Counts total number of duplicate lines from a CPD output

cpd-sum.py

# Counts total number of duplicate lines from a CPD output.
# Example:
#    pmd-bin-5.0.5/bin/run.sh cpd --minimum-tokens 100 --files ../mysource --format text --language java | python cpd-sum.py

import fileinput
import re

nlines = 0
places = 0
total_dups = 0

for line in fileinput.input():

    m = re.match(r'Found a (\d+) line', line)
    if m:
        dups = nlines * (places - 1)
        total_dups += dups

        nlines = int(m.group(1))
        places = 0

    m = re.match(r'Starting at line', line)
    if m:
        places += 1

print total_dups