docs/export-0.10.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         Moves <logitem> to its right location.
  25         Add parentid to revision.
  26         Fix type for <id> within <contributor> to "nonNegativeInteger"
  27
  28         Version 0.8 adds support for a <model> and a <format> tag for
  29         each revision. See contenthandler.txt.
  30
  31         Version 0.9 adds the database name to the site information.
  32
  33         Version 0.10 moved the <model> and <format> tags before the <text> tag.
  34
  35         The canonical URL to the schema document is:
  36         http://www.mediawiki.org/xml/export-0.10.xsd
  37
  38         Use the namespace:
  39         http://www.mediawiki.org/xml/export-0.10/
  40 -->
  41 <schema xmlns="http://www.w3.org/2001/XMLSchema"
  42                 xmlns:mw="http://www.mediawiki.org/xml/export-0.10/"
  43                 targetNamespace="http://www.mediawiki.org/xml/export-0.10/"
  44                 elementFormDefault="qualified">
  45
  46         <annotation>
  47                 <documentation xml:lang="en">
  48                         MediaWiki's page export format
  49                 </documentation>
  50         </annotation>
  51
  52         <!-- Need this to reference xml:lang -->
  53         <import namespace="http://www.w3.org/XML/1998/namespace"
  54                         schemaLocation="http://www.w3.org/2001/xml.xsd" />
  55
  56         <!-- Our root element -->
  57         <element name="mediawiki" type="mw:MediaWikiType">
  58                 <!-- Page ID contraint, see bug 4220 -->
  59                 <unique name="PageIDConstraint">
  60                         <selector xpath="mw:page" />
  61                         <field xpath="mw:id" />
  62                 </unique>
  63                 <!-- Revision ID contraint, see bug 4220 -->
  64                 <unique name="RevIDConstraint">
  65                         <selector xpath="mw:page/mw:revision" />
  66                         <field xpath="mw:id" />
  67                 </unique>
  68         </element>
  69
  70         <complexType name="MediaWikiType">
  71                 <sequence>
  72                         <element name="siteinfo" type="mw:SiteInfoType"
  73                                          minOccurs="0" maxOccurs="1" />
  74                         <element name="page" type="mw:PageType"
  75                                          minOccurs="0" maxOccurs="unbounded" />
  76                         <element name="logitem" type="mw:LogItemType"
  77                                          minOccurs="0" maxOccurs="unbounded" />
  78                 </sequence>
  79                 <attribute name="version" type="string" use="required" />
  80                 <attribute ref="xml:lang" use="required" />
  81         </complexType>
  82
  83         <complexType name="SiteInfoType">
  84                 <sequence>
  85                         <element name="sitename" type="string" minOccurs="0" />
  86             <element name="dbname" type="string" minOccurs="0" />
  87                         <element name="base" type="anyURI" minOccurs="0" />
  88                         <element name="generator" type="string" minOccurs="0" />
  89                         <element name="case" type="mw:CaseType" minOccurs="0" />
  90                         <element name="namespaces" type="mw:NamespacesType" minOccurs="0" />
  91                 </sequence>
  92         </complexType>
  93
  94         <simpleType name="CaseType">
  95                 <restriction base="NMTOKEN">
  96                         <!-- Cannot have two titles differing only by case of first letter. -->
  97                         <!-- Default behavior through 1.5, $wgCapitalLinks = true -->
  98                         <enumeration value="first-letter" />
  99
 100                         <!-- Complete title is case-sensitive -->
 101                         <!-- Behavior when $wgCapitalLinks = false -->
 102                         <enumeration value="case-sensitive" />
 103
 104                         <!-- Cannot have non-case senstitive titles eg [[FOO]] == [[Foo]] -->
 105                         <!-- Not yet implemented as of MediaWiki 1.18 -->
 106                         <enumeration value="case-insensitive" />
 107                 </restriction>
 108         </simpleType>
 109
 110         <simpleType name="DeletedFlagType">
 111                 <restriction base="NMTOKEN">
 112                         <enumeration value="deleted" />
 113                 </restriction>
 114         </simpleType>
 115
 116         <complexType name="NamespacesType">
 117                 <sequence>
 118                         <element name="namespace" type="mw:NamespaceType"
 119                                          minOccurs="0" maxOccurs="unbounded" />
 120                 </sequence>
 121         </complexType>
 122
 123         <complexType name="NamespaceType">
 124                 <simpleContent>
 125                         <extension base="string">
 126                                 <attribute name="key" type="integer" />
 127                                 <attribute name="case" type="mw:CaseType" />
 128                         </extension>
 129                 </simpleContent>
 130         </complexType>
 131
 132         <complexType name="RedirectType">
 133                 <simpleContent>
 134                         <extension base="string">
 135                                 <attribute name="title" type="string" />
 136                         </extension>
 137                 </simpleContent>
 138         </complexType>
 139
 140         <simpleType name="ContentModelType">
 141                 <restriction base="string">
 142                         <pattern value="[a-zA-Z][-+./a-zA-Z0-9]*" />
 143                 </restriction>
 144         </simpleType>
 145
 146         <simpleType name="ContentFormatType">
 147                 <restriction base="string">
 148                         <pattern value="[a-zA-Z][-+.a-zA-Z0-9]*/[a-zA-Z][-+.a-zA-Z0-9]*" />
 149                 </restriction>
 150         </simpleType>
 151
 152         <complexType name="PageType">
 153                 <sequence>
 154                         <!-- Title in text form. (Using spaces, not underscores; with namespace ) -->
 155                         <element name="title" type="string" />
 156
 157                         <!-- Namespace in canonical form -->
 158                         <element name="ns" type="nonNegativeInteger" />
 159
 160                         <!-- optional page ID number -->
 161                         <element name="id" type="positiveInteger" />
 162
 163                         <!-- flag if the current revision is a redirect -->
 164                         <element name="redirect" type="mw:RedirectType" minOccurs="0" maxOccurs="1" />
 165
 166                         <!-- comma-separated list of string tokens, if present -->
 167                         <element name="restrictions" type="string" minOccurs="0" />
 168
 169                         <!-- Zero or more sets of revision or upload data -->
 170                         <choice minOccurs="0" maxOccurs="unbounded">
 171                                 <element name="revision" type="mw:RevisionType" />
 172                                 <element name="upload" type="mw:UploadType" />
 173                         </choice>
 174
 175                         <!-- Zero or One sets of discussion threading data -->
 176                         <element name="discussionthreadinginfo" minOccurs="0" maxOccurs="1" type="mw:DiscussionThreadingInfo" />
 177                 </sequence>
 178         </complexType>
 179
 180         <complexType name="RevisionType">
 181                 <sequence>
 182                         <element name="id" type="positiveInteger" />
 183                         <element name="parentid" type="positiveInteger" minOccurs="0" />
 184                         <element name="timestamp" type="dateTime" />
 185                         <element name="contributor" type="mw:ContributorType" />
 186                         <element name="minor" minOccurs="0" maxOccurs="1" />
 187                         <element name="comment" type="mw:CommentType" minOccurs="0" maxOccurs="1" />
 188                         <element name="model" type="mw:ContentModelType" />
 189                         <element name="format" type="mw:ContentFormatType" />
 190                         <element name="text" type="mw:TextType" />
 191                         <element name="sha1" type="string" />
 192                 </sequence>
 193         </complexType>
 194
 195         <complexType name="LogItemType">
 196                 <sequence>
 197                         <element name="id" type="positiveInteger" />
 198                         <element name="timestamp" type="dateTime" />
 199                         <element name="contributor" type="mw:ContributorType" />
 200                         <element name="comment" type="mw:CommentType" minOccurs="0" />
 201                         <element name="type" type="string" />
 202                         <element name="action" type="string" />
 203                         <element name="text" type="mw:LogTextType" minOccurs="0" maxOccurs="1" />
 204                         <element name="logtitle" type="string" minOccurs="0" maxOccurs="1" />
 205                         <element name="params" type="mw:LogParamsType" minOccurs="0" maxOccurs="1" />
 206                 </sequence>
 207         </complexType>
 208
 209         <complexType name="CommentType">
 210                 <simpleContent>
 211                         <extension base="string">
 212                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 213                                 <attribute name="deleted" use="optional" type="mw:DeletedFlagType" />
 214                         </extension>
 215                 </simpleContent>
 216         </complexType>
 217
 218         <complexType name="TextType">
 219                 <simpleContent>
 220                         <extension base="string">
 221                                 <attribute ref="xml:space" use="optional" default="preserve" />
 222                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 223                                 <attribute name="deleted" use="optional" type="mw:DeletedFlagType" />
 224                                 <!-- This isn't a good idea; we should be using "ID" instead of "NMTOKEN" -->
 225                                 <!-- However, "NMTOKEN" is strictest definition that is both compatible with existing -->
 226                                 <!-- usage ([0-9]+) and with the "ID" type. -->
 227                                 <attribute name="id" type="NMTOKEN" />
 228                                 <attribute name="bytes" use="optional" type="nonNegativeInteger" />
 229                         </extension>
 230                 </simpleContent>
 231         </complexType>
 232
 233         <complexType name="LogTextType">
 234                 <simpleContent>
 235                         <extension base="string">
 236                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 237                                 <attribute name="deleted" use="optional" type="mw:DeletedFlagType" />
 238                         </extension>
 239                 </simpleContent>
 240         </complexType>
 241
 242         <complexType name="LogParamsType">
 243                 <simpleContent>
 244                         <extension base="string">
 245                                 <attribute ref="xml:space" use="optional" default="preserve" />
 246                         </extension>
 247                 </simpleContent>
 248         </complexType>
 249
 250         <complexType name="ContributorType">
 251                 <sequence>
 252                         <element name="username" type="string" minOccurs="0" />
 253                         <element name="id" type="nonNegativeInteger" minOccurs="0" />
 254
 255                         <element name="ip" type="string" minOccurs="0" />
 256                 </sequence>
 257                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 258                 <attribute name="deleted" use="optional" type="mw:DeletedFlagType" />
 259         </complexType>
 260
 261         <complexType name="UploadType">
 262                 <sequence>
 263                         <!-- Revision-style data... -->
 264                         <element name="timestamp" type="dateTime" />
 265                         <element name="contributor" type="mw:ContributorType" />
 266                         <element name="comment" type="string" minOccurs="0" />
 267
 268                         <!-- Filename. (Using underscores, not spaces. No 'File:' namespace marker.) -->
 269                         <element name="filename" type="string" />
 270
 271                         <!-- URI at which this resource can be obtained -->
 272                         <element name="src" type="anyURI" />
 273
 274                         <element name="size" type="positiveInteger" />
 275
 276                         <!-- TODO: add other metadata fields -->
 277                 </sequence>
 278         </complexType>
 279
 280         <!-- Discussion threading data for LiquidThreads -->
 281         <complexType name="DiscussionThreadingInfo">
 282                 <sequence>
 283                         <element name="ThreadSubject" type="string" />
 284                         <element name="ThreadParent" type="positiveInteger" />
 285                         <element name="ThreadAncestor" type="positiveInteger" />
 286                         <element name="ThreadPage" type="string" />
 287                         <element name="ThreadID" type="positiveInteger" />
 288                         <element name="ThreadAuthor" type="string" />
 289                         <element name="ThreadEditStatus" type="string" />
 290                         <element name="ThreadType" type="string" />
 291                 </sequence>
 292         </complexType>
 293
 294 </schema>