First commit

.formatter.exs

@@ -0,0 +1,4 @@
+# Used by "mix format"
+[
+  inputs: ["{mix,.formatter}.exs", "{config,lib,test}/**/*.{ex,exs}"]
+]

.github/workflows/elixir.yml

@@ -14,8 +14,8 @@ jobs:
     runs-on: ubuntu-20.04
     strategy:
       matrix:
-        otp: ["25.1"]
-        elixir: ["1.14.2"]
+        elixir: ["1.14.3"]
+        otp: ["23.3", "24.3.4", "25.2.3"]
     steps:
       - uses: actions/checkout@v3
       - name: Set up Elixir

.gitignore

@@ -1,10 +1,26 @@
-/_build
-/cover
-/deps
-/doc
+# The directory Mix will write compiled artifacts to.
+/_build/
+
+# If you run "mix test --cover", coverage assets end up here.
+/cover/
+
+# The directory Mix downloads your dependencies sources to.
+/deps/
+
+# Where third-party dependencies like ExDoc output generated docs.
+/doc/
+
+# Ignore .fetch files in case you like to edit your project deps locally.
 /.fetch
+
+# If the VM crashes, it generates a dump, let's ignore it too.
 erl_crash.dump
+
+# Also ignore archive artifacts (built via "mix archive.build").
 *.ez
-*.beam
-/config/*.secret.exs
-.elixir_ls/
+
+# Ignore package tarball (built via "mix hex.build").
+vasov-*.tar
+
+# Temporary files, for example, from tests.
+/tmp/

README.md

@@ -0,0 +1,32 @@
+# Vasov
+
+![Elixir CI](https://github.com/Efesto/vasov/workflows/Elixir%20CI/badge.svg)
+[![Hex pm](https://img.shields.io/hexpm/v/vasov.svg?style=flat)](https://hex.pm/packages/vasov)
+[![Hexdocs.pm](https://img.shields.io/badge/hex-docs-lightgreen.svg)](https://hexdocs.pm/vasov/)
+
+Transliterates from bulgarian cyrillic to latin.
+
+The name is an homage to [Ivan Vazov (Иван Вазов)](https://en.wikipedia.org/wiki/Ivan_Vazov).
+
+## Installation
+
+The package can be installed by adding `vasov` to your list of dependencies in `mix.exs`:
+
+```elixir
+def deps do
+  [
+    {:vasov, "~> 0.1.0"}
+  ]
+end
+```
+
+## Usage
+
+```Elixir
+iex> Vasov.transliterate_to_latin("Бургас")
+"Burgas"
+iex> Vasov.transliterate_to_latin("София")
+"Sofia"
+iex> Vasov.transliterate_to_latin("България")
+"Bulgaria"
+```

lib/vasov.ex

@@ -0,0 +1,122 @@
+defmodule Vasov do
+  @moduledoc """
+  Transliterates from bulgarian cyrillic to roman latin
+
+  The transliteration implements the [streamlined system](https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/1105090/ROMANIZATION_OF_BULGARIAN_with_examples.pdf)
+  officially adopted in Bulgaria.
+  """
+  @bg_to_latin %{
+    "Р" => "R",
+    "з" => "z",
+    "Т" => "T",
+    "Ш" => "Sh",
+    "т" => "t",
+    "А" => "A",
+    "ч" => "ch",
+    "р" => "r",
+    "И" => "I",
+    "Ь" => "Y",
+    "м" => "m",
+    "ц" => "ts",
+    "Е" => "E",
+    "щ" => "sht",
+    "У" => "U",
+    "Л" => "L",
+    "Ч" => "Ch",
+    "н" => "n",
+    "Й" => "Y",
+    "Ж" => "Zh",
+    "о" => "o",
+    "Ю" => "Yu",
+    "ь" => "y",
+    "Б" => "B",
+    "х" => "h",
+    "г" => "g",
+    "ш" => "sh",
+    "л" => "l",
+    "Ц" => "Ts",
+    "П" => "P",
+    "в" => "v",
+    "К" => "K",
+    "с" => "s",
+    "ъ" => "a",
+    "С" => "S",
+    "ж" => "zh",
+    "ф" => "f",
+    "д" => "d",
+    "Х" => "H",
+    "а" => "a",
+    "б" => "b",
+    "Я" => "Ya",
+    "М" => "M",
+    "й" => "y",
+    "у" => "u",
+    "п" => "p",
+    "Г" => "G",
+    "О" => "O",
+    "ю" => "yu",
+    "е" => "e",
+    "к" => "k",
+    "Н" => "N",
+    "я" => "ya",
+    "В" => "V",
+    "Ъ" => "A",
+    "Ф" => "F",
+    "и" => "i",
+    "З" => "Z",
+    "Д" => "D",
+    "Щ" => "Sht"
+  }
+
+  @doc """
+  Transliterates a text from bulgarian cyrillic language to roman latin
+
+  Usage:
+  ```
+  iex> Vasov.transliterate_to_latin("Бургас")
+  "Burgas"
+  iex> Vasov.transliterate_to_latin("София")
+  "Sofia"
+  iex> Vasov.transliterate_to_latin("България")
+  "Bulgaria"
+  ```
+  """
+  def transliterate_to_latin(text) do
+    text
+    |> normalize()
+    |> String.graphemes()
+    |> Enum.reduce("", fn
+      original, acc -> acc <> Map.get(@bg_to_latin, original, original)
+    end)
+  end
+
+  defp normalize(text) do
+    text
+    |> normalize_state_name()
+    |> normalize_final_ya()
+  end
+
+  defp normalize_state_name(text) do
+    Regex.replace(~r/^(б)(ъ)(лгария)/ui, text, fn _word, token_1, ua_token, token_2 ->
+      replacement =
+        case ua_token do
+          "ъ" -> "у"
+          "Ъ" -> "У"
+        end
+
+      token_1 <> replacement <> token_2
+    end)
+  end
+
+  defp normalize_final_ya(text) do
+    Regex.replace(~r/^(.+и)(я)\b/ui, text, fn _word, word, ending ->
+      replacement =
+        case ending do
+          "я" -> "а"
+          "Я" -> "А"
+        end
+
+      word <> replacement
+    end)
+  end
+end

mix.exs

@@ -0,0 +1,38 @@
+defmodule Vasov.MixProject do
+  use Mix.Project
+
+  def project do
+    [
+      app: :vasov,
+      version: "0.1.0",
+      elixir: "~> 1.14",
+      start_permanent: Mix.env() == :prod,
+      deps: deps(),
+      docs: docs()
+    ]
+  end
+
+  def application do
+    [
+      extra_applications: [:logger]
+    ]
+  end
+
+  defp docs do
+    [
+      main: "Vasov",
+      source_ref: "master",
+      source_url: "https://github.com/Efesto/vasov",
+      extras: ["README.md"]
+    ]
+  end
+
+  defp deps do
+    [
+      {:credo, "~> 1.6", only: [:dev, :test], runtime: false},
+      {:mix_audit, "~> 2.0", only: [:dev, :test], runtime: false},
+      {:ex_doc, ">= 0.0.0", only: :dev, runtime: false},
+      {:mix_test_interactive, "~> 1.0", only: :dev, runtime: false}
+    ]
+  end
+end

mix.lock

@@ -0,0 +1,17 @@
+%{
+  "bunt": {:hex, :bunt, "0.2.1", "e2d4792f7bc0ced7583ab54922808919518d0e57ee162901a16a1b6664ef3b14", [:mix], [], "hexpm", "a330bfb4245239787b15005e66ae6845c9cd524a288f0d141c148b02603777a5"},
+  "credo": {:hex, :credo, "1.6.7", "323f5734350fd23a456f2688b9430e7d517afb313fbd38671b8a4449798a7854", [:mix], [{:bunt, "~> 0.2.1", [hex: :bunt, repo: "hexpm", optional: false]}, {:file_system, "~> 0.2.8", [hex: :file_system, repo: "hexpm", optional: false]}, {:jason, "~> 1.0", [hex: :jason, repo: "hexpm", optional: false]}], "hexpm", "41e110bfb007f7eda7f897c10bf019ceab9a0b269ce79f015d54b0dcf4fc7dd3"},
+  "earmark_parser": {:hex, :earmark_parser, "1.4.30", "0b938aa5b9bafd455056440cdaa2a79197ca5e693830b4a982beada840513c5f", [:mix], [], "hexpm", "3b5385c2d36b0473d0b206927b841343d25adb14f95f0110062506b300cd5a1b"},
+  "ex_doc": {:hex, :ex_doc, "0.29.1", "b1c652fa5f92ee9cf15c75271168027f92039b3877094290a75abcaac82a9f77", [:mix], [{:earmark_parser, "~> 1.4.19", [hex: :earmark_parser, repo: "hexpm", optional: false]}, {:makeup_elixir, "~> 0.14", [hex: :makeup_elixir, repo: "hexpm", optional: false]}, {:makeup_erlang, "~> 0.1", [hex: :makeup_erlang, repo: "hexpm", optional: false]}], "hexpm", "b7745fa6374a36daf484e2a2012274950e084815b936b1319aeebcf7809574f6"},
+  "file_system": {:hex, :file_system, "0.2.10", "fb082005a9cd1711c05b5248710f8826b02d7d1784e7c3451f9c1231d4fc162d", [:mix], [], "hexpm", "41195edbfb562a593726eda3b3e8b103a309b733ad25f3d642ba49696bf715dc"},
+  "jason": {:hex, :jason, "1.4.0", "e855647bc964a44e2f67df589ccf49105ae039d4179db7f6271dfd3843dc27e6", [:mix], [{:decimal, "~> 1.0 or ~> 2.0", [hex: :decimal, repo: "hexpm", optional: true]}], "hexpm", "79a3791085b2a0f743ca04cec0f7be26443738779d09302e01318f97bdb82121"},
+  "makeup": {:hex, :makeup, "1.1.0", "6b67c8bc2882a6b6a445859952a602afc1a41c2e08379ca057c0f525366fc3ca", [:mix], [{:nimble_parsec, "~> 1.2.2 or ~> 1.3", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm", "0a45ed501f4a8897f580eabf99a2e5234ea3e75a4373c8a52824f6e873be57a6"},
+  "makeup_elixir": {:hex, :makeup_elixir, "0.16.0", "f8c570a0d33f8039513fbccaf7108c5d750f47d8defd44088371191b76492b0b", [:mix], [{:makeup, "~> 1.0", [hex: :makeup, repo: "hexpm", optional: false]}, {:nimble_parsec, "~> 1.2.3", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm", "28b2cbdc13960a46ae9a8858c4bebdec3c9a6d7b4b9e7f4ed1502f8159f338e7"},
+  "makeup_erlang": {:hex, :makeup_erlang, "0.1.1", "3fcb7f09eb9d98dc4d208f49cc955a34218fc41ff6b84df7c75b3e6e533cc65f", [:mix], [{:makeup, "~> 1.0", [hex: :makeup, repo: "hexpm", optional: false]}], "hexpm", "174d0809e98a4ef0b3309256cbf97101c6ec01c4ab0b23e926a9e17df2077cbb"},
+  "mix_audit": {:hex, :mix_audit, "2.1.0", "3c0dafb29114dffcdb508164a3d35311a9ac2c5baeba6495c9cd5315c25902b9", [:make, :mix], [{:jason, "~> 1.1", [hex: :jason, repo: "hexpm", optional: false]}, {:yaml_elixir, "~> 2.9", [hex: :yaml_elixir, repo: "hexpm", optional: false]}], "hexpm", "14c57a23e0a5f652c1e7f6e8dab93f166f66d63bd0c85f97278f5972b14e2be0"},
+  "mix_test_interactive": {:hex, :mix_test_interactive, "1.2.2", "72f72faa7007d6cb9634ee5f6989b25ee5b194c5729e5e45a962e68b2e217374", [:mix], [{:file_system, "~> 0.2", [hex: :file_system, repo: "hexpm", optional: false]}, {:typed_struct, "~> 0.3.0", [hex: :typed_struct, repo: "hexpm", optional: false]}], "hexpm", "f49f2a70d00aee93418506dde4d95387fe56bdba501ef9d2aa06ea07d4823508"},
+  "nimble_parsec": {:hex, :nimble_parsec, "1.2.3", "244836e6e3f1200c7f30cb56733fd808744eca61fd182f731eac4af635cc6d0b", [:mix], [], "hexpm", "c8d789e39b9131acf7b99291e93dae60ab48ef14a7ee9d58c6964f59efb570b0"},
+  "typed_struct": {:hex, :typed_struct, "0.3.0", "939789e3c1dca39d7170c87f729127469d1315dcf99fee8e152bb774b17e7ff7", [:mix], [], "hexpm", "c50bd5c3a61fe4e198a8504f939be3d3c85903b382bde4865579bc23111d1b6d"},
+  "yamerl": {:hex, :yamerl, "0.10.0", "4ff81fee2f1f6a46f1700c0d880b24d193ddb74bd14ef42cb0bcf46e81ef2f8e", [:rebar3], [], "hexpm", "346adb2963f1051dc837a2364e4acf6eb7d80097c0f53cbdc3046ec8ec4b4e6e"},
+  "yaml_elixir": {:hex, :yaml_elixir, "2.9.0", "9a256da867b37b8d2c1ffd5d9de373a4fda77a32a45b452f1708508ba7bbcb53", [:mix], [{:yamerl, "~> 0.10", [hex: :yamerl, repo: "hexpm", optional: false]}], "hexpm", "0cb0e7d4c56f5e99a6253ed1a670ed0e39c13fc45a6da054033928607ac08dfc"},
+}

test/test_helper.exs

@@ -0,0 +1 @@
+ExUnit.start()

test/vasov_test.exs

@@ -0,0 +1,89 @@
+defmodule VasovTest do
+  use ExUnit.Case
+
+  doctest Vasov
+
+  describe "transliterate_to_latin/1" do
+    test "transliterates from bulgarian cyrillic to latin" do
+      Enum.each(
+        [
+          {"основните", "osnovnite"},
+          {"Асеновград", "Asenovgrad"},
+          {"Враца", "Vratsa"},
+          {"Габрово", "Gabrovo"},
+          {"Добрич", "Dobrich"},
+          {"Елхово", "Elhovo"},
+          {"Кърджали", "Kardzhali"},
+          {"Златица", "Zlatitsa"},
+          {"Исперих", "Isperih"},
+          {"Айтос", "Aytos"},
+          {"Казанлък", "Kazanlak"},
+          {"Ловеч", "Lovech"},
+          {"Монтана", "Montana"},
+          {"Никопол", "Nikopol"},
+          {"Омуртаг", "Omurtag"},
+          {"Пловдив", "Plovdiv"},
+          {"Разград", "Razgrad"},
+          {"Твърдица", "Tvarditsa"},
+          {"Угърчин", "Ugarchin"},
+          {"Хасково", "Haskovo"},
+          {"Царево", "Tsarevo"},
+          {"Чирпан", "Chirpan"},
+          {"Шумен", "Shumen"},
+          {"Търговище", "Targovishte"},
+          {"Гълъбово", "Galabovo"},
+          {"каньон", "kanyon"},
+          {"Кюстендил", "Kyustendil"},
+          {"Ямбол", "Yambol"},
+          {"мира", "mira"},
+          {"Софиа е ного красива", "Sofia e nogo krasiva"},
+          {"Аз обичам лутеница", "Az obicham lutenitsa"},
+          {"Ти си чувек", "Ti si chuvek"},
+          {"хелло Маик, хелло Джое", "hello Maik, hello Dzhoe"}
+        ],
+        fn {word, trans} ->
+          assert_transliteration(trans, word)
+        end
+      )
+    end
+
+    test "when ия is in final position is transliterated with ia" do
+      Enum.each(
+        [
+          {"Пияница", "Piyanitsa"},
+          {"Катия", "Katia"},
+          {"СофИя", "SofIa"},
+          {"СофиЯ", "SofiA"},
+          {"фият", "fiyat"},
+          {"София-Град", "Sofia-Grad"}
+        ],
+        fn {word, trans} ->
+          assert_transliteration(trans, word)
+        end
+      )
+    end
+
+    test "България is always transliterated in Bulgaria" do
+      Enum.each(
+        [
+          {"българия", "bulgaria"},
+          {"бУлГариЯ", "bUlGariA"},
+          {"България-град", "Bulgaria-grad"},
+          {"Българияград", "Bulgariyagrad"},
+          {"Сбългария", "Sbalgaria"}
+        ],
+        fn {word, trans} ->
+          assert_transliteration(trans, word)
+        end
+      )
+    end
+
+    test "does not transliterate latin letters" do
+      assert_transliteration("bulgaria", "bulgaria")
+    end
+
+    defp assert_transliteration(expected, original) do
+      assert expected == Vasov.transliterate_to_latin(original)
+    end
+  end
+end