Compare commits

...

3 Commits

Author SHA1 Message Date
gpt-engineer-app[bot]
ffd71f51fb Fix logging and robots.txt 2025-11-04 22:01:27 +00:00
gpt-engineer-app[bot]
40ebc3c11b Fix logging policy violation 2025-11-04 21:52:42 +00:00
gpt-engineer-app[bot]
deabb72330 feat: Implement sitemap generator 2025-11-04 21:48:50 +00:00
6 changed files with 445 additions and 14 deletions

View File

@@ -15,6 +15,7 @@ type VercelResponse = ServerResponse & {
}; };
import { detectBot } from './botDetection/index.js'; import { detectBot } from './botDetection/index.js';
import { vercelLogger } from './utils/logger.js';
interface PageData { interface PageData {
title: string; title: string;
@@ -76,7 +77,10 @@ async function getPageData(pathname: string, fullUrl: string): Promise<PageData>
} }
} }
} catch (error) { } catch (error) {
console.error(`[SSR-OG] Error fetching park data: ${error}`); vercelLogger.error('Error fetching park data', {
error: error instanceof Error ? error.message : String(error),
slug
});
} }
} }
@@ -115,7 +119,10 @@ async function getPageData(pathname: string, fullUrl: string): Promise<PageData>
} }
} }
} catch (error) { } catch (error) {
console.error(`[SSR-OG] Error fetching ride data: ${error}`); vercelLogger.error('Error fetching ride data', {
error: error instanceof Error ? error.message : String(error),
slug: rideSlug
});
} }
} }
@@ -204,20 +211,29 @@ export default async function handler(req: VercelRequest, res: VercelResponse):
// Enhanced logging with detection details // Enhanced logging with detection details
if (botDetection.isBot) { if (botDetection.isBot) {
console.log(`[SSR-OG] ✅ Bot detected: ${botDetection.platform || 'unknown'} | Confidence: ${botDetection.confidence} (${botDetection.score}%) | Method: ${botDetection.detectionMethod}`); vercelLogger.info('Bot detected', {
console.log(`[SSR-OG] Path: ${req.method} ${pathname}`); platform: botDetection.platform || 'unknown',
console.log(`[SSR-OG] UA: ${userAgent}`); confidence: botDetection.confidence,
if (botDetection.metadata.signals.length > 0) { score: botDetection.score,
console.log(`[SSR-OG] Signals: ${botDetection.metadata.signals.slice(0, 5).join(', ')}${botDetection.metadata.signals.length > 5 ? '...' : ''}`); method: botDetection.detectionMethod,
} path: `${req.method} ${pathname}`,
userAgent,
signals: botDetection.metadata.signals.slice(0, 5)
});
} else { } else {
// Log potential false negatives // Log potential false negatives
if (botDetection.score > 30) { if (botDetection.score > 30) {
console.warn(`[SSR-OG] ⚠️ Low confidence bot (${botDetection.score}%) - not serving SSR | ${req.method} ${pathname}`); vercelLogger.warn('Low confidence bot - not serving SSR', {
console.warn(`[SSR-OG] UA: ${userAgent}`); score: botDetection.score,
console.warn(`[SSR-OG] Signals: ${botDetection.metadata.signals.join(', ')}`); path: `${req.method} ${pathname}`,
userAgent,
signals: botDetection.metadata.signals
});
} else { } else {
console.log(`[SSR-OG] Regular user (score: ${botDetection.score}%) | ${req.method} ${pathname}`); vercelLogger.info('Regular user request', {
score: botDetection.score,
path: `${req.method} ${pathname}`
});
} }
} }
@@ -228,7 +244,10 @@ export default async function handler(req: VercelRequest, res: VercelResponse):
if (botDetection.isBot) { if (botDetection.isBot) {
// Fetch page-specific data // Fetch page-specific data
const pageData = await getPageData(pathname, fullUrl); const pageData = await getPageData(pathname, fullUrl);
console.log(`[SSR-OG] Generated OG tags: ${pageData.title}`); vercelLogger.info('Generated OG tags', {
title: pageData.title,
pathname
});
// Generate and inject OG tags // Generate and inject OG tags
const ogTags = generateOGTags(pageData); const ogTags = generateOGTags(pageData);
@@ -246,7 +265,10 @@ export default async function handler(req: VercelRequest, res: VercelResponse):
res.status(200).send(html); res.status(200).send(html);
} catch (error) { } catch (error) {
console.error('[SSR-OG] Error:', error); vercelLogger.error('SSR processing failed', {
error: error instanceof Error ? error.message : String(error),
pathname
});
// Fallback: serve original HTML // Fallback: serve original HTML
try { try {

33
api/utils/logger.ts Normal file
View File

@@ -0,0 +1,33 @@
/**
* Vercel Serverless Function Logger
* Provides structured JSON logging for Vercel API routes
* Matches the edge function logging pattern for consistency
*/
type LogLevel = 'info' | 'warn' | 'error';
interface LogContext {
[key: string]: unknown;
}
function formatLog(level: LogLevel, message: string, context?: LogContext): string {
return JSON.stringify({
timestamp: new Date().toISOString(),
level,
message,
service: 'vercel-ssrog',
...context
});
}
export const vercelLogger = {
info: (message: string, context?: LogContext) => {
console.info(formatLog('info', message, context));
},
warn: (message: string, context?: LogContext) => {
console.warn(formatLog('warn', message, context));
},
error: (message: string, context?: LogContext) => {
console.error(formatLog('error', message, context));
}
};

View File

@@ -12,3 +12,5 @@ Allow: /
User-agent: * User-agent: *
Allow: / Allow: /
Sitemap: https://thrillwiki.com/sitemap.xml

View File

@@ -1,5 +1,8 @@
project_id = "ydvtmnrszybqnbcqbdcy" project_id = "ydvtmnrszybqnbcqbdcy"
[functions.sitemap]
verify_jwt = false
[functions.admin-delete-user] [functions.admin-delete-user]
verify_jwt = true verify_jwt = true

View File

@@ -0,0 +1,367 @@
import { createClient } from 'https://esm.sh/@supabase/supabase-js@2.57.4';
import { edgeLogger } from '../_shared/logger.ts';
const BASE_URL = 'https://dev.thrillwiki.com';
// ============================================================================
// TYPE DEFINITIONS
// ============================================================================
interface SitemapUrl {
loc: string;
lastmod: string;
changefreq: 'always' | 'hourly' | 'daily' | 'weekly' | 'monthly' | 'yearly' | 'never';
priority: number;
}
interface SitemapStats {
total_urls: number;
parks: number;
rides: number;
manufacturers: number;
models: number;
designers: number;
operators: number;
owners: number;
static_pages: number;
generation_time_ms: number;
}
// ============================================================================
// IN-MEMORY CACHE
// ============================================================================
let cachedSitemap: string | null = null;
let cacheTimestamp: number = 0;
const CACHE_TTL_MS = 60 * 60 * 1000; // 1 hour
const cacheHeaders = {
'Cache-Control': 'public, s-maxage=3600, stale-while-revalidate=86400',
'CDN-Cache-Control': 'public, s-maxage=3600',
'Vercel-CDN-Cache-Control': 'public, s-maxage=3600',
};
function isCacheValid(): boolean {
if (!cachedSitemap) return false;
const age = Date.now() - cacheTimestamp;
return age < CACHE_TTL_MS;
}
// ============================================================================
// XML GENERATION UTILITIES
// ============================================================================
function escapeXml(unsafe: string): string {
return unsafe
.replace(/&/g, '&amp;')
.replace(/</g, '&lt;')
.replace(/>/g, '&gt;')
.replace(/"/g, '&quot;')
.replace(/'/g, '&apos;');
}
function calculatePriority(entityType: string, metadata?: { ride_count?: number }): number {
switch (entityType) {
case 'home': return 1.0;
case 'park':
const rideCount = metadata?.ride_count || 0;
return rideCount > 10 ? 0.9 : 0.8;
case 'ride': return 0.9;
case 'manufacturer': return 0.7;
case 'model': return 0.6;
case 'designer': return 0.6;
case 'operator': return 0.6;
case 'owner': return 0.6;
case 'list': return 0.5;
case 'static': return 0.3;
default: return 0.5;
}
}
function getChangeFreq(entityType: string): SitemapUrl['changefreq'] {
switch (entityType) {
case 'home': return 'daily';
case 'park':
case 'ride':
case 'manufacturer': return 'weekly';
case 'model':
case 'designer':
case 'operator':
case 'owner': return 'monthly';
case 'list': return 'daily';
case 'static': return 'yearly';
default: return 'monthly';
}
}
function createUrl(
path: string,
entityType: string,
lastmod: string,
metadata?: { ride_count?: number }
): SitemapUrl {
return {
loc: `${BASE_URL}${path}`,
lastmod: new Date(lastmod).toISOString().split('T')[0],
changefreq: getChangeFreq(entityType),
priority: calculatePriority(entityType, metadata),
};
}
function generateSitemapXml(urls: SitemapUrl[]): string {
const header = '<?xml version="1.0" encoding="UTF-8"?>\n' +
'<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n';
const entries = urls.map(url =>
` <url>\n` +
` <loc>${escapeXml(url.loc)}</loc>\n` +
` <lastmod>${url.lastmod}</lastmod>\n` +
` <changefreq>${url.changefreq}</changefreq>\n` +
` <priority>${url.priority.toFixed(1)}</priority>\n` +
` </url>`
).join('\n');
const footer = '\n</urlset>';
return header + entries + footer;
}
// ============================================================================
// SITEMAP GENERATION
// ============================================================================
async function generateSitemap(requestId: string): Promise<{
xml: string;
stats: SitemapStats;
}> {
const startTime = Date.now();
const urls: SitemapUrl[] = [];
const stats: SitemapStats = {
total_urls: 0,
parks: 0,
rides: 0,
manufacturers: 0,
models: 0,
designers: 0,
operators: 0,
owners: 0,
static_pages: 0,
generation_time_ms: 0,
};
const supabase = createClient(
Deno.env.get('SUPABASE_URL') ?? '',
Deno.env.get('SUPABASE_ANON_KEY') ?? ''
);
// Static pages
const now = new Date().toISOString();
urls.push(
createUrl('/', 'home', now),
createUrl('/parks', 'list', now),
createUrl('/rides', 'list', now),
createUrl('/manufacturers', 'list', now),
createUrl('/designers', 'list', now),
createUrl('/operators', 'list', now),
createUrl('/owners', 'list', now),
createUrl('/blog', 'list', now),
createUrl('/terms', 'static', now),
createUrl('/privacy', 'static', now),
createUrl('/submission-guidelines', 'static', now),
createUrl('/contact', 'static', now),
);
stats.static_pages = 12;
// Parallel database queries
const [parksResult, ridesResult, companiesResult, modelsResult] = await Promise.all([
supabase
.from('parks')
.select('slug, updated_at')
.not('slug', 'is', null)
.order('updated_at', { ascending: false }),
supabase
.from('rides')
.select('slug, updated_at, park:parks!inner(slug)')
.not('slug', 'is', null)
.order('updated_at', { ascending: false }),
supabase
.from('companies')
.select('slug, updated_at, company_type')
.not('slug', 'is', null)
.order('updated_at', { ascending: false }),
supabase
.from('ride_models')
.select('slug, updated_at, manufacturer:companies!ride_models_manufacturer_id_fkey(slug)')
.not('slug', 'is', null)
.order('updated_at', { ascending: false }),
]);
// Process parks
if (parksResult.data) {
for (const park of parksResult.data) {
urls.push(createUrl(`/parks/${park.slug}`, 'park', park.updated_at));
urls.push(createUrl(`/parks/${park.slug}/rides`, 'list', park.updated_at));
stats.parks++;
}
}
// Process rides
if (ridesResult.data) {
for (const ride of ridesResult.data) {
if (ride.park?.slug) {
urls.push(createUrl(`/parks/${ride.park.slug}/rides/${ride.slug}`, 'ride', ride.updated_at));
stats.rides++;
}
}
}
// Process companies
if (companiesResult.data) {
for (const company of companiesResult.data) {
const type = company.company_type;
if (type === 'manufacturer') {
urls.push(createUrl(`/manufacturers/${company.slug}`, 'manufacturer', company.updated_at));
urls.push(createUrl(`/manufacturers/${company.slug}/rides`, 'list', company.updated_at));
urls.push(createUrl(`/manufacturers/${company.slug}/models`, 'list', company.updated_at));
stats.manufacturers++;
} else if (type === 'designer') {
urls.push(createUrl(`/designers/${company.slug}`, 'designer', company.updated_at));
urls.push(createUrl(`/designers/${company.slug}/rides`, 'list', company.updated_at));
stats.designers++;
} else if (type === 'operator') {
urls.push(createUrl(`/operators/${company.slug}`, 'operator', company.updated_at));
urls.push(createUrl(`/operators/${company.slug}/parks`, 'list', company.updated_at));
stats.operators++;
} else if (type === 'property_owner') {
urls.push(createUrl(`/owners/${company.slug}`, 'owner', company.updated_at));
urls.push(createUrl(`/owners/${company.slug}/parks`, 'list', company.updated_at));
stats.owners++;
}
}
}
// Process ride models
if (modelsResult.data) {
for (const model of modelsResult.data) {
if (model.manufacturer?.slug) {
urls.push(
createUrl(`/manufacturers/${model.manufacturer.slug}/models/${model.slug}`, 'model', model.updated_at)
);
urls.push(
createUrl(`/manufacturers/${model.manufacturer.slug}/models/${model.slug}/rides`, 'list', model.updated_at)
);
stats.models++;
}
}
}
stats.total_urls = urls.length;
stats.generation_time_ms = Date.now() - startTime;
const xml = generateSitemapXml(urls);
edgeLogger.info('Sitemap generated', {
requestId,
stats,
sizeKB: (xml.length / 1024).toFixed(2),
});
return { xml, stats };
}
function generateFallbackSitemap(): string {
const now = new Date().toISOString();
const urls: SitemapUrl[] = [
createUrl('/', 'home', now),
createUrl('/parks', 'list', now),
createUrl('/rides', 'list', now),
createUrl('/manufacturers', 'list', now),
createUrl('/designers', 'list', now),
createUrl('/operators', 'list', now),
createUrl('/owners', 'list', now),
];
return generateSitemapXml(urls);
}
// ============================================================================
// MAIN HANDLER
// ============================================================================
Deno.serve(async (req) => {
const requestId = crypto.randomUUID();
const startTime = Date.now();
try {
// Return cached version if valid
if (isCacheValid()) {
const duration = Date.now() - startTime;
edgeLogger.info('Sitemap cache hit', {
requestId,
cacheAge: Date.now() - cacheTimestamp,
duration,
});
return new Response(cachedSitemap, {
headers: {
'Content-Type': 'application/xml; charset=utf-8',
'X-Request-ID': requestId,
'X-Cache': 'HIT',
'X-Generation-Time': `${duration}ms`,
...cacheHeaders,
},
});
}
// Generate fresh sitemap
const sitemap = await generateSitemap(requestId);
// Update cache
cachedSitemap = sitemap.xml;
cacheTimestamp = Date.now();
const duration = Date.now() - startTime;
edgeLogger.info('Sitemap cache miss - generated', {
requestId,
duration,
stats: sitemap.stats,
});
return new Response(sitemap.xml, {
headers: {
'Content-Type': 'application/xml; charset=utf-8',
'X-Request-ID': requestId,
'X-Cache': 'MISS',
'X-Generation-Time': `${duration}ms`,
...cacheHeaders,
},
});
} catch (error) {
const duration = Date.now() - startTime;
edgeLogger.error('Sitemap generation failed', {
requestId,
error: error instanceof Error ? error.message : String(error),
duration,
});
// Return minimal valid sitemap on error (graceful degradation)
const fallbackSitemap = generateFallbackSitemap();
return new Response(fallbackSitemap, {
status: 200, // Still return 200 for SEO
headers: {
'Content-Type': 'application/xml; charset=utf-8',
'X-Request-ID': requestId,
'X-Error': 'true',
'Cache-Control': 'public, max-age=300', // Cache errors for 5min only
},
});
}
});

View File

@@ -2,6 +2,10 @@
"installCommand": "bun install", "installCommand": "bun install",
"buildCommand": "bun run build", "buildCommand": "bun run build",
"rewrites": [ "rewrites": [
{
"source": "/sitemap.xml",
"destination": "https://api.thrillwiki.com/functions/v1/sitemap"
},
{ {
"source": "/", "source": "/",
"destination": "/api/ssrOG" "destination": "/api/ssrOG"