extract

README.md

@@ -100,12 +100,12 @@ evaluate(Levenshtein(), "New York", "New York")
 ```
 
 ## Extract
-An experimental `extract` funciton finds the best match in an iterator of AbstractStrings:
+On master, there is an experimental `extract` function that returns the best match in an iterator of AbstractStrings:
 ```julia
 extract("New York", ["NewYork", "Newark", "San Francisco"], Levenshtein())
 #> "NewYork"
 ```
-The function works for `Levenshtein`, `DamerauLevenshtein`, possibly modified by `Partial`, `TokenSort`, `TokenSet`, `TokenMax`
+The function is particularly fast for `Levenshtein` and `DamerauLevenshtein` distances (potentially modified by `Partial`, `TokenSort`, `TokenSet`, or `TokenMax`)
 
 ## Which distance should I use?
 

benchmark/benchmark.jl

@@ -19,6 +19,10 @@ end
 @time f(DamerauLevenshtein(), x, y, min_dist = 0.8)
 # 0.39s.  Much faster than StringDist
 
+@time extract.(x[1:10], Ref(y), Ref(DamerauLevenshtein()))
+
+
+
 function g(t, x, y)
     [evaluate(t, x[i], y[i]) for i in 1:length(x)]
 end

src/compare.jl

@@ -246,7 +246,21 @@ function extract(s1::AbstractString, iter_s2, dist::Union{T, Partial{T}, TokenSo
     end
     return best_s2
 end
-function extract(::Missing, iter_s2, dist::Union{T, Partial{T}, TokenSort{T}, TokenSet{T}, TokenMax{T}}) where T <: Union{Levenshtein, DamerauLevenshtein}
-    missing
+function extract(s1::AbstractString, iter_s2, dist::PreMetric)
+    best_score = 0.0
+    best_s2 = nothing
+    for s2 in iter_s2
+        score = compare(s1, s2, dist)
+        if (score !== missing) && (score > best_score)
+            best_s2 = s2
+            best_score = score
+        end
+    end
+    return best_s2
+end
+
+
+function extract(::Missing, iter_s2, dist::PreMetric)
+    return missing
 end
 

test/modifiers.jl

@@ -152,6 +152,7 @@ dist = QGram(2)
 
 # check extract
 @test extract("New York", ["NewYork", "Newark", "San Francisco"], Levenshtein()) == "NewYork"
+@test extract("New York", ["NewYork", "Newark", "San Francisco"], Jaro()) == "NewYork"
 @test extract("New York", ["NewYork", "Newark", missing], Levenshtein()) == "NewYork"
 @test extract("New York", [missing, "NewYork", "Newark"], Levenshtein()) == "NewYork"