- Roman numbers
m/^m*(d?c{0,3}|c[dm])(l?x{0,3}|x[lc])(v?i{0,3}|i[vx])$/i
- Swap first two words
s/(\S+)(\s+)(\S+)/$3$2$1/
- Keyword = Value
m/(\w+)\s*=\s*(.*)\s*$/ # keyword is $1, value is $2
- Line of at least 80 characters
m/.{80,}/
- MM/DD/YY HH:MM:SS
m|(\d+)/(\d+)/(\d+) (\d+):(\d+):(\d+)|
- Changing directories
s(/usr/bin)(/usr/local/bin)g
- Expanding %7E (hex) escapes
s/%([0-9A-Fa-f][0-9A-Fa-f])/chr hex $1/ge
- Deleting C comments (imperfectly)
s{
/\* # Match the opening delimiter
.*? # Match a minimal number of characters
\*/ # Match the closing delimiter
} []gsx;
- Removing leading and trailing whitespace
s/^\s+//;
s/\s+$//;
- Turning \ followed by n into a real newline
s/\\n/\n/g;
- Removing package portion of fully qualified symbols
s/^.*:://
- IP address
m/^([01]?\d\d|2[0-4]\d|25[0-5])\.([01]?\d\d|2[0-4]\d|25[0-5])\.
([01]?\d\d|2[0-4]\d|25[0-5])\.([01]?\d\d|2[0-4]\d|25[0-5])$/;
- Removing leading path from filename
s(^.*/)()
- Extracting columns setting from TERMCAP
$cols = ( ($ENV{TERMCAP} || " ") =~ m/:co#(\d+):/ ) ? $1 : 80;
- Removing directory components from program name and arguments
($name = " $0 @ARGV") =~ s, /\S+/, ,g;
- Checking your operating system
die "This isn't Linux" unless $^O =~ m/linux/i;
- Joining continuation lines in multiline string
s/\n\s+/ /g
- Extracting all numbers from a string
@nums = m/(\d+\.?\d*|\.\d+)/g;
- Finding all-caps words
@capwords = m/(\b[^\Wa-z0-9_]+\b)/g;
- Finding all-lowercase words
@lowords = m/(\b[^\WA-Z0-9_]+\b)/g;
- Finding initial-caps word
@icwords = m/(\b[^\Wa-z0-9_][^\WA-Z0-9_]*\b)/;
- Finding links in simple HTML
@links = m/<A[^>]+?HREF\s*=\s*["']?([^'" >]+?)[ '"]?>/sig;
- Finding middle initial in $_
($initial) = m/^\S+\s+(\S)\S*\s+\S/ ? $1 : "";
- Changing inch marks to quotes
s/"([^"]*)"/``$1''/g
- Extracting sentences (two spaces required)
{ local $/ = "";
while (<>) {
s/\n/ /g;
s/ {3,}/ /g;
push @sentences, m/(\S.*?[!?.])(?= |\Z)/g;
}
}
- YYYY-MM-DD
m/(\d{4})-(\d\d)-(\d\d)/ # YYYY in $1, MM in $2, DD in $3
- North American telephone numbers
m/ ^
(?:
1 \s (?: \d\d\d \s)? # 1, or 1 and area code
| # ... or ...
\(\d\d\d\) \s # area code with parens
| # ... or ...
(?: \+\d\d?\d? \s)? # optional +country code
\d\d\d ([\s\-]) # and area code
)
\d\d\d (\s|\1) # prefix (and area code separator)
\d\d\d\d # exchange
$
/x
- Exclamations
m/\boh\s+my\s+gh?o(d(dess(es)?|s?)|odness|sh)\b/i
- Extracting lines regardless of line terminator
push(@lines, $1)
while ($input =~ s/^([^\012\015]*)(\012\015?|\015\012?)//);