evita la extracció quan no es necesari

processors/checks.py

@@ -7,18 +7,21 @@ from core.constants import IMAGE_EXTENSIONS, TRASH_FILES
 from core.result import StepResult
 
 
-def check_trash(work_dir: str) -> StepResult:
+def check_trash(names: list[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) + "/")
+    reported = set()
+    for name in names:
+        parts = name.replace("\\", "/").rstrip("/").split("/")
+        for i, part in enumerate(parts):
+            if part.lower() in TRASH_FILES:
+                key = "/".join(parts[: i + 1])
+                if key not in reported:
+                    found.append(key)
+                    reported.add(key)
+                break
 
-    warnings = [f"Basura detectada: {f}" for f in found]
+    warnings = [f"Basura detectada: {f}" for f in sorted(found)]
     return StepResult(step="check_trash", changed=False, warnings=warnings)
 
 
@@ -27,15 +30,16 @@ def _natural_sort_key(name: str):
     return [int(p) if p.isdigit() else p.lower() for p in parts]
 
 
-def check_page_numbering(work_dir: str) -> StepResult:
+def check_page_numbering(names: list[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]))
+    images = sorted(
+        [
+            name.replace("\\", "/").rsplit("/", 1)[-1]
+            for name in names
+            if os.path.splitext(name)[1].lower() in IMAGE_EXTENSIONS
+        ],
+        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)
@@ -82,16 +86,15 @@ def check_page_numbering(work_dir: str) -> StepResult:
     return StepResult(step="check_page_numbering", changed=False, warnings=warnings)
 
 
-def check_image_extensions(work_dir: str) -> StepResult:
+def check_image_extensions(names: list[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)
+    for name in names:
+        ext = os.path.splitext(name)[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:
@@ -101,19 +104,11 @@ def check_image_extensions(work_dir: str) -> StepResult:
     return StepResult(step="check_image_extensions", changed=False, warnings=warnings)
 
 
-def check_comicinfo(work_dir: str) -> StepResult:
+def check_comicinfo(names: list[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")
-
+    found = any(
+        name.replace("\\", "/").rsplit("/", 1)[-1].lower() == "comicinfo.xml"
+        for name in names
+    )
+    warnings = [] if found else ["Falta ComicInfo.xml"]
     return StepResult(step="check_comicinfo", changed=False, warnings=warnings)