adding some updates to how illumina fastqs are matched

src/cli.rs

@@ -42,10 +42,10 @@ pub struct Cli {
 #[derive(Subcommand)]
 pub enum Commands {
  #[clap(
- about = "Generate an input samplesheet for `nf-core/viralrecon`.",
- aliases = &["vr", "virrec", "vrc"]
- )]
- Viralrecon {
+  about = "Generate an input samplesheet for `nf-core/scrnaseq`.",
+  aliases = &["sc", "scr"]
+  )]
+ Scrnaseq {
  /// Input directory to traverse for FASTQ files.
  #[arg(short, long, required = false)]
  input_dir: PathBuf,
@@ -54,22 +54,19 @@ pub enum Commands {
  #[arg(short, long, required = false, default_value = ".fastq.gz")]
  fastq_ext: String,
 
- /// The sequencing platform where FASTQs came from
- #[arg(short, long, required = true)]
- platform: SeqPlatform,
+ /// the number of cells expected
+ #[arg(short, long, required = true, default_value_t = 10000)]
+ expected_cells: i64,
 
  /// Output file prefix (the part before the `_samplesheet.csv`)
  #[arg(short, long, required = false, default_value = None)]
  output_prefix: Option<String>,
- // /// Check a pre-existing samplesheet
- // #[arg(short, long, required = false, default_value = "samplesheet.csv")]
- // check: Option<String>,
  },
  #[clap(
-  about = "Generate an input samplesheet for `nf-core/scrnaseq`.",
-  aliases = &["sc", "scr"]
-  )]
- Scrnaseq {
+ about = "Generate an input samplesheet for `nf-core/viralrecon`.",
+ aliases = &["vr", "virrec", "vrc"]
+ )]
+ Viralrecon {
  /// Input directory to traverse for FASTQ files.
  #[arg(short, long, required = false)]
  input_dir: PathBuf,
@@ -78,12 +75,15 @@ pub enum Commands {
  #[arg(short, long, required = false, default_value = ".fastq.gz")]
  fastq_ext: String,
 
- /// the number of cells expected
+ /// The sequencing platform where FASTQs came from
  #[arg(short, long, required = true)]
- expected_cells: i64,
+ platform: SeqPlatform,
 
  /// Output file prefix (the part before the `_samplesheet.csv`)
  #[arg(short, long, required = false, default_value = None)]
  output_prefix: Option<String>,
+ // /// Check a pre-existing samplesheet
+ // #[arg(short, long, required = false, default_value = "samplesheet.csv")]
+ // check: Option<String>,
  },
 }

src/main.rs

@@ -8,6 +8,11 @@ pub mod scrnaseq;
 pub mod utils;
 pub mod viralrecon;
 
+/// .
+///
+/// # Errors
+///
+/// This function will return an error if .
 fn main() -> Result<()> {
  let cli = Cli::parse();
  match &cli.command {

src/scrnaseq.rs

@@ -6,10 +6,15 @@ use crate::utils::write_lines;
 pub use crate::viralrecon::find_files;
 use color_eyre::eyre::Result;
 
-fn retrieve_samples(file_paths: &[Rc<Path>]) -> HashSet<Rc<str>> {
- let illumina_pattern = Regex::new(r"_L\d{3}_R\d_\d{3}\.fastq\.gz$").unwrap();
+/// .
+///
+/// # Panics
+///
+/// Panics if .
+fn retrieve_samples(file_paths: &[Rc<Path>]) -> Result<HashSet<Rc<str>>> {
+ let illumina_pattern = Regex::new(r".*_R[12].*\.fastq\.gz$")?;
 
- file_paths
+ let hits = file_paths
  .iter()
  .map(|path| {
  Rc::from(
@@ -20,7 +25,9 @@ fn retrieve_samples(file_paths: &[Rc<Path>]) -> HashSet<Rc<str>> {
  )
  })
  .map(|x| Rc::from(illumina_pattern.replace_all(&x, "").to_string()))
- .collect()
+ .collect();
+
+ Ok(hits)
 }
 
 fn check_sample_ids(sample_ids: &HashSet<Rc<str>>) {
@@ -31,6 +38,15 @@ fn check_sample_ids(sample_ids: &HashSet<Rc<str>>) {
  }
 }
 
+/// .
+///
+/// # Panics
+///
+/// Panics if .
+///
+/// # Errors
+///
+/// This function will return an error if .
 fn collect_per_sample(
  sample_id: &Rc<str>,
  fastq_paths: &[Rc<Path>],
@@ -61,6 +77,7 @@ fn collect_per_sample(
  Ok([sample_id.as_ref(), fastq1, fastq2, &cell_str].join(","))
 }
 
+/// .
 fn concat_lines(
  sample_ids: &HashSet<Rc<str>>,
  fastq_paths: &[Rc<Path>],
@@ -72,6 +89,11 @@ fn concat_lines(
  .collect::<Vec<String>>()
 }
 
+/// .
+///
+/// # Errors
+///
+/// This function will return an error if .
 pub fn give_a_sheet(
  input_dir: &Path,
  fastq_ext: &str,
@@ -80,7 +102,7 @@ pub fn give_a_sheet(
 ) -> Result<()> {
  // find the FASTQ files and separate out the unique sample IDs
  let fastq_paths = find_files(input_dir, fastq_ext)?;
- let sample_ids: HashSet<Rc<str>> = retrieve_samples(&fastq_paths);
+ let sample_ids = retrieve_samples(&fastq_paths)?;
 
  // check the sample IDs for any that are too long
  check_sample_ids(&sample_ids);

src/utils.rs

@@ -26,6 +26,11 @@ pub trait RetrieveSampleIds {
  fn retrieve_samples(&self, file_paths: &[Rc<Path>]) -> Result<HashSet<Rc<str>>>;
 }
 
+/// .
+///
+/// # Errors
+///
+/// This function will return an error if .
 pub fn write_lines(lines: &[String], header: &str, output_prefix: &Option<String>) -> Result<()> {
  let out_name = match output_prefix {
  Some(prefix) => format!("{}_samplesheet.csv", prefix),

src/viralrecon.rs

@@ -6,6 +6,15 @@ use std::{collections::HashSet, ffi::OsStr, path::Path, rc::Rc};
 
 use crate::utils::RetrieveSampleIds;
 
+/// .
+///
+/// # Panics
+///
+/// Panics if .
+///
+/// # Errors
+///
+/// This function will return an error if .
 pub fn find_files(search_dir: &Path, fastq_suffix: &str) -> Result<Vec<Rc<Path>>> {
  // define the full pattern
  let pattern = format!("{}/*{}", &search_dir.display(), &fastq_suffix);
@@ -112,6 +121,7 @@ impl CollectByPlatform for SeqPlatform {
  }
 }
 
+/// .
 pub fn concat_lines(
  sample_ids: &HashSet<Rc<str>>,
  fastq_paths: &[Rc<Path>],
@@ -123,6 +133,11 @@ pub fn concat_lines(
  .collect::<Vec<String>>()
 }
 
+/// .
+///
+/// # Errors
+///
+/// This function will return an error if .
 pub fn give_a_sheet(
  input_dir: &Path,
  fastq_ext: &str,