Mix format

botsquad · Mar 7, 2024 · 9ef48e4 · 9ef48e4
1 parent 41a2b68
commit 9ef48e4
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 5 deletions.
diff --git a/lib/bubble_match/parser.ex b/lib/bubble_match/parser.ex
@@ -9,7 +9,7 @@ defmodule BubbleMatch.Parser do
   @ws [9, 10, 11, 12, 13, 32]
   ws = ignore(utf8_string(@ws, min: 1))
 
-  special_chars = '`~!@#$%^&*()_+=-{}|\\][\';":?><,./' ++ @ws
+  special_chars = ~c"`~!@#$%^&*()_+=-{}|\\][';\":?><,./" ++ @ws
 
   string = utf8_string(Enum.map(special_chars, &{:not, &1}), min: 1)
 

diff --git a/lib/bubble_match/unidekode.ex b/lib/bubble_match/unidekode.ex
@@ -44,6 +44,9 @@ defmodule BubbleMatch.Unidekode do
 
       iex> BubbleMatch.Unidekode.drop_accented("código 👍")
       "codigo 👍"
+
+      iex> BubbleMatch.Unidekode.drop_accented("éé немає 👍")
+      "ee немає 👍"
   """
   @spec drop_accented(binary()) :: binary()
   def drop_accented(string), do: drop_accented(string, <<>>)
@@ -92,7 +95,7 @@ defmodule BubbleMatch.Unidekode do
            end)
            |> Stream.concat(
              for x <-
-                   '!"#%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\s\t\n',
+                   ~c"!\"#%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\s\t\n",
                  do: {x, <<x>>}
            )
            |> Enum.uniq()

diff --git a/test/bubble_match/sentence_test.exs b/test/bubble_match/sentence_test.exs
@@ -142,9 +142,9 @@ defmodule BubbleMatch.SentenceTest do
   end
 
   @spacy_json2 """
-              {"detected_language": null, "detected_language_prob": 0.12450417876243591, "ents": [], "nlp_language": "en", "sents": [{"end": 8, "start": 0}], "text": "Thanks 8", "tokens": [{"dep": "compound", "end": 6, "head": 1, "id": 0, "lemma": "thanks", "norm": "thanks", "pos": "INTJ", "start": 0, "string": "Thanks ", "tag": "UH"}, {"dep": "ROOT", "end": 8, "head": 1, "id": 1, "lemma": "8", "norm": "8", "pos": "PROPN", "start": 7, "string": "8", "tag": "NNP"}]}
-              """
-              |> Jason.decode!()
+               {"detected_language": null, "detected_language_prob": 0.12450417876243591, "ents": [], "nlp_language": "en", "sents": [{"end": 8, "start": 0}], "text": "Thanks 8", "tokens": [{"dep": "compound", "end": 6, "head": 1, "id": 0, "lemma": "thanks", "norm": "thanks", "pos": "INTJ", "start": 0, "string": "Thanks ", "tag": "UH"}, {"dep": "ROOT", "end": 8, "head": 1, "id": 1, "lemma": "8", "norm": "8", "pos": "PROPN", "start": 7, "string": "8", "tag": "NNP"}]}
+               """
+               |> Jason.decode!()
 
   test "Emoji false positive" do
     s = %{tokenizations: [_]} = Sentence.from_spacy(@spacy_json2)