XML/XML Schema/pattern
Содержание
- 1 Define a comma-separated list ignoring whitespaces between values and commas
- 2 Define the intersection of the block L (all the letters) and the BasicLatin (ASCII characters below #x7F)
- 3 ISBN type by pattern
- 4 Oring and Grouping: "|" character is the "or" operator
- 5 The xs:pattern facet is the only facet that can be applied multiple times.
- 6 Unicode blocks
- 7 Use pattern to control the extension name of image type
- 8 Wildcard: integers that are multiples of 10
- 9 xs:pattern defines a pattern that must be matched by the lexical value of the datatype:
Define a comma-separated list ignoring whitespaces between values and commas
<?xml version="1.0"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru" xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xs:simpleType name="myType">
<xs:restriction base="xs:token">
<xs:pattern value="(1|2|3)( *, *(1|2|3))*" />
</xs:restriction>
</xs:simpleType>
</xs:schema>
Define the intersection of the block L (all the letters) and the BasicLatin (ASCII characters below #x7F)
<?xml version="1.0"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru" xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xs:simpleType name="BasicLatinLetters">
<xs:restriction>
<xs:simpleType>
<xs:restriction base="xs:token">
<xs:pattern value="\p{IsBasicLatin}*" />
</xs:restriction>
</xs:simpleType>
<xs:pattern value="\p{L}*" />
</xs:restriction>
</xs:simpleType>
</xs:schema>
ISBN type by pattern
File: Data.xml
<?xml version="1.0"?>
<Books xmlns="http://www.wbex.ru"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.wbex.ru Schema.xsd">
<Book>
<Title>title 1</Title>
<Author>author 1</Author>
<Date>2008</Date>
<ISBN>1-11111-111-1</ISBN>
<Publisher>Publisher 1</Publisher>
</Book>
<Book>
<Title>title 2</Title>
<Author>author 2</Author>
<Date>2007</Date>
<ISBN>0-111-11111-1</ISBN>
<Publisher>Publisher 2</Publisher>
</Book>
</Books>
File: Schema.xsd
<?xml version="1.0"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru"
xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xsd:simpleType name="ISBN-type">
<xsd:restriction base="xsd:string">
<xsd:pattern value="\d{1}-\d{5}-\d{3}-\d{1}|\d{1}-\d{3}-\d{5}-\d{1}|\d{1}-\d{2}-\d{6}-\d{1}"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:element name="Books">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="Book" maxOccurs="unbounded">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="Title" type="xsd:string"/>
<xsd:element name="Author" type="xsd:string"/>
<xsd:element name="Date" type="xsd:gYear"/>
<xsd:element name="ISBN" type="ISBN-type"/>
<xsd:element name="Publisher" type="xsd:string"/>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
</xsd:schema>
Oring and Grouping: "|" character is the "or" operator
<?xml version="1.0"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru" xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xs:simpleType name="myByte">
<xs:restriction base="xs:byte">
<xs:pattern value="1|2|3" />
</xs:restriction>
</xs:simpleType>
</xs:schema>
The xs:pattern facet is the only facet that can be applied multiple times.
<?xml version="1.0"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru" xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xsd:simpleType name="nonScientific">
<xsd:restriction base="xsd:float">
<xsd:pattern value="[^eE]*" />
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="noScientificNoLeading0">
<xsd:restriction base="nonScientific">
<xsd:pattern value="[^0].*" />
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>
Unicode blocks
<?xml version="1.0"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru" xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xs:simpleType name="BasicLatinToken">
<xs:restriction base="xs:token">
<xs:pattern value="\p{IsBasicLatin}*" />
</xs:restriction>
</xs:simpleType>
<xs:simpleType name="Latin-1Token">
<xs:restriction base="xs:token">
<xs:pattern value="[\p{IsBasicLatin}\p{IsLatin-1Supplement}]*" />
</xs:restriction>
</xs:simpleType>
</xs:schema>
Use pattern to control the extension name of image type
File: Data.xml
<?xml version="1.0"?>
<products xmlns ="http://www.wbex.ru"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.wbex.ru Schema.xsd">
<product>
<name>name 1</name>
<image>a.gif</image>
<description>description 1</description>
<warranty>lifetime warranty</warranty>
<cost>41.95</cost>
<retailer>http://www.wbex.ru</retailer>
</product>
<product>
<name>name 2</name>
<image>b.gif</image>
<description>description 2</description>
<cost>239.00</cost>
<retailer>http://www.wbex.ru</retailer>
</product>
</products>
File: Schema.xsd
<?xml version="1.0"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru"
xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xsd:element name="products">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="product" minOccurs="0" maxOccurs="unbounded">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="name" type="xsd:string"/>
<xsd:element name="image" type="imageType"/>
<xsd:element name="description" type="xsd:string"/>
<xsd:element name="warranty" type="xsd:string" minOccurs="0"/>
<xsd:element name="weight" type="xsd:positiveInteger" minOccurs="0"/>
<xsd:element name="cost" type="money" maxOccurs="unbounded"/>
<xsd:element name="retailer" type="xsd:anyURI"/>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
<xsd:simpleType name="money">
<xsd:restriction base="xsd:decimal">
<xsd:fractionDigits value="2"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="imageType">
<xsd:restriction base="xsd:string">
<xsd:pattern value="(.)+\.(gif|jpg|jpeg|bmp)"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>
Wildcard: integers that are multiples of 10
<?xml version="1.0"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru"
xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xs:simpleType name="multipleOfTen">
<xs:restriction base="xs:integer">
<xs:pattern value=".*0" />
</xs:restriction>
</xs:simpleType>
</xs:schema>
xs:pattern defines a pattern that must be matched by the lexical value of the datatype:
<?xml version="1.0"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://www.wbex.ru" xmlns="http://www.wbex.ru"
elementFormDefault="qualified">
<xsd:simpleType name="nonScientific">
<xsd:restriction base="xsd:float">
<xsd:pattern value="[^eE]*" />
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="noLeading0">
<xsd:restriction base="xsd:float">
<xsd:pattern value="[^0].*" />
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>