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
135
136
137
138
139
140
|
import sys
import json
import itertools
import fatcat_client
from .common import EntityImporter, clean
def or_none(s):
if s is None:
return None
if len(s) == 0:
return None
return s
def truthy(s):
if s is None:
return None
s = s.lower()
if s in ('true', 't', 'yes', 'y', '1'):
return True
elif s in ('false', 'f', 'no', 'n', '0'):
return False
else:
return None
class JournalMetadataImporter(EntityImporter):
"""
Imports journal metadata ("containers") by ISSN, currently from a custom
munged JSON format (see ../extra/journal_metadata/).
See guide for details on the many 'extra' fields used here.
"""
def __init__(self, api, **kwargs):
eg_desc = kwargs.get('editgroup_description',
"Automated import of container-level metadata, by ISSN. Metadata from Internet Archive munging.")
eg_extra = kwargs.get('editgroup_extra', dict())
eg_extra['agent'] = eg_extra.get('agent', 'fatcat_tools.JournalMetadataImporter')
super().__init__(api,
editgroup_description=eg_desc,
editgroup_extra=eg_extra,
**kwargs)
def want(self, raw_record):
if raw_record.get('issnl') and raw_record.get('name'):
return True
return False
def parse_record(self, row):
"""
row is a python dict (parsed from JSON).
returns a ContainerEntity (or None if invalid or couldn't parse)
"""
if not row.get('name'):
# Name is required (by schema)
return None
extra = dict()
for key in ('issne', 'issnp', 'languages', 'country', 'urls', 'abbrev',
'coden', 'aliases', 'original_name', 'first_year', 'last_year',
'platform', 'default_license', 'road', 'mimetypes',
'sherpa_romeo', 'kbart'):
if row.get(key):
extra[key] = row[key]
# TODO: not including for now: norwegian, dois/crossref, ia
extra_doaj = dict()
if row.get('doaj'):
if row['doaj'].get('as_of'):
extra_doaj['as_of'] = row['doaj']['as_of']
if row['doaj'].get('works'):
extra_doaj['works'] = row['doaj']['works']
if extra_doaj:
extra['doaj'] = extra_doaj
extra_ia = dict()
# TODO: would like an ia.longtail_ia flag
if row.get('sim'):
# NB: None case of the .get() here is blech, but othrwise
# extra['ia'].get('sim') would be false-y, breaking 'any_ia_sim' later on
extra_ia['sim'] = {
'year_spans': row['sim'].get('year_spans'),
}
if extra_ia:
extra['ia'] = extra_ia
name = clean(row.get('name'))
if not name:
return None
ce = fatcat_client.ContainerEntity(
issnl=row['issnl'],
container_type=None, # TODO
name=name,
publisher=clean(row.get('publisher')),
wikidata_qid=None, # TODO
extra=extra)
return ce
def try_update(self, ce):
existing = None
try:
existing = self.api.lookup_container(issnl=ce.issnl)
except fatcat_client.rest.ApiException as err:
if err.status != 404:
raise err
if not existing:
# doesn't exist, create it
return True
# for now, only update KBART, and only if there is new content
if not existing.extra:
existing.extra = dict()
if ce.extra.get('kbart') and (existing.extra.get('kbart') != ce.extra['kbart']):
if not existing.extra.get('kbart'):
existing.extra['kbart'] = {}
existing.extra['kbart'].update(ce.extra['kbart'])
self.api.update_container(self.get_editgroup_id(), existing.ident, existing)
self.counts['update'] += 1
return False
else:
self.counts['exists'] += 1
return False
# if we got this far, it's a bug
raise NotImplementedError
def insert_batch(self, batch):
self.api.create_container_auto_batch(fatcat_client.ContainerAutoBatch(
editgroup=fatcat_client.Editgroup(
description=self.editgroup_description,
extra=self.editgroup_extra),
entity_list=batch))
|