# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(# the number at the beginning
[-+]? # optional leading sign
\d+# the digits to the left of the decimal
(?:\.\d+)? # an optional decimal amount
)
(#units
\/? #optional slash
[a-zA-Z]+ # must be alphabetic
(\^?[-+]?\d+(?:\.\d+)?)? # a caret followed by our same/initial digit pattern
)+
"""
test_str = ("Very much a stupid beginner question, but trying to make a regex expression which would take in \"5ms-1\", \"17km/h\" or \"9ms^-2\" etc. with these ambiguous units and ambiguous formats. Please help, I can't manage it\n"
"5ms-1\n"
"17km/h\n"
"9ms^-2\n\n"
"-5mph\n"
"6.8m/h\n"
"+8liters/hectacre^2\n\n"
"5/h\n"
"1m^2s^2\n\n"
"this will also match the 21st century, 7eleven, 3M, and similar things.\n\n")
matches = re.finditer(regex, test_str, re.MULTILINE | re.VERBOSE)
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