transliterate_dcs.user.js

// ==UserScript==
// @name         Transliterate DCS
// @namespace    http://www.gist.github.com/
// @version      1.1
// @description  Transliterate IAST text from DCS into Devanagari
// @author       Hrishikesh Terdalkar
// @match        http://www.sanskrit-linguistics.org/dcs/index.php?contents=texte&IDTextDisplay=*
// @require      https://raw.githubusercontent.com/sanskrit/sanscript.js/master/sanscript.js
// ==/UserScript==

(function() {
    'use strict';
    const corpus_selector = document.getElementById("text_id");
    const options = corpus_selector.getElementsByTagName("option");
    for(var i=0; i < options.length; ++i) {
        options[i].innerHTML = Sanscript.t(options[i].innerHTML.toLowerCase(), 'iast', 'devanagari');
    }


    const button_1 = document.createElement('button');
    button_1.innerHTML = "Transliterate";
    corpus_selector.parentNode.insertBefore(button_1, corpus_selector.nextSibling);

    button_1.addEventListener("click", function () {
        transliterate_sentences();
        transliterate_analysis();
    });
})();

function transliterate_sentences() {
    const display_text = document.getElementById("sentences");
    const sentences = display_text.getElementsByClassName("sentence_div");
    for(var i=0; i < sentences.length; ++i) {
        var _html = sentences[i].innerHTML;
        var _parts = split_text_html(_html);
        for (var j=0; j < _parts.length; ++j) {
            if (_parts[j] == "&nbsp;") {
                break;
            }
            if (_parts[j].match(/^[^&\[<]*$/g)) {
                _parts[j] = Sanscript.t(_parts[j], 'iast', 'devanagari');
            }
        }
        _html = _parts.join("");
        sentences[i].innerHTML = _html;
    }
}

function transliterate_analysis() {
    const display_text = document.getElementById("sentences");
    const lemmas = display_text.getElementsByClassName("text-lemma-link");
    for(var i=0; i < lemmas.length; ++i) {
        lemmas[i].innerHTML = Sanscript.t(lemmas[i].innerHTML, 'iast', 'devanagari');
    }
}

function split_text_html(s) {
    var patterns = [
        "&[^; ]*;",     // valid html token
        "<[^>]*>",     // valid html tag
        "\\\[[^\\\]]*\\\]",  // text in brackets
        "[^&\\\[<]*"     // any text until the start of next tag or token
    ];
    /* NOTE:
           If the & is not used as a start of an html tag
           (as in, there is a whitespace after it before the ";" (or no ";" at all))
           then that "&" will get ommitted by this
        */

    var pattern = "";
    for (var i=0; i < patterns.length - 1; ++i) {
        pattern += patterns[i] + "|";
    }
    pattern += patterns[i];
    var re = new RegExp(pattern, "g");
    return s.match(re)
}