utils/pdf2xml.dtd

<?xml version="1.0" encoding="UTF-8"?>
<!ELEMENT pdf2xml (page+, outline?)>
<!ATTLIST pdf2xml
	producer CDATA #REQUIRED
	version CDATA #REQUIRED
>
<!ELEMENT page (fontspec*, image*, text*)>
<!ATTLIST page
	number CDATA #REQUIRED
	position CDATA #REQUIRED
	top CDATA #REQUIRED
	left CDATA #REQUIRED
	height CDATA #REQUIRED
	width CDATA #REQUIRED
>
<!ELEMENT fontspec EMPTY>
<!ATTLIST fontspec
	id CDATA #REQUIRED
	size CDATA #REQUIRED
	family CDATA #REQUIRED
	color CDATA #REQUIRED
>
<!ELEMENT text (#PCDATA | b | i | a)*>
<!ATTLIST text
	top CDATA #REQUIRED
	left CDATA #REQUIRED
	width CDATA #REQUIRED
	height CDATA #REQUIRED
	font CDATA #REQUIRED
>
<!ELEMENT b (#PCDATA | i)*>
<!ELEMENT i (#PCDATA | b)*>
<!ELEMENT a (#PCDATA)>
<!ATTLIST a
    href CDATA #REQUIRED
>
<!ELEMENT image EMPTY>
<!ATTLIST image
	top CDATA #REQUIRED
	left CDATA #REQUIRED
	width CDATA #REQUIRED
	height CDATA #REQUIRED
	src CDATA #REQUIRED
>
<!ELEMENT outline (item | outline)*>
<!ELEMENT item (#PCDATA)>
<!ATTLIST item
	page CDATA #IMPLIED
>