qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-10-26 23:34:13 +01:00
Code Issues Projects Releases Wiki Activity

return_boxes_of_images_by_order_of_reading_new: fix no-mother case

Browse source 
- when handling lines without mother,
  and biggest line already accounts for all columns,
  but some are too close to the top and therefore must be removed,
  avoid invalidating `biggest` index, causing `IndexError`
- remove try-catch (now unnecessary)
- array instead of list operations
This commit is contained in:
Robert Sachunsky 2025-10-20 16:47:35 +02:00
parent 7c3e418588
commit 0fc4b2535d
1 changed files with 29 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

62
src/eynollah/utils/__init__.py
View file

@ -1919,54 +1919,50 @@ def return_boxes_of_images_by_order_of_reading_new(
x_starting_all_between_nm_wc = x_starting[ind_all_lines_between_nm_wc] x_starting_all_between_nm_wc = x_starting[ind_all_lines_between_nm_wc]
x_ending_all_between_nm_wc = x_ending[ind_all_lines_between_nm_wc] x_ending_all_between_nm_wc = x_ending[ind_all_lines_between_nm_wc]
x_diff_all_between_nm_wc = x_ending_all_between_nm_wc - x_starting_all_between_nm_wc
if len(x_diff_all_between_nm_wc)>0:
biggest=np.argmax(x_diff_all_between_nm_wc)
columns_covered_by_mothers = set() columns_covered_by_mothers = set()
for dj in range(len(x_starting_all_between_nm_wc)): for dj in range(len(ind_all_lines_between_nm_wc)):
columns_covered_by_mothers.update( columns_covered_by_mothers.update(
range(x_starting_all_between_nm_wc[dj], range(x_starting_all_between_nm_wc[dj],
x_ending_all_between_nm_wc[dj])) x_ending_all_between_nm_wc[dj]))
child_columns = set(range(i_s_nc, x_end_biggest_column)) child_columns = set(range(i_s_nc, x_end_biggest_column))
columns_not_covered = list(child_columns - columns_covered_by_mothers) columns_not_covered = list(child_columns - columns_covered_by_mothers)
should_longest_line_be_extended=0 if len(ind_all_lines_between_nm_wc):
if (len(x_diff_all_between_nm_wc) > 0 and biggest = np.argmax(x_ending_all_between_nm_wc -
set(list(range(x_starting_all_between_nm_wc[biggest], x_starting_all_between_nm_wc)
x_ending_all_between_nm_wc[biggest])) + if columns_covered_by_mothers == set(
list(columns_not_covered)) != child_columns): range(x_starting_all_between_nm_wc[biggest],
should_longest_line_be_extended=1 x_ending_all_between_nm_wc[biggest])):
index_lines_so_close_to_top_separator = \ # biggest accounts for all columns alone,
np.arange(len(y_all_between_nm_wc))[(y_all_between_nm_wc>y_column_nc[i_c]) & # longest line should be extended
(y_all_between_nm_wc<=(y_column_nc[i_c]+500))] lines_so_close_to_top_separator = \
if len(index_lines_so_close_to_top_separator) > 0: ((y_all_between_nm_wc > y_column_nc[i_c]) &
indexes_remained_after_deleting_closed_lines= \ (y_all_between_nm_wc <= y_column_nc[i_c] + 500))
np.array(list(set(list(range(len(y_all_between_nm_wc)))) - if (np.count_nonzero(lines_so_close_to_top_separator) and
set(list(index_lines_so_close_to_top_separator)))) np.count_nonzero(lines_so_close_to_top_separator) <
if len(indexes_remained_after_deleting_closed_lines) > 0: len(ind_all_lines_between_nm_wc)):
y_all_between_nm_wc = \ y_all_between_nm_wc = \
y_all_between_nm_wc[indexes_remained_after_deleting_closed_lines] y_all_between_nm_wc[~lines_so_close_to_top_separator]
x_starting_all_between_nm_wc = \ x_starting_all_between_nm_wc = \
x_starting_all_between_nm_wc[indexes_remained_after_deleting_closed_lines] x_starting_all_between_nm_wc[~lines_so_close_to_top_separator]
x_ending_all_between_nm_wc = \ x_ending_all_between_nm_wc = \
x_ending_all_between_nm_wc[indexes_remained_after_deleting_closed_lines] x_ending_all_between_nm_wc[~lines_so_close_to_top_separator]
y_all_between_nm_wc = np.append(y_all_between_nm_wc, y_column_nc[i_c]) y_all_between_nm_wc = np.append(y_all_between_nm_wc, y_column_nc[i_c])
x_starting_all_between_nm_wc = np.append(x_starting_all_between_nm_wc, i_s_nc) x_starting_all_between_nm_wc = np.append(x_starting_all_between_nm_wc, i_s_nc)
x_ending_all_between_nm_wc = np.append(x_ending_all_between_nm_wc, x_end_biggest_column) x_ending_all_between_nm_wc = np.append(x_ending_all_between_nm_wc, x_end_biggest_column)
else:
if len(x_diff_all_between_nm_wc) > 0:
try:
y_all_between_nm_wc = np.append(y_all_between_nm_wc, y_column_nc[i_c]) y_all_between_nm_wc = np.append(y_all_between_nm_wc, y_column_nc[i_c])
x_starting_all_between_nm_wc = np.append(x_starting_all_between_nm_wc, x_starting_all_between_nm_wc[biggest]) x_starting_all_between_nm_wc = np.append(x_starting_all_between_nm_wc, x_starting_all_between_nm_wc[biggest])
x_ending_all_between_nm_wc = np.append(x_ending_all_between_nm_wc, x_ending_all_between_nm_wc[biggest]) x_ending_all_between_nm_wc = np.append(x_ending_all_between_nm_wc, x_ending_all_between_nm_wc[biggest])
except:
logger.exception("cannot append")
y_all_between_nm_wc = np.append(y_all_between_nm_wc, [y_column_nc[i_c]] * len(columns_not_covered)) if len(columns_not_covered):
x_starting_all_between_nm_wc = np.append(x_starting_all_between_nm_wc, np.array(columns_not_covered, int)) y_all_between_nm_wc = np.append(
x_ending_all_between_nm_wc = np.append(x_ending_all_between_nm_wc, np.array(columns_not_covered, int) + 1) y_all_between_nm_wc, [y_column_nc[i_c]] * len(columns_not_covered))
x_starting_all_between_nm_wc = np.append(
x_starting_all_between_nm_wc, np.array(columns_not_covered, int))
x_ending_all_between_nm_wc = np.append(
x_ending_all_between_nm_wc, np.array(columns_not_covered, int) + 1)
ind_args_between=np.arange(len(x_ending_all_between_nm_wc)) ind_args_between=np.arange(len(x_ending_all_between_nm_wc))
for column in range(int(i_s_nc), int(x_end_biggest_column)): for column in range(int(i_s_nc), int(x_end_biggest_column)):