Added the filter for noise words as per A5 requirements.

src/components/pages/App.js

@@ -1,5 +1,5 @@
 import React, { useState } from 'react'
-import { KWIC, display, pipe } from '../../utils/helpers'
+import { display, pipe, KWICv2 } from '../../utils/helpers'
 import '../../styles/globals.css'
 
 function App() {
@@ -9,8 +9,8 @@ function App() {
   const handleInputChange = e => setInputText(e.target.value.replace(/[^a-zA-Z\n ]/g, '')) // Ensure only a..zA..Z characters are entered
   const handleResetInput = () => setInputText('')
   const handleResetOutput = () => setOutputText('')
-  const handleKWIC = () => setOutputText(pipe(display)(KWIC(inputText.trim().split('\n').filter(line => line.trim() !== '')).result))
-  
+  const handleKWIC = () => setOutputText(pipe(display)(KWICv2(inputText.trim().split('\n').filter(line => line.trim() !== '')).result))
+
   return (
     <div className="flex justify-center items-center h-screen bg-blue-100 overflow-y-auto p-16">
       <div className="flex flex-col space-y-4">

src/utils/helpers.js

@@ -1,3 +1,6 @@
+// ---- Constants
+// hash table for maximum efficiency in looking it up
+export const NOISE_WORDS = { "a": true, "an": true, "the": true, "and": true, "or": true, "of": true, "to": true, "be": true, "is": true, "in": true, "out": true, "by": true, "as": true, "at": true, "off": true }
 // ---- Predicates
 export const isLetter = char => !char || typeof char !== 'string' || char.length > 1 ? false : /^[a-zA-Z]/.test(char) // A letter is a..zA..Z only
 export const isWord = word => typeof word === 'string' && word.length >= 1 && Array.from(word).every(isLetter) // A word is a string of characters 
@@ -36,14 +39,25 @@ export const processInput = lines => isValidLines(lines)
 export const convertLines = linesResult => mapResult(linesResult, [...new Set(linesResult.result.map(line => line.replace(/\s+/g, ' ')))].filter(line => line.trim() !== ''))
 export const allCircularShiftsAllLines = linesResult => mapResult(linesResult, linesResult.result.map(line => allCircularShifts(line)).flat())
 export const sortLines = linesResult => mapResult(linesResult, orderedSet(linesResult.result.flat()))
+export const filterNoiseWords = (linesResult, noiseWords = NOISE_WORDS) => mapResult(linesResult, linesResult.result.filter(line =>
+	!noiseWords[line.trim().split(' ')[0].toLowerCase()]))
 
 // ---- Display function
 export const display = list => list.join('\n')
 
-// ---- KWIC Pipeline as per instructions
+// ---- KWIC Pipeline as per instructions (Version 1)
 export const KWIC = lines => pipe(
 	processInput, // verifies input is correct and returns result 
 	convertLines, // converts lines to set and remove extra whitespaces and empty lines (removes duplicates, extra whitespaces, and empty lines)
 	allCircularShiftsAllLines, // makes a list of list containing all the circular shifts for each line
 	sortLines, // takes a list of lines, removes duplicate lines, then sorts them line-by-line and character-by-character, and returns a result
+)(lines)
+
+// ---- KWIC Pipeline as per instructions (Version 2, A5)
+export const KWICv2 = lines => pipe(
+	processInput, // verifies input is correct and returns result 
+	convertLines, // converts lines to set and remove extra whitespaces and empty lines (removes duplicates, extra whitespaces, and empty lines)
+	allCircularShiftsAllLines, // makes a list of list containing all the circular shifts for each line
+	sortLines, // takes a list of lines, removes duplicate lines, then sorts them line-by-line and character-by-character, and returns a result
+	filterNoiseWords, // No line prefix of (lower/upper case): “a”, “an”, “the”, “and”, “or”, “of”, “to”, “be”, “is”, “in”, “out”, “by”, “as”, “at”, “off”
 )(lines)

src/utils/helpers.test.js

@@ -11,6 +11,7 @@ import {
 	sortLines,
 	display,
 	KWIC,
+	filterNoiseWords,
 } from './helpers.js'
 
 describe('orderedSet', () => {
@@ -456,4 +457,49 @@ describe('KWIC', () => {
 			expect(result).toEqual(testCase.expected)
 		})
 	})
+})
+
+describe('filterNoiseWords', () => {
+	const testCases = [
+		{
+		  input: [
+			"The quick brown fox",
+			"A lazy dog jumps",
+			"An apple a day keeps the doctor away",
+			"And now for something completely different"
+		  ],
+		  expectedOutput: [
+		  ]
+		},
+		{
+		  input: [
+			"In the beginning was the word",
+			"word was with God",
+			"And the word was God"
+		  ],
+		  expectedOutput: [
+			"word was with God",
+		  ]
+		},
+		{
+		  input: [
+			"tale of two cities",
+			"not to be, that is the question",
+			"frying pan and into the fire"
+		  ],
+		  expectedOutput: [
+			"tale of two cities",
+			"not to be, that is the question",
+			"frying pan and into the fire"
+		  ]
+		}
+	  ]
+
+	  test.each(testCases)('filters out noise words from input lines', ({ input, expectedOutput }) => {
+		// Act
+		const result = filterNoiseWords({ result: input, error: '' })
+
+		// Assert
+		expect(result.result).toEqual(expectedOutput)
+	  })
 })