feat: add isGurmukhi function to check if string is Unicode Gurmukhi (#…

…141)

README.hbs

@@ -20,17 +20,28 @@ Want to speak with us? <p>[![Slack](https://slack.shabados.com/badge.svg)](https
 
 The library can be imported into Node as below:
 ```javascript
-const { toUnicode, toAscii, firstLetters, transliterate, toShahmukhi } = require('gurmukhi-utils')
+const {
+  toUnicode,
+  toAscii,
+  firstLetters,
+  toEnglish,
+  toHindi,
+  toShahmukhi,
+  stripAccents,
+  stripVishraams,
+  isGurmukhi,
+} = require( 'gurmukhi-utils' )
 
 toUnicode('Koj')    // => ਖੋਜ
 toAscii('ਖੋਜ')      // => Koj
 firstLetters('hir hir hir gunI')  // => hhhg
 firstLetters('ਹਰਿ ਹਰਿ ਹਰਿ ਗੁਨੀ')   // => ਹਹਹਗ
-transliterate('hukmI hukmu clwey rwhu ]')  // => hukamee hukam chalaae raahu ||
+toEnglish('hukmI hukmu clwey rwhu ]')  // => hukamee hukam chalaae raahu ||
 toHindi('ਕੁਲ ਜਨ ਮਧੇ ਮਿਲੵੋਿ ਸਾਰਗ ਪਾਨ ਰੇ ॥')    // => कुल जन मधे मिल्यो सारग पान रे ॥
 toShahmukhi('ਹਰਿ ਹਰਿ ਹਰਿ ਗੁਨੀ') // => هر هر هر گُنی
 stripAccents('ਜ਼ਫ਼ੈਸ਼ਸ') // => ਜਫੈਸਸ
 stripVishraams('sbid mrY. so mir rhY; iPir.') // => sbid mrY so mir rhY iPir
+isGurmukhi('ਗੁਰਮੁਖੀ') // t=> true
 ```
 
 Additionally, the package is available for web use via [unpkg CDN](https://unpkg.com/gurmukhi-utils).

README.md

@@ -20,6 +20,7 @@ Want to speak with us? <p>[![Slack](https://slack.shabados.com/badge.svg)](https
 - [Usage](#usage)
 - [API](#api)
   * [firstLetters(line, [stripNukta], [withVishraams]) ⇒ String](#firstlettersline-stripnukta-withvishraams-%E2%87%92-string)
+  * [isGurmukhi(text, [exhaustive]) ⇒ boolean](#isgurmukhitext-exhaustive-%E2%87%92-boolean)
   * [stripAccents(text) ⇒ String](#stripaccentstext-%E2%87%92-string)
   * [stripVishraams(text, options) ⇒ String](#stripvishraamstext-options-%E2%87%92-string)
   * [toAscii(text) ⇒ String](#toasciitext-%E2%87%92-string)
@@ -96,6 +97,20 @@ firstLetters('iZir&qym sMdUk* drIXw AmIk* ]', false) // => Zsda
 ```js
 firstLetters('sbid mrY. so mir rhY; iPir. mrY n, dUjI vwr ]', true, true) // => sm.smr;P.mn,dv
 ```
+### isGurmukhi(text, [exhaustive]) ⇒ <code>boolean</code>
+Checks if first char in string is part of the Gurmukhi Unicode block.
+
+**Returns**: <code>boolean</code> - True if Unicode Gurmukhi, false if other.  
+
+| Param | Type | Description |
+| --- | --- | --- |
+| text | <code>String</code> | The text to check. |
+| [exhaustive] | <code>boolean</code> | If `true`, checks if the whole string is Unicode Gurmukhi. |
+
+**Example**  
+```js
+isGurmukhi('ਗੁਰਮੁਖੀ') // => trueisGurmukhi('gurmuKI') // => false
+```
 ### stripAccents(text) ⇒ <code>String</code>
 Removes accents from ASCII/Unicode Gumrukhi letters with their base letter.
 Useful for generalising search queries.

docs/README.md

@@ -20,6 +20,7 @@ Want to speak with us? <p>[![Slack](https://slack.shabados.com/badge.svg)](https
 - [Usage](#usage)
 - [API](#api)
   * [firstLetters(line, [stripNukta], [withVishraams]) ⇒ String](#firstlettersline-stripnukta-withvishraams-%E2%87%92-string)
+  * [isGurmukhi(text, [exhaustive]) ⇒ boolean](#isgurmukhitext-exhaustive-%E2%87%92-boolean)
   * [stripAccents(text) ⇒ String](#stripaccentstext-%E2%87%92-string)
   * [stripVishraams(text, options) ⇒ String](#stripvishraamstext-options-%E2%87%92-string)
   * [toAscii(text) ⇒ String](#toasciitext-%E2%87%92-string)
@@ -96,6 +97,20 @@ firstLetters('iZir&qym sMdUk* drIXw AmIk* ]', false) // => Zsda
 ```js
 firstLetters('sbid mrY. so mir rhY; iPir. mrY n, dUjI vwr ]', true, true) // => sm.smr;P.mn,dv
 ```
+### isGurmukhi(text, [exhaustive]) ⇒ <code>boolean</code>
+Checks if first char in string is part of the Gurmukhi Unicode block.
+
+**Returns**: <code>boolean</code> - True if Unicode Gurmukhi, false if other.  
+
+| Param | Type | Description |
+| --- | --- | --- |
+| text | <code>String</code> | The text to check. |
+| [exhaustive] | <code>boolean</code> | If `true`, checks if the whole string is Unicode Gurmukhi. |
+
+**Example**  
+```js
+isGurmukhi('ਗੁਰਮੁਖੀ') // => trueisGurmukhi('gurmuKI') // => false
+```
 ### stripAccents(text) ⇒ <code>String</code>
 Removes accents from ASCII/Unicode Gumrukhi letters with their base letter.
 Useful for generalising search queries.

example.js

@@ -4,16 +4,19 @@ const {
   toAscii,
   toUnicode,
   firstLetters,
-  transliterate,
+  toEnglish,
   stripAccents,
+  stripVishraams,
+  isGurmukhi
 } = require( 'gurmukhi-utils' )
 
 console.log(toUnicode( 'Koj' ))
 console.log(toAscii('ਖੋਜ'))
 console.log(firstLetters( 'hir hir hir gun gwvhu ]' ))
 console.log(firstLetters( 'ਹਰਿ ਹਰਿ ਹਰਿ ਗੁਨੀ' ))
-console.log(transliterate( 'ਹੁਕਮੀ ਹੁਕਮੁ ਚਲਾਏ ਰਾਹੁ ॥' ))
+console.log(toEnglish( 'ਹੁਕਮੀ ਹੁਕਮੁ ਚਲਾਏ ਰਾਹੁ ॥' ))
 console.log(toShahmukhi( 'ਹਰਿ ਹਰਿ ਹਰਿ ਗੁਨੀ' ))
 console.log(toHindi( 'ਕੁਲ ਜਨ ਮਧੇ ਮਿਲੵੋਿ ਸਾਰਗ ਪਾਨ ਰੇ ॥' ))
 console.log(stripAccents('ਜ਼ਫ਼ੈਸ਼ਸ'))
 console.log(stripVishraams('sbid mrY. so mir rhY; iPir.'))
+console.log(isGurmukhi('ਗੁਰਮੁਖੀ'))

index.d.ts

@@ -10,6 +10,8 @@ export function toShamukhi(text: string): string
 
 export function firstLetters(text: string, stripNukta?: boolean = true, withVishraams?: boolean): string
 
+export function isGurmukhi(text: string, exhaustive?: boolean): boolean
+
 export function stripAccents(text: string): string
 interface StripVishraamsOptions {
   heavy?: boolean;

index.js

@@ -4,6 +4,7 @@ const firstLetters = require( './lib/firstLetters' )
 const toEnglish = require( './lib/toEnglish' )
 const toShahmukhi = require( './lib/toShahmukhi' )
 const toHindi = require( './lib/toHindi' )
+const isGurmukhi = require( './lib/isGurmukhi' )
 const stripAccents = require( './lib/stripAccents' )
 const stripVishraams = require( './lib/stripVishraams' )
 
@@ -14,6 +15,7 @@ module.exports = {
   toEnglish,
   toShahmukhi,
   toHindi,
+  isGurmukhi,
   stripAccents,
   stripVishraams,
 }

lib/isGurmukhi.js

@@ -0,0 +1,32 @@
+const vishraams = Object.values( require( './vishraams.json' ) )
+
+// Checks if Unicode Text is in Gurmukhi Block (U+0A00 - U+0A7F)
+const checkCharCode = text => ( text.charCodeAt( 0 ) >= 2560 && text.charCodeAt( 0 ) <= 2687 )
+
+// Characters to filter from text if doing an exhaustive check
+const filteredChars = [
+  ' ',
+  '\u200B',
+  '।',
+  '॥',
+  ...vishraams,
+]
+
+/**
+ * Checks if first char in string is part of the Gurmukhi Unicode block.
+ * @param {String} text The text to check.
+ * @param {boolean} [exhaustive] If `true`, checks if the whole string is Unicode Gurmukhi.
+ * @return {boolean} True if Unicode Gurmukhi, false if other.
+ * @example
+ * isGurmukhi('ਗੁਰਮੁਖੀ') // => true
+ * isGurmukhi('gurmuKI') // => false
+ */
+const isGurmukhi = ( text, exhaustive ) => (
+  exhaustive
+    ? text.split( '' )
+      .filter( i => !filteredChars.includes( i ) )
+      .every( checkCharCode )
+    : checkCharCode( text )
+)
+
+module.exports = isGurmukhi

test/isGurmukhi.spec.js

@@ -0,0 +1,35 @@
+const { expect } = require( 'chai' )
+
+const { isGurmukhi } = require( '../index' )
+
+describe( 'isGurmukhi(line)', () => {
+  const lines = [
+    [ 'ਗੁਰਮੁਖੀ', true ],
+    [ 'ਮੈਂ ਗੁਰਮੁਖੀ ਵਿਚ ਲਿਖ ਰਿਹਾ ਹਾਂ।', true ],
+    [ 'ਲੜੀਵਾਰ​ਗੁਰਬਾਣੀ', true ], // Has U+200B, Zero Width Space
+    [ 'मैं हिंदी में लिख रहा हूँ।', false ],
+    [ 'میں شاہ رخ میں لکھ رہا ہوں۔', false ],
+    [ 'ਗੁਰਮੁਖੀ & English', true ],
+    [ 'English & ਗੁਰਮੁਖੀ', false ],
+  ]
+
+  lines.map( ( [ string, result ] ) => it( `String '${string}' should return ${result}`, () => {
+    expect( isGurmukhi( string ) ).to.equal( result )
+  } ) )
+} )
+
+describe( 'isGurmukhi(line, true)', () => {
+  const lines = [
+    [ 'ਗੁਰਮੁਖੀ', true ],
+    [ 'ਮੈਂ ਗੁਰਮੁਖੀ ਵਿਚ ਲਿਖ ਰਿਹਾ ਹਾਂ।', true ],
+    [ 'ਲੜੀਵਾਰ​ਗੁਰਬਾਣੀ', true ], // Has U+200B, Zero Width Space
+    [ 'मैं हिंदी में लिख रहा हूँ।', false ],
+    [ 'میں شاہ رخ میں لکھ رہا ہوں۔', false ],
+    [ 'ਗੁਰਮੁਖੀ & English', false ],
+    [ 'English & ਗੁਰਮੁਖੀ', false ],
+  ]
+
+  lines.map( ( [ string, result ] ) => it( `String '${string}' should return ${result}`, () => {
+    expect( isGurmukhi( string, true ) ).to.equal( result )
+  } ) )
+} )