def test_replace_white_space( self ):
# declare variables
start_string = ""
test_string = ""
expected_string = ""
# initialize
start_string = "one bird two shoes and a cat"
expected_string = "one bird two shoes and a cat"
# do work
test_string = StringHelper.replace_white_space( start_string, replace_with_IN = " " )
# and the assert
self.assertEqual( test_string, expected_string )
# it is text - convert it to string.
current_paragraph_text = unicode( paragraph_element )
else:
# not text - just grab all the text out of it.
#current_paragraph_text = ' '.join( paragraph_element.findAll( text = True ) )
current_paragraph_text = HTMLHelper.remove_html( str( paragraph_element ) )
#-- END check to see if current element is text. --#
# clean up - convert HTML entities
current_paragraph_text = bs_helper.convert_html_entities( current_paragraph_text )
# strip out extra white space
current_paragraph_text = StringHelper.replace_white_space( current_paragraph_text )
# got any paragraph text?
current_paragraph_text = current_paragraph_text.strip()
if ( ( current_paragraph_text != None ) and ( current_paragraph_text != "" ) ):
# yes. Add to paragraph text.
paragraph_text_list.append( current_paragraph_text )
#-- END check to see if any text. --#
#-- END loop over paragraph elements. --#
# convert paragraph list to string
paragraph_text = ' '.join( paragraph_text_list )
def get_unique_mention_string_list(self,
replace_white_space_IN=False,
*args,
**kwargs):
'''
Retrieves all DataSetMention-s that relate to this DataSet, across
all citations. Builds and returns a set of the distinct strings
used to refer to the dataset.
'''
# return reference
mention_list_OUT = []
# declare variables
my_id = -1
mention_set = set()
data_set_citation_data_qs = None
citation_data = None
mention_qs = None
mention = None
mention_string = None
# get citation data
data_set_citation_data_qs = DataSetCitationData.objects.filter(
data_set_citation__data_set=self)
# for each citation data, get all mentions, and add the value of each
# to set.
for citation_data in data_set_citation_data_qs:
# get mentions
mention_qs = citation_data.datasetmention_set.all()
# for each mention, grab value and add to set if not already there.
for mention in mention_qs:
# get value
mention_string = mention.value
# is it in set?
if (mention_string not in mention_set):
# are we replacing white space for javascript?
if (replace_white_space_IN == True):
# replace more than one contiguous white space character
# with a space.
mention_string = StringHelper.replace_white_space(
mention_string)
#-- END check if we unicode_escape --#
# no - add it.
mention_set.add(mention_string)
#-- END check to see if in set. --#
#-- END loop over mentions. --#
#-- END loop over citation data related to current data set --#
# convert set to list.
mention_list_OUT = list(mention_set)
mention_list_OUT.sort()
return mention_list_OUT
