整理内容

kr2r/Cargo.toml

@@ -17,14 +17,6 @@ path = "src/bin/build_db.rs"
 name = "classify"
 path = "src/bin/classify.rs"
 
-[[bin]]
-name = "cht"
-path = "src/bin/cht.rs"
-
-[[bin]]
-name = "taxo"
-path = "src/bin/taxo.rs"
-
 
 [features]
 default = ["dna"]

kr2r/src/bin/classify.rs

@@ -46,10 +46,9 @@ struct Args {
     )]
     confidence_threshold: f64,
 
-    /// Enable quick mode for faster processing.
-    #[clap(short = 'q', long = "quick-mode", action)]
-    quick_mode: bool,
-
+    // /// Enable quick mode for faster processing.
+    // #[clap(short = 'q', long = "quick-mode", action)]
+    // quick_mode: bool,
     /// The number of threads to use, default is 1.
     #[clap(short = 'p', long = "num-threads", value_parser, default_value_t = 1)]
     num_threads: i32,
@@ -71,38 +70,36 @@ struct Args {
     #[clap(short = 'S', long = "single-file-pairs", action)]
     single_file_pairs: bool,
 
-    /// Use mpa-style report format.
-    #[clap(short = 'm', long = "mpa-style-report", action)]
-    mpa_style_report: bool,
-
-    /// Report k-mer data in the output.
-    #[clap(short = 'K', long = "report-kmer-data", action)]
-    report_kmer_data: bool,
+    // /// Use mpa-style report format.
+    // #[clap(short = 'm', long = "mpa-style-report", action)]
+    // mpa_style_report: bool,
 
-    /// File path for outputting the report.
-    #[clap(short = 'R', long = "report-filename", value_parser)]
-    report_filename: Option<String>,
+    // /// Report k-mer data in the output.
+    // #[clap(short = 'K', long = "report-kmer-data", action)]
+    // report_kmer_data: bool,
 
-    /// Report taxa with zero count.
-    #[clap(short = 'z', long = "report-zero-counts", action)]
-    report_zero_counts: bool,
+    // /// File path for outputting the report.
+    // #[clap(short = 'R', long = "report-filename", value_parser)]
+    // report_filename: Option<String>,
 
-    /// File path for outputting classified sequences.
-    #[clap(short = 'C', long = "classified-output-filename", value_parser)]
-    classified_output_filename: Option<String>,
+    // /// Report taxa with zero count.
+    // #[clap(short = 'z', long = "report-zero-counts", action)]
+    // report_zero_counts: bool,
 
-    /// File path for outputting unclassified sequences.
-    #[clap(short = 'U', long = "unclassified-output-filename", value_parser)]
-    unclassified_output_filename: Option<String>,
+    // /// File path for outputting classified sequences.
+    // #[clap(short = 'C', long = "classified-output-filename", value_parser)]
+    // classified_output_filename: Option<String>,
 
+    // /// File path for outputting unclassified sequences.
+    // #[clap(short = 'U', long = "unclassified-output-filename", value_parser)]
+    // unclassified_output_filename: Option<String>,
     /// File path for outputting normal Kraken output.
     #[clap(short = 'O', long = "kraken-output-filename", value_parser)]
     kraken_output_filename: Option<String>,
 
-    /// Print scientific name instead of taxid in Kraken output.
-    #[clap(short = 'n', long = "print-scientific-name", action)]
-    print_scientific_name: bool,
-
+    // /// Print scientific name instead of taxid in Kraken output.
+    // #[clap(short = 'n', long = "print-scientific-name", action)]
+    // print_scientific_name: bool,
     /// Minimum quality score for FASTQ data, default is 0.
     #[clap(
         short = 'Q',
@@ -112,10 +109,6 @@ struct Args {
     )]
     minimum_quality_score: i32,
 
-    /// Use memory mapping to access hash and taxonomy data.
-    #[clap(short = 'M', long = "use-memory-mapping", action)]
-    use_memory_mapping: bool,
-
     /// Input files for processing.
     ///
     /// A list of input file paths (FASTA/FASTQ) to be processed by the classify program.

kr2r/src/bin/estimate_capacity.rs

@@ -47,9 +47,11 @@ struct Args {
     #[clap(short = 'T', long, value_parser = parse_binary)]
     toggle_mask: Option<u64>,
 
-    /// Read block size
-    #[clap(short = 'B', long, default_value = "31457280")]
-    block_size: usize,
+    /// Proportion of the hash table to be populated
+    /// (build task only; def: 0.7, must be
+    ///    between 0 and 1).
+    #[clap(long, long, default_value_t = 0.7)]
+    load_factor: f64,
 
     /// Number of threads
     #[clap(short = 'p', long, default_value = "4")]
@@ -145,6 +147,23 @@ fn process_sequence(
     hllp
 }
 
+fn format_bytes(size: f64) -> String {
+    let suffixes = ["B", "kB", "MB", "GB", "TB", "PB", "EB"];
+    let mut size = size;
+    let mut current_suffix = &suffixes[0];
+
+    for suffix in &suffixes[1..] {
+        if size >= 1024.0 {
+            current_suffix = suffix;
+            size /= 1024.0;
+        } else {
+            break;
+        }
+    }
+
+    format!("{:.2}{}", size, current_suffix)
+}
+
 fn main() {
     let mut args = Args::parse();
     if args.k_mer < args.l_mer as u64 {
@@ -182,5 +201,11 @@ fn main() {
 
     let hllp_count = (hllp.count() * RANGE_SECTIONS as f64 / args.n as f64).round() as u64;
     // println!("Final count: {:?}", final_count);
-    println!("estimate count: {:?}", hllp_count);
+    let required_capacity = (hllp_count + 8192) as f64 / args.load_factor;
+    println!(
+        "estimate count: {:?}, required capacity: {:?}, Estimated hash table requirement: {:?}",
+        hllp_count,
+        required_capacity.ceil(),
+        format_bytes(required_capacity)
+    );
 }