mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-12-04 01:39:16 +08:00
55 lines
2.0 KiB
Groff
55 lines
2.0 KiB
Groff
|
'\" t
|
||
|
|
.\" Title: wordlist2dawg
|
||
|
|
.\" Author: [FIXME: author] [see http://docbook.sf.net/el/author]
|
||
|
|
.\" Generator: DocBook XSL Stylesheets v1.75.2 <http://docbook.sf.net/>
|
||
|
|
.\" Date: 09/30/2010
|
||
|
|
.\" Manual: \ \&
|
||
|
|
.\" Source: \ \&
|
||
|
|
.\" Language: English
|
||
|
|
.\"
|
||
|
|
.TH "WORDLIST2DAWG" "1" "09/30/2010" "\ \&" "\ \&"
|
||
|
|
.\" -----------------------------------------------------------------
|
||
|
|
.\" * Define some portability stuff
|
||
|
|
.\" -----------------------------------------------------------------
|
||
|
|
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||
|
|
.\" http://bugs.debian.org/507673
|
||
|
|
.\" http://lists.gnu.org/archive/html/groff/2009-02/msg00013.html
|
||
|
|
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||
|
|
.ie \n(.g .ds Aq \(aq
|
||
|
|
.el .ds Aq '
|
||
|
|
.\" -----------------------------------------------------------------
|
||
|
|
.\" * set default formatting
|
||
|
|
.\" -----------------------------------------------------------------
|
||
|
|
.\" disable hyphenation
|
||
|
|
.nh
|
||
|
|
.\" disable justification (adjust text to left margin only)
|
||
|
|
.ad l
|
||
|
|
.\" -----------------------------------------------------------------
|
||
|
|
.\" * MAIN CONTENT STARTS HERE *
|
||
|
|
.\" -----------------------------------------------------------------
|
||
|
|
.SH "NAME"
|
||
|
|
wordlist2dawg \- convert a wordlist to a DAWG for Tesseract
|
||
|
|
.SH "SYNOPSIS"
|
||
|
|
.sp
|
||
|
|
\fBwordlist2dawg\fR \fIWORDLIST\fR \fIDAWG\fR \fIlang\&.unicharset\fR
|
||
|
|
.SH "DESCRIPTION"
|
||
|
|
.sp
|
||
|
|
wordlist2dawg(1) converts a wordlist to a Directed Acyclic Word Graph (DAWG) for use with Tesseract\&.
|
||
|
|
.sp
|
||
|
|
The wordlists are split into two: one with high frequency words, and one with the rest\&.
|
||
|
|
.SH "OPTIONS"
|
||
|
|
.sp
|
||
|
|
\fIWORDLIST\fR A plain text file in UTF\-8, one word per line
|
||
|
|
.sp
|
||
|
|
\fIDAWG\fR The output DAWG to write
|
||
|
|
.sp
|
||
|
|
\fIlang\&.unicharset\fR The unicharset of the language\&. This is the unicharset generated by mftraining(1)
|
||
|
|
.SH "SEE ALSO"
|
||
|
|
.sp
|
||
|
|
tesseract(1), mftraining(1)
|
||
|
|
.sp
|
||
|
|
\m[blue]\fBhttp://code\&.google\&.com/p/tesseract\-ocr/wiki/TrainingTesseract3\fR\m[]
|
||
|
|
.SH "COPYING"
|
||
|
|
.sp
|
||
|
|
Copyright (c) 2006 Google, Inc\&. Licensed under the Apache License, Version 2\&.0
|