qurator-spk/ocrd_repair_inconsistencies
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd_repair_inconsistencies.git synced 2025-10-31 08:54:13 +01:00
Code Issues Releases Wiki Activity

add MetadataItem about processor

Browse source
This commit is contained in:
Robert Sachunsky 2019-11-29 18:15:56 +01:00
parent ad8f25666b
commit e16438a377
1 changed files with 15 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

14
ocrd_repair_inconsistencies/ocrd_repair_inconsistencies.py
View file

@ -7,6 +7,7 @@ from ocrd import Processor
from ocrd_modelfactory import page_from_file from ocrd_modelfactory import page_from_file
from ocrd_models.ocrd_page import ( from ocrd_models.ocrd_page import (
TextRegionType, TextLineType, WordType, TextRegionType, TextLineType, WordType,
MetadataItemType, LabelsType, LabelType,
to_xml to_xml
) )
from ocrd_utils import ( from ocrd_utils import (
@ -35,6 +36,19 @@ class RepairInconsistencies(Processor):
pcgts = page_from_file(self.workspace.download_file(input_file)) pcgts = page_from_file(self.workspace.download_file(input_file))
page = pcgts.get_Page() page = pcgts.get_Page()
# add metadata about this operation and its runtime parameters:
metadata = pcgts.get_Metadata() # ensured by from_file()
metadata.add_MetadataItem(
MetadataItemType(type_="processingStep",
name=self.ocrd_tool['steps'][0],
value=TOOL,
Labels=[LabelsType(
externalModel="ocrd-tool",
externalId="parameters",
Label=[LabelType(type_=name,
value=self.parameter[name])
for name in self.parameter.keys()])]))
regions = page.get_TextRegion() regions = page.get_TextRegion()
for region in regions: for region in regions: