updated readme and cli tool

README.md

@@ -1,24 +1,51 @@
 # Progetto ASD 2023/2024
 
-## Usage
+Creazione e analisi di un Pangenome Graph
+
+## Obbiettivi
+
+- [x] Caricare un Pangenome Graph dal formato GFA
+
+- [x] Classificare i nodi del grafo in base al tipo tree, back, forward, cross
+
+- [x] Rimuovere tutti i nodi di tipo back per rendere il grafo un DAG
+
+- [x] Restringere il grafo alla componente connessa più grande
 
--   `cargo run -- --help`
+- [x] Ricostruire le sequenze dei nodi del grafo in base ai cammini ed alla direzione di percorrenza dei nodi (forward o reverse)
 
-    Display help message.
+- [x] Ricerca di un pattern k-mer in queste sequenze utilizzando il rolling hash
 
--   `cargo run -- show -i ./dataset/example.gfa`
+- [~] Calcolare le frequenze di occorrenza di tutti i k-mer presenti nel grafo
 
-    Parses the GFA file and prints the graph and various information.
+## CLI Options
+
+- `-i, --input <input>`: file to read
+
+- `-c, --path_count <path_count>`: number of paths to visit when searching for the pattern (default: 1)
+
+- `-p, --pattern <pattern>`: k-mer pattern to search (default: "ACGT")
+
+- `-k, --kmer_size <kmer_size>`: k-mer length (default: 4)
+
+## Usage
 
--   Visualize the graph using EGUI, go to `examples/configurable` and run:
+-   To show help message:
 
-    `cargo run -- ../../dataset/example.gfa`
+    ```
+    cargo run -- --help`
+    ```
 
-    `cargo run -- ../../dataset/DRB1-3123_unsorted.gfa`
+-   For example to try out the `chrX` dataset:
 
--   Running the project with all the flags:
+    ```bash
+    GFA_URL='https://s3-us-west-2.amazonaws.com/human-pangenomics/pangenomes/freeze/freeze1/pggb/chroms/chrX.hprc-v1.0-pggb.gfa.gz'
+    wget $GFA_URL -O dataset/chrX.hprc-v1.0-pggb.local.gfa.gz
+    gunzip dataset/chrX.hprc-v1.0-pggb.local.gfa.gz
+    cargo run --release -- -i dataset/chrX.hprc-v1.0-pggb.local.gfa -c 2 -p ACGT -k 3
+    ```
 
-    `cargo run --release -- show -i dataset/chrX.hprc-v1.0-pggb.local.gfa -c 2 -p ACGT -k 3`
+    altri dataset sono elencati in [Note](#Note)
 
 ## Example GFA
 

src/main.rs

@@ -21,20 +21,6 @@ use rolling_hash::RollingHasher;
 #[derive(FromArgs, PartialEq, Debug)]
 /// Strumento CLI per il progetto di Algoritmi e Strutture Dati 2024
 struct CliTool {
-    #[argh(subcommand)]
-    nested: CliSubcommands,
-}
-
-#[derive(FromArgs, PartialEq, Debug)]
-#[argh(subcommand)]
-enum CliSubcommands {
-    Show(CommandShow),
-}
-
-#[derive(FromArgs, PartialEq, Debug)]
-/// Parse and show the content of a file
-#[argh(subcommand, name = "show")]
-struct CommandShow {
     #[argh(option, short = 'i')]
     /// file to read
     input: String,
@@ -55,8 +41,6 @@ struct CommandShow {
 fn main() -> std::io::Result<()> {
     let opts = argh::from_env::<CliTool>();
 
-    match opts.nested {
-        CliSubcommands::Show(opts) => {
     // validate opts.pattern is a valid DNA sequence
     if opts.pattern.chars().any(|c| !"ACGT".contains(c)) {
         eprintln!("Invalid pattern: {:?}", opts.pattern);
@@ -70,8 +54,7 @@ fn main() -> std::io::Result<()> {
         .progress_with(indicatif::ProgressBar::new_spinner())
         .count() as u64;
 
-            let entries =
+    let entries = gfa::parser::parse_source(std::fs::File::open(opts.input)?, file_lines_count)?;
-                gfa::parser::parse_source(std::fs::File::open(opts.input)?, file_lines_count)?;
 
     println!("Number of entries: {}", entries.len());
 
@@ -172,8 +155,6 @@ fn main() -> std::io::Result<()> {
 
     println!("Cleaning up...");
     process::exit(0);
-        }
-    }
 }
 
 fn compute_kmer_histogram_lb(