feat: Agregar soporte OCR con Tesseract para PDFs escaneados

- Integrar Tesseract OCR para leer PDFs escaneados automáticamente
- Detectar automáticamente si el PDF tiene texto o requiere OCR
- Agregar servicio ocr_service.py con funciones de OCR
- Actualizar Dockerfile con tesseract-ocr, tesseract-ocr-spa y poppler-utils
- Agregar variables de configuración OCR (OCR_ENABLED, OCR_LANGUAGE, OCR_DPI, OCR_TIMEOUT)
- Crear endpoint de debug para ver texto extraído (/api/v1/debug/extract-text)
- Agregar scripts de instalación y prueba (install_ocr.ps1, test_ocr.py, debug_pdf.ps1)
- Documentación completa (OCR_SETUP.md, DOCKER_OCR.md, COMO_PROBAR.md)
- Actualizar docker-compose.yml con variables de entorno OCR
- Modificar pdf_text.py para usar OCR cuando sea necesario
- Actualizar requirements.txt con pytesseract, Pillow, pdf2image

app/services/pdf_text.py

@@ -1,9 +1,10 @@
-"""PDF text extraction service using PyMuPDF and pdfplumber."""
+"""PDF text extraction service using PyMuPDF, pdfplumber, and OCR."""
 import fitz  # PyMuPDF
 import pdfplumber
 import logging
 from typing import Tuple, Optional
 from io import BytesIO
+from .ocr_service import extract_text_with_ocr, is_pdf_scanned, OCRError
 
 logger = logging.getLogger(__name__)
 
@@ -82,16 +83,19 @@ def extract_text_with_pdfplumber(pdf_bytes: bytes) -> Tuple[str, int]:
         raise PDFExtractionError(f"pdfplumber extraction failed: {str(e)}")
 
 
-def extract_text_from_pdf(pdf_bytes: bytes) -> Tuple[str, int, str]:
+def extract_text_from_pdf(pdf_bytes: bytes, enable_ocr: bool = True, ocr_lang: str = "spa") -> Tuple[str, int, str]:
     """
     Extract text from PDF using available methods.
-    Tries PyMuPDF first, falls back to pdfplumber.
+    Tries PyMuPDF first, falls back to pdfplumber, and uses OCR for scanned PDFs.
     
     Args:
         pdf_bytes: PDF file content as bytes
+        enable_ocr: Whether to use OCR for scanned PDFs (default: True)
+        ocr_lang: Language for OCR - "spa" for Spanish, "eng" for English (default: "spa")
         
     Returns:
         Tuple of (extracted_text, page_count, method_used)
+        method_used can be: "pymupdf", "pdfplumber", "ocr"
         
     Raises:
         PDFExtractionError: If all extraction methods fail
@@ -99,14 +103,41 @@ def extract_text_from_pdf(pdf_bytes: bytes) -> Tuple[str, int, str]:
     # Try PyMuPDF first
     try:
         text, pages = extract_text_with_pymupdf(pdf_bytes)
-        return text, pages, "text"
+        
+        # Check if the PDF is scanned (no text content)
+        if enable_ocr and is_pdf_scanned(text):
+            logger.info("PDF appears to be scanned, attempting OCR extraction")
+            try:
+                ocr_text, ocr_pages = extract_text_with_ocr(pdf_bytes, lang=ocr_lang)
+                return ocr_text, ocr_pages, "ocr"
+            except OCRError as ocr_e:
+                logger.error(f"OCR failed: {str(ocr_e)}")
+                # Return the minimal text we got, if any
+                if text.strip():
+                    return text, pages, "pymupdf"
+                raise PDFExtractionError(f"PDF appears to be scanned and OCR failed: {str(ocr_e)}")
+        
+        return text, pages, "pymupdf"
     except PDFExtractionError as e:
         logger.warning(f"PyMuPDF failed, trying pdfplumber: {str(e)}")
     
     # Fallback to pdfplumber
     try:
         text, pages = extract_text_with_pdfplumber(pdf_bytes)
-        return text, pages, "text"
+        
+        # Check if the PDF is scanned
+        if enable_ocr and is_pdf_scanned(text):
+            logger.info("PDF appears to be scanned (pdfplumber), attempting OCR extraction")
+            try:
+                ocr_text, ocr_pages = extract_text_with_ocr(pdf_bytes, lang=ocr_lang)
+                return ocr_text, ocr_pages, "ocr"
+            except OCRError as ocr_e:
+                logger.error(f"OCR failed: {str(ocr_e)}")
+                if text.strip():
+                    return text, pages, "pdfplumber"
+                raise PDFExtractionError(f"PDF appears to be scanned and OCR failed: {str(ocr_e)}")
+        
+        return text, pages, "pdfplumber"
     except PDFExtractionError as e:
         logger.error(f"All extraction methods failed: {str(e)}")
         raise PDFExtractionError("Failed to extract text from PDF using all available methods")