docs/export-0.7.xsd

   1 <?xml version="1.0" encoding="UTF-8" ?>
   2 <!--
   3         This is an XML Schema description of the format
   4         output by MediaWiki's Special:Export system.
   5
   6         Version 0.2 adds optional basic file upload info support,
   7         which is used by our OAI export/import submodule.
   8
   9         Version 0.3 adds some site configuration information such
  10         as a list of defined namespaces.
  11
  12         Version 0.4 adds per-revision delete flags, log exports,
  13         discussion threading data, a per-page redirect flag, and
  14         per-namespace capitalization.
  15
  16         Version 0.5 adds byte count per revision.
  17
  18         Version 0.6 adds a separate namespace tag, and resolves the
  19         redirect target and adds a separate sha1 tag for each revision.
  20
  21         Version 0.7 adds a unique identity constraint for both page and
  22         revision identifiers. See also bug 4220.
  23         Fix type for <ns> from "positiveInteger" to "nonNegativeInteger" to allow 0
  24
  25         The canonical URL to the schema document is:
  26         http://www.mediawiki.org/xml/export-0.7.xsd
  27
  28         Use the namespace:
  29         http://www.mediawiki.org/xml/export-0.7/
  30 -->
  31 <schema xmlns="http://www.w3.org/2001/XMLSchema"
  32                 xmlns:mw="http://www.mediawiki.org/xml/export-0.7/"
  33                 targetNamespace="http://www.mediawiki.org/xml/export-0.7/"
  34                 elementFormDefault="qualified">
  35
  36         <annotation>
  37                 <documentation xml:lang="en">
  38                         MediaWiki's page export format
  39                 </documentation>
  40         </annotation>
  41
  42         <!-- Need this to reference xml:lang -->
  43         <import namespace="http://www.w3.org/XML/1998/namespace"
  44                         schemaLocation="http://www.w3.org/2001/xml.xsd"/>
  45
  46         <!-- Our root element -->
  47         <element name="mediawiki" type="mw:MediaWikiType">
  48                 <!-- Page ID contraint, see bug 4220 -->
  49                 <unique name="PageIDConstraint">
  50                         <selector xpath="mw:page"/>
  51                         <field xpath="mw:id"/>
  52                 </unique>
  53                 <!-- Revision ID contraint, see bug 4220 -->
  54                 <unique name="RevIDConstraint">
  55                         <selector xpath="mw:page/mw:revision"/>
  56                         <field xpath="mw:id"/>
  57                 </unique>
  58         </element>
  59
  60         <complexType name="MediaWikiType">
  61                 <sequence>
  62                         <element name="siteinfo" type="mw:SiteInfoType"
  63                                          minOccurs="0" maxOccurs="1"/>
  64                         <element name="page" type="mw:PageType"
  65                                          minOccurs="0" maxOccurs="unbounded"/>
  66                 </sequence>
  67                 <attribute name="version" type="string" use="required"/>
  68                 <attribute ref="xml:lang" use="required"/>
  69         </complexType>
  70
  71         <complexType name="SiteInfoType">
  72                 <sequence>
  73                         <element name="sitename" type="string" minOccurs="0" />
  74                         <element name="base" type="anyURI" minOccurs="0" />
  75                         <element name="generator" type="string" minOccurs="0" />
  76                         <element name="case" type="mw:CaseType" minOccurs="0" />
  77                         <element name="namespaces" type="mw:NamespacesType" minOccurs="0" />
  78                 </sequence>
  79         </complexType>
  80
  81         <simpleType name="CaseType">
  82                 <restriction base="NMTOKEN">
  83                         <!-- Cannot have two titles differing only by case of first letter. -->
  84                         <!-- Default behavior through 1.5, $wgCapitalLinks = true -->
  85                         <enumeration value="first-letter" />
  86
  87                         <!-- Complete title is case-sensitive -->
  88                         <!-- Behavior when $wgCapitalLinks = false -->
  89                         <enumeration value="case-sensitive" />
  90
  91                         <!-- Cannot have non-case senstitive titles eg [[FOO]] == [[Foo]] -->
  92                         <!-- Not yet implemented as of MediaWiki 1.18 -->
  93                         <enumeration value="case-insensitive" />
  94                 </restriction>
  95         </simpleType>
  96
  97         <simpleType name="DeletedFlagType">
  98                 <restriction base="NMTOKEN">
  99                         <enumeration value="deleted"/>
 100                 </restriction>
 101         </simpleType>
 102
 103         <complexType name="NamespacesType">
 104                 <sequence>
 105                         <element name="namespace" type="mw:NamespaceType"
 106                                          minOccurs="0" maxOccurs="unbounded" />
 107                 </sequence>
 108         </complexType>
 109
 110         <complexType name="NamespaceType">
 111                 <simpleContent>
 112                         <extension base="string">
 113                                 <attribute name="key" type="integer" />
 114                                 <attribute name="case" type="mw:CaseType" />
 115                         </extension>
 116                 </simpleContent>
 117         </complexType>
 118
 119         <complexType name="PageType">
 120                 <sequence>
 121                         <!-- Title in text form. (Using spaces, not underscores; with namespace ) -->
 122                         <element name="title" type="string"/>
 123
 124                         <!-- Namespace in canonical form -->
 125                         <element name="ns" type="nonNegativeInteger"/>
 126
 127                         <!-- optional page ID number -->
 128                         <element name="id" type="positiveInteger" minOccurs="0"/>
 129
 130                         <!-- flag if the current revision is a redirect -->
 131                         <element name="redirect" type="string" minOccurs="0"/>
 132
 133                         <!-- comma-separated list of string tokens, if present -->
 134                         <element name="restrictions" type="string" minOccurs="0"/>
 135
 136                         <!-- Zero or more sets of revision or upload data -->
 137                         <choice minOccurs="0" maxOccurs="unbounded">
 138                                 <element name="revision" type="mw:RevisionType" />
 139                                 <element name="upload" type="mw:UploadType" />
 140                                 <element name="logitem" type="mw:LogItemType" />
 141                         </choice>
 142
 143                         <!-- Zero or One sets of discussion threading data -->
 144                         <element name="discussionthreadinginfo" minOccurs="0" maxOccurs="1" type="mw:DiscussionThreadingInfo" />
 145                 </sequence>
 146         </complexType>
 147
 148         <complexType name="RevisionType">
 149                 <sequence>
 150                         <element name="id" type="positiveInteger" minOccurs="0"/>
 151                         <element name="timestamp" type="dateTime"/>
 152                         <element name="contributor" type="mw:ContributorType"/>
 153                         <element name="minor" minOccurs="0" />
 154                         <element name="comment" type="mw:CommentType" minOccurs="0"/>
 155                         <element name="sha1" type="string" />
 156                         <element name="text" type="mw:TextType" />
 157                 </sequence>
 158         </complexType>
 159
 160         <complexType name="LogItemType">
 161                 <sequence>
 162                         <element name="id" type="positiveInteger" minOccurs="0"/>
 163                         <element name="timestamp" type="dateTime"/>
 164                         <element name="contributor" type="mw:ContributorType"/>
 165                         <element name="comment" type="mw:CommentType" minOccurs="0"/>
 166                         <element name="type" type="string" />
 167                         <element name="action" type="string" />
 168                         <element name="text" type="mw:TextType" />
 169                 </sequence>
 170         </complexType>
 171
 172         <complexType name="CommentType">
 173                 <simpleContent>
 174                         <extension base="string">
 175                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 176                                 <attribute name="deleted" use="optional" type="mw:DeletedFlagType"/>
 177                         </extension>
 178                 </simpleContent>
 179         </complexType>
 180
 181         <complexType name="TextType">
 182                 <simpleContent>
 183                         <extension base="string">
 184                                 <attribute ref="xml:space" use="optional" default="preserve" />
 185                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 186                                 <attribute name="deleted" use="optional" type="mw:DeletedFlagType"/>
 187                                 <!-- This isn't a good idea; we should be using "ID" instead of "NMTOKEN" -->
 188                                 <!-- However, "NMTOKEN" is strictest definition that is both compatible with existing -->
 189                                 <!-- usage ([0-9]+) and with the "ID" type. -->
 190                                 <attribute name="id" type="NMTOKEN"/>
 191                                 <attribute name="bytes" use="optional" type="nonNegativeInteger"/>
 192                         </extension>
 193                 </simpleContent>
 194         </complexType>
 195
 196         <complexType name="ContributorType">
 197                 <sequence>
 198                         <element name="username" type="string" minOccurs="0"/>
 199                         <element name="id" type="positiveInteger" minOccurs="0" />
 200
 201                         <element name="ip" type="string" minOccurs="0"/>
 202                 </sequence>
 203                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 204                 <attribute name="deleted" use="optional" type="mw:DeletedFlagType"/>
 205         </complexType>
 206
 207         <complexType name="UploadType">
 208                 <sequence>
 209                         <!-- Revision-style data... -->
 210                         <element name="timestamp" type="dateTime"/>
 211                         <element name="contributor" type="mw:ContributorType"/>
 212                         <element name="comment" type="string" minOccurs="0"/>
 213
 214                         <!-- Filename. (Using underscores, not spaces. No 'Image:' namespace marker.) -->
 215                         <element name="filename" type="string"/>
 216
 217                         <!-- URI at which this resource can be obtained -->
 218                         <element name="src" type="anyURI"/>
 219
 220                         <element name="size" type="positiveInteger" />
 221
 222                         <!-- TODO: add other metadata fields -->
 223                 </sequence>
 224         </complexType>
 225
 226         <!-- Discussion threading data for LiquidThreads -->
 227         <complexType name="DiscussionThreadingInfo">
 228                 <sequence>
 229                         <element name="ThreadSubject" type="string" />
 230                         <element name="ThreadParent" type="positiveInteger" />
 231                         <element name="ThreadAncestor" type="positiveInteger" />
 232                         <element name="ThreadPage" type="string" />
 233                         <element name="ThreadID" type="positiveInteger" />
 234                         <element name="ThreadAuthor" type="string" />
 235                         <element name="ThreadEditStatus" type="string" />
 236                         <element name="ThreadType" type="string" />
 237                 </sequence>
 238         </complexType>
 239
 240 </schema>