@Override
public final boolean incrementToken() throws IOException {
clearAttributes();
if (delimitersCount == -1) {
int length = 0;
delimiterPositions.add(0);
while (true) {
int c = input.read();
if (c < 0) {
break;
}
length++;
if (c == delimiter) {
delimiterPositions.add(length);
resultToken.append(replacement);
} else {
resultToken.append((char) c);
}
}
delimitersCount = delimiterPositions.size();
if (delimiterPositions.get(delimitersCount - 1) < length) {
delimiterPositions.add(length);
delimitersCount++;
}
if (resultTokenBuffer.length < resultToken.length()) {
resultTokenBuffer = new char[resultToken.length()];
}
resultToken.getChars(0, resultToken.length(), resultTokenBuffer, 0);
resultToken.setLength(0);
int idx = delimitersCount - 1 - skip;
if (idx >= 0) {
// otherwise its ok, because we will skip and return false
endPosition = delimiterPositions.get(idx);
}
finalOffset = correctOffset(length);
posAtt.setPositionIncrement(1);
} else {
posAtt.setPositionIncrement(0);
}
while (skipped < delimitersCount - skip - 1) {
int start = delimiterPositions.get(skipped);
termAtt.copyBuffer(resultTokenBuffer, start, endPosition - start);
offsetAtt.setOffset(correctOffset(start), correctOffset(endPosition));
skipped++;
return true;
}
return false;
}
@Override
public boolean incrementToken() throws IOException {
if (tokenIter == null || !tokenIter.hasNext()) {
if (input.incrementToken()) {
tokStart = offsetAtt.startOffset();
tokEnd = offsetAtt.endOffset();
hasIllegalOffsets = (tokStart + termAtt.length()) != tokEnd;
tokenBuffer = wordSegmenter.getTokendWords(termAtt.toString());
tokenIter = tokenBuffer.iterator();
if (!tokenIter.hasNext()) return false;
} else {
return false;
}
}
clearAttributes();
TokendWords nextWord = tokenIter.next();
termAtt.copyBuffer(nextWord.next(), 0, nextWord.next().length);
if (hasIllegalOffsets) {
offsetAtt.setOffset(tokStart, tokEnd);
} else {
offsetAtt.setOffset(nextWord.start, nextWord.end);
}
typeAtt.setType("word");
return true;
}
@Override
public boolean incrementToken() throws IOException {
if (tokenIter == null || !tokenIter.hasNext()) {
// there are no remaining tokens from the current sentence... are there more sentences?
if (input.incrementToken()) {
tokStart = offsetAtt.startOffset();
tokEnd = offsetAtt.endOffset();
// if length by start + end offsets doesn't match the term text then assume
// this is a synonym and don't adjust the offsets.
hasIllegalOffsets = (tokStart + termAtt.length()) != tokEnd;
// a new sentence is available: process it.
tokenBuffer = splitIntoTokens(termAtt.toString(), offsetAtt.startOffset());
tokenIter = tokenBuffer.iterator();
// it should not be possible to have a sentence with 0 words, check just in case.
// returning EOS isn't the best either, but its the behavior of the original code.
if (!tokenIter.hasNext()) return false;
} else {
return false; // no more sentences, end of stream!
}
}
// WordTokenFilter must clear attributes, as it is creating new tokens.
clearAttributes();
// There are remaining tokens from the current sentence, return the next one.
SegToken nextWord = tokenIter.next();
termAtt.append(nextWord.term);
// termAtt.copyBuffer(nextWord.charArray, 0, nextWord.charArray.length);
if (hasIllegalOffsets) {
offsetAtt.setOffset(tokStart, tokEnd);
} else {
offsetAtt.setOffset(nextWord.start, nextWord.end);
}
typeAtt.setType("word");
return true;
}
private void emit(Token token) {
emit(token.tok);
OffsetAttribute offAttr = getOffsetAttribute();
if (token.endPos > token.startPos && token.startPos >= 0) {
offAttr.setOffset(token.startPos, token.endPos);
}
}
@Override
public final boolean incrementToken() throws IOException {
while (true) {
if (curTermBuffer == null) {
if (!input.incrementToken()) {
return false;
} else {
curTermBuffer = termAtt.buffer().clone();
curTermLength = termAtt.length();
curGramSize = minGram;
tokStart = offsetAtt.startOffset();
}
}
if (curGramSize <= maxGram) {
if (!(curGramSize
> curTermLength // if the remaining input is too short, we can't generate any
// n-grams
|| curGramSize > maxGram)) { // if we have hit the end of our n-gram size range, quit
// grab gramSize chars from front or back
int start = side == Side.FRONT ? 0 : curTermLength - curGramSize;
int end = start + curGramSize;
clearAttributes();
offsetAtt.setOffset(tokStart + start, tokStart + end);
termAtt.copyBuffer(curTermBuffer, start, curGramSize);
curGramSize++;
return true;
}
}
curTermBuffer = null;
}
}
/* (non-Javadoc)
* @see org.apache.lucene.analysis.TokenStream#incrementToken()
*/
@Override
public boolean incrementToken() throws IOException {
// 清除所有的词元属性
clearAttributes();
skippedPositions = 0;
Lexeme nextLexeme = _IKImplement.next();
if (nextLexeme != null) {
posIncrAtt.setPositionIncrement(skippedPositions + 1);
// 将Lexeme转成Attributes
// 设置词元文本
termAtt.append(nextLexeme.getLexemeText());
// 设置词元长度
termAtt.setLength(nextLexeme.getLength());
// 设置词元位移
offsetAtt.setOffset(
correctOffset(nextLexeme.getBeginPosition()), correctOffset(nextLexeme.getEndPosition()));
// 记录分词的最后位置
endPosition = nextLexeme.getEndPosition();
// 记录词元分类
typeAtt.setType(nextLexeme.getLexemeTypeString());
// 返会true告知还有下个词元
return true;
}
// 返会false告知词元输出完毕
return false;
}
@Override
public final void end() throws IOException {
super.end();
// set final offset
int finalOffset = correctOffset(charsRead);
offsetAtt.setOffset(finalOffset, finalOffset);
}
@Override
public final boolean incrementToken() throws IOException {
if (!tokens.isEmpty()) {
assert current != null;
CompoundToken token = tokens.removeFirst();
restoreState(current); // keep all other attributes untouched
termAtt.setEmpty().append(token.txt);
offsetAtt.setOffset(token.startOffset, token.endOffset);
posIncAtt.setPositionIncrement(0);
return true;
}
current = null; // not really needed, but for safety
if (input.incrementToken()) {
// Only words longer than minWordSize get processed
if (termAtt.length() >= this.minWordSize) {
decompose();
// only capture the state if we really need it for producing new tokens
if (!tokens.isEmpty()) {
current = captureState();
}
}
// return original token:
return true;
} else {
return false;
}
}
@Override
public void end() throws IOException {
super.end();
// Set final offset
int finalOffset = correctOffset(pos);
offsetAtt.setOffset(finalOffset, finalOffset);
}
/*
* (non-Javadoc)
*
* @see org.apache.lucene.analysis.TokenStream#next()
*/
@Override
public final boolean incrementToken() throws IOException {
clearAttributes();
skippedPositions = 0;
while (true) {
int tokenType = scanner.getNextToken();
if (tokenType == StandardTokenizerInterface.YYEOF) {
return false;
}
if (scanner.yylength() <= maxTokenLength) {
posIncrAtt.setPositionIncrement(skippedPositions + 1);
scanner.getText(termAtt);
final int start = scanner.yychar();
offsetAtt.setOffset(correctOffset(start), correctOffset(start + termAtt.length()));
// This 'if' should be removed in the next release. For now, it converts
// invalid acronyms to HOST. When removed, only the 'else' part should
// remain.
if (tokenType == StandardTokenizer.ACRONYM_DEP) {
typeAtt.setType(StandardTokenizer.TOKEN_TYPES[StandardTokenizer.HOST]);
termAtt.setLength(termAtt.length() - 1); // remove extra '.'
} else {
typeAtt.setType(StandardTokenizer.TOKEN_TYPES[tokenType]);
}
return true;
} else
// When we skip a too-long term, we still increment the
// position increment
skippedPositions++;
}
}
/*
* (non-Javadoc)
*
* @see org.apache.lucene.analysis.TokenStream#next()
*/
@Override
public final boolean incrementToken() throws IOException {
clearAttributes();
skippedPositions = 0;
while (true) {
int tokenType = scanner.getNextToken();
if (tokenType == StandardTokenizerImpl.YYEOF) {
return false;
}
if (scanner.yylength() <= maxTokenLength) {
posIncrAtt.setPositionIncrement(skippedPositions + 1);
scanner.getText(termAtt);
final int start = scanner.yychar();
offsetAtt.setOffset(correctOffset(start), correctOffset(start + termAtt.length()));
typeAtt.setType(StandardTokenizer.TOKEN_TYPES[tokenType]);
return true;
} else
// When we skip a too-long term, we still increment the
// position increment
skippedPositions++;
}
}
@Override
public boolean incrementToken() throws IOException {
if (!getNextPartialSnippet()) return false;
clearAttributes();
termAtt.setEmpty().append(snippet, startTerm, startTerm + lenTerm);
offsetAtt.setOffset(correctOffset(startOffset), correctOffset(startOffset + lenTerm));
return true;
}
@Override
public final void end() throws IOException {
super.end();
// set final offset
int finalOffset = correctOffset(this.endPosition);
offsetAtt.setOffset(finalOffset, finalOffset);
posIncrAtt.setPositionIncrement(posIncrAtt.getPositionIncrement() + skippedPositions);
}
@Override
public boolean incrementToken() throws IOException {
if (index >= str.length()) return false;
clearAttributes();
if (group >= 0) {
// match a specific group
while (matcher.find()) {
final String match = matcher.group(group);
if (match.length() == 0) continue;
termAtt.setEmpty().append(match);
index = matcher.start(group);
offsetAtt.setOffset(correctOffset(index), correctOffset(matcher.end(group)));
return true;
}
index = Integer.MAX_VALUE; // mark exhausted
return false;
} else {
// String.split() functionality
while (matcher.find()) {
if (matcher.start() - index > 0) {
// found a non-zero-length token
termAtt.setEmpty().append(str, index, matcher.start());
offsetAtt.setOffset(correctOffset(index), correctOffset(matcher.start()));
index = matcher.end();
return true;
}
index = matcher.end();
}
if (str.length() - index == 0) {
index = Integer.MAX_VALUE; // mark exhausted
return false;
}
termAtt.setEmpty().append(str, index, str.length());
offsetAtt.setOffset(correctOffset(index), correctOffset(str.length()));
index = Integer.MAX_VALUE; // mark exhausted
return true;
}
}
@Override
public final void end() throws IOException {
super.end();
// set final offset
int finalOffset = correctOffset(scanner.yychar() + scanner.yylength());
offsetAtt.setOffset(finalOffset, finalOffset);
// adjust any skipped tokens
posIncrAtt.setPositionIncrement(posIncrAtt.getPositionIncrement() + skippedPositions);
}
public boolean incrementToken() throws IOException {
if (inPhrase) {
inPhrase = false;
clearAttributes();
termAtt.setTermBuffer("phrase2");
offsetAtt.setOffset(savedStart, savedEnd);
return true;
} else
while (input.incrementToken()) {
if (termAtt.term().equals("phrase")) {
inPhrase = true;
savedStart = offsetAtt.startOffset();
savedEnd = offsetAtt.endOffset();
termAtt.setTermBuffer("phrase1");
offsetAtt.setOffset(savedStart, savedEnd);
return true;
} else if (!termAtt.term().equals("stop")) return true;
}
return false;
}
@Override
public boolean incrementToken() {
if (used) {
return false;
}
clearAttributes();
termAttribute.append(value);
offsetAttribute.setOffset(0, value.length());
used = true;
return true;
}
/**
* Generates a word/number part, updating the appropriate attributes
*
* @param isSingleWord {@code true} if the generation is occurring from a single word, {@code
* false} otherwise
*/
private void generatePart(boolean isSingleWord) {
clearAttributes();
termAttribute.copyBuffer(savedBuffer, iterator.current, iterator.end - iterator.current);
int startOffset = savedStartOffset + iterator.current;
int endOffset = savedStartOffset + iterator.end;
if (hasIllegalOffsets) {
// historically this filter did this regardless for 'isSingleWord',
// but we must do a sanity check:
if (isSingleWord && startOffset <= savedEndOffset) {
offsetAttribute.setOffset(startOffset, savedEndOffset);
} else {
offsetAttribute.setOffset(savedStartOffset, savedEndOffset);
}
} else {
offsetAttribute.setOffset(startOffset, endOffset);
}
posIncAttribute.setPositionIncrement(position(false));
typeAttribute.setType(savedType);
}
@Override
public void end() throws IOException {
super.end();
// NOTE: somewhat... hackish, but we need this to
// satisfy BTSTC:
final int lastOffset;
if (tokens != null && !tokens.isEmpty()) {
lastOffset = tokens.get(tokens.size() - 1).endOffset();
} else {
lastOffset = 0;
}
offsetAtt.setOffset(correctOffset(lastOffset), correctOffset(inputLength));
}
public boolean incrementToken() throws IOException {
clearAttributes();
Token token = nextToken(reusableToken);
if (token != null) {
termAtt.copyBuffer(token.buffer(), 0, token.length());
offsetAtt.setOffset(token.startOffset(), token.endOffset());
typeAtt.setType(token.type());
return true;
} else {
end();
return false;
}
}
@Override
public boolean incrementToken() throws IOException {
clearAttributes();
// 已经穷尽tokensIteractor的Token对象，则继续请求reader流入数据
while (tokenIteractor == null || !tokenIteractor.hasNext()) {
// System.out.println(dissected);
int read = 0;
int remainning = -1; // 重新从reader读入字符前，buffer中还剩下的字符数，负数表示当前暂不需要从reader中读入字符
if (dissected >= beef.length()) {
remainning = 0;
} else if (dissected < 0) {
remainning = bufferLength + dissected;
}
if (remainning >= 0) {
if (remainning > 0) {
System.arraycopy(buffer, -dissected, buffer, 0, remainning);
}
read = input.read(buffer, remainning, bufferLength - remainning);
inputLength += read;
int charCount = remainning + read;
if (charCount < 0) {
// reader已尽，按接口next()要求返回null.
return false;
}
if (charCount < bufferLength) {
buffer[charCount++] = 0;
}
// 构造“牛”，并使用knife“解”之
beef.set(0, charCount);
offset += Math.abs(dissected);
// offset -= remainning;
dissected = 0;
}
dissected = knife.dissect(this, beef, dissected);
// offset += read;// !!!
tokenIteractor = tokenCollector.iterator();
}
if (tokenIteractor.hasNext()) {
// 返回tokensIteractor下一个Token对象
Token token = tokenIteractor.next();
termAtt.setEmpty();
termAtt.append(token.charSequence());
offsetAtt.setOffset(correctOffset(token.startOffset()), correctOffset(token.endOffset()));
positionIncrementAttribute.setPositionIncrement(token.endOffset());
return true;
}
return tokenIteractor.hasNext();
}
@Override
public boolean incrementToken() throws IOException {
if (index >= tokens.length) return false;
else {
clearAttributes();
Token token = tokens[index++];
termAtt.setEmpty().append(token);
offsetAtt.setOffset(token.startOffset(), token.endOffset());
posIncAtt.setPositionIncrement(token.getPositionIncrement());
flagsAtt.setFlags(token.getFlags());
typeAtt.setType(token.type());
payloadAtt.setPayload(token.getPayload());
return true;
}
}
@Override
public boolean incrementToken() throws IOException {
if (iterator == null) {
initializeIterator();
}
if (iterator.hasNext()) {
clearAttributes();
AnnotationFS next = iterator.next();
termAttr.append(next.getCoveredText());
offsetAttr.setOffset(correctOffset(next.getBegin()), correctOffset(next.getEnd()));
return true;
} else {
return false;
}
}
@Override
public boolean incrementToken() throws IOException {
boolean tokenAvailable = false;
int builtGramSize = 0;
if (gramSize.atMinValue() || inputWindow.size() < gramSize.getValue()) {
shiftInputWindow();
gramBuilder.setLength(0);
} else {
builtGramSize = gramSize.getPreviousValue();
}
if (inputWindow.size() >= gramSize.getValue()) {
boolean isAllFiller = true;
InputWindowToken nextToken = null;
Iterator<InputWindowToken> iter = inputWindow.iterator();
for (int gramNum = 1; iter.hasNext() && builtGramSize < gramSize.getValue(); ++gramNum) {
nextToken = iter.next();
if (builtGramSize < gramNum) {
if (builtGramSize > 0) {
gramBuilder.append(tokenSeparator);
}
gramBuilder.append(nextToken.termAtt.buffer(), 0, nextToken.termAtt.length());
++builtGramSize;
}
if (isAllFiller && nextToken.isFiller) {
if (gramNum == gramSize.getValue()) {
gramSize.advance();
}
} else {
isAllFiller = false;
}
}
if (!isAllFiller && builtGramSize == gramSize.getValue()) {
inputWindow.getFirst().attSource.copyTo(this);
posIncrAtt.setPositionIncrement(isOutputHere ? 0 : 1);
termAtt.setEmpty().append(gramBuilder);
if (gramSize.getValue() > 1) {
typeAtt.setType(tokenType);
noShingleOutput = false;
}
offsetAtt.setOffset(offsetAtt.startOffset(), nextToken.offsetAtt.endOffset());
posLenAtt.setPositionLength(builtGramSize);
isOutputHere = true;
gramSize.advance();
tokenAvailable = true;
}
}
return tokenAvailable;
}
@Override
public boolean incrementToken() throws IOException {
clearAttributes();
buffer.setLength(0);
int ci;
char ch, pch;
boolean atBegin = true;
tokenStart = tokenEnd;
ci = input.read();
ch = (char) ci;
while (true) {
if (ci == -1) {
break;
} else if (PUNCTION.indexOf(ch) != -1) {
// End of a sentence
buffer.append(ch);
tokenEnd++;
break;
} else if (atBegin && SPACES.indexOf(ch) != -1) {
tokenStart++;
tokenEnd++;
ci = input.read();
ch = (char) ci;
} else {
buffer.append(ch);
atBegin = false;
tokenEnd++;
pch = ch;
ci = input.read();
ch = (char) ci;
// Two spaces, such as CR, LF
if (SPACES.indexOf(ch) != -1 && SPACES.indexOf(pch) != -1) {
// buffer.append(ch);
tokenEnd++;
break;
}
}
}
if (buffer.length() == 0) return false;
else {
termAtt.setEmpty().append(buffer);
offsetAtt.setOffset(correctOffset(tokenStart), correctOffset(tokenEnd));
typeAtt.setType("sentence");
return true;
}
}
/** Writes the joined unhyphenated term */
private void unhyphenate() {
int endOffset = offsetAttribute.endOffset();
restoreState(savedState);
savedState = null;
char term[] = termAttribute.buffer();
int length = hyphenated.length();
if (length > termAttribute.length()) {
term = termAttribute.resizeBuffer(length);
}
hyphenated.getChars(0, length, term, 0);
termAttribute.setLength(length);
offsetAttribute.setOffset(offsetAttribute.startOffset(), endOffset);
hyphenated.setLength(0);
}
@Override
public boolean incrementToken() {
if (upto < tokens.length) {
final Token token = tokens[upto++];
// TODO: can we just capture/restoreState so
// we get all attrs...?
clearAttributes();
termAtt.setEmpty();
termAtt.append(token.toString());
posIncrAtt.setPositionIncrement(token.getPositionIncrement());
posLengthAtt.setPositionLength(token.getPositionLength());
offsetAtt.setOffset(token.startOffset(), token.endOffset());
payloadAtt.setPayload(token.getPayload());
return true;
} else {
return false;
}
}
@Override
public boolean incrementToken() throws IOException {
// parse() is able to return w/o producing any new
// tokens, when the tokens it had produced were entirely
// punctuation. So we loop here until we get a real
// token or we end:
while (pending.size() == 0) {
if (end) {
return false;
}
// Push Viterbi forward some more:
parse();
}
final Token token = pending.remove(pending.size() - 1);
int position = token.getPosition();
int length = token.getLength();
clearAttributes();
assert length > 0;
// System.out.println("off=" + token.getOffset() + " len=" + length + " vs " +
// token.getSurfaceForm().length);
termAtt.copyBuffer(token.getSurfaceForm(), token.getOffset(), length);
offsetAtt.setOffset(correctOffset(position), correctOffset(position + length));
basicFormAtt.setToken(token);
posAtt.setToken(token);
readingAtt.setToken(token);
inflectionAtt.setToken(token);
if (token.getPosition() == lastTokenPos) {
posIncAtt.setPositionIncrement(0);
posLengthAtt.setPositionLength(token.getPositionLength());
} else {
assert token.getPosition() > lastTokenPos;
posIncAtt.setPositionIncrement(1);
posLengthAtt.setPositionLength(1);
}
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": incToken: return token=" + token);
}
lastTokenPos = token.getPosition();
return true;
}
@Override
public boolean incrementToken() throws IOException {
if (tokens == null) {
fillTokens();
}
// System.out.println("graphTokenizer: incr upto=" + upto + " vs " + tokens.size());
if (upto == tokens.size()) {
// System.out.println(" END @ " + tokens.size());
return false;
}
final Token t = tokens.get(upto++);
// System.out.println(" return token=" + t);
clearAttributes();
termAtt.append(t.toString());
offsetAtt.setOffset(t.startOffset(), t.endOffset());
posIncrAtt.setPositionIncrement(t.getPositionIncrement());
posLengthAtt.setPositionLength(t.getPositionLength());
return true;
}
@Override
public final boolean incrementToken() throws IOException {
while (true) {
if (curTermBuffer == null) {
if (!input.incrementToken()) {
return false;
} else {
curTermBuffer = termAtt.buffer().clone();
curTermLength = termAtt.length();
curCodePointCount = charUtils.codePointCount(termAtt);
curGramSize = minGram;
tokStart = offsetAtt.startOffset();
tokEnd = offsetAtt.endOffset();
savePosIncr += posIncrAtt.getPositionIncrement();
savePosLen = posLenAtt.getPositionLength();
}
}
if (curGramSize <= maxGram) { // if we have hit the end of our n-gram size range, quit
if (curGramSize
<= curCodePointCount) { // if the remaining input is too short, we can't generate any
// n-grams
// grab gramSize chars from front or back
clearAttributes();
offsetAtt.setOffset(tokStart, tokEnd);
// first ngram gets increment, others don't
if (curGramSize == minGram) {
posIncrAtt.setPositionIncrement(savePosIncr);
savePosIncr = 0;
} else {
posIncrAtt.setPositionIncrement(0);
}
posLenAtt.setPositionLength(savePosLen);
final int charLength =
charUtils.offsetByCodePoints(curTermBuffer, 0, curTermLength, 0, curGramSize);
termAtt.copyBuffer(curTermBuffer, 0, charLength);
curGramSize++;
return true;
}
}
curTermBuffer = null;
}
}
