Spaces:
Sleeping
Sleeping
File size: 4,578 Bytes
ea4d0fa 2f27244 a9127b0 2f27244 6c04839 ea4d0fa 481f2d5 67105c9 6f5ef35 b5793e9 b04cbde cf8d7e8 b04cbde 0d8ea05 cf8d7e8 ea4d0fa |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
import httpx
from cytoolz import groupby
from functools import lru_cache
from rich import print
from functools import partial
import gradio as gr
from typing import Optional
def query_author(author_name: str):
url = f"https://api.semanticscholar.org/graph/v1/author/search?query={author_name}&fields=name,url,externalIds,papers.externalIds,papers.title,papers.year"
resp = httpx.get(url)
resp.raise_for_status()
return resp.json()["data"]
def get_arxiv_paper(papers):
papers_with_externalIds = [paper for paper in papers if paper.get("externalIds")]
return [
paper for paper in papers_with_externalIds if paper["externalIds"].get("ArXiv")
]
def check_arxiv_in_papers(arxiv_ids, papers):
papers_with_externalIds = [paper for paper in papers if paper.get("externalIds")]
papers_with_arxiv_ids = [
paper for paper in papers_with_externalIds if paper["externalIds"].get("ArXiv")
]
return any(
paper
for paper in papers_with_arxiv_ids
if paper["externalIds"].get("ArXiv") in arxiv_ids
)
def get_author_from_options(potential_authors, positive_arxiv_ids):
return next(
(
author
for author in potential_authors
if check_arxiv_in_papers(set(positive_arxiv_ids), author["papers"])
),
None,
)
def sort_by_date(papers):
return sorted(papers, key=lambda paper: paper["year"], reverse=True)
@lru_cache()
def lookup_hf_paper(arxiv_id):
url = f"https://huggingface.co/api/papers/{arxiv_id}"
resp = httpx.get(url)
return resp.json()
def check_if_index_hf_paper(paper):
arxiv_id = paper["externalIds"]["ArXiv"]
data = lookup_hf_paper(arxiv_id)
return not data.get("error")
def groupby_indexed_by_hf_papers(papers):
return groupby(check_if_index_hf_paper, papers)
def check_hf_user_in_authors(paper, hf_user_name):
authors = paper["authors"]
authors = [author for author in authors if author.get("user")]
return any(author["user"]["user"] == hf_user_name for author in authors)
def groupby_hf_user_papers(papers, hf_user_name):
check_hf_user_in_authors_partial = partial(
check_hf_user_in_authors, hf_user_name=hf_user_name
)
return groupby(check_hf_user_in_authors_partial, papers)
def get_papers(
author_name, positive_arxiv_ids, hf_user_name: Optional[gr.OAuthProfile]
):
hf_user_name = hf_user_name.preferred_username
positive_arxiv_ids = positive_arxiv_ids.split(",")
potential_authors = query_author(author_name)
author = get_author_from_options(potential_authors, positive_arxiv_ids)
papers = get_arxiv_paper(author["papers"])
papers = sort_by_date(papers)
papers_indexed_by_hf = groupby_indexed_by_hf_papers(papers)
# print(papers_indexed_by_hf[True])
indexed_papers = [
lookup_hf_paper(paper["externalIds"]["ArXiv"])
for paper in papers_indexed_by_hf[True]
]
already_claimed = groupby_hf_user_papers(indexed_papers, hf_user_name)
results = (
"# Papers already indexed by Hugging Face which you haven't claimed\n"
+ "These papers are already indexed by Hugging Face, but you haven't claimed them yet. You can claim them by clicking on the link and then clicking on the 'Claim' button on the Hugging Face papers page.\n"
)
for paper in already_claimed[False]:
url = f"https://huggingface.co/papers/{paper['id']}"
results += f"- [{paper['title']}]({url})\n"
if len(papers_indexed_by_hf[False]) > 0:
results += f"# Papers not yet indexed by Hugging Face\n"
for paper in papers_indexed_by_hf[False]:
paper_title = paper["title"]
arxiv_id = paper["externalIds"]["ArXiv"]
url = f"https://huggingface.co/papers/{arxiv_id}"
results += f"- [{paper_title}]({url})\n"
return results
with gr.Blocks() as demo:
gr.HTML("<h1 style='text-align:center;'>Hugging Face Paper Claimer</h1>")
gr.Markdown("This Space helps you claim your papers on Hugging Face papers")
with gr.Row():
gr.LoginButton(size="sm")
gr.LogoutButton(size="sm")
author_name = gr.Textbox(
placeholder="daniel van strien", label="Your name", interactive=True
)
positive_arxiv_ids = gr.Textbox(
placeholder="1910.01108",
label="ArXiv ID for a paper for which you are an author",
interactive=True,
)
btn = gr.Button("Get papers")
btn.click(get_papers, [author_name, positive_arxiv_ids], gr.Markdown())
demo.launch(debug=True)
|