def enrich_release_entity(entity):
if entity.state in ('redirect', 'deleted'):
return entity
if entity.state == "active":
entity._es = release_to_elasticsearch(entity, force_bool=False)
if entity.container and entity.container.state == "active":
entity.container._es = container_to_elasticsearch(entity.container,
force_bool=False)
if entity.filesets:
for fs in entity.filesets:
fs._total_size = sum([f.size for f in fs.manifest])
if entity.webcaptures:
for wc in entity.webcaptures:
wc._wayback_suffix = wayback_suffix(wc)
for ref in entity.refs:
# this is a UI hack to get rid of XML crud in unstructured refs like:
# LOCKSS (2014) Available: <ext-link
# xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri"
# xlink:href="http://lockss.org/"
# xlink:type="simple">http://lockss.org/</ext-link>. Accessed: 2014
# November 1.
if ref.extra and ref.extra.get('unstructured'):
ref.extra['unstructured'] = strip_extlink_xml(
ref.extra['unstructured'])
# author list to display; ensure it's sorted by index (any othors with
# index=None go to end of list)
authors = [c for c in entity.contribs if c.role in ('author', None)]
entity._authors = sorted(authors,
key=lambda c:
(c.index == None and 99999999) or c.index)
# hack to show plain text instead of latex abstracts
if entity.abstracts:
if 'latex' in entity.abstracts[0].mimetype:
entity.abstracts.reverse()
return entity
def enrich_release_entity(entity):
if entity.state in ('redirect', 'deleted'):
return entity
if entity.state == "active":
entity._es = release_to_elasticsearch(entity, force_bool=False)
if entity.container and entity.container.state == "active":
entity.container._es = container_to_elasticsearch(entity.container, force_bool=False)
if entity.files:
# remove shadows-only files with no URLs
entity.files = [f for f in entity.files
if not (f.extra and f.extra.get('shadows') and not f.urls)]
if entity.filesets:
for fs in entity.filesets:
fs._total_size = sum([f.size for f in fs.manifest])
if entity.webcaptures:
for wc in entity.webcaptures:
wc._wayback_suffix = wayback_suffix(wc)
for ref in entity.refs:
# this is a UI hack to get rid of XML crud in unstructured refs like:
# LOCKSS (2014) Available: <ext-link
# xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri"
# xlink:href="http://lockss.org/"
# xlink:type="simple">http://lockss.org/</ext-link>. Accessed: 2014
# November 1.
if ref.extra and ref.extra.get('unstructured'):
ref.extra['unstructured'] = strip_extlink_xml(ref.extra['unstructured'])
# author list to display; ensure it's sorted by index (any othors with
# index=None go to end of list)
authors = [c for c in entity.contribs if c.role in ('author', None)]
entity._authors = sorted(authors, key=lambda c: (c.index == None and 99999999) or c.index)
if entity.abstracts:
# hack to show plain text instead of latex abstracts
if 'latex' in entity.abstracts[0].mimetype:
entity.abstracts.reverse()
# hack to (partially) clean up common JATS abstract display case
if entity.abstracts[0].mimetype == 'application/xml+jats':
for tag in ('p', 'jats', 'jats:p'):
entity.abstracts[0].content = entity.abstracts[0].content.replace('<{}>'.format(tag), '')
entity.abstracts[0].content = entity.abstracts[0].content.replace('</{}>'.format(tag), '')
# ugh, double encoding happens
entity.abstracts[0].content = entity.abstracts[0].content.replace('</{}>'.format(tag), '')
entity.abstracts[0].content = entity.abstracts[0].content.replace('<{}>'.format(tag), '')
return entity
def enrich_webcapture_entity(entity):
if entity.state in ('redirect', 'deleted'):
return entity
entity._wayback_suffix = wayback_suffix(entity)
return entity
def enrich_release_entity(entity: ReleaseEntity) -> ReleaseEntity:
if entity.state in ("redirect", "deleted"):
return entity
if entity.state == "active":
entity._es = release_to_elasticsearch(entity, force_bool=False)
if entity.container and entity.container.state == "active":
entity.container._es = container_to_elasticsearch(entity.container,
force_bool=False)
if entity.files:
# remove shadows-only files with no URLs
entity.files = [
f for f in entity.files
if not (f.extra and f.extra.get("shadows") and not f.urls)
]
if entity.filesets:
for fs in entity.filesets:
fs._total_size = sum([f.size for f in fs.manifest])
if entity.webcaptures:
for wc in entity.webcaptures:
wc._wayback_suffix = wayback_suffix(wc)
for ref in entity.refs:
# this is a UI hack to get rid of XML crud in unstructured refs like:
# LOCKSS (2014) Available: <ext-link
# xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri"
# xlink:href="http://lockss.org/"
# xlink:type="simple">http://lockss.org/</ext-link>. Accessed: 2014
# November 1.
if ref.extra and ref.extra.get("unstructured"):
ref.extra["unstructured"] = strip_extlink_xml(
ref.extra["unstructured"])
# for backwards compatibility, copy extra['subtitle'] to subtitle
if not entity.subtitle and entity.extra and entity.extra.get("subtitle"):
if isinstance(entity.extra["subtitle"], str):
entity.subtitle = entity.extra["subtitle"]
elif isinstance(entity.extra["subtitle"], list):
entity.subtitle = entity.extra["subtitle"][0] or None
# author list to display; ensure it's sorted by index (any othors with
# index=None go to end of list)
authors = [
c for c in entity.contribs if c.role in ("author", None) and (
c.surname or c.raw_name or (c.creator and c.creator.surname))
]
entity._authors = sorted(authors,
key=lambda c:
(c.index is None and 99999999) or c.index)
# need authors, title for citeproc to work
entity._can_citeproc = bool(entity._authors) and bool(entity.title)
if entity.abstracts and entity.abstracts[0].mimetype:
# hack to show plain text instead of latex abstracts
if "latex" in entity.abstracts[0].mimetype:
entity.abstracts.reverse()
# hack to (partially) clean up common JATS abstract display case
if entity.abstracts[0].mimetype == "application/xml+jats":
for tag in ("p", "jats", "jats:p"):
entity.abstracts[0].content = entity.abstracts[
0].content.replace("<{}>".format(tag), "")
entity.abstracts[0].content = entity.abstracts[
0].content.replace("</{}>".format(tag), "")
# ugh, double encoding happens
entity.abstracts[0].content = entity.abstracts[
0].content.replace("</{}>".format(tag), "")
entity.abstracts[0].content = entity.abstracts[
0].content.replace("<{}>".format(tag), "")
return entity
def enrich_webcapture_entity(entity: WebcaptureEntity) -> WebcaptureEntity:
if entity.state in ("redirect", "deleted"):
return entity
entity._wayback_suffix = wayback_suffix(entity)
return entity