Integrated state into TermDict streamer

CHANGELOG.md

@@ -7,13 +7,10 @@ Tantivy 0.11.0
     - Better handling of whitespaces.
 - Closes #498 - add support for Elastic-style unbounded range queries for alphanumeric types eg. "title:>hello", "weight:>=70.5", "height:<200" (@petr-tik)
 - API change around `Box<BoxableTokenizer>`. See detail in #629
-- Avoid rebuilding Regex automaton whenever a regex query is reused. #630 (@brainlock)
- 
+
 ## How to update?
 
-- `Box<dyn BoxableTokenizer>` has been replaced by a `BoxedTokenizer` struct.
-- Regex are now compiled when the `RegexQuery` instance is built. As a result, it can now return
-an error and handling the `Result` is required.
+`Box<dyn BoxableTokenizer>` has been replaced by a `BoxedTokenizer` struct.
 
 Tantivy 0.10.1
 =====================

Cargo.toml

@@ -15,9 +15,9 @@ edition = "2018"
 [dependencies]
 base64 = "0.10.0"
 byteorder = "1.0"
-once_cell = "1.0"
+once_cell = "0.2"
 regex = "1.0"
-tantivy-fst = "0.1"
+tantivy-fst = {git="https://github.com/tantivy-search/fst"}
 memmap = {version = "0.7", optional=true}
 lz4 = {version="1.20", optional=true}
 snap = {version="0.2"}
@@ -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"
 
@@ -101,7 +97,3 @@ features = ["failpoints"]
 name = "failpoints"
 path = "tests/failpoints/mod.rs"
 required-features = ["fail/failpoints"]
-
-
-[workspace]
-members = ["tantivy-schema", "tantivy-common", "tantivy-tokenizer"]

examples/basic_search.rs

@@ -5,17 +5,20 @@
 //
 // We will :
 // - define our schema
-// - create an index in a directory
-// - index a few documents into our index
-// - search for the best document matching a basic query
-// - retrieve the best document's original content.
+// = create an index in a directory
+// - index few documents in our index
+// - search for the best document matchings "sea whale"
+// - retrieve the best document original content.
 
 // ---
 // Importing tantivy...
+#[macro_use]
+extern crate tantivy;
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
-use tantivy::{doc, Index, ReloadPolicy};
+use tantivy::Index;
+use tantivy::ReloadPolicy;
 use tempfile::TempDir;
 
 fn main() -> tantivy::Result<()> {
@@ -30,7 +33,7 @@ fn main() -> tantivy::Result<()> {
     // and for each field, its type and "the way it should
     // be indexed".
 
-    // First we need to define a schema ...
+    // first we need to define a schema ...
     let mut schema_builder = Schema::builder();
 
     // Our first field is title.
@@ -45,7 +48,7 @@ fn main() -> tantivy::Result<()> {
     //
     // `STORED` means that the field will also be saved
     // in a compressed, row-oriented key-value store.
-    // This store is useful for reconstructing the
+    // This store is useful to reconstruct the
     // documents that were selected during the search phase.
     schema_builder.add_text_field("title", TEXT | STORED);
 
@@ -54,7 +57,8 @@ fn main() -> tantivy::Result<()> {
     // need to be able to be able to retrieve it
     // for our application.
     //
-    // We can make our index lighter by omitting the `STORED` flag.
+    // We can make our index lighter and
+    // by omitting `STORED` flag.
     schema_builder.add_text_field("body", TEXT);
 
     let schema = schema_builder.build();
@@ -67,7 +71,7 @@ fn main() -> tantivy::Result<()> {
     // with our schema in the directory.
     let index = Index::create_in_dir(&index_path, schema.clone())?;
 
-    // To insert a document we will need an index writer.
+    // To insert document we need an index writer.
     // There must be only one writer at a time.
     // This single `IndexWriter` is already
     // multithreaded.
@@ -145,8 +149,8 @@ fn main() -> tantivy::Result<()> {
     // At this point our documents are not searchable.
     //
     //
-    // We need to call `.commit()` explicitly to force the
-    // `index_writer` to finish processing the documents in the queue,
+    // We need to call .commit() explicitly to force the
+    // index_writer to finish processing the documents in the queue,
     // flush the current index to the disk, and advertise
     // the existence of new documents.
     //
@@ -158,14 +162,14 @@ fn main() -> tantivy::Result<()> {
     // persistently indexed.
     //
     // In the scenario of a crash or a power failure,
-    // tantivy behaves as if it has rolled back to its last
+    // tantivy behaves as if has rolled back to its last
     // commit.
 
     // # Searching
     //
     // ### Searcher
     //
-    // A reader is required first in order to search an index.
+    // A reader is required to get search the index.
     // It acts as a `Searcher` pool that reloads itself,
     // depending on a `ReloadPolicy`.
     //
@@ -181,7 +185,7 @@ fn main() -> tantivy::Result<()> {
 
     // We now need to acquire a searcher.
     //
-    // A searcher points to a snapshotted, immutable version of the index.
+    // A searcher points to snapshotted, immutable version of the index.
     //
     // Some search experience might require more than
     // one query. Using the same searcher ensures that all of these queries will run on the
@@ -201,7 +205,7 @@ fn main() -> tantivy::Result<()> {
     // in both title and body.
     let query_parser = QueryParser::for_index(&index, vec![title, body]);
 
-    // `QueryParser` may fail if the query is not in the right
+    // QueryParser may fail if the query is not in the right
     // format. For user facing applications, this can be a problem.
     // A ticket has been opened regarding this problem.
     let query = query_parser.parse_query("sea whale")?;
@@ -217,7 +221,7 @@ fn main() -> tantivy::Result<()> {
     //
     // We are not interested in all of the documents but
     // only in the top 10. Keeping track of our top 10 best documents
-    // is the role of the `TopDocs` collector.
+    // is the role of the TopDocs.
 
     // We can now perform our query.
     let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;

examples/custom_collector.rs

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

examples/custom_tokenizer.rs

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

examples/deleting_updating_documents.rs

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

examples/faceted_search.rs

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

examples/integer_range_search.rs

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

examples/iterating_docs_and_positions.rs

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

examples/multiple_producer.rs

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

examples/snippet.rs

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

examples/stop_words.rs

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

src/collector/count_collector.rs

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

src/collector/facet_collector.rs

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

src/collector/mod.rs

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

src/collector/multi_collector.rs

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

src/collector/top_score_collector.rs

@@ -23,10 +23,13 @@ use std::fmt;
 /// is `O(n log K)`.
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::DocAddress;
+/// use tantivy::schema::{Schema, TEXT};
+/// use tantivy::{Index, Result};
 /// use tantivy::collector::TopDocs;
 /// use tantivy::query::QueryParser;
-/// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, DocAddress, Index, Result};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {
@@ -84,8 +87,10 @@ impl TopDocs {
     /// Set top-K to rank documents by a given fast field.
     ///
     /// ```rust
+    /// #[macro_use]
+    /// extern crate tantivy;
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{doc, Index, Result, DocAddress};
+    /// # use tantivy::{Index, Result, DocAddress};
     /// # use tantivy::query::{Query, QueryParser};
     /// use tantivy::Searcher;
     /// use tantivy::collector::TopDocs;
@@ -123,7 +128,7 @@ impl TopDocs {
     /// ///
     /// /// `field` is required to be a FAST field.
     /// fn docs_sorted_by_rating(searcher: &Searcher,
-    ///                          query: &dyn Query,
+    ///                          query: &Query,
     ///                          sort_by_field: Field)
     ///     -> Result<Vec<(u64, DocAddress)>> {
     ///
@@ -192,8 +197,10 @@ impl TopDocs {
     /// learning-to-rank model over various features
     ///
     /// ```rust
+    /// #[macro_use]
+    /// extern crate tantivy;
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{doc, Index, DocAddress, DocId, Score};
+    /// # use tantivy::{Index, DocAddress, DocId, Score};
     /// # use tantivy::query::QueryParser;
     /// use tantivy::SegmentReader;
     /// use tantivy::collector::TopDocs;
@@ -295,8 +302,10 @@ impl TopDocs {
     /// # Example
     ///
     /// ```rust
+    /// # #[macro_use]
+    /// # extern crate tantivy;
     /// # use tantivy::schema::{Schema, FAST, TEXT};
-    /// # use tantivy::{doc, Index, DocAddress, DocId};
+    /// # use tantivy::{Index, DocAddress, DocId};
     /// # use tantivy::query::QueryParser;
     /// use tantivy::SegmentReader;
     /// use tantivy::collector::TopDocs;

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/index.rs

@@ -216,22 +216,8 @@ impl Index {
         Index::open(mmap_directory)
     }
 
-    /// Returns the list of the segment metas tracked by the index.
-    ///
-    /// Such segments can of course be part of the index,
-    /// but also they could be segments being currently built or in the middle of a merge
-    /// operation.
-    pub fn list_all_segment_metas(&self) -> Vec<SegmentMeta> {
-        self.inventory.all()
-    }
-
-    /// Creates a new segment_meta (Advanced user only).
-    ///
-    /// As long as the `SegmentMeta` lives, the files associated with the
-    /// `SegmentMeta` are guaranteed to not be garbage collected, regardless of
-    /// whether the segment is recorded as part of the index or not.
-    pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
-        self.inventory.new_segment_meta(segment_id, max_doc)
+    pub(crate) fn inventory(&self) -> &SegmentMetaInventory {
+        &self.inventory
     }
 
     /// Open the index using the provided directory

src/core/index_meta.rs

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

src/core/segment_id.rs

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

src/core/segment_reader.rs

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

src/directory/mmap_directory.rs

@@ -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/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/fieldnorm/serializer.rs

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

src/indexer/index_writer.rs

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

src/indexer/segment_updater.rs

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

src/lib.rs

@@ -11,12 +11,21 @@
 //! Think `Lucene`, but in Rust.
 //!
 //! ```rust
+
+//! # extern crate tempfile;
+//! #
+//! #[macro_use]
+//! extern crate tantivy;
+//!
+//! // ...
+//!
 //! # use std::path::Path;
 //! # use tempfile::TempDir;
+//! # use tantivy::Index;
+//! # use tantivy::schema::*;
+//! # use tantivy::{Score, DocAddress};
 //! # use tantivy::collector::TopDocs;
 //! # use tantivy::query::QueryParser;
-//! # use tantivy::schema::*;
-//! # use tantivy::{doc, DocAddress, Index, Score};
 //! #
 //! # fn main() {
 //! #     // Let's create a temporary directory for the
@@ -102,6 +111,9 @@
 #[macro_use]
 extern crate serde_derive;
 
+#[cfg_attr(test, macro_use)]
+extern crate serde_json;
+
 #[macro_use]
 extern crate log;
 
@@ -118,9 +130,6 @@ mod functional_test;
 #[macro_use]
 mod macros;
 
-mod composite_file;
-pub(crate) use composite_file::{CompositeFile, CompositeWrite};
-
 pub use crate::error::TantivyError;
 
 #[deprecated(since = "0.7.0", note = "please use `tantivy::TantivyError` instead")]
@@ -133,22 +142,22 @@ pub type Result<T> = std::result::Result<T, error::TantivyError>;
 /// Tantivy DateTime
 pub type DateTime = chrono::DateTime<chrono::Utc>;
 
-pub use tantivy_common as common;
-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 +261,7 @@ mod tests {
     use crate::Postings;
     use crate::ReloadPolicy;
     use rand::distributions::Bernoulli;
+    use rand::distributions::Uniform;
     use rand::rngs::StdRng;
     use rand::{Rng, SeedableRng};
 
@@ -268,6 +278,14 @@ mod tests {
         (a - b).abs() < 0.0005 * (a + b).abs()
     }
 
+    pub fn generate_nonunique_unsorted(max_value: u32, n_elems: usize) -> Vec<u32> {
+        let seed: [u8; 32] = [1; 32];
+        StdRng::from_seed(seed)
+            .sample_iter(&Uniform::new(0u32, max_value))
+            .take(n_elems)
+            .collect::<Vec<u32>>()
+    }
+
     pub fn sample_with_seed(n: u32, ratio: f64, seed_val: u8) -> Vec<u32> {
         StdRng::from_seed([seed_val; 32])
             .sample_iter(&Bernoulli::new(ratio).unwrap())
@@ -277,6 +295,10 @@ mod tests {
             .collect()
     }
 
+    pub fn sample(n: u32, ratio: f64) -> Vec<u32> {
+        sample_with_seed(n, ratio, 4)
+    }
+
     #[test]
     #[cfg(feature = "mmap")]
     fn test_indexing() {

src/macros.rs

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

src/postings/serializer.rs

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

src/postings/term_info.rs

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

src/query/automaton_weight.rs

@@ -8,30 +8,30 @@ use crate::termdict::{TermDictionary, TermStreamer};
 use crate::DocId;
 use crate::TantivyError;
 use crate::{Result, SkipResult};
-use std::sync::Arc;
 use tantivy_fst::Automaton;
 
 /// A weight struct for Fuzzy Term and Regex Queries
-pub struct AutomatonWeight<A> {
+pub struct AutomatonWeight<A>
+where
+    A: Automaton + Send + Sync + 'static,
+    A::State: Clone + Default + Sized,
+{
     field: Field,
-    automaton: Arc<A>,
+    automaton: A,
 }
 
 impl<A> AutomatonWeight<A>
 where
     A: Automaton + Send + Sync + 'static,
+    A::State: Clone + Default + Sized,
 {
     /// Create a new AutomationWeight
-    pub fn new<IntoArcA: Into<Arc<A>>>(field: Field, automaton: IntoArcA) -> AutomatonWeight<A> {
-        AutomatonWeight {
-            field,
-            automaton: automaton.into(),
-        }
+    pub fn new(field: Field, automaton: A) -> AutomatonWeight<A> {
+        AutomatonWeight { field, automaton }
     }
 
     fn automaton_stream<'a>(&'a self, term_dict: &'a TermDictionary) -> TermStreamer<'a, &'a A> {
-        let automaton: &A = &*self.automaton;
-        let term_stream_builder = term_dict.search(automaton);
+        let term_stream_builder = term_dict.search(&self.automaton);
         term_stream_builder.into_stream()
     }
 }
@@ -39,6 +39,7 @@ where
 impl<A> Weight for AutomatonWeight<A>
 where
     A: Automaton + Send + Sync + 'static,
+    A::State: Clone + Default + Sized,
 {
     fn scorer(&self, reader: &SegmentReader) -> Result<Box<dyn Scorer>> {
         let max_doc = reader.max_doc();

src/query/bitset/mod.rs

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

src/query/fuzzy_query.rs

@@ -28,10 +28,12 @@ static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Laz
 /// containing a specific term that is within
 /// Levenshtein distance
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Schema, TEXT};
+/// use tantivy::{Index, Result, Term};
 /// use tantivy::collector::{Count, TopDocs};
 /// use tantivy::query::FuzzyTermQuery;
-/// use tantivy::schema::{Schema, TEXT};
-/// use tantivy::{doc, Index, Result, Term};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {

src/query/range_query.rs

@@ -38,10 +38,14 @@ fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
 /// # Example
 ///
 /// ```rust
-/// # use tantivy::collector::Count;
-/// # use tantivy::query::RangeQuery;
+///
+/// # #[macro_use]
+/// # extern crate tantivy;
+/// # use tantivy::Index;
 /// # use tantivy::schema::{Schema, INDEXED};
-/// # use tantivy::{doc, Index, Result};
+/// # use tantivy::collector::Count;
+/// # use tantivy::Result;
+/// # use tantivy::query::RangeQuery;
 /// #
 /// # fn run() -> Result<()> {
 /// #     let mut schema_builder = Schema::builder();

src/query/regex_query.rs

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

src/query/term_query/term_query.rs

@@ -20,10 +20,12 @@ use std::fmt;
 /// * `field norm` - number of tokens in the field.
 ///
 /// ```rust
+/// #[macro_use]
+/// extern crate tantivy;
+/// use tantivy::schema::{Schema, TEXT, IndexRecordOption};
+/// use tantivy::{Index, Result, Term};
 /// use tantivy::collector::{Count, TopDocs};
 /// use tantivy::query::TermQuery;
-/// use tantivy::schema::{Schema, TEXT, IndexRecordOption};
-/// use tantivy::{doc, Index, Result, Term};
 ///
 /// # fn main() { example().unwrap(); }
 /// fn example() -> Result<()> {

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.
 ///

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);
@@ -301,26 +301,28 @@ impl Schema {
 
         let mut doc = Document::default();
         for (field_name, json_value) in json_obj.iter() {
-            let field = self
-                .get_field(field_name)
-                .ok_or_else(|| DocParsingError::NoSuchFieldInSchema(field_name.clone()))?;
-            let field_entry = self.get_field_entry(field);
-            let field_type = field_entry.field_type();
-            match *json_value {
-                JsonValue::Array(ref json_items) => {
-                    for json_item in json_items {
-                        let value = field_type
-                            .value_from_json(json_item)
-                            .map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
-                        doc.add(FieldValue::new(field, value));
+            match self.get_field(field_name) {
+                Some(field) => {
+                    let field_entry = self.get_field_entry(field);
+                    let field_type = field_entry.field_type();
+                    match *json_value {
+                        JsonValue::Array(ref json_items) => {
+                            for json_item in json_items {
+                                let value = field_type.value_from_json(json_item).map_err(|e| {
+                                    DocParsingError::ValueError(field_name.clone(), e)
+                                })?;
+                                doc.add(FieldValue::new(field, value));
+                            }
+                        }
+                        _ => {
+                            let value = field_type
+                                .value_from_json(json_value)
+                                .map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
+                            doc.add(FieldValue::new(field, value));
+                        }
                     }
                 }
-                _ => {
-                    let value = field_type
-                        .value_from_json(json_value)
-                        .map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
-                    doc.add(FieldValue::new(field, value));
-                }
+                None => return Err(DocParsingError::NoSuchFieldInSchema(field_name.clone())),
             }
         }
         Ok(doc)

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;
@@ -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
@@ -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/snippet/mod.rs

@@ -213,9 +213,11 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
 /// # Example
 ///
 /// ```rust
-/// # use tantivy::query::QueryParser;
+/// # #[macro_use]
+/// # extern crate tantivy;
+/// # use tantivy::Index;
 /// # use tantivy::schema::{Schema, TEXT};
-/// # use tantivy::{doc, Index};
+/// # use tantivy::query::QueryParser;
 /// use tantivy::SnippetGenerator;
 ///
 /// # fn main() -> tantivy::Result<()> {

src/termdict/streamer.rs

@@ -2,7 +2,7 @@ use super::TermDictionary;
 use crate::postings::TermInfo;
 use crate::termdict::TermOrdinal;
 use tantivy_fst::automaton::AlwaysMatch;
-use tantivy_fst::map::{Stream, StreamBuilder};
+use tantivy_fst::map::{Stream, StreamBuilder, StreamWithState};
 use tantivy_fst::Automaton;
 use tantivy_fst::{IntoStreamer, Streamer};
 
@@ -11,6 +11,7 @@ use tantivy_fst::{IntoStreamer, Streamer};
 pub struct TermStreamerBuilder<'a, A = AlwaysMatch>
 where
     A: Automaton,
+    A::State: Clone,
 {
     fst_map: &'a TermDictionary,
     stream_builder: StreamBuilder<'a, A>,
@@ -19,6 +20,7 @@ where
 impl<'a, A> TermStreamerBuilder<'a, A>
 where
     A: Automaton,
+    A::State: Clone + Default + Sized,
 {
     pub(crate) fn new(fst_map: &'a TermDictionary, stream_builder: StreamBuilder<'a, A>) -> Self {
         TermStreamerBuilder {
@@ -56,10 +58,11 @@ where
     pub fn into_stream(self) -> TermStreamer<'a, A> {
         TermStreamer {
             fst_map: self.fst_map,
-            stream: self.stream_builder.into_stream(),
+            stream: self.stream_builder.with_state().into_stream(),
             term_ord: 0u64,
             current_key: Vec::with_capacity(100),
             current_value: TermInfo::default(),
+            state: Default::default(),
         }
     }
 }
@@ -69,27 +72,31 @@ where
 pub struct TermStreamer<'a, A = AlwaysMatch>
 where
     A: Automaton,
+    A::State: Clone + Default + Sized,
 {
     fst_map: &'a TermDictionary,
-    stream: Stream<'a, A>,
+    stream: StreamWithState<'a, A>,
     term_ord: TermOrdinal,
     current_key: Vec<u8>,
     current_value: TermInfo,
+    state: A::State,
 }
 
 impl<'a, A> TermStreamer<'a, A>
 where
     A: Automaton,
+    A::State: Clone + Default + Sized,
 {
     /// Advance position the stream on the next item.
     /// Before the first call to `.advance()`, the stream
     /// is an unitialized state.
     pub fn advance(&mut self) -> bool {
-        if let Some((term, term_ord)) = self.stream.next() {
+        if let Some((term, term_ord, state)) = self.stream.next() {
             self.current_key.clear();
             self.current_key.extend_from_slice(term);
             self.term_ord = term_ord;
             self.current_value = self.fst_map.term_info_from_ord(term_ord);
+            self.state = state;
             true
         } else {
             false
@@ -118,6 +125,10 @@ where
         &self.current_key
     }
 
+    pub fn state(&self) -> &A::State {
+        &self.state
+    }
+
     /// Accesses the current value.
     ///
     /// Calling `.value()` after the end of the stream will return the

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/termdict/termdict.rs

@@ -197,7 +197,11 @@ impl TermDictionary {
 
     /// Returns a search builder, to stream all of the terms
     /// within the Automaton
-    pub fn search<'a, A: Automaton + 'a>(&'a self, automaton: A) -> TermStreamerBuilder<'a, A> {
+    pub fn search<'a, A>(&'a self, automaton: A) -> TermStreamerBuilder<'a, A>
+    where
+        A: Automaton + 'a,
+        A::State: Clone + Default + Sized,
+    {
         let stream_builder = self.fst_index.search(automaton);
         TermStreamerBuilder::<A>::new(self, stream_builder)
     }

src/tokenizer/alphanum_only.rs

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

src/tokenizer/ascii_folding_filter.rs

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

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

@@ -29,8 +29,9 @@ use super::{Token, TokenStream, Tokenizer};
 ///
 /// # Example
 ///
-/// ```rust
-/// use tantivy_tokenizer::*;
+/// ```
+/// # extern crate tantivy;
+/// use tantivy::tokenizer::*;
 /// # fn main() {
 /// let tokenizer = NgramTokenizer::new(2, 3, false);
 /// let mut stream = tokenizer.token_stream("hello");
@@ -308,9 +309,9 @@ mod tests {
     use super::CodepointFrontiers;
     use super::NgramTokenizer;
     use super::StutteringIterator;
-    use crate::tests::assert_token;
-    use crate::tokenizer::{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 +1,7 @@
 //! # Example
-//! ```rust
-//! use tantivy_tokenizer::*;
+//! ```
+//! extern crate tantivy;
+//! use tantivy::tokenizer::*;
 //!
 //! # fn main() {
 //!

src/tokenizer/stemmer.rs

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

src/tokenizer/stop_word_filter.rs

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

src/tokenizer/token_stream_chain.rs

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

src/tokenizer/tokenizer.rs

@@ -1,4 +1,4 @@
-use crate::TokenStreamChain;
+use crate::tokenizer::TokenStreamChain;
 /// The tokenizer module contains all of the tools used to process
 /// text in `tantivy`.
 use std::borrow::{Borrow, BorrowMut};
@@ -56,7 +56,7 @@ 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"}