very-small-parser/lib/html/parsers.js

A very small Markdown, HTML, and CSS parser.

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.parsers = exports.el = void 0;
const tslib_1 = require("tslib");
const util_1 = require("../util");
const reg = tslib_1.__importStar(require("../markdown/regex"));
const REG_COMMENT = /^<!--(?!-?>)[\s\S]*?-->/;
const comment = (_, src) => {
    const matches = src.match(REG_COMMENT);
    if (matches) {
        const match = matches[0];
        const value = match.slice(4, -3);
        return (0, util_1.token)(match, 'comment', void 0, { value });
    }
};
const REG_TEXT = /^[^<]+/;
const text = (dhe) => (_, src) => {
    const matches = src.match(REG_TEXT);
    if (!matches)
        return;
    let value = matches[0];
    if (dhe)
        value = dhe(value);
    return (0, util_1.token)(value, 'text', void 0, { value }, value.length);
};
const unescapeAttr = (str) => {
    return str
        .replace(/&lt;/g, '<')
        .replace(/&gt;/g, '>')
        .replace(/&quot;/g, '"')
        .replace(/&apos;/g, "'")
        .replace(/&amp;/g, '&')
        .replace(/&#(\d+);/g, (_, code) => String.fromCharCode(code));
};
const REG_ATTR = / +[a-zA-Z:_][\w.:-]*(?: *= *"[^"\n]*"| *= *'[^'\n]*'| *= *[^\s"'=<>`]+)?/;
const REG_OPEN_TAG = reg.replace(/^<([a-z][\w-]*)(?:attr)*? *(\/?)>/, { attr: REG_ATTR });
const REG_ATTRS = /([\w|data-]+)=["']?((?:.(?!["']?\s+(?:\S+)=|\s*\/?[>"']))*.)["']?/gm;
const REG_CLOSE_TAG = /^<\/([a-z][\w-]*)>/;
const el = (parser, src) => {
    const matchOpen = src.match(REG_OPEN_TAG);
    if (!matchOpen)
        return;
    const [match, tagName, selfClosing] = matchOpen;
    const matchLength = match.length;
    const attrSrc = match.slice(tagName.length + 1, -1 - selfClosing.length);
    const properties = {};
    if (attrSrc) {
        const attrs = attrSrc.matchAll(REG_ATTRS);
        for (const [, key, value] of attrs)
            properties[key] = unescapeAttr(value);
    }
    const token = {
        type: 'element',
        tagName,
        properties,
        children: [],
        len: matchLength,
    };
    if (!selfClosing) {
        const substr = src.slice(matchLength);
        const fragment = parser.parsef(substr);
        const fragmentLen = fragment.len;
        if (selfClosing) {
            token.len += fragment.len;
        }
        else {
            const matchClose = substr.slice(fragmentLen).match(REG_CLOSE_TAG);
            if (!matchClose)
                return token;
            token.len += fragment.len + (matchClose?.[0].length ?? 0);
        }
        token.children = fragment.children;
    }
    return token;
};
exports.el = el;
const parsers = (dhe) => [
    text(dhe),
    comment,
    exports.el,
];
exports.parsers = parsers;