# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r".{1,}?([。.」??!!]+|\n)"
test_str = (" そこは純白の空間だった。\n\n"
" 四方の壁は継ぎ目の無い白塗り、中央に鎮座する祭壇も雪を固めたように真っ白で、この部屋を満たす光もまた白く輝いていた。\n\n"
"「供物を捧げよ」\n\n"
" どこからとも無く部屋中に響き渡る声。\n\n"
" 開け放たれた両開きの扉、その暗い通路の向こうから人の列がやってくる。白い部屋と同じように、その人々もまた白尽くめであった。\n\n"
"染み一つ無い清潔な白いローブで全身を覆い、顔には白いマスクを被り、素肌を露出している部分が一切無い。")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE | 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