Switch to slog

Closes #111

.gitignore

@@ -12,3 +12,4 @@ cpp/simdcomp/bitpackingbenchmark
 *.bk
 .idea
 trace.dat
+cargo-timing*

CHANGELOG.md

@@ -1,9 +1,14 @@
+Tantivy 0.14.0
+=========================
+- Remove dependency to atomicwrites #833. Implemented by @pmasurel upon suggestion and research from @asafigan). 
+- Migrated tantivy error from the now deprecated `failure` crate to `thiserror` #760. (@hirevo)
+- Switched to structure logging (via the `slog` crate). (@pmasurel)
+
 Tantivy 0.13.1
-======================
+===================
 Made `Query` and `Collector` `Send + Sync`.
 Updated misc dependency versions.
 
-
 Tantivy 0.13.0
 ======================
 Tantivy 0.13 introduce a change in the index format that will require

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy"
-version = "0.13.1"
+version = "0.14.0-dev"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]
@@ -22,9 +22,9 @@ tantivy-fst = "0.3"
 memmap = {version = "0.7", optional=true}
 lz4 = {version="1", optional=true}
 snap = "1"
-atomicwrites = {version="0.2", optional=true}
-tempfile = "3"
-log = "0.4"
+tempfile = {version="3", optional=true}
+slog = "2.5"
+slog-stdlog = "4"
 serde = {version="1", features=["derive"]}
 serde_json = "1"
 num_cpus = "1"
@@ -35,15 +35,15 @@ uuid = { version = "0.8", features = ["v4", "serde"] }
 crossbeam = "0.7"
 futures = {version = "0.3",  features=["thread-pool"] }
 owning_ref = "0.4"
+tantivy-query-grammar = { version="0.14.0-dev", path="./query-grammar" }
 stable_deref_trait = "1"
 rust-stemmers = "1"
 downcast-rs = "1"
-tantivy-query-grammar = { version="0.13", path="./query-grammar" }
 bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
 census = "0.4"
 fnv = "1"
 owned-read = "0.4"
-failure = "0.1"
+thiserror = "1.0"
 htmlescape = "0.3"
 fail = "0.4"
 murmurhash32 = "0.2"
@@ -75,12 +75,11 @@ overflow-checks = true
 
 [features]
 default = ["mmap"]
-mmap = ["atomicwrites", "fs2", "memmap", "notify"]
+mmap = ["fs2", "tempfile", "memmap", "notify"]
 lz4-compression = ["lz4"]
 failpoints = ["fail/failpoints"]
 unstable = [] # useful for benches.
 wasm-bindgen = ["uuid/wasm-bindgen"]
-scoref64 = [] # scores are f64 instead of f32. was introduced to debug blockwand.
 
 [workspace]
 members = ["query-grammar"]

README.md

@@ -34,11 +34,6 @@ Tantivy is, in fact, strongly inspired by Lucene's design.
 The following [benchmark](https://tantivy-search.github.io/bench/) break downs 
 performance for different type of queries / collection.
 
-
-In general, Tantivy tends to be 
-- slower than Lucene on union with a Top-K due to Block-WAND optimization.
-- faster than Lucene on intersection and phrase queries. 
-
 Your mileage WILL vary depending on the nature of queries and their load.
 
 # Features

examples/basic_search.rs

@@ -112,18 +112,6 @@ fn main() -> tantivy::Result<()> {
             limbs and branches that arch over the pool"
     ));
 
-    index_writer.add_document(doc!(
-    title => "Of Mice and Men",
-    body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
-            bank and runs deep and green. The water is warm too, for it has slipped twinkling \
-            over the yellow sands in the sunlight before reaching the narrow pool. On one \
-            side of the river the golden foothill slopes curve up to the strong and rocky \
-            Gabilan Mountains, but on the valley side the water is lined with trees—willows \
-            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"
-    ));
-
     // Multivalued field just need to be repeated.
     index_writer.add_document(doc!(
     title => "Frankenstein",

query-grammar/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tantivy-query-grammar"
-version = "0.13.0"
+version = "0.14.0-dev"
 authors = ["Paul Masurel <paul.masurel@gmail.com>"]
 license = "MIT"
 categories = ["database-implementations", "data-structures"]

query-grammar/src/occur.rs

@@ -52,7 +52,7 @@ mod test {
     use crate::Occur;
 
     #[test]
-    fn test_Occur_compose() {
+    fn test_occur_compose() {
         assert_eq!(Occur::compose(Occur::Should, Occur::Should), Occur::Should);
         assert_eq!(Occur::compose(Occur::Should, Occur::Must), Occur::Must);
         assert_eq!(

query-grammar/src/query_grammar.rs

@@ -9,8 +9,10 @@ use combine::{
 
 fn field<'a>() -> impl Parser<&'a str, Output = String> {
     (
-        letter(),
-        many(satisfy(|c: char| c.is_alphanumeric() || c == '_')),
+        (letter().or(char('_'))),
+        many(satisfy(|c: char| {
+            c.is_alphanumeric() || c == '_' || c == '-'
+        })),
     )
         .skip(char(':'))
         .map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
@@ -279,6 +281,8 @@ pub fn parse_to_ast<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
 #[cfg(test)]
 mod test {
 
+    type TestParseResult = Result<(), StringStreamError>;
+
     use super::*;
     use combine::parser::Parser;
 
@@ -296,9 +300,10 @@ mod test {
     }
 
     #[test]
-    fn test_occur_symbol() {
-        assert_eq!(super::occur_symbol().parse("-"), Ok((Occur::MustNot, "")));
-        assert_eq!(super::occur_symbol().parse("+"), Ok((Occur::Must, "")));
+    fn test_occur_symbol() -> TestParseResult {
+        assert_eq!(super::occur_symbol().parse("-")?, (Occur::MustNot, ""));
+        assert_eq!(super::occur_symbol().parse("+")?, (Occur::Must, ""));
+        Ok(())
     }
 
     #[test]
@@ -410,6 +415,25 @@ mod test {
         assert_eq!(format!("{:?}", ast), "\"abc\"");
     }
 
+    #[test]
+    fn test_field_name() -> TestParseResult {
+        assert_eq!(
+            super::field().parse("my-field-name:a")?,
+            ("my-field-name".to_string(), "a")
+        );
+        assert_eq!(
+            super::field().parse("my_field_name:a")?,
+            ("my_field_name".to_string(), "a")
+        );
+        assert!(super::field().parse(":a").is_err());
+        assert!(super::field().parse("-my_field:a").is_err());
+        assert_eq!(
+            super::field().parse("_my_field:a")?,
+            ("_my_field".to_string(), "a")
+        );
+        Ok(())
+    }
+
     #[test]
     fn test_range_parser() {
         // testing the range() parser separately

src/collector/facet_collector.rs

@@ -472,7 +472,7 @@ mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
 
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         let num_facets: usize = 3 * 4 * 5;
         let facets: Vec<Facet> = (0..num_facets)
             .map(|mut n| {
@@ -531,7 +531,7 @@ mod tests {
         let facet_field = schema_builder.add_facet_field("facets");
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(
             facet_field => Facet::from_text(&"/subjects/A/a"),
             facet_field => Facet::from_text(&"/subjects/B/a"),
@@ -550,12 +550,12 @@ mod tests {
     }
 
     #[test]
-    fn test_doc_search_by_facet() {
+    fn test_doc_search_by_facet() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let facet_field = schema_builder.add_facet_field("facet");
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         index_writer.add_document(doc!(
             facet_field => Facet::from_text(&"/A/A"),
         ));
@@ -568,8 +568,8 @@ mod tests {
         index_writer.add_document(doc!(
             facet_field => Facet::from_text(&"/D/C/A"),
         ));
-        index_writer.commit().unwrap();
-        let reader = index.reader().unwrap();
+        index_writer.commit()?;
+        let reader = index.reader()?;
         let searcher = reader.searcher();
         assert_eq!(searcher.num_docs(), 4);
 
@@ -586,17 +586,17 @@ mod tests {
         assert_eq!(count_facet("/A/C"), 1);
         assert_eq!(count_facet("/A/C/A"), 1);
         assert_eq!(count_facet("/C/A"), 0);
+
+        let query_parser = QueryParser::for_index(&index, vec![]);
         {
-            let query_parser = QueryParser::for_index(&index, vec![]);
-            {
-                let query = query_parser.parse_query("facet:/A/B").unwrap();
-                assert_eq!(1, searcher.search(&query, &Count).unwrap());
-            }
-            {
-                let query = query_parser.parse_query("facet:/A").unwrap();
-                assert_eq!(3, searcher.search(&query, &Count).unwrap());
-            }
+            let query = query_parser.parse_query("facet:/A/B")?;
+            assert_eq!(1, searcher.search(&query, &Count).unwrap());
         }
+        {
+            let query = query_parser.parse_query("facet:/A")?;
+            assert_eq!(3, searcher.search(&query, &Count)?);
+        }
+        Ok(())
     }
 
     #[test]
@@ -631,7 +631,7 @@ mod tests {
             .collect();
         docs[..].shuffle(&mut thread_rng());
 
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         for doc in docs {
             index_writer.add_document(doc);
         }
@@ -684,7 +684,7 @@ mod bench {
         // 40425 docs
         docs[..].shuffle(&mut thread_rng());
 
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         for doc in docs {
             index_writer.add_document(doc);
         }

src/collector/int_facet_collector.rs

@@ -89,7 +89,7 @@ mod tests {
         let index = Index::create_in_ram(schema.clone());
 
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             {
                 for i in 0u64..10u64 {
                     index_writer.add_document(doc!(

src/collector/multi_collector.rs

@@ -259,7 +259,7 @@ mod tests {
 
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(text=>"abc"));
             index_writer.add_document(doc!(text=>"abc abc abc"));
             index_writer.add_document(doc!(text=>"abc abc"));

src/collector/top_score_collector.rs

@@ -38,7 +38,7 @@ use std::fmt;
 /// let schema = schema_builder.build();
 /// let index = Index::create_in_ram(schema);
 ///
-/// let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+/// let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
 /// index_writer.add_document(doc!(title => "The Name of the Wind"));
 /// index_writer.add_document(doc!(title => "The Diary of Muadib"));
 /// index_writer.add_document(doc!(title => "A Dairy Cow"));
@@ -123,7 +123,7 @@ impl TopDocs {
     /// let schema = schema_builder.build();
     /// let index = Index::create_in_ram(schema);
     ///
-    /// let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+    /// let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
     /// index_writer.add_document(doc!(title => "The Name of the Wind"));
     /// index_writer.add_document(doc!(title => "The Diary of Muadib"));
     /// index_writer.add_document(doc!(title => "A Dairy Cow"));
@@ -163,7 +163,7 @@ impl TopDocs {
     /// #   let schema = schema_builder.build();
     /// #  
     /// #   let index = Index::create_in_ram(schema);
-    /// #   let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
+    /// #   let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
     /// #   index_writer.add_document(doc!(title => "The Name of the Wind", rating => 92u64));
     /// #   index_writer.add_document(doc!(title => "The Diary of Muadib", rating => 97u64));
     /// #   index_writer.add_document(doc!(title => "A Dairy Cow", rating => 63u64));
@@ -264,7 +264,7 @@ impl TopDocs {
     /// fn create_index() -> tantivy::Result<Index> {
     ///   let schema = create_schema();
     ///   let index = Index::create_in_ram(schema);
-    ///   let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
+    ///   let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
     ///   let product_name = index.schema().get_field("product_name").unwrap();
     ///   let popularity: Field = index.schema().get_field("popularity").unwrap();
     ///   index_writer.add_document(doc!(product_name => "The Diary of Muadib", popularity => 1u64));
@@ -371,7 +371,7 @@ impl TopDocs {
     /// # fn main() -> tantivy::Result<()> {
     /// #   let schema = create_schema();
     /// #   let index = Index::create_in_ram(schema);
-    /// #   let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
+    /// #   let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
     /// #   let product_name = index.schema().get_field("product_name").unwrap();
     /// #   
     /// let popularity: Field = index.schema().get_field("popularity").unwrap();
@@ -561,7 +561,7 @@ mod tests {
         let index = Index::create_in_ram(schema);
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
             index_writer.add_document(doc!(text_field=>"Hello happy tax payer."));
             index_writer.add_document(doc!(text_field=>"Droopy says hello happy tax payer"));
             index_writer.add_document(doc!(text_field=>"I like Droopy"));
@@ -821,7 +821,7 @@ mod tests {
     ) -> (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();
+        let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
         doc_adder(&mut index_writer);
         index_writer.commit().unwrap();
         let query_parser = QueryParser::for_index(&index, vec![query_field]);

src/core/executor.rs

@@ -1,5 +1,6 @@
 use crossbeam::channel;
 use rayon::{ThreadPool, ThreadPoolBuilder};
+use slog::{error, Logger};
 
 /// Search executor whether search request are single thread or multithread.
 ///
@@ -43,6 +44,7 @@ impl Executor {
         &self,
         f: F,
         args: AIterator,
+        logger: Logger,
     ) -> crate::Result<Vec<R>> {
         match self {
             Executor::SingleThread => args.map(f).collect::<crate::Result<_>>(),
@@ -57,7 +59,7 @@ impl Executor {
                                 let (idx, arg) = arg_with_idx;
                                 let fruit = f(arg);
                                 if let Err(err) = fruit_sender.send((idx, fruit)) {
-                                    error!("Failed to send search task. It probably means all search threads have panicked. {:?}", err);
+                                    error!(logger, "Failed to send search task. It probably means all search threads have panicked. {:?}", err);
                                 }
                             });
                         }
@@ -87,17 +89,21 @@ impl Executor {
 #[cfg(test)]
 mod tests {
 
+    use slog::{o, Discard, Logger};
+
     use super::Executor;
 
     #[test]
     #[should_panic(expected = "panic should propagate")]
     fn test_panic_propagates_single_thread() {
+        let logger = Logger::root(Discard, o!());
         let _result: Vec<usize> = Executor::single_thread()
             .map(
                 |_| {
                     panic!("panic should propagate");
                 },
                 vec![0].into_iter(),
+                logger,
             )
             .unwrap();
     }
@@ -105,6 +111,7 @@ mod tests {
     #[test]
     #[should_panic] //< unfortunately the panic message is not propagated
     fn test_panic_propagates_multi_thread() {
+        let logger = Logger::root(Discard, o!());
         let _result: Vec<usize> = Executor::multi_thread(1, "search-test")
             .unwrap()
             .map(
@@ -112,14 +119,16 @@ mod tests {
                     panic!("panic should propagate");
                 },
                 vec![0].into_iter(),
+                logger,
             )
             .unwrap();
     }
 
     #[test]
     fn test_map_singlethread() {
+        let logger = Logger::root(Discard, o!());
         let result: Vec<usize> = Executor::single_thread()
-            .map(|i| Ok(i * 2), 0..1_000)
+            .map(|i| Ok(i * 2), 0..1_000, logger)
             .unwrap();
         assert_eq!(result.len(), 1_000);
         for i in 0..1_000 {
@@ -129,9 +138,10 @@ mod tests {
 
     #[test]
     fn test_map_multithread() {
+        let logger = Logger::root(Discard, o!());
         let result: Vec<usize> = Executor::multi_thread(3, "search-test")
             .unwrap()
-            .map(|i| Ok(i * 2), 0..10)
+            .map(|i| Ok(i * 2), 0..10, logger)
             .unwrap();
         assert_eq!(result.len(), 10);
         for i in 0..10 {

src/core/index.rs

@@ -21,6 +21,7 @@ use crate::schema::FieldType;
 use crate::schema::Schema;
 use crate::tokenizer::{TextAnalyzer, TokenizerManager};
 use crate::IndexWriter;
+use slog::Logger;
 use std::borrow::BorrowMut;
 use std::collections::HashSet;
 use std::fmt;
@@ -57,7 +58,14 @@ pub struct Index {
 }
 
 impl Index {
-    /// Examines the director to see if it contains an index
+
+    pub(crate) fn logger(&self) -> &Logger {
+        self.directory.logger()
+    }
+
+    /// Examines the directory to see if it contains an index.
+    ///
+    /// Effectively, it only checks for the presence of the `meta.json` file.
     pub fn exists<Dir: Directory>(dir: &Dir) -> bool {
         dir.exists(&META_FILEPATH)
     }
@@ -140,16 +148,18 @@ impl Index {
         Index::create(mmap_directory, schema)
     }
 
-    /// Creates a new index given an implementation of the trait `Directory`
+    /// Creates a new index given an implementation of the trait `Directory`.
+    ///
+    /// If a directory previously existed, it will be erased.
     pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
         let directory = ManagedDirectory::wrap(dir)?;
-        Index::from_directory(directory, schema)
+        Index::new_from_directory(directory, schema)
     }
 
     /// Create a new index from a directory.
     ///
     /// This will overwrite existing meta.json
-    fn from_directory(mut directory: ManagedDirectory, schema: Schema) -> crate::Result<Index> {
+    fn new_from_directory(mut directory: ManagedDirectory, schema: Schema) -> crate::Result<Index> {
         save_new_metas(schema.clone(), directory.borrow_mut())?;
         let metas = IndexMeta::with_schema(schema);
         Index::create_from_metas(directory, &metas, SegmentMetaInventory::default())
@@ -240,6 +250,8 @@ impl Index {
 
     /// Open the index using the provided directory
     pub fn open<D: Directory>(directory: D) -> crate::Result<Index> {
+        let logger: &Logger = directory.logger();
+        slog::info!(logger, "index-open"; "directory" => format!("{:?}", directory));
         let directory = ManagedDirectory::wrap(directory)?;
         let inventory = SegmentMetaInventory::default();
         let metas = load_metas(&directory, &inventory)?;
@@ -300,6 +312,15 @@ impl Index {
         )
     }
 
+    /// Helper to create an index writer for tests.
+    ///
+    /// That index writer only simply has a single thread and a heap of 5 MB.
+    /// Using a single thread gives us a deterministic allocation of DocId.
+    #[cfg(test)]
+    pub fn writer_for_tests(&self) -> crate::Result<IndexWriter> {
+        self.writer_with_num_threads(1, 10_000_000)
+    }
+
     /// Creates a multithreaded writer
     ///
     /// Tantivy will automatically define the number of threads to use.
@@ -502,7 +523,7 @@ mod tests {
             let schema = throw_away_schema();
             let field = schema.get_field("num_likes").unwrap();
             let mut index = Index::create_from_tempdir(schema).unwrap();
-            let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut writer = index.writer_for_tests().unwrap();
             writer.commit().unwrap();
             let reader = index
                 .reader_builder()
@@ -539,23 +560,33 @@ mod tests {
             test_index_on_commit_reload_policy_aux(field, &write_index, &reader);
         }
     }
-
     fn test_index_on_commit_reload_policy_aux(field: Field, index: &Index, reader: &IndexReader) {
         let mut reader_index = reader.index();
         let (sender, receiver) = crossbeam::channel::unbounded();
         let _watch_handle = reader_index.directory_mut().watch(Box::new(move || {
             let _ = sender.send(());
         }));
-        let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut writer = index.writer_for_tests().unwrap();
         assert_eq!(reader.searcher().num_docs(), 0);
         writer.add_document(doc!(field=>1u64));
         writer.commit().unwrap();
-        assert!(receiver.recv().is_ok());
-        assert_eq!(reader.searcher().num_docs(), 1);
+        // We need a loop here because it is possible for notify to send more than
+        // one modify event. It was observed on CI on MacOS.
+        loop {
+            assert!(receiver.recv().is_ok());
+            if reader.searcher().num_docs() == 1 {
+                break;
+            }
+        }
         writer.add_document(doc!(field=>2u64));
         writer.commit().unwrap();
-        assert!(receiver.recv().is_ok());
-        assert_eq!(reader.searcher().num_docs(), 2);
+        // ... Same as above
+        loop {
+            assert!(receiver.recv().is_ok());
+            if reader.searcher().num_docs() == 2 {
+                break;
+            }
+        }
     }
 
     // This test will not pass on windows, because windows

src/core/inverted_index_reader.rs

@@ -3,7 +3,6 @@ use crate::directory::ReadOnlySource;
 use crate::positions::PositionReader;
 use crate::postings::TermInfo;
 use crate::postings::{BlockSegmentPostings, SegmentPostings};
-use crate::schema::FieldType;
 use crate::schema::IndexRecordOption;
 use crate::schema::Term;
 use crate::termdict::TermDictionary;
@@ -54,10 +53,7 @@ impl InvertedIndexReader {
 
     /// Creates an empty `InvertedIndexReader` object, which
     /// contains no terms at all.
-    pub fn empty(field_type: &FieldType) -> InvertedIndexReader {
-        let record_option = field_type
-            .get_index_record_option()
-            .unwrap_or(IndexRecordOption::Basic);
+    pub fn empty(record_option: IndexRecordOption) -> InvertedIndexReader {
         InvertedIndexReader {
             termdict: TermDictionary::empty(),
             postings_source: ReadOnlySource::empty(),

src/core/searcher.rs

@@ -143,6 +143,7 @@ impl Searcher {
                 collector.collect_segment(weight.as_ref(), segment_ord as u32, segment_reader)
             },
             segment_readers.iter().enumerate(),
+            self.index.logger().clone(),
         )?;
         collector.merge_fruits(fruits)
     }

src/core/segment_id.rs

@@ -21,6 +21,12 @@ use std::sync::atomic;
 #[derive(Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
 pub struct SegmentId(Uuid);
 
+impl ToString for SegmentId {
+    fn to_string(&self) -> String {
+        self.short_uuid_string()
+    }
+}
+
 #[cfg(test)]
 static AUTO_INC_COUNTER: Lazy<atomic::AtomicUsize> = Lazy::new(|| atomic::AtomicUsize::default());
 

src/core/segment_reader.rs

@@ -9,14 +9,15 @@ use crate::fastfield::DeleteBitSet;
 use crate::fastfield::FacetReader;
 use crate::fastfield::FastFieldReaders;
 use crate::fieldnorm::{FieldNormReader, FieldNormReaders};
-use crate::schema::Field;
 use crate::schema::FieldType;
 use crate::schema::Schema;
+use crate::schema::{Field, IndexRecordOption};
 use crate::space_usage::SegmentSpaceUsage;
 use crate::store::StoreReader;
 use crate::termdict::TermDictionary;
 use crate::DocId;
 use fail::fail_point;
+use slog::{warn, Logger};
 use std::collections::HashMap;
 use std::fmt;
 use std::sync::Arc;
@@ -53,6 +54,7 @@ pub struct SegmentReader {
     store_source: ReadOnlySource,
     delete_bitset_opt: Option<DeleteBitSet>,
     schema: Schema,
+    logger: Logger,
 }
 
 impl SegmentReader {
@@ -125,17 +127,15 @@ impl SegmentReader {
     ///
     /// They are simply stored as a fast field, serialized in
     /// the `.fieldnorm` file of the segment.
-    pub fn get_fieldnorms_reader(&self, field: Field) -> FieldNormReader {
-        if let Some(fieldnorm_reader) = self.fieldnorm_readers.get_field(field) {
-            fieldnorm_reader
-        } else {
+    pub fn get_fieldnorms_reader(&self, field: Field) -> crate::Result<FieldNormReader> {
+        self.fieldnorm_readers.get_field(field).ok_or_else(|| {
             let field_name = self.schema.get_field_name(field);
             let err_msg = format!(
                 "Field norm not found for field {:?}. Was it market as indexed during indexing.",
                 field_name
             );
-            panic!(err_msg);
-        }
+            crate::TantivyError::SchemaError(err_msg)
+        })
     }
 
     /// Accessor to the segment's `StoreReader`.
@@ -202,6 +202,7 @@ impl SegmentReader {
             positions_composite,
             positions_idx_composite,
             schema,
+            logger: segment.index().logger().clone(),
         })
     }
 
@@ -212,6 +213,11 @@ impl SegmentReader {
     /// The field reader is in charge of iterating through the
     /// term dictionary associated to a specific field,
     /// and opening the posting list associated to any term.
+    ///
+    /// If the field is marked as index, a warn is logged and an empty `InvertedIndexReader`
+    /// is returned.
+    /// Similarly if the field is marked as indexed but no term has been indexed for the given
+    /// index. an empty `InvertedIndexReader` is returned (but no warning is logged).
     pub fn inverted_index(&self, field: Field) -> Arc<InvertedIndexReader> {
         if let Some(inv_idx_reader) = self
             .inv_idx_reader_cache
@@ -226,21 +232,25 @@ impl SegmentReader {
         let record_option_opt = field_type.get_index_record_option();
 
         if record_option_opt.is_none() {
-            panic!("Field {:?} does not seem indexed.", field_entry.name());
+            warn!(
+                self.logger,
+                "Field {:?} does not seem indexed.",
+                field_entry.name()
+            );
         }
 
-        let record_option = record_option_opt.unwrap();
-
         let postings_source_opt = self.postings_composite.open_read(field);
 
-        if postings_source_opt.is_none() {
+        if postings_source_opt.is_none() || record_option_opt.is_none() {
             // no documents in the segment contained this field.
             // As a result, no data is associated to the inverted index.
             //
             // Returns an empty inverted index.
-            return Arc::new(InvertedIndexReader::empty(field_type));
+            let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);
+            return Arc::new(InvertedIndexReader::empty(record_option));
         }
 
+        let record_option = record_option_opt.unwrap();
         let postings_source = postings_source_opt.unwrap();
 
         let termdict_source = self.termdict_composite.open_read(field).expect(
@@ -339,7 +349,7 @@ mod test {
         let name = schema.get_field("name").unwrap();
 
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(name => "tantivy"));
             index_writer.add_document(doc!(name => "horse"));
             index_writer.add_document(doc!(name => "jockey"));

src/directory/directory.rs

@@ -1,3 +1,5 @@
+use slog::{error, Logger};
+
 use crate::directory::directory_lock::Lock;
 use crate::directory::error::LockError;
 use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
@@ -64,7 +66,10 @@ impl<T: Send + Sync + 'static> From<Box<T>> for DirectoryLock {
 impl Drop for DirectoryLockGuard {
     fn drop(&mut self) {
         if let Err(e) = self.directory.delete(&*self.path) {
-            error!("Failed to remove the lock file. {:?}", e);
+            error!(
+                self.directory.logger(),
+                "Failed to remove the lock file. {:?}", e
+            );
         }
     }
 }
@@ -80,7 +85,7 @@ fn try_acquire_lock(
 ) -> Result<DirectoryLock, TryAcquireLockError> {
     let mut write = directory.open_write(filepath).map_err(|e| match e {
         OpenWriteError::FileAlreadyExists(_) => TryAcquireLockError::FileExists,
-        OpenWriteError::IOError(io_error) => TryAcquireLockError::IOError(io_error.into()),
+        OpenWriteError::IOError { io_error, .. } => TryAcquireLockError::IOError(io_error),
     })?;
     write.flush().map_err(TryAcquireLockError::IOError)?;
     Ok(DirectoryLock::from(Box::new(DirectoryLockGuard {
@@ -209,6 +214,9 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
     /// `OnCommit` `ReloadPolicy`. Not implementing watch in a `Directory` only prevents the
     /// `OnCommit` `ReloadPolicy` to work properly.
     fn watch(&self, watch_callback: WatchCallback) -> crate::Result<WatchHandle>;
+
+    /// Returns the `slog::Logger` configured for the `Directory`.
+    fn logger(&self) -> &Logger;
 }
 
 /// DirectoryClone

src/directory/error.rs

@@ -1,160 +1,60 @@
 use crate::Version;
-use std::error::Error as StdError;
 use std::fmt;
 use std::io;
 use std::path::PathBuf;
 
 /// Error while trying to acquire a directory lock.
-#[derive(Debug, Fail)]
+#[derive(Debug, Error)]
 pub enum LockError {
     /// Failed to acquired a lock as it is already held by another
     /// client.
     /// - In the context of a blocking lock, this means the lock was not released within some `timeout` period.
     /// - In the context of a non-blocking lock, this means the lock was busy at the moment of the call.
-    #[fail(
-        display = "Could not acquire lock as it is already held, possibly by a different process."
-    )]
+    #[error("Could not acquire lock as it is already held, possibly by a different process.")]
     LockBusy,
     /// Trying to acquire a lock failed with an `IOError`
-    #[fail(display = "Failed to acquire the lock due to an io:Error.")]
+    #[error("Failed to acquire the lock due to an io:Error.")]
     IOError(io::Error),
 }
 
-/// General IO error with an optional path to the offending file.
-#[derive(Debug)]
-pub struct IOError {
-    path: Option<PathBuf>,
-    err: io::Error,
-}
-
-impl Into<io::Error> for IOError {
-    fn into(self) -> io::Error {
-        self.err
-    }
-}
-
-impl fmt::Display for IOError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match self.path {
-            Some(ref path) => write!(f, "io error occurred on path '{:?}': '{}'", path, self.err),
-            None => write!(f, "io error occurred: '{}'", self.err),
-        }
-    }
-}
-
-impl StdError for IOError {
-    fn description(&self) -> &str {
-        "io error occurred"
-    }
-
-    fn cause(&self) -> Option<&dyn StdError> {
-        Some(&self.err)
-    }
-}
-
-impl IOError {
-    pub(crate) fn with_path(path: PathBuf, err: io::Error) -> Self {
-        IOError {
-            path: Some(path),
-            err,
-        }
-    }
-}
-
-impl From<io::Error> for IOError {
-    fn from(err: io::Error) -> IOError {
-        IOError { path: None, err }
-    }
-}
-
 /// Error that may occur when opening a directory
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum OpenDirectoryError {
     /// The underlying directory does not exists.
+    #[error("Directory does not exist: '{0}'.")]
     DoesNotExist(PathBuf),
     /// The path exists but is not a directory.
+    #[error("Path exists but is not a directory: '{0}'.")]
     NotADirectory(PathBuf),
+    /// Failed to create a temp directory.
+    #[error("Failed to create a temporary directory: '{0}'.")]
+    FailedToCreateTempDir(io::Error),
     /// IoError
-    IoError(io::Error),
-}
-
-impl From<io::Error> for OpenDirectoryError {
-    fn from(io_err: io::Error) -> Self {
-        OpenDirectoryError::IoError(io_err)
-    }
-}
-
-impl fmt::Display for OpenDirectoryError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match *self {
-            OpenDirectoryError::DoesNotExist(ref path) => {
-                write!(f, "the underlying directory '{:?}' does not exist", path)
-            }
-            OpenDirectoryError::NotADirectory(ref path) => {
-                write!(f, "the path '{:?}' exists but is not a directory", path)
-            }
-            OpenDirectoryError::IoError(ref err) => write!(
-                f,
-                "IOError while trying to open/create the directory. {:?}",
-                err
-            ),
-        }
-    }
-}
-
-impl StdError for OpenDirectoryError {
-    fn description(&self) -> &str {
-        "error occurred while opening a directory"
-    }
-
-    fn cause(&self) -> Option<&dyn StdError> {
-        None
-    }
+    #[error("IOError '{io_error:?}' while create directory in: '{directory_path:?}'.")]
+    IoError {
+        /// underlying io Error.
+        io_error: io::Error,
+        /// directory we tried to open.
+        directory_path: PathBuf,
+    },
 }
 
 /// Error that may occur when starting to write in a file
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum OpenWriteError {
     /// Our directory is WORM, writing an existing file is forbidden.
     /// Checkout the `Directory` documentation.
+    #[error("File already exists: '{0}'")]
     FileAlreadyExists(PathBuf),
     /// Any kind of IO error that happens when
     /// writing in the underlying IO device.
-    IOError(IOError),
-}
-
-impl From<IOError> for OpenWriteError {
-    fn from(err: IOError) -> OpenWriteError {
-        OpenWriteError::IOError(err)
-    }
-}
-
-impl fmt::Display for OpenWriteError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match *self {
-            OpenWriteError::FileAlreadyExists(ref path) => {
-                write!(f, "the file '{:?}' already exists", path)
-            }
-            OpenWriteError::IOError(ref err) => write!(
-                f,
-                "an io error occurred while opening a file for writing: '{}'",
-                err
-            ),
-        }
-    }
-}
-
-impl StdError for OpenWriteError {
-    fn description(&self) -> &str {
-        "error occurred while opening a file for writing"
-    }
-
-    fn cause(&self) -> Option<&dyn StdError> {
-        match *self {
-            OpenWriteError::FileAlreadyExists(_) => None,
-            OpenWriteError::IOError(ref err) => Some(err),
-        }
-    }
+    #[error("IOError '{io_error:?}' while opening file for write: '{filepath}'.")]
+    IOError {
+        /// The underlying `io::Error`.
+        io_error: io::Error,
+        /// File path of the file that tantivy failed to open for write.
+        filepath: PathBuf,
+    },
 }
 
 /// Type of index incompatibility between the library and the index found on disk
@@ -217,55 +117,41 @@ impl fmt::Debug for Incompatibility {
 }
 
 /// Error that may occur when accessing a file read
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum OpenReadError {
     /// The file does not exists.
+    #[error("Files does not exists: {0:?}")]
     FileDoesNotExist(PathBuf),
-    /// Any kind of IO error that happens when
-    /// interacting with the underlying IO device.
-    IOError(IOError),
-    /// This library doesn't support the index version found on disk
+    /// Any kind of io::Error.
+    #[error(
+        "IOError: '{io_error:?}' happened while opening the following file for Read: {filepath}."
+    )]
+    IOError {
+        /// The underlying `io::Error`.
+        io_error: io::Error,
+        /// File path of the file that tantivy failed to open for read.
+        filepath: PathBuf,
+    },
+    /// This library does not support the index version found in file footer.
+    #[error("Index version unsupported: {0:?}")]
     IncompatibleIndex(Incompatibility),
 }
 
-impl From<IOError> for OpenReadError {
-    fn from(err: IOError) -> OpenReadError {
-        OpenReadError::IOError(err)
-    }
-}
-
-impl fmt::Display for OpenReadError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match *self {
-            OpenReadError::FileDoesNotExist(ref path) => {
-                write!(f, "the file '{:?}' does not exist", path)
-            }
-            OpenReadError::IOError(ref err) => write!(
-                f,
-                "an io error occurred while opening a file for reading: '{}'",
-                err
-            ),
-            OpenReadError::IncompatibleIndex(ref footer) => {
-                write!(f, "Incompatible index format: {:?}", footer)
-            }
-        }
-    }
-}
-
 /// Error that may occur when trying to delete a file
-#[derive(Debug)]
+#[derive(Debug, Error)]
 pub enum DeleteError {
     /// The file does not exists.
+    #[error("File does not exists: '{0}'.")]
     FileDoesNotExist(PathBuf),
     /// Any kind of IO error that happens when
     /// interacting with the underlying IO device.
-    IOError(IOError),
-}
-
-impl From<IOError> for DeleteError {
-    fn from(err: IOError) -> DeleteError {
-        DeleteError::IOError(err)
-    }
+    #[error("The following IO error happened while deleting file '{filepath}': '{io_error:?}'.")]
+    IOError {
+        /// The underlying `io::Error`.
+        io_error: io::Error,
+        /// File path of the file that tantivy failed to delete.
+        filepath: PathBuf,
+    },
 }
 
 impl From<Incompatibility> for OpenReadError {
@@ -273,29 +159,3 @@ impl From<Incompatibility> for OpenReadError {
         OpenReadError::IncompatibleIndex(incompatibility)
     }
 }
-
-impl fmt::Display for DeleteError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match *self {
-            DeleteError::FileDoesNotExist(ref path) => {
-                write!(f, "the file '{:?}' does not exist", path)
-            }
-            DeleteError::IOError(ref err) => {
-                write!(f, "an io error occurred while deleting a file: '{}'", err)
-            }
-        }
-    }
-}
-
-impl StdError for DeleteError {
-    fn description(&self) -> &str {
-        "error occurred while deleting a file"
-    }
-
-    fn cause(&self) -> Option<&dyn StdError> {
-        match *self {
-            DeleteError::FileDoesNotExist(_) => None,
-            DeleteError::IOError(ref err) => Some(err),
-        }
-    }
-}

src/directory/footer.rs

@@ -271,7 +271,11 @@ mod tests {
         let mut vec = Vec::new();
         let footer_proxy = FooterProxy::new(&mut vec);
         assert!(footer_proxy.terminate().is_ok());
-        assert_eq!(vec.len(), 167);
+        if crate::store::COMPRESSION == "lz4" {
+            assert_eq!(vec.len(), 158);
+        } else {
+            assert_eq!(vec.len(), 167);
+        }
         let footer = Footer::deserialize(&mut &vec[..]).unwrap();
         assert!(matches!(
            footer.versioned_footer,

src/directory/managed_directory.rs

@@ -1,5 +1,5 @@
-use crate::core::MANAGED_FILEPATH;
-use crate::directory::error::{DeleteError, IOError, LockError, OpenReadError, OpenWriteError};
+use crate::core::{MANAGED_FILEPATH, META_FILEPATH};
+use crate::directory::error::{DeleteError, LockError, OpenReadError, OpenWriteError};
 use crate::directory::footer::{Footer, FooterProxy};
 use crate::directory::DirectoryLock;
 use crate::directory::GarbageCollectionResult;
@@ -11,9 +11,9 @@ use crate::error::DataCorruption;
 use crate::Directory;
 
 use crc32fast::Hasher;
+use slog::{debug, error, info};
 use std::collections::HashSet;
 use std::io;
-use std::io::Write;
 use std::path::{Path, PathBuf};
 use std::result;
 use std::sync::RwLockWriteGuard;
@@ -56,9 +56,9 @@ fn save_managed_paths(
     directory: &mut dyn Directory,
     wlock: &RwLockWriteGuard<'_, MetaInformation>,
 ) -> io::Result<()> {
-    let mut w = serde_json::to_vec(&wlock.managed_paths)?;
-    writeln!(&mut w)?;
-    directory.atomic_write(&MANAGED_FILEPATH, &w[..])?;
+    let mut managed_json = serde_json::to_string_pretty(&wlock.managed_paths)?;
+    managed_json.push_str("\n");
+    directory.atomic_write(&MANAGED_FILEPATH, managed_json.as_bytes())?;
     Ok(())
 }
 
@@ -86,7 +86,12 @@ impl ManagedDirectory {
                 directory: Box::new(directory),
                 meta_informations: Arc::default(),
             }),
-            Err(OpenReadError::IOError(e)) => Err(From::from(e)),
+            Err(OpenReadError::IOError { io_error, filepath }) => {
+                Err(crate::TantivyError::OpenReadError(OpenReadError::IOError {
+                    io_error,
+                    filepath,
+                }))
+            }
             Err(OpenReadError::IncompatibleIndex(incompatibility)) => {
                 // For the moment, this should never happen  `meta.json`
                 // do not have any footer and cannot detect incompatibility.
@@ -113,7 +118,7 @@ impl ManagedDirectory {
         &mut self,
         get_living_files: L,
     ) -> crate::Result<GarbageCollectionResult> {
-        info!("Garbage collect");
+        info!(self.directory.logger(), "gc"; "stage"=>"start");
         let mut files_to_delete = vec![];
 
         // It is crucial to get the living files after acquiring the
@@ -148,7 +153,7 @@ impl ManagedDirectory {
                     }
                 }
                 Err(err) => {
-                    error!("Failed to acquire lock for GC");
+                    error!(self.logger(), "Failed to acquire lock for GC");
                     return Err(crate::TantivyError::from(err));
                 }
             }
@@ -160,7 +165,7 @@ impl ManagedDirectory {
         for file_to_delete in files_to_delete {
             match self.delete(&file_to_delete) {
                 Ok(_) => {
-                    info!("Deleted {:?}", file_to_delete);
+                    debug!(self.logger(), "deleted-success"; "file"=>format!("{:?}", file_to_delete));
                     deleted_files.push(file_to_delete);
                 }
                 Err(file_error) => {
@@ -168,12 +173,12 @@ impl ManagedDirectory {
                         DeleteError::FileDoesNotExist(_) => {
                             deleted_files.push(file_to_delete.clone());
                         }
-                        DeleteError::IOError(_) => {
+                        DeleteError::IOError { .. } => {
                             failed_to_delete_files.push(file_to_delete.clone());
                             if !cfg!(target_os = "windows") {
                                 // On windows, delete is expected to fail if the file
                                 // is mmapped.
-                                error!("Failed to delete {:?}", file_to_delete);
+                                error!(self.logger(), "delete-file-fail"; "path"=>file_to_delete.to_str().unwrap_or("<invalid-utf8>"));
                             }
                         }
                     }
@@ -195,6 +200,10 @@ impl ManagedDirectory {
             save_managed_paths(self.directory.as_mut(), &meta_informations_wlock)?;
         }
 
+        info!(self.directory.logger(), "gc"; "stage"=>"end", 
+                "num-sucess-file-deletes"=>deleted_files.len(), 
+                "num-failed-file-deletes"=>failed_to_delete_files.len());
+
         Ok(GarbageCollectionResult {
             deleted_files,
             failed_to_delete_files,
@@ -231,8 +240,11 @@ impl ManagedDirectory {
     /// Verify checksum of a managed file
     pub fn validate_checksum(&self, path: &Path) -> result::Result<bool, OpenReadError> {
         let reader = self.directory.open_read(path)?;
-        let (footer, data) = Footer::extract_footer(reader)
-            .map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
+        let (footer, data) =
+            Footer::extract_footer(reader).map_err(|io_error| OpenReadError::IOError {
+                io_error,
+                filepath: path.to_path_buf(),
+            })?;
         let mut hasher = Hasher::new();
         hasher.update(data.as_slice());
         let crc = hasher.finalize();
@@ -245,35 +257,46 @@ impl ManagedDirectory {
 
     /// List files for which checksum does not match content
     pub fn list_damaged(&self) -> result::Result<HashSet<PathBuf>, OpenReadError> {
-        let mut hashset = HashSet::new();
-        let managed_paths = self
+        let mut managed_paths = self
             .meta_informations
             .read()
             .expect("Managed directory rlock poisoned in list damaged.")
             .managed_paths
             .clone();
 
-        for path in managed_paths.into_iter() {
+        managed_paths.remove(*META_FILEPATH);
+
+        let mut damaged_files = HashSet::new();
+        for path in managed_paths {
             if !self.validate_checksum(&path)? {
-                hashset.insert(path);
+                damaged_files.insert(path);
             }
         }
-        Ok(hashset)
+        Ok(damaged_files)
     }
 }
 
 impl Directory for ManagedDirectory {
     fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
+        slog::debug!(self.logger(), "open-read"; "path" => path.to_str().unwrap_or("<invalid-utf8>"));
         let read_only_source = self.directory.open_read(path)?;
-        let (footer, reader) = Footer::extract_footer(read_only_source)
-            .map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
+        let (footer, reader) = Footer::extract_footer(read_only_source).map_err(|io_error| {
+            OpenReadError::IOError {
+                io_error,
+                filepath: path.to_path_buf(),
+            }
+        })?;
         footer.is_compatible()?;
         Ok(reader)
     }
 
     fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
+        slog::debug!(self.logger(), "open-write"; "path" => path.to_str().unwrap_or("<invalid-utf8>"));
         self.register_file_as_managed(path)
-            .map_err(|e| IOError::with_path(path.to_owned(), e))?;
+            .map_err(|io_error| OpenWriteError::IOError {
+                io_error,
+                filepath: path.to_path_buf(),
+            })?;
         Ok(io::BufWriter::new(Box::new(FooterProxy::new(
             self.directory
                 .open_write(path)?
@@ -283,9 +306,11 @@ impl Directory for ManagedDirectory {
         ))))
     }
 
-    fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
+    fn atomic_write(&mut self, path: &Path, content: &[u8]) -> io::Result<()> {
+        let content_str = std::str::from_utf8(content).unwrap_or("<content-not-utf-8>");
+        slog::debug!(self.logger(), "Atomic write"; "path" => format!("{:?}", path), "content_length"=>content_str);
         self.register_file_as_managed(path)?;
-        self.directory.atomic_write(path, data)
+        self.directory.atomic_write(path, content)
     }
 
     fn atomic_read(&self, path: &Path) -> result::Result<Vec<u8>, OpenReadError> {
@@ -307,6 +332,10 @@ impl Directory for ManagedDirectory {
     fn watch(&self, watch_callback: WatchCallback) -> crate::Result<WatchHandle> {
         self.directory.watch(watch_callback)
     }
+
+    fn logger(&self) -> &slog::Logger {
+        self.directory.logger()
+    }
 }
 
 impl Clone for ManagedDirectory {

src/directory/mmap_directory.rs

@@ -1,8 +1,6 @@
 use crate::core::META_FILEPATH;
 use crate::directory::error::LockError;
-use crate::directory::error::{
-    DeleteError, IOError, OpenDirectoryError, OpenReadError, OpenWriteError,
-};
+use crate::directory::error::{DeleteError, OpenDirectoryError, OpenReadError, OpenWriteError};
 use crate::directory::read_only_source::BoxedData;
 use crate::directory::AntiCallToken;
 use crate::directory::Directory;
@@ -19,6 +17,8 @@ use notify::RawEvent;
 use notify::RecursiveMode;
 use notify::Watcher;
 use serde::{Deserialize, Serialize};
+use slog::{debug, o, Drain, Logger};
+use slog_stdlog::StdLog;
 use std::collections::HashMap;
 use std::convert::From;
 use std::fmt;
@@ -36,11 +36,6 @@ use std::sync::Weak;
 use std::thread;
 use tempfile::TempDir;
 
-/// Create a default io error given a string.
-pub(crate) fn make_io_err(msg: String) -> io::Error {
-    io::Error::new(io::ErrorKind::Other, msg)
-}
-
 /// Returns None iff the file exists, can be read, but is empty (and hence
 /// cannot be mmapped)
 fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
@@ -48,13 +43,17 @@ fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
         if e.kind() == io::ErrorKind::NotFound {
             OpenReadError::FileDoesNotExist(full_path.to_owned())
         } else {
-            OpenReadError::IOError(IOError::with_path(full_path.to_owned(), e))
+            OpenReadError::IOError {
+                io_error: e,
+                filepath: full_path.to_owned(),
+            }
         }
     })?;
 
-    let meta_data = file
-        .metadata()
-        .map_err(|e| IOError::with_path(full_path.to_owned(), e))?;
+    let meta_data = file.metadata().map_err(|e| OpenReadError::IOError {
+        io_error: e,
+        filepath: full_path.to_owned(),
+    })?;
     if meta_data.len() == 0 {
         // if the file size is 0, it will not be possible
         // to mmap the file, so we return None
@@ -64,7 +63,10 @@ fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
     unsafe {
         memmap::Mmap::map(&file)
             .map(Some)
-            .map_err(|e| From::from(IOError::with_path(full_path.to_owned(), e)))
+            .map_err(|e| OpenReadError::IOError {
+                io_error: e,
+                filepath: full_path.to_owned(),
+            })
     }
 }
 
@@ -144,7 +146,7 @@ struct WatcherWrapper {
 }
 
 impl WatcherWrapper {
-    pub fn new(path: &Path) -> Result<Self, OpenDirectoryError> {
+    pub(crate) fn new(path: &Path, logger: Logger) -> Result<Self, OpenDirectoryError> {
         let (tx, watcher_recv): (Sender<RawEvent>, Receiver<RawEvent>) = channel();
         // We need to initialize the
         let watcher = notify::raw_watcher(tx)
@@ -158,7 +160,8 @@ impl WatcherWrapper {
                     panic!("Unknown error while starting watching directory {:?}", path);
                 }
             })?;
-        let watcher_router: Arc<WatchCallbackList> = Default::default();
+        let watcher_router: Arc<WatchCallbackList> =
+            Arc::new(WatchCallbackList::with_logger(logger));
         let watcher_router_clone = watcher_router.clone();
         thread::Builder::new()
             .name("meta-file-watch-thread".to_string())
@@ -183,6 +186,10 @@ impl WatcherWrapper {
                         }
                     }
                 }
+            })
+            .map_err(|io_error| OpenDirectoryError::IoError {
+                io_error,
+                directory_path: path.to_path_buf(),
             })?;
         Ok(WatcherWrapper {
             _watcher: Mutex::new(watcher),
@@ -217,15 +224,21 @@ struct MmapDirectoryInner {
     mmap_cache: RwLock<MmapCache>,
     _temp_directory: Option<TempDir>,
     watcher: RwLock<Option<WatcherWrapper>>,
+    logger: Logger,
 }
 
 impl MmapDirectoryInner {
-    fn new(root_path: PathBuf, temp_directory: Option<TempDir>) -> MmapDirectoryInner {
+    fn new(
+        root_path: PathBuf,
+        temp_directory: Option<TempDir>,
+        logger: Logger,
+    ) -> MmapDirectoryInner {
         MmapDirectoryInner {
             root_path,
             mmap_cache: Default::default(),
             _temp_directory: temp_directory,
             watcher: RwLock::new(None),
+            logger,
         }
     }
 
@@ -237,7 +250,7 @@ impl MmapDirectoryInner {
         // The downside is that we might create a watch wrapper that is not useful.
         let need_initialization = self.watcher.read().unwrap().is_none();
         if need_initialization {
-            let watch_wrapper = WatcherWrapper::new(&self.root_path)?;
+            let watch_wrapper = WatcherWrapper::new(&self.root_path, self.logger.clone())?;
             let mut watch_wlock = self.watcher.write().unwrap();
             // the watcher could have been initialized when we released the lock, and
             // we do not want to lose the watched files that were set.
@@ -260,8 +273,8 @@ impl fmt::Debug for MmapDirectory {
 }
 
 impl MmapDirectory {
-    fn new(root_path: PathBuf, temp_directory: Option<TempDir>) -> MmapDirectory {
-        let inner = MmapDirectoryInner::new(root_path, temp_directory);
+    fn new(root_path: PathBuf, temp_directory: Option<TempDir>, logger: Logger) -> MmapDirectory {
+        let inner = MmapDirectoryInner::new(root_path, temp_directory, logger);
         MmapDirectory {
             inner: Arc::new(inner),
         }
@@ -272,16 +285,19 @@ impl MmapDirectory {
     /// This is mostly useful to test the MmapDirectory itself.
     /// For your unit tests, prefer the RAMDirectory.
     pub fn create_from_tempdir() -> Result<MmapDirectory, OpenDirectoryError> {
-        let tempdir = TempDir::new().map_err(OpenDirectoryError::IoError)?;
-        let tempdir_path = PathBuf::from(tempdir.path());
-        Ok(MmapDirectory::new(tempdir_path, Some(tempdir)))
+        let tempdir = TempDir::new().map_err(OpenDirectoryError::FailedToCreateTempDir)?;
+        let logger = Logger::root(StdLog.fuse(), o!());
+        Ok(MmapDirectory::new(tempdir.path().to_owned(), Some(tempdir), logger))
     }
 
     /// Opens a MmapDirectory in a directory.
     ///
     /// Returns an error if the `directory_path` does not
     /// exist or if it is not a directory.
-    pub fn open<P: AsRef<Path>>(directory_path: P) -> Result<MmapDirectory, OpenDirectoryError> {
+    pub fn open_with_logger<P: AsRef<Path>>(
+        directory_path: P,
+        logger: Logger,
+    ) -> Result<MmapDirectory, OpenDirectoryError> {
         let directory_path: &Path = directory_path.as_ref();
         if !directory_path.exists() {
             Err(OpenDirectoryError::DoesNotExist(PathBuf::from(
@@ -292,10 +308,20 @@ impl MmapDirectory {
                 directory_path,
             )))
         } else {
-            Ok(MmapDirectory::new(PathBuf::from(directory_path), None))
+            Ok(MmapDirectory::new(
+                PathBuf::from(directory_path),
+                None,
+                logger,
+            ))
         }
     }
 
+    /// Creates an `MmapDirectory` at the given path.
+    pub fn open<P: AsRef<Path>>(directory_path: P) -> Result<MmapDirectory, OpenDirectoryError> {
+        let logger = Logger::root(StdLog.fuse(), o!());
+        Self::open_with_logger(directory_path, logger)
+    }
+
     /// Joins a relative_path to the directory `root_path`
     /// to create a proper complete `filepath`.
     fn resolve_path(&self, relative_path: &Path) -> PathBuf {
@@ -355,11 +381,12 @@ impl MmapDirectory {
 struct ReleaseLockFile {
     _file: File,
     path: PathBuf,
+    logger: Logger,
 }
 
 impl Drop for ReleaseLockFile {
     fn drop(&mut self) {
-        debug!("Releasing lock {:?}", self.path);
+        debug!(self.logger, "Releasing lock {:?}", self.path);
     }
 }
 
@@ -398,16 +425,18 @@ impl TerminatingWrite for SafeFileWriter {
 
 impl Directory for MmapDirectory {
     fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
-        debug!("Open Read {:?}", path);
         let full_path = self.resolve_path(path);
-
         let mut mmap_cache = self.inner.mmap_cache.write().map_err(|_| {
             let msg = format!(
                 "Failed to acquired write lock \
                  on mmap cache while reading {:?}",
                 path
             );
-            IOError::with_path(path.to_owned(), make_io_err(msg))
+            let io_error = io::Error::new(io::ErrorKind::Other, msg);
+            OpenReadError::IOError {
+                io_error,
+                filepath: path.to_owned(),
+            }
         })?;
         Ok(mmap_cache
             .get_mmap(&full_path)?
@@ -420,14 +449,18 @@ impl Directory for MmapDirectory {
     fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
         let full_path = self.resolve_path(path);
         match fs::remove_file(&full_path) {
-            Ok(_) => self
-                .sync_directory()
-                .map_err(|e| IOError::with_path(path.to_owned(), e).into()),
+            Ok(_) => self.sync_directory().map_err(|e| DeleteError::IOError {
+                io_error: e,
+                filepath: path.to_path_buf(),
+            }),
             Err(e) => {
                 if e.kind() == io::ErrorKind::NotFound {
                     Err(DeleteError::FileDoesNotExist(path.to_owned()))
                 } else {
-                    Err(IOError::with_path(path.to_owned(), e).into())
+                    Err(DeleteError::IOError {
+                        io_error: e,
+                        filepath: path.to_path_buf(),
+                    })
                 }
             }
         }
@@ -439,9 +472,7 @@ impl Directory for MmapDirectory {
     }
 
     fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
-        debug!("Open Write {:?}", path);
         let full_path = self.resolve_path(path);
-
         let open_res = OpenOptions::new()
             .write(true)
             .create_new(true)
@@ -451,18 +482,25 @@ impl Directory for MmapDirectory {
             if err.kind() == io::ErrorKind::AlreadyExists {
                 OpenWriteError::FileAlreadyExists(path.to_owned())
             } else {
-                IOError::with_path(path.to_owned(), err).into()
+                OpenWriteError::IOError {
+                    io_error: err,
+                    filepath: path.to_owned(),
+                }
             }
         })?;
 
         // making sure the file is created.
-        file.flush()
-            .map_err(|e| IOError::with_path(path.to_owned(), e))?;
+        file.flush().map_err(|io_error| OpenWriteError::IOError {
+            io_error,
+            filepath: path.to_owned(),
+        })?;
 
         // Apparetntly, on some filesystem syncing the parent
         // directory is required.
-        self.sync_directory()
-            .map_err(|e| IOError::with_path(path.to_owned(), e))?;
+        self.sync_directory().map_err(|e| OpenWriteError::IOError {
+            io_error: e,
+            filepath: path.to_owned(),
+        })?;
 
         let writer = SafeFileWriter::new(file);
         Ok(BufWriter::new(Box::new(writer)))
@@ -474,24 +512,31 @@ impl Directory for MmapDirectory {
         match File::open(&full_path) {
             Ok(mut file) => {
                 file.read_to_end(&mut buffer)
-                    .map_err(|e| IOError::with_path(path.to_owned(), e))?;
+                    .map_err(|io_error| OpenReadError::IOError {
+                        io_error,
+                        filepath: path.to_owned(),
+                    })?;
                 Ok(buffer)
             }
-            Err(e) => {
-                if e.kind() == io::ErrorKind::NotFound {
+            Err(io_error) => {
+                if io_error.kind() == io::ErrorKind::NotFound {
                     Err(OpenReadError::FileDoesNotExist(path.to_owned()))
                 } else {
-                    Err(IOError::with_path(path.to_owned(), e).into())
+                    Err(OpenReadError::IOError {
+                        io_error,
+                        filepath: path.to_owned(),
+                    })
                 }
             }
         }
     }
 
-    fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
-        debug!("Atomic Write {:?}", path);
+    fn atomic_write(&mut self, path: &Path, content: &[u8]) -> io::Result<()> {
+        let mut tempfile = tempfile::Builder::new().tempfile_in(&self.inner.root_path)?;
+        tempfile.write_all(content)?;
+        tempfile.flush()?;
         let full_path = self.resolve_path(path);
-        let meta_file = atomicwrites::AtomicFile::new(full_path, atomicwrites::AllowOverwrite);
-        meta_file.write(|f| f.write_all(data))?;
+        tempfile.into_temp_path().persist(full_path)?;
         Ok(())
     }
 
@@ -508,16 +553,22 @@ impl Directory for MmapDirectory {
         } else {
             file.try_lock_exclusive().map_err(|_| LockError::LockBusy)?
         }
+        let logger = self.inner.logger.clone();
         // dropping the file handle will release the lock.
         Ok(DirectoryLock::from(Box::new(ReleaseLockFile {
             path: lock.filepath.clone(),
             _file: file,
+            logger,
         })))
     }
 
     fn watch(&self, watch_callback: WatchCallback) -> crate::Result<WatchHandle> {
         self.inner.watch(watch_callback)
     }
+
+    fn logger(&self) -> &Logger {
+        &self.inner.logger
+    }
 }
 
 #[cfg(test)]
@@ -627,7 +678,8 @@ mod tests {
         let counter_clone = counter.clone();
         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 logger = Logger::root(slog::Discard, o!());
+        let mut watch_wrapper = WatcherWrapper::new(&tmp_dirpath, logger).unwrap();
         let tmp_file = tmp_dirpath.join(*META_FILEPATH);
         let _handle = watch_wrapper.watch(Box::new(move || {
             counter_clone.fetch_add(1, Ordering::SeqCst);
@@ -652,7 +704,7 @@ mod tests {
         {
             let index = Index::create(mmap_directory.clone(), schema).unwrap();
 
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             let mut log_merge_policy = LogMergePolicy::default();
             log_merge_policy.set_min_merge_size(3);
             index_writer.set_merge_policy(Box::new(log_merge_policy));

src/directory/mod.rs

@@ -23,7 +23,8 @@ pub use self::directory::{Directory, DirectoryClone};
 pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
 pub use self::ram_directory::RAMDirectory;
 pub use self::read_only_source::ReadOnlySource;
-pub use self::watch_event_router::{WatchCallback, WatchCallbackList, WatchHandle};
+pub(crate) use self::watch_event_router::WatchCallbackList;
+pub use self::watch_event_router::{WatchCallback, WatchHandle};
 use std::io::{self, BufWriter, Write};
 use std::path::PathBuf;
 /// Outcome of the Garbage collection

src/directory/ram_directory.rs

@@ -5,6 +5,8 @@ use crate::directory::WatchCallbackList;
 use crate::directory::{Directory, ReadOnlySource, WatchCallback, WatchHandle};
 use crate::directory::{TerminatingWrite, WritePtr};
 use fail::fail_point;
+use slog::{o, Drain, Logger};
+use slog_stdlog::StdLog;
 use std::collections::HashMap;
 use std::fmt;
 use std::io::{self, BufWriter, Cursor, Seek, SeekFrom, Write};
@@ -66,7 +68,7 @@ impl Write for VecWriter {
 
     fn flush(&mut self) -> io::Result<()> {
         self.is_flushed = true;
-        let mut fs = self.shared_directory.fs.write().unwrap();
+        let mut fs = self.shared_directory.fs.inner_directory.write().unwrap();
         fs.write(self.path.clone(), self.data.get_ref());
         Ok(())
     }
@@ -78,13 +80,19 @@ impl TerminatingWrite for VecWriter {
     }
 }
 
-#[derive(Default)]
 struct InnerDirectory {
     fs: HashMap<PathBuf, ReadOnlySource>,
     watch_router: WatchCallbackList,
 }
 
 impl InnerDirectory {
+    fn with_logger(logger: Logger) -> Self {
+        InnerDirectory {
+            fs: Default::default(),
+            watch_router: WatchCallbackList::with_logger(logger.clone()),
+        }
+    }
+
     fn write(&mut self, path: PathBuf, data: &[u8]) -> bool {
         let data = ReadOnlySource::new(Vec::from(data));
         self.fs.insert(path, data).is_some()
@@ -117,20 +125,32 @@ impl InnerDirectory {
     }
 }
 
+impl Default for RAMDirectory {
+    fn default() -> RAMDirectory {
+        let logger = Logger::root(StdLog.fuse(), o!());
+        Self::with_logger(logger)
+    }
+}
+
 impl fmt::Debug for RAMDirectory {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "RAMDirectory")
     }
 }
 
+struct Inner {
+    inner_directory: RwLock<InnerDirectory>,
+    logger: Logger,
+}
+
 /// A Directory storing everything in anonymous memory.
 ///
 /// It is mainly meant for unit testing.
 /// Writes are only made visible upon flushing.
 ///
-#[derive(Clone, Default)]
+#[derive(Clone)]
 pub struct RAMDirectory {
-    fs: Arc<RwLock<InnerDirectory>>,
+    fs: Arc<Inner>,
 }
 
 impl RAMDirectory {
@@ -139,10 +159,21 @@ impl RAMDirectory {
         Self::default()
     }
 
+    /// Create a `RAMDirectory` with a custom logger.
+    pub fn with_logger(logger: Logger) -> RAMDirectory {
+        let inner_directory = InnerDirectory::with_logger(logger.clone()).into();
+        RAMDirectory {
+            fs: Arc::new(Inner {
+                inner_directory,
+                logger,
+            }),
+        }
+    }
+
     /// Returns the sum of the size of the different files
     /// in the RAMDirectory.
     pub fn total_mem_usage(&self) -> usize {
-        self.fs.read().unwrap().total_mem_usage()
+        self.fs.inner_directory.read().unwrap().total_mem_usage()
     }
 
     /// Write a copy of all of the files saved in the RAMDirectory in the target `Directory`.
@@ -152,7 +183,7 @@ impl RAMDirectory {
     ///
     /// If an error is encounterred, files may be persisted partially.
     pub fn persist(&self, dest: &mut dyn Directory) -> crate::Result<()> {
-        let wlock = self.fs.write().unwrap();
+        let wlock = self.fs.inner_directory.write().unwrap();
         for (path, source) in wlock.fs.iter() {
             let mut dest_wrt = dest.open_write(path)?;
             dest_wrt.write_all(source.as_slice())?;
@@ -164,24 +195,25 @@ impl RAMDirectory {
 
 impl Directory for RAMDirectory {
     fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
-        self.fs.read().unwrap().open_read(path)
+        self.fs.inner_directory.read().unwrap().open_read(path)
     }
 
     fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
         fail_point!("RAMDirectory::delete", |_| {
-            use crate::directory::error::IOError;
-            let io_error = IOError::from(io::Error::from(io::ErrorKind::Other));
-            Err(DeleteError::from(io_error))
+            Err(DeleteError::IOError {
+                io_error: io::Error::from(io::ErrorKind::Other),
+                filepath: path.to_path_buf(),
+            })
         });
-        self.fs.write().unwrap().delete(path)
+        self.fs.inner_directory.write().unwrap().delete(path)
     }
 
     fn exists(&self, path: &Path) -> bool {
-        self.fs.read().unwrap().exists(path)
+        self.fs.inner_directory.read().unwrap().exists(path)
     }
 
     fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
-        let mut fs = self.fs.write().unwrap();
+        let mut fs = self.fs.inner_directory.write().unwrap();
         let path_buf = PathBuf::from(path);
         let vec_writer = VecWriter::new(path_buf.clone(), self.clone());
         let exists = fs.write(path_buf.clone(), &[]);
@@ -205,19 +237,38 @@ impl Directory for RAMDirectory {
         let path_buf = PathBuf::from(path);
 
         // Reserve the path to prevent calls to .write() to succeed.
-        self.fs.write().unwrap().write(path_buf.clone(), &[]);
+        self.fs
+            .inner_directory
+            .write()
+            .unwrap()
+            .write(path_buf.clone(), &[]);
 
         let mut vec_writer = VecWriter::new(path_buf, self.clone());
         vec_writer.write_all(data)?;
         vec_writer.flush()?;
         if path == Path::new(&*META_FILEPATH) {
-            let _ = self.fs.write().unwrap().watch_router.broadcast();
+            let _ = self
+                .fs
+                .inner_directory
+                .write()
+                .unwrap()
+                .watch_router
+                .broadcast();
         }
         Ok(())
     }
 
     fn watch(&self, watch_callback: WatchCallback) -> crate::Result<WatchHandle> {
-        Ok(self.fs.write().unwrap().watch(watch_callback))
+        Ok(self
+            .fs
+            .inner_directory
+            .write()
+            .unwrap()
+            .watch(watch_callback))
+    }
+
+    fn logger(&self) -> &Logger {
+        &self.fs.logger
     }
 }
 

src/directory/tests.rs

@@ -211,19 +211,19 @@ fn test_watch(directory: &mut dyn Directory) {
         .unwrap();
 
     for i in 0..10 {
-        assert_eq!(i, counter.load(SeqCst));
+        assert!(i <= counter.load(SeqCst));
         assert!(directory
             .atomic_write(Path::new("meta.json"), b"random_test_data_2")
             .is_ok());
         assert_eq!(receiver.recv_timeout(Duration::from_millis(500)), Ok(i));
-        assert_eq!(i + 1, counter.load(SeqCst));
+        assert!(i + 1 <= counter.load(SeqCst)); // notify can trigger more than once.
     }
     mem::drop(watch_handle);
     assert!(directory
         .atomic_write(Path::new("meta.json"), b"random_test_data")
         .is_ok());
     assert!(receiver.recv_timeout(Duration::from_millis(500)).is_ok());
-    assert_eq!(10, counter.load(SeqCst));
+    assert!(10 <= counter.load(SeqCst));
 }
 
 fn test_lock_non_blocking(directory: &mut dyn Directory) {

src/directory/watch_event_router.rs

@@ -1,5 +1,6 @@
 use futures::channel::oneshot;
 use futures::{Future, TryFutureExt};
+use slog::{error, Logger};
 use std::sync::Arc;
 use std::sync::RwLock;
 use std::sync::Weak;
@@ -11,9 +12,9 @@ pub type WatchCallback = Box<dyn Fn() + Sync + Send>;
 ///
 /// It registers callbacks (See `.subscribe(...)`) and
 /// calls them upon calls to `.broadcast(...)`.
-#[derive(Default)]
-pub struct WatchCallbackList {
+pub(crate) struct WatchCallbackList {
     router: RwLock<Vec<Weak<WatchCallback>>>,
+    logger: Logger,
 }
 
 /// Controls how long a directory should watch for a file change.
@@ -32,6 +33,13 @@ impl WatchHandle {
 }
 
 impl WatchCallbackList {
+    pub fn with_logger(logger: Logger) -> Self {
+        WatchCallbackList {
+            logger,
+            router: Default::default(),
+        }
+    }
+
     /// Subscribes a new callback and returns a handle that controls the lifetime of the callback.
     pub fn subscribe(&self, watch_callback: WatchCallback) -> WatchHandle {
         let watch_callback_arc = Arc::new(watch_callback);
@@ -74,8 +82,8 @@ impl WatchCallbackList {
             });
         if let Err(err) = spawn_res {
             error!(
-                "Failed to spawn thread to call watch callbacks. Cause: {:?}",
-                err
+                self.logger,
+                "Failed to spawn thread to call watch callbacks. Cause: {:?}", err
             );
         }
         result
@@ -86,13 +94,18 @@ impl WatchCallbackList {
 mod tests {
     use crate::directory::WatchCallbackList;
     use futures::executor::block_on;
+    use slog::{o, Discard, Logger};
     use std::mem;
     use std::sync::atomic::{AtomicUsize, Ordering};
     use std::sync::Arc;
 
+    fn default_watch_callback_list() -> WatchCallbackList {
+        WatchCallbackList::with_logger(Logger::root(Discard, o!()))
+    }
+
     #[test]
     fn test_watch_event_router_simple() {
-        let watch_event_router = WatchCallbackList::default();
+        let watch_event_router = default_watch_callback_list();
         let counter: Arc<AtomicUsize> = Default::default();
         let counter_clone = counter.clone();
         let inc_callback = Box::new(move || {
@@ -119,7 +132,7 @@ mod tests {
 
     #[test]
     fn test_watch_event_router_multiple_callback_same_key() {
-        let watch_event_router = WatchCallbackList::default();
+        let watch_event_router = default_watch_callback_list();
         let counter: Arc<AtomicUsize> = Default::default();
         let inc_callback = |inc: usize| {
             let counter_clone = counter.clone();
@@ -148,7 +161,7 @@ mod tests {
 
     #[test]
     fn test_watch_event_router_multiple_callback_different_key() {
-        let watch_event_router = WatchCallbackList::default();
+        let watch_event_router = default_watch_callback_list();
         let counter: Arc<AtomicUsize> = Default::default();
         let counter_clone = counter.clone();
         let inc_callback = Box::new(move || {

src/error.rs

@@ -2,11 +2,13 @@
 
 use std::io;
 
-use crate::directory::error::{IOError, OpenDirectoryError, OpenReadError, OpenWriteError};
 use crate::directory::error::{Incompatibility, LockError};
 use crate::fastfield::FastFieldNotAvailableError;
 use crate::query;
-use crate::schema;
+use crate::{
+    directory::error::{OpenDirectoryError, OpenReadError, OpenWriteError},
+    schema,
+};
 use std::fmt;
 use std::path::PathBuf;
 use std::sync::PoisonError;
@@ -43,44 +45,47 @@ impl fmt::Debug for DataCorruption {
     }
 }
 
-/// The library's failure based error enum
-#[derive(Debug, Fail)]
+/// The library's error enum
+#[derive(Debug, Error)]
 pub enum TantivyError {
-    /// Path does not exist.
-    #[fail(display = "Path does not exist: '{:?}'", _0)]
-    PathDoesNotExist(PathBuf),
-    /// File already exists, this is a problem when we try to write into a new file.
-    #[fail(display = "File already exists: '{:?}'", _0)]
-    FileAlreadyExists(PathBuf),
+    /// Failed to open the directory.
+    #[error("Failed to open the directory: '{0:?}'")]
+    OpenDirectoryError(#[from] OpenDirectoryError),
+    /// Failed to open a file for read.
+    #[error("Failed to open file for read: '{0:?}'")]
+    OpenReadError(#[from] OpenReadError),
+    /// Failed to open a file for write.
+    #[error("Failed to open file for write: '{0:?}'")]
+    OpenWriteError(#[from] OpenWriteError),
     /// Index already exists in this directory
-    #[fail(display = "Index already exists")]
+    #[error("Index already exists")]
     IndexAlreadyExists,
     /// Failed to acquire file lock
-    #[fail(display = "Failed to acquire Lockfile: {:?}. {:?}", _0, _1)]
+    #[error("Failed to acquire Lockfile: {0:?}. {1:?}")]
     LockFailure(LockError, Option<String>),
     /// IO Error.
-    #[fail(display = "An IO error occurred: '{}'", _0)]
-    IOError(#[cause] IOError),
+    #[error("An IO error occurred: '{0}'")]
+    IOError(#[from] io::Error),
     /// Data corruption.
-    #[fail(display = "{:?}", _0)]
+    #[error("Data corrupted: '{0:?}'")]
     DataCorruption(DataCorruption),
     /// A thread holding the locked panicked and poisoned the lock.
-    #[fail(display = "A thread holding the locked panicked and poisoned the lock")]
+    #[error("A thread holding the locked panicked and poisoned the lock")]
     Poisoned,
     /// Invalid argument was passed by the user.
-    #[fail(display = "An invalid argument was passed: '{}'", _0)]
+    #[error("An invalid argument was passed: '{0}'")]
     InvalidArgument(String),
     /// An Error happened in one of the thread.
-    #[fail(display = "An error occurred in a thread: '{}'", _0)]
+    #[error("An error occurred in a thread: '{0}'")]
     ErrorInThread(String),
     /// An Error appeared related to the schema.
-    #[fail(display = "Schema error: '{}'", _0)]
+    #[error("Schema error: '{0}'")]
     SchemaError(String),
     /// System error. (e.g.: We failed spawning a new thread)
-    #[fail(display = "System error.'{}'", _0)]
+    #[error("System error.'{0}'")]
     SystemError(String),
     /// Index incompatible with current version of tantivy
-    #[fail(display = "{:?}", _0)]
+    #[error("{0:?}")]
     IncompatibleIndex(Incompatibility),
 }
 
@@ -89,31 +94,17 @@ impl From<DataCorruption> for TantivyError {
         TantivyError::DataCorruption(data_corruption)
     }
 }
-
 impl From<FastFieldNotAvailableError> for TantivyError {
     fn from(fastfield_error: FastFieldNotAvailableError) -> TantivyError {
         TantivyError::SchemaError(format!("{}", fastfield_error))
     }
 }
-
 impl From<LockError> for TantivyError {
     fn from(lock_error: LockError) -> TantivyError {
         TantivyError::LockFailure(lock_error, None)
     }
 }
 
-impl From<IOError> for TantivyError {
-    fn from(io_error: IOError) -> TantivyError {
-        TantivyError::IOError(io_error)
-    }
-}
-
-impl From<io::Error> for TantivyError {
-    fn from(io_error: io::Error) -> TantivyError {
-        TantivyError::IOError(io_error.into())
-    }
-}
-
 impl From<query::QueryParserError> for TantivyError {
     fn from(parsing_error: query::QueryParserError) -> TantivyError {
         TantivyError::InvalidArgument(format!("Query is invalid. {:?}", parsing_error))
@@ -126,49 +117,12 @@ impl<Guard> From<PoisonError<Guard>> for TantivyError {
     }
 }
 
-impl From<OpenReadError> for TantivyError {
-    fn from(error: OpenReadError) -> TantivyError {
-        match error {
-            OpenReadError::FileDoesNotExist(filepath) => TantivyError::PathDoesNotExist(filepath),
-            OpenReadError::IOError(io_error) => TantivyError::IOError(io_error),
-            OpenReadError::IncompatibleIndex(incompatibility) => {
-                TantivyError::IncompatibleIndex(incompatibility)
-            }
-        }
-    }
-}
-
 impl From<schema::DocParsingError> for TantivyError {
     fn from(error: schema::DocParsingError) -> TantivyError {
         TantivyError::InvalidArgument(format!("Failed to parse document {:?}", error))
     }
 }
 
-impl From<OpenWriteError> for TantivyError {
-    fn from(error: OpenWriteError) -> TantivyError {
-        match error {
-            OpenWriteError::FileAlreadyExists(filepath) => {
-                TantivyError::FileAlreadyExists(filepath)
-            }
-            OpenWriteError::IOError(io_error) => TantivyError::IOError(io_error),
-        }
-    }
-}
-
-impl From<OpenDirectoryError> for TantivyError {
-    fn from(error: OpenDirectoryError) -> TantivyError {
-        match error {
-            OpenDirectoryError::DoesNotExist(directory_path) => {
-                TantivyError::PathDoesNotExist(directory_path)
-            }
-            OpenDirectoryError::NotADirectory(directory_path) => {
-                TantivyError::InvalidArgument(format!("{:?} is not a directory", directory_path))
-            }
-            OpenDirectoryError::IoError(err) => TantivyError::IOError(IOError::from(err)),
-        }
-    }
-}
-
 impl From<serde_json::Error> for TantivyError {
     fn from(error: serde_json::Error) -> TantivyError {
         let io_err = io::Error::from(error);

src/fastfield/bytes/mod.rs

@@ -15,7 +15,7 @@ mod tests {
         let field = schema_builder.add_bytes_field("bytesfield");
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(field=>vec![0u8, 1, 2, 3]));
         index_writer.add_document(doc!(field=>vec![]));
         index_writer.add_document(doc!(field=>vec![255u8]));

src/fastfield/error.rs

@@ -4,8 +4,8 @@ use std::result;
 /// `FastFieldNotAvailableError` is returned when the
 /// user requested for a fast field reader, and the field was not
 /// defined in the schema as a fast field.
-#[derive(Debug, Fail)]
-#[fail(display = "Fast field not available: '{:?}'", field_name)]
+#[derive(Debug, Error)]
+#[error("Fast field not available: '{field_name:?}'")]
 pub struct FastFieldNotAvailableError {
     field_name: String,
 }

src/fastfield/mod.rs

@@ -474,7 +474,7 @@ mod tests {
         let date_field = schema_builder.add_date_field("date", FAST);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.set_merge_policy(Box::new(NoMergePolicy));
         index_writer.add_document(doc!(date_field =>crate::chrono::prelude::Utc::now()));
         index_writer.commit().unwrap();
@@ -511,7 +511,7 @@ mod tests {
         );
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.set_merge_policy(Box::new(NoMergePolicy));
         index_writer.add_document(doc!(
             date_field => crate::DateTime::from_u64(1i64.to_u64()),

src/fastfield/multivalued/mod.rs

@@ -25,7 +25,7 @@ mod tests {
         );
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(field=>1u64, field=>3u64));
         index_writer.add_document(doc!());
         index_writer.add_document(doc!(field=>4u64));
@@ -64,7 +64,7 @@ mod tests {
             schema_builder.add_i64_field("time_stamp_i", IntOptions::default().set_stored());
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         let first_time_stamp = chrono::Utc::now();
         index_writer.add_document(
             doc!(date_field=>first_time_stamp, date_field=>first_time_stamp, time_i=>1i64),
@@ -186,7 +186,7 @@ mod tests {
         );
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(field=> 1i64, field => 3i64));
         index_writer.add_document(doc!());
         index_writer.add_document(doc!(field=> -4i64));
@@ -221,7 +221,7 @@ mod tests {
         let field = schema_builder.add_facet_field("facetfield");
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         for i in 0..100_000 {
             index_writer.add_document(doc!(field=> Facet::from(format!("/lang/{}", i).as_str())));
         }

src/fastfield/multivalued/reader.rs

@@ -74,7 +74,7 @@ mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         let mut index_writer = index
-            .writer_with_num_threads(1, 30_000_000)
+            .writer_for_tests()
             .expect("Failed to create index writer.");
         index_writer.add_document(doc!(
             facet_field => Facet::from("/category/cat2"),

src/indexer/index_writer.rs

@@ -27,6 +27,7 @@ use crate::Opstamp;
 use crossbeam::channel;
 use futures::executor::block_on;
 use futures::future::Future;
+use slog::{error, info, Logger};
 use smallvec::smallvec;
 use smallvec::SmallVec;
 use std::mem;
@@ -195,20 +196,21 @@ fn index_documents(
     grouped_document_iterator: &mut dyn Iterator<Item = OperationGroup>,
     segment_updater: &mut SegmentUpdater,
     mut delete_cursor: DeleteCursor,
+    logger: &Logger,
 ) -> crate::Result<bool> {
     let schema = segment.schema();
 
+    info!(logger, "segment-index"; "stage"=>"start");
     let mut segment_writer = SegmentWriter::for_segment(memory_budget, segment.clone(), &schema)?;
+    let mut buffer_limit_reached = false;
     for document_group in grouped_document_iterator {
         for doc in document_group {
             segment_writer.add_document(doc, &schema)?;
         }
         let mem_usage = segment_writer.mem_usage();
         if mem_usage >= memory_budget - MARGIN_IN_BYTES {
-            info!(
-                "Buffer limit reached, flushing segment with maxdoc={}.",
-                segment_writer.max_doc()
-            );
+            buffer_limit_reached = true;
+
             break;
         }
     }
@@ -228,6 +230,14 @@ fn index_documents(
     let segment_with_max_doc = segment.with_max_doc(max_doc);
 
     let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap());
+    info!(
+        logger,
+        "segment-index";
+        "stage" => "serialize",
+        "cause" => if buffer_limit_reached { "buffer-limit" } else { "commit" },
+        "maxdoc" => max_doc,
+        "last_docstamp" => last_docstamp
+    );
 
     let delete_bitset_opt = apply_deletes(
         &segment_with_max_doc,
@@ -241,7 +251,18 @@ fn index_documents(
         delete_cursor,
         delete_bitset_opt,
     );
+
+    info!(
+        logger,
+        "segment-index";
+        "stage" => "publish",
+    );
     block_on(segment_updater.schedule_add_segment(segment_entry))?;
+    info!(
+        logger,
+        "segment-index";
+        "stage" => "end",
+    );
     Ok(true)
 }
 
@@ -344,6 +365,10 @@ impl IndexWriter {
         Ok(index_writer)
     }
 
+    pub(crate) fn logger(&self) -> &Logger {
+        self.index.logger()
+    }
+
     fn drop_sender(&mut self) {
         let (sender, _receiver) = channel::bounded(1);
         self.operation_sender = sender;
@@ -352,6 +377,8 @@ impl IndexWriter {
     /// If there are some merging threads, blocks until they all finish their work and
     /// then drop the `IndexWriter`.
     pub fn wait_merging_threads(mut self) -> crate::Result<()> {
+        info!(self.logger(), "wait-merge-threads"; "stage"=>"start");
+
         // this will stop the indexing thread,
         // dropping the last reference to the segment_updater.
         self.drop_sender();
@@ -372,9 +399,9 @@ impl IndexWriter {
             .map_err(|_| TantivyError::ErrorInThread("Failed to join merging thread.".into()));
 
         if let Err(ref e) = result {
-            error!("Some merging thread failed {:?}", e);
+            error!(self.logger(), "some merge thread failed"; "cause"=>e.to_string());
         }
-
+        info!(self.logger(), "wait-merge-threads"; "stage"=>"stop");
         result
     }
 
@@ -434,12 +461,16 @@ impl IndexWriter {
                         return Ok(());
                     }
                     let segment = index.new_segment();
+                    let segment_id = segment.id();
                     index_documents(
                         mem_budget,
                         segment,
                         &mut document_iterator,
                         &mut segment_updater,
                         delete_cursor.clone(),
+                        &index
+                            .logger()
+                            .new(slog::o!("segment"=>segment_id.to_string())),
                     )?;
                 }
             })?;
@@ -553,7 +584,10 @@ impl IndexWriter {
     ///
     /// The opstamp at the last commit is returned.
     pub fn rollback(&mut self) -> crate::Result<Opstamp> {
-        info!("Rolling back to opstamp {}", self.committed_opstamp);
+        info!(
+            self.logger(),
+            "Rolling back to opstamp {}", self.committed_opstamp
+        );
         // marks the segment updater as killed. From now on, all
         // segment updates will be ignored.
         self.segment_updater.kill();
@@ -610,6 +644,8 @@ impl IndexWriter {
     /// using this API.
     /// See [`PreparedCommit::set_payload()`](PreparedCommit.html)
     pub fn prepare_commit(&mut self) -> crate::Result<PreparedCommit> {
+        let logger = self.logger().clone();
+
         // Here, because we join all of the worker threads,
         // all of the segment update for this commit have been
         // sent.
@@ -620,7 +656,10 @@ impl IndexWriter {
         //
         // This will move uncommitted segments to the state of
         // committed segments.
-        info!("Preparing commit");
+
+        let commit_opstamp = self.stamper.stamp();
+
+        info!(logger, "prepare-commit"; "opstamp" => commit_opstamp);
 
         // this will drop the current document channel
         // and recreate a new one.
@@ -636,9 +675,8 @@ impl IndexWriter {
             self.add_indexing_worker()?;
         }
 
-        let commit_opstamp = self.stamper.stamp();
         let prepared_commit = PreparedCommit::new(self, commit_opstamp);
-        info!("Prepared commit {}", commit_opstamp);
+        info!(logger, "Prepared commit {}", commit_opstamp);
         Ok(prepared_commit)
     }
 
@@ -800,7 +838,7 @@ mod tests {
         let mut schema_builder = schema::Schema::builder();
         let text_field = schema_builder.add_text_field("text", schema::TEXT);
         let index = Index::create_in_ram(schema_builder.build());
-        let index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let index_writer = index.writer_for_tests().unwrap();
         let operations = vec![
             UserOperation::Add(doc!(text_field=>"a")),
             UserOperation::Add(doc!(text_field=>"b")),
@@ -815,7 +853,7 @@ mod tests {
         let text_field = schema_builder.add_text_field("text", schema::TEXT);
         let index = Index::create_in_ram(schema_builder.build());
 
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(text_field => "hello1"));
         index_writer.add_document(doc!(text_field => "hello2"));
         assert!(index_writer.commit().is_ok());
@@ -864,7 +902,7 @@ mod tests {
             .reload_policy(ReloadPolicy::Manual)
             .try_into()
             .unwrap();
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         let a_term = Term::from_field_text(text_field, "a");
         let b_term = Term::from_field_text(text_field, "b");
         let operations = vec![
@@ -926,8 +964,8 @@ mod tests {
     fn test_lockfile_already_exists_error_msg() {
         let schema_builder = schema::Schema::builder();
         let index = Index::create_in_ram(schema_builder.build());
-        let _index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
-        match index.writer_with_num_threads(1, 3_000_000) {
+        let _index_writer = index.writer_for_tests().unwrap();
+        match index.writer_for_tests() {
             Err(err) => {
                 let err_msg = err.to_string();
                 assert!(err_msg.contains("already an `IndexWriter`"));
@@ -1261,7 +1299,7 @@ mod tests {
         let idfield = schema_builder.add_text_field("id", STRING);
         schema_builder.add_text_field("optfield", STRING);
         let index = Index::create_in_ram(schema_builder.build());
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(idfield=>"myid"));
         let commit = index_writer.commit();
         assert!(commit.is_ok());

src/indexer/merger.rs

@@ -25,14 +25,14 @@ use std::cmp;
 use std::collections::HashMap;
 use std::sync::Arc;
 
-fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
+fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> crate::Result<u64> {
     let mut total_tokens = 0u64;
     let mut count: [usize; 256] = [0; 256];
     for reader in readers {
         if reader.has_deletes() {
             // if there are deletes, then we use an approximation
             // using the fieldnorm
-            let fieldnorms_reader = reader.get_fieldnorms_reader(field);
+            let fieldnorms_reader = reader.get_fieldnorms_reader(field)?;
             for doc in reader.doc_ids_alive() {
                 let fieldnorm_id = fieldnorms_reader.fieldnorm_id(doc);
                 count[fieldnorm_id as usize] += 1;
@@ -41,7 +41,7 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
             total_tokens += reader.inverted_index(field).total_num_tokens();
         }
     }
-    total_tokens
+    Ok(total_tokens
         + count
             .iter()
             .cloned()
@@ -49,7 +49,7 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
             .map(|(fieldnorm_ord, count)| {
                 count as u64 * u64::from(FieldNormReader::id_to_fieldnorm(fieldnorm_ord as u8))
             })
-            .sum::<u64>()
+            .sum::<u64>())
 }
 
 pub struct IndexMerger {
@@ -175,7 +175,7 @@ impl IndexMerger {
         for field in fields {
             fieldnorms_data.clear();
             for reader in &self.readers {
-                let fieldnorms_reader = reader.get_fieldnorms_reader(field);
+                let fieldnorms_reader = reader.get_fieldnorms_reader(field)?;
                 for doc_id in reader.doc_ids_alive() {
                     let fieldnorm_id = fieldnorms_reader.fieldnorm_id(doc_id);
                     fieldnorms_data.push(fieldnorm_id);
@@ -541,7 +541,7 @@ impl IndexMerger {
         // The total number of tokens will only be exact when there has been no deletes.
         //
         // Otherwise, we approximate by removing deleted documents proportionally.
-        let total_num_tokens: u64 = compute_total_num_tokens(&self.readers, indexed_field);
+        let total_num_tokens: u64 = compute_total_num_tokens(&self.readers, indexed_field)?;
 
         // Create the total list of doc ids
         // by stacking the doc ids from the different segment.
@@ -751,7 +751,7 @@ mod tests {
         };
 
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             {
                 // writing the segment
                 {
@@ -803,7 +803,7 @@ mod tests {
             let segment_ids = index
                 .searchable_segment_ids()
                 .expect("Searchable segments failed.");
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
             index_writer.wait_merging_threads().unwrap();
         }
@@ -904,7 +904,7 @@ mod tests {
         let score_field = schema_builder.add_u64_field("score", score_fieldtype);
         let bytes_score_field = schema_builder.add_bytes_field("score_bytes");
         let index = Index::create_in_ram(schema_builder.build());
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         let reader = index.reader().unwrap();
         let search_term = |searcher: &Searcher, term: Term| {
             let collector = FastFieldTestCollector::for_field(score_field);
@@ -1211,7 +1211,7 @@ mod tests {
         let index = Index::create_in_ram(schema_builder.build());
         let reader = index.reader().unwrap();
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             let index_doc = |index_writer: &mut IndexWriter, doc_facets: &[&str]| {
                 let mut doc = Document::default();
                 for facet in doc_facets {
@@ -1276,7 +1276,7 @@ mod tests {
             let segment_ids = index
                 .searchable_segment_ids()
                 .expect("Searchable segments failed.");
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
             index_writer.wait_merging_threads().unwrap();
             reader.reload().unwrap();
@@ -1295,7 +1295,7 @@ mod tests {
 
         // Deleting one term
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             let facet = Facet::from_path(vec!["top", "a", "firstdoc"]);
             let facet_term = Term::from_facet(facet_field, &facet);
             index_writer.delete_term(facet_term);
@@ -1320,7 +1320,7 @@ mod tests {
         let mut schema_builder = schema::Schema::builder();
         let int_field = schema_builder.add_u64_field("intvals", INDEXED);
         let index = Index::create_in_ram(schema_builder.build());
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(int_field => 1u64));
         index_writer.commit().expect("commit failed");
         index_writer.add_document(doc!(int_field => 1u64));
@@ -1349,7 +1349,7 @@ mod tests {
         let index = Index::create_in_ram(schema_builder.build());
         let reader = index.reader().unwrap();
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             let mut doc = Document::default();
             doc.add_u64(int_field, 1);
             index_writer.add_document(doc.clone());
@@ -1388,7 +1388,7 @@ mod tests {
         let index = Index::create_in_ram(schema_builder.build());
 
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             let index_doc = |index_writer: &mut IndexWriter, int_vals: &[u64]| {
                 let mut doc = Document::default();
                 for &val in int_vals {
@@ -1462,7 +1462,7 @@ mod tests {
             let segment_ids = index
                 .searchable_segment_ids()
                 .expect("Searchable segments failed.");
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             assert!(block_on(index_writer.merge(&segment_ids)).is_ok());
             assert!(index_writer.wait_merging_threads().is_ok());
         }
@@ -1516,7 +1516,7 @@ mod tests {
 
         let index = Index::create_in_ram(builder.build());
 
-        let mut writer = index.writer_with_num_threads(1, 3_000_000)?;
+        let mut writer = index.writer_for_tests()?;
 
         // Make sure we'll attempt to merge every created segment
         let mut policy = crate::indexer::LogMergePolicy::default();
@@ -1548,7 +1548,7 @@ mod tests {
         let mut builder = schema::SchemaBuilder::new();
         let text = builder.add_text_field("text", TEXT);
         let index = Index::create_in_ram(builder.build());
-        let mut writer = index.writer_with_num_threads(1, 3_000_000)?;
+        let mut writer = index.writer_for_tests()?;
         let happy_term = Term::from_field_text(text, "happy");
         let term_query = TermQuery::new(happy_term, IndexRecordOption::WithFreqs);
         for _ in 0..62 {

src/indexer/mod.rs

@@ -29,8 +29,9 @@ pub use self::segment_writer::SegmentWriter;
 /// Alias for the default merge policy, which is the `LogMergePolicy`.
 pub type DefaultMergePolicy = LogMergePolicy;
 
+#[cfg(feature = "mmap")]
 #[cfg(test)]
-mod tests {
+mod tests_mmap {
     use crate::schema::{self, Schema};
     use crate::{Index, Term};
 
@@ -39,7 +40,7 @@ mod tests {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", schema::TEXT);
         let index = Index::create_from_tempdir(schema_builder.build()).unwrap();
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         // there must be one deleted document in the segment
         index_writer.add_document(doc!(text_field=>"b"));
         index_writer.delete_term(Term::from_field_text(text_field, "b"));

src/indexer/prepared_commit.rs

@@ -1,6 +1,7 @@
 use super::IndexWriter;
 use crate::Opstamp;
 use futures::executor::block_on;
+use slog::info;
 
 /// A prepared commit
 pub struct PreparedCommit<'a> {
@@ -31,7 +32,7 @@ impl<'a> PreparedCommit<'a> {
     }
 
     pub fn commit(self) -> crate::Result<Opstamp> {
-        info!("committing {}", self.opstamp);
+        info!(self.index_writer.logger(), "committing {}", self.opstamp);
         let _ = block_on(
             self.index_writer
                 .segment_updater()

src/indexer/segment_manager.rs

@@ -1,3 +1,5 @@
+use slog::{warn, Logger};
+
 use super::segment_register::SegmentRegister;
 use crate::core::SegmentId;
 use crate::core::SegmentMeta;
@@ -42,9 +44,9 @@ impl SegmentRegisters {
 ///
 /// It guarantees the atomicity of the
 /// changes (merges especially)
-#[derive(Default)]
 pub struct SegmentManager {
     registers: RwLock<SegmentRegisters>,
+    logger: Logger,
 }
 
 impl Debug for SegmentManager {
@@ -77,12 +79,14 @@ impl SegmentManager {
     pub fn from_segments(
         segment_metas: Vec<SegmentMeta>,
         delete_cursor: &DeleteCursor,
+        logger: Logger,
     ) -> SegmentManager {
         SegmentManager {
             registers: RwLock::new(SegmentRegisters {
                 uncommitted: SegmentRegister::default(),
                 committed: SegmentRegister::new(segment_metas, delete_cursor),
             }),
+            logger,
         }
     }
 
@@ -186,7 +190,7 @@ impl SegmentManager {
         let segments_status = registers_lock
             .segments_status(before_merge_segment_ids)
             .ok_or_else(|| {
-                warn!("couldn't find segment in SegmentManager");
+                warn!(self.logger, "couldn't find segment in SegmentManager");
                 crate::TantivyError::InvalidArgument(
                     "The segments that were merged could not be found in the SegmentManager. \
                      This is not necessarily a bug, and can happen after a rollback for instance."

src/indexer/segment_updater.rs

@@ -23,9 +23,9 @@ use futures::channel::oneshot;
 use futures::executor::{ThreadPool, ThreadPoolBuilder};
 use futures::future::Future;
 use futures::future::TryFutureExt;
+use slog::{debug, error, info, warn};
 use std::borrow::BorrowMut;
 use std::collections::HashSet;
-use std::io::Write;
 use std::ops::Deref;
 use std::path::PathBuf;
 use std::sync::atomic::{AtomicBool, Ordering};
@@ -65,12 +65,11 @@ pub fn save_new_metas(schema: Schema, directory: &mut dyn Directory) -> crate::R
 ///
 /// This method is not part of tantivy's public API
 fn save_metas(metas: &IndexMeta, directory: &mut dyn Directory) -> crate::Result<()> {
-    info!("save metas");
-    let mut buffer = serde_json::to_vec_pretty(metas)?;
+    let mut meta_json = serde_json::to_string_pretty(metas)?;
     // Just adding a new line at the end of the buffer.
-    writeln!(&mut buffer)?;
-    directory.atomic_write(&META_FILEPATH, &buffer[..])?;
-    debug!("Saved metas {:?}", serde_json::to_string_pretty(&metas));
+    meta_json.push_str("\n");
+    debug!(directory.logger(), "save meta"; "content"=>&meta_json);
+    directory.atomic_write(&META_FILEPATH, meta_json.as_bytes())?;
     Ok(())
 }
 
@@ -97,7 +96,6 @@ impl Deref for SegmentUpdater {
 async fn garbage_collect_files(
     segment_updater: SegmentUpdater,
 ) -> crate::Result<GarbageCollectionResult> {
-    info!("Running garbage collection");
     let mut index = segment_updater.index.clone();
     index
         .directory_mut()
@@ -107,14 +105,12 @@ async fn garbage_collect_files(
 /// Merges a list of segments the list of segment givens in the `segment_entries`.
 /// This function happens in the calling thread and is computationally expensive.
 fn merge(
+    merged_segment: Segment,
     index: &Index,
     mut segment_entries: Vec<SegmentEntry>,
     target_opstamp: Opstamp,
 ) -> crate::Result<SegmentEntry> {
-    // first we need to apply deletes to our segment.
-    let merged_segment = index.new_segment();
-
-    // First we apply all of the delet to the merged segment, up to the target opstamp.
+    // First we apply all of the delete to the merged segment, up to the target opstamp.
     for segment_entry in &mut segment_entries {
         let segment = index.segment(segment_entry.meta().clone());
         advance_deletes(segment, segment_entry, target_opstamp)?;
@@ -167,7 +163,8 @@ impl SegmentUpdater {
         delete_cursor: &DeleteCursor,
     ) -> crate::Result<SegmentUpdater> {
         let segments = index.searchable_segment_metas()?;
-        let segment_manager = SegmentManager::from_segments(segments, delete_cursor);
+        let segment_manager =
+            SegmentManager::from_segments(segments, delete_cursor, index.logger().clone());
         let pool = ThreadPoolBuilder::new()
             .name_prefix("segment_updater")
             .pool_size(1)
@@ -387,7 +384,18 @@ impl SegmentUpdater {
             .segment_manager
             .start_merge(merge_operation.segment_ids())?;
 
-        info!("Starting merge  - {:?}", merge_operation.segment_ids());
+        let segment_ids_str: String = merge_operation
+            .segment_ids()
+            .iter()
+            .map(|segment_id| segment_id.to_string())
+            .collect::<Vec<String>>()
+            .join(",");
+
+        let merged_segment = self.index.new_segment();
+        let logger = self.index.logger().new(slog::o!("segments"=>segment_ids_str, "merged-segment"=>merged_segment.id().to_string()));
+
+        let num_merges: usize = self.merge_operations.list().len();
+        slog::info!(&logger, "merge"; "stage"=>"start", "num-merges" => num_merges);
 
         let (merging_future_send, merging_future_recv) =
             oneshot::channel::<crate::Result<SegmentMeta>>();
@@ -398,22 +406,20 @@ impl SegmentUpdater {
             // as well as which segment is currently in merge and therefore should not be
             // candidate for another merge.
             match merge(
+                merged_segment,
                 &segment_updater.index,
                 segment_entries,
                 merge_operation.target_opstamp(),
             ) {
                 Ok(after_merge_segment_entry) => {
+                    info!(&logger, "merge"; "stage" => "end");
                     let segment_meta = segment_updater
                         .end_merge(merge_operation, after_merge_segment_entry)
                         .await;
                     let _send_result = merging_future_send.send(segment_meta);
                 }
                 Err(e) => {
-                    warn!(
-                        "Merge of {:?} was cancelled: {:?}",
-                        merge_operation.segment_ids().to_vec(),
-                        e
-                    );
+                    error!(&logger, "merge"; "stage" => "fail", "cause"=>e.to_string());
                     // ... cancel merge
                     if cfg!(test) {
                         panic!("Merge failed.");
@@ -454,11 +460,12 @@ impl SegmentUpdater {
             .collect::<Vec<_>>();
         merge_candidates.extend(committed_merge_candidates.into_iter());
 
+        let logger = self.index.logger();
         for merge_operation in merge_candidates {
             if let Err(err) = self.start_merge(merge_operation) {
                 warn!(
-                    "Starting the merge failed for the following reason. This is not fatal. {}",
-                    err
+                    logger,
+                    "merge-start-fail (not fatal, not necessarily a problem)"; "reason" => format!("{}", err),
                 );
             }
         }
@@ -471,8 +478,11 @@ impl SegmentUpdater {
     ) -> impl Future<Output = crate::Result<SegmentMeta>> {
         let segment_updater = self.clone();
         let after_merge_segment_meta = after_merge_segment_entry.meta().clone();
+        let logger = self.index.logger().new(
+            slog::o!("segment"=>after_merge_segment_meta.id().to_string(),
+            "delete-opstamp"=>after_merge_segment_meta.delete_opstamp()),
+        );
         let end_merge_future = self.schedule_future(async move {
-            info!("End merge {:?}", after_merge_segment_entry.meta());
             {
                 let mut delete_cursor = after_merge_segment_entry.delete_cursor().clone();
                 if let Some(delete_operation) = delete_cursor.get() {
@@ -486,6 +496,7 @@ impl SegmentUpdater {
                             committed_opstamp,
                         ) {
                             error!(
+                                logger,
                                 "Merge of {:?} was cancelled (advancing deletes failed): {:?}",
                                 merge_operation.segment_ids(),
                                 e
@@ -555,7 +566,7 @@ mod tests {
         let index = Index::create_in_ram(schema);
 
         // writing the segment
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.set_merge_policy(Box::new(MergeWheneverPossible));
 
         {
@@ -608,7 +619,7 @@ mod tests {
         let index = Index::create_in_ram(schema);
 
         // writing the segment
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
 
         {
             for _ in 0..100 {
@@ -679,7 +690,7 @@ mod tests {
         let index = Index::create_in_ram(schema);
 
         // writing the segment
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
 
         {
             for _ in 0..100 {

src/indexer/segment_writer.rs

@@ -1,5 +1,4 @@
 use super::operation::AddOperation;
-use crate::core::Segment;
 use crate::core::SerializableSegment;
 use crate::fastfield::FastFieldsWriter;
 use crate::fieldnorm::{FieldNormReaders, FieldNormsWriter};
@@ -15,9 +14,9 @@ use crate::tokenizer::{BoxTokenStream, PreTokenizedStream};
 use crate::tokenizer::{FacetTokenizer, TextAnalyzer};
 use crate::tokenizer::{TokenStreamChain, Tokenizer};
 use crate::Opstamp;
+use crate::{core::Segment, tokenizer::MAX_TOKEN_LEN};
 use crate::{DocId, SegmentComponent};
 use std::io;
-use std::str;
 
 /// Computes the initial size of the hash table.
 ///
@@ -48,6 +47,7 @@ pub struct SegmentWriter {
     fieldnorms_writer: FieldNormsWriter,
     doc_opstamps: Vec<Opstamp>,
     tokenizers: Vec<Option<TextAnalyzer>>,
+    term_buffer: Term,
 }
 
 impl SegmentWriter {
@@ -91,6 +91,7 @@ impl SegmentWriter {
             fast_field_writers: FastFieldsWriter::from_schema(schema),
             doc_opstamps: Vec::with_capacity(1_000),
             tokenizers,
+            term_buffer: Term::new(),
         })
     }
 
@@ -128,24 +129,29 @@ impl SegmentWriter {
             if !field_options.is_indexed() {
                 continue;
             }
+            let (term_buffer, multifield_postings) =
+                (&mut self.term_buffer, &mut self.multifield_postings);
             match *field_options.field_type() {
                 FieldType::HierarchicalFacet => {
-                    let facets: Vec<&str> = field_values
-                        .iter()
-                        .flat_map(|field_value| match *field_value.value() {
-                            Value::Facet(ref facet) => Some(facet.encoded_str()),
-                            _ => {
-                                panic!("Expected hierarchical facet");
-                            }
-                        })
-                        .collect();
-                    let mut term = Term::for_field(field); // we set the Term
+                    term_buffer.set_field(field);
+                    let facets =
+                        field_values
+                            .iter()
+                            .flat_map(|field_value| match *field_value.value() {
+                                Value::Facet(ref facet) => Some(facet.encoded_str()),
+                                _ => {
+                                    panic!("Expected hierarchical facet");
+                                }
+                            });
                     for fake_str in facets {
                         let mut unordered_term_id_opt = None;
                         FacetTokenizer.token_stream(fake_str).process(&mut |token| {
-                            term.set_text(&token.text);
+                            if token.text.len() > MAX_TOKEN_LEN {
+                                return;
+                            }
+                            term_buffer.set_text(&token.text);
                             let unordered_term_id =
-                                self.multifield_postings.subscribe(doc_id, &term);
+                                multifield_postings.subscribe(doc_id, &term_buffer);
                             unordered_term_id_opt = Some(unordered_term_id);
                         });
                         if let Some(unordered_term_id) = unordered_term_id_opt {
@@ -168,7 +174,6 @@ impl SegmentWriter {
                                 if let Some(last_token) = tok_str.tokens.last() {
                                     total_offset += last_token.offset_to;
                                 }
-
                                 token_streams
                                     .push(PreTokenizedStream::from(tok_str.clone()).into());
                             }
@@ -178,7 +183,6 @@ impl SegmentWriter {
                                 {
                                     offsets.push(total_offset);
                                     total_offset += text.len();
-
                                     token_streams.push(tokenizer.token_stream(text));
                                 }
                             }
@@ -190,8 +194,12 @@ impl SegmentWriter {
                         0
                     } else {
                         let mut token_stream = TokenStreamChain::new(offsets, token_streams);
-                        self.multifield_postings
-                            .index_text(doc_id, field, &mut token_stream)
+                        multifield_postings.index_text(
+                            doc_id,
+                            field,
+                            &mut token_stream,
+                            term_buffer,
+                        )
                     };
 
                     self.fieldnorms_writer.record(doc_id, field, num_tokens);
@@ -199,44 +207,36 @@ impl SegmentWriter {
                 FieldType::U64(ref int_option) => {
                     if int_option.is_indexed() {
                         for field_value in field_values {
-                            let term = Term::from_field_u64(
-                                field_value.field(),
-                                field_value.value().u64_value(),
-                            );
-                            self.multifield_postings.subscribe(doc_id, &term);
+                            term_buffer.set_field(field_value.field());
+                            term_buffer.set_u64(field_value.value().u64_value());
+                            multifield_postings.subscribe(doc_id, &term_buffer);
                         }
                     }
                 }
                 FieldType::Date(ref int_option) => {
                     if int_option.is_indexed() {
                         for field_value in field_values {
-                            let term = Term::from_field_i64(
-                                field_value.field(),
-                                field_value.value().date_value().timestamp(),
-                            );
-                            self.multifield_postings.subscribe(doc_id, &term);
+                            term_buffer.set_field(field_value.field());
+                            term_buffer.set_i64(field_value.value().date_value().timestamp());
+                            multifield_postings.subscribe(doc_id, &term_buffer);
                         }
                     }
                 }
                 FieldType::I64(ref int_option) => {
                     if int_option.is_indexed() {
                         for field_value in field_values {
-                            let term = Term::from_field_i64(
-                                field_value.field(),
-                                field_value.value().i64_value(),
-                            );
-                            self.multifield_postings.subscribe(doc_id, &term);
+                            term_buffer.set_field(field_value.field());
+                            term_buffer.set_i64(field_value.value().i64_value());
+                            multifield_postings.subscribe(doc_id, &term_buffer);
                         }
                     }
                 }
                 FieldType::F64(ref int_option) => {
                     if int_option.is_indexed() {
                         for field_value in field_values {
-                            let term = Term::from_field_f64(
-                                field_value.field(),
-                                field_value.value().f64_value(),
-                            );
-                            self.multifield_postings.subscribe(doc_id, &term);
+                            term_buffer.set_field(field_value.field());
+                            term_buffer.set_f64(field_value.value().f64_value());
+                            multifield_postings.subscribe(doc_id, &term_buffer);
                         }
                     }
                 }

src/lib.rs

@@ -102,10 +102,7 @@
 extern crate serde_json;
 
 #[macro_use]
-extern crate log;
-
-#[macro_use]
-extern crate failure;
+extern crate thiserror;
 
 #[cfg(all(test, feature = "unstable"))]
 extern crate test;
@@ -148,6 +145,7 @@ pub mod schema;
 pub mod space_usage;
 pub mod store;
 pub mod termdict;
+pub use slog;
 
 mod reader;
 
@@ -245,18 +243,10 @@ pub type DocId = u32;
 /// with opstamp `n+1`.
 pub type Opstamp = u64;
 
-/// A Score that represents the relevance of the document to the query
-///
-/// This is modelled internally as a `f64`, because tantivy was compiled with the `scoref64`
-/// feature. The larger the number, the more relevant the document is to the search query.
-#[cfg(feature = "scoref64")]
-pub type Score = f64;
-
 /// A Score that represents the relevance of the document to the query
 ///
 /// This is modelled internally as a `f32`. The larger the number, the more relevant
 /// the document to the search query.
-#[cfg(not(feature = "scoref64"))]
 pub type Score = f32;
 
 /// A `SegmentLocalId` identifies a segment.
@@ -296,7 +286,6 @@ mod tests {
     use crate::schema::*;
     use crate::DocAddress;
     use crate::Index;
-    use crate::IndexWriter;
     use crate::Postings;
     use crate::ReloadPolicy;
     use rand::distributions::Bernoulli;
@@ -361,14 +350,14 @@ mod tests {
 
     #[test]
     #[cfg(feature = "mmap")]
-    fn test_indexing() {
+    fn test_indexing() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
         let index = Index::create_from_tempdir(schema).unwrap();
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests()?;
             {
                 let doc = doc!(text_field=>"af b");
                 index_writer.add_document(doc);
@@ -383,29 +372,30 @@ mod tests {
             }
             assert!(index_writer.commit().is_ok());
         }
+        Ok(())
     }
 
     #[test]
-    fn test_docfreq1() {
+    fn test_docfreq1() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let index = Index::create_in_ram(schema_builder.build());
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         {
             index_writer.add_document(doc!(text_field=>"a b c"));
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
         }
         {
             index_writer.add_document(doc!(text_field=>"a"));
             index_writer.add_document(doc!(text_field=>"a a"));
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
         }
         {
             index_writer.add_document(doc!(text_field=>"c"));
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
         }
         {
-            let reader = index.reader().unwrap();
+            let reader = index.reader()?;
             let searcher = reader.searcher();
             let term_a = Term::from_field_text(text_field, "a");
             assert_eq!(searcher.doc_freq(&term_a), 3);
@@ -416,67 +406,50 @@ mod tests {
             let term_d = Term::from_field_text(text_field, "d");
             assert_eq!(searcher.doc_freq(&term_d), 0);
         }
+        Ok(())
     }
 
     #[test]
-    fn test_fieldnorm_no_docs_with_field() {
+    fn test_fieldnorm_no_docs_with_field() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let title_field = schema_builder.add_text_field("title", TEXT);
         let text_field = schema_builder.add_text_field("text", TEXT);
         let index = Index::create_in_ram(schema_builder.build());
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(text_field=>"a b c"));
+        index_writer.commit()?;
+        let index_reader = index.reader()?;
+        let searcher = index_reader.searcher();
+        let reader = searcher.segment_reader(0);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
-            {
-                let doc = doc!(text_field=>"a b c");
-                index_writer.add_document(doc);
-            }
-            index_writer.commit().unwrap();
+            let fieldnorm_reader = reader.get_fieldnorms_reader(text_field)?;
+            assert_eq!(fieldnorm_reader.fieldnorm(0), 3);
         }
         {
-            let index_reader = index.reader().unwrap();
-            let searcher = index_reader.searcher();
-            let reader = searcher.segment_reader(0);
-            {
-                let fieldnorm_reader = reader.get_fieldnorms_reader(text_field);
-                assert_eq!(fieldnorm_reader.fieldnorm(0), 3);
-            }
-            {
-                let fieldnorm_reader = reader.get_fieldnorms_reader(title_field);
-                assert_eq!(fieldnorm_reader.fieldnorm_id(0), 0);
-            }
+            let fieldnorm_reader = reader.get_fieldnorms_reader(title_field)?;
+            assert_eq!(fieldnorm_reader.fieldnorm_id(0), 0);
         }
+        Ok(())
     }
 
     #[test]
-    fn test_fieldnorm() {
+    fn test_fieldnorm() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let index = Index::create_in_ram(schema_builder.build());
-        {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
-            {
-                let doc = doc!(text_field=>"a b c");
-                index_writer.add_document(doc);
-            }
-            {
-                let doc = doc!();
-                index_writer.add_document(doc);
-            }
-            {
-                let doc = doc!(text_field=>"a b");
-                index_writer.add_document(doc);
-            }
-            index_writer.commit().unwrap();
-        }
-        {
-            let reader = index.reader().unwrap();
-            let searcher = reader.searcher();
-            let segment_reader: &SegmentReader = searcher.segment_reader(0);
-            let fieldnorms_reader = segment_reader.get_fieldnorms_reader(text_field);
-            assert_eq!(fieldnorms_reader.fieldnorm(0), 3);
-            assert_eq!(fieldnorms_reader.fieldnorm(1), 0);
-            assert_eq!(fieldnorms_reader.fieldnorm(2), 2);
-        }
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(text_field=>"a b c"));
+        index_writer.add_document(doc!());
+        index_writer.add_document(doc!(text_field=>"a b"));
+        index_writer.commit()?;
+        let reader = index.reader()?;
+        let searcher = reader.searcher();
+        let segment_reader: &SegmentReader = searcher.segment_reader(0);
+        let fieldnorms_reader = segment_reader.get_fieldnorms_reader(text_field)?;
+        assert_eq!(fieldnorms_reader.fieldnorm(0), 3);
+        assert_eq!(fieldnorms_reader.fieldnorm(1), 0);
+        assert_eq!(fieldnorms_reader.fieldnorm(2), 2);
+        Ok(())
     }
 
     fn advance_undeleted(docset: &mut dyn DocSet, reader: &SegmentReader) -> bool {
@@ -491,7 +464,7 @@ mod tests {
     }
 
     #[test]
-    fn test_delete_postings1() {
+    fn test_delete_postings1() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let term_abcd = Term::from_field_text(text_field, "abcd");
@@ -507,7 +480,7 @@ mod tests {
             .unwrap();
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests()?;
             // 0
             index_writer.add_document(doc!(text_field=>"a b"));
             // 1
@@ -523,10 +496,10 @@ mod tests {
             index_writer.add_document(doc!(text_field=>" b c"));
             // 5
             index_writer.add_document(doc!(text_field=>" a"));
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
         }
         {
-            reader.reload().unwrap();
+            reader.reload()?;
             let searcher = reader.searcher();
             let segment_reader = searcher.segment_reader(0);
             let inverted_index = segment_reader.inverted_index(text_field);
@@ -554,15 +527,15 @@ mod tests {
         }
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests()?;
             // 0
             index_writer.add_document(doc!(text_field=>"a b"));
             // 1
             index_writer.delete_term(Term::from_field_text(text_field, "c"));
-            index_writer.rollback().unwrap();
+            index_writer.rollback()?;
         }
         {
-            reader.reload().unwrap();
+            reader.reload()?;
             let searcher = reader.searcher();
             let seg_reader = searcher.segment_reader(0);
             let inverted_index = seg_reader.inverted_index(term_abcd.field());
@@ -591,15 +564,15 @@ mod tests {
         }
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests()?;
             index_writer.add_document(doc!(text_field=>"a b"));
             index_writer.delete_term(Term::from_field_text(text_field, "c"));
-            index_writer.rollback().unwrap();
+            index_writer.rollback()?;
             index_writer.delete_term(Term::from_field_text(text_field, "a"));
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
         }
         {
-            reader.reload().unwrap();
+            reader.reload()?;
             let searcher = reader.searcher();
             let segment_reader = searcher.segment_reader(0);
             let inverted_index = segment_reader.inverted_index(term_abcd.field());
@@ -631,19 +604,20 @@ mod tests {
                 assert!(!advance_undeleted(&mut postings, segment_reader));
             }
         }
+        Ok(())
     }
 
     #[test]
-    fn test_indexed_u64() {
+    fn test_indexed_u64() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let field = schema_builder.add_u64_field("value", INDEXED);
         let schema = schema_builder.build();
 
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         index_writer.add_document(doc!(field=>1u64));
-        index_writer.commit().unwrap();
-        let reader = index.reader().unwrap();
+        index_writer.commit()?;
+        let reader = index.reader()?;
         let searcher = reader.searcher();
         let term = Term::from_field_u64(field, 1u64);
         let mut postings = searcher
@@ -653,20 +627,21 @@ mod tests {
             .unwrap();
         assert_eq!(postings.doc(), 0);
         assert_eq!(postings.advance(), TERMINATED);
+        Ok(())
     }
 
     #[test]
-    fn test_indexed_i64() {
+    fn test_indexed_i64() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let value_field = schema_builder.add_i64_field("value", INDEXED);
         let schema = schema_builder.build();
 
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         let negative_val = -1i64;
         index_writer.add_document(doc!(value_field => negative_val));
-        index_writer.commit().unwrap();
-        let reader = index.reader().unwrap();
+        index_writer.commit()?;
+        let reader = index.reader()?;
         let searcher = reader.searcher();
         let term = Term::from_field_i64(value_field, negative_val);
         let mut postings = searcher
@@ -676,20 +651,21 @@ mod tests {
             .unwrap();
         assert_eq!(postings.doc(), 0);
         assert_eq!(postings.advance(), TERMINATED);
+        Ok(())
     }
 
     #[test]
-    fn test_indexed_f64() {
+    fn test_indexed_f64() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let value_field = schema_builder.add_f64_field("value", INDEXED);
         let schema = schema_builder.build();
 
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         let val = std::f64::consts::PI;
         index_writer.add_document(doc!(value_field => val));
-        index_writer.commit().unwrap();
-        let reader = index.reader().unwrap();
+        index_writer.commit()?;
+        let reader = index.reader()?;
         let searcher = reader.searcher();
         let term = Term::from_field_f64(value_field, val);
         let mut postings = searcher
@@ -699,26 +675,29 @@ mod tests {
             .unwrap();
         assert_eq!(postings.doc(), 0);
         assert_eq!(postings.advance(), TERMINATED);
+        Ok(())
     }
 
     #[test]
-    fn test_indexedfield_not_in_documents() {
+    fn test_indexedfield_not_in_documents() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let absent_field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(2, 6_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         index_writer.add_document(doc!(text_field=>"a"));
         assert!(index_writer.commit().is_ok());
-        let reader = index.reader().unwrap();
+        let reader = index.reader()?;
         let searcher = reader.searcher();
         let segment_reader = searcher.segment_reader(0);
-        segment_reader.inverted_index(absent_field); //< should not panic
+        let inverted_index = segment_reader.inverted_index(absent_field); //< should not panic
+        assert_eq!(inverted_index.terms().num_terms(), 0);
+        Ok(())
     }
 
     #[test]
-    fn test_delete_postings2() {
+    fn test_delete_postings2() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
@@ -726,53 +705,40 @@ mod tests {
         let reader = index
             .reader_builder()
             .reload_policy(ReloadPolicy::Manual)
-            .try_into()
-            .unwrap();
+            .try_into()?;
 
         // writing the segment
-        let mut index_writer = index.writer_with_num_threads(2, 6_000_000).unwrap();
-
-        let add_document = |index_writer: &mut IndexWriter, val: &'static str| {
-            let doc = doc!(text_field=>val);
-            index_writer.add_document(doc);
-        };
-
-        let remove_document = |index_writer: &mut IndexWriter, val: &'static str| {
-            let delterm = Term::from_field_text(text_field, val);
-            index_writer.delete_term(delterm);
-        };
-
-        add_document(&mut index_writer, "63");
-        add_document(&mut index_writer, "70");
-        add_document(&mut index_writer, "34");
-        add_document(&mut index_writer, "1");
-        add_document(&mut index_writer, "38");
-        add_document(&mut index_writer, "33");
-        add_document(&mut index_writer, "40");
-        add_document(&mut index_writer, "17");
-        remove_document(&mut index_writer, "38");
-        remove_document(&mut index_writer, "34");
-        index_writer.commit().unwrap();
-        reader.reload().unwrap();
-        let searcher = reader.searcher();
-        assert_eq!(searcher.num_docs(), 6);
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(text_field=>"63"));
+        index_writer.add_document(doc!(text_field=>"70"));
+        index_writer.add_document(doc!(text_field=>"34"));
+        index_writer.add_document(doc!(text_field=>"1"));
+        index_writer.add_document(doc!(text_field=>"38"));
+        index_writer.add_document(doc!(text_field=>"33"));
+        index_writer.add_document(doc!(text_field=>"40"));
+        index_writer.add_document(doc!(text_field=>"17"));
+        index_writer.delete_term(Term::from_field_text(text_field, "38"));
+        index_writer.delete_term(Term::from_field_text(text_field, "34"));
+        index_writer.commit()?;
+        reader.reload()?;
+        assert_eq!(reader.searcher().num_docs(), 6);
+        Ok(())
     }
 
     #[test]
-    fn test_termfreq() {
+    fn test_termfreq() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
-            let doc = doc!(text_field=>"af af af bc bc");
-            index_writer.add_document(doc);
-            index_writer.commit().unwrap();
+            let mut index_writer = index.writer_for_tests()?;
+            index_writer.add_document(doc!(text_field=>"af af af bc bc"));
+            index_writer.commit()?;
         }
         {
-            let index_reader = index.reader().unwrap();
+            let index_reader = index.reader()?;
             let searcher = index_reader.searcher();
             let reader = searcher.segment_reader(0);
             let inverted_index = reader.inverted_index(text_field);
@@ -788,63 +754,63 @@ mod tests {
             assert_eq!(postings.term_freq(), 3);
             assert_eq!(postings.advance(), TERMINATED);
         }
+        Ok(())
     }
 
     #[test]
-    fn test_searcher_1() {
+    fn test_searcher_1() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let reader = index.reader().unwrap();
-        {
-            // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
-            index_writer.add_document(doc!(text_field=>"af af af b"));
-            index_writer.add_document(doc!(text_field=>"a b c"));
-            index_writer.add_document(doc!(text_field=>"a b c d"));
-            index_writer.commit().unwrap();
-        }
-        {
-            reader.reload().unwrap();
-            let searcher = reader.searcher();
-            let get_doc_ids = |terms: Vec<Term>| {
-                let query = BooleanQuery::new_multiterms_query(terms);
-                let topdocs = searcher.search(&query, &TEST_COLLECTOR_WITH_SCORE).unwrap();
-                topdocs.docs().to_vec()
-            };
-            assert_eq!(
-                get_doc_ids(vec![Term::from_field_text(text_field, "a")]),
-                vec![DocAddress(0, 1), DocAddress(0, 2)]
-            );
-            assert_eq!(
-                get_doc_ids(vec![Term::from_field_text(text_field, "af")]),
-                vec![DocAddress(0, 0)]
-            );
-            assert_eq!(
-                get_doc_ids(vec![Term::from_field_text(text_field, "b")]),
-                vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
-            );
-            assert_eq!(
-                get_doc_ids(vec![Term::from_field_text(text_field, "c")]),
-                vec![DocAddress(0, 1), DocAddress(0, 2)]
-            );
-            assert_eq!(
-                get_doc_ids(vec![Term::from_field_text(text_field, "d")]),
-                vec![DocAddress(0, 2)]
-            );
-            assert_eq!(
-                get_doc_ids(vec![
-                    Term::from_field_text(text_field, "b"),
-                    Term::from_field_text(text_field, "a"),
-                ]),
-                vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
-            );
-        }
+        let reader = index.reader()?;
+        // writing the segment
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(text_field=>"af af af b"));
+        index_writer.add_document(doc!(text_field=>"a b c"));
+        index_writer.add_document(doc!(text_field=>"a b c d"));
+        index_writer.commit()?;
+
+        reader.reload()?;
+        let searcher = reader.searcher();
+        let get_doc_ids = |terms: Vec<Term>| {
+            let query = BooleanQuery::new_multiterms_query(terms);
+            searcher
+                .search(&query, &TEST_COLLECTOR_WITH_SCORE)
+                .map(|topdocs| topdocs.docs().to_vec())
+        };
+        assert_eq!(
+            get_doc_ids(vec![Term::from_field_text(text_field, "a")])?,
+            vec![DocAddress(0, 1), DocAddress(0, 2)]
+        );
+        assert_eq!(
+            get_doc_ids(vec![Term::from_field_text(text_field, "af")])?,
+            vec![DocAddress(0, 0)]
+        );
+        assert_eq!(
+            get_doc_ids(vec![Term::from_field_text(text_field, "b")])?,
+            vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
+        );
+        assert_eq!(
+            get_doc_ids(vec![Term::from_field_text(text_field, "c")])?,
+            vec![DocAddress(0, 1), DocAddress(0, 2)]
+        );
+        assert_eq!(
+            get_doc_ids(vec![Term::from_field_text(text_field, "d")])?,
+            vec![DocAddress(0, 2)]
+        );
+        assert_eq!(
+            get_doc_ids(vec![
+                Term::from_field_text(text_field, "b"),
+                Term::from_field_text(text_field, "a"),
+            ])?,
+            vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
+        );
+        Ok(())
     }
 
     #[test]
-    fn test_searcher_2() {
+    fn test_searcher_2() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
@@ -852,19 +818,17 @@ mod tests {
         let reader = index
             .reader_builder()
             .reload_policy(ReloadPolicy::Manual)
-            .try_into()
-            .unwrap();
+            .try_into()?;
         assert_eq!(reader.searcher().num_docs(), 0u64);
-        {
-            // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
-            index_writer.add_document(doc!(text_field=>"af b"));
-            index_writer.add_document(doc!(text_field=>"a b c"));
-            index_writer.add_document(doc!(text_field=>"a b c d"));
-            index_writer.commit().unwrap();
-        }
-        reader.reload().unwrap();
+        // writing the segment
+        let mut index_writer = index.writer_for_tests()?;
+        index_writer.add_document(doc!(text_field=>"af b"));
+        index_writer.add_document(doc!(text_field=>"a b c"));
+        index_writer.add_document(doc!(text_field=>"a b c d"));
+        index_writer.commit()?;
+        reader.reload()?;
         assert_eq!(reader.searcher().num_docs(), 3u64);
+        Ok(())
     }
 
     #[test]
@@ -886,7 +850,7 @@ mod tests {
     }
 
     #[test]
-    fn test_wrong_fast_field_type() {
+    fn test_wrong_fast_field_type() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();
         let fast_field_unsigned = schema_builder.add_u64_field("unsigned", FAST);
         let fast_field_signed = schema_builder.add_i64_field("signed", FAST);
@@ -896,14 +860,14 @@ mod tests {
         let schema = schema_builder.build();
 
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 50_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         {
             let document =
                 doc!(fast_field_unsigned => 4u64, fast_field_signed=>4i64, fast_field_float=>4f64);
             index_writer.add_document(document);
-            index_writer.commit().unwrap();
+            index_writer.commit()?;
         }
-        let reader = index.reader().unwrap();
+        let reader = index.reader()?;
         let searcher = reader.searcher();
         let segment_reader: &SegmentReader = searcher.segment_reader(0);
         {
@@ -942,11 +906,12 @@ mod tests {
             let fast_field_reader = fast_field_reader_opt.unwrap();
             assert_eq!(fast_field_reader.get(0), 4f64)
         }
+        Ok(())
     }
 
     // motivated by #729
     #[test]
-    fn test_update_via_delete_insert() {
+    fn test_update_via_delete_insert() -> crate::Result<()> {
         use crate::collector::Count;
         use crate::indexer::NoMergePolicy;
         use crate::query::AllQuery;
@@ -960,17 +925,17 @@ mod tests {
         let schema = schema_builder.build();
 
         let index = Index::create_in_ram(schema.clone());
-        let index_reader = index.reader().unwrap();
+        let index_reader = index.reader()?;
 
-        let mut index_writer = index.writer(3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests()?;
         index_writer.set_merge_policy(Box::new(NoMergePolicy));
 
         for doc_id in 0u64..DOC_COUNT {
             index_writer.add_document(doc!(id => doc_id));
         }
-        index_writer.commit().unwrap();
+        index_writer.commit()?;
 
-        index_reader.reload().unwrap();
+        index_reader.reload()?;
         let searcher = index_reader.searcher();
 
         assert_eq!(
@@ -981,12 +946,11 @@ mod tests {
         // update the 10 elements by deleting and re-adding
         for doc_id in 0u64..DOC_COUNT {
             index_writer.delete_term(Term::from_field_u64(id, doc_id));
-            index_writer.commit().unwrap();
-            index_reader.reload().unwrap();
-            let doc = doc!(id =>  doc_id);
-            index_writer.add_document(doc);
-            index_writer.commit().unwrap();
-            index_reader.reload().unwrap();
+            index_writer.commit()?;
+            index_reader.reload()?;
+            index_writer.add_document(doc!(id =>  doc_id));
+            index_writer.commit()?;
+            index_reader.reload()?;
             let searcher = index_reader.searcher();
             // The number of document should be stable.
             assert_eq!(
@@ -995,7 +959,7 @@ mod tests {
             );
         }
 
-        index_reader.reload().unwrap();
+        index_reader.reload()?;
         let searcher = index_reader.searcher();
         let segment_ids: Vec<SegmentId> = searcher
             .segment_readers()
@@ -1004,12 +968,18 @@ mod tests {
             .collect();
         block_on(index_writer.merge(&segment_ids)).unwrap();
 
-        index_reader.reload().unwrap();
+        index_reader.reload()?;
         let searcher = index_reader.searcher();
+        assert_eq!(searcher.search(&AllQuery, &Count)?, DOC_COUNT as usize);
+        Ok(())
+    }
 
-        assert_eq!(
-            searcher.search(&AllQuery, &Count).unwrap(),
-            DOC_COUNT as usize
-        );
+    #[test]
+    fn test_validate_checksum() -> crate::Result<()> {
+        let index_path = tempfile::tempdir().expect("dir");
+        let schema = Schema::builder().build();
+        let index = Index::create_in_dir(&index_path, schema)?;
+        assert!(index.validate_checksum()?.is_empty());
+        Ok(())
     }
 }

src/postings/block_segment_postings.rs

@@ -455,7 +455,7 @@ mod tests {
         let int_field = schema_builder.add_u64_field("id", INDEXED);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         let mut last_doc = 0u32;
         for &doc in docs {
             for _ in last_doc..doc {
@@ -496,7 +496,7 @@ mod tests {
         let int_field = schema_builder.add_u64_field("id", INDEXED);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         // create two postings list, one containg even number,
         // the other containing odd numbers.
         for i in 0..6 {

src/postings/compression/mod.rs

@@ -310,6 +310,7 @@ pub mod tests {
 mod bench {
 
     use super::*;
+    use crate::TERMINATED;
     use rand::rngs::StdRng;
     use rand::Rng;
     use rand::SeedableRng;
@@ -340,7 +341,7 @@ mod bench {
         let mut encoder = BlockEncoder::new();
         let data = generate_array(COMPRESSION_BLOCK_SIZE, 0.1);
         let (num_bits, compressed) = encoder.compress_block_sorted(&data, 0u32);
-        let mut decoder = BlockDecoder::new();
+        let mut decoder = BlockDecoder::default();
         b.iter(|| {
             decoder.uncompress_block_sorted(compressed, 0u32, num_bits);
         });
@@ -375,9 +376,9 @@ mod bench {
         let mut encoder = BlockEncoder::new();
         let data = generate_array(NUM_INTS_BENCH_VINT, 0.001);
         let compressed = encoder.compress_vint_sorted(&data, 0u32);
-        let mut decoder = BlockDecoder::new();
+        let mut decoder = BlockDecoder::default();
         b.iter(|| {
-            decoder.uncompress_vint_sorted(compressed, 0u32, NUM_INTS_BENCH_VINT);
+            decoder.uncompress_vint_sorted(compressed, 0u32, NUM_INTS_BENCH_VINT, TERMINATED);
         });
     }
 }

src/postings/mod.rs

@@ -91,7 +91,7 @@ pub mod tests {
         let title = schema_builder.add_text_field("title", TEXT);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 30_000_000)?;
+        let mut index_writer = index.writer_for_tests()?;
         index_writer.add_document(doc!(title => r#"abc abc abc"#));
         index_writer.add_document(doc!(title => r#"abc be be be be abc"#));
         for _ in 0..1_000 {
@@ -176,7 +176,7 @@ pub mod tests {
             .tokenizers()
             .register("simple_no_truncation", SimpleTokenizer);
         let reader = index.reader().unwrap();
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.set_merge_policy(Box::new(NoMergePolicy));
         {
             index_writer.add_document(doc!(text_field=>exceeding_token_text));
@@ -205,7 +205,7 @@ pub mod tests {
     }
 
     #[test]
-    pub fn test_position_and_fieldnorm1() {
+    pub fn test_position_and_fieldnorm1() -> crate::Result<()> {
         let mut positions = Vec::new();
         let mut schema_builder = Schema::builder();
         let text_field = schema_builder.add_text_field("text", TEXT);
@@ -217,42 +217,38 @@ pub mod tests {
             let mut segment_writer =
                 SegmentWriter::for_segment(3_000_000, segment.clone(), &schema).unwrap();
             {
-                let mut doc = Document::default();
                 // checking that position works if the field has two values
-                doc.add_text(text_field, "a b a c a d a a.");
-                doc.add_text(text_field, "d d d d a");
                 let op = AddOperation {
                     opstamp: 0u64,
-                    document: doc,
+                    document: doc!(
+                       text_field => "a b a c a d a a.",
+                       text_field => "d d d d a"
+                    ),
                 };
-                segment_writer.add_document(op, &schema).unwrap();
+                segment_writer.add_document(op, &schema)?;
             }
             {
-                let mut doc = Document::default();
-                doc.add_text(text_field, "b a");
                 let op = AddOperation {
                     opstamp: 1u64,
-                    document: doc,
+                    document: doc!(text_field => "b a"),
                 };
                 segment_writer.add_document(op, &schema).unwrap();
             }
             for i in 2..1000 {
-                let mut doc = Document::default();
-                let mut text = iter::repeat("e ").take(i).collect::<String>();
+                let mut text: String = iter::repeat("e ").take(i).collect();
                 text.push_str(" a");
-                doc.add_text(text_field, &text);
                 let op = AddOperation {
                     opstamp: 2u64,
-                    document: doc,
+                    document: doc!(text_field => text),
                 };
                 segment_writer.add_document(op, &schema).unwrap();
             }
-            segment_writer.finalize().unwrap();
+            segment_writer.finalize()?;
         }
         {
-            let segment_reader = SegmentReader::open(&segment).unwrap();
+            let segment_reader = SegmentReader::open(&segment)?;
             {
-                let fieldnorm_reader = segment_reader.get_fieldnorms_reader(text_field);
+                let fieldnorm_reader = segment_reader.get_fieldnorms_reader(text_field)?;
                 assert_eq!(fieldnorm_reader.fieldnorm(0), 8 + 5);
                 assert_eq!(fieldnorm_reader.fieldnorm(1), 2);
                 for i in 2..1000 {
@@ -312,6 +308,7 @@ pub mod tests {
                 assert_eq!(postings_e.doc(), TERMINATED);
             }
         }
+        Ok(())
     }
 
     #[test]
@@ -322,7 +319,7 @@ pub mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(text_field => "g b b d c g c"));
             index_writer.add_document(doc!(text_field => "g a b b a d c g c"));
             assert!(index_writer.commit().is_ok());
@@ -354,7 +351,7 @@ pub mod tests {
 
             let index = Index::create_in_ram(schema);
             {
-                let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+                let mut index_writer = index.writer_for_tests().unwrap();
                 for i in 0u64..num_docs as u64 {
                     let doc = doc!(value_field => 2u64, value_field => i % 2u64);
                     index_writer.add_document(doc);
@@ -425,7 +422,7 @@ pub mod tests {
 
         // delete some of the documents
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.delete_term(term_0);
             assert!(index_writer.commit().is_ok());
         }
@@ -479,7 +476,7 @@ pub mod tests {
 
         // delete everything else
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.delete_term(term_1);
             assert!(index_writer.commit().is_ok());
         }
@@ -522,7 +519,7 @@ pub mod tests {
         let index = Index::create_in_ram(schema);
         let posting_list_size = 1_000_000;
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             for _ in 0..posting_list_size {
                 let mut doc = Document::default();
                 if rng.gen_bool(1f64 / 15f64) {
@@ -730,7 +727,7 @@ mod bench {
             let mut s = 0u32;
             while segment_postings.doc() != TERMINATED {
                 s += (segment_postings.doc() & n) % 1024;
-                segment_postings.advance()
+                segment_postings.advance();
             }
             s
         });

src/postings/postings_writer.rs

@@ -105,6 +105,7 @@ impl MultiFieldPostingsWriter {
         doc: DocId,
         field: Field,
         token_stream: &mut dyn TokenStream,
+        term_buffer: &mut Term,
     ) -> u32 {
         let postings_writer =
             self.per_field_postings_writers[field.field_id() as usize].deref_mut();
@@ -114,6 +115,7 @@ impl MultiFieldPostingsWriter {
             field,
             token_stream,
             &mut self.heap,
+            term_buffer,
         )
     }
 
@@ -220,21 +222,22 @@ pub trait PostingsWriter {
         field: Field,
         token_stream: &mut dyn TokenStream,
         heap: &mut MemoryArena,
+        term_buffer: &mut Term,
     ) -> u32 {
-        let mut term = Term::for_field(field);
+        term_buffer.set_field(field);
         let mut sink = |token: &Token| {
             // We skip all tokens with a len greater than u16.
-            if token.text.len() <= MAX_TOKEN_LEN {
-                term.set_text(token.text.as_str());
-                self.subscribe(term_index, doc_id, token.position as u32, &term, heap);
-            } else {
-                info!(
-                    "A token exceeding MAX_TOKEN_LEN ({}>{}) was dropped. Search for \
-                     MAX_TOKEN_LEN in the documentation for more information.",
-                    token.text.len(),
-                    MAX_TOKEN_LEN
-                );
+            if token.text.len() > MAX_TOKEN_LEN {
+                return;
             }
+            term_buffer.set_text(token.text.as_str());
+            self.subscribe(
+                term_index,
+                doc_id,
+                token.position as u32,
+                &term_buffer,
+                heap,
+            );
         };
         token_stream.process(&mut sink)
     }

src/postings/segment_postings.rs

@@ -114,7 +114,7 @@ impl SegmentPostings {
                     .iter()
                     .map(|&fieldnorm| fieldnorm as u64)
                     .sum::<u64>();
-                total_num_tokens as Score / fieldnorms.len() as f32
+                total_num_tokens as Score / fieldnorms.len() as Score
             })
             .unwrap_or(0.0);
         let mut postings_serializer = PostingsSerializer::new(

src/query/all_query.rs

@@ -83,7 +83,7 @@ mod tests {
         let field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(field=>"aaa"));
         index_writer.add_document(doc!(field=>"bbb"));
         index_writer.commit().unwrap();

src/query/automaton_weight.rs

@@ -5,7 +5,6 @@ use crate::query::{BitSetDocSet, Explanation};
 use crate::query::{Scorer, Weight};
 use crate::schema::{Field, IndexRecordOption};
 use crate::termdict::{TermDictionary, TermStreamer};
-use crate::Result;
 use crate::TantivyError;
 use crate::{DocId, Score};
 use std::sync::Arc;
@@ -40,7 +39,7 @@ impl<A> Weight for AutomatonWeight<A>
 where
     A: Automaton + Send + Sync + 'static,
 {
-    fn scorer(&self, reader: &SegmentReader, boost: Score) -> Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         let max_doc = reader.max_doc();
         let mut doc_bitset = BitSet::with_max_value(max_doc);
         let inverted_index = reader.inverted_index(self.field);
@@ -66,7 +65,7 @@ where
         Ok(Box::new(const_scorer))
     }
 
-    fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         let mut scorer = self.scorer(reader, 1.0)?;
         if scorer.seek(doc) == doc {
             Ok(Explanation::new("AutomatonScorer", 1.0))
@@ -91,7 +90,7 @@ mod tests {
         let mut schema = Schema::builder();
         let title = schema.add_text_field("title", STRING);
         let index = Index::create_in_ram(schema.build());
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(title=>"abc"));
         index_writer.add_document(doc!(title=>"bcd"));
         index_writer.add_document(doc!(title=>"abcd"));

src/query/boolean_query/block_wand.rs

@@ -4,19 +4,6 @@ use crate::{DocId, DocSet, Score, TERMINATED};
 use std::ops::Deref;
 use std::ops::DerefMut;
 
-fn is_sorted<I: Iterator<Item = DocId>>(mut it: I) -> bool {
-    if let Some(first) = it.next() {
-        let mut prev = first;
-        for doc in it {
-            if doc < prev {
-                return false;
-            }
-            prev = doc;
-        }
-    }
-    true
-}
-
 /// Takes a term_scorers sorted by their current doc() and a threshold and returns
 /// Returns (pivot_len, pivot_ord) defined as follows:
 /// - `pivot_doc` lowest document that has a chance of exceeding (>) the threshold score.
@@ -55,37 +42,12 @@ fn find_pivot_doc(
     Some((before_pivot_len, pivot_len, pivot_doc))
 }
 
-struct TermScorerWithMaxScore<'a> {
-    scorer: &'a mut TermScorer,
-    max_score: Score,
-}
-
-impl<'a> From<&'a mut TermScorer> for TermScorerWithMaxScore<'a> {
-    fn from(scorer: &'a mut TermScorer) -> Self {
-        let max_score = scorer.max_score();
-        TermScorerWithMaxScore { scorer, max_score }
-    }
-}
-
-impl<'a> Deref for TermScorerWithMaxScore<'a> {
-    type Target = TermScorer;
-
-    fn deref(&self) -> &Self::Target {
-        self.scorer
-    }
-}
-
-impl<'a> DerefMut for TermScorerWithMaxScore<'a> {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        self.scorer
-    }
-}
-
 // Before and after calling this method, scorers need to be sorted by their `.doc()`.
 fn block_max_was_too_low_advance_one_scorer(
     scorers: &mut Vec<TermScorerWithMaxScore>,
     pivot_len: usize,
 ) {
+    debug_assert!(is_sorted(scorers.iter().map(|scorer| scorer.doc())));
     let mut scorer_to_seek = pivot_len - 1;
     let mut doc_to_seek_after = scorers[scorer_to_seek].doc();
     for scorer_ord in (0..pivot_len - 1).rev() {
@@ -102,6 +64,7 @@ fn block_max_was_too_low_advance_one_scorer(
     }
     scorers[scorer_to_seek].seek(doc_to_seek_after + 1);
     restore_ordering(scorers, scorer_to_seek);
+    debug_assert!(is_sorted(scorers.iter().map(|scorer| scorer.doc())));
 }
 
 // Given a list of term_scorers and a `ord` and assuming that `term_scorers[ord]` is sorted
@@ -177,64 +140,99 @@ pub fn block_wand(
         .map(TermScorerWithMaxScore::from)
         .collect();
     scorers.sort_by_key(|scorer| scorer.doc());
-    loop {
-        // At this point we need to ensure that the scorers are sorted!
+    // At this point we need to ensure that the scorers are sorted!
+    debug_assert!(is_sorted(scorers.iter().map(|scorer| scorer.doc())));
+    while let Some((before_pivot_len, pivot_len, pivot_doc)) =
+        find_pivot_doc(&scorers[..], threshold)
+    {
         debug_assert!(is_sorted(scorers.iter().map(|scorer| scorer.doc())));
-        if let Some((before_pivot_len, pivot_len, pivot_doc)) =
-            find_pivot_doc(&scorers[..], threshold)
-        {
-            debug_assert_ne!(pivot_doc, TERMINATED);
-            debug_assert!(before_pivot_len < pivot_len);
+        debug_assert_ne!(pivot_doc, TERMINATED);
+        debug_assert!(before_pivot_len < pivot_len);
 
-            let block_max_score_upperbound: Score = scorers[..pivot_len]
-                .iter_mut()
-                .map(|scorer| {
-                    scorer.shallow_seek(pivot_doc);
-                    scorer.block_max_score()
-                })
-                .sum();
+        let block_max_score_upperbound: Score = scorers[..pivot_len]
+            .iter_mut()
+            .map(|scorer| {
+                scorer.shallow_seek(pivot_doc);
+                scorer.block_max_score()
+            })
+            .sum();
 
-            // Beware after shallow advance, skip readers can be in advance compared to
-            // the segment posting lists.
-            //
-            // `block_segment_postings.load_block()` need to be called separately.
-            if block_max_score_upperbound <= threshold {
-                // Block max condition was not reached
-                // We could get away by simply advancing the scorers to DocId + 1 but it would
-                // be inefficient. The optimization requires proper explanation and was
-                // isolated in a different function.
-                block_max_was_too_low_advance_one_scorer(&mut scorers, pivot_len);
-                continue;
-            }
-
-            // Block max condition is observed.
-            //
-            // Let's try and advance all scorers before the pivot to the pivot.
-            if !align_scorers(&mut scorers, pivot_doc, before_pivot_len) {
-                // At least of the scorer does not contain the pivot.
-                //
-                // Let's stop scoring this pivot and go through the pivot selection again.
-                // Note that the current pivot is not necessarily a bad candidate and it
-                // may be picked again.
-                continue;
-            }
-
-            // At this point, all scorers are positioned on the doc.
-            let score = scorers[..pivot_len]
-                .iter_mut()
-                .map(|scorer| scorer.score())
-                .sum();
-            if score > threshold {
-                threshold = callback(pivot_doc, score);
-            }
-            // let's advance all of the scorers that are currently positioned on the pivot.
-            advance_all_scorers_on_pivot(&mut scorers, pivot_len);
-        } else {
-            return;
+        // Beware after shallow advance, skip readers can be in advance compared to
+        // the segment posting lists.
+        //
+        // `block_segment_postings.load_block()` need to be called separately.
+        if block_max_score_upperbound <= threshold {
+            // Block max condition was not reached
+            // We could get away by simply advancing the scorers to DocId + 1 but it would
+            // be inefficient. The optimization requires proper explanation and was
+            // isolated in a different function.
+            block_max_was_too_low_advance_one_scorer(&mut scorers, pivot_len);
+            continue;
         }
+
+        // Block max condition is observed.
+        //
+        // Let's try and advance all scorers before the pivot to the pivot.
+        if !align_scorers(&mut scorers, pivot_doc, before_pivot_len) {
+            // At least of the scorer does not contain the pivot.
+            //
+            // Let's stop scoring this pivot and go through the pivot selection again.
+            // Note that the current pivot is not necessarily a bad candidate and it
+            // may be picked again.
+            continue;
+        }
+
+        // At this point, all scorers are positioned on the doc.
+        let score = scorers[..pivot_len]
+            .iter_mut()
+            .map(|scorer| scorer.score())
+            .sum();
+        if score > threshold {
+            threshold = callback(pivot_doc, score);
+        }
+        // let's advance all of the scorers that are currently positioned on the pivot.
+        advance_all_scorers_on_pivot(&mut scorers, pivot_len);
     }
 }
 
+struct TermScorerWithMaxScore<'a> {
+    scorer: &'a mut TermScorer,
+    max_score: Score,
+}
+
+impl<'a> From<&'a mut TermScorer> for TermScorerWithMaxScore<'a> {
+    fn from(scorer: &'a mut TermScorer) -> Self {
+        let max_score = scorer.max_score();
+        TermScorerWithMaxScore { scorer, max_score }
+    }
+}
+
+impl<'a> Deref for TermScorerWithMaxScore<'a> {
+    type Target = TermScorer;
+
+    fn deref(&self) -> &Self::Target {
+        self.scorer
+    }
+}
+
+impl<'a> DerefMut for TermScorerWithMaxScore<'a> {
+    fn deref_mut(&mut self) -> &mut Self::Target {
+        self.scorer
+    }
+}
+
+fn is_sorted<I: Iterator<Item = DocId>>(mut it: I) -> bool {
+    if let Some(first) = it.next() {
+        let mut prev = first;
+        for doc in it {
+            if doc < prev {
+                return false;
+            }
+            prev = doc;
+        }
+    }
+    true
+}
 #[cfg(test)]
 mod tests {
     use crate::query::score_combiner::SumCombiner;
@@ -248,17 +246,21 @@ mod tests {
     use std::iter;
 
     struct Float(Score);
+
     impl Eq for Float {}
+
     impl PartialEq for Float {
         fn eq(&self, other: &Self) -> bool {
             self.cmp(&other) == Ordering::Equal
         }
     }
+
     impl PartialOrd for Float {
         fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
             Some(self.cmp(other))
         }
     }
+
     impl Ord for Float {
         fn cmp(&self, other: &Self) -> Ordering {
             other.0.partial_cmp(&self.0).unwrap_or(Ordering::Equal)

src/query/boolean_query/mod.rs

@@ -32,7 +32,7 @@ mod tests {
         let index = Index::create_in_ram(schema);
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             {
                 index_writer.add_document(doc!(text_field => "a b c"));
                 index_writer.add_document(doc!(text_field => "a c"));
@@ -224,7 +224,7 @@ mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(text_field => "a b c"));
             index_writer.add_document(doc!(text_field => "a c"));
             index_writer.add_document(doc!(text_field => "b c"));

src/query/boost_query.rs

@@ -144,7 +144,7 @@ mod tests {
     fn test_boost_query_explain() {
         let schema = Schema::builder().build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(Document::new());
         assert!(index_writer.commit().is_ok());
         let reader = index.reader().unwrap();

src/query/fuzzy_query.rs

@@ -177,7 +177,7 @@ mod test {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(
                 country_field => "japan",
             ));

src/query/phrase_query/mod.rs

@@ -24,7 +24,7 @@ pub mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             for &text in texts {
                 let doc = doc!(text_field=>text);
                 index_writer.add_document(doc);
@@ -135,7 +135,7 @@ pub mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(text_field=>"a b c"));
             assert!(index_writer.commit().is_ok());
         }
@@ -186,7 +186,7 @@ pub mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(text_field=>"b"));
             index_writer.add_document(doc!(text_field=>"a b"));
             index_writer.add_document(doc!(text_field=>"b a"));
@@ -217,7 +217,7 @@ pub mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(text_field=>"a b c d e f g h"));
             assert!(index_writer.commit().is_ok());
         }

src/query/phrase_query/phrase_weight.rs

@@ -9,8 +9,8 @@ use crate::query::Weight;
 use crate::query::{EmptyScorer, Explanation};
 use crate::schema::IndexRecordOption;
 use crate::schema::Term;
+use crate::Score;
 use crate::{DocId, DocSet};
-use crate::{Result, Score};
 
 pub struct PhraseWeight {
     phrase_terms: Vec<(usize, Term)>,
@@ -32,7 +32,7 @@ impl PhraseWeight {
         }
     }
 
-    fn fieldnorm_reader(&self, reader: &SegmentReader) -> FieldNormReader {
+    fn fieldnorm_reader(&self, reader: &SegmentReader) -> crate::Result<FieldNormReader> {
         let field = self.phrase_terms[0].1.field();
         reader.get_fieldnorms_reader(field)
     }
@@ -41,9 +41,9 @@ impl PhraseWeight {
         &self,
         reader: &SegmentReader,
         boost: Score,
-    ) -> Result<Option<PhraseScorer<SegmentPostings>>> {
+    ) -> crate::Result<Option<PhraseScorer<SegmentPostings>>> {
         let similarity_weight = self.similarity_weight.boost_by(boost);
-        let fieldnorm_reader = self.fieldnorm_reader(reader);
+        let fieldnorm_reader = self.fieldnorm_reader(reader)?;
         if reader.has_deletes() {
             let mut term_postings_list = Vec::new();
             for &(offset, ref term) in &self.phrase_terms {
@@ -85,7 +85,7 @@ impl PhraseWeight {
 }
 
 impl Weight for PhraseWeight {
-    fn scorer(&self, reader: &SegmentReader, boost: Score) -> Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         if let Some(scorer) = self.phrase_scorer(reader, boost)? {
             Ok(Box::new(scorer))
         } else {
@@ -93,7 +93,7 @@ impl Weight for PhraseWeight {
         }
     }
 
-    fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         let scorer_opt = self.phrase_scorer(reader, 1.0)?;
         if scorer_opt.is_none() {
             return Err(does_not_match(doc));
@@ -102,7 +102,7 @@ impl Weight for PhraseWeight {
         if scorer.seek(doc) != doc {
             return Err(does_not_match(doc));
         }
-        let fieldnorm_reader = self.fieldnorm_reader(reader);
+        let fieldnorm_reader = self.fieldnorm_reader(reader)?;
         let fieldnorm_id = fieldnorm_reader.fieldnorm_id(doc);
         let phrase_count = scorer.phrase_count();
         let mut explanation = Explanation::new("Phrase Scorer", scorer.score());

src/query/query_parser/query_parser.rs

@@ -21,51 +21,48 @@ 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)]
+#[derive(Debug, PartialEq, Eq, Error)]
 pub enum QueryParserError {
     /// Error in the query syntax
-    #[fail(display = "Syntax Error")]
+    #[error("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)]
+    #[error("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)]
+    #[error("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")]
+    #[error("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")]
+    #[error("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")]
+    #[error("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)]
+    #[error("The field '{0:?}' is not declared as indexed")]
     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)]
+    #[error("The field '{0:?}' does not have positions indexed")]
     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
-    )]
+    #[error("The tokenizer '{0:?}' for the field '{1:?}' is unknown")]
     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")]
+    #[error("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")]
+    #[error("The date field has an invalid format")]
     DateFormatError(chrono::ParseError),
 }
 

src/query/range_query.rs

@@ -9,7 +9,6 @@ use crate::query::{Query, Scorer, Weight};
 use crate::schema::Type;
 use crate::schema::{Field, IndexRecordOption, Term};
 use crate::termdict::{TermDictionary, TermStreamer};
-use crate::Result;
 use crate::{DocId, Score};
 use std::collections::Bound;
 use std::ops::Range;
@@ -48,7 +47,7 @@ fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
 /// 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)?;
+/// let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
 /// for year in 1950u64..2017u64 {
 ///     let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
 ///     for _ in 0..num_docs_within_year {
@@ -246,7 +245,11 @@ impl RangeQuery {
 }
 
 impl Query for RangeQuery {
-    fn weight(&self, searcher: &Searcher, _scoring_enabled: bool) -> Result<Box<dyn Weight>> {
+    fn weight(
+        &self,
+        searcher: &Searcher,
+        _scoring_enabled: bool,
+    ) -> crate::Result<Box<dyn Weight>> {
         let schema = searcher.schema();
         let value_type = schema.get_field_entry(self.field).field_type().value_type();
         if value_type != self.value_type {
@@ -289,7 +292,7 @@ impl RangeWeight {
 }
 
 impl Weight for RangeWeight {
-    fn scorer(&self, reader: &SegmentReader, boost: Score) -> Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         let max_doc = reader.max_doc();
         let mut doc_bitset = BitSet::with_max_value(max_doc);
 
@@ -315,7 +318,7 @@ impl Weight for RangeWeight {
         Ok(Box::new(ConstScorer::new(doc_bitset, boost)))
     }
 
-    fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         let mut scorer = self.scorer(reader, 1.0)?;
         if scorer.seek(doc) != doc {
             return Err(does_not_match(doc));
@@ -342,7 +345,7 @@ mod tests {
 
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             for year in 1950u64..2017u64 {
                 let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
                 for _ in 0..num_docs_within_year {
@@ -485,7 +488,7 @@ mod tests {
         schema_builder.add_i64_field("year", INDEXED);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema.clone());
-        let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
+        let mut index_writer = index.writer_for_tests()?;
         let title = schema.get_field("title").unwrap();
         let year = schema.get_field("year").unwrap();
         index_writer.add_document(doc!(

src/query/regex_query.rs

@@ -103,7 +103,7 @@ mod test {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(
                 country_field => "japan",
             ));

src/query/term_query/mod.rs

@@ -25,7 +25,7 @@ mod tests {
         let index = Index::create_in_ram(schema);
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             let doc = doc!(text_field => "a");
             index_writer.add_document(doc);
             assert!(index_writer.commit().is_ok());
@@ -50,7 +50,7 @@ mod tests {
         let index = Index::create_in_ram(schema);
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
+            let mut index_writer = index.writer_for_tests()?;
             for _ in 0..COMPRESSION_BLOCK_SIZE {
                 let doc = doc!(text_field => "a");
                 index_writer.add_document(doc);
@@ -86,7 +86,7 @@ mod tests {
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
         {
-            let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(
                 left_field => "left1 left2 left2 left2f2 left2f2 left3 abcde abcde abcde abcde abcde abcde abcde abcde abcde abcewde abcde abcde",
                 right_field => "right1 right2",
@@ -136,7 +136,7 @@ mod tests {
         let text_field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 5_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(text_field=>"a b"));
         index_writer.add_document(doc!(text_field=>"a c"));
         index_writer.delete_term(Term::from_field_text(text_field, "b"));
@@ -153,7 +153,7 @@ mod tests {
         let text_field = schema_builder.add_text_field("text", TEXT);
         let schema = schema_builder.build();
         let index = Index::create_in_ram(schema);
-        let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+        let mut index_writer = index.writer_for_tests().unwrap();
         index_writer.add_document(doc!(text_field=>"a"));
         index_writer.add_document(doc!(text_field=>"a"));
         index_writer.commit()?;

src/query/term_query/term_weight.rs

@@ -4,11 +4,10 @@ use crate::docset::DocSet;
 use crate::postings::SegmentPostings;
 use crate::query::bm25::BM25Weight;
 use crate::query::explanation::does_not_match;
-use crate::query::weight::{for_each_pruning_scorer, for_each_scorer};
+use crate::query::weight::for_each_scorer;
 use crate::query::Weight;
 use crate::query::{Explanation, Scorer};
 use crate::schema::IndexRecordOption;
-use crate::Result;
 use crate::Term;
 use crate::{DocId, Score};
 
@@ -19,12 +18,12 @@ pub struct TermWeight {
 }
 
 impl Weight for TermWeight {
-    fn scorer(&self, reader: &SegmentReader, boost: Score) -> Result<Box<dyn Scorer>> {
+    fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
         let term_scorer = self.specialized_scorer(reader, boost)?;
         Ok(Box::new(term_scorer))
     }
 
-    fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
+    fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
         let mut scorer = self.specialized_scorer(reader, 1.0)?;
         if scorer.seek(doc) != doc {
             return Err(does_not_match(doc));
@@ -32,7 +31,7 @@ impl Weight for TermWeight {
         Ok(scorer.explain())
     }
 
-    fn count(&self, reader: &SegmentReader) -> Result<u32> {
+    fn count(&self, reader: &SegmentReader) -> crate::Result<u32> {
         if let Some(delete_bitset) = reader.delete_bitset() {
             Ok(self.scorer(reader, 1.0)?.count(delete_bitset))
         } else {
@@ -73,8 +72,8 @@ impl Weight for TermWeight {
         reader: &SegmentReader,
         callback: &mut dyn FnMut(DocId, Score) -> Score,
     ) -> crate::Result<()> {
-        let mut scorer = self.scorer(reader, 1.0)?;
-        for_each_pruning_scorer(&mut scorer, threshold, callback);
+        let scorer = self.specialized_scorer(reader, 1.0)?;
+        crate::query::boolean_query::block_wand(vec![scorer], threshold, callback);
         Ok(())
     }
 }
@@ -96,10 +95,10 @@ impl TermWeight {
         &self,
         reader: &SegmentReader,
         boost: Score,
-    ) -> Result<TermScorer> {
+    ) -> crate::Result<TermScorer> {
         let field = self.term.field();
         let inverted_index = reader.inverted_index(field);
-        let fieldnorm_reader = reader.get_fieldnorms_reader(field);
+        let fieldnorm_reader = reader.get_fieldnorms_reader(field)?;
         let similarity_weight = self.similarity_weight.boost_by(boost);
         let postings_opt: Option<SegmentPostings> =
             inverted_index.read_postings(&self.term, self.index_record_option);

src/query/union.rs

@@ -398,9 +398,9 @@ mod bench {
 
     use crate::query::score_combiner::DoNothingCombiner;
     use crate::query::{ConstScorer, Union, VecDocSet};
-    use crate::tests;
     use crate::DocId;
     use crate::DocSet;
+    use crate::{tests, TERMINATED};
     use test::Bencher;
 
     #[bench]
@@ -414,10 +414,12 @@ mod bench {
                 union_docset
                     .iter()
                     .map(|doc_ids| VecDocSet::from(doc_ids.clone()))
-                    .map(ConstScorer::new)
+                    .map(|docset| ConstScorer::new(docset, 1.0))
                     .collect::<Vec<_>>(),
             );
-            while v.advance() {}
+            while v.doc() != TERMINATED {
+                v.advance();
+            }
         });
     }
     #[bench]
@@ -432,10 +434,12 @@ mod bench {
                 union_docset
                     .iter()
                     .map(|doc_ids| VecDocSet::from(doc_ids.clone()))
-                    .map(ConstScorer::new)
+                    .map(|docset| ConstScorer::new(docset, 1.0))
                     .collect::<Vec<_>>(),
             );
-            while v.advance() {}
+            while v.doc() != TERMINATED {
+                v.advance();
+            }
         });
     }
 }

src/reader/mod.rs

@@ -1,5 +1,7 @@
 mod pool;
 
+use slog::error;
+
 pub use self::pool::LeasedItem;
 use self::pool::Pool;
 use crate::core::Segment;
@@ -62,6 +64,7 @@ impl IndexReaderBuilder {
     /// to open different segment readers. It may take hundreds of milliseconds
     /// of time and it may return an error.
     pub fn try_into(self) -> crate::Result<IndexReader> {
+        let logger = self.index.logger().clone();
         let inner_reader = InnerIndexReader {
             index: self.index,
             num_searchers: self.num_searchers,
@@ -80,8 +83,8 @@ impl IndexReaderBuilder {
                 let callback = move || {
                     if let Err(err) = inner_reader_arc_clone.reload() {
                         error!(
-                            "Error while loading searcher after commit was detected. {:?}",
-                            err
+                            logger,
+                            "Error while loading searcher after commit was detected. {:?}", err
                         );
                     }
                 };
@@ -138,9 +141,11 @@ impl InnerIndexReader {
                 .collect::<crate::Result<_>>()?
         };
         let schema = self.index.schema();
-        let searchers = (0..self.num_searchers)
-            .map(|_| Searcher::new(schema.clone(), self.index.clone(), segment_readers.clone()))
-            .collect();
+        let searchers = std::iter::repeat_with(|| {
+            Searcher::new(schema.clone(), self.index.clone(), segment_readers.clone())
+        })
+        .take(self.num_searchers)
+        .collect();
         self.searcher_pool.publish_new_generation(searchers);
         Ok(())
     }

src/schema/document.rs

@@ -74,9 +74,8 @@ impl Document {
     }
 
     /// Add a text field.
-    pub fn add_text(&mut self, field: Field, text: &str) {
-        let value = Value::Str(String::from(text));
-        self.add(FieldValue::new(field, value));
+    pub fn add_text<S: ToString>(&mut self, field: Field, text: S) {
+        self.add(FieldValue::new(field, Value::Str(text.to_string())));
     }
 
     /// Add a pre-tokenized text field.
@@ -110,8 +109,8 @@ impl Document {
     }
 
     /// Add a bytes field
-    pub fn add_bytes(&mut self, field: Field, value: Vec<u8>) {
-        self.add(FieldValue::new(field, Value::Bytes(value)))
+    pub fn add_bytes<T: Into<Vec<u8>>>(&mut self, field: Field, value: T) {
+        self.add(FieldValue::new(field, Value::Bytes(value.into())))
     }
 
     /// Add a field value

src/schema/field_entry.rs

@@ -1,5 +1,5 @@
-use crate::schema::IntOptions;
 use crate::schema::TextOptions;
+use crate::schema::{is_valid_field_name, IntOptions};
 
 use crate::schema::FieldType;
 use serde::de::{self, MapAccess, Visitor};
@@ -24,6 +24,7 @@ impl FieldEntry {
     /// Creates a new u64 field entry in the schema, given
     /// a name, and some options.
     pub fn new_text(field_name: String, text_options: TextOptions) -> FieldEntry {
+        assert!(is_valid_field_name(&field_name));
         FieldEntry {
             name: field_name,
             field_type: FieldType::Str(text_options),
@@ -33,6 +34,7 @@ impl FieldEntry {
     /// Creates a new u64 field entry in the schema, given
     /// a name, and some options.
     pub fn new_u64(field_name: String, field_type: IntOptions) -> FieldEntry {
+        assert!(is_valid_field_name(&field_name));
         FieldEntry {
             name: field_name,
             field_type: FieldType::U64(field_type),
@@ -42,6 +44,7 @@ impl FieldEntry {
     /// Creates a new i64 field entry in the schema, given
     /// a name, and some options.
     pub fn new_i64(field_name: String, field_type: IntOptions) -> FieldEntry {
+        assert!(is_valid_field_name(&field_name));
         FieldEntry {
             name: field_name,
             field_type: FieldType::I64(field_type),
@@ -51,6 +54,7 @@ impl FieldEntry {
     /// Creates a new f64 field entry in the schema, given
     /// a name, and some options.
     pub fn new_f64(field_name: String, field_type: IntOptions) -> FieldEntry {
+        assert!(is_valid_field_name(&field_name));
         FieldEntry {
             name: field_name,
             field_type: FieldType::F64(field_type),
@@ -60,6 +64,7 @@ impl FieldEntry {
     /// Creates a new date field entry in the schema, given
     /// a name, and some options.
     pub fn new_date(field_name: String, field_type: IntOptions) -> FieldEntry {
+        assert!(is_valid_field_name(&field_name));
         FieldEntry {
             name: field_name,
             field_type: FieldType::Date(field_type),
@@ -68,6 +73,7 @@ impl FieldEntry {
 
     /// Creates a field entry for a facet.
     pub fn new_facet(field_name: String) -> FieldEntry {
+        assert!(is_valid_field_name(&field_name));
         FieldEntry {
             name: field_name,
             field_type: FieldType::HierarchicalFacet,
@@ -76,6 +82,7 @@ impl FieldEntry {
 
     /// Creates a field entry for a bytes field
     pub fn new_bytes(field_name: String) -> FieldEntry {
+        assert!(is_valid_field_name(&field_name));
         FieldEntry {
             name: field_name,
             field_type: FieldType::Bytes,
@@ -268,6 +275,12 @@ mod tests {
     use crate::schema::TEXT;
     use serde_json;
 
+    #[test]
+    #[should_panic]
+    fn test_invalid_field_name_should_panic() {
+        FieldEntry::new_text("-hello".to_string(), TEXT);
+    }
+
     #[test]
     fn test_json_serialization() {
         let field_value = FieldEntry::new_text(String::from("title"), TEXT);

src/schema/mod.rs

@@ -149,14 +149,16 @@ pub use self::int_options::IntOptions;
 use once_cell::sync::Lazy;
 use regex::Regex;
 
+/// Regular expression representing the restriction on a valid field names.
+pub const FIELD_NAME_PATTERN: &str = r#"^[_a-zA-Z][_\-a-zA-Z0-9]*$"#;
+
 /// Validator for a potential `field_name`.
 /// Returns true iff the name can be use for a field name.
 ///
 /// A field name must start by a letter `[a-zA-Z]`.
 /// The other characters can be any alphanumic character `[a-ZA-Z0-9]` or `_`.
 pub fn is_valid_field_name(field_name: &str) -> bool {
-    static FIELD_NAME_PTN: Lazy<Regex> =
-        Lazy::new(|| Regex::new("^[a-zA-Z][_a-zA-Z0-9]*$").unwrap());
+    static FIELD_NAME_PTN: Lazy<Regex> = Lazy::new(|| Regex::new(FIELD_NAME_PATTERN).unwrap());
     FIELD_NAME_PTN.is_match(field_name)
 }
 
@@ -170,6 +172,11 @@ mod tests {
         assert!(is_valid_field_name("text"));
         assert!(is_valid_field_name("text0"));
         assert!(!is_valid_field_name("0text"));
+        assert!(is_valid_field_name("field-name"));
+        assert!(is_valid_field_name("field_name"));
+        assert!(!is_valid_field_name("field!name"));
+        assert!(!is_valid_field_name("-fieldname"));
+        assert!(is_valid_field_name("_fieldname"));
         assert!(!is_valid_field_name(""));
         assert!(!is_valid_field_name("シャボン玉"));
         assert!(is_valid_field_name("my_text_field"));

src/schema/schema.rs

@@ -381,19 +381,16 @@ impl<'de> Deserialize<'de> for Schema {
 
 /// Error that may happen when deserializing
 /// a document from JSON.
-#[derive(Debug, Fail, PartialEq)]
+#[derive(Debug, Error, PartialEq)]
 pub enum DocParsingError {
     /// The payload given is not valid JSON.
-    #[fail(display = "The provided string is not valid JSON")]
+    #[error("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)]
+    #[error("The field '{0:?}' could not be parsed: {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
-    )]
+    #[error("The document contains a field that is not declared in the schema: {0:?}")]
     NoSuchFieldInSchema(String),
 }
 

src/schema/term.rs

@@ -4,7 +4,6 @@ use super::Field;
 use crate::common;
 use crate::schema::Facet;
 use crate::DateTime;
-use byteorder::{BigEndian, ByteOrder};
 use std::str;
 
 /// Size (in bytes) of the buffer of a int field.
@@ -19,6 +18,10 @@ where
     B: AsRef<[u8]>;
 
 impl Term {
+    pub(crate) fn new() -> Term {
+        Term(Vec::with_capacity(100))
+    }
+
     /// 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,
@@ -93,6 +96,12 @@ impl Term {
         term
     }
 
+    pub(crate) fn from_field_bytes(field: Field, bytes: &[u8]) -> Term {
+        let mut term = Term::for_field(field);
+        term.set_bytes(bytes);
+        term
+    }
+
     /// Creates a new Term for a given field.
     pub(crate) fn for_field(field: Field) -> Term {
         let mut term = Term(Vec::with_capacity(100));
@@ -100,12 +109,10 @@ impl Term {
         term
     }
 
-    /// Returns the field.
-    pub fn set_field(&mut self, field: Field) {
-        if self.0.len() < 4 {
-            self.0.resize(4, 0u8);
-        }
-        BigEndian::write_u32(&mut self.0[0..4], field.field_id());
+    pub(crate) fn set_field(&mut self, field: Field) {
+        self.0.clear();
+        self.0
+            .extend_from_slice(&field.field_id().to_be_bytes()[..]);
     }
 
     /// Sets a u64 value in the term.
@@ -116,7 +123,7 @@ impl Term {
     /// the natural order of the values.
     pub fn set_u64(&mut self, val: u64) {
         self.0.resize(INT_TERM_LEN, 0u8);
-        BigEndian::write_u64(&mut self.0[4..], val);
+        self.0[4..12].copy_from_slice(val.to_be_bytes().as_ref());
     }
 
     /// Sets a `i64` value in the term.
@@ -134,12 +141,6 @@ impl Term {
         self.0.extend(bytes);
     }
 
-    pub(crate) fn from_field_bytes(field: Field, bytes: &[u8]) -> Term {
-        let mut term = Term::for_field(field);
-        term.set_bytes(bytes);
-        term
-    }
-
     /// Set the texts only, keeping the field untouched.
     pub fn set_text(&mut self, text: &str) {
         self.set_bytes(text.as_bytes());
@@ -157,7 +158,9 @@ where
 
     /// Returns the field.
     pub fn field(&self) -> Field {
-        Field::from_field_id(BigEndian::read_u32(&self.0.as_ref()[..4]))
+        let mut field_id_bytes = [0u8; 4];
+        field_id_bytes.copy_from_slice(&self.0.as_ref()[..4]);
+        Field::from_field_id(u32::from_be_bytes(field_id_bytes))
     }
 
     /// Returns the `u64` value stored in a term.
@@ -166,7 +169,9 @@ where
     /// ... or returns an invalid value
     /// if the term is not a `u64` field.
     pub fn get_u64(&self) -> u64 {
-        BigEndian::read_u64(&self.0.as_ref()[4..])
+        let mut field_id_bytes = [0u8; 8];
+        field_id_bytes.copy_from_slice(self.value_bytes());
+        u64::from_be_bytes(field_id_bytes)
     }
 
     /// Returns the `i64` value stored in a term.
@@ -175,7 +180,7 @@ where
     /// ... or returns an invalid value
     /// if the term is not a `i64` field.
     pub fn get_i64(&self) -> i64 {
-        common::u64_to_i64(BigEndian::read_u64(&self.0.as_ref()[4..]))
+        common::u64_to_i64(self.get_u64())
     }
 
     /// Returns the `f64` value stored in a term.
@@ -184,7 +189,7 @@ where
     /// ... or returns an invalid value
     /// 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..]))
+        common::u64_to_f64(self.get_u64())
     }
 
     /// Returns the text associated with the term.

src/schema/value.rs

@@ -221,6 +221,12 @@ impl<'a> From<&'a str> for Value {
     }
 }
 
+impl<'a> From<&'a [u8]> for Value {
+    fn from(bytes: &'a [u8]) -> Value {
+        Value::Bytes(bytes.to_vec())
+    }
+}
+
 impl<'a> From<Facet> for Value {
     fn from(facet: Facet) -> Value {
         Value::Facet(facet)

src/snippet/mod.rs

@@ -221,7 +221,7 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
 /// #    let text_field = schema_builder.add_text_field("text", TEXT);
 /// #    let schema = schema_builder.build();
 /// #    let index = Index::create_in_ram(schema);
-/// #    let mut index_writer = index.writer_with_num_threads(1, 30_000_000)?;
+/// #    let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
 /// #    let doc = doc!(text_field => r#"Comme je descendais des Fleuves impassibles,
 /// #   Je ne me sentis plus guidé par les haleurs :
 /// #  Des Peaux-Rouges criards les avaient pris pour cibles,
@@ -506,7 +506,7 @@ Survey in 2016, 2017, and 2018."#;
         let index = Index::create_in_ram(schema);
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(text_field => "a"));
             index_writer.add_document(doc!(text_field => "a"));
             index_writer.add_document(doc!(text_field => "a b"));
@@ -562,7 +562,7 @@ Survey in 2016, 2017, and 2018."#;
         let index = Index::create_in_ram(schema);
         {
             // writing the segment
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             {
                 let doc = doc ! (text_field => TEST_TEXT);
                 index_writer.add_document(doc);

src/space_usage/mod.rs

@@ -336,7 +336,7 @@ mod test {
         let index = Index::create_in_ram(schema.clone());
 
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(name => 1u64));
             index_writer.add_document(doc!(name => 2u64));
             index_writer.add_document(doc!(name => 10u64));
@@ -374,7 +374,7 @@ mod test {
         let index = Index::create_in_ram(schema.clone());
 
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(name => "hi"));
             index_writer.add_document(doc!(name => "this is a test"));
             index_writer.add_document(
@@ -414,7 +414,7 @@ mod test {
         let index = Index::create_in_ram(schema.clone());
 
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(name => "hi"));
             index_writer.add_document(doc!(name => "this is a test"));
             index_writer.add_document(
@@ -453,7 +453,7 @@ mod test {
         let index = Index::create_in_ram(schema.clone());
 
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             index_writer.add_document(doc!(name => 1u64));
             index_writer.add_document(doc!(name => 2u64));
             index_writer.add_document(doc!(name => 3u64));

src/store/skiplist/skiplist_builder.rs

@@ -68,19 +68,17 @@ impl<T: BinarySerializable> SkipListBuilder<T> {
     }
 
     pub fn insert(&mut self, key: u64, dest: &T) -> io::Result<()> {
-        let mut layer_id = 0;
         let mut skip_pointer = self.data_layer.insert(key, dest)?;
-        loop {
-            skip_pointer = match skip_pointer {
-                Some((skip_doc_id, skip_offset)) => self
+        for layer_id in 0.. {
+            if let Some((skip_doc_id, skip_offset)) = skip_pointer {
+                skip_pointer = self
                     .get_skip_layer(layer_id)
-                    .insert(skip_doc_id, &skip_offset)?,
-                None => {
-                    return Ok(());
-                }
-            };
-            layer_id += 1;
+                    .insert(skip_doc_id, &skip_offset)?;
+            } else {
+                break;
+            }
         }
+        Ok(())
     }
 
     pub fn write<W: Write>(self, output: &mut W) -> io::Result<()> {

src/termdict/mod.rs

@@ -138,7 +138,7 @@ mod tests {
         let text_field = schema_builder.add_text_field("text", TEXT);
         let index = Index::create_in_ram(schema_builder.build());
         {
-            let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
+            let mut index_writer = index.writer_for_tests().unwrap();
             {
                 {
                     let mut doc = Document::default();