wikiparser-node 0.4.0 → 0.6.2-b

package/lib/text.js

@@ -1,146 +0,0 @@
-'use strict';
-
-const AstNode = require('./node'),
-	Parser = require('..');
-
-/** 文本节点 */
-class AstText extends AstNode {
-	type = 'text';
-	/** @type {string} */ data;
-
-	/** 文本长度 */
-	get length() {
-		return this.data.length;
-	}
-
-	/** @param {string} text 包含文本 */
-	constructor(text = '') {
-		super();
-		Object.defineProperties(this, {
-			data: {value: text, writable: false},
-			childNodes: {enumerable: false, configurable: false},
-			type: {enumerable: false, writable: false, configurable: false},
-		});
-	}
-
-	/** 复制 */
-	cloneNode() {
-		return new AstText(this.data);
-	}
-
-	/**
-	 * @override
-	 * @template {string} T
-	 * @param {T} key 属性键
-	 * @returns {TokenAttribute<T>}
-	 */
-	getAttribute(key) {
-		return key === 'verifyChild'
-			? () => {
-				throw new Error('文本节点没有子节点！');
-			}
-			: super.getAttribute(key);
-	}
-
-	/** 输出字符串 */
-	toString() {
-		return this.data;
-	}
-
-	/** @override */
-	text() {
-		return this.data;
-	}
-
-	/**
-	 * 修改内容
-	 * @param {string} text 新内容
-	 */
-	#setData(text) {
-		text = String(text);
-		const {data} = this,
-			e = new Event('text', {bubbles: true});
-		this.setAttribute('data', text);
-		if (data !== text) {
-			this.dispatchEvent(e, {oldText: data, newText: text});
-		}
-		return this;
-	}
-
-	/**
-	 * 在后方添加字符串
-	 * @param {string} text 添加的字符串
-	 * @throws `Error` 禁止外部调用
-	 */
-	appendData(text) {
-		this.#setData(this.data + text);
-	}
-
-	/**
-	 * 删减字符串
-	 * @param {number} offset 起始位置
-	 * @param {number} count 删减字符数
-	 * @throws `RangeError` 错误的删减位置
-	 * @throws `Error` 禁止外部调用
-	 */
-	deleteData(offset, count) {
-		this.#setData(this.data.slice(0, offset) + this.data.slice(offset + count));
-	}
-
-	/**
-	 * 插入字符串
-	 * @param {number} offset 插入位置
-	 * @param {string} text 待插入的字符串
-	 * @throws `RangeError` 错误的插入位置
-	 * @throws `Error` 禁止外部调用
-	 */
-	insertData(offset, text) {
-		this.#setData(this.data.slice(0, offset) + text + this.data.slice(offset));
-	}
-
-	/**
-	 * 替换字符串
-	 * @param {string} text 替换的字符串
-	 * @throws `Error` 禁止外部调用
-	 */
-	replaceData(text = '') {
-		this.#setData(text);
-	}
-
-	/**
-	 * 提取子串
-	 * @param {number} offset 起始位置
-	 * @param {number} count 字符数
-	 */
-	substringData(offset, count) {
-		return this.data.slice(offset, offset + count);
-	}
-
-	/**
-	 * 将文本子节点分裂为两部分
-	 * @param {number} offset 分裂位置
-	 * @throws `RangeError` 错误的断开位置
-	 * @throws `Error` 没有父节点
-	 */
-	splitText(offset) {
-		if (typeof offset !== 'number') {
-			this.typeError('splitText', 'Number');
-		} else if (offset > this.length || offset < -this.length || !Number.isInteger(offset)) {
-			throw new RangeError(`错误的断开位置！${offset}`);
-		}
-		const {parentNode, data} = this;
-		if (!parentNode) {
-			throw new Error('待分裂的文本节点没有父节点！');
-		}
-		const newText = new AstText(data.slice(offset)),
-			childNodes = [...parentNode.childNodes];
-		this.setAttribute('data', data.slice(0, offset));
-		childNodes.splice(childNodes.indexOf(this) + 1, 0, newText);
-		newText.setAttribute('parentNode', parentNode);
-		parentNode.setAttribute('childNodes', childNodes);
-		return newText;
-	}
-}
-
-Parser.classes.AstText = __filename;
-module.exports = AstText;

package/lib/title.js

@@ -1,69 +0,0 @@
-'use strict';
-
-const Parser = require('..');
-
-/** MediaWiki页面标题对象 */
-class Title {
-	title = '';
-	main = '';
-	prefix = '';
-	ns = 0;
-	interwiki = '';
-	fragment = '';
-	valid = true;
-
-	/**
-	 * @param {string} title 标题（含或不含命名空间前缀）
-	 * @param {number} defaultNs 命名空间
-	 */
-	constructor(title, defaultNs = 0, config = Parser.getConfig()) {
-		const {namespaces, nsid} = config;
-		let namespace = namespaces[defaultNs];
-		title = title.replaceAll('_', ' ').trim();
-		if (title[0] === ':') {
-			namespace = '';
-			title = title.slice(1).trim();
-		}
-		const iw = defaultNs ? null : Parser.isInterwiki(title, config);
-		if (iw) {
-			this.interwiki = iw[1].toLowerCase();
-			title = title.slice(iw[0].length);
-		}
-		const m = title.split(':');
-		if (m.length > 1) {
-			const id = namespaces[nsid[m[0].trim().toLowerCase()]];
-			if (id !== undefined) {
-				namespace = id;
-				title = m.slice(1).join(':').trim();
-			}
-		}
-		this.ns = nsid[namespace.toLowerCase()];
-		const i = title.indexOf('#');
-		if (i !== -1) {
-			const fragment = title.slice(i + 1).trimEnd();
-			if (fragment.includes('%')) {
-				try {
-					this.fragment = decodeURIComponent(fragment);
-				} catch {}
-			} else if (fragment.includes('.')) {
-				try {
-					this.fragment = decodeURIComponent(fragment.replaceAll('.', '%'));
-				} catch {}
-			}
-			this.fragment ||= fragment;
-			title = title.slice(0, i).trim();
-		}
-		this.main = title && `${title[0].toUpperCase()}${title.slice(1)}`;
-		this.prefix = `${namespace}${namespace && ':'}`;
-		this.title = `${iw ? `${this.interwiki}:` : ''}${this.prefix}${this.main}`;
-		this.valid = Boolean(this.main || this.fragment) && !/\0\d+[eh!+-]\x7F|[<>[\]{}|]/u.test(this.title);
-	}
-
-	/** @override */
-	toString() {
-		return `${this.title}${this.fragment && '#'}${this.fragment}`;
-	}
-}
-
-Parser.classes.Title = __filename;
-module.exports = Title;

package/mixin/attributeParent.js

@@ -1,113 +0,0 @@
-'use strict';
-
-const Parser = require('..'),
-	AttributeToken = require('../src/attribute');
-
-/**
- * 子节点含有AttributeToken的类
- * @template T
- * @param {T} Constructor 基类
- * @param {number} i AttributeToken子节点的位置
- * @returns {T}
- */
-const attributeParent = (Constructor, i = 0) => class extends Constructor {
-	/**
-	 * getAttr()方法的getter写法
-	 * @returns {Record<string, string|true>}
-	 */
-	get attributes() {
-		return this.getAttr();
-	}
-
-	/** 以字符串表示的class属性 */
-	get className() {
-		const attr = this.getAttr('class');
-		return typeof attr === 'string' ? attr : '';
-	}
-
-	set className(className) {
-		this.setAttr('class', className);
-	}
-
-	/** 以Set表示的class属性 */
-	get classList() {
-		return new Set(this.className.split(/\s/u));
-	}
-
-	/** id属性 */
-	get id() {
-		const attr = this.getAttr('id');
-		return typeof attr === 'string' ? attr : '';
-	}
-
-	set id(id) {
-		this.setAttr('id', id);
-	}
-
-	/**
-	 * AttributeToken子节点是否具有某属性
-	 * @this {{childNodes: AttributeToken[]}}
-	 * @param {string} key 属性键
-	 */
-	hasAttr(key) {
-		return this.childNodes.at(i).hasAttr(key);
-	}
-
-	/**
-	 * 获取AttributeToken子节点的属性
-	 * @this {{childNodes: AttributeToken[]}}
-	 * @template {string|undefined} T
-	 * @param {T} key 属性键
-	 */
-	getAttr(key) {
-		return this.childNodes.at(i).getAttr(key);
-	}
-
-	/**
-	 * 列举AttributeToken子节点的属性键
-	 * @this {{childNodes: AttributeToken[]}}
-	 */
-	getAttrNames() {
-		return this.childNodes.at(i).getAttrNames();
-	}
-
-	/**
-	 * AttributeToken子节点是否具有任意属性
-	 * @this {{childNodes: AttributeToken[]}}
-	 */
-	hasAttrs() {
-		return this.childNodes.at(i).hasAttrs();
-	}
-
-	/**
-	 * 对AttributeToken子节点设置属性
-	 * @this {{childNodes: AttributeToken[]}}
-	 * @param {string} key 属性键
-	 * @param {string|boolean} value 属性值
-	 */
-	setAttr(key, value) {
-		return this.childNodes.at(i).setAttr(key, value);
-	}
-
-	/**
-	 * 移除AttributeToken子节点的某属性
-	 * @this {{childNodes: AttributeToken[]}}
-	 * @param {string} key 属性键
-	 */
-	removeAttr(key) {
-		this.childNodes.at(i).removeAttr(key);
-	}
-
-	/**
-	 * 开关AttributeToken子节点的某属性
-	 * @this {{childNodes: AttributeToken[]}}
-	 * @param {string} key 属性键
-	 * @param {boolean|undefined} force 强制开启或关闭
-	 */
-	toggleAttr(key, force) {
-		this.childNodes.at(i).toggleAttr(key, force);
-	}
-};
-
-Parser.mixins.attributeParent = __filename;
-module.exports = attributeParent;

package/mixin/fixedToken.js

@@ -1,40 +0,0 @@
-'use strict';
-
-const Parser = require('..'),
-	Token = require('../src');
-
-/**
- * 不可增删子节点的类
- * @template T
- * @param {T} Constructor 基类
- * @returns {T}
- */
-const fixedToken = Constructor => class extends Constructor {
-	static fixed = true;
-
-	/**
-	 * 移除子节点
-	 * @throws `Error`
-	 */
-	removeAt() {
-		throw new Error(`${this.constructor.name} 不可删除元素！`);
-	}
-
-	/**
-	 * 插入子节点
-	 * @template {Token} T
-	 * @param {T} token 待插入的子节点
-	 * @param {number} i 插入位置
-	 * @throws `Error`
-	 */
-	insertAt(token, i = this.childNodes.length) {
-		if (!Parser.running) {
-			throw new Error(`${this.constructor.name} 不可插入元素！`);
-		}
-		super.insertAt(token, i);
-		return token;
-	}
-};
-
-Parser.mixins.fixedToken = __filename;
-module.exports = fixedToken;

package/mixin/hidden.js

@@ -1,19 +0,0 @@
-'use strict';
-
-const Parser = require('..');
-
-/**
- * 解析后不可见的类
- * @template T
- * @param {T} Constructor 基类
- * @returns {T}
- */
-const hidden = Constructor => class extends Constructor {
-	/** 没有可见部分 */
-	text() { // eslint-disable-line class-methods-use-this
-		return '';
-	}
-};
-
-Parser.mixins.hidden = __filename;
-module.exports = hidden;

package/mixin/sol.js

@@ -1,59 +0,0 @@
-'use strict';
-
-const Parser = require('..'),
-	Token = require('../src');
-
-/**
- * 只能位于行首的类
- * @template T
- * @param {T} Constructor 基类
- * @returns {T}
- */
-const sol = Constructor => class extends Constructor {
-	/**
-	 * 在前方插入newline
-	 * @this {Token}
-	 */
-	prependNewLine() {
-		const {previousVisibleSibling = '', parentNode} = this;
-		return (previousVisibleSibling || parentNode?.type !== 'root') && String(previousVisibleSibling).at(-1) !== '\n'
-			? '\n'
-			: '';
-	}
-
-	/**
-	 * 在后方插入newline
-	 * @this {Token}
-	 */
-	appendNewLine() {
-		const {nextVisibleSibling = '', parentNode} = this;
-		return (nextVisibleSibling || parentNode?.type !== 'root') && String(nextVisibleSibling ?? '')[0] !== '\n'
-			? '\n'
-			: '';
-	}
-
-	/**
-	 * 还原为wikitext
-	 * @param {string} selector
-	 * @param {boolean} ownLine 是否独占一行
-	 */
-	toString(selector, ownLine) {
-		return `${this.prependNewLine()}${super.toString(selector)}${ownLine ? this.appendNewLine() : ''}`;
-	}
-
-	/** 获取padding */
-	getPadding() {
-		return this.prependNewLine().length;
-	}
-
-	/**
-	 * 可见部分
-	 * @param {booean} ownLine 是否独占一行
-	 */
-	text(ownLine) {
-		return `${this.prependNewLine()}${super.text()}${ownLine ? this.appendNewLine() : ''}`;
-	}
-};
-
-Parser.mixins.sol = __filename;
-module.exports = sol;

package/parser/brackets.js

@@ -1,112 +0,0 @@
-'use strict';
-
-const {removeComment} = require('../util/string'),
-	Parser = require('..');
-
-/**
- * 解析花括号
- * @param {string} text wikitext
- * @param {accum} accum
- * @throws TranscludeToken.constructor()
- */
-const parseBrackets = (text, config = Parser.getConfig(), accum = []) => {
-	const source = '^(\0\\d+c\x7F)*={1,6}|\\[\\[|\\{{2,}|-\\{(?!\\{)',
-		/** @type {BracketExecArray[]} */ stack = [],
-		closes = {'=': '\n', '{': '\\}{2,}|\\|', '-': '\\}-', '[': '\\]\\]'},
-		/** @type {Record<string, string>} */ marks = {'!': '!', '!!': '+', '(!': '{', '!)': '}', '!-': '-', '=': '~'};
-	let regex = new RegExp(source, 'gmu'),
-		/** @type {BracketExecArray} */ mt = regex.exec(text),
-		moreBraces = text.includes('}}'),
-		lastIndex;
-	while (mt || lastIndex <= text.length && stack.at(-1)?.[0]?.[0] === '=') {
-		if (mt?.[1]) {
-			const [, {length}] = mt;
-			mt[0] = mt[0].slice(length);
-			mt.index += length;
-		}
-		const {0: syntax, index: curIndex} = mt ?? {0: '\n', index: text.length},
-			/** @type {BracketExecArray} */ top = stack.pop() ?? {},
-			{0: open, index, parts, findEqual: topFindEqual, pos: topPos} = top,
-			innerEqual = syntax === '=' && topFindEqual;
-		if (syntax === ']]' || syntax === '}-') { // 情形1：闭合内链或转换
-			lastIndex = curIndex + 2;
-		} else if (syntax === '\n') { // 情形2：闭合标题
-			lastIndex = curIndex + 1;
-			const {pos, findEqual} = stack.at(-1) ?? {};
-			if (!pos || findEqual || removeComment(text.slice(pos, index)) !== '') {
-				const rmt = /^(={1,6})(.+)\1((?:\s|\0\d+c\x7F)*)$/u.exec(text.slice(index, curIndex));
-				if (rmt) {
-					text = `${text.slice(0, index)}\0${accum.length}h\x7F${text.slice(curIndex)}`;
-					lastIndex = index + 4 + String(accum.length).length;
-					const HeadingToken = require('../src/heading');
-					new HeadingToken(rmt[1].length, rmt.slice(2), config, accum);
-				}
-			}
-		} else if (syntax === '|' || innerEqual) { // 情形3：模板内部，含行首单个'='
-			lastIndex = curIndex + 1;
-			parts.at(-1).push(text.slice(topPos, curIndex));
-			if (syntax === '|') {
-				parts.push([]);
-			}
-			top.pos = lastIndex;
-			top.findEqual = syntax === '|';
-			stack.push(top);
-		} else if (syntax.startsWith('}}')) { // 情形4：闭合模板
-			const close = syntax.slice(0, Math.min(open.length, 3)),
-				rest = open.length - close.length,
-				{length} = accum;
-			lastIndex = curIndex + close.length; // 这不是最终的lastIndex
-			parts.at(-1).push(text.slice(topPos, curIndex));
-			const ch = close.length === 2 ? marks[removeComment(parts[0][0])] ?? 't' : 't'; // 标记{{!}}等
-			let skip = false;
-			if (close.length === 3) {
-				const ArgToken = require('../src/arg');
-				new ArgToken(parts.map(part => part.join('=')), config, accum);
-			} else {
-				try {
-					const TranscludeToken = require('../src/transclude');
-					new TranscludeToken(parts[0][0], parts.slice(1), config, accum);
-				} catch (e) {
-					if (e instanceof Error && e.message.startsWith('非法的模板名称：')) {
-						lastIndex = index + open.length;
-						skip = true;
-					} else {
-						throw e;
-					}
-				}
-			}
-			if (!skip) {
-				text = `${text.slice(0, index + rest)}\0${length}${ch}\x7F${text.slice(lastIndex)}`;
-				lastIndex = index + rest + 3 + String(length).length;
-				if (rest > 1) {
-					stack.push({0: open.slice(0, rest), index, pos: index + rest, parts: [[]]});
-				} else if (rest === 1 && text[index - 1] === '-') {
-					stack.push({0: '-{', index: index - 1, pos: index + 1, parts: [[]]});
-				}
-			}
-		} else { // 情形5：开启
-			lastIndex = curIndex + syntax.length;
-			if (syntax[0] === '{') {
-				mt.pos = lastIndex;
-				mt.parts = [[]];
-			}
-			stack.push(...'0' in top ? [top] : [], mt);
-		}
-		moreBraces &&= text.slice(lastIndex).includes('}}');
-		let curTop = stack.at(-1);
-		if (!moreBraces && curTop?.[0]?.[0] === '{') {
-			stack.pop();
-			curTop = stack.at(-1);
-		}
-		regex = new RegExp(source + (curTop
-			? `|${closes[curTop[0][0]]}${curTop.findEqual ? '|=' : ''}`
-			: ''
-		), 'gmu');
-		regex.lastIndex = lastIndex;
-		mt = regex.exec(text);
-	}
-	return text;
-};
-
-Parser.parsers.parseBrackets = __filename;
-module.exports = parseBrackets;

package/parser/commentAndExt.js

@@ -1,63 +0,0 @@
-'use strict';
-
-const Parser = require('..');
-
-/**
- * 解析HTML注释和扩展标签
- * @param {string} text wikitext
- * @param {accum} accum
- * @param {boolean} includeOnly 是否嵌入
- */
-const parseCommentAndExt = (text, config = Parser.getConfig(), accum = [], includeOnly = false) => {
-	const onlyinclude = /<onlyinclude>(.*?)<\/onlyinclude>/gsu;
-	if (includeOnly && text.search(onlyinclude) !== -1) { // `<onlyinclude>`拥有最高优先级
-		return text.replaceAll(onlyinclude, /** @param {string} inner */ (_, inner) => {
-			const str = `\0${accum.length}e\x7F`;
-			const OnlyincludeToken = require('../src/onlyinclude');
-			new OnlyincludeToken(inner, config, accum);
-			return str;
-		}).replaceAll(/(?<=^|\0\d+e\x7F).*?(?=$|\0\d+e\x7F)/gsu, substr => {
-			if (substr === '') {
-				return '';
-			}
-			const NoincludeToken = require('../src/nowiki/noinclude');
-			new NoincludeToken(substr, config, accum);
-			return `\0${accum.length - 1}c\x7F`;
-		});
-	}
-	const ext = config.ext.join('|'),
-		includeRegex = includeOnly ? 'includeonly' : '(?:no|only)include',
-		noincludeRegex = includeOnly ? 'noinclude' : 'includeonly',
-		regex = new RegExp(
-			'<!--.*?(?:-->|$)|' // comment
-			+ `<${includeRegex}(?:\\s[^>]*?)?>|</${includeRegex}\\s*>|` // <includeonly>
-			+ `<(${ext})(\\s[^>]*?)?(?:/>|>(.*?)</(\\1\\s*)>)|` // 扩展标签
-			+ `<(${noincludeRegex})(\\s[^>]*?)?(?:/>|>(.*?)(?:</(\\5\\s*)>|$))`, // <noinclude>
-			'gisu',
-		);
-	return text.replace(
-		regex,
-		/** @type {function(...string): string} */
-		(substr, name, attr, inner, closing, include, includeAttr, includeInner, includeClosing) => {
-			const str = `\0${accum.length}${name ? 'e' : 'c'}\x7F`;
-			if (name) {
-				const ExtToken = require('../src/tagPair/ext');
-				new ExtToken(name, attr, inner, closing, config, accum);
-			} else if (substr.startsWith('<!--')) {
-				const CommentToken = require('../src/nowiki/comment');
-				const closed = substr.endsWith('-->');
-				new CommentToken(substr.slice(4, closed ? -3 : undefined), closed, config, accum);
-			} else if (include) {
-				const IncludeToken = require('../src/tagPair/include');
-				new IncludeToken(include, includeAttr, includeInner, includeClosing, config, accum);
-			} else {
-				const NoincludeToken = require('../src/nowiki/noinclude');
-				new NoincludeToken(substr, config, accum);
-			}
-			return str;
-		},
-	);
-};
-
-Parser.parsers.parseCommentAndExt = __filename;
-module.exports = parseCommentAndExt;

package/parser/converter.js

@@ -1,45 +0,0 @@
-'use strict';
-
-const Parser = require('..');
-
-/**
- * 解析语言变体转换
- * @param {string} wikitext wikitext
- * @param {accum} accum
- */
-const parseConverter = (wikitext, config = Parser.getConfig(), accum = []) => {
-	const ConverterToken = require('../src/converter');
-	const regex1 = /-\{/gu,
-		regex2 = /-\{|\}-/gu,
-		/** @type {RegExpExecArray[]} */ stack = [];
-	let regex = regex1,
-		mt = regex.exec(wikitext);
-	while (mt) {
-		const {0: syntax, index} = mt;
-		if (syntax === '}-') {
-			const top = stack.pop(),
-				{length} = accum,
-				str = wikitext.slice(top.index + 2, index),
-				i = str.indexOf('|'),
-				[flags, text] = i === -1 ? [[], str] : [str.slice(0, i).split(';'), str.slice(i + 1)],
-				temp = text.replace(/(&[#a-z\d]+);/iu, '$1\x01'),
-				variants = `(?:${config.variants.join('|')})`,
-				rules = temp.split(new RegExp(`;(?=\\s*(?:${variants}|[^;]*?=>\\s*${variants})\\s*:)`, 'u'))
-					.map(rule => rule.replaceAll('\x01', ';'));
-			new ConverterToken(flags, rules, config, accum);
-			wikitext = `${wikitext.slice(0, top.index)}\0${length}v\x7F${wikitext.slice(index + 2)}`;
-			if (stack.length === 0) {
-				regex = regex1;
-			}
-			regex.lastIndex = top.index + 3 + String(length).length;
-		} else {
-			stack.push(mt);
-			regex = regex2;
-		}
-		mt = regex.exec(wikitext);
-	}
-	return wikitext;
-};
-
-Parser.parsers.parseConverter = __filename;
-module.exports = parseConverter;

package/parser/externalLinks.js

@@ -1,31 +0,0 @@
-'use strict';
-
-const {extUrlChar} = require('../util/string'),
-	Parser = require('..');
-
-/**
- * 解析外部链接
- * @param {string} wikitext wikitext
- * @param {accum} accum
- */
-const parseExternalLinks = (wikitext, config = Parser.getConfig(), accum = []) => {
-	const ExtLinkToken = require('../src/extLink');
-	const regex = new RegExp(
-		`\\[((?:${config.protocol}|//)${extUrlChar})(\\p{Zs}*)([^\\]\x01-\x08\x0A-\x1F\uFFFD]*)\\]`,
-		'giu',
-	);
-	return wikitext.replace(regex, /** @type {function(...string): string} */ (_, 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}${text}`;
-		}
-		new ExtLinkToken(url, space, text, config, accum);
-		return `\0${length}w\x7F`;
-	});
-};
-
-Parser.parsers.parseExternalLinks = __filename;
-module.exports = parseExternalLinks;