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