rubysl-rexml 1.0.0

data/lib/rexml/quickpath.rb

@@ -0,0 +1,266 @@
+require 'rexml/functions'
+require 'rexml/xmltokens'
+
+module REXML
+	class QuickPath
+		include Functions
+		include XMLTokens
+
+		EMPTY_HASH = {}
+
+		def QuickPath::first element, path, namespaces=EMPTY_HASH
+			match(element, path, namespaces)[0]
+		end
+
+		def QuickPath::each element, path, namespaces=EMPTY_HASH, &block
+			path = "*" unless path
+			match(element, path, namespaces).each( &block )
+		end
+
+		def QuickPath::match element, path, namespaces=EMPTY_HASH
+			raise "nil is not a valid xpath" unless path
+			results = nil
+			Functions::namespace_context = namespaces
+			case path
+			when /^\/([^\/]|$)/u
+				# match on root
+				path = path[1..-1]
+				return [element.root.parent] if path == ''
+				results = filter([element.root], path)
+			when /^[-\w]*::/u
+				results = filter([element], path)
+			when /^\*/u
+				results = filter(element.to_a, path)
+			when /^[\[!\w:]/u
+				# match on child
+				matches = []
+				children = element.to_a
+				results = filter(children, path)
+			else
+				results = filter([element], path)
+			end
+			return results
+		end
+
+		# Given an array of nodes it filters the array based on the path. The
+		# result is that when this method returns, the array will contain elements
+		# which match the path
+		def QuickPath::filter elements, path
+			return elements if path.nil? or path == '' or elements.size == 0
+			case path
+			when /^\/\//u											# Descendant
+				return axe( elements, "descendant-or-self", $' )
+			when /^\/?\b(\w[-\w]*)\b::/u							# Axe
+				axe_name = $1
+				rest = $'
+				return axe( elements, $1, $' )
+			when /^\/(?=\b([:!\w][-\.\w]*:)?[-!\*\.\w]*\b([^:(]|$)|\*)/u	# Child
+				rest = $'
+				results = []
+				elements.each do |element|
+					results |= filter( element.to_a, rest )
+				end
+				return results
+			when /^\/?(\w[-\w]*)\(/u							# / Function
+				return function( elements, $1, $' )
+			when Namespace::NAMESPLIT		# Element name
+				name = $2
+				ns = $1
+				rest = $'
+				elements.delete_if do |element|
+					!(element.kind_of? Element and 
+						(element.expanded_name == name or
+						 (element.name == name and
+						  element.namespace == Functions.namespace_context[ns])))
+				end
+				return filter( elements, rest )
+			when /^\/\[/u
+				matches = []
+				elements.each do |element|
+					matches |= predicate( element.to_a, path[1..-1] ) if element.kind_of? Element
+				end
+				return matches
+			when /^\[/u												# Predicate
+				return predicate( elements, path )
+			when /^\/?\.\.\./u										# Ancestor
+				return axe( elements, "ancestor", $' )
+			when /^\/?\.\./u											# Parent
+				return filter( elements.collect{|e|e.parent}, $' )
+			when /^\/?\./u												# Self
+				return filter( elements, $' )
+			when /^\*/u													# Any
+				results = []
+				elements.each do |element|
+					results |= filter( [element], $' ) if element.kind_of? Element
+					#if element.kind_of? Element
+					#	children = element.to_a
+					#	children.delete_if { |child| !child.kind_of?(Element) }
+					#	results |= filter( children, $' )
+					#end
+				end
+				return results
+			end
+			return []
+		end
+
+		def QuickPath::axe( elements, axe_name, rest )
+			matches = []
+			matches = filter( elements.dup, rest ) if axe_name =~ /-or-self$/u
+			case axe_name
+			when /^descendant/u
+				elements.each do |element|
+					matches |= filter( element.to_a, "descendant-or-self::#{rest}" ) if element.kind_of? Element
+				end
+			when /^ancestor/u
+				elements.each do |element|
+					while element.parent
+						matches << element.parent
+						element = element.parent
+					end
+				end
+				matches = filter( matches, rest )
+			when "self"
+				matches = filter( elements, rest )
+			when "child"
+				elements.each do |element|
+					matches |= filter( element.to_a, rest ) if element.kind_of? Element
+				end
+			when "attribute"
+				elements.each do |element|
+					matches << element.attributes[ rest ] if element.kind_of? Element
+				end
+			when "parent"
+				matches = filter(elements.collect{|element| element.parent}.uniq, rest)
+			when "following-sibling"
+				matches = filter(elements.collect{|element| element.next_sibling}.uniq,
+					rest)
+			when "previous-sibling"
+				matches = filter(elements.collect{|element| 
+					element.previous_sibling}.uniq, rest )
+			end
+			return matches.uniq
+		end
+
+		# A predicate filters a node-set with respect to an axis to produce a
+		# new node-set. For each node in the node-set to be filtered, the 
+		# PredicateExpr is evaluated with that node as the context node, with 
+		# the number of nodes in the node-set as the context size, and with the 
+		# proximity position of the node in the node-set with respect to the
+		# axis as the context position; if PredicateExpr evaluates to true for
+		# that node, the node is included in the new node-set; otherwise, it is
+		# not included.
+		#
+		# A PredicateExpr is evaluated by evaluating the Expr and converting
+		# the result to a boolean. If the result is a number, the result will
+		# be converted to true if the number is equal to the context position
+		# and will be converted to false otherwise; if the result is not a
+		# number, then the result will be converted as if by a call to the
+		# boolean function. Thus a location path para[3] is equivalent to
+		# para[position()=3].
+		def QuickPath::predicate( elements, path ) 
+			ind = 1
+			bcount = 1
+			while bcount > 0
+				bcount += 1 if path[ind] == ?[
+				bcount -= 1 if path[ind] == ?]
+				ind += 1
+			end
+			ind -= 1
+			predicate = path[1..ind-1]
+			rest = path[ind+1..-1]
+
+			# have to change 'a [=<>] b [=<>] c' into 'a [=<>] b and b [=<>] c'
+			predicate.gsub!( /([^\s(and)(or)<>=]+)\s*([<>=])\s*([^\s(and)(or)<>=]+)\s*([<>=])\s*([^\s(and)(or)<>=]+)/u ) { 
+				"#$1 #$2 #$3 and #$3 #$4 #$5"
+			}
+			# Let's do some Ruby trickery to avoid some work:
+			predicate.gsub!( /&/u, "&&" )
+			predicate.gsub!( /=/u, "==" )
+			predicate.gsub!( /@(\w[-\w.]*)/u ) {
+				"attribute(\"#$1\")" 
+			}
+			predicate.gsub!( /\bmod\b/u, "%" )
+			predicate.gsub!( /\b(\w[-\w.]*\()/u ) {
+				fname = $1
+				fname.gsub( /-/u, "_" )
+			}
+			
+			Functions.pair = [ 0, elements.size ]
+			results = []
+			elements.each do |element|
+				Functions.pair[0] += 1
+				Functions.node = element
+				res = eval( predicate )
+				case res
+				when true
+					results << element
+				when Fixnum
+					results << element if Functions.pair[0] == res
+				when String
+					results << element
+				end
+			end
+			return filter( results, rest )
+		end
+
+		def QuickPath::attribute( name )
+			return Functions.node.attributes[name] if Functions.node.kind_of? Element
+		end
+
+		def QuickPath::name()
+			return Functions.node.name if Functions.node.kind_of? Element
+		end
+
+		def QuickPath::method_missing( id, *args )
+			begin
+				Functions.send( id.id2name, *args )
+			rescue Exception
+				raise "METHOD: #{id.id2name}(#{args.join ', '})\n#{$!.message}"
+			end
+		end
+
+		def QuickPath::function( elements, fname, rest )
+			args = parse_args( elements, rest )
+			Functions.pair = [0, elements.size]
+			results = []
+			elements.each do |element|
+				Functions.pair[0] += 1
+				Functions.node = element
+				res = Functions.send( fname, *args )
+				case res
+				when true
+					results << element
+				when Fixnum
+					results << element if Functions.pair[0] == res
+				end
+			end
+			return results
+		end
+
+		def QuickPath::parse_args( element, string )
+			# /.*?(?:\)|,)/
+			arguments = []
+			buffer = ""
+			while string and string != ""
+				c = string[0]
+				string.sub!(/^./u, "")
+				case c
+				when ?,
+					# if depth = 1, then we start a new argument
+					arguments << evaluate( buffer )
+					#arguments << evaluate( string[0..count] )
+				when ?(
+					# start a new method call
+					function( element, buffer, string )
+					buffer = ""
+				when ?)
+					# close the method call and return arguments
+					return arguments
+				else
+					buffer << c
+				end
+			end
+			""
+		end
+	end
+end

data/lib/rexml/rexml.rb

@@ -0,0 +1,32 @@
+# -*- encoding: utf-8 -*-
+# REXML is an XML toolkit for Ruby[http://www.ruby-lang.org], in Ruby.
+#
+# REXML is a _pure_ Ruby, XML 1.0 conforming,
+# non-validating[http://www.w3.org/TR/2004/REC-xml-20040204/#sec-conformance]
+# toolkit with an intuitive API.  REXML passes 100% of the non-validating Oasis
+# tests[http://www.oasis-open.org/committees/xml-conformance/xml-test-suite.shtml],
+# and provides tree, stream, SAX2, pull, and lightweight APIs.  REXML also 
+# includes a full XPath[http://www.w3c.org/tr/xpath] 1.0 implementation. Since 
+# Ruby 1.8, REXML is included in the standard Ruby distribution.
+#
+# Main page:: http://www.germane-software.com/software/rexml
+# Author:: Sean Russell <serATgermaneHYPHENsoftwareDOTcom>
+# Version:: 3.1.7.2
+# Date:: 2007/275
+# Revision:: $Revision$
+# 
+# This API documentation can be downloaded from the REXML home page, or can
+# be accessed online[http://www.germane-software.com/software/rexml_doc]
+#
+# A tutorial is available in the REXML distribution in docs/tutorial.html,
+# or can be accessed 
+# online[http://www.germane-software.com/software/rexml/docs/tutorial.html]
+module REXML
+  COPYRIGHT = "Copyright \xC2\xA9 2001-2006 Sean Russell <ser@germane-software.com>"
+  VERSION = "3.1.7.3"
+  DATE = "2007/275"
+  REVISION = "$Revision$".gsub(/\$Revision:|\$/,'').strip
+
+  Copyright = COPYRIGHT
+  Version = VERSION
+end

data/lib/rexml/sax2listener.rb

@@ -0,0 +1,97 @@
+module REXML
+	# A template for stream parser listeners.
+	# Note that the declarations (attlistdecl, elementdecl, etc) are trivially
+	# processed; REXML doesn't yet handle doctype entity declarations, so you 
+	# have to parse them out yourself.
+	# === Missing methods from SAX2
+	#  ignorable_whitespace
+	# === Methods extending SAX2 
+	# +WARNING+
+	# These methods are certainly going to change, until DTDs are fully
+	# supported.  Be aware of this.
+	#  start_document
+	#  end_document
+	#  doctype
+	#  elementdecl
+	#  attlistdecl
+	#  entitydecl
+	#  notationdecl
+	#  cdata
+	#  xmldecl
+	#  comment
+	module SAX2Listener
+		def start_document
+		end
+		def end_document
+		end
+		def start_prefix_mapping prefix, uri
+		end
+		def end_prefix_mapping prefix
+		end
+		def start_element uri, localname, qname, attributes
+		end
+		def end_element uri, localname, qname
+		end
+		def characters text
+		end
+		def processing_instruction target, data
+		end
+		# Handles a doctype declaration. Any attributes of the doctype which are
+		# not supplied will be nil.  # EG, <!DOCTYPE me PUBLIC "foo" "bar">
+		# @p name the name of the doctype; EG, "me"
+		# @p pub_sys "PUBLIC", "SYSTEM", or nil.  EG, "PUBLIC"
+		# @p long_name the supplied long name, or nil.  EG, "foo"
+		# @p uri the uri of the doctype, or nil.  EG, "bar"
+		def doctype name, pub_sys, long_name, uri
+		end
+		# If a doctype includes an ATTLIST declaration, it will cause this
+		# method to be called.  The content is the declaration itself, unparsed.
+		# EG, <!ATTLIST el attr CDATA #REQUIRED> will come to this method as "el
+		# attr CDATA #REQUIRED".  This is the same for all of the .*decl
+		# methods.
+		def attlistdecl(element, pairs, contents)
+		end
+		# <!ELEMENT ...>
+		def elementdecl content
+		end
+		# <!ENTITY ...>
+		# The argument passed to this method is an array of the entity
+		# declaration.  It can be in a number of formats, but in general it
+		# returns (example, result):
+		#  <!ENTITY % YN '"Yes"'>  
+		#  ["%", "YN", "'\"Yes\"'", "\""]
+		#  <!ENTITY % YN 'Yes'>
+		#  ["%", "YN", "'Yes'", "s"]
+		#  <!ENTITY WhatHeSaid "He said %YN;">
+		#  ["WhatHeSaid", "\"He said %YN;\"", "YN"]
+		#  <!ENTITY open-hatch SYSTEM "http://www.textuality.com/boilerplate/OpenHatch.xml">
+		#  ["open-hatch", "SYSTEM", "\"http://www.textuality.com/boilerplate/OpenHatch.xml\""]
+		#  <!ENTITY open-hatch PUBLIC "-//Textuality//TEXT Standard open-hatch boilerplate//EN" "http://www.textuality.com/boilerplate/OpenHatch.xml">
+		#  ["open-hatch", "PUBLIC", "\"-//Textuality//TEXT Standard open-hatch boilerplate//EN\"", "\"http://www.textuality.com/boilerplate/OpenHatch.xml\""]
+		#  <!ENTITY hatch-pic SYSTEM "../grafix/OpenHatch.gif" NDATA gif>
+		#  ["hatch-pic", "SYSTEM", "\"../grafix/OpenHatch.gif\"", "\n\t\t\t\t\t\t\tNDATA gif", "gif"]
+		def entitydecl name, decl
+		end
+		# <!NOTATION ...>
+		def notationdecl content
+		end
+		# Called when <![CDATA[ ... ]]> is encountered in a document.
+		# @p content "..."
+		def cdata content
+		end
+		# Called when an XML PI is encountered in the document.
+		# EG: <?xml version="1.0" encoding="utf"?>
+		# @p version the version attribute value.  EG, "1.0"
+		# @p encoding the encoding attribute value, or nil.  EG, "utf"
+		# @p standalone the standalone attribute value, or nil.  EG, nil
+    # @p spaced the declaration is followed by a line break
+		def xmldecl version, encoding, standalone
+		end
+		# Called when a comment is encountered.
+		# @p comment The content of the comment
+		def comment comment
+		end
+    def progress position
+    end
+	end	
+end

data/lib/rexml/source.rb

@@ -0,0 +1,251 @@
+require 'rexml/encoding'
+
+module REXML
+  # Generates Source-s.  USE THIS CLASS.
+  class SourceFactory
+    # Generates a Source object
+    # @param arg Either a String, or an IO
+    # @return a Source, or nil if a bad argument was given
+    def SourceFactory::create_from(arg)
+      if arg.kind_of? String
+        Source.new(arg)
+      elsif arg.respond_to? :read and
+            arg.respond_to? :readline and
+            arg.respond_to? :nil? and
+            arg.respond_to? :eof?
+        IOSource.new(arg)
+      elsif arg.kind_of? Source
+        arg
+      else
+        raise "#{arg.class} is not a valid input stream.  It must walk \n"+
+          "like either a String, an IO, or a Source."
+      end
+    end
+  end
+
+  # A Source can be searched for patterns, and wraps buffers and other
+  # objects and provides consumption of text
+  class Source
+    include Encoding
+    # The current buffer (what we're going to read next)
+    attr_reader :buffer
+    # The line number of the last consumed text
+    attr_reader :line
+    attr_reader :encoding
+
+    # Constructor
+    # @param arg must be a String, and should be a valid XML document
+    # @param encoding if non-null, sets the encoding of the source to this
+    # value, overriding all encoding detection
+    def initialize(arg, encoding=nil)
+      @orig = @buffer = arg
+      if encoding
+        self.encoding = encoding
+      else
+        self.encoding = check_encoding( @buffer )
+      end
+      @line = 0
+    end
+
+
+    # Inherited from Encoding
+    # Overridden to support optimized en/decoding
+    def encoding=(enc)
+      return unless super
+      @line_break = encode( '>' )
+      if enc != UTF_8
+        @buffer = decode(@buffer)
+        @to_utf = true
+      else
+        @to_utf = false
+      end
+    end
+
+    # Scans the source for a given pattern.  Note, that this is not your
+    # usual scan() method.  For one thing, the pattern argument has some
+    # requirements; for another, the source can be consumed.  You can easily
+    # confuse this method.  Originally, the patterns were easier
+    # to construct and this method more robust, because this method 
+    # generated search regexes on the fly; however, this was 
+    # computationally expensive and slowed down the entire REXML package 
+    # considerably, since this is by far the most commonly called method.
+    # @param pattern must be a Regexp, and must be in the form of
+    # /^\s*(#{your pattern, with no groups})(.*)/.  The first group
+    # will be returned; the second group is used if the consume flag is
+    # set.
+    # @param consume if true, the pattern returned will be consumed, leaving
+    # everything after it in the Source.
+    # @return the pattern, if found, or nil if the Source is empty or the
+    # pattern is not found.
+    def scan(pattern, cons=false)
+      return nil if @buffer.nil?
+      rv = @buffer.scan(pattern)
+      @buffer = $' if cons and rv.size>0
+      rv
+    end
+
+    def read
+    end
+
+    def consume( pattern )
+      @buffer = $' if pattern.match( @buffer )
+    end
+
+    def match_to( char, pattern )
+      return pattern.match(@buffer)
+    end
+
+    def match_to_consume( char, pattern )
+      md = pattern.match(@buffer)
+      @buffer = $'
+      return md
+    end
+
+    def match(pattern, cons=false)
+      md = pattern.match(@buffer)
+      @buffer = $' if cons and md
+      return md
+    end
+
+    # @return true if the Source is exhausted
+    def empty?
+      @buffer == ""
+    end
+
+    def position
+      @orig.index( @buffer )
+    end
+
+    # @return the current line in the source
+    def current_line
+      lines = @orig.split
+      res = lines.grep @buffer[0..30]
+      res = res[-1] if res.kind_of? Array
+      lines.index( res ) if res
+    end
+  end
+
+  # A Source that wraps an IO.  See the Source class for method
+  # documentation
+  class IOSource < Source
+    #attr_reader :block_size
+
+    # block_size has been deprecated
+    def initialize(arg, block_size=500, encoding=nil)
+      @er_source = @source = arg
+      @to_utf = false
+
+      # Determining the encoding is a deceptively difficult issue to resolve.
+      # First, we check the first two bytes for UTF-16.  Then we
+      # assume that the encoding is at least ASCII enough for the '>', and
+      # we read until we get one of those.  This gives us the XML declaration,
+      # if there is one.  If there isn't one, the file MUST be UTF-8, as per
+      # the XML spec.  If there is one, we can determine the encoding from
+      # it.
+      @buffer = ""
+      str = @source.read( 2 )
+      if encoding
+        self.encoding = encoding
+      elsif 0xfe == str[0] && 0xff == str[1]
+        @line_break = "\000>"
+      elsif 0xff == str[0] && 0xfe == str[1]
+        @line_break = ">\000"
+      elsif 0xef == str[0] && 0xbb == str[1]
+        str += @source.read(1)
+        str = '' if (0xbf == str[2])
+        @line_break = ">"
+      else
+        @line_break = ">"
+      end
+      super str+@source.readline( @line_break )
+    end
+
+    def scan(pattern, cons=false)
+      rv = super
+      # You'll notice that this next section is very similar to the same
+      # section in match(), but just a liiittle different.  This is
+      # because it is a touch faster to do it this way with scan()
+      # than the way match() does it; enough faster to warrent duplicating
+      # some code
+      if rv.size == 0
+        until @buffer =~ pattern or @source.nil?
+          begin
+            # READLINE OPT
+            #str = @source.read(@block_size)
+            str = @source.readline(@line_break)
+            str = decode(str) if @to_utf and str
+            @buffer << str
+          rescue Iconv::IllegalSequence
+            raise
+          rescue
+            @source = nil
+          end
+        end
+        rv = super
+      end
+      rv.taint
+      rv
+    end
+
+    def read
+      begin
+        str = @source.readline(@line_break)
+        str = decode(str) if @to_utf and str 
+        @buffer << str
+      rescue Exception, NameError
+        @source = nil
+      end
+    end
+
+    def consume( pattern )
+      match( pattern, true )
+    end
+
+    def match( pattern, cons=false )
+      rv = pattern.match(@buffer)
+      @buffer = $' if cons and rv
+      while !rv and @source
+        begin
+          str = @source.readline(@line_break)
+          str = decode(str) if @to_utf and str
+          @buffer << str
+          rv = pattern.match(@buffer)
+          @buffer = $' if cons and rv
+        rescue
+          @source = nil
+        end
+      end
+      rv.taint
+      rv
+    end
+    
+    def empty?
+      super and ( @source.nil? || @source.eof? )
+    end
+
+    def position
+      @er_source.stat.pipe? ? 0 : @er_source.pos
+    end
+
+    # @return the current line in the source
+    def current_line
+      begin
+        pos = @er_source.pos        # The byte position in the source
+        lineno = @er_source.lineno  # The XML < position in the source
+        @er_source.rewind
+        line = 0                    # The \r\n position in the source
+        begin
+          while @er_source.pos < pos
+            @er_source.readline
+            line += 1
+          end
+        rescue
+        end
+      rescue IOError
+        pos = -1
+        line = -1
+      end
+      [pos, lineno, line]
+    end
+  end
+end