bug fix

Author: dagou

README.md

@@ -346,8 +346,11 @@ Options:
           Minimum quality score for FASTQ data [default: 0]
   -p, --num-threads <NUM_THREADS>
           The number of threads to use [default: 10]
-      --batch-size <BATCH_SIZE>
+     --buffer-size <BUFFER_SIZE>
           [default: 16777216]
+      --batch-size <BATCH_SIZE>
+          The size of each batch for processing taxid match results, used to control memory usage
+          [default: 16]
   -T, --confidence-threshold <CONFIDENCE_THRESHOLD>
           Confidence score threshold [default: 0]
   -g, --minimum-hit-groups <MINIMUM_HIT_GROUPS>
@@ -358,8 +361,6 @@ Options:
           In comb. w/ -R, provide minimizer information in report
   -z, --report-zero-counts
           In comb. w/ -R, report taxa w/ 0 count
-      --full-output
-          output file contains all unclassified sequence
   -h, --help
           Print help (see more with '--help')
   -V, --version

kr2r/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "kr2r"
-version = "0.6.3"
+version = "0.6.8"
 edition = "2021"
 authors = ["eric9n@gmail.com"]
 

kr2r/src/args.rs

@@ -117,10 +117,9 @@ pub struct ClassifyArgs {
     #[clap(short = 'z', long, value_parser, default_value_t = false)]
     pub report_zero_counts: bool,
 
-    /// output file contains all unclassified sequence
-    #[clap(long, value_parser, default_value_t = false)]
-    pub full_output: bool,
-
+    // /// output file contains all unclassified sequence
+    // #[clap(long, value_parser, default_value_t = false)]
+    // pub full_output: bool,
     /// A list of input file paths (FASTA/FASTQ) to be processed by the classify program.
     /// Supports fasta or fastq format files (e.g., .fasta, .fastq) and gzip compressed files (e.g., .fasta.gz, .fastq.gz).
     // #[clap(short = 'F', long = "files")]

kr2r/src/bin/kun.rs

@@ -97,7 +97,7 @@ impl From<ClassifyArgs> for resolve::Args {
             kraken_output_dir: item.kraken_output_dir,
             report_kmer_data: item.report_kmer_data,
             report_zero_counts: item.report_zero_counts,
-            full_output: item.full_output,
+            // full_output: item.full_output,
             num_threads: item.num_threads,
         }
     }

kr2r/src/bin/resolve.rs

@@ -8,7 +8,7 @@ use kr2r::utils::{find_and_trans_bin_files, find_and_trans_files, open_file};
 use kr2r::HitGroup;
 // use rayon::prelude::*;
 use seqkmer::{buffer_map_parallel, trim_pair_info, OptionPair};
-use std::collections::{HashMap, HashSet};
+use std::collections::HashMap;
 use std::fs::File;
 use std::io::{self, BufRead, BufReader, BufWriter, Read, Result, Write};
 use std::path::{Path, PathBuf};
@@ -65,9 +65,9 @@ pub struct Args {
     #[clap(long = "output-dir", value_parser)]
     pub kraken_output_dir: Option<PathBuf>,
 
-    /// output file contains all unclassified sequence
-    #[clap(long, value_parser, default_value_t = false)]
-    pub full_output: bool,
+    // /// output file contains all unclassified sequence
+    // #[clap(long, value_parser, default_value_t = false)]
+    // pub full_output: bool,
     /// Confidence score threshold, default is 0.0.
     #[clap(
         short = 'T',
@@ -120,8 +120,7 @@ fn process_batch<P: AsRef<Path>>(
     id_map: &HashMap<u32, (String, String, usize, Option<usize>)>,
     writer: &mut Box<dyn Write + Send>,
     value_mask: usize,
-) -> Result<(TaxonCountersDash, usize, HashSet<u32>)> {
-    let hit_seq_id_set = HashSet::new();
+) -> Result<(TaxonCountersDash, usize)> {
     let confidence_threshold = args.confidence_threshold;
     let minimum_hit_groups = args.minimum_hit_groups;
 
@@ -138,6 +137,7 @@ fn process_batch<P: AsRef<Path>>(
                 if let Some(item) = id_map.get(&k) {
                     let mut rows = rows.to_owned();
                     rows.sort_unstable();
+
                     let dna_id = trim_pair_info(&item.0);
                     let range =
                         OptionPair::from(((0, item.2), item.3.map(|size| (item.2, size + item.2))));
@@ -179,11 +179,7 @@ fn process_batch<P: AsRef<Path>>(
         .expect("failed");
     }
 
-    Ok((
-        cur_taxon_counts,
-        classify_counter.load(Ordering::SeqCst),
-        hit_seq_id_set,
-    ))
+    Ok((cur_taxon_counts, classify_counter.load(Ordering::SeqCst)))
 }
 
 pub fn run(args: Args) -> Result<()> {
@@ -218,7 +214,7 @@ pub fn run(args: Args) -> Result<()> {
             }
             None => Box::new(BufWriter::new(io::stdout())) as Box<dyn Write + Send>,
         };
-        let (thread_taxon_counts, thread_classified, hit_seq_set) = process_batch::<PathBuf>(
+        let (thread_taxon_counts, thread_classified) = process_batch::<PathBuf>(
             sam_files,
             &args,
             &taxo,
@@ -227,22 +223,22 @@ pub fn run(args: Args) -> Result<()> {
             value_mask,
         )?;
 
-        if args.full_output {
-            sample_id_map
-                .iter()
-                .filter(|(key, _)| !hit_seq_set.contains(key))
-                .for_each(|(_, value)| {
-                    let dna_id = trim_pair_info(&value.0); // 假设 key 是 &str 类型
-                    let output_line = format!(
-                        "U\t{}\t0\t{}\t{}\n",
-                        dna_id,
-                        value.1,
-                        if value.3.is_none() { "" } else { " |:| " }
-                    );
-
-                    writer.write_all(output_line.as_bytes()).unwrap();
-                });
-        }
+        // if args.full_output {
+        //     sample_id_map
+        //         .iter()
+        //         .filter(|(key, _)| !hit_seq_set.contains(key))
+        //         .for_each(|(_, value)| {
+        //             let dna_id = trim_pair_info(&value.0); // 假设 key 是 &str 类型
+        //             let output_line = format!(
+        //                 "U\t{}\t0\t{}\t{}\n",
+        //                 dna_id,
+        //                 value.1,
+        //                 if value.3.is_none() { "" } else { " |:| " }
+        //             );
+
+        //             writer.write_all(output_line.as_bytes()).unwrap();
+        //         });
+        // }
 
         let mut sample_taxon_counts: HashMap<
             u64,