Merge pull request #7 from DavidsonGroup/refactor

Refactor and rewrite

Author: olliecheng

.github/workflows/build.yml

@@ -16,7 +16,19 @@ jobs:
     name: test-linux
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+      
+      - name: Cache Rust dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-cargo-test-${{ hashFiles('**/Cargo.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-cargo-test-
+      
       - name: Test
         uses: houseabsolute/actions-rust-cross@v0
         with:
@@ -28,7 +40,18 @@ jobs:
     needs: test
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+
+      - name: Cache Rust dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-cargo-build-${{ hashFiles('**/Cargo.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-cargo-build-
 
       - name: Add build information to environment
         run: echo "CARGO_BUILD_DESC= [$(git rev-parse --short HEAD)]" >> $GITHUB_ENV
@@ -60,7 +83,18 @@ jobs:
     needs: test
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+
+      - name: Cache Rust dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-cargo-macos-${{ hashFiles('**/Cargo.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-cargo-macos-
 
       - name: Add x86_64-apple-darwin target
         run: rustup target add x86_64-apple-darwin

.gitignore

@@ -1,6 +1,7 @@
 /debug
 /target
 /temp
+/scratch
 
 .DS_Store
 .idea
@@ -11,3 +12,4 @@
 Cargo.lock
 **/*.rs.bk
 
+.github/copilot-instructions.md

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "nailpolish"
-version = "0.1.0"
+version = "0.2.0"
 edition = "2021"
 
 [dependencies]
@@ -14,16 +14,27 @@ env_logger = "0.11.3"
 handlebars = "6.2.0"
 indexmap = "2.5.0"
 log = "0.4.22"
-needletail = "^0.6.1"
+needletail = "^0.6.3"
 rayon = "1.10.0"
 regex = "1.10.6"
-serde = { version = "1.0.203", features = ["derive"] }
-serde_json = "1.0.118"
 spoa = { git = "https://github.com/olliecheng/spoa-rs" }
-tempfile = "3.14.0"
 thiserror = "1.0.64"
 predicates = "3.1.2"
 indoc = "2.0.5"
+rkyv = { version = "0.8.10", features = [
+  "alloc",
+  "bytecheck",
+  "std",
+  "indexmap-2",
+  "smallvec-1",
+] }
+smallvec = "1.15.0"
+memmap = "0.7.0"
+bio = "2.2.0"
+itertools = "0.14.0"
+git-version = "0.3.9"
+serde = "1.0.219"
+serde_json = "1.0.140"
 
 [[bin]]
 name = "nailpolish"

readme.md

@@ -2,7 +2,6 @@
 
 [![Build status](https://github.com/olliecheng/nailpolish/actions/workflows/build.yml/badge.svg)](https://github.com/olliecheng/nailpolish/actions/workflows/build.yml) ![Static Badge](https://img.shields.io/badge/libc-%E2%89%A5%202.17-blue) ![GitHub Release](https://img.shields.io/github/v/release/olliecheng/nailpolish?include_prereleases)
 
-
 `nailpolish` is a collection of tools made for the deduplication of UMIs when working with long read single cell data.
 
 <div align="center">
@@ -50,7 +49,7 @@ $ nailpolish summary --index index.tsv
 and I can also transparently remove duplicate reads using:
 
 ```sh
-$ nailpolish call \
+$ nailpolish consensus \
   --index index.tsv \
   --input sample.fastq \
   --output sample_called.fastq \