public virtual void Test()
{
CharArraySet cas = new CharArraySet(TEST_VERSION_CURRENT, 3, false);
cas.add("jjp");
cas.add("wlmwoknt");
cas.add("tcgyreo");
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.Add("mtqlpi", "");
builder.Add("mwoknt", "jjp");
builder.Add("tcgyreo", "zpfpajyws");
NormalizeCharMap map = builder.Build();
Analyzer a = Analyzer.NewAnonymous(createComponents: (fieldName, reader) =>
{
Tokenizer t = new MockTokenizer(new TestRandomChains.CheckThatYouDidntReadAnythingReaderWrapper(reader), MockTokenFilter.ENGLISH_STOPSET, false, -65);
TokenFilter f = new CommonGramsFilter(TEST_VERSION_CURRENT, t, cas);
return(new TokenStreamComponents(t, f));
}, initReader: (fieldName, reader) =>
{
reader = new MockCharFilter(reader, 0);
reader = new MappingCharFilter(map, reader);
return(reader);
});
CheckAnalysisConsistency(Random, a, false, "wmgddzunizdomqyj");
}
public virtual void TestChangedOffsets()
{
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.Add("a", "一二");
builder.Add("b", "二三");
NormalizeCharMap norm = builder.Build();
Analyzer analyzer = new AnalyzerAnonymousInnerClassHelper(this, norm);
AssertAnalyzesTo(analyzer, "ab", new string[] { "一二", "二二", "二三" }, new int[] { 0, 0, 1 }, new int[] { 1, 1, 2 });
// note: offsets are strange since this is how the charfilter maps them...
// before bigramming, the 4 tokens look like:
// { 0, 0, 1, 1 },
// { 0, 1, 1, 2 }
}
public virtual void Test()
{
CharArraySet cas = new CharArraySet(TEST_VERSION_CURRENT, 3, false);
cas.add("jjp");
cas.add("wlmwoknt");
cas.add("tcgyreo");
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.Add("mtqlpi", "");
builder.Add("mwoknt", "jjp");
builder.Add("tcgyreo", "zpfpajyws");
NormalizeCharMap map = builder.Build();
Analyzer a = new AnalyzerAnonymousInnerClassHelper(this, cas, map);
CheckAnalysisConsistency(Random(), a, false, "wmgddzunizdomqyj");
}
public virtual void TestChangedOffsets()
{
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.Add("a", "一二");
builder.Add("b", "二三");
NormalizeCharMap norm = builder.Build();
Analyzer analyzer = Analyzer.NewAnonymous(createComponents: (fieldName, reader) =>
{
Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
return(new TokenStreamComponents(tokenizer, new CJKBigramFilter(tokenizer)));
}, initReader: (fieldName, reader) => new MappingCharFilter(norm, reader));
AssertAnalyzesTo(analyzer, "ab", new string[] { "一二", "二二", "二三" }, new int[] { 0, 0, 1 }, new int[] { 1, 1, 2 });
// note: offsets are strange since this is how the charfilter maps them...
// before bigramming, the 4 tokens look like:
// { 0, 0, 1, 1 },
// { 0, 1, 1, 2 }
}
public virtual void TestNormalizeWinDelimToLinuxDelim()
{
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.Add("\\", "/");
NormalizeCharMap normMap = builder.Build();
string path = "c:\\a\\b\\c";
Reader cs = new MappingCharFilter(normMap, new StringReader(path));
PathHierarchyTokenizer t = new PathHierarchyTokenizer(cs);
AssertTokenStreamContents(t, new string[] { "c:", "c:/a", "c:/a/b", "c:/a/b/c" }, new int[] { 0, 0, 0, 0 }, new int[] { 2, 4, 6, 8 }, new int[] { 1, 0, 0, 0 }, path.Length);
}
public virtual void TestInvalidOffsets()
{
CharArraySet dict = makeDictionary("fall");
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.Add("ü", "ue");
NormalizeCharMap normMap = builder.Build();
Analyzer analyzer = new AnalyzerAnonymousInnerClassHelper(this, dict, normMap);
AssertAnalyzesTo(analyzer, "banküberfall", new string[] { "bankueberfall", "fall" }, new int[] { 0, 0 }, new int[] { 12, 12 });
}
protected override TextReader InitReader(string fieldName, TextReader reader)
{
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
// different apostrophes
builder.Add("\u2019", "'");
builder.Add("\u2018", "'");
builder.Add("\u02BC", "'");
builder.Add("`", "'");
builder.Add("´", "'");
// ignored characters
builder.Add("\u0301", "");
builder.Add("\u00AD", "");
builder.Add("ґ", "г");
builder.Add("Ґ", "Г");
NormalizeCharMap normMap = builder.Build();
reader = new MappingCharFilter(normMap, reader);
return(reader);
}
public object Create(Random random)
{
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
// we can't add duplicate keys, or NormalizeCharMap gets angry
ISet <string> keys = new HashSet <string>();
int num = random.nextInt(5);
//System.out.println("NormalizeCharMap=");
for (int i = 0; i < num; i++)
{
string key = TestUtil.RandomSimpleString(random);
if (!keys.contains(key) && key.Length > 0)
{
string value = TestUtil.RandomSimpleString(random);
builder.Add(key, value);
keys.add(key);
//System.out.println("mapping: '" + key + "' => '" + value + "'");
}
}
return(builder.Build());
}
public virtual void TestOffsetCorrection()
{
const string INPUT = "Günther Günther is here";
// create MappingCharFilter
IList <string> mappingRules = new JCG.List <string>();
mappingRules.Add("\"ü\" => \"ü\"");
NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
builder.Add("ü", "ü");
NormalizeCharMap normMap = builder.Build();
CharFilter charStream = new MappingCharFilter(normMap, new StringReader(INPUT));
// create PatternTokenizer
TokenStream stream = new PatternTokenizer(charStream, new Regex("[,;/\\s]+", RegexOptions.Compiled), -1);
AssertTokenStreamContents(stream, new string[] { "Günther", "Günther", "is", "here" }, new int[] { 0, 13, 26, 29 }, new int[] { 12, 25, 28, 33 }, INPUT.Length);
charStream = new MappingCharFilter(normMap, new StringReader(INPUT));
stream = new PatternTokenizer(charStream, new Regex("Günther", RegexOptions.Compiled), 0);
AssertTokenStreamContents(stream, new string[] { "Günther", "Günther" }, new int[] { 0, 13 }, new int[] { 12, 25 }, INPUT.Length);
}
