Add application file

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,152 @@
+
+import requests
+import pprint
+import json
+import os
+import gradio as gr
+import requests
+from bs4 import BeautifulSoup
+
+def get_dblp_bibref(title):
+
+    print(f'DBLP query: {title}')
+
+    try:
+        # Replace spaces in the title with '+'
+        title = title.replace(' ', '+')
+
+        # Send a GET request to the DBLP search page with the paper title
+        response = requests.get(f'https://dblp.org/search/publ/api?q={title}&format=xml')
+        soup = BeautifulSoup(response.content, 'lxml')
+
+        # Get the URL of the first paper in the search results
+        url = soup.select_one('url').text + '.bib'
+        response = requests.get(url)
+
+        return response.text
+    except Exception as e:
+        return f'Error during get bibref from DBLP: {e}'
+
+# set pprint width
+pp = pprint.PrettyPrinter(width=128)
+API_KEY = 'eRLnjZeWSs4gHjSemy5af1X7IbugACFg1tSX6F3R'
+FIELDS = "paperId,title,url,year,authors,venue,abstract,citationCount,openAccessPdf,fieldsOfStudy,publicationDate,citations,references"
+
+
+# def get_name_mapping(venues_data='/nfs/delong/data/s2orc/s2ag_full/publication-venues'):
+#     name_mapping = {} # from full name to abbreviated name
+#     for file in os.listdir(venues_data):
+#         with open(os.path.join(venues_data, file), 'r') as f:
+#             venues = [json.loads(line) for line in f.readlines()]
+#             print(f"Total number of venues in {file}: {len(venues)}")
+#             for venue in venues:
+#                 if len(venue['alternate_names'])>0: 
+#                     # name_mapping[venue['name']] = venue['alternate_names'][0]
+#                     # instead of using the first alternate name, use the shortest one
+#                     name_mapping[venue['name']] = min(venue['alternate_names'], key=len)
+
+#     name_mapping['Neural Information Processing Systems'] = 'NeurIPS'
+
+#     print(f'loaded {len(name_mapping)} venues from {venues_data}')
+#     return name_mapping
+
+
+# name_mapping = get_name_mapping()
+# json.dump(name_mapping, open('name_mapping.json', 'w'), indent=4)
+
+name_mapping = json.load(open('name_mapping.json', 'r'))
+print(f'loaded {len(name_mapping)} venues from name_mapping.json')
+
+def search_paper_title_semanticscholar(title):
+    url = "https://api.semanticscholar.org/graph/v1/paper/search"
+    headers = {"Accept": "application/json", "x-api-key": API_KEY}
+    params = {"query": title, "limit": 1}
+    
+    response = requests.get(url, headers=headers, params=params)
+    
+    if response.status_code == 200:
+        data = response.json()
+        if data['total']!=0:
+            paper_id = data['data'][0]['paperId']
+            url = f"https://api.semanticscholar.org/graph/v1/paper/{paper_id}"
+            
+            params = {"fields": FIELDS}
+            response = requests.get(url, headers=headers, params=params)
+            if response.status_code == 200:
+                data = response.json()
+                return data
+            else:
+                print(f"Error: {response.status_code}")
+                return None
+        else:
+            print("No paper found with the given title.")
+            return None
+    else:
+        print(f"Error: {response.status_code}")
+        return None
+
+def get_abbreviated_venue(name):
+    if name in name_mapping:
+        return name_mapping[name]
+    else:
+        return name
+
+def get_md_citation(paper_info):
+
+    # citation_str = paper_info['authors'][0]['name'] + " *et al.* "
+    citation_str = ', '.join([author['name'] for author in paper_info['authors']]) + '. '
+    citation_str += f"[**{paper_info['title']}**]({paper_info['url']}). "
+    citation_str += f"*{get_abbreviated_venue(paper_info['venue'])}*"
+    # citation_str += f" ({paper_info['year']})."
+    citation_str += f" ({paper_info['publicationDate'][:-3].replace('-', '.')})."
+    return citation_str
+
+def summarize_paper_info(paper_info):
+    info_str = ""
+    # info_str += f"**Venue**: {paper_info['venue']}\n\n"
+
+    author_str = ''
+    for author in paper_info['authors']:
+        author_str += f"[{author['name']}](https://www.semanticscholar.org/author/{author['authorId']}), "
+    author_str = author_str[:-2]
+
+    info_str += f"**Authors**: {author_str}\n\n"
+
+    info_str += f"**Abstract**: {paper_info['abstract']}\n\n"
+    info_str += f"**Citation Count**: {paper_info['citationCount']}\n\n"
+    return info_str
+
+def get_output(title):
+    print(f"Title query: {title}")
+
+    paper_info = search_paper_title_semanticscholar(title)
+    if paper_info is not None:
+        citation_str = get_md_citation(paper_info)
+    else:
+        citation_str = "No paper found with that title."
+
+    citation_str = f"""
+**Citation**:
+\n\n{citation_str}\n\n
+**Markdown source code**:\n\n```markdown\n{citation_str}\n```\n\n
+**BibTex**\n\n```bibtex\n{get_dblp_bibref(paper_info['title'])}\n```\n\n
+---
+\n\n{summarize_paper_info(paper_info)}\n\n
+"""
+
+    print(citation_str)
+
+    return citation_str
+
+def main():
+    iface = gr.Interface(fn=get_output, 
+                         inputs=gr.components.Textbox(lines=2, label="Please input the title of the paper"), 
+                         outputs="markdown", 
+                         allow_flagging='never',
+                         title="Citation Tool",
+                         )
+    iface.launch()
+
+if __name__=="__main__":
+    main()
+

name_mapping.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36b822eb89d6d428f67c84a4611be067f3ba2231f35ad703752994a71fb761ac
+size 14314956

requirements.txt

@@ -0,0 +1,3 @@
+lxml
+gradio
+beautifulsoup4