def test_initialise(self):
aSection = Section('aTitle', 1)
self.assertIsInstance(aSection, Section)
self.assertEqual(aSection._title, 'aTitle')
self.assertEqual(aSection._level, 1)
self.assertTrue(aSection.is_section())
self.assertFalse(aSection.is_document())
def test_subsection(self):
aSection = Section('aTitle', 1)
newSection = aSection.add_subsection('other', 2)
self.assertEqual(len(aSection._ordered_subsections), 1)
retrieved = aSection.section('other')
self.assertIsNotNone(retrieved)
self.assertIsInstance(retrieved, Section)
def test_get_all_paragraphs(self):
aSection = Section('aTitle', 1)
subSection = aSection.add_subsection('other', 2)
subSection.add_paragraph('This is a sub section paragraph')
paragraphs = aSection.get_all_paragraphs()
self.assertEqual(len(paragraphs), 1)
self.assertEqual(paragraphs[0]['text'].text,
'This is a sub section paragraph')
def parseText(text):
"""
Wraps the parser with logic to create the appropriate data structures
"""
#splits text into paragraphs to parse, which is easier than making the parser
#more complex
separated = LINESEP.split(text)
rootSection = None
currentSection = None
while bool(separated):
current = separated.pop(0)
if current == "":
continue
try:
results = ROOT.parseString(current)
except Exception as e:
logging.info('Parser Issue with: {}'.format(current))
raise e
#parsed a header, create a section
if not bool(results):
results = "Nothing, just add the paragraph"
if isinstance(results[0], HEADER) and rootSection is None:
#a new, root section
currentSection = Section(results[0].title, results[0].level)
rootSection = currentSection
for res in results[1:]:
if isinstance(res, TAG):
currentSection.add_tag(res.text)
elif isinstance(results[0], HEADER):
#a subsection
if results[0].level > currentSection._level:
currentSection = currentSection.add_subsection(results[0].title,
results[0].level)
elif results[0].level <= currentSection._level:
#a subsection of an ancestor
while results[0].level <= currentSection._level:
currentSection = currentSection.get_parent()
currentSection = currentSection.add_subsection(results[0].title,
results[0].level)
for res in results[1:]:
if isinstance(res, TAG):
currentSection.add_tag(res.text)
else:
#Paragraphs of a section
currentParagraph = currentSection.add_paragraph(current)
for res in results:
if isinstance(res, TAG):
currentParagraph['tags'].add(res.text)
elif isinstance(res, CITATION):
currentParagraph['citations'].add(res.text)
return rootSection
def test_deep_tags_paragraphs(self):
aSection = Section('aTitle', 1)
aParagraph = aSection.add_paragraph('This is some random text')
self.assertIn('text', aParagraph)
self.assertIn('tags', aParagraph)
self.assertIn('citations', aParagraph)
aParagraph['tags'].add('atag')
self.assertIn('atag', aParagraph['tags'])
self.assertTrue(aSection.has_tag('aTag'))
self.assertFalse(aSection.has_tag('bloo'))
def test_local_sentence_count(self):
aSection = Section('aTitle', 1)
aSection.add_paragraph('This is a single sentence.')
self.assertEqual(aSection.get_sentence_count(), 1)
aSection.add_paragraph(
'This adds a second, and third, sentence. How is the weather today?'
)
self.assertEqual(aSection.get_sentence_count(), 3)
def test_deep_word_count(self):
aSection = Section('aTitle', 1)
subSection = aSection.add_subsection('other', 2)
aSection.add_paragraph(
'This is the word sections paragraph. And a second sentence.')
subSection.add_paragraph(
'This is a sub word paragraph. The weather today is fairly nice.')
self.assertEqual(aSection.get_word_count(), 22)
def test_paragraphs(self):
aSection = Section('aTitle', 1)
self.assertEqual(len(aSection._paragraphs), 0)
aSection.add_paragraph("this is a test text.")
self.assertEqual(len(aSection._paragraphs), 1)
aSection.add_paragraph("this is another test text.")
self.assertEqual(len(aSection._paragraphs), 2)
paragraphs = aSection.get_paragraphs()
self.assertEqual(len(paragraphs), 2)
self.assertEqual(paragraphs[0]['text'].text, "this is a test text.")
self.assertEqual(paragraphs[1]['text'].text,
"this is another test text.")
def test_subsection_bad_level(self):
aSection = Section('aTitle', 1)
with self.assertRaises(Exception):
aSection.add_subsection('other', 1)
def test_tags(self):
aSection = Section('aTitle', 1)
aSection.add_tag('blah').add_tag('bloo')
self.assertTrue(aSection.has_tag('blah'))
self.assertTrue(aSection.has_tag('bloo'))
self.assertFalse(aSection.has_tag('blee'))
def test_bad_set_parent(self):
aSection = Section('aTitle', 1)
anotherSection = Section('AnotherTitle', 2)
self.assertIsNone(aSection.get_parent())
with self.assertRaises(Exception):
aSection.set_parent(anotherSection)
def test_set_parent(self):
aSection = Section('aTitle', 1)
anotherSection = Section('AnotherTitle', 2)
self.assertIsNone(anotherSection.get_parent())
anotherSection.set_parent(aSection)
self.assertIsNotNone(anotherSection.get_parent())
def test_should_retrieval(self):
aSection = Section('aTitle', 1)
self.assertIsInstance(aSection.should, Should)
self.assertEqual(aSection.should._ref, aSection)
def test_citations_paragraphs(self):
aSection = Section('aTitle', 1)
aParagraph = aSection.add_paragraph('this is some text')
aParagraph['citations'].add('graeber 99')
self.assertTrue(aSection.has_citation('graeber 99'))
def test_deep_tags_sections(self):
aSection = Section('aTitle', 1)
aSubSection = aSection.add_subsection('subsection', 2)
aSubSection.add_tag('blah')
self.assertTrue(aSection.has_tag('blah'))