Merge #465

465: Update dependencies r=ManyTheFish a=Kerollmops

This PR upgrade and updates this crate's dependencies but first, it removes three dependencies that we don't use anymore. I used [cargo udeps](https://github.com/est31/cargo-udeps) to upgrade them ⬆️

Co-authored-by: Kerollmops <clement@meilisearch.com>
Co-authored-by: Clément Renault <clement@meilisearch.com>

benchmarks/Cargo.toml

@@ -6,8 +6,8 @@ publish = false
 
 [dependencies]
 milli = { path = "../milli" }
-anyhow = "1.0"
-serde_json = { version = "1.0.62", features = ["preserve_order"] }
+anyhow = "1.0.56"
+serde_json = { version = "1.0.79", features = ["preserve_order"] }
 csv = "1.1.6"
 
 [target.'cfg(target_os = "linux")'.dependencies]
@@ -15,14 +15,14 @@ jemallocator = "0.3.2"
 
 [dev-dependencies]
 heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.1" }
-criterion = { version = "0.3.4", features = ["html_reports"] }
+criterion = { version = "0.3.5", features = ["html_reports"] }
 
 [build-dependencies]
-anyhow = "1.0"
-bytes = "1.0"
-flate2 = "1.0.20"
-convert_case = "0.4"
-reqwest = { version = "0.11.3", features = ["blocking", "rustls-tls"], default-features = false }
+anyhow = "1.0.56"
+bytes = "1.1.0"
+flate2 = "1.0.22"
+convert_case = "0.5.0"
+reqwest = { version = "0.11.9", features = ["blocking", "rustls-tls"], default-features = false }
 
 [[bench]]
 name = "search_songs"

cli/Cargo.toml

@@ -8,15 +8,15 @@ description = "A CLI to interact with a milli index"
 
 [dependencies]
 indicatif = "0.16.2"
-serde = "1.0.129"
-serde_json = "1.0.66"
-structopt = "0.3.22"
+serde = "1.0.136"
+serde_json = "1.0.79"
+structopt = "0.3.26"
 milli = { path = "../milli" }
-eyre = "0.6.5"
-color-eyre = "0.5.11"
+eyre = "0.6.7"
+color-eyre = "0.6.1"
 heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.1", default-features = false, features = ["lmdb", "sync-read-txn"] }
-byte-unit = { version = "4.0.12", features = ["serde"] }
-bimap = "0.6.1"
+byte-unit = { version = "4.0.14", features = ["serde"] }
+bimap = "0.6.2"
 csv = "1.1.6"
 stderrlog = "0.5.1"
 

filter-parser/Cargo.toml

@@ -6,5 +6,5 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-nom = "7.0.0"
+nom = "7.1.0"
 nom_locate = "4.0.0"

helpers/Cargo.toml

@@ -5,12 +5,12 @@ authors = ["Clément Renault <clement@meilisearch.com>"]
 edition = "2018"
 
 [dependencies]
-anyhow = "1.0.38"
-byte-unit = { version = "4.0.9", default-features = false, features = ["std"] }
+anyhow = "1.0.56"
+byte-unit = { version = "4.0.14", default-features = false, features = ["std"] }
 heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.1" }
 milli = { path = "../milli" }
 stderrlog = "0.5.1"
-structopt = { version = "0.3.21", default-features = false }
+structopt = { version = "0.3.26", default-features = false }
 
 [target.'cfg(target_os = "linux")'.dependencies]
 jemallocator = "0.3.2"

http-ui/Cargo.toml

@@ -6,43 +6,43 @@ authors = ["Clément Renault <clement@meilisearch.com>"]
 edition = "2018"
 
 [dependencies]
-anyhow = "1.0.38"
-byte-unit = { version = "4.0.9", default-features = false, features = ["std"] }
-crossbeam-channel = "0.5.0"
+anyhow = "1.0.56"
+byte-unit = { version = "4.0.14", default-features = false, features = ["std"] }
+crossbeam-channel = "0.5.2"
 heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.1" }
-meilisearch-tokenizer = { git = "https://github.com/meilisearch/tokenizer.git", tag = "v0.2.7" }
-memmap2 = "0.5.0"
+memmap2 = "0.5.3"
 milli = { path = "../milli" }
-once_cell = "1.5.2"
-rayon = "1.5.0"
-structopt = { version = "0.3.21", default-features = false, features = ["wrap_help"] }
-tempfile = "3.2.0"
+once_cell = "1.10.0"
+rayon = "1.5.1"
+structopt = { version = "0.3.26", default-features = false, features = ["wrap_help"] }
+tempfile = "3.3.0"
 
 # http server
-askama = "0.10.5"
-askama_warp = "0.10.0"
-bytes = "0.5.6"
+askama = "0.11.1"
+askama_warp = "0.12.0"
+bytes = "1.1.0"
 either = "1.6.1"
-flate2 = "1.0.20"
-futures = "0.3.12"
-serde = { version = "1.0.123", features = ["derive"] }
-serde_json = { version = "1.0.62", features = ["preserve_order"] }
-tokio = { version = "0.2.25", features = ["full"] }
-warp = "0.2.5"
+flate2 = "1.0.22"
+futures = "0.3.21"
+serde = { version = "1.0.136", features = ["derive"] }
+serde_json = { version = "1.0.79", features = ["preserve_order"] }
+tokio = { version = "1.17.0", features = ["full"] }
+tokio-stream = { version = "0.1.8", default-features = false, features = ["sync"] }
+warp = "0.3.2"
 
 # logging
 log = "0.4.14"
 stderrlog = "0.5.1"
-fst = "0.4.5"
+fst = "0.4.7"
 
 # Temporary fix for bitvec, remove once fixed. (https://github.com/bitvecto-rs/bitvec/issues/105)
-funty = "=1.1"
-bimap = "0.6.1"
+funty = "2.0.0"
+bimap = "0.6.2"
 csv = "1.1.6"
 
 [dev-dependencies]
 maplit = "1.0.2"
-serde_test = "1.0.125"
+serde_test = "1.0.136"
 
 [target.'cfg(target_os = "linux")'.dependencies]
 jemallocator = "0.3.2"

http-ui/src/main.rs

@@ -3,7 +3,7 @@ mod update_store;
 use std::collections::{BTreeMap, BTreeSet, HashMap, HashSet};
 use std::fmt::Display;
 use std::fs::{create_dir_all, File};
-use std::io::{BufRead, BufReader, Cursor};
+use std::io::{BufRead, BufReader, Cursor, Read};
 use std::net::SocketAddr;
 use std::num::{NonZeroU32, NonZeroUsize};
 use std::path::PathBuf;
@@ -18,8 +18,8 @@ use either::Either;
 use flate2::read::GzDecoder;
 use futures::{stream, FutureExt, StreamExt};
 use heed::EnvOpenOptions;
-use meilisearch_tokenizer::{Analyzer, AnalyzerConfig};
 use milli::documents::DocumentBatchReader;
+use milli::tokenizer::{Analyzer, AnalyzerConfig};
 use milli::update::UpdateIndexingStep::*;
 use milli::update::{
     ClearDocuments, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Setting,
@@ -35,6 +35,7 @@ use structopt::StructOpt;
 use tokio::fs::File as TFile;
 use tokio::io::AsyncWriteExt;
 use tokio::sync::broadcast;
+use tokio_stream::wrappers::BroadcastStream;
 use warp::filters::ws::Message;
 use warp::http::Response;
 use warp::Filter;
@@ -885,7 +886,8 @@ async fn main() -> anyhow::Result<()> {
         let mut file = TFile::from_std(file);
 
         while let Some(result) = stream.next().await {
-            let bytes = result.unwrap().to_bytes();
+            let mut bytes = Vec::new();
+            result.unwrap().reader().read_to_end(&mut bytes).unwrap();
             file.write_all(&bytes[..]).await.unwrap();
         }
 
@@ -1004,8 +1006,7 @@ async fn main() -> anyhow::Result<()> {
             let update_status_receiver = update_status_sender.subscribe();
             ws.on_upgrade(|websocket| {
                 // Just echo all updates messages...
-                update_status_receiver
-                    .into_stream()
+                BroadcastStream::new(update_status_receiver)
                     .flat_map(|result| match result {
                         Ok(status) => {
                             let msg = serde_json::to_string(&status).unwrap();

infos/Cargo.toml

@@ -5,15 +5,15 @@ authors = ["Clément Renault <clement@meilisearch.com>"]
 edition = "2018"
 
 [dependencies]
-anyhow = "1.0.38"
-byte-unit = { version = "4.0.9", default-features = false, features = ["std"] }
-csv = "1.1.5"
+anyhow = "1.0.56"
+byte-unit = { version = "4.0.14", default-features = false, features = ["std"] }
+csv = "1.1.6"
 heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.1" }
 milli = { path = "../milli" }
-roaring = "0.6.6"
-serde_json = "1.0.62"
+roaring = "0.9.0"
+serde_json = "1.0.79"
 stderrlog = "0.5.1"
-structopt = { version = "0.3.21", default-features = false }
+structopt = { version = "0.3.26", default-features = false }
 
 [target.'cfg(target_os = "linux")'.dependencies]
 jemallocator = "0.3.2"

milli/Cargo.toml

@@ -5,53 +5,50 @@ authors = ["Kerollmops <clement@meilisearch.com>"]
 edition = "2018"
 
 [dependencies]
-bimap = { version = "0.6.1", features = ["serde"] }
+bimap = { version = "0.6.2", features = ["serde"] }
 bincode = "1.3.3"
-bstr = "0.2.15"
-byteorder = "1.4.2"
+bstr = "0.2.17"
+byteorder = "1.4.3"
 concat-arrays = "0.1.2"
-crossbeam-channel = "0.5.1"
+crossbeam-channel = "0.5.2"
 either = "1.6.1"
-flate2 = "1.0.20"
-fst = "0.4.5"
+fst = "0.4.7"
 fxhash = "0.2.1"
 grenad = { version = "0.4.1", default-features = false, features = ["tempfile"] }
 geoutils = "0.4.1"
 heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.1", default-features = false, features = ["lmdb", "sync-read-txn"] }
-human_format = "1.0.3"
-levenshtein_automata = { version = "0.2.0", features = ["fst_automaton"] }
-linked-hash-map = "0.5.4"
-meilisearch-tokenizer = { git = "https://github.com/meilisearch/tokenizer.git", tag = "v0.2.7" }
-memmap2 = "0.5.0"
+levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
+meilisearch-tokenizer = { git = "https://github.com/meilisearch/tokenizer.git", tag = "v0.2.8" }
+memmap2 = "0.5.3"
 obkv = "0.2.0"
-once_cell = "1.5.2"
-ordered-float = "2.1.1"
-rayon = "1.5.0"
-roaring = "0.6.6"
-rstar = { version = "0.9.1", features = ["serde"] }
-serde = { version = "1.0.123", features = ["derive"] }
-serde_json = { version = "1.0.62", features = ["preserve_order"] }
-slice-group-by = "0.2.6"
-smallstr =  { version = "0.2.0", features = ["serde"] }
-smallvec = "1.6.1"
-tempfile = "3.2.0"
+once_cell = "1.10.0"
+ordered-float = "2.10.0"
+rayon = "1.5.1"
+roaring = "0.9.0"
+rstar = { version = "0.9.2", features = ["serde"] }
+serde = { version = "1.0.136", features = ["derive"] }
+serde_json = { version = "1.0.79", features = ["preserve_order"] }
+slice-group-by = "0.3.0"
+smallstr =  { version = "0.3.0", features = ["serde"] }
+smallvec = "1.8.0"
+tempfile = "3.3.0"
 time = { version = "0.3.7", features = ["serde-well-known", "formatting", "parsing", "macros"] }
 uuid = { version = "0.8.2", features = ["v4"] }
 
 filter-parser = { path = "../filter-parser" }
 
 # documents words self-join
-itertools = "0.10.0"
+itertools = "0.10.3"
 
 # logging
 log = "0.4.14"
-logging_timer = "1.0.0"
+logging_timer = "1.1.0"
 csv = "1.1.6"
 
 [dev-dependencies]
 big_s = "1.0.2"
 maplit = "1.0.2"
-rand = "0.8.3"
+rand = "0.8.5"
 
 [features]
 default = []

milli/src/heed_codec/roaring_bitmap/cbo_roaring_bitmap_codec.rs

@@ -82,7 +82,8 @@ impl CboRoaringBitmapCodec {
                     buffer.extend_from_slice(&integer.to_ne_bytes());
                 }
             } else {
-                let roaring = RoaringBitmap::from_sorted_iter(vec.into_iter());
+                // We can unwrap safely because the vector is sorted upper.
+                let roaring = RoaringBitmap::from_sorted_iter(vec.into_iter()).unwrap();
                 roaring.serialize_into(buffer)?;
             }
         } else {
@@ -152,25 +153,25 @@ mod tests {
         let mut buffer = Vec::new();
 
         let small_data = vec![
-            RoaringBitmap::from_sorted_iter(1..4),
-            RoaringBitmap::from_sorted_iter(2..5),
-            RoaringBitmap::from_sorted_iter(4..6),
-            RoaringBitmap::from_sorted_iter(1..3),
+            RoaringBitmap::from_sorted_iter(1..4).unwrap(),
+            RoaringBitmap::from_sorted_iter(2..5).unwrap(),
+            RoaringBitmap::from_sorted_iter(4..6).unwrap(),
+            RoaringBitmap::from_sorted_iter(1..3).unwrap(),
         ];
 
         let small_data: Vec<_> =
             small_data.iter().map(|b| CboRoaringBitmapCodec::bytes_encode(b).unwrap()).collect();
         CboRoaringBitmapCodec::merge_into(small_data.as_slice(), &mut buffer).unwrap();
         let bitmap = CboRoaringBitmapCodec::deserialize_from(&buffer).unwrap();
-        let expected = RoaringBitmap::from_sorted_iter(1..6);
+        let expected = RoaringBitmap::from_sorted_iter(1..6).unwrap();
         assert_eq!(bitmap, expected);
 
         let medium_data = vec![
-            RoaringBitmap::from_sorted_iter(1..4),
-            RoaringBitmap::from_sorted_iter(2..5),
-            RoaringBitmap::from_sorted_iter(4..8),
-            RoaringBitmap::from_sorted_iter(0..3),
-            RoaringBitmap::from_sorted_iter(7..23),
+            RoaringBitmap::from_sorted_iter(1..4).unwrap(),
+            RoaringBitmap::from_sorted_iter(2..5).unwrap(),
+            RoaringBitmap::from_sorted_iter(4..8).unwrap(),
+            RoaringBitmap::from_sorted_iter(0..3).unwrap(),
+            RoaringBitmap::from_sorted_iter(7..23).unwrap(),
         ];
 
         let medium_data: Vec<_> =
@@ -179,7 +180,7 @@ mod tests {
         CboRoaringBitmapCodec::merge_into(medium_data.as_slice(), &mut buffer).unwrap();
 
         let bitmap = CboRoaringBitmapCodec::deserialize_from(&buffer).unwrap();
-        let expected = RoaringBitmap::from_sorted_iter(0..23);
+        let expected = RoaringBitmap::from_sorted_iter(0..23).unwrap();
         assert_eq!(bitmap, expected);
     }
 }

milli/src/search/criteria/mod.rs

@@ -498,6 +498,7 @@ fn query_pair_proximity_docids(
 #[cfg(test)]
 pub mod test {
     use std::collections::HashMap;
+    use std::iter;
 
     use maplit::hashmap;
     use rand::rngs::StdRng;
@@ -567,7 +568,8 @@ pub mod test {
                     .iter()
                     .enumerate()
                     .map(|(i, w)| {
-                        (w.clone(), RoaringBitmap::from_sorted_iter(std::iter::once(i as u32)))
+                        let bitmap = RoaringBitmap::from_sorted_iter(iter::once(i as u32)).unwrap();
+                        (w.clone(), bitmap)
                     })
                     .collect())
             } else {
@@ -622,7 +624,7 @@ pub mod test {
                 }
                 values.sort_unstable();
 
-                RoaringBitmap::from_sorted_iter(values.into_iter())
+                RoaringBitmap::from_sorted_iter(values.into_iter()).unwrap()
             }
 
             let word_docids = hashmap! {

milli/src/search/query_tree.rs

@@ -587,8 +587,7 @@ mod test {
                     values.push(rng.gen());
                 }
                 values.sort_unstable();
-
-                RoaringBitmap::from_sorted_iter(values.into_iter())
+                RoaringBitmap::from_sorted_iter(values.into_iter()).unwrap()
             }
 
             TestContext {

milli/src/update/delete_documents.rs

@@ -186,7 +186,7 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
 
         // We create the FST map of the external ids that we must delete.
         external_ids.sort_unstable();
-        let external_ids_to_delete = fst::Set::from_iter(external_ids.iter().map(AsRef::as_ref))?;
+        let external_ids_to_delete = fst::Set::from_iter(external_ids)?;
 
         // We acquire the current external documents ids map...
         let mut new_external_documents_ids = self.index.external_documents_ids(self.wtxn)?;
@@ -209,7 +209,7 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
             // the LMDB B-Tree two times but only once.
             let mut iter = word_docids.prefix_iter_mut(self.wtxn, &word)?;
             if let Some((key, mut docids)) = iter.next().transpose()? {
-                if key == word.as_ref() {
+                if key == word.as_str() {
                     let previous_len = docids.len();
                     docids -= &self.documents_ids;
                     if docids.is_empty() {
@@ -230,7 +230,7 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
             words.iter().filter_map(
                 |(word, must_remove)| {
                     if *must_remove {
-                        Some(word.as_ref())
+                        Some(word.as_str())
                     } else {
                         None
                     }