# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(34[0-9]{2}[ -])([0-9]{6}[ -])[0-9]{5}\b|\b34[0-9]{13}\b|\b(37[0-9]{2}[ -])([0-9]{6}[ -])[0-9]{5}\b|\b37[0-9]{13}\b"
test_str = ("American Express\n\n"
"Requirements: American Express cards start with the number 34 or 37 and have 15 digits. Pattern is 4-6-5 when having spaces or dashes.\n\n"
"Pattern Parts:\n"
"Starts with number 34 and 15 length:\n"
"1) \\b(34[0-9]{2}[ -])([0-9]{6}[ -])[0-9]{5}\\b|\\b34[0-9]{13}\\b \n\n"
"Starts with number 37 and 15 length:\n"
"2) \\b(37[0-9]{2}[ -])([0-9]{6}[ -])[0-9]{5}\\b|\\b37[0-9]{13}\\b\n\n"
"Combining 1-2 to form one pattern:\n"
"\\b(34[0-9]{2}[ -])([0-9]{6}[ -])[0-9]{5}\\b|\\b34[0-9]{13}\\b|\\b(37[0-9]{2}[ -])([0-9]{6}[ -])[0-9]{5}\\b|\\b37[0-9]{13}\\b\n\n\n"
"Test Cases:\n"
"Positive (Should fire):\n"
"15 length, no space, start with 34 Here is the cc: 342312341234123 Thanks.\n"
"15 length, dashes, start with 34 3423-123456-12345 \n"
"15 length, spaces, start with 34 3423 123456 12345 \n\n"
"15 length, no space, start with 37 372112341234123\n"
"15 length, dashes, start with 37 3721-123456-12345\n"
"15 length, spaces, start with 37 3721 123456 12345\n\n"
"Embedded in sentence with space:\n"
"15 length, no space, start with 34 Here is the cc: 342312341234112\n"
"15 length, dashes, start with 34 Here is the cc: 3423-123456-12345\n"
"15 length, spaces, start with 34 Here is the cc: 3423 123456 12345\n\n"
"15 length, no space, start with 37 Here is the cc: 372112341234123\n"
"15 length, dashes, start with 37 Here is the cc: 3721-123456-12345\n"
"15 length, spaces, start with 37 Here is the cc: 3721 123456 12345\n\n"
"15 length, no space, start with 34 Credit Card#:342312341234112\n"
"15 length, dashes, start with 34 Credit Card#:3423-123456-12345\n"
"15 length, spaces, start with 34 Credit Card#:3423 123456 12345\n\n"
"15 length, no space, start with 37 Credit Card#:372112341234123\n"
"15 length, dashes, start with 37 Credit Card#:3721-123456-12345\n"
"15 length, spaces, start with 37 Credit Card#:3721 123456 12345\n\n"
"Negative (Should Not Fire):\n"
"15 length, no space, not start with 34 352312341234112\n"
"15 length, dashes, not start with 34 3523-123456-12345\n"
"15 length, spaces, not start with 34 3523 123456 12345\n\n"
"15 length, no space, not start with 37 362112341234123\n"
"15 length, dashes, not start with 37 3621-123456-12345\n"
"15 length, spaces, not start with 37 3621 123456 12345\n\n"
"15 length, no space, start with 34, embedded Credit Card Number342312341234112\n"
"15 length, dashes, start with 34, malformed 3423-1234-1234-112\n\n"
"15 length num matching pattern but embedded User ID: 000000342312341234112000000")
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