带有排序规则的校对搜索排序

为了解决排序问题，我创建了自己的NorwegianCollat​​ionFactory。这不是完美的解决方案，因为我从旧版本的Hibernate Search（IndexableBinaryStringTools.class）复制了代码，但效果很好。 NorwegianCollat​​ionFactory类：

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.util.TokenFilterFactory;

import java.text.Collator;
import java.util.Locale;
import java.util.Map;

public final class NorwegianCollationFactory extends TokenFilterFactory {

  public NorwegianCollationFactory(Map<String, String> args) {
      super(args);
  }

  @Override
  public TokenStream create(TokenStream input) {
      Collator norwegianCollator = Collator.getInstance(new Locale("no", "NO"));
      return new CollationKeyFilter(input, norwegianCollator);
  }

}

Collat​​ionKeyFilter类：

import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

import java.io.IOException;
import java.text.Collator;
import java.util.Objects;

public final class CollationKeyFilter extends TokenFilter {

  // This code is copied from IndexableBinaryStringTools.class from the old version of hibernate search  4.3.0.Final
  private static final CollationKeyFilter.CodingCase[] CODING_CASES = {
          new CollationKeyFilter.CodingCase(7, 1),
          new CollationKeyFilter.CodingCase(14, 6, 2),
          new CollationKeyFilter.CodingCase(13, 5, 3),
          new CollationKeyFilter.CodingCase(12, 4, 4),
          new CollationKeyFilter.CodingCase(11, 3, 5),
          new CollationKeyFilter.CodingCase(10, 2, 6),
          new CollationKeyFilter.CodingCase(9, 1, 7),
          new CollationKeyFilter.CodingCase(8, 0)
  };

  private final Collator collator;
  private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);

  public CollationKeyFilter(TokenStream input, Collator collator) {
      super(input);
      this.collator = (Collator) collator.clone();
  }

  @Override
  public boolean incrementToken() throws IOException {
      if (input.incrementToken()) {
          byte[] collationKey = collator.getCollationKey(termAtt.toString()).toByteArray();
          int encodedLength = getBinaryStringEncodedLength(collationKey.length);
          termAtt.resizeBuffer(encodedLength);
          termAtt.setLength(encodedLength);
          encodeToBinaryString(collationKey, collationKey.length, termAtt.buffer());
          return true;
      } else {
          return false;
      }
  }

  // This code is copied from IndexableBinaryStringTools class from the old version of hibernate search  4.3.0.Final
  private void encodeToBinaryString(byte[] inputArray, int inputLength, char[] outputArray) {
      if (inputLength > 0) {
          int inputByteNum = 0;
          int caseNum = 0;
          int outputCharNum = 0;
          CollationKeyFilter.CodingCase codingCase;
          for (; inputByteNum + CODING_CASES[caseNum].numBytes <= inputLength; ++outputCharNum) {
              codingCase = CODING_CASES[caseNum];
              if (codingCase.numBytes == 2) {
                  outputArray[outputCharNum] = (char) (((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift)
                          + (((inputArray[inputByteNum + 1] & 0xFF) >>> codingCase.finalShift) & codingCase.finalMask) & (short) 0x7FFF);
              } else {
                  outputArray[outputCharNum] = (char) (((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift)
                          + ((inputArray[inputByteNum + 1] & 0xFF) << codingCase.middleShift)
                          + (((inputArray[inputByteNum + 2] & 0xFF) >>> codingCase.finalShift) & codingCase.finalMask) & (short) 0x7FFF);
              }
              inputByteNum += codingCase.advanceBytes;
              if (++caseNum == CODING_CASES.length) {
                  caseNum = 0;
              }
          }
          codingCase = CODING_CASES[caseNum];
          if (inputByteNum + 1 < inputLength) {
              outputArray[outputCharNum++] = (char) ((((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift)
                      + ((inputArray[inputByteNum + 1] & 0xFF) << codingCase.middleShift)) & (short) 0x7FFF);
              outputArray[outputCharNum] = (char) 1;
          } else if (inputByteNum < inputLength) {
              outputArray[outputCharNum++] = (char) (((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift) & (short) 0x7FFF);
              outputArray[outputCharNum] = caseNum == 0 ? (char) 1 : (char) 0;
          } else {
              outputArray[outputCharNum] = (char) 1;
          }
      }
  }

  // This code is copied from IndexableBinaryStringTools class from the old version of hibernate search 4.3.0.Final
  private int getBinaryStringEncodedLength(int inputLength) {
      return (int) ((8L * inputLength + 14L) / 15L) + 1;
  }

  // This code is copied from IndexableBinaryStringTools class from the old version of hibernate search 4.3.0.Final
  private static class CodingCase {
      int numBytes;
      int initialShift;
      int middleShift;
      int finalShift;
      int advanceBytes = 2;
      short middleMask;
      short finalMask;

      CodingCase(int initialShift, int middleShift, int finalShift) {
          this.numBytes = 3;
          this.initialShift = initialShift;
          this.middleShift = middleShift;
          this.finalShift = finalShift;
          this.finalMask = (short) ((short) 0xFF >>> finalShift);
          this.middleMask = (short) ((short) 0xFF << middleShift);
      }

      CodingCase(int initialShift, int finalShift) {
          this.numBytes = 2;
          this.initialShift = initialShift;
          this.finalShift = finalShift;
          this.finalMask = (short) ((short) 0xFF >>> finalShift);
          if (finalShift != 0) {
              advanceBytes = 1;
          }
      }
  }

  @Override
  public boolean equals(Object o) {
      if (this == o) {
          return true;
      }
      if (o == null || getClass() != o.getClass()) {
          return false;
      }
      if (!super.equals(o)) {
          return false;
      }
      CollationKeyFilter that = (CollationKeyFilter) o;
      return Objects.equals(collator, that.collator) &&
              Objects.equals(termAtt, that.termAtt);
  }

  @Override
  public int hashCode() {
      return Objects.hash(super.hashCode(), collator, termAtt);
  }

}

实体映射示例：

@Entity
@NormalizerDef(name = "textSortNormalizer",
      filters = {
              @TokenFilterDef(factory = LowerCaseFilterFactory.class),
              @TokenFilterDef(factory = PatternReplaceFilterFactory.class, params = {
                      @Parameter(name = "pattern", value = "('-&\\.,\\(\\))"),
                      @Parameter(name = "replacement", value = " "),
                      @Parameter(name = "replace", value = "all")
              }),
              @TokenFilterDef(factory = PatternReplaceFilterFactory.class, params = {
                      @Parameter(name = "pattern", value = "([^0-9\\p{L} ])"),
                      @Parameter(name = "replacement", value = ""),
                      @Parameter(name = "replace", value = "all")
              }),
              @TokenFilterDef(factory = NorwegianCollationFactory.class)
      }
)
public class Entity {

  @Field(name = "name_for_sort", normalizer = @Normalizer(definition = "textSortNormalizer"))
  @SortableField(forField = "name_for_sort")
  private String name;

}

回答来源：Stack Overflow