@@ -73,12 +81,4 @@ where
 
         false
     }
-
-    fn token(&self) -> &Token {
-        self.tail.token()
-    }
-
-    fn token_mut(&mut self) -> &mut Token {
-        self.tail.token_mut()
-    }
 }

src/tokenizer/ascii_folding_filter.rs

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

src/tokenizer/facet_tokenizer.rs

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

src/tokenizer/lower_caser.rs

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

src/tokenizer/mod.rs

@@ -5,7 +5,7 @@
 //! each of your fields :
 //!
 //! ```rust
-//! use tantivy_schema::*;
+//! use tantivy::schema::*;
 //!
 //! # fn main() {
 //! let mut schema_builder = Schema::builder();
@@ -64,7 +64,7 @@
 //! For instance, the `en_stem` is defined as follows.
 //!
 //! ```rust
-//! use tantivy_tokenizer::*;
+//! use tantivy::tokenizer::*;
 //!
 //! # fn main() {
 //! let en_stem = SimpleTokenizer
@@ -78,8 +78,8 @@
 //! register it with a name in your index's [`TokenizerManager`](./struct.TokenizerManager.html).
 //!
 //! ```rust
-//! # use tantivy_schema::Schema;
-//! # use tantivy_tokenizer::*;
+//! # use tantivy::schema::Schema;
+//! # use tantivy::tokenizer::*;
 //! # use tantivy::Index;
 //! # fn main() {
 //! # let custom_en_tokenizer = SimpleTokenizer;
@@ -98,8 +98,8 @@
 //! # Example
 //!
 //! ```rust
-//! use tantivy_schema::{Schema, IndexRecordOption, TextOptions, TextFieldIndexing};
-//! use tantivy_tokenizer::*;
+//! use tantivy::schema::{Schema, IndexRecordOption, TextOptions, TextFieldIndexing};
+//! use tantivy::tokenizer::*;
 //! use tantivy::Index;
 //!
 //! # fn main() {
@@ -150,10 +150,8 @@ 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 use self::tokenizer::BoxedTokenizer;
 
-pub(crate) const FACET_SEP_BYTE: u8 = 0u8;
 pub use self::tokenizer::{Token, TokenFilter, TokenStream, Tokenizer};
 pub use self::tokenizer_manager::TokenizerManager;
 

src/tokenizer/ngram_tokenizer.rs

@@ -30,7 +30,7 @@ use super::{Token, TokenStream, Tokenizer};
 /// # Example
 ///
 /// ```rust
-/// use tantivy_tokenizer::*;
+/// use tantivy::tokenizer::*;
 /// # fn main() {
 /// let tokenizer = NgramTokenizer::new(2, 3, false);
 /// let mut stream = tokenizer.token_stream("hello");
@@ -308,9 +308,9 @@ mod tests {
     use super::CodepointFrontiers;
     use super::NgramTokenizer;
     use super::StutteringIterator;
-    use crate::tests::assert_token;
-    use crate::tokenizer::{TokenStream, Tokenizer};
-    use crate::Token;
+    use crate::tokenizer::tests::assert_token;
+    use crate::tokenizer::tokenizer::{TokenStream, Tokenizer};
+    use crate::tokenizer::Token;
 
     fn test_helper<T: TokenStream>(mut tokenizer: T) -> Vec<Token> {
         let mut tokens: Vec<Token> = vec![];

src/tokenizer/remove_long.rs

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

src/tokenizer/stemmer.rs

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

src/tokenizer/stop_word_filter.rs

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

src/tokenizer/token_stream_chain.rs

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

src/tokenizer/tokenizer.rs

@@ -1,4 +1,4 @@
-use crate::TokenStreamChain;
+use crate::tokenizer::TokenStreamChain;
 /// The tokenizer module contains all of the tools used to process
 /// text in `tantivy`.
 use std::borrow::{Borrow, BorrowMut};
@@ -56,7 +56,7 @@ pub trait Tokenizer<'a>: Sized + Clone {
     /// # Example
     ///
     /// ```rust
-    /// use tantivy_tokenizer::*;
+    /// use tantivy::tokenizer::*;
     ///
     /// # fn main() {
     /// let en_stem = SimpleTokenizer
@@ -186,7 +186,7 @@ impl<'b> TokenStream for Box<dyn TokenStream + 'b> {
 /// # Example
 ///
 /// ```
-/// use tantivy_tokenizer::*;
+/// use tantivy::tokenizer::*;
 ///
 /// # fn main() {
 /// let tokenizer = SimpleTokenizer
@@ -227,7 +227,7 @@ pub trait TokenStream {
     /// and `.token()`.
     ///
     /// ```
-    /// # use tantivy_tokenizer::*;
+    /// # use tantivy::tokenizer::*;
     /// #
     /// # fn main() {
     /// # let tokenizer = SimpleTokenizer

src/tokenizer/tokenizer_manager.rs

@@ -1,11 +1,11 @@
-use crate::stemmer::Language;
-use crate::BoxedTokenizer;
-use crate::LowerCaser;
-use crate::RawTokenizer;
-use crate::RemoveLongFilter;
-use crate::SimpleTokenizer;
-use crate::Stemmer;
-use crate::Tokenizer;
+use crate::tokenizer::stemmer::Language;
+use crate::tokenizer::BoxedTokenizer;
+use crate::tokenizer::LowerCaser;
+use crate::tokenizer::RawTokenizer;
+use crate::tokenizer::RemoveLongFilter;
+use crate::tokenizer::SimpleTokenizer;
+use crate::tokenizer::Stemmer;
+use crate::tokenizer::Tokenizer;
 use std::collections::HashMap;
 use std::sync::{Arc, RwLock};
 
@@ -32,10 +32,11 @@ impl TokenizerManager {
     where
         A: Into<BoxedTokenizer>,
     {
+        let boxed_tokenizer = tokenizer.into();
         self.tokenizers
             .write()
             .expect("Acquiring the lock should never fail")
-            .insert(tokenizer_name.to_string(), tokenizer.into());
+            .insert(tokenizer_name.to_string(), boxed_tokenizer);
     }
 
     /// Accessing a tokenizer given its name.

tantivy-common/Cargo.toml

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

tantivy-common/src/composite_file.rs

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

tantivy-schema/Cargo.toml

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

tantivy-tokenizer/Cargo.toml

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