Merge remote-tracking branch 'origin/main' into xml-rfct

qurator/eynollah/eynollah.py

@@ -1666,10 +1666,17 @@ class Eynollah:
             cx_bigest_d_big, cy_biggest_d_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest_d])
             cx_bigest_d, cy_biggest_d, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent_d)
             try:
-                cx_bigest_d_last5 = cx_bigest_d[-5:]
+                if len(cx_bigest_d) >= 5:
-                cy_biggest_d_last5 = cy_biggest_d[-5:]
+                    cx_bigest_d_last5 = cx_bigest_d[-5:]
-                dists_d = [math.sqrt((cx_bigest_big[0] - cx_bigest_d_last5[j]) ** 2 + (cy_biggest_big[0] - cy_biggest_d_last5[j]) ** 2) for j in range(len(cy_biggest_d_last5))]
+                    cy_biggest_d_last5 = cy_biggest_d[-5:]
-                ind_largest = len(cx_bigest_d) -5 + np.argmin(dists_d)
+                    dists_d = [math.sqrt((cx_bigest_big[0] - cx_bigest_d_last5[j]) ** 2 + (cy_biggest_big[0] - cy_biggest_d_last5[j]) ** 2) for j in range(len(cy_biggest_d_last5))]
+                    ind_largest = len(cx_bigest_d) -5 + np.argmin(dists_d)
+                else:
+                    cx_bigest_d_last5 = cx_bigest_d[-len(cx_bigest_d):]
+                    cy_biggest_d_last5 = cy_biggest_d[-len(cx_bigest_d):]
+                    dists_d = [math.sqrt((cx_bigest_big[0]-cx_bigest_d_last5[j])**2 + (cy_biggest_big[0]-cy_biggest_d_last5[j])**2) for j in range(len(cy_biggest_d_last5))]
+                    ind_largest = len(cx_bigest_d) - len(cx_bigest_d) + np.argmin(dists_d)
+                    
                 cx_bigest_d_big[0] = cx_bigest_d[ind_largest]
                 cy_biggest_d_big[0] = cy_biggest_d[ind_largest]
             except Exception as why:

qurator/eynollah/utils/__init__.py

@@ -2116,13 +2116,17 @@ def return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_witho
                 x_start_by_order=[]
                 x_end_by_order=[]
                 if len(x_starting)>0:
+                    all_columns = np.array(range(len(peaks_neg_tot)-1))
                     columns_covered_by_lines_covered_more_than_2col=[]
                     
                     for dj in range(len(x_starting)):
-                        columns_covered_by_lines_covered_more_than_2col=columns_covered_by_lines_covered_more_than_2col+list(np.array(range(x_starting[dj],x_ending[dj])) )
+                        if set( list(np.array(range(x_starting[dj],x_ending[dj])) ) ) == set(all_columns):
+                            pass
+                        else:
+                            columns_covered_by_lines_covered_more_than_2col=columns_covered_by_lines_covered_more_than_2col+list(np.array(range(x_starting[dj],x_ending[dj])) )
                     columns_covered_by_lines_covered_more_than_2col=list(set(columns_covered_by_lines_covered_more_than_2col))
                     
-                    all_columns=np.array(range(len(peaks_neg_tot)-1))
+                    
                     
                     columns_not_covered=list( set(all_columns)-set(columns_covered_by_lines_covered_more_than_2col) )
                     

qurator/eynollah/utils/xml.py

@@ -46,16 +46,15 @@ def xml_reading_order(page, order_of_texts, id_of_texts, id_of_marginalia):
     region_order_sub = ET.SubElement(region_order, 'OrderedGroup')
     region_order_sub.set('id', "ro357564684568544579089")
     region_counter = EynollahIdCounter()
-    indexer_region = 0
     for idx_textregion, _ in enumerate(order_of_texts):
         name = ET.SubElement(region_order_sub, 'RegionRefIndexed')
-        name.set('index', str(indexer_region))
+        name.set('index', str(region_counter.get('region')))
         name.set('regionRef', region_counter.region_id(order_of_texts[idx_textregion]))
-        indexer_region += 1
     for id_marginal in id_of_marginalia:
         name = ET.SubElement(region_order_sub, 'RegionRefIndexed')
-        name.set('index', str(indexer_region))
+        name.set('index', str(region_counter.get('region')))
         name.set('regionRef', id_marginal)
+        region_counter.inc('region')
 
 def order_and_id_of_texts(found_polygons_text_region, found_polygons_text_region_h, matrix_of_orders, indexes_sorted, index_of_types, kind_of_texts, ref_point):
     indexes_sorted = np.array(indexes_sorted)