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

remove unnecessary if

Browse source
This commit is contained in:
Konstantin Baierer 2021-03-02 15:26:05 +01:00
parent 24da879844
commit 20fcac6232
1 changed files with 33 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

68
qurator/eynollah/writer.py
View file

@ -152,14 +152,15 @@ class EynollahXmlWriter():
if len(found_polygons_text_region) > 0: if len(found_polygons_text_region) > 0:
xml_reading_order(page, order_of_texts, id_of_texts, found_polygons_marginals) xml_reading_order(page, order_of_texts, id_of_texts, found_polygons_marginals)
for mm in range(len(found_polygons_text_region)):
textregion = ET.SubElement(page, 'TextRegion') for mm in range(len(found_polygons_text_region)):
textregion.set('id', counter_textregions.next_region_id) textregion = ET.SubElement(page, 'TextRegion')
textregion.set('type', 'paragraph') textregion.set('id', counter_textregions.next_region_id)
coord_text = ET.SubElement(textregion, 'Coords') textregion.set('type', 'paragraph')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region, mm, page_coord)) coord_text = ET.SubElement(textregion, 'Coords')
id_indexer_l = self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, id_indexer_l) coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region, mm, page_coord))
add_textequiv(textregion) id_indexer_l = self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, id_indexer_l)
add_textequiv(textregion)
for idx_marginal, _ in enumerate(found_polygons_marginals): for idx_marginal, _ in enumerate(found_polygons_marginals):
marginal = ET.SubElement(page, 'TextRegion') marginal = ET.SubElement(page, 'TextRegion')
@ -201,36 +202,33 @@ class EynollahXmlWriter():
for _ in found_polygons_marginals: for _ in found_polygons_marginals:
id_of_marginalia.append(counter_marginals.next_region_id) id_of_marginalia.append(counter_marginals.next_region_id)
if len(found_polygons_text_region) > 0: xml_reading_order(page, order_of_texts, id_of_texts, found_polygons_marginals)
xml_reading_order(page, order_of_texts, id_of_texts, found_polygons_marginals) for mm in range(len(found_polygons_text_region)):
for mm in range(len(found_polygons_text_region)): textregion=ET.SubElement(page, 'TextRegion')
textregion=ET.SubElement(page, 'TextRegion') textregion.set('id', counter_textregions.next_region_id)
textregion.set('id', counter_textregions.next_region_id) textregion.set('type', 'paragraph')
textregion.set('type', 'paragraph') coord_text = ET.SubElement(textregion, 'Coords')
coord_text = ET.SubElement(textregion, 'Coords') coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region, mm, page_coord))
coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region, mm, page_coord)) id_indexer_l = self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, id_indexer_l)
id_indexer_l = self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, id_indexer_l) add_textequiv(textregion)
add_textequiv(textregion)
self.logger.debug('len(found_polygons_text_region_h) %s', len(found_polygons_text_region_h)) self.logger.debug('len(found_polygons_text_region_h) %s', len(found_polygons_text_region_h))
if len(found_polygons_text_region_h) > 0: for mm in range(len(found_polygons_text_region_h)):
for mm in range(len(found_polygons_text_region_h)): textregion=ET.SubElement(page, 'TextRegion')
textregion=ET.SubElement(page, 'TextRegion') textregion.set('id', counter_textregions.next_region_id)
textregion.set('id', counter_textregions.next_region_id) textregion.set('type','header')
textregion.set('type','header') coord_text = ET.SubElement(textregion, 'Coords')
coord_text = ET.SubElement(textregion, 'Coords') coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region_h, mm, page_coord))
coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region_h, mm, page_coord)) id_indexer_l = self.serialize_lines_in_region(textregion, all_found_texline_polygons_h, mm, page_coord, all_box_coord_h, slopes, id_indexer_l)
id_indexer_l = self.serialize_lines_in_region(textregion, all_found_texline_polygons_h, mm, page_coord, all_box_coord_h, slopes, id_indexer_l) add_textequiv(textregion)
add_textequiv(textregion)
if len(found_polygons_drop_capitals) > 0: for mm in range(len(found_polygons_drop_capitals)):
for mm in range(len(found_polygons_drop_capitals)): textregion=ET.SubElement(page, 'TextRegion')
textregion=ET.SubElement(page, 'TextRegion') textregion.set('id', counter_textregions.next_region_id)
textregion.set('id', counter_textregions.next_region_id) textregion.set('type', 'drop-capital')
textregion.set('type', 'drop-capital') coord_text = ET.SubElement(textregion, 'Coords')
coord_text = ET.SubElement(textregion, 'Coords') coord_text.set('points', self.calculate_polygon_coords(found_polygons_drop_capitals, mm, page_coord))
coord_text.set('points', self.calculate_polygon_coords(found_polygons_drop_capitals, mm, page_coord)) add_textequiv(textregion)
add_textequiv(textregion)
for mm in range(len(found_polygons_marginals)): for mm in range(len(found_polygons_marginals)):
marginal = ET.SubElement(page, 'TextRegion') marginal = ET.SubElement(page, 'TextRegion')