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

fixed most of the encoding bugs

Browse Source
This commit is contained in:
Guilhem Fauré 2023-05-11 11:36:23 +02:00
parent b3fa5023c4
commit 995fee5b6a
1 changed files with 78 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

78
spip2md/convert.py
View File

@ -1,6 +1,7 @@
import re import re
mappings = ( mappings = (
# SPIP syntax to Markdown
( # horizontal-rule ( # horizontal-rule
re.compile(r"- ?- ?- ?- ?[\- ]*|<hr ?.*?>", re.S | re.I), re.compile(r"- ?- ?- ?- ?[\- ]*|<hr ?.*?>", re.S | re.I),
# r"---", # r"---",
@ -97,18 +98,95 @@ mappings = (
), ),
r"\1", r"\1",
), ),
# Broken encoding
( # Fix UTF-8 appostrophe that was interpreted as ISO 8859-1 and saved like so ( # Fix UTF-8 appostrophe that was interpreted as ISO 8859-1 and saved like so
re.compile("’"), re.compile("’"),
r"’", r"’",
), ),
( # Fix UTF-8 † 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 ( # Fix UTF-8 é that was interpreted as ISO 8859-1 and saved like so
re.compile("eÌ\u0081"), re.compile("eÌ\u0081"),
r"é", r"é",
), ),
( # Fix UTF-8 è that was interpreted as ISO 8859-1 and saved like so
re.compile("è"),
r"è",
),
( # Fix UTF-8 ê that was interpreted as ISO 8859-1 and saved like so
re.compile("ê"),
r"ê",
),
( # Fix UTF-8 ê that was interpreted as ISO 8859-1 and saved like so
re.compile("ô"),
r"ô",
),
( # Fix UTF-8 î that was interpreted as ISO 8859-1 and saved like so
re.compile("î"),
r"î",
),
( # Fix UTF-8 ï that was interpreted as ISO 8859-1 and saved like so
re.compile("ï"),
r"ï",
),
( # Fix UTF-8 ö that was interpreted as ISO 8859-1 and saved like so
re.compile("ö"),
r"ö",
),
( # Fix UTF-8 ö that was interpreted as ISO 8859-1 and saved like so
re.compile("ü"),
r"ü",
),
( # WARNING Fix UTF-8 é ? that was interpreted as ISO 8859-1 and saved like so
re.compile("eÌ "),
r"é",
),
( # Fix UTF-8 é that was interpreted as ISO 8859-1 and saved like so ( # Fix UTF-8 é that was interpreted as ISO 8859-1 and saved like so
re.compile("à"), re.compile("à"),
r"à", r"à",
), ),
( # Fix UTF-8 … that was interpreted as ISO 8859-1 and saved like so
re.compile("…"),
r"…",
),
( # Fix UTF-8 “ that was interpreted as ISO 8859-1 and saved like so
re.compile("“"),
r"“",
),
( # Fix UTF-8 ” that was interpreted as ISO 8859-1 and saved like so
re.compile("â€\u009d"),
r"”",
),
( # Fix UTF-8 – that was interpreted as ISO 8859-1 and saved like so
re.compile("–"),
r"–",
),
( # Fix UTF-8 – that was interpreted as ISO 8859-1 and saved like so
re.compile("—"),
r"—",
),
( # Fix UTF-8 − that was interpreted as ISO 8859-1 and saved like so
re.compile("â€\u0090"),
r"−",
),
( # Fix UTF-8 • that was interpreted as ISO 8859-1 and saved like so
re.compile("•"),
r"•",
),
( # Fix UTF-8 † that was interpreted as ISO 8859-1 and saved like so
re.compile("†"),
r"† ",
),
( # Delete unknown 

re.compile("
"),
r"",
),
( # Delete unknown Ì\u0081
re.compile("Ì\u0081"),
r"",
),
) )