def fix_length(row) :
"""Takes in a row and return it with the event name, first name and last
name columns truncated after 30 characters.
Parameters:
row (str): String of data with comma separators.
Return:
str: The modified row is returned.
Preconditions:
row != None
"""
eventname = get_column(row, 0) #Get event name column from 'row'.
firstname = get_column(row, 1)
lastname = get_column(row, 2)
if len(firstname) > 30 :
firstname = truncate_string(firstname, 30) #truncate firstname if it's over 30 characters long
if len(lastname) > 30 :
lastname = truncate_string(lastname, 30) #truncate lastname if it's over 30 characters long
if len(eventname) > 30 :
eventname = truncate_string(eventname, 30) #truncate eventname if it's over 30 characters long
row = replace_column(row, eventname, 0) #replace first name column with the truncated firstname
row = replace_column(row, firstname, 1) #replace first name column with the truncated firstname
row = replace_column(row, lastname, 2) #replace last name column with the truncated lastname
return row
def check_name(row) :
"""Checks a row to see whether the first name and last name columns contains valid data.
Parameters:
row (str): String of data with comma separators.
Return:
bool: Return True if data is corrupt, otherwise return False.
Preconditions:
row != None
"""
first_name = get_column(row, 1) #Get the first name column from 'row'.
last_name = get_column(row, 2)
with open("athlete_names.csv", "r") as names: #Imports the athlete_names.csv master file.
for row in names :
row = row[:-1] #Removes the new line characters (\n) from the end of each row.
first_master = get_column(row, 0) #First name extracted from the master file.
first_master = truncate_string(first_master, 30) #We are comparing between truncated versions of the strings.
last_master = get_column(row, 1)
last_master = truncate_string(last_master, 30)
if (first_name == first_master) and (last_name == last_master) :
return False #If a match is found, return False.
return True
def truncate_names_in_row(row):
"""Return the row with columns 2, 3, & 4 truncated
Parameters
row (list): list of columns in the row
Return
row (list): list of columns in the row now with column 2, 3, & 4 truncated
Preconditions
row != None
"""
row[1] = truncate_string(row[1], MAX_CHARACTERS_COLUMN_2)
row[2] = truncate_string(row[2], MAX_CHARACTERS_COLUMN_3)
row[3] = truncate_string(row[3], MAX_CHARACTERS_COLUMN_4)
return row
def max_char_30(row): # Truncates sport, atheletes' first and family name to 30 characters
""" Truncate data in indicated column to 30 characters.
Parameters:
row (str): String of data with comma separators (CSV format).
Return:
str: Updated row with truncated data in columns 1 ~ 4.
"""
for i in range(4):
row_update = get_column(row, i) # row_update now contain data from row and in the 'i' value of column
row_updated = truncate_string(row_update, 30) # Truncates string to 30 characters and stores in row_updated
row = replace_column(row, row_updated, i) # Updated data replaces the exisiting data at indicated column in the row
return row
def check_event_name(row) :
"""Checks a row to see whether the event name column contains valid data.
Parameters:
row (str): String of data with comma separators.
Return:
bool: return True if data is corrupt, otherwise return false
Preconditions:
row != None
"""
event_name = get_column(row, 0) #Get the event name column from 'row'.
with open("event_names.csv", "r") as event_names: #Imports the event_names.csv master file.
for row in event_names :
row = row[:-1] #Removes the new line characters (\n) from the end of each row.
row = truncate_string(row, 30) #We are comparing between truncated versions of the strings.
if event_name == row :
return False #If a match is found between 'event_name' and one of the event names in the master file, set invalid_event to False.
return True #No match is found, so return True.
def truncate_name_length(row_to_process):
"""Returns a row with first three columns truncated to size 30.
Parameters:
row_to_process (str): Row whose column values are to be truncated.
Returns:
str: Row with event and athlete names truncated to size 30.
Preconditions:
maximum character length of the columns is specified as constant variable.
functions get_column, replace_column and truncate_string have been \
imported from assign1_utilities.
"""
column_position = 0
row_length_check = row_to_process
while column_position < 3:
value = get_column(row_to_process, column_position)
if len(value) > NAME_MAX_CHARACTER_LENGTH:
value = truncate_string(value, NAME_MAX_CHARACTER_LENGTH)
row_length_check = replace_column(row_length_check, value,
column_position)
column_position += 1
return (row_length_check)
def check_valid_rules(row_to_process, corrupt):
"""Returns a string with value True if values are invalid or \
row doesn't follow rules checked earlier
Parameters:
row_to_process (str): Row whose values are to be validated.
corrupt (boolean) : status of row
Returns:
boolean: corrupt value as input or set as True if columns doesn't have valid values
Preconditions:
corrupt value is already True if the row doesn't abide with rules checked before.
functions get_column and replace_column have been imported from assign1_utilities.
column position specified as constant variable.
"""
corrupt_after_check = corrupt
"""Check for invalid event name"""
event_name_value = get_column(row_to_process, EVENT_NAME_POSITION)
is_event_name_valid = False
# For the event name matches with any valid name in file it is valid
with open("event_names.csv", "r") as valid_event_name_file:
for row in valid_event_name_file:
valid_event_name = row[:-1] # Remove /n
valid_event_name = truncate_string(valid_event_name,
NAME_MAX_CHARACTER_LENGTH)
if valid_event_name == event_name_value:
is_event_name_valid = True
if is_event_name_valid == False:
corrupt_after_check = True
"""Check for invalid country code"""
country_code_value = get_column(row_to_process, COUNTRY_CODE_POSITION)
is_country_code_valid = False
# If the country code matches with any valid name in file it is valid
with open("country_codes.csv", "r") as valid_country_code_file:
for row in valid_country_code_file:
valid_country_code = row[:-1] # Remove /n
if valid_country_code == country_code_value:
is_country_code_valid = True
if is_country_code_valid == False:
corrupt_after_check = True
"""Check for invalid athlete name"""
athlete_first_name_value = get_column(row_to_process,
ATHLETE_FIRST_NAME_POSITION)
athlete_surname_value = get_column(row_to_process,
ATHLETE_SURNAME_POSITION)
is_athlete_name_valid = False
# If the event name matches with any valid name in file it is valid
with open("athlete_names.csv", "r") as valid_athlete_names_file:
for row in valid_athlete_names_file:
valid_athlete_first_name = get_column(row, 0)
valid_athlete_surname = get_column(row, 1)
valid_athlete_surname = valid_athlete_surname[:-1] # Remove /n
valid_athlete_first_name = truncate_string(
valid_athlete_first_name, NAME_MAX_CHARACTER_LENGTH)
valid_athlete_surname = truncate_string(valid_athlete_surname,
NAME_MAX_CHARACTER_LENGTH)
if valid_athlete_first_name == athlete_first_name_value \
and valid_athlete_surname == athlete_surname_value:
is_athlete_name_valid = True
if is_athlete_name_valid == False:
corrupt_after_check = True
# Return input corrupt value or set corrupt value as True if names are invalid
return (corrupt_after_check)