Replace certain arabic words in text string using Javascript

by

You can build your own Unicode word boundaries:

  1. Left-hand (leading) word boundary pattern can be defined as a position that is not immediately preceded with letter + any potential diacritics or a digit or an underscore: (?<!\p{L}\p{M}*|[\p{N}_])
  2. Right-hand (trailing) word boundary pattern can be defined as a position that is not immediately followed with a letter, digit or underscore: (?![\p{L}\p{N}_]).

Thus, you can use

var wordsToBold = ["Properties", "How To Use"];

function makeBold(input, wordsToBold) {
    return input.replace(new RegExp('(?<!\\p{L}\\p{M}*|[\\p{N}_])(?:' + wordsToBold.join('|') + ')(?![\\p{L}\\p{N}_])', 'igu'),
        '<br><br><i class="fas fa-ellipsis-h fa-xs mr-2"></i><b>$&</b>');
}
console.log(makeBold("How To Use These Properties: 00How To Use These Properties00", wordsToBold));
// => <br><br><i class="fas fa-ellipsis-h fa-xs mr-2"></i><b>How To Use</b> These <br><br><i class="fas fa-ellipsis-h fa-xs mr-2"></i><b>Properties</b>: 00How To Use These Properties00
var wordsToBold = ["الخصائص", "طريقة الاستعمال"];
var arString = `فرانكوا اراب الخصائص: لوريم ايبسوم دولار سيت أميت ,كونسيكتيتور أدايبا يسكينج أليايت,سيت دو أيوسمود تيمبور

أنكايديديونتيوت لابوري ات دولار ماجنا أليكيوا . طريقة الاستعمال: وت انيم أد مينيم فينايم,كيواس نوستريد

أكسير سيتاشن يللأمكو لابورأس`;
console.log(makeBold(arString, wordsToBold));
// => فرانكوا اراب <br><br><i class="fas fa-ellipsis-h fa-xs mr-2"></i><b>الخصائص</b>: لوريم ايبسوم دولار سيت أميت ,كونسيكتيتور أدايبا يسكينج أليايت,سيت دو أيوسمود تيمبور أنكايديديونتيوت لابوري ات دولار ماجنا أليكيوا . <br><br><i class="fas fa-ellipsis-h fa-xs mr-2"></i><b>طريقة الاستعمال</b>: وت انيم أد مينيم فينايم,كيواس نوستريد أكسير سيتاشن يللأمكو لابورأس

If you want a more generic Unicode-aware \b, you should keep in mind what a Unicode-aware \w actually matches ([\p{Alphabetic}\p{Mark}\p{Decimal_Number}\p{Connector_Punctuation}\p{Join_Control}]), and keeping in mind that \b can be written as (?:(?<=^)(?=\w)|(?<=\w)(?=$)|(?<=\W)(?=\w)|(?<=\w)(?=\W)), you can use the following:

const w = String.raw`[\p{Alphabetic}\p{Mark}\p{Decimal_Number}\p{Connector_Punctuation}\p{Join_Control}]`;
const nw = String.raw`[^\p{Alphabetic}\p{Mark}\p{Decimal_Number}\p{Connector_Punctuation}\p{Join_Control}]`;
const uwb = String.raw`(?:(?<=^)(?=${w})|(?<=${w})(?=$)|(?<=${nw})(?=${w})|(?<=${w})(?=${nw}))`;
console.log(uwb);

The makeBold function will look like

const w = String.raw`[\p{Alphabetic}\p{Mark}\p{Decimal_Number}\p{Connector_Punctuation}\p{Join_Control}]`;
const nw = String.raw`[^\p{Alphabetic}\p{Mark}\p{Decimal_Number}\p{Connector_Punctuation}\p{Join_Control}]`;
const uwb = String.raw`(?:(?<=^)(?=${w})|(?<=${w})(?=$)|(?<=${nw})(?=${w})|(?<=${w})(?=${nw}))`;

function makeBold(input, wordsToBold) {
    return input.replace(new RegExp(`${uwb}(?:${wordsToBold.join('|')})${uwb}`, 'gu'),
        '<br><br><i class="fas fa-ellipsis-h fa-xs mr-2"></i><b>$&</b>');
}

// Test
var wordsToBold = ["الخصائص", "طريقة الاستعمال"];
var arString = `فرانكوا اراب الخصائص: لوريم ايبسوم دولار سيت أميت ,كونسيكتيتور أدايبا يسكينج أليايت,سيت دو أيوسمود تيمبور     أنكايديديونتيوت لابوري ات دولار ماجنا أليكيوا . طريقة الاستعمال: وت انيم أد مينيم فينايم,كيواس نوستريد     أكسير سيتاشن يللأمكو لابورأس`;
console.log(makeBold(arString, wordsToBold));

Please bear in mind the u flag that makes it possible to use Unicode category classes inside the ECMAScript 2018+ compliant RegExp patterns.

More Related Contents:

  1. Regex – To allow numeric, only characters R, N, X, B, @ [closed]
  2. Regex for Email Address along with name format [duplicate]
  3. Negative lookbehind equivalent in JavaScript
  4. JavaScript regex multiline text between two tags
  5. Case insensitive regex in JavaScript
  6. Remove not alphanumeric characters from string
  7. I want to remove double quotes from a String
  8. Count number of matches of a regex in Javascript
  9. Password REGEX with min 6 chars, at least one letter and one number and may contain special characters
  10. Replace a Regex capture group with uppercase in Javascript
  11. Regular Expression | Leap Years and More
  12. How to write regex to validate dates?
  13. Javascript Regex to replace text NOT in html attributes [duplicate]
  14. Javascript – Regex to validate date format [duplicate]
  15. JavaScript Regex Global Match Groups
  16. How can I put [] (square brackets) in RegExp javascript?
  17. What does the regular expression /_/g mean?
  18. Interesting test of Javascript RegExp [duplicate]
  19. Javascript Regex to match only a single occurrence no more or less
  20. Highlight current page in jquery
  21. Highlight word in HTML text (but not markup)
  22. RegEx to match stuff between parentheses
  23. Regex eError when using {1}+ possessive quantifier in JavaScript regex
  24. Check if string contains only letters in javascript
  25. How can I use regex to get all the characters after a specific character, e.g. comma (“,”)
  26. RegEx Ignore Case
  27. Javascript – regex – word boundary (\b) issue
  28. Regex that matches anything except for all whitespace
  29. How to properly escape characters in regexp
  30. How to loop all the elements that match the regex?

Leave a Comment