adding basic test

.#scratch.jl

@@ -0,0 +1,5 @@
+XSym
+0040
+ab1f61d72a7b8770c9d0b5379dff8a6c
+jw@Js-MacBook-Air.local.22816:1704653445
+

Project.toml

@@ -4,10 +4,16 @@ authors = ["Jack R. Williams <contact@jackryanwilliams.com>"]
 version = "0.1.1"
 
 [deps]
-BenchmarkTools = "6e4b80f9-dd63-53aa-95a3-0cdb28fa8baf"
-CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
 PooledArrays = "2dfb63ee-cc39-5dd5-95bd-886bf059d720"
 StringDistances = "88034a9c-02f8-509d-84a9-84ec65e18404"
+
+[extras]
+BenchmarkTools = "6e4b80f9-dd63-53aa-95a3-0cdb28fa8baf"
+CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+Pkg = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
+
+[targets]
+test = ["Test", "CSV", "Pkg"]

src/fastlink/fastlink.jl

@@ -209,8 +209,7 @@ function fastLink(dfA::DataFrame, dfB::DataFrame,
 
     res=ResultMatrix(comparison_levels, (obs_a,obs_b))
 
-    fastlink_settings=FastLinkVars(varnames,res,vartypes,stringdist_method,jw_weight,
-                 cut_a,cut_p,upper_case,partials,fuzzy,comparison_levels)
+    fastlink_settings=FastLinkVars(varnames,res,vartypes,stringdist_method,jw_weight,cut_a,cut_p,upper_case,partials,fuzzy,comparison_levels)
 
 
 
@@ -223,7 +222,7 @@ function fastLink(dfA::DataFrame, dfB::DataFrame,
 
         # iterate through variables and execute function over them
         for i in eachindex(varnames)
-            @info "Now match $(varnames[i])"
+            @info "Now matching var $(varnames[i]) using $(match_method[i])"
             fastlink_settings.comparison_funs[i](dfA[!,varnames[i]],dfB[!,varnames[i]])
         end
 

src/gammas/gammaCKfuzzy.jl

@@ -224,7 +224,7 @@ function gammaCKfuzzy!(results::SubArray,array_2Dindex::Function,
             end
 
             query_len = UInt8(min(ncodeunits(query_name),16))
-            query_masks_lookup = maskify(query_name,query_len,space_char=0x40,max_char=max_char)
+            query_masks_lookup = maskify(query_name,query_len,space_char=space_char,max_char=max_char)
             query_partial = UInt16(1024 ÷ query_len)
             candidate_scores = deepcopy(base_candidate_scores)
 

test/runtests.jl

@@ -1,8 +1,43 @@
 
 using FastLink
 using Test
+import DataFrames: DataFrame
+import CSV
+import Pkg.Artifacts: @artifact_str
 
+a_fil = @artifact_str "dfA"
+b_fil = @artifact_str "dfB"
+
+dfA=CSV.read("$(a_fil)/dfA.csv", DataFrame,
+             ntasks=1,
+             pool=true,
+             missingstring=["", "NA"])
+dfB=CSV.read("$(b_fil)/dfB.csv", DataFrame,
+             ntasks=1,
+             pool=true,
+             missingstring=["", "NA"])
 
 @testset "FastLink.jl" begin
-    1 === 1
+    varnames = ["firstname","middlename", "lastname","housenum"]
+    cut_a = [0.92,0.92,0.92,1]
+    cut_p = [0.88,0.88,0.88,2]
+    match_method = ["string","string","string","float"]
+    partials = [true,true,false,true]
+    fuzzy = [true,false,true,false]
+    stringdist_method = ["jw","jw","jw",""]
+    upper_case = [false,false,false,false]
+    jw_weight = [0.1,0.1,0.1,0.0]
+
+    fastLink(dfA,dfB,varnames,
+             match_method=match_method,
+             partials=partials,
+             fuzzy=fuzzy,
+             upper_case=upper_case,
+             stringdist_method=stringdist_method,
+             cut_a=cut_a,
+             cut_p=cut_p,
+             jw_weight=jw_weight)()
+
+    println("completed")
+    return true
 end