sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2024-12-26 18:34:18 +00:00
Code Issues Projects Releases Wiki Activity

Codestyle update

Browse Source
This commit is contained in:
Patrick Jentsch 2022-01-18 13:45:17 +01:00
parent c057d324cf
commit 00c4b17018
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
ocr
View File

@ -385,7 +385,6 @@ class MainWorkflow(WorkflowRunner):
self.input_dir = input_dir self.input_dir = input_dir
self.lang = lang self.lang = lang
self.output_dir = output_dir self.output_dir = output_dir
self.output_files = []
self.binarize = binarize self.binarize = binarize
self.jobs = [] self.jobs = []
@ -528,33 +527,34 @@ class MainWorkflow(WorkflowRunner):
create_txt_tasks.append(task) create_txt_tasks.append(task)
self.waitForTasks() self.waitForTasks()
output_files = []
for job in self.jobs: for job in self.jobs:
# Remove temporary directory # Remove temporary directory
os.rmdir(job.tmp_dir) os.rmdir(job.tmp_dir)
# Track output files # Track output files
relative_output_dir = os.path.relpath(job.output_dir, start=self.output_dir) # noqa relative_output_dir = os.path.relpath(job.output_dir, start=self.output_dir) # noqa
self.output_files.append( output_files.append(
{ {
'description': 'Post correction package (.png and .hocr).', 'description': 'Post correction package (.png and .hocr).',
'file': os.path.join(relative_output_dir, '{}.poco.zip'.format(job.name)), # noqa 'file': os.path.join(relative_output_dir, '{}.poco.zip'.format(job.name)), # noqa
'mimetype': 'application/zip' 'mimetype': 'application/zip'
} }
) )
self.output_files.append( output_files.append(
{ {
'description': 'PDF file with text layer.', 'description': 'PDF file with text layer.',
'file': os.path.join(relative_output_dir, '{}.pdf'.format(job.name)), # noqa 'file': os.path.join(relative_output_dir, '{}.pdf'.format(job.name)), # noqa
'mimetype': 'application/pdf' 'mimetype': 'application/pdf'
} }
) )
self.output_files.append( output_files.append(
{ {
'description': 'Plain text file.', 'description': 'Plain text file.',
'file': os.path.join(relative_output_dir, '{}.txt'.format(job.name)), # noqa 'file': os.path.join(relative_output_dir, '{}.txt'.format(job.name)), # noqa
'mimetype': 'text/plain' 'mimetype': 'text/plain'
} }
) )
self.output_files.append( output_files.append(
{ {
'description': 'TEI compliant XML file.', 'description': 'TEI compliant XML file.',
'file': os.path.join(relative_output_dir, '{}.tei.xml'.format(job.name)), # noqa 'file': os.path.join(relative_output_dir, '{}.tei.xml'.format(job.name)), # noqa
@ -562,7 +562,7 @@ class MainWorkflow(WorkflowRunner):
} }
) )
with open(os.path.join(self.output_dir, 'output_records.json'), 'w') as f: # noqa with open(os.path.join(self.output_dir, 'output_records.json'), 'w') as f: # noqa
json.dump(self.output_files, f, indent=4) json.dump(output_files, f, indent=4)
def parse_args(): def parse_args():