2015-12-16 00:07:31 -05:00
|
|
|
# frozen_string_literal: false
|
2018-11-02 13:52:33 -04:00
|
|
|
require_relative 'child'
|
|
|
|
require_relative 'source'
|
|
|
|
require_relative 'xmltokens'
|
2003-06-09 21:31:01 -04:00
|
|
|
|
|
|
|
module REXML
|
2008-10-01 09:46:53 -04:00
|
|
|
class Entity < Child
|
|
|
|
include XMLTokens
|
|
|
|
PUBIDCHAR = "\x20\x0D\x0Aa-zA-Z0-9\\-()+,./:=?;!*@$_%#"
|
|
|
|
SYSTEMLITERAL = %Q{((?:"[^"]*")|(?:'[^']*'))}
|
|
|
|
PUBIDLITERAL = %Q{("[#{PUBIDCHAR}']*"|'[#{PUBIDCHAR}]*')}
|
|
|
|
EXTERNALID = "(?:(?:(SYSTEM)\\s+#{SYSTEMLITERAL})|(?:(PUBLIC)\\s+#{PUBIDLITERAL}\\s+#{SYSTEMLITERAL}))"
|
|
|
|
NDATADECL = "\\s+NDATA\\s+#{NAME}"
|
|
|
|
PEREFERENCE = "%#{NAME};"
|
|
|
|
ENTITYVALUE = %Q{((?:"(?:[^%&"]|#{PEREFERENCE}|#{REFERENCE})*")|(?:'([^%&']|#{PEREFERENCE}|#{REFERENCE})*'))}
|
|
|
|
PEDEF = "(?:#{ENTITYVALUE}|#{EXTERNALID})"
|
|
|
|
ENTITYDEF = "(?:#{ENTITYVALUE}|(?:#{EXTERNALID}(#{NDATADECL})?))"
|
|
|
|
PEDECL = "<!ENTITY\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>"
|
|
|
|
GEDECL = "<!ENTITY\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>"
|
|
|
|
ENTITYDECL = /\s*(?:#{GEDECL})|(?:#{PEDECL})/um
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
attr_reader :name, :external, :ref, :ndata, :pubid
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# Create a new entity. Simple entities can be constructed by passing a
|
|
|
|
# name, value to the constructor; this creates a generic, plain entity
|
|
|
|
# reference. For anything more complicated, you have to pass a Source to
|
2010-03-19 23:30:59 -04:00
|
|
|
# the constructor with the entity definition, or use the accessor methods.
|
2008-10-01 09:46:53 -04:00
|
|
|
# +WARNING+: There is no validation of entity state except when the entity
|
|
|
|
# is read from a stream. If you start poking around with the accessors,
|
2017-11-02 16:06:38 -04:00
|
|
|
# you can easily create a non-conformant Entity.
|
2009-03-05 22:56:38 -05:00
|
|
|
#
|
2008-10-01 09:46:53 -04:00
|
|
|
# e = Entity.new( 'amp', '&' )
|
|
|
|
def initialize stream, value=nil, parent=nil, reference=false
|
|
|
|
super(parent)
|
|
|
|
@ndata = @pubid = @value = @external = nil
|
|
|
|
if stream.kind_of? Array
|
|
|
|
@name = stream[1]
|
|
|
|
if stream[-1] == '%'
|
2009-03-05 22:56:38 -05:00
|
|
|
@reference = true
|
2008-10-01 09:46:53 -04:00
|
|
|
stream.pop
|
|
|
|
else
|
|
|
|
@reference = false
|
|
|
|
end
|
|
|
|
if stream[2] =~ /SYSTEM|PUBLIC/
|
|
|
|
@external = stream[2]
|
|
|
|
if @external == 'SYSTEM'
|
|
|
|
@ref = stream[3]
|
|
|
|
@ndata = stream[4] if stream.size == 5
|
|
|
|
else
|
|
|
|
@pubid = stream[3]
|
|
|
|
@ref = stream[4]
|
|
|
|
end
|
|
|
|
else
|
|
|
|
@value = stream[2]
|
|
|
|
end
|
|
|
|
else
|
|
|
|
@reference = reference
|
|
|
|
@external = nil
|
|
|
|
@name = stream
|
|
|
|
@value = value
|
|
|
|
end
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2013-12-19 02:58:36 -05:00
|
|
|
# Evaluates whether the given string matches an entity definition,
|
2008-10-01 09:46:53 -04:00
|
|
|
# returning true if so, and false otherwise.
|
|
|
|
def Entity::matches? string
|
|
|
|
(ENTITYDECL =~ string) == 0
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# Evaluates to the unnormalized value of this entity; that is, replacing
|
|
|
|
# all entities -- both %ent; and &ent; entities. This differs from
|
|
|
|
# +value()+ in that +value+ only replaces %ent; entities.
|
|
|
|
def unnormalized
|
2008-11-06 12:03:40 -05:00
|
|
|
document.record_entity_expansion unless document.nil?
|
2008-10-01 09:46:53 -04:00
|
|
|
v = value()
|
|
|
|
return nil if v.nil?
|
|
|
|
@unnormalized = Text::unnormalize(v, parent)
|
|
|
|
@unnormalized
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
#once :unnormalized
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# Returns the value of this entity unprocessed -- raw. This is the
|
|
|
|
# normalized value; that is, with all %ent; and &ent; entities intact
|
|
|
|
def normalized
|
|
|
|
@value
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# Write out a fully formed, correct entity definition (assuming the Entity
|
|
|
|
# object itself is valid.)
|
Merges upstream changes for REXML v3.1.7
http://www.germane-software.com/repos/rexml/tags/3.1.7
r1278@bean: ser | 2007-06-07 00:53:06 -0400
Fixed a double-encoding bug. This was a regression, related
to ticket:48.
r1292@bean: ser | 2007-07-25 08:19:36 -0400
r1279@bean: ser | 2007-06-09 23:19:02 -0400
Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same
problem.
Also in this patch is a fix to merge.rb (unused, but it should at least
contain no errors), and a unit test for ticket:88.
r1293@bean: ser | 2007-07-25 08:19:37 -0400
r1281@bean: ser | 2007-07-24 11:08:48 -0400
Addresses ticket:85
This is a major rewrite of the XML formatting code. The XML writers have all
been extracted out of the classes and put into their own class containers.
This makes writing parsers easier, and cleaner.
There are three formatters, which correspond to the previous three XML writing
modes:
REXML::Formatters::Default
Prints the XML document exactly as it was parsed
REXML::Formatters::Pretty
Pretty prints the XML document, destroying whitespace in the document
REXML::Formatters::Transitive
Pretty prints the XML document, preserving whitespace
All of the write() functions have been deprecated (some are still used, but
these will also go away) except the write() function on Document, which is left
for convenience. To pretty print an XML document the canonical way:
formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces
formatter.write( document, output )
r1294@bean: ser | 2007-07-25 08:19:38 -0400
r1283@bean: ser | 2007-07-24 19:53:30 -0400
This goes with the previous commit.
r1295@bean: ser | 2007-07-25 08:19:39 -0400
r1285@bean: ser | 2007-07-24 20:02:07 -0400
And THIS goes with the previous two patches. Dammit.
r1296@bean: ser | 2007-07-25 08:19:40 -0400
r1287@bean: ser | 2007-07-24 20:12:25 -0400
Applied patch from Jeff Barczewski. Note that this changes what the values of
the name and IDs are from the previous behavior -- the values no longer include
the quotes. This is the correct behavior, so I'm leaving it in, but it is not
backwards compatible. Also fixes the serializer so that it outputs the doctype
in a correct format (needed as a result of this change).
r1297@bean: ser | 2007-07-25 08:38:38 -0400
Version update
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 08:47:23 -04:00
|
|
|
#
|
|
|
|
# out::
|
2019-01-04 04:10:10 -05:00
|
|
|
# An object implementing <TT><<</TT> to which the entity will be
|
Merges upstream changes for REXML v3.1.7
http://www.germane-software.com/repos/rexml/tags/3.1.7
r1278@bean: ser | 2007-06-07 00:53:06 -0400
Fixed a double-encoding bug. This was a regression, related
to ticket:48.
r1292@bean: ser | 2007-07-25 08:19:36 -0400
r1279@bean: ser | 2007-06-09 23:19:02 -0400
Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same
problem.
Also in this patch is a fix to merge.rb (unused, but it should at least
contain no errors), and a unit test for ticket:88.
r1293@bean: ser | 2007-07-25 08:19:37 -0400
r1281@bean: ser | 2007-07-24 11:08:48 -0400
Addresses ticket:85
This is a major rewrite of the XML formatting code. The XML writers have all
been extracted out of the classes and put into their own class containers.
This makes writing parsers easier, and cleaner.
There are three formatters, which correspond to the previous three XML writing
modes:
REXML::Formatters::Default
Prints the XML document exactly as it was parsed
REXML::Formatters::Pretty
Pretty prints the XML document, destroying whitespace in the document
REXML::Formatters::Transitive
Pretty prints the XML document, preserving whitespace
All of the write() functions have been deprecated (some are still used, but
these will also go away) except the write() function on Document, which is left
for convenience. To pretty print an XML document the canonical way:
formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces
formatter.write( document, output )
r1294@bean: ser | 2007-07-25 08:19:38 -0400
r1283@bean: ser | 2007-07-24 19:53:30 -0400
This goes with the previous commit.
r1295@bean: ser | 2007-07-25 08:19:39 -0400
r1285@bean: ser | 2007-07-24 20:02:07 -0400
And THIS goes with the previous two patches. Dammit.
r1296@bean: ser | 2007-07-25 08:19:40 -0400
r1287@bean: ser | 2007-07-24 20:12:25 -0400
Applied patch from Jeff Barczewski. Note that this changes what the values of
the name and IDs are from the previous behavior -- the values no longer include
the quotes. This is the correct behavior, so I'm leaving it in, but it is not
backwards compatible. Also fixes the serializer so that it outputs the doctype
in a correct format (needed as a result of this change).
r1297@bean: ser | 2007-07-25 08:38:38 -0400
Version update
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 08:47:23 -04:00
|
|
|
# output
|
|
|
|
# indent::
|
|
|
|
# *DEPRECATED* and ignored
|
2008-10-01 09:46:53 -04:00
|
|
|
def write out, indent=-1
|
|
|
|
out << '<!ENTITY '
|
|
|
|
out << '% ' if @reference
|
|
|
|
out << @name
|
|
|
|
out << ' '
|
|
|
|
if @external
|
|
|
|
out << @external << ' '
|
|
|
|
if @pubid
|
|
|
|
q = @pubid.include?('"')?"'":'"'
|
|
|
|
out << q << @pubid << q << ' '
|
|
|
|
end
|
|
|
|
q = @ref.include?('"')?"'":'"'
|
|
|
|
out << q << @ref << q
|
|
|
|
out << ' NDATA ' << @ndata if @ndata
|
|
|
|
else
|
|
|
|
q = @value.include?('"')?"'":'"'
|
|
|
|
out << q << @value << q
|
|
|
|
end
|
|
|
|
out << '>'
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# Returns this entity as a string. See write().
|
|
|
|
def to_s
|
|
|
|
rv = ''
|
|
|
|
write rv
|
|
|
|
rv
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
PEREFERENCE_RE = /#{PEREFERENCE}/um
|
|
|
|
# Returns the value of this entity. At the moment, only internal entities
|
|
|
|
# are processed. If the value contains internal references (IE,
|
|
|
|
# %blah;), those are replaced with their values. IE, if the doctype
|
|
|
|
# contains:
|
|
|
|
# <!ENTITY % foo "bar">
|
|
|
|
# <!ENTITY yada "nanoo %foo; nanoo>
|
|
|
|
# then:
|
|
|
|
# doctype.entity('yada').value #-> "nanoo bar nanoo"
|
|
|
|
def value
|
|
|
|
if @value
|
|
|
|
matches = @value.scan(PEREFERENCE_RE)
|
|
|
|
rv = @value.clone
|
|
|
|
if @parent
|
2014-10-27 07:18:02 -04:00
|
|
|
sum = 0
|
2008-10-01 09:46:53 -04:00
|
|
|
matches.each do |entity_reference|
|
|
|
|
entity_value = @parent.entity( entity_reference[0] )
|
2014-10-27 07:18:02 -04:00
|
|
|
if sum + entity_value.bytesize > Security.entity_expansion_text_limit
|
|
|
|
raise "entity expansion has grown too large"
|
|
|
|
else
|
|
|
|
sum += entity_value.bytesize
|
|
|
|
end
|
2008-10-01 09:46:53 -04:00
|
|
|
rv.gsub!( /%#{entity_reference.join};/um, entity_value )
|
|
|
|
end
|
|
|
|
end
|
|
|
|
return rv
|
|
|
|
end
|
|
|
|
nil
|
|
|
|
end
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# This is a set of entity constants -- the ones defined in the XML
|
|
|
|
# specification. These are +gt+, +lt+, +amp+, +quot+ and +apos+.
|
2014-11-13 08:29:50 -05:00
|
|
|
# CAUTION: these entities does not have parent and document
|
2008-10-01 09:46:53 -04:00
|
|
|
module EntityConst
|
|
|
|
# +>+
|
|
|
|
GT = Entity.new( 'gt', '>' )
|
|
|
|
# +<+
|
|
|
|
LT = Entity.new( 'lt', '<' )
|
|
|
|
# +&+
|
|
|
|
AMP = Entity.new( 'amp', '&' )
|
|
|
|
# +"+
|
|
|
|
QUOT = Entity.new( 'quot', '"' )
|
|
|
|
# +'+
|
|
|
|
APOS = Entity.new( 'apos', "'" )
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
end
|