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

writer: use a single counter for all regions/lines

Browse Source
pull/28/head
Konstantin Baierer 4 years ago
parent a678bbf966
commit 3d9da4feaa
1 changed files with 19 additions and 22 deletions
Show Stats Download Patch File Download Diff File

41
qurator/eynollah/writer.py
Unescape Escape View File

@ -137,33 +137,32 @@ class EynollahXmlWriter():
coord_page = ET.SubElement(page_print_sub, "Coords") coord_page = ET.SubElement(page_print_sub, "Coords")
coord_page.set('points', self.calculate_page_coords(cont_page)) coord_page.set('points', self.calculate_page_coords(cont_page))
counter_textregions = EynollahIdCounter() counter = EynollahIdCounter()
counter_marginals = EynollahIdCounter(region_idx=len(order_of_texts))
id_of_marginalia = [counter_marginals.next_region_id for _ in found_polygons_marginals]
if len(found_polygons_text_region) > 0: if len(found_polygons_text_region) > 0:
_counter_marginals = EynollahIdCounter(region_idx=len(order_of_texts))
id_of_marginalia = [_counter_marginals.next_region_id for _ in found_polygons_marginals]
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 = ET.SubElement(page, 'TextRegion') textregion = ET.SubElement(page, 'TextRegion')
textregion.set('id', counter_textregions.next_region_id) textregion.set('id', counter.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))
self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, counter_textregions) self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, counter)
add_textequiv(textregion) add_textequiv(textregion)
for idx_marginal, marginal_polygon in enumerate(found_polygons_marginals): for marginal_polygon in found_polygons_marginals:
marginal = ET.SubElement(page, 'TextRegion') marginal = ET.SubElement(page, 'TextRegion')
marginal.set('id', id_of_marginalia[idx_marginal]) marginal.set('id', counter.next_region_id)
marginal.set('type', 'marginalia') marginal.set('type', 'marginalia')
coord_text = ET.SubElement(marginal, 'Coords') coord_text = ET.SubElement(marginal, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(marginal_polygon, page_coord)) coord_text.set('points', self.calculate_polygon_coords(marginal_polygon, page_coord))
self.serialize_lines_in_marginal(marginal, all_found_texline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter_textregions) 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_text_region_img)): for mm in range(len(found_polygons_text_region_img)):
textregion = ET.SubElement(page, 'ImageRegion') textregion = ET.SubElement(page, 'ImageRegion')
textregion.set('id', counter_textregions.next_region_id) textregion.set('id', counter.next_region_id)
coord_text = ET.SubElement(textregion, 'Coords') coord_text = ET.SubElement(textregion, 'Coords')
points_co = '' points_co = ''
for lmm in range(len(found_polygons_text_region_img[mm])): for lmm in range(len(found_polygons_text_region_img[mm])):
@ -184,15 +183,14 @@ class EynollahXmlWriter():
coord_page = ET.SubElement(page_print_sub, "Coords") coord_page = ET.SubElement(page_print_sub, "Coords")
coord_page.set('points', self.calculate_page_coords(cont_page)) coord_page.set('points', self.calculate_page_coords(cont_page))
counter_textregions = EynollahIdCounter() counter = EynollahIdCounter()
counter_marginals = EynollahIdCounter(region_idx=len(order_of_texts)) _counter_marginals = EynollahIdCounter(region_idx=len(order_of_texts))
id_of_marginalia = [_counter_marginals.next_region_id for _ in found_polygons_marginals]
id_of_marginalia = [counter_marginals.next_region_id for _ in found_polygons_marginals]
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=ET.SubElement(page, 'TextRegion') textregion=ET.SubElement(page, 'TextRegion')
textregion.set('id', counter_textregions.next_region_id) textregion.set('id', counter.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))
@ -202,7 +200,7 @@ 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=ET.SubElement(page, 'TextRegion') textregion=ET.SubElement(page, 'TextRegion')
textregion.set('id', counter_textregions.next_region_id) textregion.set('id', counter.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))
@ -211,7 +209,7 @@ class EynollahXmlWriter():
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.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))
@ -220,22 +218,21 @@ class EynollahXmlWriter():
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')
add_textequiv(textregion) add_textequiv(textregion)
marginal.set('id', id_of_marginalia[mm]) marginal.set('id', counter.next_region_id)
marginal.set('type', 'marginalia') marginal.set('type', 'marginalia')
coord_text = ET.SubElement(marginal, 'Coords') coord_text = ET.SubElement(marginal, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord)) coord_text.set('points', self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord))
self.serialize_lines_in_marginal(marginal, all_found_texline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter_textregions) self.serialize_lines_in_marginal(marginal, all_found_texline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter)
counter_textregions.inc('region', counter_marginals.get('region'))
for mm in range(len(found_polygons_text_region_img)): for mm in range(len(found_polygons_text_region_img)):
textregion=ET.SubElement(page, 'ImageRegion') textregion=ET.SubElement(page, 'ImageRegion')
textregion.set('id', counter_textregions.next_region_id) textregion.set('id', counter.next_region_id)
coord_text = ET.SubElement(textregion, 'Coords') coord_text = ET.SubElement(textregion, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region_img[mm], page_coord)) coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region_img[mm], page_coord))
for mm in range(len(found_polygons_tables)): for mm in range(len(found_polygons_tables)):
textregion = ET.SubElement(page, 'TableRegion') textregion = ET.SubElement(page, 'TableRegion')
textregion.set('id', counter_textregions.next_region_id) textregion.set('id', counter.next_region_id)
coord_text = ET.SubElement(textregion, 'Coords') coord_text = ET.SubElement(textregion, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_tables[mm], page_coord)) coord_text.set('points', self.calculate_polygon_coords(found_polygons_tables[mm], page_coord))

Write Preview
Loading…
Cancel
Save