wikiparser-node 1.4.0 → 1.4.1-b

package/dist/parser/converter.js

@@ -1,40 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseConverter = void 0;
-const constants_1 = require("../util/constants");
-const Parser = require("../index");
-const converter_1 = require("../src/converter");
-/**
- * 解析语言变体转换
- * @param text
- * @param config
- * @param accum
- */
-const parseConverter = (text, config = Parser.getConfig(), accum = []) => {
-    const regex1 = /-\{/gu, regex2 = /-\{|\}-/gu, stack = [];
-    let regex = regex1, mt = regex.exec(text);
-    while (mt) {
-        const { 0: syntax, index } = mt;
-        if (syntax === '}-') {
-            // eslint-disable-next-line @typescript-eslint/no-unused-expressions
-            /;(?=(?:[^;]*?=>)?\s*foo\s*:|(?:\s|\0\d+c\x7F)*$)/u;
-            const top = stack.pop(), { length } = accum, str = text.slice(top.index + 2, index), i = str.indexOf('|'), [flags, raw] = i === -1 ? [[], str] : [str.slice(0, i).split(';'), str.slice(i + 1)], temp = raw.replace(/(&[#a-z\d]+);/giu, '$1\x01'), variants = `(?:${config.variants.join('|')})`, rules = temp.split(new RegExp(`;(?=(?:[^;]*?=>)?\\s*${variants}\\s*:|(?:\\s|\0\\d+c\x7F)*$)`, 'u'))
-                .map(rule => rule.replace(/\x01/gu, ';'));
-            new converter_1.ConverterToken(flags, rules, config, accum);
-            text = `${text.slice(0, top.index)}\0${length}v\x7F${text.slice(index + 2)}`;
-            if (stack.length === 0) {
-                regex = regex1;
-            }
-            regex.lastIndex = top.index + 3 + String(length).length;
-        }
-        else {
-            stack.push(mt);
-            regex = regex2;
-            regex.lastIndex = index + 2;
-        }
-        mt = regex.exec(text);
-    }
-    return text;
-};
-exports.parseConverter = parseConverter;
-constants_1.parsers['parseConverter'] = __filename;

package/dist/parser/externalLinks.js

@@ -1,31 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseExternalLinks = void 0;
-const string_1 = require("../util/string");
-const constants_1 = require("../util/constants");
-const Parser = require("../index");
-const extLink_1 = require("../src/extLink");
-/**
- * 解析外部链接
- * @param wikitext
- * @param config
- * @param accum
- */
-const parseExternalLinks = (wikitext, config = Parser.getConfig(), accum = []) => {
-    // eslint-disable-next-line @typescript-eslint/no-unused-expressions
-    /\[((?:\[[\da-f:.]+\]|[^[\]\t\n\p{Zs}])[^[\]\t\n\p{Zs}]*(?=[[\]\t\p{Zs}]|\0\d))(\p{Zs}*(?=\P{Zs}))([^\]\n]*)\]/giu;
-    const regex = new RegExp(`\\[((?:(?:${config.protocol}|//)${string_1.extUrlCharFirst}|\0\\d+m\x7F)${string_1.extUrlChar}(?=[[\\]<>"\\t\\p{Zs}]|\0\\d))`
-        + '(\\p{Zs}*(?=\\P{Zs}))([^\\]\x01-\x08\x0A-\x1F\uFFFD]*)\\]', 'giu');
-    return wikitext.replace(regex, (_, url, space, text) => {
-        const { length } = accum, mt = /&[lg]t;/u.exec(url);
-        if (mt) {
-            url = url.slice(0, mt.index);
-            space = '';
-            text = `${url.slice(mt.index)}${space}${text}`;
-        }
-        new extLink_1.ExtLinkToken(url, space, text, config, accum);
-        return `\0${length}w\x7F`;
-    });
-};
-exports.parseExternalLinks = parseExternalLinks;
-constants_1.parsers['parseExternalLinks'] = __filename;

package/dist/parser/hrAndDoubleUnderscore.js

@@ -1,38 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseHrAndDoubleUnderscore = void 0;
-const constants_1 = require("../util/constants");
-const Parser = require("../index");
-const hr_1 = require("../src/nowiki/hr");
-const doubleUnderscore_1 = require("../src/nowiki/doubleUnderscore");
-const heading_1 = require("../src/heading");
-/**
- * 解析`<hr>`和状态开关
- * @param {Token} root 根节点
- * @param config
- * @param accum
- */
-const parseHrAndDoubleUnderscore = ({ firstChild: { data }, type, name }, config = Parser.getConfig(), accum = []) => {
-    const { doubleUnderscore } = config, insensitive = new Set(doubleUnderscore[0]), sensitive = new Set(doubleUnderscore[1]);
-    if (type !== 'root' && (type !== 'ext-inner' || name !== 'poem')) {
-        data = `\0${data}`;
-    }
-    data = data.replace(/^((?:\0\d+c\x7F)*)(-{4,})/gmu, (_, lead, m) => {
-        new hr_1.HrToken(m, config, accum);
-        return `${lead}\0${accum.length - 1}r\x7F`;
-    }).replace(new RegExp(`__(${doubleUnderscore.flat().join('|')})__`, 'giu'), (m, p1) => {
-        const caseSensitive = sensitive.has(p1);
-        if (caseSensitive || insensitive.has(p1.toLowerCase())) {
-            new doubleUnderscore_1.DoubleUnderscoreToken(p1, caseSensitive, config, accum);
-            return `\0${accum.length - 1}u\x7F`;
-        }
-        return m;
-    }).replace(/^((?:\0\d+c\x7F)*)(={1,6})(.+)\2((?:[^\S\n]|\0\d+c\x7F)*)$/gmu, (_, lead, equals, heading, trail) => {
-        const text = `${lead}\0${accum.length}h\x7F`;
-        new heading_1.HeadingToken(equals.length, [heading, trail], config, accum);
-        return text;
-    });
-    return type === 'root' || type === 'ext-inner' && name === 'poem' ? data : data.slice(1);
-};
-exports.parseHrAndDoubleUnderscore = parseHrAndDoubleUnderscore;
-constants_1.parsers['parseHrAndDoubleUnderscore'] = __filename;

package/dist/parser/html.js

@@ -1,36 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseHtml = void 0;
-const constants_1 = require("../util/constants");
-const Parser = require("../index");
-const attributes_1 = require("../src/attributes");
-const html_1 = require("../src/html");
-/**
- * 解析HTML标签
- * @param wikitext
- * @param config
- * @param accum
- */
-const parseHtml = (wikitext, config = Parser.getConfig(), accum = []) => {
-    const regex = /^(\/?)([a-z][^\s/>]*)((?:\s|\/(?!>))[^>]*?)?(\/?>)([^<]*)$/iu, elements = new Set(config.html.flat()), bits = wikitext.split('<');
-    let text = bits.shift();
-    for (const x of bits) {
-        const mt = regex.exec(x), t = mt?.[2], name = t?.toLowerCase();
-        if (!mt || !elements.has(name)) {
-            text += `<${x}`;
-            continue;
-        }
-        const [, slash, , params = '', brace, rest] = mt, attr = new attributes_1.AttributesToken(params, 'html-attrs', name, config, accum), itemprop = attr.getAttr('itemprop');
-        if (name === 'meta' && (itemprop === undefined || attr.getAttr('content') === undefined)
-            || name === 'link' && (itemprop === undefined || attr.getAttr('href') === undefined)) {
-            text += `<${x}`;
-            accum.pop();
-            continue;
-        }
-        text += `\0${accum.length}x\x7F${rest}`;
-        new html_1.HtmlToken(t, attr, slash === '/', brace === '/>', config, accum);
-    }
-    return text;
-};
-exports.parseHtml = parseHtml;
-constants_1.parsers['parseHtml'] = __filename;

package/dist/parser/links.js

@@ -1,94 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseLinks = void 0;
-const constants_1 = require("../util/constants");
-const Parser = require("../index");
-const index_1 = require("../src/link/index");
-const file_1 = require("../src/link/file");
-const category_1 = require("../src/link/category");
-/**
- * 解析内部链接
- * @param wikitext
- * @param config
- * @param accum
- */
-const parseLinks = (wikitext, config = Parser.getConfig(), accum = []) => {
-    const { parseQuotes } = require('./quotes');
-    const regex = /^((?:(?!\0\d+!\x7F)[^\n[\]{}|])+)(?:(\||\0\d+!\x7F)(.*?[^\]]))?\]\](.*)$/su, regexImg = /^((?:(?!\0\d+!\x7F)[^\n[\]{}|])+)(\||\0\d+!\x7F)(.*)$/su, regexExt = new RegExp(`^\\s*(?:${config.protocol}|//)`, 'iu'), bits = wikitext.split('[[');
-    let s = bits.shift();
-    for (let i = 0; i < bits.length; i++) {
-        let mightBeImg = false, link, delimiter, text, after;
-        const x = bits[i], m = regex.exec(x);
-        if (m) {
-            [, link, delimiter, text, after] = m;
-            if (after.startsWith(']') && text?.includes('[')) {
-                text += ']';
-                after = after.slice(1);
-            }
-        }
-        else {
-            const m2 = regexImg.exec(x);
-            if (m2) {
-                mightBeImg = true;
-                [, link, delimiter, text] = m2;
-            }
-        }
-        if (link === undefined || regexExt.test(link) || /\0\d+[exhbru]\x7F/u.test(link)) {
-            s += `[[${x}`;
-            continue;
-        }
-        const force = link.trim().startsWith(':');
-        if (force && mightBeImg) {
-            s += `[[${x}`;
-            continue;
-        }
-        const title = Parser.normalizeTitle(link, 0, false, config, true, true, true), { ns, interwiki, valid, } = title;
-        if (!valid) {
-            s += `[[${x}`;
-            continue;
-        }
-        else if (mightBeImg) {
-            if (interwiki || ns !== 6) {
-                s += `[[${x}`;
-                continue;
-            }
-            let found = false;
-            for (i++; i < bits.length; i++) {
-                const next = bits[i], p = next.split(']]');
-                if (p.length > 2) {
-                    found = true;
-                    text += `[[${p[0]}]]${p[1]}`;
-                    after = p.slice(2).join(']]');
-                    break;
-                }
-                else if (p.length === 2) {
-                    text += `[[${p[0]}]]${p[1]}`;
-                }
-                else {
-                    text += `[[${next}`;
-                    break;
-                }
-            }
-            text = (0, exports.parseLinks)(text, config, accum);
-            if (!found) {
-                s += `[[${link}${delimiter}${text}`;
-                continue;
-            }
-        }
-        text &&= parseQuotes(text, config, accum);
-        s += `\0${accum.length}l\x7F${after}`;
-        let SomeLinkToken = index_1.LinkToken;
-        if (!force) {
-            if (!interwiki && ns === 6) {
-                SomeLinkToken = file_1.FileToken;
-            }
-            else if (!interwiki && ns === 14) {
-                SomeLinkToken = category_1.CategoryToken;
-            }
-        }
-        new SomeLinkToken(link, text, config, accum, delimiter);
-    }
-    return s;
-};
-exports.parseLinks = parseLinks;
-constants_1.parsers['parseLinks'] = __filename;

package/dist/parser/list.js

@@ -1,66 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseList = void 0;
-const constants_1 = require("../util/constants");
-const Parser = require("../index");
-const list_1 = require("../src/nowiki/list");
-const dd_1 = require("../src/nowiki/dd");
-/**
- * 解析列表
- * @param wikitext
- * @param config
- * @param accum
- */
-const parseList = (wikitext, config = Parser.getConfig(), accum = []) => {
-    const mt = /^((?:\0\d+c\x7F)*)([;:*#]+)/u.exec(wikitext);
-    if (!mt) {
-        return wikitext;
-    }
-    const [total, comment, prefix] = mt;
-    let text = `${comment}\0${accum.length}d\x7F${wikitext.slice(total.length)}`, dt = prefix.split(';').length - 1;
-    new list_1.ListToken(prefix, config, accum);
-    if (!dt) {
-        return text;
-    }
-    let regex = /:+|-\{/gu, ex = regex.exec(text), lc = 0;
-    /**
-     * 创建`DdToken`
-     * @param syntax `:`
-     * @param index 起点
-     */
-    const dd = (syntax, index) => {
-        new dd_1.DdToken(syntax, config, accum);
-        return `${text.slice(0, index)}\0${accum.length - 1}d\x7F${text.slice(index + syntax.length)}`;
-    };
-    while (ex && dt) {
-        const { 0: syntax, index } = ex;
-        if (syntax.startsWith(':')) {
-            if (syntax.length >= dt) {
-                return dd(syntax.slice(0, dt), index);
-            }
-            dt -= syntax.length;
-            regex.lastIndex = index + 4 + String(accum.length).length;
-            text = dd(syntax, index);
-        }
-        else if (syntax === '-{') {
-            if (!lc) {
-                const { lastIndex } = regex;
-                regex = /-\{|\}-/gu;
-                regex.lastIndex = lastIndex;
-            }
-            lc++;
-        }
-        else {
-            lc--;
-            if (!lc) {
-                const { lastIndex } = regex;
-                regex = /:+|-\{/gu;
-                regex.lastIndex = lastIndex;
-            }
-        }
-        ex = regex.exec(text);
-    }
-    return text;
-};
-exports.parseList = parseList;
-constants_1.parsers['parseList'] = __filename;

package/dist/parser/magicLinks.js

@@ -1,42 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseMagicLinks = void 0;
-const string_1 = require("../util/string");
-const constants_1 = require("../util/constants");
-const Parser = require("../index");
-const magicLink_1 = require("../src/magicLink");
-/**
- * 解析自由外链
- * @param wikitext
- * @param config
- * @param accum
- */
-const parseMagicLinks = (wikitext, config = Parser.getConfig(), accum = []) => {
-    // eslint-disable-next-line @typescript-eslint/no-unused-expressions
-    /(^|[^\p{L}\d_])((?:\[[\da-f:.]+\]|[^[\]<>"\t\n\p{Zs}])(?:[^[\]<>"\0\t\n\p{Zs}]|\0\d+c\x7F)*)/giu;
-    const regex = new RegExp(`(^|[^\\p{L}\\d_])(?:${config.protocol})(${string_1.extUrlCharFirst}${string_1.extUrlChar})`, 'giu');
-    return wikitext.replace(regex, (m, lead, p1) => {
-        let trail = '', url = lead ? m.slice(1) : m;
-        const m2 = /&(?:lt|gt|nbsp|#x0*(?:3[ce]|a0)|#0*(?:6[02]|160));/iu.exec(url);
-        if (m2) {
-            trail = url.slice(m2.index);
-            url = url.slice(0, m2.index);
-        }
-        const sep = new RegExp(`[,;.:!?${url.includes('(') ? '' : ')'}]+$`, 'u'), sepChars = sep.exec(url);
-        if (sepChars) {
-            let correction = 0;
-            if (sepChars[0].startsWith(';') && /&(?:[a-z]+|#x[\da-f]+|#\d+)$/iu.test(url.slice(0, sepChars.index))) {
-                correction = 1;
-            }
-            trail = `${url.slice(sepChars.index + correction)}${trail}`;
-            url = url.slice(0, sepChars.index + correction);
-        }
-        if (trail.length >= p1.length) {
-            return m;
-        }
-        new magicLink_1.MagicLinkToken(url, false, config, accum);
-        return `${lead}\0${accum.length - 1}w\x7F${trail}`;
-    });
-};
-exports.parseMagicLinks = parseMagicLinks;
-constants_1.parsers['parseMagicLinks'] = __filename;

package/dist/parser/quotes.js

@@ -1,67 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseQuotes = void 0;
-const constants_1 = require("../util/constants");
-const Parser = require("../index");
-const quote_1 = require("../src/nowiki/quote");
-/**
- * 解析单引号
- * @param wikitext
- * @param config
- * @param accum
- */
-const parseQuotes = (wikitext, config = Parser.getConfig(), accum = []) => {
-    const arr = wikitext.split(/('{2,})/u), { length } = arr;
-    if (length === 1) {
-        return wikitext;
-    }
-    let nBold = 0, nItalic = 0, firstSingle, firstMulti, firstSpace;
-    for (let i = 1; i < length; i += 2) {
-        const { length: len } = arr[i];
-        switch (len) {
-            case 2:
-                nItalic++;
-                break;
-            case 4:
-                arr[i - 1] += `'`;
-                arr[i] = `'''`;
-            // fall through
-            case 3:
-                nBold++;
-                if (firstSingle !== undefined) {
-                    break;
-                }
-                else if (arr[i - 1].endsWith(' ')) {
-                    if (firstMulti === undefined && firstSpace === undefined) {
-                        firstSpace = i;
-                    }
-                }
-                else if (arr[i - 1].slice(-2, -1) === ' ') {
-                    firstSingle = i;
-                }
-                else {
-                    firstMulti ??= i;
-                }
-                break;
-            default:
-                arr[i - 1] += `'`.repeat(len - 5);
-                arr[i] = `'''''`;
-                nItalic++;
-                nBold++;
-        }
-    }
-    if (nItalic % 2 === 1 && nBold % 2 === 1) {
-        const i = firstSingle ?? firstMulti ?? firstSpace;
-        if (i !== undefined) {
-            arr[i] = `''`;
-            arr[i - 1] += `'`;
-        }
-    }
-    for (let i = 1; i < length; i += 2) {
-        new quote_1.QuoteToken(arr[i], config, accum);
-        arr[i] = `\0${accum.length - 1}q\x7F`;
-    }
-    return arr.join('');
-};
-exports.parseQuotes = parseQuotes;
-constants_1.parsers['parseQuotes'] = __filename;

package/dist/parser/selector.js

@@ -1,162 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseSelector = void 0;
-const constants_1 = require("../util/constants");
-const string_1 = require("../util/string");
-const Parser = require("../index");
-const simplePseudos = new Set([
-    'root',
-    'first-child',
-    'first-of-type',
-    'last-child',
-    'last-of-type',
-    'only-child',
-    'only-of-type',
-    'empty',
-    'parent',
-    'header',
-    'hidden',
-    'visible',
-    'only-whitespace',
-    'any-link',
-    'local-link',
-    'invalid',
-    'required',
-    'optional',
-]);
-const complexPseudos = [
-    'is',
-    'not',
-    'nth-child',
-    'nth-of-type',
-    'nth-last-child',
-    'nth-last-of-type',
-    'contains',
-    'has',
-    'lang',
-    'regex',
-];
-const specialChars = [
-    ['[', '['],
-    [']', ']'],
-    ['(', '('],
-    [')', ')'],
-    ['"', '"'],
-    [`'`, '''],
-    [':', ':'],
-    ['\\', '\'],
-    ['&', '&'],
-];
-const pseudoRegex = new RegExp(`:(${complexPseudos.join('|')})$`, 'u'), regularRegex = /[[(,>+~]|\s+/u, attributeRegex = /^\s*(\w+)\s*(?:([~|^$*!]?=)\s*("[^"]*"|'[^']*'|[^\s[\]]+)(?:\s+(i))?\s*)?\]/u, functionRegex = /^(\s*"[^"]*"\s*|\s*'[^']*'\s*|[^()]*)\)/u, grouping = new Set([',', '>', '+', '~']), combinator = new Set(['>', '+', '~', '']);
-/**
- * 清理转义符号
- * @param selector
- */
-const sanitize = (selector) => {
-    for (const [c, escaped] of specialChars) {
-        selector = selector.replace(new RegExp((0, string_1.escapeRegExp)(`\\${c}`), 'gu'), escaped);
-    }
-    return selector;
-};
-/**
- * 还原转义符号
- * @param selector
- */
-const desanitize = (selector) => {
-    for (const [c, escaped] of specialChars) {
-        selector = selector.replace(new RegExp(escaped, 'gu'), c);
-    }
-    return selector.trim();
-};
-/**
- * 去除首尾的引号
- * @param val 属性值或伪选择器函数的参数
- */
-const deQuote = (val) => /^(["']).*\1$/u.test(val) ? val.slice(1, -1) : val.trim();
-/**
- * 解析选择器
- * @param selector
- * @throws `SyntaxError` 非法的选择器
- */
-const parseSelector = (selector) => {
-    selector = selector.trim();
-    const stack = [[[]]];
-    let sanitized = sanitize(selector), regex = regularRegex, mt = regex.exec(sanitized), [condition] = stack, [step] = condition;
-    /**
-     * 解析简单伪选择器
-     * @param index 伪选择器的终点位置
-     * @throws `SyntaxError` 非法的选择器
-     */
-    const pushSimple = (index) => {
-        const str = sanitized.slice(0, index), pieces = str.trim().split(':'), 
-        // eslint-disable-next-line unicorn/explicit-length-check
-        i = pieces.slice(1).findIndex(pseudo => simplePseudos.has(pseudo)) + 1 || pieces.length;
-        if (pieces.slice(i).some(pseudo => !simplePseudos.has(pseudo))) {
-            throw new SyntaxError(`非法的选择器！\n${str}\n可能需要将':'转义为'\\:'。`);
-        }
-        step.push(desanitize(pieces.slice(0, i).join(':')), ...pieces.slice(i).map(piece => `:${piece}`));
-    };
-    while (mt) {
-        let { 0: syntax, index } = mt;
-        if (syntax.trim() === '') {
-            index += syntax.length;
-            const char = sanitized[index];
-            syntax = grouping.has(char) ? char : '';
-        }
-        if (syntax === ',') { // 情形1：并列
-            pushSimple(index);
-            condition = [[]];
-            [step] = condition;
-            stack.push(condition);
-        }
-        else if (combinator.has(syntax)) { // 情形2：关系
-            pushSimple(index);
-            if (!step.some(Boolean)) {
-                throw new SyntaxError(`非法的选择器！\n${selector}\n可能需要通用选择器'*'。`);
-            }
-            step.relation = syntax;
-            step = [];
-            condition.push(step);
-        }
-        else if (syntax === '[') { // 情形3：属性开启
-            pushSimple(index);
-            regex = attributeRegex;
-        }
-        else if (syntax.endsWith(']')) { // 情形4：属性闭合
-            mt[3] &&= desanitize(deQuote(mt[3]));
-            step.push(mt.slice(1));
-            regex = regularRegex;
-        }
-        else if (syntax === '(') { // 情形5：伪选择器开启
-            const pseudoExec = pseudoRegex.exec(sanitized.slice(0, index));
-            if (!pseudoExec) {
-                throw new SyntaxError(`非法的选择器！\n${desanitize(sanitized)}\n请检查伪选择器是否存在。`);
-            }
-            pushSimple(pseudoExec.index);
-            step.push(pseudoExec[1]); // 临时存放复杂伪选择器
-            regex = functionRegex;
-        }
-        else { // 情形6：伪选择器闭合
-            mt.push(step.pop());
-            mt[1] &&= deQuote(mt[1]);
-            step.push(mt.slice(1));
-            regex = regularRegex;
-        }
-        sanitized = sanitized.slice(index + syntax.length);
-        if (grouping.has(syntax)) {
-            sanitized = sanitized.trim();
-        }
-        mt = regex.exec(sanitized);
-    }
-    if (regex === regularRegex) {
-        pushSimple(Infinity);
-        const pseudos = new Set(stack.flat(2).filter((e) => typeof e === 'string' && e.startsWith(':')));
-        if (pseudos.size > 0) {
-            Parser.warn('检测到伪选择器，请确认是否需要将":"转义成"\\:"。', pseudos);
-        }
-        return stack;
-    }
-    throw new SyntaxError(`非法的选择器！\n${selector}\n检测到未闭合的'${regex === attributeRegex ? '[' : '('}'`);
-};
-exports.parseSelector = parseSelector;
-constants_1.parsers['parseSelector'] = __filename;