From 1c54ae47d86971e4dca0820613654fde22af17a8 Mon Sep 17 00:00:00 2001
From: jeff-k <jeff_k@fastmail.com>
Date: Sun, 12 May 2024 18:06:38 +0100
Subject: [PATCH] update readme

---
 .github/workflows/rust.yml | 22 +++++++++++++
 Cargo.toml                 |  4 +--
 README.md                  | 63 ++++++++++++++++++++++++++++++++++++--
 3 files changed, 85 insertions(+), 4 deletions(-)
 create mode 100644 .github/workflows/rust.yml

diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
new file mode 100644
index 0000000..31000a2
--- /dev/null
+++ b/.github/workflows/rust.yml
@@ -0,0 +1,22 @@
+name: Rust
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Build
+      run: cargo build --verbose
+    - name: Run tests
+      run: cargo test --verbose
diff --git a/Cargo.toml b/Cargo.toml
index d550015..753b17a 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -6,12 +6,12 @@ edition = "2021"
 [dependencies]
 futures = "0.3"
 futures-test = "0.3"
-bio-seq = { path="../bio-seq/bio-seq" }
+bio-seq = "0.12"
 
 [dev-dependencies]
 flate2 = "1"
 clap = { version="4", features=["derive"] }
-bio-seq = { path="../bio-seq/bio-seq" }
+bio-seq = "0.12"
 
 [[example]]
 name = "fqcheck"
diff --git a/README.md b/README.md
index 9f8cb50..5a6dcfd 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,65 @@
-# bio-streams
+[![Docs.rs](https://docs.rs/bio-streams/badge.svg)](https://docs.rs/bio-streams)
+[![CI status](https://github.com/jeff-k/bio-streams/actions/workflows/rust.yml/badge.svg)](https://github.com/jeff-k/bio-streams/actions/workflows/rust.yml)
 
-## examples
+<div class="title-block" style="text-align: center;" align="center">
+
+# bio-steams
+
+### Types and datastructures for streaming genomics data
+
+#### This crate is in early development. Contributions are very welcome.
+
+Webassembly example: (https://jeff-k.github.io/fqdemo/)[Remove non M. TB reads from streaming fastqs], (https://jeff-k.github.io/amplicon-tiling/)[amplicon bases SARS-CoV-2 assembly]
+</div>
+
+## Features
+
+Shared `Record` type by `Fastq` and `Fasta` streams:
+
+```rust
+pub struct Record<T: for<'a> TryFrom<&'a [u8]> = Vec<u8>> {
+    pub fields: Vec<u8>,
+    pub seq: T,
+    pub quality: Option<Vec<Phred>>, // fasta records set quality to `None`
+}
+```
+
+Records can be read into custom types: `pub struct Fastq<R: BufRead, T = Seq<Dna>>`
+
+## Examples
+
+```rust
+// Open a pair of gzipped fastq files as streams of `Record`s with `Seq<Dna>` sequences
+
+let fq1: Fastq<BufReader<MultiGzDecoder<File>>> = Fastq::new(BufReader::new(
+    MultiGzDecoder::new(File::open(&file1).unwrap()),
+));
+
+let fq2: Fastq<BufReader<MultiGzDecoder<File>>> = Fastq::new(BufReader::new(
+    MultiGzDecoder::new(File::open(&file2).unwrap()),
+));
+
+for zipped in fq1.zip(fq2) {
+    match zipped {
+        (Ok(r1), Ok(r2)) => {
+            // check that the last characters of the name strings are 1 and 2
+            if r1.fields[r1.fields.len() - 1] != b'1' || r2.fields[r2.fields.len() - 1] != b'2'
+            {
+                eprintln!("paired records do not end in 1/2");
+            }
+
+            // check that the description fields are equal up to the last character
+            if r1.fields[..r1.fields.len() - 1] != r2.fields[..r2.fields.len() - 1] {
+                eprintln!("reads do not have the same names");
+                exit(1);
+            }
+        }
+        _ => {
+            eprintln!("Parse error in fastq files");
+        }
+    }
+}
+```
 
 To run the `fqcheck` example program with read files `r1.fq.gz` and `f2.fq.gz`: