Current section

12 Versions

Jump to

Compare versions

6 files changed
+27 additions
-27 deletions
  @@ -15,7 +15,7 @@ Add `paasaa` to your list of dependencies in `mix.exs`:
15 15
16 16 ```elixir
17 17 def deps do
18 - [{:paasaa, "~> 0.5.0"}]
18 + [{:paasaa, "~> 0.6.0"}]
19 19 end
20 20 ```
  @@ -1,7 +1,7 @@
1 1 {<<"app">>,<<"paasaa">>}.
2 2 {<<"build_tools">>,[<<"mix">>]}.
3 3 {<<"description">>,<<"Natural language detection">>}.
4 - {<<"elixir">>,<<"~> 1.8">>}.
4 + {<<"elixir">>,<<"~> 1.10">>}.
5 5 {<<"files">>,
6 6 [<<"lib">>,<<"lib/paasaa.ex">>,<<"lib/paasaa">>,<<"lib/paasaa/scripts.ex">>,
7 7 <<"lib/paasaa/languages.ex">>,<<"lib/paasaa/data.ex">>,<<"mix.exs">>,
  @@ -10,4 +10,4 @@
10 10 {<<"links">>,[{<<"GitHub">>,<<"https://github.com/minibikini/paasaa">>}]}.
11 11 {<<"name">>,<<"paasaa">>}.
12 12 {<<"requirements">>,[]}.
13 - {<<"version">>,<<"0.5.1">>}.
13 + {<<"version">>,<<"0.6.0">>}.
  @@ -90,10 +90,10 @@ defmodule Paasaa do
90 90 iex> Paasaa.all("Detect this!") |> Enum.take(5)
91 91 [
92 92 {"eng", 1.0},
93 - {"sco", 0.8675529295913343},
94 - {"nob", 0.6065977351058591},
95 - {"swe", 0.5923190546528804},
96 - {"nno", 0.5534219596258001}
93 + {"sco", 0.8230731943771207},
94 + {"nob", 0.6030053320407174},
95 + {"nno", 0.5525933107125545},
96 + {"swe", 0.508482792050412}
97 97 ]
98 98 """
unknownlib/paasaa/languages.ex
File is too large to be displayed (100 KB limit).
  @@ -3,38 +3,38 @@ defmodule Paasaa.Scripts do
3 3
4 4 @data %{
5 5 "Arabic" =>
6 - "[؀-؄؆-؋؍-ؚ؜؞ؠ-ؿف-يٖ-ٯٱ-ۜ۞-ۿݐ-ݿࢠ-ࢴࢶ-ࢽ࣓-ࣣ࣡-ࣿﭐ-﯁ﯓ-ﴽﵐ-ﶏﶒ-ﷇﷰ-﷽ﹰ-ﹴﹶ-ﻼ]|�[�-�]|�[�-��-������-��-��������-�������������-��-��-��-���-��-��-��-��-���]",
6 + "[؀-؄؆-؋؍-ؚ؜-؞ؠ-ؿف-يٖ-ٯٱ-ۜ۞-ۿݐ-ݿࡰ-ࢎ࢐࢑࢘-ࣣ࣡-ࣿﭐ-﯂ﯓ-ﴽ﵀-ﶏﶒ-ﷇ﷏ﷰ-﷿ﹰ-ﹴﹶ-ﻼ]|�[�-�]|�[�-��-������-��-��������-�������������-��-��-��-���-��-��-��-��-���]",
7 7 "Cyrillic" => "[Ѐ-҄҇-ԯᲀ-ᲈᴫᵸⷠ-ⷿꙀ-ꚟ︮︯]",
8 8 "Devanagari" => "[ऀ-ॐॕ-ॣ०-ॿ꣠-ꣿ]",
9 9 "Ethiopic" =>
10 - "[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]",
10 + "[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]|�[�-��-����-�]",
11 11 "Hebrew" => "[֑-ׇא-תׯ-״יִ-זּטּ-לּמּנּסּףּפּצּ-ﭏ]",
12 12 "Latin" =>
13 - "[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]",
13 + "[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]|�[�-��-��-�]|�[�-�]",
14 14 "Myanmar" => "[က-႟ꧠ-ꧾꩠ-ꩿ]",
15 15 "aii" => "[܀-܍܏-݊ݍ-ݏࡠ-ࡪ]",
16 16 "ben" => "[ঀ-ঃঅ-ঌএঐও-নপ-রলশ-হ়-ৄেৈো-ৎৗড়ঢ়য়-ৣ০-৾]",
17 17 "bod" => "[ༀ-ཇཉ-ཬཱ-ྗྙ-ྼ྾-࿌࿎-࿔࿙࿚]",
18 18 "cmn" =>
19 - "[⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〻㐀-䶵一-鿯豈-舘並-龎]|[�-��-��-��-�][�-�]|�[�-��-�]|�[�-��-�]|�[�-��-�]|�[�-��-�]|�[�-�]|�[�-�]",
19 + "[⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〻㐀-䶿一-鿿豈-舘並-龎]|�[����]|[�-��-��-��-��-�][�-�]|�[�-��-�]|�[�-��-�]|�[�-��-�]|�[�-��-�]|�[�-�]|�[�-�]|�[�-�]",
20 20 "ell" =>
21 21 "[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]|�[�-��]|�[�-�]",
22 22 "guj" => "[ઁ-ઃઅ-ઍએ-ઑઓ-નપ-રલળવ-હ઼-ૅે-ૉો-્ૐૠ-ૣ૦-૱ૹ-૿]",
23 - "hye" => "[Ա-Ֆՙ-ֈ֊֍-֏ﬓ-ﬗ]",
23 + "hye" => "[Ա-Ֆՙ-֊֍-֏ﬓ-ﬗ]",
24 24 "iii" => "[ꀀ-ꒌ꒐-꓆]",
25 - "jpn" => "[ぁ-ゖゝ-ゟ]|�[�-��-�]|🈀|[ァ-ヺヽ-ヿㇰ-ㇿ㋐-㋾㌀-㍗ヲ-ッア-ン]|�[��-�]|[㐀-䶵一-龯]",
26 - "kan" => "[ಀ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ಼-ೄೆ-ೈೊ-್ೕೖೞೠ-ೣ೦-೯ೱೲ]",
25 + "jav" => "[ꦀ-꧍꧐-꧙꧞꧟]",
26 + "jpn" => "[ぁ-ゖゝ-ゟ]|�[�-��-�]|🈀|[ァ-ヺヽ-ヿㇰ-ㇿ㋐-㋾㌀-㍗ヲ-ッア-ン]|�[�-��-���]|�[��-��-�]|[㐀-䶵一-龯]",
27 + "kan" => "[ಀ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ಼-ೄೆ-ೈೊ-್ೕೖೝೞೠ-ೣ೦-೯ೱೲ]",
27 28 "kat" => "[Ⴀ-ჅჇჍა-ჺჼ-ჿᲐ-ᲺᲽ-Ჿⴀ-ⴥⴧⴭ]",
28 29 "khm" => "[ក-៝០-៩៰-៹᧠-᧿]",
29 30 "kor" => "[ᄀ-ᇿ〮〯ㄱ-ㆎ㈀-㈞㉠-㉾ꥠ-ꥼ가-힣ힰ-ퟆퟋ-ퟻᅠ-하-ᅦᅧ-ᅬᅭ-ᅲᅳ-ᅵ]",
30 31 "lao" => "[ກຂຄຆ-ຊຌ-ຣລວ-ຽເ-ໄໆ່-ໍ໐-໙ໜ-ໟ]",
31 - "mal" => "[ഀ-ഃഅ-ഌഎ-ഐഒ-ൄെ-ൈൊ-൏ൔ-ൣ൦-ൿ]",
32 - "ori" => "[ଁ-ଃଅ-ଌଏଐଓ-ନପ-ରଲଳଵ-ହ଼-ୄେୈୋ-୍ୖୗଡ଼ଢ଼ୟ-ୣ୦-୷]",
32 + "mal" => "[ഀ-ഌഎ-ഐഒ-ൄെ-ൈൊ-൏ൔ-ൣ൦-ൿ]",
33 33 "pan" => "[ਁ-ਃਅ-ਊਏਐਓ-ਨਪ-ਰਲਲ਼ਵਸ਼ਸਹ਼ਾ-ੂੇੈੋ-੍ੑਖ਼-ੜਫ਼੦-੶]",
34 34 "sat" => "[᱐-᱿]",
35 - "sin" => "[ංඃඅ-ඖක-නඳ-රලව-ෆ්ා-ුූෘ-ෟ෦-෯ෲ-෴]|�[�-�]",
35 + "sin" => "[ඁ-ඃඅ-ඖක-නඳ-රලව-ෆ්ා-ුූෘ-ෟ෦-෯ෲ-෴]|�[�-�]",
36 36 "tam" => "[ஂஃஅ-ஊஎ-ஐஒ-கஙசஜஞடணதந-பம-ஹா-ூெ-ைொ-்ௐௗ௦-௺]|�[�-��]",
37 - "tel" => "[ఀ-ఌఎ-ఐఒ-నప-హఽ-ౄె-ైొ-్ౕౖౘ-ౚౠ-ౣ౦-౯౷-౿]",
37 + "tel" => "[ఀ-ఌఎ-ఐఒ-నప-హ఼-ౄె-ైొ-్ౕౖౘ-ౚౝౠ-ౣ౦-౯౷-౿]",
38 38 "tha" => "[ก-ฺเ-๛]",
39 39 "zgh" => "[ⴰ-ⵧⵯ⵰⵿]"
40 40 }
Loading more files…