mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-12-23 06:57:50 +08:00
70 lines
3.3 KiB
XML
70 lines
3.3 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>WORDLIST2DAWG(1)</title>
|
|
</refentryinfo>
|
|
<refmeta>
|
|
<refentrytitle>wordlist2dawg</refentrytitle>
|
|
<manvolnum>1</manvolnum>
|
|
<refmiscinfo class="source"> </refmiscinfo>
|
|
<refmiscinfo class="manual"> </refmiscinfo>
|
|
</refmeta>
|
|
<refnamediv>
|
|
<refname>wordlist2dawg</refname>
|
|
<refpurpose>convert a wordlist to a DAWG for Tesseract</refpurpose>
|
|
</refnamediv>
|
|
<refsynopsisdiv id="_synopsis">
|
|
<simpara><emphasis role="strong">wordlist2dawg</emphasis> <emphasis>WORDLIST</emphasis> <emphasis>DAWG</emphasis> <emphasis>lang.unicharset</emphasis></simpara>
|
|
<simpara><emphasis role="strong">wordlist2dawg</emphasis> -t <emphasis>WORDLIST</emphasis> <emphasis>DAWG</emphasis> <emphasis>lang.unicharset</emphasis></simpara>
|
|
<simpara><emphasis role="strong">wordlist2dawg</emphasis> -r 1 <emphasis>WORDLIST</emphasis> <emphasis>DAWG</emphasis> <emphasis>lang.unicharset</emphasis></simpara>
|
|
<simpara><emphasis role="strong">wordlist2dawg</emphasis> -r 2 <emphasis>WORDLIST</emphasis> <emphasis>DAWG</emphasis> <emphasis>lang.unicharset</emphasis></simpara>
|
|
<simpara><emphasis role="strong">wordlist2dawg</emphasis> -l <short> <long> <emphasis>WORDLIST</emphasis> <emphasis>DAWG</emphasis> <emphasis>lang.unicharset</emphasis></simpara>
|
|
</refsynopsisdiv>
|
|
<refsect1 id="_description">
|
|
<title>DESCRIPTION</title>
|
|
<simpara>wordlist2dawg(1) converts a wordlist to a Directed Acyclic Word Graph
|
|
(DAWG) for use with Tesseract. A DAWG is a compressed, space and time
|
|
efficient representation of a word list.</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_options">
|
|
<title>OPTIONS</title>
|
|
<simpara>-t
|
|
Verify that a given dawg file is equivalent to a given wordlist.</simpara>
|
|
<simpara>-r 1
|
|
Reverse a word if it contains an RTL character.</simpara>
|
|
<simpara>-r 2
|
|
Reverse all words.</simpara>
|
|
<simpara>-l <short> <long>
|
|
Produce a file with several dawgs in it, one each for words
|
|
of length <short>, <short+1>,… <long></simpara>
|
|
</refsect1>
|
|
<refsect1 id="_arguments">
|
|
<title>ARGUMENTS</title>
|
|
<simpara><emphasis>WORDLIST</emphasis>
|
|
A plain text file in UTF-8, one word per line.</simpara>
|
|
<simpara><emphasis>DAWG</emphasis>
|
|
The output DAWG to write.</simpara>
|
|
<simpara><emphasis>lang.unicharset</emphasis>
|
|
The unicharset of the language. This is the unicharset
|
|
generated by mftraining(1).</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_see_also">
|
|
<title>SEE ALSO</title>
|
|
<simpara>tesseract(1), combine_tessdata(1), dawg2wordlist(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) 2006 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>
|