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

replace lxml with OCR-D/core PAGE API

Browse Source
pull/31/head
Konstantin Baierer 4 years ago
parent 7a859ffae4
commit 416a84e542
4 changed files with 126 additions and 133 deletions
Show Stats Download Patch File Download Diff File

2
qurator/eynollah/eynollah.py
Unescape Escape View File

@ -1639,7 +1639,7 @@ class Eynollah:
if not num_col:
self.logger.info("No columns detected, outputting an empty PAGE-XML")
pcgts = self.writer.build_pagexml_no_full_layout([], page_coord, [], [], [], [], [], [], [], [], [], cont_page)
pcgts = self.writer.build_pagexml_no_full_layout([], page_coord, [], [], [], [], [], [], [], [], [], [], cont_page)
self.logger.info("Job done in %ss", str(time.time() - t1))
return pcgts

93
qurator/eynollah/utils/xml.py
Unescape Escape View File

@ -1,60 +1,63 @@
# pylint: disable=too-many-locals,wrong-import-position,too-many-lines,too-many-statements,chained-comparison,fixme,broad-except,c-extension-no-member
# pylint: disable=invalid-name
from lxml import etree as ET
from .counter import EynollahIdCounter
import numpy as np
NAMESPACES = {}
NAMESPACES['page'] = "http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"
NAMESPACES['xsi'] = "http://www.w3.org/2001/XMLSchema-instance"
NAMESPACES[None] = NAMESPACES['page']
from datetime import datetime
from ocrd_models.ocrd_page import (
CoordsType,
GlyphType,
ImageRegionType,
MathsRegionType,
MetadataType,
MetadataItemType,
NoiseRegionType,
OrderedGroupIndexedType,
OrderedGroupType,
PcGtsType,
PageType,
ReadingOrderType,
RegionRefIndexedType,
RegionRefType,
SeparatorRegionType,
TableRegionType,
TextEquivType,
TextLineType,
TextRegionType,
UnorderedGroupIndexedType,
UnorderedGroupType,
WordType,
to_xml)
def create_page_xml(imageFilename, height, width):
pcgts = ET.Element("PcGts", nsmap=NAMESPACES)
pcgts.set("{%s}schemaLocation" % NAMESPACES['xsi'], NAMESPACES['page'])
metadata = ET.SubElement(pcgts, "Metadata")
author = ET.SubElement(metadata, "Creator")
author.text = "SBB_QURATOR"
created = ET.SubElement(metadata, "Created")
created.text = "2019-06-17T18:15:12"
changetime = ET.SubElement(metadata, "LastChange")
changetime.text = "2019-06-17T18:15:12"
page = ET.SubElement(pcgts, "Page")
page.set("imageFilename", imageFilename)
page.set("imageHeight", str(height))
page.set("imageWidth", str(width))
page.set("type", "content")
page.set("readingDirection", "left-to-right")
page.set("textLineOrder", "top-to-bottom")
return pcgts, page
def add_textequiv(parent, text=''):
textequiv = ET.SubElement(parent, 'TextEquiv')
unireg = ET.SubElement(textequiv, 'Unicode')
unireg.text = text
now = datetime.now()
pcgts = PcGtsType(
Metadata=MetadataType(
Creator='SBB_QURATOR',
Created=now,
LastChange=now
),
Page=PageType(
imageWidth=str(width),
imageHeight=str(height),
imageFilename=imageFilename,
readingDirection='left-to-right',
textLineOrder='top-to-bottom'
))
return pcgts
def xml_reading_order(page, order_of_texts, id_of_marginalia):
region_order = ET.SubElement(page, 'ReadingOrder')
region_order_sub = ET.SubElement(region_order, 'OrderedGroup')
region_order_sub.set('id', "ro357564684568544579089")
region_order = ReadingOrderType()
og = OrderedGroupType(id="ro357564684568544579089")
page.set_ReadingOrder(region_order)
region_order.set_OrderedGroup(og)
region_counter = EynollahIdCounter()
for idx_textregion, _ in enumerate(order_of_texts):
name = ET.SubElement(region_order_sub, 'RegionRefIndexed')
name.set('index', str(region_counter.get('region')))
name.set('regionRef', region_counter.region_id(order_of_texts[idx_textregion] + 1))
og.add_RegionRefIndexed(RegionRefIndexedType(index=str(region_counter.get('region')), regionRef=region_counter.region_id(order_of_texts[idx_textregion] + 1)))
region_counter.inc('region')
for id_marginal in id_of_marginalia:
name = ET.SubElement(region_order_sub, 'RegionRefIndexed')
name.set('index', str(region_counter.get('region')))
name.set('regionRef', id_marginal)
og.add_RegionRefIndexed(RegionRefIndexedType(index=str(region_counter.get('region')), regionRef=id_marginal))
region_counter.inc('region')
def order_and_id_of_texts(found_polygons_text_region, found_polygons_text_region_h, matrix_of_orders, indexes_sorted, index_of_types, kind_of_texts, ref_point):

147
qurator/eynollah/writer.py
Unescape Escape View File

@ -1,23 +1,36 @@
# pylint: disable=too-many-locals,wrong-import-position,too-many-lines,too-many-statements,chained-comparison,fixme,broad-except,c-extension-no-member
# pylint: disable=import-error
from pathlib import Path
import os.path
from .utils.xml import create_page_xml, add_textequiv, xml_reading_order
from .utils.xml import create_page_xml, xml_reading_order
from .utils.counter import EynollahIdCounter
from ocrd_utils import getLogger
from lxml import etree as ET
from ocrd_models.ocrd_page import (
BorderType,
CoordsType,
TextEquivType,
PcGtsType,
TextLineType,
TextRegionType,
ImageRegionType,
TableRegionType,
to_xml
)
import numpy as np
class EynollahXmlWriter():
def __init__(self, *, dir_out, image_filename, curved_line):
def __init__(self, *, dir_out, image_filename, curved_line, pcgts=None):
self.logger = getLogger('eynollah.writer')
self.counter = EynollahIdCounter()
self.dir_out = dir_out
self.image_filename = image_filename
self.image_filename_stem = Path(Path(image_filename).name).stem
self.curved_line = curved_line
self.pcgts = pcgts if pcgts else PcGtsType()
self.scale_x = None # XXX set outside __init__
self.scale_y = None # XXX set outside __init__
self.height_org = None # XXX set outside __init__
@ -38,12 +51,12 @@ class EynollahXmlWriter():
points_page_print = points_page_print + ' '
return points_page_print[:-1]
def serialize_lines_in_marginal(self, marginal, 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])):
textline = ET.SubElement(marginal, 'TextLine')
textline.set('id', counter.next_line_id)
coord = ET.SubElement(textline, 'Coords')
add_textequiv(textline)
coords = CoordsType()
textline = TextLineType(id=counter.next_line_id, coords=coords)
marginal_region.add_TextLine(textline)
textline.add_TextEquiv(TextEquivType(Unicode=''))
points_co = ''
for l in range(len(all_found_texline_polygons_marginals[marginal_idx][j])):
if not self.curved_line:
@ -64,7 +77,7 @@ class EynollahXmlWriter():
points_co += str(int((all_found_texline_polygons_marginals[marginal_idx][j][l][0][0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((all_found_texline_polygons_marginals[marginal_idx][j][l][0][1] + page_coord[0]) / self.scale_y))
elif self.curved_line and np.abs(slopes_marginals[marginal_idx]) > 45:
if len(all_found_texline_polygons_marginals[marginal_idx][j][l]) == 2:
points_co += str(int((all_found_texline_polygons_marginals[marginal_idx][j][l][0] + all_box_coord_marginals[marginal_idx][2] + page_coord[2]) / self.scale_x))
@ -74,20 +87,16 @@ class EynollahXmlWriter():
points_co += str(int((all_found_texline_polygons_marginals[marginal_idx][j][l][0][0] + all_box_coord_marginals[marginal_idx][2] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((all_found_texline_polygons_marginals[marginal_idx][j][l][0][1] + all_box_coord_marginals[marginal_idx][0] + page_coord[0]) / self.scale_y))
points += ' '
coords.set_points(points_co[:-1])
if l < len(all_found_texline_polygons_marginals[marginal_idx][j]) - 1:
points_co += ' '
coord.set('points',points_co)
def serialize_lines_in_region(self, textregion, all_found_texline_polygons, region_idx, page_coord, all_box_coord, slopes, counter):
def serialize_lines_in_region(self, text_region, all_found_texline_polygons, region_idx, page_coord, all_box_coord, slopes, counter):
self.logger.debug('enter serialize_lines_in_region')
for j in range(len(all_found_texline_polygons[region_idx])):
textline = ET.SubElement(textregion, 'TextLine')
textline.set('id', counter.next_line_id)
coord = ET.SubElement(textline, 'Coords')
add_textequiv(textline)
coords = CoordsType()
textline = TextLineType(id=counter.next_line_id, coords=coords, TextEquiv=[TextEquivType(index=0, Unicode='')])
text_region.add_TextLine(textline)
region_bboxes = all_box_coord[region_idx]
points_co = ''
for idx_contour_textline, contour_textline in enumerate(all_found_texline_polygons[region_idx][j]):
if not self.curved_line:
@ -119,23 +128,22 @@ class EynollahXmlWriter():
points_co += str(int((contour_textline[0][0] + region_bboxes[2]+page_coord[2])/self.scale_x))
points_co += ','
points_co += str(int((contour_textline[0][1] + region_bboxes[0]+page_coord[0])/self.scale_y))
points_co += ' '
coord.set('points', points_co[:-1])
coords.set_points(points_co[:-1])
def write_pagexml(self, pcgts):
self.logger.info("filename stem: '%s'", self.image_filename_stem)
tree = ET.ElementTree(pcgts)
tree.write(os.path.join(self.dir_out, self.image_filename_stem) + ".xml")
out_fname = os.path.join(self.dir_out, self.image_filename_stem) + ".xml"
self.logger.info("output filename: '%s'", out_fname)
with open(out_fname, 'w') as f:
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_texline_polygons, all_box_coord, found_polygons_text_region_img, found_polygons_marginals, all_found_texline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page):
self.logger.debug('enter build_pagexml_no_full_layout')
# create the file structure
pcgts, page = create_page_xml(self.image_filename, self.height_org, self.width_org)
page_print_sub = ET.SubElement(page, "Border")
coord_page = ET.SubElement(page_print_sub, "Coords")
coord_page.set('points', self.calculate_page_coords(cont_page))
pcgts = create_page_xml(self.image_filename, self.height_org, self.width_org)
page = pcgts.get_Page()
page.set_Border(BorderType(Coords=CoordsType(points=self.calculate_page_coords(cont_page))))
counter = EynollahIdCounter()
if len(found_polygons_text_region) > 0:
@ -144,33 +152,28 @@ class EynollahXmlWriter():
xml_reading_order(page, order_of_texts, id_of_marginalia)
for mm in range(len(found_polygons_text_region)):
textregion = ET.SubElement(page, 'TextRegion')
textregion.set('id', counter.next_region_id)
textregion.set('type', 'paragraph')
coord_text = ET.SubElement(textregion, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord))
textregion = TextRegionType(id=counter.next_region_id, type='paragraph',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord)),
TextEquiv=[TextEquivType(index=0, Unicode='')])
page.add_TextRegion(textregion)
self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, counter)
add_textequiv(textregion)
for mm in range(len(found_polygons_marginals)):
marginal = ET.SubElement(page, 'TextRegion')
marginal.set('id', counter.next_region_id)
marginal.set('type', 'marginalia')
coord_text = ET.SubElement(marginal, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord))
marginal = TextRegionType(id=counter.next_region_id, type='marginalia',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord)))
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)
for mm in range(len(found_polygons_text_region_img)):
textregion = ET.SubElement(page, 'ImageRegion')
textregion.set('id', counter.next_region_id)
coord_text = ET.SubElement(textregion, 'Coords')
img_region = ImageRegionType(id=counter.next_region_id, Coords=CoordsType())
page.add_ImageRegion(img_region)
points_co = ''
for lmm in range(len(found_polygons_text_region_img[mm])):
points_co += str(int((found_polygons_text_region_img[mm][lmm,0,0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((found_polygons_text_region_img[mm][lmm,0,1] + page_coord[0]) / self.scale_y))
points_co += ' '
coord_text.set('points', points_co[:-1])
img_region.get_Coords().set_points(points_co[:-1])
return pcgts
@ -178,10 +181,9 @@ class EynollahXmlWriter():
self.logger.debug('enter build_pagexml_full_layout')
# create the file structure
pcgts, page = create_page_xml(self.image_filename, self.height_org, self.width_org)
page_print_sub = ET.SubElement(page, "Border")
coord_page = ET.SubElement(page_print_sub, "Coords")
coord_page.set('points', self.calculate_page_coords(cont_page))
pcgts = create_page_xml(self.image_filename, self.height_org, self.width_org)
page = pcgts.get_Page()
page.set_Border(BorderType(Coords=CoordsType(points=self.calculate_page_coords(cont_page))))
counter = EynollahIdCounter()
_counter_marginals = EynollahIdCounter(region_idx=len(order_of_texts))
@ -189,52 +191,37 @@ class EynollahXmlWriter():
xml_reading_order(page, order_of_texts, id_of_marginalia)
for mm in range(len(found_polygons_text_region)):
textregion=ET.SubElement(page, 'TextRegion')
textregion.set('id', counter.next_region_id)
textregion.set('type', 'paragraph')
coord_text = ET.SubElement(textregion, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord))
textregion = TextRegionType(id=counter.next_region_id, type='paragraph',
TextEquiv=[TextEquivType(index=0, Unicode='')],
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord)))
page.add_TextRegion(textregion)
self.serialize_lines_in_region(textregion, all_found_texline_polygons, mm, page_coord, all_box_coord, slopes, counter)
add_textequiv(textregion)
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)):
textregion=ET.SubElement(page, 'TextRegion')
textregion.set('id', counter.next_region_id)
textregion.set('type','header')
coord_text = ET.SubElement(textregion, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region_h[mm], page_coord))
textregion = TextRegionType(id=counter.next_region_id, type='header',
TextEquiv=[TextEquivType(index=0, Unicode='')],
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region_h[mm], page_coord)))
page.add_TextRegion(textregion)
self.serialize_lines_in_region(textregion, all_found_texline_polygons_h, mm, page_coord, all_box_coord_h, slopes, counter)
add_textequiv(textregion)
for mm in range(len(found_polygons_marginals)):
marginal = ET.SubElement(page, 'TextRegion')
add_textequiv(textregion)
marginal.set('id', counter.next_region_id)
marginal.set('type', 'marginalia')
coord_text = ET.SubElement(marginal, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord))
marginal = TextRegionType(id=counter.next_region_id, type='marginalia',
TextEquiv=[TextEquivType(index=0, Unicode='')],
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord)))
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)
for mm in range(len(found_polygons_drop_capitals)):
textregion=ET.SubElement(page, 'TextRegion')
textregion.set('id', counter.next_region_id)
textregion.set('type', 'drop-capital')
coord_text = ET.SubElement(textregion, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_drop_capitals[mm], page_coord))
add_textequiv(textregion)
page.add_TextRegion(TextRegionType(id=counter.next_region_id, type='drop-capital',
TextEquiv=[TextEquivType(index=0, Unicode='')],
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_drop_capitals[mm], page_coord))))
for mm in range(len(found_polygons_text_region_img)):
textregion=ET.SubElement(page, 'ImageRegion')
textregion.set('id', counter.next_region_id)
coord_text = ET.SubElement(textregion, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_text_region_img[mm], page_coord))
page.add_ImageRegion(ImageRegionType(id=counter.next_region_id, Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region_img[mm], page_coord))))
for mm in range(len(found_polygons_tables)):
textregion = ET.SubElement(page, 'TableRegion')
textregion.set('id', counter.next_region_id)
coord_text = ET.SubElement(textregion, 'Coords')
coord_text.set('points', self.calculate_polygon_coords(found_polygons_tables[mm], page_coord))
page.add_TableRegion(TableRegionType(id=counter.next_region_id, Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_tables[mm], page_coord))))
return pcgts

17
tests/test_xml.py
Unescape Escape View File

@ -1,11 +1,14 @@
from lxml import etree as ET
from qurator.eynollah.utils.xml import create_page_xml, NAMESPACES
from pytest import main
from qurator.eynollah.utils.xml import create_page_xml
from ocrd_models.ocrd_page import to_xml
def tostring(el):
return ET.tostring(el).decode('utf-8')
PAGE_2019 = 'http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15'
def test_create_xml():
pcgts, page = create_page_xml('/path/to/img.tif', 100, 100)
xmlstr = tostring(pcgts)
assert 'xmlns="%s"' % NAMESPACES[None] in xmlstr
pcgts = create_page_xml('/path/to/img.tif', 100, 100)
xmlstr = to_xml(pcgts)
assert 'xmlns:pc="%s"' % PAGE_2019 in xmlstr
assert 'Metadata' in xmlstr
if __name__ == '__main__':
main([__file__])

Write Preview
Loading…
Cancel
Save