OxiRanker փաստաթղթեր

OXIRANKER_EXPORT_API_BASE_URL=https://oxiranker.com
OXIRANKER_EXPORT_API_TOKEN=YOUR_EXPORT_TOKEN
OXIRANKER_WEBHOOK_SECRET=YOUR_WEBHOOK_SECRET
OXIRANKER_WEBHOOK_MAX_SKEW_MS=300000
OXIRANKER_SOURCE_PROVIDER=oxiranker
OXIRANKER_SOURCE_DOMAIN_IDS=1

SITE_ARTICLE_IMAGE_UPLOAD_DIR=/var/www/example.com/uploads/site-articles
SITE_ARTICLE_IMAGE_MAX_BYTES=10485760

PUBLIC_BASE_URL=https://example.com

OXIRANKER_SYNC_ENABLED=true
OXIRANKER_SYNC_HOUR=3
OXIRANKER_SYNC_MINUTE=10
OXIRANKER_SYNC_PAGE_LIMIT=20
OXIRANKER_SYNC_MAX_PAGES=50

import express from "express";
import crypto from "crypto";

const app = express();

app.use(
  express.json({
    verify: (req, _res, buf) => {
      (req as any).rawBody = Buffer.from(buf);
    },
  })
);

function getHeader(req: express.Request, name: string): string {
  const value = req.headers[name.toLowerCase()];
  if (Array.isArray(value)) return String(value[0] || "").trim();
  return String(value || "").trim();
}

function getRawBody(req: express.Request): string {
  const raw = (req as any).rawBody;
  if (Buffer.isBuffer(raw)) return raw.toString("utf8");
  return JSON.stringify(req.body || {});
}

function createSignature(secret: string, timestamp: string, rawBody: string): string {
  const payload = `${timestamp}.${rawBody}`;
  const digest = crypto
    .createHmac("sha256", secret)
    .update(payload, "utf8")
    .digest("hex");

  return `sha256=${digest}`;
}

function timingSafeEqualText(a: string, b: string): boolean {
  const ab = Buffer.from(a, "utf8");
  const bb = Buffer.from(b, "utf8");

  if (ab.length !== bb.length) return false;
  return crypto.timingSafeEqual(ab, bb);
}

function isTimestampValid(timestamp: string): boolean {
  const maxSkewMs = Number(process.env.OXIRANKER_WEBHOOK_MAX_SKEW_MS || 300000);
  const date = new Date(timestamp);

  if (Number.isNaN(date.getTime())) return false;

  const diff = Math.abs(Date.now() - date.getTime());
  return diff <= maxSkewMs;
}

app.post("/api/oxiranker/webhook", async (req, res) => {
  const secret = String(process.env.OXIRANKER_WEBHOOK_SECRET || "").trim();

  if (!secret) {
    return res.status(500).json({
      error: "webhook_secret_missing",
      message: "Webhook secret is not configured.",
    });
  }

  const eventHeader = getHeader(req, "x-oxiranker-event");
  const domainIdHeader = getHeader(req, "x-oxiranker-domain-id");
  const timestamp = getHeader(req, "x-oxiranker-timestamp");
  const receivedSignature = getHeader(req, "x-oxiranker-signature");
  const rawBody = getRawBody(req);

  if (!eventHeader) {
    return res.status(400).json({
      error: "missing_webhook_event",
      message: "Webhook event header is required.",
    });
  }

  if (!domainIdHeader) {
    return res.status(400).json({
      error: "missing_webhook_domain_id",
      message: "Webhook domain id header is required.",
    });
  }

  if (!timestamp) {
    return res.status(400).json({
      error: "missing_webhook_timestamp",
      message: "Webhook timestamp header is required.",
    });
  }

  if (!receivedSignature) {
    return res.status(400).json({
      error: "missing_webhook_signature",
      message: "Webhook signature header is required.",
    });
  }

  if (!isTimestampValid(timestamp)) {
    return res.status(401).json({
      error: "invalid_webhook_timestamp",
      message: "Webhook timestamp is expired or invalid.",
    });
  }

  const expectedSignature = createSignature(secret, timestamp, rawBody);

  if (!timingSafeEqualText(expectedSignature, receivedSignature)) {
    return res.status(401).json({
      error: "invalid_webhook_signature",
      message: "Invalid webhook signature.",
    });
  }

  const payload = req.body || {};
  const event = String(payload.event || eventHeader || "").trim();

  if (event === "webhook.test") {
    const sourceDomainId = Number(payload.domain_id || domainIdHeader);

    return res.status(200).json({
      ok: true,
      message: "Webhook test received successfully.",
      event,
      source_domain_id:
        Number.isFinite(sourceDomainId) && sourceDomainId > 0 ? sourceDomainId : null,
      test: true,
    });
  }

  if (event !== "article.created" && event !== "article.updated") {
    return res.status(400).json({
      error: "unsupported_webhook_event",
      message: "Webhook event is not supported.",
    });
  }

  const sourceDomainId = Number(payload.domain_id || domainIdHeader);
  const sourceArticleId = Number(payload.article_id);

  if (!Number.isFinite(sourceDomainId) || sourceDomainId <= 0) {
    return res.status(400).json({
      error: "invalid_domain_id",
      message: "Webhook domain id is invalid.",
    });
  }

  if (!Number.isFinite(sourceArticleId) || sourceArticleId <= 0) {
    return res.status(400).json({
      error: "invalid_article_id",
      message: "Webhook article id is invalid.",
    });
  }

  // Fetch the full article from Export API and store it in the database here.
  // await syncArticleFromOxiranker(sourceDomainId, sourceArticleId);

  return res.status(200).json({
    ok: true,
    message: "Webhook processed successfully.",
    event,
    source_domain_id: sourceDomainId,
    source_article_id: sourceArticleId,
  });
});

CREATE TABLE public.site_articles (
  id BIGSERIAL PRIMARY KEY,

  source_provider VARCHAR NOT NULL DEFAULT 'oxiranker',
  source_domain_id BIGINT NOT NULL,
  source_article_id BIGINT NOT NULL,
  source_request_id BIGINT NULL,

  lang VARCHAR NOT NULL,
  lang_label VARCHAR NULL,
  dir VARCHAR NOT NULL,
  is_rtl BOOLEAN NULL,

  length VARCHAR NULL,
  topic_text TEXT NULL,

  slug VARCHAR NOT NULL,
  canonical_path VARCHAR NULL,
  effective_canonical_url TEXT NULL,

  title TEXT NOT NULL,
  meta_description TEXT NULL,
  html_body TEXT NULL,

  focus_keywords JSONB NOT NULL DEFAULT '[]'::jsonb,
  category VARCHAR NULL,
  tags JSONB NOT NULL DEFAULT '[]'::jsonb,

  reading_time_minutes INTEGER NULL,

  og_title TEXT NULL,
  og_description TEXT NULL,

  cover_image_url TEXT NULL,
  og_image_url TEXT NULL,

  article_schema JSONB NOT NULL DEFAULT '{}'::jsonb,

  raw_list_item JSONB NOT NULL DEFAULT '{}'::jsonb,
  raw_detail_payload JSONB NOT NULL DEFAULT '{}'::jsonb,

  source_created_at TIMESTAMPTZ NULL,
  source_updated_at TIMESTAMPTZ NULL,

  sync_status VARCHAR NOT NULL DEFAULT 'synced',
  last_synced_at TIMESTAMPTZ NOT NULL DEFAULT now(),
  last_sync_error TEXT NULL,

  publish_status VARCHAR NOT NULL DEFAULT 'draft',
  published_at TIMESTAMPTZ NULL,
  deleted_at TIMESTAMPTZ NULL,

  created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
  updated_at TIMESTAMPTZ NOT NULL DEFAULT now(),

  source_cover_image_url TEXT NULL,
  source_og_image_url TEXT NULL,

  image_mirror_status VARCHAR NOT NULL DEFAULT 'pending',
  image_mirror_error TEXT NULL,
  image_mirrored_at TIMESTAMPTZ NULL,

  CONSTRAINT site_articles_dir_check
    CHECK (dir IN ('ltr', 'rtl')),

  CONSTRAINT site_articles_reading_time_check
    CHECK (reading_time_minutes IS NULL OR reading_time_minutes >= 0),

  CONSTRAINT site_articles_sync_status_check
    CHECK (sync_status IN ('pending', 'syncing', 'synced', 'failed')),

  CONSTRAINT site_articles_publish_status_check
    CHECK (publish_status IN ('draft', 'published', 'archived')),

  CONSTRAINT site_articles_image_mirror_status_check
    CHECK (image_mirror_status IN ('pending', 'not_needed', 'mirrored', 'failed')),

  CONSTRAINT site_articles_source_unique
    UNIQUE (source_provider, source_domain_id, source_article_id)
);

CREATE INDEX site_articles_source_lookup_idx
ON public.site_articles (source_provider, source_domain_id, source_article_id);

CREATE INDEX site_articles_source_updated_at_idx
ON public.site_articles (source_updated_at DESC);

CREATE INDEX site_articles_slug_idx
ON public.site_articles (slug)
WHERE deleted_at IS NULL;

CREATE UNIQUE INDEX site_articles_lang_slug_active_unique
ON public.site_articles (lang, slug)
WHERE deleted_at IS NULL;

CREATE INDEX site_articles_lang_publish_idx
ON public.site_articles (lang, publish_status)
WHERE deleted_at IS NULL;

CREATE INDEX site_articles_published_at_idx
ON public.site_articles (published_at DESC)
WHERE deleted_at IS NULL;

CREATE INDEX site_articles_focus_keywords_gin_idx
ON public.site_articles USING gin (focus_keywords);

CREATE INDEX site_articles_tags_gin_idx
ON public.site_articles USING gin (tags);

CREATE INDEX site_articles_article_schema_gin_idx
ON public.site_articles USING gin (article_schema);

INSERT INTO public.site_articles (
  source_provider,
  source_domain_id,
  source_article_id,
  source_request_id,
  lang,
  dir,
  slug,
  title,
  meta_description,
  html_body,
  focus_keywords,
  category,
  tags,
  reading_time_minutes,
  cover_image_url,
  og_image_url,
  article_schema,
  source_created_at,
  source_updated_at,
  sync_status,
  last_synced_at,
  publish_status,
  published_at,
  created_at,
  updated_at
)
VALUES (
  'oxiranker',
  1,
  5,
  5,
  'fa',
  'rtl',
  'smart-internal-links',
  'Article title',
  'Meta description',
  '<p>HTML body</p>',
  '[]'::jsonb,
  'SEO',
  '[]'::jsonb,
  7,
  'https://example.com/uploads/site-articles/oxiranker/1/5/cover.webp',
  'https://example.com/uploads/site-articles/oxiranker/1/5/cover.webp',
  '{}'::jsonb,
  '2026-05-20T19:33:23.618Z',
  '2026-05-20T19:34:09.629Z',
  'synced',
  now(),
  'published',
  now(),
  now(),
  now()
)
ON CONFLICT (source_provider, source_domain_id, source_article_id)
DO UPDATE SET
  source_request_id = EXCLUDED.source_request_id,
  lang = EXCLUDED.lang,
  dir = EXCLUDED.dir,
  slug = EXCLUDED.slug,
  title = EXCLUDED.title,
  meta_description = EXCLUDED.meta_description,
  html_body = EXCLUDED.html_body,
  focus_keywords = EXCLUDED.focus_keywords,
  category = EXCLUDED.category,
  tags = EXCLUDED.tags,
  reading_time_minutes = EXCLUDED.reading_time_minutes,
  cover_image_url = EXCLUDED.cover_image_url,
  og_image_url = EXCLUDED.og_image_url,
  article_schema = EXCLUDED.article_schema,
  source_created_at = EXCLUDED.source_created_at,
  source_updated_at = EXCLUDED.source_updated_at,
  sync_status = 'synced',
  last_synced_at = now(),
  last_sync_error = NULL,
  publish_status = CASE
    WHEN public.site_articles.publish_status = 'archived'
    THEN public.site_articles.publish_status
    ELSE 'published'
  END,
  published_at = COALESCE(public.site_articles.published_at, EXCLUDED.published_at, now()),
  deleted_at = NULL,
  updated_at = now();

async function fetchOxirankerArticleDetail(args: {
  baseUrl: string;
  token: string;
  domainId: number;
  articleId: number;
}) {
  const url = `${args.baseUrl.replace(/\/+$/, "")}/api/v1/users/domains/${args.domainId}/articles/${args.articleId}/export/json`;

  const response = await fetch(url, {
    method: "GET",
    headers: {
      Authorization: `Bearer ${args.token}`,
      Accept: "application/json",
      "User-Agent": "My-Site-Oxiranker-Sync/1.0",
    },
  });

  const bodyText = await response.text();

  if (response.status < 200 || response.status > 299) {
    throw new Error(
      `Export API request failed with HTTP status ${response.status}. Response: ${bodyText.slice(0, 1000)}`
    );
  }

  try {
    return JSON.parse(bodyText);
  } catch {
    throw new Error("Export API returned invalid JSON.");
  }
}

async function syncArticleFromWebhook(payload: any) {
  const sourceDomainId = Number(payload.domain_id);
  const sourceArticleId = Number(payload.article_id);

  if (!Number.isFinite(sourceDomainId) || sourceDomainId <= 0) {
    throw new Error("Webhook domain id is invalid.");
  }

  if (!Number.isFinite(sourceArticleId) || sourceArticleId <= 0) {
    throw new Error("Webhook article id is invalid.");
  }

  const article = await fetchOxirankerArticleDetail({
    baseUrl: process.env.OXIRANKER_EXPORT_API_BASE_URL!,
    token: process.env.OXIRANKER_EXPORT_API_TOKEN!,
    domainId: sourceDomainId,
    articleId: sourceArticleId,
  });

  const mirroredImages = await mirrorArticleImages(article);

  const finalHtmlBody = replaceImageUrls(article.html_body, mirroredImages);
  const finalArticleSchema = replaceImageUrlsInJson(article.article_schema, mirroredImages);

  await upsertSiteArticle({
    source_provider: process.env.OXIRANKER_SOURCE_PROVIDER || "oxiranker",
    source_domain_id: sourceDomainId,
    source_article_id: sourceArticleId,
    source_request_id: article.request_id,
    lang: article.lang,
    dir: article.dir,
    slug: article.slug,
    title: article.title,
    meta_description: article.meta_description,
    html_body: finalHtmlBody,
    focus_keywords: article.focus_keywords,
    category: article.category,
    tags: article.tags,
    reading_time_minutes: article.reading_time_minutes,
    cover_image_url: mirroredImages.cover_image_url,
    og_image_url: mirroredImages.og_image_url,
    article_schema: finalArticleSchema,
    raw_detail_payload: article,
    source_created_at: article.created_at,
    source_updated_at: article.updated_at,
  });
}