(bug 4220) dump schema get unique contraints on id

This patch was made in December 2005 by Elvis Stansvik on bug 4220, you
will find below the rewritten introduction for his patch contribution.

"""
The XML Schema for the XML dump format used by MediaWiki has no
constraints for the page and revision identifiers. This patch solve that
issue by enforcing the constraint in the XSD.

It most probably makes sense, since I think that:

 - some parsers capable of Schema validation can work more efficiently
   if constraints are in the XSD.
 - Another reason is that (however unlikely) some other software might
   output files in this format are not obliged to keep the IDs unique,
   according the the XSD in its current form.
"""

Updating the http://www.mediawiki.org/xml/export-0.7/ public URL is
tracked by bug 37111.

Change-Id: Idb82fe620c3395acaa8f051b4d4d0d770cd33d44

diff --git a/CREDITS b/CREDITS
index dcd4a43..89154a3 100644 (file)
--- a/CREDITS
+++ b/CREDITS
@@ -109,6 +109,7 @@ following names for their contribution to the product.
 * David Baumgarten
 * Denny Vrandecic
 * Edward Z. Yang
+* Elvis Stansvik
 * Erwin Dokter
 * FunPika
 * fomafix

diff --git a/RELEASE-NOTES-1.20 b/RELEASE-NOTES-1.20
index e40ec30..b5e7cce 100644 (file)
--- a/RELEASE-NOTES-1.20
+++ b/RELEASE-NOTES-1.20
@@ -63,6 +63,8 @@ upgrade PHP if you have not done so prior to upgrading MediaWiki.
   Arguments signature has changed. First arguments is now an options object of which
   'config' can be a property. Previously 'config' itself was the first and only argument.
 * New getCreator and getOldestRevision methods added to WikiPage class
+* (bug 4220) the XML dump format schema now have unique identity constraints
+  for page and revision identifiers. Patch by Elvis Stansvik.
 
 === Bug fixes in 1.20 ===
 * (bug 30245) Use the correct way to construct a log page title.

diff --git a/docs/export-0.7.xsd b/docs/export-0.7.xsd
new file mode 100644 (file)
index 0000000..0b2a9db
--- /dev/null
+++ b/docs/export-0.7.xsd
@@ -0,0 +1,240 @@
+<?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.
+       
+       The canonical URL to the schema document is:
+       http://www.mediawiki.org/xml/export-0.7.xsd
+       
+       Use the namespace:
+       http://www.mediawiki.org/xml/export-0.7/
+-->
+<schema xmlns="http://www.w3.org/2001/XMLSchema"
+        xmlns:mw="http://www.mediawiki.org/xml/export-0.7/"
+        targetNamespace="http://www.mediawiki.org/xml/export-0.7/"
+        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"/>
+               </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="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="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="positiveInteger"/>
+                       
+                       <!-- optional page ID number -->
+                       <element name="id" type="positiveInteger" minOccurs="0"/>
+                       
+                       <!-- flag if the current revision is a redirect -->
+                       <element name="redirect" type="string" minOccurs="0"/>  
+
+                       <!-- 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" />
+                               <element name="logitem" type="mw:LogItemType" />
+                       </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" minOccurs="0"/>
+                       <element name="timestamp" type="dateTime"/>
+                       <element name="contributor" type="mw:ContributorType"/>
+                       <element name="minor" minOccurs="0" />
+                       <element name="comment" type="mw:CommentType" minOccurs="0"/>
+                       <element name="sha1" type="string" />
+                       <element name="text" type="mw:TextType" />
+               </sequence>
+       </complexType>
+
+       <complexType name="LogItemType">
+               <sequence>
+                       <element name="id" type="positiveInteger" minOccurs="0"/>
+                       <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:TextType" />
+               </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" use="optional" type="mw:DeletedFlagType"/>
+                       </extension>
+               </simpleContent>
+       </complexType>
+
+
+       <complexType name="TextType">
+               <simpleContent>
+                       <extension base="string">
+                               <attribute ref="xml:space" use="optional" default="preserve" />
+                               <!-- This allows deleted=deleted on non-empty elements, but XSD is not omnipotent -->
+                               <attribute name="deleted" use="optional" 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="bytes" use="optional" type="nonNegativeInteger"/>
+                       </extension>
+               </simpleContent>
+       </complexType>
+       
+       <complexType name="ContributorType">
+               <sequence>
+                       <element name="username" type="string" minOccurs="0"/>
+                       <element name="id" type="positiveInteger" 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" use="optional" 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 'Image:' 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>