<!--

			      A DTD for
	           LDC LCTL Tokenized Text XML Files

		      Linguistic Data Consortium
			    August 15, 2006

			     Version 1.2

-->

<!ELEMENT LCTL_TEXT (DOC+)                         >
<!ATTLIST LCTL_TEXT lang CDATA         #IMPLIED   
                    source_file CDATA  #IMPLIED   
                    source_type CDATA  #IMPLIED   
                    author CDATA       #IMPLIED   
                    encoding CDATA     #IMPLIED    >

<!ELEMENT DOC (HEADLINE|DATELINE|AUTHORLINE|TEXT)+ >
<!ATTLIST DOC id    ID     #REQUIRED           
              lang  CDATA  #IMPLIED                
>

<!ELEMENT HEADLINE (SEG+)                          >
<!ELEMENT DATELINE (#PCDATA)                       >
<!ELEMENT AUTHORLINE (#PCDATA)                     >
<!ELEMENT TEXT (P|SEG)+                            >

<!ELEMENT P (SEG+)                                 >

<!ELEMENT SEG (ORIGINAL_TEXT?, TOKEN*)             >
<!ATTLIST SEG id             ID     #REQUIRED            
              start_token    IDREF  #IMPLIED
              end_token      IDREF  #IMPLIED
	      start_char     CDATA  #IMPLIED
	      end_char       CDATA  #IMPLIED        
>

<!ELEMENT ORIGINAL_TEXT (#PCDATA)                  >

<!ELEMENT TOKEN (#PCDATA)                          >
<!ATTLIST TOKEN id           ID     #REQUIRED            
                attach       (LEFT|RIGHT|BOTH) 
			            #IMPLIED            
		pos          CDATA  #IMPLIED            
		morph        CDATA  #IMPLIED            	
		gloss        CDATA  #IMPLIED            	
		start_char   CDATA  #IMPLIED
		end_char     CDATA  #IMPLIED        
>
