1
0

redoing the dedup csv, something wrong with the other one

This commit is contained in:
mgaughan 2025-05-30 13:52:13 -05:00
parent d7e3d54e0f
commit 83e9f3b25c
4 changed files with 3081 additions and 13362 deletions

File diff suppressed because one or more lines are too long

3049
cites/auto_dedup_results.csv Normal file

File diff suppressed because one or more lines are too long

16
cites/bib_to_csv.py Normal file
View File

@ -0,0 +1,16 @@
import csv
import bibtexparser
from tqdm import tqdm
with open("auto_dedup_results.bib") as bibfile:
bib_db = bibtexparser.load(bibfile)
fields = ['duplicate_id', 'bibtype', 'title', 'abstract', 'doi']
with open('auto_dedup_results.csv', 'w', newline="", encoding='utf-8') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fields)
writer.writeheader()
for entry in tqdm(bib_db.entries, desc="Converting BibTeX to CSV"):
row = {field: entry.get(field, '') for field in fields}
writer.writerow(row)

16
cites/shell.nix Normal file
View File

@ -0,0 +1,16 @@
{
pkgs ? import <nixpkgs> { },
}:
pkgs.mkShell {
name = "trial-env";
packages = with pkgs; [
pkgs.python312
pkgs.python312Packages.bibtexparser
pkgs.python312Packages.tqdm
git
];
shellHook = ''
echo "trying to find a good quote for here"
'';
}