mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-12-12 15:39:04 +08:00
e34ab8c3d5
Remove spaces at line endings and replace CRLF by LF. Signed-off-by: Stefan Weil <sw@weilnetz.de>
54 lines
2.1 KiB
XML
54 lines
2.1 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook XML V4.5//EN" "http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd">
|
|
<?asciidoc-toc?>
|
|
<?asciidoc-numbered?>
|
|
<refentry lang="en">
|
|
<refentryinfo>
|
|
<title>DAWG2WORDLIST(1)</title>
|
|
</refentryinfo>
|
|
<refmeta>
|
|
<refentrytitle>dawg2wordlist</refentrytitle>
|
|
<manvolnum>1</manvolnum>
|
|
<refmiscinfo class="source"> </refmiscinfo>
|
|
<refmiscinfo class="manual"> </refmiscinfo>
|
|
</refmeta>
|
|
<refnamediv>
|
|
<refname>dawg2wordlist</refname>
|
|
<refpurpose>convert a Tesseract DAWG to a wordlist</refpurpose>
|
|
</refnamediv>
|
|
<refsynopsisdiv id="_synopsis">
|
|
<simpara><emphasis role="strong">dawg2wordlist</emphasis> <emphasis>UNICHARSET</emphasis> <emphasis>DAWG</emphasis> <emphasis>WORDLIST</emphasis></simpara>
|
|
</refsynopsisdiv>
|
|
<refsect1 id="_description">
|
|
<title>DESCRIPTION</title>
|
|
<simpara>dawg2wordlist(1) converts a Tesseract Directed Acyclic Word
|
|
Graph (DAWG) to a list of words using a unicharset as key.</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_options">
|
|
<title>OPTIONS</title>
|
|
<simpara><emphasis>UNICHARSET</emphasis>
|
|
The unicharset of the language. This is the unicharset
|
|
generated by mftraining(1).</simpara>
|
|
<simpara><emphasis>DAWG</emphasis>
|
|
The input DAWG, created by wordlist2dawg(1)</simpara>
|
|
<simpara><emphasis>WORDLIST</emphasis>
|
|
Plain text (output) file in UTF-8, one word per line</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_see_also">
|
|
<title>SEE ALSO</title>
|
|
<simpara>tesseract(1), mftraining(1), wordlist2dawg(1), unicharset(5),
|
|
combine_tessdata(1)</simpara>
|
|
<simpara><ulink url="https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract">https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract</ulink></simpara>
|
|
</refsect1>
|
|
<refsect1 id="_copying">
|
|
<title>COPYING</title>
|
|
<simpara>Copyright (C) 2012 Google, Inc.
|
|
Licensed under the Apache License, Version 2.0</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_author">
|
|
<title>AUTHOR</title>
|
|
<simpara>The Tesseract OCR engine was written by Ray Smith and his research groups
|
|
at Hewlett Packard (1985-1995) and Google (2006-present).</simpara>
|
|
</refsect1>
|
|
</refentry>
|