# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^
# Uncomment to allow prefix continuation (second letter of a dangling match)
# ([abcdefghiklmnoprstuvy\ ])?
( \
|(?: # Single-letter elements
[BCFHIKNOPSUVWY]
)
|(?: # Two-letter elements.
(?:A[cglmrstu])|(?:B[aehikr])|(?:C[adeflmnorsu])|(?:D[bsy])
| (?:E[rsu])|(?:F[elmr])|(?:G[ade])|(?:H[efgos])|(?:I[nr])
| (?:K[r])|(?:L[airuv])|(?:M[cdgnot])|(?:N[abdehiop])
| (?:O[gs])|(?:P[abdmortu])|(?:R[abefghnu])|(?:S[bcegimnr])
| (?:T[abcehilms])|(?:X[e])|(?:Yb)|(?:Z[nr])
)
|(?: # Smushed trigrams. No need to go past trigrams because two twos make four
(?:A(?:ga|gd|ge|la|lr|md|mg|mt|ra|re|rg|ta|te|tl|tm))
|(?:E(?:ra|re|rg))
|(?:G(?:ag|al|am|ar|at|er))
|(?:L(?:ag|al|am|ar|at|ra|re|rg))
|(?:M(?:ga|gd|ge|ta|te|tl|tm))
|(?:R(?:ag|al|am|ar|at|er|ga|gd|ge))
|(?:T(?:ag|al|am|ar|at|er|la|lr|md|mg|mt))
|(?:X(?:er))
|(?:Z(?:ra|re|rg))
)
# repeated any number of times
)+
# Uncomment to allow last letter if it's a potential first letter of the next word
# ([ADEGLMRTXZ]\ *)?
$
"""
test_str = ("**(See bottom for Javascript/one-line version)**\n"
"If you want continuation -- to look for \"fez\" \"rave\" \"rites\" chains, strike the second and second-to-last lines. Latex needs a suffix and ear needs a prefix.\n"
"latex\n"
"ear\n"
"latexear\n"
"fez\n"
"rave\n"
"rites\n"
"fezraverites\n"
"if you don't want overlap, comment out the big group with (?<=..) tests. Walter and lag will not match: lag is La + Ag but can't be L+Ag or La+G; walter is W+Al+Te+Er but there's no single A, L, T, E or R to make it a strict chain of elements.\n"
"Walter\n"
"aga\n"
"McLvinandfezrobHogwartsWizrdsofMoney\n"
"## Match:\n"
"McLvIn\n"
"McLvinandfezrobHogwartsWizrdsofMoney\n"
"zr\n"
"McLvinand\n"
"ergo\n"
"Orgasmicallabkitscashflow\n"
"update\n"
"Organicfurbies\n"
"Babkes\n"
"WalterWhite\n"
"That\n"
"ibexesnogladybirds\n"
"Xenophobic\n"
"picnicforgus\n"
"snapes\n"
"siriusblack\n\n\n"
"## match until last letter, and last letter potentially starts a new word (allows continuation)\n"
"fez\n"
"McLvinandfez\n"
"bobatea\n\n"
"# La + At + Te\n"
"late\n"
"# the x awaits an e in the next word\n"
"latex\n"
"# N + Nd + Dy + Y + Yb\n"
"ndyb\n"
"# the a is a potential continuation\n"
"andy\n"
"# ...but the x can't be a second letter\n"
"xndyb\n\n"
"## Don't Match at some interior point in line\n"
"Jemmamead\n"
"## Don't Match anywhere in line\n"
"JemmaQmead\n\n"
"### For Javascript:\n\n"
"^([abcdefghiklmnoprstuvy\\s])?(\\ |(?:[BCFHIKNOPSUVWY])|(?:(?:A[cglmrstu])|(?:B[aehikr])|(?:C[adeflmnorsu])|(?:D[bsy])|(?:E[rsu])|(?:F[elmr])|(?:G[ade])|(?:H[efgos])|(?:I[nr])|(?:K[r])|(?:L[airuv])|(?:M[cdgnot])|(?:N[abdehiop])|(?:O[gs])|(?:P[abdmortu])|(?:R[abefghnu])|(?:S[bcegimnr])|(?:T[abcehilms])|(?:X[e])|(?:Yb)|(?:Z[nr]))|(?:(?:A(?:ga|gd|ge|la|lr|md|mg|mt|ra|re|rg|ta|te|tl|tm))|(?:E(?:ra|re|rg))|(?:G(?:ag|al|am|ar|at|er))|(?:L(?:ag|al|am|ar|at|ra|re|rg))|(?:M(?:ga|gd|ge|ta|te|tl|tm))|(?:R(?:ag|al|am|ar|at|er|ga|gd|ge))|(?:T(?:ag|al|am|ar|at|er|la|lr|md|mg|mt))|(?:X(?:er))|(?:Z(?:ra|re|rg))))+([ADEGLMRTXZ]\\ *)?$")
matches = re.finditer(regex, test_str, re.IGNORECASE | re.MULTILINE | re.VERBOSE)
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