.\" -*- mode: troff; coding: utf-8 -*-
.\" Automatically generated by Pod::Man 5.01 (Pod::Simple 3.43)
.\"
.\" 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
..
.\" \*(C` and \*(C' are quotes in nroff, nothing in troff, for use with C<>.
.ie n \{\
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    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
.\" ========================================================================
.\"
.IX Title "KinoSearch1::Analysis::Stopalizer 3pm"
.TH KinoSearch1::Analysis::Stopalizer 3pm 2024-03-10 "perl v5.38.2" "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
KinoSearch1::Analysis::Stopalizer \- suppress a "stoplist" of common words
.SH SYNOPSIS
.IX Header "SYNOPSIS"
.Vb 6
\&    my $stopalizer = KinoSearch1::Analysis::Stopalizer\->new(
\&        language => \*(Aqfr\*(Aq,
\&    );
\&    my $polyanalyzer = KinoSearch1::Analysis::PolyAnalyzer\->new(
\&        analyzers => [ $lc_normalizer, $tokenizer, $stopalizer, $stemmer ],
\&    );
.Ve
.SH DESCRIPTION
.IX Header "DESCRIPTION"
A "stoplist" is collection of "stopwords": words which are common enough to be
of little value when determining search results.  For example, so many
documents in English contain "the", "if", and "maybe" that it may improve both
performance and relevance to block them.
.PP
.Vb 2
\&    # before
\&    @token_texts = (\*(Aqi\*(Aq, \*(Aqam\*(Aq, \*(Aqthe\*(Aq, \*(Aqwalrus\*(Aq);
\&    
\&    # after
\&    @token_texts = (\*(Aq\*(Aq,  \*(Aq\*(Aq,   \*(Aq\*(Aq,    \*(Aqwalrus\*(Aq);
.Ve
.SH CONSTRUCTOR
.IX Header "CONSTRUCTOR"
.SS new
.IX Subsection "new"
.Vb 3
\&    my $stopalizer = KinoSearch1::Analysis::Stopalizer\->new(
\&        language => \*(Aqde\*(Aq,
\&    );
\&    
\&    # or...
\&    my $stopalizer = KinoSearch1::Analysis::Stopalizer\->new(
\&        stoplist => \e%stoplist,
\&    );
.Ve
.PP
\&\fBnew()\fR takes two possible parameters, \f(CW\*(C`language\*(C'\fR and \f(CW\*(C`stoplist\*(C'\fR.  If
\&\f(CW\*(C`stoplist\*(C'\fR is supplied, it will be used, overriding the behavior indicated by
the value of \f(CW\*(C`language\*(C'\fR.
.IP \(bu 4
\&\fBstoplist\fR \- must be a hashref, with stopwords as the keys of the hash and
values set to 1.
.IP \(bu 4
\&\fBlanguage\fR \- must be the ISO code for a language.  Loads a default stoplist
supplied by Lingua::StopWords.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
Lingua::StopWords
.SH COPYRIGHT
.IX Header "COPYRIGHT"
Copyright 2005\-2010 Marvin Humphrey
.SH "LICENSE, DISCLAIMER, BUGS, etc."
.IX Header "LICENSE, DISCLAIMER, BUGS, etc."
See KinoSearch1 version 1.01.