qurator-spk
/
eynollah
mirror of https://github.com/qurator-spk/eynollah.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge pull request #32 from qurator-spk/ocrd-page-api-fix

Browse Source 
Ocrd page api fix
pull/34/head
vahidrezanezhad 4 years ago committed by GitHub
parent b643ced9fb c95529725a
commit 3e4ac11347
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File

16
qurator/eynollah/writer.py
Unescape Escape View File

@ -54,7 +54,7 @@ class EynollahXmlWriter():
def serialize_lines_in_marginal(self, marginal_region, all_found_texline_polygons_marginals, marginal_idx, page_coord, all_box_coord_marginals, slopes_marginals, counter): def serialize_lines_in_marginal(self, marginal_region, all_found_texline_polygons_marginals, marginal_idx, page_coord, all_box_coord_marginals, slopes_marginals, counter):
for j in range(len(all_found_texline_polygons_marginals[marginal_idx])): for j in range(len(all_found_texline_polygons_marginals[marginal_idx])):
coords = CoordsType() coords = CoordsType()
textline = TextLineType(id=counter.next_line_id, coords=coords) textline = TextLineType(id=counter.next_line_id, Coords=coords)
marginal_region.add_TextLine(textline) marginal_region.add_TextLine(textline)
textline.add_TextEquiv(TextEquivType(Unicode='')) textline.add_TextEquiv(TextEquivType(Unicode=''))
points_co = '' points_co = ''
@ -94,7 +94,7 @@ class EynollahXmlWriter():
self.logger.debug('enter serialize_lines_in_region') self.logger.debug('enter serialize_lines_in_region')
for j in range(len(all_found_texline_polygons[region_idx])): for j in range(len(all_found_texline_polygons[region_idx])):
coords = CoordsType() coords = CoordsType()
textline = TextLineType(id=counter.next_line_id, coords=coords, TextEquiv=[TextEquivType(index=0, Unicode='')]) textline = TextLineType(id=counter.next_line_id, Coords=coords, TextEquiv=[TextEquivType(index=0, Unicode='')])
text_region.add_TextLine(textline) text_region.add_TextLine(textline)
region_bboxes = all_box_coord[region_idx] region_bboxes = all_box_coord[region_idx]
points_co = '' points_co = ''
@ -152,14 +152,14 @@ class EynollahXmlWriter():
xml_reading_order(page, order_of_texts, id_of_marginalia) xml_reading_order(page, order_of_texts, id_of_marginalia)
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)), Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord)),
TextEquiv=[TextEquivType(index=0, Unicode='')]) TextEquiv=[TextEquivType(index=0, Unicode='')])
page.add_TextRegion(textregion) page.add_TextRegion(textregion)
self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, counter) self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, 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',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord))) Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord)))
page.add_TextRegion(marginal) page.add_TextRegion(marginal)
self.serialize_lines_in_marginal(marginal, all_found_texline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter) self.serialize_lines_in_marginal(marginal, all_found_texline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter)
@ -191,7 +191,7 @@ class EynollahXmlWriter():
xml_reading_order(page, order_of_texts, id_of_marginalia) xml_reading_order(page, order_of_texts, id_of_marginalia)
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',
TextEquiv=[TextEquivType(index=0, Unicode='')], TextEquiv=[TextEquivType(index=0, Unicode='')],
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord))) Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord)))
page.add_TextRegion(textregion) page.add_TextRegion(textregion)
@ -199,21 +199,21 @@ class EynollahXmlWriter():
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))
for mm in range(len(found_polygons_text_region_h)): for mm in range(len(found_polygons_text_region_h)):
textregion = TextRegionType(id=counter.next_region_id, type='header', textregion = TextRegionType(id=counter.next_region_id, type_='header',
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, 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',
TextEquiv=[TextEquivType(index=0, Unicode='')], TextEquiv=[TextEquivType(index=0, Unicode='')],
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord))) Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord)))
page.add_TextRegion(marginal) page.add_TextRegion(marginal)
self.serialize_lines_in_marginal(marginal, all_found_texline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter) self.serialize_lines_in_marginal(marginal, all_found_texline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter)
for mm in range(len(found_polygons_drop_capitals)): for mm in range(len(found_polygons_drop_capitals)):
page.add_TextRegion(TextRegionType(id=counter.next_region_id, type='drop-capital', page.add_TextRegion(TextRegionType(id=counter.next_region_id, type_='drop-capital',
TextEquiv=[TextEquivType(index=0, Unicode='')], TextEquiv=[TextEquivType(index=0, Unicode='')],
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_drop_capitals[mm], page_coord)))) Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_drop_capitals[mm], page_coord))))

Write Preview
Loading…
Cancel
Save