Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add missing Vietnamese diacritics #46

Merged
merged 1 commit into from
Jul 31, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 57 additions & 1 deletion index.js
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,11 @@ var characterMap = {
"Ầ": "A",
"Ằ": "A",
"Ȃ": "A",
"Ả": "A",
"Ạ": "A",
"Ẩ": "A",
"Ẫ": "A",
"Ậ": "A",
"Ç": "C",
"Ḉ": "C",
"È": "E",
Expand All @@ -26,12 +31,20 @@ var characterMap = {
"Ḕ": "E",
"Ḝ": "E",
"Ȇ": "E",
"Ẻ": "E",
"Ẽ": "E",
"Ẹ": "E",
"Ể": "E",
"Ễ": "E",
"Ệ": "E",
"Ì": "I",
"Í": "I",
"Î": "I",
"Ï": "I",
"Ḯ": "I",
"Ȋ": "I",
"Ỉ": "I",
"Ị": "I",
"Ð": "D",
"Ñ": "N",
"Ò": "O",
Expand All @@ -44,10 +57,25 @@ var characterMap = {
"Ṍ": "O",
"Ṓ": "O",
"Ȏ": "O",
"Ỏ": "O",
"Ọ": "O",
"Ổ": "O",
"Ỗ": "O",
"Ộ": "O",
"Ờ": "O",
"Ở": "O",
"Ỡ": "O",
"Ớ": "O",
"Ợ": "O",
"Ù": "U",
"Ú": "U",
"Û": "U",
"Ü": "U",
"Ủ": "U",
"Ụ": "U",
"Ử": "U",
"Ữ": "U",
"Ự": "U",
"Ý": "Y",
"à": "a",
"á": "a",
Expand All @@ -64,6 +92,11 @@ var characterMap = {
"ầ": "a",
"ằ": "a",
"ȃ": "a",
"ả": "a",
"ạ": "a",
"ẩ": "a",
"ẫ": "a",
"ậ": "a",
"ç": "c",
"ḉ": "c",
"è": "e",
Expand All @@ -76,12 +109,20 @@ var characterMap = {
"ḕ": "e",
"ḝ": "e",
"ȇ": "e",
"ẻ": "e",
"ẽ": "e",
"ẹ": "e",
"ể": "e",
"ễ": "e",
"ệ": "e",
"ì": "i",
"í": "i",
"î": "i",
"ï": "i",
"ḯ": "i",
"ȋ": "i",
"ỉ": "i",
"ị": "i",
"ð": "d",
"ñ": "n",
"ò": "o",
Expand All @@ -94,10 +135,25 @@ var characterMap = {
"ṍ": "o",
"ṓ": "o",
"ȏ": "o",
"ỏ": "o",
"ọ": "o",
"ổ": "o",
"ỗ": "o",
"ộ": "o",
"ờ": "o",
"ở": "o",
"ỡ": "o",
"ớ": "o",
"ợ": "o",
"ù": "u",
"ú": "u",
"û": "u",
"ü": "u",
"ủ": "u",
"ụ": "u",
"ử": "u",
"ữ": "u",
"ự": "u",
"ý": "y",
"ÿ": "y",
"Ā": "A",
Expand Down Expand Up @@ -412,7 +468,7 @@ function matcher(match) {
return characterMap[match];
}

var removeAccents = function(string) {
var removeAccents = function(string) {
return string.replace(allAccents, matcher);
};

Expand Down
5 changes: 2 additions & 3 deletions test.js
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@ var tape = require('tape');
var removeAccents = require('./');

tape('remove accents from string', function(t) {
var input = 'ÀÁÂÃÄÅẤẮÆẦẰÇḈÈÉÊËẾḖỀḔÌÍÎÏḮÐÑÒÓÔÕÖØỐṌṒÙÚÛÜÝàáâãäåấắæầằçḉèéêëếḗềḕìíîïḯñòóôõöøốṍṓùúûüýÿĀāĂ㥹ĆćĈĉĊċČčĎďĐđĒēĔĕĖėĘęĚěĜĝĞğĠġĢģǴǵĤĥĦħĨĩĪīĬĭĮįİıIJijĴĵĶķḰḱĹĺĻļĽľĿŀŁłḾḿŃńŅņŇňʼnŌōŎŏŐőŒœŔŕŖŗŘřŚśŜŝŞşŠšŢţŤťŦŧŨũŪūŬŭŮůŰűŲųŴŵẂẃŶŷŸŹźŻżŽžſƒƠơƯưǍǎǏǐǑǒǓǔǕǖǗǘǙǚǛǜỨứṸṹǺǻǼǽǾǿðÞþṔṕṤṥX́x́ЃѓЌќA̋a̋E̋e̋I̋i̋ǸǹỒồṐṑỪừẀẁỲỳȀȁȄȅȈȉȌȍȐȑȔȕẲẴẶḜẳẵặḝC̆c̆ḪḫK̆k̆M̆m̆N̆n̆P̆p̆R̆r̆T̆t̆V̆v̆X̆x̆Y̆y̆ȂȆȊȎȃȇȋȏȒȓȖȗșțȘȚB̌b̌F̌f̌ǦǧȞȟJ̌ǰǨǩM̌m̌P̌p̌Q̌q̌ṦṧV̌v̌W̌w̌X̌x̌Y̌y̌A̧a̧B̧b̧ḐḑȨȩƐ̧ɛ̧ḨḩI̧i̧Ɨ̧ɨ̧M̧m̧O̧o̧Q̧q̧U̧u̧X̧x̧Z̧z̧';
var input = 'ÀÁÂÃÄÅẤẮÆẦẰẢẠẨẪẬÇḈÈÉÊËẾḖỀḔẺẼẸỂỄỆÌÍÎÏḮỈỊÐÑÒÓÔÕÖØỐṌṒỎỌỔỖỘỜỞỠỚỢÙÚÛÜỦỤỬỮỰÝàáâãäåấắæầằảạẩẫậçḉèéêëếḗềḕẻẽẹểễệìíîïḯỉịñòóôõöøốṍṓỏọổỗộờởỡớợùúûüủụửữựýÿĀāĂ㥹ĆćĈĉĊċČčĎďĐđĒēĔĕĖėĘęĚěĜĝĞğĠġĢģǴǵĤĥĦħĨĩĪīĬĭĮįİıIJijĴĵĶķḰḱĹĺĻļĽľĿŀŁłḾḿŃńŅņŇňʼnŌōŎŏŐőŒœŔŕŖŗŘřŚśŜŝŞşŠšŢţŤťŦŧŨũŪūŬŭŮůŰűŲųŴŵẂẃŶŷŸŹźŻżŽžſƒƠơƯưǍǎǏǐǑǒǓǔǕǖǗǘǙǚǛǜỨứṸṹǺǻǼǽǾǿðÞþṔṕṤṥX́x́ЃѓЌќA̋a̋E̋e̋I̋i̋ǸǹỒồṐṑỪừẀẁỲỳȀȁȄȅȈȉȌȍȐȑȔȕẲẴẶḜẳẵặḝC̆c̆ḪḫK̆k̆M̆m̆N̆n̆P̆p̆R̆r̆T̆t̆V̆v̆X̆x̆Y̆y̆ȂȆȊȎȃȇȋȏȒȓȖȗșțȘȚB̌b̌F̌f̌ǦǧȞȟJ̌ǰǨǩM̌m̌P̌p̌Q̌q̌ṦṧV̌v̌W̌w̌X̌x̌Y̌y̌A̧a̧B̧b̧ḐḑȨȩƐ̧ɛ̧ḨḩI̧i̧Ɨ̧ɨ̧M̧m̧O̧o̧Q̧q̧U̧u̧X̧x̧Z̧z';
var output = removeAccents(input);
var expected = 'AAAAAAAAAEAACCEEEEEEEEIIIIIDNOOOOOOOOOUUUUYaaaaaaaaaeaacceeeeeeeeiiiiinooooooooouuuuyyAaAaAaCcCcCcCcDdDdEeEeEeEeEeGgGgGgGgGgHhHhIiIiIiIiIiIJijJjKkKkLlLlLlLlllMmNnNnNnnOoOoOoOEoeRrRrRrSsSsSsSsTtTtTtUuUuUuUuUuUuWwWwYyYZzZzZzsfOoUuAaIiOoUuUuUuUuUuUuUuAaAEaeOodTHthPpSsXxГгКкAaEeIiNnOoOoUuWwYyAaEeIiOoRrUuAAAEaaaeCcHhKkMmNnPpRrTtVvXxYyAEIOaeioRrUustSTBbFfGgHhJjKkMmPpQqSsVvWwXxYyAaBbDdEeEeHhIiIiMmOoQqUuXxZz';
var expected = 'AAAAAAAAAEAAAAAAACCEEEEEEEEEEEEEEIIIIIIIDNOOOOOOOOOOOOOOOOOOOUUUUUUUUUYaaaaaaaaaeaaaaaaacceeeeeeeeeeeeeeiiiiiiinooooooooooooooooooouuuuuuuuuyyAaAaAaCcCcCcCcDdDdEeEeEeEeEeGgGgGgGgGgHhHhIiIiIiIiIiIJijJjKkKkLlLlLlLlllMmNnNnNnnOoOoOoOEoeRrRrRrSsSsSsSsTtTtTtUuUuUuUuUuUuWwWwYyYZzZzZzsfOoUuAaIiOoUuUuUuUuUuUuUuAaAEaeOodTHthPpSsXxГгКкAaEeIiNnOoOoUuWwYyAaEeIiOoRrUuAAAEaaaeCcHhKkMmNnPpRrTtVvXxYyAEIOaeioRrUustSTBbFfGgHhJjKkMmPpQqSsVvWwXxYyAaBbDdEeEeHhIiIiMmOoQqUuXxZz';

t.same( output, expected );

Expand Down Expand Up @@ -54,4 +54,3 @@ tape('ß is not accented', function(t) {
t.same(removeAccents.remove('Straße'), 'Straße');
t.end();
});