Integrated state into TermDict streamer

Closes #629

.travis.yml

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

CHANGELOG.md

@@ -2,6 +2,15 @@ Tantivy 0.11.0
 =====================
 
 - Added f64 field. Internally reuse u64 code the same way i64 does (@fdb-hiroshima)
+- Various bugfixes in the query parser.
+    - Better handling of hyphens in query parser. (#609)
+    - Better handling of whitespaces.
+- Closes #498 - add support for Elastic-style unbounded range queries for alphanumeric types eg. "title:>hello", "weight:>=70.5", "height:<200" (@petr-tik)
+- API change around `Box<BoxableTokenizer>`. See detail in #629
+
+## How to update?
+
+`Box<dyn BoxableTokenizer>` has been replaced by a `BoxedTokenizer` struct.
 
 Tantivy 0.10.1
 =====================

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy"
-version = "0.10.1"
+version = "0.11.0"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
@@ -17,7 +17,7 @@ base64 = "0.10.0"
 byteorder = "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"}
@@ -25,7 +25,6 @@ atomicwrites = {version="0.2.2", optional=true}
 tempfile = "3.0"
 log = "0.4"
 combine = ">=3.6.0,<4.0.0"
-tempdir = "0.3"
 serde = "1.0"
 serde_derive = "1.0"
 serde_json = "1.0"
@@ -36,7 +35,7 @@ levenshtein_automata = {version="0.1", features=["fst_automaton"]}
 notify = {version="4", optional=true}
 bit-set = "0.5"
 uuid = { version = "0.7.2", features = ["v4", "serde"] }
-crossbeam = "0.5"
+crossbeam = "0.7"
 futures = "0.1"
 futures-cpupool = "0.1"
 owning_ref = "0.4"
@@ -87,7 +86,6 @@ travis-ci = { repository = "tantivy-search/tantivy" }
 [dev-dependencies.fail]
 features = ["failpoints"]
 
-
 # Following the "fail" crate best practises, we isolate
 # tests that define specific behavior in fail check points
 # in a different binary.
@@ -98,4 +96,4 @@ features = ["failpoints"]
 [[test]]
 name = "failpoints"
 path = "tests/failpoints/mod.rs"
-required-features = ["fail/failpoints"]
+required-features = ["fail/failpoints"]

examples/basic_search.rs

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

examples/faceted_search.rs

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

examples/snippet.rs

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

src/collector/top_score_collector.rs

@@ -13,6 +13,7 @@ use crate::Result;
 use crate::Score;
 use crate::SegmentLocalId;
 use crate::SegmentReader;
+use std::fmt;
 
 /// The Top Score Collector keeps track of the K documents
 /// sorted by their score.
@@ -68,6 +69,12 @@ use crate::SegmentReader;
 /// ```
 pub struct TopDocs(TopCollector<Score>);
 
+impl fmt::Debug for TopDocs {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "TopDocs({})", self.0.limit())
+    }
+}
+
 impl TopDocs {
     /// Creates a top score collector, with a number of documents equal to "limit".
     ///
@@ -584,7 +591,7 @@ mod tests {
         query_field: Field,
         schema: Schema,
         mut doc_adder: impl FnMut(&mut IndexWriter) -> (),
-    ) -> (Index, Box<Query>) {
+    ) -> (Index, Box<dyn Query>) {
         let index = Index::create_in_ram(schema);
 
         let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();

src/common/mod.rs

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

src/core/index.rs

@@ -173,11 +173,11 @@ impl Index {
     }
 
     /// Helper to access the tokenizer associated to a specific field.
-    pub fn tokenizer_for_field(&self, field: Field) -> Result<Box<dyn BoxedTokenizer>> {
+    pub fn tokenizer_for_field(&self, field: Field) -> Result<BoxedTokenizer> {
         let field_entry = self.schema.get_field_entry(field);
         let field_type = field_entry.field_type();
         let tokenizer_manager: &TokenizerManager = self.tokenizers();
-        let tokenizer_name_opt: Option<Box<dyn BoxedTokenizer>> = match field_type {
+        let tokenizer_name_opt: Option<BoxedTokenizer> = match field_type {
             FieldType::Str(text_options) => text_options
                 .get_indexing_options()
                 .map(|text_indexing_options| text_indexing_options.tokenizer().to_string())
@@ -459,13 +459,13 @@ mod tests {
 
         use super::*;
         use std::path::PathBuf;
-        use tempdir::TempDir;
+        use tempfile::TempDir;
 
         #[test]
         fn test_index_on_commit_reload_policy_mmap() {
             let schema = throw_away_schema();
             let field = schema.get_field("num_likes").unwrap();
-            let tempdir = TempDir::new("index").unwrap();
+            let tempdir = TempDir::new().unwrap();
             let tempdir_path = PathBuf::from(tempdir.path());
             let index = Index::create_in_dir(&tempdir_path, schema).unwrap();
             let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
@@ -504,7 +504,7 @@ mod tests {
         fn test_index_on_commit_reload_policy_different_directories() {
             let schema = throw_away_schema();
             let field = schema.get_field("num_likes").unwrap();
-            let tempdir = TempDir::new("index").unwrap();
+            let tempdir = TempDir::new().unwrap();
             let tempdir_path = PathBuf::from(tempdir.path());
             let write_index = Index::create_in_dir(&tempdir_path, schema).unwrap();
             let read_index = Index::open_in_dir(&tempdir_path).unwrap();

src/directory/directory.rs

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

src/directory/managed_directory.rs

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

src/directory/mmap_directory.rs

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

src/directory/ram_directory.rs

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

src/fastfield/writer.rs

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

src/indexer/index_writer.rs

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

src/indexer/segment_writer.rs

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

src/lib.rs

@@ -1,9 +1,9 @@
 #![doc(html_logo_url = "http://fulmicoton.com/tantivy-logo/tantivy-logo.png")]
+#![recursion_limit = "100"]
 #![cfg_attr(all(feature = "unstable", test), feature(test))]
 #![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))]
 #![doc(test(attr(allow(unused_variables), deny(warnings))))]
 #![warn(missing_docs)]
-#![recursion_limit = "80"]
 
 //! # `tantivy`
 //!
@@ -12,7 +12,7 @@
 //!
 //! ```rust
 
-//! # extern crate tempdir;
+//! # extern crate tempfile;
 //! #
 //! #[macro_use]
 //! extern crate tantivy;
@@ -20,7 +20,7 @@
 //! // ...
 //!
 //! # use std::path::Path;
-//! # use tempdir::TempDir;
+//! # use tempfile::TempDir;
 //! # use tantivy::Index;
 //! # use tantivy::schema::*;
 //! # use tantivy::{Score, DocAddress};
@@ -30,7 +30,7 @@
 //! # fn main() {
 //! #     // Let's create a temporary directory for the
 //! #     // sake of this example
-//! #     if let Ok(dir) = TempDir::new("tantivy_example_dir") {
+//! #     if let Ok(dir) = TempDir::new() {
 //! #         run_example(dir.path()).unwrap();
 //! #         dir.close().unwrap();
 //! #     }
@@ -171,16 +171,16 @@ pub use self::snippet::{Snippet, SnippetGenerator};
 mod docset;
 pub use self::docset::{DocSet, SkipResult};
 
+pub use crate::common::{f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
 pub use crate::core::SegmentComponent;
 pub use crate::core::{Index, IndexMeta, Searcher, Segment, SegmentId, SegmentMeta};
 pub use crate::core::{InvertedIndexReader, SegmentReader};
 pub use crate::directory::Directory;
 pub use crate::indexer::IndexWriter;
 pub use crate::postings::Postings;
+pub use crate::reader::LeasedItem;
 pub use crate::schema::{Document, Term};
 
-pub use crate::common::{i64_to_u64, u64_to_i64, f64_to_u64, u64_to_f64};
-
 /// Expose the current version of tantivy, as well
 /// whether it was compiled with the simd compression.
 pub fn version() -> &'static str {
@@ -849,7 +849,8 @@ mod tests {
         let index = Index::create_in_ram(schema);
         let mut index_writer = index.writer_with_num_threads(1, 50_000_000).unwrap();
         {
-            let document = doc!(fast_field_unsigned => 4u64, fast_field_signed=>4i64, fast_field_float=>4f64);
+            let document =
+                doc!(fast_field_unsigned => 4u64, fast_field_signed=>4i64, fast_field_float=>4f64);
             index_writer.add_document(document);
             index_writer.commit().unwrap();
         }

src/query/automaton_weight.rs

@@ -14,6 +14,7 @@ use tantivy_fst::Automaton;
 pub struct AutomatonWeight<A>
 where
     A: Automaton + Send + Sync + 'static,
+    A::State: Clone + Default + Sized,
 {
     field: Field,
     automaton: A,
@@ -22,6 +23,7 @@ where
 impl<A> AutomatonWeight<A>
 where
     A: Automaton + Send + Sync + 'static,
+    A::State: Clone + Default + Sized,
 {
     /// Create a new AutomationWeight
     pub fn new(field: Field, automaton: A) -> AutomatonWeight<A> {
@@ -37,6 +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/fuzzy_query.rs

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

src/query/query_parser/logical_ast.rs

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

src/query/query_parser/query_grammar.rs

@@ -1,4 +1,3 @@
-use super::query_grammar;
 use super::user_input_ast::*;
 use crate::query::occur::Occur;
 use crate::query::query_parser::user_input_ast::UserInputBound;
@@ -13,22 +12,25 @@ parser! {
         (
             letter(),
             many(satisfy(|c: char| c.is_alphanumeric() || c == '_')),
-        ).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
+        ).skip(char(':')).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
     }
 }
 
 parser! {
     fn word[I]()(I) -> String
     where [I: Stream<Item = char>] {
-        many1(satisfy(|c: char| c.is_alphanumeric() || c=='.'))
-               .and_then(|s: String| {
-                   match s.as_str() {
-                     "OR" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
-                     "AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
-                     "NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
-                     _ => Ok(s)
-                   }
-               })
+        (
+            satisfy(|c: char| !c.is_whitespace() && !['-', '`', ':', '{', '}', '"', '[', ']', '(',')'].contains(&c) ),
+            many(satisfy(|c: char| !c.is_whitespace() && ![':', '{', '}', '"', '[', ']', '(',')'].contains(&c)))
+        )
+        .map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
+        .and_then(|s: String|
+           match s.as_str() {
+             "OR" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
+             "AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
+             "NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
+             _ => Ok(s)
+           })
     }
 }
 
@@ -37,12 +39,13 @@ parser! {
     where [I: Stream<Item = char>]
     {
         let term_val = || {
-            let phrase = (char('"'), many1(satisfy(|c| c != '"')), char('"')).map(|(_, s, _)| s);
+            let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
             phrase.or(word())
         };
         let term_val_with_field = negative_number().or(term_val());
         let term_query =
-            (field(), char(':'), term_val_with_field).map(|(field_name, _, phrase)| UserInputLiteral {
+            (field(), term_val_with_field)
+            .map(|(field_name, phrase)| UserInputLiteral {
                 field_name: Some(field_name),
                 phrase,
             });
@@ -60,8 +63,15 @@ parser! {
     fn negative_number[I]()(I) -> String
     where [I: Stream<Item = char>]
     {
-            (char('-'), many1(satisfy(char::is_numeric)))
-                .map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
+        (char('-'), many1(satisfy(char::is_numeric)),
+         optional((char('.'), many1(satisfy(char::is_numeric)))))
+            .map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
+                if let Some(('.', s3)) = s3 {
+                    format!("{}{}.{}", s1, s2, s3)
+                } else {
+                    format!("{}{}", s1, s2)
+                }
+            })
     }
 }
 
@@ -73,55 +83,93 @@ parser! {
 }
 
 parser! {
+    /// Function that parses a range out of a Stream
+    /// Supports ranges like:
+    /// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
+    /// [a TO *], [a TO c], [abc TO bcd}
     fn range[I]()(I) -> UserInputLeaf
     where [I: Stream<Item = char>] {
-        let term_val = || {
-            word().or(negative_number()).or(char('*').map(|_| "*".to_string()))
+        let range_term_val = || {
+            word().or(negative_number()).or(char('*').with(value("*".to_string())))
         };
-        let lower_bound = {
-            let excl = (char('{'), term_val()).map(|(_, w)| UserInputBound::Exclusive(w));
-            let incl = (char('['), term_val()).map(|(_, w)| UserInputBound::Inclusive(w));
-            attempt(excl).or(incl)
-        };
-        let upper_bound = {
-            let excl = (term_val(), char('}')).map(|(w, _)| UserInputBound::Exclusive(w));
-            let incl = (term_val(), char(']')).map(|(w, _)| UserInputBound::Inclusive(w));
-            attempt(excl).or(incl)
-        };
-        (
-            optional((field(), char(':')).map(|x| x.0)),
-            lower_bound,
-            spaces(),
-            string("TO"),
-            spaces(),
-            upper_bound,
-        ).map(|(field, lower, _, _, _, upper)| UserInputLeaf::Range {
-                field,
-                lower,
-                upper
+
+        // check for unbounded range in the form of <5, <=10, >5, >=5
+        let elastic_unbounded_range = (choice([attempt(string(">=")),
+                                               attempt(string("<=")),
+                                               attempt(string("<")),
+                                               attempt(string(">"))])
+                                       .skip(spaces()),
+                                       range_term_val()).
+            map(|(comparison_sign, bound): (&str, String)|
+                match comparison_sign {
+                    ">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
+                    "<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
+                    "<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
+                    ">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
+                    // default case
+                    _ => (UserInputBound::Unbounded, UserInputBound::Unbounded)
+                });
+        let lower_bound = (one_of("{[".chars()), range_term_val())
+            .map(|(boundary_char, lower_bound): (char, String)|
+                 if lower_bound == "*" {
+                     UserInputBound::Unbounded
+                 } else if boundary_char == '{' {
+                         UserInputBound::Exclusive(lower_bound)
+                 } else {
+                     UserInputBound::Inclusive(lower_bound)
+                 });
+        let upper_bound = (range_term_val(), one_of("}]".chars()))
+            .map(|(higher_bound, boundary_char): (String, char)|
+                 if higher_bound == "*" {
+                     UserInputBound::Unbounded
+                 } else if boundary_char == '}' {
+                     UserInputBound::Exclusive(higher_bound)
+                 } else {
+                     UserInputBound::Inclusive(higher_bound)
+                 });
+         // return only lower and upper
+        let lower_to_upper = (lower_bound.
+                                    skip((spaces(),
+                                          string("TO"),
+                                          spaces())),
+                                    upper_bound);
+
+        (optional(field()).skip(spaces()),
+         // try elastic first, if it matches, the range is unbounded
+         attempt(elastic_unbounded_range).or(lower_to_upper))
+            .map(|(field, (lower, upper))|
+                 // Construct the leaf from extracted field (optional)
+                 // and bounds
+                 UserInputLeaf::Range {
+                     field,
+                     lower,
+                     upper
         })
     }
 }
 
+fn negate(expr: UserInputAST) -> UserInputAST {
+    expr.unary(Occur::MustNot)
+}
+
+fn must(expr: UserInputAST) -> UserInputAST {
+    expr.unary(Occur::Must)
+}
+
 parser! {
     fn leaf[I]()(I) -> UserInputAST
     where [I: Stream<Item = char>] {
-         (char('-'), leaf()).map(|(_, expr)| expr.unary(Occur::MustNot) )
-        .or((char('+'), leaf()).map(|(_, expr)| expr.unary(Occur::Must) ))
-        .or((char('('), parse_to_ast(), char(')')).map(|(_, expr, _)| expr))
-        .or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All) ))
-        .or(attempt(
-            (string("NOT"), spaces1(), leaf()).map(|(_, _, expr)| expr.unary(Occur::MustNot))
-            )
-         )
-        .or(attempt(
-            range().map(UserInputAST::from)
-            )
-        )
-        .or(literal().map(|leaf| UserInputAST::Leaf(Box::new(leaf))))
+            char('-').with(leaf()).map(negate)
+        .or(char('+').with(leaf()).map(must))
+        .or(char('(').with(ast()).skip(char(')')))
+        .or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All)))
+        .or(attempt(string("NOT").skip(spaces1()).with(leaf()).map(negate)))
+        .or(attempt(range().map(UserInputAST::from)))
+        .or(literal().map(UserInputAST::from))
     }
 }
 
+#[derive(Clone, Copy)]
 enum BinaryOperand {
     Or,
     And,
@@ -129,27 +177,54 @@ enum BinaryOperand {
 
 parser! {
     fn binary_operand[I]()(I) -> BinaryOperand
-    where [I: Stream<Item = char>] {
-        (spaces1(),
-         (
-            string("AND").map(|_| BinaryOperand::And)
-           .or(string("OR").map(|_| BinaryOperand::Or))
-         ),
-         spaces1()).map(|(_, op,_)| op)
+    where [I: Stream<Item = char>]
+    {
+       string("AND").with(value(BinaryOperand::And))
+       .or(string("OR").with(value(BinaryOperand::Or)))
     }
 }
 
-enum Element {
-    SingleEl(UserInputAST),
-    NormalDisjunctive(Vec<Vec<UserInputAST>>),
+fn aggregate_binary_expressions(
+    left: UserInputAST,
+    others: Vec<(BinaryOperand, UserInputAST)>,
+) -> UserInputAST {
+    let mut dnf: Vec<Vec<UserInputAST>> = vec![vec![left]];
+    for (operator, operand_ast) in others {
+        match operator {
+            BinaryOperand::And => {
+                if let Some(last) = dnf.last_mut() {
+                    last.push(operand_ast);
+                }
+            }
+            BinaryOperand::Or => {
+                dnf.push(vec![operand_ast]);
+            }
+        }
+    }
+    if dnf.len() == 1 {
+        UserInputAST::and(dnf.into_iter().next().unwrap()) //< safe
+    } else {
+        let conjunctions = dnf.into_iter().map(UserInputAST::and).collect();
+        UserInputAST::or(conjunctions)
+    }
 }
 
-impl Element {
-    pub fn into_dnf(self) -> Vec<Vec<UserInputAST>> {
-        match self {
-            Element::NormalDisjunctive(conjunctions) => conjunctions,
-            Element::SingleEl(el) => vec![vec![el]],
-        }
+parser! {
+    pub fn ast[I]()(I) -> UserInputAST
+    where [I: Stream<Item = char>]
+    {
+        let operand_leaf = (binary_operand().skip(spaces()), leaf().skip(spaces()));
+        let boolean_expr = (leaf().skip(spaces().silent()), many1(operand_leaf)).map(
+            |(left, right)| aggregate_binary_expressions(left,right));
+        let whitespace_separated_leaves = many1(leaf().skip(spaces().silent()))
+        .map(|subqueries: Vec<UserInputAST>|
+            if subqueries.len() == 1 {
+                subqueries.into_iter().next().unwrap()
+            } else {
+                UserInputAST::Clause(subqueries.into_iter().collect())
+            });
+        let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
+        spaces().with(expr).skip(spaces())
     }
 }
 
@@ -157,56 +232,7 @@ parser! {
     pub fn parse_to_ast[I]()(I) -> UserInputAST
     where [I: Stream<Item = char>]
     {
-        (
-            attempt(
-                chainl1(
-                    leaf().map(Element::SingleEl),
-                    binary_operand().map(|op: BinaryOperand|
-                        move |left: Element, right: Element| {
-                            let mut dnf = left.into_dnf();
-                            if let Element::SingleEl(el) = right {
-                                match op {
-                                    BinaryOperand::And => {
-                                        if let Some(last) = dnf.last_mut() {
-                                            last.push(el);
-                                        }
-                                    }
-                                    BinaryOperand::Or => {
-                                        dnf.push(vec!(el));
-                                    }
-                                }
-                            } else {
-                                unreachable!("Please report.")
-                            }
-                            Element::NormalDisjunctive(dnf)
-                        }
-                    )
-                )
-                .map(query_grammar::Element::into_dnf)
-                .map(|fnd| {
-                    if fnd.len() == 1 {
-                        UserInputAST::and(fnd.into_iter().next().unwrap()) //< safe
-                    } else {
-                        let conjunctions = fnd
-                        .into_iter()
-                        .map(UserInputAST::and)
-                        .collect();
-                        UserInputAST::or(conjunctions)
-                    }
-                })
-            )
-            .or(
-                sep_by(leaf(), spaces())
-                .map(|subqueries: Vec<UserInputAST>| {
-                    if subqueries.len() == 1 {
-                        subqueries.into_iter().next().unwrap()
-                    } else {
-                        UserInputAST::Clause(subqueries.into_iter().collect())
-                    }
-                })
-            )
-        )
-
+        spaces().with(optional(ast()).skip(eof())).map(|opt_ast| opt_ast.unwrap_or_else(UserInputAST::empty_query))
     }
 }
 
@@ -225,6 +251,18 @@ mod test {
         assert!(parse_to_ast().parse(query).is_err());
     }
 
+    #[test]
+    fn test_parse_empty_to_ast() {
+        test_parse_query_to_ast_helper("", "<emptyclause>");
+    }
+
+    #[test]
+    fn test_parse_query_to_ast_hyphen() {
+        test_parse_query_to_ast_helper("\"www-form-encoded\"", "\"www-form-encoded\"");
+        test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
+        test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
+    }
+
     #[test]
     fn test_parse_query_to_ast_not_op() {
         assert_eq!(
@@ -259,8 +297,67 @@ mod test {
         );
     }
 
+    #[test]
+    fn test_parse_elastic_query_ranges() {
+        test_parse_query_to_ast_helper("title: >a", "title:{\"a\" TO \"*\"}");
+        test_parse_query_to_ast_helper("title:>=a", "title:[\"a\" TO \"*\"}");
+        test_parse_query_to_ast_helper("title: <a", "title:{\"*\" TO \"a\"}");
+        test_parse_query_to_ast_helper("title:<=a", "title:{\"*\" TO \"a\"]");
+        test_parse_query_to_ast_helper("title:<=bsd", "title:{\"*\" TO \"bsd\"]");
+
+        test_parse_query_to_ast_helper("weight: >70", "weight:{\"70\" TO \"*\"}");
+        test_parse_query_to_ast_helper("weight:>=70", "weight:[\"70\" TO \"*\"}");
+        test_parse_query_to_ast_helper("weight: <70", "weight:{\"*\" TO \"70\"}");
+        test_parse_query_to_ast_helper("weight:<=70", "weight:{\"*\" TO \"70\"]");
+        test_parse_query_to_ast_helper("weight: >60.7", "weight:{\"60.7\" TO \"*\"}");
+
+        test_parse_query_to_ast_helper("weight: <= 70", "weight:{\"*\" TO \"70\"]");
+
+        test_parse_query_to_ast_helper("weight: <= 70.5", "weight:{\"*\" TO \"70.5\"]");
+    }
+
+    #[test]
+    fn test_range_parser() {
+        // testing the range() parser separately
+        let res = range().parse("title: <hello").unwrap().0;
+        let expected = UserInputLeaf::Range {
+            field: Some("title".to_string()),
+            lower: UserInputBound::Unbounded,
+            upper: UserInputBound::Exclusive("hello".to_string()),
+        };
+        let res2 = range().parse("title:{* TO hello}").unwrap().0;
+        assert_eq!(res, expected);
+        assert_eq!(res2, expected);
+        let expected_weight = UserInputLeaf::Range {
+            field: Some("weight".to_string()),
+            lower: UserInputBound::Inclusive("71.2".to_string()),
+            upper: UserInputBound::Unbounded,
+        };
+
+        let res3 = range().parse("weight: >=71.2").unwrap().0;
+        let res4 = range().parse("weight:[71.2 TO *}").unwrap().0;
+        assert_eq!(res3, expected_weight);
+        assert_eq!(res4, expected_weight);
+    }
+
+    #[test]
+    fn test_parse_query_to_triming_spaces() {
+        test_parse_query_to_ast_helper("   abc", "\"abc\"");
+        test_parse_query_to_ast_helper("abc ", "\"abc\"");
+        test_parse_query_to_ast_helper("(  a OR abc)", "(?(\"a\") ?(\"abc\"))");
+        test_parse_query_to_ast_helper("(a  OR abc)", "(?(\"a\") ?(\"abc\"))");
+        test_parse_query_to_ast_helper("(a OR  abc)", "(?(\"a\") ?(\"abc\"))");
+        test_parse_query_to_ast_helper("a OR abc ", "(?(\"a\") ?(\"abc\"))");
+        test_parse_query_to_ast_helper("(a OR abc )", "(?(\"a\") ?(\"abc\"))");
+        test_parse_query_to_ast_helper("(a OR  abc) ", "(?(\"a\") ?(\"abc\"))");
+    }
+
     #[test]
     fn test_parse_query_to_ast() {
+        test_parse_query_to_ast_helper("abc", "\"abc\"");
+        test_parse_query_to_ast_helper("a b", "(\"a\" \"b\")");
+        test_parse_query_to_ast_helper("+(a b)", "+((\"a\" \"b\"))");
+        test_parse_query_to_ast_helper("+d", "+(\"d\")");
         test_parse_query_to_ast_helper("+(a b) +d", "(+((\"a\" \"b\")) +(\"d\"))");
         test_parse_query_to_ast_helper("(+a +b) d", "((+(\"a\") +(\"b\")) \"d\")");
         test_parse_query_to_ast_helper("(+a)", "+(\"a\")");
@@ -276,7 +373,7 @@ mod test {
         test_parse_query_to_ast_helper("[1 TO 5]", "[\"1\" TO \"5\"]");
         test_parse_query_to_ast_helper("foo:{a TO z}", "foo:{\"a\" TO \"z\"}");
         test_parse_query_to_ast_helper("foo:[1 TO toto}", "foo:[\"1\" TO \"toto\"}");
-        test_parse_query_to_ast_helper("foo:[* TO toto}", "foo:[\"*\" TO \"toto\"}");
+        test_parse_query_to_ast_helper("foo:[* TO toto}", "foo:{\"*\" TO \"toto\"}");
         test_parse_query_to_ast_helper("foo:[1 TO *}", "foo:[\"1\" TO \"*\"}");
         test_parse_query_to_ast_helper("foo:[1.1 TO *}", "foo:[\"1.1\" TO \"*\"}");
         test_is_parse_err("abc +    ");

src/query/query_parser/query_parser.rs

@@ -18,42 +18,56 @@ use crate::schema::{FieldType, Term};
 use crate::tokenizer::TokenizerManager;
 use combine::Parser;
 use std::borrow::Cow;
-use std::num::{ParseIntError, ParseFloatError};
+use std::num::{ParseFloatError, ParseIntError};
 use std::ops::Bound;
 use std::str::FromStr;
 
 /// Possible error that may happen when parsing a query.
-#[derive(Debug, PartialEq, Eq)]
+#[derive(Debug, PartialEq, Eq, Fail)]
 pub enum QueryParserError {
     /// Error in the query syntax
+    #[fail(display = "Syntax Error")]
     SyntaxError,
     /// `FieldDoesNotExist(field_name: String)`
     /// The query references a field that is not in the schema
+    #[fail(display = "File does not exists: '{:?}'", _0)]
     FieldDoesNotExist(String),
     /// The query contains a term for a `u64` or `i64`-field, but the value
     /// is neither.
+    #[fail(display = "Expected a valid integer: '{:?}'", _0)]
     ExpectedInt(ParseIntError),
     /// The query contains a term for a `f64`-field, but the value
     /// is not a f64.
+    #[fail(display = "Invalid query: Only excluding terms given")]
     ExpectedFloat(ParseFloatError),
     /// It is forbidden queries that are only "excluding". (e.g. -title:pop)
+    #[fail(display = "Invalid query: Only excluding terms given")]
     AllButQueryForbidden,
     /// If no default field is declared, running a query without any
     /// field specified is forbbidden.
+    #[fail(display = "No default field declared and no field specified in query")]
     NoDefaultFieldDeclared,
     /// The field searched for is not declared
     /// as indexed in the schema.
+    #[fail(display = "The field '{:?}' is not declared as indexed", _0)]
     FieldNotIndexed(String),
     /// A phrase query was requested for a field that does not
     /// have any positions indexed.
+    #[fail(display = "The field '{:?}' does not have positions indexed", _0)]
     FieldDoesNotHavePositionsIndexed(String),
     /// The tokenizer for the given field is unknown
     /// The two argument strings are the name of the field, the name of the tokenizer
+    #[fail(
+        display = "The tokenizer '{:?}' for the field '{:?}' is unknown",
+        _0, _1
+    )]
     UnknownTokenizer(String, String),
     /// The query contains a range query with a phrase as one of the bounds.
     /// Only terms can be used as bounds.
+    #[fail(display = "A range query cannot have a phrase as one of the bounds")]
     RangeMustNotHavePhrase,
     /// The format for the date field is not RFC 3339 compliant.
+    #[fail(display = "The date field has an invalid format")]
     DateFormatError(chrono::ParseError),
 }
 
@@ -355,6 +369,7 @@ impl QueryParser {
         match *bound {
             UserInputBound::Inclusive(_) => Ok(Bound::Included(term)),
             UserInputBound::Exclusive(_) => Ok(Bound::Excluded(term)),
+            UserInputBound::Unbounded => Ok(Bound::Unbounded),
         }
     }
 
@@ -614,7 +629,7 @@ mod test {
     pub fn test_parse_query_untokenized() {
         test_parse_query_to_logical_ast_helper(
             "nottokenized:\"wordone wordtwo\"",
-            "Term([0, 0, 0, 7, 119, 111, 114, 100, 111, 110, \
+            "Term(field=7,bytes=[119, 111, 114, 100, 111, 110, \
              101, 32, 119, 111, 114, 100, 116, 119, 111])",
             false,
         );
@@ -658,7 +673,7 @@ mod test {
             .is_ok());
         test_parse_query_to_logical_ast_helper(
             "unsigned:2324",
-            "Term([0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 9, 20])",
+            "Term(field=3,bytes=[0, 0, 0, 0, 0, 0, 9, 20])",
             false,
         );
 
@@ -676,22 +691,22 @@ mod test {
     }
 
     #[test]
-    pub fn test_parse_query_to_ast_disjunction() {
+    pub fn test_parse_query_to_ast_single_term() {
         test_parse_query_to_logical_ast_helper(
             "title:toto",
-            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
+            "Term(field=0,bytes=[116, 111, 116, 111])",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto",
-            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
+            "Term(field=0,bytes=[116, 111, 116, 111])",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto -titi",
-            "(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
-             -(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
-             Term([0, 0, 0, 1, 116, 105, 116, 105])))",
+            "(+Term(field=0,bytes=[116, 111, 116, 111]) \
+             -(Term(field=0,bytes=[116, 105, 116, 105]) \
+             Term(field=1,bytes=[116, 105, 116, 105])))",
             false,
         );
         assert_eq!(
@@ -700,49 +715,67 @@ mod test {
                 .unwrap(),
             QueryParserError::AllButQueryForbidden
         );
+    }
+
+    #[test]
+    pub fn test_parse_query_to_ast_two_terms() {
         test_parse_query_to_logical_ast_helper(
             "title:a b",
-            "(Term([0, 0, 0, 0, 97]) (Term([0, 0, 0, 0, 98]) \
-             Term([0, 0, 0, 1, 98])))",
+            "(Term(field=0,bytes=[97]) (Term(field=0,bytes=[98]) Term(field=1,bytes=[98])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:\"a b\"",
-            "\"[(0, Term([0, 0, 0, 0, 97])), \
-             (1, Term([0, 0, 0, 0, 98]))]\"",
+            "\"[(0, Term(field=0,bytes=[97])), \
+             (1, Term(field=0,bytes=[98]))]\"",
             false,
         );
+    }
+
+    #[test]
+    pub fn test_parse_query_to_ast_ranges() {
         test_parse_query_to_logical_ast_helper(
             "title:[a TO b]",
-            "(Included(Term([0, 0, 0, 0, 97])) TO \
-             Included(Term([0, 0, 0, 0, 98])))",
+            "(Included(Term(field=0,bytes=[97])) TO Included(Term(field=0,bytes=[98])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "[a TO b]",
-            "((Included(Term([0, 0, 0, 0, 97])) TO \
-             Included(Term([0, 0, 0, 0, 98]))) \
-             (Included(Term([0, 0, 0, 1, 97])) TO \
-             Included(Term([0, 0, 0, 1, 98]))))",
+            "((Included(Term(field=0,bytes=[97])) TO \
+             Included(Term(field=0,bytes=[98]))) \
+             (Included(Term(field=1,bytes=[97])) TO \
+             Included(Term(field=1,bytes=[98]))))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:{titi TO toto}",
-            "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO \
-             Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
+            "(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO \
+             Excluded(Term(field=0,bytes=[116, 111, 116, 111])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:{* TO toto}",
-            "(Unbounded TO \
-             Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
+            "(Unbounded TO Excluded(Term(field=0,bytes=[116, 111, 116, 111])))",
             false,
         );
         test_parse_query_to_logical_ast_helper(
             "title:{titi TO *}",
-            "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO Unbounded)",
+            "(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO Unbounded)",
             false,
         );
+        test_parse_query_to_logical_ast_helper(
+            "signed:{-5 TO 3}",
+            "(Excluded(Term(field=2,bytes=[127, 255, 255, 255, 255, 255, 255, 251])) TO \
+             Excluded(Term(field=2,bytes=[128, 0, 0, 0, 0, 0, 0, 3])))",
+            false,
+        );
+        test_parse_query_to_logical_ast_helper(
+            "float:{-1.5 TO 1.5}",
+            "(Excluded(Term(field=10,bytes=[64, 7, 255, 255, 255, 255, 255, 255])) TO \
+             Excluded(Term(field=10,bytes=[191, 248, 0, 0, 0, 0, 0, 0])))",
+            false,
+        );
+
         test_parse_query_to_logical_ast_helper("*", "*", false);
     }
 
@@ -844,19 +877,19 @@ mod test {
     pub fn test_parse_query_to_ast_conjunction() {
         test_parse_query_to_logical_ast_helper(
             "title:toto",
-            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
+            "Term(field=0,bytes=[116, 111, 116, 111])",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto",
-            "Term([0, 0, 0, 0, 116, 111, 116, 111])",
+            "Term(field=0,bytes=[116, 111, 116, 111])",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "+title:toto -titi",
-            "(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
-             -(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
-             Term([0, 0, 0, 1, 116, 105, 116, 105])))",
+            "(+Term(field=0,bytes=[116, 111, 116, 111]) \
+             -(Term(field=0,bytes=[116, 105, 116, 105]) \
+             Term(field=1,bytes=[116, 105, 116, 105])))",
             true,
         );
         assert_eq!(
@@ -867,16 +900,25 @@ mod test {
         );
         test_parse_query_to_logical_ast_helper(
             "title:a b",
-            "(+Term([0, 0, 0, 0, 97]) \
-             +(Term([0, 0, 0, 0, 98]) \
-             Term([0, 0, 0, 1, 98])))",
+            "(+Term(field=0,bytes=[97]) \
+             +(Term(field=0,bytes=[98]) \
+             Term(field=1,bytes=[98])))",
             true,
         );
         test_parse_query_to_logical_ast_helper(
             "title:\"a b\"",
-            "\"[(0, Term([0, 0, 0, 0, 97])), \
-             (1, Term([0, 0, 0, 0, 98]))]\"",
+            "\"[(0, Term(field=0,bytes=[97])), \
+             (1, Term(field=0,bytes=[98]))]\"",
             true,
         );
     }
+
+    #[test]
+    pub fn test_query_parser_hyphen() {
+        test_parse_query_to_logical_ast_helper(
+            "title:www-form-encoded",
+            "\"[(0, Term(field=0,bytes=[119, 119, 119])), (1, Term(field=0,bytes=[102, 111, 114, 109])), (2, Term(field=0,bytes=[101, 110, 99, 111, 100, 101, 100]))]\"",
+            false
+        );
+    }
 }

src/query/query_parser/stemmer.rs

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

src/query/query_parser/user_input_ast.rs

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

src/query/range_query.rs

@@ -338,39 +338,33 @@ mod tests {
     use crate::collector::Count;
     use crate::schema::{Document, Field, Schema, INDEXED};
     use crate::Index;
-    use crate::Result;
     use std::collections::Bound;
 
     #[test]
     fn test_range_query_simple() {
-        fn run() -> Result<()> {
-            let mut schema_builder = Schema::builder();
-            let year_field = schema_builder.add_u64_field("year", INDEXED);
-            let schema = schema_builder.build();
+        let mut schema_builder = Schema::builder();
+        let year_field = schema_builder.add_u64_field("year", INDEXED);
+        let schema = schema_builder.build();
 
-            let index = Index::create_in_ram(schema);
-            {
-                let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
-                for year in 1950u64..2017u64 {
-                    let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
-                    for _ in 0..num_docs_within_year {
-                        index_writer.add_document(doc!(year_field => year));
-                    }
+        let index = Index::create_in_ram(schema);
+        {
+            let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
+            for year in 1950u64..2017u64 {
+                let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
+                for _ in 0..num_docs_within_year {
+                    index_writer.add_document(doc!(year_field => year));
                 }
-                index_writer.commit().unwrap();
             }
-            let reader = index.reader().unwrap();
-            let searcher = reader.searcher();
-
-            let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960u64..1970u64);
-
-            // ... or `1960..=1969` if inclusive range is enabled.
-            let count = searcher.search(&docs_in_the_sixties, &Count)?;
-            assert_eq!(count, 2285);
-            Ok(())
+            index_writer.commit().unwrap();
         }
+        let reader = index.reader().unwrap();
+        let searcher = reader.searcher();
 
-        run().unwrap();
+        let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960u64..1970u64);
+
+        // ... or `1960..=1969` if inclusive range is enabled.
+        let count = searcher.search(&docs_in_the_sixties, &Count).unwrap();
+        assert_eq!(count, 2285);
     }
 
     #[test]
@@ -460,7 +454,10 @@ mod tests {
         let count_multiples =
             |range_query: RangeQuery| searcher.search(&range_query, &Count).unwrap();
 
-        assert_eq!(count_multiples(RangeQuery::new_f64(float_field, 10.0..11.0)), 9);
+        assert_eq!(
+            count_multiples(RangeQuery::new_f64(float_field, 10.0..11.0)),
+            9
+        );
         assert_eq!(
             count_multiples(RangeQuery::new_f64_bounds(
                 float_field,

src/query/term_query/mod.rs

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

src/query/term_query/term_query.rs

@@ -7,6 +7,7 @@ use crate::Result;
 use crate::Searcher;
 use crate::Term;
 use std::collections::BTreeSet;
+use std::fmt;
 
 /// A Term query matches all of the documents
 /// containing a specific term.
@@ -61,12 +62,18 @@ use std::collections::BTreeSet;
 ///     Ok(())
 /// }
 /// ```
-#[derive(Clone, Debug)]
+#[derive(Clone)]
 pub struct TermQuery {
     term: Term,
     index_record_option: IndexRecordOption,
 }
 
+impl fmt::Debug for TermQuery {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "TermQuery({:?})", self.term)
+    }
+}
+
 impl TermQuery {
     /// Creates a new term query.
     pub fn new(term: Term, segment_postings_options: IndexRecordOption) -> TermQuery {

src/reader/mod.rs

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

src/reader/pool.rs

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

src/schema/facet.rs

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

src/schema/field_entry.rs

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

src/schema/field_type.rs

@@ -10,7 +10,7 @@ use serde_json::Value as JsonValue;
 
 /// Possible error that may occur while parsing a field value
 /// At this point the JSON is known to be valid.
-#[derive(Debug)]
+#[derive(Debug, PartialEq)]
 pub enum ValueParsingError {
     /// Encountered a numerical value that overflows or underflow its integer type.
     OverflowError(String),
@@ -83,9 +83,9 @@ impl FieldType {
     pub fn is_indexed(&self) -> bool {
         match *self {
             FieldType::Str(ref text_options) => text_options.get_indexing_options().is_some(),
-            FieldType::U64(ref int_options) | FieldType::I64(ref int_options) | FieldType::F64(ref int_options) => {
-                int_options.is_indexed()
-            }
+            FieldType::U64(ref int_options)
+            | FieldType::I64(ref int_options)
+            | FieldType::F64(ref int_options) => int_options.is_indexed(),
             FieldType::Date(ref date_options) => date_options.is_indexed(),
             FieldType::HierarchicalFacet => true,
             FieldType::Bytes => false,
@@ -125,9 +125,12 @@ impl FieldType {
         match *json {
             JsonValue::String(ref field_text) => match *self {
                 FieldType::Str(_) => Ok(Value::Str(field_text.clone())),
-                FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => Err(
-                    ValueParsingError::TypeError(format!("Expected an integer, got {:?}", json)),
-                ),
+                FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => {
+                    Err(ValueParsingError::TypeError(format!(
+                        "Expected an integer, got {:?}",
+                        json
+                    )))
+                }
                 FieldType::HierarchicalFacet => Ok(Value::Facet(Facet::from(field_text))),
                 FieldType::Bytes => decode(field_text).map(Value::Bytes).map_err(|_| {
                     ValueParsingError::InvalidBase64(format!(
@@ -152,7 +155,7 @@ impl FieldType {
                         let msg = format!("Expected a u64 int, got {:?}", json);
                         Err(ValueParsingError::OverflowError(msg))
                     }
-                },
+                }
                 FieldType::F64(_) => {
                     if let Some(field_val_f64) = field_val_num.as_f64() {
                         Ok(Value::F64(field_val_f64))

src/schema/schema.rs

@@ -246,6 +246,25 @@ impl Schema {
         self.0.fields_map.get(field_name).cloned()
     }
 
+    /// Create a named document off the doc.
+    pub fn convert_named_doc(
+        &self,
+        named_doc: NamedFieldDocument,
+    ) -> Result<Document, DocParsingError> {
+        let mut document = Document::new();
+        for (field_name, values) in named_doc.0 {
+            if let Some(field) = self.get_field(&field_name) {
+                for value in values {
+                    let field_value = FieldValue::new(field, value);
+                    document.add(field_value);
+                }
+            } else {
+                return Err(DocParsingError::NoSuchFieldInSchema(field_name));
+            }
+        }
+        Ok(document)
+    }
+
     /// Create a named document off the doc.
     pub fn to_named_doc(&self, doc: &Document) -> NamedFieldDocument {
         let mut field_map = BTreeMap::new();
@@ -360,13 +379,19 @@ impl<'de> Deserialize<'de> for Schema {
 
 /// Error that may happen when deserializing
 /// a document from JSON.
-#[derive(Debug)]
+#[derive(Debug, Fail, PartialEq)]
 pub enum DocParsingError {
     /// The payload given is not valid JSON.
+    #[fail(display = "The provided string is not valid JSON")]
     NotJSON(String),
     /// One of the value node could not be parsed.
+    #[fail(display = "The field '{:?}' could not be parsed: {:?}", _0, _1)]
     ValueError(String, ValueParsingError),
     /// The json-document contains a field that is not declared in the schema.
+    #[fail(
+        display = "The document contains a field that is not declared in the schema: {:?}",
+        _0
+    )]
     NoSuchFieldInSchema(String),
 }
 
@@ -378,6 +403,7 @@ mod tests {
     use crate::schema::*;
     use matches::{assert_matches, matches};
     use serde_json;
+    use std::collections::BTreeMap;
 
     #[test]
     pub fn is_indexed_test() {
@@ -492,6 +518,54 @@ mod tests {
         assert_eq!(doc, doc_serdeser);
     }
 
+    #[test]
+    pub fn test_document_from_nameddoc() {
+        let mut schema_builder = Schema::builder();
+        let title = schema_builder.add_text_field("title", TEXT);
+        let val = schema_builder.add_i64_field("val", INDEXED);
+        let schema = schema_builder.build();
+        let mut named_doc_map = BTreeMap::default();
+        named_doc_map.insert(
+            "title".to_string(),
+            vec![Value::from("title1"), Value::from("title2")],
+        );
+        named_doc_map.insert(
+            "val".to_string(),
+            vec![Value::from(14u64), Value::from(-1i64)],
+        );
+        let doc = schema
+            .convert_named_doc(NamedFieldDocument(named_doc_map))
+            .unwrap();
+        assert_eq!(
+            doc.get_all(title),
+            vec![
+                &Value::from("title1".to_string()),
+                &Value::from("title2".to_string())
+            ]
+        );
+        assert_eq!(
+            doc.get_all(val),
+            vec![&Value::from(14u64), &Value::from(-1i64)]
+        );
+    }
+
+    #[test]
+    pub fn test_document_from_nameddoc_error() {
+        let schema = Schema::builder().build();
+        let mut named_doc_map = BTreeMap::default();
+        named_doc_map.insert(
+            "title".to_string(),
+            vec![Value::from("title1"), Value::from("title2")],
+        );
+        let err = schema
+            .convert_named_doc(NamedFieldDocument(named_doc_map))
+            .unwrap_err();
+        assert_eq!(
+            err,
+            DocParsingError::NoSuchFieldInSchema("title".to_string())
+        );
+    }
+
     #[test]
     pub fn test_parse_document() {
         let mut schema_builder = Schema::builder();

src/schema/term.rs

@@ -224,7 +224,12 @@ where
 
 impl fmt::Debug for Term {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(f, "Term({:?})", &self.0[..])
+        write!(
+            f,
+            "Term(field={},bytes={:?})",
+            self.field().0,
+            self.value_bytes()
+        )
     }
 }
 

src/schema/value.rs

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

src/snippet/mod.rs

@@ -63,7 +63,7 @@ impl FragmentCandidate {
     fn try_add_token(&mut self, token: &Token, terms: &BTreeMap<String, f32>) {
         self.stop_offset = token.offset_to;
 
-        if let Some(score) = terms.get(&token.text.to_lowercase()) {
+        if let Some(&score) = terms.get(&token.text.to_lowercase()) {
             self.score += score;
             self.highlighted
                 .push(HighlightSection::new(token.offset_from, token.offset_to));
@@ -142,7 +142,7 @@ impl Snippet {
 /// Fragments must be valid in the sense that `&text[fragment.start..fragment.stop]`\
 /// has to be a valid string.
 fn search_fragments<'a>(
-    tokenizer: &dyn BoxedTokenizer,
+    tokenizer: &BoxedTokenizer,
     text: &'a str,
     terms: &BTreeMap<String, f32>,
     max_num_chars: usize,
@@ -150,7 +150,6 @@ fn search_fragments<'a>(
     let mut token_stream = tokenizer.token_stream(text);
     let mut fragment = FragmentCandidate::new(0);
     let mut fragments: Vec<FragmentCandidate> = vec![];
-
     while let Some(next) = token_stream.next() {
         if (next.offset_to - fragment.start_offset) > max_num_chars {
             if fragment.score > 0.0 {
@@ -254,7 +253,7 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
 /// ```
 pub struct SnippetGenerator {
     terms_text: BTreeMap<String, f32>,
-    tokenizer: Box<dyn BoxedTokenizer>,
+    tokenizer: BoxedTokenizer,
     field: Field,
     max_num_chars: usize,
 }
@@ -316,12 +315,8 @@ impl SnippetGenerator {
 
     /// Generates a snippet for the given text.
     pub fn snippet(&self, text: &str) -> Snippet {
-        let fragment_candidates = search_fragments(
-            &*self.tokenizer,
-            &text,
-            &self.terms_text,
-            self.max_num_chars,
-        );
+        let fragment_candidates =
+            search_fragments(&self.tokenizer, &text, &self.terms_text, self.max_num_chars);
         select_best_fragment_combination(&fragment_candidates[..], &text)
     }
 }
@@ -331,7 +326,7 @@ mod tests {
     use super::{search_fragments, select_best_fragment_combination};
     use crate::query::QueryParser;
     use crate::schema::{IndexRecordOption, Schema, TextFieldIndexing, TextOptions, TEXT};
-    use crate::tokenizer::{box_tokenizer, SimpleTokenizer};
+    use crate::tokenizer::SimpleTokenizer;
     use crate::Index;
     use crate::SnippetGenerator;
     use maplit::btreemap;
@@ -355,12 +350,12 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
         let terms = btreemap! {
             String::from("rust") => 1.0,
             String::from("language") => 0.9
         };
-        let fragments = search_fragments(&*boxed_tokenizer, TEST_TEXT, &terms, 100);
+        let fragments = search_fragments(&boxed_tokenizer, TEST_TEXT, &terms, 100);
         assert_eq!(fragments.len(), 7);
         {
             let first = &fragments[0];
@@ -382,13 +377,13 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_scored_fragment() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
         {
             let terms = btreemap! {
                 String::from("rust") =>1.0f32,
                 String::from("language") => 0.9f32
             };
-            let fragments = search_fragments(&*boxed_tokenizer, TEST_TEXT, &terms, 20);
+            let fragments = search_fragments(&boxed_tokenizer, TEST_TEXT, &terms, 20);
             {
                 let first = &fragments[0];
                 assert_eq!(first.score, 1.0);
@@ -397,13 +392,13 @@ Survey in 2016, 2017, and 2018."#;
             let snippet = select_best_fragment_combination(&fragments[..], &TEST_TEXT);
             assert_eq!(snippet.to_html(), "<b>Rust</b> is a systems")
         }
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
         {
             let terms = btreemap! {
                 String::from("rust") =>0.9f32,
                 String::from("language") => 1.0f32
             };
-            let fragments = search_fragments(&*boxed_tokenizer, TEST_TEXT, &terms, 20);
+            let fragments = search_fragments(&boxed_tokenizer, TEST_TEXT, &terms, 20);
             //assert_eq!(fragments.len(), 7);
             {
                 let first = &fragments[0];
@@ -417,14 +412,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_in_second_fragment() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         let text = "a b c d e f g";
 
         let mut terms = BTreeMap::new();
         terms.insert(String::from("c"), 1.0);
 
-        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 3);
+        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 3);
 
         assert_eq!(fragments.len(), 1);
         {
@@ -441,14 +436,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_term_at_the_end_of_fragment() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         let text = "a b c d e f f g";
 
         let mut terms = BTreeMap::new();
         terms.insert(String::from("f"), 1.0);
 
-        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 3);
+        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 3);
 
         assert_eq!(fragments.len(), 2);
         {
@@ -465,7 +460,7 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_second_fragment_has_the_highest_score() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         let text = "a b c d e f g";
 
@@ -473,7 +468,7 @@ Survey in 2016, 2017, and 2018."#;
         terms.insert(String::from("f"), 1.0);
         terms.insert(String::from("a"), 0.9);
 
-        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 7);
+        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 7);
 
         assert_eq!(fragments.len(), 2);
         {
@@ -490,14 +485,14 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_term_not_in_text() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         let text = "a b c d";
 
         let mut terms = BTreeMap::new();
         terms.insert(String::from("z"), 1.0);
 
-        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 3);
+        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 3);
 
         assert_eq!(fragments.len(), 0);
 
@@ -508,12 +503,12 @@ Survey in 2016, 2017, and 2018."#;
 
     #[test]
     fn test_snippet_with_no_terms() {
-        let boxed_tokenizer = box_tokenizer(SimpleTokenizer);
+        let boxed_tokenizer = SimpleTokenizer.into();
 
         let text = "a b c d";
 
         let terms = BTreeMap::new();
-        let fragments = search_fragments(&*boxed_tokenizer, &text, &terms, 3);
+        let fragments = search_fragments(&boxed_tokenizer, &text, &terms, 3);
         assert_eq!(fragments.len(), 0);
 
         let snippet = select_best_fragment_combination(&fragments[..], &text);

src/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/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/mod.rs

@@ -155,7 +155,6 @@ pub use self::simple_tokenizer::SimpleTokenizer;
 pub use self::stemmer::{Language, Stemmer};
 pub use self::stop_word_filter::StopWordFilter;
 pub(crate) use self::token_stream_chain::TokenStreamChain;
-pub(crate) use self::tokenizer::box_tokenizer;
 pub use self::tokenizer::BoxedTokenizer;
 
 pub use self::tokenizer::{Token, TokenFilter, TokenStream, Tokenizer};

src/tokenizer/tokenizer.rs

@@ -56,8 +56,6 @@ pub trait Tokenizer<'a>: Sized + Clone {
     /// # Example
     ///
     /// ```rust
-    /// # extern crate tantivy;
-    ///
     /// use tantivy::tokenizer::*;
     ///
     /// # fn main() {
@@ -80,7 +78,7 @@ pub trait Tokenizer<'a>: Sized + Clone {
 }
 
 /// A boxed tokenizer
-pub trait BoxedTokenizer: Send + Sync {
+trait BoxedTokenizerTrait: Send + Sync {
     /// Tokenize a `&str`
     fn token_stream<'a>(&self, text: &'a str) -> Box<dyn TokenStream + 'a>;
 
@@ -92,7 +90,41 @@ pub trait BoxedTokenizer: Send + Sync {
     fn token_stream_texts<'b>(&self, texts: &'b [&'b str]) -> Box<dyn TokenStream + 'b>;
 
     /// Return a boxed clone of the tokenizer
-    fn boxed_clone(&self) -> Box<dyn BoxedTokenizer>;
+    fn boxed_clone(&self) -> BoxedTokenizer;
+}
+
+/// A boxed tokenizer
+pub struct BoxedTokenizer(Box<dyn BoxedTokenizerTrait>);
+
+impl<T> From<T> for BoxedTokenizer
+where
+    T: 'static + Send + Sync + for<'a> Tokenizer<'a>,
+{
+    fn from(tokenizer: T) -> BoxedTokenizer {
+        BoxedTokenizer(Box::new(BoxableTokenizer(tokenizer)))
+    }
+}
+
+impl BoxedTokenizer {
+    /// Tokenize a `&str`
+    pub fn token_stream<'a>(&self, text: &'a str) -> Box<dyn TokenStream + 'a> {
+        self.0.token_stream(text)
+    }
+
+    /// Tokenize an array`&str`
+    ///
+    /// The resulting `TokenStream` is equivalent to what would be obtained if the &str were
+    /// one concatenated `&str`, with an artificial position gap of `2` between the different fields
+    /// to prevent accidental `PhraseQuery` to match accross two terms.
+    pub fn token_stream_texts<'b>(&self, texts: &'b [&'b str]) -> Box<dyn TokenStream + 'b> {
+        self.0.token_stream_texts(texts)
+    }
+}
+
+impl Clone for BoxedTokenizer {
+    fn clone(&self) -> BoxedTokenizer {
+        self.0.boxed_clone()
+    }
 }
 
 #[derive(Clone)]
@@ -100,7 +132,7 @@ struct BoxableTokenizer<A>(A)
 where
     A: for<'a> Tokenizer<'a> + Send + Sync;
 
-impl<A> BoxedTokenizer for BoxableTokenizer<A>
+impl<A> BoxedTokenizerTrait for BoxableTokenizer<A>
 where
     A: 'static + Send + Sync + for<'a> Tokenizer<'a>,
 {
@@ -125,18 +157,11 @@ where
         }
     }
 
-    fn boxed_clone(&self) -> Box<dyn BoxedTokenizer> {
-        Box::new(self.clone())
+    fn boxed_clone(&self) -> BoxedTokenizer {
+        self.0.clone().into()
     }
 }
 
-pub(crate) fn box_tokenizer<A>(a: A) -> Box<dyn BoxedTokenizer>
-where
-    A: 'static + Send + Sync + for<'a> Tokenizer<'a>,
-{
-    Box::new(BoxableTokenizer(a))
-}
-
 impl<'b> TokenStream for Box<dyn TokenStream + 'b> {
     fn advance(&mut self) -> bool {
         let token_stream: &mut dyn TokenStream = self.borrow_mut();
@@ -161,7 +186,6 @@ impl<'b> TokenStream for Box<dyn TokenStream + 'b> {
 /// # Example
 ///
 /// ```
-/// extern crate tantivy;
 /// use tantivy::tokenizer::*;
 ///
 /// # fn main() {
@@ -203,7 +227,6 @@ pub trait TokenStream {
     /// and `.token()`.
     ///
     /// ```
-    /// # extern crate tantivy;
     /// # use tantivy::tokenizer::*;
     /// #
     /// # fn main() {

src/tokenizer/tokenizer_manager.rs

@@ -1,4 +1,3 @@
-use crate::tokenizer::box_tokenizer;
 use crate::tokenizer::stemmer::Language;
 use crate::tokenizer::BoxedTokenizer;
 use crate::tokenizer::LowerCaser;
@@ -8,7 +7,6 @@ use crate::tokenizer::SimpleTokenizer;
 use crate::tokenizer::Stemmer;
 use crate::tokenizer::Tokenizer;
 use std::collections::HashMap;
-use std::ops::Deref;
 use std::sync::{Arc, RwLock};
 
 /// The tokenizer manager serves as a store for
@@ -25,16 +23,16 @@ use std::sync::{Arc, RwLock};
 ///  search engine.
 #[derive(Clone)]
 pub struct TokenizerManager {
-    tokenizers: Arc<RwLock<HashMap<String, Box<dyn BoxedTokenizer>>>>,
+    tokenizers: Arc<RwLock<HashMap<String, BoxedTokenizer>>>,
 }
 
 impl TokenizerManager {
     /// Registers a new tokenizer associated with a given name.
     pub fn register<A>(&self, tokenizer_name: &str, tokenizer: A)
     where
-        A: 'static + Send + Sync + for<'a> Tokenizer<'a>,
+        A: Into<BoxedTokenizer>,
     {
-        let boxed_tokenizer = box_tokenizer(tokenizer);
+        let boxed_tokenizer = tokenizer.into();
         self.tokenizers
             .write()
             .expect("Acquiring the lock should never fail")
@@ -42,13 +40,12 @@ impl TokenizerManager {
     }
 
     /// Accessing a tokenizer given its name.
-    pub fn get(&self, tokenizer_name: &str) -> Option<Box<dyn BoxedTokenizer>> {
+    pub fn get(&self, tokenizer_name: &str) -> Option<BoxedTokenizer> {
         self.tokenizers
             .read()
             .expect("Acquiring the lock should never fail")
             .get(tokenizer_name)
-            .map(Deref::deref)
-            .map(BoxedTokenizer::boxed_clone)
+            .cloned()
     }
 }
 

tests/failpoints/mod.rs

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