# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?'DateTime'(?'Month'[A-Za-z]+)\s+(?'Day'0?[1-9]|[12][0-9]|3[01])\s+(?'Time'[0-9]{2}:[0-9]{2}:[0-9]{2}(\.[0-9]{1,3})?))\W(?'Full_Host'[alnum]|(?:(?'Host_prefix'(?:[A-Za-z])-?)(?'Host'[A-Za-z]+)-*(?'Host_suffix'-{1}[A-Za-z]+)))\W(?'Msg_Sender'(?:\s?\S+:\s)+)?(?'Log_Msg'[[:blank:][:alnum:][:punct:]]+)"
test_str = ("May 18 11:02:26 example-host-name kernel: Linux version 6.9.0-gentoo-x86_64 (root@example-host-builder) (x86_64-pc-linux-gnu-gcc (Gentoo Hardened 13.2.1_p20240210 p14) 13.2.1 20240210, GNU ld (Gentoo 2.42 p3) 2.42.0) #1 SMP PREEMPT_DYNAMIC Fri May 17 01:42:56 PDT 2024\n"
"May 18 11:02:26 example-host-name kernel: Kernel is locked down from Kernel configuration; see man kernel_lockdown.7\n"
"May 18 11:02:26 example-host-name kernel: Command line: BOOT_IMAGE=(lvm/vg0-gentoo--root--two)/boot/vmlinuz-6.9.0-gentoo-x86_64.signed root=/dev/dm-4\n"
"May 18 11:02:26 example-host-name kernel: x86/split lock detection: #AC: crashing the kernel on kernel split_locks and warning on user-space split_locks\n"
"May 18 11:02:26 example-host-name kernel: BIOS-provided physical RAM map:\n"
"May 18 11:02:26 example-host-name kernel: BIOS-e820: [mem 0x0000000000000000-0x000000000009dfff] usable\n"
"May 18 11:02:26 example-host-name kernel: BIOS-e820: [mem 0x000000000009e000-0x000000000009efff] reserved\n"
"May 18 11:02:26 example-host-name kernel: BIOS-e820: [mem 0x000000000009f000-0x000000000009ffff] usable\n"
"May 18 11:02:26 example-host-name kernel: BIOS-e820: [mem 0x00000000000a0000-0x00000000000fffff] reserved\n"
"May 18 11:02:26 example-host-name kernel: BIOS-e820: [mem 0x0000000000100000-0x000000003aae7fff] usable\n"
"May 18 11:02:26 example-host-name kernel: BIOS-e820: [mem 0x000000003aae8000-0x000000004395efff] reserved\n")
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