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

find_number_of_columns_in_document: simplify

Browse source
This commit is contained in:
Robert Sachunsky 2025-10-24 01:43:41 +02:00
parent b2a79cc6ed
commit acee4c1bfe
1 changed files with 10 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

20
src/eynollah/utils/__init__.py
View file

@ -1551,23 +1551,23 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, tables,
(x_max_head>=.84*region_pre_p.shape[1])] (x_max_head>=.84*region_pre_p.shape[1])]
cy_seps_splitters = np.append(cy_seps_splitters, cy_seps_splitters_head) cy_seps_splitters = np.append(cy_seps_splitters, cy_seps_splitters_head)
cy_seps_splitters = np.sort(cy_seps_splitters) cy_seps_splitters = np.sort(cy_seps_splitters).astype(int)
splitter_y_new = [0] + list(cy_seps_splitters) + [region_pre_p.shape[0]] splitter_y_new = [0] + list(cy_seps_splitters) + [region_pre_p.shape[0]]
splitter_y_new_diff = np.diff(splitter_y_new) / float(region_pre_p.shape[0]) * 100 big_part = 22 * region_pre_p.shape[0] // 100 # percent height
args_big_parts=np.arange(len(splitter_y_new_diff))[ splitter_y_new_diff>22 ]
regions_without_separators=return_regions_without_separators(region_pre_p) regions_without_separators=return_regions_without_separators(region_pre_p)
length_y_threshold=regions_without_separators.shape[0]/4.0
num_col_fin=0 num_col_fin=0
peaks_neg_fin_fin=[] peaks_neg_fin_fin=[]
for itiles in args_big_parts: num_big_parts = 0
regions_without_separators_tile=regions_without_separators[int(splitter_y_new[itiles]): for top, bot in pairwise(splitter_y_new):
int(splitter_y_new[itiles+1]),:] if bot - top < big_part:
continue
num_big_parts += 1
try: try:
num_col, peaks_neg_fin = find_num_col(regions_without_separators_tile, num_col, peaks_neg_fin = find_num_col(regions_without_separators[top: bot],
num_col_classifier, tables, multiplier=7.0) num_col_classifier, tables, multiplier=7.0)
#print("big part %d:%d has %d columns" % (top, bot, num_col), peaks_neg_fin)
except: except:
num_col = 0 num_col = 0
peaks_neg_fin = [] peaks_neg_fin = []
@ -1575,7 +1575,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, tables,
num_col_fin=num_col num_col_fin=num_col
peaks_neg_fin_fin=peaks_neg_fin peaks_neg_fin_fin=peaks_neg_fin
if len(args_big_parts)==1 and (len(peaks_neg_fin_fin)+1)<num_col_classifier: if num_big_parts == 1 and len(peaks_neg_fin_fin) + 1 < num_col_classifier:
peaks_neg_fin=find_num_col_by_vertical_lines(vertical) peaks_neg_fin=find_num_col_by_vertical_lines(vertical)
peaks_neg_fin=peaks_neg_fin[peaks_neg_fin>=500] peaks_neg_fin=peaks_neg_fin[peaks_neg_fin>=500]
peaks_neg_fin=peaks_neg_fin[peaks_neg_fin<=(vertical.shape[1]-500)] peaks_neg_fin=peaks_neg_fin[peaks_neg_fin<=(vertical.shape[1]-500)]