# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:[cC][hH]|[lL][lL]|[rR][rR]|[qQ][uU]|[mnñvzsyjhxwMNÑVZSYJHXW]|[fpbtdkgcFPBTDKGC][lrLR]?|[lrLR])?(?:[iuüIUÜ][eaoéáóEAOÉÁÓ][iyuIYU]|[aáAÁ][hH]?[uúUÚ][aáAÁ]|[iuüIUÜ][hH]?[eaoéáóEAOÉÁÓ]|[eaoéáóEAOÉÁÓ][hH]?[iyuIYU]|[iíIÍ][hH]?[uúUÚ]|[uúüUÚÜ][hH]?[iíyIÍY]|[ieaouíéáóúüIEAOUÍÉÁÓÚÜ])(?:(?:(?:(?:[nmNM]|[rR](?![rR]))s?(?![ieaouíéáóúüIEAOUÍÉÁÓÚÜ]))|(?:(?:[mnñvzsyjhxwMNÑVZSYJHXW]|[lL](?![lL]))(?![ieaouíéáóúüIEAOUÍÉÁÓÚÜ]))|(?:(?:[fpbtdkgFPBTDKG]|[cC](?![hH]))(?![lrLR]?[ieaouíéáóúüIEAOUÍÉÁÓÚÜ])))(?!\s|$))?(?:[ndrlsxNDRLSX](?=\s|$))?"
test_str = ("SÍLABA CV\n"
" casado\n"
" caro\n\n"
"NÚCLEOS VOCÁLICOS\n"
" DIPTONGOS\n"
" ai, au, ei, eu, oi, ou, ui, iu, ia, ua, ie, ue, io, uo\n"
" varió comió diario miel\n\n"
" CON DOS CERRADAS\n"
" distribuido atribuir atribuí\n"
" muy fui rey\n"
" pausa tierra\n"
" ciudad buitre \n\n"
" CON H INTERCALADA\n"
" desahuciar, ahijado\n\n"
" TRIPTONGOS\n"
" santigüeis\n"
" guay guau rey\n"
" haliéutica hioides huaico\n\n"
" AUA\n"
" palauano\n"
" nahuatl cacahuatal\n\n"
" HIATOS NORMATIVOS (DOS CONSONANTES ABIERTAS)\n"
" aorta\n"
" héroe\n"
" almohada\n"
" línea\n\n"
" HIATOS\n"
" tú sabrías, sabías, vosotros sabíais\n"
" raúl oído búho\n"
" tío púa \n\n"
"ATAQUE C+LÍQUIDA\n"
" cromo\n"
" claro\n"
" cabra\n"
" triple\n"
" dígrafos \n\n\n"
"CODAS\n"
" silbo\n"
" cansado\n"
" tacto\n"
" texto\n"
" anticiparse\n"
" álbumes\n"
" asfixia\n"
" enloquecer\n\n"
" SUCESIÓN NS MS RS\n"
" transportar\n"
" transacción\n"
" torso\n"
" perspectivas\n"
" samsara \n\n"
" CODAS A FINAL DE PALABRA\n"
" hablan hablar hablad\n"
" riel rieles\n"
" sílex\n"
" recto\n\n"
"DÍGRAFOS\n"
" chica\n"
" coche\n"
" llave\n"
" calle\n"
" carro\n\n"
"EXTRANJERISMOS\n"
" pícnic\n"
" hámster\n"
" mozzarella\n"
" marketing\n"
" búnker\n"
" sándwich\n")
matches = re.finditer(regex, test_str, re.MULTILINE)
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