120 lines
4.1 KiB
Python
120 lines
4.1 KiB
Python
# processors/checks.py
|
|
|
|
import os
|
|
import re
|
|
|
|
from core.constants import IMAGE_EXTENSIONS, TRASH_FILES
|
|
from core.result import StepResult
|
|
|
|
|
|
def check_trash(work_dir: str) -> StepResult:
|
|
"""Detecta ficheros y directorios de basura presentes en el archivo."""
|
|
found = []
|
|
for root, dirs, files in os.walk(work_dir):
|
|
for name in files:
|
|
if name.lower() in TRASH_FILES:
|
|
found.append(os.path.relpath(os.path.join(root, name), work_dir))
|
|
for name in dirs:
|
|
if name.lower() in TRASH_FILES:
|
|
found.append(os.path.relpath(os.path.join(root, name), work_dir) + "/")
|
|
|
|
warnings = [f"Basura detectada: {f}" for f in found]
|
|
return StepResult(step="check_trash", changed=False, warnings=warnings)
|
|
|
|
|
|
def _natural_sort_key(name: str):
|
|
parts = re.split(r"(\d+)", name)
|
|
return [int(p) if p.isdigit() else p.lower() for p in parts]
|
|
|
|
|
|
def check_page_numbering(work_dir: str) -> StepResult:
|
|
"""Detecta páginas mal numeradas: sin zero-padding, padding inconsistente, saltos."""
|
|
images = []
|
|
for root, _, files in os.walk(work_dir):
|
|
for f in files:
|
|
if os.path.splitext(f)[1].lower() in IMAGE_EXTENSIONS:
|
|
images.append(f)
|
|
|
|
images.sort(key=lambda f: _natural_sort_key(os.path.splitext(f)[0]))
|
|
total = len(images)
|
|
if total == 0:
|
|
return StepResult(step="check_page_numbering", changed=False)
|
|
|
|
warnings = []
|
|
|
|
# Extraer primer bloque numérico del stem de cada imagen
|
|
numeric_values = []
|
|
numeric_widths = []
|
|
for img in images:
|
|
stem = os.path.splitext(img)[0]
|
|
m = re.search(r"(\d+)", stem)
|
|
if m:
|
|
numeric_values.append(int(m.group(1)))
|
|
numeric_widths.append(len(m.group(1)))
|
|
else:
|
|
numeric_values.append(None)
|
|
numeric_widths.append(None)
|
|
|
|
has_numbers = [v for v in numeric_values if v is not None]
|
|
if not has_numbers:
|
|
return StepResult(step="check_page_numbering", changed=False)
|
|
|
|
# Comprobar zero-padding si hay >= 10 imágenes
|
|
if total >= 10:
|
|
required_width = len(str(total))
|
|
widths_set = set(w for w in numeric_widths if w is not None)
|
|
if len(widths_set) > 1:
|
|
warnings.append("Padding inconsistente entre páginas")
|
|
elif widths_set and min(widths_set) < required_width:
|
|
warnings.append(
|
|
f"Páginas no zero-padded: se necesita ancho {required_width}, "
|
|
f"encontrado {min(widths_set)}"
|
|
)
|
|
|
|
# Comprobar secuencia continua
|
|
sorted_values = sorted(v for v in numeric_values if v is not None)
|
|
if sorted_values:
|
|
first = sorted_values[0]
|
|
expected = list(range(first, first + len(sorted_values)))
|
|
if sorted_values != expected:
|
|
warnings.append("Páginas no secuenciales: hay saltos en la numeración")
|
|
|
|
return StepResult(step="check_page_numbering", changed=False, warnings=warnings)
|
|
|
|
|
|
def check_image_extensions(work_dir: str) -> StepResult:
|
|
"""Detecta mezcla de formatos de imagen en el archivo."""
|
|
ext_set = set()
|
|
for root, _, files in os.walk(work_dir):
|
|
for f in files:
|
|
ext = os.path.splitext(f)[1].lower()
|
|
if ext in IMAGE_EXTENSIONS:
|
|
# Normalizar .jpeg → .jpg
|
|
normalized = ".jpg" if ext == ".jpeg" else ext
|
|
ext_set.add(normalized)
|
|
|
|
warnings = []
|
|
if len(ext_set) > 1:
|
|
exts_str = ", ".join(sorted(ext_set))
|
|
warnings.append(f"Extensiones de imagen mezcladas: {exts_str}")
|
|
|
|
return StepResult(step="check_image_extensions", changed=False, warnings=warnings)
|
|
|
|
|
|
def check_comicinfo(work_dir: str) -> StepResult:
|
|
"""Detecta ausencia de ComicInfo.xml."""
|
|
warnings = []
|
|
found = False
|
|
for root, _, files in os.walk(work_dir):
|
|
for f in files:
|
|
if f.lower() == "comicinfo.xml":
|
|
found = True
|
|
break
|
|
if found:
|
|
break
|
|
|
|
if not found:
|
|
warnings.append("Falta ComicInfo.xml")
|
|
|
|
return StepResult(step="check_comicinfo", changed=False, warnings=warnings)
|