blob: 253940ce2a612413d8d4699b558613593ccd97fd (
plain)
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
|
import csv
from typing import Iterable, Optional
from chocula.util import clean_str, clean_issn, parse_lang, parse_country
from chocula.common import DirectoryLoader
from chocula.database import DirectoryInfo
class VanishedInactiveLoader(DirectoryLoader):
"""
Journal-level metadata from the "Vanished Journals" project. This is the
"inactive" dataset.
CSV headers:
- Source
- Title
- Identifier
- Publisher
- Comment
- Language
- ISSN
- EISSN
- Keyword
- Start Year
- End Year
- Added on date
- Subjects
- Country
- Publication fee
- Further Information
"""
source_slug = "vanished_inactive"
def open_file(self) -> Iterable:
return csv.DictReader(open(self.config.vanished_inactive.filepath))
def parse_record(self, record) -> Optional[DirectoryInfo]:
info = DirectoryInfo(
directory_slug=self.source_slug,
raw_issn=clean_issn(record["ISSN"]),
issne=clean_issn(record["EISSN"]),
name=clean_str(record["Title"]),
publisher=clean_str(record["Publisher"]),
langs=[lang for lang in [parse_lang(record["Language"])] if lang],
country=parse_country(record["Country"]),
)
return info
|