qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-08 11:49:55 +02:00
Code Issues Projects Releases Wiki Activity

Merge remote-tracking branch 'vahidrezanezhad/main' into main

Browse source
This commit is contained in:
Konstantin Baierer 2021-07-01 15:11:50 +02:00
commit 6b810eb682
2 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
qurator/eynollah/eynollah.py
View file

@ -2007,10 +2007,10 @@ class Eynollah:
if self.full_layout: if self.full_layout:
if np.abs(slope_deskew) >= SLOPE_THRESHOLD: if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
contours_only_text_parent_d_ordered = list(np.array(contours_only_text_parent_d_ordered)[index_by_text_par_con]) contours_only_text_parent_d_ordered = list(np.array(contours_only_text_parent_d_ordered)[index_by_text_par_con])
text_regions_p, contours_only_text_parent, contours_only_text_parent_h, all_box_coord, all_box_coord_h, all_found_texline_polygons, all_found_texline_polygons_h, slopes, _, contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered = check_any_text_region_in_model_one_is_main_or_header(text_regions_p, regions_fully, contours_only_text_parent, all_box_coord, all_found_texline_polygons, slopes, contours_only_text_parent_d_ordered) text_regions_p, contours_only_text_parent, contours_only_text_parent_h, all_box_coord, all_box_coord_h, all_found_texline_polygons, all_found_texline_polygons_h, slopes, slopes_h, contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered = check_any_text_region_in_model_one_is_main_or_header(text_regions_p, regions_fully, contours_only_text_parent, all_box_coord, all_found_texline_polygons, slopes, contours_only_text_parent_d_ordered)
else: else:
contours_only_text_parent_d_ordered = None contours_only_text_parent_d_ordered = None
text_regions_p, contours_only_text_parent, contours_only_text_parent_h, all_box_coord, all_box_coord_h, all_found_texline_polygons, all_found_texline_polygons_h, slopes, _, contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered = check_any_text_region_in_model_one_is_main_or_header(text_regions_p, regions_fully, contours_only_text_parent, all_box_coord, all_found_texline_polygons, slopes, contours_only_text_parent_d_ordered) text_regions_p, contours_only_text_parent, contours_only_text_parent_h, all_box_coord, all_box_coord_h, all_found_texline_polygons, all_found_texline_polygons_h, slopes, slopes_h, contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered = check_any_text_region_in_model_one_is_main_or_header(text_regions_p, regions_fully, contours_only_text_parent, all_box_coord, all_found_texline_polygons, slopes, contours_only_text_parent_d_ordered)
if self.plotter: if self.plotter:
self.plotter.save_plot_of_layout(text_regions_p, image_page) self.plotter.save_plot_of_layout(text_regions_p, image_page)
@ -2071,7 +2071,7 @@ class Eynollah:
else: else:
order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered, boxes_d, textline_mask_tot_d) order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered, boxes_d, textline_mask_tot_d)
pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_texline_polygons, all_found_texline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, polygons_of_tabels, polygons_of_drop_capitals, polygons_of_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_xml) pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_texline_polygons, all_found_texline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, polygons_of_tabels, polygons_of_drop_capitals, polygons_of_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_xml)
self.logger.info("Job done in %ss", str(time.time() - t0)) self.logger.info("Job done in %ss", str(time.time() - t0))
return pcgts return pcgts
else: else:

4
qurator/eynollah/writer.py
View file

@ -192,7 +192,7 @@ class EynollahXmlWriter():
return pcgts return pcgts
def build_pagexml_full_layout(self, found_polygons_text_region, found_polygons_text_region_h, page_coord, order_of_texts, id_of_texts, all_found_texline_polygons, all_found_texline_polygons_h, all_box_coord, all_box_coord_h, found_polygons_text_region_img, found_polygons_tables, found_polygons_drop_capitals, found_polygons_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_to_be_written_in_xml): def build_pagexml_full_layout(self, found_polygons_text_region, found_polygons_text_region_h, page_coord, order_of_texts, id_of_texts, all_found_texline_polygons, all_found_texline_polygons_h, all_box_coord, all_box_coord_h, found_polygons_text_region_img, found_polygons_tables, found_polygons_drop_capitals, found_polygons_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_to_be_written_in_xml):
self.logger.debug('enter build_pagexml_full_layout') self.logger.debug('enter build_pagexml_full_layout')
# create the file structure # create the file structure
@ -218,7 +218,7 @@ class EynollahXmlWriter():
TextEquiv=[TextEquivType(index=0, Unicode='')], TextEquiv=[TextEquivType(index=0, Unicode='')],
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region_h[mm], page_coord))) Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region_h[mm], page_coord)))
page.add_TextRegion(textregion) page.add_TextRegion(textregion)
self.serialize_lines_in_region(textregion, all_found_texline_polygons_h, mm, page_coord, all_box_coord_h, slopes, counter) self.serialize_lines_in_region(textregion, all_found_texline_polygons_h, mm, page_coord, all_box_coord_h, slopes_h, counter)
for mm in range(len(found_polygons_marginals)): for mm in range(len(found_polygons_marginals)):
marginal = TextRegionType(id=counter.next_region_id, type_='marginalia', marginal = TextRegionType(id=counter.next_region_id, type_='marginalia',