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.

Sign up for GitHub

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

Improve performance #27

Merged
merged 1 commit into from
Sep 8, 2023
Merged

Improve performance #27

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
37 changes: 24 additions & 13 deletions lib/hepburn.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,6 +180,10 @@ var nihonShiki = {
"DYO": "JO"
};

function keysToRegex(obj) {
return new RegExp(Object.keys(obj).join('|'), "g");
}

// For use with toHiragana
var hiraganaMap = {};

Expand All @@ -200,6 +204,8 @@ Object.keys(hiraganaDigraphs).forEach(function(key) {
var hiraganaRegex = new RegExp(Object.keys(hiraganaMap).sort(function(a, b) {
return b.length - a.length;
}).join("|"), "g");
var hiraganaMonographsRegex = keysToRegex(hiraganaMonographs);
var hiraganaDigraphsRegex = keysToRegex(hiraganaDigraphs);

// For use with toKatakana
var katakanaMap = {};
Expand Down Expand Up @@ -228,17 +234,23 @@ Object.keys(katakanaTrigraphs).forEach(function(key) {
var katakanaRegex = new RegExp(Object.keys(katakanaMap).sort(function(a, b) {
return b.length - a.length;
}).join("|"), "g");
var katakanaMonographsRegex = keysToRegex(katakanaMonographs);
var katakanaDigraphsRegex = keysToRegex(katakanaDigraphs);
var katakanaHalfwidthsCombinedRegex = keysToRegex(katakanaHalfwidthsCombined);
var katakanaHalfwidthsRegex = keysToRegex(katakanaHalfwidths);

var nihonShikiRegex = keysToRegex(nihonShiki);

// API

exports.fromKana = function(str) {
// Initial transliteration
str = bulkReplace(str, katakanaHalfwidthsCombined);
str = bulkReplace(str, katakanaHalfwidths);
str = bulkReplace(str, hiraganaDigraphs);
str = bulkReplace(str, katakanaDigraphs);
str = bulkReplace(str, hiraganaMonographs);
str = bulkReplace(str, katakanaMonographs);
str = bulkReplace(str, katakanaHalfwidthsCombinedRegex, katakanaHalfwidthsCombined);
str = bulkReplace(str, katakanaHalfwidthsRegex, katakanaHalfwidths);
str = bulkReplace(str, hiraganaDigraphsRegex, hiraganaDigraphs);
str = bulkReplace(str, katakanaDigraphsRegex, katakanaDigraphs);
str = bulkReplace(str, hiraganaMonographsRegex, hiraganaMonographs);
str = bulkReplace(str, katakanaMonographsRegex, katakanaMonographs);

// Correct use of sokuon
str = str.replace(/[っッ]C/g, "TC").replace(/[っッ](.)/g, "$1$1");
Expand Down Expand Up @@ -312,7 +324,7 @@ exports.cleanRomaji = function(str) {
str = str.replace(/OH([^AIEO]|$)/g, "OO$1");

// Replace old Nihon-shiki usage with modern Hepburn form
str = bulkReplace(str, nihonShiki);
str = bulkReplace(str, nihonShikiRegex, nihonShiki);

return str;
};
Expand Down Expand Up @@ -369,20 +381,19 @@ exports.splitRomaji = function(str) {
}

exports.containsHiragana = function(str) {
return new RegExp(Object.keys(hiraganaMonographs).join('|')).test(str);
hiraganaMonographsRegex.lastIndex = 0;
return hiraganaMonographsRegex.test(str);
};

exports.containsKatakana = function(str) {
return (
new RegExp(Object.keys(katakanaMonographs).join('|')).test(str) ||
new RegExp(Object.keys(katakanaHalfwidths).join('|')).test(str)
);
katakanaMonographsRegex.lastIndex = katakanaHalfwidthsRegex.lastIndex = 0;
return katakanaMonographsRegex.test(str) || katakanaHalfwidthsRegex.test(str);
};

exports.containsKana = function(str){
return (exports.containsHiragana(str) || exports.containsKatakana(str));
};

exports.containsKanji = function(str){
return new RegExp(/[\u4e00-\u9fcf\uf900-\ufaff\u3400-\u4dbf]/).test(str);
return /[\u4e00-\u9fcf\uf900-\ufaff\u3400-\u4dbf]/.test(str);
}