在Ruby中处理XML和XSLT以及XPath的简单教程

#!/usr/bin/ruby -w
 
require 'rexml/document'
include REXML
 
xmlfile = File.new("movies.xml")
xmldoc = Document.new(xmlfile)
 
# 获取 root 元素
root = xmldoc.root
puts "Root element : " + root.attributes["shelf"]
 
# 以下将输出电影标题
xmldoc.elements.each("collection/movie"){
  |e| puts "Movie Title : " + e.attributes["title"]
}
 
# 以下将输出所有电影类型
xmldoc.elements.each("collection/movie/type") {
  |e| puts "Movie Type : " + e.text
}
 
# 以下将输出所有电影描述
xmldoc.elements.each("collection/movie/description") {
  |e| puts "Movie Description : " + e.text
}

Root element : New Arrivals
Movie Title : Enemy Behind
Movie Title : Transformers
Movie Title : Trigun
Movie Title : Ishtar
Movie Type : War, Thriller
Movie Type : Anime, Science Fiction
Movie Type : Anime, Action
Movie Type : Comedy
Movie Description : Talk about a US-Japan war
Movie Description : A schientific fiction
Movie Description : Vash the Stampede!
Movie Description : Viewable boredom
SAX-like Parsing:

#!/usr/bin/ruby -w
 
require 'rexml/document'
require 'rexml/streamlistener'
include REXML
 
 
class MyListener
 include REXML::StreamListener
 def tag_start(*args)
  puts "tag_start: #{args.map {|x| x.inspect}.join(', ')}"
 end
 
 def text(data)
  return if data =~ /^\w*$/   # whitespace only
  abbrev = data[0..40] + (data.length > 40 "..." : "")
  puts " text  :  #{abbrev.inspect}"
 end
end
 
list = MyListener.new
xmlfile = File.new("movies.xml")
Document.parse_stream(xmlfile, list)

tag_start: "collection", {"shelf"=>"New Arrivals"}
tag_start: "movie", {"title"=>"Enemy Behind"}
tag_start: "type", {}
 text  :  "War, Thriller"
tag_start: "format", {}
tag_start: "year", {}
tag_start: "rating", {}
tag_start: "stars", {}
tag_start: "description", {}
 text  :  "Talk about a US-Japan war"
tag_start: "movie", {"title"=>"Transformers"}
tag_start: "type", {}
 text  :  "Anime, Science Fiction"
tag_start: "format", {}
tag_start: "year", {}
tag_start: "rating", {}
tag_start: "stars", {}
tag_start: "description", {}
 text  :  "A schientific fiction"
tag_start: "movie", {"title"=>"Trigun"}
tag_start: "type", {}
 text  :  "Anime, Action"
tag_start: "format", {}
tag_start: "episodes", {}
tag_start: "rating", {}
tag_start: "stars", {}
tag_start: "description", {}
 text  :  "Vash the Stampede!"
tag_start: "movie", {"title"=>"Ishtar"}
tag_start: "type", {}
tag_start: "format", {}
tag_start: "rating", {}
tag_start: "stars", {}
tag_start: "description", {}
 text  :  "Viewable boredom"

#!/usr/bin/ruby -w
 
require 'rexml/document'
include REXML
 
xmlfile = File.new("movies.xml")
xmldoc = Document.new(xmlfile)
 
# 第一个电影的信息
movie = XPath.first(xmldoc, "//movie")
p movie
 
# 打印所有电影类型
XPath.each(xmldoc, "//type") { |e| puts e.text }
 
# 获取所有电影格式的类型，返回数组
names = XPath.match(xmldoc, "//format").map {|x| x.text }
p names

<movie title='Enemy Behind'> ... </>
War, Thriller
Anime, Science Fiction
Anime, Action
Comedy
["DVD", "DVD", "DVD", "VHS"]

ruby xslt.rb stylesheet.xsl document.xml [arguments]

require "xslt"
 
stylesheet = File.readlines("stylesheet.xsl").to_s
xml_doc = File.readlines("document.xml").to_s
arguments = { 'image_dir' => '/....' }
 
sheet = XSLT::Stylesheet.new( stylesheet, arguments )
 
# output to StdOut
sheet.apply( xml_doc )
 
# output to 'str'
str = ""
sheet.output = [ str ]
sheet.apply( xml_doc )