Class: REXML::Text (Ruby 2.3.4)

In Files

  • rexml/text.rb

Class/Module Index [+]

Quicksearch

REXML::Text

Represents text nodes in an XML document

Constants

EREFERENCE
NEEDS_A_SECOND_CHECK
NUMERICENTITY
REFERENCE
SETUTITSBUS
SLAICEPS

Characters which are substituted in written strings

SPECIALS

The order in which the substitutions occur

SUBSTITUTES
VALID_CHAR
VALID_XML_CHARS

Attributes

raw[RW]

If raw is true, then REXML leaves the value alone

Public Class Methods

check(string, pattern, doctype)

check for illegal characters

 
               # File rexml/text.rb, line 130
def Text.check string, pattern, doctype

  # illegal anywhere
  if string !~ VALID_XML_CHARS
    if String.method_defined? :encode
      string.chars.each do |c|
        case c.ord
        when *VALID_CHAR
        else
          raise "Illegal character #{c.inspect} in raw string \"#{string}\""
        end
      end
    else
      string.scan(/[\x00-\x7F]|[\x80-\xBF][\xC0-\xF0]*|[\xC0-\xF0]/n) do |c|
        case c.unpack('U')
        when *VALID_CHAR
        else
          raise "Illegal character #{c.inspect} in raw string \"#{string}\""
        end
      end
    end
  end

  # context sensitive
  string.scan(pattern) do
    if $1[-1] != ?;
      raise "Illegal character '#{$1}' in raw string \"#{string}\""
    elsif $1[0] == ?&
      if $5 and $5[0] == ?#
        case ($5[1] == ?x ? $5[2..-1].to_i(16) : $5[1..-1].to_i)
        when *VALID_CHAR
        else
          raise "Illegal character '#{$1}' in raw string \"#{string}\""
        end
      # FIXME: below can't work but this needs API change.
      # elsif @parent and $3 and !SUBSTITUTES.include?($1)
      #   if !doctype or !doctype.entities.has_key?($3)
      #     raise "Undeclared entity '#{$1}' in raw string \"#{string}\""
      #   end
      end
    end
  end
end
            
new(arg, respect_whitespace=false, parent=nil, raw=nil, entity_filter=nil, illegal=NEEDS_A_SECOND_CHECK )

Constructor arg if a String, the content is set to the String. If a Text, the object is shallowly cloned.

respect_whitespace (boolean, false) if true, whitespace is respected

parent (nil) if this is a Parent object, the parent will be set to this.

raw (nil) This argument can be given three values. If true, then the value of used to construct this object is expected to contain no unescaped XML markup, and REXML will not change the text. If this value is false, the string may contain any characters, and REXML will escape any and all defined entities whose values are contained in the text. If this value is nil (the default), then the raw value of the parent will be used as the raw value for this node. If there is no raw value for the parent, and no value is supplied, the default is false. Use this field if you have entities defined for some text, and you don't want REXML to escape that text in output.

Text.new( "<&", false, nil, false ) #-> "&lt;&amp;"
Text.new( "&lt;&amp;", false, nil, false ) #-> "&amp;lt;&amp;amp;"
Text.new( "<&", false, nil, true )  #-> Parse exception
Text.new( "&lt;&amp;", false, nil, true )  #-> "&lt;&amp;"
# Assume that the entity "s" is defined to be "sean"
# and that the entity    "r" is defined to be "russell"
Text.new( "sean russell" )          #-> "&s; &r;"
Text.new( "sean russell", false, nil, true ) #-> "sean russell"

entity_filter (nil) This can be an array of entities to match in the supplied text. This argument is only useful if raw is set to false.

Text.new( "sean russell", false, nil, false, ["s"] ) #-> "&s; russell"
Text.new( "sean russell", false, nil, true, ["s"] ) #-> "sean russell"

In the last example, the entity_filter argument is ignored.

illegal INTERNAL USE ONLY

 
               # File rexml/text.rb, line 94
def initialize(arg, respect_whitespace=false, parent=nil, raw=nil,
  entity_filter=nil, illegal=NEEDS_A_SECOND_CHECK )

  @raw = false
  @parent = nil

  if parent
    super( parent )
    @raw = parent.raw
  end

  @raw = raw unless raw.nil?
  @entity_filter = entity_filter
  clear_cache

  if arg.kind_of? String
    @string = arg.dup
    @string.squeeze!(" \n\t") unless respect_whitespace
  elsif arg.kind_of? Text
    @string = arg.to_s
    @raw = arg.raw
  elsif
    raise "Illegal argument of type #{arg.type} for Text constructor (#{arg})"
  end

  @string.gsub!( /\r\n?/, "\n" )

  Text.check(@string, illegal, doctype) if @raw
end
            

Public Instance Methods

<<( to_append )

Appends text to this text node. The text is appended in the raw mode of this text node.

returns the text itself to enable method chain like 'text << "XXX" << "YYY"'.

 
               # File rexml/text.rb, line 193
def <<( to_append )
  @string << to_append.gsub( /\r\n?/, "\n" )
  clear_cache
  self
end
            
<=>( other )

other a String or a Text returns the result of (to_s <=> arg.to_s)

 
               # File rexml/text.rb, line 202
def <=>( other )
  to_s() <=> other.to_s
end
            
clone()
 
               # File rexml/text.rb, line 183
def clone
  return Text.new(self)
end
            
doctype()
 
               # File rexml/text.rb, line 206
def doctype
  if @parent
    doc = @parent.document
    doc.doctype if doc
  end
end
            
empty?()
 
               # File rexml/text.rb, line 178
def empty?
  @string.size==0
end
            
indent_text(string, level=1, style="\t", indentfirstline=true)
 
               # File rexml/text.rb, line 280
def indent_text(string, level=1, style="\t", indentfirstline=true)
  return string if level < 0
  new_string = ''
  string.each_line { |line|
    indent_string = style * level
    new_line = (indent_string + line).sub(/[\s]+$/,'')
    new_string << new_line
  }
  new_string.strip! unless indentfirstline
  return new_string
end
            
inspect()
 
               # File rexml/text.rb, line 234
def inspect
  @string.inspect
end
            
node_type()
 
               # File rexml/text.rb, line 174
def node_type
  :text
end
            
parent=(parent)
 
               # File rexml/text.rb, line 124
def parent= parent
  super(parent)
  Text.check(@string, NEEDS_A_SECOND_CHECK, doctype) if @raw and @parent
end
            
to_s()

Returns the string value of this text node. This string is always escaped, meaning that it is a valid XML text node string, and all entities that can be escaped, have been inserted. This method respects the entity filter set in the constructor.

# Assume that the entity "s" is defined to be "sean", and that the
# entity "r" is defined to be "russell"
t = Text.new( "< & sean russell", false, nil, false, ['s'] )
t.to_s   #-> "&lt; &amp; &s; russell"
t = Text.new( "< & &s; russell", false, nil, false )
t.to_s   #-> "&lt; &amp; &s; russell"
u = Text.new( "sean russell", false, nil, true )
u.to_s   #-> "sean russell"
 
               # File rexml/text.rb, line 227
def to_s
  return @string if @raw
  return @normalized if @normalized

  @normalized = Text::normalize( @string, doctype, @entity_filter )
end
            
value()

Returns the string value of this text. This is the text without entities, as it might be used programmatically, or printed to the console. This ignores the ‘raw’ attribute setting, and any entity_filter.

# Assume that the entity "s" is defined to be "sean", and that the
# entity "r" is defined to be "russell"
t = Text.new( "< & sean russell", false, nil, false, ['s'] )
t.value   #-> "< & sean russell"
t = Text.new( "< & &s; russell", false, nil, false )
t.value   #-> "< & sean russell"
u = Text.new( "sean russell", false, nil, true )
u.value   #-> "sean russell"
 
               # File rexml/text.rb, line 251
def value
  return @unnormalized if @unnormalized
  @unnormalized = Text::unnormalize( @string, doctype )
end
            
value=( val )

Sets the contents of this text node. This expects the text to be unnormalized. It returns self.

e = Element.new( "a" )
e.add_text( "foo" )   # <a>foo</a>
e[0].value = "bar"    # <a>bar</a>
e[0].value = "<a>"    # <a>&lt;a&gt;</a>
 
               # File rexml/text.rb, line 263
def value=( val )
  @string = val.gsub( /\r\n?/, "\n" )
  clear_cache
  @raw = false
end
            
wrap(string, width, addnewline=false)
 
               # File rexml/text.rb, line 269
def wrap(string, width, addnewline=false)
  # Recursively wrap string at width.
  return string if string.length <= width
  place = string.rindex(' ', width) # Position in string with last ' ' before cutoff
  if addnewline then
    return "\n" + string[0,place] + "\n" + wrap(string[place+1..-1], width)
  else
    return string[0,place] + "\n" + wrap(string[place+1..-1], width)
  end
end
            
write( writer, indent=-1, transitive=false, ie_hack=false )

DEPRECATED

See REXML::Formatters

 
               # File rexml/text.rb, line 295
def write( writer, indent=-1, transitive=false, ie_hack=false )
  Kernel.warn("#{self.class.name}.write is deprecated.  See REXML::Formatters")
  formatter = if indent > -1
      REXML::Formatters::Pretty.new( indent )
    else
      REXML::Formatters::Default.new
    end
  formatter.write( self, writer )
end
            
write_with_substitution(out, input)

Writes out text, substituting special characters beforehand. out A String, IO, or any other object supporting <<( String ) input the text to substitute and the write out

z=utf8.unpack("U*")
ascOut=""
z.each{|r|
  if r <  0x100
    ascOut.concat(r.chr)
  else
    ascOut.concat(sprintf("&#x%x;", r))
  end
}
puts ascOut
 
               # File rexml/text.rb, line 327
def write_with_substitution out, input
  copy = input.clone
  # Doing it like this rather than in a loop improves the speed
  copy.gsub!( SPECIALS[0], SUBSTITUTES[0] )
  copy.gsub!( SPECIALS[1], SUBSTITUTES[1] )
  copy.gsub!( SPECIALS[2], SUBSTITUTES[2] )
  copy.gsub!( SPECIALS[3], SUBSTITUTES[3] )
  copy.gsub!( SPECIALS[4], SUBSTITUTES[4] )
  copy.gsub!( SPECIALS[5], SUBSTITUTES[5] )
  out << copy
end
            
xpath()

FIXME This probably won’t work properly

 
               # File rexml/text.rb, line 307
def xpath
  path = @parent.xpath
  path += "/text()"
  return path
end