From b9030f5203d063f22c447c0b0e788dbbc5041962 Mon Sep 17 00:00:00 2001 From: cneud <952378+cneud@users.noreply.github.com> Date: Tue, 25 Mar 2025 21:42:49 +0100 Subject: [PATCH] replace multi-step list initialization with list literal --- src/eynollah/utils/__init__.py | 21 +++++++-------------- src/eynollah/utils/separate_lines.py | 6 ++---- 2 files changed, 9 insertions(+), 18 deletions(-) diff --git a/src/eynollah/utils/__init__.py b/src/eynollah/utils/__init__.py index b1d5918..6ba445d 100644 --- a/src/eynollah/utils/__init__.py +++ b/src/eynollah/utils/__init__.py @@ -135,8 +135,7 @@ def return_x_start_end_mothers_childs_and_type_of_reading_order( min_ys=np.min(y_sep) max_ys=np.max(y_sep) - y_mains=[] - y_mains.append(min_ys) + y_mains= [min_ys] y_mains_sep_ohne_grenzen=[] for ii in range(len(new_main_sep_y)): @@ -492,8 +491,7 @@ def find_num_col(regions_without_separators, num_col_classifier, tables, multipl # print(forest[np.argmin(z[forest]) ] ) if not isNaN(forest[np.argmin(z[forest])]): peaks_neg_true.append(forest[np.argmin(z[forest])]) - forest = [] - forest.append(peaks_neg_fin[i + 1]) + forest = [peaks_neg_fin[i + 1]] if i == (len(peaks_neg_fin) - 1): # print(print(forest[np.argmin(z[forest]) ] )) if not isNaN(forest[np.argmin(z[forest])]): @@ -661,8 +659,7 @@ def find_num_col_only_image(regions_without_separators, multiplier=3.8): # print(forest[np.argmin(z[forest]) ] ) if not isNaN(forest[np.argmin(z[forest])]): peaks_neg_true.append(forest[np.argmin(z[forest])]) - forest = [] - forest.append(peaks_neg_fin[i + 1]) + forest = [peaks_neg_fin[i + 1]] if i == (len(peaks_neg_fin) - 1): # print(print(forest[np.argmin(z[forest]) ] )) if not isNaN(forest[np.argmin(z[forest])]): @@ -1219,8 +1216,7 @@ def order_of_regions(textline_mask, contours_main, contours_header, y_ref): y_max_header = np.array([np.max(contours_header[j][:, 0, 1]) for j in range(len(contours_header))]) # print(cy_main,'mainy') - peaks_neg_new = [] - peaks_neg_new.append(0 + y_ref) + peaks_neg_new = [0 + y_ref] for iii in range(len(peaks_neg)): peaks_neg_new.append(peaks_neg[iii] + y_ref) peaks_neg_new.append(textline_mask.shape[0] + y_ref) @@ -1388,8 +1384,7 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new( return img_p_in[:,:,0], special_separators def return_points_with_boundies(peaks_neg_fin, first_point, last_point): - peaks_neg_tot = [] - peaks_neg_tot.append(first_point) + peaks_neg_tot = [first_point] for ii in range(len(peaks_neg_fin)): peaks_neg_tot.append(peaks_neg_fin[ii]) peaks_neg_tot.append(last_point) @@ -1571,8 +1566,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, tables, args_cy_splitter=np.argsort(cy_main_splitters) cy_main_splitters_sort=cy_main_splitters[args_cy_splitter] - splitter_y_new=[] - splitter_y_new.append(0) + splitter_y_new= [0] for i in range(len(cy_main_splitters_sort)): splitter_y_new.append( cy_main_splitters_sort[i] ) splitter_y_new.append(region_pre_p.shape[0]) @@ -1646,8 +1640,7 @@ def return_boxes_of_images_by_order_of_reading_new( num_col, peaks_neg_fin = find_num_col( regions_without_separators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),:], num_col_classifier, tables, multiplier=3.) - peaks_neg_fin_early=[] - peaks_neg_fin_early.append(0) + peaks_neg_fin_early= [0] #print(peaks_neg_fin,'peaks_neg_fin') for p_n in peaks_neg_fin: peaks_neg_fin_early.append(p_n) diff --git a/src/eynollah/utils/separate_lines.py b/src/eynollah/utils/separate_lines.py index af83105..26e1ebe 100644 --- a/src/eynollah/utils/separate_lines.py +++ b/src/eynollah/utils/separate_lines.py @@ -1180,8 +1180,7 @@ def separate_lines_new_inside_tiles(img_path, thetha): # print(forest[np.argmin(z[forest]) ] ) if not np.isnan(forest[np.argmin(z[forest])]): peaks_neg_true.append(forest[np.argmin(z[forest])]) - forest = [] - forest.append(peaks_neg[i + 1]) + forest = [peaks_neg[i + 1]] if i == (len(peaks_neg) - 1): # print(print(forest[np.argmin(z[forest]) ] )) if not np.isnan(forest[np.argmin(z[forest])]): @@ -1203,8 +1202,7 @@ def separate_lines_new_inside_tiles(img_path, thetha): # print(forest[np.argmin(z[forest]) ] ) if not np.isnan(forest[np.argmax(z[forest])]): peaks_pos_true.append(forest[np.argmax(z[forest])]) - forest = [] - forest.append(peaks[i + 1]) + forest = [peaks[i + 1]] if i == (len(peaks) - 1): # print(print(forest[np.argmin(z[forest]) ] )) if not np.isnan(forest[np.argmax(z[forest])]):