Merge pull request #24 from fireproofsocks/general-update

General update to 0.6.0

Author: minibikini

CHANGELOG.md

@@ -22,3 +22,20 @@
 ### Changed
 
 - Update language data
+
+## 0.6.0 - 2022-06-10
+
+### Added
+
+- Adds parsing of the `data.js` file to `generate_language_data.exs` script.
+
+### Changed
+
+- Updates `languages_url` target in `generate_language_data.exs` script so it downloads `data.js` (the old `data.json` file was removed in <https://github.com/wooorm/franc/commit/556d2a7ba3375cb04e7f6a94b4f5b540b55e9488>)
+- Refactors script to use `:jsx.decode()` to decode the JSON instead of `Jason` because `Jason` is not a direct dependency of `paasaa`.
+- Updates `languages.ex` and `scripts.ex` to reflect latest changes in <https://github.com/wooorm/franc/> package per the updated `data.js` file.
+- Manually updates `fixtures.ex` to include the latest fixture data.
+- Updates all hex dependencies to latest.
+- Updates doctests to reflect statistical changes due to language updates.
+- Updates tests to utilize modified fixture structure.
+- Updates tests to assert on all available languages/fixtures for minimum 98% certainty (instead of limiting the test coverage to the first 10 languages)

README.md

@@ -15,7 +15,7 @@ Add `paasaa` to your list of dependencies in `mix.exs`:
 
 ```elixir
 def deps do
-  [{:paasaa, "~> 0.5.0"}]
+  [{:paasaa, "~> 0.6.0"}]
 end
 ```
 

lib/paasaa.ex

@@ -90,10 +90,10 @@ defmodule Paasaa do
       iex> Paasaa.all("Detect this!") |> Enum.take(5)
       [
         {"eng", 1.0},
-        {"sco", 0.8675529295913343},
-        {"nob", 0.6065977351058591},
-        {"swe", 0.5923190546528804},
-        {"nno", 0.5534219596258001}
+        {"sco", 0.8230731943771207},
+        {"nob", 0.6030053320407174},
+        {"nno", 0.5525933107125545},
+        {"swe", 0.508482792050412}
       ]
   """
 

lib/paasaa/languages.ex

@@ -3,38 +3,38 @@ defmodule Paasaa.Scripts do
 
   @data %{
     "Arabic" =>
-      "[؀-؄؆-؋؍-ؚ؜؞ؠ-ؿف-يٖ-ٯٱ-ۜ۞-ۿݐ-ݿࢠ-ࢴࢶ-ࢽ࣓-ࣣ࣡-ࣿﭐ-﯁ﯓ-ﴽﵐ-ﶏﶒ-ﷇﷰ-﷽ﹰ-ﹴﹶ-ﻼ]|�[�-�]|�[�-��-������-��-��������-�������������-��-��-��-���-��-��-��-��-���]",
+      "[؀-؄؆-؋؍-ؚ؜-؞ؠ-ؿف-يٖ-ٯٱ-ۜ۞-ۿݐ-ݿࡰ-ࢎ࢐࢑࢘-ࣣ࣡-ࣿﭐ-﯂ﯓ-ﴽ﵀-ﶏﶒ-ﷇ﷏ﷰ-﷿ﹰ-ﹴﹶ-ﻼ]|�[�-�]|�[�-��-������-��-��������-�������������-��-��-��-���-��-��-��-��-���]",
     "Cyrillic" => "[Ѐ-҄҇-ԯᲀ-ᲈᴫᵸⷠ-ⷿꙀ-ꚟ︮︯]",
     "Devanagari" => "[ऀ-ॐॕ-ॣ०-ॿ꣠-ꣿ]",
     "Ethiopic" =>
-      "[ሀ-ቈቊ-ቍቐ-ቖቘቚ-ቝበ-ኈኊ-ኍነ-ኰኲ-ኵኸ-ኾዀዂ-ዅወ-ዖዘ-ጐጒ-ጕጘ-ፚ፝-፼ᎀ-᎙ⶀ-ⶖⶠ-ⶦⶨ-ⶮⶰ-ⶶⶸ-ⶾⷀ-ⷆⷈ-ⷎⷐ-ⷖⷘ-ⷞꬁ-ꬆꬉ-ꬎꬑ-ꬖꬠ-ꬦꬨ-ꬮ]",
+      "[ሀ-ቈቊ-ቍቐ-ቖቘቚ-ቝበ-ኈኊ-ኍነ-ኰኲ-ኵኸ-ኾዀዂ-ዅወ-ዖዘ-ጐጒ-ጕጘ-ፚ፝-፼ᎀ-᎙ⶀ-ⶖⶠ-ⶦⶨ-ⶮⶰ-ⶶⶸ-ⶾⷀ-ⷆⷈ-ⷎⷐ-ⷖⷘ-ⷞꬁ-ꬆꬉ-ꬎꬑ-ꬖꬠ-ꬦꬨ-ꬮ]|�[�-��-����-�]",
     "Hebrew" => "[֑-ׇא-תׯ-״יִ-זּטּ-לּמּנּסּףּפּצּ-ﭏ]",
     "Latin" =>
-      "[A-Za-z\\xAA\\xBA\\xC0-\\xD6\\xD8-\\xF6\\xF8-ʸˠ-ˤᴀ-ᴥᴬ-ᵜᵢ-ᵥᵫ-ᵷᵹ-ᶾḀ-ỿⁱⁿₐ-ₜKÅℲⅎⅠ-ↈⱠ-ⱿꜢ-ꞇꞋ-ꞿꟂ-Ᶎꟷ-ꟿꬰ-ꭚꭜ-ꭤꭦꭧff-stＡ-Ｚａ-ｚ]",
+      "[A-Za-zªºÀ-ÖØ-öø-ʸˠ-ˤᴀ-ᴥᴬ-ᵜᵢ-ᵥᵫ-ᵷᵹ-ᶾḀ-ỿⁱⁿₐ-ₜKÅℲⅎⅠ-ↈⱠ-ⱿꜢ-ꞇꞋ-ꟊꟐꟑꟓꟕ-ꟙꟲ-ꟿꬰ-ꭚꭜ-ꭤꭦ-ꭩff-stＡ-Ｚａ-ｚ]|�[�-��-��-�]|�[�-�]",
     "Myanmar" => "[က-႟ꧠ-ꧾꩠ-ꩿ]",
     "aii" => "[܀-܍܏-݊ݍ-ݏࡠ-ࡪ]",
     "ben" => "[ঀ-ঃঅ-ঌএঐও-নপ-রলশ-হ়-ৄেৈো-ৎৗড়ঢ়য়-ৣ০-৾]",
     "bod" => "[ༀ-ཇཉ-ཬཱ-ྗྙ-ྼ྾-࿌࿎-࿔࿙࿚]",
     "cmn" =>
-      "[⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〻㐀-䶵一-鿯豈-舘並-龎]|[�-��-��-��-�][�-�]|�[�-��-�]|�[�-��-�]|�[�-��-�]|�[�-��-�]|�[�-�]|�[�-�]",
+      "[⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〻㐀-䶿一-鿿豈-舘並-龎]|�[����]|[�-��-��-��-��-�][�-�]|�[�-��-�]|�[�-��-�]|�[�-��-�]|�[�-��-�]|�[�-�]|�[�-�]|�[�-�]",
     "ell" =>
       "[Ͱ-ͳ͵-ͷͺ-ͽͿ΄ΆΈ-ΊΌΎ-ΡΣ-ϡϰ-Ͽᴦ-ᴪᵝ-ᵡᵦ-ᵪᶿἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ῄῆ-ΐῖ-Ί῝-`ῲ-ῴῶ-῾Ωꭥ]|�[�-��]|�[�-�]",
     "guj" => "[ઁ-ઃઅ-ઍએ-ઑઓ-નપ-રલળવ-હ઼-ૅે-ૉો-્ૐૠ-ૣ૦-૱ૹ-૿]",
-    "hye" => "[Ա-Ֆՙ-ֈ֊֍-֏ﬓ-ﬗ]",
+    "hye" => "[Ա-Ֆՙ-֊֍-֏ﬓ-ﬗ]",
     "iii" => "[ꀀ-ꒌ꒐-꓆]",
-    "jpn" => "[ぁ-ゖゝ-ゟ]|�[�-��-�]|🈀|[ァ-ヺヽ-ヿㇰ-ㇿ㋐-㋾㌀-㍗ｦ-ｯｱ-ﾝ]|�[��-�]|[㐀-䶵一-龯]",
-    "kan" => "[ಀ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ಼-ೄೆ-ೈೊ-್ೕೖೞೠ-ೣ೦-೯ೱೲ]",
+    "jav" => "[ꦀ-꧍꧐-꧙꧞꧟]",
+    "jpn" => "[ぁ-ゖゝ-ゟ]|�[�-��-�]|🈀|[ァ-ヺヽ-ヿㇰ-ㇿ㋐-㋾㌀-㍗ｦ-ｯｱ-ﾝ]|�[�-��-���]|�[��-��-�]|[㐀-䶵一-龯]",
+    "kan" => "[ಀ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ಼-ೄೆ-ೈೊ-್ೕೖೝೞೠ-ೣ೦-೯ೱೲ]",
     "kat" => "[Ⴀ-ჅჇჍა-ჺჼ-ჿᲐ-ᲺᲽ-Ჿⴀ-ⴥⴧⴭ]",
     "khm" => "[ក-៝០-៩៰-៹᧠-᧿]",
     "kor" => "[ᄀ-ᇿ〮〯ㄱ-ㆎ㈀-㈞㉠-㉾ꥠ-ꥼ가-힣ힰ-ퟆퟋ-ퟻﾠ-ﾾￂ-ￇￊ-ￏￒ-ￗￚ-ￜ]",
     "lao" => "[ກຂຄຆ-ຊຌ-ຣລວ-ຽເ-ໄໆ່-ໍ໐-໙ໜ-ໟ]",
-    "mal" => "[ഀ-ഃഅ-ഌഎ-ഐഒ-ൄെ-ൈൊ-൏ൔ-ൣ൦-ൿ]",
-    "ori" => "[ଁ-ଃଅ-ଌଏଐଓ-ନପ-ରଲଳଵ-ହ଼-ୄେୈୋ-୍ୖୗଡ଼ଢ଼ୟ-ୣ୦-୷]",
+    "mal" => "[ഀ-ഌഎ-ഐഒ-ൄെ-ൈൊ-൏ൔ-ൣ൦-ൿ]",
     "pan" => "[ਁ-ਃਅ-ਊਏਐਓ-ਨਪ-ਰਲਲ਼ਵਸ਼ਸਹ਼ਾ-ੂੇੈੋ-੍ੑਖ਼-ੜਫ਼੦-੶]",
     "sat" => "[᱐-᱿]",
-    "sin" => "[ංඃඅ-ඖක-නඳ-රලව-ෆ්ා-ුූෘ-ෟ෦-෯ෲ-෴]|�[�-�]",
+    "sin" => "[ඁ-ඃඅ-ඖක-නඳ-රලව-ෆ්ා-ුූෘ-ෟ෦-෯ෲ-෴]|�[�-�]",
     "tam" => "[ஂஃஅ-ஊஎ-ஐஒ-கஙசஜஞடணதந-பம-ஹா-ூெ-ைொ-்ௐௗ௦-௺]|�[�-��]",
-    "tel" => "[ఀ-ఌఎ-ఐఒ-నప-హఽ-ౄె-ైొ-్ౕౖౘ-ౚౠ-ౣ౦-౯౷-౿]",
+    "tel" => "[ఀ-ఌఎ-ఐఒ-నప-హ఼-ౄె-ైొ-్ౕౖౘ-ౚౝౠ-ౣ౦-౯౷-౿]",
     "tha" => "[ก-ฺเ-๛]",
     "zgh" => "[ⴰ-ⵧⵯ⵰⵿]"
   }

lib/paasaa/scripts.ex

@@ -4,7 +4,7 @@ defmodule Paasaa.Mixfile do
   def project do
     [
       app: :paasaa,
-      version: "0.5.1",
+      version: "0.6.0",
       elixir: "~> 1.10",
       description: description(),
       package: package(),
@@ -35,14 +35,14 @@ defmodule Paasaa.Mixfile do
 
   defp deps do
     [
-      {:ex_doc, "~> 0.12", only: :dev},
-      {:mix_test_watch, "~> 1.0.2", only: :dev},
+      {:ex_doc, "~> 0.28", only: :dev},
+      {:mix_test_watch, "~> 1.1.0", only: :dev},
       {:benchfella, "~> 0.3.0", only: :dev},
       {:credo, "~> 1.6.4", only: [:dev, :test]},
-      {:excoveralls, "~> 0.5", only: :test},
-      {:jsx, "~> 2.10", only: :dev},
-      {:tesla, "~> 1.3.0", only: :dev},
-      {:dialyxir, "~> 1.0.0", only: [:dev]}
+      {:excoveralls, "~> 0.14.5", only: :test},
+      {:jsx, "~> 3.1.0", only: :dev},
+      {:tesla, "~> 1.4.4", only: :dev},
+      {:dialyxir, "~> 1.1.0", only: [:dev]}
     ]
   end