def ops_family_inpadoc_json_handler(request):
reference_type = request.matchdict.get('reference_type')
patent = request.matchdict.get('patent')
# constituents: biblio, legal
constituents = request.params.get('constituents', '')
return ops_family_inpadoc(reference_type, patent, constituents)
def to_zip(self, request=None, options=None):
"""
u'options': {u'media': {u'biblio': False,
u'claims': False,
u'description': False,
u'pdf': True,
u'register': False},
u'report': {u'csv': True,
u'json': True,
u'pdf': False,
u'xlsx': False}},
"""
# TODO: Text representations for biblio, register, family
# TODO: PDF Extracts
options = options or bunchify({'report': {}, 'media': {}})
# Remove entries with empty/undefined document numbers
self.df_documents.dropna(subset=['document'], inplace=True)
# Reject entries with seen == True
filtered = self.df_documents[(self.df_documents.seen == False)]
documents = list(filtered.document)
buffer = BytesIO()
with ZipFile(buffer, 'w', ZIP_DEFLATED) as zipfile:
# FIXME: Add TERMS (liability waiver) and more...
zipfile.writestr('@readme.txt',
u'Zip archive created by IP Navigator.')
# Add text summary
zipfile.writestr('@metadata.txt',
self.get_metadata().encode('utf-8'))
zipfile.writestr('@summary.txt',
self.get_summary().encode('utf-8'))
# Report files
# ------------
# Add Workbook
workbook_payload = None
if options.report.xlsx:
workbook_payload = DossierXlsx(self.data).create()
zipfile.writestr('report/@dossier.xlsx', workbook_payload)
# Add Workbook in PDF format
if options.report.pdf:
try:
zipfile.writestr(
'report/@dossier.pdf',
DossierXlsx(
self.data).to_pdf(payload=workbook_payload))
except Exception as ex:
log.error(u'Rendering dossier to PDF failed. ' \
u'Exception: {ex}\n{trace}'.format(ex=ex, trace=exception_traceback()))
# Add CSV
if options.report.csv:
zipfile.writestr('report/csv/01-queries.csv',
self.to_csv(self.df_queries))
zipfile.writestr('report/csv/02-documents.csv',
self.to_csv(self.df_documents))
zipfile.writestr('report/csv/03-comments.csv',
self.to_csv(self.df_comments))
# Add JSON
if options.report.json:
zipfile.writestr('report/json/01-queries.json',
self.to_json(self.df_queries))
zipfile.writestr('report/json/02-documents.json',
self.to_json(self.df_documents))
zipfile.writestr('report/json/03-comments.json',
self.to_json(self.df_comments))
# Media files
# -----------
# FIXME: This should go to some configuration setting.
fulltext_countries_excluded_ops = [
'BE', 'CN', 'DD', 'DE', 'DK', 'FR', 'GR', 'HU', 'JP', 'LU',
'KR', 'RU', 'PT', 'SE', 'TR', 'SK', 'US'
]
# Add full PDF documents
if options.media.pdf:
pdf_ziparchive_add(zipfile, documents, path='media/pdf')
# Add XML data
# TODO: Add @report.txt for reflecting missing documents, differentiate between different XML kinds.
# TODO: Add more TEXT formats (.abstract.txt, .biblio.txt, .register.txt)
# TODO: Add ST.36 XML; e.g. from https://register.epo.org/download?number=EP08835045&tab=main&xml=st36
# via https://register.epo.org/application?number=EP08835045
# TODO: Add equivalents, e.g. http://ops.epo.org/3.1/rest-services/published-data/publication/epodoc/EP1000000/equivalents/biblio
status = OrderedDict()
for document in documents:
if not document or not document.strip():
continue
log.info('Data acquisition for document {document}'.format(
document=document))
status.setdefault(document, OrderedDict())
patent = decode_patent_number(document)
# Add XML "bibliographic" data (full-cycle)
if options.media.biblio:
try:
biblio_payload = get_ops_biblio_data('publication',
document,
xml=True)
zipfile.writestr(
'media/xml/{document}.biblio.xml'.format(
document=document), biblio_payload)
status[document]['biblio'] = True
except Exception as ex:
status[document]['biblio'] = False
self.handle_exception(ex, 'biblio', document)
self.clear_request_errors(request)
# Add XML "description" full text data
# OPS does not have full texts for DE, US, ...
if options.media.description:
status[document]['description'] = False
if patent.country not in fulltext_countries_excluded_ops:
try:
# Write XML
document_number = encode_epodoc_number(patent)
description_payload = ops_description(
document_number, xml=True)
zipfile.writestr(
'media/xml/{document}.description.xml'.format(
document=document), description_payload)
status[document]['description'] = True
# Write TEXT
with ignored():
text_payload = self.get_fulltext(
description_payload, 'description')
if text_payload:
zipfile.writestr(
'media/txt/{document}.description.txt'.
format(document=document),
text_payload.encode('utf-8'))
except Exception as ex:
self.handle_exception(ex, 'description', document)
self.clear_request_errors(request)
# Add XML "claims" full text data
# OPS does not have full texts for DE, US, ...
if options.media.claims:
status[document]['claims'] = False
if patent.country not in fulltext_countries_excluded_ops:
try:
# Write XML
document_number = encode_epodoc_number(patent)
claims_payload = ops_claims(document_number,
xml=True)
zipfile.writestr(
'media/xml/{document}.claims.xml'.format(
document=document), claims_payload)
status[document]['claims'] = True
# Write TEXT
with ignored():
text_payload = self.get_fulltext(
claims_payload.replace(
'<claim-text>',
'<p>').replace('</claim-text>',
'</p>'), 'claims')
if text_payload:
zipfile.writestr(
'media/txt/{document}.claims.txt'.
format(document=document),
text_payload.encode('utf-8'))
except Exception as ex:
self.handle_exception(ex, 'claims', document)
self.clear_request_errors(request)
# Add XML register data
if options.media.register:
try:
register_payload = ops_register('publication',
document,
xml=True)
zipfile.writestr(
'media/xml/{document}.register.xml'.format(
document=document), register_payload)
status[document]['register'] = True
except Exception as ex:
status[document]['register'] = False
self.handle_exception(ex, 'register', document)
self.clear_request_errors(request)
# Add XML family data
if options.media.family:
try:
document_number = encode_epodoc_number(
patent, {'nokind': True})
family_payload = ops_family_inpadoc('publication',
document_number,
'biblio',
xml=True)
zipfile.writestr(
'media/xml/{document}.family.xml'.format(
document=document), family_payload)
status[document]['family'] = True
except Exception as ex:
status[document]['family'] = False
self.handle_exception(ex, 'family', document)
self.clear_request_errors(request)
#from pprint import pprint; print '====== status:'; pprint(status)
# Generate report
# ---------------
# TODO: Format more professionally incl. generator description
# TODO: Unify with "pdf_universal_multi"
delivered_items = []
missing_items = []
for document, kinds in status.iteritems():
delivered = []
missing = []
for kind, ok in kinds.iteritems():
if ok:
delivered.append(kind)
else:
missing.append(kind)
if delivered:
item = u'{document:20}{delivered}'.format(
document=document, delivered=u', '.join(delivered))
delivered_items.append(item)
if missing:
item = u'{document:20}{missing}'.format(
document=document, missing=u', '.join(missing))
missing_items.append(item)
if delivered_items or missing_items:
report_template = dedent("""
Delivered artifacts ({delivered_count}):
{delivered_files}
Missing artifacts ({missing_count}):
{missing_files}
""").strip()
report = report_template.format(
delivered_count=len(delivered_items),
missing_count=len(missing_items),
delivered_files='\n'.join(delivered_items),
missing_files='\n'.join(missing_items),
)
log.info('Export report:\n{report}'.format(report=report))
zipfile.writestr('media/xml/@report.txt', report)
payload = buffer.getvalue()
return payload