WordDelimiterGraphFilter can't correct offsets if a CharFilter had changed them

This commit is contained in:
Mike McCandless 2017-01-18 11:03:08 -05:00
parent 188a19e67e
commit 57626c9a99
1 changed files with 3 additions and 0 deletions

View File

@ -80,6 +80,7 @@ import org.apache.lucene.analysis.miscellaneous.LimitTokenPositionFilter;
import org.apache.lucene.analysis.miscellaneous.StemmerOverrideFilter.StemmerOverrideMap;
import org.apache.lucene.analysis.miscellaneous.StemmerOverrideFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter;
import org.apache.lucene.analysis.path.PathHierarchyTokenizer;
import org.apache.lucene.analysis.path.ReversePathHierarchyTokenizer;
import org.apache.lucene.analysis.payloads.IdentityEncoder;
@ -152,6 +153,8 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
ValidatingTokenFilter.class,
// TODO: needs to be a tokenizer, doesnt handle graph inputs properly (a shingle or similar following will then cause pain)
WordDelimiterFilter.class,
// Cannot correct offsets when a char filter had changed them:
WordDelimiterGraphFilter.class,
// clones of core's filters:
org.apache.lucene.analysis.core.StopFilter.class,
org.apache.lucene.analysis.core.LowerCaseFilter.class)) {