Class: REXML::Parsers::BaseParser

Inherits:
Object
  • Object
show all
Defined in:
lib/rexml/parsers/baseparser.rb

Overview

Using the Pull Parser

This API is experimental, and subject to change.

parser = PullParser.new( "<a>text<b att='val'/>txet</a>" )
while parser.has_next?
  res = parser.next
  puts res[1]['att'] if res.start_tag? and res[0] == 'b'
end

See the PullEvent class for information on the content of the results. The data is identical to the arguments passed for the various events to the StreamListener API.

Notice that:

parser = PullParser.new( "<a>BAD DOCUMENT" )
while parser.has_next?
  res = parser.next
  raise res[1] if res.error?
end

Nat Price gave me some good ideas for the API.

Constant Summary collapse

LETTER =
'[:alpha:]'
DIGIT =
'[:digit:]'
COMBININGCHAR =

TODO

''
EXTENDER =

TODO

''
NCNAME_STR =
"[#{LETTER}_:][-[:alnum:]._:#{COMBININGCHAR}#{EXTENDER}]*"
NAME_STR =
"(?:(#{NCNAME_STR}):)?(#{NCNAME_STR})"
UNAME_STR =
"(?:#{NCNAME_STR}:)?#{NCNAME_STR}"
NAMECHAR =
'[\-\w\.:]'
NAME =
"([\\w:]#{NAMECHAR}*)"
NMTOKEN =
"(?:#{NAMECHAR})+"
NMTOKENS =
"#{NMTOKEN}(\\s+#{NMTOKEN})*"
REFERENCE =
"&(?:#{NAME};|#\\d+;|#x[0-9a-fA-F]+;)"
REFERENCE_RE =
/#{REFERENCE}/
DOCTYPE_START =
/\A\s*<!DOCTYPE\s/um
DOCTYPE_END =
/\A\s*\]\s*>/um
DOCTYPE_PATTERN =
/\s*<!DOCTYPE\s+(.*?)(\[|>)/um
ATTRIBUTE_PATTERN =
/\s*(#{NAME_STR})\s*=\s*(["'])(.*?)\4/um
COMMENT_START =
/\A<!--/u
COMMENT_PATTERN =
/<!--(.*?)-->/um
CDATA_START =
/\A<!\[CDATA\[/u
CDATA_END =
/\A\s*\]\s*>/um
CDATA_PATTERN =
/<!\[CDATA\[(.*?)\]\]>/um
XMLDECL_START =
/\A<\?xml\s/u
XMLDECL_PATTERN =
/<\?xml\s+(.*?)\?>/um
INSTRUCTION_START =
/\A<\?/u
INSTRUCTION_PATTERN =
/<\?(.*?)(\s+.*?)?\?>/um
TAG_MATCH =
/^<((?>#{NAME_STR}))\s*((?>\s+#{UNAME_STR}\s*=\s*(["']).*?\5)*)\s*(\/)?>/um
CLOSE_MATCH =
/^\s*<\/(#{NAME_STR})\s*>/um
VERSION =
/\bversion\s*=\s*["'](.*?)['"]/um
ENCODING =
/\bencoding\s*=\s*["'](.*?)['"]/um
STANDALONE =
/\bstandalone\s*=\s*["'](.*?)['"]/um
ENTITY_START =
/\A\s*<!ENTITY/
IDENTITY =
/^([!\*\w\-]+)(\s+#{NCNAME_STR})?(\s+["'](.*?)['"])?(\s+['"](.*?)["'])?/u
ELEMENTDECL_START =
/\A\s*<!ELEMENT/um
ELEMENTDECL_PATTERN =
/\A\s*(<!ELEMENT.*?)>/um
SYSTEMENTITY =
/\A\s*(%.*?;)\s*$/um
ENUMERATION =
"\\(\\s*#{NMTOKEN}(?:\\s*\\|\\s*#{NMTOKEN})*\\s*\\)"
NOTATIONTYPE =
"NOTATION\\s+\\(\\s*#{NAME}(?:\\s*\\|\\s*#{NAME})*\\s*\\)"
ENUMERATEDTYPE =
"(?:(?:#{NOTATIONTYPE})|(?:#{ENUMERATION}))"
ATTTYPE =
"(CDATA|ID|IDREF|IDREFS|ENTITY|ENTITIES|NMTOKEN|NMTOKENS|#{ENUMERATEDTYPE})"
ATTVALUE =
"(?:\"((?:[^<&\"]|#{REFERENCE})*)\")|(?:'((?:[^<&']|#{REFERENCE})*)')"
DEFAULTDECL =
"(#REQUIRED|#IMPLIED|(?:(#FIXED\\s+)?#{ATTVALUE}))"
ATTDEF =
"\\s+#{NAME}\\s+#{ATTTYPE}\\s+#{DEFAULTDECL}"
ATTDEF_RE =
/#{ATTDEF}/
ATTLISTDECL_START =
/\A\s*<!ATTLIST/um
ATTLISTDECL_PATTERN =
/\A\s*<!ATTLIST\s+#{NAME}(?:#{ATTDEF})*\s*>/um
NOTATIONDECL_START =
/\A\s*<!NOTATION/um
PUBLIC =
/\A\s*<!NOTATION\s+(\w[\-\w]*)\s+(PUBLIC)\s+(["'])(.*?)\3(?:\s+(["'])(.*?)\5)?\s*>/um
SYSTEM =
/\A\s*<!NOTATION\s+(\w[\-\w]*)\s+(SYSTEM)\s+(["'])(.*?)\3\s*>/um
TEXT_PATTERN =
/\A([^<]*)/um
PUBIDCHAR =

Entity constants

"\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
EREFERENCE =
/&(?!#{NAME};)/
DEFAULT_ENTITIES =
{
  'gt' => [/&gt;/, '&gt;', '>', />/],
  'lt' => [/&lt;/, '&lt;', '<', /</],
  'quot' => [/&quot;/, '&quot;', '"', /"/],
  "apos" => [/&apos;/, "&apos;", "'", /'/]
}
MISSING_ATTRIBUTE_QUOTES =

These are patterns to identify common markup errors, to make the error messages more informative.

/^<#{NAME_STR}\s+#{NAME_STR}\s*=\s*[^"']/um

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(source) ⇒ BaseParser


116
117
118
119
# File 'lib/rexml/parsers/baseparser.rb', line 116

def initialize( source )
  self.stream = source
  @listeners = []
end

Instance Attribute Details

#sourceObject (readonly)

Returns the value of attribute source


125
126
127
# File 'lib/rexml/parsers/baseparser.rb', line 125

def source
  @source
end

Instance Method Details

#add_listener(listener) ⇒ Object


121
122
123
# File 'lib/rexml/parsers/baseparser.rb', line 121

def add_listener( listener )
  @listeners << listener
end

#empty?Boolean

Returns true if there are no more events


147
148
149
# File 'lib/rexml/parsers/baseparser.rb', line 147

def empty?
  return (@source.empty? and @stack.empty?)
end

#entity(reference, entities) ⇒ Object


448
449
450
451
452
453
454
455
456
# File 'lib/rexml/parsers/baseparser.rb', line 448

def entity( reference, entities )
  value = nil
  value = entities[ reference ] if entities
  if not value
    value = DEFAULT_ENTITIES[ reference ]
    value = value[2] if value
  end
  unnormalize( value, entities ) if value
end

#has_next?Boolean

Returns true if there are more events. Synonymous with !empty?


152
153
154
# File 'lib/rexml/parsers/baseparser.rb', line 152

def has_next?
  return !(@source.empty? and @stack.empty?)
end

#normalize(input, entities = nil, entity_filter = nil) ⇒ Object

Escapes all possible entities


459
460
461
462
463
464
465
466
467
468
469
470
471
472
# File 'lib/rexml/parsers/baseparser.rb', line 459

def normalize( input, entities=nil, entity_filter=nil )
  copy = input.clone
  # Doing it like this rather than in a loop improves the speed
  copy.gsub!( EREFERENCE, '&amp;' )
  entities.each do |key, value|
    copy.gsub!( value, "&#{key};" ) unless entity_filter and
                                entity_filter.include?(entity)
  end if entities
  copy.gsub!( EREFERENCE, '&amp;' )
  DEFAULT_ENTITIES.each do |key, value|
    copy.gsub!( value[3], value[1] )
  end
  copy
end

#peek(depth = 0) ⇒ Object

Peek at the depth event in the stack. The first element on the stack is at depth 0. If depth is -1, will parse to the end of the input stream and return the last event, which is always :end_document. Be aware that this causes the stream to be parsed up to the depth event, so you can effectively pre-parse the entire document (pull the entire thing into memory) using this method.


168
169
170
171
172
173
174
175
176
177
178
179
180
# File 'lib/rexml/parsers/baseparser.rb', line 168

def peek depth=0
  raise %Q[Illegal argument "#{depth}"] if depth < -1
  temp = []
  if depth == -1
    temp.push(pull()) until empty?
  else
    while @stack.size+temp.size < depth+1
      temp.push(pull())
    end
  end
  @stack += temp if temp.size > 0
  @stack[depth]
end

#positionObject


137
138
139
140
141
142
143
144
# File 'lib/rexml/parsers/baseparser.rb', line 137

def position
  if @source.respond_to? :position
    @source.position
  else
    # FIXME
    0
  end
end

#pullObject

Returns the next event. This is a PullEvent object.


183
184
185
186
187
188
189
# File 'lib/rexml/parsers/baseparser.rb', line 183

def pull
  pull_event.tap do |event|
    @listeners.each do |listener|
      listener.receive event
    end
  end
end

#stream=(source) ⇒ Object


127
128
129
130
131
132
133
134
135
# File 'lib/rexml/parsers/baseparser.rb', line 127

def stream=( source )
  @source = SourceFactory.create_from( source )
  @closed = nil
  @document_status = nil
  @tags = []
  @stack = []
  @entities = []
  @nsstack = []
end

#unnormalize(string, entities = nil, filter = nil) ⇒ Object

Unescapes all possible entities


475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
# File 'lib/rexml/parsers/baseparser.rb', line 475

def unnormalize( string, entities=nil, filter=nil )
  rv = string.clone
  rv.gsub!( /\r\n?/, "\n" )
  matches = rv.scan( REFERENCE_RE )
  return rv if matches.size == 0
  rv.gsub!( /&#0*((?:\d+)|(?:x[a-fA-F0-9]+));/ ) {
    m=$1
    m = "0#{m}" if m[0] == ?x
    [Integer(m)].pack('U*')
  }
  matches.collect!{|x|x[0]}.compact!
  if matches.size > 0
    matches.each do |entity_reference|
      unless filter and filter.include?(entity_reference)
        entity_value = entity( entity_reference, entities )
        if entity_value
          re = /&#{entity_reference};/
          rv.gsub!( re, entity_value )
        else
          er = DEFAULT_ENTITIES[entity_reference]
          rv.gsub!( er[0], er[2] ) if er
        end
      end
    end
    rv.gsub!( /&amp;/, '&' )
  end
  rv
end

#unshift(token) ⇒ Object

Push an event back on the head of the stream. This method has (theoretically) infinite depth.


158
159
160
# File 'lib/rexml/parsers/baseparser.rb', line 158

def unshift token
  @stack.unshift(token)
end