Added script and workflows to check broken links

.github/workflows/broken-links.yml

@@ -0,0 +1,68 @@
+name: Check Broken Links
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  check-broken-links:
+    name: Broken Link Checker
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Set Up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 18
+
+      - name: Install Dependencies
+        run: |
+          cd broken-links-script
+          npm install
+
+      - name: Run Broken Link Checker
+        run: |
+          cd broken-links-script
+          node BrokenLinkChecker.js
+
+      - name: Parse and Comment Broken Links
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const fs = require('fs');
+            const path = './broken-links-script/broken_links_markdown.csv';
+            let body;
+            if (fs.existsSync(path)) {
+              const data = fs.readFileSync(path, 'utf8').trim();
+              const lines = data.split('\n').slice(1); // Skip the header line
+              const broken404Links = lines.filter(line => line.includes(',404')); // Filter only 404 errors
+
+              if (broken404Links.length > 0) {
+                body = `### :warning: The following 404 broken links were found:\n\n${broken404Links
+                  .map((line) => {
+                    const [url, file, status] = line.split(',');
+                    return `- **[${url}](${url})** in file \`${file}\` (Status: ${status})`;
+                  })
+                  .join('\n')}`;
+              } else {
+                body = 'No broken links with 404 status found.';
+              }
+            } else {
+              body = 'Error: Broken link checker did not produce a CSV report.';
+            }
+
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: body
+            });

broken-links-script/BrokenLinkChecker.js

@@ -0,0 +1,126 @@
+import fs from "fs";
+import path from "path";
+import fetch from "node-fetch";
+import pLimit from "p-limit";
+
+const getMarkdownFiles = (dir) => {
+  const files = fs.readdirSync(dir, { withFileTypes: true });
+  let markdownFiles = [];
+  for (const file of files) {
+    const fullPath = path.join(dir, file.name);
+    if (file.isDirectory()) {
+      markdownFiles = markdownFiles.concat(getMarkdownFiles(fullPath));
+    } else if (file.isFile() && file.name.endsWith(".md")) {
+      markdownFiles.push(fullPath);
+    }
+  }
+  return markdownFiles;
+};
+
+const BASE_URL = "https://cumulocity.com/docs";
+
+const shortcodeMapping = {
+  "product-c8y-iot": "Cumulocity",
+  "c8y-edge-current-version-alt": "10.18",
+  "domain-c8y": "cumulocity.com",
+  "link-c8y-github": "https://github.com/Cumulocity-IoT/",
+  "c8y-edge-current-version-alt" : "10.18",
+  "c8y-edge-current-version" : "1018",
+  "c8y-support-link" : "https://cumulocity.com/support",
+  "link-apamadoc-api" : "https://cumulocity.com/apama/docs/latest/related/ApamaDoc/index.html",
+  "link-c8y-doc-baseurl" : ".Page.Site.BaseURL",
+  "link-device-portal": "https://ecosystem.cumulocity.com/devices/?filter_cumulocity_certified=yes",
+  "c8y-support-link": "https://cumulocity.atlassian.net/servicedesk/customer/user/login?destination=portals",
+  "link-apama-webhelp" : "https://cumulocity.com/apama/docs/latest",
+  "link-c8y-training": "https://cumulocity.moodlecloud.com/",
+  "c8y-resources-server-link": "https://download.cumulocity.com/",
+  "c8y-tech-community-link" : "https://techcommunity.cumulocity.com/",
+  "c8y-support-email" : "[email protected]",
+  "email-c8y-info" : "[email protected]"
+
+};
+
+const resolveHugoShortcode = (link) => {
+  return link.replace(/\{\{<\s*(.*?)\s*>\}\}/g, (match, shortcode) => {
+    const resolvedValue = shortcodeMapping[shortcode];
+    return resolvedValue !== undefined && resolvedValue !== null ? resolvedValue : ""; 
+  });
+};
+
+const resolveFullUrl = (link) => {
+  if (link.startsWith("mailto:") || link.startsWith("tel:")) {
+    return null; 
+  }
+
+  const resolvedLink = resolveHugoShortcode(link);
+  if (resolvedLink.startsWith("http://") || resolvedLink.startsWith("https://")) {
+    return resolvedLink;
+  }
+
+  return `${BASE_URL.replace(/\/$/, "")}/${resolvedLink.replace(/^\//, "")}`;
+};
+
+const checkLink = async (link, mdFile) => {
+  const fullUrl = resolveFullUrl(link);
+  if (!fullUrl) {
+    return null; 
+  }
+
+  try {
+    let response = await fetch(fullUrl, { method: "HEAD" });
+    if (response.status === 405) {
+      response = await fetch(fullUrl, { method: "GET" });
+    }
+
+    if (!response.ok) {
+      return { url: fullUrl, file: mdFile, status: response.status };
+    }
+  } catch (error) {
+    return { url: fullUrl, file: mdFile, status: "Error" };
+  }
+
+  return null;
+};
+
+(async () => {
+  const projectDir = ".././content"; 
+  const markdownFiles = getMarkdownFiles(projectDir);
+
+  const brokenLinks = [];
+  const limit = pLimit(10); 
+
+
+  const tasks = markdownFiles.map((mdFile) => {
+    const content = fs.readFileSync(mdFile, "utf8");
+    const links = [...content.matchAll(/(?<!\!)\[.*?\]\((.+?)\)/g)].map(
+      (match) => {
+        let link = match[1];
+        if (link.includes("(") && !link.endsWith(")")) {
+          link += ")"; // Add closing bracket if there's an opening bracket but no closing bracket
+        }
+        return link;
+      }
+    );
+
+
+
+    return links.map((link) =>
+      limit(async () => {
+        const result = await checkLink(link, mdFile);
+        if (result) brokenLinks.push(result);
+      })
+    );
+  });
+
+  await Promise.all(tasks.flat());
+
+  const filteredBrokenLinks = brokenLinks.filter((link) => link.status === 404);
+
+  const csvData =
+    "URL,File Path,Status Code\n" +
+    filteredBrokenLinks.map((link) => `${link.url},${link.file},${link.status}`).join("\n");
+
+  fs.writeFileSync("broken_links_markdown.csv", csvData);
+  console.log("Broken links in markdown files saved to broken_links_markdown.csv");
+  process.exit(0);
+})();

broken-links-script/broken_links_markdown.csv

@@ -0,0 +1,7 @@
+URL,File Path,Status Code
+https://github.com/Cumulocity-IoT//cumulocity-examples/snmp,..\content\change-logs\device-management\SNMP-removed-from-docs.md,404
+https://openmobilealliance.org/iot/lightweight-m2m-lwm2m,..\content\protocol-integration\lwm2m-bundle\introduction.md,404
+https://cumulocity.com/apama/docs/latest/related/ApamaDoc/index.htmlcom/apama/cumulocity/package-summary.html,..\content\streaming-analytics\epl-apps-bundle\basic-functionality.md,404
+https://cumulocity.com/apama/docs/latest/related/ApamaDoc/index.html/com/apama/cumulocity/package-summary.html,..\content\streaming-analytics\epl-apps-bundle\basic-functionality.md,404
+https://cumulocity.com/apama/docs/latest/related/ApamaDoc/index.htmlcom/softwareag/connectivity/httpclient/package-summary.html,..\content\streaming-analytics\epl-apps-bundle\microservices.md,404
+https://cumulocity.com/docs/<https://en.wikipedia.org/wiki/Glob_(programming),..\content\web\upgrade-bundle\c8y-cli.md,404