def format(bfo):
"""
Print Award.
"""
total_output = []
for award_field in bfo.fields('586__a', escape=2):
if award_field and award_field.strip():
if not ',' in award_field:
award_name = award_field.strip()
award_name = get_kb_mapping(kb_name='awards',
key=award_name,
default=award_name)
if type(award_name) == dict:
award_name = award_name['value']
total_output.append(award_name)
award_name = ','.join(award_field.split(',')[:-1])
award_year = award_field.split(',')[-1].strip()
award_name = get_kb_mapping(kb_name='awards',
key=award_name,
default=award_name)
if type(award_name) == dict:
award_name = award_name['value']
total_output.append('%s, %s' % (award_name, award_year))
return "<br>".join(total_output)
def format(bfo, brief="no"):
"""
Print host (Order: Name of publisher, place of publication and date of publication).
"""
_ = gettext_set_language(bfo.lang)
output = []
is_epfl_thesis = bfo.field("980__a") == 'THESIS' and bfo.field(
"973__a") == 'EPFL'
if not is_epfl_thesis:
#return '(%s)' % bfo.field('260__c')
return ''
thesis_number = bfo.field('088__a', escape=2)
if brief != "yes":
output = _(
"Thèse École polytechnique fédérale de Lausanne EPFL, n° %(number)s (%(year)s)"
)
output %= {'number': thesis_number, 'year': bfo.field('920__b')}
else:
return "Thèse EPFL, n° %(number)s (%(year)s)" % {
'number': thesis_number,
'year': bfo.field('920__b', escape=2)
}
output += '<br />'
hierarchy = []
if bfo.field('918__d'):
hierarchy.append(
get_kb_mapping(kb_name='doctoral-fre', key=bfo.field('918__d')))
if bfo.field('918__b'):
hierarchy.append(
get_kb_mapping(kb_name='section-fre', key=bfo.field('918__b')))
if bfo.field('918__a'):
hierarchy.append(
get_kb_mapping(kb_name='school-fre', key=bfo.field('918__a')))
if bfo.field('918__c'):
hierarchy.append(
get_kb_mapping(kb_name='institute-fre', key=bfo.field('918__c')))
if bfo.fields('919__a'):
hierarchy.extend([
get_kb_mapping(kb_name='theses-units-fre', key=unit)
for unit in bfo.fields('919__a')
])
if bfo.field('502__a'):
hierarchy.append({'value': 'Jury: ' + bfo.field('502__a')})
output += '<br />'.join([elem['value'] for elem in hierarchy if elem])
return output
def _tokenize_from_country_name_tag(self, instID):
"""Get country name and country code tokens reading the
country_name_tag tag from record instID.
Returns a list of tokens (empty if something fails)
"""
tokens = []
record = get_record(instID)
# Read the country name tags that are not marked as secondary
country_name_list = []
for field in record[self.address_field]:
if "secondary" not in field.get_subfield_values(
self.secondary_address_subfield):
country_name_list += field.get_subfield_values(
self.country_name_subfield
)
country_name_list = [s.encode('utf-8') for s in country_name_list]
for country_name in country_name_list:
# Find the country code using KB
kb_country_code = get_kb_mapping(
kb_name=self.kb_country_codes,
value=country_name
)
if kb_country_code:
country_code = kb_country_code["key"]
if country_name and country_code:
tokens += [country_name, country_code]
return tokens
def _getter(field):
if field.data:
val = get_kb_mapping('json_projects', str(field.data))
if val:
data = json_projects_kb_mapper(val)
return data['fields'][key_name]
return ''
def _tokenize_from_country_name_tag(self, instID):
"""Get country name and country code tokens reading the
country_name_tag tag from record instID.
Returns a list of tokens (empty if something fails)
"""
tokens = []
record = get_record(instID)
# Read the country name tags that are not marked as secondary
country_name_list = []
for field in record[self.address_field]:
if "secondary" not in field.get_subfield_values(
self.secondary_address_subfield):
country_name_list += field.get_subfield_values(
self.country_name_subfield
)
country_name_list = [s.encode('utf-8') for s in country_name_list]
for country_name in country_name_list:
# Find the country code using KB
kb_country_code = get_kb_mapping(
kb_name=self.kb_country_codes,
value=country_name
)
if kb_country_code:
country_code = kb_country_code["key"]
if country_name and country_code:
tokens += [country_name, country_code]
return tokens
def format_element(bfo, resource_type="photo"):
"""
Used to put a copyright overlay on top of a resource (photo, video, ..)
@param resource_type: the type of the resource the overlay will be placed on top of
"""
if resource_type != 'photo':
#not implement
return ''
output = """
<script type="text/javascript">
hs.creditsText = '© %(credit_text)s';
hs.creditsHref = '%(credit_url)s';
hs.creditsTitle = 'The use of photos requires prior authorization from %(credit_text)s';
</script>"""
# There might be more that one copyright and licence, select the one that
# applies to the record, not a single file (one without '8' subfield)
copyrights = bfo.fields('542__')
copyright_holder = ""
copyright_url = ""
for copyright in copyrights:
if not copyright.get('8', None):
copyright_holder = copyright.get('d')
copyright_url = copyright.get('u')
break
licences = bfo.fields('540__')
licence = ""
for lic in licences:
if not lic.get('8', None):
licence = lic.get('a')
break
if licence.startswith('CC-BY'):
return """
<script type="text/javascript">
hs.creditsText = '%(credit_text)s';
hs.creditsHref = '%(credit_url)s';
hs.creditsTitle = '%(credit_text)s';
</script>""" % {'credit_text': licence,
'credit_url' : get_kb_mapping(kb_name='LICENSE2URL', key=licence)['value']}
if not copyright_holder:
copyright_holder = 'CERN'
if copyright_holder == 'CERN' and not copyright_url:
copyright_url = CFG_CERN_LICENSE_URL
if copyright_holder == 'CERN':
output += """
<script type="text/javascript" src="/js/overlay.min.js"></script>
<script type="text/javascript" src="/js/copyright_notice.min.js"></script>
<link href="/img/overlay.css" type="text/css" rel="stylesheet" />
"""
return output % {'credit_text': copyright_holder,
'credit_url': copyright_url}
def grants_validator(form, field):
if field.data:
for item in field.data:
val = get_kb_mapping('json_projects', str(item['id']))
if val:
data = json_projects_kb_mapper(val)
item['acronym'] = data['fields']['acronym']
item['title'] = data['fields']['title']
continue
raise ValidationError("Invalid grant identifier %s" % item['id'])
def process_recjson(deposition, recjson):
"""
Process exported recjson (common for both new and edited records)
"""
# ===========
# Communities
# ===========
# FIXME: Properly deal with provisional/non-provisional
try:
# Extract identifier (i.e. elements are mapped from dict ->
# string)
recjson['provisional_communities'] = list(set(map(
lambda x: x['identifier'],
recjson.get('provisional_communities', [])
)))
recjson['communities'] = list(set(map(
lambda x: x['identifier'],
recjson.get('communities', [])
)))
except TypeError:
# Happens on re-run
pass
# =================
# License
# =================
if recjson['access_right'] in ["open", "embargoed"]:
info = get_kb_mapping(CFG_LICENSE_KB, str(recjson['license']))
if info:
info = json.loads(info['value'])
recjson['license'] = dict(
identifier=recjson['license'],
source=CFG_LICENSE_SOURCE,
license=info['title'],
url=info['url'],
)
elif 'license' in recjson:
del recjson['license']
# =======================
# Journal
# =======================
# Set year or delete fields if no title is provided
if recjson.get('journal.title', None):
recjson['journal.year'] = recjson['publication_date'].year
# =======================
# Book/chaper/report
# =======================
if 'imprint.publisher' in recjson and 'imprint.place' in recjson:
recjson['imprint.year'] = recjson['publication_date'].year
if 'part_of.title' in recjson:
mapping = [
('part_of.publisher', 'imprint.publisher'),
('part_of.place', 'imprint.place'),
('part_of.year', 'imprint.year'),
('part_of.isbn', 'isbn'),
]
for new, old in mapping:
if old in recjson:
try:
recjson[new] = recjson[old]
del recjson[old]
except KeyError:
pass
# =================
# Grants
# =================
# Remap incoming dictionary
recjson['grants'] = map(
lambda x: dict(
title="%s - %s (%s)" % (x['acronym'], x['title'], x['id']),
identifier=x['id']
),
recjson.get('grants', [])
)
# =======================
# Filter out empty fields
# =======================
filter_empty_elements(recjson)
return recjson
def process_recjson(deposition, recjson):
"""
Process exported recjson (common for both new and edited records)
"""
# ===========
# Communities
# ===========
# FIXME: Properly deal with provisional/non-provisional
try:
# Extract identifier (i.e. elements are mapped from dict ->
# string)
recjson['provisional_communities'] = list(
set(
map(lambda x: x['identifier'],
recjson.get('provisional_communities', []))))
recjson['communities'] = list(
set(map(lambda x: x['identifier'], recjson.get('communities',
[]))))
except TypeError:
# Happens on re-run
pass
# =================
# License
# =================
if recjson['access_right'] in ["open", "embargoed"]:
info = get_kb_mapping(CFG_LICENSE_KB, str(recjson['license']))
if info:
info = json.loads(info['value'])
recjson['license'] = dict(
identifier=recjson['license'],
source=CFG_LICENSE_SOURCE,
license=info['title'],
url=info['url'],
)
elif 'license' in recjson:
del recjson['license']
# =======================
# Journal
# =======================
# Set year or delete fields if no title is provided
if recjson.get('journal.title', None):
recjson['journal.year'] = recjson['publication_date'].year
# =======================
# Book/chaper/report
# =======================
if 'imprint.publisher' in recjson and 'imprint.place' in recjson:
recjson['imprint.year'] = recjson['publication_date'].year
if 'part_of.title' in recjson:
mapping = [
('part_of.publisher', 'imprint.publisher'),
('part_of.place', 'imprint.place'),
('part_of.year', 'imprint.year'),
('part_of.isbn', 'isbn'),
]
for new, old in mapping:
if old in recjson:
try:
recjson[new] = recjson[old]
del recjson[old]
except KeyError:
pass
# =================
# Grants
# =================
# Remap incoming dictionary
recjson['grants'] = map(
lambda x: dict(title="%s - %s (%s)" %
(x['acronym'], x['title'], x['id']),
identifier=x['id']), recjson.get('grants', []))
# =======================
# Filter out empty fields
# =======================
filter_empty_elements(recjson)
return recjson
def format_element(bfo, magnify='yes', check_existence='yes', source="auto", display_name="no", display_reference="yes", display_description="yes", display_comment="yes", display_tirage="yes", submission_doctype=""):
"""
Prints html image and link to photo resources, if 8567 exists print only 8567
otherwise if exists 8564.
@param magnify If 'yes', images will be magnified when mouse is over images
@param check_existence if 'yes' check that file is reachable
@param source where to look for photos. Possible values are 'mediaarchive', 'doc', 'bibdoc' or 'auto' (check everywhere)
"""
out = ""
rec_is_restricted = bfo.recID in get_all_restricted_recids()
# Hack to know about copyright while we do not have this stored in
# the metatada.
copyright_prefix = ''
report_number = bfo.field('037__a')
author = bfo.field('100__a').lower()
if report_number.startswith('ATL') or \
'claudia marcelloni' in author or \
'atlas' in author or \
'joao pequenao' in author or \
'tiina wickstroem' in author or \
'nikolai topilin' in author:
copyright_prefix = '<br/>The ATLAS Experiment '
cond_of_use = '''<a href="http://copyright.cern.ch/">Conditions of Use</a> '''
if bfo.field('540__u') or bfo.field('542__u') or bfo.field('542__d') != 'CERN' or bfo.field('540__a'):
cond_of_use = ''
# Check if image is under creative commons license
creative_commons = False
if bfo.field('540__a').startswith('CC-BY'):
creative_commons = True
out += '<div about="%s" rev="license">' % get_kb_mapping(kb_name='LICENSE2URL', key=bfo.field('540__a'))['value']
multimedia = {}
if source in ['auto', 'mediaarchive']:
multimedia = get_media(bfo, check_existence=(check_existence.lower() == 'yes'))
# Also append master information to the multimedia structure
masters = get_media(bfo, path_code='d', internal_note_code='x', check_existence=(check_existence.lower() == 'yes'))
for (tirage, info) in masters.iteritems():
if multimedia.has_key(tirage):
multimedia[tirage]['master'] = info['master']
if multimedia != {} and source in ['auto', 'mediaarchive']:
out += '''<center><small><strong>%s%s</strong></small></center><br />''' % (cond_of_use, bfe_copyright.format_element(bfo) or '© CERN')
out += '''<center><small><a href="%(CFG_SITE_URL)s/help/high-res-multimedia?ln=%(ln)s">%(label)s</a></small></center>''' % \
{'CFG_SITE_URL': CFG_SITE_URL,
'ln': bfo.lang,
'label': bfo.lang == "fr" and 'Besoin d\'aide pour accéder aux photos en haute résolution?' or \
'Need help to download high-resolutions?'}
mediaarchive_pictures = print_images(multimedia=multimedia, magnify=magnify,
reference=bfo.field('037__a'), bfo=bfo)
if len(multimedia) > 1 and not rec_is_restricted: # we have at least 2 photos
out += generate_view_button(bfo, report_number, mediaarchive_pictures)
else:
out += mediaarchive_pictures
out += '''<script type="text/javascript">
window.onload = function() {
if (location.hash != ''){
var pic = document.getElementById('thumb'+location.hash.substring(1));
if (pic != null){
hs.expand(pic)
}
}
}
</script>'''
elif not source in ['mediaarchive']:
out += '''<center><small><strong>%s%s</strong></small></center><br />''' % (cond_of_use, bfe_copyright.format_element(bfo) or '© CERN')
bibdoc_pictures = get_bibdoc_pictures(bfo, display_name, display_reference,
display_description, display_comment,
display_tirage, submission_doctype)
if bibdoc_pictures and source in ['auto', 'bibdoc']:
if bibdoc_pictures.count('<img ') > 1 and not rec_is_restricted:# we have at least 1 photo
out += generate_view_button(bfo, report_number, bibdoc_pictures)
else:
out += bibdoc_pictures
elif source in ['auto', 'doc']:
# Use picture from doc
out += get_doc_pictures(bfo)
if creative_commons:
out += '</div>'
return out
def generate_mediaexport(recid, is_image, resource_id, tirage, wrapped, json_format=True):
"""Generates the JSON with the info needed to export a media resource to CERN-Drupal"""
"""Mandatory fields to export: title_en, title_fr, caption_en, caption_fr,
copyright_holder, copyright_date, attribution (image),
keywords (image), directors (video), producer (video)
"""
MEDIA_CONFIG = {'title_en': ('245', ' ', ' ', 'a'),
'title_fr': ('246', ' ', '1', 'a'),
'keywords': ('653', '1', ' ', 'a'),
'copyright_holder': ('542', ' ', ' ', 'd'),
'copyright_date': ('542', ' ', ' ', 'g'),
'license_url': ('540', ' ', ' ', 'a'),
'license_desc': ('540', ' ', ' ', 'b'),
'license_body': ('540', ' ', ' ', 'u'),
'author': ('100', ' ', ' ', 'a'),
'affiliation': ('100', ' ', ' ', 'u'),
'directors': ('700', ' ', ' ', 'a'),
'video_length': ('300', ' ', ' ', 'a'),
'language': ('041', ' ', ' ', 'a'),
'creation_date': ('269', ' ', ' ', 'c'),
'abstract_en': ('520', ' ', ' ', 'a'),
'abstract_fr': ('590', ' ', ' ', 'a')}
entry = {}
record = get_record(recid)
for key in MEDIA_CONFIG:
entry[key] = record_get_field_value(record, *MEDIA_CONFIG[key])#.encode('utf-8')
entry['id'] = resource_id
entry['record_id'] = str(recid)
entry['type'] = is_image and "image" or "video"
entry['entry_date'] = get_creation_date(recid)
toc_recid = 0
toc_record = {}
if not is_image and 'asset' in record_get_field_value(record, *('970', ' ', ' ', 'a')):
toc_repnum = record_get_field_value(record, *('773', ' ', ' ', 'r'))
if toc_repnum:
try:
toc_recid = search_pattern(p='reportnumber:"%s"' %toc_repnum)[0]
except IndexError:
pass
#corner cases for copyright & licence
if not entry['copyright_holder']:
entry['copyright_holder'] = 'CERN'
if not entry['license_body']:
entry['license_body'] = 'CERN'
if not entry['license_desc']:
entry['license_desc'] = 'CERN'
if not entry['license_url']:
from invenio.bibknowledge import get_kb_mapping
try:
entry['license_url'] = get_kb_mapping(kb_name='LICENSE2URL', key=entry['license_desc'])['value']
except KeyError:
pass
#keywords
entry['keywords'] = ','.join(record_get_field_values(record, *MEDIA_CONFIG['keywords']))
#attribution
if not entry.get('author', '') and not entry.get('attribution', '') and toc_recid > 0:
if not toc_record:
toc_record = get_record(toc_recid)
entry['author'] = record_get_field_value(toc_record, *MEDIA_CONFIG['author'])
entry['affiliation'] = record_get_field_value(toc_record, *MEDIA_CONFIG['affiliation'])
if not entry.get('directors', ''):
entry['directors'] = ','.join(record_get_field_values(toc_record, *MEDIA_CONFIG['directors']))
#photos
if is_image:
if entry['author']:
entry['attribution'] = entry['author']
if entry['affiliation']:
entry['attribution'] += ': %s' % entry['affiliation']
del entry['directors']
else: #videos
if entry['author']:
entry['producer'] = entry['author']
# Get all files from record
files_field = ('856', '7', ' ', 'u')
# Filter all that are images
thumbnails = [
image for image in record_get_field_values(record, *files_field)
if 'jpg' in image
]
# If exists get the first one
if thumbnails:
entry['thumbnail'] = thumbnails[0]
del entry['author']
del entry['affiliation']
#
#title
if not entry['title_en'] and not entry['title_fr'] and toc_recid > 0:
if not toc_record:
toc_record = get_record(toc_recid)
entry['title_en'] = record_get_field_value(toc_record, *MEDIA_CONFIG['title_en'])
entry['title_fr'] = record_get_field_value(toc_record, *MEDIA_CONFIG['title_fr'])
#crop, media storage, caption
if is_image:
entry['file_params'] = {'size': ['small', 'medium', 'large'], 'crop': False}
if 'MediaArchive' in record_get_field_values(record, *('856', '7', ' ', '2')):
entry['caption_en'] = get_photolab_image_caption(record, tirage)
entry['caption_fr'] = ''
else:
brd = BibRecDocs(recid, deleted_too=True)
doc_numbers = [(bibdoc.get_id(), bibdoc) for bibdoc in brd.list_bibdocs()]
doc_numbers.sort()
bibdoc = doc_numbers[tirage-1][1]
entry['filename'] = brd.get_docname(bibdoc.get_id()) #bibdoc.get_docname()
if 'crop' in [bibdocfile.get_subformat() for bibdocfile in bibdoc.list_latest_files()]:
entry['file_params']['crop'] = True
if not bibdoc.deleted_p():
for bibdoc_file in bibdoc.list_latest_files():
entry['caption_en'] = bibdoc_file.get_comment()
entry['caption_fr'] = bibdoc_file.get_description()
if entry.get('caption_en', ''):
break
if not entry.get('caption_en', ''):
entry['caption_en'] = entry['abstract_en']
if not entry.get('caption_fr', ''):
entry['caption_fr'] = entry['abstract_fr']
if is_image:
del entry['language']
del entry['video_length']
# we don't need it
del entry['abstract_en']
del entry['abstract_fr']
#make sure all mandatory fields are sent
MANDATORY_FIELDS = ['title_en', 'title_fr', 'caption_en', 'caption_fr', 'copyright_holder', 'copyright_date']
MANDATORY_FIELDS_IMAGE = MANDATORY_FIELDS + ['attribution', 'keywords']
MANDATORY_FIELDS_VIDEO = MANDATORY_FIELDS + ['directors', 'producer', 'thumbnail']
if is_image:
mandatory_fields_all = MANDATORY_FIELDS_IMAGE
else:
mandatory_fields_all = MANDATORY_FIELDS_VIDEO
for field in mandatory_fields_all:
entry.setdefault(field, '')
# In case we want to embed the object
if wrapped:
final = {}
final['entries'] = [{'entry': entry}]
if not CFG_JSON_AVAILABLE:
return ''
if json_format:
return json.dumps(final)
else:
return final
else:
return entry
def _f1(x):
info = get_kb_mapping('json_projects', str(x))
data = json.loads(info['value'])
return {'id': x, 'title': data.get('title', ''), 'acronym': data.get('acronym', '')}
