qurator-spk/ocrd_calamari
1
0
Fork 0
mirror of https://github.com/mikegerber/ocrd_calamari.git synced 2025-11-04 09:34:13 +01:00
Code Releases Activity

📝 unwanted()

Browse source
This commit is contained in:
Gerber, Mike 2020-02-03 15:33:38 +01:00
parent 91cca1e1b8
commit 3149e1d9e0
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ocrd_calamari/recognize.py
View file

@ -106,6 +106,11 @@ class CalamariRecognize(Processor):
# a strict hierarchy of lines > words > glyphs. # a strict hierarchy of lines > words > glyphs.
def unwanted(c): def unwanted(c):
"""
Define unwanted characters
Words only containing these e.g. whitespace characters are not considered as words.
"""
return c == " " return c == " "
word_no = 0 word_no = 0