clippy (#2349)

* fix clippy

* fix clippy

* fix duplicate imports

Cargo.toml

@@ -11,7 +11,7 @@ repository = "https://github.com/quickwit-oss/tantivy"
 readme = "README.md"
 keywords = ["search", "information", "retrieval"]
 edition = "2021"
-rust-version = "1.62"
+rust-version = "1.63"
 exclude = ["benches/*.json", "benches/*.txt"]
 
 [dependencies]

columnar/src/column_index/merge/shuffled.rs

@@ -140,7 +140,7 @@ mod tests {
     #[test]
     fn test_merge_column_index_optional_shuffle() {
         let optional_index: ColumnIndex = OptionalIndex::for_test(2, &[0]).into();
-        let column_indexes = vec![optional_index, ColumnIndex::Full];
+        let column_indexes = [optional_index, ColumnIndex::Full];
         let row_addrs = vec![
             RowAddr {
                 segment_ord: 0u32,

columnar/src/column_values/mod.rs

@@ -75,7 +75,7 @@ pub trait ColumnValues<T: PartialOrd = u64>: Send + Sync + DowncastSync {
         let out_and_idx_chunks = output
             .chunks_exact_mut(4)
             .into_remainder()
-            .into_iter()
+            .iter_mut()
             .zip(indexes.chunks_exact(4).remainder());
         for (out, idx) in out_and_idx_chunks {
             *out = self.get_val(*idx);
@@ -102,7 +102,7 @@ pub trait ColumnValues<T: PartialOrd = u64>: Send + Sync + DowncastSync {
         let out_and_idx_chunks = output
             .chunks_exact_mut(4)
             .into_remainder()
-            .into_iter()
+            .iter_mut()
             .zip(indexes.chunks_exact(4).remainder());
         for (out, idx) in out_and_idx_chunks {
             *out = Some(self.get_val(*idx));

columnar/src/column_values/u128_based/compact_space/mod.rs

@@ -148,7 +148,7 @@ impl CompactSpace {
             .binary_search_by_key(&compact, |range_mapping| range_mapping.compact_start)
             // Correctness: Overflow. The first range starts at compact space 0, the error from
             // binary search can never be 0
-            .map_or_else(|e| e - 1, |v| v);
+            .unwrap_or_else(|e| e - 1);
 
         let range_mapping = &self.ranges_mapping[pos];
         let diff = compact - range_mapping.compact_start;

common/src/serialize.rs

@@ -290,8 +290,7 @@ impl<'a> BinarySerializable for Cow<'a, [u8]> {
 #[cfg(test)]
 pub mod test {
 
-    use super::{VInt, *};
-    use crate::serialize::BinarySerializable;
+    use super::*;
     pub fn fixed_size_test<O: BinarySerializable + FixedSize + Default>() {
         let mut buffer = Vec::new();
         O::default().serialize(&mut buffer).unwrap();

src/aggregation/bucket/histogram/histogram.rs

@@ -1,7 +1,5 @@
 use std::cmp::Ordering;
 
-use columnar::ColumnType;
-use itertools::Itertools;
 use rustc_hash::FxHashMap;
 use serde::{Deserialize, Serialize};
 use tantivy_bitpacker::minmax;
@@ -17,7 +15,7 @@ use crate::aggregation::intermediate_agg_result::{
     IntermediateHistogramBucketEntry,
 };
 use crate::aggregation::segment_agg_result::{
-    build_segment_agg_collector, AggregationLimits, SegmentAggregationCollector,
+    build_segment_agg_collector, SegmentAggregationCollector,
 };
 use crate::aggregation::*;
 use crate::TantivyError;

src/aggregation/bucket/range.rs

@@ -1,7 +1,6 @@
 use std::fmt::Debug;
 use std::ops::Range;
 
-use columnar::{ColumnType, MonotonicallyMappableToU64};
 use rustc_hash::FxHashMap;
 use serde::{Deserialize, Serialize};
 
@@ -450,7 +449,6 @@ pub(crate) fn range_to_key(range: &Range<u64>, field_type: &ColumnType) -> crate
 #[cfg(test)]
 mod tests {
 
-    use columnar::MonotonicallyMappableToU64;
     use serde_json::Value;
 
     use super::*;
@@ -459,7 +457,6 @@ mod tests {
         exec_request, exec_request_with_query, get_test_index_2_segments,
         get_test_index_with_num_docs,
     };
-    use crate::aggregation::AggregationLimits;
 
     pub fn get_collector_from_ranges(
         ranges: Vec<RangeAggregationRange>,

src/aggregation/metric/percentiles.rs

@@ -1,6 +1,5 @@
 use std::fmt::Debug;
 
-use columnar::ColumnType;
 use serde::{Deserialize, Serialize};
 
 use super::*;

src/aggregation/metric/stats.rs

@@ -1,4 +1,3 @@
-use columnar::ColumnType;
 use serde::{Deserialize, Serialize};
 
 use super::*;

src/aggregation/mod.rs

@@ -417,7 +417,6 @@ mod tests {
     use time::OffsetDateTime;
 
     use super::agg_req::Aggregations;
-    use super::segment_agg_result::AggregationLimits;
     use super::*;
     use crate::indexer::NoMergePolicy;
     use crate::query::{AllQuery, TermQuery};

src/collector/histogram_collector.rs

@@ -160,7 +160,7 @@ mod tests {
     use super::{add_vecs, HistogramCollector, HistogramComputer};
     use crate::schema::{Schema, FAST};
     use crate::time::{Date, Month};
-    use crate::{doc, query, DateTime, Index};
+    use crate::{query, DateTime, Index};
 
     #[test]
     fn test_add_histograms_simple() {

src/collector/tests.rs

@@ -1,15 +1,11 @@
 use columnar::{BytesColumn, Column};
 
 use super::*;
-use crate::collector::{Count, FilterCollector, TopDocs};
-use crate::index::SegmentReader;
 use crate::query::{AllQuery, QueryParser};
 use crate::schema::{Schema, FAST, TEXT};
 use crate::time::format_description::well_known::Rfc3339;
 use crate::time::OffsetDateTime;
-use crate::{
-    doc, DateTime, DocAddress, DocId, Index, Score, Searcher, SegmentOrdinal, TantivyDocument,
-};
+use crate::{DateTime, DocAddress, Index, Searcher, TantivyDocument};
 
 pub const TEST_COLLECTOR_WITH_SCORE: TestCollector = TestCollector {
     compute_score: true,

src/directory/composite_file.rs

@@ -1,6 +1,5 @@
 use std::collections::HashMap;
 use std::io::{self, Read, Write};
-use std::iter::ExactSizeIterator;
 use std::ops::Range;
 
 use common::{BinarySerializable, CountingWriter, HasLen, VInt};

src/directory/directory.rs

@@ -1,5 +1,4 @@
 use std::io::Write;
-use std::marker::{Send, Sync};
 use std::path::{Path, PathBuf};
 use std::sync::Arc;
 use std::time::Duration;
@@ -40,6 +39,7 @@ impl RetryPolicy {
 /// The `DirectoryLock` is an object that represents a file lock.
 ///
 /// It is associated with a lock file, that gets deleted on `Drop.`
+#[allow(dead_code)]
 pub struct DirectoryLock(Box<dyn Send + Sync + 'static>);
 
 struct DirectoryLockGuard {

src/directory/tests.rs

@@ -1,6 +1,6 @@
 use std::io::Write;
 use std::mem;
-use std::path::{Path, PathBuf};
+use std::path::Path;
 use std::sync::atomic::Ordering::SeqCst;
 use std::sync::atomic::{AtomicBool, AtomicUsize};
 use std::sync::Arc;

src/directory/watch_event_router.rs

@@ -32,6 +32,7 @@ pub struct WatchCallbackList {
 /// file change is detected.
 #[must_use = "This `WatchHandle` controls the lifetime of the watch and should therefore be used."]
 #[derive(Clone)]
+#[allow(dead_code)]
 pub struct WatchHandle(Arc<WatchCallback>);
 
 impl WatchHandle {

src/fastfield/mod.rs

@@ -79,7 +79,7 @@ mod tests {
     use std::ops::{Range, RangeInclusive};
     use std::path::Path;
 
-    use columnar::{Column, MonotonicallyMappableToU64, StrColumn};
+    use columnar::StrColumn;
     use common::{ByteCount, HasLen, TerminatingWrite};
     use once_cell::sync::Lazy;
     use rand::prelude::SliceRandom;

src/index/segment_id.rs

@@ -1,4 +1,4 @@
-use std::cmp::{Ord, Ordering};
+use std::cmp::Ordering;
 use std::error::Error;
 use std::fmt;
 use std::str::FromStr;

src/index/segment_reader.rs

@@ -516,8 +516,8 @@ impl fmt::Debug for SegmentReader {
 mod test {
     use super::*;
     use crate::index::Index;
-    use crate::schema::{Schema, SchemaBuilder, Term, STORED, TEXT};
-    use crate::{DocId, IndexWriter};
+    use crate::schema::{SchemaBuilder, Term, STORED, TEXT};
+    use crate::IndexWriter;
 
     #[test]
     fn test_merge_field_meta_data_same() {

src/indexer/flat_map_with_buffer.rs

@@ -22,6 +22,7 @@ where
     }
 }
 
+#[allow(dead_code)]
 pub trait FlatMapWithBufferIter: Iterator {
     /// Function similar to `flat_map`, but allows reusing a shared `Vec`.
     fn flat_map_with_buffer<F, T>(self, fill_buffer: F) -> FlatMapWithBuffer<T, F, Self>

src/indexer/log_merge_policy.rs

@@ -145,7 +145,6 @@ mod tests {
 
     use super::*;
     use crate::index::SegmentMetaInventory;
-    use crate::indexer::merge_policy::MergePolicy;
     use crate::schema::INDEXED;
     use crate::{schema, SegmentId};
 

src/indexer/merge_policy.rs

@@ -39,7 +39,6 @@ impl MergePolicy for NoMergePolicy {
 pub mod tests {
 
     use super::*;
-    use crate::index::{SegmentId, SegmentMeta};
 
     /// `MergePolicy` useful for test purposes.
     ///

src/indexer/merger.rs

@@ -576,7 +576,7 @@ impl IndexMerger {
                     //
                     // Overall the reliable way to know if we have actual frequencies loaded or not
                     // is to check whether the actual decoded array is empty or not.
-                    if has_term_freq != !postings.block_cursor.freqs().is_empty() {
+                    if has_term_freq == postings.block_cursor.freqs().is_empty() {
                         return Err(DataCorruption::comment_only(
                             "Term freqs are inconsistent across segments",
                         )

src/postings/compression/mod.rs

@@ -14,7 +14,6 @@ pub fn compressed_block_size(num_bits: u8) -> usize {
 pub struct BlockEncoder {
     bitpacker: BitPacker4x,
     pub output: [u8; COMPRESSED_BLOCK_MAX_SIZE],
-    pub output_len: usize,
 }
 
 impl Default for BlockEncoder {
@@ -28,7 +27,6 @@ impl BlockEncoder {
         BlockEncoder {
             bitpacker: BitPacker4x::new(),
             output: [0u8; COMPRESSED_BLOCK_MAX_SIZE],
-            output_len: 0,
         }
     }
 

src/postings/skip.rs

@@ -1,5 +1,3 @@
-use std::convert::TryInto;
-
 use crate::directory::OwnedBytes;
 use crate::postings::compression::{compressed_block_size, COMPRESSION_BLOCK_SIZE};
 use crate::query::Bm25Weight;

src/postings/term_info.rs

@@ -1,5 +1,4 @@
 use std::io;
-use std::iter::ExactSizeIterator;
 use std::ops::Range;
 
 use common::{BinarySerializable, FixedSize};

src/query/exist_query.rs

@@ -149,7 +149,7 @@ mod tests {
     use crate::query::exist_query::ExistsQuery;
     use crate::query::{BooleanQuery, RangeQuery};
     use crate::schema::{Facet, FacetOptions, Schema, FAST, INDEXED, STRING, TEXT};
-    use crate::{doc, Index, Searcher};
+    use crate::{Index, Searcher};
 
     #[test]
     fn test_exists_query_simple() -> crate::Result<()> {

src/query/fuzzy_query.rs

@@ -84,7 +84,7 @@ pub struct FuzzyTermQuery {
     distance: u8,
     /// Should a transposition cost 1 or 2?
     transposition_cost_one: bool,
-    ///
+    /// is a starts with query
     prefix: bool,
 }
 

src/query/range_query/range_query.rs

@@ -477,7 +477,7 @@ mod tests {
     use crate::schema::{
         Field, IntoIpv6Addr, Schema, TantivyDocument, FAST, INDEXED, STORED, TEXT,
     };
-    use crate::{doc, Index, IndexWriter};
+    use crate::{Index, IndexWriter};
 
     #[test]
     fn test_range_query_simple() -> crate::Result<()> {

src/query/term_query/term_query.rs

@@ -139,7 +139,7 @@ mod tests {
     use crate::collector::{Count, TopDocs};
     use crate::query::{Query, QueryParser, TermQuery};
     use crate::schema::{IndexRecordOption, IntoIpv6Addr, Schema, INDEXED, STORED};
-    use crate::{doc, Index, IndexWriter, Term};
+    use crate::{Index, IndexWriter, Term};
 
     #[test]
     fn search_ip_test() {

src/query/vec_docset.rs

@@ -53,8 +53,7 @@ impl HasLen for VecDocSet {
 pub mod tests {
 
     use super::*;
-    use crate::docset::{DocSet, COLLECT_BLOCK_BUFFER_LEN};
-    use crate::DocId;
+    use crate::docset::COLLECT_BLOCK_BUFFER_LEN;
 
     #[test]
     pub fn test_vec_postings() {

src/schema/document/de.rs

@@ -819,7 +819,6 @@ mod tests {
     use crate::schema::document::existing_type_impls::JsonObjectIter;
     use crate::schema::document::se::BinaryValueSerializer;
     use crate::schema::document::{ReferenceValue, ReferenceValueLeaf};
-    use crate::schema::OwnedValue;
 
     fn serialize_value<'a>(value: ReferenceValue<'a, &'a serde_json::Value>) -> Vec<u8> {
         let mut writer = Vec::new();

src/schema/document/default_document.rs

@@ -256,7 +256,6 @@ impl DocParsingError {
 
 #[cfg(test)]
 mod tests {
-    use crate::schema::document::default_document::TantivyDocument;
     use crate::schema::*;
 
     #[test]

src/schema/document/owned_value.rs

@@ -443,9 +443,7 @@ impl<'a> Iterator for ObjectMapIter<'a> {
 mod tests {
     use super::*;
     use crate::schema::{BytesOptions, Schema};
-    use crate::time::format_description::well_known::Rfc3339;
-    use crate::time::OffsetDateTime;
-    use crate::{DateTime, Document, TantivyDocument};
+    use crate::{Document, TantivyDocument};
 
     #[test]
     fn test_parse_bytes_doc() {

src/schema/field_entry.rs

@@ -136,7 +136,6 @@ impl FieldEntry {
 
 #[cfg(test)]
 mod tests {
-    use serde_json;
 
     use super::*;
     use crate::schema::{Schema, TextFieldIndexing, TEXT};

src/schema/schema.rs

@@ -6,10 +6,8 @@ use serde::de::{SeqAccess, Visitor};
 use serde::ser::SerializeSeq;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
 
-use super::ip_options::IpAddrOptions;
 use super::*;
 use crate::json_utils::split_json_path;
-use crate::schema::bytes_options::BytesOptions;
 use crate::TantivyError;
 
 /// Tantivy has a very strict schema.
@@ -421,9 +419,7 @@ mod tests {
 
     use matches::{assert_matches, matches};
     use pretty_assertions::assert_eq;
-    use serde_json;
 
-    use crate::schema::document::Value;
     use crate::schema::field_type::ValueParsingError;
     use crate::schema::schema::DocParsingError::InvalidJson;
     use crate::schema::*;

src/schema/term.rs

@@ -1,4 +1,3 @@
-use std::convert::TryInto;
 use std::hash::{Hash, Hasher};
 use std::net::Ipv6Addr;
 use std::{fmt, str};

src/store/compression_lz4_block.rs

@@ -1,4 +1,3 @@
-use core::convert::TryInto;
 use std::io::{self};
 use std::mem;
 

src/store/compressors.rs

@@ -2,12 +2,6 @@ use std::io;
 
 use serde::{Deserialize, Deserializer, Serialize};
 
-pub trait StoreCompressor {
-    fn compress(&self, uncompressed: &[u8], compressed: &mut Vec<u8>) -> io::Result<()>;
-    fn decompress(&self, compressed: &[u8], decompressed: &mut Vec<u8>) -> io::Result<()>;
-    fn get_compressor_id() -> u8;
-}
-
 /// Compressor can be used on `IndexSettings` to choose
 /// the compressor used to compress the doc store.
 ///