From 2d35a0598d6164d9ccad9ef77d715db4250161c6 Mon Sep 17 00:00:00 2001 From: cneud <952378+cneud@users.noreply.github.com> Date: Thu, 30 Oct 2025 22:16:48 +0100 Subject: [PATCH] Revert "replace list declaration with list literal (faster)" This reverts commit 9733d575bfd2caa19df0465a0fac9e5f352303b8. --- src/eynollah/utils/__init__.py | 18 ++++++++++++------ src/eynollah/utils/separate_lines.py | 6 ++++-- 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/src/eynollah/utils/__init__.py b/src/eynollah/utils/__init__.py index 9cf30b0..d6c927b 100644 --- a/src/eynollah/utils/__init__.py +++ b/src/eynollah/utils/__init__.py @@ -151,7 +151,8 @@ 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= [min_ys] + y_mains=[] + y_mains.append(min_ys) y_mains_sep_ohne_grenzen=[] for ii in range(len(new_main_sep_y)): @@ -524,7 +525,8 @@ 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 = [peaks_neg_fin[i + 1]] + forest = [] + forest.append(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])]): @@ -692,7 +694,8 @@ 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 = [peaks_neg_fin[i + 1]] + forest = [] + forest.append(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])]): @@ -1343,7 +1346,8 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new( return img_p_in, special_separators def return_points_with_boundies(peaks_neg_fin, first_point, last_point): - peaks_neg_tot = [first_point] + peaks_neg_tot = [] + peaks_neg_tot.append(first_point) for ii in range(len(peaks_neg_fin)): peaks_neg_tot.append(peaks_neg_fin[ii]) peaks_neg_tot.append(last_point) @@ -1511,7 +1515,8 @@ 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= [0] + splitter_y_new=[] + splitter_y_new.append(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]) @@ -1587,7 +1592,8 @@ def return_boxes_of_images_by_order_of_reading_new( num_col, peaks_neg_fin = find_num_col( regions_without_separators[splitter_y_new[i]:splitter_y_new[i+1], :], num_col_classifier, tables, multiplier=3.) - peaks_neg_fin_early= [0] + peaks_neg_fin_early=[] + peaks_neg_fin_early.append(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 275bfac..22ef00d 100644 --- a/src/eynollah/utils/separate_lines.py +++ b/src/eynollah/utils/separate_lines.py @@ -1227,7 +1227,8 @@ def separate_lines_new_inside_tiles(img_path, thetha): if diff_peaks[i] > cut_off: if not np.isnan(forest[np.argmin(z[forest])]): peaks_neg_true.append(forest[np.argmin(z[forest])]) - forest = [peaks_neg[i + 1]] + forest = [] + forest.append(peaks_neg[i + 1]) if i == (len(peaks_neg) - 1): if not np.isnan(forest[np.argmin(z[forest])]): peaks_neg_true.append(forest[np.argmin(z[forest])]) @@ -1247,7 +1248,8 @@ def separate_lines_new_inside_tiles(img_path, thetha): if diff_peaks_pos[i] > cut_off: if not np.isnan(forest[np.argmax(z[forest])]): peaks_pos_true.append(forest[np.argmax(z[forest])]) - forest = [peaks[i + 1]] + forest = [] + forest.append(peaks[i + 1]) if i == (len(peaks) - 1): if not np.isnan(forest[np.argmax(z[forest])]): peaks_pos_true.append(forest[np.argmax(z[forest])])