Unicode::LineBreak~[ja]

XX

XXXXXXXXXXXXX

XXXXXmandatory breakXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX [UAX #14] XXXXXXXXXXXXXXXXXdirect breakXXXXXXXindirect breakXXXXXX

XXXXXXXXXalphabetic charactersXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXideographic charactersXXXXXXXXXXXXXXXXXXXX [UAX #14] XXXXXXXXXXXXXXXX AL XXXXXXXXXXXXXXXX ID XXXXXXX (XXXXXXXXXXXXXXXXXXXXXXXX)X XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXwideXXXXXXnarrowXXXXXXXXXXXnonspacingXXXXXXXXXXXXX 2 XX1 XX0 XXXXXX XXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXXXXX

XXXX

new ([KEY => VALUE, ...])

XXXXXXXX KEY => VALUE XXXXXXX "XXXXX" XXXX

break (STRING)

XXXXXXXXXXX Unicode XXX STRING XXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX

break_partial (STRING)

XXXXXXXXXXX break() XXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXSTRING XXX "undef" XXXXX

config (KEY)

config (KEY => VALUE, ...)

XXXXXXXXXXX XXXXXXXXXXXXX KEY => VALUE XXXXXXX "XXXXX" XXXX

copy

XXXXXXXXXXX XXXXXXXXXXXXXXXXXXXX

XXXXX

breakingRule (BEFORESTR, AFTERSTR)

XXXXXXXXXXX XXX BEFORESTR X AFTERSTR XXXXXXXXXXXXX XXXXXXX "XX" XXXX

X: XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXbreak() XXXXXXXXXXXXXX

context ([Charset => CHARSET], [Language => LANGUAGE])

XXX XXXXXXXX CHARSET XXXXXXXX LANGUAGE XXXXXXXXXX/XXXXXXXXX

XXXXX

"new"X"config" XXXXXXXXXXXXXXXXXXX XXXXX ([E])XXXXXXXXXX ([G]) (Unicode::GCString~[ja] XXX)XXXXXX ([L]) XXXXXXXXXXX

BreakIndent => "YES" | "NO"

[L] XXX SPACE XXX (XXXXX) XXXXXXXXXXXX [UAX #14] X SPACE XXXXXXXXXXXXXXXXX XXXX "YES"X

X: XXXXXXXXXXXX 1.011 XXXXXXX

CharMax => NUMBER

[L] XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXX XXXX 998X 0 XXXXXXX

ColMin => NUMBER

[L] XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXX 0X

ColMax => NUMBER

[L] XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXX 76X

"Urgent" XXXXXXXX "XXXXXXXXXXX" XXXX

ComplexBreaking => "YES" | "NO"

[L] XXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXXXXX "YES"X

Context => CONTEXT

[E][L] XX/XXXXXXXXXXX XXXXXXXX "EASTASIAN" X "NONEASTASIAN"X XXXXXX "NONEASTASIAN"X

"EASTASIAN" XXXXXEast_Asian_Width XXXXX (A) XXXXXXXXXXXXXXXXXXXXX AI XXXXXXXXX (ID) XXXXX

"NONEASTASIAN" XXXXXEast_Asian_Width XXXXX (A) XXXXXXXXXXXXXXXXXXXXX AI XXXXXXXXX (AL) XXXXX

EAWidth => "[" ORD "=>" PROPERTY "]"

EAWidth => "undef"

[E] XXXXXX East_Asian_Width XXXXXXXXX ORD XXXX UCS XXXXXXXXXXXXXXXXXXX PROPERTY X East_Asian_Width XXXXXXXXXXXX ("XX" XXX)X XXXXXXXXXXXXXXXXX "undef" XXXXXXXXXXXXXXXXXXXXXXXX

XXXXXXEast_Asian_width XXXXXXXXXXX "XXXXXXXXX" XXXX

Format => METHOD

[L] XXXXXXXXXXXXXXXXXX

HangulAsAL => "YES" | "NO"

[L] XXXXXXXXXXXXXXXXXconjoining jamoXXXXXXXXXX (AL) XXXX XXXX "NO"X

LBClass => "[" ORD "=>" CLASS "]"

LBClass => "undef"

[G][L] XXXXXXXXXXX (XX) XXXXXXX ORD XXXX UCS XXXXXXXXXXXXXXXXXXX CLASS XXXXXXXXXXXX ("XX" XXX)X XXXXXXXXXXXXXXXXX "undef" XXXXXXXXXXXXXXXXXXXXXXXX

XXXXXXXXXXXXXXXXXXXX "XXXXXXXXX" XXXX

LegacyCM => "YES" | "NO"

[G][L] XXXXXXXXXXXXXXXXXXXXXX (ID) XXXX Unicode 5.0 XXXXXXXXXXXXXXXXXXXXXXXXXXX XXXX "YES"X

Newline => STRING

[L] XXXXXXXXX Unicode XXXX XXXX "\n"X

Prep => METHOD

[L] XXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXX METHOD XXXXXXXXXXXXXX

Sizing => METHOD

[L] XXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXX

Urgent => METHOD

[L] XXXXXXXXXXXXXXXX XXXXXXXXXXXXX

ViramaAsJoiner => "YES" | "NO"

[G] XXXXXXX (XXXXXXXXXXXXXXXXXXXXXXXXX) XXXXXXXXXXXXXXX XXXX "YES"X X: XXXXXXXXXXXX 2011.001_29 XXXXXXX XXXXXXXXX "NO" XXXXXXXX XXXX[UAX #29] XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

XX

"EA_Na", "EA_N", "EA_A", "EA_W", "EA_H", "EA_F"

[UAX #11] XXXXXX 6 XX East_Asian_Width XXXX X (Na)XXX (N)XXX (A)XX (W)XXX (H)XXX (F)X

"EA_Z"

XXXXXXXXXX East_Asian_Width XXXXX

X: XXXXXXXXXXXXXXXXXXXXXXXXXXXX [UAX #11] XXXXXXXX

"LB_BK", "LB_CR", "LB_LF", "LB_NL", "LB_SP", "LB_OP", "LB_CL", "LB_CP", "LB_QU", "LB_GL", "LB_NS", "LB_EX", "LB_SY", "LB_IS", "LB_PR", "LB_PO", "LB_NU", "LB_AL", "LB_HL", "LB_ID", "LB_IN", "LB_HY", "LB_BA", "LB_BB", "LB_B2", "LB_CB", "LB_ZW", "LB_CM", "LB_WJ", "LB_H2", "LB_H3", "LB_JL", "LB_JV", "LB_JT", "LB_SG", "LB_AI", "LB_CJ", "LB_SA", "LB_XX", "LB_RI"

[UAX #14] XXXXXX 40 XXXXXXX (XX)X

X: XXX CP XUnicode 5.2.0XXXXXXXX XXX HL X CJ XUnicode 6.1.0XXXXXXXX XXX RI X Unicode 6.2.0XXXXXXXX

"MANDATORY", "DIRECT", "INDIRECT", "PROHIBITED"

XXXXXXXX 4 XXXX XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

"Unicode::LineBreak::SouthEastAsian::supported"

XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXX XXXXXXX "undef"X

X: XXXXXXXXXXXXXXXXXXXXXXXXXXX

"UNICODE_VERSION"

XXXXXXXXXXXX Unicode XXXXXXXXXXX

XXXX

"Format" XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX 3 XXXXXXXXXXXXXXXX

    $XXX = &XXXXXX(SELF, EVENT, STR);

SELF X Unicode::LineBreak XXXXXXXEVENT XXXXXXXXXXXXXXXXXXXXXSTR XXXXXXXXXXXX Unicode XXXXXXX

    EVENT |XXXXX           |STR
    -----------------------------------------------------------------
    "sot" |XXXXXX         |XXXXXXX
    "sop" |XXXXXX         |XXXXXX
    "sol" |XXXXXX         |XXXXXXX
    ""    |XXXXX           |XXX (XXXXXXXXXX)
    "eol" |XXXX             |XXXXXXXXXXX
    "eop" |XXXX             |XXXXXXXXXXX
    "eot" |XXXXXX         |XXXXXXXXXXX (XXX)
    -----------------------------------------------------------------

XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"undef" XXXXXXX XXX"sot"X"sop"X"sol" XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

XX: XXXXXXXXXXXXXXXXXXXXXXX Unicode::GCString~[ja] XXX

XXXXXXXXXXXXXXXXXXXXXXXXXXXXX

    sub fmt {
        if ($_[1] =~ /^eo/) {
            return "\n";
        }
        return undef;
    }
    my $lb = Unicode::LineBreak->new(Format => \&fmt);
    $output = $lb->break($text);

XXXXXXXXXXX

XXXXXXXXXXXXX CharMaxXColMaxXColMin XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX "Urgent" XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX 2 XXXXXXXXXXXXXXXX

    @XXX = &XXXXXX(SELF, STR);

SELF X Unicode::LineBreak XXXXXXXSTR XXXXXX Unicode XXXX

XXXXXXXXXXX STR XXXXXXXXXXXXXXXXXXXXXX

XX: XXXXXXXXXXXXXXXXXXXXXXX Unicode::GCString~[ja] XXX

XXXXXXXXXXXXXXXXXX (XXXXXXX) XXXXXXXXXXXXXXXXXXXXXXXXX

    sub hyphenize {
        return map {$_ =~ s/yl$/yl-/; $_} split /(\w+?yl(?=\w))/, $_[1];
    }
    my $lb = Unicode::LineBreak->new(Urgent => \&hyphenize);
    $output = $lb->break("Methionylthreonylthreonylglutaminylarginyl...");

"Prep" XXXXXX [REGEX, SUBREF] XXXXXXXXXXXXXXXXXXXX 2 XXXXXXXXXXXXXXXX

    @XXX = &XXXXXX(SELF, STR);

SELF X Unicode::LineBreak XXXXXXXSTR X REGEX XXXXXXXXXXX Unicode XXXX

XXXXXXXXXXX STR XXXXXXXXXXXXXXXXXXXXXX

XXXXXXXXXXXHTTP URL X [CMOS] XXXXXXXXXXXX

    my $url = qr{http://[\x21-\x7E]+}i;
    sub breakurl {
        my $self = shift;
        my $str = shift;
        return split m{(?<=[/]) (?=[^/]) |
                       (?<=[^-.]) (?=[-~.,_?\#%=&]) |
                       (?<=[=&]) (?=.)}x, $str;
    }
    my $lb = Unicode::LineBreak->new(Prep => [$url, \&breakurl]);
    $output = $lb->break($string);

XXXXX

Unicode::LineBreak XXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXXXX

XXXXXXXXXXXXXXXXXXXXX

    sub paraformat {
        my $self = shift;
        my $action = shift;
        my $str = shift;
        
        if ($action eq 'sot' or $action eq 'sop') {
            $self->{'line'} = '';
        } elsif ($action eq '') {
            $self->{'line'} = $str;
        } elsif ($action eq 'eol') {
            return "\n";
        } elsif ($action eq 'eop') {
            if (length $self->{'line'}) {
                return "\n\n";
            } else {
                return "\n";
            }
        } elsif ($action eq 'eot') {
            return "\n";
        }
        return undef;
    }
    my $lb = Unicode::LineBreak->new(Format => \&paraformat);
    $output = $lb->break($string);

XXXXXXX

"Sizing" XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX 5 XXXXXXXXXXXXXXXX

    $XX = &XXXXXX(SELF, LEN, PRE, SPC, STR);

SELF X Unicode::LineBreak XXXXXXXLEN XXXXXXXXXXXXPRE XXXXX Unicode XXXXSPC XXXXXXXXXXXSTR XXXXX Unicode XXXX

XXXXXXX "PRE.SPC.STR" XXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXXXXXX"ColMin" XXXXXXXX "ColMax" XXXXXXXXXXXXXXXXXXXXXX

XX: XXXXXXXXXXXXXXXXXXXXXXX Unicode::GCString~[ja] XXX

XXXXXXXXXXXXX 8 XXXXXXXXXXXXXXXXXXXXXXX

    sub tabbedsizing {
        my ($self, $cols, $pre, $spc, $str) = @_;
     
        my $spcstr = $spc.$str;
        while ($spcstr->lbc == LB_SP) {
            my $c = $spcstr->item(0);
            if ($c eq "\t") {
                $cols += 8 - $cols % 8;
            } else {
                $cols += $c->columns;
            }
            $spcstr = $spcstr->substr(1);
        }
        $cols += $spcstr->columns;
        return $cols;
    };
    my $lb = Unicode::LineBreak->new(LBClass => [ord("\t") => LB_SP],
                                     Sizing => \&tabbedsizing);
    $output = $lb->break($string);

XXXXXXXXX

"LBClass" XXXXXXXX "EAWidth" XXXXXXXXXXXXXXXXX (XX) X East_Asian_Width XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

XXXXX

XXXXXXXXXXX

XXXXXXXXXXXXXXXXXXXXXXXXXXX (NS XXX CJ) XXXX XXXXX LBClass XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX (ID) XXXXX

"KANA_NONSTARTERS() => LB_ID"

XXXXXXXXX

"IDEOGRAPHIC_ITERATION_MARKS() => LB_ID"

XXXXXXXXXXXXX U+3005 XXXXXXU+303B XXXXXU+309D XXXXXXXXXU+309E XXXXXXXX (XX)XU+30FD XXXXXXXXXU+30FE XXXXXXXX (XX)X

XXXXXXXXXXXXXX

"KANA_SMALL_LETTERS() => LB_ID"

"KANA_PROLONGED_SOUND_MARKS() => LB_ID"

XXXXXX XXXXXX U+3041 X, U+3043 X, U+3045 X, U+3047 X, U+3049 X, U+3063 X, U+3083 X, U+3085 X, U+3087 X, U+308E X, U+3095 X, U+3096 XX XXXXXX U+30A1 X, U+30A3 X, U+30A5 X, U+30A7 X, U+30A9 X, U+30C3 X, U+30E3 X, U+30E5 X, U+30E7 X, U+30EE X, U+30F5 X, U+30F6 XX XXXXXXX U+31F0 X - U+31FF XX XXXXXX (XXXX) U+FF67 X - U+FF6F XX

XXXXX U+30FC XXXXXU+FF70 XXXX (XXXX)X

XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX[JIS X 4051] 6.1.1X[JLREQ] 3.1.7 X [UAX14] XXXX

XXU+3095 X, U+3096 X, U+30F5 X, U+30F6 X XXXXXXXXXXXX

"MASU_MARK() => LB_ID"

U+303C XXXXX

XXXXXXXXXXXXXXXXX "XX" X "XX" XXXXXXXXXXXX

XXXXXXX [UAX #14] XXXXXXXX (NS) XXXXXXXX[JIS X 4051] X [JLREQ] XXXXXXX (13) X cl-19 (ID XXX) XXXXXXX

XXXXXX

XXXXXXXXXXXXXXXXXX (QU) XXXX

"BACKWARD_QUOTES() => LB_OP, FORWARD_QUOTES() => LB_CL"

XXXX (XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXX) XXXXXXXX 9 XXXXXXXXXXX (X X) XXXXXXX 9 XXXXXXX (X X) XXXXX

"FORWARD_QUOTES() => LB_OP, BACKWARD_QUOTES() => LB_CL"

XXXXX (XXXXXXXXXXXXXXXX) XXX9 XXXXXXX (X X) XXXXXXX9 XXXXXXXXXXX (X X) XXXXXXXXXX

"BACKWARD_GUILLEMETS() => LB_OP, FORWARD_GUILLEMETS() => LB_CL"

XXXXXXXXXXXXXXXXXXXXXXXXXXXX (X X) XXXXXXXXXXXXXX (X X) XXXXXXXXXX

"FORWARD_GUILLEMETS() => LB_OP, BACKWARD_GUILLEMETS() => LB_CL"

XXXXXXXXXXXXXXXXXXXXX (X X) XXXXXXXXXXXXXX (X X) XXXXXXXXXX

XXXXXXXXXXXXXXXXXXXXXXXXXXX9 XXXXXXXX XXXXXXX (X X X X) XXXXXXXXXXXXXXXXX

XXXX

"IDEOGRAPHIC_SPACE() => LB_BA"

U+3000 XXXXXXXXXXXXXXXXX XXXXXXXXXXXX

"IDEOGRAPHIC_SPACE() => LB_ID"

XXXXXXXXXXXXXXXX Unicode 6.2XXXXXXXXXXXXXXXX

"IDEOGRAPHIC_SPACE() => LB_SP"

XXXXXXXXXXXXXXXXXXXXXXXXX

East_Asian_Width XX

XXXXXXXXXXXXXXXXXXXXXXXXXXXX (A) X East_Asian_Width XXXXXXXXXXXXXXXXXXXXXX "EASTASIAN" XXXXXXXXXXXXX "EAWidth => [ AMBIGUOUS_"*"() => EA_N ]" XXXXXXXXXXXXXXXXXXXXXXXXXXX

"AMBIGUOUS_ALPHABETICS() => EA_N"

XXXXXXXXX East_Asian_Width XX N (XX) XXXXXXX

"AMBIGUOUS_CYRILLIC() => EA_N"

"AMBIGUOUS_GREEK() => EA_N"

"AMBIGUOUS_LATIN() => EA_N"

XX (A) XXXXXXXXXXXXXXXXXXXXXXXXXX (N) XXXXXXX

XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXUnicode XXXXXX (F) XXXXXXXXXXXXXX (Na) XXXXXXXXXXXXXXXXEAWidth XXXXXXXXXXXXXXXXXXXXXXXXXXX "EASTASIAN" XXXXXXXXXXXX

"QUESTIONABLE_NARROW_SIGNS() => EA_A"

U+00A2 XXXXXXU+00A3 XXXXXXU+00A5 XXX (XXXXXX)XU+00A6 XXXXU+00AC XXXU+00AF XXXXX

XXXXXX

"new" XXXXXXX "config" XXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXX Unicode/LineBreak/Defaults.pmX XXX Unicode/LineBreak/Defaults.pm.sample XXXXXXXX

XXXXXX

2012.06

XXXXXXX

XXXXXXXXXXXXXXXXXXXXXUnicode XX 6.3.0XXXXX

XXXXXXXXXXXXXX UAX14-C2 XXXXXXXXXXX