aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/jstor.py
blob: 8c7bfad47999431d4e6f73da348de565bece1514 (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
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
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
import datetime
import json
import sys
import warnings

import fatcat_openapi_client
from bs4 import BeautifulSoup

from .common import LANG_MAP_MARC, EntityImporter, clean
from .crossref import CONTAINER_TYPE_MAP

# TODO: more entries?
JSTOR_CONTRIB_MAP = {
    "author": "author",
    "editor": "editor",
    "translator": "translator",
    "illustrator": "illustrator",
}

JSTOR_TYPE_MAP = {
    "book-review": "review-book",
    "editorial": "editorial",
    "misc": "stub",
    "news": "article",
    "research-article": "article-journal",
}


class JstorImporter(EntityImporter):
    """
    Importer for JSTOR bulk XML metadata (eg, from their Early Journals
    Collection)
    """

    def __init__(self, api, issn_map_file, **kwargs):

        eg_desc = kwargs.get("editgroup_description", "Automated import of JSTOR XML metadata")
        eg_extra = kwargs.get("editgroup_extra", dict())
        eg_extra["agent"] = eg_extra.get("agent", "fatcat_tools.JstorImporter")
        super().__init__(
            api,
            issn_map_file=issn_map_file,
            editgroup_description=eg_desc,
            editgroup_extra=eg_extra,
            **kwargs
        )

        self.create_containers = kwargs.get("create_containers", True)

        self.read_issn_map_file(issn_map_file)

    def map_container_type(self, crossref_type):
        return CONTAINER_TYPE_MAP.get(crossref_type)

    def want(self, obj):
        return True

    def parse_record(self, article):

        journal_meta = article.front.find("journal-meta")
        article_meta = article.front.find("article-meta")

        extra = dict()
        extra_jstor = dict()

        release_type = JSTOR_TYPE_MAP.get(article["article-type"])
        title = article_meta.find("article-title")
        if title and title.get_text():
            title = title.get_text().replace("\n", " ").strip()
        elif title and not title.get_text():
            title = None

        if not title and release_type.startswith("review") and article_meta.product.source:
            title = "Review: {}".format(
                article_meta.product.source.replace("\n", " ").get_text()
            )

        if not title:
            return None

        if title.endswith("."):
            title = title[:-1]

        if "[Abstract]" in title:
            # TODO: strip the "[Abstract]" bit?
            release_type = "abstract"
        elif "[Editorial" in title:
            release_type = "editorial"
        elif "[Letter" in title:
            release_type = "letter"
        elif "[Poem" in title or "[Photograph" in title:
            release_type = None

        if title.startswith("[") and title.endswith("]"):
            # strip brackets if that is all that is there (eg, translation or non-english)
            title = title[1:-1]

        # JSTOR journal-id
        journal_ids = [j.string for j in journal_meta.find_all("journal-id")]
        if journal_ids:
            extra_jstor["journal_ids"] = journal_ids

        journal_title = journal_meta.find("journal-title").get_text().replace("\n", " ")
        publisher = journal_meta.find("publisher-name").get_text().replace("\n", " ")
        issn = journal_meta.find("issn")
        if issn:
            issn = issn.string
            if len(issn) == 8:
                issn = "{}-{}".format(issn[0:4], issn[4:8])
            else:
                assert len(issn) == 9

        issnl = self.issn2issnl(issn)
        container_id = None
        if issnl:
            container_id = self.lookup_issnl(issnl)

        # create container if it doesn't exist
        if (
            container_id is None
            and self.create_containers
            and (issnl is not None)
            and journal_title
        ):
            ce = fatcat_openapi_client.ContainerEntity(
                issnl=issnl,
                publisher=publisher,
                container_type=self.map_container_type(release_type),
                name=clean(journal_title, force_xml=True),
            )
            ce_edit = self.create_container(ce)
            container_id = ce_edit.ident
            self._issnl_id_map[issnl] = container_id

        doi = article_meta.find("article-id", {"pub-id-type": "doi"})
        if doi:
            doi = doi.string.lower().strip()

        jstor_id = article_meta.find("article-id", {"pub-id-type": "jstor"})
        if jstor_id:
            jstor_id = jstor_id.string.strip()
        if not jstor_id and doi:
            assert doi.startswith("10.2307/")
            jstor_id = doi.replace("10.2307/", "")
        assert jstor_id and int(jstor_id)

        contribs = []
        cgroup = article_meta.find("contrib-group")
        if cgroup:
            for c in cgroup.find_all("contrib"):
                given = c.find("given-names")
                if given:
                    given = clean(given.get_text().replace("\n", " "))
                surname = c.find("surname")
                if surname:
                    surname = clean(surname.get_text().replace("\n", " "))
                raw_name = c.find("string-name")
                if raw_name:
                    raw_name = clean(raw_name.get_text().replace("\n", " "))

                if not raw_name:
                    if given and surname:
                        raw_name = "{} {}".format(given, surname)
                    elif surname:
                        raw_name = surname

                role = JSTOR_CONTRIB_MAP.get(c.get("contrib-type", "author"))
                if not role and c.get("contrib-type"):
                    sys.stderr.write("NOT IN JSTOR_CONTRIB_MAP: {}\n".format(c["contrib-type"]))
                contribs.append(
                    fatcat_openapi_client.ReleaseContrib(
                        role=role,
                        raw_name=raw_name,
                        given_name=given,
                        surname=surname,
                    )
                )

        for i, contrib in enumerate(contribs):
            if contrib.raw_name != "et al.":
                contrib.index = i

        release_year = None
        release_date = None
        pub_date = article_meta.find("pub-date")
        if pub_date and pub_date.year:
            release_year = int(pub_date.year.string)
            if pub_date.month and pub_date.day:
                release_date = datetime.date(
                    release_year, int(pub_date.month.string), int(pub_date.day.string)
                )
                if release_date.day == 1 and release_date.month == 1:
                    # suspect jan 1st dates get set by JSTOR when actual
                    # date not known (citation needed), so drop them
                    release_date = None

        volume = None
        if article_meta.volume:
            volume = article_meta.volume.string or None

        issue = None
        if article_meta.issue:
            issue = article_meta.issue.string or None

        pages = None
        if article_meta.find("page-range"):
            pages = article_meta.find("page-range").string
        elif article_meta.fpage:
            pages = article_meta.fpage.string

        language = None
        cm = article_meta.find("custom-meta")
        if cm.find("meta-name").string == "lang":
            language = cm.find("meta-value").string.split()[0]
            language = LANG_MAP_MARC.get(language)
            if not language:
                warnings.warn("MISSING MARC LANG: {}".format(cm.find("meta-value").string))

        # JSTOR issue-id
        if article_meta.find("issue-id"):
            issue_id = clean(article_meta.find("issue-id").string)
            if issue_id:
                extra_jstor["issue_id"] = issue_id

        # everything in JSTOR is published
        release_stage = "published"

        # extra:
        #   withdrawn_date
        #   translation_of
        #   subtitle
        #   aliases
        #   container_name
        #   group-title
        #   pubmed: retraction refs
        if extra_jstor:
            extra["jstor"] = extra_jstor
        if not extra:
            extra = None

        re = fatcat_openapi_client.ReleaseEntity(
            # work_id
            title=title,
            # original_title
            release_type=release_type,
            release_stage=release_stage,
            release_date=release_date,
            release_year=release_year,
            ext_ids=fatcat_openapi_client.ReleaseExtIds(
                doi=doi,
                jstor=jstor_id,
            ),
            volume=volume,
            issue=issue,
            pages=pages,
            publisher=publisher,
            language=language,
            # license_slug
            # content, mimetype, lang
            # abstracts=abstracts,
            contribs=contribs,
            # key, year, container_name, title, locator
            # extra: volume, authors, issue, publisher, identifiers
            # refs=refs,
            #   name, type, publisher, issnl
            #   extra: issnp, issne, original_name, languages, country
            container_id=container_id,
            extra=extra,
        )
        return re

    def try_update(self, re):

        # first, lookup existing by JSTOR id (which much be defined)
        existing = None
        try:
            existing = self.api.lookup_release(jstor=re.ext_ids.jstor)
        except fatcat_openapi_client.rest.ApiException as err:
            if err.status != 404:
                raise err

        # then try DOI lookup if there is one (try JSTOR prefix+jstor_id if
        # there isn't a DOI set)
        if not existing:
            doi = re.ext_ids.doi
            if not doi:
                doi = "10.2307/{}".format(re.ext_ids.jstor)
            try:
                existing = self.api.lookup_release(doi=doi)
            except fatcat_openapi_client.rest.ApiException as err:
                if err.status != 404:
                    raise err

        if existing and existing.ext_ids.jstor:
            # don't update if it already has JSTOR ID
            self.counts["exists"] += 1
            return False
        elif existing:
            # but do update if only DOI was set
            existing.ext_ids.jstor = re.ext_ids.jstor
            existing.extra["jstor"] = re.extra["jstor"]
            # better release_type detection, and some other fields
            # TODO: don't do this over-writing in the future? assuming here
            # this is a one-time batch import over/extending bootstrap crossref
            # metadata
            existing.release_type = re.release_type
            existing.publisher = re.publisher
            existing.contribs = re.contribs
            existing.language = re.language
            self.api.update_release(self.get_editgroup_id(), existing.ident, existing)
            self.counts["update"] += 1
            return False

        return True

    def insert_batch(self, batch):
        self.api.create_release_auto_batch(
            fatcat_openapi_client.ReleaseAutoBatch(
                editgroup=fatcat_openapi_client.Editgroup(
                    description=self.editgroup_description, extra=self.editgroup_extra
                ),
                entity_list=batch,
            )
        )

    def parse_file(self, handle):

        # 1. open with beautiful soup
        soup = BeautifulSoup(handle, "xml")

        # 2. iterate over articles, call parse_article on each
        for article in soup.find_all("article"):
            resp = self.parse_record(article)
            print(json.dumps(resp))
            # sys.exit(-1)


if __name__ == "__main__":
    parser = JstorImporter(None, None)
    parser.parse_file(open(sys.argv[1]))