lucene | lucene实现web项目近实时搜索【solr和NRTManager、SearcherManager】

(*searchText* AND Privacy:false)

(*searchText* AND Privacy:false) OR (UserId:*searchText*)

(*searchText* AND Privacy:false)

(*searchText* AND Privacy:false) OR (UserId:*searchText*)

public interface PdfMapRepository extends JpaRepository<PdfMap, Integer> {

  @Query("select pm.pdfField from PdfMap pf where pf.id = :id")
  Optional<String> findPdfFieldByPdfMapId(Integer id); 

}

TypedQuery<String> query = em.createQuery("select pm.pdfField from PdfMap pf where pf.id = :id", String.class);
List<String> results = query.getResultList();

Session session = sessionFactory.openSession();

CriteriaQuery<Double> cr = cb.createQuery(String.class);
Root<PdfMap> root = cr.from(PdfMap.class);
cr.select(root.get("pdfField"));

Query<String> query = session.createQuery(cr);
List<String> formFields = query.getResultList();

public interface PdfMapRepository extends JpaRepository<PdfMap, Integer> {

  @Query("select pm.pdfField from PdfMap pf where pf.id = :id")
  Optional<String> findPdfFieldByPdfMapId(Integer id); 

}

TypedQuery<String> query = em.createQuery("select pm.pdfField from PdfMap pf where pf.id = :id", String.class);
List<String> results = query.getResultList();

Session session = sessionFactory.openSession();

CriteriaQuery<Double> cr = cb.createQuery(String.class);
Root<PdfMap> root = cr.from(PdfMap.class);
cr.select(root.get("pdfField"));

Query<String> query = session.createQuery(cr);
List<String> formFields = query.getResultList();

public interface PdfMapRepository extends JpaRepository<PdfMap, Integer> {

  @Query("select pm.pdfField from PdfMap pf where pf.id = :id")
  Optional<String> findPdfFieldByPdfMapId(Integer id); 

}

TypedQuery<String> query = em.createQuery("select pm.pdfField from PdfMap pf where pf.id = :id", String.class);
List<String> results = query.getResultList();

Session session = sessionFactory.openSession();

CriteriaQuery<Double> cr = cb.createQuery(String.class);
Root<PdfMap> root = cr.from(PdfMap.class);
cr.select(root.get("pdfField"));

Query<String> query = session.createQuery(cr);
List<String> formFields = query.getResultList();

@Test
public void testWriteAndQueryIndex() throws IOException {
    // Persist and read the data
    try (MMapDirectory dir = new MMapDirectory(indexPath)) {
        // Write index
        int indexedDoc = writeIndex(dir, vectors);
        // Read index
        readAndQuery(dir, vectors, indexedDoc);
    }
}

Test vectors:
0 => [0.13|0.37]
1 => [0.99|0.49]
2 => [0.98|0.57]
3 => [0.23|0.64]
4 => [0.72|0.92]
5 => [0.08|0.74]
6 => [0.50|0.27]
7 => [0.97|0.02]
8 => [0.90|0.21]
9 => [0.89|0.09]
10 => [0.11|0.95]

Doc Based Search:
Searching for NN of [0.98 | 0.01]
TotalHits: 11
7 => [0.97|0.02]
9 => [0.89|0.09]

@Test
public void testWriteAndQueryIndex() throws IOException {
    // Persist and read the data
    try (MMapDirectory dir = new MMapDirectory(indexPath)) {
        // Write index
        int indexedDoc = writeIndex(dir, vectors);
        // Read index
        readAndQuery(dir, vectors, indexedDoc);
    }
}

Test vectors:
0 => [0.13|0.37]
1 => [0.99|0.49]
2 => [0.98|0.57]
3 => [0.23|0.64]
4 => [0.72|0.92]
5 => [0.08|0.74]
6 => [0.50|0.27]
7 => [0.97|0.02]
8 => [0.90|0.21]
9 => [0.89|0.09]
10 => [0.11|0.95]

Doc Based Search:
Searching for NN of [0.98 | 0.01]
TotalHits: 11
7 => [0.97|0.02]
9 => [0.89|0.09]

try (IndexReader reader = DirectoryReader.open(dir)) {
    IndexSearcher searcher = new IndexSearcher(reader);
    System.out.println("Query: [" + String.format("%.2f", queryVector[0]) + ", " + String.format("%.2f", queryVector[1]) + "]");
    TopDocs results = searcher.search(new KnnVectorQuery("field", queryVector, 3), 10);
    System.out.println("Hits: " + results.totalHits);
    for (ScoreDoc sdoc : results.scoreDocs) {
        Document doc = reader.document(sdoc.doc);
        StoredField idField = (StoredField) doc.getField("id");
        System.out.println("Found: " + idField.numericValue() + " = " + String.format("%.1f", sdoc.score));
    }
}

POST _aliases
{
  "actions": [
    {
      "add": {
        "index": "myIndex",
        "alias": "myAlias",
        "filter": {
          "bool": {
            "must": [
              {
                "query_string": {
                  "query": "documentDate:[now-365d TO now]"
                }
              },
              {
                "bool": {
                  "should": [
                    {
                      "script": {
                        "script": {
                          "source": "doc['lastAnalysisDate'].value.toInstant().toEpochMilli() >= doc['documentDate'].value.minusYears(1).toInstant().toEpochMilli() && doc['lastAnalysisDate'].value.toInstant().toEpochMilli() <= doc['documentDate'].value.toInstant().toEpochMilli()"
                        }
                      }
                    }
                  ]
                }
              }
            ]
          }
        }
      }
    }
  ]
}

final Directory dir = new ByteBuffersDirectory();

Directory to = FSDirectory.open(Paths.get(OUT_DIR_PATH));

IOContext ctx = new IOContext();
for (String file : dir.listAll()) {
    System.out.println(file); // just for testing
    to.copyFrom(dir, file, file, ctx);
}

_0.cfe
_0.cfs
_0.si
segments_1

final Directory dir = new ByteBuffersDirectory();

Directory to = FSDirectory.open(Paths.get(OUT_DIR_PATH));

IOContext ctx = new IOContext();
for (String file : dir.listAll()) {
    System.out.println(file); // just for testing
    to.copyFrom(dir, file, file, ctx);
}

_0.cfe
_0.cfs
_0.si
segments_1

final Directory dir = new ByteBuffersDirectory();

Directory to = FSDirectory.open(Paths.get(OUT_DIR_PATH));

IOContext ctx = new IOContext();
for (String file : dir.listAll()) {
    System.out.println(file); // just for testing
    to.copyFrom(dir, file, file, ctx);
}

_0.cfe
_0.cfs
_0.si
segments_1

final Directory dir = new ByteBuffersDirectory();

Directory to = FSDirectory.open(Paths.get(OUT_DIR_PATH));

IOContext ctx = new IOContext();
for (String file : dir.listAll()) {
    System.out.println(file); // just for testing
    to.copyFrom(dir, file, file, ctx);
}

_0.cfe
_0.cfs
_0.si
segments_1

    @SneakyThrows
    public static void copyIndex(ByteBuffersDirectory ramDirectory, Path destination) {
        FSDirectory fsDirectory = FSDirectory.open(destination);
        Arrays.stream(ramDirectory.listAll())
                .forEach(fileName -> {
                    try {
                        // IOContext is null because in fact is not used (at least for the moment)
                        fsDirectory.copyFrom(ramDirectory, fileName, fileName, null);
                    } catch (IOException e) {
                        log.error(e.getMessage(), e);
                    }
                });
    }

...
{
  "name": "Summary",
  "type": "Edm.String",
  "retrievable": true,
  "searchable": true,
  "analyzer": "custom_analyzer_for_tokenizing_as_is"
},
...

{
    "name": "FieldName",
    "type": "Edm.String",
    "searchable": true,
    "filterable": true,
    "retrievable": true,
    "sortable": true,
    "facetable": true,
    "key": false,
    "indexAnalyzer": null,
    "searchAnalyzer": null,
    "analyzer": "specialcharanalyzer",
    "synonymMaps": []
},

"analyzers": [
    {
        "@odata.type": "#Microsoft.Azure.Search.CustomAnalyzer",
        "name": "specialcharanalyzer",
        "tokenizer": "whitespace",
        "tokenFilters": [
            "lowercase"
        ],
        "charFilters": []
    }
],

+ - & | ! ( ) { } [ ] ^ " ~ * ? : \ /

"search": "/.*SearchChar.*/",

"search": "/.*$.*/",

"search" : "/.*\\escapingcharacter.*/",

"search" : "/.*\\+.*/",

"search":"/\\**/",

{
    "name": "FieldName",
    "type": "Edm.String",
    "searchable": true,
    "filterable": true,
    "retrievable": true,
    "sortable": true,
    "facetable": true,
    "key": false,
    "indexAnalyzer": null,
    "searchAnalyzer": null,
    "analyzer": "specialcharanalyzer",
    "synonymMaps": []
},

"analyzers": [
    {
        "@odata.type": "#Microsoft.Azure.Search.CustomAnalyzer",
        "name": "specialcharanalyzer",
        "tokenizer": "whitespace",
        "tokenFilters": [
            "lowercase"
        ],
        "charFilters": []
    }
],

+ - & | ! ( ) { } [ ] ^ " ~ * ? : \ /

"search": "/.*SearchChar.*/",

"search": "/.*$.*/",

"search" : "/.*\\escapingcharacter.*/",

"search" : "/.*\\+.*/",

"search":"/\\**/",

{
    "name": "FieldName",
    "type": "Edm.String",
    "searchable": true,
    "filterable": true,
    "retrievable": true,
    "sortable": true,
    "facetable": true,
    "key": false,
    "indexAnalyzer": null,
    "searchAnalyzer": null,
    "analyzer": "specialcharanalyzer",
    "synonymMaps": []
},

"analyzers": [
    {
        "@odata.type": "#Microsoft.Azure.Search.CustomAnalyzer",
        "name": "specialcharanalyzer",
        "tokenizer": "whitespace",
        "tokenFilters": [
            "lowercase"
        ],
        "charFilters": []
    }
],

+ - & | ! ( ) { } [ ] ^ " ~ * ? : \ /

"search": "/.*SearchChar.*/",

"search": "/.*$.*/",

"search" : "/.*\\escapingcharacter.*/",

"search" : "/.*\\+.*/",

"search":"/\\**/",

{
    "name": "FieldName",
    "type": "Edm.String",
    "searchable": true,
    "filterable": true,
    "retrievable": true,
    "sortable": true,
    "facetable": true,
    "key": false,
    "indexAnalyzer": null,
    "searchAnalyzer": null,
    "analyzer": "specialcharanalyzer",
    "synonymMaps": []
},

"analyzers": [
    {
        "@odata.type": "#Microsoft.Azure.Search.CustomAnalyzer",
        "name": "specialcharanalyzer",
        "tokenizer": "whitespace",
        "tokenFilters": [
            "lowercase"
        ],
        "charFilters": []
    }
],

+ - & | ! ( ) { } [ ] ^ " ~ * ? : \ /

"search": "/.*SearchChar.*/",

"search": "/.*$.*/",

"search" : "/.*\\escapingcharacter.*/",

"search" : "/.*\\+.*/",

"search":"/\\**/",

{
    "name": "FieldName",
    "type": "Edm.String",
    "searchable": true,
    "filterable": true,
    "retrievable": true,
    "sortable": true,
    "facetable": true,
    "key": false,
    "indexAnalyzer": null,
    "searchAnalyzer": null,
    "analyzer": "specialcharanalyzer",
    "synonymMaps": []
},

"analyzers": [
    {
        "@odata.type": "#Microsoft.Azure.Search.CustomAnalyzer",
        "name": "specialcharanalyzer",
        "tokenizer": "whitespace",
        "tokenFilters": [
            "lowercase"
        ],
        "charFilters": []
    }
],

+ - & | ! ( ) { } [ ] ^ " ~ * ? : \ /

"search": "/.*SearchChar.*/",

"search": "/.*$.*/",

"search" : "/.*\\escapingcharacter.*/",

"search" : "/.*\\+.*/",

"search":"/\\**/",

{
    "name": "FieldName",
    "type": "Edm.String",
    "searchable": true,
    "filterable": true,
    "retrievable": true,
    "sortable": true,
    "facetable": true,
    "key": false,
    "indexAnalyzer": null,
    "searchAnalyzer": null,
    "analyzer": "specialcharanalyzer",
    "synonymMaps": []
},

"analyzers": [
    {
        "@odata.type": "#Microsoft.Azure.Search.CustomAnalyzer",
        "name": "specialcharanalyzer",
        "tokenizer": "whitespace",
        "tokenFilters": [
            "lowercase"
        ],
        "charFilters": []
    }
],

+ - & | ! ( ) { } [ ] ^ " ~ * ? : \ /

"search": "/.*SearchChar.*/",

"search": "/.*$.*/",

"search" : "/.*\\escapingcharacter.*/",

"search" : "/.*\\+.*/",

"search":"/\\**/",

{
    "name": "FieldName",
    "type": "Edm.String",
    "searchable": true,
    "filterable": true,
    "retrievable": true,
    "sortable": true,
    "facetable": true,
    "key": false,
    "indexAnalyzer": null,
    "searchAnalyzer": null,
    "analyzer": "specialcharanalyzer",
    "synonymMaps": []
},

"analyzers": [
    {
        "@odata.type": "#Microsoft.Azure.Search.CustomAnalyzer",
        "name": "specialcharanalyzer",
        "tokenizer": "whitespace",
        "tokenFilters": [
            "lowercase"
        ],
        "charFilters": []
    }
],

+ - & | ! ( ) { } [ ] ^ " ~ * ? : \ /

"search": "/.*SearchChar.*/",

"search": "/.*$.*/",

"search" : "/.*\\escapingcharacter.*/",

"search" : "/.*\\+.*/",

"search":"/\\**/",

{
    "name": "FieldName",
    "type": "Edm.String",
    "searchable": true,
    "filterable": true,
    "retrievable": true,
    "sortable": true,
    "facetable": true,
    "key": false,
    "indexAnalyzer": null,
    "searchAnalyzer": null,
    "analyzer": "specialcharanalyzer",
    "synonymMaps": []
},

"analyzers": [
    {
        "@odata.type": "#Microsoft.Azure.Search.CustomAnalyzer",
        "name": "specialcharanalyzer",
        "tokenizer": "whitespace",
        "tokenFilters": [
            "lowercase"
        ],
        "charFilters": []
    }
],

+ - & | ! ( ) { } [ ] ^ " ~ * ? : \ /

"search": "/.*SearchChar.*/",

"search": "/.*$.*/",

"search" : "/.*\\escapingcharacter.*/",

"search" : "/.*\\+.*/",

"search":"/\\**/",

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilterFactory;
import java.util.Map;
import java.util.HashMap;

public class IdentifierAnalyzer extends Analyzer {

    private WordDelimiterGraphFilterFactory getWordDelimiter() {
        Map<String, String> settings = new HashMap<>();
        settings.put("generateWordParts", "1");   // e.g. "PowerShot" => "Power" "Shot"
        settings.put("generateNumberParts", "1"); // e.g. "500-42" => "500" "42"
        settings.put("catenateAll", "1");         // e.g. "wi-fi" => "wifi" and "500-42" => "50042"
        settings.put("preserveOriginal", "1");    // e.g. "500-42" => "500" "42" "500-42"
        settings.put("splitOnCaseChange", "1");   // e.g. "fooBar" => "foo" "Bar"
        return new WordDelimiterGraphFilterFactory(settings);
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer tokenizer = new KeywordTokenizer();
        TokenStream tokenStream = new LowerCaseFilter(tokenizer);
        tokenStream = getWordDelimiter().create(tokenStream);
        return new TokenStreamComponents(tokenizer, tokenStream);
    }
    
    @Override
    protected TokenStream normalize(String fieldName, TokenStream in) {
        TokenStream tokenStream = new LowerCaseFilter(in);
        return tokenStream;
    }

}

978-3-86680-192-9
TS 123
123.abc

public static void buildIndex() throws IOException, FileNotFoundException, ParseException {
    final Directory dir = FSDirectory.open(Paths.get(INDEX_PATH));
    Analyzer analyzer = new IdentifierAnalyzer();
    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    Document doc;

    List<String> identifiers = Arrays.asList("978-3-86680-192-9", "TS 123", "123.abc");

    try (IndexWriter writer = new IndexWriter(dir, iwc)) {
        for (String identifier : identifiers) {
            doc = new Document();
            doc.add(new TextField("identifiers", identifier, Field.Store.YES));
            writer.addDocument(doc);
        }
    }
}

public static void doSearch() throws IOException, ParseException {
    Analyzer analyzer = new IdentifierAnalyzer();
    QueryParser parser = new QueryParser("identifiers", analyzer);

    List<String> searches = Arrays.asList("9783", "9783*", "978 3", "978-3", "TS1*", "TS 1*");

    for (String search : searches) {
        Query query = parser.parse(search);
        printHits(query, search);
    }
}

private static void printHits(Query query, String search) throws IOException {
    System.out.println("search term: " + search);
    System.out.println("parsed query: " + query.toString());
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(INDEX_PATH)));
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results = searcher.search(query, 100);
    ScoreDoc[] hits = results.scoreDocs;
    System.out.println("hits: " + hits.length);
    for (ScoreDoc hit : hits) {
        System.out.println("");
        System.out.println("  doc id: " + hit.doc + "; score: " + hit.score);
        Document doc = searcher.doc(hit.doc);
        System.out.println("  identifier: " + doc.get("identifiers"));
    }
    System.out.println("-----------------------------------------");
}

9783
9783*
978 3
978-3
TS1*
TS 1*

search term: 9783
parsed query: identifiers:9783
hits: 0

search term: TS 1*
parsed query: identifiers:ts identifiers:1*
hits: 3

  doc id: 1; score: 1.590861
  identifier: TS 123

  doc id: 0; score: 1.0
  identifier: 978-3-86680-192-9

  doc id: 2; score: 1.0
  identifier: 123.abc

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilterFactory;
import java.util.Map;
import java.util.HashMap;

public class IdentifierAnalyzer extends Analyzer {

    private WordDelimiterGraphFilterFactory getWordDelimiter() {
        Map<String, String> settings = new HashMap<>();
        settings.put("generateWordParts", "1");   // e.g. "PowerShot" => "Power" "Shot"
        settings.put("generateNumberParts", "1"); // e.g. "500-42" => "500" "42"
        settings.put("catenateAll", "1");         // e.g. "wi-fi" => "wifi" and "500-42" => "50042"
        settings.put("preserveOriginal", "1");    // e.g. "500-42" => "500" "42" "500-42"
        settings.put("splitOnCaseChange", "1");   // e.g. "fooBar" => "foo" "Bar"
        return new WordDelimiterGraphFilterFactory(settings);
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer tokenizer = new KeywordTokenizer();
        TokenStream tokenStream = new LowerCaseFilter(tokenizer);
        tokenStream = getWordDelimiter().create(tokenStream);
        return new TokenStreamComponents(tokenizer, tokenStream);
    }
    
    @Override
    protected TokenStream normalize(String fieldName, TokenStream in) {
        TokenStream tokenStream = new LowerCaseFilter(in);
        return tokenStream;
    }

}

978-3-86680-192-9
TS 123
123.abc

public static void buildIndex() throws IOException, FileNotFoundException, ParseException {
    final Directory dir = FSDirectory.open(Paths.get(INDEX_PATH));
    Analyzer analyzer = new IdentifierAnalyzer();
    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    Document doc;

    List<String> identifiers = Arrays.asList("978-3-86680-192-9", "TS 123", "123.abc");

    try (IndexWriter writer = new IndexWriter(dir, iwc)) {
        for (String identifier : identifiers) {
            doc = new Document();
            doc.add(new TextField("identifiers", identifier, Field.Store.YES));
            writer.addDocument(doc);
        }
    }
}

public static void doSearch() throws IOException, ParseException {
    Analyzer analyzer = new IdentifierAnalyzer();
    QueryParser parser = new QueryParser("identifiers", analyzer);

    List<String> searches = Arrays.asList("9783", "9783*", "978 3", "978-3", "TS1*", "TS 1*");

    for (String search : searches) {
        Query query = parser.parse(search);
        printHits(query, search);
    }
}

private static void printHits(Query query, String search) throws IOException {
    System.out.println("search term: " + search);
    System.out.println("parsed query: " + query.toString());
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(INDEX_PATH)));
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results = searcher.search(query, 100);
    ScoreDoc[] hits = results.scoreDocs;
    System.out.println("hits: " + hits.length);
    for (ScoreDoc hit : hits) {
        System.out.println("");
        System.out.println("  doc id: " + hit.doc + "; score: " + hit.score);
        Document doc = searcher.doc(hit.doc);
        System.out.println("  identifier: " + doc.get("identifiers"));
    }
    System.out.println("-----------------------------------------");
}

9783
9783*
978 3
978-3
TS1*
TS 1*

search term: 9783
parsed query: identifiers:9783
hits: 0

search term: TS 1*
parsed query: identifiers:ts identifiers:1*
hits: 3

  doc id: 1; score: 1.590861
  identifier: TS 123

  doc id: 0; score: 1.0
  identifier: 978-3-86680-192-9

  doc id: 2; score: 1.0
  identifier: 123.abc

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilterFactory;
import java.util.Map;
import java.util.HashMap;

public class IdentifierAnalyzer extends Analyzer {

    private WordDelimiterGraphFilterFactory getWordDelimiter() {
        Map<String, String> settings = new HashMap<>();
        settings.put("generateWordParts", "1");   // e.g. "PowerShot" => "Power" "Shot"
        settings.put("generateNumberParts", "1"); // e.g. "500-42" => "500" "42"
        settings.put("catenateAll", "1");         // e.g. "wi-fi" => "wifi" and "500-42" => "50042"
        settings.put("preserveOriginal", "1");    // e.g. "500-42" => "500" "42" "500-42"
        settings.put("splitOnCaseChange", "1");   // e.g. "fooBar" => "foo" "Bar"
        return new WordDelimiterGraphFilterFactory(settings);
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer tokenizer = new KeywordTokenizer();
        TokenStream tokenStream = new LowerCaseFilter(tokenizer);
        tokenStream = getWordDelimiter().create(tokenStream);
        return new TokenStreamComponents(tokenizer, tokenStream);
    }
    
    @Override
    protected TokenStream normalize(String fieldName, TokenStream in) {
        TokenStream tokenStream = new LowerCaseFilter(in);
        return tokenStream;
    }

}

978-3-86680-192-9
TS 123
123.abc

public static void buildIndex() throws IOException, FileNotFoundException, ParseException {
    final Directory dir = FSDirectory.open(Paths.get(INDEX_PATH));
    Analyzer analyzer = new IdentifierAnalyzer();
    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    Document doc;

    List<String> identifiers = Arrays.asList("978-3-86680-192-9", "TS 123", "123.abc");

    try (IndexWriter writer = new IndexWriter(dir, iwc)) {
        for (String identifier : identifiers) {
            doc = new Document();
            doc.add(new TextField("identifiers", identifier, Field.Store.YES));
            writer.addDocument(doc);
        }
    }
}

public static void doSearch() throws IOException, ParseException {
    Analyzer analyzer = new IdentifierAnalyzer();
    QueryParser parser = new QueryParser("identifiers", analyzer);

    List<String> searches = Arrays.asList("9783", "9783*", "978 3", "978-3", "TS1*", "TS 1*");

    for (String search : searches) {
        Query query = parser.parse(search);
        printHits(query, search);
    }
}

private static void printHits(Query query, String search) throws IOException {
    System.out.println("search term: " + search);
    System.out.println("parsed query: " + query.toString());
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(INDEX_PATH)));
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results = searcher.search(query, 100);
    ScoreDoc[] hits = results.scoreDocs;
    System.out.println("hits: " + hits.length);
    for (ScoreDoc hit : hits) {
        System.out.println("");
        System.out.println("  doc id: " + hit.doc + "; score: " + hit.score);
        Document doc = searcher.doc(hit.doc);
        System.out.println("  identifier: " + doc.get("identifiers"));
    }
    System.out.println("-----------------------------------------");
}

9783
9783*
978 3
978-3
TS1*
TS 1*

search term: 9783
parsed query: identifiers:9783
hits: 0

search term: TS 1*
parsed query: identifiers:ts identifiers:1*
hits: 3

  doc id: 1; score: 1.590861
  identifier: TS 123

  doc id: 0; score: 1.0
  identifier: 978-3-86680-192-9

  doc id: 2; score: 1.0
  identifier: 123.abc

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilterFactory;
import java.util.Map;
import java.util.HashMap;

public class IdentifierAnalyzer extends Analyzer {

    private WordDelimiterGraphFilterFactory getWordDelimiter() {
        Map<String, String> settings = new HashMap<>();
        settings.put("generateWordParts", "1");   // e.g. "PowerShot" => "Power" "Shot"
        settings.put("generateNumberParts", "1"); // e.g. "500-42" => "500" "42"
        settings.put("catenateAll", "1");         // e.g. "wi-fi" => "wifi" and "500-42" => "50042"
        settings.put("preserveOriginal", "1");    // e.g. "500-42" => "500" "42" "500-42"
        settings.put("splitOnCaseChange", "1");   // e.g. "fooBar" => "foo" "Bar"
        return new WordDelimiterGraphFilterFactory(settings);
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer tokenizer = new KeywordTokenizer();
        TokenStream tokenStream = new LowerCaseFilter(tokenizer);
        tokenStream = getWordDelimiter().create(tokenStream);
        return new TokenStreamComponents(tokenizer, tokenStream);
    }
    
    @Override
    protected TokenStream normalize(String fieldName, TokenStream in) {
        TokenStream tokenStream = new LowerCaseFilter(in);
        return tokenStream;
    }

}

978-3-86680-192-9
TS 123
123.abc

public static void buildIndex() throws IOException, FileNotFoundException, ParseException {
    final Directory dir = FSDirectory.open(Paths.get(INDEX_PATH));
    Analyzer analyzer = new IdentifierAnalyzer();
    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    Document doc;

    List<String> identifiers = Arrays.asList("978-3-86680-192-9", "TS 123", "123.abc");

    try (IndexWriter writer = new IndexWriter(dir, iwc)) {
        for (String identifier : identifiers) {
            doc = new Document();
            doc.add(new TextField("identifiers", identifier, Field.Store.YES));
            writer.addDocument(doc);
        }
    }
}

public static void doSearch() throws IOException, ParseException {
    Analyzer analyzer = new IdentifierAnalyzer();
    QueryParser parser = new QueryParser("identifiers", analyzer);

    List<String> searches = Arrays.asList("9783", "9783*", "978 3", "978-3", "TS1*", "TS 1*");

    for (String search : searches) {
        Query query = parser.parse(search);
        printHits(query, search);
    }
}

private static void printHits(Query query, String search) throws IOException {
    System.out.println("search term: " + search);
    System.out.println("parsed query: " + query.toString());
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(INDEX_PATH)));
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results = searcher.search(query, 100);
    ScoreDoc[] hits = results.scoreDocs;
    System.out.println("hits: " + hits.length);
    for (ScoreDoc hit : hits) {
        System.out.println("");
        System.out.println("  doc id: " + hit.doc + "; score: " + hit.score);
        Document doc = searcher.doc(hit.doc);
        System.out.println("  identifier: " + doc.get("identifiers"));
    }
    System.out.println("-----------------------------------------");
}

9783
9783*
978 3
978-3
TS1*
TS 1*

search term: 9783
parsed query: identifiers:9783
hits: 0

search term: TS 1*
parsed query: identifiers:ts identifiers:1*
hits: 3

  doc id: 1; score: 1.590861
  identifier: TS 123

  doc id: 0; score: 1.0
  identifier: 978-3-86680-192-9

  doc id: 2; score: 1.0
  identifier: 123.abc

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilterFactory;
import java.util.Map;
import java.util.HashMap;

public class IdentifierAnalyzer extends Analyzer {

    private WordDelimiterGraphFilterFactory getWordDelimiter() {
        Map<String, String> settings = new HashMap<>();
        settings.put("generateWordParts", "1");   // e.g. "PowerShot" => "Power" "Shot"
        settings.put("generateNumberParts", "1"); // e.g. "500-42" => "500" "42"
        settings.put("catenateAll", "1");         // e.g. "wi-fi" => "wifi" and "500-42" => "50042"
        settings.put("preserveOriginal", "1");    // e.g. "500-42" => "500" "42" "500-42"
        settings.put("splitOnCaseChange", "1");   // e.g. "fooBar" => "foo" "Bar"
        return new WordDelimiterGraphFilterFactory(settings);
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer tokenizer = new KeywordTokenizer();
        TokenStream tokenStream = new LowerCaseFilter(tokenizer);
        tokenStream = getWordDelimiter().create(tokenStream);
        return new TokenStreamComponents(tokenizer, tokenStream);
    }
    
    @Override
    protected TokenStream normalize(String fieldName, TokenStream in) {
        TokenStream tokenStream = new LowerCaseFilter(in);
        return tokenStream;
    }

}

978-3-86680-192-9
TS 123
123.abc

public static void buildIndex() throws IOException, FileNotFoundException, ParseException {
    final Directory dir = FSDirectory.open(Paths.get(INDEX_PATH));
    Analyzer analyzer = new IdentifierAnalyzer();
    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    Document doc;

    List<String> identifiers = Arrays.asList("978-3-86680-192-9", "TS 123", "123.abc");

    try (IndexWriter writer = new IndexWriter(dir, iwc)) {
        for (String identifier : identifiers) {
            doc = new Document();
            doc.add(new TextField("identifiers", identifier, Field.Store.YES));
            writer.addDocument(doc);
        }
    }
}

public static void doSearch() throws IOException, ParseException {
    Analyzer analyzer = new IdentifierAnalyzer();
    QueryParser parser = new QueryParser("identifiers", analyzer);

    List<String> searches = Arrays.asList("9783", "9783*", "978 3", "978-3", "TS1*", "TS 1*");

    for (String search : searches) {
        Query query = parser.parse(search);
        printHits(query, search);
    }
}

private static void printHits(Query query, String search) throws IOException {
    System.out.println("search term: " + search);
    System.out.println("parsed query: " + query.toString());
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(INDEX_PATH)));
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results = searcher.search(query, 100);
    ScoreDoc[] hits = results.scoreDocs;
    System.out.println("hits: " + hits.length);
    for (ScoreDoc hit : hits) {
        System.out.println("");
        System.out.println("  doc id: " + hit.doc + "; score: " + hit.score);
        Document doc = searcher.doc(hit.doc);
        System.out.println("  identifier: " + doc.get("identifiers"));
    }
    System.out.println("-----------------------------------------");
}

9783
9783*
978 3
978-3
TS1*
TS 1*

search term: 9783
parsed query: identifiers:9783
hits: 0

search term: TS 1*
parsed query: identifiers:ts identifiers:1*
hits: 3

  doc id: 1; score: 1.590861
  identifier: TS 123

  doc id: 0; score: 1.0
  identifier: 978-3-86680-192-9

  doc id: 2; score: 1.0
  identifier: 123.abc

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilterFactory;
import java.util.Map;
import java.util.HashMap;

public class IdentifierAnalyzer extends Analyzer {

    private WordDelimiterGraphFilterFactory getWordDelimiter() {
        Map<String, String> settings = new HashMap<>();
        settings.put("generateWordParts", "1");   // e.g. "PowerShot" => "Power" "Shot"
        settings.put("generateNumberParts", "1"); // e.g. "500-42" => "500" "42"
        settings.put("catenateAll", "1");         // e.g. "wi-fi" => "wifi" and "500-42" => "50042"
        settings.put("preserveOriginal", "1");    // e.g. "500-42" => "500" "42" "500-42"
        settings.put("splitOnCaseChange", "1");   // e.g. "fooBar" => "foo" "Bar"
        return new WordDelimiterGraphFilterFactory(settings);
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer tokenizer = new KeywordTokenizer();
        TokenStream tokenStream = new LowerCaseFilter(tokenizer);
        tokenStream = getWordDelimiter().create(tokenStream);
        return new TokenStreamComponents(tokenizer, tokenStream);
    }
    
    @Override
    protected TokenStream normalize(String fieldName, TokenStream in) {
        TokenStream tokenStream = new LowerCaseFilter(in);
        return tokenStream;
    }

}

978-3-86680-192-9
TS 123
123.abc

public static void buildIndex() throws IOException, FileNotFoundException, ParseException {
    final Directory dir = FSDirectory.open(Paths.get(INDEX_PATH));
    Analyzer analyzer = new IdentifierAnalyzer();
    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    Document doc;

    List<String> identifiers = Arrays.asList("978-3-86680-192-9", "TS 123", "123.abc");

    try (IndexWriter writer = new IndexWriter(dir, iwc)) {
        for (String identifier : identifiers) {
            doc = new Document();
            doc.add(new TextField("identifiers", identifier, Field.Store.YES));
            writer.addDocument(doc);
        }
    }
}

public static void doSearch() throws IOException, ParseException {
    Analyzer analyzer = new IdentifierAnalyzer();
    QueryParser parser = new QueryParser("identifiers", analyzer);

    List<String> searches = Arrays.asList("9783", "9783*", "978 3", "978-3", "TS1*", "TS 1*");

    for (String search : searches) {
        Query query = parser.parse(search);
        printHits(query, search);
    }
}

private static void printHits(Query query, String search) throws IOException {
    System.out.println("search term: " + search);
    System.out.println("parsed query: " + query.toString());
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(INDEX_PATH)));
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results = searcher.search(query, 100);
    ScoreDoc[] hits = results.scoreDocs;
    System.out.println("hits: " + hits.length);
    for (ScoreDoc hit : hits) {
        System.out.println("");
        System.out.println("  doc id: " + hit.doc + "; score: " + hit.score);
        Document doc = searcher.doc(hit.doc);
        System.out.println("  identifier: " + doc.get("identifiers"));
    }
    System.out.println("-----------------------------------------");
}

9783
9783*
978 3
978-3
TS1*
TS 1*

search term: 9783
parsed query: identifiers:9783
hits: 0

search term: TS 1*
parsed query: identifiers:ts identifiers:1*
hits: 3

  doc id: 1; score: 1.590861
  identifier: TS 123

  doc id: 0; score: 1.0
  identifier: 978-3-86680-192-9

  doc id: 2; score: 1.0
  identifier: 123.abc

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilterFactory;
import java.util.Map;
import java.util.HashMap;

public class IdentifierAnalyzer extends Analyzer {

    private WordDelimiterGraphFilterFactory getWordDelimiter() {
        Map<String, String> settings = new HashMap<>();
        settings.put("generateWordParts", "1");   // e.g. "PowerShot" => "Power" "Shot"
        settings.put("generateNumberParts", "1"); // e.g. "500-42" => "500" "42"
        settings.put("catenateAll", "1");         // e.g. "wi-fi" => "wifi" and "500-42" => "50042"
        settings.put("preserveOriginal", "1");    // e.g. "500-42" => "500" "42" "500-42"
        settings.put("splitOnCaseChange", "1");   // e.g. "fooBar" => "foo" "Bar"
        return new WordDelimiterGraphFilterFactory(settings);
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer tokenizer = new KeywordTokenizer();
        TokenStream tokenStream = new LowerCaseFilter(tokenizer);
        tokenStream = getWordDelimiter().create(tokenStream);
        return new TokenStreamComponents(tokenizer, tokenStream);
    }
    
    @Override
    protected TokenStream normalize(String fieldName, TokenStream in) {
        TokenStream tokenStream = new LowerCaseFilter(in);
        return tokenStream;
    }

}

978-3-86680-192-9
TS 123
123.abc

public static void buildIndex() throws IOException, FileNotFoundException, ParseException {
    final Directory dir = FSDirectory.open(Paths.get(INDEX_PATH));
    Analyzer analyzer = new IdentifierAnalyzer();
    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    Document doc;

    List<String> identifiers = Arrays.asList("978-3-86680-192-9", "TS 123", "123.abc");

    try (IndexWriter writer = new IndexWriter(dir, iwc)) {
        for (String identifier : identifiers) {
            doc = new Document();
            doc.add(new TextField("identifiers", identifier, Field.Store.YES));
            writer.addDocument(doc);
        }
    }
}

public static void doSearch() throws IOException, ParseException {
    Analyzer analyzer = new IdentifierAnalyzer();
    QueryParser parser = new QueryParser("identifiers", analyzer);

    List<String> searches = Arrays.asList("9783", "9783*", "978 3", "978-3", "TS1*", "TS 1*");

    for (String search : searches) {
        Query query = parser.parse(search);
        printHits(query, search);
    }
}

private static void printHits(Query query, String search) throws IOException {
    System.out.println("search term: " + search);
    System.out.println("parsed query: " + query.toString());
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(INDEX_PATH)));
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results = searcher.search(query, 100);
    ScoreDoc[] hits = results.scoreDocs;
    System.out.println("hits: " + hits.length);
    for (ScoreDoc hit : hits) {
        System.out.println("");
        System.out.println("  doc id: " + hit.doc + "; score: " + hit.score);
        Document doc = searcher.doc(hit.doc);
        System.out.println("  identifier: " + doc.get("identifiers"));
    }
    System.out.println("-----------------------------------------");
}

9783
9783*
978 3
978-3
TS1*
TS 1*

search term: 9783
parsed query: identifiers:9783
hits: 0

search term: TS 1*
parsed query: identifiers:ts identifiers:1*
hits: 3

  doc id: 1; score: 1.590861
  identifier: TS 123

  doc id: 0; score: 1.0
  identifier: 978-3-86680-192-9

  doc id: 2; score: 1.0
  identifier: 123.abc

open Lucene.Net.Util

let id = doc.GetField("id").GetInt32Value().Value
let bytes = BytesRef(NumericUtils.BUF_SIZE_INT32)
NumericUtils.Int32ToPrefixCodedBytes(id, 0, bytes)
let term = Term("id", bytes)

Sort sort = new Sort(new SortedNumericSortField("number", SortField.Type.LONG, true));
TopDocs docs = searcher.search(new MatchAllDocsQuery(), 100, sort);

  
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

 /** Tests sorting on type int */
  public void testInt() throws IOException {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);

    Document doc = new Document();
    doc.add(new NumericDocValuesField("value", 300000));
    doc.add(newStringField("value", "300000", Field.Store.YES));
    writer.addDocument(doc);
    
    doc = new Document();
    doc.add(new NumericDocValuesField("value", -1));
    doc.add(newStringField("value", "-1", Field.Store.YES));
    writer.addDocument(doc);

    doc = new Document();
    doc.add(new NumericDocValuesField("value", 4));
    doc.add(newStringField("value", "4", Field.Store.YES));
    writer.addDocument(doc);
    
    IndexReader ir = writer.getReader();
    writer.close();
    
    IndexSearcher searcher = newSearcher(ir);
    Sort sort = new Sort(new SortField("value", SortField.Type.INT));

    TopDocs td = searcher.search(new MatchAllDocsQuery(), 10, sort);
    assertEquals(3, td.totalHits.value);
    // numeric order
    assertEquals("-1", searcher.doc(td.scoreDocs[0].doc).get("value"));
    assertEquals("4", searcher.doc(td.scoreDocs[1].doc).get("value"));
    assertEquals("300000", searcher.doc(td.scoreDocs[2].doc).get("value"));

    ir.close();
    dir.close();
  }

public void NumericDocValueSort() {

            Analyzer standardAnalyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48);
            Directory indexDir = new RAMDirectory();
            IndexWriterConfig iwc = new IndexWriterConfig(LuceneVersion.LUCENE_48, standardAnalyzer);

            IndexWriter indexWriter = new IndexWriter(indexDir, iwc);

            Document doc = new Document();

            doc.Add(new TextField("name", "A1", Field.Store.YES));
            //doc.Add(new StoredField("number", 1000L));              //uncomment this line to optionally be able to retrieve it from the doc later, can be  done for every doc
            doc.Add(new NumericDocValuesField("number", 1000L));
            indexWriter.AddDocument(doc);

            doc.Fields.Clear();
            doc.Add(new TextField("name", "A2", Field.Store.YES));
            doc.Add(new NumericDocValuesField("number", 1001L));
            indexWriter.AddDocument(doc);

            doc.Fields.Clear();
            doc.Add(new TextField("name", "A3", Field.Store.YES));
            doc.Add(new NumericDocValuesField("number", 990L));
            indexWriter.AddDocument(doc);

            doc.Fields.Clear();
            doc.Add(new TextField("name", "A4", Field.Store.YES));
            doc.Add(new NumericDocValuesField("number", 300L));
            indexWriter.AddDocument(doc);

            indexWriter.Commit();

            IndexReader reader = indexWriter.GetReader(applyAllDeletes: true);
            IndexSearcher searcher = new IndexSearcher(reader);

            Sort sort;
            TopDocs docs;
            SortField sortField = new SortField("number", SortFieldType.INT64);
            sort = new Sort(sortField);

            docs = searcher.Search(new MatchAllDocsQuery(), 1000, sort);
            

            foreach (ScoreDoc scoreDoc in docs.ScoreDocs) {
                Document curDoc = searcher.Doc(scoreDoc.Doc);
                string name = curDoc.Get("name");
            }

            reader.Dispose();               //reader.close() in java
        }

  
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

 /** Tests sorting on type int */
  public void testInt() throws IOException {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);

    Document doc = new Document();
    doc.add(new NumericDocValuesField("value", 300000));
    doc.add(newStringField("value", "300000", Field.Store.YES));
    writer.addDocument(doc);
    
    doc = new Document();
    doc.add(new NumericDocValuesField("value", -1));
    doc.add(newStringField("value", "-1", Field.Store.YES));
    writer.addDocument(doc);

    doc = new Document();
    doc.add(new NumericDocValuesField("value", 4));
    doc.add(newStringField("value", "4", Field.Store.YES));
    writer.addDocument(doc);
    
    IndexReader ir = writer.getReader();
    writer.close();
    
    IndexSearcher searcher = newSearcher(ir);
    Sort sort = new Sort(new SortField("value", SortField.Type.INT));

    TopDocs td = searcher.search(new MatchAllDocsQuery(), 10, sort);
    assertEquals(3, td.totalHits.value);
    // numeric order
    assertEquals("-1", searcher.doc(td.scoreDocs[0].doc).get("value"));
    assertEquals("4", searcher.doc(td.scoreDocs[1].doc).get("value"));
    assertEquals("300000", searcher.doc(td.scoreDocs[2].doc).get("value"));

    ir.close();
    dir.close();
  }

public void NumericDocValueSort() {

            Analyzer standardAnalyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48);
            Directory indexDir = new RAMDirectory();
            IndexWriterConfig iwc = new IndexWriterConfig(LuceneVersion.LUCENE_48, standardAnalyzer);

            IndexWriter indexWriter = new IndexWriter(indexDir, iwc);

            Document doc = new Document();

            doc.Add(new TextField("name", "A1", Field.Store.YES));
            //doc.Add(new StoredField("number", 1000L));              //uncomment this line to optionally be able to retrieve it from the doc later, can be  done for every doc
            doc.Add(new NumericDocValuesField("number", 1000L));
            indexWriter.AddDocument(doc);

            doc.Fields.Clear();
            doc.Add(new TextField("name", "A2", Field.Store.YES));
            doc.Add(new NumericDocValuesField("number", 1001L));
            indexWriter.AddDocument(doc);

            doc.Fields.Clear();
            doc.Add(new TextField("name", "A3", Field.Store.YES));
            doc.Add(new NumericDocValuesField("number", 990L));
            indexWriter.AddDocument(doc);

            doc.Fields.Clear();
            doc.Add(new TextField("name", "A4", Field.Store.YES));
            doc.Add(new NumericDocValuesField("number", 300L));
            indexWriter.AddDocument(doc);

            indexWriter.Commit();

            IndexReader reader = indexWriter.GetReader(applyAllDeletes: true);
            IndexSearcher searcher = new IndexSearcher(reader);

            Sort sort;
            TopDocs docs;
            SortField sortField = new SortField("number", SortFieldType.INT64);
            sort = new Sort(sortField);

            docs = searcher.Search(new MatchAllDocsQuery(), 1000, sort);
            

            foreach (ScoreDoc scoreDoc in docs.ScoreDocs) {
                Document curDoc = searcher.Doc(scoreDoc.Doc);
                string name = curDoc.Get("name");
            }

            reader.Dispose();               //reader.close() in java
        }

/*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *     http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */

public sealed class Lucene41StoredFieldsHighCompressionFormat : CompressingStoredFieldsFormat {
        /// <summary>
        /// Sole constructor. </summary>
        public Lucene41StoredFieldsHighCompressionFormat()
            : base("Lucene41StoredFieldsHighCompression", CompressionMode.HIGH_COMPRESSION, 1 << 14) {
        }
    }

/*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *     http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */

    using Lucene40LiveDocsFormat = Lucene.Net.Codecs.Lucene40.Lucene40LiveDocsFormat;
    using Lucene41StoredFieldsFormat = Lucene.Net.Codecs.Lucene41.Lucene41StoredFieldsFormat;
    using Lucene42NormsFormat = Lucene.Net.Codecs.Lucene42.Lucene42NormsFormat;
    using Lucene42TermVectorsFormat = Lucene.Net.Codecs.Lucene42.Lucene42TermVectorsFormat;
    using PerFieldDocValuesFormat = Lucene.Net.Codecs.PerField.PerFieldDocValuesFormat;
    using PerFieldPostingsFormat = Lucene.Net.Codecs.PerField.PerFieldPostingsFormat;

    /// <summary>
    /// Implements the Lucene 4.6 index format, with configurable per-field postings
    /// and docvalues formats.
    /// <para/>
    /// If you want to reuse functionality of this codec in another codec, extend
    /// <see cref="FilterCodec"/>.
    /// <para/>
    /// See <see cref="Lucene.Net.Codecs.Lucene46"/> package documentation for file format details.
    /// <para/>
    /// @lucene.experimental 
    /// </summary>
    // NOTE: if we make largish changes in a minor release, easier to just make Lucene46Codec or whatever
    // if they are backwards compatible or smallish we can probably do the backwards in the postingsreader
    // (it writes a minor version, etc).
    [CodecName("Lucene46HighCompression")]
    public class Lucene46HighCompressionCodec : Codec {
        private readonly StoredFieldsFormat fieldsFormat = new Lucene41StoredFieldsHighCompressionFormat();    //<--This is the only line different then the stock Lucene46Codec
        private readonly TermVectorsFormat vectorsFormat = new Lucene42TermVectorsFormat();
        private readonly FieldInfosFormat fieldInfosFormat = new Lucene46FieldInfosFormat();
        private readonly SegmentInfoFormat segmentInfosFormat = new Lucene46SegmentInfoFormat();
        private readonly LiveDocsFormat liveDocsFormat = new Lucene40LiveDocsFormat();

        private readonly PostingsFormat postingsFormat;

        private class PerFieldPostingsFormatAnonymousInnerClassHelper : PerFieldPostingsFormat {
            private readonly Lucene46HighCompressionCodec outerInstance;

            public PerFieldPostingsFormatAnonymousInnerClassHelper(Lucene46HighCompressionCodec outerInstance) {
                this.outerInstance = outerInstance;
            }

            [MethodImpl(MethodImplOptions.AggressiveInlining)]
            public override PostingsFormat GetPostingsFormatForField(string field) {
                return outerInstance.GetPostingsFormatForField(field);
            }
        }

        private readonly DocValuesFormat docValuesFormat;

        private class PerFieldDocValuesFormatAnonymousInnerClassHelper : PerFieldDocValuesFormat {
            private readonly Lucene46HighCompressionCodec outerInstance;

            public PerFieldDocValuesFormatAnonymousInnerClassHelper(Lucene46HighCompressionCodec outerInstance) {
                this.outerInstance = outerInstance;
            }

            [MethodImpl(MethodImplOptions.AggressiveInlining)]
            public override DocValuesFormat GetDocValuesFormatForField(string field) {
                return outerInstance.GetDocValuesFormatForField(field);
            }
        }

        /// <summary>
        /// Sole constructor. </summary>
        public Lucene46HighCompressionCodec()
            : base() {
            postingsFormat = new PerFieldPostingsFormatAnonymousInnerClassHelper(this);
            docValuesFormat = new PerFieldDocValuesFormatAnonymousInnerClassHelper(this);
        }

        public override sealed StoredFieldsFormat StoredFieldsFormat => fieldsFormat;

        public override sealed TermVectorsFormat TermVectorsFormat => vectorsFormat;

        public override sealed PostingsFormat PostingsFormat => postingsFormat;

        public override sealed FieldInfosFormat FieldInfosFormat => fieldInfosFormat;

        public override sealed SegmentInfoFormat SegmentInfoFormat => segmentInfosFormat;

        public override sealed LiveDocsFormat LiveDocsFormat => liveDocsFormat;

        /// <summary>
        /// Returns the postings format that should be used for writing
        /// new segments of <paramref name="field"/>.
        /// <para/>
        /// The default implementation always returns "Lucene41"
        /// </summary>
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public virtual PostingsFormat GetPostingsFormatForField(string field) {
            // LUCENENET specific - lazy initialize the codec to ensure we get the correct type if overridden.
            if (defaultFormat == null) {
                defaultFormat = Lucene.Net.Codecs.PostingsFormat.ForName("Lucene41");
            }
            return defaultFormat;
        }

        /// <summary>
        /// Returns the docvalues format that should be used for writing
        /// new segments of <paramref name="field"/>.
        /// <para/>
        /// The default implementation always returns "Lucene45"
        /// </summary>
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public virtual DocValuesFormat GetDocValuesFormatForField(string field) {
            // LUCENENET specific - lazy initialize the codec to ensure we get the correct type if overridden.
            if (defaultDVFormat == null) {
                defaultDVFormat = Lucene.Net.Codecs.DocValuesFormat.ForName("Lucene45");
            }
            return defaultDVFormat;
        }

        public override sealed DocValuesFormat DocValuesFormat => docValuesFormat;

        // LUCENENET specific - lazy initialize the codecs to ensure we get the correct type if overridden.
        private PostingsFormat defaultFormat;
        private DocValuesFormat defaultDVFormat;

        private readonly NormsFormat normsFormat = new Lucene42NormsFormat();

        public override sealed NormsFormat NormsFormat => normsFormat;
    }

Codec.SetCodecFactory(new DefaultCodecFactory {
    CustomCodecTypes = new Type[] { typeof(Lucene46HighCompressionCodec) }
});

public class TestCompression {


        [Fact]
        public void HighCompression() {
            FxTest.Setup();

            Directory indexDir = new RAMDirectory();

            Analyzer standardAnalyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48);

            IndexWriterConfig indexConfig = new IndexWriterConfig(LuceneVersion.LUCENE_48, standardAnalyzer);
            indexConfig.Codec = new Lucene46HighCompressionCodec();     //<--------Install the High Compression codec.

            indexConfig.UseCompoundFile = true;

            IndexWriter writer = new IndexWriter(indexDir, indexConfig);

            //souce: https://github.com/apache/lucenenet/blob/Lucene.Net_4_8_0_beta00006/src/Lucene.Net/Search/SearcherFactory.cs
            SearcherManager searcherManager = new SearcherManager(writer, applyAllDeletes: true, new SearchWarmer());

            Document doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "001", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Unique gifts are great gifts.", Field.Store.YES));
            writer.AddDocument(doc);

            doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "002", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Everyone is gifted.", Field.Store.YES));
            writer.AddDocument(doc);

            doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "003", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Gifts are meant to be shared.", Field.Store.YES));
            writer.AddDocument(doc);

            writer.Commit();

            searcherManager.MaybeRefreshBlocking();
            IndexSearcher indexSearcher = searcherManager.Acquire();
            try {
                QueryParser parser = new QueryParser(LuceneVersion.LUCENE_48, "exampleField", standardAnalyzer);
                Query query = parser.Parse("everyone");

                TopDocs topDocs = indexSearcher.Search(query, int.MaxValue);

                int numMatchingDocs = topDocs.ScoreDocs.Length;
                Assert.Equal(1, numMatchingDocs);


                Document docRead = indexSearcher.Doc(topDocs.ScoreDocs[0].Doc);
                string primaryKey = docRead.Get("examplePrimaryKey");
                Assert.Equal("002", primaryKey);

            } finally {
                searcherManager.Release(indexSearcher);
            }

        }

    }

/*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *     http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */

public sealed class Lucene41StoredFieldsHighCompressionFormat : CompressingStoredFieldsFormat {
        /// <summary>
        /// Sole constructor. </summary>
        public Lucene41StoredFieldsHighCompressionFormat()
            : base("Lucene41StoredFieldsHighCompression", CompressionMode.HIGH_COMPRESSION, 1 << 14) {
        }
    }

/*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *     http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */

    using Lucene40LiveDocsFormat = Lucene.Net.Codecs.Lucene40.Lucene40LiveDocsFormat;
    using Lucene41StoredFieldsFormat = Lucene.Net.Codecs.Lucene41.Lucene41StoredFieldsFormat;
    using Lucene42NormsFormat = Lucene.Net.Codecs.Lucene42.Lucene42NormsFormat;
    using Lucene42TermVectorsFormat = Lucene.Net.Codecs.Lucene42.Lucene42TermVectorsFormat;
    using PerFieldDocValuesFormat = Lucene.Net.Codecs.PerField.PerFieldDocValuesFormat;
    using PerFieldPostingsFormat = Lucene.Net.Codecs.PerField.PerFieldPostingsFormat;

    /// <summary>
    /// Implements the Lucene 4.6 index format, with configurable per-field postings
    /// and docvalues formats.
    /// <para/>
    /// If you want to reuse functionality of this codec in another codec, extend
    /// <see cref="FilterCodec"/>.
    /// <para/>
    /// See <see cref="Lucene.Net.Codecs.Lucene46"/> package documentation for file format details.
    /// <para/>
    /// @lucene.experimental 
    /// </summary>
    // NOTE: if we make largish changes in a minor release, easier to just make Lucene46Codec or whatever
    // if they are backwards compatible or smallish we can probably do the backwards in the postingsreader
    // (it writes a minor version, etc).
    [CodecName("Lucene46HighCompression")]
    public class Lucene46HighCompressionCodec : Codec {
        private readonly StoredFieldsFormat fieldsFormat = new Lucene41StoredFieldsHighCompressionFormat();    //<--This is the only line different then the stock Lucene46Codec
        private readonly TermVectorsFormat vectorsFormat = new Lucene42TermVectorsFormat();
        private readonly FieldInfosFormat fieldInfosFormat = new Lucene46FieldInfosFormat();
        private readonly SegmentInfoFormat segmentInfosFormat = new Lucene46SegmentInfoFormat();
        private readonly LiveDocsFormat liveDocsFormat = new Lucene40LiveDocsFormat();

        private readonly PostingsFormat postingsFormat;

        private class PerFieldPostingsFormatAnonymousInnerClassHelper : PerFieldPostingsFormat {
            private readonly Lucene46HighCompressionCodec outerInstance;

            public PerFieldPostingsFormatAnonymousInnerClassHelper(Lucene46HighCompressionCodec outerInstance) {
                this.outerInstance = outerInstance;
            }

            [MethodImpl(MethodImplOptions.AggressiveInlining)]
            public override PostingsFormat GetPostingsFormatForField(string field) {
                return outerInstance.GetPostingsFormatForField(field);
            }
        }

        private readonly DocValuesFormat docValuesFormat;

        private class PerFieldDocValuesFormatAnonymousInnerClassHelper : PerFieldDocValuesFormat {
            private readonly Lucene46HighCompressionCodec outerInstance;

            public PerFieldDocValuesFormatAnonymousInnerClassHelper(Lucene46HighCompressionCodec outerInstance) {
                this.outerInstance = outerInstance;
            }

            [MethodImpl(MethodImplOptions.AggressiveInlining)]
            public override DocValuesFormat GetDocValuesFormatForField(string field) {
                return outerInstance.GetDocValuesFormatForField(field);
            }
        }

        /// <summary>
        /// Sole constructor. </summary>
        public Lucene46HighCompressionCodec()
            : base() {
            postingsFormat = new PerFieldPostingsFormatAnonymousInnerClassHelper(this);
            docValuesFormat = new PerFieldDocValuesFormatAnonymousInnerClassHelper(this);
        }

        public override sealed StoredFieldsFormat StoredFieldsFormat => fieldsFormat;

        public override sealed TermVectorsFormat TermVectorsFormat => vectorsFormat;

        public override sealed PostingsFormat PostingsFormat => postingsFormat;

        public override sealed FieldInfosFormat FieldInfosFormat => fieldInfosFormat;

        public override sealed SegmentInfoFormat SegmentInfoFormat => segmentInfosFormat;

        public override sealed LiveDocsFormat LiveDocsFormat => liveDocsFormat;

        /// <summary>
        /// Returns the postings format that should be used for writing
        /// new segments of <paramref name="field"/>.
        /// <para/>
        /// The default implementation always returns "Lucene41"
        /// </summary>
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public virtual PostingsFormat GetPostingsFormatForField(string field) {
            // LUCENENET specific - lazy initialize the codec to ensure we get the correct type if overridden.
            if (defaultFormat == null) {
                defaultFormat = Lucene.Net.Codecs.PostingsFormat.ForName("Lucene41");
            }
            return defaultFormat;
        }

        /// <summary>
        /// Returns the docvalues format that should be used for writing
        /// new segments of <paramref name="field"/>.
        /// <para/>
        /// The default implementation always returns "Lucene45"
        /// </summary>
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public virtual DocValuesFormat GetDocValuesFormatForField(string field) {
            // LUCENENET specific - lazy initialize the codec to ensure we get the correct type if overridden.
            if (defaultDVFormat == null) {
                defaultDVFormat = Lucene.Net.Codecs.DocValuesFormat.ForName("Lucene45");
            }
            return defaultDVFormat;
        }

        public override sealed DocValuesFormat DocValuesFormat => docValuesFormat;

        // LUCENENET specific - lazy initialize the codecs to ensure we get the correct type if overridden.
        private PostingsFormat defaultFormat;
        private DocValuesFormat defaultDVFormat;

        private readonly NormsFormat normsFormat = new Lucene42NormsFormat();

        public override sealed NormsFormat NormsFormat => normsFormat;
    }

Codec.SetCodecFactory(new DefaultCodecFactory {
    CustomCodecTypes = new Type[] { typeof(Lucene46HighCompressionCodec) }
});

public class TestCompression {


        [Fact]
        public void HighCompression() {
            FxTest.Setup();

            Directory indexDir = new RAMDirectory();

            Analyzer standardAnalyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48);

            IndexWriterConfig indexConfig = new IndexWriterConfig(LuceneVersion.LUCENE_48, standardAnalyzer);
            indexConfig.Codec = new Lucene46HighCompressionCodec();     //<--------Install the High Compression codec.

            indexConfig.UseCompoundFile = true;

            IndexWriter writer = new IndexWriter(indexDir, indexConfig);

            //souce: https://github.com/apache/lucenenet/blob/Lucene.Net_4_8_0_beta00006/src/Lucene.Net/Search/SearcherFactory.cs
            SearcherManager searcherManager = new SearcherManager(writer, applyAllDeletes: true, new SearchWarmer());

            Document doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "001", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Unique gifts are great gifts.", Field.Store.YES));
            writer.AddDocument(doc);

            doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "002", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Everyone is gifted.", Field.Store.YES));
            writer.AddDocument(doc);

            doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "003", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Gifts are meant to be shared.", Field.Store.YES));
            writer.AddDocument(doc);

            writer.Commit();

            searcherManager.MaybeRefreshBlocking();
            IndexSearcher indexSearcher = searcherManager.Acquire();
            try {
                QueryParser parser = new QueryParser(LuceneVersion.LUCENE_48, "exampleField", standardAnalyzer);
                Query query = parser.Parse("everyone");

                TopDocs topDocs = indexSearcher.Search(query, int.MaxValue);

                int numMatchingDocs = topDocs.ScoreDocs.Length;
                Assert.Equal(1, numMatchingDocs);


                Document docRead = indexSearcher.Doc(topDocs.ScoreDocs[0].Doc);
                string primaryKey = docRead.Get("examplePrimaryKey");
                Assert.Equal("002", primaryKey);

            } finally {
                searcherManager.Release(indexSearcher);
            }

        }

    }

/*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *     http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */

public sealed class Lucene41StoredFieldsHighCompressionFormat : CompressingStoredFieldsFormat {
        /// <summary>
        /// Sole constructor. </summary>
        public Lucene41StoredFieldsHighCompressionFormat()
            : base("Lucene41StoredFieldsHighCompression", CompressionMode.HIGH_COMPRESSION, 1 << 14) {
        }
    }

/*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *     http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */

    using Lucene40LiveDocsFormat = Lucene.Net.Codecs.Lucene40.Lucene40LiveDocsFormat;
    using Lucene41StoredFieldsFormat = Lucene.Net.Codecs.Lucene41.Lucene41StoredFieldsFormat;
    using Lucene42NormsFormat = Lucene.Net.Codecs.Lucene42.Lucene42NormsFormat;
    using Lucene42TermVectorsFormat = Lucene.Net.Codecs.Lucene42.Lucene42TermVectorsFormat;
    using PerFieldDocValuesFormat = Lucene.Net.Codecs.PerField.PerFieldDocValuesFormat;
    using PerFieldPostingsFormat = Lucene.Net.Codecs.PerField.PerFieldPostingsFormat;

    /// <summary>
    /// Implements the Lucene 4.6 index format, with configurable per-field postings
    /// and docvalues formats.
    /// <para/>
    /// If you want to reuse functionality of this codec in another codec, extend
    /// <see cref="FilterCodec"/>.
    /// <para/>
    /// See <see cref="Lucene.Net.Codecs.Lucene46"/> package documentation for file format details.
    /// <para/>
    /// @lucene.experimental 
    /// </summary>
    // NOTE: if we make largish changes in a minor release, easier to just make Lucene46Codec or whatever
    // if they are backwards compatible or smallish we can probably do the backwards in the postingsreader
    // (it writes a minor version, etc).
    [CodecName("Lucene46HighCompression")]
    public class Lucene46HighCompressionCodec : Codec {
        private readonly StoredFieldsFormat fieldsFormat = new Lucene41StoredFieldsHighCompressionFormat();    //<--This is the only line different then the stock Lucene46Codec
        private readonly TermVectorsFormat vectorsFormat = new Lucene42TermVectorsFormat();
        private readonly FieldInfosFormat fieldInfosFormat = new Lucene46FieldInfosFormat();
        private readonly SegmentInfoFormat segmentInfosFormat = new Lucene46SegmentInfoFormat();
        private readonly LiveDocsFormat liveDocsFormat = new Lucene40LiveDocsFormat();

        private readonly PostingsFormat postingsFormat;

        private class PerFieldPostingsFormatAnonymousInnerClassHelper : PerFieldPostingsFormat {
            private readonly Lucene46HighCompressionCodec outerInstance;

            public PerFieldPostingsFormatAnonymousInnerClassHelper(Lucene46HighCompressionCodec outerInstance) {
                this.outerInstance = outerInstance;
            }

            [MethodImpl(MethodImplOptions.AggressiveInlining)]
            public override PostingsFormat GetPostingsFormatForField(string field) {
                return outerInstance.GetPostingsFormatForField(field);
            }
        }

        private readonly DocValuesFormat docValuesFormat;

        private class PerFieldDocValuesFormatAnonymousInnerClassHelper : PerFieldDocValuesFormat {
            private readonly Lucene46HighCompressionCodec outerInstance;

            public PerFieldDocValuesFormatAnonymousInnerClassHelper(Lucene46HighCompressionCodec outerInstance) {
                this.outerInstance = outerInstance;
            }

            [MethodImpl(MethodImplOptions.AggressiveInlining)]
            public override DocValuesFormat GetDocValuesFormatForField(string field) {
                return outerInstance.GetDocValuesFormatForField(field);
            }
        }

        /// <summary>
        /// Sole constructor. </summary>
        public Lucene46HighCompressionCodec()
            : base() {
            postingsFormat = new PerFieldPostingsFormatAnonymousInnerClassHelper(this);
            docValuesFormat = new PerFieldDocValuesFormatAnonymousInnerClassHelper(this);
        }

        public override sealed StoredFieldsFormat StoredFieldsFormat => fieldsFormat;

        public override sealed TermVectorsFormat TermVectorsFormat => vectorsFormat;

        public override sealed PostingsFormat PostingsFormat => postingsFormat;

        public override sealed FieldInfosFormat FieldInfosFormat => fieldInfosFormat;

        public override sealed SegmentInfoFormat SegmentInfoFormat => segmentInfosFormat;

        public override sealed LiveDocsFormat LiveDocsFormat => liveDocsFormat;

        /// <summary>
        /// Returns the postings format that should be used for writing
        /// new segments of <paramref name="field"/>.
        /// <para/>
        /// The default implementation always returns "Lucene41"
        /// </summary>
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public virtual PostingsFormat GetPostingsFormatForField(string field) {
            // LUCENENET specific - lazy initialize the codec to ensure we get the correct type if overridden.
            if (defaultFormat == null) {
                defaultFormat = Lucene.Net.Codecs.PostingsFormat.ForName("Lucene41");
            }
            return defaultFormat;
        }

        /// <summary>
        /// Returns the docvalues format that should be used for writing
        /// new segments of <paramref name="field"/>.
        /// <para/>
        /// The default implementation always returns "Lucene45"
        /// </summary>
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public virtual DocValuesFormat GetDocValuesFormatForField(string field) {
            // LUCENENET specific - lazy initialize the codec to ensure we get the correct type if overridden.
            if (defaultDVFormat == null) {
                defaultDVFormat = Lucene.Net.Codecs.DocValuesFormat.ForName("Lucene45");
            }
            return defaultDVFormat;
        }

        public override sealed DocValuesFormat DocValuesFormat => docValuesFormat;

        // LUCENENET specific - lazy initialize the codecs to ensure we get the correct type if overridden.
        private PostingsFormat defaultFormat;
        private DocValuesFormat defaultDVFormat;

        private readonly NormsFormat normsFormat = new Lucene42NormsFormat();

        public override sealed NormsFormat NormsFormat => normsFormat;
    }

Codec.SetCodecFactory(new DefaultCodecFactory {
    CustomCodecTypes = new Type[] { typeof(Lucene46HighCompressionCodec) }
});

public class TestCompression {


        [Fact]
        public void HighCompression() {
            FxTest.Setup();

            Directory indexDir = new RAMDirectory();

            Analyzer standardAnalyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48);

            IndexWriterConfig indexConfig = new IndexWriterConfig(LuceneVersion.LUCENE_48, standardAnalyzer);
            indexConfig.Codec = new Lucene46HighCompressionCodec();     //<--------Install the High Compression codec.

            indexConfig.UseCompoundFile = true;

            IndexWriter writer = new IndexWriter(indexDir, indexConfig);

            //souce: https://github.com/apache/lucenenet/blob/Lucene.Net_4_8_0_beta00006/src/Lucene.Net/Search/SearcherFactory.cs
            SearcherManager searcherManager = new SearcherManager(writer, applyAllDeletes: true, new SearchWarmer());

            Document doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "001", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Unique gifts are great gifts.", Field.Store.YES));
            writer.AddDocument(doc);

            doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "002", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Everyone is gifted.", Field.Store.YES));
            writer.AddDocument(doc);

            doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "003", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Gifts are meant to be shared.", Field.Store.YES));
            writer.AddDocument(doc);

            writer.Commit();

            searcherManager.MaybeRefreshBlocking();
            IndexSearcher indexSearcher = searcherManager.Acquire();
            try {
                QueryParser parser = new QueryParser(LuceneVersion.LUCENE_48, "exampleField", standardAnalyzer);
                Query query = parser.Parse("everyone");

                TopDocs topDocs = indexSearcher.Search(query, int.MaxValue);

                int numMatchingDocs = topDocs.ScoreDocs.Length;
                Assert.Equal(1, numMatchingDocs);


                Document docRead = indexSearcher.Doc(topDocs.ScoreDocs[0].Doc);
                string primaryKey = docRead.Get("examplePrimaryKey");
                Assert.Equal("002", primaryKey);

            } finally {
                searcherManager.Release(indexSearcher);
            }

        }

    }

/*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *     http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */

public sealed class Lucene41StoredFieldsHighCompressionFormat : CompressingStoredFieldsFormat {
        /// <summary>
        /// Sole constructor. </summary>
        public Lucene41StoredFieldsHighCompressionFormat()
            : base("Lucene41StoredFieldsHighCompression", CompressionMode.HIGH_COMPRESSION, 1 << 14) {
        }
    }

/*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *     http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */

    using Lucene40LiveDocsFormat = Lucene.Net.Codecs.Lucene40.Lucene40LiveDocsFormat;
    using Lucene41StoredFieldsFormat = Lucene.Net.Codecs.Lucene41.Lucene41StoredFieldsFormat;
    using Lucene42NormsFormat = Lucene.Net.Codecs.Lucene42.Lucene42NormsFormat;
    using Lucene42TermVectorsFormat = Lucene.Net.Codecs.Lucene42.Lucene42TermVectorsFormat;
    using PerFieldDocValuesFormat = Lucene.Net.Codecs.PerField.PerFieldDocValuesFormat;
    using PerFieldPostingsFormat = Lucene.Net.Codecs.PerField.PerFieldPostingsFormat;

    /// <summary>
    /// Implements the Lucene 4.6 index format, with configurable per-field postings
    /// and docvalues formats.
    /// <para/>
    /// If you want to reuse functionality of this codec in another codec, extend
    /// <see cref="FilterCodec"/>.
    /// <para/>
    /// See <see cref="Lucene.Net.Codecs.Lucene46"/> package documentation for file format details.
    /// <para/>
    /// @lucene.experimental 
    /// </summary>
    // NOTE: if we make largish changes in a minor release, easier to just make Lucene46Codec or whatever
    // if they are backwards compatible or smallish we can probably do the backwards in the postingsreader
    // (it writes a minor version, etc).
    [CodecName("Lucene46HighCompression")]
    public class Lucene46HighCompressionCodec : Codec {
        private readonly StoredFieldsFormat fieldsFormat = new Lucene41StoredFieldsHighCompressionFormat();    //<--This is the only line different then the stock Lucene46Codec
        private readonly TermVectorsFormat vectorsFormat = new Lucene42TermVectorsFormat();
        private readonly FieldInfosFormat fieldInfosFormat = new Lucene46FieldInfosFormat();
        private readonly SegmentInfoFormat segmentInfosFormat = new Lucene46SegmentInfoFormat();
        private readonly LiveDocsFormat liveDocsFormat = new Lucene40LiveDocsFormat();

        private readonly PostingsFormat postingsFormat;

        private class PerFieldPostingsFormatAnonymousInnerClassHelper : PerFieldPostingsFormat {
            private readonly Lucene46HighCompressionCodec outerInstance;

            public PerFieldPostingsFormatAnonymousInnerClassHelper(Lucene46HighCompressionCodec outerInstance) {
                this.outerInstance = outerInstance;
            }

            [MethodImpl(MethodImplOptions.AggressiveInlining)]
            public override PostingsFormat GetPostingsFormatForField(string field) {
                return outerInstance.GetPostingsFormatForField(field);
            }
        }

        private readonly DocValuesFormat docValuesFormat;

        private class PerFieldDocValuesFormatAnonymousInnerClassHelper : PerFieldDocValuesFormat {
            private readonly Lucene46HighCompressionCodec outerInstance;

            public PerFieldDocValuesFormatAnonymousInnerClassHelper(Lucene46HighCompressionCodec outerInstance) {
                this.outerInstance = outerInstance;
            }

            [MethodImpl(MethodImplOptions.AggressiveInlining)]
            public override DocValuesFormat GetDocValuesFormatForField(string field) {
                return outerInstance.GetDocValuesFormatForField(field);
            }
        }

        /// <summary>
        /// Sole constructor. </summary>
        public Lucene46HighCompressionCodec()
            : base() {
            postingsFormat = new PerFieldPostingsFormatAnonymousInnerClassHelper(this);
            docValuesFormat = new PerFieldDocValuesFormatAnonymousInnerClassHelper(this);
        }

        public override sealed StoredFieldsFormat StoredFieldsFormat => fieldsFormat;

        public override sealed TermVectorsFormat TermVectorsFormat => vectorsFormat;

        public override sealed PostingsFormat PostingsFormat => postingsFormat;

        public override sealed FieldInfosFormat FieldInfosFormat => fieldInfosFormat;

        public override sealed SegmentInfoFormat SegmentInfoFormat => segmentInfosFormat;

        public override sealed LiveDocsFormat LiveDocsFormat => liveDocsFormat;

        /// <summary>
        /// Returns the postings format that should be used for writing
        /// new segments of <paramref name="field"/>.
        /// <para/>
        /// The default implementation always returns "Lucene41"
        /// </summary>
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public virtual PostingsFormat GetPostingsFormatForField(string field) {
            // LUCENENET specific - lazy initialize the codec to ensure we get the correct type if overridden.
            if (defaultFormat == null) {
                defaultFormat = Lucene.Net.Codecs.PostingsFormat.ForName("Lucene41");
            }
            return defaultFormat;
        }

        /// <summary>
        /// Returns the docvalues format that should be used for writing
        /// new segments of <paramref name="field"/>.
        /// <para/>
        /// The default implementation always returns "Lucene45"
        /// </summary>
        [MethodImpl(MethodImplOptions.AggressiveInlining)]
        public virtual DocValuesFormat GetDocValuesFormatForField(string field) {
            // LUCENENET specific - lazy initialize the codec to ensure we get the correct type if overridden.
            if (defaultDVFormat == null) {
                defaultDVFormat = Lucene.Net.Codecs.DocValuesFormat.ForName("Lucene45");
            }
            return defaultDVFormat;
        }

        public override sealed DocValuesFormat DocValuesFormat => docValuesFormat;

        // LUCENENET specific - lazy initialize the codecs to ensure we get the correct type if overridden.
        private PostingsFormat defaultFormat;
        private DocValuesFormat defaultDVFormat;

        private readonly NormsFormat normsFormat = new Lucene42NormsFormat();

        public override sealed NormsFormat NormsFormat => normsFormat;
    }

Codec.SetCodecFactory(new DefaultCodecFactory {
    CustomCodecTypes = new Type[] { typeof(Lucene46HighCompressionCodec) }
});

public class TestCompression {


        [Fact]
        public void HighCompression() {
            FxTest.Setup();

            Directory indexDir = new RAMDirectory();

            Analyzer standardAnalyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48);

            IndexWriterConfig indexConfig = new IndexWriterConfig(LuceneVersion.LUCENE_48, standardAnalyzer);
            indexConfig.Codec = new Lucene46HighCompressionCodec();     //<--------Install the High Compression codec.

            indexConfig.UseCompoundFile = true;

            IndexWriter writer = new IndexWriter(indexDir, indexConfig);

            //souce: https://github.com/apache/lucenenet/blob/Lucene.Net_4_8_0_beta00006/src/Lucene.Net/Search/SearcherFactory.cs
            SearcherManager searcherManager = new SearcherManager(writer, applyAllDeletes: true, new SearchWarmer());

            Document doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "001", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Unique gifts are great gifts.", Field.Store.YES));
            writer.AddDocument(doc);

            doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "002", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Everyone is gifted.", Field.Store.YES));
            writer.AddDocument(doc);

            doc = new Document();
            doc.Add(new StringField("examplePrimaryKey", "003", Field.Store.YES));
            doc.Add(new TextField("exampleField", "Gifts are meant to be shared.", Field.Store.YES));
            writer.AddDocument(doc);

            writer.Commit();

            searcherManager.MaybeRefreshBlocking();
            IndexSearcher indexSearcher = searcherManager.Acquire();
            try {
                QueryParser parser = new QueryParser(LuceneVersion.LUCENE_48, "exampleField", standardAnalyzer);
                Query query = parser.Parse("everyone");

                TopDocs topDocs = indexSearcher.Search(query, int.MaxValue);

                int numMatchingDocs = topDocs.ScoreDocs.Length;
                Assert.Equal(1, numMatchingDocs);


                Document docRead = indexSearcher.Doc(topDocs.ScoreDocs[0].Doc);
                string primaryKey = docRead.Get("examplePrimaryKey");
                Assert.Equal("002", primaryKey);

            } finally {
                searcherManager.Release(indexSearcher);
            }

        }

    }