# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\b.+)(?=\1)"
test_str = ("...\n"
"bedeubedeu France The Provençal name for tripe\n"
"bee balmbee balm Bergamot\n"
"beechmastbeechmast Beech nut\n"
"beech nutbeech nut A small nut from the beech tree,\n\n"
"genus Fagus and Nothofagus, similar in\n"
"flavour to a hazelnut but not commonly used.\n"
"A flavoursome oil can be extracted from\n"
"them. Also called beechmast\n\n"
"beechwheatbeechwheat Buckwheat\n"
"beefbeef The meat of the animal known as a cow\n\n"
"(female) or bull (male) (NOTE: The Anglo-\n"
"saxon name ‘Ox’ is still used for some of what\n"
"were once the less desirable parts e.g. oxtail,\n"
"ox liver)\n\n"
"beef bourguignonnebeef bourguignonne See boeuf à la\n"
"bourguignonne\n"
"...")
matches = re.finditer(regex, test_str)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html