@sonordev/site-kit 1.5.3 → 1.5.4

package/dist/cli/index.mjs

@@ -36384,9 +36384,17 @@ async function syncPagesToPortal(apiUrl, apiKey, dryRun) {
   }
   const pages = discoverPages(appDir);
   spinner.succeed(`Found ${pages.length} pages`);
+  const contentSpinner = ora("Extracting page content from build...").start();
+  const enrichedCount = enrichPagesWithContent(pages);
+  if (enrichedCount > 0) {
+    contentSpinner.succeed(`Extracted content from ${enrichedCount}/${pages.length} pages`);
+  } else {
+    contentSpinner.warn("No build output found \u2014 run after `next build` for content extraction");
+  }
   console.log(source_default.bold("  Pages to sync:"));
   for (const page of pages.slice(0, 10)) {
-    console.log(source_default.gray(`    ${page.path} (priority: ${page.priority})`));
+    const contentTag = page.content ? source_default.green(`${page.content.wordCount}w`) : source_default.gray("no content");
+    console.log(source_default.gray(`    ${page.path} (${contentTag})`));
   }
   if (pages.length > 10) {
     console.log(source_default.gray(`    ... and ${pages.length - 10} more`));
@@ -36408,7 +36416,15 @@ async function syncPagesToPortal(apiUrl, apiKey, dryRun) {
         entries: pages.map((p) => ({
           path: p.path,
           priority: p.priority,
-          changefreq: p.changeFreq
+          changefreq: p.changeFreq,
+          // Build-time content extraction
+          ...p.content ? {
+            content_text: p.content.text,
+            content_title: p.content.title,
+            content_h1: p.content.h1,
+            content_headings: p.content.headings,
+            content_word_count: p.content.wordCount
+          } : {}
         })),
         mode: "full-replace"
       })
@@ -36417,7 +36433,7 @@ async function syncPagesToPortal(apiUrl, apiKey, dryRun) {
       throw new Error(`HTTP ${response.status}: ${await response.text()}`);
     }
     const result = await response.json();
-    syncSpinner.succeed(`Synced pages: ${result.created || 0} created, ${result.updated || 0} updated`);
+    syncSpinner.succeed(`Synced pages: ${result.created || 0} created, ${result.updated || 0} updated, ${result.content_updated || 0} with content`);
   } catch (error) {
     syncSpinner.fail(`Sync failed: ${error.message}`);
   }
@@ -36475,6 +36491,136 @@ function discoverPages(appDir, currentPath = "", pages = []) {
   }
   return pages;
 }
+function findNextBuildDir() {
+  const cwd = process.cwd();
+  const candidate = path4.join(cwd, ".next", "server", "app");
+  return existsSync(candidate) ? candidate : null;
+}
+function extractPageContent(buildDir, pagePath) {
+  const baseName = pagePath === "/" ? "index" : pagePath.replace(/^\//, "");
+  const htmlCandidates = [
+    path4.join(buildDir, `${baseName}.html`),
+    path4.join(buildDir, baseName, "index.html")
+  ];
+  let html = null;
+  for (const candidate of htmlCandidates) {
+    if (existsSync(candidate)) {
+      try {
+        html = readFileSync(candidate, "utf-8");
+        break;
+      } catch {
+        continue;
+      }
+    }
+  }
+  const rscCandidates = [
+    path4.join(buildDir, `${baseName}.rsc`),
+    path4.join(buildDir, baseName, "index.rsc")
+  ];
+  let rsc = null;
+  for (const candidate of rscCandidates) {
+    if (existsSync(candidate)) {
+      try {
+        rsc = readFileSync(candidate, "utf-8");
+        break;
+      } catch {
+        continue;
+      }
+    }
+  }
+  if (!html && !rsc) return null;
+  let title;
+  let metaDescription;
+  if (html) {
+    const titleMatch = html.match(/<title[^>]*>([^<]+)<\/title>/i);
+    title = titleMatch?.[1]?.trim();
+    const descMatch = html.match(/<meta\s+name="description"\s+content="([^"]+)"/i);
+    metaDescription = descMatch?.[1]?.trim();
+  }
+  if (rsc) {
+    return parseRscContent(rsc, title, metaDescription);
+  }
+  if (html) {
+    return parseHtmlContent(html);
+  }
+  return null;
+}
+function parseRscContent(rsc, title, metaDescription) {
+  const textParts = [];
+  const headings = [];
+  const childrenRegex = /,"children":"([^"]+)"/g;
+  let match;
+  while ((match = childrenRegex.exec(rsc)) !== null) {
+    const text2 = match[1].trim();
+    if (!text2) continue;
+    if (/^[A-Z]?\[/.test(text2)) continue;
+    if (/^\//.test(text2) && !text2.includes(" ")) continue;
+    if (/^\$L[0-9a-f]+$/i.test(text2)) continue;
+    if (/^\$/.test(text2) && text2.length < 10) continue;
+    textParts.push(text2);
+  }
+  const h1Regex = /\["\$","h1",[^,]*,\{[^}]*"children":"([^"]+)"/g;
+  let h1;
+  while ((match = h1Regex.exec(rsc)) !== null) {
+    const text2 = match[1].trim();
+    if (text2) {
+      if (!h1) h1 = text2;
+      headings.push(text2);
+    }
+  }
+  const hRegex = /\["\$","h[2-6]",[^,]*,\{[^}]*"children":"([^"]+)"/g;
+  while ((match = hRegex.exec(rsc)) !== null) {
+    const text2 = match[1].trim();
+    if (text2) headings.push(text2);
+  }
+  let text = textParts.join(" ").replace(/\s+/g, " ").trim();
+  if (metaDescription && !text.includes(metaDescription)) {
+    text = metaDescription + " \u2014 " + text;
+  }
+  if (text.length > 1e4) {
+    text = text.substring(0, 1e4) + "...";
+  }
+  const wordCount = text.split(/\s+/).filter(Boolean).length;
+  return { text, title, h1, headings, wordCount };
+}
+function parseHtmlContent(html) {
+  const titleMatch = html.match(/<title[^>]*>([^<]+)<\/title>/i);
+  const title = titleMatch?.[1]?.trim();
+  let cleaned = html.replace(/<script[\s\S]*?<\/script>/gi, "").replace(/<style[\s\S]*?<\/style>/gi, "").replace(/<svg[\s\S]*?<\/svg>/gi, "").replace(/<nav[\s\S]*?<\/nav>/gi, "").replace(/<footer[\s\S]*?<\/footer>/gi, "").replace(/<header[\s\S]*?<\/header>/gi, "").replace(/<[^>]+(?:hidden|display:\s*none|aria-hidden="true")[^>]*>[\s\S]*?<\/[^>]+>/gi, "");
+  const h1Match = cleaned.match(/<h1[^>]*>([\s\S]*?)<\/h1>/i);
+  const h1 = h1Match ? stripTags(h1Match[1]).trim() : void 0;
+  const headingRegex = /<h[1-6][^>]*>([\s\S]*?)<\/h[1-6]>/gi;
+  const headings = [];
+  let match;
+  while ((match = headingRegex.exec(cleaned)) !== null) {
+    const text2 = stripTags(match[1]).trim();
+    if (text2) headings.push(text2);
+  }
+  const mainMatch = cleaned.match(/<main[\s\S]*?>([\s\S]*?)<\/main>/i) || cleaned.match(/<article[\s\S]*?>([\s\S]*?)<\/article>/i);
+  const contentHtml = mainMatch ? mainMatch[1] : cleaned;
+  let text = stripTags(contentHtml).replace(/\s+/g, " ").trim();
+  if (text.length > 1e4) {
+    text = text.substring(0, 1e4) + "...";
+  }
+  const wordCount = text.split(/\s+/).filter(Boolean).length;
+  return { text, title, h1, headings, wordCount };
+}
+function stripTags(html) {
+  return html.replace(/<[^>]+>/g, " ").replace(/&nbsp;/g, " ").replace(/&amp;/g, "&").replace(/&lt;/g, "<").replace(/&gt;/g, ">").replace(/&#\d+;/g, "");
+}
+function enrichPagesWithContent(pages) {
+  const buildDir = findNextBuildDir();
+  if (!buildDir) return 0;
+  let enriched = 0;
+  for (const page of pages) {
+    const content = extractPageContent(buildDir, page.path);
+    if (content && content.wordCount > 10) {
+      page.content = content;
+      enriched++;
+    }
+  }
+  return enriched;
+}
 var BLOG_DIRS = ["app/blog", "content/blog", "posts", "src/content/blog"];
 var BLOG_EXTENSIONS = [".mdx", ".md"];
 function findBlogDir() {