.\" 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 "LANGIDENT 1p"
.TH LANGIDENT 1p "2010-05-21" "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"
langident \- identifies the language files are written in
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 1
\&  langident [OPTIONS] file1 [file2 ...]
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Identifies the language files are written in using Perl module
Lingua::Identify.
.SS "\s-1OPTIONS\s0"
.IX Subsection "OPTIONS"
.SS "\-a"
.IX Subsection "-a"
Show all results (not just the most probable language).
.SS "\-c"
.IX Subsection "-c"
Show confidence level for most probable language (it will be the first value
right after the most probable language).
.SS "\-d"
.IX Subsection "-d"
Debug (development only).
.SS "\-E \s-1ENCODING\s0"
.IX Subsection "-E ENCODING"
Select an input encoding. Defaults to \s-1UTF\-8.\s0
.PP
.Vb 2
\&  # use ISO\-8859\-1 (latin1)
\&  langident \-E ISO\-8859\-1 file
.Ve
.SS "\-e \s-1METHODS\s0"
.IX Subsection "-e METHODS"
Select the method(s) to use. There are three ways of doing this:
.PP
.Vb 2
\&  # simply using a method
\&  langident \-e ngrams3 file
\&
\&  # using several methods (separate them with a comma)
\&  langident \-e prefixes3,suffixes3
\&
\&  # using several methods and assign different weights to each of them
\&  langident \-e smallwords=2,prefixes=1,ngrams3=1.3
.Ve
.PP
The available methods are the following: \fBsmallwords\fR, \fBprefixes1\fR,
\&\fBprefixes2\fR, \fBprefixes3\fR, \fBprefixes4\fR, \fBsuffixes1\fR, \fBsuffixes2\fR,
\&\fBsuffixes3\fR, \fBsuffixes4\fR, \fBngrams1\fR, \fBngrams2\fR, \fBngrams3\fR and \fBngrams4\fR.
.SS "\-h"
.IX Subsection "-h"
Display help message and exit.
.SS "\-l"
.IX Subsection "-l"
List all available languages and exit.
.SS "\-m \s-1NUMBER\s0"
.IX Subsection "-m NUMBER"
Set maximum number of results (languages) to display (shows the N most probable
languages, by descending order of probability).
.PP
Overrides the \-a switch.
.SS "\-o \s-1LANGUAGES\s0"
.IX Subsection "-o LANGUAGES"
Only work with specified languages.
.PP
.Vb 2
\&  # identify between Portuguese and English only
\&  langident \-o pt,en *
.Ve
.SS "\-p"
.IX Subsection "-p"
Also show percentages.
.SS "\-s \s-1SIZE\s0"
.IX Subsection "-s SIZE"
Maximum size to examine.
.SS "\-v"
.IX Subsection "-v"
Show version and exit.
.SH "EXAMPLES"
.IX Header "EXAMPLES"
Use methods ngrams2 and ngrams1, assigning the double of importance to ngrams2
(\-e switch); output will include the three most probable languages (\-m switch)
with its percentages (\-p switch) and also the confidence level (\-c switch) of
the first result.
.PP
.Vb 3
\&  $ langident \-e ngrams2=2,ngrams1 \-c \-p \-m 3 README 
\&  README:en 65.7209505939491 7.8971987481393 ga 4.11905889385895 tr 4.08487011400505
\&  $
.Ve
.SH "TO DO"
.IX Header "TO DO"
.IP "\(bu" 6
Add a switch to ignore \s-1HTML\s0 tags (and maybe other formats too)
.SH "SEE ALSO"
.IX Header "SEE ALSO"
\&\fILingua::Identify\fR\|(3), \fIText::ExtractWords\fR\|(3), \fIText::Ngram\fR\|(3), \fIText::Affixes\fR\|(3).
.PP
A linguist and/or a shrink.
.PP
The latest \s-1CVS\s0 version of \f(CW\*(C`Lingua::Identify\*(C'\fR (which includes \fIlangident\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 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.