.\" -*- 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::InvIndexer 3pm"
.TH KinoSearch1::InvIndexer 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::InvIndexer \- build inverted indexes
.SH SYNOPSIS
.IX Header "SYNOPSIS"
.Vb 2
\&    use KinoSearch1::InvIndexer;
\&    use KinoSearch1::Analysis::PolyAnalyzer;
\&
\&    my $analyzer
\&        = KinoSearch1::Analysis::PolyAnalyzer\->new( language => \*(Aqen\*(Aq );
\&
\&    my $invindexer = KinoSearch1::InvIndexer\->new(
\&        invindex => \*(Aq/path/to/invindex\*(Aq,
\&        create   => 1,
\&        analyzer => $analyzer,
\&    );
\&
\&    $invindexer\->spec_field( 
\&        name  => \*(Aqtitle\*(Aq 
\&        boost => 3,
\&    );
\&    $invindexer\->spec_field( name => \*(Aqbodytext\*(Aq );
\&
\&    while ( my ( $title, $bodytext ) = each %source_documents ) {
\&        my $doc = $invindexer\->new_doc($title);
\&
\&        $doc\->set_value( title    => $title );
\&        $doc\->set_value( bodytext => $bodytext );
\&
\&        $invindexer\->add_doc($doc);
\&    }
\&
\&    $invindexer\->finish;
.Ve
.SH DESCRIPTION
.IX Header "DESCRIPTION"
The InvIndexer class is KinoSearch1's primary tool for creating and
modifying inverted indexes, which may be searched using
KinoSearch1::Searcher.
.SH METHODS
.IX Header "METHODS"
.SS new
.IX Subsection "new"
.Vb 5
\&    my $invindexer = KinoSearch1::InvIndexer\->new(
\&        invindex => \*(Aq/path/to/invindex\*(Aq,  # required
\&        create   => 1,                    # default: 0
\&        analyzer => $analyzer,            # default: no\-op Analyzer
\&    );
.Ve
.PP
Create an InvIndexer object.
.IP \(bu 4
\&\fBinvindex\fR \- can be either a filepath, or an InvIndex subclass such as
KinoSearch1::Store::FSInvIndex or 
KinoSearch1::Store::RAMInvIndex.
.IP \(bu 4
\&\fBcreate\fR \- create a new invindex, clobbering an existing one if necessary.
.IP \(bu 4
\&\fBanalyzer\fR \- an object which subclasses KinoSearch1::Analysis::Analyzer,
such as a PolyAnalyzer.
.SS spec_field
.IX Subsection "spec_field"
.Vb 10
\&    $invindexer\->spec_field(
\&        name       => \*(Aqurl\*(Aq,      # required
\&        boost      => 1,          # default: 1,
\&        analyzer   => undef,      # default: analyzer spec\*(Aqd in new()
\&        indexed    => 0,          # default: 1
\&        analyzed   => 0,          # default: 1
\&        stored     => 1,          # default: 1
\&        compressed => 0,          # default: 0
\&        vectorized => 0,          # default: 1
\&    );
.Ve
.PP
Define a field.
.IP \(bu 4
\&\fBname\fR \- the field's name.
.IP \(bu 4
\&\fBboost\fR \- A multiplier which determines how much a field contributes
to a document's score.
.IP \(bu 4
\&\fBanalyzer\fR \- By default, all indexed fields are analyzed using the analyzer
that was supplied to \fBnew()\fR.  Supplying an alternate for a given field
overrides the primary analyzer.
.IP \(bu 4
\&\fBindexed\fR \- index the field, so that it can be searched later.
.IP \(bu 4
\&\fBanalyzed\fR \- analyze the field, using the relevant Analyzer.  Fields such as
"category" or "product_number" might be indexed but not analyzed.
.IP \(bu 4
\&\fBstored\fR \- store the field, so that it can be retrieved when the document
turns up in a search.
.IP \(bu 4
\&\fBcompressed\fR \- compress the stored field, using the zlib compression algorithm.
.IP \(bu 4
\&\fBvectorized\fR \- store the field's "term vectors", which are required by
KinoSearch1::Highlight::Highlighter for
excerpt selection and search term highlighting.
.SS new_doc
.IX Subsection "new_doc"
.Vb 1
\&    my $doc = $invindexer\->new_doc;
.Ve
.PP
Spawn an empty KinoSearch1::Document::Doc object,
primed to accept values for the fields spec'd by spec_field.
.SS add_doc
.IX Subsection "add_doc"
.Vb 1
\&    $invindexer\->add_doc($doc);
.Ve
.PP
Add a document to the invindex.
.SS add_invindexes
.IX Subsection "add_invindexes"
.Vb 6
\&    my $invindexer = KinoSearch1::InvIndexer\->new( 
\&        invindex => $invindex,
\&        analyzer => $analyzer,
\&    );
\&    $invindexer\->add_invindexes( $another_invindex, $yet_another_invindex );
\&    $invindexer\->finish;
.Ve
.PP
Absorb existing invindexes into this one.  May only be called once per
InvIndexer.  \fBadd_invindexes()\fR and \fBadd_doc()\fR cannot be called on the same
InvIndexer.
.SS delete_docs_by_term
.IX Subsection "delete_docs_by_term"
.Vb 2
\&    my $term = KinoSearch1::Index::Term\->new( \*(Aqid\*(Aq, $unique_id );
\&    $invindexer\->delete_docs_by_term($term);
.Ve
.PP
Mark any document which contains the supplied term as deleted, so that it will
be excluded from search results.  For more info, see
Deletions in
KinoSearch1::Docs::FileFormat.
.SS finish
.IX Subsection "finish"
.Vb 3
\&    $invindexer\->finish( 
\&        optimize => 1, # default: 0
\&    );
.Ve
.PP
Finish the invindex.  Invalidates the InvIndexer.  Takes one hash-style
parameter.
.IP \(bu 4
\&\fBoptimize\fR \- If optimize is set to 1, the invindex will be collapsed to its
most compact form, which will yield the fastest queries.
.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.