.\" -*- 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::PolyAnalyzer 3pm"
.TH KinoSearch1::Analysis::PolyAnalyzer 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::PolyAnalyzer \- multiple analyzers in series
.SH SYNOPSIS
.IX Header "SYNOPSIS"
.Vb 3
\&    my $analyzer = KinoSearch1::Analysis::PolyAnalyzer\->new(
\&        language  => \*(Aqes\*(Aq,
\&    );
\&    
\&    # or...
\&    my $analyzer = KinoSearch1::Analysis::PolyAnalyzer\->new(
\&        analyzers => [
\&            $lc_normalizer,
\&            $custom_tokenizer,
\&            $snowball_stemmer,
\&        ],
\&    );
.Ve
.SH DESCRIPTION
.IX Header "DESCRIPTION"
A PolyAnalyzer is a series of Analyzers \-\- objects which inherit from
KinoSearch1::Analysis::Analyzer \-\- each of
which will be called upon to "analyze" text in turn.  You can either provide
the Analyzers yourself, or you can specify a supported language, in which case
a PolyAnalyzer consisting of an
LCNormalizer, a
Tokenizer, and a
Stemmer will be generated for you.
.PP
Supported languages:
.PP
.Vb 12
\&    en => English,
\&    da => Danish,
\&    de => German,
\&    es => Spanish,
\&    fi => Finnish,
\&    fr => French,
\&    it => Italian,
\&    nl => Dutch,
\&    no => Norwegian,
\&    pt => Portuguese,
\&    ru => Russian,
\&    sv => Swedish,
.Ve
.SH CONSTRUCTOR
.IX Header "CONSTRUCTOR"
.SS \fBnew()\fP
.IX Subsection "new()"
.Vb 3
\&    my $analyzer = KinoSearch1::Analysis::PolyAnalyzer\->new(
\&        language   => \*(Aqen\*(Aq,
\&    );
.Ve
.PP
Construct a PolyAnalyzer object.  If the parameter \f(CW\*(C`analyzers\*(C'\fR is specified,
it will override \f(CW\*(C`language\*(C'\fR and no attempt will be made to generate a default
set of Analyzers.
.IP \(bu 4
\&\fBlanguage\fR \- Must be an ISO code from the list of supported languages.
.IP \(bu 4
\&\fBanalyzers\fR \- Must be an arrayref.  Each element in the array must inherit
from KinoSearch1::Analysis::Analyzer.  The order of the analyzers matters.
Don't put a Stemmer before a Tokenizer (can't stem whole documents or
paragraphs \-\- just individual words), or a Stopalizer after a Stemmer (stemmed
words, e.g. "themselv", will not appear in a stoplist).  In general, the
sequence should be: normalize, tokenize, stopalize, stem.
.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.