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 read_variables(self, startmarker, endmarker):
"""Read variables table from document and return as list of VariableSpecification objects."""
# get relevant paragraphs
paragraphs_variables = parsedoc.get_paragraphs_between(
self.paragraphs_all, startmarker, endmarker)
# build list
variables = []
current_variable = None
for paragraph in paragraphs_variables:
if paragraph.startswith('Variable: '):
fields = paragraph.split(' ')
name = fields[1]
dtype = VARIABLE_TYPES[fields[2]]
current_variable = VariableSpecification(name, dtype)
variables.append(current_variable)
elif paragraph:
key = paragraph.split(': ')[0]
value = paragraph[(len(key) + 2):]
# allow arrays of integers as needed for flag meanings
if value and (value[0] == '['):
value = ast.literal_eval(value)
current_variable.add_metadata(key, value)
# return result
return variables
def read_name_list(self, startmarker, endmarker):
"""Read a comma-separated list."""
# Read relevant line (comma-separated list)
namelines = parsedoc.get_paragraphs_between(self.paragraphs_all,
startmarker, endmarker)
# Parse
return namelines[0].strip().split(', ')
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 read_attributes(self, startmarker, endmarker):
"""Read attributes table from document and return as dictionary."""
# get relevant paragraphs
paragraphs_attributes = parsedoc.get_paragraphs_between(
self.paragraphs_all, startmarker, endmarker)
# parse attributes table
attributes = {}
for paragraph in paragraphs_attributes:
column = paragraph.split(': ')
key = column[0]
value = column[1]
attributes[key] = value
# return result
return attributes
def read_dimensions(self, startmarker, endmarker):
"""Read required dimensions from document and return as dictionary of required values (or None to indicate UNLIMITED)."""
# get relevant paragraphs
paragraphs_dimensions = parsedoc.get_paragraphs_between(
self.paragraphs_all, startmarker, endmarker)
# parse dimensions required
dimensions_required = {}
for paragraph in paragraphs_dimensions[1:]:
column = paragraph.split(': ')
if column[1] == DIMENSION_UNLIMITED:
dimensions_required[column[0]] = None
else:
dimensions_required[column[0]] = int(column[1])
# return result
return dimensions_required