nokogiri 1.1.1-java

data/lib/nokogiri/xml/notation.rb

@@ -0,0 +1,6 @@
+module Nokogiri
+  module XML
+    class Notation < Struct.new(:name, :public_id, :system_id)
+    end
+  end
+end

data/lib/nokogiri/xml/reader.rb

@@ -0,0 +1,20 @@
+module Nokogiri
+  module XML
+    class Reader
+      include Enumerable
+
+      def attributes
+        Hash[*(attribute_nodes.map { |node|
+          [node.name, node.to_s]
+        }.flatten)].merge(namespaces || {})
+      end
+
+      def each(&block)
+        while node = self.read
+          block.call(node)
+        end
+      end
+      private :initialize
+    end
+  end
+end

data/lib/nokogiri/xml/sax.rb

@@ -0,0 +1,9 @@
+require 'nokogiri/xml/sax/document'
+require 'nokogiri/xml/sax/parser'
+
+module Nokogiri
+  module XML
+    module SAX
+    end
+  end
+end

data/lib/nokogiri/xml/sax/document.rb

@@ -0,0 +1,59 @@
+module Nokogiri
+  module XML
+    module SAX
+      class Document
+        ###
+        # Called when document starts parsing
+        def start_document
+        end
+
+        ###
+        # Called when document ends parsing
+        def end_document
+        end
+
+        ###
+        # Called at the beginning of an element
+        # +name+ is the name of the tag with +attrs+ as attributes
+        def start_element name, attrs = []
+        end
+
+        ###
+        # Called at the end of an element
+        # +name+ is the tag name
+        def end_element name
+        end
+
+        ###
+        # Characters read between a tag
+        # +string+ contains the character data
+        def characters string
+        end
+
+        ###
+        # Called when comments are encountered
+        # +string+ contains the comment data
+        def comment string
+        end
+
+        ###
+        # Called on document warnings
+        # +string+ contains the warning
+        def warning string
+        end
+
+        ###
+        # Called on document errors
+        # +string+ contains the error
+        def error string
+        end
+
+        ###
+        # Called when cdata blocks are found
+        # +string+ contains the cdata content
+        def cdata_block string
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/sax/parser.rb

@@ -0,0 +1,37 @@
+module Nokogiri
+  module XML
+    module SAX
+      class Parser
+        attr_accessor :document
+        def initialize(doc = XML::SAX::Document.new)
+          @document = doc
+        end
+
+        ###
+        # Parse given +thing+ which may be a string containing xml, or an
+        # IO object.
+        def parse thing
+          if thing.respond_to?(:read) && thing.respond_to?(:close)
+            parse_io(thing)
+          else
+            parse_memory(thing)
+          end
+        end
+
+        ###
+        # Parse given +io+
+        def parse_io io, encoding = 0
+          native_parse_io io, encoding
+        end
+
+        ###
+        # Parse a file with +filename+
+        def parse_file filename
+          raise Errno::ENOENT unless File.exists?(filename)
+          raise Errno::EISDIR if File.directory?(filename)
+          native_parse_file filename
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/syntax_error.rb

@@ -0,0 +1,21 @@
+module Nokogiri
+  module XML
+    class SyntaxError < SyntaxError
+      def none?
+        level == 0
+      end
+
+      def warning?
+        level == 1
+      end
+
+      def error?
+        level == 2
+      end
+
+      def fatal?
+        level == 3
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/text.rb

@@ -0,0 +1,6 @@
+module Nokogiri
+  module XML
+    class Text < Node
+    end
+  end
+end

data/lib/nokogiri/xml/xpath.rb

@@ -0,0 +1,10 @@
+require 'nokogiri/xml/xpath/syntax_error'
+
+module Nokogiri
+  module XML
+    class XPath
+      attr_accessor :document
+
+    end
+  end
+end

data/lib/nokogiri/xml/xpath/syntax_error.rb

@@ -0,0 +1,8 @@
+module Nokogiri
+  module XML
+    class XPath
+      class SyntaxError < ::SyntaxError
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/xpath_context.rb

@@ -0,0 +1,14 @@
+module Nokogiri
+  module XML
+    class XPathContext
+
+      def register_namespaces(namespaces)
+        namespaces.each do |k, v|
+          k = k.gsub(/.*:/,'') # strip off 'xmlns:' or 'xml:'
+          register_ns(k, v)
+        end
+      end
+
+    end
+  end
+end

data/lib/nokogiri/xslt.rb

@@ -0,0 +1,28 @@
+require 'nokogiri/xslt/stylesheet'
+
+module Nokogiri
+  module XSLT
+    class << self
+      def parse(string)
+        Stylesheet.parse_stylesheet_doc(XML.parse(string))
+      end
+      
+      def quote_params params
+        parray = (params.instance_of?(Hash) ? params.to_a.flatten : params).dup
+        parray.each_with_index do |v,i|
+          if i % 2 > 0
+            parray[i]=
+              if v =~ /'/
+                "concat('#{ v.gsub(/'/, %q{', "'", '}) }')"
+              else
+                "'#{v}'";
+              end
+          else
+            parray[i] = v.to_s
+          end
+        end
+        parray.flatten
+      end
+    end
+  end
+end

data/lib/nokogiri/xslt/stylesheet.rb

@@ -0,0 +1,6 @@
+module Nokogiri
+  module XSLT
+    class Stylesheet
+    end
+  end
+end

data/test/css/test_nthiness.rb

@@ -0,0 +1,159 @@
+require File.expand_path(File.join(File.dirname(__FILE__), '..', "helper"))
+
+module Nokogiri
+  module CSS
+    class TestNthiness < Nokogiri::TestCase
+      def setup
+        doc = <<EOF
+<html>
+<table>
+  <tr><td>row1 </td></tr>
+  <tr><td>row2 </td></tr>
+  <tr><td>row3 </td></tr>
+  <tr><td>row4 </td></tr>
+  <tr><td>row5 </td></tr>
+  <tr><td>row6 </td></tr>
+  <tr><td>row7 </td></tr>
+  <tr><td>row8 </td></tr>
+  <tr><td>row9 </td></tr>
+  <tr><td>row10 </td></tr>
+  <tr><td>row11 </td></tr>
+  <tr><td>row12 </td></tr>
+  <tr><td>row13 </td></tr>
+  <tr><td>row14 </td></tr>
+</table>
+<div>
+  <b>bold1 </b>
+  <i>italic1 </i>
+  <b>bold2 </b>
+  <i>italic2 </i>
+  <p>para1 </p>
+  <b>bold3 </b>
+</div>
+<div>
+  <p>para2 </p>
+  <p>para3 </p>
+</div>
+<div>
+  <p>para4 </p>
+</div>
+<p class='empty'></p>
+<p class='not-empty'><b></b></p>
+</html>
+EOF
+        @parser = Nokogiri.Hpricot doc
+      end
+
+
+      def test_even
+        assert_result_rows [2,4,6,8,10,12,14], @parser.search("table/tr:nth(even)")
+      end
+
+      def test_odd
+        assert_result_rows [1,3,5,7,9,11,13], @parser.search("table/tr:nth(odd)")
+      end
+
+      def test_2n
+        assert_equal @parser.search("table/tr:nth(even)").inner_text, @parser.search("table/tr:nth(2n)").inner_text
+      end
+
+      def test_2np1
+        assert_equal @parser.search("table/tr:nth(odd)").inner_text, @parser.search("table/tr:nth(2n+1)").inner_text
+      end
+
+      def test_4np3
+        assert_result_rows [3,7,11], @parser.search("table/tr:nth(4n+3)")
+      end
+
+      def test_3np4
+        assert_result_rows [4,7,10,13], @parser.search("table/tr:nth(3n+4)")
+      end
+
+      def test_mnp3
+        assert_result_rows [1,2,3], @parser.search("table/tr:nth(-n+3)")
+      end
+
+      def test_np3
+        assert_result_rows [3,4,5,6,7,8,9,10,11,12,13,14], @parser.search("table/tr:nth(n+3)")
+      end
+
+      def test_first
+        assert_result_rows [1], @parser.search("table/tr:first")
+        assert_result_rows [1], @parser.search("table/tr:first()")
+      end
+
+      def test_last
+        assert_result_rows [14], @parser.search("table/tr:last")
+        assert_result_rows [14], @parser.search("table/tr:last()")
+      end
+
+      def test_first_child
+        assert_result_rows [1], @parser.search("div/b:first-child"), "bold"
+        assert_result_rows [1], @parser.search("table/tr:first-child")
+      end
+
+      def test_last_child
+        assert_result_rows [3], @parser.search("div/b:last-child"), "bold"
+        assert_result_rows [14], @parser.search("table/tr:last-child")
+      end
+
+      def test_first_of_type
+        assert_result_rows [1], @parser.search("table/tr:first-of-type")
+        assert_result_rows [1], @parser.search("div/b:first-of-type"), "bold"
+      end
+
+      def test_last_of_type
+        assert_result_rows [14], @parser.search("table/tr:last-of-type")
+        assert_result_rows [3], @parser.search("div/b:last-of-type"), "bold"
+      end
+
+      def test_only_of_type
+        assert_result_rows [1,4], @parser.search("div/p:only-of-type"), "para"
+      end
+
+      def test_only_child
+        assert_result_rows [4], @parser.search("div/p:only-child"), "para"
+      end
+
+      def test_empty
+        result = @parser.search("p:empty")
+        assert_equal 1, result.size, "unexpected number of rows returned: '#{result.inner_text}'"
+        assert_equal 'empty', result.first['class']
+      end
+
+      def test_parent
+        result = @parser.search("p:parent")
+        assert_equal 5, result.size
+        0.upto(3) do |j|
+          assert_equal "para#{j+1} ", result[j].inner_text
+        end
+        assert_equal "not-empty", result[4]['class']
+      end
+
+      def test_siblings
+        doc = <<-EOF
+<html><body><div>
+<p id="1">p1 </p>
+<p id="2">p2 </p>
+<p id="3">p3 </p>
+<p id="4">p4 </p>
+<p id="5">p5 </p>
+EOF
+        parser = Nokogiri.Hpricot doc
+        
+        assert_equal 2, parser.search("#3 ~ p").size
+        assert_equal "p4 p5 ", parser.search("#3 ~ p").inner_text
+        assert_equal 0, parser.search("#5 ~ p").size
+
+        assert_equal 1, parser.search("#3 + p").size
+        assert_equal "p4 ", parser.search("#3 + p").inner_text
+        assert_equal 0, parser.search("#5 + p").size
+      end
+
+      def assert_result_rows intarray, result, word="row"
+        assert_equal intarray.size, result.size, "unexpected number of rows returned: '#{result.inner_text}'"
+        assert_equal intarray.map{|j| "#{word}#{j}"}.join(' '), result.inner_text.strip, result.inner_text
+      end
+    end
+  end
+end

data/test/css/test_parser.rb

@@ -0,0 +1,237 @@
+require File.expand_path(File.join(File.dirname(__FILE__), '..', "helper"))
+
+module Nokogiri
+  module CSS
+    class TestParser < Nokogiri::TestCase
+      def setup
+        @parser = Nokogiri::CSS::Parser.new
+      end
+
+      def test_syntax_error_raised
+        assert_raises(CSS::SyntaxError) { @parser.parse("a[x=]") }
+      end
+
+      def test_find_by_type
+        ast = @parser.parse("a:nth-child(2)").first
+        matches = ast.find_by_type(
+          [:CONDITIONAL_SELECTOR,
+            [:ELEMENT_NAME],
+            [:PSEUDO_CLASS,
+              [:FUNCTION]
+            ]
+          ]
+        )
+        assert_equal(1, matches.length)
+        assert_equal(ast, matches.first)
+      end
+
+      def test_to_type
+        ast = @parser.parse("a:nth-child(2)").first
+        assert_equal(
+          [:CONDITIONAL_SELECTOR,
+            [:ELEMENT_NAME],
+            [:PSEUDO_CLASS,
+              [:FUNCTION]
+            ]
+          ], ast.to_type
+        )
+      end
+
+      def test_to_a
+        asts = @parser.parse("a:nth-child(2)")
+        assert_equal(
+          [:CONDITIONAL_SELECTOR,
+            [:ELEMENT_NAME, ["a"]],
+            [:PSEUDO_CLASS,
+              [:FUNCTION, ["nth-child("], ["2"]]
+            ]
+          ], asts.first.to_a
+        )
+      end
+
+      def test_function_with_arguments
+        assert_xpath  "//*[position() = 2 and self::a]",
+                      @parser.parse("a[2]")
+        assert_xpath  "//*[position() = 2 and self::a]",
+                      @parser.parse("a:nth-child(2)")
+      end
+
+      def test_carrot
+        assert_xpath  "//a[starts-with(@id, 'Boing')]",
+                      @parser.parse("a[id^='Boing']")
+      end
+
+      def test_attributes_with_at
+        ## This is non standard CSS
+        assert_xpath  "//a[@id = 'Boing']",
+                      @parser.parse("a[@id='Boing']")
+      end
+
+      def test_not_equal
+        ## This is non standard CSS
+        assert_xpath  "//a[child::text() != 'Boing']",
+                      @parser.parse("a[text()!='Boing']")
+      end
+
+      def test_function
+        ## This is non standard CSS
+        assert_xpath  "//a[child::text()]",
+                      @parser.parse("a[text()]")
+
+        ## This is non standard CSS
+        assert_xpath  "//child::text()",
+                      @parser.parse("text()")
+
+        ## This is non standard CSS
+        assert_xpath  "//a[contains(child::text(), 'Boing')]",
+                      @parser.parse("a[text()*='Boing']")
+
+        ## This is non standard CSS
+        assert_xpath  "//script//comment()",
+                      @parser.parse("script comment()")
+      end
+
+      def test_nonstandard_nth_selectors
+        ## These are non standard CSS
+        assert_xpath '//a[position() = 99]', @parser.parse('a:eq(99)')
+        assert_xpath '//a[position() = 1]', @parser.parse('a:first') # no parens
+        assert_xpath '//a[position() = last()]', @parser.parse('a:last') # no parens
+        assert_xpath '//a[position() = 99]', @parser.parse('a:nth(99)')
+        assert_xpath '//a[position() = 1]', @parser.parse('a:first()')
+        assert_xpath '//a[position() = last()]', @parser.parse('a:last()')
+        assert_xpath '//a[node()]', @parser.parse('a:parent')
+      end
+
+      def test_standard_nth_selectors
+        assert_xpath '//a[position() = 99]', @parser.parse('a:nth-of-type(99)')
+        assert_xpath '//a[position() = 1]', @parser.parse('a:first-of-type()')
+        assert_xpath '//a[position() = last()]', @parser.parse('a:last-of-type()')
+        assert_xpath '//a[position() = 1]', @parser.parse('a:first-of-type') # no parens
+        assert_xpath '//a[position() = last()]', @parser.parse('a:last-of-type') # no parens
+        assert_xpath '//a[position() = last() - 99]', @parser.parse('a:nth-last-of-type(99)')
+        assert_xpath '//a[position() = last() - 99]', @parser.parse('a:nth-last-of-type(99)')
+      end
+
+      def test_nth_child_selectors
+        assert_xpath '//*[position() = 1 and self::a]', @parser.parse('a:first-child')
+        assert_xpath '//*[position() = last() and self::a]', @parser.parse('a:last-child')
+        assert_xpath '//*[position() = 99 and self::a]', @parser.parse('a:nth-child(99)')
+        assert_xpath '//*[position() = last() - 99 and self::a]', @parser.parse('a:nth-last-child(99)')
+      end
+
+      def test_miscellaneous_selectors
+        assert_xpath '//*[last() = 1 and self::a]',
+          @parser.parse('a:only-child')
+        assert_xpath '//a[last() = 1]', @parser.parse('a:only-of-type')
+        assert_xpath '//a[not(node())]', @parser.parse('a:empty')
+      end
+
+      def test_nth_a_n_plus_b
+        assert_xpath '//a[(position() mod 2) = 0]', @parser.parse('a:nth-of-type(2n)')
+        assert_xpath '//a[(position() >= 1) and (((position()-1) mod 2) = 0)]', @parser.parse('a:nth-of-type(2n+1)')
+        assert_xpath '//a[(position() mod 2) = 0]', @parser.parse('a:nth-of-type(even)')
+        assert_xpath '//a[(position() >= 1) and (((position()-1) mod 2) = 0)]', @parser.parse('a:nth-of-type(odd)')
+        assert_xpath '//a[(position() >= 3) and (((position()-3) mod 4) = 0)]', @parser.parse('a:nth-of-type(4n+3)')
+        assert_xpath '//a[(position() <= 3) and (((position()-3) mod 1) = 0)]', @parser.parse('a:nth-of-type(-1n+3)')
+        assert_xpath '//a[(position() <= 3) and (((position()-3) mod 1) = 0)]', @parser.parse('a:nth-of-type(-n+3)')
+        assert_xpath '//a[(position() >= 3) and (((position()-3) mod 1) = 0)]', @parser.parse('a:nth-of-type(1n+3)')
+        assert_xpath '//a[(position() >= 3) and (((position()-3) mod 1) = 0)]', @parser.parse('a:nth-of-type(n+3)')
+      end
+
+      def test_preceding_selector
+        assert_xpath  "//F[preceding-sibling::E]",
+                      @parser.parse("E ~ F")
+      end
+
+      def test_direct_preceding_selector
+        assert_xpath  "//E/following-sibling::*[1]/self::F",
+                      @parser.parse("E + F")
+      end
+
+      def test_attribute
+        assert_xpath  "//h1[@a = 'Tender Lovemaking']",
+                      @parser.parse("h1[a='Tender Lovemaking']")
+      end
+
+      def test_id
+        assert_xpath "//*[@id = 'foo']", @parser.parse('#foo')
+      end
+
+      def test_pseudo_class_no_ident
+        assert_xpath "//*[link(.)]", @parser.parse(':link')
+      end
+
+      def test_pseudo_class
+        assert_xpath "//a[link(.)]", @parser.parse('a:link')
+        assert_xpath "//a[visited(.)]", @parser.parse('a:visited')
+        assert_xpath "//a[hover(.)]", @parser.parse('a:hover')
+        assert_xpath "//a[active(.)]", @parser.parse('a:active')
+        assert_xpath  "//a[active(.) and contains(concat(' ', @class, ' '), ' foo ')]",
+                      @parser.parse('a:active.foo')
+      end
+
+      def test_star
+        assert_xpath "//*", @parser.parse('*')
+        assert_xpath "//*[contains(concat(' ', @class, ' '), ' pastoral ')]",
+                      @parser.parse('*.pastoral')
+      end
+
+      def test_class
+        assert_xpath  "//*[contains(concat(' ', @class, ' '), ' a ') and contains(concat(' ', @class, ' '), ' b ')]",
+                      @parser.parse('.a.b')
+        assert_xpath  "//*[contains(concat(' ', @class, ' '), ' awesome ')]",
+                      @parser.parse('.awesome')
+        assert_xpath  "//foo[contains(concat(' ', @class, ' '), ' awesome ')]",
+                      @parser.parse('foo.awesome')
+        assert_xpath  "//foo//*[contains(concat(' ', @class, ' '), ' awesome ')]",
+                      @parser.parse('foo .awesome')
+      end
+
+      def test_not_so_simple_not
+        assert_xpath "//*[@id = 'p' and not(contains(concat(' ', @class, ' '), ' a '))]",
+                     @parser.parse('#p:not(.a)')
+        assert_xpath "//p[contains(concat(' ', @class, ' '), ' a ') and not(contains(concat(' ', @class, ' '), ' b '))]",
+                     @parser.parse('p.a:not(.b)')
+        assert_xpath "//p[@a = 'foo' and not(contains(concat(' ', @class, ' '), ' b '))]",
+                     @parser.parse("p[a='foo']:not(.b)")
+      end
+
+      def test_ident
+        assert_xpath '//x', @parser.parse('x')
+      end
+
+      def test_parse_space
+        assert_xpath '//x//y', @parser.parse('x y')
+      end
+
+      def test_parse_descendant
+        assert_xpath '//x/y', @parser.parse('x > y')
+      end
+
+      def test_parse_slash
+        ## This is non standard CSS
+        assert_xpath '//x/y', @parser.parse('x/y')
+      end
+
+      def test_parse_doubleslash
+        ## This is non standard CSS
+        assert_xpath '//x//y', @parser.parse('x//y')
+      end
+
+      def test_multi_path
+        assert_xpath ['//x/y', '//y/z'], @parser.parse('x > y, y > z')
+        assert_xpath ['//x/y', '//y/z'], @parser.parse('x > y,y > z')
+        ###
+        # TODO: should we make this work?
+        # assert_xpath ['//x/y', '//y/z'], @parser.parse('x > y | y > z')
+      end
+
+      def assert_xpath expecteds, asts
+        expecteds = [expecteds].flatten
+        expecteds.zip(asts).each do |expected, actual|
+          assert_equal expected, actual.to_xpath
+        end
+      end
+    end
+  end
+end