本文整理了Java中org.apache.lucene.util.fst.Builder.<init>()
方法的一些代码示例,展示了Builder.<init>()
的具体用法。这些代码示例主要来源于Github
/Stackoverflow
/Maven
等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。Builder.<init>()
方法的具体详情如下:
包路径:org.apache.lucene.util.fst.Builder
类名称:Builder
方法名:<init>
[英]Instantiates an FST/FSA builder with all the possible tuning and construction tweaks. Read parameter documentation carefully.
[中]实例化一个FST/FSA生成器,其中包含所有可能的调优和构造调整。仔细阅读参数文档。
代码示例来源:origin: org.apache.lucene/lucene-core
final Builder<BytesRef> indexBuilder = new Builder<>(FST.INPUT_TYPE.BYTE1,
0, 0, true, false, Integer.MAX_VALUE,
outputs, true, 15);
代码示例来源:origin: org.apache.lucene/lucene-analyzers-common
private FST<CharsRef> parseConversions(LineNumberReader reader, int num) throws IOException, ParseException {
Map<String,String> mappings = new TreeMap<>();
for (int i = 0; i < num; i++) {
String line = reader.readLine();
String parts[] = line.split("\\s+");
if (parts.length != 3) {
throw new ParseException("invalid syntax: " + line, reader.getLineNumber());
}
if (mappings.put(parts[1], parts[2]) != null) {
throw new IllegalStateException("duplicate mapping specified for: " + parts[1]);
}
}
Outputs<CharsRef> outputs = CharSequenceOutputs.getSingleton();
Builder<CharsRef> builder = new Builder<>(FST.INPUT_TYPE.BYTE2, outputs);
IntsRefBuilder scratchInts = new IntsRefBuilder();
for (Map.Entry<String,String> entry : mappings.entrySet()) {
Util.toUTF16(entry.getKey(), scratchInts);
builder.add(scratchInts.get(), new CharsRef(entry.getValue()));
}
return builder.finish();
}
代码示例来源:origin: org.elasticsearch/elasticsearch
public XBuilder(int maxSurfaceFormsPerAnalyzedForm, boolean hasPayloads, int payloadSep) {
this.payloadSep = payloadSep;
this.outputs = new PairOutputs<>(PositiveIntOutputs.getSingleton(), ByteSequenceOutputs.getSingleton());
this.builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
this.maxSurfaceFormsPerAnalyzedForm = maxSurfaceFormsPerAnalyzedForm;
this.hasPayloads = hasPayloads;
surfaceFormsAndPayload = new SurfaceFormAndPayload[maxSurfaceFormsPerAnalyzedForm];
}
public void startTerm(BytesRef analyzed) {
代码示例来源:origin: org.apache.lucene/lucene-analyzers-common
private FST<IntsRef> affixFST(TreeMap<String,List<Integer>> affixes) throws IOException {
IntSequenceOutputs outputs = IntSequenceOutputs.getSingleton();
Builder<IntsRef> builder = new Builder<>(FST.INPUT_TYPE.BYTE4, outputs);
IntsRefBuilder scratch = new IntsRefBuilder();
for (Map.Entry<String,List<Integer>> entry : affixes.entrySet()) {
Util.toUTF32(entry.getKey(), scratch);
List<Integer> entries = entry.getValue();
IntsRef output = new IntsRef(entries.size());
for (Integer c : entries) {
output.ints[output.length++] = c;
}
builder.add(scratch.get(), output);
}
return builder.finish();
}
代码示例来源:origin: org.apache.lucene/lucene-analyzers-common
/** Builds the NormalizeCharMap; call this once you
* are done calling {@link #add}. */
public NormalizeCharMap build() {
final FST<CharsRef> map;
try {
final Outputs<CharsRef> outputs = CharSequenceOutputs.getSingleton();
final org.apache.lucene.util.fst.Builder<CharsRef> builder = new org.apache.lucene.util.fst.Builder<>(FST.INPUT_TYPE.BYTE2, outputs);
final IntsRefBuilder scratch = new IntsRefBuilder();
for(Map.Entry<String,String> ent : pendingPairs.entrySet()) {
builder.add(Util.toUTF16(ent.getKey(), scratch),
new CharsRef(ent.getValue()));
}
map = builder.finish();
pendingPairs.clear();
} catch (IOException ioe) {
// Bogus FST IOExceptions!! (will never happen)
throw new RuntimeException(ioe);
}
return new NormalizeCharMap(map);
}
}
代码示例来源:origin: org.apache.lucene/lucene-analyzers-common
Builder<IntsRef> b = new Builder<>(FST.INPUT_TYPE.BYTE4, o);
readDictionaryFiles(tempDir, tempFileNamePrefix, dictionaries, decoder, b);
words = b.finish();
代码示例来源:origin: org.apache.lucene/lucene-analyzers-common
new org.apache.lucene.util.fst.Builder<>(FST.INPUT_TYPE.BYTE4, outputs);
代码示例来源:origin: org.apache.lucene/lucene-codecs
public TermsWriter(IndexOutput out, FieldInfo field) {
this.out = out;
this.field = field;
builder = new Builder<>(FST.INPUT_TYPE.BYTE1, 0, 0, true, true, Integer.MAX_VALUE, outputs, true, 15);
}
代码示例来源:origin: org.apache.lucene/lucene-analyzers-common
/**
* Returns an {@link StemmerOverrideMap} to be used with the {@link StemmerOverrideFilter}
* @return an {@link StemmerOverrideMap} to be used with the {@link StemmerOverrideFilter}
* @throws IOException if an {@link IOException} occurs;
*/
public StemmerOverrideMap build() throws IOException {
ByteSequenceOutputs outputs = ByteSequenceOutputs.getSingleton();
org.apache.lucene.util.fst.Builder<BytesRef> builder = new org.apache.lucene.util.fst.Builder<>(
FST.INPUT_TYPE.BYTE4, outputs);
final int[] sort = hash.sort();
IntsRefBuilder intsSpare = new IntsRefBuilder();
final int size = hash.size();
BytesRef spare = new BytesRef();
for (int i = 0; i < size; i++) {
int id = sort[i];
BytesRef bytesRef = hash.get(id, spare);
intsSpare.copyUTF8Bytes(bytesRef);
builder.add(intsSpare.get(), new BytesRef(outputValues.get(id)));
}
return new StemmerOverrideMap(builder.finish(), ignoreCase);
}
代码示例来源:origin: org.elasticsearch/elasticsearch
Builder<Pair<Long,BytesRef>> builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
代码示例来源:origin: org.apache.lucene/lucene-codecs
TermsWriter(FieldInfo fieldInfo) {
this.numTerms = 0;
this.fieldInfo = fieldInfo;
this.longsSize = postingsWriter.setField(fieldInfo);
this.outputs = new FSTTermOutputs(fieldInfo, longsSize);
this.builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
}
代码示例来源:origin: org.apache.lucene/lucene-codecs
TermsWriter(FieldInfo fieldInfo) {
this.numTerms = 0;
this.fieldInfo = fieldInfo;
this.longsSize = postingsWriter.setField(fieldInfo);
this.outputs = PositiveIntOutputs.getSingleton();
this.builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
this.lastBlockStatsFP = 0;
this.lastBlockMetaLongsFP = 0;
this.lastBlockMetaBytesFP = 0;
this.lastBlockLongs = new long[longsSize];
this.lastLongs = new long[longsSize];
this.lastMetaBytesFP = 0;
}
代码示例来源:origin: harbby/presto-connectors
/**
* Create a builder for {@link NRTSuggester}
*/
public NRTSuggesterBuilder() {
this.payloadSep = PAYLOAD_SEP;
this.endByte = END_BYTE;
this.outputs = new PairOutputs<>(PositiveIntOutputs.getSingleton(), ByteSequenceOutputs.getSingleton());
this.entries = new PriorityQueue<>();
this.builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
}
代码示例来源:origin: com.strapdata.elasticsearch/elasticsearch
public XBuilder(int maxSurfaceFormsPerAnalyzedForm, boolean hasPayloads, int payloadSep) {
this.payloadSep = payloadSep;
this.outputs = new PairOutputs<>(PositiveIntOutputs.getSingleton(), ByteSequenceOutputs.getSingleton());
this.builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
this.maxSurfaceFormsPerAnalyzedForm = maxSurfaceFormsPerAnalyzedForm;
this.hasPayloads = hasPayloads;
surfaceFormsAndPayload = new SurfaceFormAndPayload[maxSurfaceFormsPerAnalyzedForm];
}
public void startTerm(BytesRef analyzed) {
代码示例来源:origin: org.apache.servicemix.bundles/org.apache.servicemix.bundles.elasticsearch
public XBuilder(int maxSurfaceFormsPerAnalyzedForm, boolean hasPayloads, int payloadSep) {
this.payloadSep = payloadSep;
this.outputs = new PairOutputs<>(PositiveIntOutputs.getSingleton(), ByteSequenceOutputs.getSingleton());
this.builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
this.maxSurfaceFormsPerAnalyzedForm = maxSurfaceFormsPerAnalyzedForm;
this.hasPayloads = hasPayloads;
surfaceFormsAndPayload = new SurfaceFormAndPayload[maxSurfaceFormsPerAnalyzedForm];
}
public void startTerm(BytesRef analyzed) {
代码示例来源:origin: apache/servicemix-bundles
public XBuilder(int maxSurfaceFormsPerAnalyzedForm, boolean hasPayloads, int payloadSep) {
this.payloadSep = payloadSep;
this.outputs = new PairOutputs<>(PositiveIntOutputs.getSingleton(), ByteSequenceOutputs.getSingleton());
this.builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
this.maxSurfaceFormsPerAnalyzedForm = maxSurfaceFormsPerAnalyzedForm;
this.hasPayloads = hasPayloads;
surfaceFormsAndPayload = new SurfaceFormAndPayload[maxSurfaceFormsPerAnalyzedForm];
}
public void startTerm(BytesRef analyzed) {
代码示例来源:origin: org.apache.lucene/lucene-classification
private void updateFST(SortedMap<String, Double> weights) throws IOException {
PositiveIntOutputs outputs = PositiveIntOutputs.getSingleton();
Builder<Long> fstBuilder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
BytesRefBuilder scratchBytes = new BytesRefBuilder();
IntsRefBuilder scratchInts = new IntsRefBuilder();
for (Map.Entry<String, Double> entry : weights.entrySet()) {
scratchBytes.copyChars(entry.getKey());
fstBuilder.add(Util.toIntsRef(scratchBytes.get(), scratchInts), entry
.getValue().longValue());
}
fst = fstBuilder.finish();
}
代码示例来源:origin: harbby/presto-connectors
public XBuilder(int maxSurfaceFormsPerAnalyzedForm, boolean hasPayloads, int payloadSep) {
this.payloadSep = payloadSep;
this.outputs = new PairOutputs<>(PositiveIntOutputs.getSingleton(), ByteSequenceOutputs.getSingleton());
this.builder = new Builder<>(FST.INPUT_TYPE.BYTE1, outputs);
this.maxSurfaceFormsPerAnalyzedForm = maxSurfaceFormsPerAnalyzedForm;
this.hasPayloads = hasPayloads;
surfaceFormsAndPayload = new SurfaceFormAndPayload[maxSurfaceFormsPerAnalyzedForm];
}
public void startTerm(BytesRef analyzed) {
代码示例来源:origin: org.infinispan/infinispan-embedded-query
private FST<IntsRef> affixFST(TreeMap<String,List<Integer>> affixes) throws IOException {
IntSequenceOutputs outputs = IntSequenceOutputs.getSingleton();
Builder<IntsRef> builder = new Builder<>(FST.INPUT_TYPE.BYTE4, outputs);
IntsRefBuilder scratch = new IntsRefBuilder();
for (Map.Entry<String,List<Integer>> entry : affixes.entrySet()) {
Util.toUTF32(entry.getKey(), scratch);
List<Integer> entries = entry.getValue();
IntsRef output = new IntsRef(entries.size());
for (Integer c : entries) {
output.ints[output.length++] = c;
}
builder.add(scratch.get(), output);
}
return builder.finish();
}
代码示例来源:origin: org.apache.lucene/lucene-codecs
public FSTFieldWriter(FieldInfo fieldInfo, long termsFilePointer) throws IOException {
this.fieldInfo = fieldInfo;
fstOutputs = PositiveIntOutputs.getSingleton();
fstBuilder = new Builder<>(FST.INPUT_TYPE.BYTE1, fstOutputs);
indexStart = out.getFilePointer();
////System.out.println("VGW: field=" + fieldInfo.name);
// Always put empty string in
fstBuilder.add(new IntsRef(), termsFilePointer);
startTermsFilePointer = termsFilePointer;
}
内容来源于网络,如有侵权,请联系作者删除!