apertium/apertium/format.dtd

   1 <!--
   2       DTD for the format specification files
   3       Sergio Ortiz  2005.05.13
   4 -->
   5
   6
   7 <!ELEMENT format (options,rules)>
   8 <!ATTLIST format name CDATA #REQUIRED>
   9 <!--
  10       'format' is the root element containing the whole format specification
  11       file.  The attribute 'name' specifies the name of the format
  12 -->
  13
  14 <!ELEMENT options (largeblocks,input,output, tag-name, escape-chars,space-chars,case-sensitive)>
  15 <!--
  16       General options of the format
  17 -->
  18
  19 <!ELEMENT largeblocks EMPTY>
  20 <!ATTLIST largeblocks size CDATA #REQUIRED>
  21 <!--
  22       The attribute size is used to define the maximal size in bytes of
  23       inline format blocks
  24 -->
  25
  26 <!ELEMENT input EMPTY>
  27 <!ATTLIST input zip-path CDATA #IMPLIED>
  28 <!ATTLIST input encoding CDATA #REQUIRED>
  29 <!--
  30       Reserved for future extensions
  31 -->
  32
  33 <!ELEMENT output EMPTY>
  34 <!ATTLIST output zip-path CDATA #IMPLIED>
  35 <!ATTLIST output encoding CDATA #REQUIRED>
  36 <!--
  37       Reserved for future extensions
  38 -->
  39
  40 <!ELEMENT tag-name EMPTY>
  41 <!ATTLIST tag-name regexp CDATA #REQUIRED>
  42 <!--
  43       The attribute regexp defines (whith a _flex_ regular expression) how
  44       take a tag name from a whole tag. '\'
  45 -->
  46
  47 <!ELEMENT escape-chars EMPTY>
  48 <!ATTLIST escape-chars regexp CDATA #REQUIRED>
  49 <!--
  50       The attribute regexp defines (whith a _flex_ regular expression) the
  51       set of characters to be escaped with preceding a backslash '\'
  52 -->
  53
  54 <!ELEMENT space-chars EMPTY>
  55 <!ATTLIST space-chars regexp CDATA #REQUIRED>
  56 <!--
  57       Define the space characters (in regexp) with a _flex_ regular
  58       expression
  59 -->
  60
  61 <!ELEMENT case-sensitive EMPTY>
  62 <!ATTLIST case-sensitive value (yes|no) #REQUIRED>
  63 <!--
  64       The attribute 'value' is set to 'yes' if the case is relevant in the
  65       specification of the format.  Otherwise is set to 'no'
  66 -->
  67
  68
  69 <!ELEMENT rules (format-rule|replacement-rule)+>
  70 <!--
  71       Group the rules of processing format and the rules of substitute
  72       expressions by characters that are part of the text
  73 -->
  74
  75 <!ELEMENT format-rule (tag|(begin,end))>
  76 <!ATTLIST format-rule type (comment|empty|open|close) #IMPLIED>
  77 <!ATTLIST format-rule eos (yes|no) #IMPLIED>
  78 <!ATTLIST format-rule priority CDATA #REQUIRED>
  79 <!--
  80       Format rule parent element.  It may include a 'tag' element or
  81       a couple of elements 'begin', 'end'.  In the first case, this element is
  82       considered to be part of the format.  In the second case, the begin and
  83       the end element are considered to enclosing format.  The attribute
  84       'eos' (end of sentence) is set to 'yes' if that rule defines a dot in
  85       the text being processed (is no by default).  The attribute 'priority'
  86       marks the order of precedence of the rule
  87 -->
  88
  89 <!ELEMENT tag EMPTY>
  90 <!ATTLIST tag regexp CDATA #REQUIRED>
  91 <!--
  92       Define an element that is part of the format by the pattern specified
  93       as a value for the regexp attribute
  94 -->
  95
  96 <!ELEMENT begin EMPTY>
  97 <!ATTLIST begin regexp CDATA #REQUIRED>
  98 <!--
  99       The attribute 'regexp' is the regular expression that detects the
 100       begining delimiter of a block of format
 101 -->
 102
 103 <!ELEMENT end EMPTY>
 104 <!ATTLIST end regexp CDATA #REQUIRED>
 105 <!--
 106       The attribute 'regexp' is the regular expression that detects the
 107       ending delimiter of a block of format
 108 -->
 109
 110 <!ELEMENT replacement-rule (replace+)>
 111 <!ATTLIST replacement-rule regexp CDATA #REQUIRED>
 112 <!--
 113       Root element for a replacement rule.  The attribute 'regexp' is the
 114       general expression to detect the elements to replace
 115 -->
 116
 117 <!ELEMENT replace EMPTY>
 118 <!ATTLIST replace source CDATA #REQUIRED>
 119 <!ATTLIST replace target CDATA #REQUIRED>
 120 <!ATTLIST replace prefer (yes|no) #IMPLIED>
 121 <!--
 122       Replacement rule.  The 'source' is a string of one or more characters.
 123       The 'target' MUST be a single character.  The 'prefer' attribute, when
 124       set to 'yes' defines the preferred reverse translation of the
 125       replacement.
 126 -->