# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b\p{Greek}+"
test_str = ("Ὁμώνυμα λέγεται Aequivoca dicuntur ὧν ὄνομα μόνον κοινόν, quorum nomen solum commune est\n"
"ὁ δὲ κατὰ τοὔνομα λόγος τῆς οὐσίας ἕτερος secundum nomen vero substantiae ratio diversa, οἷον ζῷον ut animal ὅ τε ἄνθρωπος καὶ τὸ γεγραμμένον homo et quod pingitur· \n\n\n"
"ἀ·κρασία, -ας, ἡ\n"
"Noun (Fem. 1st Decl.)\n\n"
"Not all forms below are necessarily attested. Highlighted words may or may not be a match to the GNT or LXX, if another word also inflects the same way.\n\n"
"1st Decl. Feminine Noun\n"
"Contracted Uncontracted\n"
"Sg Voc ακρασια ακρασι·α\n"
"Nom\n"
"Acc ακρασιαν[GNT] ακρασι·αν\n"
"Dat ακρασιᾳ ακρασι·ᾳ\n"
"Gen ακρασιας[GNT] ακρασι·ας\n"
"Pl Voc ακρασιαι ακρασι·αι\n"
"Nom\n"
"Acc ακρασιας[GNT] ακρασι·ας\n"
"Dat ακρασιαις[LXX] ακρασι·αις\n"
"Gen ακρασιων ακρασι·ων\n")
matches = re.finditer(regex, test_str, re.UNICODE)
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