File Coverage

blib/lib/Unicode/Japanese.pm

Criterion	Covered	Total	%
statement	509	557	91.3
branch	333	502	66.3
condition	49	111	44.1
subroutine	64	64	100.0
pod	1	2	50.0
total	956	1236	77.3

# -----------------------------------------------------------------------------
# Unicode::Japanese
# Unicode::Japanese::PurePerl
# -----------------------------------------------------------------------------
# $Id: Japanese_stub.pm 41491 2008-02-15 07:21:13Z hio $
# -----------------------------------------------------------------------------
package Unicode::Japanese::PurePerl;
package Unicode::Japanese;

use strict;
use vars qw($VERSION $XS_VERSION $PurePerl $xs_loaderror);
$VERSION    = '0.51';
$XS_VERSION = $VERSION;
$VERSION    = eval $VERSION;

# `use bytes' and `use Encode' if we are on perl-5.8.0 or later.
if( $] >= 5.008 )
{
  my $evalerr;
  {
    local($SIG{__DIE__}) = 'DEFAULT';
    local($@);
    eval 'use bytes;use Encode;';
    $evalerr = $@;
  }
  $evalerr and CORE::die($evalerr);
}

# -----------------------------------------------------------------------------
# import
#
sub import
{
  my $pkg = shift;
  my ($callerpkg) = caller;
  my %exp =
  (
    '&unijp' => \&unijp,
  );
  my @na;
  my @add = (grep{$_ eq ':all'} @_) ? keys %exp : ();
  foreach(@_, @add)
  {
    $_ eq 'PurePerl' and $PurePerl=1, next;
    if( $exp{$_} || $exp{'&'.$_} )
    {
      no strict 'refs';
      (my $name = $_) =~ s/^\W//;
      my $obj = $exp{$_} || $exp{'&'.$_};
      *{$callerpkg.'::'.$name} = $obj;
    }elsif( $_ eq 'no_I18N_Japanese' )
    {
      $^H &= ~0x0f00_0000;
      package Unicode::Japanese::PurePerl;
      $^H &= ~0x0f00_0000;
      package Unicode::Japanese;
      next;
    }
    push(@na,$_);
  }
  if( @na )
  {
    #use Carp;
    #croak("invalid parameter (".join(',',@na).")");
  }
}

# -----------------------------------------------------------------------------
# DESTROY
#
sub DESTROY
{
}

# -----------------------------------------------------------------------------
# load_xs.
#   loading xs-subs.
#   this method is called from new (through new=>_init_table=>load_xs)
#
sub load_xs
{
  #print STDERR "load_xs\n";
  if( $PurePerl )
  {
    #print STDERR "PurePerl mode\n";
    $xs_loaderror = 'disabled';
    return;
  }
  #print STDERR "XS mode\n";

  my $use_xs;
  LoadXS:
  {

    #print STDERR "* * bootstrap...\n";
    eval q
    {
      use strict;
      require DynaLoader;
      use vars qw(@ISA);
      @ISA = qw(DynaLoader);
      local($SIG{__DIE__}) = 'DEFAULT';
      Unicode::Japanese->bootstrap($XS_VERSION);
    };
    #print STDERR "* * the trial has been done.\n";
    #undef @ISA;
    if( $@ )
    {
      #print STDERR "failed.\n";
      #print STDERR "$@\n";
      $use_xs = 0;
      $xs_loaderror = $@;
      undef $@;
      last LoadXS;
    }
    #print STDERR "succeeded.\n";
    $use_xs = 1;
    eval q
    {
      #print STDERR "overriding _s2u,_u2s\n";
      do_memmap();
      #print STDERR "memmap done\n";
      END{ do_memunmap(); }
      #print STDERR "binding xsubs has been done.\n";
    };
    if( $@ )
    {
      #print STDERR "error in the last part of operation to load XS.\n";
      $xs_loaderror = $@;
      CORE::die($@);
    }

    #print STDERR "done.\n";
  }

  if( $@ )
  {
    $xs_loaderror = $@;
    CORE::die("Cannot load Unicode::Japanese of neither XS nor PurePerl side\n$@");
  }
  if( !$use_xs )
  {
    #print STDERR "no xs.\n";
    eval q
    {
      sub do_memmap($){}
      sub do_memunmap($){}
    };
  }
  $xs_loaderror = '' if( !defined($xs_loaderror) );
  #print STDERR "load_xs done.\n";
}

# -----------------------------------------------------------------------------
# Unicode::Japanese->new();
# cache for char conversion.
# 2bytes.
#  JIS C 6226-1979  \e$@
#  JIS X 0208-1983  \e$B
#  JIS X 0208-1990  \e&@\e$B
#  JIS X 0212-1990  \e$(D
# 1byte.
#  JIS ROMAN  \e(J
#  JIS ROMAN  \e(H
#  ASCII      \e(B
#  JIS KANA   \e(I
# -----------------------------------------------------------------------------
# $unijp = Unicode::Japanese->new([$str,[$icode]]);
#
sub new
{
  my $pkg = shift;
  my $this = {};

  if( defined($pkg) )
  {
    bless $this, $pkg;
  $this->_init_table;
  }else
  {
    bless $this;
  $this->_init_table;
  }

  @_ and $this->set(@_);

  $this;
}


# -----------------------------------------------------------------------------
# _got_undefined_subroutine
#   die with message 'undefiend subroutine'.
#
sub _got_undefined_subroutine
{
  my $subname = pop;
  CORE::die "Undefined subroutine \&$subname got called.\n";
}

# -----------------------------------------------------------------------------
# AUTOLOAD
#   AUTOLOAD of Unicode::Japanese.
#   imports PurePerl methods.
#
AUTOLOAD
{
  # load pure perl subs.
  use vars qw($AUTOLOAD);

  #print "AUTOLOAD... $AUTOLOAD\n";

  if(!defined($Unicode::Japanese::xs_loaderror) )
  {
    Unicode::Japanese::PurePerl::_init_table();
    if( defined(&$AUTOLOAD) )
    {
      no strict 'refs';
      goto &$AUTOLOAD;
    }
  }

  my ($pkg, $subname) = do{
    local($1, $2);
    $AUTOLOAD =~ /^(.*)::(\w+)$/
  } or got_undefined_subroutine($AUTOLOAD);

  my $pppkg     = $pkg . '::PurePerl';
  my $ppsubname = $pkg . '::PurePerl::' . $subname;
  if( !defined(&$ppsubname) )
  {
    my $save = $@;
    my @BAK = @_;
    $pppkg->_loadsub($ppsubname);
    $@ = $save;
    @_ = @BAK;
  }

  my $sub = \&$ppsubname;
  {
    no strict  'refs';
    *$AUTOLOAD = $sub; # copy.
  }
  goto &$sub;
}

# -----------------------------------------------------------------------------
# Unicode::Japanese::PurePerl
# -----------------------------------------------------------------------------
package Unicode::Japanese::PurePerl;


use strict;
use vars qw(%CHARCODE %ESC %RE @CHARSET_LIST);

use vars qw(@J2S @S2J @S2E @E2S @U2T %T2U %S2U %U2S %SA2U1 %U2SA1 %SA2U2 %U2SA2);

%CHARCODE = (
	     UNDEF_EUC  =>     "\xa2\xae",
	     UNDEF_SJIS =>     "\x81\xac",
	     UNDEF_JIS  =>     "\xa2\xf7",
	     UNDEF_UNICODE  => "\x20\x20",
	 );

%ESC =  (
	 JIS_0208      => "\e\$B",
	 JIS_0212      => "\e\$(D",
	 ASC           => "\e\(B",
	 KANA          => "\e\(I",
	 E_JSKY_START  => "\e\$",
	 E_JSKY_END    => "\x0f",
	 );

%RE =
    (
     ASCII     => '[\x00-\x7f]',
     EUC_0212  => '\x8f[\xa1-\xfe][\xa1-\xfe]',
     EUC_C     => '[\xa1-\xfe][\xa1-\xfe]',
     EUC_KANA  => '\x8e[\xa1-\xdf]',
     JIS_0208  => '\e\$\@|\e\$B|\e&\@\e\$B',
     JIS_0212  => "\e" . '\$\(D',
     JIS_ASC   => "\e" . '\([BJ]',
     JIS_KANA  => "\e" . '\(I',
     SJIS_DBCS => '[\x81-\x9f\xe0-\xef\xfa-\xfc][\x40-\x7e\x80-\xfc]',
     SJIS_KANA => '[\xa1-\xdf]',
     UTF8      => '[\x00-\x7f]|[\xc0-\xdf][\x80-\xbf]|[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xf7][\x80-\xbf]{3}|[\xf8-\xfb][\x80-\xbf]{4}|[\xfc-\xfd][\x80-\xbf]{5}',
     BOM2_BE    => '\xfe\xff',
     BOM2_LE    => '\xff\xfe',
     BOM4_BE    => '\x00\x00\xfe\xff',
     BOM4_LE    => '\xff\xfe\x00\x00',
     UTF32_BE   => '\x00[\x00-\x10][\x00-\xff]{2}',
     UTF32_LE   => '[\x00-\xff]{2}[\x00-\x10]\x00',
     E_IMODEv1  => '\xf8[\x9f-\xfc]|\xf9[\x40-\x49\x50-\x52\x55-\x57\x5b-\x5e\x72-\x7e\x80-\xb0]',
     E_IMODEv2  => '\xf9[\xb1-\xfc]',
     E_IMODE    => '\xf8[\x9f-\xfc]|\xf9[\x40-\x49\x50-\x52\x55-\x57\x5b-\x5e\x72-\x7e\x80-\xfc]',
     E_JSKY1    => '[EFGOPQ]',
     E_JSKY1v1  => '[EFG]',
     E_JSKY1v2  => '[OPQ]',
     E_JSKY2    => '[\!-z]',
     E_DOTI     => '\xf0[\x40-\x7e\x80-\xfc]|\xf1[\x40-\x7e\x80-\xd6]|\xf2[\x40-\x7e\x80-\xab\xb0-\xd5\xdf-\xfc]|\xf3[\x40-\x7e\x80-\xfa]|\xf4[\x40-\x4f\x80\x84-\x8a\x8c-\x8e\x90\x94-\x96\x98-\x9c\xa0-\xa4\xa8-\xaf\xb4\xb5\xbc-\xbe\xc4\xc5\xc8\xcc]',
     E_JIS_AU   => '[\x75-\x7b][\x21-\x7e]',
     E_SJIS_AU  => '[\xf3\xf4\xf6\xf7][\x40-\xfc]',
     E_ICON_AU_START => '
304
     E_ICON_AU_END   => '">',
     E_JSKY_START => quotemeta($ESC{E_JSKY_START}),
     E_JSKY_END   => '(?:'.quotemeta($ESC{E_JSKY_END}).'|\z)',
     E_JSKYv1_UTF8 => '\xee(?:\x80[\x81-\xbf]|\x81[\x80-\x9a]|\x84[\x81-\xbf]|\x85[\x80-\x9a]|\x88[\x81-\xbf]|\x89[\x80-\x9a])',
     E_JSKYv2_UTF8 => '\xee(?:\x8c[\x81-\xbf]|\x8d[\x80-\x8d]|\x90[\x81-\xbf]|\x91[\x80-\x8c]|\x94[\x81-\xb7])',
     );

$]<5.005 and $RE{E_JSKY_END} =~ s/\\z/\$/;
$RE{E_JSKY}     =  $RE{E_JSKY_START}
  . $RE{E_JSKY1} . $RE{E_JSKY2} . '+'
  . $RE{E_JSKY_END};
$RE{E_JSKYv1}     =  $RE{E_JSKY_START}
  . $RE{E_JSKY1v1} . $RE{E_JSKY2} . '+'
  . $RE{E_JSKY_END};
$RE{E_JSKYv2}     =  $RE{E_JSKY_START}
  . $RE{E_JSKY1v2} . $RE{E_JSKY2} . '+'
  . $RE{E_JSKY_END};

@CHARSET_LIST = qw(
  utf8
  ucs2
  ucs4
  utf16

  sjis
  sjis-imode
  sjis-doti
  sjis-jsky
  sjis-icon-au
  cp932

  jis
  jis-jsky
  jis-au
  jis-icon-au

  euc
  euc-jp
  euc-icon-au

  utf8-jsky
  utf8-icon-au
  utf8-imode
);

use vars qw($s2u_table $u2s_table);
use vars qw($ei2u1 $ei2u2 $ed2u $ej2u1 $ej2u2 $ea2u1 $ea2u2 $ea2u1s $ea2u2s);
use vars qw($eu2i1 $eu2i2 $eu2d $eu2j1 $eu2j2 $eu2a1 $eu2a2 $eu2a1s $eu2a2s);

use vars qw(%_h2zNum %_z2hNum %_h2zAlpha %_z2hAlpha %_h2zSym %_z2hSym %_h2zKanaK %_z2hKanaK %_h2zKanaD %_z2hKanaD %_hira2kata %_kata2hira);



use vars qw($PID $FH $TABLE $HEADLEN $PROGLEN);

# -----------------------------------------------------------------------------
# AUTOLOAD
#   AUTOLOAD of Unicode::Japanese::PurePerl.
#   load PurePerl methods from embedded data.
#
AUTOLOAD
{
  use strict;
  use vars qw($AUTOLOAD);

  #print "AUTOLOAD... $AUTOLOAD\n";

  my $save = $@;
  my @BAK = @_;

  my ($pkg, $subname) = do{
    local($1, $2);
    $AUTOLOAD =~ /^(.*)::(\w+)$/
  } or got_undefined_subroutine($AUTOLOAD);

  $pkg->_loadsub($AUTOLOAD);

  $@ = $save;
  @_ = @BAK;
  goto &$AUTOLOAD;
}

sub _loadsub
{
  my $pkg = shift;
  my $fullsubname = shift;
  #print "subs..\n",join("\n",keys %$TABLE,'');
  use vars qw($AUTOLOAD);

  local($1, $2);
  my ($subpkg,$subname) = $fullsubname =~ /^(.*)::(\w+)$/
    or got_undefined_subroutine($fullsubname);

  # check
  if(!defined($TABLE->{$subname}{offset}))
    {
      _init_table();
      if( !defined($TABLE->{$subname}{offset}) )
      {
	if( $subname eq 'DESTROY' )
	{
	  my $sub = sub{};
	  {
	    no strict 'refs';
	    *$fullsubname = $sub;
	  }
	  return $sub;
	}

        CORE::die "Undefined subroutine \&$fullsubname got called.\n";
      }
    }
  if($TABLE->{$subname}{offset} == -1)
    {
      CORE::die "\&$fullsubname is getting loaded twice. There must be a problem in AUTOLOAD.\n";
    }

  _check_and_update_fh();
  seek($FH, $PROGLEN + $HEADLEN + $TABLE->{$subname}{offset}, 0)
    or die "Can't seek $subname. [$!]\n";

  my $sub;
  read($FH, $sub, $TABLE->{$subname}{'length'})
    or die "Can't read $subname. [$!]\n";

  if( $]>=5.008 )
  {
    $sub = 'use bytes;'.$sub;
  }

  CORE::eval(($sub=~/(.*)/s)[0]);
  if ($@)
    {
      CORE::die $@;
    }
  $DB::sub = $fullsubname; # Now debugger knows where we are.

  # evaled
  $TABLE->{$subname}{offset} = -1;

}

# -----------------------------------------------------------------------------
# Unicode::Japanese::PurePerl->new()
#
sub new
{
  goto &Unicode::Japanese::new;
}

# -----------------------------------------------------------------------------
# DESTROY
#
sub DESTROY
{
}

# -----------------------------------------------------------------------------
# gensym
#
sub gensym {
  package Unicode::Japanese::Symbol;
  no strict;
  $genpkg = "Unicode::Japanese::Symbol::";
  $genseq = 0;
  my $name = "GEN" . $genseq++;
  my $ref = \*{$genpkg . $name};
  delete $$genpkg{$name};
  $ref;
}

sub _check_and_update_fh {
  _open_fh() if not ($PID == $$);
}
sub _open_fh {
  my $file = "Unicode/Japanese.pm";
  $PID = $$;
  OPEN:
  {
    if( $INC{$file} )
    {
      open($FH,$INC{$file}) || CORE::die("could not open file [$INC{$file}] for input : $!");
      last OPEN;
    }
    foreach my $path (@INC)
      {
        my $mypath = $path;
        $mypath =~ s#/$##;
        if (-f "$mypath/$file")
          {
            open($FH,"$mypath/$file") || CORE::die("could not open file [$INC{$file}] for input : $!");
            last OPEN;
          }
      }
    CORE::die "Can't find Japanese.pm in \@INC\n";
  }
  binmode($FH);
}

# -----------------------------------------------------------------------------
# _init_table
#
sub _init_table {

  if(!defined($HEADLEN))
    {
      $FH = gensym;

      _open_fh();

      local($/) = "\n";
      my $line;
      while(defined($line = <$FH>))
	{
	  last if($line =~ m/^__DATA__/);
	}
      $PROGLEN = tell($FH);

      read($FH, $HEADLEN, 4)
	or die "Can't read the table. [$!]\n";
      $HEADLEN = unpack('N', $HEADLEN);
      read($FH, $TABLE, $HEADLEN)
	or die "Can't seek the table. [$!]\n";
      $TABLE =~ /(.*)/s;
      $TABLE = eval(($TABLE=~/(.*)/s)[0]);
      if($@)
	{
	  die "Internal Error. [$@]\n";
	}
      if(!defined($TABLE))
	{
	  die "Internal Error.\n";
	}
      $HEADLEN += 4;

      # load xs.
      Unicode::Japanese::load_xs();
    }
}

# -----------------------------------------------------------------------------
# _getFile
#   load embedded file data.
#
sub _getFile {
  my $this = shift;

  my $file = shift;

  exists($TABLE->{$file})
    or die "no such file [$file]\n";

  _check_and_update_fh();
  #my $offset16 = $TABLE->{$file}{offset} % 16;
  #print STDERR "_getFile($file, $TABLE->{$file}{offset}, $TABLE->{$file}{'length'}, $offset16)\n";
  seek($FH, $PROGLEN + $HEADLEN + $TABLE->{$file}{offset}, 0)
    or die "Can't seek $file. [$!]\n";

  my $data;
  read($FH, $data, $TABLE->{$file}{'length'})
    or die "Can't read $file. [$!]\n";

  $data;
}

# -----------------------------------------------------------------------------
# use_I18N_Japanese
#   copied from I18N::Japanese in jperl-5.5.3
#
sub use_I18N_Japanese
{
  shift;
  if( @_ )
  {
    my $bits = 0;
    foreach( @_ )
    {
      $bits |= 0x1000000 if $_ eq 're';
      $bits |= 0x2000000 if $_ eq 'tr';
      $bits |= 0x4000000 if $_ eq 'format';
      $bits |= 0x8000000 if $_ eq 'string';
    }
    $^H |= $bits;
  }else
  {
    $^H |= 0x0f00_0000;
  }
}

# -----------------------------------------------------------------------------
# no_I18N_Japanese
#   copied from I18N::Japanese in jperl-5.5.3
#
sub no_I18N_Japanese
{
  shift;
  if( @_ )
  {
    my $bits = 0;
    foreach( @_ )
    {
      $bits |= 0x1000000 if $_ eq 're';
      $bits |= 0x2000000 if $_ eq 'tr';
      $bits |= 0x4000000 if $_ eq 'format';
      $bits |= 0x8000000 if $_ eq 'string';
    }
    $^H &= ~$bits;
  }else
  {
    $^H &= ~0x0f00_0000;
  }
}

1;

=encoding utf-8

=head1 NAME

Unicode::Japanese - Convert encoding of japanese text


=head1 SYNOPSIS

 use Unicode::Japanese;
 use Unicode::Japanese qw(unijp);

 # convert utf8 -> sjis

 print Unicode::Japanese->new($str)->sjis;
 print unijp($str)->sjis; # same as above.

 # convert sjis -> utf8

 print Unicode::Japanese->new($str,'sjis')->get;

 # convert sjis (imode_EMOJI) -> utf8

 print Unicode::Japanese->new($str,'sjis-imode')->get;

 # convert zenkaku (utf8) -> hankaku (utf8)

 print Unicode::Japanese->new($str)->z2h->get;

=head1 DESCRIPTION

The Unicode::Japanese module converts encoding of japanese text from one
encoding to another.


=head2 FEATURES

=over 2

=item *



An instance of Unicode::Japanese internally holds a string in UTF-8.


=item *



This module is implemented in two ways: XS and pure perl. If efficiency is
important for you, you should build and install the XS module. If you don't want
to, or if you can't build the XS module, you may use the pure perl module
instead. In that case, only you have to do is to copy Japanese.pm into somewhere
in @INC.


=item *



This module can convert characters from zenkaku (full-width) form to hankaku
(half-width) form, and vice versa. Conversion between hiragana (one of two sets
of japanese phonetical alphabet) and katakana (another set of japanese
phonetical alphabet) is also supported.


=item *



This module has mapping tables for emoji (graphic characters) defined by various
japanese mobile phones; DoCoMo i-mode, ASTEL dot-i and J-PHONE J-Sky. Those
letters are mapped on Unicode Private Use Area so unicode strings it outputs are
still valid even if they contain emoji, and you can safely pass them to other
software that can handle Unicode.


=item *



This module can map some emoji from one set to another. Different mobile phones
define different sets of emoji, so mapping each other is not always
possible. But since some emoji exist in two or more sets with similar
appearance, this module considers those emoji to be the same.


=item *



This module uses the mapping table for MS-CP932 instead of the standard
Shift_JIS. The Shift_JIS encoding used by MS-Windows (MS-SJIS/MS-CP932) slightly
differs from the standard.


=item *



When the module converts strings from Unicode to Shift_JIS, EUC-JP or
ISO-2022-JP, unicode letters which can't be represented in those encodings will
be encoded in "&#dddd;" form (decimal character reference). Note, however, that
letters in Unicode Private Use Area will be replaced with '?' mark ('QUESTION
MARK'; U+003F) instead of being encoded. In addition, encoding to character sets
for mobile phones makes every unrepresentable letters being '?' mark.


=item *



On perl-5.8.0 or later, this module handles the UTF-8 flag: the method utf8()
returns UTF-8 I string, and the method getu() returns UTF-8 I
string.


Currently the method get() returns UTF-8 I string but this behavior may be
changed in the future.


Methods like sjis(), jis(), utf8(), and such like return I string. new(),
set(), getcode() methods just ignore the UTF-8 flag of strings they take.


=back

=head1 REQUIREMENT

=over 4

=item *



perl 5.10.x, 5.8.x, etc. (5.004 and later)


=item *



(optional)
C Compiler.
This module supports both XS and Pure Perl.
If you have no C Compilers,
Unicode::Japanese will be installed as Pure Perl module.


=item *



(optional)
Test.pm and Test::More for testing.


=back

No other modules are required at run time.


=head1 METHODS

=over 4

=item $s = Unicode::Japanese->new($str [, $icode [, $encode]])

Create a new instance of Unicode::Japanese.


Any given parameters will be internally passed to the method L().


=item $s = unijp($str [, $icode [, $encode]])

Same as Unicode::Jananese->new(...).


=item $s->set($str [, $icode [, $encode]])
X

=over 2

=item $str: string

=item $icode: optional character encoding (default: 'utf8')

=item $encode: optional binary encoding (default: no binary encodings are assumed)

=back

Store a string into the instance.


Possible character encodings are:


 auto
 utf8 ucs2 ucs4
 utf16-be utf16-le utf16
 utf32-be utf32-le utf32
 sjis cp932 euc euc-jp jis
 sjis-imode sjis-imode1 sjis-imode2
 utf8-imode utf8-imode1 utf8-imode2
 sjis-doti sjis-doti1
 sjis-jsky sjis-jsky1 sjis-jsky2
 jis-jsky  jis-jsky1  jis-jsky2
 utf8-jsky utf8-jsky1 utf8-jsky2
 sjis-au sjis-au1 sjis-au2
 jis-au  jis-au1  jis-au2
 sjis-icon-au sjis-icon-au1 sjis-icon-au2
 euc-icon-au  euc-icon-au1  euc-icon-au2
 jis-icon-au  jis-icon-au1  jis-icon-au2
 utf8-icon-au utf8-icon-au1 utf8-icon-au2
 ascii binary

(see also L.)


If you want the Unicode::Japanese detect the character encoding of string, you
must explicitly specify 'auto' as the second argument. In that case, the given
string will be passed to the method getcode() to guess the encoding.


For binary encodings, only 'base64' is currently supported. If you specify
'base64' as the third argument, the given string will be decoded using Base64
decoder.


Specify 'binary' as the second argument if you want your string to be stored
without modification.


When you specify 'sjis-imode' or 'sjis-doti' as the character encoding, any
occurences of '&#dddd;' (decimal character reference) in the string will be
interpreted and decoded as code point of emoji, just like emoji implanted into
the string in binary form.


Since encoded forms of strings in various encodings are not clearly distinctive
to each other, it is not always certainly possible to detect what encoding is
used for a given string.


When a given string is possibly interpreted as both Shift_JIS and UTF-8 string,
this module considers such a string to be encoded in Shift_JIS. And if the
encoding is not distinguishable between 'sjis-au' and 'sjis-doti', this module
considers it 'sjis-au'.


=item $str = $s->get

=over 2

=item $str: string (UTF-8)

=back

Get the internal string in UTF-8.


This method currently returns a byte string (whose UTF-8 flag is turned off),
but this behavior may be changed in the future.


If you absolutely want a byte string, you should use the method utf8()
instead. And if you want a character string (whose UTF-8 flag is turned on), you
have to use the method getu().


=item $str = $s->getu

=over 2

=item $str: string (UTF-8)

=back

Get the internal string in UTF-8.


On perl-5.8.0 or later, this method returns a character string with its UTF-8
flag turned on.


=item $code = $s->getcode($str)

=over 2

=item $str: string

=item $code: name of character encoding

=back

Detect the character encoding of given string.


Note that this method, exceptionaly, doesn't deal with the internal string of an
instance.


To guess the encoding, the following algorithm is used:


(For pure perl implementation)


=over 4

=item 1



If the string has an UTF-32 BOM, its encoding is 'utf32'.


=item 2



If it has an UTF-16 BOM, its encoding is 'utf16'.


=item 3



If it is valid for UTF-32BE, its encoding is 'utf32-be'.


=item 4



If it is valid for UTF-32LE, its encoding is 'utf32-le'.


=item 5



If it contains no ESC characters or bytes whose eighth bit is on, its encoding
is 'ascii'. Every ASCII control characters (0x00-0x1F and 0x7F) except ESC
(0x1B) are considered to be in the range of 'ascii'.


=item 6



If it contains escape sequences of ISO-2022-JP, its encoding is 'jis'.


=item 7



If it contains any emoji defined for J-PHONE, its encoding is 'sjis-jsky'.


=item 8



If it is valid for EUC-JP, its encoding is 'euc'.


=item 9



If it is valid for Shift_JIS, its encoding is 'sjis'.


=item 10



If it contains any emoji defined for au, and everything else is valid for
Shift_JIS, its encoding is 'sjis-au'.


=item 11



If it contains any emoji defined for i-mode, and everything else is valid for
Shift_JIS, its encoding is 'sjis-imode'.


=item 12



If it contains any emoji defined for dot-i, and everything else is valid for
Shift_JIS, its encoding is 'sjis-doti'.


=item 13



If it is valid for UTF-8, its encoding is 'utf8'.


=item 14



If no conditions above are fulfilled, its encoding is 'unknown'.


=back

(For XS implementation)


=over 4

=item 1



If the string has an UTF-32 BOM, its encoding is 'utf32'.


=item 2



If it has an UTF-16 BOM, its encoding is 'utf16'.


=item 3



Find all possible encodings that might have been applied to the string from the
following:


ascii / euc / sjis / jis / utf8 / utf32-be / utf32-le / sjis-jsky /
sjis-imode / sjis-au / sjis-doti


=item 4



If any encodings have been found possible, this module picks out one encoding
having the highest priority among them. The priority order is as follows:


utf32-be / utf32-le / ascii / jis / euc / sjis / sjis-jsky / sjis-imode /
sjis-au / sjis-doti / utf8


=item 5



If no conditions above are fulfilled, its encoding is 'unknown'.


=back

Pay attention to the following pitfalls in the above algorithm:


=over 2

=item *



UTF-8 strings might be accidentally considered to be encoded in Shift_JIS.


=item *



UCS-2 strings (sequence of raw UCS-2 letters in big-endian; each letters has
always 2 bytes) can't be detected because they look like nothing but sequences
of random bytes whose length is an even number.


=item *



UTF-16 strings must have BOM to be detected.


=item *



Emoji are only be recognized if they are implanted into the string in binary
form. If they are described in '&#dddd;' form, they aren't considered to be
emoji.


=back

Since the XS and pure perl implementations use different algorithms to guess
encoding, they may guess differently for the same string. Especially, the pure
perl implementation finds Shift_JIS strings containing ESC character (0x1B) to
be actually encoded in Shift_JIS but XS implementation doesn't. This is because
such strings can hardly be distinguished from 'sjis-jsky'. In addition, EUC-JP
strings containing ESC character are also rejected for the same reason.


=item $code = $s->getcodelist($str)

=over 2

=item $str: string

=item $code: name of character encodings

=back

Detect the character encoding of given string.


Unlike the method getcode(), getcodelist() returns a list of possible encodings.


=item $str = $s->conv($ocode, $encode)

=over 2

=item $ocode: character encoding (possible encodings are:)

 utf8 ucs2 ucs4 utf16
 sjis cp932 euc euc-jp jis
 sjis-imode sjis-imode1 sjis-imode2
 utf8-imode utf8-imode1 utf8-imode2
 sjis-doti sjis-doti1
 sjis-jsky sjis-jsky1 sjis-jsky2
 jis-jsky  jis-jsky1  jis-jsky2
 utf8-jsky utf8-jsky1 utf8-jsky2
 sjis-au sjis-au1 sjis-au2
 jis-au  jis-au1  jis-au2
 sjis-icon-au sjis-icon-au1 sjis-icon-au2
 euc-icon-au  euc-icon-au1  euc-icon-au2
 jis-icon-au  jis-icon-au1  jis-icon-au2
 utf8-icon-au utf8-icon-au1 utf8-icon-au2
 binary

(see also L.)


Some encodings for mobile phones have a trailing digit like 'sjis-au2'. Those
digits represent the version number of encodings. Such encodings have a variant
with no trailing digits, like 'sjis-au', which is the same as the latest version
among its variants.


=item $encode: optional binary encoding

=item $str: string

=back

Get the internal string of instance with encoding it using a given character
encoding method.


If you want the resulting string to be encoded in Base64, specify 'base64' as
the second argument.


On perl-5.8.0 or later, the UTF-8 flag of resulting string is turned off even if
you specify 'utf8' to the first argument.


=item $s->tag2bin

Interpret decimal character references (&#dddd;) in the instance, and replaces
them with single characters they represent.


=item $s->z2h

Replace zenkaku (full-width) letters in the instance with hankaku (half-width)
letters.


=item $s->h2z

Replace hankaku (half-width) letters in the instance with zenkaku (full-width)
letters.


=item $s->hira2kata

Replace any hiragana in the instance with katakana.


=item $s->kata2hira

Replace any katakana in the instance with hiragana.


=item $str = $s->jis

$str: byte string in ISO-2022-JP


Get the internal string of instance with encoding it in ISO-2022-JP.


=item $str = $s->euc

$str: byte string in EUC-JP


Get the internal string of instance with encoding it in EUC-JP.


=item $str = $s->utf8

$str: byte string in UTF-8


Get the internal UTF-8 string of instance.


On perl-5.8.0 or later, the UTF-8 flag of resulting string is turned off.


=item $str = $s->ucs2

$str: byte string in UCS-2


Get the internal string of instance as a sequence of raw UCS-2 letters in
big-endian. Note that this is different from UTF-16BE as raw UCS-2 sequence has
no concept of surrogate pair.


=item $str = $s->ucs4

$str: byte string in UCS-4


Get the internal string of instance as a sequence of raw UCS-4 letters in
big-endian. This is practically the same as UTF-32BE.


=item $str = $s->utf16

$str: byte string in UTF-16


Get the insternal string of instance with encoding it in UTF-16 in big-endian
with no BOM prepended.


=item $str = $s->sjis

$str: byte string in Shift_JIS


Get the internal string of instance with encoding it in Shift_JIS (MS-SJIS /
MS-CP932).


=item $str = $s->sjis_imode

$str: byte string in 'sjis-imode'


Get the internal string of instance with encoding it in 'sjis-imode'.


=item $str = $s->sjis_imode1

$str: byte string in 'sjis-imode1'


Get the internal string of instance with encoding it in 'sjis-imode1'.


=item $str = $s->sjis_imode2

$str: byte string in 'sjis-imode2'


Get the internal string of instance with encoding it in 'sjis-imode2'.


=item $str = $s->sjis_doti

$str: byte string in 'sjis-doti'


Get the internal string of instance with encoding it in 'sjis-doti'.


=item $str = $s->sjis_jsky

$str: byte string in 'sjis-jsky'


Get the internal string of instance with encoding it in 'sjis-jsky'.


=item $str = $s->sjis_jsky1

$str: byte string in 'sjis-jsky1'


Get the internal string of instance with encoding it in 'sjis-jsky1'.


=item $str = $s->sjis_jsky

$str: byte string in 'sjis-jsky'


Get the internal string of instance with encoding it in 'sjis-jsky'.


=item $str = $s->sjis_icon_au

$str: byte string in 'sjis-icon-au'


Get the internal string of instance with encoding it in 'sjis-icon-au'.


=item $str_arrayref = $s->strcut($len)

=over 2

=item $len: maximum length of each chunks (in number of
full-width characters)

=item $str_arrayref: reference to array of strings

=back

Split the internal string of instance into chunks of a given length.


On perl-5.8.0 or later, UTF-8 flags of each chunks are turned on.


=item $len = $s->strlen

$len: character width of the internal string


Calculate the character width of the internal string. Half-width characters have
width of one unit, and full-width characters have width of two units.


=item $s->join_csv(@values);

@values: array of strings


Build a line of CSV from the arguments, and store it into the instance. The
resulting line has a trailing line break ("\n").


=item @values = $s->split_csv;

@values: array of strings


Parse a line of CSV in the instance and return each columns. The line will be
chomp()ed before getting parsed.


If the internal string was decoded from 'binary' encoding (see methods new() and
set()), the UTF-8 flags of the resulting array of strings are turned
off. Otherwise the flags are turned on.


=back

=head1 SUPPORTED ENCODINGS

 +---------------+----+-----+-------+
 |encoding       | in | out | guess |
 +---------------+----+-----+-------+
 |auto           : OK : --  | ----- |
 +---------------+----+-----+-------+
 |utf8           : OK : OK  | OK    |
 |ucs2           : OK : OK  | ----- |
 |ucs4           : OK : OK  | ----- |
 |utf16-be       : OK : --  | ----- |
 |utf16-le       : OK : --  | ----- |
 |utf16          : OK : OK  | OK(#) |
 |utf32-be       : OK : --  | OK    |
 |utf32-le       : OK : --  | OK    |
 |utf32          : OK : --  | OK(#) |
 +---------------+----+-----+-------+
 |sjis           : OK : OK  | OK    |
 |cp932          : OK : OK  | ----- |
 |euc            : OK : OK  | OK    |
 |euc-jp         : OK : OK  | ----- |
 |jis            : OK : OK  | OK    |
 +---------------+----+-----+-------+
 |sjis-imode     : OK : OK  | OK    |
 |sjis-imode1    : OK : OK  | ----- |
 |sjis-imode2    : OK : OK  | ----- |
 |utf8-imode     : OK : OK  | ----- |
 |utf8-imode1    : OK : OK  | ----- |
 |utf8-imode2    : OK : OK  | ----- |
 +---------------+----+-----+-------+
 |sjis-doti      : OK : OK  | OK    |
 |sjis-doti1     : OK : OK  | ----- |
 +---------------+----+-----+-------+
 |sjis-jsky      : OK : OK  | OK    |
 |sjis-jsky1     : OK : OK  | ----- |
 |sjis-jsky2     : OK : OK  | ----- |
 |jis-jsky       : OK : OK  | ----- |
 |jis-jsky1      : OK : OK  | ----- |
 |jis-jsky2      : OK : OK  | ----- |
 |utf8-jsky      : OK : OK  | ----- |
 |utf8-jsky1     : OK : OK  | ----- |
 |utf8-jsky2     : OK : OK  | ----- |
 +---------------+----+-----+-------+
 |sjis-au        : OK : OK  | OK    |
 |sjis-au1       : OK : OK  | ----- |
 |sjis-au2       : OK : OK  | ----- |
 |jis-au         : OK : OK  | ----- |
 |jis-au1        : OK : OK  | ----- |
 |jis-au2        : OK : OK  | ----- |
 |sjis-icon-au   : OK : OK  | ----- |
 |sjis-icon-au1  : OK : OK  | ----- |
 |sjis-icon-au2  : OK : OK  | ----- |
 |euc-icon-au    : OK : OK  | ----- |
 |euc-icon-au1   : OK : OK  | ----- |
 |euc-icon-au2   : OK : OK  | ----- |
 |jis-icon-au    : OK : OK  | ----- |
 |jis-icon-au1   : OK : OK  | ----- |
 |jis-icon-au2   : OK : OK  | ----- |
 |utf8-icon-au   : OK : OK  | ----- |
 |utf8-icon-au1  : OK : OK  | ----- |
 |utf8-icon-au2  : OK : OK  | ----- |
 +---------------+----+-----+-------+
 |ascii          : OK : --  | OK    |
 |binary         : OK : OK  | ----- |
 +---------------+----+-----+-------+
 (#): guessed when it has bom.

=head2 GUESSING ORDER

 1.  utf32 (#)
 2.  utf16 (#)
 3.  utf32-be
 4.  utf32-le
 5.  ascii
 6.  jis
 7.  sjis-jsky (pp)
 8.  euc
 9.  sjis
 10. sjis-jsky (xs)
 11. sjis-au
 12. sjis-imode
 13. sjis-doti
 14. utf8
 15. unknown

=head1 DESCRIPTION OF UNICODE MAPPING

Transcoding between Unicode encodings and other ones is performed as below:


=over 2

=item Shift_JIS

This module uses the mapping table of MS-CP932.


L<< ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP932.TXT >>


When the module tries to convert Unicode string to Shift_JIS, it represents most
letters which isn't available in Shift_JIS as decimal character reference
('&#dddd;'). There is one exception to this: every graphic characters for mobile
phones are replaced with '?' mark.


For variants of Shift_JIS defined for mobile phones, every unrepresentable
characters are replaced with '?' mark unlike the plain Shift_JIS.


=item EUC-JP/ISO-2022-JP

This module doesn't directly convert Unicode string from/to EUC-JP or
ISO-2022-JP: it once converts from/to Shift_JIS and then do the rest
translation. So characters which aren't available in the Shift_JIS can not be
properly translated.


=item DoCoMo i-mode

This module maps emoji in the range of F800 - F9FF to U+0FF800 - U+0FF9FF.


=item ASTEL dot-i

This module maps emoji in the range of F000 - F4FF to U+0FF000 - U+0FF4FF.


=item J-PHONE J-SKY

The encoding method defined by J-SKY is as follows: first an escape sequence
"\e\$" comes to indicate the beginning of emoji, then the first byte of an emoji
comes next, then the second bytes of at least one emoji comes next, then "\x0f"
comes last to indicate the end of emoji. If a string contains a series of emoji
whose first bytes are identical, such sequence can be compressed by cascading
second bytes of them to the single first byte.


This module considers a pair of those first and second bytes to be one letter,
and map them from 4500 - 47FF to U+0FFB00 - U+0FFDFF.


When the module encodes J-SKY emoji, it performs the compression automatically.


=item AU

This module maps AU emoji to U+0FF500 - U+0FF6FF.


=back

=head1 PurePerl mode

   use Unicode::Japanese qw(PurePerl);

If you want to explicitly take the pure perl implementation, pass
C<'PurePerl'> to the argument of the C statement.


=head1 BUGS

Please report bugs and requests to C or
L. If you
report them to the web interface, any progress to your report will be
automatically sent back to you.


=over 2

=item *



This module doesn't directly convert Unicode string from/to EUC-JP or
ISO-2022-JP: it once converts from/to Shift_JIS and then do the rest
translation. So characters which aren't available in the Shift_JIS can not be
properly translated.


=item *



The XS implementation of getcode() fails to detect the encoding when the given
string contains \e while its encoding is EUC-JP or Shift_JIS.


=item *



Japanese.pm is composed of textual perl script and binary character conversion
table. If you transfer it on FTP using ASCII mode, the file will collapse.


=back

=head1 SUPPORT

You can find documentation for this module with the perldoc command.


    perldoc Unicode::Japanese

You can find more information at:


=over 4

=item * AnnoCPAN: Annotated CPAN documentation

L


=item * CPAN Ratings

L


=item * RT: CPAN's request tracker

L


=item * Search CPAN

L


=back

=head1 CREDITS

Thanks very much to:


NAKAYAMA Nao


SUGIURA Tatsuki & Debian JP Project


=head1 COPYRIGHT & LICENSE

Copyright 2001-2008
SANO Taku (SAWATARI Mikage) and YAMASHINA Hio,
all rights reserved.


This program is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.



=cut



__DATA__