lint-wiki-dumps 0.0.0

package/README.md

@@ -0,0 +1,59 @@
+[![npm version](https://badge.fury.io/js/lint-wiki-dumps.svg)](https://www.npmjs.com/package/lint-wiki-dumps)
+[![CodeQL](https://github.com/bhsd-harry/lint-wiki-dumps/actions/workflows/codeql.yml/badge.svg)](https://github.com/bhsd-harry/lint-wiki-dumps/actions/workflows/codeql.yml)
+[![Codacy Badge](https://app.codacy.com/project/badge/Grade/12aacc9d0f3e4629ae96114f7c40cf31)](https://app.codacy.com/gh/bhsd-harry/lint-wiki-dumps/dashboard)
+
+# Lint-Wiki-Dumps
+
+This is a tool for linting Wikitext articles from Wikipedia with the help of [WikiLint](https://www.npmjs.com/package/wikilint). It will download the latest dump of a specified Wikipedia language edition and then lint the articles in the dump.
+
+## Installation
+
+To run this tool, you need to have [curl](https://curl.se/) installed on your system. You can install this tool via npm:
+
+```sh
+npm i lint-wiki-dumps
+```
+
+You can also install its optional dependency [vscode-css-languageservice](https://npmjs.com/package/vscode-css-languageservice) to lint inline CSS in Wikitext:
+
+```sh
+npm i vscode-css-languageservice
+```
+
+## Usage
+
+```sh
+npx lint-wiki-dumps <language> <path to download directory>
+# For example:
+npx lint-wiki-dumps zh-yue ~/Downloads/dumps
+```
+
+or execute the Bash script `scan.sh` directly:
+
+```sh
+bash scan.sh <language> <path to download>
+# For example:
+bash scan.sh zh-yue ~/Downloads/dumps
+```
+
+## Advanced Usage
+
+If you have already downloaded the dump, you can scan the dump directly and generate JSON reports:
+
+```sh
+node parser.js <language> <path to dump>
+# For example:
+node parser.js zh-yue ~/Downloads/dumps/zh-yuewiki-lastest-pages-articles.xml.bz2
+```
+
+To generate HTML reports, you can use the following command:
+
+```sh
+node report.js <language>
+# For example:
+node report.js zh-yue
+```
+
+## Report
+
+The tool will generate reports in two formats: JSON and HTML. The JSON report will be saved in the `results` folder, while the HTML report will be available at `reports/index.html`.

package/package.json

@@ -0,0 +1,71 @@
+{
+	"name": "lint-wiki-dumps",
+	"version": "0.0.0",
+	"description": "Lint Wikipedia dumps",
+	"keywords": [
+		"lint",
+		"wikipedia"
+	],
+	"homepage": "https://github.com/bhsd-harry/lint-wiki-dumps#readme",
+	"bugs": {
+		"url": "https://github.com/bhsd-harry/lint-wiki-dumps/issues"
+	},
+	"license": "GPL-3.0",
+	"author": "Bhsd",
+	"files": [
+		"scan.sh",
+		"*.js",
+		"reports/*.html",
+		"reports/dist/",
+		"reports/*.css"
+	],
+	"bin": {
+		"lint-wiki-dumps": "scan.sh"
+	},
+	"repository": {
+		"type": "git",
+		"url": "git+https://github.com/bhsd-harry/lint-wiki-dumps.git"
+	},
+	"scripts": {
+		"prepublishOnly": "npm run build",
+		"build": "tsc && mv dist/* . && tsc --project reports/tsconfig.json",
+		"lint": "tsc --noEmit && tsc --project reports/tsconfig.json --noEmit && eslint --cache ."
+	},
+	"dependencies": {
+		"@bhsd/common": "^0.9.0",
+		"chalk": "^4.1.2",
+		"unbzip2-stream": "^1.4.3",
+		"wikilint": "^2.18.3",
+		"xml-stream": "^0.4.5"
+	},
+	"optionalDependencies": {
+		"vscode-css-languageservice": "^6.3.2"
+	},
+	"devDependencies": {
+		"@stylistic/eslint-plugin": "^3.1.0",
+		"@stylistic/stylelint-plugin": "^3.1.2",
+		"@types/mocha": "^10.0.10",
+		"@types/node": "^22.13.1",
+		"@types/unbzip2-stream": "^1.4.3",
+		"@typescript-eslint/eslint-plugin": "^8.23.0",
+		"@typescript-eslint/parser": "^8.23.0",
+		"esbuild": "^0.25.0",
+		"eslint": "^8.57.1",
+		"eslint-plugin-es-x": "^8.4.1",
+		"eslint-plugin-eslint-comments": "^3.2.0",
+		"eslint-plugin-jsdoc": "^50.6.3",
+		"eslint-plugin-json-es": "^1.6.0",
+		"eslint-plugin-markdown": "4.0.1",
+		"eslint-plugin-n": "^17.15.1",
+		"eslint-plugin-promise": "^7.2.1",
+		"eslint-plugin-regexp": "^2.7.0",
+		"eslint-plugin-unicorn": "^56.0.1",
+		"http-server": "^14.1.1",
+		"mocha": "^11.1.0",
+		"stylelint": "^16.14.1",
+		"typescript": "^5.7.3"
+	},
+	"engines": {
+		"node": ">=18.17.0"
+	}
+}

package/parser.js

@@ -0,0 +1,100 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+const fs_1 = __importDefault(require("fs"));
+const path_1 = __importDefault(require("path"));
+const os_1 = __importDefault(require("os"));
+const perf_hooks_1 = require("perf_hooks");
+const chalk_1 = __importDefault(require("chalk"));
+const unbzip2_stream_1 = __importDefault(require("unbzip2-stream"));
+const xml_stream_1 = __importDefault(require("xml-stream"));
+const wikilint_1 = __importDefault(require("wikilint"));
+const common_1 = require("@bhsd/common");
+const n = Number(process.argv[4]) || Infinity, [, , site, file, , restart] = process.argv;
+wikilint_1.default.config = `${site}wiki`;
+if (!fs_1.default.existsSync('results')) {
+    fs_1.default.mkdirSync('results');
+}
+const stream = new xml_stream_1.default(fs_1.default.createReadStream(file.replace(/^~/u, os_1.default.homedir())).pipe((0, unbzip2_stream_1.default)())), output = path_1.default.join('results', `${site}.json`);
+let old;
+try {
+    old = require(`./${output}`); // eslint-disable-line @typescript-eslint/no-require-imports
+}
+catch { }
+const time = old?.['#timestamp'], last = time && new Date(time), results = fs_1.default.createWriteStream(output, { flags: restart ? 'a' : 'w' }), ignore = new Set(['no-arg', 'url-encoding', 'h1', 'var-anchor']);
+let i = 0, latest = last, failed = 0, comma = restart ? ',' : '', stopping = false, restarted = !restart, worst;
+stream.preserve('text', true);
+if (!restart) {
+    results.write('{');
+}
+results.on('close', () => {
+    process.exit(); // eslint-disable-line n/no-process-exit
+});
+const stop = () => {
+    stopping = true;
+    console.timeEnd('parse');
+    console.log(chalk_1.default.green(`Parsed ${i} pages`));
+    if (failed) {
+        console.error(chalk_1.default.red(`${failed} pages failed to parse`));
+    }
+    if (worst) {
+        console.info(chalk_1.default.yellow(`Worst page: ${worst.title} (${worst.duration.toFixed(3)} ms)`));
+    }
+    results.write(`${comma}\n"#timestamp": ${JSON.stringify(latest)}\n}`);
+    results.close();
+};
+const newEntry = (title, errors) => {
+    results.write(`${comma}\n${JSON.stringify(title)}: ${JSON.stringify(errors, null, '\t')}`);
+    comma ||= ',';
+};
+console.time('parse');
+stream.on('endElement: page', ({ title, ns, revision: { model, timestamp, text: { $text } } }) => {
+    if (i === n) {
+        if (!stopping) {
+            stop();
+        }
+    }
+    else if (restarted && model === 'wikitext' && $text && ns === '0') {
+        (0, common_1.refreshStdout)(`${i++} ${title}`);
+        const date = new Date(timestamp);
+        if (last && date <= last) {
+            const previous = old[title];
+            if (previous) {
+                newEntry(title, previous);
+            }
+        }
+        else {
+            latest = !latest || date > latest ? date : latest;
+            try {
+                const start = perf_hooks_1.performance.now(), errors = wikilint_1.default.parse($text).lint()
+                    .filter(({ severity, rule }) => severity === 'error' && !ignore.has(rule)), duration = perf_hooks_1.performance.now() - start;
+                if (errors.length > 0) {
+                    newEntry(title, errors.map(({ severity, suggestions, fix, ...e }) => ({
+                        ...e,
+                        ...suggestions && {
+                            suggestions: suggestions.map(action => ({
+                                ...action,
+                                original: $text.slice(...action.range),
+                            })),
+                        },
+                        ...fix && { fix: { ...fix, original: $text.slice(...fix.range) } },
+                        excerpt: $text.slice(e.startIndex, e.endIndex),
+                    })));
+                }
+                if (!worst || duration > worst.duration) {
+                    worst = { title, duration };
+                }
+            }
+            catch (e) {
+                console.error(chalk_1.default.red(`Error parsing ${title}`), e);
+                failed++;
+            }
+        }
+    }
+    else if (title === restart) {
+        restarted = true;
+    }
+});
+stream.on('end', stop);

package/report.js

@@ -0,0 +1,71 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+const fs_1 = __importDefault(require("fs"));
+const path_1 = __importDefault(require("path"));
+const crypto_1 = require("crypto");
+const chalk_1 = __importDefault(require("chalk"));
+const [, , lang] = process.argv;
+const mkdir = (dir) => {
+    if (!fs_1.default.existsSync(dir)) {
+        fs_1.default.mkdirSync(dir);
+    }
+};
+const dataDir = path_1.default.join('reports', 'data');
+mkdir(dataDir);
+const writeJS = (data, file) => {
+    fs_1.default.writeFileSync(path_1.default.join(dataDir, `${file}.js`), `window.data=${JSON.stringify(data)}`);
+};
+const dir = fs_1.default.readdirSync('results'), summary = [], MAX = 100;
+for (const file of dir) {
+    try {
+        // eslint-disable-next-line @typescript-eslint/no-require-imports
+        const data = require(`./results/${file}`);
+        const site = file.slice(0, -5);
+        summary.push(site);
+        delete data['#timestamp'];
+        if (!lang || lang === site) {
+            const siteDir = path_1.default.join(dataDir, site);
+            mkdir(siteDir);
+            // wiki
+            const values = Object.values(data), rules = [...new Set(values.flat().map(({ rule }) => rule))].sort((a, b) => a.localeCompare(b)), wiki = [];
+            for (const rule of rules) {
+                wiki.push([rule, values.filter(errors => errors.some(({ rule: r }) => r === rule)).length]);
+                // rule
+                const articles = Object.entries(data).filter(([, errors]) => errors.some(({ rule: r }) => r === rule))
+                    .sort(([a], [b]) => a.localeCompare(b))
+                    .map(([page, errors]) => {
+                    const { startLine, startCol, message, excerpt } = errors.find(({ rule: r }) => r === rule);
+                    return [page, startLine + 1, startCol + 1, message, excerpt.slice(0, MAX * 0.8)];
+                }), batches = Math.ceil(articles.length / 200);
+                for (let i = 0; i < batches; i++) {
+                    writeJS({
+                        articles: articles.slice(i * 200, (i + 1) * 200),
+                        batches,
+                    }, path_1.default.join(site, `${rule}-${i}`));
+                }
+            }
+            writeJS(wiki, path_1.default.join(site, 'index'));
+            // article
+            const articlesDir = path_1.default.join(siteDir, 'pages');
+            mkdir(articlesDir);
+            for (const [page, errors] of Object.entries(data)) {
+                const hash = (0, crypto_1.createHash)('sha256').update(page).digest('hex')
+                    .slice(0, 8), info = errors.map(({ startLine, startCol, rule, message, excerpt, }) => [
+                    rule,
+                    startLine + 1,
+                    startCol + 1,
+                    message,
+                    excerpt.slice(0, MAX),
+                ]);
+                writeJS(info, path_1.default.join(site, 'pages', hash));
+            }
+        }
+    }
+    catch {
+        console.error(chalk_1.default.red(`Failed to read ${file}`));
+    }
+}
+writeJS(summary, 'index');

package/reports/article.html

@@ -0,0 +1,47 @@
+<!DOCTYPE html>
+<html dir="ltr" lang="en-US">
+	<head>
+		<title>Diagnostic Report for Wikipedia</title>
+		<meta charset="utf-8">
+		<meta name="viewport" content="initial-scale=1.0, user-scalable=yes, minimum-scale=0.25, maximum-scale=5.0, width=device-width">
+		<link rel="stylesheet" href="reports.css">
+		<style>td:nth-child(-n+3){text-align:center}</style>
+		<script defer="" src="dist/article.js"></script>
+	</head>
+	<body>
+		<main>
+			<article>
+				<div id="container">
+					<div>
+						<a href="./index.html">Homepage</a>
+					</div>
+					<div>
+						<a id="wiki" href="./wiki.html">Wikipedia</a>
+					</div>
+				</div>
+				<h2>
+					Diagnostic Report for 
+					<a id="article">Article</a>
+				</h2>
+				<table style="table-layout:fixed;width:100%">
+					<colgroup>
+						<col span="1">
+						<col span="1" style="width:calc(1.6em + 7ch)">
+						<col span="1" style="width:calc(1.6em + 7ch)">
+						<col span="1" style="width:20%">
+						<col span="1" style="width:50%">
+					</colgroup>
+					<tbody>
+						<tr>
+							<th>Description</th>
+							<th>Line</th>
+							<th>Column</th>
+							<th>Detail</th>
+							<th>Notice</th>
+						</tr>
+					</tbody>
+				</table>
+			</article>
+		</main>
+	</body>
+</html>

package/reports/dist/article.js

@@ -0,0 +1,30 @@
+"use strict";
+(async () => {
+    const search = new URLSearchParams(location.search), page = search.get('page'), lang = search.get('lang'), buffer = await crypto.subtle.digest('SHA-256', new TextEncoder().encode(page)), hash = [...new Uint8Array(buffer)].slice(0, 4)
+        .map(b => b.toString(16).padStart(2, '0'))
+        .join(''), title = document.querySelector('title'), h2 = document.getElementById('article'), wiki = document.getElementById('wiki'), tbody = document.querySelector('tbody'), script = document.createElement('script');
+    title.textContent = title.textContent.replace('Wikipedia', page);
+    h2.textContent = page;
+    h2.href = `https://${lang}.wikipedia.org/wiki/${encodeURIComponent(page)}?redirect=no`;
+    wiki.textContent = `${lang}wiki`;
+    wiki.href += `?lang=${lang}`;
+    script.src = `./data/${lang}/pages/${hash}.js`;
+    script.addEventListener('load', () => {
+        for (const entry of data) {
+            const [rule, startLine, startCol, message, excerpt] = entry, tr = document.createElement('tr'), description = document.createElement('td'), line = document.createElement('td'), column = document.createElement('td'), detail = document.createElement('td'), notice = document.createElement('td'), descriptionLink = document.createElement('a');
+            descriptionLink.textContent = rule;
+            descriptionLink.href = `./rule.html?lang=${lang}&rule=${rule}`;
+            description.className = 'excerpt';
+            description.append(descriptionLink);
+            line.textContent = String(startLine);
+            column.textContent = String(startCol);
+            detail.textContent = message;
+            detail.className = 'excerpt';
+            notice.textContent = excerpt;
+            notice.className = 'excerpt mono';
+            tr.append(description, line, column, detail, notice);
+            tbody.append(tr);
+        }
+    });
+    document.head.append(script);
+})();

package/reports/dist/index.js

@@ -0,0 +1,15 @@
+"use strict";
+(() => {
+    const container = document.getElementById('container'), script = document.createElement('script');
+    script.src = './data/index.js';
+    script.addEventListener('load', () => {
+        container.append(...window.data.map(lang => {
+            const div = document.createElement('div'), a = document.createElement('a');
+            a.href = `./wiki.html?lang=${lang}`;
+            a.innerText = `${lang}.wikipedia.org`;
+            div.append(a);
+            return div;
+        }));
+    });
+    document.head.append(script);
+})();

package/reports/dist/rule.js

@@ -0,0 +1,48 @@
+"use strict";
+(() => {
+    const search = new URLSearchParams(location.search), lang = search.get('lang'), rule = search.get('rule'), batch = Math.floor(Number(search.get('start') || 0) / 200), endStr = String((batch + 1) * 200), prev = document.getElementById('prev'), next = document.getElementById('next'), start = document.getElementById('start'), end = document.getElementById('end'), title = document.querySelector('title'), h2 = document.querySelector('h2'), wiki = document.getElementById('wiki'), tbody = document.querySelector('tbody'), script = document.createElement('script');
+    h2.textContent = h2.textContent.replace('Wikipedia', `${lang}.wikipedia.org: ${rule}`);
+    title.textContent = title.textContent.replace('Wikipedia', `${lang}.wikipedia.org`);
+    wiki.textContent = `${lang}wiki`;
+    wiki.href += `?lang=${lang}`;
+    if (batch === 0) {
+        prev.removeAttribute('href');
+    }
+    else {
+        start.textContent = String(batch * 200 + 1);
+        end.textContent = endStr;
+        search.set('start', String((batch - 1) * 200));
+        prev.href = `${location.pathname}?${search}`;
+    }
+    search.set('start', endStr);
+    next.href = `${location.pathname}?${search}`;
+    script.src = `./data/${lang}/${rule}-${batch}.js`;
+    script.addEventListener('load', () => {
+        if (data.batches === batch + 1) {
+            next.removeAttribute('href');
+            end.textContent = String(batch * 200 + data.articles.length);
+        }
+        for (const [page, startLine, startCol, message, excerpt] of data.articles) {
+            const tr = document.createElement('tr'), article = document.createElement('td'), edit = document.createElement('td'), line = document.createElement('td'), column = document.createElement('td'), detail = document.createElement('td'), notice = document.createElement('td'), more = document.createElement('td'), articleLink = document.createElement('a'), editLink = document.createElement('a'), moreLink = document.createElement('a');
+            articleLink.textContent = page;
+            articleLink.href = `https://${lang}.wikipedia.org/wiki/${encodeURIComponent(page)}?redirect=no`;
+            article.className = 'excerpt';
+            article.append(articleLink);
+            editLink.textContent = 'edit';
+            editLink.href = `https://${lang}.wikipedia.org/wiki/${encodeURIComponent(page)}?action=edit`;
+            edit.append(editLink);
+            line.textContent = String(startLine);
+            column.textContent = String(startCol);
+            detail.textContent = message;
+            detail.className = 'excerpt';
+            notice.textContent = excerpt;
+            notice.className = 'excerpt mono';
+            moreLink.textContent = 'more';
+            moreLink.href = `./article.html?lang=${lang}&page=${encodeURIComponent(page)}`;
+            more.append(moreLink);
+            tr.append(article, edit, line, column, detail, notice, more);
+            tbody.append(tr);
+        }
+    });
+    document.head.append(script);
+})();

package/reports/dist/wiki.js

@@ -0,0 +1,19 @@
+"use strict";
+(() => {
+    const lang = new URLSearchParams(location.search).get('lang'), script = document.createElement('script'), title = document.querySelector('title'), h2 = document.querySelector('h2'), tbody = document.querySelector('tbody');
+    h2.textContent = h2.textContent.replace('Wikipedia', `${lang}.wikipedia.org`);
+    title.textContent = title.textContent.replace('Wikipedia', `${lang}.wikipedia.org`);
+    script.src = `./data/${lang}/index.js`;
+    script.addEventListener('load', () => {
+        for (const [rule, count] of data) {
+            const tr = document.createElement('tr'), description = document.createElement('td'), pages = document.createElement('td'), a = document.createElement('a');
+            a.textContent = rule;
+            a.href = `./rule.html?lang=${lang}&rule=${rule}`;
+            description.append(a);
+            pages.textContent = String(count);
+            tr.append(description, pages);
+            tbody.append(tr);
+        }
+    });
+    document.head.append(script);
+})();

package/reports/index.html

@@ -0,0 +1,18 @@
+<!DOCTYPE html>
+<html dir="ltr" lang="en-US">
+	<head>
+		<title>Diagnostic Report for Wikipedia Dumps</title>
+		<meta charset="utf-8">
+		<meta name="viewport" content="initial-scale=1.0, user-scalable=yes, minimum-scale=0.25, maximum-scale=5.0, width=device-width">
+		<link rel="stylesheet" href="reports.css">
+		<script defer="" src="dist/index.js"></script>
+	</head>
+	<body>
+		<main>
+			<article>
+				<h2>Please choose the language edition.</h2>
+				<div id="container"></div>
+			</article>
+		</main>
+	</body>
+</html>

package/reports/reports.css

@@ -0,0 +1,79 @@
+html, body, div, article, main {
+	margin: 0;
+	padding: 0;
+	border: 0;
+	font: inherit;
+	vertical-align: baseline;
+}
+:root {
+	font-size: 14px;
+	font-family: sans-serif;
+}
+body {
+	display: flex;
+	flex-direction: column;
+	align-items: center;
+	background-color: #f0f0f0;
+	line-height: 1.6;
+}
+main {
+	display: flex;
+	width: 90vw;
+	max-width: 1200px;
+	margin: 3rem 0;
+	background-color: #fff;
+	box-shadow: 0 0 .5rem rgba(0, 0, 0, .1);
+	border-radius: .5rem;
+}
+article {
+	display: block;
+	width: 100%;
+	padding: 1rem 2rem 2rem;
+}
+h2 {
+	font-size: 1.3em;
+	margin: .5rem 0;
+	font-weight: bold;
+	text-align: center;
+}
+#container, #nav {
+	font-size: 1.3em;
+	text-align: center;
+}
+#container > div {
+	margin: .1em 0;
+}
+table {
+	margin: 1em auto;
+	background-color: #f8f9fa;
+	color: #202122;
+	border: 1px solid #a2a9b1;
+	border-collapse: collapse;
+}
+th, td {
+	border: 1px solid #a2a9b1;
+	padding: .4em .8em;
+}
+th {
+	background-color: #eaecf0;
+	text-align: center;
+}
+.excerpt {
+	overflow: hidden;
+	white-space: nowrap;
+	text-overflow: ellipsis;
+}
+.mono {
+	font-family: monospace;
+}
+
+@media screen and (max-width: 720px) {
+	main {
+		width: 100%;
+		margin: 0;
+		border-radius: 0;
+	}
+	article {
+		padding: 1rem;
+	}
+}

package/reports/rule.html

@@ -0,0 +1,55 @@
+<!DOCTYPE html>
+<html dir="ltr" lang="en-US">
+	<head>
+		<title>Diagnostic Report for Wikipedia</title>
+		<meta charset="utf-8">
+		<meta name="viewport" content="initial-scale=1.0, user-scalable=yes, minimum-scale=0.25, maximum-scale=5.0, width=device-width">
+		<link rel="stylesheet" href="reports.css">
+		<style>td:nth-child(-n+4):not(:first-child),td:last-child{text-align:center}</style>
+		<script defer="" src="dist/rule.js"></script>
+	</head>
+	<body>
+		<main>
+			<article>
+				<div id="container">
+					<div>
+						<a href="./index.html">Homepage</a>
+					</div>
+					<div>
+						<a id="wiki" href="./wiki.html">Wikipedia</a>
+					</div>
+				</div>
+				<h2>Diagnostic Report for Wikipedia</h2>
+				<div id="nav">
+					<a href="#" id="prev" title="Previous">←</a>
+					<span id="start">0</span>
+					~
+					<span id="end">200</span>
+					<a href="#" id="next" title="Next">→</a>
+				</div>
+				<table style="table-layout:fixed;width:100%">
+					<colgroup>
+						<col span="1">
+						<col span="1" style="width:calc(1.6em + 5ch)">
+						<col span="1" style="width:calc(1.6em + 7ch)">
+						<col span="1" style="width:calc(1.6em + 7ch)">
+						<col span="1" style="width:20%">
+						<col span="1" style="width:40%">
+						<col span="1" style="width:calc(1.6em + 5ch)">
+					</colgroup>
+					<tbody>
+						<tr>
+							<th>Article</th>
+							<th>Edit</th>
+							<th>Line</th>
+							<th>Column</th>
+							<th>Detail</th>
+							<th>Notice</th>
+							<th>More</th>
+						</tr>
+					</tbody>
+				</table>
+			</article>
+		</main>
+	</body>
+</html>

package/reports/wiki.html

@@ -0,0 +1,28 @@
+<!DOCTYPE html>
+<html dir="ltr" lang="en-US">
+	<head>
+		<title>Diagnostic Report for Wikipedia</title>
+		<meta charset="utf-8">
+		<meta name="viewport" content="initial-scale=1.0, user-scalable=yes, minimum-scale=0.25, maximum-scale=5.0, width=device-width">
+		<link rel="stylesheet" href="reports.css">
+		<script defer="" src="dist/wiki.js"></script>
+	</head>
+	<body>
+		<main>
+			<article>
+				<div id="container">
+					<a href="./index.html">Homepage</a>
+				</div>
+				<h2>Diagnostic Report for Wikipedia</h2>
+				<table style="text-align:center">
+					<tbody>
+						<tr>
+							<th>Description</th>
+							<th>Pages</th>
+						</tr>
+					</tbody>
+				</table>
+			</article>
+		</main>
+	</body>
+</html>

package/scan.sh

@@ -0,0 +1,16 @@
+#!/usr/local/bin/bash
+if (( $# < 2 ))
+then
+	echo 'Usage: npx lint-wiki-dumps <language> <path to download>'
+	echo 'Example: npx lint-wiki-dumps zh-yue ~/Downloads/dumps'
+	exit 1
+fi
+site="${1}wiki" # example: zh-yuewiki
+target="${1//-/_}wiki" # example: zh_yuewiki
+file="${target}-latest-pages-articles.xml.bz2"
+if (( $# < 3 ))
+then
+	curl --output-dir "$2" -O "https://dumps.wikimedia.org/$target/latest/$file"
+	npx getParserConfig "$site" "https://$1.wikipedia.org/w/"
+fi
+node parser.js "$1" "$2/$file" "$3" "$4" && node report.js "$1"