def create_gannt_corpus_obj():
corpus = Corpus()
doc_id = 0
source_file_directory = 'GANNT/high/'
target_file_directory = 'GANNT/low/'
# Gets a list of the source document file names and sort by ID number
source_file_names = [
f for f in listdir(source_file_directory)
if isfile(join(source_file_directory, f))
]
source_file_names.sort()
# Iterates through the source document files and stores it's contents and names in document dictionary
# Dictionary's key is an id number that increments with each document.
for fileName in source_file_names:
doc_name = fileName.rstrip('.txt')
temp_document = Document(
doc_id, doc_name,
open(source_file_directory + fileName, 'r').read().rstrip("\n"))
corpus.add_source_document(temp_document)
doc_id += 1
# Gets a list of the target document file names and sort by ID number
target_file_names = [
f for f in listdir(target_file_directory)
if isfile(join(target_file_directory, f))
]
target_file_names.sort()
# Get and add to
for fileName in target_file_names:
doc_name = fileName.rstrip('.txt')
temp_document = Document(
doc_id, doc_name,
open(target_file_directory + fileName, 'r').read().rstrip("\n"))
corpus.add_target_document(temp_document)
doc_id += 1
return corpus
def create_icebreaker_corpus_obj():
source_file = 'IceBreaker/Requirements.csv'
target_file = 'IceBreaker/ClassDiagram.csv'
corpus = Corpus()
index = 0
with open(source_file) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
for name, desc in csv_reader:
doc = Document(index, name, desc)
corpus.add_source_document(doc)
csv_file.close()
with open(target_file) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
for name, desc in csv_reader:
doc = Document(index, name, desc)
corpus.add_target_document(doc)
csv_file.close()
return corpus
