switched to memmap2-rs

move rand to optional dependencies

Cargo.toml

@@ -19,7 +19,7 @@ crc32fast = "1.2.1"
 once_cell = "1.7.2"
 regex ={ version = "1.5.4", default-features = false, features = ["std"] }
 tantivy-fst = "0.3"
-memmap = {version = "0.7", optional=true}
+memmap2 = {version = "0.3", optional=true}
 lz4_flex = { version = "0.8.0", default-features = false, features = ["checked-decode"], optional = true }
 brotli = { version = "3.3", optional = true }
 snap = { version = "1.0.5", optional = true }
@@ -81,7 +81,7 @@ overflow-checks = true
 
 [features]
 default = ["mmap", "lz4-compression" ]
-mmap = ["fs2", "tempfile", "memmap"]
+mmap = ["fs2", "tempfile", "memmap2"]
 
 brotli-compression = ["brotli"]
 lz4-compression = ["lz4_flex"]

fastfield_codecs/Cargo.toml

@@ -12,14 +12,13 @@ description = "Fast field codecs used by tantivy"
 common = { path = "../common/" }
 tantivy-bitpacker = { path = "../bitpacker/" }
 prettytable-rs = {version="0.8.0", optional= true}
-#prettytable-rs = {version="0.8.0" }
-rand = "0.8.3"
+rand = {version="0.8.3", optional= true}
 
 [dev-dependencies]
 more-asserts = "0.2.1"
 rand = "0.8.3"
 
 [features]
-bin = ["prettytable-rs"]
+bin = ["prettytable-rs", "rand"]
 default = ["bin"]
 

fastfield_codecs/src/multilinearinterpol.rs

@@ -1,3 +1,17 @@
+/*!
+
+MultiLinearInterpol compressor uses linear interpolation to guess a values and stores the offset, but in blocks of 512.
+
+With a CHUNK_SIZE of 512 and 29 byte metadata per block, we get a overhead for metadata of 232 / 512 = 0,45 bits per element.
+The additional space required per element in a block is the the maximum deviation of the linear interpolation estimation function.
+
+E.g. if the maximum deviation of an element is 12, all elements cost 4bits.
+
+Size per block:
+Num Elements * Maximum Deviation from Interpolation + 29 Byte Metadata
+
+*/
+
 use crate::FastFieldCodecReader;
 use crate::FastFieldCodecSerializer;
 use crate::FastFieldDataAccess;

src/collector/filter_collector_wrapper.rs

@@ -16,7 +16,7 @@ use crate::fastfield::{DynamicFastFieldReader, FastFieldReader, FastValue};
 use crate::schema::Field;
 use crate::{Score, SegmentReader, TantivyError};
 
-/// The `FilterCollector` collector filters docs using a u64 fast field value and a predicate.
+/// The `FilterCollector` collector filters docs using a fast field value and a predicate.
 /// Only the documents for which the predicate returned "true" will be passed on to the next collector.
 ///
 /// ```rust

src/core/segment_reader.rs

@@ -31,9 +31,6 @@ use std::{collections::HashMap, io};
 ///
 /// The segment reader has a very low memory footprint,
 /// as close to all of the memory data is mmapped.
-///
-///
-/// TODO fix not decoding docfreq
 #[derive(Clone)]
 pub struct SegmentReader {
     inv_idx_reader_cache: Arc<RwLock<HashMap<Field, Arc<InvertedIndexReader>>>>,
@@ -56,15 +53,12 @@ pub struct SegmentReader {
 impl SegmentReader {
     /// Returns the highest document id ever attributed in
     /// this segment + 1.
-    /// Today, `tantivy` does not handle deletes, so it happens
-    /// to also be the number of documents in the index.
     pub fn max_doc(&self) -> DocId {
         self.max_doc
     }
 
     /// Returns the number of alive documents.
     /// Deleted documents are not counted.
-    ///
     pub fn num_docs(&self) -> DocId {
         self.num_docs
     }

src/directory/mmap_directory.rs

@@ -11,7 +11,7 @@ use crate::directory::{AntiCallToken, FileHandle, OwnedBytes};
 use crate::directory::{ArcBytes, WeakArcBytes};
 use crate::directory::{TerminatingWrite, WritePtr};
 use fs2::FileExt;
-use memmap::Mmap;
+use memmap2::Mmap;
 use serde::{Deserialize, Serialize};
 use stable_deref_trait::StableDeref;
 use std::convert::From;
@@ -53,7 +53,7 @@ fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
         return Ok(None);
     }
     unsafe {
-        memmap::Mmap::map(&file)
+        memmap2::Mmap::map(&file)
             .map(Some)
             .map_err(|io_err| OpenReadError::wrap_io_error(io_err, full_path.to_path_buf()))
     }