Merge pull request #129 from qurator-spk/resolving_issue_106

fix OCR-D regression

qurator/eynollah/cli.py

@@ -198,9 +198,11 @@ def main(
         light_version=light_version,
         ignore_page_extraction=ignore_page_extraction,
     )
+    if dir_in:
         eynollah.run()
-    #pcgts = eynollah.run()
+    else:
-    ##eynollah.writer.write_pagexml(pcgts)
+        pcgts = eynollah.run()
+        eynollah.writer.write_pagexml(pcgts)
 
 if __name__ == "__main__":
     main()

qurator/eynollah/eynollah.py

@@ -3091,7 +3091,8 @@ class Eynollah:
 
                 pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_found_textline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, contours_tables, polygons_of_drop_capitals, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_xml)
                 self.logger.info("Job done in %.1fs", time.time() - t0)
-                ##return pcgts
+                if not self.dir_in:
+                    return pcgts
             else:
                 contours_only_text_parent_h = None
                 if np.abs(slope_deskew) < SLOPE_THRESHOLD:
@@ -3101,7 +3102,10 @@ class Eynollah:
                     order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h, boxes_d, textline_mask_tot_d)
                 pcgts = self.writer.build_pagexml_no_full_layout(txt_con_org, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_box_coord, polygons_of_images, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_xml, contours_tables)
                 self.logger.info("Job done in %.1fs", time.time() - t0)
-                ##return pcgts
+                if not self.dir_in:
+                    return pcgts
+            
+            if self.dir_in:
                 self.writer.write_pagexml(pcgts)
                 #self.logger.info("Job done in %.1fs", time.time() - t0)
         if self.dir_in:

qurator/eynollah/processor.py

@@ -42,7 +42,7 @@ class EynollahProcessor(Processor):
             page = pcgts.get_Page()
             # XXX loses DPI information
             # page_image, _, _ = self.workspace.image_from_page(page, page_id, feature_filter='binarized')
-            image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(url=page.imageFilename))).local_filename
+            image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(local_filename=page.imageFilename))).local_filename
             eynollah_kwargs = {
                 'dir_models': self.resolve_resource(self.parameter['models']),
                 'allow_enhancement': False,