使用XPath计算节点的数量

本例主要涉及三点：
  1、计算XML中各个节点的数量
  2、输出符合特定条件的XML

  3、使用sum

 

首先，我们来看下使用XPath计算XML中各个节点的数量。

 

include REXML

def index
    xml = <<XML
  <root>
    <a>
      <name>ayz</name>
      <b>
        <c>g234</c>
      </b>
    </a>
    <a>
      <name>aerd</name>
      <b>
        <c>g554</c>
        <c>g564</c>
        <c>g664</c>
      </b>
      <b>
        <c>g5544</c>
      </b>
    </a>
    <a>
      <name>cyz</name>
      <b>
        <c>g734</c>
      </b>
    </a>
  </root>
XML

    doc = Document.new(xml)
    #输出a节点的数量
    a_num = XPath.first(doc.root, 'count(//a)')
    #输出b节点的数量
    b_num = XPath.first(doc.root, 'count(//b)')
    #输出c节点的数量
    c_num = XPath.first(doc.root, 'count(//c)')
    #输出d节点的数量
    d_num = XPath.first(doc.root, 'count(//d)')

    puts a_num  # => 3
    puts b_num  # => 4
    puts c_num  # => 6
    puts d_num  # => 0   
  end

 

接着，来看下使用XPath输出符合特定条件的XML。

 

    #输出所有a节点下b节点的数量小于2的b节点及其子节点
    b_node = XPath.match(doc.root, '//a[count(b) < 2]/b')
    #输出所有b节点下c节点的数量小于3的c节点
    c_node = XPath.match(doc.root, '//a[count(b//c) < 3]/b/c')
    
    puts b_node # => <b>
                #      <c>g234</c>
                 #    </b>
                 #    <b>
                 #     <c>g734</c>
                 #    </b>
    puts c_node # => <c>g234</c>
                 #   <c>g734</c>

 

xml = <<XML
<root>
  <item>1</item>
  <item>2</item>
  <item>3</item>
  <item>4</item>
  <item>5</item>
  <item>6</item>
  <item>7</item>
</root>
XML

    doc = Document.new(xml)
    #输出位置为3和4的节点
    node = XPath.match(doc.root,'item[position() > 2 and position() < 5]')
    puts node  # => <item>3</item>
               #     <item>4</item>

 

    xml = <<XML
<root>
  <summary><task>clean bathroom</task></summary>
  <records>
    <x>
      <summary><task>clean bath</task></summary>
      <records>
        <x><summary><task>rinse surfaces with water</task></summary><records/></x>
        <x><summary><task>apply pine fresh flash cleaner</task></summary><records/></x>
      </records>
    </x>
    <x>
      <summary><task>clean sink</task></summary>
      <records>
        <x><summary><task>remove items around the sink</task></summary><records/></x>
        <x><summary><task>using a sponge apply warm water to the sink surfaces</task></summary><records/></x>
      </records>
    </x>
    <x><summary><task>mop the floor</task></summary>records/></x>
  </records>
</root>
XML

    document = Document.new(xml)
    titles = []
    document.root.each_recursive do |elem|
      #输出所有task节点的内容
      titles << elem.text.to_s if elem.name == "task"
    end
    puts titles
    #clean bathroom
    #clean bath
    #rinse surfaces with water
    #apply pine fresh flash cleaner
    #clean sink
    #remove items around the sink
    #using a sponge apply warm water to the sink surfaces
    #mop the floor

 

    xml = <<XML
<list>
  <link>www.linux.com</link>
  <link>http://www.rubyforge.org</link>
  <link>www.learningruby.com</link>
  <link>http://snippets.dzone.com</link>
</list>
XML

    Document.new(xml).root.elements.each("link[starts-with(., 'http')]") do |node|
      puts node.text  # => http://www.rubyforge.org
                      #    http://snippets.dzone.com
    end

 

doc = Document.new("<a1><b1>3</b1><b1>5</b1><b1>1</b1><b1>7</b1><b1>9</b1></a1>")
a = doc.root.elements.to_a.sort {|x, y| x.text.to_s <=> y.text.to_s}
a.each {|x| puts x}
# => <b1>1</b1>
#    <b1>3</b1>
#    <b1>5</b1>
#    <b1>7</b1>
#    <b1>9</b1>

 

    xml = <<XML
<task>
  <summary><tags>reth, etrert, rtj64f, sitto</tags></summary>
  <records>
    <task>
      <summary><tags>retert, etert, rtu4f, sitto</tags></summary>
      <records>
        <task>
          <summary>
            <name>abcdef</name>
            <tags>jjy, rf57, lgk78</tags>
          </summary>
          <records>
          </records>
        </task>
      </records>
    </task>
  </records>
</task>
XML

    doc = Document.new(xml)
    doc.root.elements.each('//tags') {|element| element.parent.delete(element)}
    puts doc
    #<task>
    #  <summary/>
    #  <records>
    #    <task>
    #      <summary/>
    #      <records>
    #        <task>
    #          <summary>
    #            <name>abcdef</name>
    #          </summary>
    #          <records>
    #          </records>
    #        </task>
    #      </records>
    #    </task>
    #  </records>
    #</task>

 

xml = <<XML
<entries> 
 <entry id='93391' catid='0701'></entry>
  <entry id='93394' catid='0701'></entry>
  <entry id='93397' catid='0304'></entry> 
  <entry id='93400' catid='0506'></entry> 
  <entry id='94396' catid='0701'></entry> 
  <entry id='95398' catid='0701'></entry>
  <entry id='95610' catid='0506'></entry>
</entries>
XML

    document = Document.new(xml)
    puts document.root.elements['entry[last()]']  # => <entry id='95610' catid='0506'/> 
    p document.root.elements.each('entry/@catid').collect {|d| d.value}.uniq  # => ["0701", "0304", "0506"]

 

    xml = "<a><records><bun id='1'/><bun id='2'/><bun id='3'/><bun id='4'/></records></a>"
    doc = Document.new(xml)
    node_cake = Element.new("cake")
    node_bun = doc.root.elements['records/*[1]']
    node_bun.parent.insert_before(node_bun, node_cake)
    puts doc
    #<a><records><cake/><bun id='1'/><bun id='2'/><bun id='3'/><bun id='4'/></records></a>

 

doc = Document.new("<a><b>format's<c>just fine</c></b><b3><c/></b3></a>")
c = doc.root.elements.each('//c'){}
puts c
#<c>just fine</c>
#<c/>

 

最后，我们来看下关于sum的例子。

 

 items = <<ITEMS
<items>
  <item>2</item>
  <item>4</item>
</items>
ITEMS

    puts Document.new(items).root.elements['sum(item)']  # => 6.0

 

    items = <<ITEMS
<items>
  <item1>2</item1><item2>10</item2>
  <item1>4</item1><item2>20</item2>
</items>
ITEMS
    
    puts Document.new(items).root.elements['sum(item1 + item2)']  # => 12.0
    puts Document.new(items).root.elements['sum(item1[1] + item2[1])']  # => 12.0
    puts Document.new(items).root.elements['sum(item1[2] + item2[2])']  # => 24.0
    puts Document.new(items).root.elements['sum(sum(item1) + sum(item2))']  # => 36.0

 

评论

1 楼 pangyq 2010-02-02  

很实用啊。。