2022-08-31 06:33:37 +05:00
|
|
|
/*
|
|
|
|
|
This file is part of the Notesnook project (https://notesnook.com/)
|
|
|
|
|
|
|
|
|
|
Copyright (C) 2022 Streetwriters (Private) Limited
|
|
|
|
|
|
|
|
|
|
This program is free software: you can redistribute it and/or modify
|
|
|
|
|
it under the terms of the GNU General Public License as published by
|
|
|
|
|
the Free Software Foundation, either version 3 of the License, or
|
|
|
|
|
(at your option) any later version.
|
|
|
|
|
|
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
|
GNU General Public License for more details.
|
|
|
|
|
|
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
|
|
|
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
|
*/
|
2022-08-30 16:13:11 +05:00
|
|
|
|
2022-01-20 00:18:35 +05:00
|
|
|
import { decodeHTML5 } from "entities";
|
2022-11-10 15:16:13 +05:00
|
|
|
import { Parser } from "htmlparser2";
|
2022-04-19 00:04:57 +05:00
|
|
|
|
|
|
|
|
export const parseHTML = (input) =>
|
2022-07-15 09:42:30 +05:00
|
|
|
new globalThis.DOMParser().parseFromString(
|
|
|
|
|
wrapIntoHTMLDocument(input),
|
|
|
|
|
"text/html"
|
|
|
|
|
);
|
2021-12-08 19:32:58 +05:00
|
|
|
|
|
|
|
|
export function getDummyDocument() {
|
|
|
|
|
const doc = parseHTML("<div></div>");
|
2022-04-19 00:04:57 +05:00
|
|
|
return doc;
|
2021-12-08 19:32:58 +05:00
|
|
|
}
|
2021-12-16 10:10:00 +05:00
|
|
|
|
|
|
|
|
export function getInnerText(element) {
|
2022-01-20 00:18:35 +05:00
|
|
|
return decodeHTML5(element.innerText || element.textContent);
|
2021-12-16 10:10:00 +05:00
|
|
|
}
|
2022-04-19 00:28:42 +05:00
|
|
|
|
|
|
|
|
function wrapIntoHTMLDocument(input) {
|
2022-07-07 18:39:57 +05:00
|
|
|
if (typeof input !== "string") return input;
|
2022-04-19 00:28:42 +05:00
|
|
|
if (input.includes("<body>")) return input;
|
|
|
|
|
|
|
|
|
|
return `<!doctype html><html lang="en"><head><title>Document Fragment</title></head><body>${input}</body></html>`;
|
|
|
|
|
}
|
2022-11-10 15:16:13 +05:00
|
|
|
|
|
|
|
|
export function extractFirstParagraph(html) {
|
|
|
|
|
let text = "";
|
|
|
|
|
let start = false;
|
|
|
|
|
const parser = new Parser(
|
|
|
|
|
{
|
|
|
|
|
onopentag: (name) => {
|
|
|
|
|
if (name === "p") start = true;
|
|
|
|
|
},
|
|
|
|
|
onclosetag: (name) => {
|
|
|
|
|
if (name === "p") {
|
|
|
|
|
start = false;
|
|
|
|
|
parser.pause();
|
|
|
|
|
parser.reset();
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
ontext: (data) => {
|
|
|
|
|
if (start) text += data;
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
lowerCaseTags: false,
|
|
|
|
|
decodeEntities: true
|
|
|
|
|
}
|
|
|
|
|
);
|
|
|
|
|
parser.end(html);
|
|
|
|
|
return text;
|
|
|
|
|
}
|
