def extract_document_name(file_name):
"""
Extracts document name from its id
:param file_name:
:return:
"""
lines = reader.read_file_line('data/458/ids/' + file_name)
name = converter.convert_to_latin(lines[1])
return name.split(':')[0]
def extract_link_names(file_path):
lines = reader.read_file_line(file_path)
ret_val = []
for line in lines:
if line.endswith('\r\n'):
ret_val.append(line[:-2])
else:
ret_val.append(line)
return ret_val
def load_doc_num(file_path):
lines = reader.read_file_line(file_path)
doc_num_mapper = {}
num_doc_mapper = {}
clean_lines = [line[:-2] for line in lines if line.endswith('\r\n')]
clean_lines.append(lines[-1])
for line in clean_lines:
number = int(line.split(',')[0])
text = line[len(str(number)) + 1:]
doc_num_mapper[text] = number
num_doc_mapper[number] = text
return doc_num_mapper, num_doc_mapper
def extract_file_references(file_path):
lines = reader.read_file_line(file_path)
clean_lines = [line[:-2] for line in lines if line.endswith('\r\n')]
#clean_lines.append(lines[-1][:-2])
srcs = []
dists = []
for line in clean_lines:
splits = line.split('\t\t\t')
srcs.append(splits[0])
dists.append(splits[1])
return clean_lines, srcs, dists
def extract_document_links(file_name):
"""
Extracts linked documents for given document
:param file_name:
:return:
"""
destination_file = 'data/latin/links/' + file_name
if is_file_in_directory(file_name, 'data/458/links'):
all_lines = reader.read_file_line('data/458/links/' + file_name)
new_lines = []
for line in all_lines:
latin_line = converter.convert_to_latin(line)
new_lines.append(latin_line.split(':')[0])
writer.write_list_of_lines(destination_file, new_lines)