qurator-spk/sbb_binarization
1
0
Fork 0
mirror of https://github.com/qurator-spk/sbb_binarization.git synced 2025-10-31 01:24:14 +01:00
Code Issues Releases Wiki Activity

combine SBB_BINARIZE_DATA and model parameter

Browse source
This commit is contained in:
Konstantin Baierer 2020-10-23 11:19:14 +02:00
parent d675ffc066
commit b62b32c998
2 changed files with 15 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

4
sbb_binarize/ocrd-tool.json
View file

@ -17,9 +17,9 @@
"description": "PAGE XML hierarchy level to operate on" "description": "PAGE XML hierarchy level to operate on"
}, },
"model": { "model": {
"description": "models directory.", "description": "Directory containing HDF5 models. Can be an absolute path or a path relative to the current working directory or $SBB_BINARIZE_DATA environment variable (if set)",
"type": "string", "type": "string",
"required": false "required": true
} }
} }
} }

21
sbb_binarize/ocrd_cli.py
View file

@ -1,4 +1,6 @@
import os.path from os import environ
from os.path import join
from pathlib import Path
from pkg_resources import resource_string from pkg_resources import resource_string
from json import loads from json import loads
@ -38,13 +40,16 @@ class SbbBinarizeProcessor(Processor):
kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL] kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL]
kwargs['version'] = OCRD_TOOL['version'] kwargs['version'] = OCRD_TOOL['version']
if not(kwargs.get('show_help', None) or kwargs.get('dump_json', None) or kwargs.get('show_version')): if not(kwargs.get('show_help', None) or kwargs.get('dump_json', None) or kwargs.get('show_version')):
if not 'parameter' in kwargs:
kwargs['parameter'] = {}
if not 'model' in kwargs['parameter']: if not 'model' in kwargs['parameter']:
if 'SBB_BINARIZE_DATA' in os.environ: raise ValueError("'model' parameter is required")
kwargs['parameter']['model'] = os.environ['SBB_BINARIZE_DATA'] model_path = Path(kwargs['parameter']['model'])
else: if not model_path.is_absolute():
raise ValueError("Must pass 'model' parameter or set SBB_BINARIZE_DATA environment variable") if 'SBB_BINARIZE_DATA' in environ:
model_path = Path(environ['SBB_BINARIZE_DATA']).joinpath(model_path)
model_path = model_path.resolve()
if not model_path.is_dir():
raise FileNotFoundError("Does not exist or is not a directory: %s" % model_path)
kwargs['parameter']['model'] = str(model_path)
super().__init__(*args, **kwargs) super().__init__(*args, **kwargs)
def process(self): def process(self):
@ -114,7 +119,7 @@ class SbbBinarizeProcessor(Processor):
file_grp=self.output_file_grp, file_grp=self.output_file_grp,
pageId=input_file.pageId, pageId=input_file.pageId,
mimetype=MIMETYPE_PAGE, mimetype=MIMETYPE_PAGE,
local_filename=os.path.join(self.output_file_grp, file_id + '.xml'), local_filename=join(self.output_file_grp, file_id + '.xml'),
content=to_xml(pcgts)) content=to_xml(pcgts))
@command() @command()