trunk/attic/apertium-dictionary-form/dix.dtd

   1 <!--
   2       DTD for the format of dictionaries
   3 -->
   4 <!ELEMENT dictionary (alphabet?, sdefs?,
   5                       pardefs?, section+)>
   6         <!-- root element-->
   7
   8 <!ELEMENT alphabet (#PCDATA)>
   9         <!-- alphabetic character list -->
  10
  11 <!ELEMENT sdefs (sdef+)>
  12         <!-- symbol definition section -->
  13
  14 <!ELEMENT sdef EMPTY>
  15         <!-- symbol definition -->
  16 <!ATTLIST sdef
  17         n ID #REQUIRED
  18         c CDATA  #IMPLIED
  19 >
  20         <!-- n: symbol (tag) name -->
  21         <!-- c: symbol (tag) comment -->
  22
  23 <!ELEMENT pardefs (pardef+)>
  24         <!-- paradigm definition section -->
  25
  26 <!ELEMENT pardef (e+)>
  27         <!-- paradigm definition -->
  28 <!ATTLIST pardef
  29         n CDATA #REQUIRED
  30 >
  31         <!-- n: paradigm name -->
  32
  33 <!ELEMENT section (e+)>
  34         <!-- dictionary section -->
  35 <!ATTLIST section
  36         id ID #REQUIRED
  37         type (standard|inconditional|postblank) #REQUIRED
  38
  39 >
  40         <!-- id: dictionary section identifier -->
  41         <!-- type: dictionary section type -->
  42
  43 <!ELEMENT e (i | p | par | re)+>
  44         <!-- entry -->
  45 <!ATTLIST e
  46         r (LR|RL) #IMPLIED
  47         lm CDATA #IMPLIED
  48         a CDATA #IMPLIED
  49         c CDATA #IMPLIED
  50         i CDATA #IMPLIED
  51         slr CDATA #IMPLIED
  52         srl CDATA #IMPLIED
  53 >
  54         <!-- r: restriction LR: left-to-right,
  55                             RL: right-to-left -->
  56         <!-- lm: lemma -->
  57         <!-- a: author -->
  58         <!-- c: comment -->
  59         <!-- i: ignore ('yes') means ignore, otherwise it is not ignored) -->
  60         <!-- slr: translation sense when translating from left to right -->
  61         <!-- srl: translation sense when translating from right to left -->
  62 <!ELEMENT par EMPTY>
  63         <!-- reference to paradigm -->
  64 <!ATTLIST par
  65         n CDATA #REQUIRED
  66
  67 >
  68         <!-- n: paradigm name -->
  69
  70 <!ELEMENT i (#PCDATA | b | s | g | j | a)*>
  71         <!-- identity -->
  72
  73 <!ELEMENT re (#PCDATA)>
  74         <!-- regular expression identification -->
  75
  76 <!ELEMENT p (l, r)>
  77         <!-- pair of strings -->
  78
  79 <!ELEMENT l (#PCDATA | a | b | g | j | s)*>
  80         <!-- left part of p -->
  81
  82 <!ELEMENT r (#PCDATA | a | b | g | j | s)*>
  83         <!-- right part of p -->
  84
  85 <!ELEMENT a EMPTY>
  86         <!-- post-generator wake-up mark -->
  87
  88 <!ELEMENT b EMPTY>
  89         <!-- blank chars block mark -->
  90
  91 <!ELEMENT g (#PCDATA | a | b | j | s)*>
  92         <!-- mark special groups in lemmas -->
  93 <!ATTLIST g
  94         i CDATA #IMPLIED
  95 >
  96         <!-- i is used to co-index groups in the left with those -->
  97         <!-- on the right of a pair -->
  98
  99 <!ELEMENT j EMPTY>
 100         <!-- join lexical forms -->
 101
 102 <!ELEMENT s EMPTY>
 103         <!-- reference to symbol (tag) -->
 104 <!ATTLIST s
 105         n IDREF #REQUIRED
 106
 107 >
 108         <!-- n: symbol (tag) name -->