Add automatic database population from PDGA numbers file at startup

- Read pdga-numbers.txt at server startup and check for missing players
- Automatically scrape and populate any missing players into database
- Maintain respectful 2-second delays between PDGA requests
- Add comprehensive logging for population process
- Include new API endpoints for manual database population and status checking
- Ensure database is fully populated before server accepts requests

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

server.js

@@ -94,6 +94,62 @@ function initializeDatabase() {
   });
 }
 
+// Check and populate database from PDGA numbers file at startup
+async function checkAndPopulateDatabase() {
+  try {
+    console.log('=== Checking database population against PDGA numbers file ===');
+    
+    const pdgaNumbers = fs.readFileSync('pdga-numbers.txt', 'utf-8')
+      .split('\n')
+      .map(num => num.trim())
+      .filter(num => num);
+    
+    console.log(`Found ${pdgaNumbers.length} PDGA numbers in file`);
+    
+    const missingPlayers = [];
+    
+    // Check which players are missing from database
+    for (const pdgaNumber of pdgaNumbers) {
+      const player = await getPlayerFromDB(pdgaNumber);
+      if (!player) {
+        missingPlayers.push(pdgaNumber);
+      }
+    }
+    
+    if (missingPlayers.length === 0) {
+      console.log('✓ All players from PDGA numbers file are already in database');
+      return;
+    }
+    
+    console.log(`Found ${missingPlayers.length} missing players: [${missingPlayers.join(', ')}]`);
+    console.log('=== Starting automatic population of missing players ===');
+    
+    // Populate missing players
+    for (let i = 0; i < missingPlayers.length; i++) {
+      const pdgaNumber = missingPlayers[i];
+      console.log(`[${i + 1}/${missingPlayers.length}] Scraping missing player PDGA ${pdgaNumber}...`);
+      
+      try {
+        const playerData = await scrapePDGARating(pdgaNumber);
+        console.log(`✓ Added PDGA ${pdgaNumber}: ${playerData.name}`);
+        
+        // Delay between requests to be respectful to PDGA
+        if (i < missingPlayers.length - 1) {
+          console.log('Waiting 2s before next request...');
+          await new Promise(resolve => setTimeout(resolve, 2000));
+        }
+      } catch (error) {
+        console.error(`✗ Failed to add PDGA ${pdgaNumber}: ${error.message}`);
+      }
+    }
+    
+    console.log('=== Database population complete ===');
+    
+  } catch (error) {
+    console.error('Error during database population check:', error.message);
+  }
+}
+
 // Database helper functions
 function getPlayerFromDB(pdgaNumber) {
   return new Promise((resolve, reject) => {
@@ -1399,8 +1455,8 @@ async function getAllRatingsFromDB(progressCallback = null) {
             current: i + 1,
             total,
             pdgaNumber,
-            status: 'completed',
-            name: playerData.name
+            status: playerData ? 'completed' : 'skipped',
+            name: playerData ? playerData.name : 'Not in DB'
           });
         }
       } catch (error) {
@@ -1472,6 +1528,58 @@ app.get('/api/ratings/progress', (req, res) => {
   });
 });
 
+// Endpoint to populate database from PDGA numbers file
+app.post('/api/populate-database', (req, res) => {
+  res.writeHead(200, {
+    'Content-Type': 'text/event-stream',
+    'Cache-Control': 'no-cache',
+    'Connection': 'keep-alive',
+    'Access-Control-Allow-Origin': '*',
+  });
+
+  const progressCallback = (progress) => {
+    res.write(`data: ${JSON.stringify(progress)}\n\n`);
+  };
+
+  console.log('=== Starting database population from PDGA numbers file ===');
+  
+  // Use the scraping function to populate database
+  getAllRatingsWithScraping(progressCallback).then(ratings => {
+    console.log(`=== Database population complete: ${ratings.length} players added ===`);
+    res.write(`data: ${JSON.stringify({ status: 'complete', ratings, message: `Successfully populated database with ${ratings.length} players` })}\n\n`);
+    res.end();
+  }).catch(error => {
+    console.error('Error populating database:', error);
+    res.write(`data: ${JSON.stringify({ status: 'error', message: error.message })}\n\n`);
+    res.end();
+  });
+});
+
+// Simple endpoint to check if database needs population
+app.get('/api/database-status', async (req, res) => {
+  try {
+    const pdgaNumbers = fs.readFileSync('pdga-numbers.txt', 'utf-8')
+      .split('\n')
+      .map(num => num.trim())
+      .filter(num => num);
+    
+    let playersInDB = 0;
+    for (const pdgaNumber of pdgaNumbers) {
+      const player = await getPlayerFromDB(pdgaNumber);
+      if (player) playersInDB++;
+    }
+    
+    res.json({
+      totalExpected: pdgaNumbers.length,
+      playersInDB: playersInDB,
+      needsPopulation: playersInDB === 0,
+      populationProgress: Math.round((playersInDB / pdgaNumbers.length) * 100)
+    });
+  } catch (error) {
+    res.status(500).json({ error: 'Failed to check database status' });
+  }
+});
+
 app.get('/api/load-all-players', (req, res) => {
   res.writeHead(200, {
     'Content-Type': 'text/event-stream',
@@ -1524,25 +1632,21 @@ async function getAllRatingsWithScraping(progressCallback = null) {
       }
       
       try {
-        const playerData = await getPlayerDataFromDB(pdgaNumber);
-        if (playerData) {
-          ratings.push(playerData);
-        } else {
-          console.log(`PDGA ${pdgaNumber} not found in DB - skipping`);
-          // Skip players not in DB instead of scraping
-        }
+        const playerData = await scrapePDGARating(pdgaNumber);
+        ratings.push(playerData);
         
         if (progressCallback) {
           progressCallback({
             current: i + 1,
             total,
             pdgaNumber,
-            status: playerData ? 'completed' : 'skipped',
-            name: playerData ? playerData.name : 'Not in DB'
+            status: 'completed',
+            name: playerData.name
           });
         }
         
-        // No delay needed - just reading from DB
+        // Delay between PDGA scraping requests to be respectful
+        await new Promise(resolve => setTimeout(resolve, 2000));
       } catch (error) {
         console.error(`Failed to scrape PDGA ${pdgaNumber}:`, error.message);
         const errorData = {
@@ -2136,7 +2240,10 @@ async function testPDGARateLimit() {
 // testPDGARateLimit();
 
 // Initialize database and start server
-initializeDatabase().then(() => {
+initializeDatabase().then(async () => {
+  // Check and populate missing players from PDGA numbers file
+  await checkAndPopulateDatabase();
+  
   app.listen(PORT, () => {
     console.log(`PDGA Ratings app running on http://localhost:${PORT}`);
   });