public virtual void TestStopwordsCasing()
{
#pragma warning disable 612, 618
FrenchAnalyzer a = new FrenchAnalyzer(LuceneVersion.LUCENE_31);
#pragma warning restore 612, 618
AssertAnalyzesTo(a, "Votre", new string[] { });
}
public virtual void TestAccentInsensitive()
{
Analyzer a = new FrenchAnalyzer(TEST_VERSION_CURRENT);
CheckOneTerm(a, "sécuritaires", "securitair");
CheckOneTerm(a, "securitaires", "securitair");
}
public virtual void TestReusableTokenStream()
{
FrenchAnalyzer fa = new FrenchAnalyzer(TEST_VERSION_CURRENT);
// stopwords
AssertAnalyzesTo(fa, "le la chien les aux chat du des à cheval", new string[] { "chien", "chat", "cheval" });
// some nouns and adjectives
AssertAnalyzesTo(fa, "lances chismes habitable chiste éléments captifs", new string[] { "lanc", "chism", "habitabl", "chist", "element", "captif" });
}
public virtual void TestExclusionTableViaCtor()
{
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("habitable");
FrenchAnalyzer fa = new FrenchAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
AssertAnalyzesTo(fa, "habitable chiste", new string[] { "habitable", "chist" });
fa = new FrenchAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
AssertAnalyzesTo(fa, "habitable chiste", new string[] { "habitable", "chist" });
}
public virtual void TestAnalyzer30()
{
FrenchAnalyzer fa = new FrenchAnalyzer(LuceneVersion.LUCENE_30);
AssertAnalyzesTo(fa, "", new string[] { });
AssertAnalyzesTo(fa, "chien chat cheval", new string[] { "chien", "chat", "cheval" });
AssertAnalyzesTo(fa, "chien CHAT CHEVAL", new string[] { "chien", "chat", "cheval" });
AssertAnalyzesTo(fa, " chien ,? + = - CHAT /: > CHEVAL", new string[] { "chien", "chat", "cheval" });
AssertAnalyzesTo(fa, "chien++", new string[] { "chien" });
AssertAnalyzesTo(fa, "mot \"entreguillemet\"", new string[] { "mot", "entreguillemet" });
// let's do some french specific tests now
/* 1. couldn't resist
I would expect this to stay one term as in French the minus
sign is often used for composing words */
AssertAnalyzesTo(fa, "Jean-François", new string[] { "jean", "françois" });
// 2. stopwords
AssertAnalyzesTo(fa, "le la chien les aux chat du des à cheval", new string[] { "chien", "chat", "cheval" });
// some nouns and adjectives
AssertAnalyzesTo(fa, "lances chismes habitable chiste éléments captifs", new string[] { "lanc", "chism", "habit", "chist", "élément", "captif" });
// some verbs
AssertAnalyzesTo(fa, "finissions souffrirent rugissante", new string[] { "fin", "souffr", "rug" });
// some everything else
// aujourd'hui stays one term which is OK
AssertAnalyzesTo(fa, "C3PO aujourd'hui oeuf ïâöûàä anticonstitutionnellement Java++ ", new string[] { "c3po", "aujourd'hui", "oeuf", "ïâöûàä", "anticonstitutionnel", "jav" });
// some more everything else
// here 1940-1945 stays as one term, 1940:1945 not ?
AssertAnalyzesTo(fa, "33Bis 1940-1945 1940:1945 (---i+++)*", new string[] { "33bis", "1940-1945", "1940", "1945", "i" });
}
public virtual void TestAnalyzer30()
{
FrenchAnalyzer fa = new FrenchAnalyzer(LuceneVersion.LUCENE_30);
AssertAnalyzesTo(fa, "", new string[] { });
AssertAnalyzesTo(fa, "chien chat cheval", new string[] { "chien", "chat", "cheval" });
AssertAnalyzesTo(fa, "chien CHAT CHEVAL", new string[] { "chien", "chat", "cheval" });
AssertAnalyzesTo(fa, " chien ,? + = - CHAT /: > CHEVAL", new string[] { "chien", "chat", "cheval" });
AssertAnalyzesTo(fa, "chien++", new string[] { "chien" });
AssertAnalyzesTo(fa, "mot \"entreguillemet\"", new string[] { "mot", "entreguillemet" });
// let's do some french specific tests now
/* 1. couldn't resist
* I would expect this to stay one term as in French the minus
* sign is often used for composing words */
AssertAnalyzesTo(fa, "Jean-François", new string[] { "jean", "françois" });
// 2. stopwords
AssertAnalyzesTo(fa, "le la chien les aux chat du des à cheval", new string[] { "chien", "chat", "cheval" });
// some nouns and adjectives
AssertAnalyzesTo(fa, "lances chismes habitable chiste éléments captifs", new string[] { "lanc", "chism", "habit", "chist", "élément", "captif" });
// some verbs
AssertAnalyzesTo(fa, "finissions souffrirent rugissante", new string[] { "fin", "souffr", "rug" });
// some everything else
// aujourd'hui stays one term which is OK
AssertAnalyzesTo(fa, "C3PO aujourd'hui oeuf ïâöûàä anticonstitutionnellement Java++ ", new string[] { "c3po", "aujourd'hui", "oeuf", "ïâöûàä", "anticonstitutionnel", "jav" });
// some more everything else
// here 1940-1945 stays as one term, 1940:1945 not ?
AssertAnalyzesTo(fa, "33Bis 1940-1945 1940:1945 (---i+++)*", new string[] { "33bis", "1940-1945", "1940", "1945", "i" });
}
public void TestExclusionTableReuse()
{
FrenchAnalyzer fa = new FrenchAnalyzer(Version.LUCENE_CURRENT);
AssertAnalyzesToReuse(fa, "habitable", new String[] { "habit" });
fa.SetStemExclusionTable(new String[] { "habitable" });
AssertAnalyzesToReuse(fa, "habitable", new String[] { "habitable" });
}
public void TestReusableTokenStream()
{
FrenchAnalyzer fa = new FrenchAnalyzer(Version.LUCENE_CURRENT);
// stopwords
AssertAnalyzesToReuse(
fa,
"le la chien les aux chat du des à cheval",
new String[] {"chien", "chat", "cheval"});
// some nouns and adjectives
AssertAnalyzesToReuse(
fa,
"lances chismes habitable chiste éléments captifs",
new String[]
{
"lanc",
"chism",
"habit",
"chist",
"élément",
"captif"
});
}
public virtual void TestBuggyStopwordsCasing()
{
FrenchAnalyzer a = new FrenchAnalyzer(LuceneVersion.LUCENE_30);
AssertAnalyzesTo(a, "Votre", new string[] { "votr" });
}
public virtual void TestElision()
{
FrenchAnalyzer fa = new FrenchAnalyzer(TEST_VERSION_CURRENT);
AssertAnalyzesTo(fa, "voir l'embrouille", new string[] { "voir", "embrouil" });
}
public virtual void TestAccentInsensitive()
{
Analyzer a = new FrenchAnalyzer(TEST_VERSION_CURRENT);
CheckOneTerm(a, "sécuritaires", "securitair");
CheckOneTerm(a, "securitaires", "securitair");
}
public virtual void TestStopwordsCasing()
{
#pragma warning disable 612, 618
FrenchAnalyzer a = new FrenchAnalyzer(LuceneVersion.LUCENE_31);
#pragma warning restore 612, 618
AssertAnalyzesTo(a, "Votre", new string[] { });
}
public virtual void TestBuggyStopwordsCasing()
{
FrenchAnalyzer a = new FrenchAnalyzer(LuceneVersion.LUCENE_30);
AssertAnalyzesTo(a, "Votre", new string[] { "votr" });
}
public virtual void TestElision()
{
FrenchAnalyzer fa = new FrenchAnalyzer(TEST_VERSION_CURRENT);
AssertAnalyzesTo(fa, "voir l'embrouille", new string[] { "voir", "embrouil" });
}
public virtual void TestExclusionTableViaCtor()
{
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("habitable");
FrenchAnalyzer fa = new FrenchAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
AssertAnalyzesTo(fa, "habitable chiste", new string[] { "habitable", "chist" });
fa = new FrenchAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
AssertAnalyzesTo(fa, "habitable chiste", new string[] { "habitable", "chist" });
}
public virtual void TestReusableTokenStream()
{
FrenchAnalyzer fa = new FrenchAnalyzer(TEST_VERSION_CURRENT);
// stopwords
AssertAnalyzesTo(fa, "le la chien les aux chat du des à cheval", new string[] { "chien", "chat", "cheval" });
// some nouns and adjectives
AssertAnalyzesTo(fa, "lances chismes habitable chiste éléments captifs", new string[] { "lanc", "chism", "habitabl", "chist", "element", "captif" });
}
