From 149d3a79bb62a22401f9da151e083b9faa467447 Mon Sep 17 00:00:00 2001
From: Jakob Nybo Nissen <jakobnybonissen@gmail.com>
Date: Tue, 2 May 2023 10:31:36 +0200
Subject: [PATCH] Implement copy! for records

---
 CHANGELOG.md         |  4 ++++
 Project.toml         |  2 +-
 src/fasta/record.jl  | 10 ++++++++++
 src/fastq/record.jl  | 10 ++++++++++
 test/fasta/record.jl | 24 +++++++++++++++++++-----
 test/fastq/record.jl | 29 ++++++++++++++++++++++-------
 6 files changed, 66 insertions(+), 13 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b4e2c60..b751020 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [2.1.0]
+### Additions
+* Implement `Base.copy!` for `FASTQRecord` and `FASTARecord`
+
 ## [2.0.1]
 ### Bugfix
 * Fix `Base.read!(::FASTQReader, ::FASTQRecord)` (issue #95)
diff --git a/Project.toml b/Project.toml
index b947fbd..29aeec9 100644
--- a/Project.toml
+++ b/Project.toml
@@ -1,7 +1,7 @@
 name = "FASTX"
 uuid = "c2308a5c-f048-11e8-3e8a-31650f418d12"
 authors = ["Sabrina J. Ward <sabrinajward@protonmail.com>", "Jakob N. Nissen <jakobnybonissen@gmail.com>"]
-version = "2.0.1"
+version = "2.1.0"
 
 [weakdeps]
 BioSequences = "7e6ae17a-c86d-528c-b3b9-7f778a29fe59"
diff --git a/src/fasta/record.jl b/src/fasta/record.jl
index b53801c..c6d4208 100644
--- a/src/fasta/record.jl
+++ b/src/fasta/record.jl
@@ -122,6 +122,16 @@ function Base.copy(record::Record)
     )
 end
 
+function Base.copy!(dst::Record, src::Record)
+    n = filled(src)
+    length(dst.data) < n && resize!(dst.data, n)
+    unsafe_copyto!(dst.data, 1, src.data, 1, n)
+    dst.identifier_len = src.identifier_len
+    dst.description_len = src.description_len
+    dst.sequence_len = src.sequence_len
+    dst
+end
+
 function Base.write(io::IO, record::Record)
     data = record.data
     write(io, UInt8('>'))
diff --git a/src/fastq/record.jl b/src/fastq/record.jl
index 25377f5..1a4bb64 100644
--- a/src/fastq/record.jl
+++ b/src/fastq/record.jl
@@ -178,6 +178,16 @@ function Base.copy(record::Record)
     )
 end
 
+function Base.copy!(dst::Record, src::Record)
+    n = filled(src)
+    length(dst.data) < n && resize!(dst.data, n)
+    unsafe_copyto!(dst.data, 1, src.data, 1, n)
+    dst.identifier_len = src.identifier_len
+    dst.description_len = src.description_len
+    dst.has_description_seq_len = src.has_description_seq_len
+    dst
+end
+
 function Base.write(io::IO, record::Record)
     data = record.data
     len = UInt(seqsize(record))
diff --git a/test/fasta/record.jl b/test/fasta/record.jl
index 9163914..fa13a02 100644
--- a/test/fasta/record.jl
+++ b/test/fasta/record.jl
@@ -10,11 +10,6 @@
     empty!(record)
     @test record == record2
 
-    # Copying
-    cp = copy(record)
-    @test record == cp
-    @test record.data !== cp.data
-
     # Components of empty records
     @test identifier(record) isa AbstractString
     @test isempty(identifier(record))
@@ -129,6 +124,25 @@ end
     @test sequence(String, cp) == "OOJMQQ"
 end
 
+@testset "Copying" begin 
+    record = parse(Record, ">some_identifier \tmy_description  | text\nAAT\nTA\nCCG")
+    resize!(record.data, 1000)
+    cp = copy(record)
+
+    @test record !== cp
+    @test record == cp
+    @test sequence(record) == sequence(cp)
+    @test identifier(record) == identifier(cp)
+    @test description(record) == description(cp)
+    @test record.data !== cp.data
+
+    record = parse(Record, ">another record\r\nUAGWMPK\nKKLLAAM")
+    @test record != cp
+    copy!(record, cp)
+    @test record !== cp
+    @test record == cp
+end
+
 # Get sequence as String/StringView
 @testset "Get sequence" begin
     record = Record(codeunits("ab cAACCAAGGTTKKKMMMM"), 2, 4, 10)
diff --git a/test/fastq/record.jl b/test/fastq/record.jl
index 533642c..97d64ed 100644
--- a/test/fastq/record.jl
+++ b/test/fastq/record.jl
@@ -10,13 +10,6 @@
     empty!(record)
     @test record == record2
 
-    # Copying
-    resize!(record.data, 1000)
-    cp = copy(record)
-    empty!(record.data)
-    @test record == cp
-    @test record.data !== cp.data
-
     # Components of empty records
     @test identifier(record) == ""
     @test description(record) == ""
@@ -122,6 +115,28 @@ end
     end
 end
 
+@testset "Copying" begin 
+    record = parse(Record, "@A\nTGGAA\n+\nJJJAA")
+    resize!(record.data, 1000)
+    cp = copy(record)
+
+    @test record !== cp
+    @test record == cp
+    @test sequence(record) == sequence(cp)
+    @test identifier(record) == identifier(cp)
+    @test description(record) == description(cp)
+    @test quality(record) == quality(cp)
+    @test record.data !== cp.data
+    # Test that we don't unnecessarily copy noncoding data
+    @test length(record.data) > length(cp.data)
+
+    record = parse(Record, "@some other record\r\nTAGA\r\n+\r\nJJJK")
+    @test record != cp
+    copy!(record, cp)
+    @test record !== cp
+    @test record == cp
+end
+
 @testset "Get sequence as String/StringView" begin
     records = map(i -> parse(Record, i), TEST_RECORD_STRINGS)