/usr/share/apertium/format.dtd is in apertium 3.1.0-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | <!--
DTD for the format specification files
Sergio Ortiz 2005.05.13
-->
<!ELEMENT format (options,rules)>
<!ATTLIST format name CDATA #REQUIRED>
<!--
'format' is the root element containing the whole format specification
file. The attribute 'name' specifies the name of the format
-->
<!ELEMENT options (largeblocks,input,output, tag-name, escape-chars,space-chars,case-sensitive)>
<!--
General options of the format
-->
<!ELEMENT largeblocks EMPTY>
<!ATTLIST largeblocks size CDATA #REQUIRED>
<!--
The attribute size is used to define the maximal size in bytes of
inline format blocks
-->
<!ELEMENT input EMPTY>
<!ATTLIST input zip-path CDATA #IMPLIED>
<!ATTLIST input encoding CDATA #REQUIRED>
<!--
Reserved for future extensions
-->
<!ELEMENT output EMPTY>
<!ATTLIST output zip-path CDATA #IMPLIED>
<!ATTLIST output encoding CDATA #REQUIRED>
<!--
Reserved for future extensions
-->
<!ELEMENT tag-name EMPTY>
<!ATTLIST tag-name regexp CDATA #REQUIRED>
<!--
The attribute regexp defines (whith a _flex_ regular expression) how
take a tag name from a whole tag. '\'
-->
<!ELEMENT escape-chars EMPTY>
<!ATTLIST escape-chars regexp CDATA #REQUIRED>
<!--
The attribute regexp defines (whith a _flex_ regular expression) the
set of characters to be escaped with preceding a backslash '\'
-->
<!ELEMENT space-chars EMPTY>
<!ATTLIST space-chars regexp CDATA #REQUIRED>
<!--
Define the space characters (in regexp) with a _flex_ regular
expression
-->
<!ELEMENT case-sensitive EMPTY>
<!ATTLIST case-sensitive value (yes|no) #REQUIRED>
<!--
The attribute 'value' is set to 'yes' if the case is relevant in the
specification of the format. Otherwise is set to 'no'
-->
<!ELEMENT rules (format-rule|replacement-rule)+>
<!--
Group the rules of processing format and the rules of substitute
expressions by characters that are part of the text
-->
<!ELEMENT format-rule (tag|(begin,end))>
<!ATTLIST format-rule type (comment|empty|open|close) #IMPLIED>
<!ATTLIST format-rule eos (yes|no) #IMPLIED>
<!ATTLIST format-rule priority CDATA #REQUIRED>
<!--
Format rule parent element. It may include a 'tag' element or
a couple of elements 'begin', 'end'. In the first case, this element is
considered to be part of the format. In the second case, the begin and
the end element are considered to enclosing format. The attribute
'eos' (end of sentence) is set to 'yes' if that rule defines a dot in
the text being processed (is no by default). The attribute 'priority'
marks the order of precedence of the rule
-->
<!ELEMENT tag EMPTY>
<!ATTLIST tag regexp CDATA #REQUIRED>
<!--
Define an element that is part of the format by the pattern specified
as a value for the regexp attribute
-->
<!ELEMENT begin EMPTY>
<!ATTLIST begin regexp CDATA #REQUIRED>
<!--
The attribute 'regexp' is the regular expression that detects the
begining delimiter of a block of format
-->
<!ELEMENT end EMPTY>
<!ATTLIST end regexp CDATA #REQUIRED>
<!--
The attribute 'regexp' is the regular expression that detects the
ending delimiter of a block of format
-->
<!ELEMENT replacement-rule (replace+)>
<!ATTLIST replacement-rule regexp CDATA #REQUIRED>
<!--
Root element for a replacement rule. The attribute 'regexp' is the
general expression to detect the elements to replace
-->
<!ELEMENT replace EMPTY>
<!ATTLIST replace source CDATA #REQUIRED>
<!ATTLIST replace target CDATA #REQUIRED>
<!ATTLIST replace prefer (yes|no) #IMPLIED>
<!--
Replacement rule. The 'source' is a string of one or more characters.
The 'target' MUST be a single character. The 'prefer' attribute, when
set to 'yes' defines the preferred reverse translation of the
replacement.
-->
|