Add PyMuPDF fallback and comprehensive poppler packages for PDF processing

apt.txt

@@ -2,5 +2,8 @@ poppler-utils
 poppler-data
 libpoppler-dev
 libpoppler-cpp-dev
+libpoppler-glib-dev
+libpoppler-qt5-dev
 tesseract-ocr
 libzbar0
+ghostscript

pdf_comparator.py

@@ -16,6 +16,14 @@ from skimage.measure import label, regionprops
 from skimage.morphology import dilation, rectangle
 import gradio as gr
 
+# Alternative PDF processing
+try:
+    import fitz  # PyMuPDF
+    HAS_PYMUPDF = True
+except Exception:
+    fitz = None
+    HAS_PYMUPDF = False
+
 # Optional features
 try:
     import pytesseract
@@ -49,7 +57,7 @@ def _is_pdf(path: str) -> bool:
 
 def load_first_page(path: str, dpi: int = 300) -> Image.Image:
     if _is_pdf(path):
-        # Try multiple poppler paths
+        # Try pdf2image with multiple poppler paths first
         poppler_paths = ["/usr/bin", "/usr/local/bin", "/bin", None]
         
         for poppler_path in poppler_paths:
@@ -64,9 +72,25 @@ def load_first_page(path: str, dpi: int = 300) -> Image.Image:
                     
                 return imgs[0].convert("RGB")
             except Exception as e:
-                if poppler_path is None:  # Last attempt failed
-                    raise ValueError(f"Failed to convert PDF to image with all poppler paths. Last error: {str(e)}. Make sure poppler-utils is installed.")
+                if poppler_path is None:  # All pdf2image attempts failed
+                    break
                 continue  # Try next path
+        
+        # Fallback to PyMuPDF if pdf2image fails
+        if HAS_PYMUPDF:
+            try:
+                doc = fitz.open(path)
+                page = doc[0]  # First page
+                mat = fitz.Matrix(dpi/72, dpi/72)  # Scale factor for DPI
+                pix = page.get_pixmap(matrix=mat)
+                img_data = pix.tobytes("ppm")
+                img = Image.open(io.BytesIO(img_data))
+                doc.close()
+                return img.convert("RGB")
+            except Exception as e:
+                raise ValueError(f"Failed to convert PDF with both pdf2image and PyMuPDF. pdf2image error: poppler not found. PyMuPDF error: {str(e)}")
+        else:
+            raise ValueError(f"Failed to convert PDF to image with all poppler paths. Last error: poppler not found. PyMuPDF not available as fallback.")
                 
         raise ValueError(f"No pages in PDF: {path}")
     return Image.open(path).convert("RGB")

requirements.txt

@@ -15,3 +15,4 @@ pandas==2.0.3
 reportlab==4.0.4
 regex==2023.10.3
 gradio==4.44.1
+PyMuPDF==1.23.8