You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
36 lines
1.4 KiB
Python
36 lines
1.4 KiB
Python
from typing import Optional
|
|
from ocrd.processor.ocrd_page_result import OcrdPageResult
|
|
from ocrd_models import OcrdPage
|
|
from ocrd import Processor
|
|
|
|
from .eynollah import Eynollah
|
|
|
|
class EynollahProcessor(Processor):
|
|
|
|
@property
|
|
def metadata_location(self) -> str:
|
|
return 'eynollah/ocrd-tool.json'
|
|
|
|
def process_page_pcgts(self, *input_pcgts: Optional[OcrdPage], page_id: Optional[str] = None) -> OcrdPageResult:
|
|
assert input_pcgts
|
|
assert input_pcgts[0]
|
|
pcgts = input_pcgts[0]
|
|
page = pcgts.get_Page()
|
|
# XXX loses DPI information
|
|
# page_image, _, _ = self.workspace.image_from_page(page, page_id, feature_filter='binarized')
|
|
image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(local_filename=page.imageFilename))).local_filename
|
|
Eynollah(
|
|
dir_models=self.resolve_resource(self.parameter['models']),
|
|
allow_enhancement=False,
|
|
curved_line=self.parameter['curved_line'],
|
|
full_layout=self.parameter['full_layout'],
|
|
allow_scaling=self.parameter['allow_scaling'],
|
|
headers_off=self.parameter['headers_off'],
|
|
tables=self.parameter['tables'],
|
|
override_dpi=self.parameter['dpi'],
|
|
logger=self.logger,
|
|
pcgts=pcgts,
|
|
image_filename=image_filename
|
|
).run()
|
|
return OcrdPageResult(pcgts)
|