mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-12-04 01:39:16 +08:00
997 lines
23 KiB
HTML
997 lines
23 KiB
HTML
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
|
|
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
|
|
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
|
|
<head>
|
|
<meta http-equiv="Content-Type" content="application/xhtml+xml; charset=UTF-8" />
|
|
<meta name="generator" content="AsciiDoc 8.6.9" />
|
|
<title>COMBINE_TESSDATA(1)</title>
|
|
<style type="text/css">
|
|
/* Shared CSS for AsciiDoc xhtml11 and html5 backends */
|
|
|
|
/* Default font. */
|
|
body {
|
|
font-family: Georgia,serif;
|
|
}
|
|
|
|
/* Title font. */
|
|
h1, h2, h3, h4, h5, h6,
|
|
div.title, caption.title,
|
|
thead, p.table.header,
|
|
#toctitle,
|
|
#author, #revnumber, #revdate, #revremark,
|
|
#footer {
|
|
font-family: Arial,Helvetica,sans-serif;
|
|
}
|
|
|
|
body {
|
|
margin: 1em 5% 1em 5%;
|
|
}
|
|
|
|
a {
|
|
color: blue;
|
|
text-decoration: underline;
|
|
}
|
|
a:visited {
|
|
color: fuchsia;
|
|
}
|
|
|
|
em {
|
|
font-style: italic;
|
|
color: navy;
|
|
}
|
|
|
|
strong {
|
|
font-weight: bold;
|
|
color: #083194;
|
|
}
|
|
|
|
h1, h2, h3, h4, h5, h6 {
|
|
color: #527bbd;
|
|
margin-top: 1.2em;
|
|
margin-bottom: 0.5em;
|
|
line-height: 1.3;
|
|
}
|
|
|
|
h1, h2, h3 {
|
|
border-bottom: 2px solid silver;
|
|
}
|
|
h2 {
|
|
padding-top: 0.5em;
|
|
}
|
|
h3 {
|
|
float: left;
|
|
}
|
|
h3 + * {
|
|
clear: left;
|
|
}
|
|
h5 {
|
|
font-size: 1.0em;
|
|
}
|
|
|
|
div.sectionbody {
|
|
margin-left: 0;
|
|
}
|
|
|
|
hr {
|
|
border: 1px solid silver;
|
|
}
|
|
|
|
p {
|
|
margin-top: 0.5em;
|
|
margin-bottom: 0.5em;
|
|
}
|
|
|
|
ul, ol, li > p {
|
|
margin-top: 0;
|
|
}
|
|
ul > li { color: #aaa; }
|
|
ul > li > * { color: black; }
|
|
|
|
.monospaced, code, pre {
|
|
font-family: "Courier New", Courier, monospace;
|
|
font-size: inherit;
|
|
color: navy;
|
|
padding: 0;
|
|
margin: 0;
|
|
}
|
|
pre {
|
|
white-space: pre-wrap;
|
|
}
|
|
|
|
#author {
|
|
color: #527bbd;
|
|
font-weight: bold;
|
|
font-size: 1.1em;
|
|
}
|
|
#email {
|
|
}
|
|
#revnumber, #revdate, #revremark {
|
|
}
|
|
|
|
#footer {
|
|
font-size: small;
|
|
border-top: 2px solid silver;
|
|
padding-top: 0.5em;
|
|
margin-top: 4.0em;
|
|
}
|
|
#footer-text {
|
|
float: left;
|
|
padding-bottom: 0.5em;
|
|
}
|
|
#footer-badges {
|
|
float: right;
|
|
padding-bottom: 0.5em;
|
|
}
|
|
|
|
#preamble {
|
|
margin-top: 1.5em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.imageblock, div.exampleblock, div.verseblock,
|
|
div.quoteblock, div.literalblock, div.listingblock, div.sidebarblock,
|
|
div.admonitionblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.admonitionblock {
|
|
margin-top: 2.0em;
|
|
margin-bottom: 2.0em;
|
|
margin-right: 10%;
|
|
color: #606060;
|
|
}
|
|
|
|
div.content { /* Block element content. */
|
|
padding: 0;
|
|
}
|
|
|
|
/* Block element titles. */
|
|
div.title, caption.title {
|
|
color: #527bbd;
|
|
font-weight: bold;
|
|
text-align: left;
|
|
margin-top: 1.0em;
|
|
margin-bottom: 0.5em;
|
|
}
|
|
div.title + * {
|
|
margin-top: 0;
|
|
}
|
|
|
|
td div.title:first-child {
|
|
margin-top: 0.0em;
|
|
}
|
|
div.content div.title:first-child {
|
|
margin-top: 0.0em;
|
|
}
|
|
div.content + div.title {
|
|
margin-top: 0.0em;
|
|
}
|
|
|
|
div.sidebarblock > div.content {
|
|
background: #ffffee;
|
|
border: 1px solid #dddddd;
|
|
border-left: 4px solid #f0f0f0;
|
|
padding: 0.5em;
|
|
}
|
|
|
|
div.listingblock > div.content {
|
|
border: 1px solid #dddddd;
|
|
border-left: 5px solid #f0f0f0;
|
|
background: #f8f8f8;
|
|
padding: 0.5em;
|
|
}
|
|
|
|
div.quoteblock, div.verseblock {
|
|
padding-left: 1.0em;
|
|
margin-left: 1.0em;
|
|
margin-right: 10%;
|
|
border-left: 5px solid #f0f0f0;
|
|
color: #888;
|
|
}
|
|
|
|
div.quoteblock > div.attribution {
|
|
padding-top: 0.5em;
|
|
text-align: right;
|
|
}
|
|
|
|
div.verseblock > pre.content {
|
|
font-family: inherit;
|
|
font-size: inherit;
|
|
}
|
|
div.verseblock > div.attribution {
|
|
padding-top: 0.75em;
|
|
text-align: left;
|
|
}
|
|
/* DEPRECATED: Pre version 8.2.7 verse style literal block. */
|
|
div.verseblock + div.attribution {
|
|
text-align: left;
|
|
}
|
|
|
|
div.admonitionblock .icon {
|
|
vertical-align: top;
|
|
font-size: 1.1em;
|
|
font-weight: bold;
|
|
text-decoration: underline;
|
|
color: #527bbd;
|
|
padding-right: 0.5em;
|
|
}
|
|
div.admonitionblock td.content {
|
|
padding-left: 0.5em;
|
|
border-left: 3px solid #dddddd;
|
|
}
|
|
|
|
div.exampleblock > div.content {
|
|
border-left: 3px solid #dddddd;
|
|
padding-left: 0.5em;
|
|
}
|
|
|
|
div.imageblock div.content { padding-left: 0; }
|
|
span.image img { border-style: none; vertical-align: text-bottom; }
|
|
a.image:visited { color: white; }
|
|
|
|
dl {
|
|
margin-top: 0.8em;
|
|
margin-bottom: 0.8em;
|
|
}
|
|
dt {
|
|
margin-top: 0.5em;
|
|
margin-bottom: 0;
|
|
font-style: normal;
|
|
color: navy;
|
|
}
|
|
dd > *:first-child {
|
|
margin-top: 0.1em;
|
|
}
|
|
|
|
ul, ol {
|
|
list-style-position: outside;
|
|
}
|
|
ol.arabic {
|
|
list-style-type: decimal;
|
|
}
|
|
ol.loweralpha {
|
|
list-style-type: lower-alpha;
|
|
}
|
|
ol.upperalpha {
|
|
list-style-type: upper-alpha;
|
|
}
|
|
ol.lowerroman {
|
|
list-style-type: lower-roman;
|
|
}
|
|
ol.upperroman {
|
|
list-style-type: upper-roman;
|
|
}
|
|
|
|
div.compact ul, div.compact ol,
|
|
div.compact p, div.compact p,
|
|
div.compact div, div.compact div {
|
|
margin-top: 0.1em;
|
|
margin-bottom: 0.1em;
|
|
}
|
|
|
|
tfoot {
|
|
font-weight: bold;
|
|
}
|
|
td > div.verse {
|
|
white-space: pre;
|
|
}
|
|
|
|
div.hdlist {
|
|
margin-top: 0.8em;
|
|
margin-bottom: 0.8em;
|
|
}
|
|
div.hdlist tr {
|
|
padding-bottom: 15px;
|
|
}
|
|
dt.hdlist1.strong, td.hdlist1.strong {
|
|
font-weight: bold;
|
|
}
|
|
td.hdlist1 {
|
|
vertical-align: top;
|
|
font-style: normal;
|
|
padding-right: 0.8em;
|
|
color: navy;
|
|
}
|
|
td.hdlist2 {
|
|
vertical-align: top;
|
|
}
|
|
div.hdlist.compact tr {
|
|
margin: 0;
|
|
padding-bottom: 0;
|
|
}
|
|
|
|
.comment {
|
|
background: yellow;
|
|
}
|
|
|
|
.footnote, .footnoteref {
|
|
font-size: 0.8em;
|
|
}
|
|
|
|
span.footnote, span.footnoteref {
|
|
vertical-align: super;
|
|
}
|
|
|
|
#footnotes {
|
|
margin: 20px 0 20px 0;
|
|
padding: 7px 0 0 0;
|
|
}
|
|
|
|
#footnotes div.footnote {
|
|
margin: 0 0 5px 0;
|
|
}
|
|
|
|
#footnotes hr {
|
|
border: none;
|
|
border-top: 1px solid silver;
|
|
height: 1px;
|
|
text-align: left;
|
|
margin-left: 0;
|
|
width: 20%;
|
|
min-width: 100px;
|
|
}
|
|
|
|
div.colist td {
|
|
padding-right: 0.5em;
|
|
padding-bottom: 0.3em;
|
|
vertical-align: top;
|
|
}
|
|
div.colist td img {
|
|
margin-top: 0.3em;
|
|
}
|
|
|
|
@media print {
|
|
#footer-badges { display: none; }
|
|
}
|
|
|
|
#toc {
|
|
margin-bottom: 2.5em;
|
|
}
|
|
|
|
#toctitle {
|
|
color: #527bbd;
|
|
font-size: 1.1em;
|
|
font-weight: bold;
|
|
margin-top: 1.0em;
|
|
margin-bottom: 0.1em;
|
|
}
|
|
|
|
div.toclevel0, div.toclevel1, div.toclevel2, div.toclevel3, div.toclevel4 {
|
|
margin-top: 0;
|
|
margin-bottom: 0;
|
|
}
|
|
div.toclevel2 {
|
|
margin-left: 2em;
|
|
font-size: 0.9em;
|
|
}
|
|
div.toclevel3 {
|
|
margin-left: 4em;
|
|
font-size: 0.9em;
|
|
}
|
|
div.toclevel4 {
|
|
margin-left: 6em;
|
|
font-size: 0.9em;
|
|
}
|
|
|
|
span.aqua { color: aqua; }
|
|
span.black { color: black; }
|
|
span.blue { color: blue; }
|
|
span.fuchsia { color: fuchsia; }
|
|
span.gray { color: gray; }
|
|
span.green { color: green; }
|
|
span.lime { color: lime; }
|
|
span.maroon { color: maroon; }
|
|
span.navy { color: navy; }
|
|
span.olive { color: olive; }
|
|
span.purple { color: purple; }
|
|
span.red { color: red; }
|
|
span.silver { color: silver; }
|
|
span.teal { color: teal; }
|
|
span.white { color: white; }
|
|
span.yellow { color: yellow; }
|
|
|
|
span.aqua-background { background: aqua; }
|
|
span.black-background { background: black; }
|
|
span.blue-background { background: blue; }
|
|
span.fuchsia-background { background: fuchsia; }
|
|
span.gray-background { background: gray; }
|
|
span.green-background { background: green; }
|
|
span.lime-background { background: lime; }
|
|
span.maroon-background { background: maroon; }
|
|
span.navy-background { background: navy; }
|
|
span.olive-background { background: olive; }
|
|
span.purple-background { background: purple; }
|
|
span.red-background { background: red; }
|
|
span.silver-background { background: silver; }
|
|
span.teal-background { background: teal; }
|
|
span.white-background { background: white; }
|
|
span.yellow-background { background: yellow; }
|
|
|
|
span.big { font-size: 2em; }
|
|
span.small { font-size: 0.6em; }
|
|
|
|
span.underline { text-decoration: underline; }
|
|
span.overline { text-decoration: overline; }
|
|
span.line-through { text-decoration: line-through; }
|
|
|
|
div.unbreakable { page-break-inside: avoid; }
|
|
|
|
|
|
/*
|
|
* xhtml11 specific
|
|
*
|
|
* */
|
|
|
|
div.tableblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.tableblock > table {
|
|
border: 3px solid #527bbd;
|
|
}
|
|
thead, p.table.header {
|
|
font-weight: bold;
|
|
color: #527bbd;
|
|
}
|
|
p.table {
|
|
margin-top: 0;
|
|
}
|
|
/* Because the table frame attribute is overriden by CSS in most browsers. */
|
|
div.tableblock > table[frame="void"] {
|
|
border-style: none;
|
|
}
|
|
div.tableblock > table[frame="hsides"] {
|
|
border-left-style: none;
|
|
border-right-style: none;
|
|
}
|
|
div.tableblock > table[frame="vsides"] {
|
|
border-top-style: none;
|
|
border-bottom-style: none;
|
|
}
|
|
|
|
|
|
/*
|
|
* html5 specific
|
|
*
|
|
* */
|
|
|
|
table.tableblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
thead, p.tableblock.header {
|
|
font-weight: bold;
|
|
color: #527bbd;
|
|
}
|
|
p.tableblock {
|
|
margin-top: 0;
|
|
}
|
|
table.tableblock {
|
|
border-width: 3px;
|
|
border-spacing: 0px;
|
|
border-style: solid;
|
|
border-color: #527bbd;
|
|
border-collapse: collapse;
|
|
}
|
|
th.tableblock, td.tableblock {
|
|
border-width: 1px;
|
|
padding: 4px;
|
|
border-style: solid;
|
|
border-color: #527bbd;
|
|
}
|
|
|
|
table.tableblock.frame-topbot {
|
|
border-left-style: hidden;
|
|
border-right-style: hidden;
|
|
}
|
|
table.tableblock.frame-sides {
|
|
border-top-style: hidden;
|
|
border-bottom-style: hidden;
|
|
}
|
|
table.tableblock.frame-none {
|
|
border-style: hidden;
|
|
}
|
|
|
|
th.tableblock.halign-left, td.tableblock.halign-left {
|
|
text-align: left;
|
|
}
|
|
th.tableblock.halign-center, td.tableblock.halign-center {
|
|
text-align: center;
|
|
}
|
|
th.tableblock.halign-right, td.tableblock.halign-right {
|
|
text-align: right;
|
|
}
|
|
|
|
th.tableblock.valign-top, td.tableblock.valign-top {
|
|
vertical-align: top;
|
|
}
|
|
th.tableblock.valign-middle, td.tableblock.valign-middle {
|
|
vertical-align: middle;
|
|
}
|
|
th.tableblock.valign-bottom, td.tableblock.valign-bottom {
|
|
vertical-align: bottom;
|
|
}
|
|
|
|
|
|
/*
|
|
* manpage specific
|
|
*
|
|
* */
|
|
|
|
body.manpage h1 {
|
|
padding-top: 0.5em;
|
|
padding-bottom: 0.5em;
|
|
border-top: 2px solid silver;
|
|
border-bottom: 2px solid silver;
|
|
}
|
|
body.manpage h2 {
|
|
border-style: none;
|
|
}
|
|
body.manpage div.sectionbody {
|
|
margin-left: 3em;
|
|
}
|
|
|
|
@media print {
|
|
body.manpage div#toc { display: none; }
|
|
}
|
|
|
|
|
|
</style>
|
|
<script type="text/javascript">
|
|
/*<+'])');
|
|
// Function that scans the DOM tree for header elements (the DOM2
|
|
// nodeIterator API would be a better technique but not supported by all
|
|
// browsers).
|
|
var iterate = function (el) {
|
|
for (var i = el.firstChild; i != null; i = i.nextSibling) {
|
|
if (i.nodeType == 1 /* Node.ELEMENT_NODE */) {
|
|
var mo = re.exec(i.tagName);
|
|
if (mo && (i.getAttribute("class") || i.getAttribute("className")) != "float") {
|
|
result[result.length] = new TocEntry(i, getText(i), mo[1]-1);
|
|
}
|
|
iterate(i);
|
|
}
|
|
}
|
|
}
|
|
iterate(el);
|
|
return result;
|
|
}
|
|
|
|
var toc = document.getElementById("toc");
|
|
if (!toc) {
|
|
return;
|
|
}
|
|
|
|
// Delete existing TOC entries in case we're reloading the TOC.
|
|
var tocEntriesToRemove = [];
|
|
var i;
|
|
for (i = 0; i < toc.childNodes.length; i++) {
|
|
var entry = toc.childNodes[i];
|
|
if (entry.nodeName.toLowerCase() == 'div'
|
|
&& entry.getAttribute("class")
|
|
&& entry.getAttribute("class").match(/^toclevel/))
|
|
tocEntriesToRemove.push(entry);
|
|
}
|
|
for (i = 0; i < tocEntriesToRemove.length; i++) {
|
|
toc.removeChild(tocEntriesToRemove[i]);
|
|
}
|
|
|
|
// Rebuild TOC entries.
|
|
var entries = tocEntries(document.getElementById("content"), toclevels);
|
|
for (var i = 0; i < entries.length; ++i) {
|
|
var entry = entries[i];
|
|
if (entry.element.id == "")
|
|
entry.element.id = "_toc_" + i;
|
|
var a = document.createElement("a");
|
|
a.href = "#" + entry.element.id;
|
|
a.appendChild(document.createTextNode(entry.text));
|
|
var div = document.createElement("div");
|
|
div.appendChild(a);
|
|
div.className = "toclevel" + entry.toclevel;
|
|
toc.appendChild(div);
|
|
}
|
|
if (entries.length == 0)
|
|
toc.parentNode.removeChild(toc);
|
|
},
|
|
|
|
|
|
/////////////////////////////////////////////////////////////////////
|
|
// Footnotes generator
|
|
/////////////////////////////////////////////////////////////////////
|
|
|
|
/* Based on footnote generation code from:
|
|
* http://www.brandspankingnew.net/archive/2005/07/format_footnote.html
|
|
*/
|
|
|
|
footnotes: function () {
|
|
// Delete existing footnote entries in case we're reloading the footnodes.
|
|
var i;
|
|
var noteholder = document.getElementById("footnotes");
|
|
if (!noteholder) {
|
|
return;
|
|
}
|
|
var entriesToRemove = [];
|
|
for (i = 0; i < noteholder.childNodes.length; i++) {
|
|
var entry = noteholder.childNodes[i];
|
|
if (entry.nodeName.toLowerCase() == 'div' && entry.getAttribute("class") == "footnote")
|
|
entriesToRemove.push(entry);
|
|
}
|
|
for (i = 0; i < entriesToRemove.length; i++) {
|
|
noteholder.removeChild(entriesToRemove[i]);
|
|
}
|
|
|
|
// Rebuild footnote entries.
|
|
var cont = document.getElementById("content");
|
|
var spans = cont.getElementsByTagName("span");
|
|
var refs = {};
|
|
var n = 0;
|
|
for (i=0; i<spans.length; i++) {
|
|
if (spans[i].className == "footnote") {
|
|
n++;
|
|
var note = spans[i].getAttribute("data-note");
|
|
if (!note) {
|
|
// Use [\s\S] in place of . so multi-line matches work.
|
|
// Because JavaScript has no s (dotall) regex flag.
|
|
note = spans[i].innerHTML.match(/\s*\[([\s\S]*)]\s*/)[1];
|
|
spans[i].innerHTML =
|
|
"[<a id='_footnoteref_" + n + "' href='#_footnote_" + n +
|
|
"' title='View footnote' class='footnote'>" + n + "</a>]";
|
|
spans[i].setAttribute("data-note", note);
|
|
}
|
|
noteholder.innerHTML +=
|
|
"<div class='footnote' id='_footnote_" + n + "'>" +
|
|
"<a href='#_footnoteref_" + n + "' title='Return to text'>" +
|
|
n + "</a>. " + note + "</div>";
|
|
var id =spans[i].getAttribute("id");
|
|
if (id != null) refs["#"+id] = n;
|
|
}
|
|
}
|
|
if (n == 0)
|
|
noteholder.parentNode.removeChild(noteholder);
|
|
else {
|
|
// Process footnoterefs.
|
|
for (i=0; i<spans.length; i++) {
|
|
if (spans[i].className == "footnoteref") {
|
|
var href = spans[i].getElementsByTagName("a")[0].getAttribute("href");
|
|
href = href.match(/#.*/)[0]; // Because IE return full URL.
|
|
n = refs[href];
|
|
spans[i].innerHTML =
|
|
"[<a href='#_footnote_" + n +
|
|
"' title='View footnote' class='footnote'>" + n + "</a>]";
|
|
}
|
|
}
|
|
}
|
|
},
|
|
|
|
install: function(toclevels) {
|
|
var timerId;
|
|
|
|
function reinstall() {
|
|
asciidoc.footnotes();
|
|
if (toclevels) {
|
|
asciidoc.toc(toclevels);
|
|
}
|
|
}
|
|
|
|
function reinstallAndRemoveTimer() {
|
|
clearInterval(timerId);
|
|
reinstall();
|
|
}
|
|
|
|
timerId = setInterval(reinstall, 500);
|
|
if (document.addEventListener)
|
|
document.addEventListener("DOMContentLoaded", reinstallAndRemoveTimer, false);
|
|
else
|
|
window.onload = reinstallAndRemoveTimer;
|
|
}
|
|
|
|
}
|
|
asciidoc.install();
|
|
/*]]>*/
|
|
</script>
|
|
</head>
|
|
<body class="manpage">
|
|
<div id="header">
|
|
<h1>
|
|
COMBINE_TESSDATA(1) Manual Page
|
|
</h1>
|
|
<h2>NAME</h2>
|
|
<div class="sectionbody">
|
|
<p>combine_tessdata -
|
|
combine/extract/overwrite Tesseract data
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div id="content">
|
|
<div class="sect1">
|
|
<h2 id="_synopsis">SYNOPSIS</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p><strong>combine_tessdata</strong> [<em>OPTION</em>] <em>FILE</em>…</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_description">DESCRIPTION</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>combine_tessdata(1) is the main program to combine/extract/overwrite
|
|
tessdata components in [lang].traineddata files.</p></div>
|
|
<div class="paragraph"><p>To combine all the individual tessdata components (unicharset, DAWGs,
|
|
classifier templates, ambiguities, language configs) located at, say,
|
|
/home/$USER/temp/eng.* run:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>combine_tessdata /home/$USER/temp/eng.</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>The result will be a combined tessdata file /home/$USER/temp/eng.traineddata</p></div>
|
|
<div class="paragraph"><p>Specify option -e if you would like to extract individual components
|
|
from a combined traineddata file. For example, to extract language config
|
|
file and the unicharset from tessdata/eng.traineddata run:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>combine_tessdata -e tessdata/eng.traineddata \
|
|
/home/$USER/temp/eng.config /home/$USER/temp/eng.unicharset</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>The desired config file and unicharset will be written to
|
|
/home/$USER/temp/eng.config /home/$USER/temp/eng.unicharset</p></div>
|
|
<div class="paragraph"><p>Specify option -o to overwrite individual components of the given
|
|
[lang].traineddata file. For example, to overwrite language config
|
|
and unichar ambiguities files in tessdata/eng.traineddata use:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>combine_tessdata -o tessdata/eng.traineddata \
|
|
/home/$USER/temp/eng.config /home/$USER/temp/eng.unicharambigs</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>As a result, tessdata/eng.traineddata will contain the new language config
|
|
and unichar ambigs, plus all the original DAWGs, classifier templates, etc.</p></div>
|
|
<div class="paragraph"><p>Note: the file names of the files to extract to and to overwrite from should
|
|
have the appropriate file suffixes (extensions) indicating their tessdata
|
|
component type (.unicharset for the unicharset, .unicharambigs for unichar
|
|
ambigs, etc). See k*FileSuffix variable in ccutil/tessdatamanager.h.</p></div>
|
|
<div class="paragraph"><p>Specify option -u to unpack all the components to the specified path:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>combine_tessdata -u tessdata/eng.traineddata /home/$USER/temp/eng.</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>This will create /home/$USER/temp/eng.* files with individual tessdata
|
|
components from tessdata/eng.traineddata.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_options">OPTIONS</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p><strong>-e</strong> <em>.traineddata</em> <em>FILE</em>…:
|
|
Extracts the specified components from the .traineddata file</p></div>
|
|
<div class="paragraph"><p><strong>-o</strong> <em>.traineddata</em> <em>FILE</em>…:
|
|
Overwrites the specified components of the .traineddata file
|
|
with those provided on the comand line.</p></div>
|
|
<div class="paragraph"><p><strong>-u</strong> <em>.traineddata</em> <em>PATHPREFIX</em>
|
|
Unpacks the .traineddata using the provided prefix.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_caveats">CAVEATS</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p><em>Prefix</em> refers to the full file prefix, including period (.)</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_components">COMPONENTS</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>The components in a Tesseract lang.traineddata file as of
|
|
Tesseract 3.02 are briefly described below; For more information on
|
|
many of these files, see
|
|
<a href="https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract">https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract</a></p></div>
|
|
<div class="dlist"><dl>
|
|
<dt class="hdlist1">
|
|
lang.config
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) Language-specific overrides to default config variables.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.unicharset
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Required) The list of symbols that Tesseract recognizes, with properties.
|
|
See unicharset(5).
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.unicharambigs
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) This file contains information on pairs of recognized symbols
|
|
which are often confused. For example, <em>rn</em> and <em>m</em>.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.inttemp
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Required) Character shape templates for each unichar. Produced by
|
|
mftraining(1).
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.pffmtable
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Required) The number of features expected for each unichar.
|
|
Produced by mftraining(1) from <strong>.tr</strong> files.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.normproto
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Required) Character normalization prototypes generated by cntraining(1)
|
|
from <strong>.tr</strong> files.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.punc-dawg
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) A dawg made from punctuation patterns found around words.
|
|
The "word" part is replaced by a single space.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.word-dawg
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) A dawg made from dictionary words from the language.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.number-dawg
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) A dawg made from tokens which originally contained digits.
|
|
Each digit is replaced by a space character.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.freq-dawg
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) A dawg made from the most frequent words which would have
|
|
gone into word-dawg.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.fixed-length-dawgs
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) Several dawgs of different fixed lengths — useful for
|
|
languages like Chinese.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.shapetable
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) When present, a shapetable is an extra layer between the character
|
|
classifier and the word recognizer that allows the character classifier to
|
|
return a collection of unichar ids and fonts instead of a single unichar-id
|
|
and font.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.bigram-dawg
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) A dawg of word bigrams where the words are separated by a space
|
|
and each digit is replaced by a <em>?</em>.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.unambig-dawg
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) TODO: Describe.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
lang.params-training-model
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
(Optional) TODO: Describe.
|
|
</p>
|
|
</dd>
|
|
</dl></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_history">HISTORY</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>combine_tessdata(1) first appeared in version 3.00 of Tesseract</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_see_also">SEE ALSO</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>tesseract(1), wordlist2dawg(1), cntraining(1), mftraining(1), unicharset(5),
|
|
unicharambigs(5)</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_copying">COPYING</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Copyright (C) 2009, Google Inc.
|
|
Licensed under the Apache License, Version 2.0</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_author">AUTHOR</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>The Tesseract OCR engine was written by Ray Smith and his research groups
|
|
at Hewlett Packard (1985-1995) and Google (2006-present).</p></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div id="footnotes"><hr /></div>
|
|
<div id="footer">
|
|
<div id="footer-text">
|
|
Last updated 2015-06-12 23:52:02 CEST
|
|
</div>
|
|
</div>
|
|
</body>
|
|
</html>
|