# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(*UTF16)
x (?<! \w x ) [\d._ –-]* (*SKIP) (*F)
|
order (?<! \w order ) [\W_]* (?:number)? [\W_]* [\d._ –-]* (*SKIP) (*F)
|
[1-578]
(?:[._ –-]{0,3}+\d){2}
(?: 0{2} [\d._ –-]* (*SKIP) (*F) )?
(?:[._ –-]{0,3}+\d){2}
(?=
(?: 0{4} [\d._ –-]* (*SKIP) (*F) )?
(?:[._ –-]{0,3}+\d){4}
)
|
0
(?: 0{2} [\d._ –-]* (*SKIP) (*F) )?
(?: [._ –-]{0,3}+ \d ){2}
(?: 0{2} [\d._ –-]* (*SKIP) (*F) )?
(?: [._ –-]{0,3}+ \d ){2}
(?=
(?: 0{4} [\d._ –-]* (*SKIP) (*F) )?
(?: [._ –-]{0,3}+ \d ){4}
)
|
6
(?: 6{2} [\d._ –-]* (*SKIP) (*F) )?
(?: [._ –-]{0,3}+ \d ){2}
(?: 0{2} [\d._ –-]* (*SKIP) (*F) )?
(?: [._ –-]{0,3}+ \d ){2}
(?=
(?: 0{4} [\d._ –-]* (*SKIP) (*F) )?
(?: [._ –-]{0,3}+ \d ){4}
)
|
9 [\d._ –-]* (*SKIP) (*F)
"""
test_str = ("//won't match if it is preceded with 'X' or 'x'\n"
"x123456789\n"
"X123456789\n"
"x123-456-789\n"
"X123-456-789\n"
"123-456-789\n"
"ordernumber 123-456-789\n"
"order number123-456789\n"
"order number----123-456789\n"
"order number 123456789\n"
"ordernumber-x123456787\n"
"ordernumber-123456787\n"
"ORDERNUMBER-123456789\n"
"ordernumber - 123456789\n"
"ordernumber #123456789\n"
"ordernumber *%&%*123456789\n"
"ordernumber !@#$%^&123456789\n"
"order.number 123456789\n"
"order_number 123456789\n"
"order._.number 123456789\n"
"order...number#123456789\n"
"order-.-.-.-.123456789\n"
"order 123456789\n"
"order..123456789\n"
"order#123456789\n"
"order_#123456789\n"
"order._.#123456789\n"
"order___123456789\n"
"order#number 123456789\n"
"order......number 123456789\n"
"order.number.123456789\n"
"social security number 123-456-789\n"
"ordernumber !@#$%^&x123456789\n"
"123456789\n"
"#@%#$%#$123456789#$%#$^$#\n"
"123-456789\n"
"123456789\n"
"123456789\n"
"123 45 6789\n"
"123-45-6789\n"
"123-45-6789\n"
"123 – 45 – 6789\n"
"123.45.6789\n"
"123_45_6789\n"
"123 456 789\n"
"123-456-789\n"
"123 – 456 – 789\n"
"123.456.789\n"
"123_456_789\n"
"1234 56 789\n"
"1234-56-789\n"
"1234 – 56 – 789\n"
"1234.56.789\n"
"1234_56_789\n"
"12 345 6789\n"
"12-345-6789\n"
"12 – 345 – 6789\n"
"12.345.6789\n"
"12_345_6789\n\n"
"The number should not be matched at all for the following rules.\n\n"
"If the number beginning with the number “9”\n"
"912345678\n"
"912000000\n\n"
"If the number “666” in positions 1 – 3.\n"
"666000000\n"
"666450000\n"
"666129876\n\n"
"If the number “000” in positions 1 – 3.\n"
"000000000\n"
"000450000\n"
"000120000\n\n"
"If the number “00” in positions 4 – 5.\n"
"123006789\n"
"876001234\n"
"765003456\n\n"
"if the number “0000” in positions 6 – 9\n"
"123450000\n"
"123000000\n"
"876000000\n\n"
"x123456789\n"
"X123456789\n"
"x123-456-789\n"
"X123-456-789\n")
matches = re.finditer(regex, test_str, 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