.\" -*- 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 "GENPYT 1"
.TH GENPYT 1 2024-02-10 "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
genpyt \- generate the PINYIN lexicon
.SH SYNOPSIS
.IX Header "SYNOPSIS"
\&\fBgenpyt\fR \fIlexicon-file\fR \fIresult-file\fR \fIlog-file\fR \fIslm-file\fR
.SH DESCRIPTION
.IX Header "DESCRIPTION"
\&\fBgenpyt\fR is used to generate the PINYIN lexicon. 
It only works on zh_CN.UTF\-8 locale.
.SH ARGUMENTS
.IX Header "ARGUMENTS"
.IP \fIlexicon-file\fR 4
.IX Item "lexicon-file"
Specify a dictionary file. It should be a line-based text file in utf\-8 encoding
\&. Each line looks like:
.Sp
.Vb 1
\&   CCC  id  [pinyin\*(Aqpinyin\*(Aqpinyin]*
.Ve
.Sp
A default dictionary file can be found at \fI/usr/share/sunpinyin/dict.utf8\fR.
.IP \fIresult-file\fR 4
.IX Item "result-file"
The output binary PINYIN lexicon file. This lexicon contains a trie presenting the key tree of PINYIN. And all of the candidate words are sorted using the unigram in \fIslm-file\fR. This file can be used with sunpinyin input method engines.
.IP \fIlog-file\fR 4
.IX Item "log-file"
Specify the file to where the log goes. The \fIlog-file\fR can be seen as the human-readble presentation of the binary output file.
.IP \fIslm-file\fR 4
.IX Item "slm-file"
The language model from which the unigram information are retrieved. Typically, the \fIslm-file\fR is generated by \fBslmthread\fR.
.SH AUTHOR
.IX Header "AUTHOR"
Originally written by Phill.Zhang <phill.zhang@sun.com>.
Currently maintained by Kov.Chai <tchaikov@gmail.com>.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
\&\fBslmthread\fR(1).