Class: REXML::Parsers::SAX2Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/extensions/rexml/rexml/parsers/sax2parser.rb

Overview

SAX2Parser

Instance Method Summary collapse

Constructor Details

#initialize(source) ⇒ SAX2Parser

Returns a new instance of SAX2Parser.



10
11
12
13
14
15
16
17
18
 
# File 'lib/extensions/rexml/rexml/parsers/sax2parser.rb', line 10

def initialize source
  @parser = BaseParser.new(source)
  @listeners = []
  @procs = []
  @namespace_stack = []
  @has_listeners = false
  @tag_stack = []
  @entities = {}
end

Instance Method Details

#add_listener(listener) ⇒ Object 



24
25
26
 
# File 'lib/extensions/rexml/rexml/parsers/sax2parser.rb', line 24

def add_listener( listener )
  @parser.add_listener( listener )
end

#deafen(listener = nil, &blok) ⇒ Object 



76
77
78
79
80
81
82
83
 
# File 'lib/extensions/rexml/rexml/parsers/sax2parser.rb', line 76

def deafen( listener=nil, &blok )
  if listener
    @listeners.delete_if {|item| item[-1] == listener }
    @has_listeners = false if @listeners.size == 0
  else
    @procs.delete_if {|item| item[-1] == blok }
  end
end

#listen(*args, &blok) ⇒ Object

Listen arguments:

Symbol, Array, Block Listen to Symbol events on Array elements Symbol, Block

Listen to Symbol events

Array, Listener Listen to all events on Array elements Array, Block Listen to :start_element events on Array elements Listener Listen to All events

Symbol can be one of: :start_element, :end_element, :start_prefix_mapping, :end_prefix_mapping, :characters, :processing_instruction, :doctype, :attlistdecl, :elementdecl, :entitydecl, :notationdecl, :cdata, :xmldecl, :comment

There is an additional symbol that can be listened for: :progress. This will be called for every event generated, passing in the current stream position.

Array contains regular expressions or strings which will be matched against fully qualified element names.

Listener must implement the methods in SAX2Listener

Block will be passed the same arguments as a SAX2Listener method would be, where the method name is the same as the matched Symbol. See the SAX2Listener for more information.



58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
 
# File 'lib/extensions/rexml/rexml/parsers/sax2parser.rb', line 58

def listen( *args, &blok )
  if args[0].kind_of? Symbol
    if args.size == 2
      args[1].each { |match| @procs << [args[0], match, blok] }
    else
      add( [args[0], nil, blok] )
    end
  elsif args[0].kind_of? Array
    if args.size == 2
      args[0].each { |match| add( [nil, match, args[1]] ) }
    else
      args[0].each { |match| add( [ :start_element, match, blok ] ) }
    end
  else
    add([nil, nil, args[0]])
  end
end

#parse ⇒ Object 



85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
 
# File 'lib/extensions/rexml/rexml/parsers/sax2parser.rb', line 85

def parse
  @procs.each { |sym,match,block| block.call if sym == :start_document }
  @listeners.each { |sym,match,block| 
    block.start_document if sym == :start_document or sym.nil?
  }
  root = context = []
  while true
    event = @parser.pull
    case event[0]
    when :end_document
      handle( :end_document )
      break
    when :start_doctype
      handle( :doctype, *event[1..-1])
    when :end_doctype
      context = context[1]
    when :start_element
      @tag_stack.push(event[1])
      # find the observers for namespaces
      procs = get_procs( :start_prefix_mapping, event[1] )
      listeners = get_listeners( :start_prefix_mapping, event[1] )
      if procs or listeners
        # break out the namespace declarations
        # The attributes live in event[2]
        event[2].each {|n, v| event[2][n] = @parser.normalize(v)}
        nsdecl = event[2].find_all { |n, value| n =~ /^xmlns(:|$)/ }
        nsdecl.collect! { |n, value| [ n[6..-1], value ] }
        @namespace_stack.push({})
        nsdecl.each do |n,v|
          @namespace_stack[-1][n] = v
          # notify observers of namespaces
          procs.each { |ob| ob.call( n, v ) } if procs
          listeners.each { |ob| ob.start_prefix_mapping(n, v) } if listeners
        end
      end
      event[1] =~ Namespace::NAMESPLIT
      prefix = $1
      local = $2
      uri = get_namespace(prefix)
      # find the observers for start_element
      procs = get_procs( :start_element, event[1] )
      listeners = get_listeners( :start_element, event[1] )
      # notify observers
      procs.each { |ob| ob.call( uri, local, event[1], event[2] ) } if procs
      listeners.each { |ob| 
        ob.start_element( uri, local, event[1], event[2] ) 
      } if listeners
    when :end_element
      @tag_stack.pop
      event[1] =~ Namespace::NAMESPLIT
      prefix = $1
      local = $2
      uri = get_namespace(prefix)
      # find the observers for start_element
      procs = get_procs( :end_element, event[1] )
      listeners = get_listeners( :end_element, event[1] )
      # notify observers
      procs.each { |ob| ob.call( uri, local, event[1] ) } if procs
      listeners.each { |ob| 
        ob.end_element( uri, local, event[1] ) 
      } if listeners

      namespace_mapping = @namespace_stack.pop
      # find the observers for namespaces
      procs = get_procs( :end_prefix_mapping, event[1] )
      listeners = get_listeners( :end_prefix_mapping, event[1] )
      if procs or listeners
        namespace_mapping.each do |ns_prefix, ns_uri|
          # notify observers of namespaces
          procs.each { |ob| ob.call( ns_prefix ) } if procs
          listeners.each { |ob| ob.end_prefix_mapping(ns_prefix) } if listeners
        end
      end
    when :text
      #normalized = @parser.normalize( event[1] )
      #handle( :characters, normalized )
      copy = event[1].clone

      esub = proc { |match| 
        if @entities.has_key?($1)
          @entities[$1].gsub(Text::REFERENCE, &esub)
        else
          match
        end
      }

      copy.gsub!( Text::REFERENCE, &esub )
      copy.gsub!( Text::NUMERICENTITY ) {|m|
        m=$1
        m = "0#{m}" if m[0] == ?x
        [Integer(m)].pack('U*')
      }
      handle( :characters, copy )
    when :entitydecl
      @entities[ event[1] ] = event[2] if event.size == 3
      handle( *event )
    when :processing_instruction, :comment, :attlistdecl, 
      :elementdecl, :cdata, :notationdecl, :xmldecl
      handle( *event )
    end
    handle( :progress, @parser.position )
  end
end

#source ⇒ Object 



20
21
22
 
# File 'lib/extensions/rexml/rexml/parsers/sax2parser.rb', line 20

def source
  @parser.source
end