qurator-spk/sbb_textline_detection
1
0
Fork 0
mirror of https://github.com/qurator-spk/sbb_textline_detection.git synced 2025-10-30 17:04:16 +01:00
Code Issues Releases Wiki Activity

Merge pull request #36 from kba/file-ids-and-such

Browse source 
use make_file_id and assert_file_grp_cardinality
This commit is contained in:
Mike Gerber 2020-08-12 11:50:12 +02:00 • committed by GitHub
commit 6b0fc49fe8
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

20
qurator/sbb_textline_detector/ocrd_cli.py
View file

@ -9,7 +9,13 @@ from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
from ocrd_modelfactory import page_from_file
from ocrd_models import OcrdFile
from ocrd_models.ocrd_page_generateds import MetadataItemType, LabelsType, LabelType
from ocrd_utils import concat_padded, getLogger, MIMETYPE_PAGE
from ocrd_utils import (
assert_file_grp_cardinality,
getLogger,
make_file_id,
MIMETYPE_PAGE
)
from pkg_resources import resource_string
from qurator.sbb_textline_detector import textline_detector
@ -27,7 +33,6 @@ def ocrd_sbb_textline_detector(*args, **kwargs):
TOOL = 'ocrd-sbb-textline-detector'
class OcrdSbbTextlineDetectorRecognize(Processor):
def __init__(self, *args, **kwargs):
@ -35,12 +40,6 @@ class OcrdSbbTextlineDetectorRecognize(Processor):
kwargs['version'] = OCRD_TOOL['version']
super(OcrdSbbTextlineDetectorRecognize, self).__init__(*args, **kwargs)
def _make_file_id(self, input_file, input_file_grp, n):
file_id = input_file.ID.replace(input_file_grp, self.output_file_grp)
if file_id == input_file.ID:
file_id = concat_padded(self.output_file_grp, n)
return file_id
def _resolve_image_file(self, input_file: OcrdFile) -> str:
if input_file.mimetype == MIMETYPE_PAGE:
pcgts = page_from_file(self.workspace.download_file(input_file))
@ -51,11 +50,14 @@ class OcrdSbbTextlineDetectorRecognize(Processor):
return image_file
def process(self):
assert_file_grp_cardinality(self.input_file_grp, 1)
assert_file_grp_cardinality(self.output_file_grp, 1)
for (n, input_file) in enumerate(self.input_files):
page_id = input_file.pageId or input_file.ID
log.info("INPUT FILE %i / %s", n, input_file)
file_id = self._make_file_id(input_file, self.input_file_grp, n)
file_id = make_file_id(input_file, self.output_file_grp)
# Process the files
try: