def data(self, all_fields=True):
"""
Calculate context of quotation using QuoteContext class
Optionally return a smaller subset of fields to upload to cloud
"""
data_dict = {
'sha1': self.hash(),
'citing_url': self.citing_url,
'cited_url': self.cited_url,
}
# Get text version of document
citing_doc = Document(self.citing_url)
cited_doc = Document(self.cited_url)
# Populate context fields with Document methods
document_fields = ['doc_type', 'text']
quote_context_fields = [
'context_before', 'context_after', # 'quote',
'quote_length',
'quote',
'quote_start_position', 'quote_end_position',
'context_start_position', 'context_end_position',
]
if self.raw_output:
data_dict['citing_raw'] = citing_doc.raw()
data_dict['cited_raw'] = cited_doc.raw()
# if self.text_output:
# quote_context_fields.append('text')
for doc_field in document_fields:
citing_field = ''.join(['citing_', doc_field])
cited_field = ''.join(['cited_', doc_field])
data_dict[citing_field] = citing_doc.data()[doc_field]
data_dict[cited_field] = cited_doc.data()[doc_field]
# Find context of quote from within text
citing_context = QuoteContext(self.citing_quote, citing_doc.text())
cited_context = QuoteContext(self.citing_quote, cited_doc.text())
for field in quote_context_fields:
citing_field = ''.join(['citing_', field])
cited_field = ''.join(['cited_', field])
data_dict[citing_field] = citing_context.data()[field]
data_dict[cited_field] = cited_context.data()[field]
# Stop Elapsed Timer
elapsed_time = time.time() - self.start_time
data_dict['create_elapsed_time'] = format(elapsed_time, '.5f')
if not all_fields:
excluded_fields = [
'cited_raw', 'citing_raw',
'citing_text', 'cited_text',
'citing_quote_length',
'cited_quote_start_position', 'citing_quote_start_position',
'cited_quote_end_position', 'citing_quote_end_position',
'cited_context_start_position',
'citing_context_start_position',
'cited_context_end_position', 'citing_context_end_position',
'create_elapsed_time',
] # 'cited_cache_url', 'cited_archive_url',
for excluded_field in excluded_fields:
data_dict.pop(excluded_field)
return data_dict
def raw(self):
raw = ''
doc = Document(self.url)
raw = doc.raw()
return raw
