LCPQ/spip2md
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix some encoding bugs with regex replace

Browse Source
This commit is contained in:
Guilhem Fauré 2023-05-11 10:33:35 +02:00
parent 5c78dcd753
commit b3fa5023c4
1 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spip2md/convert.py
View File

@ -97,10 +97,23 @@ mappings = (
), ),
r"\1", r"\1",
), ),
( # Fix UTF-8 appostrophe that was interpreted as ISO 8859-1 and saved like so
re.compile("’"),
r"’",
),
( # Fix UTF-8 é that was interpreted as ISO 8859-1 and saved like so
re.compile("eÌ\u0081"),
r"é",
),
( # Fix UTF-8 é that was interpreted as ISO 8859-1 and saved like so
re.compile("à"),
r"à",
),
) )
def convert(markup): def convert(markup):
for spip, markdown in mappings: for spip, markdown in mappings:
markup = spip.sub(markdown, markup) markup = spip.sub(markdown, markup)
return markup.encode("utf-8").decode("utf-8") # return markup.encode("utf-8").decode("utf-8")
return markup