Current File : /home/opti/optisoftcom-new/perl5/man/man3/Unicode::Stringprep.3pm
.\" Automatically generated by Pod::Man 2.27 (Pod::Simple 3.28)
.\"
.\" 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" ''
. ds C`
. ds C'
'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.
.\"
.\" Avoid warning from groff about undefined register 'F'.
.de IX
..
.nr rF 0
.if \n(.g .if rF .nr rF 1
.if (\n(rF:(\n(.g==0)) \{
. if \nF \{
. de IX
. tm Index:\\$1\t\\n%\t"\\$2"
..
. if !\nF==2 \{
. nr % 0
. nr F 2
. \}
. \}
.\}
.rr rF
.\"
.\" 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 "Unicode::Stringprep 3"
.TH Unicode::Stringprep 3 "2018-12-11" "perl v5.16.3" "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"
Unicode::Stringprep \- Preparation of Internationalized Strings (RFC\ 3454)
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 3
\& use Unicode::Stringprep;
\& use Unicode::Stringprep::Mapping;
\& use Unicode::Stringprep::Prohibited;
\&
\& my $prepper = Unicode::Stringprep\->new(
\& 3.2,
\& [ { 32 => \*(Aq<SPACE>\*(Aq}, ],
\& \*(AqKC\*(Aq,
\& [ @Unicode::Stringprep::Prohibited::C12, @Unicode::Stringprep::Prohibited::C22,
\& @Unicode::Stringprep::Prohibited::C3, @Unicode::Stringprep::Prohibited::C4,
\& @Unicode::Stringprep::Prohibited::C5, @Unicode::Stringprep::Prohibited::C6,
\& @Unicode::Stringprep::Prohibited::C7, @Unicode::Stringprep::Prohibited::C8,
\& @Unicode::Stringprep::Prohibited::C9 ],
\& 1, 0 );
\& $output = $prepper\->($input)
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
This module implements the \fIstringprep\fR framework for preparing
Unicode text strings in order to increase the likelihood that
string input and string comparison work in ways that make sense
for typical users throughout the world. The \fIstringprep\fR
protocol is useful for protocol identifier values, company and
personal names, internationalized domain names, and other text
strings.
.PP
The \fIstringprep\fR framework does not specify how protocols should
prepare text strings. Protocols must create profiles of
stringprep in order to fully specify the processing options.
.SH "FUNCTIONS"
.IX Header "FUNCTIONS"
This module provides a single function, \f(CW\*(C`new\*(C'\fR, that creates a
perl function implementing a \fIstringprep\fR profile.
.PP
This module exports nothing.
.ie n .IP "\fBnew($unicode_version, \fB$mapping_tables\fB, \f(BI$unicode_normalization\fB, \f(CB$prohibited_tables\fB, \f(CB$bidi_check\fB, \f(CB$unassigned_check\fB)\fR" 4
.el .IP "\fBnew($unicode_version, \f(CB$mapping_tables\fB, \f(CB$unicode_normalization\fB, \f(CB$prohibited_tables\fB, \f(CB$bidi_check\fB, \f(CB$unassigned_check\fB)\fR" 4
.IX Item "new($unicode_version, $mapping_tables, $unicode_normalization, $prohibited_tables, $bidi_check, $unassigned_check)"
Creates a \f(CW\*(C`bless\*(C'\fRed function reference that implements a stringprep profile.
.Sp
This function takes the following parameters:
.RS 4
.ie n .IP "$unicode_version" 4
.el .IP "\f(CW$unicode_version\fR" 4
.IX Item "$unicode_version"
The Unicode version specified by the stringprep profile.
.Sp
Currently, this parameter must be \f(CW3.2\fR (numeric).
.ie n .IP "$mapping_tables" 4
.el .IP "\f(CW$mapping_tables\fR" 4
.IX Item "$mapping_tables"
The mapping tables used for stringprep.
.Sp
The parameter may be a reference to a hash or an array, or \f(CW\*(C`undef\*(C'\fR. A hash
must map Unicode codepoints (as integers, e.\ g. \f(CW0x0020\fR for U+0020) to
replacement strings (as perl strings). An array may contain pairs of Unicode
codepoints and replacement strings as well as references to nested hashes and
arrays.
.Sp
Unicode::Stringprep::Mapping provides the tables from \s-1RFC\s0\ 3454,
Appendix\ B.
.Sp
For further information on the mapping step, see \s-1RFC\s0\ 3454, section\ 3.
.ie n .IP "$unicode_normalization" 4
.el .IP "\f(CW$unicode_normalization\fR" 4
.IX Item "$unicode_normalization"
The Unicode normalization to be used.
.Sp
Currently, \f(CW\*(C`undef\*(C'\fR/\f(CW\*(Aq\*(Aq\fR (no normalization) and \f(CW\*(AqKC\*(Aq\fR (compatibility
composed) are specified for \fIstringprep\fR.
.Sp
For further information on the normalization step, see \s-1RFC\s0\ 3454,
section\ 4.
.Sp
Normalization form \s-1KC\s0 will also enable checks for some problem sequences for
which the normalization can't be implemented in an interoperable way.
.Sp
For more information, see \*(L"\s-1CAVEATS\*(R"\s0 below.
.ie n .IP "$prohibited_tables" 4
.el .IP "\f(CW$prohibited_tables\fR" 4
.IX Item "$prohibited_tables"
The list of prohibited output characters for stringprep.
.Sp
The parameter may be a reference to an array, or \f(CW\*(C`undef\*(C'\fR. The
array contains \fBpairs\fR of codepoints, which define the \fBstart\fR
and \fBend\fR of a Unicode character range (as integers). The end
character may be \f(CW\*(C`undef\*(C'\fR, specifying a single-character range.
The array may also contain references to nested arrays.
.Sp
Unicode::Stringprep::Prohibited provides the tables from \s-1RFC\s0\ 3454,
Appendix\ C.
.Sp
For further information on the prohibition checking step, see
\&\s-1RFC\s0\ 3454, section\ 5.
.ie n .IP "$bidi_check" 4
.el .IP "\f(CW$bidi_check\fR" 4
.IX Item "$bidi_check"
Whether to employ checks for confusing bidirectional text. A boolean value.
.Sp
For further information on the bidi checking step, see \s-1RFC\s0\ 3454,
section\ 6.
.ie n .IP "$unassigned_check" 4
.el .IP "\f(CW$unassigned_check\fR" 4
.IX Item "$unassigned_check"
Whether to check for and prohibit unassigned characters. A boolean value.
.Sp
The check must be used when creating \fIstored\fR strings. It should not be used
for \fIquery\fR strings, increasing the chance that newly assigned characters work
as expected.
.Sp
For further information on \fIstored\fR and \fIquery\fR strings, see \s-1RFC\s0\ 3454,
section\ 7.
.RE
.RS 4
.Sp
The function returned can be called with a single parameter, the string to be
prepared, and returns the prepared string. It will die if the input string
cannot be successfully prepared because it would contain invalid output (so use
\&\f(CW\*(C`eval\*(C'\fR if necessary).
.Sp
For performance reasons, it is strongly recommended to call the
\&\f(CW\*(C`new\*(C'\fR function as few times as possible, i.\ e. exactly once per
\&\fIstringprep\fR profile. It might also be better not to use this
module directly but to use (or write) a module implementing a
profile, such as Authen::SASL::SASLprep.
.RE
.SH "IMPLEMENTING PROFILES"
.IX Header "IMPLEMENTING PROFILES"
You can easily implement a \fIstringprep\fR profile without subclassing:
.PP
.Vb 1
\& package ACME::ExamplePrep;
\&
\& use Unicode::Stringprep;
\&
\& use Unicode::Stringprep::Mapping;
\& use Unicode::Stringprep::Prohibited;
\&
\& *exampleprep = Unicode::Stringprep\->new(
\& 3.2,
\& [ \e@Unicode::Stringprep::Mapping::B1, ],
\& \*(Aq\*(Aq,
\& [ \e@Unicode::Stringprep::Prohibited::C12,
\& \e@Unicode::Stringprep::Prohibited::C22, ],
\& 1,
\& );
.Ve
.PP
This binds \f(CW\*(C`ACME::ExamplePrep::exampleprep\*(C'\fR to the function
created by \f(CW\*(C`Unicode::Stringprep\->new\*(C'\fR.
.PP
Usually, it is not necessary to subclass this module. Sublassing
this module is not recommended.
.SH "DATA TABLES"
.IX Header "DATA TABLES"
The following modules contain the data tables from \s-1RFC\s0\ 3454.
These modules are automatically loaded when loading
\&\f(CW\*(C`Unicode::Stringprep\*(C'\fR.
.IP "\(bu" 4
Unicode::Stringprep::Unassigned
.Sp
.Vb 1
\& @Unicode::Stringprep::Unassigned::A1 # Appendix A.1
.Ve
.IP "\(bu" 4
Unicode::Stringprep::Mapping
.Sp
.Vb 3
\& @Unicode::Stringprep::Mapping::B1 # Appendix B.1
\& @Unicode::Stringprep::Mapping::B2 # Appendix B.2
\& @Unicode::Stringprep::Mapping::B2 # Appendix B.3
.Ve
.IP "\(bu" 4
Unicode::Stringprep::Prohibited
.Sp
.Vb 11
\& @Unicode::Stringprep::Prohibited::C11 # Appendix C.1.1
\& @Unicode::Stringprep::Prohibited::C12 # Appendix C.1.2
\& @Unicode::Stringprep::Prohibited::C21 # Appendix C.2.1
\& @Unicode::Stringprep::Prohibited::C22 # Appendix C.2.2
\& @Unicode::Stringprep::Prohibited::C3 # Appendix C.3
\& @Unicode::Stringprep::Prohibited::C4 # Appendix C.4
\& @Unicode::Stringprep::Prohibited::C5 # Appendix C.5
\& @Unicode::Stringprep::Prohibited::C6 # Appendix C.6
\& @Unicode::Stringprep::Prohibited::C7 # Appendix C.7
\& @Unicode::Stringprep::Prohibited::C8 # Appendix C.8
\& @Unicode::Stringprep::Prohibited::C9 # Appendix C.9
.Ve
.IP "\(bu" 4
Unicode::Stringprep::BiDi
.Sp
.Vb 2
\& @Unicode::Stringprep::BiDi::D1 # Appendix D.1
\& @Unicode::Stringprep::BiDi::D2 # Appendix D.2
.Ve
.SH "CAVEATS"
.IX Header "CAVEATS"
In Unicode 3.2 to 4.0.1, the specification of \s-1UAX\s0 #15: Unicode Normalization
Forms for forms \s-1NFC\s0 and \s-1NFKC\s0 is not logically self-consistent. This has been
fixed in Corrigendum #5 (<http://unicode.org/versions/corrigendum5.html>).
.PP
Unfortunately, this yields two ways to implement \s-1NFC\s0 and \s-1NFKC\s0 in Unicode 3.2,
on which the Stringprep standard is based: one based on a literal
interpretation of the original specification and one based on the corrected
specification. The output of these implementations differs for a small class of
strings, all of which can't appear in meaningful text. See \s-1UAX\s0 #15, section 19
<http://unicode.org/reports/tr15/#Stability_Prior_to_Unicode41> for details.
.PP
This module will check for these strings and, if normalization is done,
prohibit them in output as it is not possible to interoperate under these
circumstandes.
.PP
Please note that due to this, the \fInormalization\fR step may cause the
preparation to fail. That is, the preparation function may die even if there
are no prohibited characters and no checks for bidi sequences and unassigned
characters, which may be surprising.
.SH "AUTHOR"
.IX Header "AUTHOR"
Claus Fa\*:rber <CFAERBER@cpan.org>
.SH "LICENSE"
.IX Header "LICENSE"
Copyright 2007\-2009 Claus Fa\*:rber.
.PP
This library is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
Unicode::Normalize, \s-1RFC\s0\ 3454 (<http://www.ietf.org/rfc/rfc3454.txt>)
Mini Shell