Enhance DocumentManager and DocumentProcessingStatus for improved document processing flow and error handling; update formatDocumentsData for consistent data structure and add detailed comments

Author: Novapool

frontend/src/components/DocumentManager.tsx

@@ -87,13 +87,19 @@ const DocumentManager: React.FC = () => {
 
               // Upload document
               const uploadDocument = httpsCallable(functions, 'uploadDocument');
-              await uploadDocument({
+              const result = await uploadDocument({
                 documentType,
                 documentName: file.name,
                 documentBase64: base64String
               });
 
-              setStatus(`Uploaded ${file.name} as ${documentType}`);
+              setStatus(`Uploaded ${file.name} as ${documentType}. Processing started.`);
+              
+              // Store the document ID for reference
+              const documentId = (result.data as any).documentId;
+              if (documentId) {
+                console.log(`Document ID: ${documentId}`);
+              }
               resolve();
             } catch (err) {
               reject(err);

frontend/src/components/DocumentProcessingStatus.tsx

@@ -99,25 +99,26 @@ const DocumentProcessingStatus: React.FC<DocumentProcessingStatusProps> = ({ onP
     }
   };
 
-  // Handle manual text extraction
-  const handleExtractText = async (documentId: string) => {
+  // Handle document processing retry
+  const handleRetryProcessing = async (documentId: string) => {
     if (!currentUser) return;
 
-    setStatus(`Extracting text for document ${documentId}...`);
+    setStatus(`Retrying processing for document ${documentId}...`);
     setError(null);
 
     try {
-      const extractPdfText = httpsCallable(functions, 'extractPdfText');
-      const result = await extractPdfText({ documentId });
+      // We'll use the formatDocumentsData function to process all documents
+      const formatDocumentsData = httpsCallable(functions, 'formatDocumentsData');
+      const result = await formatDocumentsData({});
 
       if ((result.data as any).success) {
-        setStatus('Text extracted successfully');
+        setStatus('Document processing initiated successfully');
       } else {
-        setError((result.data as any).message || 'Failed to extract text');
+        setError((result.data as any).message || 'Failed to process document');
       }
     } catch (err: any) {
-      console.error('Error extracting text:', err);
-      setError(`Text extraction failed: ${err.message || 'Unknown error'}`);
+      console.error('Error processing document:', err);
+      setError(`Processing failed: ${err.message || 'Unknown error'}`);
     }
   };
 
@@ -252,18 +253,18 @@ const DocumentProcessingStatus: React.FC<DocumentProcessingStatusProps> = ({ onP
                   <td style={styles.tableCell}>
                     {doc.status === 'uploaded' && (
                       <button
-                        onClick={() => handleExtractText(doc.id)}
+                        onClick={() => handleRetryProcessing(doc.id)}
                         style={styles.actionButton}
                       >
-                        Extract Text
+                        Process Document
                       </button>
                     )}
                     {doc.status === 'error' && (
                       <button
-                        onClick={() => handleExtractText(doc.id)}
+                        onClick={() => handleRetryProcessing(doc.id)}
                         style={styles.actionButton}
                       >
-                        Retry
+                        Retry Processing
                       </button>
                     )}
                     {doc.error && (

functions-node/formatDocumentsData.js

@@ -2,6 +2,11 @@ const OpenAI = require('openai');
 const functions = require('firebase-functions');
 const admin = require('firebase-admin');
 
+/**
+ * Formats all document data using a single OpenAI API call to ensure consistent structure
+ * @param {string} userId - The user ID
+ * @returns {Promise<Object>} Formatted data for calculations and predictions
+ */
 /**
  * Formats all document data using a single OpenAI API call to ensure consistent structure
  * @param {string} userId - The user ID
@@ -50,7 +55,7 @@ exports.formatDocumentsData = async (userId) => {
       apiKey: apiKey
     });
 
-    // Create a prompt with all document texts
+    // Create a unified prompt with all document texts
     const prompt = createFormattingPrompt(documentsByType);
 
     // Call OpenAI API
@@ -87,6 +92,11 @@ exports.formatDocumentsData = async (userId) => {
   }
 };
 
+/**
+ * Creates the prompt for OpenAI formatting
+ * @param {Object} documentsByType - Documents organized by type
+ * @returns {string} Formatted prompt
+ */
 /**
  * Creates the prompt for OpenAI formatting
  * @param {Object} documentsByType - Documents organized by type
@@ -169,6 +179,12 @@ For the academicHistory.relevantCourses, analyze the transcript to find courses
 `;
 }
 
+/**
+ * Stores the formatted data in Firestore
+ * @param {string} userId - The user ID
+ * @param {Object} formattedData - The formatted data
+ * @returns {Promise<void>}
+ */
 /**
  * Stores the formatted data in Firestore
  * @param {string} userId - The user ID
@@ -192,6 +208,12 @@ async function storeFormattedData(userId, formattedData) {
   }
 }
 
+/**
+ * Updates the status of processed documents
+ * @param {string} userId - The user ID
+ * @param {Array} documents - The document snapshots
+ * @returns {Promise<void>}
+ */
 /**
  * Updates the status of processed documents
  * @param {string} userId - The user ID
@@ -215,6 +237,11 @@ async function updateDocumentStatus(userId, documents) {
   console.log('Successfully updated document statuses');
 }
 
+/**
+ * Creates a fallback formatted data structure if OpenAI fails
+ * @param {Object} documentsByType - Documents organized by type
+ * @returns {Object} Fallback formatted data
+ */
 /**
  * Creates a fallback formatted data structure if OpenAI fails
  * @param {Object} documentsByType - Documents organized by type
@@ -266,6 +293,11 @@ function createFallbackFormattedData(documentsByType) {
   };
 }
 
+/**
+ * Extract grade weights using regex patterns
+ * @param {string} text - Text to extract grade weights from
+ * @returns {Array} Array of {name, weight} objects
+ */
 /**
  * Extract grade weights using regex patterns
  * @param {string} text - Text to extract grade weights from
@@ -312,6 +344,9 @@ function extractGradeWeights(text) {
   }
 }
 
+/**
+ * Helper function to get OpenAI API key
+ */
 /**
  * Helper function to get OpenAI API key
  */