| Current Path : /usr/opt/perl530/man/man3/ |
FreeBSD hs32.drive.ne.jp 9.1-RELEASE FreeBSD 9.1-RELEASE #1: Wed Jan 14 12:18:08 JST 2015 root@hs32.drive.ne.jp:/sys/amd64/compile/hs32 amd64 |
| Current File : //usr/opt/perl530/man/man3/Unicode::Normalize.3 |
.\" Automatically generated by Pod::Man 4.11 (Pod::Simple 3.35)
.\"
.\" 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 >0, 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::Normalize 3"
.TH Unicode::Normalize 3 "2019-10-24" "perl v5.30.2" "Perl Programmers Reference Guide"
.\" 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::Normalize \- Unicode Normalization Forms
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
(1) using function names exported by default:
.PP
.Vb 1
\& use Unicode::Normalize;
\&
\& $NFD_string = NFD($string); # Normalization Form D
\& $NFC_string = NFC($string); # Normalization Form C
\& $NFKD_string = NFKD($string); # Normalization Form KD
\& $NFKC_string = NFKC($string); # Normalization Form KC
.Ve
.PP
(2) using function names exported on request:
.PP
.Vb 1
\& use Unicode::Normalize \*(Aqnormalize\*(Aq;
\&
\& $NFD_string = normalize(\*(AqD\*(Aq, $string); # Normalization Form D
\& $NFC_string = normalize(\*(AqC\*(Aq, $string); # Normalization Form C
\& $NFKD_string = normalize(\*(AqKD\*(Aq, $string); # Normalization Form KD
\& $NFKC_string = normalize(\*(AqKC\*(Aq, $string); # Normalization Form KC
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Parameters:
.PP
\&\f(CW$string\fR is used as a string under character semantics (see perlunicode).
.PP
\&\f(CW$code_point\fR should be an unsigned integer representing a Unicode code point.
.PP
Note: Between \s-1XSUB\s0 and pure Perl, there is an incompatibility
about the interpretation of \f(CW$code_point\fR as a decimal number.
\&\s-1XSUB\s0 converts \f(CW$code_point\fR to an unsigned integer, but pure Perl does not.
Do not use a floating point nor a negative sign in \f(CW$code_point\fR.
.SS "Normalization Forms"
.IX Subsection "Normalization Forms"
.ie n .IP """$NFD_string = NFD($string)""" 4
.el .IP "\f(CW$NFD_string = NFD($string)\fR" 4
.IX Item "$NFD_string = NFD($string)"
It returns the Normalization Form D (formed by canonical decomposition).
.ie n .IP """$NFC_string = NFC($string)""" 4
.el .IP "\f(CW$NFC_string = NFC($string)\fR" 4
.IX Item "$NFC_string = NFC($string)"
It returns the Normalization Form C (formed by canonical decomposition
followed by canonical composition).
.ie n .IP """$NFKD_string = NFKD($string)""" 4
.el .IP "\f(CW$NFKD_string = NFKD($string)\fR" 4
.IX Item "$NFKD_string = NFKD($string)"
It returns the Normalization Form \s-1KD\s0 (formed by compatibility decomposition).
.ie n .IP """$NFKC_string = NFKC($string)""" 4
.el .IP "\f(CW$NFKC_string = NFKC($string)\fR" 4
.IX Item "$NFKC_string = NFKC($string)"
It returns the Normalization Form \s-1KC\s0 (formed by compatibility decomposition
followed by \fBcanonical\fR composition).
.ie n .IP """$FCD_string = FCD($string)""" 4
.el .IP "\f(CW$FCD_string = FCD($string)\fR" 4
.IX Item "$FCD_string = FCD($string)"
If the given string is in \s-1FCD\s0 (\*(L"Fast C or D\*(R" form; cf. \s-1UTN\s0 #5),
it returns the string without modification; otherwise it returns an \s-1FCD\s0 string.
.Sp
Note: \s-1FCD\s0 is not always unique, then plural forms may be equivalent
each other. \f(CW\*(C`FCD()\*(C'\fR will return one of these equivalent forms.
.ie n .IP """$FCC_string = FCC($string)""" 4
.el .IP "\f(CW$FCC_string = FCC($string)\fR" 4
.IX Item "$FCC_string = FCC($string)"
It returns the \s-1FCC\s0 form (\*(L"Fast C Contiguous\*(R"; cf. \s-1UTN\s0 #5).
.Sp
Note: \s-1FCC\s0 is unique, as well as four normalization forms (NF*).
.ie n .IP """$normalized_string = normalize($form_name, $string)""" 4
.el .IP "\f(CW$normalized_string = normalize($form_name, $string)\fR" 4
.IX Item "$normalized_string = normalize($form_name, $string)"
It returns the normalization form of \f(CW$form_name\fR.
.Sp
As \f(CW$form_name\fR, one of the following names must be given.
.Sp
.Vb 4
\& \*(AqC\*(Aq or \*(AqNFC\*(Aq for Normalization Form C (UAX #15)
\& \*(AqD\*(Aq or \*(AqNFD\*(Aq for Normalization Form D (UAX #15)
\& \*(AqKC\*(Aq or \*(AqNFKC\*(Aq for Normalization Form KC (UAX #15)
\& \*(AqKD\*(Aq or \*(AqNFKD\*(Aq for Normalization Form KD (UAX #15)
\&
\& \*(AqFCD\*(Aq for "Fast C or D" Form (UTN #5)
\& \*(AqFCC\*(Aq for "Fast C Contiguous" (UTN #5)
.Ve
.SS "Decomposition and Composition"
.IX Subsection "Decomposition and Composition"
.ie n .IP """$decomposed_string = decompose($string [, $useCompatMapping])""" 4
.el .IP "\f(CW$decomposed_string = decompose($string [, $useCompatMapping])\fR" 4
.IX Item "$decomposed_string = decompose($string [, $useCompatMapping])"
It returns the concatenation of the decomposition of each character
in the string.
.Sp
If the second parameter (a boolean) is omitted or false,
the decomposition is canonical decomposition;
if the second parameter (a boolean) is true,
the decomposition is compatibility decomposition.
.Sp
The string returned is not always in \s-1NFD/NFKD.\s0 Reordering may be required.
.Sp
.Vb 2
\& $NFD_string = reorder(decompose($string)); # eq. to NFD()
\& $NFKD_string = reorder(decompose($string, TRUE)); # eq. to NFKD()
.Ve
.ie n .IP """$reordered_string = reorder($string)""" 4
.el .IP "\f(CW$reordered_string = reorder($string)\fR" 4
.IX Item "$reordered_string = reorder($string)"
It returns the result of reordering the combining characters
according to Canonical Ordering Behavior.
.Sp
For example, when you have a list of \s-1NFD/NFKD\s0 strings,
you can get the concatenated \s-1NFD/NFKD\s0 string from them, by saying
.Sp
.Vb 2
\& $concat_NFD = reorder(join \*(Aq\*(Aq, @NFD_strings);
\& $concat_NFKD = reorder(join \*(Aq\*(Aq, @NFKD_strings);
.Ve
.ie n .IP """$composed_string = compose($string)""" 4
.el .IP "\f(CW$composed_string = compose($string)\fR" 4
.IX Item "$composed_string = compose($string)"
It returns the result of canonical composition
without applying any decomposition.
.Sp
For example, when you have a \s-1NFD/NFKD\s0 string,
you can get its \s-1NFC/NFKC\s0 string, by saying
.Sp
.Vb 2
\& $NFC_string = compose($NFD_string);
\& $NFKC_string = compose($NFKD_string);
.Ve
.ie n .IP """($processed, $unprocessed) = splitOnLastStarter($normalized)""" 4
.el .IP "\f(CW($processed, $unprocessed) = splitOnLastStarter($normalized)\fR" 4
.IX Item "($processed, $unprocessed) = splitOnLastStarter($normalized)"
It returns two strings: the first one, \f(CW$processed\fR, is a part
before the last starter, and the second one, \f(CW$unprocessed\fR is
another part after the first part. A starter is a character having
a combining class of zero (see \s-1UAX\s0 #15).
.Sp
Note that \f(CW$processed\fR may be empty (when \f(CW$normalized\fR contains no
starter or starts with the last starter), and then \f(CW$unprocessed\fR
should be equal to the entire \f(CW$normalized\fR.
.Sp
When you have a \f(CW$normalized\fR string and an \f(CW$unnormalized\fR string
following it, a simple concatenation is wrong:
.Sp
.Vb 1
\& $concat = $normalized . normalize($form, $unnormalized); # wrong!
.Ve
.Sp
Instead of it, do like this:
.Sp
.Vb 2
\& ($processed, $unprocessed) = splitOnLastStarter($normalized);
\& $concat = $processed . normalize($form,$unprocessed.$unnormalized);
.Ve
.Sp
\&\f(CW\*(C`splitOnLastStarter()\*(C'\fR should be called with a pre-normalized parameter
\&\f(CW$normalized\fR, that is in the same form as \f(CW$form\fR you want.
.Sp
If you have an array of \f(CW@string\fR that should be concatenated and then
normalized, you can do like this:
.Sp
.Vb 11
\& my $result = "";
\& my $unproc = "";
\& foreach my $str (@string) {
\& $unproc .= $str;
\& my $n = normalize($form, $unproc);
\& my($p, $u) = splitOnLastStarter($n);
\& $result .= $p;
\& $unproc = $u;
\& }
\& $result .= $unproc;
\& # instead of normalize($form, join(\*(Aq\*(Aq, @string))
.Ve
.ie n .IP """$processed = normalize_partial($form, $unprocessed)""" 4
.el .IP "\f(CW$processed = normalize_partial($form, $unprocessed)\fR" 4
.IX Item "$processed = normalize_partial($form, $unprocessed)"
A wrapper for the combination of \f(CW\*(C`normalize()\*(C'\fR and \f(CW\*(C`splitOnLastStarter()\*(C'\fR.
Note that \f(CW$unprocessed\fR will be modified as a side-effect.
.Sp
If you have an array of \f(CW@string\fR that should be concatenated and then
normalized, you can do like this:
.Sp
.Vb 8
\& my $result = "";
\& my $unproc = "";
\& foreach my $str (@string) {
\& $unproc .= $str;
\& $result .= normalize_partial($form, $unproc);
\& }
\& $result .= $unproc;
\& # instead of normalize($form, join(\*(Aq\*(Aq, @string))
.Ve
.ie n .IP """$processed = NFD_partial($unprocessed)""" 4
.el .IP "\f(CW$processed = NFD_partial($unprocessed)\fR" 4
.IX Item "$processed = NFD_partial($unprocessed)"
It does like \f(CW\*(C`normalize_partial(\*(AqNFD\*(Aq, $unprocessed)\*(C'\fR.
Note that \f(CW$unprocessed\fR will be modified as a side-effect.
.ie n .IP """$processed = NFC_partial($unprocessed)""" 4
.el .IP "\f(CW$processed = NFC_partial($unprocessed)\fR" 4
.IX Item "$processed = NFC_partial($unprocessed)"
It does like \f(CW\*(C`normalize_partial(\*(AqNFC\*(Aq, $unprocessed)\*(C'\fR.
Note that \f(CW$unprocessed\fR will be modified as a side-effect.
.ie n .IP """$processed = NFKD_partial($unprocessed)""" 4
.el .IP "\f(CW$processed = NFKD_partial($unprocessed)\fR" 4
.IX Item "$processed = NFKD_partial($unprocessed)"
It does like \f(CW\*(C`normalize_partial(\*(AqNFKD\*(Aq, $unprocessed)\*(C'\fR.
Note that \f(CW$unprocessed\fR will be modified as a side-effect.
.ie n .IP """$processed = NFKC_partial($unprocessed)""" 4
.el .IP "\f(CW$processed = NFKC_partial($unprocessed)\fR" 4
.IX Item "$processed = NFKC_partial($unprocessed)"
It does like \f(CW\*(C`normalize_partial(\*(AqNFKC\*(Aq, $unprocessed)\*(C'\fR.
Note that \f(CW$unprocessed\fR will be modified as a side-effect.
.SS "Quick Check"
.IX Subsection "Quick Check"
(see Annex 8, \s-1UAX\s0 #15; and \fIDerivedNormalizationProps.txt\fR)
.PP
The following functions check whether the string is in that normalization form.
.PP
The result returned will be one of the following:
.PP
.Vb 3
\& YES The string is in that normalization form.
\& NO The string is not in that normalization form.
\& MAYBE Dubious. Maybe yes, maybe no.
.Ve
.ie n .IP """$result = checkNFD($string)""" 4
.el .IP "\f(CW$result = checkNFD($string)\fR" 4
.IX Item "$result = checkNFD($string)"
It returns true (\f(CW1\fR) if \f(CW\*(C`YES\*(C'\fR; false (\f(CW\*(C`empty string\*(C'\fR) if \f(CW\*(C`NO\*(C'\fR.
.ie n .IP """$result = checkNFC($string)""" 4
.el .IP "\f(CW$result = checkNFC($string)\fR" 4
.IX Item "$result = checkNFC($string)"
It returns true (\f(CW1\fR) if \f(CW\*(C`YES\*(C'\fR; false (\f(CW\*(C`empty string\*(C'\fR) if \f(CW\*(C`NO\*(C'\fR;
\&\f(CW\*(C`undef\*(C'\fR if \f(CW\*(C`MAYBE\*(C'\fR.
.ie n .IP """$result = checkNFKD($string)""" 4
.el .IP "\f(CW$result = checkNFKD($string)\fR" 4
.IX Item "$result = checkNFKD($string)"
It returns true (\f(CW1\fR) if \f(CW\*(C`YES\*(C'\fR; false (\f(CW\*(C`empty string\*(C'\fR) if \f(CW\*(C`NO\*(C'\fR.
.ie n .IP """$result = checkNFKC($string)""" 4
.el .IP "\f(CW$result = checkNFKC($string)\fR" 4
.IX Item "$result = checkNFKC($string)"
It returns true (\f(CW1\fR) if \f(CW\*(C`YES\*(C'\fR; false (\f(CW\*(C`empty string\*(C'\fR) if \f(CW\*(C`NO\*(C'\fR;
\&\f(CW\*(C`undef\*(C'\fR if \f(CW\*(C`MAYBE\*(C'\fR.
.ie n .IP """$result = checkFCD($string)""" 4
.el .IP "\f(CW$result = checkFCD($string)\fR" 4
.IX Item "$result = checkFCD($string)"
It returns true (\f(CW1\fR) if \f(CW\*(C`YES\*(C'\fR; false (\f(CW\*(C`empty string\*(C'\fR) if \f(CW\*(C`NO\*(C'\fR.
.ie n .IP """$result = checkFCC($string)""" 4
.el .IP "\f(CW$result = checkFCC($string)\fR" 4
.IX Item "$result = checkFCC($string)"
It returns true (\f(CW1\fR) if \f(CW\*(C`YES\*(C'\fR; false (\f(CW\*(C`empty string\*(C'\fR) if \f(CW\*(C`NO\*(C'\fR;
\&\f(CW\*(C`undef\*(C'\fR if \f(CW\*(C`MAYBE\*(C'\fR.
.Sp
Note: If a string is not in \s-1FCD,\s0 it must not be in \s-1FCC.\s0
So \f(CW\*(C`checkFCC($not_FCD_string)\*(C'\fR should return \f(CW\*(C`NO\*(C'\fR.
.ie n .IP """$result = check($form_name, $string)""" 4
.el .IP "\f(CW$result = check($form_name, $string)\fR" 4
.IX Item "$result = check($form_name, $string)"
It returns true (\f(CW1\fR) if \f(CW\*(C`YES\*(C'\fR; false (\f(CW\*(C`empty string\*(C'\fR) if \f(CW\*(C`NO\*(C'\fR;
\&\f(CW\*(C`undef\*(C'\fR if \f(CW\*(C`MAYBE\*(C'\fR.
.Sp
As \f(CW$form_name\fR, one of the following names must be given.
.Sp
.Vb 4
\& \*(AqC\*(Aq or \*(AqNFC\*(Aq for Normalization Form C (UAX #15)
\& \*(AqD\*(Aq or \*(AqNFD\*(Aq for Normalization Form D (UAX #15)
\& \*(AqKC\*(Aq or \*(AqNFKC\*(Aq for Normalization Form KC (UAX #15)
\& \*(AqKD\*(Aq or \*(AqNFKD\*(Aq for Normalization Form KD (UAX #15)
\&
\& \*(AqFCD\*(Aq for "Fast C or D" Form (UTN #5)
\& \*(AqFCC\*(Aq for "Fast C Contiguous" (UTN #5)
.Ve
.PP
\&\fBNote\fR
.PP
In the cases of \s-1NFD, NFKD,\s0 and \s-1FCD,\s0 the answer must be
either \f(CW\*(C`YES\*(C'\fR or \f(CW\*(C`NO\*(C'\fR. The answer \f(CW\*(C`MAYBE\*(C'\fR may be returned
in the cases of \s-1NFC, NFKC,\s0 and \s-1FCC.\s0
.PP
A \f(CW\*(C`MAYBE\*(C'\fR string should contain at least one combining character
or the like. For example, \f(CW\*(C`COMBINING ACUTE ACCENT\*(C'\fR has
the \s-1MAYBE_NFC/MAYBE_NFKC\s0 property.
.PP
Both \f(CW\*(C`checkNFC("A\eN{COMBINING ACUTE ACCENT}")\*(C'\fR
and \f(CW\*(C`checkNFC("B\eN{COMBINING ACUTE ACCENT}")\*(C'\fR will return \f(CW\*(C`MAYBE\*(C'\fR.
\&\f(CW"A\eN{COMBINING ACUTE ACCENT}"\fR is not in \s-1NFC\s0
(its \s-1NFC\s0 is \f(CW"\eN{LATIN CAPITAL LETTER A WITH ACUTE}"\fR),
while \f(CW"B\eN{COMBINING ACUTE ACCENT}"\fR is in \s-1NFC.\s0
.PP
If you want to check exactly, compare the string with its \s-1NFC/NFKC/FCC.\s0
.PP
.Vb 5
\& if ($string eq NFC($string)) {
\& # $string is exactly normalized in NFC;
\& } else {
\& # $string is not normalized in NFC;
\& }
\&
\& if ($string eq NFKC($string)) {
\& # $string is exactly normalized in NFKC;
\& } else {
\& # $string is not normalized in NFKC;
\& }
.Ve
.SS "Character Data"
.IX Subsection "Character Data"
These functions are interface of character data used internally.
If you want only to get Unicode normalization forms, you don't need
call them yourself.
.ie n .IP """$canonical_decomposition = getCanon($code_point)""" 4
.el .IP "\f(CW$canonical_decomposition = getCanon($code_point)\fR" 4
.IX Item "$canonical_decomposition = getCanon($code_point)"
If the character is canonically decomposable (including Hangul Syllables),
it returns the (full) canonical decomposition as a string.
Otherwise it returns \f(CW\*(C`undef\*(C'\fR.
.Sp
\&\fBNote:\fR According to the Unicode standard, the canonical decomposition
of the character that is not canonically decomposable is same as
the character itself.
.ie n .IP """$compatibility_decomposition = getCompat($code_point)""" 4
.el .IP "\f(CW$compatibility_decomposition = getCompat($code_point)\fR" 4
.IX Item "$compatibility_decomposition = getCompat($code_point)"
If the character is compatibility decomposable (including Hangul Syllables),
it returns the (full) compatibility decomposition as a string.
Otherwise it returns \f(CW\*(C`undef\*(C'\fR.
.Sp
\&\fBNote:\fR According to the Unicode standard, the compatibility decomposition
of the character that is not compatibility decomposable is same as
the character itself.
.ie n .IP """$code_point_composite = getComposite($code_point_here, $code_point_next)""" 4
.el .IP "\f(CW$code_point_composite = getComposite($code_point_here, $code_point_next)\fR" 4
.IX Item "$code_point_composite = getComposite($code_point_here, $code_point_next)"
If two characters here and next (as code points) are composable
(including Hangul Jamo/Syllables and Composition Exclusions),
it returns the code point of the composite.
.Sp
If they are not composable, it returns \f(CW\*(C`undef\*(C'\fR.
.ie n .IP """$combining_class = getCombinClass($code_point)""" 4
.el .IP "\f(CW$combining_class = getCombinClass($code_point)\fR" 4
.IX Item "$combining_class = getCombinClass($code_point)"
It returns the combining class (as an integer) of the character.
.ie n .IP """$may_be_composed_with_prev_char = isComp2nd($code_point)""" 4
.el .IP "\f(CW$may_be_composed_with_prev_char = isComp2nd($code_point)\fR" 4
.IX Item "$may_be_composed_with_prev_char = isComp2nd($code_point)"
It returns a boolean whether the character of the specified codepoint
may be composed with the previous one in a certain composition
(including Hangul Compositions, but excluding
Composition Exclusions and Non-Starter Decompositions).
.ie n .IP """$is_exclusion = isExclusion($code_point)""" 4
.el .IP "\f(CW$is_exclusion = isExclusion($code_point)\fR" 4
.IX Item "$is_exclusion = isExclusion($code_point)"
It returns a boolean whether the code point is a composition exclusion.
.ie n .IP """$is_singleton = isSingleton($code_point)""" 4
.el .IP "\f(CW$is_singleton = isSingleton($code_point)\fR" 4
.IX Item "$is_singleton = isSingleton($code_point)"
It returns a boolean whether the code point is a singleton
.ie n .IP """$is_non_starter_decomposition = isNonStDecomp($code_point)""" 4
.el .IP "\f(CW$is_non_starter_decomposition = isNonStDecomp($code_point)\fR" 4
.IX Item "$is_non_starter_decomposition = isNonStDecomp($code_point)"
It returns a boolean whether the code point has Non-Starter Decomposition.
.ie n .IP """$is_Full_Composition_Exclusion = isComp_Ex($code_point)""" 4
.el .IP "\f(CW$is_Full_Composition_Exclusion = isComp_Ex($code_point)\fR" 4
.IX Item "$is_Full_Composition_Exclusion = isComp_Ex($code_point)"
It returns a boolean of the derived property Comp_Ex
(Full_Composition_Exclusion). This property is generated from
Composition Exclusions + Singletons + Non-Starter Decompositions.
.ie n .IP """$NFD_is_NO = isNFD_NO($code_point)""" 4
.el .IP "\f(CW$NFD_is_NO = isNFD_NO($code_point)\fR" 4
.IX Item "$NFD_is_NO = isNFD_NO($code_point)"
It returns a boolean of the derived property \s-1NFD_NO\s0
(NFD_Quick_Check=No).
.ie n .IP """$NFC_is_NO = isNFC_NO($code_point)""" 4
.el .IP "\f(CW$NFC_is_NO = isNFC_NO($code_point)\fR" 4
.IX Item "$NFC_is_NO = isNFC_NO($code_point)"
It returns a boolean of the derived property \s-1NFC_NO\s0
(NFC_Quick_Check=No).
.ie n .IP """$NFC_is_MAYBE = isNFC_MAYBE($code_point)""" 4
.el .IP "\f(CW$NFC_is_MAYBE = isNFC_MAYBE($code_point)\fR" 4
.IX Item "$NFC_is_MAYBE = isNFC_MAYBE($code_point)"
It returns a boolean of the derived property \s-1NFC_MAYBE\s0
(NFC_Quick_Check=Maybe).
.ie n .IP """$NFKD_is_NO = isNFKD_NO($code_point)""" 4
.el .IP "\f(CW$NFKD_is_NO = isNFKD_NO($code_point)\fR" 4
.IX Item "$NFKD_is_NO = isNFKD_NO($code_point)"
It returns a boolean of the derived property \s-1NFKD_NO\s0
(NFKD_Quick_Check=No).
.ie n .IP """$NFKC_is_NO = isNFKC_NO($code_point)""" 4
.el .IP "\f(CW$NFKC_is_NO = isNFKC_NO($code_point)\fR" 4
.IX Item "$NFKC_is_NO = isNFKC_NO($code_point)"
It returns a boolean of the derived property \s-1NFKC_NO\s0
(NFKC_Quick_Check=No).
.ie n .IP """$NFKC_is_MAYBE = isNFKC_MAYBE($code_point)""" 4
.el .IP "\f(CW$NFKC_is_MAYBE = isNFKC_MAYBE($code_point)\fR" 4
.IX Item "$NFKC_is_MAYBE = isNFKC_MAYBE($code_point)"
It returns a boolean of the derived property \s-1NFKC_MAYBE\s0
(NFKC_Quick_Check=Maybe).
.SH "EXPORT"
.IX Header "EXPORT"
\&\f(CW\*(C`NFC\*(C'\fR, \f(CW\*(C`NFD\*(C'\fR, \f(CW\*(C`NFKC\*(C'\fR, \f(CW\*(C`NFKD\*(C'\fR: by default.
.PP
\&\f(CW\*(C`normalize\*(C'\fR and other some functions: on request.
.SH "CAVEATS"
.IX Header "CAVEATS"
.IP "Perl's version vs. Unicode version" 4
.IX Item "Perl's version vs. Unicode version"
Since this module refers to perl core's Unicode database in the directory
\&\fI/lib/unicore\fR (or formerly \fI/lib/unicode\fR), the Unicode version of
normalization implemented by this module depends on what has been
compiled into your perl. The following table lists the default Unicode
version that comes with various perl versions. (It is possible to change
the Unicode version in any perl version to be any earlier Unicode version,
so one could cause Unicode 3.2 to be used in any perl version starting with
5.8.0. Read \fI\f(CI$Config{privlib}\fI/unicore/README.perl\fR for details.
.Sp
.Vb 10
\& perl\*(Aqs version implemented Unicode version
\& 5.6.1 3.0.1
\& 5.7.2 3.1.0
\& 5.7.3 3.1.1 (normalization is same as 3.1.0)
\& 5.8.0 3.2.0
\& 5.8.1\-5.8.3 4.0.0
\& 5.8.4\-5.8.6 4.0.1 (normalization is same as 4.0.0)
\& 5.8.7\-5.8.8 4.1.0
\& 5.10.0 5.0.0
\& 5.8.9, 5.10.1 5.1.0
\& 5.12.x 5.2.0
\& 5.14.x 6.0.0
\& 5.16.x 6.1.0
\& 5.18.x 6.2.0
\& 5.20.x 6.3.0
\& 5.22.x 7.0.0
.Ve
.IP "Correction of decomposition mapping" 4
.IX Item "Correction of decomposition mapping"
In older Unicode versions, a small number of characters (all of which are
\&\s-1CJK\s0 compatibility ideographs as far as they have been found) may have
an erroneous decomposition mapping (see \fINormalizationCorrections.txt\fR).
Anyhow, this module will neither refer to \fINormalizationCorrections.txt\fR
nor provide any specific version of normalization. Therefore this module
running on an older perl with an older Unicode database may use
the erroneous decomposition mapping blindly conforming to the Unicode database.
.IP "Revised definition of canonical composition" 4
.IX Item "Revised definition of canonical composition"
In Unicode 4.1.0, the definition D2 of canonical composition (which
affects \s-1NFC\s0 and \s-1NFKC\s0) has been changed (see Public Review Issue #29
and recent \s-1UAX\s0 #15). This module has used the newer definition
since the version 0.07 (Oct 31, 2001).
This module will not support the normalization according to the older
definition, even if the Unicode version implemented by perl is
lower than 4.1.0.
.SH "AUTHOR"
.IX Header "AUTHOR"
\&\s-1SADAHIRO\s0 Tomoyuki <SADAHIRO@cpan.org>
.PP
Currently maintained by <perl5\-porters@perl.org>
.PP
Copyright(C) 2001\-2012, \s-1SADAHIRO\s0 Tomoyuki. Japan. All rights reserved.
.SH "LICENSE"
.IX Header "LICENSE"
This module 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"
.IP "http://www.unicode.org/reports/tr15/" 4
.IX Item "http://www.unicode.org/reports/tr15/"
Unicode Normalization Forms \- \s-1UAX\s0 #15
.IP "http://www.unicode.org/Public/UNIDATA/CompositionExclusions.txt" 4
.IX Item "http://www.unicode.org/Public/UNIDATA/CompositionExclusions.txt"
Composition Exclusion Table
.IP "http://www.unicode.org/Public/UNIDATA/DerivedNormalizationProps.txt" 4
.IX Item "http://www.unicode.org/Public/UNIDATA/DerivedNormalizationProps.txt"
Derived Normalization Properties
.IP "http://www.unicode.org/Public/UNIDATA/NormalizationCorrections.txt" 4
.IX Item "http://www.unicode.org/Public/UNIDATA/NormalizationCorrections.txt"
Normalization Corrections
.IP "http://www.unicode.org/review/pr\-29.html" 4
.IX Item "http://www.unicode.org/review/pr-29.html"
Public Review Issue #29: Normalization Issue
.IP "http://www.unicode.org/notes/tn5/" 4
.IX Item "http://www.unicode.org/notes/tn5/"
Canonical Equivalence in Applications \- \s-1UTN\s0 #5