tim/africat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add reminder about old categories

Browse Source
This commit is contained in:
Timothy Allen 2023-12-02 00:17:58 +02:00
parent 46f533746e
commit 5dd850d1cb
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
africat/aa_create_dataset.py
View File

@ -96,6 +96,8 @@ def parse_and_extract(input_dir, verbose):
cats = list() cats = list()
for cat in doc.findall('./category'): for cat in doc.findall('./category'):
# TODO check against a list of current categories,
# and strip any non-current categories
cats.append(cat.text) cats.append(cat.text)
#entry["categories"] = cats # if you want a list #entry["categories"] = cats # if you want a list
entry["categories"] = ";".join(cats) # if you want a string entry["categories"] = ";".join(cats) # if you want a string