wikiparser-node 1.9.2-b → 1.9.2

package/dist/lib/rect.js

@@ -0,0 +1,34 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.BoundingRect = void 0;
+const constants_1 = require("../util/constants");
+/** 节点位置 */
+class BoundingRect {
+    #pos;
+    token;
+    start;
+    /** 起点行 */
+    get top() {
+        this.#pos ??= this.getPosition();
+        return this.#pos.top;
+    }
+    /** 起点列 */
+    get left() {
+        this.#pos ??= this.getPosition();
+        return this.#pos.left;
+    }
+    /**
+     * @param token 节点
+     * @param start 起点
+     */
+    constructor(token, start) {
+        this.token = token;
+        this.start = start;
+    }
+    /** 计算位置 */
+    getPosition() {
+        return this.token.getRootNode().posFromIndex(this.start);
+    }
+}
+exports.BoundingRect = BoundingRect;
+constants_1.classes['BoundingRect'] = __filename;

package/dist/lib/text.d.ts

@@ -0,0 +1,54 @@
+import { AstNode } from './node';
+import type { LintError } from '../base';
+/** 文本节点 */
+export declare class AstText extends AstNode {
+    #private;
+    readonly type = "text";
+    readonly name: undefined;
+    readonly data: string;
+    /** 文本长度 */
+    get length(): number;
+    /** @param text 包含文本 */
+    constructor(text: string);
+    /** 可见部分 */
+    text(): string;
+    /**
+     * 替换字符串
+     * @param text 替换的字符串
+     */
+    replaceData(text: string): void;
+    /** 复制 */
+    cloneNode(): AstText;
+    /**
+     * 在后方添加字符串
+     * @param text 添加的字符串
+     */
+    appendData(text: string): void;
+    /**
+     * 删减字符串
+     * @param offset 起始位置
+     * @param count 删减字符数
+     */
+    deleteData(offset: number, count: number): void;
+    /**
+     * 插入字符串
+     * @param offset 插入位置
+     * @param text 待插入的字符串
+     */
+    insertData(offset: number, text: string): void;
+    /**
+     * 提取子串
+     * @param offset 起始位置
+     * @param count 字符数
+     */
+    substringData(offset: number, count: number): string;
+    /**
+     * 将文本子节点分裂为两部分
+     * @param offset 分裂位置
+     * @throws `RangeError` 错误的断开位置
+     * @throws `Error` 没有父节点
+     */
+    splitText(offset: number): AstText;
+    /** 转义 `=` */
+    escape(): void;
+}

package/dist/lib/text.js

@@ -0,0 +1,345 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.AstText = void 0;
+const constants_1 = require("../util/constants");
+const debug_1 = require("../util/debug");
+const string_1 = require("../util/string");
+const index_1 = require("../index");
+const node_1 = require("./node");
+/* eslint-disable @typescript-eslint/no-unused-expressions */
+/<\s*(?:\/\s*)?([a-z]\w*)|\{+|\}+|\[{2,}|\[(?![^[]*?\])|((?:^|\])[^[]*?)\]+|https?[:/]\/+/giu;
+/^https?:\/\/(?:\[[\da-f:.]+\]|[^[\]<>"\t\n\p{Zs}])[^[\]<>"\t\n\p{Zs}]*\.(?:gif|png|jpg|jpeg)$/iu;
+/* eslint-enable @typescript-eslint/no-unused-expressions */
+const source = String.raw `<\s*(?:/\s*)?([a-z]\w*)|\{+|\}+|\[{2,}|\[(?![^[]*?\])|((?:^|\])[^[]*?)\]+`, errorSyntax = new RegExp(String.raw `${source}|https?[:/]/+`, 'giu'), errorSyntaxUrl = new RegExp(source, 'giu'), extImage = new RegExp(String.raw `^https?://${string_1.extUrlCharFirst}${string_1.extUrlChar}\.(?:gif|png|jpg|jpeg)$`, 'iu'), regexes = {
+    '[': /[[\]]/u,
+    '{': /[{}]/u,
+    ']': /[[\]](?=[^[\]]*$)/u,
+    '}': /[{}](?=[^{}]*$)/u,
+}, ruleMap = {
+    '<': 'tag-like',
+    '[': 'lonely-bracket',
+    '{': 'lonely-bracket',
+    ']': 'lonely-bracket',
+    '}': 'lonely-bracket',
+    h: 'lonely-http',
+}, disallowedTags = [
+    'html',
+    'base',
+    'head',
+    'style',
+    'title',
+    'body',
+    'menu',
+    'a',
+    'area',
+    'audio',
+    'img',
+    'map',
+    'track',
+    'video',
+    'embed',
+    'iframe',
+    'object',
+    'picture',
+    'source',
+    'canvas',
+    'script',
+    'col',
+    'colgroup',
+    'tbody',
+    'tfoot',
+    'thead',
+    'button',
+    'datalist',
+    'fieldset',
+    'form',
+    'input',
+    'label',
+    'legend',
+    'meter',
+    'optgroup',
+    'option',
+    'output',
+    'progress',
+    'select',
+    'textarea',
+    'details',
+    'dialog',
+    'slot',
+    'template',
+    'dir',
+    'frame',
+    'frameset',
+    'marquee',
+    'param',
+    'xmp',
+];
+/** 文本节点 */
+class AstText extends node_1.AstNode {
+    type = 'text';
+    data = '';
+    /* NOT FOR BROWSER */
+    /** 文本长度 */
+    get length() {
+        return this.data.length;
+    }
+    /* NOT FOR BROWSER END */
+    /** @param text 包含文本 */
+    constructor(text) {
+        super();
+        Object.defineProperties(this, {
+            childNodes: { enumerable: false, configurable: false },
+            type: { enumerable: false, writable: false },
+            data: {
+                value: text,
+                /* NOT FOR BROWSER */
+                writable: false,
+            },
+        });
+    }
+    /** @private */
+    toString() {
+        return this.data;
+    }
+    /** 可见部分 */
+    text() {
+        return this.data;
+    }
+    /** @private */
+    lint(start = this.getAbsoluteIndex(), errorRegex) {
+        const { data, parentNode, nextSibling, previousSibling } = this;
+        if (!parentNode) {
+            throw new Error('An isolated text node cannot be linted!');
+        }
+        const { type, name, parentNode: grandparent } = parentNode;
+        let isHtmlAttrVal = false;
+        if (type === 'attr-value') {
+            const { type: grandType, name: grandName, tag } = grandparent;
+            if (grandType !== 'ext-attr') {
+                isHtmlAttrVal = true;
+            }
+            else if (tag === 'choose' && (grandName === 'before' || grandName === 'after')) {
+                return [];
+            }
+        }
+        errorRegex ??= type === 'free-ext-link'
+            || type === 'ext-link-url'
+            || type === 'image-parameter' && name === 'link'
+            || isHtmlAttrVal
+            ? errorSyntaxUrl
+            : errorSyntax;
+        if (data.search(errorRegex) === -1) {
+            return [];
+        }
+        errorRegex.lastIndex = 0;
+        const errors = [], nextType = nextSibling?.type, nextName = nextSibling?.name, previousType = previousSibling?.type, root = this.getRootNode(), { ext, html } = root.getAttribute('config'), { top, left } = root.posFromIndex(start), tags = new Set(['onlyinclude', 'noinclude', 'includeonly', ext, html, disallowedTags].flat(2));
+        for (let mt = errorRegex.exec(data); mt; mt = errorRegex.exec(data)) {
+            const [, tag, prefix] = mt;
+            let { 0: error, index } = mt;
+            if (prefix && prefix !== ']') {
+                const { length } = prefix;
+                index += length;
+                error = error.slice(length);
+            }
+            const { 0: char, length } = error;
+            if (char === '<' && !tags.has(tag.toLowerCase())
+                || char === '['
+                    && type === 'ext-link-text'
+                    && (/&(?:rbrack|#93|#x5[Dd];);/u.test(data.slice(index + 1))
+                        || nextType === 'ext'
+                            && nextName === 'nowiki'
+                            && nextSibling.innerText?.includes(']'))) {
+                continue;
+            }
+            else if (char === ']' && (index || length > 1)) {
+                errorRegex.lastIndex--;
+            }
+            else if (char === 'h' && index === 0 && type === 'ext-link-text' && extImage.test(data)) {
+                continue;
+            }
+            const startIndex = start + index, endIndex = startIndex + length, rootStr = root.toString(), nextChar = rootStr[endIndex], previousChar = rootStr[startIndex - 1], severity = length > 1 && !(char === '<' && !/[\s/>]/u.test(nextChar ?? '')
+                || isHtmlAttrVal && (char === '[' || char === ']'))
+                || char === '{' && (nextChar === char || previousChar === '-')
+                || char === '}' && (previousChar === char || nextChar === '-')
+                || char === '[' && (nextChar === char
+                    || type === 'ext-link-text'
+                    || nextType === 'free-ext-link' && !data.slice(index + 1).trim())
+                || char === ']' && (previousChar === char
+                    || previousType === 'free-ext-link' && !data.slice(0, index).includes(']'))
+                ? 'error'
+                : 'warning';
+            const leftBracket = char === '{' || char === '[', rightBracket = char === ']' || char === '}';
+            if (severity === 'warning' && (leftBracket || rightBracket)) {
+                const regex = regexes[char], remains = leftBracket ? data.slice(index + 1) : data.slice(0, index);
+                if (char === '{' && regex.exec(remains)?.[0] === '}'
+                    || char === '}' && regex.exec(remains)?.[0] === '{') {
+                    continue;
+                }
+                else if (!remains.includes(char)) {
+                    const sibling = leftBracket ? 'nextSibling' : 'previousSibling';
+                    let cur = this[sibling];
+                    while (cur && (cur.type !== 'text' || !regex.test(cur.data))) {
+                        cur = cur[sibling];
+                    }
+                    if (cur && regex.exec(cur.data)[0] !== char) {
+                        continue;
+                    }
+                }
+            }
+            const lines = data.slice(0, index).split('\n'), startLine = lines.length + top - 1, line = lines[lines.length - 1], startCol = lines.length === 1 ? left + line.length : line.length, e = {
+                rule: ruleMap[char],
+                message: index_1.default.msg('lonely "$1"', char === 'h' ? error : char),
+                severity,
+                startIndex,
+                endIndex,
+                startLine,
+                endLine: startLine,
+                startCol,
+                endCol: startCol + length,
+            };
+            if (char === '<') {
+                e.suggestions = [
+                    {
+                        desc: 'escape',
+                        range: [startIndex, startIndex + 1],
+                        text: '&lt;',
+                    },
+                ];
+            }
+            else if (char === 'h'
+                && !(type === 'ext-link-text' || type === 'link-text')
+                && /[\p{L}\d_]/u.test(previousChar || '')) {
+                e.suggestions = [
+                    {
+                        desc: 'whitespace',
+                        range: [startIndex, startIndex],
+                        text: ' ',
+                    },
+                ];
+            }
+            else if (char === '[' && type === 'ext-link-text') {
+                const i = parentNode.getAbsoluteIndex() + parentNode.toString().length;
+                e.suggestions = [
+                    {
+                        desc: 'escape',
+                        range: [i, i + 1],
+                        text: '&#93;',
+                    },
+                ];
+            }
+            else if (char === ']' && previousType === 'free-ext-link' && severity === 'error') {
+                const i = start - previousSibling.toString().length;
+                e.fix = {
+                    range: [i, i],
+                    text: '[',
+                };
+            }
+            errors.push(e);
+        }
+        return errors;
+    }
+    /**
+     * 修改内容
+     * @param text 新内容
+     */
+    #setData(text) {
+        /* NOT FOR BROWSER */
+        const { data } = this, e = new Event('text', { bubbles: true });
+        /* NOT FOR BROWSER END */
+        this.setAttribute('data', text);
+        /* NOT FOR BROWSER */
+        if (data !== text) {
+            this.dispatchEvent(e, { type: 'text', oldText: data });
+        }
+    }
+    /**
+     * 替换字符串
+     * @param text 替换的字符串
+     */
+    replaceData(text) {
+        this.#setData(text);
+    }
+    /** @private */
+    print() {
+        return (0, string_1.escape)(this.data);
+    }
+    /* NOT FOR BROWSER */
+    /** 复制 */
+    cloneNode() {
+        return new AstText(this.data);
+    }
+    /**
+     * 在后方添加字符串
+     * @param text 添加的字符串
+     */
+    appendData(text) {
+        this.#setData(this.data + text);
+    }
+    /**
+     * 删减字符串
+     * @param offset 起始位置
+     * @param count 删减字符数
+     */
+    deleteData(offset, count) {
+        this.#setData(this.data.slice(0, offset) + (offset < 0 && offset + count >= 0 ? '' : this.data.slice(offset + count)));
+    }
+    /**
+     * 插入字符串
+     * @param offset 插入位置
+     * @param text 待插入的字符串
+     */
+    insertData(offset, text) {
+        this.#setData(this.data.slice(0, offset) + text + this.data.slice(offset));
+    }
+    /**
+     * 提取子串
+     * @param offset 起始位置
+     * @param count 字符数
+     */
+    substringData(offset, count) {
+        return this.data.substr(offset, count);
+    }
+    /**
+     * 将文本子节点分裂为两部分
+     * @param offset 分裂位置
+     * @throws `RangeError` 错误的断开位置
+     * @throws `Error` 没有父节点
+     */
+    splitText(offset) {
+        if (offset > this.length || offset < -this.length) {
+            throw new RangeError(`Wrong offset to split: ${offset}`);
+        }
+        const { parentNode, data } = this;
+        if (!parentNode) {
+            throw new Error('The text node to be split has no parent node!');
+        }
+        const newText = new AstText(data.slice(offset));
+        (0, debug_1.setChildNodes)(parentNode, parentNode.childNodes.indexOf(this) + 1, 0, [newText]);
+        this.setAttribute('data', data.slice(0, offset));
+        return newText;
+    }
+    /** @private */
+    getRelativeIndex(j) {
+        if (j === undefined) {
+            return super.getRelativeIndex();
+        }
+        else if (j < 0 || j > this.length) {
+            throw new RangeError('Exceeding the text length range!');
+        }
+        return j;
+    }
+    /** 转义 `=` */
+    escape() {
+        const { TranscludeToken } = require('../src/transclude');
+        for (let i = this.data.lastIndexOf('='); i >= 0; i = this.data.lastIndexOf('=', i - 1)) {
+            if (i < this.length - 1) {
+                this.splitText(i + 1);
+            }
+            // @ts-expect-error abstract class
+            this.after(new TranscludeToken('=', [], this.parentNode.getAttribute('config')));
+            this.#setData(this.data.slice(0, i));
+        }
+    }
+}
+exports.AstText = AstText;
+constants_1.classes['AstText'] = __filename;

package/dist/lib/title.d.ts

@@ -0,0 +1,40 @@
+import type { Config } from '../base';
+/** MediaWiki页面标题对象 */
+export declare class Title {
+    #private;
+    ns: number;
+    fragment: string | undefined;
+    interwiki: string;
+    readonly valid: boolean;
+    /** 不含命名空间的标题主体部分 */
+    get main(): string;
+    set main(title: string);
+    /** 命名空间前缀 */
+    get prefix(): string;
+    /** 完整标题 */
+    get title(): string;
+    /** 扩展名 */
+    get extension(): string | undefined;
+    set extension(extension: string | undefined);
+    /**
+     * @see MediaWikiTitleCodec::splitTitleString
+     *
+     * @param title 标题（含或不含命名空间前缀）
+     * @param defaultNs 命名空间
+     * @param decode 是否需要解码
+     * @param selfLink 是否允许selfLink
+     */
+    constructor(title: string, defaultNs: number, config: Config, decode: boolean, selfLink: boolean);
+    /** 执行单向转换 */
+    autoConvert(): void;
+    /** 转换为主页面 */
+    toSubjectPage(): void;
+    /** 转换为讨论页面 */
+    toTalkPage(): void;
+    /** 是否是讨论页 */
+    isTalkPage(): boolean;
+    /** 转换为上一级页面 */
+    toBasePage(): void;
+    /** 转换为根页面 */
+    toRootPage(): void;
+}

package/dist/lib/title.js

@@ -0,0 +1,197 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.Title = void 0;
+const string_1 = require("../util/string");
+const constants_1 = require("../util/constants");
+const index_1 = require("../index");
+/**
+ * PHP的`rawurldecode`函数的JavaScript实现
+ * @param str 要解码的字符串
+ */
+const rawurldecode = (str) => decodeURIComponent(str.replace(/%(?![\da-f]{2})/giu, '%25'));
+/** MediaWiki页面标题对象 */
+class Title {
+    #main;
+    #namespaces;
+    ns;
+    fragment;
+    interwiki = '';
+    valid;
+    /** @private */
+    encoded = false;
+    /* NOT FOR BROWSER */
+    #fragment;
+    /** @private */
+    conversionTable = new Map();
+    /** @private */
+    redirects = new Map();
+    /* NOT FOR BROWSER END */
+    /** 不含命名空间的标题主体部分 */
+    get main() {
+        return this.#main;
+    }
+    set main(title) {
+        title = title.replace(/_/gu, ' ').trim();
+        this.#main = title && title[0].toUpperCase() + title.slice(1);
+    }
+    /** 命名空间前缀 */
+    get prefix() {
+        const namespace = this.#namespaces[this.ns];
+        return namespace + (namespace && ':');
+    }
+    /** 完整标题 */
+    get title() {
+        const prefix = this.interwiki + (this.interwiki && ':') + this.prefix;
+        let title = (prefix + this.main).replace(/ /gu, '_');
+        /* NOT FOR BROWSER */
+        let redirected = this.#redirect(title);
+        if (redirected) {
+            return redirected;
+        }
+        this.autoConvert();
+        title = (prefix + this.main).replace(/ /gu, '_');
+        redirected = this.#redirect(title);
+        if (redirected) {
+            return redirected;
+        }
+        /* NOT FOR BROWSER END */
+        return title;
+    }
+    /** 扩展名 */
+    get extension() {
+        const { main } = this, i = main.lastIndexOf('.');
+        return i === -1 ? undefined : main.slice(i + 1).toLowerCase();
+    }
+    /* NOT FOR BROWSER */
+    set extension(extension) {
+        extension ||= '';
+        const { main } = this, i = main.lastIndexOf('.');
+        this.main = (i === -1 ? main : main.slice(0, i)) + (extension && '.') + extension;
+    }
+    /* NOT FOR BROWSER END */
+    /**
+     * @see MediaWikiTitleCodec::splitTitleString
+     *
+     * @param title 标题（含或不含命名空间前缀）
+     * @param defaultNs 命名空间
+     * @param decode 是否需要解码
+     * @param selfLink 是否允许selfLink
+     */
+    constructor(title, defaultNs, config, decode, selfLink) {
+        const subpage = title.trim().startsWith('../');
+        title = (0, string_1.decodeHtml)(title);
+        if (decode && title.includes('%')) {
+            try {
+                const encoded = /%(?!21|3[ce]|5[bd]|7[b-d])[\da-f]{2}/iu.test(title);
+                title = rawurldecode(title);
+                this.encoded = encoded;
+            }
+            catch { }
+        }
+        title = title.replace(/_/gu, ' ').trim();
+        if (subpage) {
+            this.ns = 0;
+        }
+        else {
+            let ns = defaultNs;
+            if (title.startsWith(':')) {
+                ns = 0;
+                title = title.slice(1).trim();
+            }
+            /* NOT FOR BROWSER */
+            const iw = defaultNs ? null : index_1.default.isInterwiki(title, config);
+            if (iw) {
+                this.interwiki = iw[1].toLowerCase();
+                title = title.slice(iw.indices[0][1]);
+            }
+            /* NOT FOR BROWSER END */
+            const m = title.split(':');
+            if (m.length > 1) {
+                const id = config.nsid[m[0].trim().toLowerCase()];
+                if (id) {
+                    ns = id;
+                    title = m.slice(1).join(':').trim();
+                }
+            }
+            this.ns = ns;
+        }
+        const i = title.indexOf('#');
+        if (i !== -1) {
+            let fragment = title.slice(i + 1).trimEnd();
+            if (fragment.includes('%')) {
+                try {
+                    fragment = rawurldecode(fragment);
+                }
+                catch { }
+            }
+            this.fragment = fragment;
+            title = title.slice(0, i).trim();
+        }
+        this.valid = Boolean(title || this.interwiki || selfLink && this.ns === 0 && this.fragment !== undefined)
+            && !/^:|\0\d+[eh!+-]\x7F|[<>[\]{}|\n]|%[\da-f]{2}|(?:^|\/)\.{1,2}(?:$|\/)/iu.test(subpage ? /^(?:\.\.\/)+(.*)/u.exec(title)[1] : title);
+        this.main = title;
+        Object.defineProperties(this, {
+            encoded: { enumerable: false, writable: false },
+            /* NOT FOR BROWSER */
+            valid: { writable: false },
+            conversionTable: { enumerable: false },
+            redirects: { enumerable: false },
+        });
+        this.#namespaces = config.namespaces;
+    }
+    /** @private */
+    toString() {
+        return `${this.title}${this.fragment === undefined
+            && this.#fragment === undefined
+            ? ''
+            : `#${this.fragment
+                ?? this.#fragment}`}`;
+    }
+    /* NOT FOR BROWSER */
+    /**
+     * 处理重定向
+     * @param title 原标题
+     */
+    #redirect(title) {
+        const redirected = this.redirects.get(title);
+        if (redirected) {
+            [title, this.#fragment] = redirected.split('#', 2);
+            return title;
+        }
+        return '';
+    }
+    /** 执行单向转换 */
+    autoConvert() {
+        const { conversionTable } = this;
+        if (conversionTable.size > 0) {
+            const regex = new RegExp([...conversionTable.keys()].sort().reverse().map(string_1.escapeRegExp).join('|'), 'gu');
+            this.main = this.main.replace(regex, p => conversionTable.get(p));
+        }
+    }
+    /** 转换为主页面 */
+    toSubjectPage() {
+        if (this.isTalkPage()) {
+            this.ns--;
+        }
+    }
+    /** 转换为讨论页面 */
+    toTalkPage() {
+        if (!this.isTalkPage()) {
+            this.ns++;
+        }
+    }
+    /** 是否是讨论页 */
+    isTalkPage() {
+        return this.ns % 2 === 1;
+    }
+    /** 转换为上一级页面 */
+    toBasePage() {
+        this.main = this.main.replace(/\/[^/]*$/u, '');
+    }
+    /** 转换为根页面 */
+    toRootPage() {
+        this.main = this.main.replace(/\/.*/u, '');
+    }
+}
+exports.Title = Title;
+constants_1.classes['Title'] = __filename;