def generic_get_entity(entity_type, ident):
try:
if entity_type == 'container':
return enrich_container_entity(api.get_container(ident))
elif entity_type == 'creator':
return enrich_creator_entity(api.get_creator(ident))
elif entity_type == 'file':
return enrich_file_entity(api.get_file(ident, expand="releases"))
elif entity_type == 'fileset':
return enrich_fileset_entity(
api.get_fileset(ident, expand="releases"))
elif entity_type == 'webcapture':
return enrich_webcapture_entity(
api.get_webcapture(ident, expand="releases"))
elif entity_type == 'release':
return enrich_release_entity(
api.get_release(ident,
expand="container,files,filesets,webcaptures"))
elif entity_type == 'work':
return enrich_work_entity(api.get_work(ident))
else:
raise NotImplementedError
except ApiException as ae:
abort(ae.status)
except ApiValueError:
abort(400)
def reference_match_json() -> AnyResponse:
form = ReferenceMatchForm(request.args)
if form.validate():
if form.submit_type.data == "match":
matches = (close_fuzzy_biblio_matches(
es_client=app.es_client, biblio=form.data, match_limit=10)
or [])
else:
raise NotImplementedError()
resp = []
for m in matches:
# expand releases more completely
m.release = api.get_release(
m.release.ident,
expand="container,files,filesets,webcaptures",
hide="abstract,refs",
)
# hack in access options
m.access_options = release_access_options(m.release)
# and manually convert to dict (for jsonify)
info = m.__dict__
info["release"] = entity_to_dict(m.release)
info["access_options"] = [o.dict() for o in m.access_options]
resp.append(info)
return jsonify(resp), 200
else:
return Response(json.dumps(dict(errors=form.errors)),
mimetype="application/json",
status=400)
def release_view(ident):
try:
entity = api.get_release(ident,
expand="container,files,filesets,webcaptures")
container = entity.container
filesets = entity.filesets
except ApiException as ae:
abort(ae.status)
if entity.state == "redirect":
return redirect('/release/{}'.format(entity.redirect))
if entity.state == "deleted":
return render_template('deleted_entity.html',
entity=entity,
entity_type="release")
if entity.container and entity.container.state == "active":
entity.container.es = container_to_elasticsearch(entity.container,
force_bool=False)
if entity.state == "active":
entity.es = release_to_elasticsearch(entity, force_bool=False)
for fs in filesets:
fs.total_size = sum([f.size for f in fs.manifest])
entity.filesets = filesets
authors = [c for c in entity.contribs if c.role in ('author', None)]
authors = sorted(authors, key=lambda c: c.index or 99999999)
return render_template('release_view.html',
release=entity,
authors=authors,
container=container)
def release_bibtex(ident):
try:
entity = api.get_release(ident)
except ApiException as ae:
raise ae
csl = release_to_csl(entity)
bibtex = citeproc_csl(csl, 'bibtex')
return Response(bibtex, mimetype="text/plain")
def release_history(ident):
try:
entity = api.get_release(ident)
history = api.get_release_history(ident)
except ApiException as ae:
abort(ae.status)
return render_template('entity_history.html',
entity_type="release",
entity=entity,
history=history)
def generic_get_entity(entity_type: str,
ident: str,
enrich: bool = True) -> Any:
try:
if entity_type == "container" and enrich:
return enrich_container_entity(api.get_container(ident))
elif entity_type == "container":
return api.get_container(ident)
elif entity_type == "creator" and enrich:
return enrich_creator_entity(api.get_creator(ident))
elif entity_type == "creator":
return api.get_creator(ident)
elif entity_type == "file" and enrich:
return enrich_file_entity(api.get_file(ident, expand="releases"))
elif entity_type == "file":
return api.get_file(ident, expand="releases")
elif entity_type == "fileset" and enrich:
return enrich_fileset_entity(
api.get_fileset(ident, expand="releases"))
elif entity_type == "fileset":
return api.get_fileset(ident)
elif entity_type == "webcapture" and enrich:
return enrich_webcapture_entity(
api.get_webcapture(ident, expand="releases"))
elif entity_type == "webcapture":
return api.get_webcapture(ident)
elif entity_type == "release" and enrich:
return enrich_release_entity(
api.get_release(
ident,
expand="container,creators,files,filesets,webcaptures"))
elif entity_type == "release":
return api.get_release(ident)
elif entity_type == "work" and enrich:
return enrich_work_entity(api.get_work(ident))
elif entity_type == "work":
return api.get_work(ident)
else:
raise NotImplementedError
except ApiException as ae:
abort(ae.status)
except ApiValueError:
abort(400)
def release_save(ident):
form = SavePaperNowForm()
# lookup release ident, ensure it exists
try:
release = api.get_release(ident)
except ApiException as ae:
abort(ae.status)
if not Config.KAFKA_PIXY_ENDPOINT:
return render_template('release_save.html',
entity=release,
form=form,
spn_status='not-configured'), 501
if form.is_submitted():
if form.validate_on_submit():
# got a valid spn request! try to send to kafka-pixy
msg = form.to_ingest_request(
release, ingest_request_source="savepapernow-web")
try:
kafka_pixy_produce(
Config.KAFKA_SAVEPAPERNOW_TOPIC,
json.dumps(msg, sort_keys=True),
)
except:
return render_template('release_save.html',
entity=release,
form=form,
spn_status='kafka-error'), 500
return render_template('release_save.html',
entity=release,
form=form,
spn_status='success'), 200
elif form.errors:
return render_template('release_save.html',
entity=release,
form=form), 400
# form was not submitted; populate defaults
if release.release_stage:
form.release_stage.data = release.release_stage
if release.ext_ids.doi:
form.base_url.data = "https://doi.org/{}".format(release.ext_ids.doi)
elif release.ext_ids.arxiv:
form.base_url.data = "https://arxiv.org/pdf/{}.pdf".format(
release.ext_ids.arxiv)
elif release.ext_ids.pmcid:
form.base_url.data = "http://europepmc.org/backend/ptpmcrender.fcgi?accid={}&blobtype=pdf".format(
release.ext_ids.pmcid)
return render_template('release_save.html', entity=release, form=form), 200
def webcapture_view(ident):
try:
entity = api.get_webcapture(ident)
except ApiException as ae:
abort(ae.status)
if entity.state == "redirect":
return redirect('/webcapture/{}'.format(entity.redirect))
elif entity.state == "deleted":
return render_template('deleted_entity.html',
entity=entity,
entity_type="webcapture")
else:
try:
entity.releases = []
for r in entity.release_ids:
entity.releases.append(api.get_release(r))
except ApiException as ae:
abort(ae.status)
return render_template('webcapture_view.html', webcapture=entity)
def release_citeproc(ident):
style = request.args.get('style', 'harvard1')
is_html = request.args.get('html', False)
if is_html and is_html.lower() in ('yes', '1', 'true', 'y', 't'):
is_html = True
else:
is_html = False
try:
entity = api.get_release(ident)
except ApiException as ae:
raise ae
csl = release_to_csl(entity)
cite = citeproc_csl(csl, style, is_html)
if is_html:
return Response(cite)
elif style == "csl-json":
return jsonify(json.loads(cite))
else:
return Response(cite, mimetype="text/plain")
def fileset_view(ident):
try:
entity = api.get_fileset(ident)
except ApiException as ae:
abort(ae.status)
if entity.state == "redirect":
return redirect('/fileset/{}'.format(entity.redirect))
elif entity.state == "deleted":
return render_template('deleted_entity.html',
entity=entity,
entity_type="fileset")
else:
try:
entity.releases = []
for r in entity.release_ids:
entity.releases.append(api.get_release(r))
except ApiException as ae:
abort(ae.status)
entity.total_size = sum([f.size for f in entity.manifest])
return render_template('fileset_view.html', fileset=entity)
def reference_match() -> AnyResponse:
grobid_status = None
grobid_dict = None
form = ReferenceMatchForm()
if not form.is_submitted() and request.args.get("submit_type"):
form = ReferenceMatchForm(request.args)
if form.is_submitted() or request.args.get("title"):
if form.validate():
if form.submit_type.data == "parse":
resp_xml = grobid_api_process_citation(form.raw_citation.data)
if not resp_xml:
grobid_status = "failed"
return (
render_template("reference_match.html",
form=form,
grobid_status=grobid_status),
400,
)
grobid_dict = transform_grobid_ref_xml(resp_xml)
if not grobid_dict:
grobid_status = "empty"
return (
render_template("reference_match.html",
form=form,
grobid_status=grobid_status),
200,
)
# print(grobid_dict)
release_stub = grobid_ref_to_release(grobid_dict)
# remove empty values from GROBID parsed dict
grobid_dict = {
k: v
for k, v in grobid_dict.items() if v is not None
}
form = ReferenceMatchForm.from_grobid_parse(
grobid_dict, form.raw_citation.data)
grobid_status = "success"
matches = (close_fuzzy_release_matches(es_client=app.es_client,
release=release_stub,
match_limit=10) or [])
elif form.submit_type.data == "match":
matches = (close_fuzzy_biblio_matches(
es_client=app.es_client, biblio=form.data, match_limit=10)
or [])
else:
raise NotImplementedError()
for m in matches:
# expand releases more completely
m.release = api.get_release(
m.release.ident,
expand="container,files,filesets,webcaptures",
hide="abstract,refs",
)
# hack in access options
m.access_options = release_access_options(m.release)
return (
render_template(
"reference_match.html",
form=form,
grobid_dict=grobid_dict,
grobid_status=grobid_status,
matches=matches,
),
200,
)
elif form.errors:
return render_template("reference_match.html", form=form), 400
return render_template("reference_match.html", form=form), 200
def release_edit_view(ident):
try:
entity = api.get_release(ident)
except ApiException as ae:
abort(ae.status)
return render_template('entity_edit.html')
