#---------- dupwords.py----------#
# Detect doubled words and display with context
# Include words doubled across lines but within paras

import sys, re, glob
for pat in sys.argv[1:]:
    for file in glob.glob(pat):
        newfile = 1
        for para in open(file).read().split('\n\n'):
            dups = re.findall(r'(?m)(^.*(\b\w+\b)\s*\b\2\b.*$)', para)
            if dups:
                if newfile:
                    print '%s\n%s\n' % ('-'*70,file)
                    newfile = 0
                for dup in dups:
                    print '[%s] -->' % dup[1], dup[0]