.\" Automatically generated by Pod::Man 2.27 (Pod::Simple 3.28)
.\"
.\" 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
..
.\" 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.  \*(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-
.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" ''
.    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 turned on, 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
.\"
.\" 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 "MAKE-LINGUA-IDENTIFY-LANGUAGE 1p"
.TH MAKE-LINGUA-IDENTIFY-LANGUAGE 1p "2012-01-02" "perl v5.18.1" "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"
make\-lingua\-identify\-language \- creates language modules for Lingua::Identify
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 1
\&  make\-lingua\-identify\-language Language\-Tag Language\-Name file1 [file2 ...]
.Ve
.PP
or
.PP
.Vb 1
\&  make\-lingua\-identify\-language \-d TAG1\-LANGUAGE1/ [TAG2\-LANGUAGE2/ ...]
.Ve
.PP
or
.PP
.Vb 1
\&  make\-lingua\-identify
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Creates language modules to be used by Lingua::Identify.
.PP
After creating the modules, you still have to install them.
.PP
Please note that this script is still at an early stage. Please do not even
look at the code...
.PP
Without parameters, make-lingua-identify-language assumes mode \-d and goes
through all the directories in the current one. This is useful to be used in a
directory where you something like this:
.PP
.Vb 8
\&  .
\&  |\-\- en\-english
\&  |   \`\-\- english.txt
\&  |\-\- fr\-french
\&  |   \`\-\- french1.txt
\&  |   \`\-\- french2.txt
\&  \`\-\- pt\-portuguese
\&      \`\-\- portuguese.txt
.Ve
.SS "\s-1OPTIONS\s0"
.IX Subsection "OPTIONS"
.SS "\-d"
.IX Subsection "-d"
Directory mode. Each parameter passed should be a directory whose name
must be of the form tag-name (e.g., en\-english/ ). Each of the
directories passed should contain text files that can be used to train
Lingua::Identify.
.SS "\-D"
.IX Subsection "-D"
Debug mode. Only for development.
.SS "\-h"
.IX Subsection "-h"
Display help and exit.
.SS "\-v"
.IX Subsection "-v"
Show version and exit.
.SS "\-verbose"
.IX Subsection "-verbose"
Verbose mode.
.ie n .SS "\-locale=""<locale>"""
.el .SS "\-locale=\f(CW<locale>\fP"
.IX Subsection "-locale=<locale>"
Set a specific locale. This way your text will be all lowercased before analysed.
.SH "META.yml"
.IX Header "META.yml"
\&\f(CW\*(C`META.yml\*(C'\fR files are not parsed as other files, they are ignored.
.PP
In directory mode (\f(CW\*(C`\-d\*(C'\fR switch), \f(CW\*(C`META.yml\*(C'\fR files are checked for
info on languages codes and sets.
.PP
Here's a simple \f(CW\*(C`META.yml\*(C'\fR for you to put in your directories:
.PP
.Vb 4
\&  two_letter_code:   pt
\&  three_letter_code: por
\&  sets:
\&    spoken_in_portugal
.Ve
.PP
With that, the language will be identified with the two letter code
\&\*(L"pt\*(R" or the three letter code \*(L"por\*(R"; it will also be in the set
\&\*(L":spoken_in_portugal\*(R".
.SH "CONTRIBUTING WITH NEW LANGUAGES"
.IX Header "CONTRIBUTING WITH NEW LANGUAGES"
Please do not contribute with modules you made yourself. It's easier
to contribute with unprocessed text, because that allows for new
versions of Lingua::Identify not having to drop languages down in case
I can't contact you by that time.
.PP
Use \fImake-lingua-identify-language\fR to create a new module for your
own personal use, if you must, but try to contribute with unprocessed
text rather than those modules.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
\&\fILingua::Identify\fR\|(3), \fIlangident\fR\|(1)
.PP
A linguist and/or a shrink.
.PP
The latest \s-1CVS\s0 version of \f(CW\*(C`Lingua::Identify\*(C'\fR (which includes
\&\fImake-lingua-identify\fR) can be attained at
http://natura.di.uminho.pt/natura/viewcvs.cgi/Lingua/Identify/
.PP
\&\s-1ISO 639\s0 Language Codes, at http://www.w3.org/WAI/ER/IG/ert/iso639.htm
.SH "AUTHOR"
.IX Header "AUTHOR"
Jose Alves de Castro, <cog@cpan.org>
.SH "COPYRIGHT AND LICENSE"
.IX Header "COPYRIGHT AND LICENSE"
Copyright 2004\-2005 by Jose Alves de Castro
.PP
This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.