def test_get_paragraphs_between(self):
paragraphs = parsedoc.parse_docx_paragraphs(self.rawxml)
items = parsedoc.get_paragraphs_between(paragraphs, 'Main items',
'Other stuff')
self.assertEqual(
['Very large tomatoes', 'Huge apricots', 'Mediocre marrows'],
items)
def test_get_paragraphs_containing(self):
paragraphs = parsedoc.parse_docx_paragraphs(self.rawxml)
items = parsedoc.get_paragraphs_between(paragraphs, 'Main items',
'Other stuff')
measurements = parsedoc.get_paragraphs_containing(
paragraphs, items, 'Measurement:')
self.assertEqual(
{
'Very large tomatoes': 'Measurement: 20cm',
'Huge apricots': 'Measurement: 15cm',
'Mediocre marrows': 'Measurement: 12cm'
}, measurements)
def get_dataset_list():
"""Parse and return expected array of descriptors per dataset."""
pathname = os.path.normpath(
os.path.join(eustaceconfig.SYSTEM_PATH,
DELIVERABLE_D4_3_RELATIVE_PATH))
inputfile = open(pathname, 'rb')
rawxml = retrieve_document_xml(inputfile)
paragraphs = parse_docx_paragraphs(rawxml, ignore_trailing_digits=True)
names = get_paragraphs_between(paragraphs, DATASET_CONTENTS_START,
DATASET_CONTENTS_END)
paths = get_paragraphs_containing(paragraphs, names,
eustaceconfig.WORKSPACE_PATH)
result = [CatalogueDataSet(name, paths.get(name)) for name in names]
return result
def test_parse_docx_paragraphs(self):
paragraphs = parsedoc.parse_docx_paragraphs(self.rawxml)
self.assertEqual('Test Document for Parsing with Python',
paragraphs[0])
self.assertEqual('Very large tomatoes', paragraphs[5])
def load_document(self, pathname):
"""Open specified document (MS Word format) and read all paragraphs."""
spec = open(pathname, 'r')
spec_xml = parsedoc.retrieve_document_xml(spec)
self.paragraphs_all = parsedoc.parse_docx_paragraphs(spec_xml)