# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?P<amount>-?\d+(?:\.\d*)?)[^\S\n]*(?P<degrees>°|deg(?:rees?)?|in)?[^\S\n]*(?P<unit>c(?:(?=el[cs]ius\b|entigrades?\b|\b))|f(?:(?=ahrenheit\b|\b))|k(?:(?=elvins?\b|\b)))"
test_str = ("70 degrees celsius\n"
"70 degree fahrenheit\n"
"70 degrees c\n"
"70 degrees f\n"
"70 ° f\n"
"70 ° c\n"
"70°c\n"
"70°f\n"
"70 deg celsius\n"
"70 deg centigrade\n"
"70 deg fahrenheit\n"
"-30.5 in Kelvin\n"
"-30.5 degrees Kelvin\n"
"-30.5 Kelvin\n"
"70F\n"
"70C\n"
"70 c\n"
"70 f\n"
"70k\n"
"100 deg celcius\n\n"
"Oh, it seems I have an oven from Europe. If the recipe calls for 325 degrees fahrenheit and water boils at 100 centigrades, then... multiply, and... voila! Set your oven for 650 degrees celsius--that should make your cookies crispy-brown!\n\n"
"# Failures\n\n"
"70 degrees # too ambiguous\n"
"70 deg felsius # ensure we don't mix fahrenheit and celsius\n\n")
matches = re.finditer(regex, test_str, 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