def test_highlight_document_valid_hitting_limit_300(self):
expected = 300
self.max_number_of_characters = 300
self.dhc = DocumentHighlightClass(self.document,self.query,self.source_type,self.start_highlight,
self.end_highlight,self.max_number_of_characters)
self.dhc._highlight_document()
result = len(self.dhc._snippet)
self.assertEqual(expected,result)
def setUp(self):
self.document = """Big Data Partnership, a leading 'Big Data' specialist service provider, today annouced that it has been chosen as one of a few select organizations from around the world to participate in the Microsoft Big Data Partner Incubation Program. Big Data Partnership's participation in the program followed a rigourous nomination process that was supported by Microsoft SQL Server global marketing managers and industry leads."""
self.query = "Big Data"
self.start_highlight = "[[HIGHLIGHT]]"
self.end_highlight = "[[ENDHIGHLIGHT]]"
self.source_type = None
self.max_number_of_characters = 180
self.dhc = DocumentHighlightClass(self.document,self.query,self.source_type,self.start_highlight,
self.end_highlight,self.max_number_of_characters)
def test_different_highlighting_methods(self):
##Changed highlighting words to ensure we can have control over that aspect
self.start_highlight = "[[RANDOM]]"
self.end_highlight = "[[ENDRANDOM]]"
self.dhc = DocumentHighlightClass(self.document,self.query,self.source_type,self.start_highlight,
self.end_highlight,self.max_number_of_characters)
expected = ["[[RANDOM]]","Big","Data","[[ENDRANDOM]]","Partnership's","participation","."]
split_sentence = ["Big","Data","Partnership's","participation"]
result = self.dhc._find_matches_per_sentence(split_sentence)
self.assertEqual(expected,result)
class TestDocumentParserClass(unittest.TestCase):
def setUp(self):
self.document = """Big Data Partnership, a leading 'Big Data' specialist service provider, today annouced that it has been chosen as one of a few select organizations from around the world to participate in the Microsoft Big Data Partner Incubation Program. Big Data Partnership's participation in the program followed a rigourous nomination process that was supported by Microsoft SQL Server global marketing managers and industry leads."""
self.query = "Big Data"
self.start_highlight = "[[HIGHLIGHT]]"
self.end_highlight = "[[ENDHIGHLIGHT]]"
self.source_type = None
self.max_number_of_characters = 180
self.dhc = DocumentHighlightClass(self.document,self.query,self.source_type,self.start_highlight,
self.end_highlight,self.max_number_of_characters)
def test_split_document_on_delimiter(self):
expected = """Big Data Partnership's participation in the program followed a rigourous nomination process that was supported by Microsoft SQL Server global marketing managers and industry leads"""
self.dhc._split_document_on_delimiter()
result = self.dhc._doc_to_sentences
self.assertEqual(expected,result[1])
def test_find_matches_per_sentence(self):
expected = ["[[HIGHLIGHT]]","Big","Data","[[ENDHIGHLIGHT]]","Partnership's","participation","."]
split_sentence = ["Big","Data","Partnership's","participation"]
result = self.dhc._find_matches_per_sentence(split_sentence)
self.assertEqual(expected,result)
def test_format_snippet_to_compute_word_length(self):
processed_sentence = ["[[HIGHLIGHT]]","Big","Data","[[ENDHIGHLIGHT]]","Partnership's","participation"]
expected = "[[HIGHLIGHT]] Big Data [[ENDHIGHLIGHT]] Partnership's participation"
self.dhc._format_snippet(processed_sentence)
result = self.dhc._snippet
self.assertEqual(expected,result)
def test_highlight_document_valid_hitting_limit(self):
expected = 182
self.dhc._highlight_document()
result = len(self.dhc._snippet)
self.assertEqual(expected,result)
def test_highlight_document_valid_hitting_limit_300(self):
expected = 300
self.max_number_of_characters = 300
self.dhc = DocumentHighlightClass(self.document,self.query,self.source_type,self.start_highlight,
self.end_highlight,self.max_number_of_characters)
self.dhc._highlight_document()
result = len(self.dhc._snippet)
self.assertEqual(expected,result)
def test_different_highlighting_methods(self):
##Changed highlighting words to ensure we can have control over that aspect
self.start_highlight = "[[RANDOM]]"
self.end_highlight = "[[ENDRANDOM]]"
self.dhc = DocumentHighlightClass(self.document,self.query,self.source_type,self.start_highlight,
self.end_highlight,self.max_number_of_characters)
expected = ["[[RANDOM]]","Big","Data","[[ENDRANDOM]]","Partnership's","participation","."]
split_sentence = ["Big","Data","Partnership's","participation"]
result = self.dhc._find_matches_per_sentence(split_sentence)
self.assertEqual(expected,result)
