def check_load_file(filename, files):
if not os.path.exists(filename) or not os.path.isfile(filename):
print 'Error can not find the specified file'
return
filetype = filename.split('.')[1]
if filetype == 'csv':
csv_data = CSVData(filename)
csv_data.parse_vectors()
files.append(csv_data)
elif filetype == 'txt':
txt_data = TXTData(filename)
txt_data.read_document()
files.append(txt_data)
else:
print 'Error unrecognized file type ', filetype
return
print 'Parsed file: ', filename
def run_test_suite():
greater = raw_input("Find words with frequencies greater than: ")
equal = raw_input("Find words with frequencies equal to: ")
csvPath = 'data/csv'
txtPath = 'data/text'
output = ''
output += "Grabbing CSV files...\n"
csvList = os.listdir(csvPath)
output += "Grabbing TXT files...\n"
txtList = os.listdir(txtPath)
output += "Beginning CSV tests\n\n"
for fname in csvList:
if fname.split('.')[1] != 'csv':
continue
filePath = os.path.join(csvPath, fname)
data = CSVData(filePath)
output += "##################\n"
output += "Opening "
output += fname
output += "\n##################"
output += "\nParsing Vectors...\n"
data.parse_vectors()
output += data.print_output()
output += "Beginning TXT tests\n\n"
for fname in txtList:
if fname.split('.')[1] != 'txt':
continue
filePath = os.path.join(txtPath, fname)
data = TXTData(filePath)
output += "\nOpening "
output += fname
data.read_document()
output += data.print_count_statistics()
output += data.print_freq_statistics(equal, greater)
f = open('output.test', 'w')
f.write(output)
f.close()
