53 lines
1.7 KiB
XML
53 lines
1.7 KiB
XML
<?xml version="1.0"?>
|
|
<!--
|
|
first draft by Volker Simonis, reviewed by Joerg Schulenburg
|
|
Its not ready for use!
|
|
ToDo:
|
|
- lynx/links/w3c should show xml like a html file
|
|
value as <character ...>CharText</character>
|
|
or <word><character ...></character><...>WordText</word>
|
|
or as line or as block? whats more useful?
|
|
- how to code table of alternative chars/words and its probability?
|
|
- how to handle images (as image tags?)
|
|
- xmllint -\-htmlout -\-loaddtd jocr/doc/example.dtd o.xml
|
|
-->
|
|
<!ENTITY % default.attributes "x CDATA #REQUIRED
|
|
y CDATA #REQUIRED
|
|
dx CDATA #REQUIRED
|
|
dy CDATA #REQUIRED">
|
|
|
|
<!ELEMENT box EMPTY>
|
|
<!ATTLIST box %default.attributes;
|
|
value CDATA #REQUIRED;>
|
|
|
|
<!ELEMENT barcode EMPTY>
|
|
<!ATTLIST barcode %default.attributes;
|
|
value CDATA #REQUIRED;>
|
|
|
|
<!ELEMENT img EMPTY>
|
|
<!ATTLIST img %default.attributes;>
|
|
|
|
<!ELEMENT page (block*)>
|
|
<!ATTLIST page %default.attributes;>
|
|
|
|
<!ELEMENT block (line*)>
|
|
<!ATTLIST block %default.attributes;>
|
|
|
|
<!ELEMENT line ((word | space | punctuation-mark)*)>
|
|
<!ATTLIST line %default.attributes;>
|
|
|
|
<!ELEMENT word (character*)>
|
|
<!ATTLIST word %default.attributes;>
|
|
|
|
<!ELEMENT char EMPTY>
|
|
<!ATTLIST char %default.attributes;
|
|
value CDATA #REQUIRED;
|
|
(#CDATA)> <!-- is that correct? -->
|
|
|
|
<!ELEMENT space EMPTY>
|
|
<!ATTLIST space %default.attributes;
|
|
value CDATA #REQUIRED;>
|
|
|
|
<!ELEMENT punctuation-mark EMPTY>
|
|
<!ATTLIST punctuation-mark %default.attributes;
|
|
value CDATA #REQUIRED;>
|