Update core.py
Browse files
core.py
CHANGED
|
@@ -1,99 +1,167 @@
|
|
| 1 |
-
# Versión 1.
|
| 2 |
import os
|
| 3 |
from pypdf import PdfWriter, PdfReader
|
|
|
|
| 4 |
from config import TEMP_DIR
|
| 5 |
import uuid
|
| 6 |
|
| 7 |
class PDFEngine:
|
| 8 |
-
|
| 9 |
-
Motor de procesamiento de PDFs.
|
| 10 |
-
Principio SRP: Solo se encarga de manipular bytes y archivos.
|
| 11 |
-
"""
|
| 12 |
-
|
| 13 |
@staticmethod
|
| 14 |
def _get_output_path(filename: str) -> str:
|
| 15 |
-
"""Genera una ruta única para evitar colisiones."""
|
| 16 |
unique_name = f"{uuid.uuid4().hex[:8]}_{filename}"
|
| 17 |
return os.path.join(TEMP_DIR, unique_name)
|
| 18 |
|
| 19 |
-
def
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"""
|
| 21 |
-
Une
|
| 22 |
Args:
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
Ruta del archivo generado.
|
| 26 |
"""
|
| 27 |
if not file_paths:
|
| 28 |
-
raise ValueError("No
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
merger = PdfWriter()
|
| 31 |
-
|
| 32 |
try:
|
| 33 |
-
for path in
|
| 34 |
merger.append(path)
|
| 35 |
|
| 36 |
-
output_path = self._get_output_path("
|
| 37 |
with open(output_path, "wb") as f:
|
| 38 |
merger.write(f)
|
| 39 |
-
|
| 40 |
return output_path
|
| 41 |
except Exception as e:
|
| 42 |
-
raise RuntimeError(f"Error al unir
|
| 43 |
finally:
|
| 44 |
merger.close()
|
| 45 |
|
| 46 |
-
def
|
| 47 |
"""
|
| 48 |
-
|
| 49 |
-
Nota: Devuelve una lista de archivos.
|
| 50 |
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
if not file_path:
|
| 52 |
raise ValueError("Archivo no proporcionado.")
|
| 53 |
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
|
|
|
|
|
|
| 70 |
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
|
| 75 |
def protect_pdf(self, file_path: str, password: str) -> str:
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
if not file_path or not password:
|
| 80 |
-
raise ValueError("Faltan
|
| 81 |
-
|
| 82 |
try:
|
| 83 |
reader = PdfReader(file_path)
|
| 84 |
writer = PdfWriter()
|
| 85 |
-
|
| 86 |
-
# Copiar todas las páginas
|
| 87 |
-
for page in reader.pages:
|
| 88 |
-
writer.add_page(page)
|
| 89 |
-
|
| 90 |
-
# Encriptar
|
| 91 |
writer.encrypt(password)
|
| 92 |
-
|
| 93 |
output_path = self._get_output_path("protegido.pdf")
|
| 94 |
-
with open(output_path, "wb") as f:
|
| 95 |
-
writer.write(f)
|
| 96 |
-
|
| 97 |
return output_path
|
| 98 |
-
except Exception as e:
|
| 99 |
-
raise RuntimeError(f"Error al proteger PDF: {str(e)}")
|
|
|
|
| 1 |
+
# Versión 1.1: Soporte para rangos, reordenamiento y previsualización (poppler)
|
| 2 |
import os
|
| 3 |
from pypdf import PdfWriter, PdfReader
|
| 4 |
+
from pdf2image import convert_from_path
|
| 5 |
from config import TEMP_DIR
|
| 6 |
import uuid
|
| 7 |
|
| 8 |
class PDFEngine:
|
| 9 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
@staticmethod
|
| 11 |
def _get_output_path(filename: str) -> str:
|
|
|
|
| 12 |
unique_name = f"{uuid.uuid4().hex[:8]}_{filename}"
|
| 13 |
return os.path.join(TEMP_DIR, unique_name)
|
| 14 |
|
| 15 |
+
def get_pdf_info(self, file_path: str) -> dict:
|
| 16 |
+
"""Obtiene metadatos básicos del PDF."""
|
| 17 |
+
try:
|
| 18 |
+
reader = PdfReader(file_path)
|
| 19 |
+
return {"pages": len(reader.pages), "name": os.path.basename(file_path)}
|
| 20 |
+
except Exception:
|
| 21 |
+
return {"pages": 0, "name": "Error"}
|
| 22 |
+
|
| 23 |
+
def generate_preview(self, file_path: str, page_number: int) -> str:
|
| 24 |
+
"""
|
| 25 |
+
Genera una imagen de una página específica.
|
| 26 |
+
Args:
|
| 27 |
+
page_number: Número de página (1-based index para el usuario)
|
| 28 |
+
"""
|
| 29 |
+
try:
|
| 30 |
+
# Convertir solo la página solicitada (first_page es 1-based, last_page es 1-based)
|
| 31 |
+
images = convert_from_path(
|
| 32 |
+
file_path,
|
| 33 |
+
first_page=page_number,
|
| 34 |
+
last_page=page_number,
|
| 35 |
+
size=(None, 400) # Altura fija para eficiencia
|
| 36 |
+
)
|
| 37 |
+
if images:
|
| 38 |
+
output_path = self._get_output_path(f"preview_pg{page_number}.jpg")
|
| 39 |
+
images[0].save(output_path, "JPEG")
|
| 40 |
+
return output_path
|
| 41 |
+
return None
|
| 42 |
+
except Exception as e:
|
| 43 |
+
print(f"Error generando preview: {e}")
|
| 44 |
+
return None
|
| 45 |
+
|
| 46 |
+
def merge_pdfs(self, file_paths: list, order_indices: list = None) -> str:
|
| 47 |
"""
|
| 48 |
+
Une PDFs permitiendo reordenamiento.
|
| 49 |
Args:
|
| 50 |
+
order_indices: Lista de enteros indicando el orden (ej: [2, 0, 1]).
|
| 51 |
+
Si es None, usa el orden de llegada.
|
|
|
|
| 52 |
"""
|
| 53 |
if not file_paths:
|
| 54 |
+
raise ValueError("No hay archivos para unir.")
|
| 55 |
+
|
| 56 |
+
# Reordenar si se especifican índices
|
| 57 |
+
ordered_paths = []
|
| 58 |
+
if order_indices:
|
| 59 |
+
try:
|
| 60 |
+
# Validar que los índices estén dentro del rango
|
| 61 |
+
if len(order_indices) != len(file_paths):
|
| 62 |
+
# Fallback si las longitudes no coinciden
|
| 63 |
+
ordered_paths = file_paths
|
| 64 |
+
else:
|
| 65 |
+
for idx in order_indices:
|
| 66 |
+
ordered_paths.append(file_paths[int(idx)])
|
| 67 |
+
except (ValueError, IndexError):
|
| 68 |
+
# Si el usuario mete datos inválidos, usamos orden original
|
| 69 |
+
ordered_paths = file_paths
|
| 70 |
+
else:
|
| 71 |
+
ordered_paths = file_paths
|
| 72 |
|
| 73 |
merger = PdfWriter()
|
|
|
|
| 74 |
try:
|
| 75 |
+
for path in ordered_paths:
|
| 76 |
merger.append(path)
|
| 77 |
|
| 78 |
+
output_path = self._get_output_path("unido_ordenado.pdf")
|
| 79 |
with open(output_path, "wb") as f:
|
| 80 |
merger.write(f)
|
|
|
|
| 81 |
return output_path
|
| 82 |
except Exception as e:
|
| 83 |
+
raise RuntimeError(f"Error al unir: {str(e)}")
|
| 84 |
finally:
|
| 85 |
merger.close()
|
| 86 |
|
| 87 |
+
def parse_range_string(self, range_str: str, max_pages: int) -> list:
|
| 88 |
"""
|
| 89 |
+
Convierte "1-3, 5" en [0, 1, 2, 4] (0-based indices).
|
|
|
|
| 90 |
"""
|
| 91 |
+
pages = set()
|
| 92 |
+
parts = range_str.split(',')
|
| 93 |
+
|
| 94 |
+
for part in parts:
|
| 95 |
+
part = part.strip()
|
| 96 |
+
if '-' in part:
|
| 97 |
+
try:
|
| 98 |
+
start, end = map(int, part.split('-'))
|
| 99 |
+
# Ajustar a rango válido y convertir a 0-index
|
| 100 |
+
start = max(1, start)
|
| 101 |
+
end = min(max_pages, end)
|
| 102 |
+
if start <= end:
|
| 103 |
+
for p in range(start - 1, end):
|
| 104 |
+
pages.add(p)
|
| 105 |
+
except ValueError:
|
| 106 |
+
continue
|
| 107 |
+
else:
|
| 108 |
+
try:
|
| 109 |
+
p = int(part)
|
| 110 |
+
if 1 <= p <= max_pages:
|
| 111 |
+
pages.add(p - 1)
|
| 112 |
+
except ValueError:
|
| 113 |
+
continue
|
| 114 |
+
|
| 115 |
+
return sorted(list(pages))
|
| 116 |
+
|
| 117 |
+
def split_pdf_custom(self, file_path: str, range_str: str) -> list:
|
| 118 |
+
"""Divide basándose en un rango string."""
|
| 119 |
if not file_path:
|
| 120 |
raise ValueError("Archivo no proporcionado.")
|
| 121 |
|
| 122 |
+
reader = PdfReader(file_path)
|
| 123 |
+
total_pages = len(reader.pages)
|
| 124 |
+
|
| 125 |
+
# Obtener índices (0-based) a extraer
|
| 126 |
+
selected_indices = self.parse_range_string(range_str, total_pages)
|
| 127 |
+
|
| 128 |
+
if not selected_indices:
|
| 129 |
+
raise ValueError("El rango proporcionado no es válido o está vacío.")
|
| 130 |
|
| 131 |
+
output_files = []
|
| 132 |
+
base_name = os.path.basename(file_path).replace(".pdf", "")
|
| 133 |
+
|
| 134 |
+
# Agrupar páginas consecutivas podría ser una opción,
|
| 135 |
+
# pero la herramienta dice "Dividir", así que generamos un PDF por selección
|
| 136 |
+
# o un solo PDF con la selección?
|
| 137 |
+
# Interpretación estándar: "Extraer páginas" -> Crea un nuevo PDF con SOLO esas páginas
|
| 138 |
+
# Interpretación "Split": Rompe en archivos.
|
| 139 |
+
# Asumiré: Crear UN nuevo archivo con las páginas seleccionadas (Extract).
|
| 140 |
+
|
| 141 |
+
writer = PdfWriter()
|
| 142 |
+
for idx in selected_indices:
|
| 143 |
+
writer.add_page(reader.pages[idx])
|
| 144 |
|
| 145 |
+
out_name = f"{base_name}_extracto.pdf"
|
| 146 |
+
output_path = self._get_output_path(out_name)
|
| 147 |
+
|
| 148 |
+
with open(output_path, "wb") as f:
|
| 149 |
+
writer.write(f)
|
| 150 |
+
|
| 151 |
+
return output_path # Retornamos str, no lista, para esta variante de extracción.
|
| 152 |
|
| 153 |
def protect_pdf(self, file_path: str, password: str) -> str:
|
| 154 |
+
# (Sin cambios respecto a v1.0, mantener código anterior)
|
| 155 |
+
# ... (copiar lógica previa) ...
|
| 156 |
+
# Por brevedad en la respuesta, asumo que mantienes el método protect_pdf de la v1.0
|
| 157 |
if not file_path or not password:
|
| 158 |
+
raise ValueError("Faltan datos")
|
|
|
|
| 159 |
try:
|
| 160 |
reader = PdfReader(file_path)
|
| 161 |
writer = PdfWriter()
|
| 162 |
+
for page in reader.pages: writer.add_page(page)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 163 |
writer.encrypt(password)
|
|
|
|
| 164 |
output_path = self._get_output_path("protegido.pdf")
|
| 165 |
+
with open(output_path, "wb") as f: writer.write(f)
|
|
|
|
|
|
|
| 166 |
return output_path
|
| 167 |
+
except Exception as e: raise RuntimeError(f"Error: {e}")
|
|
|