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 word differences in line-dirs report

Browse source
This commit is contained in:
Gerber, Mike 2021-12-14 18:20:04 +01:00
parent dbb660615a
commit cb2be96179
1 changed files with 7 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

13
qurator/dinglehopper/cli_line_dirs.py
View file

@ -43,6 +43,7 @@ def process(gt_dir, ocr_dir, report_prefix, *, metrics=True):
cer = None
n_characters = None
char_diff_report = ""
word_diff_report = ""
for k, gt in enumerate(os.listdir(gt_dir)):
# Find a match by replacing the suffix
@ -68,13 +69,11 @@ def process(gt_dir, ocr_dir, report_prefix, *, metrics=True):
gt_text, ocr_text, css_prefix="l{0}-c".format(k), joiner="", none="·"
)
# TODO
# gt_words = words_normalized(gt_text)
# ocr_words = words_normalized(ocr_text)
# word_diff_report = gen_diff_report(
# gt_words, ocr_words, css_prefix="w", joiner=" ", none="⋯"
# )
word_diff_report = "TODO"
gt_words = words_normalized(gt_text)
ocr_words = words_normalized(ocr_text)
word_diff_report += gen_diff_report(
gt_words, ocr_words, css_prefix="l{0}-w".format(k), joiner=" ", none="⋯"
)
# XXX this is a copy from cli.py