init with basic distance calc

Manifest.toml

@@ -0,0 +1,82 @@
+# This file is machine-generated - editing it directly is not advised
+
+julia_version = "1.11.4"
+manifest_format = "2.0"
+project_hash = "0d936e24ff57e10f312c576b6073d374c23d76ee"
+
+[[deps.Artifacts]]
+uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
+version = "1.11.0"
+
+[[deps.CompilerSupportLibraries_jll]]
+deps = ["Artifacts", "Libdl"]
+uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
+version = "1.1.1+0"
+
+[[deps.Distributed]]
+deps = ["Random", "Serialization", "Sockets"]
+uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b"
+version = "1.11.0"
+
+[[deps.Libdl]]
+uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
+version = "1.11.0"
+
+[[deps.LinearAlgebra]]
+deps = ["Libdl", "OpenBLAS_jll", "libblastrampoline_jll"]
+uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
+version = "1.11.0"
+
+[[deps.OpenBLAS_jll]]
+deps = ["Artifacts", "CompilerSupportLibraries_jll", "Libdl"]
+uuid = "4536629a-c528-5b80-bd46-f80d51c5b363"
+version = "0.3.27+1"
+
+[[deps.Printf]]
+deps = ["Unicode"]
+uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
+version = "1.11.0"
+
+[[deps.ProgressMeter]]
+deps = ["Distributed", "Printf"]
+git-tree-sha1 = "13c5103482a8ed1536a54c08d0e742ae3dca2d42"
+uuid = "92933f4c-e287-5a05-a399-4b506db050ca"
+version = "1.10.4"
+
+[[deps.Random]]
+deps = ["SHA"]
+uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
+version = "1.11.0"
+
+[[deps.SHA]]
+uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
+version = "0.7.0"
+
+[[deps.Serialization]]
+uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
+version = "1.11.0"
+
+[[deps.Sockets]]
+uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
+version = "1.11.0"
+
+[[deps.Statistics]]
+deps = ["LinearAlgebra"]
+git-tree-sha1 = "ae3bb1eb3bba077cd276bc5cfc337cc65c3075c0"
+uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
+version = "1.11.1"
+
+    [deps.Statistics.extensions]
+    SparseArraysExt = ["SparseArrays"]
+
+    [deps.Statistics.weakdeps]
+    SparseArrays = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
+
+[[deps.Unicode]]
+uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
+version = "1.11.0"
+
+[[deps.libblastrampoline_jll]]
+deps = ["Artifacts", "Libdl"]
+uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
+version = "5.11.0+0"

Project.toml

@@ -0,0 +1,21 @@
+name = "MethodSimilarity"
+uuid = "a653e358-0bbe-4a80-8f0e-568b83ef5641"
+authors = ["qwjyh <urataw421@gmail.com>"]
+version = "0.1.0"
+
+[deps]
+LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
+ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
+Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
+
+[compat]
+LinearAlgebra = "1.11.0"
+ProgressMeter = "1.10.4"
+Statistics = "1.11.1"
+Test = "1.11.0"
+
+[extras]
+Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+
+[targets]
+test = ["Test"]

src/MethodSimilarity.jl

@@ -0,0 +1,17 @@
+module MethodSimilarity
+
+using Statistics
+using LinearAlgebra
+using ProgressMeter
+
+include("Utils.jl")
+using .Utils
+
+include("method_info.jl")
+include("distance.jl")
+
+include("analyze.jl")
+
+greet() = print("Hello World!")
+
+end # module MethodSimilarity

src/Utils.jl

@@ -0,0 +1,7 @@
+module Utils
+
+export Choose
+
+include("utils/choose.jl")
+
+end

src/analyze.jl

@@ -0,0 +1,21 @@
+function main()
+    all_methods = Method[]
+    for base_prop_sym in propertynames(Base)
+        base_prop = getproperty(Base, base_prop_sym)
+        if !(base_prop isa Function)
+            continue
+        end
+        if !Base.isexported(Base, base_prop_sym) && !Base.ispublic(Base, base_prop_sym)
+            continue
+        end
+
+        push!(all_methods, methods(base_prop)...)
+    end
+    num_methods = length(all_methods)
+    @info "number of methods: $(num_methods)"
+    dists = zeros((num_methods, num_methods))
+    @showprogress Threads.@threads for (i, j) in Choose(2, num_methods) |> collect
+        dists[i, j] = distance(all_methods[i], all_methods[j])
+    end
+    dists
+end

src/distance.jl

@@ -0,0 +1,42 @@
+function distance_seqs(dist_func, x, y)
+    if length(x) > length(y)
+        x, y = y, x
+    end
+    diffs = minimum(Choose(length(x), length(y))) do y_ids
+        sum(enumerate(y_ids); init=0) do v
+            xid, yid = v
+            dist_func(x[xid], y[yid])
+        end
+    end
+    diffs / length(x)
+end
+
+function distance(x::MethodInfo, y::MethodInfo)::Float64
+    arg_types = if isempty(x.sig.types) || isempty(y.sig.types)
+        1
+    else
+        distance_seqs(x.sig.types, y.sig.types) do x_type, y_type
+            x_type == y_type
+        end
+    end
+    arg_names = if isempty(x.args) || isempty(y.args)
+        1
+    else
+        distance_seqs(x.args, y.args) do x_arg, y_arg
+            x_arg == y_arg
+        end
+    end
+    kwargs = if isempty(x.kwargs) || isempty(y.kwargs)
+        1
+    else
+        distance_seqs(x.kwargs, y.kwargs) do x_kw, y_kw
+            x_kw == y_kw
+        end
+    end
+
+    mean((arg_types, arg_names, kwargs))
+end
+
+function distance(x::Method, y::Method)
+    distance(get_method_info(x), get_method_info(y))
+end

src/method_info.jl

@@ -0,0 +1,40 @@
+struct MethodInfo
+    "type vars (maybe `TypeVar`s?)"
+    tv::Vector{Any}
+    "signature"
+    sig::Type
+    "argument names, including the function itself"
+    args::Vector{Symbol}
+    "keyword arguments"
+    kwargs::Vector{Symbol}
+    "definition location"
+    file::String
+    "definition location"
+    line::Int64
+end
+
+function get_method_info(m::Method)
+    tv = Any[]
+    sig = m.sig
+    while isa(sig, UnionAll)
+        push!(tv, sig.var)
+        sig = sig.body
+    end
+    file, line = Base.updated_methodloc(m)
+    argnames = Base.method_argnames(m)
+    if length(argnames) >= m.nargs
+        show_env = Base.ImmutableDict{Symbol,Any}()
+        for t in tv
+            show_env = Base.ImmutableDict(show_env, :unionall_env => t)
+        end
+        decls = Tuple{String,String}[Base.argtype_decl(show_env, argnames[i], sig, i, m.nargs, m.isva)
+                                     for i = 1:m.nargs]
+        # decls[1] = ("", sprint(Base.show_signature_function, Base.unwrapva(sig.parameters[1]), false, decls[1][1], html,
+        #                        context = show_env))
+    else
+        # decls = Tuple{String,String}[("", "") for i = 1:length(sig.parameters::SimpleVector)]
+    end
+    # return tv, decls, file, line
+    return MethodInfo(tv, sig, argnames, Base.kwarg_decl(m), file, line)
+end
+

src/utils/choose.jl

@@ -0,0 +1,46 @@
+struct Choose{M,N}
+	function Choose(m::Integer, n::Integer)
+		if m > n
+			m, n = n, m
+		end
+		new{m,n}()
+	end
+end
+
+function Base.iterate(::Choose{M,N}) where {M,N}
+    if M == 0
+        return nothing
+    end
+	ret = ntuple(identity, M)
+	ret, ret
+end
+
+function Base.iterate(::Choose{M,N}, state) where {M,N}
+	if state[1] == N - M + 1
+		return nothing
+	end
+	for (i, v) in Iterators.reverse(enumerate(state))
+		if v != N - M + i
+			ret = ntuple(M) do j
+				if j < i
+					state[j]
+				else
+					v + (j - i) + 1
+				end
+			end
+			return ret, ret
+		end
+	end
+	error("must not reachable")
+end
+
+Base.haslength(::Choose{M,N}) where {M,N} = Base.HasLength()
+
+function Base.length(::Choose{M,N}) where {M,N}
+	binomial(N, M)
+end
+
+function Base.eltype(::Choose{M,N}) where {M,N}
+	NTuple{M, Int64}
+end
+

test/runtests.jl

@@ -0,0 +1,7 @@
+using Test
+using MethodSimilarity
+
+@testset "Choose" begin
+    itr = MethodSimilarity.Choose(2, 3)
+    @test collect(itr) == [(1, 2), (1, 3), (2, 3)]
+end