.\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.16)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.ie \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.el \{\
.    de IX
..
.\}
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "Regexp::Optimizer 3pm"
.TH Regexp::Optimizer 3pm "2004-12-05" "perl v5.14.2" "User Contributed Perl Documentation"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "NAME"
Regexp::Optimizer \- optimizes regular expressions
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 4
\&  use Regexp::Optimizer;
\&  my $o  = Regexp::Optimizer\->new;
\&  my $re = $o\->optimize(qr/foobar|fooxar|foozap/);
\&  # $re is now qr/foo(?:[bx]ar|zap)/
.Ve
.SH "ABSTRACT"
.IX Header "ABSTRACT"
This module does, ahem, attempts to, optimize regular expressions.
.SH "INSTALLATION"
.IX Header "INSTALLATION"
To install this module type the following:
.PP
.Vb 4
\&   perl Makefile.PL
\&   make
\&   make test
\&   make install
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Here is a quote from perltodo.
.Sp
.RS 4
Factoring out common suffices/prefices in regexps (trie optimization)
.Sp
Currently, the user has to optimize \*(L"foo|far\*(R" and \*(L"foo|goo\*(R" into
\&\*(L"f(?:oo|ar)\*(R" and \*(L"[fg]oo\*(R" by hand; this could be done automatically.
.RE
.PP
This module implements just that.
.SS "\s-1EXPORT\s0"
.IX Subsection "EXPORT"
Since this is an \s-1OO\s0 module there is no symbol exported.
.SH "METHODS"
.IX Header "METHODS"
This module is implemented as a subclass of Regexp::List.  For
methods not listed here, see Regexp::List.
.ie n .IP "$o  = Regexp::Optimizer\->new;" 4
.el .IP "\f(CW$o\fR  = Regexp::Optimizer\->new;" 4
.IX Item "$o  = Regexp::Optimizer->new;"
.PD 0
.ie n .IP "$o\->set(\fIkey => value, ...\fR)" 4
.el .IP "\f(CW$o\fR\->set(\fIkey => value, ...\fR)" 4
.IX Item "$o->set(key => value, ...)"
.PD
Just the same us Regexp::List except for the attribute below;
.RS 4
.IP "unexpand" 4
.IX Item "unexpand"
When set to one, \f(CW$o\fR\->\fIoptimize()\fR tries to \f(CW$o\fR\->expand before actually
starting the operation.
.Sp
.Vb 6
\&  # cases you need to set expand => 1
\&  $o\->set(expand => 1)\->optimize(qr/
\&                                   foobar|
\&                                   fooxar|
\&                                   foozar
\&                                   /x);
.Ve
.RE
.RS 4
.RE
.ie n .IP "$re = $o\->optimize(\fIregexp\fR);" 4
.el .IP "\f(CW$re\fR = \f(CW$o\fR\->optimize(\fIregexp\fR);" 4
.IX Item "$re = $o->optimize(regexp);"
Does the job.  Note that unlike \f(CW\*(C`\->list2re()\*(C'\fR in Regexp::List,
the argument is the regular expression itself.  What it basically does
is to find groups will alterations and replace it with the result of
\&\f(CW\*(C`$o\->list2re\*(C'\fR.
.ie n .IP "$re = $o\->list2re(\fIlist of words ...\fR)" 4
.el .IP "\f(CW$re\fR = \f(CW$o\fR\->list2re(\fIlist of words ...\fR)" 4
.IX Item "$re = $o->list2re(list of words ...)"
Same as \f(CW\*(C`list2re()\*(C'\fR in Regexp::List in terms of functionality but
how it tokenize \*(L"atoms\*(R" is different since the arguments can be
regular expressions, not just strings.  Here is a brief example.
.Sp
.Vb 3
\&  my @expr = qw/foobar fooba+/;
\&  Regexp::List\->new\->list2re(@expr) eq qr/fooba[\e+r]/;
\&  Regexp::Optimizer\->new\->list2re(@expr) eq qr/foob(?:a+ar)/;
.Ve
.SH "CAVEATS"
.IX Header "CAVEATS"
This module is still experimental.  Do not assume that the result is
the same as the unoptimized version.
.IP "\(bu" 4
When you just want a regular expression which matches normal words
with not metacharacters, use <Regexp::List>.  It's more robus and 
much faster.
.IP "\(bu" 4
When you have a list of regular expessions which you want to
aggregate, use \f(CW\*(C`list2re\*(C'\fR of \s-1THIS\s0 \s-1MODULE\s0.
.IP "\(bu" 4
Use \f(CW\*(C`\->optimize()\*(C'\fR when and only when you already have a big
regular expression with alterations therein.
.Sp
\&\f(CW\*(C`\->optimize()\*(C'\fR does support nested groups but its parser is not
tested very well.
.SH "BUGS"
.IX Header "BUGS"
.IP "\(bu" 4
Regex parser in this module (which itself is implemented by regular
expression) is not as thoroughly tested as Regexp::List
.IP "\(bu" 4
May still fall into deep recursion when you attempt to optimize
deeply nested regexp.  See \*(L"\s-1PRACTICALITY\s0\*(R".
.IP "\(bu" 4
Does not grok (?{expression}) and (?(cond)yes|no) constructs yet
.IP "\(bu" 4
You need to escape characters in character classes.
.Sp
.Vb 3
\&  $o\->optimize(qr/[a\-z()]|[A\-Z]/);              # wrong
\&  $o\->optimize(qr/[a\-z\e(\e)]|[A\-Z]/);            # right
\&  $o\->optimize(qr/[0\-9A\-Za\-z]|[\eQ\-_.!~*"\*(Aq()\eE]/ # right, too.
.Ve
.IP "\(bu" 4
When character(?: class(?:es)?)? are aggregated, duplicate ranges are
left as is.  Though functionally \s-1OK\s0, it is cosmetically ugly.
.Sp
.Vb 2
\&  $o\->optimize(qr/[0\-5]|[5\-9]|0123456789/);
\&  # simply turns into [0\-5][5\-9]0123456789] not [0\-9]
.Ve
.Sp
I left it that way because marking-rearranging approach can result a
humongous result when unicode characters are concerned (and
\&\ep{Properties}).
.SH "PRACTICALITY"
.IX Header "PRACTICALITY"
Though this module is still experimental, It is still good enough even
for such deeply nested regexes as the followng.
.PP
.Vb 3
\&  # See 3.2.2 of  http://www.ietf.org/rfc/rfc2616.txt
\&  # BNF faithfully turned into a regex
\&  http://(?:(?:(?:(?:(?:[a\-z]|[A\-Z])|[0\-9])|(?:(?:[a\-z]|[A\-Z])|[0\-9])(?:(?:(?:[a\-z]|[A\-Z])|[0\-9])|\-)*(?:(?:[a\-z]|[A\-Z])|[0\-9]))\e.)*(?:(?:[a\-z]|[A\-Z])|(?:[a\-z]|[A\-Z])(?:(?:(?:[a\-z]|[A\-Z])|[0\-9])|\-)*(?:(?:[a\-z]|[A\-Z])|[0\-9]))\e.?|[0\-9]+\e.[0\-9]+\e.[0\-9]+\e.[0\-9]+)(?::[0\-9]*)?(?:/(?:(?:(?:(?:[a\-z]|[A\-Z])|[0\-9])|[\e\-\e_\e.\e!\e~\e*\e\*(Aq\e(\e)])|%(?:[0\-9]|[A\-Fa\-f])(?:[0\-9]|[A\-Fa\-f])|[:@&=+$,])*(?:;(?:(?:(?:(?:[a\-z]|[A\-Z])|[0\-9])|[\e\-\e_\e.\e!\e~\e*\e\*(Aq\e(\e)])|%(?:[0\-9]|[A\-Fa\-f])(?:[0\-9]|[A\-Fa\-f])|[:@&=+$,])*)*(?:/(?:(?:(?:(?:[a\-z]|[A\-Z])|[0\-9])|[\e\-\e_\e.\e!\e~\e*\e\*(Aq\e(\e)])|%(?:[0\-9]|[A\-Fa\-f])(?:[0\-9]|[A\-Fa\-f])|[:@&=+$,])*(?:;(?:(?:(?:(?:[a\-z]|[A\-Z])|[0\-9])|[\e\-\e_\e.\e!\e~\e*\e\*(Aq\e(\e)])|%(?:[0\-9]|[A\-Fa\-f])(?:[0\-9]|[A\-Fa\-f])|[:@&=+$,])*)*)*(?:\e\e?(?:[;/?:@&=+$,]|(?:(?:(?:[a\-z]|[A\-Z])|[0\-9])|[\e\-\e_\e.\e!\e~\e*\e\*(Aq\e(\e)])|%(?:[0\-9]|[A\-Fa\-f])(?:[0\-9]|[A\-Fa\-f]))*)?)?
\&
\&  # and optimized
\&  http://(?::?[a\-zA\-Z0\-9](?:[a\-zA\-Z0\-9\e\-]*[a\-zA\-Z0\-9])?\e.[a\-zA\-Z]*(?:[a\-zA\-Z0\-9\e\-]*[a\-zA\-Z0\-9])?\e.?|[0\-9]+\e.[0\-9]+\e.[0\-9]+\e.[0\-9]+)(?::[0\-9]*)?(?:/(?:(?:(?:[a\-zA\-Z0\-9\e\-\e_\e.\e!\e~\e*\e\*(Aq\ex28\ex29]|%[0\-9A\-Fa\-f][0\-9A\-Fa\-f])|[:@&=+$,]))*(?:;(?:(?:(?:[a\-zA\-Z0\-9\e\-\e_\e.\e!\e~\e*\e\*(Aq\ex28\ex29]|%[0\-9A\-Fa\-f][0\-9A\-Fa\-f])|[:@&=+$,]))*)*(?:/(?:(?:(?:[a\-zA\-Z0\-9\e\-\e_\e.\e!\e~\e*\e\*(Aq\ex28\ex29]|%[0\-9A\-Fa\-f][0\-9A\-Fa\-f])|[:@&=+$,]))*(?:;(?:(?:(?:[a\-zA\-Z0\-9\e\-\e_\e.\e!\e~\e*\e\*(Aq\ex28\ex29]|%[0\-9A\-Fa\-f][0\-9A\-Fa\-f])|[:@&=+$,]))*)*)*(?:\e\e?(?:(?:[;/?:@&=+$,a\-zA\-Z0\-9\e\-\e_\e.\e!\e~\e*\e\*(Aq\ex28\ex29]|%[0\-9A\-Fa\-f][0\-9A\-Fa\-f]))*)?)?
.Ve
.PP
By carefully examine both you can find that character classes are
properly aggregated.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
Regexp::List \*(-- upon which this module is based
.PP
\&\f(CW\*(C`eg/\*(C'\fR directory in this package contains example scripts.
.IP "Perl standard documents" 4
.IX Item "Perl standard documents"
.Vb 1
\& L<perltodo>, L<perlre>
.Ve
.IP "\s-1CPAN\s0 Modules" 4
.IX Item "CPAN Modules"
Regexp::Presuf, Text::Trie
.IP "Books" 4
.IX Item "Books"
Mastering Regular Expressions  <http://www.oreilly.com/catalog/regex2/>
.SH "AUTHOR"
.IX Header "AUTHOR"
Dan Kogai <dankogai@dan.co.jp>
.SH "COPYRIGHT AND LICENSE"
.IX Header "COPYRIGHT AND LICENSE"
Copyright 2003 by Dan Kogai
.PP
This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.