SCRAPE-13: Create node-cron job initialization (#18)

Co-authored-by: Stephen Minakian <stephenminakian@gmail.com>
Co-committed-by: Stephen Minakian <stephenminakian@gmail.com>

jobs/scraperJob.js

@@ -1,7 +1,16 @@
+const cron = require('node-cron');
+const config = require('../config/scraper');
+const { runScrape } = require('../services/scraperService');
+const { createLogger } = require('../services/scraperLogger');
+const { v4: uuidv4 } = require('uuid');
+
 // In-process mutex state
 let isRunning = false;
 let currentJobId = null;
 
+// Scheduler state
+let scheduledJob = null;
+
 /**
  * Check if scraper is currently running
  * @returns {boolean}
@@ -40,9 +49,143 @@ function releaseLock() {
   currentJobId = null;
 }
 
+/**
+ * Get the configured schedule expression
+ * @returns {string} Cron expression or 'disabled'
+ */
+function getScheduleExpression() {
+  if (!config.SCRAPER_ENABLED) {
+    return 'disabled';
+  }
+  return config.SCRAPER_SCHEDULE;
+}
+
+/**
+ * Calculate next scheduled run time
+ * @returns {string|null} ISO timestamp or null if disabled
+ */
+function getNextScheduledRun() {
+  if (!config.SCRAPER_ENABLED || !scheduledJob) {
+    return null;
+  }
+
+  const { CronExpressionParser } = require('cron-parser');
+  try {
+    const interval = CronExpressionParser.parse(config.SCRAPER_SCHEDULE, {
+      tz: config.SCRAPER_TIMEZONE
+    });
+    return interval.next().toISOString();
+  } catch (error) {
+    return null;
+  }
+}
+
+/**
+ * Check if schedule runs more frequently than 1 hour
+ * @param {string} schedule - Cron expression
+ * @returns {boolean} True if schedule is too frequent
+ */
+function isScheduleTooFrequent(schedule) {
+  const parts = schedule.trim().split(/\s+/);
+
+  if (parts.length < 5) return false;
+
+  const minuteField = parts[0];
+
+  // If minute field is */N with N < 60, it runs more than once per hour
+  if (/^\*\/\d+$/.test(minuteField)) {
+    const interval = parseInt(minuteField.substring(2), 10);
+    if (interval < 60) return true;
+  }
+
+  // If minute field is *, it runs every minute
+  if (minuteField === '*') return true;
+
+  return false;
+}
+
+/**
+ * Initialize the scraper scheduler
+ * @param {Db} db - MongoDB database instance
+ */
+function initializeScheduler(db) {
+  const logger = createLogger('scheduler');
+
+  // Check if scheduling is enabled
+  if (!config.SCRAPER_ENABLED) {
+    logger.info('Scraper scheduling is disabled');
+    return;
+  }
+
+  // Validate cron expression
+  if (!cron.validate(config.SCRAPER_SCHEDULE)) {
+    logger.error('Invalid cron schedule expression', {
+      schedule: config.SCRAPER_SCHEDULE
+    });
+    logger.warn('Falling back to default schedule: 0 6 * * *');
+    config.SCRAPER_SCHEDULE = '0 6 * * *';
+  }
+
+  // Validate minimum interval (1 hour)
+  if (isScheduleTooFrequent(config.SCRAPER_SCHEDULE)) {
+    logger.warn('Schedule interval less than 1 hour - adjusting to hourly', {
+      originalSchedule: config.SCRAPER_SCHEDULE
+    });
+    config.SCRAPER_SCHEDULE = '0 * * * *';
+  }
+
+  // Create the scheduled job
+  scheduledJob = cron.schedule(config.SCRAPER_SCHEDULE, async () => {
+    const jobId = uuidv4();
+    const jobLogger = createLogger(jobId);
+
+    jobLogger.info('Scheduled scrape triggered');
+
+    // Check if already running
+    if (!acquireLock(jobId)) {
+      jobLogger.warn('Skipped - scrape already in progress');
+      return;
+    }
+
+    try {
+      await runScrape(db, { trigger: 'scheduled', jobId });
+    } catch (error) {
+      jobLogger.error('Scheduled scrape failed', {
+        errorType: error.name,
+        errorMessage: error.message
+      });
+    } finally {
+      releaseLock();
+    }
+  }, {
+    timezone: config.SCRAPER_TIMEZONE,
+    scheduled: true
+  });
+
+  logger.info('Scraper scheduler initialized', {
+    schedule: config.SCRAPER_SCHEDULE,
+    timezone: config.SCRAPER_TIMEZONE,
+    nextRun: getNextScheduledRun()
+  });
+}
+
+/**
+ * Stop the scheduler (for graceful shutdown)
+ */
+function stopScheduler() {
+  if (scheduledJob) {
+    scheduledJob.stop();
+    scheduledJob = null;
+  }
+}
+
 module.exports = {
   isScraperRunning,
   getCurrentJobId,
   acquireLock,
-  releaseLock
+  releaseLock,
+  getScheduleExpression,
+  getNextScheduledRun,
+  initializeScheduler,
+  stopScheduler
 };