1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
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
264
265
266
267
268
269
270
271
272
273
274
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
311
312
313
314
315
316
317
318
319
320
321
|
Description: As DFAONTCPRFinder pre-trained model is removed from the
tarball due to DFSG and ML Policy compliance, tests cannot be run.
Author: Andrius Merkys <merkys@debian.org>
Forwarded: not-needed
--- a/oscar4-recogniser-core/src/test/java/uk/ac/cam/ch/wwmm/oscarrecogniser/finder/DFANEFinderTest.java
+++ /dev/null
@@ -1,238 +0,0 @@
-package uk.ac.cam.ch.wwmm.oscarrecogniser.finder;
-
-import static org.junit.Assert.*;
-
-import java.net.URISyntaxException;
-import java.util.ArrayList;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-import org.junit.AfterClass;
-import org.junit.BeforeClass;
-import org.junit.Test;
-
-import uk.ac.cam.ch.wwmm.oscar.chemnamedict.core.ChemNameDictRegistry;
-import uk.ac.cam.ch.wwmm.oscar.chemnamedict.dictionaries.PolymerDictionary;
-import uk.ac.cam.ch.wwmm.oscar.document.NamedEntity;
-import uk.ac.cam.ch.wwmm.oscar.document.ProcessingDocument;
-import uk.ac.cam.ch.wwmm.oscar.document.ProcessingDocumentFactory;
-import uk.ac.cam.ch.wwmm.oscar.document.TokenSequence;
-import uk.ac.cam.ch.wwmm.oscar.ont.OntologyTerms;
-import uk.ac.cam.ch.wwmm.oscar.types.NamedEntityType;
-import uk.ac.cam.ch.wwmm.oscarrecogniser.tokenanalysis.NGram;
-import uk.ac.cam.ch.wwmm.oscartokeniser.TokenClassifier;
-import uk.ac.cam.ch.wwmm.oscartokeniser.Tokeniser;
-
-import com.google.common.collect.ArrayListMultimap;
-import com.google.common.collect.ListMultimap;
-
-/**
- * @author sea36
- * @author dmj30
- */
-public class DFANEFinderTest {
-
- private static Set<String> defaultRegistryNames;
- private static DFANEFinder finder;
- private static Tokeniser tokeniser;
-
- private static final double DEFAULT_NGRAM_THRESHOLD = -2;
-
- @BeforeClass
- public static void setup() {
- defaultRegistryNames = Collections.unmodifiableSet(ChemNameDictRegistry.getDefaultInstance().getAllNames());
- finder = DFANEFinder.getDefaultInstance();
- tokeniser = Tokeniser.getDefaultInstance();
- }
-
- @AfterClass
- public static void cleanUp() {
- defaultRegistryNames = null;
- finder = null;
- tokeniser = null;
- }
-
- @Test
- public void testDFANEFinder() {
- // Synthesis of 4-Pyridone-3-sulfate and an improved synthesis of 3-Hydroxy-4-Pyridone
- // Edward J Behrman
- // Chemistry Central Journal 2009, 3:1
- // doi:10.1186/1752-153X-3-1
- String paragraph = "Following removal of 4-pyridone by extraction with methyl ethyl ketone as described above, the dried salt cake was re-extracted with about 250 mL of 95% ethanol for seven hours. Cooling the solution gave 2 g of crude material as off-white crystals (17%). It was recrystallized from 95% ethanol. It gradually decomposes between 250\u2013290\u00B0C without melting. Anal. calcd. for C5H4NO5SNa + 1.5H2O: C, 25.00%; H, 2.94%; N, 5.83%. Found: C, 25.17%, H, 2.70%; N, 5.87%. Hydrolysis of the ester in 0.2 M sulfuric acid for 30 min at 95\u00B0C followed by neutralization with NaOH and drying gives a residue from which 3-hydroxy-4-pyridone may be extracted quantitatively by trituration with boiling 95% ethanol and purification by crystallization from methanol as above.";
-
- TokenSequence ts = tokeniser.tokenise(paragraph);
- List<NamedEntity> namedEntityList = finder.findNamedEntities(ts, NGram.getInstance(), DEFAULT_NGRAM_THRESHOLD);
- String expected = "[NE:STOP:18:20:of], [NE:CPR:21:23:4-], [NE:CM:21:31:4-pyridone], [NE:CM:21:31:4-pyridone], [NE:STOP:32:34:by], [NE:STOP:46:50:with], [NE:CM:51:57:methyl], [NE:CM:51:57:methyl], [NE:CM:51:57:methyl], [NE:CM:58:63:ethyl], [NE:CM:58:63:ethyl], [NE:CM:58:63:ethyl], [NE:CM:51:70:methyl ethyl ketone], [NE:CM:58:70:ethyl ketone], [NE:CM:64:70:ketone], [NE:CM:64:70:ketone], [NE:ONT:64:70:ketone], [NE:STOP:71:73:as], [NE:STOP:84:89:above], [NE:STOP:91:94:the], [NE:ONT:101:105:salt], [NE:STOP:111:114:was], [NE:STOP:128:132:with], [NE:STOP:133:138:about], [NE:STOP:146:148:of], [NE:CM:153:160:ethanol], [NE:CM:153:160:ethanol], [NE:CM:153:160:ethanol], [NE:STOP:161:164:for], [NE:STOP:186:189:the], [NE:STOP:208:210:of], [NE:STOP:226:228:as], [NE:STOP:229:232:off], [NE:AHA:255:257:It], [NE:STOP:258:261:was], [NE:STOP:277:281:from], [NE:CM:286:293:ethanol], [NE:CM:286:293:ethanol], [NE:CM:286:293:ethanol], [NE:AHA:295:297:It], [NE:STOP:319:326:between], [NE:CPR:327:331:250\u2013], [NE:STOP:337:344:without], [NE:ONT:345:352:melting], [NE:CM:360:365:calcd], [NE:CM:360:365:calcd], [NE:STOP:367:370:for], [NE:CM:371:381:C5H4NO5SNa], [NE:CM:384:390:1.5H2O], [NE:AHA:392:393:C], [NE:CM:392:393:C], [NE:CM:392:393:C], [NE:AHA:403:404:H], [NE:CM:403:404:H], [NE:CM:403:404:H], [NE:AHA:413:414:N], [NE:CM:413:414:N], [NE:CM:413:414:N], [NE:AHA:430:431:C], [NE:CM:430:431:C], [NE:CM:430:431:C], [NE:AHA:441:442:H], [NE:CM:441:442:H], [NE:CM:441:442:H], [NE:AHA:451:452:N], [NE:CM:451:452:N], [NE:CM:451:452:N], [NE:ONT:461:471:Hydrolysis], [NE:STOP:472:474:of], [NE:STOP:475:478:the], [NE:ONT:479:484:ester], [NE:STOP:485:487:in], [NE:STOP:488:493:0.2 M], [NE:AHA:492:493:M], [NE:CM:494:507:sulfuric acid], [NE:STOP:503:507:acid], [NE:ONT:503:507:acid], [NE:STOP:508:511:for], [NE:STOP:519:521:at], [NE:STOP:536:538:by], [NE:STOP:554:558:with], [NE:AHA:559:563:NaOH], [NE:CM:559:563:NaOH], [NE:CM:559:563:NaOH], [NE:STOP:564:567:and], [NE:STOP:581:582:a], [NE:STOP:591:595:from], [NE:STOP:596:601:which], [NE:CPR:602:604:3-], [NE:CM:602:622:3-hydroxy-4-pyridone], [NE:CM:602:622:3-hydroxy-4-pyridone], [NE:STOP:623:626:may], [NE:STOP:627:629:be], [NE:STOP:655:657:by], [NE:STOP:670:674:with], [NE:CM:687:694:ethanol], [NE:CM:687:694:ethanol], [NE:CM:687:694:ethanol], [NE:STOP:695:698:and], [NE:STOP:712:714:by], [NE:ONT:715:730:crystallization], [NE:STOP:731:735:from], [NE:CM:736:744:methanol], [NE:CM:736:744:methanol], [NE:CM:736:744:methanol], [NE:STOP:745:747:as], [NE:STOP:748:753:above]";
-//FIXME DFAFinder can find exactly the same entity multiple times if it is found for different reasons e.g. $INCND (is in chemnamedict), $-yl (ends in yl) etc.
- List<String> found = new ArrayList<String>();
- for (NamedEntity ne : namedEntityList) {
- StringBuilder sb = new StringBuilder("[NE:");
- NamedEntityType type = ne.getType();
- if (type.getParent() != null) {
- type = type.getParent();
- }
- sb.append(type).append(':').append(ne.getStart()).append(':').append(ne.getEnd()).append(':').append(ne.getSurface()).append(']');
- found.add(sb.toString());
- }
-
- assertEquals(Arrays.asList(expected.split(", ")), found);
- }
-
- @Test
- public void testGenerateTokenRepresentations() {
- String paragraph = "The quick brown ethyl acetate jumps over the lazy adenosine triphosphate";
- TokenSequence ts = tokeniser.tokenise(paragraph);
- List<RepresentationList> repsLists = finder.generateTokenRepresentations(ts, NGram.getInstance(), DEFAULT_NGRAM_THRESHOLD);
- assertEquals(11, repsLists.size());
- for (int i = 0; i < 11; i++) {
- if (i==3) {
- assertTrue(repsLists.get(i).toList().contains("$GP"));
- assertFalse(repsLists.get(i).toList().contains("$CM"));
- }
- else if (i==4 | i==9 | i==10) {
- assertTrue(repsLists.get(i).toList().contains("$CM"));
- assertFalse(repsLists.get(i).toList().contains("$GP"));
- }
- else {
- assertFalse(repsLists.get(i).toList().contains("$CM"));
- assertFalse(repsLists.get(i).toList().contains("$GP"));
- }
- }
- }
-
- @Test
- public void testGenerateTokenRepresentationsObeysNgramThreshold() {
- String paragraph = "The quick brown ethyl acetate jumps over the lazy adenosine triphosphate";
- TokenSequence ts = tokeniser.tokenise(paragraph);
- List<RepresentationList> repsLists = finder.generateTokenRepresentations(ts, NGram.getInstance(), 500);
- assertEquals(11, repsLists.size());
- for (int i = 0; i < 11; i++) {
- assertFalse(repsLists.get(i).toList().contains("$CM"));
- assertFalse(repsLists.get(i).toList().contains("$GP"));
- }
- }
-
- @Test
- public void testSulfuricAcid() {
- // derived from testDFANEFinder()
- StringBuffer paragraph = new StringBuffer();
- for (int i=1; i<47; i++) paragraph.append(" ");
- paragraph.append(" ");
- paragraph.append(
- "Hydrolysis of the ester in 0.2 M sulfuric acid for 30 min at 95\u00B0C."
- );
-
- TokenSequence ts = tokeniser.tokenise(paragraph.toString());
- List<NamedEntity> namedEntityList = finder.findNamedEntities(ts, NGram.getInstance(), DEFAULT_NGRAM_THRESHOLD);
- String expected = "[NE:ONT:464:474:Hydrolysis], [NE:STOP:475:477:of], [NE:STOP:478:481:the], [NE:ONT:482:487:ester], [NE:STOP:488:490:in], [NE:STOP:491:496:0.2 M], [NE:AHA:495:496:M], [NE:CM:497:510:sulfuric acid], [NE:STOP:506:510:acid], [NE:ONT:506:510:acid], [NE:STOP:511:514:for], [NE:STOP:522:524:at]";
-
- List<String> found = new ArrayList<String>();
- for (NamedEntity ne : namedEntityList) {
- StringBuilder sb = new StringBuilder("[NE:");
- NamedEntityType type = ne.getType();
- if (type.getParent() != null) {
- type = type.getParent();
- }
- sb.append(type).append(':').append(ne.getStart()).append(':').append(ne.getEnd()).append(':').append(ne.getSurface()).append(']');
- found.add(sb.toString());
- }
-
- assertEquals(Arrays.asList(expected.split(", ")), found);
- }
-
- @Test
- public void testHPEI() throws Exception {
- // derived from ChemicalTagger's ChemistryPOSTaggerTest.sentence1()
- String paragraph =
- "The synthetic procedure for partially EA- or BA-modified HPEI is exemplified for HPEI25K.";
- TokenSequence ts = tokeniser.tokenise(paragraph);
- ChemNameDictRegistry registry = new ChemNameDictRegistry();
- registry.register(new PolymerDictionary());
- DFANEFinder finder = new DFANEFinder(TermMaps.getInstance().getNeTerms(),
- TokenClassifier.getDefaultInstance(), OntologyTerms.getDefaultInstance(),
- Collections.unmodifiableSet(registry.getAllNames()));
- List<NamedEntity> neList = finder.findNamedEntities(ts, NGram.getInstance(), DEFAULT_NGRAM_THRESHOLD);
- assertTrue(namedEntityListContainsNamedEntity(neList, NamedEntityType.COMPOUND, "HPEI25K", 81, 88));
- }
-
- @Test
- public void testFindOntIds() {
- String source = "noble gas";
- ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(
- Tokeniser.getDefaultInstance(), source);
-
- List<NamedEntity> nes = finder.findNamedEntities(
- procDoc.getTokenSequences().get(0), NGram.getInstance(), DEFAULT_NGRAM_THRESHOLD);
- assertEquals(1, nes.size());
- assertTrue(NamedEntityType.ONTOLOGY.isInstance(nes.get(0).getType()));
- assertEquals(1, nes.get(0).getOntIds().size());
- assertTrue(nes.get(0).getOntIds().contains("CHEBI:33309"));
- }
-
- @Test
- public void testFindCustomOntTerms() {
- ListMultimap<String, String> terms = ArrayListMultimap.create();
- terms.put("jumps", "foo:001");
- terms.put("jumps", "foo:002");
- OntologyTerms ontologyTerms = new OntologyTerms(terms);
- DFANEFinder finder = new DFANEFinder(
- TermMaps.getInstance().getNeTerms(), TokenClassifier.getDefaultInstance(),
- ontologyTerms, defaultRegistryNames);
- String source = "The quick brown ethyl acetate jumps over the lazy acetone";
- ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(
- Tokeniser.getDefaultInstance(), source);
-
- List<NamedEntity> nes = finder.findNamedEntities(
- procDoc.getTokenSequences().get(0), NGram.getInstance(), DEFAULT_NGRAM_THRESHOLD);
- boolean foundJumps = false;
- for (NamedEntity ne : nes) {
- if ("jumps".equals(ne.getSurface())) {
- assertTrue(NamedEntityType.ONTOLOGY.isInstance(ne.getType()));
- assertEquals(2, ne.getOntIds().size());
- assertTrue(ne.getOntIds().contains("foo:001"));
- assertTrue(ne.getOntIds().contains("foo:002"));
- foundJumps = true;
- }
- else {
- assertEquals(0, ne.getOntIds().size());
- }
- if (NamedEntityType.ONTOLOGY.isInstance(ne.getType())) {
- assertEquals("jumps", ne.getSurface());
- }
- }
- assertTrue(foundJumps);
- }
-
- @Test
- public void testFindCustomChemNameDictEntries() throws URISyntaxException {
- Set <String> registryNames = new HashSet<String>();
- registryNames.add("foobar");
- DFANEFinder finder = new DFANEFinder(
- TermMaps.getInstance().getNeTerms(), TokenClassifier.getDefaultInstance(),
- OntologyTerms.getDefaultInstance(), Collections.unmodifiableSet(registryNames));
- String text = "The word 'foobar' in some English text";
- ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(
- tokeniser, text);
- TokenSequence tokSeq = procDoc.getTokenSequences().get(0);
- List <NamedEntity> neList = finder.findNamedEntities(tokSeq, NGram.getInstance(), DEFAULT_NGRAM_THRESHOLD);
- assertTrue(namedEntityListContainsNamedEntity(neList, NamedEntityType.COMPOUND, "foobar", 10, 16));
- }
-
- private boolean namedEntityListContainsNamedEntity(List <NamedEntity> nes, NamedEntityType type, String surface, int start, int end) {
- for (NamedEntity ne : nes) {
- if (type.isInstance(ne.getType())) {
- if (surface.equals(ne.getSurface())) {
- if (start == ne.getStart()) {
- if (end == ne.getEnd()) {
- return true;
- }
- }
- }
- }
- }
- return false;
- }
-}
--- a/oscar4-memmrecogniser/src/test/java/uk/ac/cam/ch/wwmm/oscarMEMM/memm/FeatureExtractorTest.java
+++ /dev/null
@@ -1,73 +0,0 @@
-package uk.ac.cam.ch.wwmm.oscarMEMM.memm;
-
-import static org.junit.Assert.assertEquals;
-
-import java.util.Arrays;
-import java.util.List;
-import java.util.Set;
-
-import org.junit.Test;
-
-import uk.ac.cam.ch.wwmm.oscar.chemnamedict.core.ChemNameDictRegistry;
-import uk.ac.cam.ch.wwmm.oscar.document.TokenSequence;
-import uk.ac.cam.ch.wwmm.oscarrecogniser.extractedtrainingdata.ExtractedTrainingData;
-import uk.ac.cam.ch.wwmm.oscarrecogniser.tokenanalysis.NGram;
-import uk.ac.cam.ch.wwmm.oscartokeniser.Tokeniser;
-
-/**
- * @author sea36
- */
-public class FeatureExtractorTest {
-
- @Test
- public void testFeatureExtractor() {
- // Regression test introduced pre-refactoring
- String s = "We have also described that benzoxasilepines can be condensed with benzaldehydes.";
- Tokeniser tokeniser = Tokeniser.getDefaultInstance();
- TokenSequence tokSeq = tokeniser.tokenise(s);
- Set <String> defaultChemNames = ChemNameDictRegistry.getDefaultInstance().getAllNames();
-
- List<FeatureList> features = FeatureExtractor.extractFeatures(
- tokSeq, NGram.getInstance(), ExtractedTrainingData.loadExtractedTrainingData("chempapers"),
- defaultChemNames);
-
- /*
- assertArrayMatch(Arrays.asList("4G=^We$", "c0:w=We", "c0:wts=We", "c0:ws=42", "c0:s=", "c1:w=have", "c1:wts=have", "c1:ws=1", "c1:s=", "bg:0:1:w=We__ws=1", "bg:0:1:ws=42__ws=1"), features.get(0));
- assertArrayMatch(Arrays.asList("4G=^hav", "3G=hav", "4G=have", "2G=av", "3G=ave", "4G=ave$", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "$STOP:CLOSEDCLASS", "$STOP:NCW", "$STOP:UDW", "c-1:w=We", "c-1:wts=We", "c-1:ws=42", "c-1:s=", "c0:w=have", "c0:wts=have", "c0:ws=1", "c0:s=", "c1:w=also", "c1:wts=also", "c1:ws=1", "c1:s=", "bg:-1:0:w=We__ws=1", "bg:-1:0:ws=42__ws=1", "bg:0:1:ws=1__ws=1"), features.get(1));
- assertArrayMatch(Arrays.asList("4G=^als", "3G=als", "4G=also", "2G=ls", "3G=lso", "4G=lso$", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "ngram-=GP", "$STOP:UDW", "c-1:w=have", "c-1:wts=have", "c-1:ws=1", "c-1:s=", "c0:w=also", "c0:wts=also", "c0:ws=1", "c0:s=", "c1:w=described", "c1:wts=described", "c1:ws=1", "c1:s=", "bg:-1:0:ws=1__ws=1", "bg:0:1:ws=1__ws=1"), features.get(2));
- assertArrayMatch(Arrays.asList("4G=^des", "3G=des", "4G=desc", "2G=es", "3G=esc", "4G=escr", "1G=s", "2G=sc", "3G=scr", "4G=scri", "1G=c", "2G=cr", "3G=cri", "4G=crib", "1G=r", "2G=ri", "3G=rib", "4G=ribe", "1G=i", "2G=ib", "3G=ibe", "4G=ibed", "1G=b", "2G=be", "3G=bed", "4G=bed$", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "$STOP:UDW", "c-1:w=also", "c-1:wts=also", "c-1:ws=1", "c-1:s=", "c0:w=described", "c0:wts=described", "c0:ws=1", "c0:s=", "c1:w=that", "c1:wts=that", "c1:ws=1", "c1:s=", "bg:-1:0:ws=1__ws=1", "bg:0:1:ws=1__ws=1"), features.get(3));
- assertArrayMatch(Arrays.asList("4G=^tha", "3G=tha", "4G=that", "2G=ha", "3G=hat", "4G=hat$", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "$STOP:CLOSEDCLASS", "$STOP:UDW", "c-1:w=described", "c-1:wts=described", "c-1:ws=1", "c-1:s=", "c0:w=that", "c0:wts=that", "c0:ws=1", "c0:s=", "c1:w=benzoxasilepines", "c1:wts=benzoxasilepine", "c1:ws=1", "c1:s=s", "c1:ct=CMS", "bg:-1:0:ws=1__ws=1", "bg:0:1:ws=1__ws=1", "bg:0:1:ws=1__ct=CMS"), features.get(4));
- assertArrayMatch(Arrays.asList("4G=^ben", "3G=ben", "4G=benz", "2G=en", "3G=enz", "4G=enzo", "1G=n", "2G=nz", "3G=nzo", "4G=nzox", "1G=z", "2G=zo", "3G=zox", "4G=zoxa", "1G=o", "2G=ox", "3G=oxa", "4G=oxas", "1G=x", "2G=xa", "3G=xas", "4G=xasi", "1G=a", "2G=as", "3G=asi", "4G=asil", "1G=s", "2G=si", "3G=sil", "4G=sile", "1G=i", "2G=il", "3G=ile", "4G=ilep", "1G=l", "2G=le", "3G=lep", "4G=lepi", "1G=e", "2G=ep", "3G=epi", "4G=epin", "1G=p", "2G=pi", "3G=pin", "4G=pine", "1G=i", "2G=in", "3G=ine", "4G=ines", "1G=n", "2G=ne", "3G=nes", "4G=nes$", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "c-1:w=that", "c-1:wts=that", "c-1:ws=1", "c-1:s=", "c0:w=benzoxasilepines", "c0:wts=benzoxasilepine", "c0:ws=1", "c0:s=s", "c0:ct=CMS", "c1:w=can", "c1:wts=can", "c1:ws=1", "c1:s=", "bg:-1:0:ws=1__ws=1", "bg:-1:0:ws=1__ct=CMS", "bg:0:1:ws=1__w=can", "bg:0:1:ws=1__ws=1", "bg:0:1:ct=CMS__w=can", "bg:0:1:ct=CMS__ws=1"), features.get(5));
- assertArrayMatch(Arrays.asList("4G=^can", "3G=can", "4G=can$", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "$STOP:CLOSEDCLASS", "$STOP:UDW", "c-1:w=benzoxasilepines", "c-1:wts=benzoxasilepine", "c-1:ws=1", "c-1:s=s", "c-1:ct=CMS", "c0:w=can", "c0:wts=can", "c0:ws=1", "c0:s=", "c1:w=be", "c1:wts=be", "c1:ws=1", "c1:s=", "bg:-1:0:ws=1__w=can", "bg:-1:0:ws=1__ws=1", "bg:-1:0:ct=CMS__w=can", "bg:-1:0:ct=CMS__ws=1", "bg:0:1:w=can__w=be", "bg:0:1:w=can__ws=1", "bg:0:1:ws=1__w=be", "bg:0:1:ws=1__ws=1"), features.get(6));
- assertArrayMatch(Arrays.asList("4G=^be$", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "$STOP:CLOSEDCLASS", "$STOP:UDW", "c-1:w=can", "c-1:wts=can", "c-1:ws=1", "c-1:s=", "c0:w=be", "c0:wts=be", "c0:ws=1", "c0:s=", "c1:w=condensed", "c1:wts=condensed", "c1:ws=1", "c1:s=", "bg:-1:0:w=can__w=be", "bg:-1:0:w=can__ws=1", "bg:-1:0:ws=1__w=be", "bg:-1:0:ws=1__ws=1", "bg:0:1:w=be__ws=1", "bg:0:1:ws=1__ws=1"), features.get(7));
- assertArrayMatch(Arrays.asList("4G=^con", "3G=con", "4G=cond", "2G=on", "3G=ond", "4G=onde", "1G=n", "2G=nd", "3G=nde", "4G=nden", "1G=d", "2G=de", "3G=den", "4G=dens", "1G=e", "2G=en", "3G=ens", "4G=ense", "1G=n", "2G=ns", "3G=nse", "4G=nsed", "1G=s", "2G=se", "3G=sed", "4G=sed$", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "$STOP:UDW", "c-1:w=be", "c-1:wts=be", "c-1:ws=1", "c-1:s=", "c0:w=condensed", "c0:wts=condensed", "c0:ws=1", "c0:s=", "c1:w=with", "c1:wts=with", "c1:ws=1", "c1:s=", "bg:-1:0:w=be__ws=1", "bg:-1:0:ws=1__ws=1", "bg:0:1:ws=1__ws=1"), features.get(8));
- assertArrayMatch(Arrays.asList("4G=^wit", "3G=wit", "4G=with", "2G=it", "3G=ith", "4G=ith$", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "ngram-=CM", "$STOP:CLOSEDCLASS", "$STOP:UDW", "c-1:w=condensed", "c-1:wts=condensed", "c-1:ws=1", "c-1:s=", "c0:w=with", "c0:wts=with", "c0:ws=1", "c0:s=", "c1:w=benzaldehydes", "c1:wts=benzaldehyde", "c1:ws=1", "c1:s=s", "c1:ct=CMS", "bg:-1:0:ws=1__ws=1", "bg:0:1:ws=1__ws=1", "bg:0:1:ws=1__ct=CMS"), features.get(9));
- assertArrayMatch(Arrays.asList("4G=^ben", "3G=ben", "4G=benz", "2G=en", "3G=enz", "4G=enza", "1G=n", "2G=nz", "3G=nza", "4G=nzal", "1G=z", "2G=za", "3G=zal", "4G=zald", "1G=a", "2G=al", "3G=ald", "4G=alde", "1G=l", "2G=ld", "3G=lde", "4G=ldeh", "1G=d", "2G=de", "3G=deh", "4G=dehy", "1G=e", "2G=eh", "3G=ehy", "4G=ehyd", "1G=h", "2G=hy", "3G=hyd", "4G=hyde", "1G=y", "2G=yd", "3G=yde", "4G=ydes", "1G=d", "2G=de", "3G=des", "4G=des$", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "ngram+=CMS", "c-1:w=with", "c-1:wts=with", "c-1:ws=1", "c-1:s=", "c0:w=benzaldehydes", "c0:wts=benzaldehyde", "c0:ws=1", "c0:s=s", "c0:ct=CMS", "c1:w=.", "c1:wts=.", "c1:s=", "bg:-1:0:ws=1__ws=1", "bg:-1:0:ws=1__ct=CMS", "bg:0:1:ws=1__w=.", "bg:0:1:ct=CMS__w=."), features.get(10));
- assertArrayMatch(Arrays.asList("c-1:w=benzaldehydes", "c-1:wts=benzaldehyde", "c-1:ws=1", "c-1:s=s", "c-1:ct=CMS", "c0:w=.", "c0:wts=.", "c0:s=", "bg:-1:0:ws=1__w=.", "bg:-1:0:ct=CMS__w=."), features.get(11));
- */
-
- assertArrayMatch(Arrays.asList("4G=^We$","$STOP:NCNW","c0:w=We","c0:wts=We","c0:ws=42","c0:s=","c1:w=have","c1:wts=have","c1:ws=1","c1:s=","bg:0:1:w=We__ws=1","bg:0:1:ws=42__ws=1"), features.get(0).toList());
- assertArrayMatch(Arrays.asList("4G=^hav","3G=hav","4G=have","2G=av","3G=ave","4G=ave$","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","$STOP:CLOSEDCLASS","$STOP:NCW","$STOP:UDW","c-1:w=We","c-1:wts=We","c-1:ws=42","c-1:s=","c0:w=have","c0:wts=have","c0:ws=1","c0:s=","c1:w=also","c1:wts=also","c1:ws=1","c1:s=","bg:-1:0:w=We__ws=1","bg:-1:0:ws=42__ws=1","bg:0:1:ws=1__ws=1"), features.get(1).toList());
- assertArrayMatch(Arrays.asList("4G=^als","3G=als","4G=also","2G=ls","3G=lso","4G=lso$","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","ngram-=GP","$STOP:NCW","$STOP:UDW","c-1:w=have","c-1:wts=have","c-1:ws=1","c-1:s=","c0:w=also","c0:wts=also","c0:ws=1","c0:s=","c1:w=described","c1:wts=described","c1:ws=1","c1:s=","bg:-1:0:ws=1__ws=1","bg:0:1:ws=1__ws=1"), features.get(2).toList());
- assertArrayMatch(Arrays.asList("4G=^des","3G=des","4G=desc","2G=es","3G=esc","4G=escr","1G=s","2G=sc","3G=scr","4G=scri","1G=c","2G=cr","3G=cri","4G=crib","1G=r","2G=ri","3G=rib","4G=ribe","1G=i","2G=ib","3G=ibe","4G=ibed","1G=b","2G=be","3G=bed","4G=bed$","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","$STOP:NCW","$STOP:UDW","c-1:w=also","c-1:wts=also","c-1:ws=1","c-1:s=","c0:w=described","c0:wts=described","c0:ws=1","c0:s=","c1:w=that","c1:wts=that","c1:ws=1","c1:s=","bg:-1:0:ws=1__ws=1","bg:0:1:ws=1__ws=1"), features.get(3).toList());
- assertArrayMatch(Arrays.asList("4G=^tha","3G=tha","4G=that","2G=ha","3G=hat","4G=hat$","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","$STOP:CLOSEDCLASS","$STOP:NCW","$STOP:UDW","c-1:w=described","c-1:wts=described","c-1:ws=1","c-1:s=","c0:w=that","c0:wts=that","c0:ws=1","c0:s=","c1:w=benzoxasilepines","c1:wts=benzoxasilepine","c1:ws=1","c1:s=s","c1:ct=CMS","bg:-1:0:ws=1__ws=1","bg:0:1:ws=1__ws=1","bg:0:1:ws=1__ct=CMS"), features.get(4).toList());
- assertArrayMatch(Arrays.asList("4G=^ben","3G=ben","4G=benz","2G=en","3G=enz","4G=enzo","1G=n","2G=nz","3G=nzo","4G=nzox","1G=z","2G=zo","3G=zox","4G=zoxa","1G=o","2G=ox","3G=oxa","4G=oxas","1G=x","2G=xa","3G=xas","4G=xasi","1G=a","2G=as","3G=asi","4G=asil","1G=s","2G=si","3G=sil","4G=sile","1G=i","2G=il","3G=ile","4G=ilep","1G=l","2G=le","3G=lep","4G=lepi","1G=e","2G=ep","3G=epi","4G=epin","1G=p","2G=pi","3G=pin","4G=pine","1G=i","2G=in","3G=ine","4G=ines","1G=n","2G=ne","3G=nes","4G=nes$","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","c-1:w=that","c-1:wts=that","c-1:ws=1","c-1:s=","c0:w=benzoxasilepines","c0:wts=benzoxasilepine","c0:ws=1","c0:s=s","c0:ct=CMS","c1:w=can","c1:wts=can","c1:ws=1","c1:s=","bg:-1:0:ws=1__ws=1","bg:-1:0:ws=1__ct=CMS","bg:0:1:ws=1__w=can","bg:0:1:ws=1__ws=1","bg:0:1:ct=CMS__w=can","bg:0:1:ct=CMS__ws=1"), features.get(5).toList());
- assertArrayMatch(Arrays.asList("4G=^can","3G=can","4G=can$","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","$STOP:CLOSEDCLASS","$STOP:NCW","$STOP:UDW","c-1:w=benzoxasilepines","c-1:wts=benzoxasilepine","c-1:ws=1","c-1:s=s","c-1:ct=CMS","c0:w=can","c0:wts=can","c0:ws=1","c0:s=","c1:w=be","c1:wts=be","c1:ws=1","c1:s=","bg:-1:0:ws=1__w=can","bg:-1:0:ws=1__ws=1","bg:-1:0:ct=CMS__w=can","bg:-1:0:ct=CMS__ws=1","bg:0:1:w=can__w=be","bg:0:1:w=can__ws=1","bg:0:1:ws=1__w=be","bg:0:1:ws=1__ws=1"), features.get(6).toList());
- assertArrayMatch(Arrays.asList("4G=^be$","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","$STOP:CLOSEDCLASS","$STOP:NCW","$STOP:UDW","c-1:w=can","c-1:wts=can","c-1:ws=1","c-1:s=","c0:w=be","c0:wts=be","c0:ws=1","c0:s=","c1:w=condensed","c1:wts=condensed","c1:ws=1","c1:s=","bg:-1:0:w=can__w=be","bg:-1:0:w=can__ws=1","bg:-1:0:ws=1__w=be","bg:-1:0:ws=1__ws=1","bg:0:1:w=be__ws=1","bg:0:1:ws=1__ws=1"), features.get(7).toList());
- assertArrayMatch(Arrays.asList("4G=^con","3G=con","4G=cond","2G=on","3G=ond","4G=onde","1G=n","2G=nd","3G=nde","4G=nden","1G=d","2G=de","3G=den","4G=dens","1G=e","2G=en","3G=ens","4G=ense","1G=n","2G=ns","3G=nse","4G=nsed","1G=s","2G=se","3G=sed","4G=sed$","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","$STOP:UDW","c-1:w=be","c-1:wts=be","c-1:ws=1","c-1:s=","c0:w=condensed","c0:wts=condensed","c0:ws=1","c0:s=","c1:w=with","c1:wts=with","c1:ws=1","c1:s=","bg:-1:0:w=be__ws=1","bg:-1:0:ws=1__ws=1","bg:0:1:ws=1__ws=1"), features.get(8).toList());
- assertArrayMatch(Arrays.asList("4G=^wit","3G=wit","4G=with","2G=it","3G=ith","4G=ith$","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","ngram-=CM","$STOP:CLOSEDCLASS","$STOP:NCW","$STOP:UDW","c-1:w=condensed","c-1:wts=condensed","c-1:ws=1","c-1:s=","c0:w=with","c0:wts=with","c0:ws=1","c0:s=","c1:w=benzaldehydes","c1:wts=benzaldehyde","c1:ws=1","c1:s=s","c1:ct=CMS","bg:-1:0:ws=1__ws=1","bg:0:1:ws=1__ws=1","bg:0:1:ws=1__ct=CMS"), features.get(9).toList());
- assertArrayMatch(Arrays.asList("4G=^ben","3G=ben","4G=benz","2G=en","3G=enz","4G=enza","1G=n","2G=nz","3G=nza","4G=nzal","1G=z","2G=za","3G=zal","4G=zald","1G=a","2G=al","3G=ald","4G=alde","1G=l","2G=ld","3G=lde","4G=ldeh","1G=d","2G=de","3G=deh","4G=dehy","1G=e","2G=eh","3G=ehy","4G=ehyd","1G=h","2G=hy","3G=hyd","4G=hyde","1G=y","2G=yd","3G=yde","4G=ydes","1G=d","2G=de","3G=des","4G=des$","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","ngram+=CMS","c-1:w=with","c-1:wts=with","c-1:ws=1","c-1:s=","c0:w=benzaldehydes","c0:wts=benzaldehyde","c0:ws=1","c0:s=s","c0:ct=CMS","c1:w=.","c1:wts=.","c1:s=","bg:-1:0:ws=1__ws=1","bg:-1:0:ws=1__ct=CMS","bg:0:1:ws=1__w=.","bg:0:1:ct=CMS__w=."), features.get(10).toList());
- assertArrayMatch(Arrays.asList("c-1:w=benzaldehydes","c-1:wts=benzaldehyde","c-1:ws=1","c-1:s=s","c-1:ct=CMS","c0:w=.","c0:wts=.","c0:s=","bg:-1:0:ws=1__w=.","bg:-1:0:ct=CMS__w=."), features.get(11).toList());
-
-
- }
-
- private void assertArrayMatch(List<String> expected, List<String> actual) {
- assertEquals(expected, actual);
-// assertEquals(expected.size(), actual.size());
-// for (String s : expected) {
-// assertTrue("Contains "+s, actual.remove(s));
-// }
- }
-
-}
|
