hepburn - npm Package Compare versions

Comparing version 0.3.0 to 0.4.0

lib/hepburn.js

@@ -67,2 +67,30 @@ var bulkReplace = require("bulk-replace");
 
+// Used to convert old Nihon-Shiki style romaji into the modern Hepburn form.
+// Source: http://nayuki.eigenstate.org/page/variations-on-japanese-romanization
+var nihonShiki = {
+    "SI": "SHI",
+    "ZI": "JI",
+    "TI": "CHI",
+    "DI": "JI",
+    "TU": "TSU",
+    "DU": "ZU",
+    "SHU": "SHU", // Prevent HU from accidentally converting
+    "HU": "FU",
+    "CYA": "CHA",
+    "CYO": "CHO",
+    "CYU": "CHU",
+    "SYA": "SHA",
+    "SYU": "SHU",
+    "SYO": "SHO",
+    "ZYA": "JA",
+    "ZYU": "JU",
+    "ZYO": "JO",
+    "TYA": "CHA",
+    "TYU": "CHU",
+    "TYO": "CHO",
+    "DYA": "JA",
+    "DYU": "JU",
+    "DYO": "JO"
+};
+
 // For use with toHiragana
@@ -131,3 +159,3 @@ var hiraganaMap = {};
 exports.toHiragana = function(str) {
-  // For to be uppercase
+  // All conversion is done in upper-case
   str = str.toUpperCase();
@@ -148,3 +176,3 @@
 exports.toKatakana = function(str) {
-  // For to be uppercase
+  // All conversion is done in upper-case
   str = str.toUpperCase();
@@ -164,2 +192,27 @@
 
+exports.cleanRomaji = function(str) {
+  // Follows many of the suggestions from:
+  // http://nayuki.eigenstate.org/page/variations-on-japanese-romanization
 
+  // All conversion is done in upper-case
+  str = str.toUpperCase();
+
+  // Should be using N instead of M
+  str = str.replace(/(\w)M([^AEIOUY]|$)/g, "$1N$2");
+
+  // Convert the NN form into the more common N'
+  str = str.replace(/NN/g, "N'");
+
+  // Convert usage of OU into the more common OO
+  // Handle cases like Toukyou
+  str = str.replace(/OU/g, "OO");
+
+  // Fix antiquated usage of OH to mean OO
+  // (handle ambiguous cases like 'Kohusai' vs. 'Tohkyoh')
+  str = str.replace(/OH([^AIEO]|$)/g, "OO$1");
+
+  // Replace old Nihon-shiki usage with modern Hepburn form
+  str = bulkReplace(str, nihonShiki);
+
+  return str;
+};

package.json

 {
   "name": "hepburn",
-  "version": "0.3.0",
+  "version": "0.4.0",
   "main": "./lib/hepburn",
@@ -5,0 +5,0 @@ "description": "Convert Japanese Hiragana and Katakana script to, and from, Romaji using Hepburn romanisation",

README.md

@@ -48,2 +48,19 @@ # Hepburn
 
+### cleanRomaji(string)
+
+```javascript
+var cleaned = hepburn.cleanRomaji("SYUNNEI");
+// cleaned === "SHUN'EI"
+```
+
+Cleans up a romaji string, changing old romaji forms into the more-modern
+Hepburn form (for further processing). Generally matches the style used by [Wapro romaji](https://en.wikipedia.org/wiki/W%C4%81puro_r%C5%8Dmaji). A larger [guide to modern romaji conventions](http://nayuki.eigenstate.org/page/variations-on-japanese-romanization) was used in building this method.
+
+What this methods fixes:
+
+* Incorrect usage of the letter M. For example "Shumman" should be written as "Shunman".
+* Changing usage of NN into N', for example "Shunnei" becomes "Shun'ei".
+* Converting the usage of OU and OH (to indicate a long vowel) into OO.
+* Correct old usages [Nihon-shiki romanization](https://en.wikipedia.org/wiki/Nihon-shiki_romanization) into Hepburn form. A full list of the conversions can be found in the `hepburn.js` file. For example "Eisyosai" becomes "Eishosai" and "Yoshihuji" becomes "Yoshifuji".
+
 ## Testing [![Build Status](https://travis-ci.org/lovell/hepburn.png?branch=master)](https://travis-ci.org/lovell/hepburn)
@@ -50,0 +67,0 @@

tests/all.js

@@ -516,2 +516,15 @@ var assert = require("assert");
 
+var cleanTests = {
+  "shunsho": "SHUNSHO",
+  "SYUNMAN": "SHUNMAN",
+  "SHUMMAN": "SHUNMAN",
+  "EISYOSAI": "EISHOSAI",
+  "SYUNNEI": "SHUN'EI",
+  "OHUCHI": "OOUCHI",
+  "TOUKYOU": "TOOKYOO",
+  "TOHKYOH": "TOOKYOO",
+  "SENCYUSYA": "SENCHUSHA",
+  "YOSHIHUJI": "YOSHIFUJI"
+};
+
 for (var hiragana in hiraganaTests) {
@@ -534,1 +547,5 @@ assert.equal(hepburn.fromKana(hiragana), hiraganaTests[hiragana], "Hiragana conversion failed on " + hiragana);
 }
+
+for (var hiragana in cleanTests) {
+  assert.equal(hepburn.cleanRomaji(hiragana), cleanTests[hiragana], "Failed to clean " + hiragana);
+}

New alerts

New author

Supply chain risk

A new npm collaborator published a version of the package for the first time. New collaborators are usually benign additions to a project, but do indicate a change to the security surface area of a package.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

24767

increased by13.08%

Lines of code

717

increased by9.3%

Number of lines in readme file

84

increased by25.37%

Worsened metrics

Number of medium supply chain risk alerts

1

increased byInfinity%

No dependency changes