macos ci

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

.travis.yml

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

Cargo.toml

@@ -16,7 +16,7 @@ edition = "2018"
 base64 = "0.10.0"
 byteorder = "1.0"
 once_cell = "1.0"
-regex = "1.0"
+regex ={version = "1.3.0", default-features = false, features = ["std"]}
 tantivy-fst = "0.1"
 memmap = {version = "0.7", optional=true}
 lz4 = {version="1.20", optional=true}
@@ -24,7 +24,6 @@ snap = {version="0.2"}
 atomicwrites = {version="0.2.2", optional=true}
 tempfile = "3.0"
 log = "0.4"
-combine = ">=3.6.0,<4.0.0"
 serde = "1.0"
 serde_derive = "1.0"
 serde_json = "1.0"
@@ -42,6 +41,7 @@ owning_ref = "0.4"
 stable_deref_trait = "1.0.0"
 rust-stemmers = "1.1"
 downcast-rs = { version="1.0" }
+tantivy-query-grammar = { path="./query-grammar" }
 bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
 census = "0.2"
 fnv = "1.0.6"
@@ -80,10 +80,14 @@ failpoints = ["fail/failpoints"]
 unstable = [] # useful for benches.
 wasm-bindgen = ["uuid/wasm-bindgen"]
 
+[workspace]
+members = ["query-grammar"]
+
 [badges]
 travis-ci = { repository = "tantivy-search/tantivy" }
 
 [dev-dependencies.fail]
+version = "0.3"
 features = ["failpoints"]
 
 # Following the "fail" crate best practises, we isolate

Makefile

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

ci/script.sh

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

examples/multiple_producer.rs

@@ -46,10 +46,9 @@ fn main() -> tantivy::Result<()> {
     thread::spawn(move || {
         // we index 100 times the document... for the sake of the example.
         for i in 0..100 {
-            let opstamp = {
-                // A read lock is sufficient here.
-                let index_writer_rlock = index_writer_clone_1.read().unwrap();
-                index_writer_rlock.add_document(
+            let opstamp = index_writer_clone_1
+                .read().unwrap() //< A read lock is sufficient here.
+                .add_document(
                     doc!(
                         title => "Of Mice and Men",
                         body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
@@ -60,8 +59,7 @@ fn main() -> tantivy::Result<()> {
                         fresh and green with every spring, carrying in their lower leaf junctures the \
                         debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
                         limbs and branches that arch over the pool"
-                    ))
-            };
+                    ));
             println!("add doc {} from thread 1 - opstamp {}", i, opstamp);
             thread::sleep(Duration::from_millis(20));
         }

query-grammar/Cargo.toml

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

query-grammar/src/lib.rs

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

query-grammar/src/occur.rs

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

query-grammar/src/query_grammar.rs

@@ -1,6 +1,5 @@
 use super::user_input_ast::*;
-use crate::query::occur::Occur;
-use crate::query::query_parser::user_input_ast::UserInputBound;
+use crate::Occur;
 use combine::char::*;
 use combine::error::StreamError;
 use combine::stream::StreamErrorFor;

query-grammar/src/user_input_ast.rs

@@ -1,7 +1,7 @@
 use std::fmt;
 use std::fmt::{Debug, Formatter};
 
-use crate::query::Occur;
+use crate::Occur;
 
 #[derive(PartialEq)]
 pub enum UserInputLeaf {
@@ -151,7 +151,7 @@ impl fmt::Debug for UserInputAST {
                 Ok(())
             }
             UserInputAST::Unary(ref occur, ref subquery) => {
-                write!(formatter, "{}({:?})", occur.to_char(), subquery)
+                write!(formatter, "{}({:?})", occur, subquery)
             }
             UserInputAST::Leaf(ref subquery) => write!(formatter, "{:?}", subquery),
         }

src/directory/mmap_directory.rs

@@ -265,7 +265,7 @@ impl MmapDirectoryInner {
             }
         }
         if let Some(watch_wrapper) = self.watcher.write().unwrap().as_mut() {
-            return Ok(watch_wrapper.watch(watch_callback));
+            Ok(watch_wrapper.watch(watch_callback))
         } else {
             unreachable!("At this point, watch wrapper is supposed to be initialized");
         }

src/fastfield/multivalued/writer.rs

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

src/fastfield/writer.rs

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

src/lib.rs

@@ -1,5 +1,4 @@
 #![doc(html_logo_url = "http://fulmicoton.com/tantivy-logo/tantivy-logo.png")]
-#![recursion_limit = "100"]
 #![cfg_attr(all(feature = "unstable", test), feature(test))]
 #![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))]
 #![doc(test(attr(allow(unused_variables), deny(warnings))))]

src/postings/postings_writer.rs

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

src/postings/serializer.rs

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

src/query/intersection.rs

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

src/query/intersection_two.rs

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

src/query/mod.rs

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

src/query/query_parser/mod.rs

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

src/query/query_parser/query_parser.rs

@@ -1,9 +1,5 @@
 use super::logical_ast::*;
-use super::query_grammar::parse_to_ast;
-use super::user_input_ast::*;
 use crate::core::Index;
-use crate::query::occur::compose_occur;
-use crate::query::query_parser::logical_ast::LogicalAST;
 use crate::query::AllQuery;
 use crate::query::BooleanQuery;
 use crate::query::EmptyQuery;
@@ -16,11 +12,11 @@ use crate::schema::IndexRecordOption;
 use crate::schema::{Field, Schema};
 use crate::schema::{FieldType, Term};
 use crate::tokenizer::TokenizerManager;
-use combine::Parser;
 use std::borrow::Cow;
 use std::num::{ParseFloatError, ParseIntError};
 use std::ops::Bound;
 use std::str::FromStr;
+use tantivy_query_grammar::{UserInputAST, UserInputBound, UserInputLeaf};
 
 /// Possible error that may happen when parsing a query.
 #[derive(Debug, PartialEq, Eq, Fail)]
@@ -222,9 +218,8 @@ impl QueryParser {
 
     /// Parse the user query into an AST.
     fn parse_query_to_logical_ast(&self, query: &str) -> Result<LogicalAST, QueryParserError> {
-        let (user_input_ast, _remaining) = parse_to_ast()
-            .parse(query)
-            .map_err(|_| QueryParserError::SyntaxError)?;
+        let user_input_ast =
+            tantivy_query_grammar::parse_query(query).map_err(|_| QueryParserError::SyntaxError)?;
         self.compute_logical_ast(user_input_ast)
     }
 
@@ -399,7 +394,7 @@ impl QueryParser {
                 let mut logical_sub_queries: Vec<(Occur, LogicalAST)> = Vec::new();
                 for sub_query in sub_queries {
                     let (occur, sub_ast) = self.compute_logical_ast_with_occur(sub_query)?;
-                    let new_occur = compose_occur(default_occur, occur);
+                    let new_occur = Occur::compose(default_occur, occur);
                     logical_sub_queries.push((new_occur, sub_ast));
                 }
                 Ok((Occur::Should, LogicalAST::Clause(logical_sub_queries)))
@@ -407,7 +402,7 @@ impl QueryParser {
             UserInputAST::Unary(left_occur, subquery) => {
                 let (right_occur, logical_sub_queries) =
                     self.compute_logical_ast_with_occur(*subquery)?;
-                Ok((compose_occur(left_occur, right_occur), logical_sub_queries))
+                Ok((Occur::compose(left_occur, right_occur), logical_sub_queries))
             }
             UserInputAST::Leaf(leaf) => {
                 let result_ast = self.compute_logical_ast_from_leaf(*leaf)?;

src/query/union.rs

@@ -28,7 +28,7 @@ where
     }
 }
 
-/// Creates a `DocSet` that iterator through the intersection of two `DocSet`s.
+/// Creates a `DocSet` that iterate through the union of two or more `DocSet`s.
 pub struct Union<TScorer, TScoreCombiner = DoNothingCombiner> {
     docsets: Vec<TScorer>,
     bitsets: Box<[TinySet; HORIZON_NUM_TINYBITSETS]>,

src/schema/index_record_option.rs

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

src/schema/term.rs

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