qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-09 11:50:00 +02:00
Code Issues Releases Wiki Activity

✨ dinglehopper: Add CLI option to choose TextEquiv level

Browse source
This commit is contained in:
Gerber, Mike 2020-10-20 19:33:39 +02:00
parent 75733039b8
commit 9744fa2567
3 changed files with 17 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

14
qurator/dinglehopper/cli.py
View file

@ -80,15 +80,15 @@ def gen_diff_report(gt_in, ocr_in, css_prefix, joiner, none):
'''.format(gtx, ocrx)
def process(gt, ocr, report_prefix, *, metrics=True):
def process(gt, ocr, report_prefix, *, metrics=True, textequiv_level='region'):
"""Check OCR result against GT.
The @click decorators change the signature of the decorated functions, so we keep this undecorated version and use
Click on a wrapper.
"""
gt_text = extract(gt)
ocr_text = extract(ocr)
gt_text = extract(gt, textequiv_level=textequiv_level)
ocr_text = extract(ocr, textequiv_level=textequiv_level)
cer, n_characters = character_error_rate_n(gt_text, ocr_text)
wer, n_words = word_error_rate_n(gt_text, ocr_text)
@ -134,8 +134,9 @@ def process(gt, ocr, report_prefix, *, metrics=True):
@click.argument('ocr', type=click.Path(exists=True))
@click.argument('report_prefix', type=click.Path(), default='report')
@click.option('--metrics/--no-metrics', default=True, help='Enable/disable metrics and green/red')
@click.option('--textequiv-level', default='region', help='PAGE TextEquiv level to extract text from', metavar='LEVEL')
@click.option('--progress', default=False, is_flag=True, help='Show progress bar')
def main(gt, ocr, report_prefix, metrics, progress):
def main(gt, ocr, report_prefix, metrics, textequiv_level, progress):
"""
Compare the PAGE/ALTO/text document GT against the document OCR.
@ -150,9 +151,12 @@ def main(gt, ocr, report_prefix, metrics, progress):
The comparison report will be written to $REPORT_PREFIX.{html,json}, where
$REPORT_PREFIX defaults to "report". The reports include the character error
rate (CER) and the word error rate (WER).
By default, the text of PAGE files is extracted on 'region' level. You may
use "--textequiv-level line" to extract from the level of TextLine tags.
"""
Config.progress = progress
process(gt, ocr, report_prefix, metrics=metrics)
process(gt, ocr, report_prefix, metrics=metrics, textequiv_level=textequiv_level)
if __name__ == '__main__':

8
qurator/dinglehopper/ocr_files.py
View file

@ -54,7 +54,7 @@ def page_namespace(tree):
raise ValueError('Not a PAGE tree')
def page_extract(tree, textequiv_level='region'):
def page_extract(tree, *, textequiv_level='region'):
"""Extract text from the given PAGE content ElementTree."""
# Internally, this is just parsing the Reading Order (if it exists) and
@ -87,7 +87,7 @@ def page_extract(tree, textequiv_level='region'):
return ExtractedText(None, regions, '\n', None)
def page_text(tree, textequiv_level='region'):
def page_text(tree, *, textequiv_level='region'):
return page_extract(tree, textequiv_level=textequiv_level).text
@ -105,7 +105,7 @@ def plain_text(filename):
return plain_extract(filename).text
def extract(filename):
def extract(filename, *, textequiv_level='region'):
"""Extract the text from the given file.
Supports PAGE, ALTO and falls back to plain text.
@ -115,7 +115,7 @@ def extract(filename):
except XMLSyntaxError:
return plain_extract(filename)
try:
return page_extract(tree)
return page_extract(tree, textequiv_level=textequiv_level)
except ValueError:
return alto_extract(tree)