mirrors
/
StringDistances.jl
mirror of https://github.com/matthieugomez/StringDistances.jl.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Update find.jl

pull/22/head
matthieugomez 2019-12-13 09:32:23 -05:00
parent bd26ecd1d5
commit ef044b04a5
1 changed files with 25 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
src/find.jl
View File

@ -1,37 +1,50 @@
"""
findmax(s::AbstractString, itr, dist::StringDistance; min_score = 0.0)
findmax(s::AbstractString, itr, dist::StringDistance; min_score = 0.0) -> (x, index)
`findmax` returns the value and index of the element of `itr` that has the
highest similarity score with `s` according to the distance `dist`.
It returns `(nothing, nothing)` if none of the elements has a similarity score
higher or equal to `min_score` (default to 0.0)
higher or equal to `min_score` (default to 0.0).
The function is optimized for `Levenshtein` and `DamerauLevenshtein` distances
(potentially modified by `Partial`, `TokenSort`, `TokenSet`, or `TokenMax`)
(as well as their modifications via `Partial`, `TokenSort`, `TokenSet`, or `TokenMax`).
"""
function Base.findmax(s::AbstractString, itr, dist::StringDistance; min_score = 0.0)
vmin = Threads.Atomic{typeof(min_score)}(min_score)
vs = [0.0 for _ in 1:Threads.nthreads()]
min_score = Threads.Atomic{typeof(min_score)}(min_score)
scores = [0.0 for _ in 1:Threads.nthreads()]
is = [0 for _ in 1:Threads.nthreads()]
Threads.@threads for i in collect(keys(itr))
v = compare(s, itr[i], dist; min_score = vmin[])
v_old = Threads.atomic_max!(vmin, v)
if v >= v_old
vs[Threads.threadid()] = v
score = compare(s, itr[i], dist; min_score = min_score[])
score_old = Threads.atomic_max!(min_score, score)
if score >= score_old
scores[Threads.threadid()] = score
is[Threads.threadid()] = i
end
end
imax = is[argmax(vs)]
imax = is[argmax(scores)]
imax == 0 ? (nothing, nothing) : (itr[imax], imax)
end
"""
argmax(s::AbstractString, itr, dist::StringDistance; min_score = 0.0)
`argmax` returns the index of the element of `itr` that has the
highest similarity score with `s` according to the distance `dist`.
It returns `nothing` if none of the elements has a similarity score
higher or equal to `min_score` (default to 0.0).
The function is optimized for `Levenshtein` and `DamerauLevenshtein` distances
(potentially modified by `Partial`, `TokenSort`, `TokenSet`, or `TokenMax`)
"""
function Base.argmax(s::AbstractString, itr, dist::StringDistance; min_score = 0.0)
findmax(s, itr, dist; min_score = min_score)[2]
end
"""
findall(s::AbstractString, itr, dist::StringDistance; min_score = 0.8)
`findall` returns the vector of indices for elements of `itr` that have a
similarity score higher or equal than `min_score` according to the distance `dist`.
similarity score higher or equal than `min_score` according to the distance `dist`.
If there are no such elements, return an empty array.
The function is optimized for `Levenshtein` and `DamerauLevenshtein` distances
(potentially modified by `Partial`, `TokenSort`, `TokenSet`, or `TokenMax`)
(as well as their modifications via `Partial`, `TokenSort`, `TokenSet`, or `TokenMax`).
"""
function Base.findall(s::AbstractString, itr, dist::StringDistance; min_score = 0.8)
out = [Int[] for _ in 1:Threads.nthreads()]