# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^([\w]+)\s(.*?)(?=\(|incl\.|[A-Z]$)(?:\(([a-zA-Z]+)-?(.*?)\))?(?:.*(incl.*))?([A-Z])$"
test_str = ("Branded 16 ft Box Truck (Entrent - Avalen Owned) incl. New DSP Insurance PaymentP\n"
"Branded Extended Van (Entrent - Avalen Owned) incl. New DSP Insurance PaymentR\n"
"Branded Custom Van (Entrent - Avalen Owned) incl. New DSP Insurance PaymentR\n"
"Branded Custom Delivery Van (Entrent -Avalen Owned) incl. New DSP\n"
"Branded Extended Van (CeasePlan - Avalen Owned)R\n"
"Branded Extended Van (Entrent - Avalen Owned)R\n"
"Owned Van incl. New DSP Insurance PaymentP\n"
"Rental Van (Unbranded CSP)R\n"
"Owned 16ft Box TruckR\n"
"Branded 24ft Box Truck (Entrent - Leased)P\n"
"Leased Van incl. New Csp Insurance PaymentR")
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