Project

General

Profile

« Previous | Next » 

Revision 49026

Testing metashare

View differences:

modules/dnet-parthenos/trunk/src/test/java/eu/dnetlib/x3m/ApplyX3MappingTest.java
99 99
		doBasicTest("dariah-GR_317_mapping.xml", "/eu/dnetlib/x3m/dariah.xml");
100 100
	}
101 101

  
102
	@Test
103
	public void testMetashare(){
104
		doBasicTest("metashare_387_mapping.xml", "/eu/dnetlib/x3m/metashare.xml");
105
	}
102 106

  
107

  
103 108
	public void doBasicTest(String mappingPath, String recordPath){
104 109
		String m = loadFromTransformationProfile(mappingPath);
105 110
		String g = loadFromTransformationProfile(parthenosPolicyPath);
modules/dnet-parthenos/trunk/src/test/resources/eu/dnetlib/x3m/metashare.xml
1
<?xml version="1.0" encoding="ASCII"?>
2
<resourceInfo xmlns="http://www.ilsp.gr/META-XMLSchema"
3
              xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
4
              xsi:schemaLocation="http://www.ilsp.gr/META-XMLSchema http://metashare.ilsp.gr/META-XMLSchema/v3.0/META-SHARE-Resource.xsd">
5
	<identificationInfo>
6
		<resourceName lang="en">Strongly Comparable and Aligned Legal News EN-FR-RO News Corpus</resourceName>
7
		<description lang="en">This corpus is a collection of strongly comparable English, French and Romanian documents collected from http://ec.europa.eu/ website that are sentence split, POS tagged, lemmatized and chunked and that are also sentence aligned using Moore's sentence aligner (http://research.microsoft.com/pubs/68886/sent-align2-amta-final.pdf).</description>
8
		<metaShareId>NOT_DEFINED_FOR_V2</metaShareId>
9
		<identifier>RACAIEnFrRoNewsCorpus</identifier>
10
	</identificationInfo>
11
	<distributionInfo>
12
		<availability>available-restrictedUse</availability>
13
		<licenceInfo>
14
			<licence>MSCommons-BY-NC-ND</licence>
15
			<restrictionsOfUse>academic-nonCommercialUse</restrictionsOfUse>
16
			<restrictionsOfUse>attribution</restrictionsOfUse>
17
			<restrictionsOfUse>informLicensor</restrictionsOfUse>
18
			<restrictionsOfUse>noRedistribution</restrictionsOfUse>
19
			<distributionAccessMedium>accessibleThroughInterface</distributionAccessMedium>
20
			<distributionAccessMedium>downloadable</distributionAccessMedium>
21
			<attributionText lang="en">Please cite this paper: "Radu Ion, Dan Tufi&#351;, Tiberiu Boro&#351;, Alexandru Ceau&#351;u, and Dan &#350;tef&#259;nescu. On-Line Compilation of Comparable Corpora and their Evaluation. In Marko Tadi&#263;, Mila Dimitrova-Vulchanova, and Svetla Koeva (eds.), Proceedings of The 7th International Conference Formal Approaches to South Slavic and Balkan Languages (FASSBL-7), pp. 29&#8212;34, Croatian Language Technologies Society &#8211; Faculty of Humanities and Social Sciences, Zagreb, Croatia, October 2010. ISBN: 978-953-55375-2-6."</attributionText>
22
			<licensor>
23
				<organizationInfo>
24
					<organizationName lang="en">Research Institute for Artificial Intelligence, Romanian Academy</organizationName>
25
					<organizationShortName lang="en">RACAI</organizationShortName>
26
					<organizationShortName lang="ro">ICIA</organizationShortName>
27
					<departmentName lang="en">NLP Group</departmentName>
28
					<communicationInfo>
29
						<email>office@racai.ro</email>
30
						<url>http://www.racai.ro/</url>
31
						<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, Bucure&#537;ti, Rom&#226;nia, 050711</address>
32
						<zipCode>050711</zipCode>
33
						<city>Bucharest</city>
34
						<country>Romania</country>
35
						<telephoneNumber>0040 21 3188103</telephoneNumber>
36
						<faxNumber>0040 21 3188142</faxNumber>
37
					</communicationInfo>
38
				</organizationInfo>
39
			</licensor>
40
			<distributionRightsHolder>
41
				<organizationInfo>
42
					<organizationName lang="en">Research Institute for Artificial Intelligence, Romanian Academy</organizationName>
43
					<organizationShortName lang="en">RACAI</organizationShortName>
44
					<organizationShortName lang="ro">ICIA</organizationShortName>
45
					<departmentName lang="en">NLP Group</departmentName>
46
					<communicationInfo>
47
						<email>office@racai.ro</email>
48
						<url>http://www.racai.ro/</url>
49
						<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, Bucure&#537;ti, Rom&#226;nia, 050711</address>
50
						<zipCode>050711</zipCode>
51
						<city>Bucharest</city>
52
						<country>Romania</country>
53
						<telephoneNumber>0040 21 3188103</telephoneNumber>
54
						<faxNumber>0040 21 3188142</faxNumber>
55
					</communicationInfo>
56
				</organizationInfo>
57
			</distributionRightsHolder>
58
			<userNature>academic</userNature>
59
			<userNature>commercial</userNature>
60
		</licenceInfo>
61
		<iprHolder>
62
			<organizationInfo>
63
				<organizationName lang="en">Research Institute for Artificial Intelligence, Romanian Academy</organizationName>
64
				<organizationShortName lang="en">RACAI</organizationShortName>
65
				<organizationShortName lang="ro">ICIA</organizationShortName>
66
				<departmentName lang="en">NLP Group</departmentName>
67
				<communicationInfo>
68
					<email>office@racai.ro</email>
69
					<url>http://www.racai.ro/</url>
70
					<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, Bucure&#537;ti, Rom&#226;nia, 050711</address>
71
					<zipCode>050711</zipCode>
72
					<city>Bucharest</city>
73
					<country>Romania</country>
74
					<telephoneNumber>0040 21 3188103</telephoneNumber>
75
					<faxNumber>0040 21 3188142</faxNumber>
76
				</communicationInfo>
77
			</organizationInfo>
78
		</iprHolder>
79
	</distributionInfo>
80
	<contactPerson>
81
		<surname lang="und">Ion</surname>
82
		<givenName lang="und">Radu</givenName>
83
		<communicationInfo>
84
			<email>radu@racai.ro</email>
85
			<url>http://www.racai.ro/~radu</url>
86
			<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3318</address>
87
			<zipCode>050711</zipCode>
88
			<city>Bucure&#537;ti</city>
89
			<country>Rom&#226;nia</country>
90
			<telephoneNumber>0040 21 3188103</telephoneNumber>
91
			<faxNumber>0040 21 3188142</faxNumber>
92
		</communicationInfo>
93
		<position>senior researcher, 3rd grade</position>
94
		<affiliation>
95
			<organizationName lang="und">"Mihai Dr&#259;g&#259;nescu" Research Institute for Artificial Intelligence of the Romanian Academy</organizationName>
96
			<organizationShortName lang="und">RACAI</organizationShortName>
97
			<departmentName lang="und">NLP Group</departmentName>
98
			<communicationInfo>
99
				<email>office@racai.ro</email>
100
				<url>http://www.racai.ro</url>
101
				<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3310</address>
102
				<zipCode>050711</zipCode>
103
				<city>Bucure&#537;ti</city>
104
				<country>Rom&#226;nia</country>
105
				<telephoneNumber>0040 21 3188103</telephoneNumber>
106
				<faxNumber>0040 21 3188142</faxNumber>
107
			</communicationInfo>
108
		</affiliation>
109
	</contactPerson>
110
	<metadataInfo>
111
		<metadataCreationDate>2012-12-18</metadataCreationDate>
112
		<metadataCreator>
113
			<surname lang="und">Ion</surname>
114
			<givenName lang="und">Radu</givenName>
115
			<communicationInfo>
116
				<email>radu@racai.ro</email>
117
				<url>http://www.racai.ro/~radu</url>
118
				<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3318</address>
119
				<zipCode>050711</zipCode>
120
				<city>Bucure&#537;ti</city>
121
				<country>Rom&#226;nia</country>
122
				<telephoneNumber>0040 21 3188103</telephoneNumber>
123
				<faxNumber>0040 21 3188142</faxNumber>
124
			</communicationInfo>
125
			<position>senior researcher, 3rd grade</position>
126
			<affiliation>
127
				<organizationName lang="und">"Mihai Dr&#259;g&#259;nescu" Research Institute for Artificial Intelligence of the Romanian Academy</organizationName>
128
				<organizationShortName lang="und">RACAI</organizationShortName>
129
				<departmentName lang="und">NLP Group</departmentName>
130
				<communicationInfo>
131
					<email>office@racai.ro</email>
132
					<url>http://www.racai.ro</url>
133
					<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3310</address>
134
					<zipCode>050711</zipCode>
135
					<city>Bucure&#537;ti</city>
136
					<country>Rom&#226;nia</country>
137
					<telephoneNumber>0040 21 3188103</telephoneNumber>
138
					<faxNumber>0040 21 3188142</faxNumber>
139
				</communicationInfo>
140
			</affiliation>
141
		</metadataCreator>
142
		<source>METANET4U</source>
143
		<originalMetadataSchema>3.0</originalMetadataSchema>
144
		<metadataLanguageName>English</metadataLanguageName>
145
		<metadataLanguageId>en</metadataLanguageId>
146
		<metadataLastDateUpdated>2012-12-18</metadataLastDateUpdated>
147
	</metadataInfo>
148
	<validationInfo>
149
		<validated>true</validated>
150
		<validationType>formal</validationType>
151
		<validationMode>automatic</validationMode>
152
		<validationModeDetails>Parsed for XCES conformance.</validationModeDetails>
153
		<validationExtent>full</validationExtent>
154
		<validator>
155
			<personInfo>
156
				<surname lang="und">Ion</surname>
157
				<givenName lang="und">Radu</givenName>
158
				<communicationInfo>
159
					<email>radu@racai.ro</email>
160
					<url>http://www.racai.ro/~radu</url>
161
					<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3318</address>
162
					<zipCode>050711</zipCode>
163
					<city>Bucure&#537;ti</city>
164
					<country>Rom&#226;nia</country>
165
					<telephoneNumber>0040 21 3188103</telephoneNumber>
166
					<faxNumber>0040 21 3188142</faxNumber>
167
				</communicationInfo>
168
				<position>senior researcher, 3rd grade</position>
169
				<affiliation>
170
					<organizationName lang="und">"Mihai Dr&#259;g&#259;nescu" Research Institute for Artificial Intelligence of the Romanian Academy</organizationName>
171
					<organizationShortName lang="und">RACAI</organizationShortName>
172
					<departmentName lang="und">NLP Group</departmentName>
173
					<communicationInfo>
174
						<email>office@racai.ro</email>
175
						<url>http://www.racai.ro</url>
176
						<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3310</address>
177
						<zipCode>050711</zipCode>
178
						<city>Bucure&#537;ti</city>
179
						<country>Rom&#226;nia</country>
180
						<telephoneNumber>0040 21 3188103</telephoneNumber>
181
						<faxNumber>0040 21 3188142</faxNumber>
182
					</communicationInfo>
183
				</affiliation>
184
			</personInfo>
185
		</validator>
186
	</validationInfo>
187
	<resourceDocumentationInfo>
188
		<documentation>
189
			<documentInfo>
190
				<documentType>manual</documentType>
191
				<title lang="en">Strongly Comparable and Aligned Legal News EN-FR-RO News Corpus</title>
192
				<author>Radu Ion</author>
193
				<url>http://ws.racai.ro:9191/narratives/batch3/EnFrRoSentenceAlignedCorpus.pdf</url>
194
				<keywords>parallel corpus, English, Romanian, French, POS-tagged, lemmatized, chunked</keywords>
195
				<documentLanguageName>English</documentLanguageName>
196
				<documentLanguageId>en</documentLanguageId>
197
			</documentInfo>
198
		</documentation>
199
		<toolDocumentationType>manual</toolDocumentationType>
200
	</resourceDocumentationInfo>
201
	<resourceCreationInfo>
202
		<resourceCreator>
203
			<personInfo>
204
				<surname lang="und">Ion</surname>
205
				<givenName lang="und">Radu</givenName>
206
				<communicationInfo>
207
					<email>radu@racai.ro</email>
208
					<url>http://www.racai.ro/~radu</url>
209
					<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3318</address>
210
					<zipCode>050711</zipCode>
211
					<city>Bucure&#537;ti</city>
212
					<country>Rom&#226;nia</country>
213
					<telephoneNumber>0040 21 3188103</telephoneNumber>
214
					<faxNumber>0040 21 3188142</faxNumber>
215
				</communicationInfo>
216
				<position>senior researcher, 3rd grade</position>
217
				<affiliation>
218
					<organizationName lang="und">"Mihai Dr&#259;g&#259;nescu" Research Institute for Artificial Intelligence of the Romanian Academy</organizationName>
219
					<organizationShortName lang="und">RACAI</organizationShortName>
220
					<departmentName lang="und">NLP Group</departmentName>
221
					<communicationInfo>
222
						<email>office@racai.ro</email>
223
						<url>http://www.racai.ro</url>
224
						<address>Casa Academiei, Calea 13 Septembrie nr. 13, etaj 3, birou 3310</address>
225
						<zipCode>050711</zipCode>
226
						<city>Bucure&#537;ti</city>
227
						<country>Rom&#226;nia</country>
228
						<telephoneNumber>0040 21 3188103</telephoneNumber>
229
						<faxNumber>0040 21 3188142</faxNumber>
230
					</communicationInfo>
231
				</affiliation>
232
			</personInfo>
233
		</resourceCreator>
234
	</resourceCreationInfo>
235
	<resourceComponentType>
236
		<corpusInfo>
237
			<resourceType>corpus</resourceType>
238
			<corpusMediaType>
239
				<corpusTextInfo>
240
					<mediaType>text</mediaType>
241
					<lingualityInfo>
242
						<lingualityType>multilingual</lingualityType>
243
						<multilingualityType>comparable</multilingualityType>
244
						<multilingualityTypeDetails>A parallel sub-corpus is extracted.</multilingualityTypeDetails>
245
					</lingualityInfo>
246
					<languageInfo>
247
						<languageId>en</languageId>
248
						<languageName>English</languageName>
249
						<sizePerLanguage>
250
							<size>1848</size>
251
							<sizeUnit>files</sizeUnit>
252
						</sizePerLanguage>
253
					</languageInfo>
254
					<languageInfo>
255
						<languageId>fr</languageId>
256
						<languageName>French</languageName>
257
						<sizePerLanguage>
258
							<size>1809</size>
259
							<sizeUnit>files</sizeUnit>
260
						</sizePerLanguage>
261
					</languageInfo>
262
					<languageInfo>
263
						<languageId>ro</languageId>
264
						<languageName>Romanian</languageName>
265
						<sizePerLanguage>
266
							<size>966</size>
267
							<sizeUnit>files</sizeUnit>
268
						</sizePerLanguage>
269
					</languageInfo>
270
					<modalityInfo>
271
						<modalityType>writtenLanguage</modalityType>
272
					</modalityInfo>
273
					<sizeInfo>
274
						<size>4623</size>
275
						<sizeUnit>files</sizeUnit>
276
					</sizeInfo>
277
					<textFormatInfo>
278
						<mimeType>text/xml</mimeType>
279
					</textFormatInfo>
280
					<characterEncodingInfo>
281
						<characterEncoding>UTF-8</characterEncoding>
282
					</characterEncodingInfo>
283
					<domainInfo>
284
						<domain>Legal news</domain>
285
						<conformanceToClassificationScheme>other</conformanceToClassificationScheme>
286
					</domainInfo>
287
					<timeCoverageInfo>
288
						<timeCoverage>Years 2010-2011</timeCoverage>
289
					</timeCoverageInfo>
290
					<creationInfo>
291
						<creationMode>automatic</creationMode>
292
					</creationInfo>
293
				</corpusTextInfo>
294
			</corpusMediaType>
295
		</corpusInfo>
296
	</resourceComponentType>
297
</resourceInfo>

Also available in: Unified diff