summaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/chocula.py
blob: d08a98e092a19e8ec4fe1a17e290e93e7749e6be (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
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174

import fatcat_openapi_client
from .common import EntityImporter, clean


class ChoculaImporter(EntityImporter):
    """
    Creates or updates container entities based on output of "chocula" script,
    which munges/processes journal metadata from several sources, including
    fatcat itself.

    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 from Chocula tool.")
        eg_extra = kwargs.get('editgroup_extra', dict())
        eg_extra['agent'] = eg_extra.get('agent', 'fatcat_tools.ChoculaImporter')
        super().__init__(api,
            editgroup_description=eg_desc,
            editgroup_extra=eg_extra,
            **kwargs)

    def want(self, raw_record):
        if not raw_record.get('ident') and not raw_record.get('_known_issnl'):
            self.counts['skip-unknown-new-issnl'] += 1
            return False
        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)
        """

        name = clean(row.get('name'))
        if not name:
            # Name is required (by schema)
            return None

        name = name.strip()

        if name.endswith(',  Proceedings of the'):
            name = "Proceedings of the " + name.split(',')[0]

        if name.endswith('.'):
            name = name[:-1]

        extra = dict()
        for k in ('urls', 'webarchive_urls', 'issne', 'issnp', 'country',
                  'sherpa_romeo', 'ezb', 'szczepanski', 'doaj', 'languages',
                  'ia', 'scielo', 'kbart', 'publisher_type', 'platform'):
            if row['extra'].get(k):
                extra[k] = row['extra'][k]

        container_type = None
        if 'proceedings' in name.lower():
            container_type = 'proceedings'
        elif 'journal ' in name.lower():
            container_type = 'journal'

        ce = fatcat_openapi_client.ContainerEntity(
            issnl=row['issnl'],
            ident=row['ident'],
            name=name,
            container_type=container_type,
            publisher=clean(row.get('publisher')),
            wikidata_qid=row.get('wikidata_qid'),
            extra=extra)
        return ce

    def try_update(self, ce):

        existing = None
        if ce.ident:
            try:
                existing = self.api.get_container(ce.ident)
            except fatcat_openapi_client.rest.ApiException as err:
                if err.status != 404:
                    raise err
                self.counts['exists'] += 1
                self.counts['exists-not-found'] += 1
                return False
            if existing.state != 'active':
                self.counts['exists'] += 1
                self.counts['exists-inactive'] += 1
                return False

        if not existing:
            # check if existing by ISSN-L
            try:
                existing = self.api.lookup_container(issnl=ce.issnl)
            except fatcat_openapi_client.rest.ApiException as err:
                if err.status != 404:
                    raise err
            if existing:
                self.counts['exists'] += 1
                self.counts['exists-by-issnl'] += 1
                return False
            # doesn't exist, always create
            return True

        # decide whether to update
        do_update = False
        if not self.do_updates:
            self.counts['exists'] += 1
            return False
        if not existing.extra:
            existing.extra = dict()
        if set(ce.extra.get('urls', [])) != set(existing.extra.get('urls', [])):
            do_update = True
        if set(ce.extra.get('webarchive_urls', [])) != set(existing.extra.get('webarchive_urls', [])):
            do_update = True
        for k in ('ezb', 'szczepanski', 'publisher_type', 'platform'):
            if ce.extra.get(k) and not existing.extra.get(k):
                do_update = True
        for k in ('kbart', 'ia', 'doaj'):
            # always update these fields if not equal (chocula override)
            if ce.extra.get(k) and ce.extra[k] != existing.extra.get(k):
                do_update = True
        if ce.publisher and not existing.publisher:
            do_update = True
        if ce.wikidata_qid and not existing.wikidata_qid:
            do_update = True

        if do_update:
            existing.wikidata_qid = existing.wikidata_qid or ce.wikidata_qid
            existing.publisher = existing.publisher or ce.publisher
            existing.container_type = existing.container_type or ce.container_type
            for k in ('urls', 'webarchive_urls'):
                # always update if available. should probably make this more
                # careful/subtle in the future!
                # note: in some cases we might *want* to remove existing (if
                # all URLs found to be bad), but being
                # conservative/inclusionist for now
                if ce.extra.get(k):
                    existing.extra[k] = ce.extra.get(k, [])
            for k in ('sherpa_romeo', 'ezb', 'szczepanski', 'doaj', 'ia',
                      'scielo', 'kbart', 'publisher_type', 'platform'):
                # always update (chocula over-rides)
                if ce.extra.get(k):
                    existing.extra[k] = ce.extra[k]
            for k in ('issne', 'issnp', 'country'):
                # only include if not set (don't clobber human edits)
                if ce.extra.get(k) and not existing.extra.get(k):
                    existing.extra[k] = ce.extra[k]
            if ce.extra.get('languages'):
                if not existing.extra.get('languages'):
                    existing.extra['languages'] = ce.extra['languages']
                elif not ce.extra['languages'][0] in existing.extra['languages']:
                    existing.extra['languages'].append(ce.extra['languages'][0])

            self.api.update_container(self.get_editgroup_id(), existing.ident, existing)
            self.counts['update'] += 1
            return False
        else:
            self.counts['exists'] += 1
            self.counts['exists-skip-update'] += 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_openapi_client.ContainerAutoBatch(
            editgroup=fatcat_openapi_client.Editgroup(
                description=self.editgroup_description,
                extra=self.editgroup_extra),
            entity_list=batch))