# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(?<!\d[,.])(?<!\d-)((?:\d+/)?\d+(?:[,.]\d+)*)\b(\s*(\w*)/)?\s*((?(2)\w+|\w+\s+per\s+\w+))(?=\s*(?:[,)]|$))"
test_str = ("3M™ Victory Series™ Bracket MBT™ 017-873, .022, UL3, 0T/8A, Hk, 5/Pack\n"
" 5/Pack\n"
"3M™ BX™ Dual Reader Protective Eyewear 11458-00000-20, Clear Anti-Fog Lens, Silver/Black Frame, +2.0 Top/Bottom Diopter, 20 ea/Case\n"
" 20 ea/Case\n"
"4220VDS-QCSHC/900-000/A CABINET EMPTY\n"
" No units\n"
"3M™ Bumpon™ Protective Product SJ5476 Fluorescent Yellow, 3.000/Case\n"
" 3.000/Case\n"
"3M™ Bumpon™ Protective Products SJ61A2 Black, 10,000/Case\n"
" 10,000/Case\n\n"
"QWERTYUI PN-DR, Coarse, TR, 1-1/2 in, 50/Carton, 200 ea/Case, Dispenser Pack\n"
" 50/Carton, 200 ea/Case\n"
"2841 PC GREY AS/AF (20/CASE)\n"
" 20/CASE\n"
"TYPE.2 86421-K40-F000, 1 Set/Pack, 100 Packs/Case\n"
" 1 Set/Pack, 100 Packs/Case\n"
"RTYU 31655, 240+, 6 in, 50 Discs/Roll, 6 Rolls/Case\n"
" 50 Discs/Roll, 6 Rolls/Case\n"
"Clear, 1 in x 36 yd, 4.8 mil, 24 rolls per case\n"
" 24 rolls per case\n"
"3M™ Victory Series™ Bracket MBT™ 017-873, .022, UL3, 0T/8A, Hk, 5/Pack\n"
" 5/Pack\n"
"3M™ BX™ Dual Reader Protective Eyewear 11458-00000-20, Clear Anti-Fog Lens, Silver/Black Frame, +2.0 Top/Bottom Diopter, 20 ea/Case\n"
" 20 ea/Case\n"
"4220VDS-QCSHC/900-000/A CABINET EMPTY\n"
" No units\n"
"3M™ Bumpon™ Protective Product SJ5476 Fluorescent Yellow, 3.000/Case\n"
" 3.000/Case\n"
"3M™ Bumpon™ Protective Products SJ61A2 Black, 10,000/Case\n"
" 10,000/Case")
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