Revision: 8992
http://languagetool.svn.sourceforge.net/languagetool/?rev=8992&view=rev
Author: jaumeortola
Date: 2013-01-13 11:34:02 +0000 (Sun, 13 Jan 2013)
Log Message:
-----------
An asterisk (*) is added to the historical annotations of the disambiguator
when isWhitespaceBefore=false. The changes in the tests correspond to the first
word of the sentences, which usually have isWhitespaceBefore=false.
Modified Paths:
--------------
trunk/JLanguageTool/src/main/java/org/languagetool/AnalyzedTokenReadings.java
trunk/JLanguageTool/src/test/java/org/languagetool/AnalyzedTokenReadingsTest.java
trunk/JLanguageTool/src/test/java/org/languagetool/JLanguageToolTest.java
trunk/JLanguageTool/src/test/java/org/languagetool/rules/patterns/UnifierTest.java
trunk/JLanguageTool/src/test/java/org/languagetool/tagging/disambiguation/rules/fr/FrenchRuleDisambiguatorTest.java
Modified:
trunk/JLanguageTool/src/main/java/org/languagetool/AnalyzedTokenReadings.java
===================================================================
---
trunk/JLanguageTool/src/main/java/org/languagetool/AnalyzedTokenReadings.java
2013-01-13 11:10:52 UTC (rev 8991)
+++
trunk/JLanguageTool/src/main/java/org/languagetool/AnalyzedTokenReadings.java
2013-01-13 11:34:02 UTC (rev 8992)
@@ -352,6 +352,8 @@
sb.append("[");
for (final AnalyzedToken element : anTokReadings) {
sb.append(element);
+ if (!element.isWhitespaceBefore())
+ sb.append("*");
sb.append(",");
}
sb.delete(sb.length() - 1, sb.length());
Modified:
trunk/JLanguageTool/src/test/java/org/languagetool/AnalyzedTokenReadingsTest.java
===================================================================
---
trunk/JLanguageTool/src/test/java/org/languagetool/AnalyzedTokenReadingsTest.java
2013-01-13 11:10:52 UTC (rev 8991)
+++
trunk/JLanguageTool/src/test/java/org/languagetool/AnalyzedTokenReadingsTest.java
2013-01-13 11:34:02 UTC (rev 8992)
@@ -72,10 +72,10 @@
public void testToString() {
AnalyzedTokenReadings tokenReadings = new AnalyzedTokenReadings(new
AnalyzedToken("word", "POS", "lemma"));
- assertEquals(tokenReadings.toString(), "word[lemma/POS]");
+ assertEquals(tokenReadings.toString(), "word[lemma/POS*]");
AnalyzedToken aTok2 = new AnalyzedToken("word", "POS2", "lemma2");
tokenReadings.addReading(aTok2);
- assertEquals(tokenReadings.toString(), "word[lemma/POS,lemma2/POS2]");
+ assertEquals(tokenReadings.toString(), "word[lemma/POS*,lemma2/POS2*]");
}
public void testHasPosTag() {
Modified:
trunk/JLanguageTool/src/test/java/org/languagetool/JLanguageToolTest.java
===================================================================
--- trunk/JLanguageTool/src/test/java/org/languagetool/JLanguageToolTest.java
2013-01-13 11:10:52 UTC (rev 8991)
+++ trunk/JLanguageTool/src/test/java/org/languagetool/JLanguageToolTest.java
2013-01-13 11:34:02 UTC (rev 8992)
@@ -188,12 +188,12 @@
//and let's test other feats
AnalyzedSentence sent = tool.getAnalyzedSentence("Z powodu pogody dobre
buty są wskazane.");
assertEquals("Disambiguator log: "
- + "\n\nMULTIWORD_CHUNKER: Z[z/prep:gen.inst] ->
Z[z/prep:gen.inst,Z powodu/<PREP:GEN>]"
+ + "\n\nMULTIWORD_CHUNKER: Z[z/prep:gen.inst*] ->
Z[z/prep:gen.inst*,Z powodu/<PREP:GEN>*]"
+ "\n\nMULTIWORD_CHUNKER: powodu[powód/subst:sg:gen:m3] ->
powodu[powód/subst:sg:gen:m3,Z powodu/</PREP:GEN>]\n",
sent.getAnnotations());
sent = tool.getAnalyzedSentence("Nie mamy żadnej ryby.");
assertEquals("Disambiguator log: "
- + "\n\nNIE_ADAMP:
Nie[nie/qub,on/ppron3:pl:acc:f.m2.m3.n.p2.p3:ter:praep,on/ppron3:sg:acc:n:ter:praep]
-> Nie[nie/qub]"
+ + "\n\nNIE_ADAMP:
Nie[nie/qub*,on/ppron3:pl:acc:f.m2.m3.n.p2.p3:ter:praep*,on/ppron3:sg:acc:n:ter:praep*]
-> Nie[nie/qub*]"
+ "\n\nunify_adj_subst:
żadnej[żaden/adj:sg:dat:f:pos,żaden/adj:sg:gen:f:pos,żaden/adj:sg:loc:f:pos] ->
żadnej[żaden/adj:sg:gen:f:pos]" +
"\n\nunify_adj_subst:
ryby[ryba/subst:pl:acc:f,ryba/subst:pl:nom:f,ryba/subst:pl:voc:f,ryba/subst:sg:gen:f]
-> ryby[ryba/subst:sg:gen:f]\n",
sent.getAnnotations());
Modified:
trunk/JLanguageTool/src/test/java/org/languagetool/rules/patterns/UnifierTest.java
===================================================================
---
trunk/JLanguageTool/src/test/java/org/languagetool/rules/patterns/UnifierTest.java
2013-01-13 11:10:52 UTC (rev 8991)
+++
trunk/JLanguageTool/src/test/java/org/languagetool/rules/patterns/UnifierTest.java
2013-01-13 11:34:02 UTC (rev 8992)
@@ -199,7 +199,7 @@
satisfied &= uni.isSatisfied(sing2, equiv);
uni.startNextToken();
assertEquals(true, satisfied);
- assertEquals("[mały[mały/adj:sg:blahblah:m],
człowiek[człowiek/subst:sg:blahblah:m]]",
Arrays.toString(uni.getUnifiedTokens()));
+ assertEquals("[mały[mały/adj:sg:blahblah:m*],
człowiek[człowiek/subst:sg:blahblah:m*]]",
Arrays.toString(uni.getUnifiedTokens()));
uni.reset();
}
@@ -258,7 +258,7 @@
uni.isUnified(sing1a, equiv, false);
uni.isUnified(sing1b, equiv, true);
assertEquals(true, uni.isUnified(sing2, equiv, true));
- assertEquals("[osobiste[osobisty/adj:sg:nom.acc.voc:n:pos:aff],
godło[godło/subst:sg:nom.acc.voc:n]]", Arrays.toString(uni.getFinalUnified()));
+ assertEquals("[osobiste[osobisty/adj:sg:nom.acc.voc:n:pos:aff*],
godło[godło/subst:sg:nom.acc.voc:n*]]", Arrays.toString(uni.getFinalUnified()));
uni.reset();
//now test a case when the last reading doesn't match at all
@@ -272,7 +272,7 @@
uni.isUnified(sing1b, equiv, true);
uni.isUnified(sing2a, equiv, false);
assertEquals(true, uni.isUnified(sing2b, equiv, true));
- assertEquals("[osobiste[osobisty/adj:sg:nom.acc.voc:n:pos:aff],
godło[godło/subst:sg:nom.acc.voc:n]]", Arrays.toString(uni.getFinalUnified()));
+ assertEquals("[osobiste[osobisty/adj:sg:nom.acc.voc:n:pos:aff*],
godło[godło/subst:sg:nom.acc.voc:n*]]", Arrays.toString(uni.getFinalUnified()));
uni.reset();
}
Modified:
trunk/JLanguageTool/src/test/java/org/languagetool/tagging/disambiguation/rules/fr/FrenchRuleDisambiguatorTest.java
===================================================================
---
trunk/JLanguageTool/src/test/java/org/languagetool/tagging/disambiguation/rules/fr/FrenchRuleDisambiguatorTest.java
2013-01-13 11:10:52 UTC (rev 8991)
+++
trunk/JLanguageTool/src/test/java/org/languagetool/tagging/disambiguation/rules/fr/FrenchRuleDisambiguatorTest.java
2013-01-13 11:34:02 UTC (rev 8992)
@@ -89,8 +89,8 @@
public void testAnnotations() throws IOException {
AnalyzedSentence sent = lt.getAnalyzedSentence("Les avions");
assertEquals(sent.getAnnotations(), "Disambiguator log: \n\n" +
- "RP-D_N_AMBIG: Les[le/D e p,les/R pers obj 3 p] -> Les[le/D e
p]"+
- "\nRB-LE_LA_LES: Les[le/D e p] -> Les[le/D e p]" +
+ "RP-D_N_AMBIG: Les[le/D e p*,les/R pers obj 3 p*] -> Les[le/D e
p*]"+
+ "\nRB-LE_LA_LES: Les[le/D e p*] -> Les[le/D e p*]" +
"\n\nRP-D_N_AMBIG: avions[avoir/V avoir ind impa 1 p,avion/N m
p,avoir/SENT_END] -> avions[avion/N m p,avoir/SENT_END]\n");
}
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
Master Visual Studio, SharePoint, SQL, ASP.NET, C# 2012, HTML5, CSS,
MVC, Windows 8 Apps, JavaScript and much more. Keep your skills current
with LearnDevNow - 3,200 step-by-step video tutorials by Microsoft
MVPs and experts. ON SALE this month only -- learn more at:
http://p.sf.net/sfu/learnmore_123012
_______________________________________________
Languagetool-commits mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/languagetool-commits
