Skip to content

Correctly reuse storage with SubArrays #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 13, 2025
Merged

Correctly reuse storage with SubArrays #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 18 additions & 30 deletions src/sais.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,19 +24,7 @@
* OTHER DEALINGS IN THE SOFTWARE.
=#

struct IntVector <: AbstractVector{Int}
vec::Array{Int,1}
off::Int
end
Base.size(v::IntVector) = (length(v.vec)-v.off,)
Base.getindex(v::IntVector, key) = v.vec[v.off+Int(key)]
Base.setindex!(v::IntVector, value, key) = v.vec[v.off+Int(key)] = value

# TODO:
# - refactor code to simplify
# - build user interface for string operations

function getcounts(T::AbstractVector{<:Integer}, C::IntVector, n::Int, k::Int)
function getcounts(T::AbstractVector{<:Integer}, C::AbstractVector{<:Integer}, n::Int, k::Int)
for i = 1:k
C[i] = 0
end
Expand All @@ -45,7 +33,7 @@ function getcounts(T::AbstractVector{<:Integer}, C::IntVector, n::Int, k::Int)
end
end

function getbuckets(C::IntVector, B::IntVector, k::Int, isend::Bool)
function getbuckets(C::AbstractVector{<:Integer}, B::AbstractVector{<:Integer}, k::Int, isend::Bool)
s = 0
if isend != false
for i = 1:k
Expand All @@ -71,28 +59,28 @@ function sais(
pidx = 0
flags = 0
if k <= 256
C = IntVector(zeros(Int, k), 0)
C = zeros(Int, k)
if k <= fs
B = IntVector(SA, n + fs - k)
B = @view SA[n+fs-k+1:end]
flags = 1
else
B = IntVector(zeros(Int, k), 0)
B = zeros(Int, k)
flags = 3
end
elseif k <= fs
C = IntVector(SA, n + fs - k)
C = @view SA[n+fs-k+1:end]
if k <= fs - k
B = IntVector(SA, n + fs - 2k)
B = @view SA[n+fs-2k+1:end]
flags = 0
elseif k <= 1024
B = IntVector(zeros(Int, k), 0)
B = zeros(Int, k)
flags = 2
else
B = C
flags = 8
end
else
C = B = IntVector(zeros(Int, k), 0)
C = B = zeros(Int, k)
flags = 4 | 8
end
# stage 1
Expand Down Expand Up @@ -156,7 +144,7 @@ function sais(
j -= 1
end
end
RA = IntVector(SA, m + newfs)
RA = @view SA[m+newfs+1:end]
sais(RA, SA, newfs, m, name, false)

i = n
Expand All @@ -183,10 +171,10 @@ function sais(
SA[i] = SA[m + SA[i] + 1]
end
if flags & 4 != 0
C = B = IntVector(zeros(Int, k), 0)
C = B = zeros(Int, k)
end
if flags & 2 != 0
B = IntVector(zeros(Int, k), 0)
B = zeros(Int, k)
end
end
# stage 3
Expand Down Expand Up @@ -231,8 +219,8 @@ end
function LMSsort(
T::AbstractVector{<:Integer},
SA::IndexVector,
C::IntVector,
B::IntVector,
C::AbstractVector{<:Integer},
B::AbstractVector{<:Integer},
n::Int,
k::Int,
)
Expand Down Expand Up @@ -345,8 +333,8 @@ end
function induceSA(
T::AbstractVector{<:Integer},
SA::IndexVector,
C::IntVector,
B::IntVector,
C::AbstractVector{<:Integer},
B::AbstractVector{<:Integer},
n::Int,
k::Int,
)
Expand Down Expand Up @@ -395,8 +383,8 @@ end
function computeBWT(
T::AbstractVector{<:Integer},
SA::IndexVector,
C::IntVector,
B::IntVector,
C::AbstractVector{<:Integer},
B::AbstractVector{<:Integer},
n::Int,
k::Int,
)
Expand Down
9 changes: 9 additions & 0 deletions test/runtests.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,3 +184,12 @@ end
suffixes = [utext[i:end] for i in sa]
@test issorted(suffixes)
end

@testset "Test memory consumption" begin
# On a random UInt8 string, with UInt32 indices, SA-IS should allocate ~4n bytes.
N = 10 * 1024^2 # 10 MiB
s = rand(UInt8, N)
# Avoid allocations from compilation
suffixsort(s)
@test (@allocated suffixsort(s)) < 4N * 1.05
end
Loading