Question

I need to. Modify my mapper to count words after removing punctuation marks during mapping.

mapper is below:

import sys

sys.path.append('.')

for line in sys.stdin:

line = line.strip() #trim spaces from beginning and end

keys = line.split() #split line by space

for key in keys:

value = 1

print ("%s\t%d" % (key,value))

Answer 1

import sys
import string

sys.path.append('.')

for line in sys.stdin:
    line = line.strip()  # trim spaces from beginning and end
    
    modified_line = ''  # create an empty string for modified line  
    for ch in line:  # go through all characters of line
        if ch not in string.punctuation:  # if the character is not a punctuation, 
            modified_line += ch  # then add it to modified line
    
    keys = modified_line.split()  # split line by space
    for key in keys:
        value = 1
        print("%s\t%d" % (key, value))