Automatic orientation issues detection and fix, experimental

copienator/commands/crop_margins.py

@@ -10,6 +10,7 @@ import signal
 import shutil
 import tempfile
 import cv2
+import pymupdf
 from collections.abc import Sequence
 from pathlib import Path
 
@@ -17,6 +18,7 @@ from copienator.cli import CliError, ExitCode, execute, target_parser, workspace
 from copienator.crop_blank_margins import process_pdf
 from copienator.filesystem import staged_files
 from copienator.workspace import EvaluationWorkspace
+from copienator.orientation import load_provenance, save_provenance
 
 
 def selected_files(workspace: EvaluationWorkspace, target: Path) -> list[Path]:
@@ -112,6 +114,10 @@ def run(workspace: EvaluationWorkspace, target: Path, *, workers: int = 5) -> Ex
         raise CliError("Aucun PDF trouvé dans Copies.", ExitCode.INVALID_ARGUMENTS)
     # Prepare the whole batch before replacing any copy. A detection failure or
     # interruption leaves the working PDFs intact; commit errors roll back.
+    origins = {}
+    for source in files:
+        with pymupdf.open(source) as document:
+            origins[source.name] = load_provenance(workspace, source, len(document))
     with staged_files(workspace.copies_dir) as staging:
         records = process_copies(files, staging, workers)
         # Detect edits made while the batch was being analysed, before saving
@@ -129,6 +135,9 @@ def run(workspace: EvaluationWorkspace, target: Path, *, workers: int = 5) -> Ex
         (backup/"report.json").write_text(json.dumps(records, ensure_ascii=False, indent=2),
                                         encoding="utf-8")
         print(f"Sauvegarde des PDF non rognés : {originals}", flush=True)
+    for source in files:
+        if origins[source.name] is not None:
+            save_provenance(workspace, source, origins[source.name])
     cropped, mean_percentage, over_thirty = crop_statistics(records)
     print(f"Terminé : {cropped}/{len(records)} pages rognées ; "
           f"{len(files)} PDF remplacés dans Copies.", flush=True)