Add access to count based collocations
Change-Id: I47b3176285974b65ec8cc2e5871892ef0d104e7b
diff --git a/test/Artifacts.toml b/test/Artifacts.toml
index 6e07db6..003db48 100644
--- a/test/Artifacts.toml
+++ b/test/Artifacts.toml
@@ -1,6 +1,6 @@
[wpd19_10000]
-git-tree-sha1 = "b4e4b99c090cdf72d6c8d1377f2d99259f8184ac"
+git-tree-sha1 = "6da73dbb0ceae824285c607ed25d3903552c6d43"
[[wpd19_10000.download]]
- sha256 = "c305219849482ffc7f01471bd8a23e16c321a35768f7568c6cbd35fece0e0171"
- url = "https://korap.ids-mannheim.de/data/wpd19_10000.tar.bz2"
+ sha256 = "5df533a2a1031a0a9b3a2de5a5e7b02690f06bb1c057ae05b01724b9d3b17bb1"
+ url = "https://korap.ids-mannheim.de/data/wpd19_10000.tar.gz"
diff --git a/test/runtests.jl b/test/runtests.jl
index e0ff466..bc29554 100644
--- a/test/runtests.jl
+++ b/test/runtests.jl
@@ -41,4 +41,14 @@
@test wpd19.total_tokens == wpd19_freqlist.total_tokens
@test isapprox(kld(wpd19_freqlist, wpd19).kld, 0)
end
+
+ @testset "DerekoVecs.jl: collocation analysis" begin
+ if (!isnothing(wpd19.cdb))
+ println(wpd19.vocab[30])
+ coll = get_collocates(wpd19, "werden")
+ @test coll[1].ldaf > 10
+ @test coll[1].ldaf > coll[3].ldaf
+ end
+ end
+
end