feat: Refactor report generation to use async methods and improve error handling; enhance spirometry table extraction with better CSV formatting

app/services/report_generator.py

@@ -10,7 +10,7 @@ from typing import Any, Dict, List
 
 import pandas as pd
 from jinja2 import Environment, FileSystemLoader
-from playwright.sync_api import sync_playwright
+from playwright.async_api import async_playwright
 from services.context_generator import ContextGenerator
 from services.graph_generator import GraphGenerator
 from services.spirometry_table_extractor import extract_spirometry_table_from_pdf
@@ -265,7 +265,7 @@ class ReportGeneratorService:
 
         return html_doc
 
-    def html_to_pdf(self, html_content: str, pdf_path: str) -> None:
+    async def html_to_pdf(self, html_content: str, pdf_path: str) -> None:
         """
         Convert HTML content to PDF file.
 
@@ -273,14 +273,14 @@ class ReportGeneratorService:
             html_content: HTML content as string
             pdf_path: Path where PDF should be saved
         """
-        with sync_playwright() as p:
-            browser = p.chromium.launch()
-            page = browser.new_page()
-            page.set_content(html_content)
-            page.pdf(path=pdf_path, format="A4", print_background=True)
-            browser.close()
+        async with async_playwright() as p:
+            browser = await p.chromium.launch()
+            page = await browser.new_page()
+            await page.set_content(html_content)
+            await page.pdf(path=pdf_path, format="A4", print_background=True)
+            await browser.close()
 
-    def generate_report(
+    async def generate_report(
         self,
         spirometry_pdf_path: str,
         pnoe_csv_path: str,
@@ -309,19 +309,18 @@ class ReportGeneratorService:
             Dictionary containing report path, graphs generated, and analysis data
         """
         # Step 1: Extract spirometry table from PDF
-        spirometry_csv_path = self.data_dir / "extracted_spirometry_table.csv"
-        extract_spirometry_table_from_pdf(spirometry_pdf_path)
-
-        # The extraction saves to current directory, move it to data_dir
-        import shutil
-
-        if Path("extracted_spirometry_table.csv").exists():
-            shutil.move("extracted_spirometry_table.csv", spirometry_csv_path)
+        print("Step 1: Extracting spirometry data from PDF...")
+        spirometry_csv_path = extract_spirometry_table_from_pdf(
+            spirometry_pdf_path, output_dir=str(self.data_dir)
+        )
+        print(f"Spirometry data saved to: {spirometry_csv_path}")
 
         # Step 2: Process Pnoe data
+        print("Step 2: Processing Pnoe data...")
         df = self.process_pnoe_data(pnoe_csv_path)
 
         # Step 3: Generate all graphs
+        print("Step 3: Generating graphs...")
         graphs_generated = self.generate_graphs(df)
 
         # Create graph dictionary with base64 encoded images
@@ -370,13 +369,20 @@ class ReportGeneratorService:
             graphs_dict["body_fat_percent"] = body_fat_b64
 
         # Generate spirometry chart
-        spirometry_df = pd.read_csv(spirometry_csv_path)
-        spirometry_chart_b64 = self.graph_generator.generate_spirometry_chart(
-            spirometry_df, save_as_base64=True
-        )
-        graphs_dict["spirometry_chart"] = spirometry_chart_b64
+        print("Step 4: Generating spirometry chart...")
+        try:
+            spirometry_df = pd.read_csv(spirometry_csv_path)
+            print(f"Spirometry data loaded: {len(spirometry_df)} rows")
+            spirometry_chart_b64 = self.graph_generator.generate_spirometry_chart(
+                spirometry_df, save_as_base64=True
+            )
+            graphs_dict["spirometry_chart"] = spirometry_chart_b64
+        except Exception as e:
+            print(f"Warning: Could not generate spirometry chart: {e}")
+            graphs_dict["spirometry_chart"] = ""
 
-        # Step 4: Generate context for all pages
+        # Step 5: Generate context for all pages
+        print("Step 5: Generating page contexts...")
         self.context_generator.load_data(
             pnoe_csv_path, str(spirometry_csv_path), seca_excel_path
         )
@@ -401,7 +407,7 @@ class ReportGeneratorService:
 
         report_path = self.reports_dir / output_filename
         print(f"Generating PDF report at {report_path}")
-        self.html_to_pdf(html_content, str(report_path))
+        await self.html_to_pdf(html_content, str(report_path))
 
         return {
             "report_path": str(report_path),