# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(^([0-9[:punct:]0-9]+|\p{No}|\d\p{No}) ?\s* ?([0-9[:punct:]0-9]+|\p{No}|\d\p{No})* ?\w* (cup|tsp|tbps|tablespoon|teaspoon|small|medium|pint|ounce|pound))|(^(small|Large|medium|Fresh))"
test_str = ("Should match:\n"
"1 Cups\n"
"2 tsp\n"
"3 tbps\n"
"1/2 tablespoon\n"
"3 tablespoons\n"
"1 tablespoon\n"
"3 teaspoons\n"
"1 small\n"
"Small chiles\n"
"23 Small chiles\n"
"1/2 a Small chile\n"
"1 1/2 cups kewpie\n"
"11/2 cups kewpie\n"
"1/3 cup fresh lemon juice\n"
"1 medium onion\n"
"Large\n"
"medium\n"
"Freshly\n"
"1½ cups Kewpie\n"
"½ cups Kewpie\n"
"1 pint\n"
"4 ounces\n"
"1 pound\n"
"2 pounds\n\n"
"Should not match:\n\n"
"1 Make the sauce\n"
"1 toast the bread\n"
"I want to make 1 piece of toast")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE)
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