本文整理汇总了Java中org.apache.lucene.util.automaton.CompiledAutomaton类的典型用法代码示例。如果您正苦于以下问题:Java CompiledAutomaton类的具体用法?Java CompiledAutomaton怎么用?Java CompiledAutomaton使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
CompiledAutomaton类属于org.apache.lucene.util.automaton包,在下文中一共展示了CompiledAutomaton类的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: initAutomata
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
/** initialize levenshtein DFAs up to maxDistance, if possible */
private List<CompiledAutomaton> initAutomata(int maxDistance) {
final List<CompiledAutomaton> runAutomata = dfaAtt.automata();
//System.out.println("cached automata size: " + runAutomata.size());
if (runAutomata.size() <= maxDistance &&
maxDistance <= LevenshteinAutomata.MAXIMUM_SUPPORTED_DISTANCE) {
LevenshteinAutomata builder =
new LevenshteinAutomata(UnicodeUtil.newString(termText, realPrefixLength, termText.length - realPrefixLength), transpositions);
String prefix = UnicodeUtil.newString(termText, 0, realPrefixLength);
for (int i = runAutomata.size(); i <= maxDistance; i++) {
Automaton a = builder.toAutomaton(i, prefix);
//System.out.println("compute automaton n=" + i);
runAutomata.add(new CompiledAutomaton(a, true, false));
}
}
return runAutomata;
}
示例2: intersect
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
@Override
public TermsEnum intersect(CompiledAutomaton compiled, BytesRef startTerm) throws IOException {
final List<MultiTermsEnum.TermsEnumIndex> termsEnums = new ArrayList<>();
for(int i=0;i<subs.length;i++) {
final TermsEnum termsEnum = subs[i].intersect(compiled, startTerm);
if (termsEnum != null) {
termsEnums.add(new MultiTermsEnum.TermsEnumIndex(termsEnum, i));
}
}
if (termsEnums.size() > 0) {
return new MultiTermsEnum(subSlices).reset(termsEnums.toArray(MultiTermsEnum.TermsEnumIndex.EMPTY_ARRAY));
} else {
return TermsEnum.EMPTY;
}
}
示例3: intersect
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
/** Returns a TermsEnum that iterates over all terms that
* are accepted by the provided {@link
* CompiledAutomaton}. If the <code>startTerm</code> is
* provided then the returned enum will only accept terms
* > <code>startTerm</code>, but you still must call
* next() first to get to the first term. Note that the
* provided <code>startTerm</code> must be accepted by
* the automaton.
*
* <p><b>NOTE</b>: the returned TermsEnum cannot
* seek</p>. */
public TermsEnum intersect(CompiledAutomaton compiled, final BytesRef startTerm) throws IOException {
// TODO: eventually we could support seekCeil/Exact on
// the returned enum, instead of only being able to seek
// at the start
if (compiled.type != CompiledAutomaton.AUTOMATON_TYPE.NORMAL) {
throw new IllegalArgumentException("please use CompiledAutomaton.getTermsEnum instead");
}
if (startTerm == null) {
return new AutomatonTermsEnum(iterator(null), compiled);
} else {
return new AutomatonTermsEnum(iterator(null), compiled) {
@Override
protected BytesRef nextSeekTerm(BytesRef term) throws IOException {
if (term == null) {
term = startTerm;
}
return super.nextSeekTerm(term);
}
};
}
}
示例4: initAutomata
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
/** initialize levenshtein DFAs up to maxDistance, if possible */
private List<CompiledAutomaton> initAutomata(int maxDistance) {
final List<CompiledAutomaton> runAutomata = dfaAtt.automata();
//System.out.println("cached automata size: " + runAutomata.size());
if (runAutomata.size() <= maxDistance &&
maxDistance <= LevenshteinAutomata.MAXIMUM_SUPPORTED_DISTANCE) {
LevenshteinAutomata builder =
new LevenshteinAutomata(UnicodeUtil.newString(termText, realPrefixLength, termText.length - realPrefixLength), transpositions);
for (int i = runAutomata.size(); i <= maxDistance; i++) {
Automaton a = builder.toAutomaton(i);
//System.out.println("compute automaton n=" + i);
// constant prefix
if (realPrefixLength > 0) {
Automaton prefix = BasicAutomata.makeString(
UnicodeUtil.newString(termText, 0, realPrefixLength));
a = BasicOperations.concatenate(prefix, a);
}
runAutomata.add(new CompiledAutomaton(a, true, false));
}
}
return runAutomata;
}
示例5: intersect
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
@Override
public TermsEnum intersect(CompiledAutomaton compiled, BytesRef startTerm) throws IOException {
final List<MultiTermsEnum.TermsEnumIndex> termsEnums = new ArrayList<MultiTermsEnum.TermsEnumIndex>();
for(int i=0;i<subs.length;i++) {
final TermsEnum termsEnum = subs[i].intersect(compiled, startTerm);
if (termsEnum != null) {
termsEnums.add(new MultiTermsEnum.TermsEnumIndex(termsEnum, i));
}
}
if (termsEnums.size() > 0) {
return new MultiTermsEnum(subSlices).reset(termsEnums.toArray(MultiTermsEnum.TermsEnumIndex.EMPTY_ARRAY));
} else {
return TermsEnum.EMPTY;
}
}
示例6: intersect
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
@Override
public TermsEnum intersect(CompiledAutomaton compiled, BytesRef startTerm) throws IOException {
if (compiled.type != CompiledAutomaton.AUTOMATON_TYPE.NORMAL) {
throw new IllegalArgumentException("please use CompiledAutomaton.getTermsEnum instead");
}
return new IntersectTermsEnum(this, compiled, startTerm);
}
示例7: getAutomatonEnum
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
/**
* return an automata-based enum for matching up to editDistance from
* lastTerm, if possible
*/
protected TermsEnum getAutomatonEnum(int editDistance, BytesRef lastTerm)
throws IOException {
final List<CompiledAutomaton> runAutomata = initAutomata(editDistance);
if (editDistance < runAutomata.size()) {
//System.out.println("FuzzyTE.getAEnum: ed=" + editDistance + " lastTerm=" + (lastTerm==null ? "null" : lastTerm.utf8ToString()));
final CompiledAutomaton compiled = runAutomata.get(editDistance);
return new AutomatonFuzzyTermsEnum(terms.intersect(compiled, lastTerm == null ? null : compiled.floor(lastTerm, new BytesRefBuilder())),
runAutomata.subList(0, editDistance + 1).toArray(new CompiledAutomaton[editDistance + 1]));
} else {
return null;
}
}
示例8: AutomatonFuzzyTermsEnum
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
public AutomatonFuzzyTermsEnum(TermsEnum tenum, CompiledAutomaton compiled[]) {
super(tenum, false);
this.matchers = new ByteRunAutomaton[compiled.length];
for (int i = 0; i < compiled.length; i++)
this.matchers[i] = compiled[i].runAutomaton;
termRef = new BytesRef(term.text());
}
示例9: copyTo
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
@Override
public void copyTo(AttributeImpl target) {
final List<CompiledAutomaton> targetAutomata =
((LevenshteinAutomataAttribute) target).automata();
targetAutomata.clear();
targetAutomata.addAll(automata);
}
示例10: AutomatonTermsEnum
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
/**
* Construct an enumerator based upon an automaton, enumerating the specified
* field, working on a supplied TermsEnum
* <p>
* @lucene.experimental
* <p>
* @param compiled CompiledAutomaton
*/
public AutomatonTermsEnum(TermsEnum tenum, CompiledAutomaton compiled) {
super(tenum);
this.finite = compiled.finite;
this.runAutomaton = compiled.runAutomaton;
assert this.runAutomaton != null;
this.commonSuffixRef = compiled.commonSuffixRef;
this.automaton = compiled.automaton;
// used for path tracking, where each bit is a numbered state.
visited = new long[runAutomaton.getSize()];
termComp = getComparator();
}
示例11: wildcardEnumeration
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
private TermsEnum wildcardEnumeration(final IndexReader reader)
throws IOException {
Terms terms = MultiFields.getTerms(reader, term.field());
if(terms == null){
return null;
}
return new AutomatonTermsEnum(
terms.iterator(),
new CompiledAutomaton(
WildcardQuery.toAutomaton(term),
false, false));
}
示例12: IntersectTermsEnum
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
IntersectTermsEnum(CompiledAutomaton compiled, BytesRef startTerm) throws IOException {
super();
//if (TEST) System.out.println("Enum init, startTerm=" + startTerm);
this.fst = dict;
this.fstReader = fst.getBytesReader();
this.fstOutputs = dict.outputs;
this.fsa = compiled.runAutomaton;
this.level = -1;
this.stack = new Frame[16];
for (int i = 0 ; i < stack.length; i++) {
this.stack[i] = new Frame();
}
Frame frame;
frame = loadVirtualFrame(newFrame());
this.level++;
frame = loadFirstFrame(newFrame());
pushFrame(frame);
this.meta = null;
this.metaUpto = 1;
this.decoded = false;
this.pending = false;
if (startTerm == null) {
pending = isAccept(topFrame());
} else {
doSeekCeil(startTerm);
pending = (term == null || !startTerm.equals(term.get())) && isValid(topFrame()) && isAccept(topFrame());
}
}
示例13: IntersectTermsEnum
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
IntersectTermsEnum(CompiledAutomaton compiled, BytesRef startTerm) throws IOException {
//if (TEST) System.out.println("Enum init, startTerm=" + startTerm);
this.fst = index;
this.fstReader = fst.getBytesReader();
this.fstOutputs = index.outputs;
this.fsa = compiled.runAutomaton;
this.level = -1;
this.stack = new Frame[16];
for (int i = 0 ; i < stack.length; i++) {
this.stack[i] = new Frame();
}
Frame frame;
frame = loadVirtualFrame(newFrame());
this.level++;
frame = loadFirstFrame(newFrame());
pushFrame(frame);
this.decoded = false;
this.pending = false;
if (startTerm == null) {
pending = isAccept(topFrame());
} else {
doSeekCeil(startTerm);
pending = (term == null || !startTerm.equals(term.get())) && isValid(topFrame()) && isAccept(topFrame());
}
}
示例14: intersect
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
@Override
public TermsEnum intersect(CompiledAutomaton compiled, BytesRef startTerm) throws IOException {
if (compiled.type != CompiledAutomaton.AUTOMATON_TYPE.NORMAL) {
throw new IllegalArgumentException("please use CompiledAutomaton.getTermsEnum instead");
}
return new OrdsIntersectTermsEnum(this, compiled, startTerm);
}
示例15: intersect
import org.apache.lucene.util.automaton.CompiledAutomaton; //导入依赖的package包/类
@Override
public TermsEnum intersect(CompiledAutomaton automaton, BytesRef bytes) throws IOException {
TermsEnum termsEnum = in.intersect(automaton, bytes);
assert termsEnum != null;
assert bytes == null || bytes.isValid();
return new AssertingTermsEnum(termsEnum);
}