<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<link rel="stylesheet" href="style.css" type="text/css">
<meta content="text/html; charset=iso-8859-1" http-equiv="Content-Type">
<link rel="Start" href="index.html">
<link rel="previous" href="Pdfglyphlist.html">
<link rel="next" href="Pdfstandard14.html">
<link rel="Up" href="index.html">
<link title="Index of types" rel=Appendix href="index_types.html">
<link title="Index of exceptions" rel=Appendix href="index_exceptions.html">
<link title="Index of values" rel=Appendix href="index_values.html">
<link title="Index of modules" rel=Appendix href="index_modules.html">
<link title="Pdfutil" rel="Chapter" href="Pdfutil.html">
<link title="Pdfio" rel="Chapter" href="Pdfio.html">
<link title="Pdftransform" rel="Chapter" href="Pdftransform.html">
<link title="Pdfunits" rel="Chapter" href="Pdfunits.html">
<link title="Pdfpaper" rel="Chapter" href="Pdfpaper.html">
<link title="Pdf" rel="Chapter" href="Pdf.html">
<link title="Pdfcrypt" rel="Chapter" href="Pdfcrypt.html">
<link title="Pdfflate" rel="Chapter" href="Pdfflate.html">
<link title="Pdfcodec" rel="Chapter" href="Pdfcodec.html">
<link title="Pdfwrite" rel="Chapter" href="Pdfwrite.html">
<link title="Pdfgenlex" rel="Chapter" href="Pdfgenlex.html">
<link title="Pdfread" rel="Chapter" href="Pdfread.html">
<link title="Pdfjpeg" rel="Chapter" href="Pdfjpeg.html">
<link title="Pdfops" rel="Chapter" href="Pdfops.html">
<link title="Pdfdest" rel="Chapter" href="Pdfdest.html">
<link title="Pdfmarks" rel="Chapter" href="Pdfmarks.html">
<link title="Pdfpagelabels" rel="Chapter" href="Pdfpagelabels.html">
<link title="Pdfpage" rel="Chapter" href="Pdfpage.html">
<link title="Pdfannot" rel="Chapter" href="Pdfannot.html">
<link title="Pdffun" rel="Chapter" href="Pdffun.html">
<link title="Pdfspace" rel="Chapter" href="Pdfspace.html">
<link title="Pdfimage" rel="Chapter" href="Pdfimage.html">
<link title="Pdfafm" rel="Chapter" href="Pdfafm.html">
<link title="Pdfafmdata" rel="Chapter" href="Pdfafmdata.html">
<link title="Pdfglyphlist" rel="Chapter" href="Pdfglyphlist.html">
<link title="Pdftext" rel="Chapter" href="Pdftext.html">
<link title="Pdfstandard14" rel="Chapter" href="Pdfstandard14.html">
<link title="Pdfgraphics" rel="Chapter" href="Pdfgraphics.html">
<link title="Pdfshapes" rel="Chapter" href="Pdfshapes.html">
<link title="Pdfdate" rel="Chapter" href="Pdfdate.html">
<link title="Pdfocg" rel="Chapter" href="Pdfocg.html">
<link title="Pdfcff" rel="Chapter" href="Pdfcff.html">
<link title="Pdftype1" rel="Chapter" href="Pdftype1.html">
<link title="Pdftruetype" rel="Chapter" href="Pdftruetype.html">
<link title="Pdftype0" rel="Chapter" href="Pdftype0.html">
<link title="Pdfmerge" rel="Chapter" href="Pdfmerge.html"><link title="Data Types " rel="Section" href="#2_DataTypes">
<link title="String representations of fonts " rel="Section" href="#2_Stringrepresentationsoffonts">
<link title="Reading a Font" rel="Section" href="#2_ReadingaFont">
<link title="Writing a Font" rel="Section" href="#2_WritingaFont">
<link title="Utility functions" rel="Section" href="#2_Utilityfunctions">
<link title="Text from strings outside page content" rel="Section" href="#2_Textfromstringsoutsidepagecontent">
<link title="Text from strings inside page content" rel="Section" href="#2_Textfromstringsinsidepagecontent">
<link title="Building text for strings inside page content" rel="Section" href="#2_Buildingtextforstringsinsidepagecontent">
<title>Pdftext</title>
</head>
<body>
<div class="navbar"><a class="pre" href="Pdfglyphlist.html" title="Pdfglyphlist">Previous</a>
<a class="up" href="index.html" title="Index">Up</a>
<a class="post" href="Pdfstandard14.html" title="Pdfstandard14">Next</a>
</div>
<h1>Module <a href="type_Pdftext.html">Pdftext</a></h1>
<pre><span class="keyword">module</span> Pdftext: <code class="code">sig</code> <a href="Pdftext.html">..</a> <code class="code">end</code></pre><div class="info module top">
Parsing fonts and extracting text from content streams and PDF strings<br>
</div>
<hr width="100%">
<br>
<h2 id="2_DataTypes">Data Types </h2><br>
<pre><code><span id="TYPEtype3_glpyhs"><span class="keyword">type</span> <code class="type"></code>type3_glpyhs</span> = {</code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTtype3_glpyhs.fontbbox">fontbbox</span> : <code class="type">float * float * float * float</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTtype3_glpyhs.fontmatrix">fontmatrix</span> : <code class="type"><a href="Pdftransform.html#TYPEtransform_matrix">Pdftransform.transform_matrix</a></code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTtype3_glpyhs.charprocs">charprocs</span> : <code class="type">(string * <a href="Pdf.html#TYPEpdfobject">Pdf.pdfobject</a>) list</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTtype3_glpyhs.type3_resources">type3_resources</span> : <code class="type"><a href="Pdf.html#TYPEpdfobject">Pdf.pdfobject</a></code>;</code></td>
</tr></table>
}
<pre><code><span id="TYPEsimple_fonttype"><span class="keyword">type</span> <code class="type"></code>simple_fonttype</span> = </code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_fonttype.Type1"><span class="constructor">Type1</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_fonttype.MMType1"><span class="constructor">MMType1</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_fonttype.Type3"><span class="constructor">Type3</span></span> <span class="keyword">of</span> <code class="type"><a href="Pdftext.html#TYPEtype3_glpyhs">type3_glpyhs</a></code></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_fonttype.Truetype"><span class="constructor">Truetype</span></span></code></td>
</tr></table>
<pre><span id="TYPEfontmetrics"><span class="keyword">type</span> <code class="type"></code>fontmetrics</span> = <code class="type">float array</code> </pre>
<pre><code><span id="TYPEfontfile"><span class="keyword">type</span> <code class="type"></code>fontfile</span> = </code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontfile.FontFile"><span class="constructor">FontFile</span></span> <span class="keyword">of</span> <code class="type">int</code></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontfile.FontFile2"><span class="constructor">FontFile2</span></span> <span class="keyword">of</span> <code class="type">int</code></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontfile.FontFile3"><span class="constructor">FontFile3</span></span> <span class="keyword">of</span> <code class="type">int</code></code></td>
</tr></table>
<pre><code><span id="TYPEfontdescriptor"><span class="keyword">type</span> <code class="type"></code>fontdescriptor</span> = {</code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontdescriptor.ascent">ascent</span> : <code class="type">float</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontdescriptor.descent">descent</span> : <code class="type">float</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontdescriptor.leading">leading</span> : <code class="type">float</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontdescriptor.avgwidth">avgwidth</span> : <code class="type">float</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontdescriptor.maxwidth">maxwidth</span> : <code class="type">float</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfontdescriptor.fontfile">fontfile</span> : <code class="type"><a href="Pdftext.html#TYPEfontfile">fontfile</a> option</code>;</code></td>
</tr></table>
}
<pre><span id="TYPEdifferences"><span class="keyword">type</span> <code class="type"></code>differences</span> = <code class="type">(string * int) list</code> </pre>
<pre><code><span id="TYPEencoding"><span class="keyword">type</span> <code class="type"></code>encoding</span> = </code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTencoding.ImplicitInFontFile"><span class="constructor">ImplicitInFontFile</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTencoding.StandardEncoding"><span class="constructor">StandardEncoding</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTencoding.MacRomanEncoding"><span class="constructor">MacRomanEncoding</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTencoding.WinAnsiEncoding"><span class="constructor">WinAnsiEncoding</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTencoding.MacExpertEncoding"><span class="constructor">MacExpertEncoding</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTencoding.CustomEncoding"><span class="constructor">CustomEncoding</span></span> <span class="keyword">of</span> <code class="type"><a href="Pdftext.html#TYPEencoding">encoding</a> * <a href="Pdftext.html#TYPEdifferences">differences</a></code></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTencoding.FillUndefinedWithStandard"><span class="constructor">FillUndefinedWithStandard</span></span> <span class="keyword">of</span> <code class="type"><a href="Pdftext.html#TYPEencoding">encoding</a></code></code></td>
</tr></table>
<pre><code><span id="TYPEsimple_font"><span class="keyword">type</span> <code class="type"></code>simple_font</span> = {</code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_font.fonttype">fonttype</span> : <code class="type"><a href="Pdftext.html#TYPEsimple_fonttype">simple_fonttype</a></code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_font.basefont">basefont</span> : <code class="type">string</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_font.fontmetrics">fontmetrics</span> : <code class="type"><a href="Pdftext.html#TYPEfontmetrics">fontmetrics</a> option</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_font.fontdescriptor">fontdescriptor</span> : <code class="type"><a href="Pdftext.html#TYPEfontdescriptor">fontdescriptor</a> option</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTsimple_font.encoding">encoding</span> : <code class="type"><a href="Pdftext.html#TYPEencoding">encoding</a></code>;</code></td>
</tr></table>
}
<pre><code><span id="TYPEstandard_font"><span class="keyword">type</span> <code class="type"></code>standard_font</span> = </code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.TimesRoman"><span class="constructor">TimesRoman</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.TimesBold"><span class="constructor">TimesBold</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.TimesItalic"><span class="constructor">TimesItalic</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.TimesBoldItalic"><span class="constructor">TimesBoldItalic</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.Helvetica"><span class="constructor">Helvetica</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.HelveticaBold"><span class="constructor">HelveticaBold</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.HelveticaOblique"><span class="constructor">HelveticaOblique</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.HelveticaBoldOblique"><span class="constructor">HelveticaBoldOblique</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.Courier"><span class="constructor">Courier</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.CourierBold"><span class="constructor">CourierBold</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.CourierOblique"><span class="constructor">CourierOblique</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.CourierBoldOblique"><span class="constructor">CourierBoldOblique</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.Symbol"><span class="constructor">Symbol</span></span></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTstandard_font.ZapfDingbats"><span class="constructor">ZapfDingbats</span></span></code></td>
</tr></table>
<pre><code><span id="TYPEcid_system_info"><span class="keyword">type</span> <code class="type"></code>cid_system_info</span> = {</code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcid_system_info.registry">registry</span> : <code class="type">string</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcid_system_info.ordering">ordering</span> : <code class="type">string</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcid_system_info.supplement">supplement</span> : <code class="type">int</code>;</code></td>
</tr></table>
}
<pre><code><span id="TYPEcomposite_CIDfont"><span class="keyword">type</span> <code class="type"></code>composite_CIDfont</span> = {</code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcomposite_CIDfont.cid_system_info">cid_system_info</span> : <code class="type"><a href="Pdftext.html#TYPEcid_system_info">cid_system_info</a></code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcomposite_CIDfont.cid_basefont">cid_basefont</span> : <code class="type">string</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcomposite_CIDfont.cid_fontdescriptor">cid_fontdescriptor</span> : <code class="type"><a href="Pdftext.html#TYPEfontdescriptor">fontdescriptor</a></code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcomposite_CIDfont.cid_widths">cid_widths</span> : <code class="type">(int * float) list</code>;</code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code> </code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcomposite_CIDfont.cid_default_width">cid_default_width</span> : <code class="type">int</code>;</code></td>
</tr></table>
}
<pre><code><span id="TYPEcmap_encoding"><span class="keyword">type</span> <code class="type"></code>cmap_encoding</span> = </code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcmap_encoding.Predefined"><span class="constructor">Predefined</span></span> <span class="keyword">of</span> <code class="type">string</code></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTcmap_encoding.CMap"><span class="constructor">CMap</span></span> <span class="keyword">of</span> <code class="type">int</code></code></td>
</tr></table>
<pre><code><span id="TYPEfont"><span class="keyword">type</span> <code class="type"></code>font</span> = </code></pre><table class="typetable">
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfont.StandardFont"><span class="constructor">StandardFont</span></span> <span class="keyword">of</span> <code class="type"><a href="Pdftext.html#TYPEstandard_font">standard_font</a> * <a href="Pdftext.html#TYPEencoding">encoding</a></code></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfont.SimpleFont"><span class="constructor">SimpleFont</span></span> <span class="keyword">of</span> <code class="type"><a href="Pdftext.html#TYPEsimple_font">simple_font</a></code></code></td>
</tr>
<tr>
<td align="left" valign="top" >
<code><span class="keyword">|</span></code></td>
<td align="left" valign="top" >
<code><span id="TYPEELTfont.CIDKeyedFont"><span class="constructor">CIDKeyedFont</span></span> <span class="keyword">of</span> <code class="type">string * <a href="Pdftext.html#TYPEcomposite_CIDfont">composite_CIDfont</a> * <a href="Pdftext.html#TYPEcmap_encoding">cmap_encoding</a></code></code></td>
</tr></table>
<br>
<h2 id="2_Stringrepresentationsoffonts">String representations of fonts </h2><br>
<pre><span id="VALstring_of_standard_font"><span class="keyword">val</span> string_of_standard_font</span> : <code class="type"><a href="Pdftext.html#TYPEstandard_font">standard_font</a> -> string</code></pre><div class="info ">
Returns a string such as "Times-Bold" for Pdftext.TimesBold etc.<br>
</div>
<pre><span id="VALstandard_font_of_name"><span class="keyword">val</span> standard_font_of_name</span> : <code class="type">string -> <a href="Pdftext.html#TYPEstandard_font">standard_font</a> option</code></pre><div class="info ">
Parses a string such as "/Times-Bold" or "/TimesNewRoman,Bold" to Pdftext.TimesRomanBold etc.<br>
</div>
<pre><span id="VALstring_of_font"><span class="keyword">val</span> string_of_font</span> : <code class="type"><a href="Pdftext.html#TYPEfont">font</a> -> string</code></pre><div class="info ">
A debug string for the whole font datatype.<br>
</div>
<br>
<h2 id="2_ReadingaFont">Reading a Font</h2><br>
<pre><span id="VALread_font"><span class="keyword">val</span> read_font</span> : <code class="type"><a href="Pdf.html#TYPEt">Pdf.t</a> -> <a href="Pdf.html#TYPEpdfobject">Pdf.pdfobject</a> -> <a href="Pdftext.html#TYPEfont">font</a></code></pre><div class="info ">
Read a font from a given document and object<br>
</div>
<br>
<h2 id="2_WritingaFont">Writing a Font</h2><br>
<pre><span id="VALwrite_font"><span class="keyword">val</span> write_font</span> : <code class="type"><a href="Pdf.html#TYPEt">Pdf.t</a> -> <a href="Pdftext.html#TYPEfont">font</a> -> int</code></pre><div class="info ">
Write a font to a given document, returning the object number for the main
font dictionary<br>
</div>
<br>
<h2 id="2_Utilityfunctions">Utility functions</h2><br>
<pre><span id="VALcodepoints_of_utf8"><span class="keyword">val</span> codepoints_of_utf8</span> : <code class="type">string -> int list</code></pre><div class="info ">
A list of unicode codepoints for a UTF8 string<br>
</div>
<pre><span id="VALutf8_of_codepoints"><span class="keyword">val</span> utf8_of_codepoints</span> : <code class="type">int list -> string</code></pre><div class="info ">
A UTF8 string for a list of unicode codepoints<br>
</div>
<br>
<h2 id="2_Textfromstringsoutsidepagecontent">Text from strings outside page content</h2><br>
<pre><span id="VALutf8_of_pdfdocstring"><span class="keyword">val</span> utf8_of_pdfdocstring</span> : <code class="type">string -> string</code></pre><div class="info ">
Take a pdf string (which will be either pdfdocencoding or UTF16BE) and
return a string representing the same unicode codepoints in UTF8<br>
</div>
<pre><span id="VALpdfdocstring_of_utf8"><span class="keyword">val</span> pdfdocstring_of_utf8</span> : <code class="type">string -> string</code></pre><div class="info ">
Take a UTF8 string and convert to pdfdocencoding (if no unicode-only
characters are used) or UTF16BE (if they are))<br>
</div>
<pre><span id="VALpdfdocstring_of_codepoints"><span class="keyword">val</span> pdfdocstring_of_codepoints</span> : <code class="type">int list -> string</code></pre><div class="info ">
Build a pdf string in pdfdocencoding (if no unicode-only characters are
used) or UTF16BE (if they are)<br>
</div>
<pre><span id="VALcodepoints_of_pdfdocstring"><span class="keyword">val</span> codepoints_of_pdfdocstring</span> : <code class="type">string -> int list</code></pre><div class="info ">
Produce a list of unicode codepoints from a pdfdocencoding or UTF16BE pdf
document string<br>
</div>
<br>
<h2 id="2_Textfromstringsinsidepagecontent">Text from strings inside page content</h2><br>
<pre><span id="TYPEtext_extractor"><span class="keyword">type</span> <code class="type"></code>text_extractor</span> </pre>
<div class="info ">
The type of text extractors.<br>
</div>
<pre><span id="VALtext_extractor_of_font"><span class="keyword">val</span> text_extractor_of_font</span> : <code class="type"><a href="Pdf.html#TYPEt">Pdf.t</a> -> <a href="Pdf.html#TYPEpdfobject">Pdf.pdfobject</a> -> <a href="Pdftext.html#TYPEtext_extractor">text_extractor</a></code></pre><div class="info ">
Build a text extractor from a document and font object<br>
</div>
<pre><span id="VALcodepoints_of_text"><span class="keyword">val</span> codepoints_of_text</span> : <code class="type"><a href="Pdftext.html#TYPEtext_extractor">text_extractor</a> -> string -> int list</code></pre><div class="info ">
Return a list of unicode points from a given extractor and string (for
example from a <code class="code">Pdfpages.Op_Tj</code> or <code class="code">Op_TJ</code> operator).<br>
</div>
<pre><span id="VALglyphnames_of_text"><span class="keyword">val</span> glyphnames_of_text</span> : <code class="type"><a href="Pdftext.html#TYPEtext_extractor">text_extractor</a> -> string -> string list</code></pre><div class="info ">
Return a list of glyph names from a given extractor and string<br>
</div>
<br>
<h2 id="2_Buildingtextforstringsinsidepagecontent">Building text for strings inside page content</h2><br>
<pre><span id="VALcharcode_extractor_of_encoding"><span class="keyword">val</span> charcode_extractor_of_encoding</span> : <code class="type"><a href="Pdftext.html#TYPEencoding">encoding</a> -> int -> int option</code></pre><div class="info ">
Return the character code for a given unicode codepoint, if it exists in
this encoding. This is only really suitable for simple stuff like standard 14
fonts, or editing text in existing fonts.<br>
</div>
</body></html>
distrib
>
Mageia
>
5
>
x86_64
>
media
>
core-release
>
by-pkgid
>
a94aa4b565ade94d0310c6e77aeea765
>
files
>
81
