docs/export-0.11.xsd
<?xml version="1.0" encoding="UTF-8" ?>
<!--
This is an XML Schema description of the format
output by MediaWiki's Special:Export system.
Version 0.2 adds optional basic file upload info support,
which is used by our OAI export/import submodule.
Version 0.3 adds some site configuration information such
as a list of defined namespaces.
Version 0.4 adds per-revision delete flags, log exports,
discussion threading data, a per-page redirect flag, and
per-namespace capitalization.
Version 0.5 adds byte count per revision.
Version 0.6 adds a separate namespace tag, and resolves the
redirect target and adds a separate sha1 tag for each revision.
Version 0.7 adds a unique identity constraint for both page and
revision identifiers. See also bug 4220.
Fix type for <ns> from "positiveInteger" to "nonNegativeInteger" to allow 0
Moves <logitem> to its right location.
Add parentid to revision.
Fix type for <id> within <contributor> to "nonNegativeInteger"
Version 0.8 adds support for a <model> and a <format> tag for
each revision. See contenthandler.md.
Version 0.9 adds the database name to the site information.
Version 0.10 moved the <model> and <format> tags before the <text> tag.
Version 0.11 introduced <content> tag.
The canonical URL to the schema document is:
https://www.mediawiki.org/xml/export-0.11.xsd
Use the namespace:
https://www.mediawiki.org/xml/export-0.11/
-->
<schema xmlns="http://www.w3.org/2001/XMLSchema"
xmlns:mw="http://www.mediawiki.org/xml/export-0.11/"
targetNamespace="http://www.mediawiki.org/xml/export-0.11/"
elementFormDefault="qualified">
<annotation>
<documentation xml:lang="en">
MediaWiki's page export format
</documentation>
</annotation>
<!-- Need this to reference xml:lang -->
<import namespace="http://www.w3.org/XML/1998/namespace"
schemaLocation="http://www.w3.org/2001/xml.xsd" />
<!-- Our root element -->
<element name="mediawiki" type="mw:MediaWikiType">
<!-- Page ID contraint, see bug 4220 -->
<unique name="PageIDConstraint">
<selector xpath="mw:page" />
<field xpath="mw:id" />
</unique>
<!-- Revision ID contraint, see bug 4220 -->
<unique name="RevIDConstraint">
<selector xpath="mw:page/mw:revision" />
<field xpath="mw:id" />
</unique>
</element>
<complexType name="MediaWikiType">
<sequence>
<element name="siteinfo" type="mw:SiteInfoType"
minOccurs="0" maxOccurs="1" />
<element name="page" type="mw:PageType"
minOccurs="0" maxOccurs="unbounded" />
<element name="logitem" type="mw:LogItemType"
minOccurs="0" maxOccurs="unbounded" />
</sequence>
<attribute name="version" type="string" use="required" />
<attribute ref="xml:lang" use="required" />
</complexType>
<complexType name="SiteInfoType">
<sequence>
<element name="sitename" type="string" minOccurs="0" />
<element name="dbname" type="string" minOccurs="0" />
<element name="base" type="anyURI" minOccurs="0" />
<element name="generator" type="string" minOccurs="0" />
<element name="case" type="mw:CaseType" minOccurs="0" />
<element name="namespaces" type="mw:NamespacesType" minOccurs="0" />
</sequence>
</complexType>
<simpleType name="CaseType">
<restriction base="NMTOKEN">
<!-- Cannot have two titles differing only by case of first letter. -->
<!-- Default behavior through 1.5, $wgCapitalLinks = true -->
<enumeration value="first-letter" />
<!-- Complete title is case-sensitive -->
<!-- Behavior when $wgCapitalLinks = false -->
<enumeration value="case-sensitive" />
<!-- Cannot have non-case senstitive titles eg [[FOO]] == [[Foo]] -->
<!-- Not yet implemented as of MediaWiki 1.18 -->
<enumeration value="case-insensitive" />
</restriction>
</simpleType>
<simpleType name="DeletedFlagType">
<restriction base="NMTOKEN">
<enumeration value="deleted" />
</restriction>
</simpleType>
<complexType name="NamespacesType">
<sequence>
<element name="namespace" type="mw:NamespaceType"
minOccurs="0" maxOccurs="unbounded" />
</sequence>
</complexType>
<complexType name="NamespaceType">
<simpleContent>
<extension base="string">
<attribute name="key" type="integer" />
<attribute name="case" type="mw:CaseType" />
</extension>
</simpleContent>
</complexType>
<complexType name="RedirectType">
<simpleContent>
<extension base="string">
<attribute name="title" type="string" />
</extension>
</simpleContent>
</complexType>
<simpleType name="ContentModelType">
<restriction base="string">
<pattern value="[a-zA-Z][-+./a-zA-Z0-9]*" />
</restriction>
</simpleType>
<simpleType name="ContentFormatType">
<restriction base="string">
<pattern value="[a-zA-Z][-+.a-zA-Z0-9]*/[a-zA-Z][-+.a-zA-Z0-9]*" />
</restriction>
</simpleType>
<complexType name="PageType">
<sequence>
<!-- Title in text form. (Using spaces, not underscores; with namespace ) -->
<element name="title" type="string" />
<!-- Namespace in canonical form -->
<element name="ns" type="nonNegativeInteger" />
<!-- optional page ID number -->
<element name="id" type="positiveInteger" />
<!-- flag if the current revision is a redirect -->
<element name="redirect" type="mw:RedirectType" minOccurs="0" maxOccurs="1" />
<!-- comma-separated list of string tokens, if present -->
<element name="restrictions" type="string" minOccurs="0" />
<!-- Zero or more sets of revision or upload data -->
<choice minOccurs="0" maxOccurs="unbounded">
<element name="revision" type="mw:RevisionType" />
<element name="upload" type="mw:UploadType" />
</choice>
<!-- Zero or One sets of discussion threading data -->
<element name="discussionthreadinginfo" minOccurs="0" maxOccurs="1" type="mw:DiscussionThreadingInfo" />
</sequence>
</complexType>
<complexType name="RevisionType">
<sequence>
<element name="id" type="positiveInteger" />
<element name="parentid" type="positiveInteger" minOccurs="0" maxOccurs="1" />
<element name="timestamp" type="dateTime" />
<element name="contributor" type="mw:ContributorType" />
<element name="minor" minOccurs="0" maxOccurs="1" />
<element name="comment" type="mw:CommentType" minOccurs="0" maxOccurs="1" />
<!-- corresponds to slot origin for the main slot -->
<element name="origin" type="positiveInteger" />
<!-- the main slot's content model -->
<element name="model" type="mw:ContentModelType" />
<!-- the main slot's serialization format -->
<element name="format" type="mw:ContentFormatType" />
<!-- the main slot's serialized content -->
<element name="text" type="mw:TextType"/>
<element name="content" type="mw:ContentType" minOccurs="0" maxOccurs="unbounded"/>
<!-- sha1 of the revision, a combined sha1 of content in all slots -->
<element name="sha1" type="string" />
</sequence>
</complexType>
<complexType name="ContentType">
<sequence>
<!-- corresponds to slot role_name -->
<element name="role" type="mw:SlotRoleType" />
<!-- corresponds to slot origin -->
<element name="origin" type="positiveInteger" />
<element name="model" type="mw:ContentModelType" />
<element name="format" type="mw:ContentFormatType" />
<element name="text" type="mw:ContentTextType" />
</sequence>
</complexType>
<simpleType name="SlotRoleType">
<restriction base="string">
<pattern value="[a-zA-Z][-+./a-zA-Z0-9]*" />
</restriction>
</simpleType>
<complexType name="ContentTextType">
<simpleContent>
<extension base="string">
<attribute ref="xml:space" default="preserve" />
<!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
<attribute name="deleted" type="mw:DeletedFlagType" />
<attribute name="location" type="anyURI" />
<attribute name="sha1" type="string" />
<attribute name="bytes" type="nonNegativeInteger" />
</extension>
</simpleContent>
</complexType>
<complexType name="LogItemType">
<sequence>
<element name="id" type="positiveInteger" />
<element name="timestamp" type="dateTime" />
<element name="contributor" type="mw:ContributorType" />
<element name="comment" type="mw:CommentType" minOccurs="0" />
<element name="type" type="string" />
<element name="action" type="string" />
<element name="text" type="mw:LogTextType" minOccurs="0" maxOccurs="1" />
<element name="logtitle" type="string" minOccurs="0" maxOccurs="1" />
<element name="params" type="mw:LogParamsType" minOccurs="0" maxOccurs="1" />
</sequence>
</complexType>
<complexType name="CommentType">
<simpleContent>
<extension base="string">
<!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
<attribute name="deleted" type="mw:DeletedFlagType" />
</extension>
</simpleContent>
</complexType>
<complexType name="TextType">
<simpleContent>
<extension base="string">
<attribute ref="xml:space" default="preserve" />
<!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
<attribute name="deleted" type="mw:DeletedFlagType" />
<!-- This isn't a good idea; we should be using "ID" instead of "NMTOKEN" -->
<!-- However, "NMTOKEN" is strictest definition that is both compatible with existing -->
<!-- usage ([0-9]+) and with the "ID" type. -->
<attribute name="id" type="NMTOKEN" />
<attribute name="location" type="anyURI" />
<attribute name="sha1" type="string"/>
<attribute name="bytes" type="nonNegativeInteger" />
</extension>
</simpleContent>
</complexType>
<complexType name="LogTextType">
<simpleContent>
<extension base="string">
<!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
<attribute name="deleted" type="mw:DeletedFlagType" />
</extension>
</simpleContent>
</complexType>
<complexType name="LogParamsType">
<simpleContent>
<extension base="string">
<attribute ref="xml:space" default="preserve" />
</extension>
</simpleContent>
</complexType>
<complexType name="ContributorType">
<sequence>
<element name="username" type="string" minOccurs="0" />
<element name="id" type="nonNegativeInteger" minOccurs="0" />
<element name="ip" type="string" minOccurs="0" />
</sequence>
<!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
<attribute name="deleted" type="mw:DeletedFlagType" />
</complexType>
<complexType name="UploadType">
<sequence>
<!-- Revision-style data... -->
<element name="timestamp" type="dateTime" />
<element name="contributor" type="mw:ContributorType" />
<element name="comment" type="string" minOccurs="0" />
<!-- Filename. (Using underscores, not spaces. No 'File:' namespace marker.) -->
<element name="filename" type="string" />
<!-- URI at which this resource can be obtained -->
<element name="src" type="anyURI" />
<element name="size" type="positiveInteger" />
<!-- TODO: add other metadata fields -->
</sequence>
</complexType>
<!-- Discussion threading data for LiquidThreads -->
<complexType name="DiscussionThreadingInfo">
<sequence>
<element name="ThreadSubject" type="string" />
<element name="ThreadParent" type="positiveInteger" />
<element name="ThreadAncestor" type="positiveInteger" />
<element name="ThreadPage" type="string" />
<element name="ThreadID" type="positiveInteger" />
<element name="ThreadAuthor" type="string" />
<element name="ThreadEditStatus" type="string" />
<element name="ThreadType" type="string" />
</sequence>
</complexType>
</schema>