Extended maintenance of Ruby versions 1.8.7 and 1.9.2 ended on July 31, 2014. Read more
Represents text nodes in an XML document
Characters which are substituted in written strings
The order in which the substitutions occur
# File rexml/text.rb, line 324
def Text.expand(ref, doctype, filter)
if ref[1] == ?#
if ref[2] == ?x
[ref[3...-1].to_i(16)].pack('U*')
else
[ref[2...-1].to_i].pack('U*')
end
elsif ref == '&'
'&'
elsif filter and filter.include?( ref[1...-1] )
ref
elsif doctype
doctype.entity( ref[1...-1] ) or ref
else
entity_value = DocType::DEFAULT_ENTITIES[ ref[1...-1] ]
entity_value ? entity_value.value : ref
end
end
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 ) #-> "<&" Text.new( "<&", false, nil, false ) #-> "&lt;&amp;" Text.new( "<&", false, nil, true ) #-> Parse exception Text.new( "<&", false, nil, true ) #-> "<&" # 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.
pattern INTERNAL USE ONLY
# File rexml/text.rb, line 61
def initialize(arg, respect_whitespace=false, parent=nil, raw=nil,
entity_filter=nil, illegal=ILLEGAL )
@raw = false
if parent
super( parent )
@raw = parent.raw
else
@parent = nil
end
@raw = raw unless raw.nil?
@entity_filter = entity_filter
@normalized = @unnormalized = nil
if arg.kind_of? String
@string = arg.clone
@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" )
# check for illegal characters
if @raw
if @string =~ illegal
raise "Illegal character '#{$1}' in raw string \"#{@string}\""
end
end
end
Escapes all possible entities
# File rexml/text.rb, line 289
def Text::normalize( input, doctype=nil, entity_filter=nil )
copy = input.to_s
# Doing it like this rather than in a loop improves the speed
#copy = copy.gsub( EREFERENCE, '&' )
copy = copy.gsub( "&", "&" )
if doctype
# Replace all ampersands that aren't part of an entity
doctype.entities.each_value do |entity|
copy = copy.gsub( entity.value,
"&#{entity.name};" ) if entity.value and
not( entity_filter and entity_filter.include?(entity) )
end
else
# Replace all ampersands that aren't part of an entity
DocType::DEFAULT_ENTITIES.each_value do |entity|
copy = copy.gsub(entity.value, "&#{entity.name};" )
end
end
copy
end
Reads text, substituting entities
# File rexml/text.rb, line 263
def Text::read_with_substitution( input, illegal=nil )
copy = input.clone
if copy =~ illegal
raise ParseException.new( "malformed text: Illegal character #$& in \"#{copy}\"" )
end if illegal
copy.gsub!( /\r\n?/, "\n" )
if copy.include? ?&
copy.gsub!( SETUTITSBUS[0], SLAICEPS[0] )
copy.gsub!( SETUTITSBUS[1], SLAICEPS[1] )
copy.gsub!( SETUTITSBUS[2], SLAICEPS[2] )
copy.gsub!( SETUTITSBUS[3], SLAICEPS[3] )
copy.gsub!( SETUTITSBUS[4], SLAICEPS[4] )
copy.gsub!( /�*((?:\d+)|(?:x[a-f0-9]+));/ ) {|m|
m=$1
#m='0' if m==''
m = "0#{m}" if m[0] == ?x
[Integer(m)].pack('U*')
}
end
copy
end
Unescapes all possible entities
# File rexml/text.rb, line 311
def Text::unnormalize( string, doctype=nil, filter=nil, illegal=nil )
sum = 0
string.gsub( /\r\n?/, "\n" ).gsub( REFERENCE ) {
s = Text.expand($&, doctype, filter)
if sum + s.bytesize > REXML.entity_expansion_text_limit
raise "entity expansion has grown too large"
else
sum += s.bytesize
end
s
}
end
Appends text to this text node. The text is appended in the
raw mode of this text node.
# File rexml/text.rb, line 113
def <<( to_append )
@string << to_append.gsub( /\r\n?/, "\n" )
end
other a String or a Text
returns the result of (to_s <=> arg.to_s)
# File rexml/text.rb, line 120
def <=>( other )
to_s() <=> other.to_s
end
# File rexml/text.rb, line 203
def indent_text(string, level=1, style="\t", indentfirstline=true)
return string if level < 0
new_string = ''
string.each { |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
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 #-> "< & &s; russell" t = Text.new( "< & &s; russell", false, nil, false ) t.to_s #-> "< & &s; russell" u = Text.new( "sean russell", false, nil, true ) u.to_s #-> "sean russell"
# File rexml/text.rb, line 138
def to_s
return @string if @raw
return @normalized if @normalized
doctype = nil
if @parent
doc = @parent.document
doctype = doc.doctype if doc
end
@normalized = Text::normalize( @string, doctype, @entity_filter )
end
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 168
def value
@unnormalized if @unnormalized
doctype = nil
if @parent
doc = @parent.document
doctype = doc.doctype if doc
end
@unnormalized = Text::unnormalize( @string, doctype )
end
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><a></a>
# File rexml/text.rb, line 185
def value=( val )
@string = val.gsub( /\r\n?/, "\n" )
@unnormalized = nil
@normalized = nil
@raw = false
end
# File rexml/text.rb, line 192
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
# File rexml/text.rb, line 218
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
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 250
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