Spico commited on
Commit
02e4a72
·
1 Parent(s): 796eb82

fix acl author

Browse files
Files changed (2) hide show
  1. run.py +3 -7
  2. src/interfaces/aclanthology.py +10 -6
run.py CHANGED
@@ -2,8 +2,8 @@ from src.interfaces.aclanthology import AclanthologyPaperList
2
  from src.interfaces.arxiv import ArxivPaperList
3
  from src.interfaces.dblp import DblpPaperList
4
  from src.utils import (
5
- dump_paper_list_to_markdown_checklist,
6
  dump_paper_list_to_jsonlines,
 
7
  )
8
 
9
  if __name__ == "__main__":
@@ -85,9 +85,7 @@ if __name__ == "__main__":
85
  dump_paper_list_to_markdown_checklist(
86
  arxiv_ee_papers, "results/arxiv-ee-paper-list.md"
87
  )
88
- dump_paper_list_to_jsonlines(
89
- arxiv_ee_papers, "results/arxiv-ee-paper-list.jsonl"
90
- )
91
 
92
  # dblp papers
93
  dblp_paper_list = DblpPaperList(
@@ -124,6 +122,4 @@ if __name__ == "__main__":
124
  dump_paper_list_to_markdown_checklist(
125
  dblp_ee_papers, "results/dblp-ee-paper-list.md"
126
  )
127
- dump_paper_list_to_jsonlines(
128
- dblp_ee_papers, "results/dblp-ee-paper-list.jsonl"
129
- )
 
2
  from src.interfaces.arxiv import ArxivPaperList
3
  from src.interfaces.dblp import DblpPaperList
4
  from src.utils import (
 
5
  dump_paper_list_to_jsonlines,
6
+ dump_paper_list_to_markdown_checklist,
7
  )
8
 
9
  if __name__ == "__main__":
 
85
  dump_paper_list_to_markdown_checklist(
86
  arxiv_ee_papers, "results/arxiv-ee-paper-list.md"
87
  )
88
+ dump_paper_list_to_jsonlines(arxiv_ee_papers, "results/arxiv-ee-paper-list.jsonl")
 
 
89
 
90
  # dblp papers
91
  dblp_paper_list = DblpPaperList(
 
122
  dump_paper_list_to_markdown_checklist(
123
  dblp_ee_papers, "results/dblp-ee-paper-list.md"
124
  )
125
+ dump_paper_list_to_jsonlines(dblp_ee_papers, "results/dblp-ee-paper-list.jsonl")
 
 
src/interfaces/aclanthology.py CHANGED
@@ -15,7 +15,7 @@ class AclanthologyPaperList(SearchAPI):
15
  self.papers = []
16
  for d in data:
17
  authors = " , ".join(
18
- [self.extract_author_full(author) for author in d.get("authors", [])]
19
  )
20
  venue = d.get("venue", [])
21
  if venue:
@@ -36,9 +36,13 @@ class AclanthologyPaperList(SearchAPI):
36
  continue
37
  self.papers.append(paper)
38
 
39
- def extract_author_full(self, name: str) -> str:
40
- match = re.search(r".*?\((.*?)\)", name)
41
- if match:
42
- return match.group(1)
 
 
43
  else:
44
- return name
 
 
 
15
  self.papers = []
16
  for d in data:
17
  authors = " , ".join(
18
+ [self.extract_author_full(author) for author in d.get("author", [])]
19
  )
20
  venue = d.get("venue", [])
21
  if venue:
 
36
  continue
37
  self.papers.append(paper)
38
 
39
+ def extract_author_full(self, name: dict) -> str:
40
+ full_name = ""
41
+ if hasattr(name, "full"):
42
+ match = re.search(r".*?\((.*?)\)", name)
43
+ if match:
44
+ full_name = match.group(1)
45
  else:
46
+ full_name = f"{name['first']} {name['last']}"
47
+
48
+ return full_name