# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
#Modifiers << NOT GOING TO DO THESE HERE.
#∂ Before After Until in?Between
#∂ onwards
#Time-Time << Don't need as both times will match
#Lonely HOURS List: 10,time or 12 <not going to do this
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - BIG TIME REGEX - - - - - - - - - - - -
#LONELY HOURS
#These guys are just \d\d. So we identify them through proximity to known times
(?:
#Boundary Lookaround
(?<=[ ]|^|[^\d\.:\r\n$£-])
#hour - you always have hours
(?:1[0-9]|2[0-4]|0?[0-9])
(?:
#Hour [or / to - , and]
#People don't say "12pm or 3?" much. Build it if it comes up.
(?:[ ]? (?:or|[,/-]|to|and) [ ]?)
)
){0,3}
#TIME BASICS:
#Basic times that are definitely times. Have to come last so longer strings match first.
#Boundary Lookaround (BREAK THIS FOR THE LONELY NUMBERS)
# (?<=[ ]|^|[^\d\.:\r\n$£-])
#hour - you always have hours
( (?:1[0-9]|2[0-4]|0?[0-9]) )
#Clarifier. Minutes, AM|PM, a TimeZone or a combination.
(
#Minutes
(?:[ ]?[\:\. ][ ]?) ([0-5][0-9])
#AM|PM
| (?:[ ]?[ap]m|[ ]?o\'?[ ]?clock)
#TimeZones
| (?:[ ]? (?:PS?T|GMT|∆USA|∆US|ET|BST|∆UK
|UK[ ]?[Tt]ime|[Ee]astern[ ]?[Tt]ime|[Pp]acific[ ]?[Tt]ime|[Cc]entral[ ]?[Tt]ime
|∆UTC|ACDT|ACST|ACT|ACT|ADT|AEDT|AEST|AFT|AKDT|AKST|AMST|AMT|AMT|ART|AST|AST|AWDT
|AWST|AZOST|AZT|BDT|BDT|BIOT|BRST|BRT|BST|BST|BST|BTT|CCT|CDT|CDT|CEDT|CEST|CET
|CHADT|CHAST|CHOT|ChST|CHUT|CIST|CIT|CKT|CLST|CLT|COT|CST|CST|CST|CST|CST|CT|CVT
|CWST|CXT|DAVT|DDUT|DFT|EASST|ECT|ECT|EDT|EEDT|EEST|EET|EGST|EGT|EIT|EST|EST|FET
|FJT|FKST|FKST|FKT|FNT|GALT|GAMT|GFT|GILT|GIT|GMT|GST|GST|GYT|HADT|HAEC|HAST|HKT
|HMT|HOVT|HST|IBST|ICT|IDT|IRDT|IRKT|IRST|IST|IST|IST|JST|KGT|KOST|KRAT|KST|LHST
|LHST|LINT|MAGT|MART|MAWT|MDT|MET|MEST|MHT|MIST|MMT|MSK|MST|MST|MST|MUT|MVT|MYT|NCT
|NDT|NFT|NPT|NST|NT|NUT|NZDT|NZST|OMST|ORAT|PDT|PETT|PGT|PHOT|PKT|PMDT|PMST|PONT
|PST|PST|PYST|PYT|RET|ROTT|SAKT|SAMT|SAST|SBT|SCT|SGT|SLST|SRET|SRT|SST|SST|SYOT
|TAHT|THA|TFT|TJT|TKT|TLT|TMT|TOT|TVT|ULAT|USZ1|UYST|UYT|UZT|VET|VLAT|VOLT|VOST
|VUT|WAKT|WAST|WAT|WEDT|WEST|WET|WST|YAKT)\b )
#Now enable the combo. Note ideally we would say "use one of each" e.g., =/10:234210
){1,3}
#Lonely HOURS: List of Military times <Here we have enough info to allow no ":".
|( (?:
#Boundary Lookaround
(?<=[ ]|^|[^\d\.:\r\n$£-])
#Must open with a military time, no "445" must be "0445"
(?:1[0-9]|2[0-4]|0[0-9])
(?:[ ]?[0-5][0-9][ ]?)
#or and
(?:[ ]? (?:or|[,/-]|to|and) [ ]?)
#2-4 military times, including the closing one
){1,3}
#Must also end with a military time
(?:1[0-9]|2[0-4]|0[0-9])
(?:[ ]?[0-5][0-9][ ]?)
)
#Post rationalise the boundary criteria (?:\b|$|,\b)
"""
test_str = ("NEW TIME MATCHING REGEX\n"
"*** REGEX 1: LONELY NUMBERS ***\n"
"12 or 3pm\n"
"4/5CET\n"
"5-6pm\n"
"2,4,5pm\n"
"1,3 or 6pm\n"
"OK. 1,2,3 and 5pm are available\n"
"12pm or 3pm <Shouldn't match \"or\"\n\n"
"#Military times\n"
"1200 or 1300.\n"
"1100,1300 or 1400.\n"
"121212121212121212 <don't match\n\n"
"*** REGEX 2: BASICS ***\n"
"1\n"
"11am or 2pm\n"
"12pm\n"
"12 CET\n"
"12pm CET\n"
"12.32pm\n"
"14 pm\n"
"10.00?\n"
"0.15\n"
"3 : 34\n"
"10 53\n"
"00.15\n"
"at3.00?\n"
"10amis good for me\n"
" 4 oclock\n"
"2o'clock\n"
"2 o clock\n"
"yes,3 am\n"
"12.50 GBP\n"
"USD 4.00\n\n"
"£12.50\n"
"10.93?\n"
"00000\n"
"0000-559\n"
"00001\n\n\n\n\n"
"00001\n"
"00001\n"
"01300\n"
"01700\n"
"from 2 - 6\n"
"there is about 3 of them\n"
"Not sure, maybe 14 apples?\n"
"how about 10 tomorrow? << should fail\n"
"10 tomorrow?\n"
"about £23.00\n\n\n"
"10,11 or 12\n"
"10, 11 or 2?\n"
"10 or 12?\n"
"10 or my place?\n"
"1030 or 1130\n"
"10.30 or 12?\n"
"10 and 11 work\n"
"10, 11, 12th?\n\n"
"1,000\n")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE | 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