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: Substitute more characters

Browse source
This commit is contained in:
Gerber, Mike 2019-08-22 15:35:19 +02:00
parent d18583348a
commit 8237b3edaf
1 changed files with 11 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

15
qurator/dinglehopper/substitute_equivalences.py
View file

@ -22,11 +22,18 @@ def substitute_equivalences(s):
'': 'ct',
'’': '\'',
'⸗': '-',
'': 'tz', # MUFI: LATIN SMALL LIGATURE TZ
'aͤ': 'ä', # LATIN SMALL LETTER A, COMBINING LATIN SMALL LETTER E
'oͤ': 'ö', # LATIN SMALL LETTER O, COMBINING LATIN SMALL LETTER E
'uͤ': 'ü', # LATIN SMALL LETTER U, COMBINING LATIN SMALL LETTER E
'': 'tz', # MUFI: LATIN SMALL LIGATURE TZ
'aͤ': 'ä', # LATIN SMALL LETTER A, COMBINING LATIN SMALL LETTER E
'oͤ': 'ö', # LATIN SMALL LETTER O, COMBINING LATIN SMALL LETTER E
'uͤ': 'ü', # LATIN SMALL LETTER U, COMBINING LATIN SMALL LETTER E
'\uf535': 'Qu', # eMOP: Latin ligature capital Q small u
'ij': 'ij', # U+0133 LATIN SMALL LIGATURE IJ
'\uE8BF': 'q&', # MUFI: LATIN SMALL LETTER Q LIGATED WITH FINAL ET XXX How to replace this correctly?
'\uEBA5': 'ſp', # MUFI: LATIN SMALL LIGATURE LONG S P
'st': 'st', # U+FB06 LATIN SMALL LIGATURE ST
'\uF50E': 'q́' # U+F50E LATIN SMALL LETTER Q WITH ACUTE ACCENT
}
for fr, to in equivalences.items():
s = s.replace(fr, to)
return s