Garmelon/PFERD
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2026-04-12 07:25:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix meeting date parsing

Browse source 
Apparently the new pattern "<relative time qualifier>: <date>," was
added. This patch adds support for it.
This commit is contained in:
I-Al-Istannen 2022-05-05 22:28:30 +02:00
parent af2cc1169a
commit 694ffb4d77
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
PFERD/crawl/ilias/kit_ilias_html.py
View file

@ -763,9 +763,14 @@ def demangle_date(date_str: str, fail_silently: bool = False) -> Optional[dateti
""" """
try: try:
date_str = re.sub(r"\s+", " ", date_str) date_str = re.sub(r"\s+", " ", date_str)
date_str = re.sub("(Gestern|Yesterday):", "", date_str, re.I)
date_str = re.sub("(Heute|Today):", "", date_str, re.I)
date_str = re.sub("(Morgen|Tomorrow):", "", date_str, re.I)
date_str = re.sub("Gestern|Yesterday", _format_date_english(_yesterday()), date_str, re.I) date_str = re.sub("Gestern|Yesterday", _format_date_english(_yesterday()), date_str, re.I)
date_str = re.sub("Heute|Today", _format_date_english(date.today()), date_str, re.I) date_str = re.sub("Heute|Today", _format_date_english(date.today()), date_str, re.I)
date_str = re.sub("Morgen|Tomorrow", _format_date_english(_tomorrow()), date_str, re.I) date_str = re.sub("Morgen|Tomorrow", _format_date_english(_tomorrow()), date_str, re.I)
date_str = date_str.strip()
for german, english in zip(german_months, english_months): for german, english in zip(german_months, english_months):
date_str = date_str.replace(german, english) date_str = date_str.replace(german, english)
# Remove trailing dots for abbreviations, e.g. "20. Apr. 2020" -> "20. Apr 2020" # Remove trailing dots for abbreviations, e.g. "20. Apr. 2020" -> "20. Apr 2020"