# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<!\d|\.)\d+(?:\.\d+)?\s*?(?:mg|kg|ml|q\.s\.|ui|M|g|µg)(?!\w)"
test_str = ("Examples: 0.9 mg, 9 mg, 9mg, 0.9mg\n"
"0.9mg is the approximate dosage \n"
"98 is not an acceptable number; it has no unit\n"
"9.4.4mg is not acceptable; it is formatted wrong\n"
"9.7kg is fine, but 9.7kgasdfghjkl is not")
matches = re.finditer(regex, test_str, re.MULTILINE)
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