Python Regex Usage

Python Regex Usage

Perl Regex Usages

Multiline Matchings:

Inside a perl script:

#! /usr/bin/perl
$str = "This is a test
Will it work
lets see
";
if ($str =~ m!^This.+test$!)
{
     print "matched\n"
}

Following are the contents of file "data"

# cat data
This is a test file
Will it work
lets see

# As perl one liners:

$ cat data | perl -w -e '$/=""; while(<>) { m!^This.+file$!m and print }'
This is a test file
Will it work
lets see


# DEFAULT BEHAVIOUR
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+file)! and print "$1\n" or print "NOMATCH\n" }'
This is a test file
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+file$)! and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+see$)! and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+see)! and print "$1\n" or print "NOMATCH\n" }'
NOMATCH

# s modifier behaviour:
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+file)!s and print "$1\n" or print "NOMATCH\n" }'
This is a test file
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+file$)!s and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work)!s and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work$)!s and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+see)!s and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
lets see
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+see$)!s and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
lets see
$ 


# m modifier behaviour:
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+see$)!m and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+file)!m and print "$1\n" or print "NOMATCH\n" }'
This is a test file
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+file$)!m and print "$1\n" or print "NOMATCH\n" }'
This is a test file
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work$)!m and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^Will.+work$)!m and print "$1\n" or print "NOMATCH\n" }'
Will it work
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+see$)!m and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+see)!m and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^let.+see$)!m and print "$1\n" or print "NOMATCH\n" }'
lets see

# sm modifier behaviour:
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+file$)!sm and print "$1\n" or print "NOMATCH\n" }'
This is a test file
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work$)!sm and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+see$)!sm and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
lets see
$ cat data | perl -w -e '$/=""; while(<>) { m!(^Will.+work$)!sm and print "$1\n" or print "NOMATCH\n" }'
Will it work
$ cat data | perl -w -e '$/=""; while(<>) { m!(^Will.+see$)!sm and print "$1\n" or print "NOMATCH\n" }'
Will it work
lets see
$ cat data | perl -w -e '$/=""; while(<>) { m!(^lets.+see$)!sm and print "$1\n" or print "NOMATCH\n" }'
lets see
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work)!sm and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
$ 

$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work).+^let.+see$!s and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work).+^let.+see$!sm and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work$).+^let.+see$!sm and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+it).+^let.+see$!sm and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it


# BACKREFRENCES:
$ echo "vis a vis" | perl -w -e '$/=""; while(<>) { m!(vis).+\1! and print "MATCHED\n"}'
MATCHED
$ echo "vis a vis" | perl -w -e '$/=""; while(<>) { m!(vis).+\g{-1}! and print "MATCHED\n"}'
MATCHED

$ echo "vis a vis" | perl -w -e '$/=""; while(<>) { m!(?vis).+\g{testmatch}! and print "MATCHED\n"}'
MATCHED

# CAPTURING and NON CAPTURING GROUPING:
$ echo "vis a vis" | perl -w -e '$/=""; while(<>) { m!(?vis).+\g{testmatch}! and print "$1\n"}'
vis  

$ echo "vis a vis" | perl -w -e '$/=""; while(<>) { m!(?:vis).+\g{testmatch}! and print "$1\n"}'
Reference to nonexistent named group in regex; marked by <-- here="" in="" m="" testmatch="">vis).+\g{testmatch <-- -e="" -w="" 1.="" a="" at="" echo="" here="" line="" perl="" vis="" while="">) { m!(?:vis).+! and print "$1\n"}'
Use of uninitialized value $1 in concatenation (.) or string at -e line 1, <> chunk 1.

$ echo "vis a vis" | perl -w -e '$/=""; while(<>) { m!(vis).+! and print "$1\n"}'
vis
$

$ echo "datchet etet it underway" | perl -w -e '$/=""; while(<>) { m!(et){2}\s+! and print "MATCHED\n"}'
MATCHED
 
# NAMED CAPTURING:
$ cat data | perl -w -e '$/=""; while(<>) { m!(?test file)! and print "$+{fm}\n" or print "NOMATCH\n" }'
test file
$ echo "vis a vis" | perl -w -e '$/=""; while(<>) { m!(?vis).+\g{testmatch}! and print "MATCHED\n"}'
MATCHED
$ cat data | perl -w -e '$/=""; while(<>) { m!(?:test file)! and print "$1" or print "NOMATCH\n" }'
Use of uninitialized value $1 in string at -e line 1, <> chunk 1.
$ cat data | perl -w -e '$/=""; while(<>) { m!(?:test file)! and print "MATCHED\n" or print "NOMATCH\n" }'
MATCHED 


# inside modifiers:
$ echo "This is a TEST" | perl -w -e '$/=""; while(<>) { m!a\s+test! and print "MATCHED\n" or print "UNMATCHED\n"}'
UNMATCHED
$ echo "This is a TEST" | perl -w -e '$/=""; while(<>) { m!a\s+TEST! and print "MATCHED\n" or print "UNMATCHED\n"}'
MATCHED
$ echo "This is a TEST" | perl -w -e '$/=""; while(<>) { m!a\s+(?i)test! and print "MATCHED\n" or print "UNMATCHED\n"}'
MATCHED
$ 

$ echo "This is a TEST" | perl -w -e '$/=""; while(<>) { m!a\s+(?i)test! and print "$1\n"}'
Use of uninitialized value $1 in concatenation (.) or string at -e line 1, <> chunk 1.

$ echo "This is a TEST" | perl -w -e '$/=""; while(<>) { m!a\s+((?i)test)! and print "$1\n"}'
TEST
$ echo "This is a TEST" | perl -w -e '$/=""; while(<>) { m!a\s+(?i:test)! and print "$1\n"}'
Use of uninitialized value $1 in concatenation (.) or string at -e line 1, <> chunk 1.

$ echo "This is a TEST" | perl -w -e '$/=""; while(<>) { m!a\s+(?i:test)! and print "MATCHED\n" or print "UNMATCHED\n"}'
MATCHED

# inside modifiers (multiline modifier trick):
$ cat data | perl -w -e '$/=""; while(<>) { m!(^This.+work)! and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(?s)(^This.+work)! and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work
$ cat data | perl -w -e '$/=""; while(<>) { m!((?s)^This.+work)! and print "$1\n" or print "NOMATCH\n" }'
This is a test file
Will it work

# inside modifiers non-capturing match:
$ cat data | perl -w -e '$/=""; while(<>) { m!(?s:^This.+work)! and print "$1\n" or print "NOMATCH\n" }'
Use of uninitialized value $1 in concatenation (.) or string at -e line 1, <> chunk 1.

$ cat data | perl -w -e '$/=""; while(<>) { m!(?s:^This.+work)! and print "MATCHED\n" or print "NOMATCH\n" }'
MATCHED


# LOOK AHEAD ASSERTIONS:
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(.+lets)(.+it.+$)!sm and print "$1 $3\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?=.+lets)(.+it.+$)!sm and print "$1 $2\n" or print "NOMATCH\n" }'
test file
Will it work
lets see
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?=.+lets)(.+it)!sm and print "$1 $2\n" or print "NOMATCH\n" }'
test file
Will it
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?=lets)(.+it.+$)!sm and print "$1 $2\n" or print "NOMATCH\n" }'
NOMATCH


# LOOK BEHIND  ASSERTIONS:
$ cat data | perl -w -e '$/=""; while(<>) { m!(?<=This is a )(it)!sm and print "$1\n" or print "NOMATCH\n" }'
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(?<=This is a )(.+it)!sm and print "$1\n" or print "NOMATCH\n" }'
test file
Will it

# CONDITIONAL MATCHING:
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?(1)(.+it.+$))!sm and print "MATCH\n" or print "NOMATCH\n" }'
MATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(asa)(?(1)(.+it.+$))!sm and print "MATCH\n" or print "NOMATCH\n" }'
NOMATCH

$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?(?=lets)(.+it.+$))!sm and print "MATCH\n" or print "NOMATCH\n" }'
MATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?=lets)(.+it.+$)!sm and print "$1 $2\n" or print "NOMATCH\n" }'        # This is not a conditional matching
NOMATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?(?=lets)(.+it.+$))!sm and print "$1 $2\n" or print "NOMATCH\n" }'
Use of uninitialized value $2 in concatenation (.) or string at -e line 1, <> chunk 1.
test file 

$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?(?=lets)(junk)|(.+it.+$))!sm and print "MATCH\n" or print "NOMATCH\n" }'
MATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?(?=lets)(junk)|(anotherjunk))!sm and print "MATCH\n" or print "NOMATCH\n" }'
NOMATCH
 
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?(?=junk)junk)!sm and print "MATCH\n" or print "NOMATCH\n" }'  # if condition is false then it simply skips
MATCH
$ cat data | perl -w -e '$/=""; while(<>) { m!(test file)(?(?=lets)(junk))!sm and print "MATCH\n" or print "NOMATCH\n" }'  # why is this working ?  no idea
MATCH

(?(?=condition)(then1|then2|then3)|(else1|else2|else3))

# Some Special cases to study:
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!(ab)*! ; print "@arr\n";}'
ab
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!((ab)*)! ; print "@arr\n";}'
ab ab
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!((a|b)*)! ; print "@arr\n";}'
aba a
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!((?:a|b)*)! ; print "@arr\n";}'
aba
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!((?:a|b)*)!g ; print "@arr\n";}'
aba  a  
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!(?:a|b)*!g ; print "@arr\n";}'
aba  a  
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m![ab]*!g ; print "@arr\n";}'
aba  a 
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!([ab]*)!g ; print "@arr\n";}'
aba  a  
$  echo "abacaddb" | perl -w -e 'while(<>) { @arr = $_ =~ m!((?:a|b)*)!g ; print "@arr\n";}'
aba  a   b  
$  echo "abacaddb" | perl -w -e 'while(<>) {  $_ =~ m!([ab]+)! ; print "$1\n";}'
aba
$  echo "abacaddb" | perl -w -e 'while(<>) {  $_ =~ m!([abc]+)! ; print "$1\n";}'
abaca
$  echo "abacaddb" | perl -w -e 'while(<>) {  $_ =~ m!((a|b|c)+)! ; print "$1\n";}'
abaca
$  echo "abacaddb" | perl -w -e 'while(<>) {  $_ =~ m!((?:a|b|c)+)! ; print "$1\n";}'
abaca


#======================================================

$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!(a|b)+! ; print "@arr\n";}'
a
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!((a|b)+)! ; print "@arr\n";}'
aba a
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m![ab]+! ; print "@arr\n";}'
1
$ echo "abaca" | perl -w -e 'while(<>) { @arr = $_ =~ m!([ab]+)! ; print "@arr\n";}'
aba