Require Julia v1.10 or later (#575)

* Require Julia v1.10 or later
* Remove `Compat` from dependencies

.github/workflows/CI.yml

@@ -34,7 +34,7 @@ jobs:
             version: '1'
           - os: ubuntu-latest
             arch: x64
-            version: '1.6'
+            version: '1.10'
           - os: ubuntu-latest
             arch: x64
             version: 'pre'
@@ -46,8 +46,6 @@ jobs:
           version: ${{ matrix.version }}
           arch: ${{ matrix.arch }}
       - uses: julia-actions/cache@v2
-        with:
-          cache-registries: ${{ !(matrix.version == '1.6' && matrix.os == 'windows-latest') }}
       - uses: julia-actions/julia-buildpkg@v1
       - uses: julia-actions/julia-runtest@v1
       - uses: julia-actions/julia-processcoverage@v1

Project.toml

@@ -4,7 +4,6 @@ version = "0.8.0"
 
 [deps]
 Bessels = "0e736298-9ec6-45e8-9647-e4fc86a2fe38"
-Compat = "34da2185-b29b-5c13-b0c7-acf172513d20"
 FFTW = "7a1cc6ca-52ef-59f5-83cd-3a7055c09341"
 IterTools = "c8e1da08-722c-5040-9ed9-7db0dc04731e"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
@@ -16,7 +15,6 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 
 [compat]
 Bessels = "0.2"
-Compat = "4.1"
 DelimitedFiles = "1.6"
 FFTW = "1.8"
 IterTools = "1.4"
@@ -28,7 +26,7 @@ Reexport = "1.0"
 SpecialFunctions = "2.0"
 Statistics = "1.6"
 Test = "1.6"
-julia = "1.6"
+julia = "1.10"
 
 [extras]
 DelimitedFiles = "8bb1440f-4735-579b-a4ab-409b98df4dab"

src/DSP.jl

@@ -3,7 +3,6 @@ module DSP
 using FFTW
 using LinearAlgebra: mul!, rmul!
 using IterTools: subsets
-using Compat: Compat
 
 export conv, deconv, filt, filt!, xcorr
 

src/Filters/Filters.jl

@@ -9,7 +9,6 @@ using Statistics: middle
 using SpecialFunctions: ellipk
 using ..DSP: optimalfftfiltlength, os_fft_complexity, SMALL_FILT_CUTOFF
 import ..DSP: filt, filt!
-using Compat: Compat
 using FFTW
 
 include("coefficients.jl")

src/Filters/design.jl

@@ -14,7 +14,7 @@ function Butterworth(::Type{T}, n::Integer) where {T<:Real}
     poles = Vector{Complex{T}}(undef, n)
     for i = 1:n÷2
         w = convert(T, 2i - 1) / 2n
-        sinpi_w, cospi_w = Compat.@inline sincospi(w)
+        sinpi_w, cospi_w = @inline sincospi(w)
         pole = complex(-sinpi_w, cospi_w)
         poles[2i-1] = pole
         poles[2i] = conj(pole)
@@ -43,7 +43,7 @@ function chebyshev_poles(::Type{T}, n::Integer, ε::Real) where {T<:Real}
     c = cosh(μ)
     for i = 1:n÷2
         w = convert(T, 2i - 1) / 2n
-        sinpi_w, cospi_w = Compat.@inline sincospi(w)
+        sinpi_w, cospi_w = @inline sincospi(w)
         pole = complex(b * sinpi_w, c * cospi_w)
         p[2i-1] = pole
         p[2i] = conj(pole)
@@ -94,7 +94,7 @@ function Chebyshev2(::Type{T}, n::Integer, ripple::Real) where {T<:Real}
     k = one(T)
     for i = 1:n÷2
         w = convert(T, 2i - 1) / 2n
-        ze = Compat.@inline complex(zero(T), -inv(cospi(w)))
+        ze = @inline complex(zero(T), -inv(cospi(w)))
         z[2i-1] = ze
         z[2i] = conj(ze)
         k *= abs2(p[2i]) / abs2(ze)
@@ -140,8 +140,8 @@ function _ellip(init::Number, landen::Vector{<:Real})
     end
     w = inv(winv)
 end
-@inline cde(u::Number, landen::Vector{<:Real}) = Compat.@inline _ellip(cospi(u / 2), landen)
-@inline sne(u::Number, landen::Vector{<:Real}) = Compat.@inline _ellip(sinpi(u / 2), landen)
+@inline cde(u::Number, landen::Vector{<:Real}) = @inline _ellip(cospi(u / 2), landen)
+@inline sne(u::Number, landen::Vector{<:Real}) = @inline _ellip(sinpi(u / 2), landen)
 
 # sne inverse
 function asne(w::Number, k::Real)

src/Filters/response.jl

@@ -160,7 +160,7 @@ function _freqrange(filter::FilterCoefficients{:s})
     filter = convert(ZeroPoleGain, filter)
     w_interesting = sort!(Float64.(abs.([filter.p; filter.z])))
     include_zero = !isempty(w_interesting) && iszero(w_interesting[1])
-    w_interesting = collect(Compat.Iterators.dropwhile(iszero, w_interesting))
+    w_interesting = collect(Iterators.dropwhile(iszero, w_interesting))
     if isempty(w_interesting) # no non-zero poles or zeros
         if !include_zero || !isfinite(1/filter.k)
             return [0; 10 .^ (0:6)] # fallback

src/dspbase.jl

@@ -51,13 +51,13 @@ function filt!(out::AbstractArray, b::Union{AbstractVector, Number}, a::Union{Ab
     end
 
     iszero(size(x, 1)) && return out
-    isone(sz) && return (k = b[1] / a[1]; Compat.@noinline mul!(out, x, k)) # Simple scaling without memory
+    isone(sz) && return (k = b[1] / a[1]; @noinline mul!(out, x, k)) # Simple scaling without memory
 
     # Filter coefficient normalization
     if !isone(a[1])
         norml = a[1]
-        a = Compat.@noinline broadcast(/, a, norml)
-        b = Compat.@noinline broadcast(/, b, norml)
+        a = @noinline broadcast(/, a, norml)
+        b = @noinline broadcast(/, b, norml)
     end
     # Pad the coefficients with zeros if needed
     bs<sz   && (b = copyto!(zeros(eltype(b), sz), b))