2012-02-10 06:55:47 +08:00
|
|
|
'\" t
|
|
|
|
|
.\" Title: dawg2wordlist
|
|
|
|
|
.\" Author: [see the "AUTHOR" section]
|
2015-06-13 06:08:05 +08:00
|
|
|
.\" Generator: DocBook XSL Stylesheets v1.78.1 <http://docbook.sf.net/>
|
|
|
|
|
.\" Date: 06/12/2015
|
2012-02-10 06:55:47 +08:00
|
|
|
.\" Manual: \ \&
|
|
|
|
|
.\" Source: \ \&
|
|
|
|
|
.\" Language: English
|
|
|
|
|
.\"
|
2015-06-13 06:08:05 +08:00
|
|
|
.TH "DAWG2WORDLIST" "1" "06/12/2015" "\ \&" "\ \&"
|
2012-02-10 06:55:47 +08:00
|
|
|
.\" -----------------------------------------------------------------
|
|
|
|
|
.\" * 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"
|
|
|
|
|
dawg2wordlist \- convert a Tesseract DAWG to a wordlist
|
|
|
|
|
.SH "SYNOPSIS"
|
|
|
|
|
.sp
|
|
|
|
|
\fBdawg2wordlist\fR \fIUNICHARSET\fR \fIDAWG\fR \fIWORDLIST\fR
|
|
|
|
|
.SH "DESCRIPTION"
|
|
|
|
|
.sp
|
|
|
|
|
dawg2wordlist(1) converts a Tesseract Directed Acyclic Word Graph (DAWG) to a list of words using a unicharset as key\&.
|
|
|
|
|
.SH "OPTIONS"
|
|
|
|
|
.sp
|
|
|
|
|
\fIUNICHARSET\fR The unicharset of the language\&. This is the unicharset generated by mftraining(1)\&.
|
|
|
|
|
.sp
|
|
|
|
|
\fIDAWG\fR The input DAWG, created by wordlist2dawg(1)
|
|
|
|
|
.sp
|
|
|
|
|
\fIWORDLIST\fR Plain text (output) file in UTF\-8, one word per line
|
|
|
|
|
.SH "SEE ALSO"
|
|
|
|
|
.sp
|
|
|
|
|
tesseract(1), mftraining(1), wordlist2dawg(1), unicharset(5), combine_tessdata(1)
|
|
|
|
|
.sp
|
2015-06-13 06:08:05 +08:00
|
|
|
\m[blue]\fBhttps://github\&.com/tesseract\-ocr/tesseract/wiki/TrainingTesseract\fR\m[]
|
2012-02-10 06:55:47 +08:00
|
|
|
.SH "COPYING"
|
|
|
|
|
.sp
|
|
|
|
|
Copyright (C) 2012 Google, Inc\&. Licensed under the Apache License, Version 2\&.0
|
|
|
|
|
.SH "AUTHOR"
|
|
|
|
|
.sp
|
|
|
|
|
The Tesseract OCR engine was written by Ray Smith and his research groups at Hewlett Packard (1985\-1995) and Google (2006\-present)\&.
|
