Automatic orientation issues detection and fix, experimental

copienator/commands/page_splitter.py

@@ -26,7 +26,8 @@ from copienator import (
     workspace_from_target,
 )
 from copienator.platform import launch_pdf_arranger
-from copienator.copy_errors import marked_copy_paths
+from copienator.copy_errors import marked_copy_paths, clear_copy_error
+from copienator.orientation import save_provenance, report_path
 
 # Keep new shortcuts available with older personal configuration files.
 PAGE_SPLITTER_KB = {
@@ -122,6 +123,7 @@ class PDFPreviewer:
         self.processing = False  # Flag to prevent multiple finish calls
         try:
             self.doc = pymupdf.open(self.pdf_path)
+            self.original_page_ids = {page.xref: index + 1 for index, page in enumerate(self.doc)}
         except (OSError, RuntimeError, ValueError) as e:
             self.failed = True
             self._temporary_directory.cleanup()
@@ -325,6 +327,7 @@ class PDFPreviewer:
             # Re-open the file from disk to reset changes (like moved pages)
             try:
                 self.doc = pymupdf.open(self.pdf_path)
+                self.original_page_ids = {page.xref: index + 1 for index, page in enumerate(self.doc)}
             except (OSError, RuntimeError, ValueError) as e:
                 messagebox.showerror("Error", f"Failed to reopen PDF file: {e}")
                 self.master.destroy()
@@ -446,7 +449,10 @@ class PDFPreviewer:
             self.split_pdf()
             self.reorder_pdfs()
             self.concate_files()
-            commit_processed_pdf(self.workspace, self.pdf_path, self.final_file)
+            output = commit_processed_pdf(self.workspace, self.pdf_path, self.final_file)
+            save_provenance(self.workspace, output, self.output_origins)
+            clear_copy_error(self.workspace, output, source='orientation')
+            report_path(self.workspace, output.stem).unlink(missing_ok=True)
         except Exception as exc:  # noqa: BLE001 - interactive boundary
             self.failed = True
             self.processing = False
@@ -505,8 +511,10 @@ class PDFPreviewer:
         print("Starting PDF processing...")
         self.clean_up_dir(self.split_dir)
 
+        self.fragment_origins = {}
         for i, settings in enumerate(self.page_settings):
             page = self.doc.load_page(i)
+            origin = getattr(self, 'original_page_ids', {}).get(page.xref, i + 1)
             line_x = settings['line_x']
             rotation_settings = settings['rotation']
             keep = settings['keep']
@@ -530,12 +538,15 @@ class PDFPreviewer:
                 boundaries = [left, *sorted({x for x in cuts if left < x < right}), right]
                 # Each side is a multi-page PDF, keeping its subpages together
                 # when the existing booklet ordering moves this side.
+                origins = []
                 with pymupdf.open() as output:
                     for x0, x1 in zip(boundaries, boundaries[1:]):
                         clip = pymupdf.Rect(x0, 0, x1, height)
                         target = output.new_page(width=clip.width, height=clip.height)
                         target.show_pdf_page(target.rect, self.doc, i, clip=clip)
+                        origins.append({'origin': origin, 'crop_points': list(clip)})
                     output.save(output_path)
+                self.fragment_origins[str(output_path)] = origins
 
         self.doc.close()
         print(f"\nProcessing complete. Files are in '{self.split_dir}' directory.")
@@ -550,6 +561,8 @@ class PDFPreviewer:
         def copy_side(source, destination):
             if os.path.isfile(source):
                 shutil.copy2(source, destination)
+                if hasattr(self, 'fragment_origins'):
+                    self.fragment_origins[str(destination)] = self.fragment_origins[str(source)]
 
         while i < len(ps):
             psk = ps[i]['keep']
@@ -630,7 +643,9 @@ class PDFPreviewer:
             key=natural_key
         )
 
+        self.output_origins = []
         for pdf in pdf_files:
+            self.output_origins.extend(getattr(self, 'fragment_origins', {}).get(str(pdf), []))
             reader = PdfReader(pdf)
             for page in reader.pages:
                 writer.add_page(page)