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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251 | def build_metadata_dict(pkg_dict):
"""
Build/extract a basic dict of metadata that can then be passed to build_xml_dict.
:param pkg_dict: dict of package details
"""
metadata_dict = {}
# collect errors instead of throwing them immediately; some data may not be correctly handled
# by this base method but will be handled correctly by plugins that implement IDoi
errors = {}
# required fields first (identifier will be added later)
required = {
'creators': [],
'titles': [],
'publisher': None,
'publicationYear': None,
'resourceType': None,
}
def _add_required(key, get_func):
try:
required[key] = get_func()
except Exception as e:
errors[key] = e
# CREATORS
_add_required('creators', lambda: [{'full_name': pkg_dict.get('author')}])
# TITLES
_add_required('titles', lambda: [{'title': pkg_dict.get('title')}])
# PUBLISHER
_add_required('publisher', lambda: toolkit.config.get('ckanext.doi.publisher'))
# PUBLICATION YEAR
_add_required('publicationYear', lambda: package_get_year(pkg_dict))
# TYPE
_add_required('resourceType', lambda: pkg_dict.get('type'))
# now the optional fields
optional = {
'subjects': [],
'contributors': [],
'dates': [],
'language': '',
'alternateIdentifiers': [],
'relatedIdentifiers': [],
'sizes': [],
'formats': [],
'version': '',
'rightsList': [],
'descriptions': [],
'geolocations': [],
'fundingReferences': [],
}
# SUBJECTS
# use the tag list
try:
tags = pkg_dict.get('tag_string', '').split(',')
tags += [
tag['name'] if isinstance(tag, dict) else tag
for tag in pkg_dict.get('tags', [])
]
optional['subjects'] = [
{'subject': tag} for tag in sorted({t for t in tags if t != ''})
]
except Exception as e:
errors['subjects'] = e
# CONTRIBUTORS
# use the author and maintainer; no splitting or parsing for either
# no try/except for this because it's just a simple .get() and if that doesn't work then we
# want to know
author = pkg_dict.get('author')
maintainer = pkg_dict.get('maintainer')
if author is not None:
optional['contributors'].append(
{'contributor_type': 'Researcher', 'full_name': author}
)
if maintainer is not None:
optional['contributors'].append(
{'contributor_type': 'DataManager', 'full_name': maintainer}
)
# DATES
# created, updated, and doi publish date
date_errors = {}
try:
optional['dates'].append(
{
'dateType': 'Created',
'date': date_or_none(pkg_dict.get('metadata_created')),
}
)
except Exception as e:
date_errors['created'] = e
try:
optional['dates'].append(
{
'dateType': 'Updated',
'date': date_or_none(pkg_dict.get('metadata_modified')),
}
)
except Exception as e:
date_errors['updated'] = e
if 'doi_date_published' in pkg_dict:
try:
optional['dates'].append(
{
'dateType': 'Issued',
'date': date_or_none(pkg_dict.get('doi_date_published')),
}
)
except Exception as e:
date_errors['doi_date_published'] = e
# LANGUAGE
# use language set in CKAN
try:
optional['language'] = ckan_lang()
except Exception as e:
errors['language'] = e
# ALTERNATE IDENTIFIERS
# add permalink back to this site
try:
permalink = f'{get_site_url()}/dataset/{pkg_dict["id"]}'
optional['alternateIdentifiers'] = [
{'alternateIdentifierType': 'URL', 'alternateIdentifier': permalink}
]
except Exception as e:
errors['alternateIdentifiers'] = e
# RELATED IDENTIFIERS
# nothing relevant in default schema
# SIZES
# sum up given sizes from resources in the package and convert from bytes to kilobytes
try:
resource_sizes = [
r.get('size') or 0 for r in pkg_dict.get('resources', []) or []
]
total_size = [f'{int(sum(resource_sizes) / 1024)} kb']
optional['sizes'] = total_size
except Exception as e:
errors['sizes'] = e
# FORMATS
# list unique formats from package resources
try:
formats = list(
set(
filter(
None, [r.get('format') for r in pkg_dict.get('resources', []) or []]
)
)
)
optional['formats'] = formats
except Exception as e:
errors['formats'] = e
# VERSION
# doesn't matter if there's no version, it'll get filtered out later
optional['version'] = pkg_dict.get('version')
# RIGHTS
# use the package license and get details from CKAN's license register
license_id = pkg_dict.get('license_id', 'notspecified')
try:
if license_id != 'notspecified' and license_id is not None:
license_register = Package.get_license_register()
license = license_register.get(license_id)
if license is not None:
optional['rightsList'] = [
{'rightsURI': license.url, 'rightsIdentifier': license.id}
]
except Exception as e:
errors['rightsList'] = e
# DESCRIPTIONS
# use package notes
optional['descriptions'] = [
{'descriptionType': 'Other', 'description': pkg_dict.get('notes', '')}
]
# GEOLOCATIONS
# nothing relevant in default schema
# FUNDING
# nothing relevant in default schema
metadata_dict.update(required)
metadata_dict.update(optional)
for plugin in PluginImplementations(IDoi):
# implementations should remove relevant errors from the errors dict if they successfully
# handle an item
metadata_dict, errors = plugin.build_metadata_dict(
pkg_dict, metadata_dict, errors
)
for k in required:
if metadata_dict.get(k) is None and errors.get(k) is None:
errors[k] = DOIMetadataException('Required field cannot be None')
required_errors = {k: e for k, e in errors.items() if k in required}
if len(required_errors) > 0:
error_msg = (
f'Could not extract metadata for the following required keys: '
f'{", ".join(required_errors)}'
)
log.exception(error_msg)
for k, e in required_errors.items():
log.exception(f'{k}: {e}')
raise DOIMetadataException(error_msg)
optional_errors = {k: e for k, e in errors.items() if k in optional}
if len(required_errors) > 0:
error_msg = (
f'Could not extract metadata for the following optional keys: '
f'{", ".join(optional_errors)}'
)
log.debug(error_msg)
for k, e in optional_errors.items():
log.debug(f'{k}: {e}')
return metadata_dict
|