Julia 1.0 support (#18)

Author: dcjones

.travis.yml

@@ -4,7 +4,7 @@ os:
   - linux
   - osx
 julia:
-  - 0.6
+  - 0.7
   - nightly
 matrix:
   allow_failures:

REQUIRE

@@ -1,9 +1,9 @@
-julia 0.6
-Automa 0.6.1
-BGZFStreams 0.1.4
-BioCore 1.4
-BioSequences 0.8.3
-BioSymbols 2.0
-BufferedStreams 0.4
-GenomicFeatures 0.2.1
-IntervalTrees 0.4.1
+julia 0.7
+Automa 0.7.0
+BGZFStreams 0.3.0
+BioCore 2.0.2
+BioSequences 1.0.0
+BioSymbols 3.1.0
+BufferedStreams 1.0.0
+GenomicFeatures 1.0.0
+IntervalTrees 1.0.0

appveyor.yml

@@ -1,11 +1,18 @@
 environment:
   matrix:
-  - JULIA_URL: "https://julialang-s3.julialang.org/bin/winnt/x64/0.6/julia-0.6-latest-win64.exe"
-  - JULIA_URL: "https://julialangnightlies-s3.julialang.org/bin/winnt/x64/julia-latest-win64.exe"
+  - julia_version: 0.7
+  - julia_version: 1
+  - julia_version: nightly 
 
-matrix:
-  allow_failures:
-  - JULIA_URL: "https://julialangnightlies-s3.julialang.org/bin/winnt/x64/julia-latest-win64.exe"
+platform:
+#  - x86 # 32-bit
+  - x64 # 64-bit
+
+# # Uncomment the following lines to allow failures on nightly julia
+# # (tests will run but not make your overall status red)
+# matrix:
+#   allow_failures:
+#   - julia_version: nightly
 
 branches:
   only:
@@ -19,24 +26,18 @@ notifications:
     on_build_status_changed: false
 
 install:
-  - ps: "[System.Net.ServicePointManager]::SecurityProtocol = [System.Net.SecurityProtocolType]::Tls12"
-# If there's a newer build queued for the same PR, cancel this one
-  - ps: if ($env:APPVEYOR_PULL_REQUEST_NUMBER -and $env:APPVEYOR_BUILD_NUMBER -ne ((Invoke-RestMethod `
-        https://ci.appveyor.com/api/projects/$env:APPVEYOR_ACCOUNT_NAME/$env:APPVEYOR_PROJECT_SLUG/history?recordsNumber=50).builds | `
-        Where-Object pullRequestId -eq $env:APPVEYOR_PULL_REQUEST_NUMBER)[0].buildNumber) { `
-        throw "There are newer queued builds for this pull request, failing early." }
-# Download most recent Julia Windows binary
-  - ps: (new-object net.webclient).DownloadFile(
-        $env:JULIA_URL,
-        "C:\projects\julia-binary.exe")
-# Run installer silently, output to C:\projects\julia
-  - C:\projects\julia-binary.exe /S /D=C:\projects\julia
+  - ps: iex ((new-object net.webclient).DownloadString("https://raw.githubusercontent.com/JuliaCI/Appveyor.jl/version-1/bin/install.ps1"))
 
 build_script:
-# Need to convert from shallow to complete for Pkg.clone to work
-  - IF EXIST .git\shallow (git fetch --unshallow)
-  - C:\projects\julia\bin\julia -e "versioninfo();
-      Pkg.clone(pwd(), \"BioAlignments\"); Pkg.build(\"BioAlignments\")"
+  - echo "%JL_BUILD_SCRIPT%"
+  - C:\julia\bin\julia -e "%JL_BUILD_SCRIPT%"
 
 test_script:
-  - C:\projects\julia\bin\julia -e "Pkg.test(\"BioAlignments\")"
+  - echo "%JL_TEST_SCRIPT%"
+  - C:\julia\bin\julia -e "%JL_TEST_SCRIPT%"
+
+# # Uncomment to support code coverage upload. Should only be enabled for packages
+# # which would have coverage gaps without running on Windows
+#on_success:
+#  - echo "%JL_CODECOV_SCRIPT%"
+#  - C:\julia\bin\julia -e "%JL_CODECOV_SCRIPT%"

src/BioAlignments.jl

@@ -90,6 +90,7 @@ import BioSequences
 import BioSymbols
 import GenomicFeatures: eachoverlap
 import IntervalTrees
+using LinearAlgebra: diagind
 
 include("operations.jl")
 include("anchors.jl")

src/alignment.jl

@@ -155,7 +155,7 @@ function cigar(aln::Alignment)
     for i in 2:length(anchors)
         n = max(anchors[i].seqpos - anchors[i-1].seqpos,
                 anchors[i].refpos - anchors[i-1].refpos)
-        print(out, n, Char(anchors[i].op))
+        print(out, n, convert(Char, anchors[i].op))
     end
     return String(take!(out))
 end
@@ -171,7 +171,7 @@ function check_alignment_anchors(anchors)
         error("Alignments must begin with on OP_START anchor.")
     end
 
-    for i in 2:endof(anchors)
+    for i in 2:lastindex(anchors)
         if anchors[i].refpos < anchors[i-1].refpos ||
            anchors[i].seqpos < anchors[i-1].seqpos
             error("Alignment anchors must be sorted.")
@@ -208,7 +208,7 @@ end
     quote
         anchors = aln.anchors
         lo = 1
-        hi = endof(anchors)
+        hi = lastindex(anchors)
         if !(anchors[lo].$pos < i ≤ anchors[hi].$pos)
             return 0
         end

src/bam/auxdata.jl

@@ -1,7 +1,7 @@
 # BAM Auxiliary Data
 # ==================
 
-struct AuxData <: Associative{String,Any}
+struct AuxData <: AbstractDict{String,Any}
     data::Vector{UInt8}
 end
 
@@ -21,15 +21,11 @@ function Base.length(aux::AuxData)
     return len
 end
 
-function Base.start(aux::AuxData)
-    return 1
-end
-
-function Base.done(aux::AuxData, pos)
-    return pos > length(aux.data)
-end
+function Base.iterate(aux::AuxData, pos=1)
+    if pos > length(aux.data)
+        return nothing
+    end
 
-function Base.next(aux::AuxData, pos)
     data = aux.data
     @label doit
     t1 = data[pos]
@@ -95,14 +91,14 @@ end
 function loadauxvalue(data::Vector{UInt8}, p::Int, ::Type{Vector{T}}) where T
     n = unsafe_load(Ptr{Int32}(pointer(data, p)))
     p += 4
-    xs = Vector{T}(n)
-    unsafe_copy!(pointer(xs), Ptr{T}(pointer(data, p)), n)
+    xs = Vector{T}(undef, n)
+    unsafe_copyto!(pointer(xs), Ptr{T}(pointer(data, p)), n)
     return p + n * sizeof(T), xs
 end
 
 function loadauxvalue(data::Vector{UInt8}, p::Int, ::Type{String})
     dataptr = pointer(data, p)
-    endptr = ccall(:memchr, Ptr{Void}, (Ptr{Void}, Cint, Csize_t),
+    endptr = ccall(:memchr, Ptr{Cvoid}, (Ptr{Cvoid}, Cint, Csize_t),
                    dataptr, '\0', length(data) - p + 1)
     q::Int = p + (endptr - dataptr) - 1
     return q + 2, String(data[p:q])

src/bam/bai.jl

@@ -12,7 +12,7 @@ struct BAI
     index::GenomicFeatures.Indexes.BGZFIndex
 
     # number of unmapped reads
-    n_no_coors::Nullable{Int}
+    n_no_coors::Union{Nothing, Int}
 end
 
 """
@@ -48,9 +48,9 @@ function read_bai(input::IO)
     n_refs = read(input, Int32)
     index = GenomicFeatures.Indexes.read_bgzfindex(input, n_refs)
     if !eof(input)
-        n_no_coors = Nullable{Int}(read(input, UInt64))
+        n_no_coors = read(input, UInt64)
     else
-        n_no_coors = Nullable{Int}()
+        n_no_coors = nothing
     end
 
     return BAI(index, n_no_coors)

src/bam/overlap.jl

@@ -7,7 +7,7 @@ struct OverlapIterator{T}
     interval::UnitRange{Int}
 end
 
-function Base.iteratorsize(::Type{OverlapIterator{T}}) where T
+function Base.IteratorSize(::Type{OverlapIterator{T}}) where T
     return Base.SizeUnknown()
 end
 
@@ -45,43 +45,39 @@ mutable struct OverlapIteratorState
     record::Record
 end
 
-function Base.start(iter::OverlapIterator)
-    refindex = findfirst(iter.reader.refseqnames, iter.refname)
+function Base.iterate(iter::OverlapIterator)
+    refindex = findfirst(isequal(iter.refname), iter.reader.refseqnames)
     if refindex == 0
         throw(ArgumentError("sequence name $(iter.refname) is not found in the header"))
     end
-    @assert !isnull(iter.reader.index)
-    chunks = GenomicFeatures.Indexes.overlapchunks(get(iter.reader.index).index, refindex, iter.interval)
+    @assert iter.reader.index !== nothing
+    chunks = GenomicFeatures.Indexes.overlapchunks(iter.reader.index.index, refindex, iter.interval)
     if !isempty(chunks)
         seek(iter.reader, first(chunks).start)
     end
-    return OverlapIteratorState(refindex, chunks, 1, Record())
+    state = OverlapIteratorState(refindex, chunks, 1, Record())
+    return iterate(iter, state)
 end
 
-function Base.done(iter::OverlapIterator, state)
-    while state.chunkid ≤ endof(state.chunks)
+function Base.iterate(iter::OverlapIterator, state)
+    while state.chunkid ≤ lastindex(state.chunks)
         chunk = state.chunks[state.chunkid]
         while BGZFStreams.virtualoffset(iter.reader.stream) < chunk.stop
             read!(iter.reader, state.record)
             c = compare_intervals(state.record, (state.refindex, iter.interval))
             if c == 0
-                # overlapping
-                return false
+                return copy(state.record), state
             elseif c > 0
                 # no more overlapping records in this chunk since records are sorted
                 break
             end
         end
         state.chunkid += 1
-        if state.chunkid ≤ endof(state.chunks)
+        if state.chunkid ≤ lastindex(state.chunks)
             seek(iter.reader, state.chunks[state.chunkid].start)
         end
     end
-    return true
-end
-
-function Base.next(::OverlapIterator, state)
-    return copy(state.record), state
+    return nothing
 end
 
 function compare_intervals(record::Record, interval::Tuple{Int,UnitRange{Int}})

src/bam/reader.jl

@@ -16,7 +16,7 @@ mutable struct Reader{T} <: BioCore.IO.AbstractReader
     start_offset::BGZFStreams.VirtualOffset
     refseqnames::Vector{String}
     refseqlens::Vector{Int}
-    index::Nullable{BAI}
+    index::Union{Nothing, BAI}
 end
 
 function Base.eltype(::Type{Reader{T}}) where T
@@ -55,7 +55,7 @@ If `fillSQ` is `true`, this function fills missing "SQ" metainfo in the header.
 function header(reader::Reader; fillSQ::Bool=false)::SAM.Header
     header = reader.header
     if fillSQ
-        if !isempty(find(reader.header, "SQ"))
+        if !isempty(findall(reader.header, "SQ"))
             throw(ArgumentError("SAM header already has SQ records"))
         end
         header = copy(header)
@@ -78,15 +78,10 @@ function Base.seekstart(reader::Reader)
     seek(reader.stream, reader.start_offset)
 end
 
-function Base.start(reader::Reader)
-    return Record()
-end
-
-function Base.done(reader::Reader, rec)
-    return eof(reader)
-end
-
-function Base.next(reader::Reader, rec)
+function Base.iterate(reader::Reader, rec=Record())
+    if eof(reader)
+        return nothing
+    end
     read!(reader, rec)
     return copy(rec), rec
 end
@@ -104,15 +99,15 @@ function init_bam_reader(input::BGZFStreams.BGZFStream)
 
     # SAM header
     textlen = read(input, Int32)
-    samreader = SAM.Reader(IOBuffer(read(input, UInt8, textlen)))
+    samreader = SAM.Reader(IOBuffer(read(input, textlen)))
 
     # reference sequences
     refseqnames = String[]
     refseqlens = Int[]
     n_refs = read(input, Int32)
     for _ in 1:n_refs
         namelen = read(input, Int32)
-        data = read(input, UInt8, namelen)
+        data = read(input, namelen)
         seqname = unsafe_string(pointer(data))
         seqlen = read(input, Int32)
         push!(refseqnames, seqname)
@@ -128,7 +123,7 @@ function init_bam_reader(input::BGZFStreams.BGZFStream)
         voffset,
         refseqnames,
         refseqlens,
-        Nullable{BAI}())
+        nothing)
 end
 
 function init_bam_reader(input::IO)

src/bam/record.jl

@@ -341,7 +341,7 @@ See also `BAM.cigar_rle`.
 function cigar(record::Record, checkCG::Bool = true)::String
     buf = IOBuffer()
     for (op, len) in zip(cigar_rle(record, checkCG)...)
-        print(buf, len, Char(op))
+        print(buf, len, convert(Char, op))
     end
     return String(take!(buf))
 end
@@ -503,9 +503,9 @@ Get the segment sequence of `record`.
 function sequence(record::Record)::BioSequences.DNASequence
     checkfilled(record)
     seqlen = seqlength(record)
-    data = Vector{UInt64}(cld(seqlen, 16))
+    data = Vector{UInt64}(undef, cld(seqlen, 16))
     src::Ptr{UInt64} = pointer(record.data, seqname_length(record) + n_cigar_op(record, false) * 4 + 1)
-    for i in 1:endof(data)
+    for i in 1:lastindex(data)
         # copy data flipping high and low nybble
         x = unsafe_load(src, i)
         data[i] = (x & 0x0f0f0f0f0f0f0f0f) << 4 | (x & 0xf0f0f0f0f0f0f0f0) >> 4