aboutsummaryrefslogtreecommitdiffstats
path: root/fatcat_scholar/schema.py
blob: 29bbe9204a9c12e49b913c6514cfe68f4ac0520a (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
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
"""
Originally wrote these as dataclasses using pydantic.dataclasses, but we don't
get serialization for free with those. This is useful for things like
auto-conversion of datetime objects.
"""

import re
import datetime
from enum import Enum
from typing import Optional, List, Any

import ftfy
from pydantic import BaseModel
from bs4 import BeautifulSoup

from fatcat_openapi_client import ReleaseEntity, ReleaseContrib
from fatcat_scholar.api_entities import entity_to_dict


class DocType(str, Enum):
    work = "work"
    sim_page = "sim_page"


class IntermediateBundle(BaseModel):
    doc_type: DocType
    releases: List[ReleaseEntity]
    biblio_release_ident: Optional[str]
    grobid_fulltext: Optional[Any]
    pdftotext_fulltext: Optional[Any]
    sim_fulltext: Optional[Any]

    class Config:
        arbitrary_types_allowed = True
        json_encoders = {
            ReleaseEntity: lambda re: entity_to_dict(re),
        }


class AccessType(str, Enum):
    ia_sim = "ia_sim"
    ia_file = "ia_file"
    wayback = "wayback"
    web = "web"
    repository = "repository"
    paywall = "paywall"
    loginwall = "loginwall"
    shadow = "shadow"


class ScholarBiblio(BaseModel):
    release_ident: Optional[str]
    title: Optional[str]
    subtitle: Optional[str]
    original_title: Optional[str]
    release_date: Optional[datetime.date]
    release_year: Optional[int]
    release_type: Optional[str]
    release_stage: Optional[str]
    withdrawn_status: Optional[str]
    lang_code: Optional[str]
    country_code: Optional[str]
    volume: Optional[str]
    volume_int: Optional[str]  # TODO: needed?
    issue: Optional[str]
    issue_int: Optional[str]  # TODO: needed?
    pages: Optional[str]
    first_page: Optional[str]
    first_page_int: Optional[str]  # TODO: needed?
    number: Optional[str]

    doi: Optional[str]
    doi_prefix: Optional[str]
    doi_registrar: Optional[str]
    pmid: Optional[str]
    pmcid: Optional[str]
    isbn13: Optional[str]
    wikidata_qid: Optional[str]
    arxiv_id: Optional[str]
    jstor_id: Optional[str]
    mag_id: Optional[str]

    license_slug: Optional[str]
    publisher: Optional[str]
    publisher_type: Optional[str]
    container_name: Optional[str]
    container_original_name: Optional[str]
    container_ident: Optional[str]
    container_issnl: Optional[str]
    container_wikidata_qid: Optional[str]
    issns: List[str]
    container_type: Optional[str]
    contrib_count: Optional[int]
    contrib_names: List[str]
    affiliations: List[str]


class ScholarFulltext(BaseModel):
    lang_code: Optional[str]
    body: str
    acknowledgement: Optional[str]
    annex: Optional[str]
    release_ident: Optional[str]
    file_ident: Optional[str]
    file_sha1: Optional[str]
    file_mimetype: Optional[str]
    thumbnail_url: Optional[str]
    access_url: Optional[str]
    access_type: Optional[AccessType]


class ScholarRelease(BaseModel):
    ident: Optional[str]
    revision: Optional[str]
    title: str
    release_date: Optional[datetime.date]
    release_year: Optional[int]
    release_type: Optional[str]
    release_stage: Optional[str]
    withdrawn_status: Optional[str]

    doi: Optional[str]
    doi_prefix: Optional[str]
    doi_registrar: Optional[str]
    pmid: Optional[str]
    pmcid: Optional[str]
    isbn13: Optional[str]
    wikidata_qid: Optional[str]
    arxiv_id: Optional[str]
    jstor_id: Optional[str]
    mag_id: Optional[str]

    license_slug: Optional[str]
    container_name: Optional[str]
    container_ident: Optional[str]
    container_issnl: Optional[str]
    container_type: Optional[str]


class ScholarSim(BaseModel):
    issue_item: str
    pub_collection: str
    sim_pubid: str
    first_page: Optional[str]


class ScholarAbstract(BaseModel):
    body: str
    lang_code: Optional[str]


class ScholarAccess(BaseModel):
    access_type: AccessType
    access_url: str
    mimetype: Optional[str]
    file_ident: Optional[str]
    release_ident: Optional[str]


class ScholarDoc(BaseModel):
    key: str
    doc_type: str  # enum: work or page
    doc_index_ts: datetime.datetime
    work_ident: Optional[str]
    tags: List[str] = []

    biblio: ScholarBiblio
    fulltext: Optional[ScholarFulltext]
    ia_sim: Optional[ScholarSim]
    abstracts: List[ScholarAbstract]
    releases: List[ScholarRelease]
    access: List[ScholarAccess]


def doi_split_prefix(doi: str) -> str:
    return doi.split("/")[0]


def release_doi_registrar(release: ReleaseEntity) -> Optional[str]:
    if not release.ext_ids.doi or not release.extra:
        return None
    for registrar in ("crossref", "datacite", "jalc"):
        if registrar in release.extra:
            return registrar
    # TODO: should we default to Crossref?
    return None


UNWANTED_ABSTRACT_PREFIXES = [
    # roughly sort this long to short
    "Abstract No Abstract ",
    "Publisher Summary ",
    "Abstract ",
    "ABSTRACT ",
    "Summary ",
    "Background: ",
    "Background ",
]


def scrub_text(raw: str, mimetype: str = None) -> str:
    """
    This function takes a mimetype-hinted string and tries to reduce it to a
    simple token-and-punctuation scheme with any and all markup removed. Eg,
    HTML tags, JATS XML tags, LaTeX, whatever.

    The output should be clean and "HTML safe" (though should still be escaped
    in HTML to get entity encoding correct).

    TODO: not using mimetype hint for latex yet
    """
    text = ftfy.fix_text(raw)

    # remove HTML
    text = BeautifulSoup(text, "html.parser").get_text()

    # TODO: for performance, compile these as globals?
    # Three regexes below adapted from Blendle cleaner.py
    # https://github.com/blendle/research-summarization/blob/master/enrichers/cleaner.py#L29
    text = re.sub(r"…", "...", text)
    text = re.sub(r"[`‘’‛⸂⸃⸌⸍⸜⸝]", "'", text)
    text = re.sub(r"[„“]|(\'\')|(,,)", '"', text)
    text = re.sub(r"\s+", " ", text).strip()

    # hack to remove abstract prefixes
    for prefix in UNWANTED_ABSTRACT_PREFIXES:
        if text.startswith(prefix):
            text = text[len(prefix) :]
            break

    assert text, "Empty abstract"
    return text


def contrib_name(contrib: ReleaseContrib) -> str:
    # TODO: support more cultural normals for name presentation
    if contrib.raw_name:
        return contrib.raw_name
    elif contrib.given_name and contrib.surname:
        return f"{contrib.given_name} {contrib.surname}"
    elif contrib.surname:
        return contrib.surname
    else:
        return contrib.given_name


def contrib_affiliation(contrib: ReleaseContrib) -> Optional[str]:
    # TODO
    return None


def es_abstracts_from_release(release: ReleaseEntity) -> List[ScholarAbstract]:

    d = dict()
    for abst in release.abstracts:
        if abst.lang not in d:
            d[abst.lang] = ScholarAbstract(
                lang_code=abst.lang, body=scrub_text(abst.content)
            )
    return list(d.values())


def es_biblio_from_release(release: ReleaseEntity) -> ScholarBiblio:

    if release.container:
        publisher = release.publisher
        container_name = release.container.name
        container_original_name = (
            release.container.extra and release.container.extra.get("original_name")
        )
        container_ident = release.container.ident
        container_type = release.container.container_type
        container_issnl = release.container.issnl
        issns = [
            container_issnl,
        ]
        if release.extra.get("issne"):
            issns.append(release.extra["issne"])
        if release.extra.get("issnp"):
            issns.append(release.extra["issnp"])
        issns = list(set(issns))
    else:
        publisher = release.extra.get("publisher")
        container_name = release.extra.get("container_name")
        container_original_name = None
        container_ident = None
        container_type = None
        container_issnl = None
        issns = []

    first_page: Optional[str] = None
    if release.pages:
        first_page = release.pages.split("-")[0]
    first_page_int: Optional[int] = None
    if first_page and first_page.isdigit():
        first_page_int = int(first_page)

    ret = ScholarBiblio(
        release_ident=release.ident,
        title=release.title,
        subtitle=release.subtitle,
        original_title=release.original_title,
        release_date=release.release_date,
        release_year=release.release_year,
        release_type=release.release_type,
        release_stage=release.release_stage,
        withdrawn_status=release.withdrawn_status,
        lang_code=release.language,
        country_code=release.extra and release.extra.get("country"),
        volume=release.volume,
        volume_int=None,
        issue=release.issue,
        issue_int=None,
        pages=release.pages,
        first_page=first_page,
        first_page_int=None,
        number=release.number,
        doi=release.ext_ids.doi,
        doi_prefix=release.ext_ids.doi and doi_split_prefix(release.ext_ids.doi),
        doi_registrar=release_doi_registrar(release),
        pmid=release.ext_ids.pmid,
        pmcid=release.ext_ids.pmcid,
        isbn13=release.ext_ids.isbn13,
        wikidata_qid=release.ext_ids.wikidata_qid,
        arxiv_id=release.ext_ids.arxiv,
        jstor_id=release.ext_ids.jstor,
        mag_id=release.ext_ids.mag,
        license_slug=release.license_slug,
        publisher=publisher,
        container_name=container_name,
        container_original_name=container_original_name,
        container_ident=container_ident,
        container_type=container_type,
        container_issnl=container_issnl,
        issns=issns,
        # TODO; these filters sort of meh. refactor to be above?
        contrib_names=list(
            filter(lambda x: bool(x), [contrib_name(c) for c in release.contribs])
        ),
        contrib_count=len([c for c in release.contribs if c.index]),
        affiliations=list(
            filter(
                lambda x: bool(x),
                [contrib_affiliation(c) for c in release.contribs if c.index],
            )
        ),
    )
    return ret


def es_release_from_release(release: ReleaseEntity) -> ScholarRelease:

    if release.container:
        container_name = release.container.name
        container_ident = release.container.ident
        container_issnl = release.container.issnl
        container_type = release.container.container_type
    else:
        container_name = release.extra.get("container_name")
        container_ident = None
        container_issnl = None
        container_type = None

    ret = ScholarRelease(
        ident=release.ident,
        revision=release.revision,
        title=release.title,
        release_date=release.release_date,
        release_year=release.release_year,
        release_type=release.release_type,
        release_stage=release.release_stage,
        withdrawn_status=release.withdrawn_status,
        doi=release.ext_ids.doi,
        doi_prefix=release.ext_ids.doi and doi_split_prefix(release.ext_ids.doi),
        doi_registrar=release_doi_registrar(release),
        pmid=release.ext_ids.pmid,
        pmcid=release.ext_ids.pmcid,
        isbn13=release.ext_ids.isbn13,
        wikidata_qid=release.ext_ids.wikidata_qid,
        arxiv_id=release.ext_ids.arxiv,
        jstor_id=release.ext_ids.jstor,
        mag_id=release.ext_ids.mag,
        license_slug=release.license_slug,
        container_name=container_name,
        container_ident=container_ident,
        container_issnl=container_issnl,
        container_type=container_type,
    )
    return ret