Reversing a Odia Unicode String

Odia is a language with lot of combining characters. Therefore simple reversal of string like str.split('').reverse().join('') will not work . With this naive approach, the reverse of string like ଜଳାର୍ଣ୍ଣବ will end up in ବଣ୍ଣ୍ରାଳଜ where as the expected reversal would be ବର୍ଣ୍ଣଳାଜ. 

Even I failed with BreakIterator of Java with Odia Locale. I also tried packages like esrever but failed. Finally I tried with basic decomposition of Unicode Odia syllables. A string like ଜଳାର୍ଣ୍ଣବ is composed of characters like [  'ଜ', 'ଳ', 'ା', 'ର',  '୍',  'ଣ', '୍',  'ଣ',  'ବ' ], therefore handling the matras and falas did the job. Here is the code in JavaScript: 

/*

 * Task: Find the length of an Odia word. Ex. length of ଦୁର୍ଯ୍ୟୋଧନ should be 4

 * Author: Dr. Swarupananda Bissoyi (swarupananda@gmail.com)

 * Original Version written on: October 7, 2022

 * Bug fixes and final version on: October 12, 2025

 */

function strlen(text) {

    let len = 0;

    let syllable = '';

    let reverseStr = '';

    const maatraas = 'ାିୀୁୂୃେୈୋୌଂଁଃ';

   

    for (let index = 0; index < text.length; index++) {

        const ch = text[index];

        const nextChar = index < text.length - 1 ? text[index + 1] : '\0';

        const nextToNextChar = index < text.length - 2 ? text[index + 2] : '\0';

       

        // Append current character to syllable

        syllable += ch;

        // Check if the next character is a maatraa

        if (maatraas.includes(nextChar)) {

            syllable += nextChar;

            index++;

            // Special case: multiple maatraas, e.g., କିଁଆ

            if (maatraas.includes(nextToNextChar)) {

                syllable += nextToNextChar;

                index++;

            }

            isEnd = true;

        } else if (nextChar === '\u200D' && nextToNextChar === '\u0B4D') {

            // Handle Zero Width Non-Joiner (ZWNJ) followed by \u0B4D

            // Case of ର‍୍ୟାକେଟ୍‌

            syllable += nextChar;

            index++;

            syllable += nextToNextChar;

            index++;

            isEnd = false;

        } else if (nextChar === '\u0B4D') {

            // Handle consonant conjunction

            syllable += nextChar;

            index++;

            // Handle cases where \u0B4D is the last character, e.g., ସ୍ବରୁପ୍

            if (nextToNextChar === '\0') {

                syllable += '\u200C'; // Add Zero Width Joiner

                isEnd = true;

            } else {

                isEnd = false;

            }

        } else {

            isEnd = true;

        }

        if (isEnd) {

            reverseStr = syllable + reverseStr;

            syllable = '';

            len++;

        }

    }

    console.log(`Reverse of [${text}] is [${reverseStr}]`);

    return len;

}

// Example usage

const strs = [

    "ଓଁ", "ଉହୁଁ", "କିଁଆ", "ସ୍ୱରୁପ", "ଅପ୍", "ବ୍ଲିଂ",

    "ସ୍ବରୁପ୍",

    "ଦୁଃଖ", "ର୍ୟାକେଟ୍‌", "ର‍୍ୟାକେଟ୍‌",

    "ସଂସ୍କୃଃ", "ଲେନ୍ସ", "ଲେନ୍‌ସ୍‌",

    "ପୁନର୍ଜ୍ଜୀବିତ",

    "କ୍ଲୀଂହ୍ଲୀ", "ରୁକ୍ମିଣୀ", "ଯାଚ୍ଞ।", "କେଁ କଟର୍", "ହଠାତ୍‌", "ନ୍ଦୁନ୍ଦୁଭି",

    "ଭର୍ତ୍ତୃହରି", "ପରାଙ୍‌ମୁଖ", "ସଂସ୍ଥାପକ", "ଦୁର୍ଯ୍ୟୋଧନ", "ଅର୍ଜ୍ଜୁନ",

    "ଜଳାର୍ଣ୍ଣବ", "କଟକ", "ଅସତ୍‌କର୍ମ", "ନୃପସ୍ଥାୟକ",

    "ଘୂର୍ଣ୍ଣିବାତ୍ୟା"

];

for (const str of strs) {

    const len = strlen(str);

    console.log(`Length of ${str} : ${len}`);

}