docs/export-0.11.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.md.
  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         Version 0.11 introduced <content> tag.
  36
  37         The canonical URL to the schema document is:
  38         https://www.mediawiki.org/xml/export-0.11.xsd
  39
  40         Use the namespace:
  41         https://www.mediawiki.org/xml/export-0.11/
  42 -->
  43 <schema xmlns="http://www.w3.org/2001/XMLSchema"
  44                 xmlns:mw="http://www.mediawiki.org/xml/export-0.11/"
  45                 targetNamespace="http://www.mediawiki.org/xml/export-0.11/"
  46                 elementFormDefault="qualified">
  47
  48         <annotation>
  49                 <documentation xml:lang="en">
  50                         MediaWiki's page export format
  51                 </documentation>
  52         </annotation>
  53
  54         <!-- Need this to reference xml:lang -->
  55         <import namespace="http://www.w3.org/XML/1998/namespace"
  56                         schemaLocation="http://www.w3.org/2001/xml.xsd" />
  57
  58         <!-- Our root element -->
  59         <element name="mediawiki" type="mw:MediaWikiType">
  60                 <!-- Page ID contraint, see bug 4220 -->
  61                 <unique name="PageIDConstraint">
  62                         <selector xpath="mw:page" />
  63                         <field xpath="mw:id" />
  64                 </unique>
  65                 <!-- Revision ID contraint, see bug 4220 -->
  66                 <unique name="RevIDConstraint">
  67                         <selector xpath="mw:page/mw:revision" />
  68                         <field xpath="mw:id" />
  69                 </unique>
  70         </element>
  71
  72         <complexType name="MediaWikiType">
  73                 <sequence>
  74                         <element name="siteinfo" type="mw:SiteInfoType"
  75                                          minOccurs="0" maxOccurs="1" />
  76                         <element name="page" type="mw:PageType"
  77                                          minOccurs="0" maxOccurs="unbounded" />
  78                         <element name="logitem" type="mw:LogItemType"
  79                                          minOccurs="0" maxOccurs="unbounded" />
  80                 </sequence>
  81                 <attribute name="version" type="string" use="required" />
  82                 <attribute ref="xml:lang" use="required" />
  83         </complexType>
  84
  85         <complexType name="SiteInfoType">
  86                 <sequence>
  87                         <element name="sitename" type="string" minOccurs="0" />
  88             <element name="dbname" type="string" minOccurs="0" />
  89                         <element name="base" type="anyURI" minOccurs="0" />
  90                         <element name="generator" type="string" minOccurs="0" />
  91                         <element name="case" type="mw:CaseType" minOccurs="0" />
  92                         <element name="namespaces" type="mw:NamespacesType" minOccurs="0" />
  93                 </sequence>
  94         </complexType>
  95
  96         <simpleType name="CaseType">
  97                 <restriction base="NMTOKEN">
  98                         <!-- Cannot have two titles differing only by case of first letter. -->
  99                         <!-- Default behavior through 1.5, $wgCapitalLinks = true -->
 100                         <enumeration value="first-letter" />
 101
 102                         <!-- Complete title is case-sensitive -->
 103                         <!-- Behavior when $wgCapitalLinks = false -->
 104                         <enumeration value="case-sensitive" />
 105
 106                         <!-- Cannot have non-case senstitive titles eg [[FOO]] == [[Foo]] -->
 107                         <!-- Not yet implemented as of MediaWiki 1.18 -->
 108                         <enumeration value="case-insensitive" />
 109                 </restriction>
 110         </simpleType>
 111
 112         <simpleType name="DeletedFlagType">
 113                 <restriction base="NMTOKEN">
 114                         <enumeration value="deleted" />
 115                 </restriction>
 116         </simpleType>
 117
 118         <complexType name="NamespacesType">
 119                 <sequence>
 120                         <element name="namespace" type="mw:NamespaceType"
 121                                          minOccurs="0" maxOccurs="unbounded" />
 122                 </sequence>
 123         </complexType>
 124
 125         <complexType name="NamespaceType">
 126                 <simpleContent>
 127                         <extension base="string">
 128                                 <attribute name="key" type="integer" />
 129                                 <attribute name="case" type="mw:CaseType" />
 130                         </extension>
 131                 </simpleContent>
 132         </complexType>
 133
 134         <complexType name="RedirectType">
 135                 <simpleContent>
 136                         <extension base="string">
 137                                 <attribute name="title" type="string" />
 138                         </extension>
 139                 </simpleContent>
 140         </complexType>
 141
 142         <simpleType name="ContentModelType">
 143                 <restriction base="string">
 144                         <pattern value="[a-zA-Z][-+./a-zA-Z0-9]*" />
 145                 </restriction>
 146         </simpleType>
 147
 148         <simpleType name="ContentFormatType">
 149                 <restriction base="string">
 150                         <pattern value="[a-zA-Z][-+.a-zA-Z0-9]*/[a-zA-Z][-+.a-zA-Z0-9]*" />
 151                 </restriction>
 152         </simpleType>
 153
 154         <complexType name="PageType">
 155                 <sequence>
 156                         <!-- Title in text form. (Using spaces, not underscores; with namespace ) -->
 157                         <element name="title" type="string" />
 158
 159                         <!-- Namespace in canonical form -->
 160                         <element name="ns" type="nonNegativeInteger" />
 161
 162                         <!-- optional page ID number -->
 163                         <element name="id" type="positiveInteger" />
 164
 165                         <!-- flag if the current revision is a redirect -->
 166                         <element name="redirect" type="mw:RedirectType" minOccurs="0" maxOccurs="1" />
 167
 168                         <!-- comma-separated list of string tokens, if present -->
 169                         <element name="restrictions" type="string" minOccurs="0" />
 170
 171                         <!-- Zero or more sets of revision or upload data -->
 172                         <choice minOccurs="0" maxOccurs="unbounded">
 173                                 <element name="revision" type="mw:RevisionType" />
 174                                 <element name="upload" type="mw:UploadType" />
 175                         </choice>
 176
 177                         <!-- Zero or One sets of discussion threading data -->
 178                         <element name="discussionthreadinginfo" minOccurs="0" maxOccurs="1" type="mw:DiscussionThreadingInfo" />
 179                 </sequence>
 180         </complexType>
 181
 182         <complexType name="RevisionType">
 183                 <sequence>
 184                         <element name="id" type="positiveInteger" />
 185                         <element name="parentid" type="positiveInteger" minOccurs="0" maxOccurs="1" />
 186                         <element name="timestamp" type="dateTime" />
 187                         <element name="contributor" type="mw:ContributorType" />
 188                         <element name="minor" minOccurs="0" maxOccurs="1" />
 189                         <element name="comment" type="mw:CommentType" minOccurs="0" maxOccurs="1" />
 190                         <!-- corresponds to slot origin for the main slot -->
 191                         <element name="origin" type="positiveInteger" />
 192                         <!-- the main slot's content model -->
 193                         <element name="model" type="mw:ContentModelType" />
 194                         <!-- the main slot's serialization format -->
 195                         <element name="format" type="mw:ContentFormatType" />
 196                         <!-- the main slot's serialized content -->
 197                         <element name="text" type="mw:TextType"/>
 198                         <element name="content" type="mw:ContentType" minOccurs="0" maxOccurs="unbounded"/>
 199                         <!-- sha1 of the revision, a combined sha1 of content in all slots -->
 200                         <element name="sha1" type="string" />
 201                 </sequence>
 202         </complexType>
 203
 204         <complexType name="ContentType">
 205                 <sequence>
 206                         <!-- corresponds to slot role_name -->
 207                         <element name="role" type="mw:SlotRoleType" />
 208                         <!-- corresponds to slot origin -->
 209                         <element name="origin" type="positiveInteger" />
 210                         <element name="model" type="mw:ContentModelType" />
 211                         <element name="format" type="mw:ContentFormatType" />
 212                         <element name="text" type="mw:ContentTextType" />
 213                 </sequence>
 214         </complexType>
 215
 216         <simpleType name="SlotRoleType">
 217                 <restriction base="string">
 218                         <pattern value="[a-zA-Z][-+./a-zA-Z0-9]*" />
 219                 </restriction>
 220         </simpleType>
 221
 222         <complexType name="ContentTextType">
 223                 <simpleContent>
 224                         <extension base="string">
 225                                 <attribute ref="xml:space" default="preserve" />
 226                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 227                                 <attribute name="deleted" type="mw:DeletedFlagType" />
 228                                 <attribute name="location" type="anyURI" />
 229                                 <attribute name="sha1" type="string" />
 230                                 <attribute name="bytes" type="nonNegativeInteger" />
 231                         </extension>
 232                 </simpleContent>
 233         </complexType>
 234
 235         <complexType name="LogItemType">
 236                 <sequence>
 237                         <element name="id" type="positiveInteger" />
 238                         <element name="timestamp" type="dateTime" />
 239                         <element name="contributor" type="mw:ContributorType" />
 240                         <element name="comment" type="mw:CommentType" minOccurs="0" />
 241                         <element name="type" type="string" />
 242                         <element name="action" type="string" />
 243                         <element name="text" type="mw:LogTextType" minOccurs="0" maxOccurs="1" />
 244                         <element name="logtitle" type="string" minOccurs="0" maxOccurs="1" />
 245                         <element name="params" type="mw:LogParamsType" minOccurs="0" maxOccurs="1" />
 246                 </sequence>
 247         </complexType>
 248
 249         <complexType name="CommentType">
 250                 <simpleContent>
 251                         <extension base="string">
 252                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 253                                 <attribute name="deleted" type="mw:DeletedFlagType" />
 254                         </extension>
 255                 </simpleContent>
 256         </complexType>
 257
 258         <complexType name="TextType">
 259                 <simpleContent>
 260                         <extension base="string">
 261                                 <attribute ref="xml:space" default="preserve" />
 262                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 263                                 <attribute name="deleted" type="mw:DeletedFlagType" />
 264                                 <!-- This isn't a good idea; we should be using "ID" instead of "NMTOKEN" -->
 265                                 <!-- However, "NMTOKEN" is strictest definition that is both compatible with existing -->
 266                                 <!-- usage ([0-9]+) and with the "ID" type. -->
 267                                 <attribute name="id" type="NMTOKEN" />
 268                                 <attribute name="location" type="anyURI" />
 269                                 <attribute name="sha1" type="string"/>
 270                                 <attribute name="bytes" type="nonNegativeInteger" />
 271                         </extension>
 272                 </simpleContent>
 273         </complexType>
 274
 275         <complexType name="LogTextType">
 276                 <simpleContent>
 277                         <extension base="string">
 278                                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 279                                 <attribute name="deleted" type="mw:DeletedFlagType" />
 280                         </extension>
 281                 </simpleContent>
 282         </complexType>
 283
 284         <complexType name="LogParamsType">
 285                 <simpleContent>
 286                         <extension base="string">
 287                                 <attribute ref="xml:space" default="preserve" />
 288                         </extension>
 289                 </simpleContent>
 290         </complexType>
 291
 292         <complexType name="ContributorType">
 293                 <sequence>
 294                         <element name="username" type="string" minOccurs="0" />
 295                         <element name="id" type="nonNegativeInteger" minOccurs="0" />
 296
 297                         <element name="ip" type="string" minOccurs="0" />
 298                 </sequence>
 299                 <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
 300                 <attribute name="deleted" type="mw:DeletedFlagType" />
 301         </complexType>
 302
 303         <complexType name="UploadType">
 304                 <sequence>
 305                         <!-- Revision-style data... -->
 306                         <element name="timestamp" type="dateTime" />
 307                         <element name="contributor" type="mw:ContributorType" />
 308                         <element name="comment" type="string" minOccurs="0" />
 309
 310                         <!-- Filename. (Using underscores, not spaces. No 'File:' namespace marker.) -->
 311                         <element name="filename" type="string" />
 312
 313                         <!-- URI at which this resource can be obtained -->
 314                         <element name="src" type="anyURI" />
 315
 316                         <element name="size" type="positiveInteger" />
 317
 318                         <!-- TODO: add other metadata fields -->
 319                 </sequence>
 320         </complexType>
 321
 322         <!-- Discussion threading data for LiquidThreads -->
 323         <complexType name="DiscussionThreadingInfo">
 324                 <sequence>
 325                         <element name="ThreadSubject" type="string" />
 326                         <element name="ThreadParent" type="positiveInteger" />
 327                         <element name="ThreadAncestor" type="positiveInteger" />
 328                         <element name="ThreadPage" type="string" />
 329                         <element name="ThreadID" type="positiveInteger" />
 330                         <element name="ThreadAuthor" type="string" />
 331                         <element name="ThreadEditStatus" type="string" />
 332                         <element name="ThreadType" type="string" />
 333                 </sequence>
 334         </complexType>
 335
 336 </schema>