Class: MultiSAX::SAX

Inherits:
Object
  • Object
show all
Defined in:
lib/multisax.rb

Overview

The class to handle XML libraries.

Instance Method Summary collapse

Constructor Details

#initialize ⇒ SAX

constructor. list cannot be passed directly, since you should check the retval of open().



26
27
28
 
# File 'lib/multisax.rb', line 26

def initialize
	@parser=nil
end

Instance Method Details

#open(*list) ⇒ Object

Library loader. Arguments are list (or Array) of libraries.

if list is empty or :XML, the following are searched (order by speed):
:ox, :libxml, :xmlparser, :nokogiri, :oga, :rexmlstream, :rexmlsax2
if list is :HTML, the following are searched (order by speed):
:oxhtml, :nokogirihtml, :ogahtml
You can also specify libraries individually.
If multiple selected, MultiSAX will try the libraries one by one and use the first usable one.



37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
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
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
 
# File 'lib/multisax.rb', line 37

def open(*list)
	return @parser if @parser
	list=XML_PARSERS_INSTALLABLE+XML_PARSERS_DEFAULT if list.empty?||list==[:XML]
	list=HTML_PARSERS_INSTALLABLE if list==[:HTML]
	list.each{|e_module|
		case e_module
			when :ox,:oxhtml
				begin
					require 'ox'
					require 'stringio' #this should be standard module.
				rescue LoadError;next end
				@parser=e_module
				@saxhelper=Class.new(::Ox::Sax){
					def __init__(obj)
						@obj=obj
						@saxwrapper_tag=nil
						@saxwrapper_attr={}
						self
					end
					def end_element(tag) @obj.sax_tag_end(tag.to_s) end
					def cdata(txt) @obj.sax_cdata(txt) end
					def text(txt) @obj.sax_text(txt) end
					def comment(txt) @obj.sax_comment(txt) end

					def start_element(tag)
						if @after_error
							@obj.sax_tag_start(tag.to_s,{})
							@after_error=false
						else
							# I hope provided Listener's sax_tag_start will NOT be used elsewhere.
							#alias :attrs_done :attrs_done_normal
							@saxwrapper_tag=tag
							@saxwrapper_attr={}
						end
					end
					def attr(name,str)
						@saxwrapper_attr[name.to_s]=str
					end
					def attrs_done_xmldecl
						@obj.sax_xmldecl(@saxwrapper_attr['version'],@saxwrapper_attr['encoding'],@saxwrapper_attr['standalone'])
					end
					def attrs_done_normal
						@obj.sax_tag_start(@saxwrapper_tag.to_s,@saxwrapper_attr)
					end
					def attrs_done
						@saxwrapper_tag ? attrs_done_normal : attrs_done_xmldecl
					end
					def error(s,i,j) @after_error=true if s.end_with?('closed but not opened') end
				}
				break
			when :libxml
				begin
					require 'libxml'
				rescue LoadError;next end
				@parser=e_module
				@saxhelper=Class.new{
					include ::LibXML::XML::SaxParser::Callbacks
					def __init__(obj)
						@obj=obj
						self
					end
					def on_start_element(tag,attrs) @obj.sax_tag_start(tag,attrs) end
					def on_end_element(tag) @obj.sax_tag_end(tag) end
					def on_characters(txt) @obj.sax_text(txt) end
					def on_cdata_block(txt) @obj.sax_cdata(txt) end
					def on_comment(txt) @obj.sax_comment(txt) end
					#actually unused
					def xmldecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
				}
				break
			when :nokogiri,:nokogirihtml
				#nokogiri 1.5.x are supported on Ruby 1.8.7.
				#next if RUBY_VERSION<'1.9'
				begin
					require 'nokogiri'
				rescue LoadError;next end
				@parser=e_module
				@saxhelper=Class.new(::Nokogiri::XML::SAX::Document){
					def __init__(obj)
						@obj=obj
						self
					end
					def start_element(tag,attrs) @obj.sax_tag_start(tag,attrs.is_a?(Array) ? Hash[*attrs.flatten(1)] : attrs) end
					def end_element(tag) @obj.sax_tag_end(tag) end
					def characters(txt) @obj.sax_text(txt) end
					def cdata_block(txt) @obj.sax_cdata(txt) end
					def comment(txt) @obj.sax_comment(txt) end
					def xmldecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
				}
				break
			when :xmlparser
				begin
					require 'xml/saxdriver'
				rescue LoadError;next end
				@parser=e_module
				@saxhelper=Class.new(::XML::Parser){
					def __init__(obj)
						@obj=obj
						@cdata=false
						self
					end
					def startElement(tag,attrs) @obj.sax_tag_start(tag,attrs) end
					def endElement(tag) @obj.sax_tag_end(tag) end
					def comment(txt) @obj.sax_comment(txt) end
					def xmlDecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
					def character(txt)
						if @cdata
							@obj.sax_cdata(txt)
						else
							@obj.sax_text(txt)
						end
					end
					def startCdata
						@cdata=true
					end
					def endCdata
						@cdata=false
					end
				}
				break
			when :oga,:ogahtml
				next if RUBY_VERSION<'1.9'
				begin
					require 'oga'
				rescue LoadError;next end
				@parser=e_module
				@saxhelper=Class.new{
					def __init__(obj)
						@obj=obj
						self
					end
					def on_element(ns,tag,attrs)
						tag_name=(ns ? (ns+':') : '')+tag
						@obj.sax_tag_start(tag_name,Hash[*attrs.flatten(1)])
						return tag_name
					end
					def after_element(ns,tag)
						tag_name=(ns ? (ns+':') : '')+tag
						@obj.sax_tag_end(tag_name)
					end
					def on_text(txt) @obj.sax_text(txt) end
					def on_cdata(txt) @obj.sax_cdata(txt) end
					def on_comment(txt) @obj.sax_comment(txt) end
					def on_xml_decl(args)
						attrs=Hash[*args.flatten(1)]
						@obj.sax_xmldecl(attrs['version'],attrs['encoding'],attrs['standalone'])
					end
				}
				break
			# :nocov:
			when :xerces
				begin
					require 'Xerces'
				rescue LoadError;next end
				@parser=e_module
				@saxhelper=Class.new(::XercesR::DocumentHandler){
					def __init__(obj)
						@obj=obj
						#@cdata=false
						self
					end
					def startElement(tag,attrs) @obj.sax_tag_start(tag,Hash[*attrs.getLength.times.map{|i|[attrs.getName(i),attrs.getValue(i)]}.flatten(1)]) end
					def endElement(tag) @obj.sax_tag_end(tag) end
					def comment(txt) @obj.sax_comment(txt) end
					#def xmlDecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
					#def notationDecl(name, publicId, systemId) end
					def characters(txt,len)
						#if @cdata
							@obj.sax_cdata(txt)
						#else
							@obj.sax_text(txt)
						#end
					end
					#def startCdata
					#	@cdata=true
					#end
					#def endCdata
					#	@cdata=false
					#end
				}
				break
			# :nocov:
			when :rexmlstream
				begin
					require 'rexml/parsers/baseparser'
					require 'rexml/parsers/streamparser'
					require 'rexml/streamlistener'
				rescue LoadError;next end
				@parser=e_module
				@saxhelper=Class.new{
					include ::REXML::StreamListener
					def __init__(obj)
						@obj=obj
						self
					end
					def tag_start(tag,attrs) @obj.sax_tag_start(tag,attrs) end
					def tag_end(tag) @obj.sax_tag_end(tag) end
					def text(txt) @obj.sax_text(txt) end
					def cdata(txt) @obj.sax_cdata(txt) end
					def comment(txt) @obj.sax_comment(txt) end
					def xmldecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
				}
				break
			when :rexmlsax2
				begin
					require 'rexml/parsers/sax2parser'
					require 'rexml/sax2listener'
				rescue LoadError;next end
				@parser=e_module
				@saxhelper=Class.new{
					include ::REXML::SAX2Listener
					def __init__(obj)
						@obj=obj
						self
					end
					def start_element(uri,tag,qname,attrs) @obj.sax_tag_start(qname,attrs) end
					def end_element(uri,tag,qname) @obj.sax_tag_end(qname) end
					def characters(txt) @obj.sax_text(txt) end
					def cdata(txt) @obj.sax_cdata(txt) end
					def comment(txt) @obj.sax_comment(txt) end
					def xmldecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
				}
				break
		end
	}
	return @parser
end

#parse(source, listener) ⇒ Object

The main parsing method. Listener can be Class.newMultiSAX::Callbacks.new. Returns the listener after SAX is applied. If you have not called open(), this will call it using default value (all libraries).

From 0.0.1, source can be IO as well as String.
SAX's listeners are usually modified destructively.
So instances shouldn't be provided.



275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
 
# File 'lib/multisax.rb', line 275

def parse(source,listener)
	if !@parser && !open
		raise "Failed to open SAX library. REXML, which is a standard Ruby module, might be also corrupted."
	end
	saxhelper=@saxhelper.new.__init__(listener)
	if source.is_a?(String)
		case @parser
			when :ox           then Ox.sax_parse(saxhelper,StringIO.new(source),:convert_special=>true)
			when :oxhtml       then Ox.sax_parse(saxhelper,StringIO.new(source),:convert_special=>true,:smart=>true)
			when :libxml       then parser=LibXML::XML::SaxParser.string(source);parser.callbacks=saxhelper;parser.parse
			when :nokogiri     then parser=Nokogiri::XML::SAX::Parser.new(saxhelper);parser.parse(source)
			when :nokogirihtml then parser=Nokogiri::HTML::SAX::Parser.new(saxhelper);parser.parse(source)
			when :xmlparser    then saxhelper.parse(source)
			when :oga          then parser=Oga::XML::SaxParser.new(saxhelper,source);parser.parse
			when :ogahtml      then parser=Oga::HTML::SaxParser.new(saxhelper,source);parser.parse
			when :xerces       then parser=XercesR::SAXParser.new;parser.setDocumentHandler(saxhelper);parser.parsebuf(source)
			when :rexmlstream  then REXML::Parsers::StreamParser.new(source,saxhelper).parse
			when :rexmlsax2    then parser=REXML::Parsers::SAX2Parser.new(source);parser.listen(saxhelper);parser.parse
		end
	else
		case @parser
			when :ox           then Ox.sax_parse(saxhelper,source,:convert_special=>true)
			when :oxhtml       then Ox.sax_parse(saxhelper,source,:convert_special=>true,:smart=>true)
			when :libxml       then parser=LibXML::XML::SaxParser.io(source);parser.callbacks=saxhelper;parser.parse
			when :nokogiri     then parser=Nokogiri::XML::SAX::Parser.new(saxhelper);parser.parse(source)
			when :nokogirihtml then parser=Nokogiri::HTML::SAX::Parser.new(saxhelper);parser.parse(source.read) # fixme: nokogirihtml IO doesn't allow errors.
			when :xmlparser    then saxhelper.parse(source)
			when :oga          then parser=Oga::XML::SaxParser.new(saxhelper,source);parser.parse
			when :ogahtml      then parser=Oga::HTML::SaxParser.new(saxhelper,source);parser.parse
			when :xerces       then parser=XercesR::SAXParser.new;parser.setDocumentHandler(saxhelper);parser.parsebuf(source.read)
			when :rexmlstream  then REXML::Parsers::StreamParser.new(source,saxhelper).parse
			when :rexmlsax2    then parser=REXML::Parsers::SAX2Parser.new(source);parser.listen(saxhelper);parser.parse
		end
	end
	listener
end

#parsefile(filename, listener) ⇒ Object

Parses file as XML. Error handling might be changed in the future.



313
314
315
316
317
318
319
320
321
322
 
# File 'lib/multisax.rb', line 313

def parsefile(filename,listener)
	#begin
		return nil unless FileTest::readable?(filename)
		File.open(filename,'rb'){|f|
			return parse(f,listener)
		}
	#rescue
	#	return nil
	#end
end

#parser ⇒ Object

Returns which module is actually chosen.



267
 
# File 'lib/multisax.rb', line 267

def parser() @parser end

#reset ⇒ Object

Reset MultiSAX state so that you can re-open() another library.



265
 
# File 'lib/multisax.rb', line 265

def reset() @parser=nil end