# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"([\w*-′]*([\[(]([\[(]?[a-zA-Zα-ωΑ-Ωµ\-′,:]+\d?[+-]?[\])]?)+[\])\d+-]{1,})[\w*-′]*)|(([A-z]+[a-z]*\d)+([A-z]+[a-z]*\d?)*)"
test_str = ("\"Fe(iii) or iron(iii) [Fe(Rtpen)X](A)n, n = 1, 2; X = Cl, Br; Rtpen = N-alkyl-N,N′,N′-tris(2-pyridylmethyl)ethane-1,2-diamine, alkyl = R = CH3CH2, CH3CH2CH2, HOCH2CH2, (CH3)2CH, C6H5, and C6H5CH2; A = ClO4, PF6.\"\n"
"\"iron(iii) \n"
"[Fe(Rtpen)(η1-OCH3)]2+ \n"
"[Fe(Rtpen)(η1-OOH)]2+ from iron(ii)\"\n"
"\"[FeIIIOOH]2+ rather than [FeIIIOO]+ species are the p\"\n"
"[(Rtpen)Fe(µ,η2:η2-O2)Fe(Rtpen)]4+\n"
"iron(iii)\n"
"Fe(iii)\n"
"[FeIIIOOH]2+\n"
"[Fe(Rtpen)Cl]+\n"
"[Fe(Rtpen)(η1-OOH)]2+\n"
"[Fe(Rtpen)X](A)n\n"
"[(Rtpen)Fe(µ,η2:η2-O2)Fe(Rtpen)]4+\n"
" Fe(Rtpen)(η2-OO)]+,\n"
"N′-tris(2-pyridylmethyl)ethane-1,2-diamine\n"
"of [Fe(Rtpen)(η1-OOH)]2+ pro\n"
" (ESR, UV-vis, ESI MS) \n"
" [Fe(Rtpen)(η1-OOH)]2+, R = CH3CH2, CH3CH2CH2, HOCH2CH2, (CH3)2CH, C6H5, and C6H5CH2.\n"
"f [Fe(ettpen)Cl]ClO4 instead of [Fe(bztpen)Cl]ClO4 \n"
"[Fe(Rtpen)Cl]A, A = ClO4, PF6, are as expected ESR silent.\n"
"[Fe(Rtpen)Cl](PF6) and [Fe(Rtpen)Cl](PF6)2\n"
"e µ-oxo complex [(bztpen)ClFe(µ-O)FeCl(bztpen)](PF6)2 which could be isolated.\n"
"H2O\n"
"[Fe(bztpen)Cl](ClO4)2\n"
" solution at 100 K, a rhombic low-spin signal (g = 2.32, 2.14, 1.93) is present in the spectra of the Fe(iii) complexes (Fig. 3a)\n"
").\n\n"
"metpen–Fe(iii)–peroxide complexes, lead to assignment of end-on coordination for the hydroperoxide species, e.g., [Fe(Rtpen)(η1-OOH)]2+, and side-on (η2) peroxide coordination in their deprotonated derivatives, e.g., [Fe(Rtpen)(η2-OO)]+ (Scheme 1)")
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