qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-11-04 11:44:15 +01:00
Code Issues Projects Releases Wiki Activity

The text region coordinates are now correctly written into the XML output when using the skip layout and reading order option

Browse source
This commit is contained in:
vahidrezanezhad 2025-05-07 14:04:01 +02:00
parent 83211ae684
commit 21ec4fbfb5
2 changed files with 21 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/eynollah/eynollah.py
View file

@ -4333,7 +4333,7 @@ class Eynollah:
cont_page, page_coord, order_text_new, id_of_texts_tot, cont_page, page_coord, order_text_new, id_of_texts_tot,
all_found_textline_polygons, page_coord, polygons_of_images, polygons_of_marginals, all_found_textline_polygons, page_coord, polygons_of_images, polygons_of_marginals,
all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals,
cont_page, polygons_lines_xml, contours_tables, ocr_all_textlines, conf_contours_textregions) cont_page, polygons_lines_xml, contours_tables, ocr_all_textlines, conf_contours_textregions, self.skip_layout_and_reading_order)
return pcgts return pcgts
#print("text region early -1 in %.1fs", time.time() - t0) #print("text region early -1 in %.1fs", time.time() - t0)

16
src/eynollah/writer.py
View file

@ -168,7 +168,7 @@ class EynollahXmlWriter():
with open(self.output_filename, 'w') as f: with open(self.output_filename, 'w') as f:
f.write(to_xml(pcgts)) f.write(to_xml(pcgts))
def build_pagexml_no_full_layout(self, found_polygons_text_region, page_coord, order_of_texts, id_of_texts, all_found_textline_polygons, all_box_coord, found_polygons_text_region_img, found_polygons_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_to_be_written_in_xml, found_polygons_tables, ocr_all_textlines, conf_contours_textregion): def build_pagexml_no_full_layout(self, found_polygons_text_region, page_coord, order_of_texts, id_of_texts, all_found_textline_polygons, all_box_coord, found_polygons_text_region_img, found_polygons_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_to_be_written_in_xml, found_polygons_tables, ocr_all_textlines, conf_contours_textregion, skip_layout_reading_order=False):
self.logger.debug('enter build_pagexml_no_full_layout') self.logger.debug('enter build_pagexml_no_full_layout')
# create the file structure # create the file structure
@ -184,7 +184,7 @@ class EynollahXmlWriter():
for mm in range(len(found_polygons_text_region)): for mm in range(len(found_polygons_text_region)):
textregion = TextRegionType(id=counter.next_region_id, type_='paragraph', textregion = TextRegionType(id=counter.next_region_id, type_='paragraph',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord), conf=conf_contours_textregion[mm]), Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord, skip_layout_reading_order), conf=conf_contours_textregion[mm]),
) )
#textregion.set_conf(conf_contours_textregion[mm]) #textregion.set_conf(conf_contours_textregion[mm])
page.add_TextRegion(textregion) page.add_TextRegion(textregion)
@ -303,10 +303,20 @@ class EynollahXmlWriter():
return pcgts return pcgts
def calculate_polygon_coords(self, contour, page_coord): def calculate_polygon_coords(self, contour, page_coord, skip_layout_reading_order=False):
self.logger.debug('enter calculate_polygon_coords') self.logger.debug('enter calculate_polygon_coords')
coords = '' coords = ''
for value_bbox in contour: for value_bbox in contour:
if skip_layout_reading_order:
if len(value_bbox) == 2:
coords += str(int((value_bbox[0]) / self.scale_x))
coords += ','
coords += str(int((value_bbox[1]) / self.scale_y))
else:
coords += str(int((value_bbox[0][0]) / self.scale_x))
coords += ','
coords += str(int((value_bbox[0][1]) / self.scale_y))
else:
if len(value_bbox) == 2: if len(value_bbox) == 2:
coords += str(int((value_bbox[0] + page_coord[2]) / self.scale_x)) coords += str(int((value_bbox[0] + page_coord[2]) / self.scale_x))
coords += ',' coords += ','