Merge pull request #1405 from nextstrain/chore/upgrade-rust

.cargo/config.toml

@@ -182,7 +182,10 @@ rustflags = [
   "-Wclippy::zero_sized_map_values",
   #
   # Disable some of the clippy lints
+  "-Aclippy::absolute_paths",
+  "-Aclippy::allow_attributes",
   "-Aclippy::arithmetic-side-effects",
+  "-Aclippy::arithmetic_side_effects",
   "-Aclippy::as_conversions",
   "-Aclippy::assign_op_pattern",
   "-Aclippy::bool-to-int-with-if",
@@ -207,13 +210,14 @@ rustflags = [
   "-Aclippy::implicit_return",
   "-Aclippy::inconsistent_digit_grouping",
   "-Aclippy::indexing_slicing",
-  "-Aclippy::integer_arithmetic",
   "-Aclippy::integer_division",
   "-Aclippy::iter_nth_zero",
   "-Aclippy::large_digit_groups",
+  "-Aclippy::len_zero",
   "-Aclippy::let_underscore_must_use",
   "-Aclippy::manual-string-new",
   "-Aclippy::match_same_arms",
+  "-Aclippy::min_ident_chars",
   "-Aclippy::missing-assert-message",
   "-Aclippy::missing_docs_in_private_items",
   "-Aclippy::missing_errors_doc",
@@ -226,6 +230,8 @@ rustflags = [
   "-Aclippy::modulo_arithmetic",
   "-Aclippy::must_use_candidate",
   "-Aclippy::needless_for_each",
+  "-Aclippy::needless_raw_string_hashes",
+  "-Aclippy::needless_raw_strings",
   "-Aclippy::new_without_default",
   "-Aclippy::non_ascii_literal",
   "-Aclippy::option_if_let_else",
@@ -245,9 +251,11 @@ rustflags = [
   "-Aclippy::shadow_unrelated",
   "-Aclippy::should_implement_trait",
   "-Aclippy::similar_names",
+  "-Aclippy::single_call_fn",
   "-Aclippy::single_char_lifetime_names",
   "-Aclippy::std-instead-of-alloc",
   "-Aclippy::std_instead_of_core",
+  "-Aclippy::struct_field_names",
   "-Aclippy::suboptimal_flops",
   "-Aclippy::too_many_arguments",
   "-Aclippy::too_many_lines",

clippy.toml

@@ -1,2 +1,5 @@
+allow-dbg-in-tests = true
+allow-expect-in-tests = true
+allow-unwrap-in-tests = true
 avoid-breaking-exported-api = false
 cognitive-complexity-threshold = 30

packages/nextclade-cli/src/cli/nextclade_dataset_get.rs

@@ -27,20 +27,19 @@ pub fn nextclade_dataset_get(
 ) -> Result<(), Report> {
   let verbose = log::max_level() > LevelFilter::Info;
 
-  let mut http = HttpClient::new(server, proxy_config, verbose)?;
-  let dataset = dataset_http_get(&mut http, name, tag)?;
+  let http = HttpClient::new(server, proxy_config, verbose)?;
+  let dataset = dataset_http_get(&http, name, tag)?;
 
   if let Some(output_dir) = &output_dir {
-    dataset_dir_download(&mut http, &dataset, output_dir)?;
+    dataset_dir_download(&http, &dataset, output_dir)?;
   } else if let Some(output_zip) = &output_zip {
-    dataset_zip_download(&mut http, &dataset, output_zip)?;
-  } else {
+    dataset_zip_download(&http, &dataset, output_zip)?;
   }
 
   Ok(())
 }
 
-pub fn dataset_http_get(http: &mut HttpClient, name: impl AsRef<str>, tag: &Option<String>) -> Result<Dataset, Report> {
+pub fn dataset_http_get(http: &HttpClient, name: impl AsRef<str>, tag: &Option<String>) -> Result<Dataset, Report> {
   let name = name.as_ref();
   let tag = tag.as_ref();
 
@@ -100,7 +99,7 @@ pub fn dataset_http_get(http: &mut HttpClient, name: impl AsRef<str>, tag: &Opti
 }
 
 pub fn dataset_file_http_get(
-  http: &mut HttpClient,
+  http: &HttpClient,
   dataset: &Dataset,
   filename: impl AsRef<str>,
 ) -> Result<String, Report> {

packages/nextclade-cli/src/cli/nextclade_dataset_list.rs

@@ -27,8 +27,8 @@ pub fn nextclade_dataset_list(
 ) -> Result<(), Report> {
   let verbose = log::max_level() > LevelFilter::Info;
 
-  let mut http = HttpClient::new(&server, &proxy_config, verbose)?;
-  let DatasetsIndexJson { collections, .. } = download_datasets_index_json(&mut http)?;
+  let http = HttpClient::new(&server, &proxy_config, verbose)?;
+  let DatasetsIndexJson { collections, .. } = download_datasets_index_json(&http)?;
 
   let filtered = collections
     .into_iter()

packages/nextclade-cli/src/cli/nextclade_seq_sort.rs

@@ -39,8 +39,8 @@ pub fn nextclade_seq_sort(args: &NextcladeSortArgs) -> Result<(), Report> {
     MinimizerIndexJson::from_path(input_minimizer_index_json)
   } else {
     // Otherwise fetch from dataset server
-    let mut http = HttpClient::new(server, proxy_config, verbose)?;
-    let index = download_datasets_index_json(&mut http)?;
+    let http = HttpClient::new(server, proxy_config, verbose)?;
+    let index = download_datasets_index_json(&http)?;
     let minimizer_index_path = index
       .minimizer_index
       .iter()

packages/nextclade-cli/src/dataset/dataset_download.rs

@@ -17,7 +17,7 @@ use nextclade::{make_error, make_internal_error, o};
 use rayon::iter::ParallelIterator;
 use std::collections::BTreeMap;
 use std::fs::File;
-use std::io::{BufReader, Read, Seek, Write};
+use std::io::{BufReader, Cursor, Read, Seek, Write};
 use std::path::{Path, PathBuf};
 use std::str::FromStr;
 use zip::ZipArchive;
@@ -50,19 +50,19 @@ pub fn nextclade_get_inputs(
 }
 
 #[inline]
-pub fn download_datasets_index_json(http: &mut HttpClient) -> Result<DatasetsIndexJson, Report> {
+pub fn download_datasets_index_json(http: &HttpClient) -> Result<DatasetsIndexJson, Report> {
   let data_bytes = http.get("/index.json")?;
   let data_str = String::from_utf8(data_bytes)?;
   DatasetsIndexJson::from_str(data_str)
 }
 
-pub fn dataset_zip_fetch(http: &mut HttpClient, dataset: &Dataset) -> Result<Vec<u8>, Report> {
+pub fn dataset_zip_fetch(http: &HttpClient, dataset: &Dataset) -> Result<Vec<u8>, Report> {
   http
     .get(&dataset.file_path("dataset.zip"))
     .wrap_err_with(|| format!("When fetching zip file for dataset '{}'", dataset.path))
 }
 
-pub fn dataset_zip_download(http: &mut HttpClient, dataset: &Dataset, output_file_path: &Path) -> Result<(), Report> {
+pub fn dataset_zip_download(http: &HttpClient, dataset: &Dataset, output_file_path: &Path) -> Result<(), Report> {
   let mut file =
     create_file_or_stdout(output_file_path).wrap_err_with(|| format!("When opening file {output_file_path:?}"))?;
 
@@ -127,9 +127,9 @@ pub fn dataset_zip_load(
   })
 }
 
-pub fn dataset_dir_download(http: &mut HttpClient, dataset: &Dataset, output_dir: &Path) -> Result<(), Report> {
+pub fn dataset_dir_download(http: &HttpClient, dataset: &Dataset, output_dir: &Path) -> Result<(), Report> {
   let mut content = dataset_zip_fetch(http, dataset)?;
-  let mut reader = std::io::Cursor::new(content.as_mut_slice());
+  let mut reader = Cursor::new(content.as_mut_slice());
   let mut zip = ZipArchive::new(&mut reader)?;
 
   ensure_dir(output_dir).wrap_err_with(|| format!("When creating directory {output_dir:#?}"))?;
@@ -278,6 +278,7 @@ pub fn dataset_individual_files_load(
   }
 }
 
+#[allow(clippy::struct_field_names)]
 pub struct DatasetFilePaths<'a> {
   input_ref: &'a Path,
   input_tree: &'a Option<PathBuf>,
@@ -286,7 +287,7 @@ pub struct DatasetFilePaths<'a> {
 }
 
 pub fn read_from_path_or_url(
-  http: &mut HttpClient,
+  http: &HttpClient,
   dataset: &Dataset,
   filepath: &Option<impl AsRef<Path>>,
   url: &Option<String>,
@@ -304,18 +305,18 @@ pub fn dataset_str_download_and_load(
   cdses: &Option<Vec<String>>,
 ) -> Result<NextcladeParams, Report> {
   let verbose = log::max_level() > LevelFilter::Info;
-  let mut http = HttpClient::new(&run_args.inputs.server, &ProxyConfig::default(), verbose)?;
+  let http = HttpClient::new(&run_args.inputs.server, &ProxyConfig::default(), verbose)?;
 
   let name = run_args
     .inputs
     .dataset_name
     .as_ref()
     .expect("Dataset name is expected, but got 'None'");
 
-  let dataset = dataset_http_get(&mut http, name, &None)?;
+  let dataset = dataset_http_get(&http, name, &None)?;
 
   let virus_properties = read_from_path_or_url(
-    &mut http,
+    &http,
     &dataset,
     &run_args.inputs.input_pathogen_json,
     &Some(o!("pathogen.json")),
@@ -325,7 +326,7 @@ pub fn dataset_str_download_and_load(
   .ok_or_else(|| eyre!("Required file not found in dataset: 'pathogen.json'. Please report it to dataset authors."))?;
 
   let ref_record = read_from_path_or_url(
-    &mut http,
+    &http,
     &dataset,
     &run_args.inputs.input_ref,
     &Some(dataset.files.reference.clone()),
@@ -334,7 +335,7 @@ pub fn dataset_str_download_and_load(
   .wrap_err("When reading reference sequence from dataset")?;
 
   let gene_map = read_from_path_or_url(
-    &mut http,
+    &http,
     &dataset,
     &run_args.inputs.input_annotation,
     &dataset.files.genome_annotation,
@@ -344,14 +345,9 @@ pub fn dataset_str_download_and_load(
   .map(|gene_map| filter_gene_map(gene_map, cdses))
   .unwrap_or_default();
 
-  let tree = read_from_path_or_url(
-    &mut http,
-    &dataset,
-    &run_args.inputs.input_tree,
-    &dataset.files.tree_json,
-  )?
-  .map_ref_fallible(AuspiceTree::from_str)
-  .wrap_err("When reading reference tree from dataset")?;
+  let tree = read_from_path_or_url(&http, &dataset, &run_args.inputs.input_tree, &dataset.files.tree_json)?
+    .map_ref_fallible(AuspiceTree::from_str)
+    .wrap_err("When reading reference tree from dataset")?;
 
   Ok(NextcladeParams {
     ref_record,

packages/nextclade-cli/src/dataset/dataset_table.rs

@@ -17,7 +17,7 @@ pub fn format_dataset_table(filtered: &[Dataset]) -> String {
 
   table.set_header([o!("name"), o!("attributes"), o!("versions")]);
 
-  for dataset in filtered.iter() {
+  for dataset in filtered {
     let Dataset {
       path,
       shortcuts,

packages/nextclade-cli/src/io/http_client.rs

@@ -6,6 +6,7 @@ use nextclade::utils::info::{this_package_name, this_package_version_str};
 use reqwest::blocking::Client;
 use reqwest::{Method, Proxy};
 use std::str::FromStr;
+use std::time::Duration;
 use url::Url;
 
 #[derive(Parser, Debug, Default)]
@@ -62,7 +63,7 @@ impl HttpClient {
 
     let client = client_builder
       .connection_verbose(verbose)
-      .connect_timeout(Some(std::time::Duration::from_secs(60)))
+      .connect_timeout(Some(Duration::from_secs(60)))
       .user_agent(user_agent)
       .build()?;
 

packages/nextclade/benches/bench_seed_alignment.rs

@@ -5,7 +5,7 @@ use criterion::{black_box, criterion_group, criterion_main, Criterion};
 use nextclade::align::params::AlignPairwiseParams;
 use nextclade::align::seed_alignment::create_alignment_band;
 use nextclade::align::seed_match::{get_seed_matches_maybe_reverse_complement, CodonSpacedIndex, SeedMatchesResult};
-use nextclade::alphabet::nuc::to_nuc_seq;
+use nextclade::alphabet::nuc::{Nuc, to_nuc_seq};
 
 pub fn bench_seed_alignment(c: &mut Criterion) {
   let params = AlignPairwiseParams::default();
@@ -40,7 +40,7 @@ pub fn bench_seed_alignment(c: &mut Criterion) {
   group.finish();
 }
 
-fn sequence_from_path(path: PathBuf) -> Vec<nextclade::alphabet::nuc::Nuc> {
+fn sequence_from_path(path: PathBuf) -> Vec<Nuc> {
   black_box(to_nuc_seq(fs::read_to_string(path).unwrap().trim()).unwrap())
 }
 

packages/nextclade/src/align/score_matrix.rs

@@ -27,6 +27,9 @@ pub fn score_matrix<T: Letter<T>>(
   stripes: &[Stripe],
   params: &AlignPairwiseParams,
 ) -> ScoreMatrixResult {
+  assert!(gap_open_close.len() > 0);
+  assert!(stripes.len() > 0);
+
   let query_size = qry_seq.len();
   let ref_len = ref_seq.len();
   let n_rows = ref_len + 1;

packages/nextclade/src/align/seed_alignment.rs

@@ -56,7 +56,6 @@ fn extend_and_rewind(
   minimal_bandwidth: isize,
   ref_len: isize,
 ) -> RewindResult {
-  let current_seed_end = (current_seed.ref_pos + current_seed.length) as isize;
   let mut current_band = current_band;
   let mut look_back_length = look_back_length;
   // generate new current trapezoid for the body of the current seed
@@ -254,6 +253,7 @@ fn trace_stripe_stats(stripes: &[Stripe]) {
   trace!("Stripe width stats: min: {min}, max: {max}, mean: {mean:.1}, median: {median}",);
 }
 
+#[cfg(feature = "debug-seed-alignment")]
 fn trace_matches(matches: &[SeedMatch2]) {
   for (i, seed) in matches.iter().enumerate() {
     trace!(
@@ -266,6 +266,7 @@ fn trace_matches(matches: &[SeedMatch2]) {
   }
 }
 
+#[cfg(feature = "debug-seed-alignment")]
 fn write_stripes_to_file(stripes: &[Stripe], filename: &str) {
   use std::io::Write;
   let mut file = std::fs::File::create(filename).unwrap();
@@ -275,6 +276,7 @@ fn write_stripes_to_file(stripes: &[Stripe], filename: &str) {
   }
 }
 
+#[cfg(feature = "debug-seed-alignment")]
 pub fn write_matches_to_file(matches: &[SeedMatch2], filename: &str) {
   use std::io::Write;
   let mut file = std::fs::File::create(filename).unwrap();

packages/nextclade/src/analyze/find_private_aa_mutations.rs

@@ -95,13 +95,8 @@ pub fn find_private_aa_mutations_for_one_gene(
   );
 
   // Iterate over sequence deletions
-  let non_reversion_deletions = process_seq_deletions(
-    cds,
-    node_mut_map,
-    aa_deletions,
-    ref_peptide,
-    &mut seq_positions_mutated_or_deleted,
-  );
+  let non_reversion_deletions =
+    process_seq_deletions(cds, node_mut_map, aa_deletions, &mut seq_positions_mutated_or_deleted);
 
   // Iterate over node substitutions and deletions and find reversions
   let reversion_substitutions = find_reversions(
@@ -110,7 +105,7 @@ pub fn find_private_aa_mutations_for_one_gene(
     aa_unknowns,
     aa_unsequenced_ranges,
     ref_peptide,
-    &mut seq_positions_mutated_or_deleted,
+    &seq_positions_mutated_or_deleted,
   );
 
   let mut private_substitutions = concat_to_vec(&reversion_substitutions, &non_reversion_substitutions);
@@ -200,7 +195,6 @@ fn process_seq_deletions(
   cds: &Cds,
   node_mut_map: &BTreeMap<AaRefPosition, Aa>,
   deletions: &[&AaDel],
-  ref_seq: &[Aa],
   seq_positions_mutated_or_deleted: &mut BTreeSet<AaRefPosition>,
 ) -> Vec<AaDel> {
   let mut non_reversion_deletions = Vec::<AaDel>::new();
@@ -249,7 +243,7 @@ fn find_reversions(
   aa_unknowns: &[&CdsAaRange],
   aa_unsequenced_ranges: &[AaRefRange],
   ref_peptide: &[Aa],
-  seq_positions_mutated_or_deleted: &mut BTreeSet<AaRefPosition>,
+  seq_positions_mutated_or_deleted: &BTreeSet<AaRefPosition>,
 ) -> Vec<AaSub> {
   let mut reversion_substitutions = Vec::<AaSub>::new();
 

packages/nextclade/src/analyze/find_private_nuc_mutations.rs

@@ -109,7 +109,7 @@ pub fn find_private_nuc_mutations(
     alignment_range,
     ref_seq,
     non_acgtns,
-    &mut seq_positions_mutated_or_deleted,
+    &seq_positions_mutated_or_deleted,
   );
 
   let (_undeletions, reversion_substitutions) = reversion_substitutions_and_undeletions
@@ -263,7 +263,7 @@ fn find_reversions(
   alignment_range: &NucRefGlobalRange,
   ref_seq: &[Nuc],
   non_acgtns: &[NucRange],
-  seq_positions_mutated_or_deleted: &mut BTreeSet<NucRefGlobalPosition>,
+  seq_positions_mutated_or_deleted: &BTreeSet<NucRefGlobalPosition>,
 ) -> Vec<NucSub> {
   let mut reversion_substitutions = Vec::<NucSub>::new();
 

packages/nextclade/src/analyze/phenotype.rs

@@ -6,7 +6,7 @@ use num_traits::real::Real;
 pub fn calculate_phenotype(phenotype_data: &PhenotypeData, aa_substitutions: &[AaSub]) -> f64 {
   let aa_substitutions = aa_substitutions
     .iter()
-    .filter_map(|sub| (sub.cds_name == phenotype_data.cds && phenotype_data.aa_range.contains(sub.pos)).then_some(sub))
+    .filter(|sub| (sub.cds_name == phenotype_data.cds && phenotype_data.aa_range.contains(sub.pos)))
     .collect_vec();
 
   let phenotype: f64 = phenotype_data