Skip to content

Make unsafe_shift_from(::Copyable) use whole chunks #39

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

Open
jakobnissen wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Make unsafe_shift_from(::Copyable) use whole chunks #39

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
94d28f8
Make unsafe_shift_from(::Copyable) use whole chunks
jakobnissen Dec 23, 2024
cbd2901
Scratch first attempt
jakobnissen Dec 26, 2024
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
85 changes: 0 additions & 85 deletions src/construction.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,91 +109,6 @@ include("construction_utils.jl")
throw(BioSequences.EncodeError(A, reinterpret(T, enc % UInt8)))
end

#=
"Extract a full kmer at a given index of a sequence.
Note: These methods don't do any bounds checking"
function unsafe_extract end

@inline function unsafe_extract(
::TwoToFour,
::Type{T},
seq::BioSequence,
from_index,
) where {T <: Kmer}
data = zero_tuple(T)
for i in from_index:(from_index + ksize(T) - 1)
encoding = left_shift(UInt(1), UInt(BioSequences.extract_encoded_element(seq, i)))
(_, data) = leftshift_carry(data, 4, encoding)
end
T(unsafe, data)
end

@inline function unsafe_extract(
::FourToTwo,
::Type{T},
seq::BioSequence,
from_index,
) where {T <: Kmer}
data = zero_tuple(T)
for i in from_index:(from_index + ksize(T) - 1)
encoding = UInt(BioSequences.extract_encoded_element(seq, i))::UInt
isone(count_ones(encoding)) || throw_uncertain(Alphabet(T), eltype(seq), encoding)
(_, data) = leftshift_carry(data, 2, trailing_zeros(encoding) % UInt)
end
T(unsafe, data)
end

@inline function unsafe_extract(
::Copyable,
::Type{T},
seq::BioSequence,
from_index,
) where {T <: Kmer}
data = zero_tuple(T)
bps = BioSequences.bits_per_symbol(Alphabet(seq))
for i in from_index:(from_index + ksize(T) - 1)
encoding = UInt(BioSequences.extract_encoded_element(seq, i))::UInt
(_, data) = leftshift_carry(data, bps, encoding)
end
T(unsafe, data)
end

@inline function unsafe_extract(
::AsciiEncode,
::Type{T},
seq::AbstractVector{UInt8},
from_index,
) where {T <: Kmer}
data = zero_tuple(T)
bps = BioSequences.bits_per_symbol(Alphabet(T))
@inbounds for i in from_index:(from_index + ksize(T) - 1)
byte = seq[i]
encoding = BioSequences.ascii_encode(Alphabet(T), byte)
if encoding > 0x7f
throw(BioSequences.EncodeError(Alphabet(T), byte))
end
(_, data) = leftshift_carry(data, bps, encoding % UInt)
end
T(unsafe, data)
end

@inline function unsafe_extract(
::GenericRecoding,
::Type{T},
seq,
from_index,
) where {T <: Kmer}
data = zero_tuple(T)
bps = BioSequences.bits_per_symbol(Alphabet(T))
@inbounds for i in 1:ksize(T)
symbol = convert(eltype(T), seq[i])
encoding = UInt(BioSequences.encode(Alphabet(T), symbol))
(_, data) = leftshift_carry(data, bps, encoding)
end
T(unsafe, data)
end
=#

################################################
# Constructors with full parameterisation
################################################
Expand Down