# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^([MF]\/\d{2})\/ (?#Gender/Age, required.)
( (?#Height, required.)
(?:\d{1}[\'\’]? (?#Optional \'\’ unit markings.)
(?: (?#Groups starting with ?: are non-capturing.)
(?:
[02-9]|1[01]?
)(?:[\"”]|\'\')? (?#Optional "\'\' unit markings.)
)?
)|
\d{1,3}cm|
[12]m(?:\d{1,2}(?:cm)?)? (?#Optional cm unit marking.)
)\ ?
(?#Weight before to after, required. ?P<weight> is a named capturing group, associated with match sub-pattern ?P=weight. It forces the user to be consistent, either using only lbs, or only kg for the entire match, also used in Lifting Stats section.)
\[(\d{2,3}\ ?(?P<weight>lbs|kg)\ to\ \d{2,3}\ ?(?P=weight))\]\ ? (?# Optional space before lbs|kg. *Changed to require space before and after "to".)
\( (?#Time Period, required)
(
(?:\d{1,2}\ ?years?)| (?#Optional space before years, optional s in years.)
(?:
(?:[2-9]|1[01]?)\ ?(?:month|week)s? (?#Optional space before months|weeks, optional s at end.)
)|
(?:\d{1,2}\ ?years?[;,]?\ ? (?#Optional space before years, optional s in years. Optional space after.)
(?:[02-9]|1[01]?)\ ?months?)| (?#Optional space before monthss, optional s in months.)
)
\)\ ?
(?:\ ?\+\ ?\( (?#Lifting Stats, optional. Optional space before/after + .)
((?:[DSBO]:\ ?(?:\d{2,3})\ ?(?P=weight)(?:[;,]\ ?)?){1,4}) (?# Optional space after [DSBO]: . Optional space before lbs|kg. Optional space after ;, delimiter. Changed from 4 repeated statements to one recursive group.)
\)(?<=[sg]\)))? (?# ?<= is a Positive Lookbehind. It requires the ; or , delimiter between stats, but prevents the delimiter after the last stat.)
(\ .*)? (?#Comments, optional. *Changed: Required space before comments section.)
$|^\[Meta\].*
"""
test_str = "M/24/5'10\" [175lbs to 150lbs] (1 year)"
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