Devil Killer Is Here MiNi Shell
MiNi SheLL

Current Path : /proc/thread-self/root/usr/local/man/man3/
Linux boscustweb5003.eigbox.net 5.4.91 #1 SMP Wed Jan 20 18:10:28 EST 2021 x86_64
Current File : //proc/thread-self/root/usr/local/man/man3/Lingua::StopWords.3
.\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sh \" Subsection heading
.br
.if t .Sp
.ne 5
.PP
\fB\\$1\fR
.PP
..
.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.  | will give a
.\" real vertical bar.  \*(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-|\(bv\*(Tr
.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\}
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.if \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.\"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.hy 0
.if n .na
.\"
.\" 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 "Lingua::StopWords 3"
.TH Lingua::StopWords 3 "2006-09-19" "perl v5.8.8" "User Contributed Perl Documentation"
.SH "NAME"
Lingua::StopWords \- Stop words for several languages
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 2
\&    use Lingua::StopWords qw( getStopWords );
\&    my $stopwords = getStopWords('en');
.Ve
.PP
.Vb 1
\&    my @words = qw( i am the walrus goo goo g'joob );
.Ve
.PP
.Vb 2
\&    # prints "walrus goo goo g'joob"
\&    print join ' ', grep { !$stopwords->{$_} } @words;
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
In keyword search, it is common practice to suppress a collection of
\&\*(L"stopwords\*(R": words such as \*(L"the\*(R", \*(L"and\*(R", \*(L"maybe\*(R", etc. which exist in in a
large number of documents and do not tell you anything important about any
document which contains them.  This module provides such \*(L"stoplists\*(R" in
several languages.
.Sh "Supported Languages"
.IX Subsection "Supported Languages"
.Vb 16
\&    |-----------------------------------------------------------|
\&    | Language   | ISO code | default encoding | also available |
\&    |-----------------------------------------------------------|
\&    | Danish     | da       | ISO-8859-1       | UTF-8          | 
\&    | Dutch      | nl       | ISO-8859-1       | UTF-8          | 
\&    | English    | en       | ISO-8859-1       | UTF-8          |
\&    | Finnish    | fi       | ISO-8859-1       | UTF-8          |
\&    | French     | fr       | ISO-8859-1       | UTF-8          |
\&    | German     | de       | ISO-8859-1       | UTF-8          | 
\&    | Italian    | it       | ISO-8859-1       | UTF-8          | 
\&    | Norwegian  | no       | ISO-8859-1       | UTF-8          | 
\&    | Portuguese | pt       | ISO-8859-1       | UTF-8          | 
\&    | Spanish    | es       | ISO-8859-1       | UTF-8          | 
\&    | Swedish    | sv       | ISO-8859-1       | UTF-8          | 
\&    | Russian    | ru       | KOI8-R           | UTF-8          | 
\&    |-----------------------------------------------------------|
.Ve
.SH "FUNCTIONS"
.IX Header "FUNCTIONS"
.Sh "getStopWords"
.IX Subsection "getStopWords"
.Vb 2
\&    my $stoplist      = getStopWords('en');
\&    my $utf8_stoplist = getStopWords('en', 'UTF-8');
.Ve
.PP
Retrieve a stoplist in the form of a hashref where the keys are all
stopwords and the values are all 1.
.PP
.Vb 5
\&    $stoplist = {
\&        and => 1,
\&        if  => 1,
\&        # ...
\&    };
.Ve
.PP
\&\fIgetStopWords()\fR expects 1\-2 arguments.  The first, which is required, is an \s-1ISO\s0
code representing a supported language.  If the \s-1ISO\s0 code cannot be found,
getStopWords returns undef.
.PP
The second argument should be '\s-1UTF\-8\s0' if you want the stopwords encoded in
\&\s-1UTF\-8\s0.  The \s-1UTF\-8\s0 flag will be turned on, so make sure you understand all the
implications of that.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
The stoplists supplied by this module were created as part of the Snowball
project (see <http://snowball.tartarus.org>,
Lingua::Stem::Snowball).
.PP
Lingua::EN::StopWords provides a different stoplist
for English.
.SH "AUTHOR"
.IX Header "AUTHOR"
Maintained by Marvin Humphrey <marvin at rectangular dot com>.
Original author Fabien Potencier, <fabpot at cpan dot org>.
.SH "COPYRIGHT AND LICENSE"
.IX Header "COPYRIGHT AND LICENSE"
Copyright 2004\-2006 Fabien Potencier, Marvin Humphrey
.PP
This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself, either Perl version 5.8.3 or,
at your option, any later version of Perl 5 you may have available.
Creat By MiNi SheLL
Email: devilkiller@gmail.com