lucene源码分析—倒排索引的写过程
lucene将倒排索引的信息写入.tim和.tip文件，这部分代码也是lucene最核心的一部分。倒排索引的写过程从BlockTreeTermsWriter的write函数开始，
BlockTreeTermsWriter::write
public void write(Fields fields) throws IOException {
String lastField = null;
for(String field : fields) {
lastField = field;
Terms terms = fields.terms(field);
if (terms == null) {
continue;
}
List<PrefixTerm> prefixTerms = null;
TermsEnum termsEnum = terms.iterator();
TermsWriter termsWriter = new TermsWriter(fieldInfos.fieldInfo(field));
int prefixTermUpto = 0;
while (true) {
BytesRef term = termsEnum.next();
termsWriter.write(term, termsEnum, null);
}
termsWriter.finish();
}
}遍历每个域，首先通过terms函数根据field名返回一个FreqProxTerms，包含了该域的所有Term；接下来fieldInfo根据域名返回域信息，并以此创建一个TermsWriter，TermsWriter是倒排索引写的主要类，接下来依次取出FreqProxTerms中的每个term，并调用TermsWriter的write函数写入.tim文件，并创建对应的索引信息，最后通过TermsWriter的finish函数将索引信息写入.tip文件中，下面依次来看。
BlockTreeTermsWriter::write->TermsWriter::write
public void write(BytesRef text, TermsEnum termsEnum, PrefixTerm prefixTerm) throws IOException {
BlockTermState state = postingsWriter.writeTerm(text, termsEnum, docsSeen);
if (state != null) {
pushTerm(text);
PendingTerm term = new PendingTerm(text, state, prefixTerm);
pending.add(term);
if (prefixTerm == null) {
sumDocFreq += state.docFreq;
sumTotalTermFreq += state.totalTermFreq;
numTerms++;
if (firstPendingTerm == null) {
firstPendingTerm = term;
}
lastPendingTerm = term;
}
}
}TermsWriter的write函数一次处理一个Term。postingsWriter是Lucene50PostingsWriter。write函数首先通过Lucene50PostingsWriter的writeTerm函数记录每个Term以及对应文档的相应信息。
成员变量pending是一个PendingEntry列表，PendingEntry用来保存一个Term或者是一个Block，pending列表用来保存多个待处理的Term。
pushTerm是write里的核心函数，用于具体处理一个Term，后面详细来看。write函数的最后统计文档频和词频信息并记录到sumDocFreq和sumTotalTermFreq两个成员变量中。
BlockTreeTermsWriter::write->TermsWriter::write->Lucene50PostingsWriter::writeTerm
public final BlockTermState writeTerm(BytesRef term, TermsEnum termsEnum, FixedBitSet docsSeen) throws IOException {
startTerm();
postingsEnum = termsEnum.postings(postingsEnum, enumFlags);
int docFreq = 0;
long totalTermFreq = 0;
while (true) {
int docID = postingsEnum.nextDoc();
if (docID == PostingsEnum.NO_MORE_DOCS) {
break;
}
docFreq++;
docsSeen.set(docID);
int freq;
if (writeFreqs) {
freq = postingsEnum.freq();
totalTermFreq += freq;
} else {
freq = -1;
}
startDoc(docID, freq);
if (writePositions) {
for(int i=0;i<freq;i++) {
int pos = postingsEnum.nextPosition();
BytesRef payload = writePayloads ? postingsEnum.getPayload() : null;
int startOffset;
int endOffset;
if (writeOffsets) {
startOffset = postingsEnum.startOffset();
endOffset = postingsEnum.endOffset();
} else {
startOffset = -1;
endOffset = -1;
}
addPosition(pos, payload, startOffset, endOffset);
}
}
finishDoc();
}
if (docFreq == 0) {
return null;
} else {
BlockTermState state = newTermState();
state.docFreq = docFreq;
state.totalTermFreq = writeFreqs ? totalTermFreq : -1;
finishTerm(state);
return state;
}
}startTerm设置.doc、.pos和.pay三个文件的指针。postings函数创建FreqProxPostingsEnum或者FreqProxDocsEnum，内部封装了FreqProxTermsWriterPerField，即第五章中每个PerField的termsHashPerField成员变量，termsHashPerField的内部保存了对应Field的所有Terms信息。
writeTerm函数接下来通过nextDoc获得下一个文档ID，获得freq词频，并累加到totalTermFreq（总词频）中。再调用startDoc记录文档的信息。addPosition函数记录词的位置、偏移和payload信息，必要时写入文件中。finishDoc记录文件指针等信息。然后创建BlockTermState，设置相应词频和文档频信息以最终返回。
writeTerm函数最后通过finishTerm写入文档信息至.doc文件，写入位置信息至.pos文件。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm
private void pushTerm(BytesRef text) throws IOException {
int limit = Math.min(lastTerm.length(), text.length);
int pos = 0;
while (pos < limit && lastTerm.byteAt(pos) == text.bytes[text.offset+pos]) {
pos++;
}
for(int i=lastTerm.length()-1;i>=pos;i--) {
int prefixTopSize = pending.size() - prefixStarts[i];
if (prefixTopSize >= minItemsInBlock) {
writeBlocks(i+1, prefixTopSize);
prefixStarts[i] -= prefixTopSize-1;
}
}
if (prefixStarts.length < text.length) {
prefixStarts = ArrayUtil.grow(prefixStarts, text.length);
}
for(int i=pos;i<text.length;i++) {
prefixStarts[i] = pending.size();
}
lastTerm.copyBytes(text);
}lastTerm保存了上一次处理的Term。pushTerm函数的核心功能是计算一定的条件，当满足一定条件时，就表示pending列表中待处理的一个或者多个Term，需要保存为一个block，此时调用writeBlocks函数进行保存。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks
void writeBlocks(int prefixLength, int count) throws IOException {
int lastSuffixLeadLabel = -1;
boolean hasTerms = false;
boolean hasPrefixTerms = false;
boolean hasSubBlocks = false;
int start = pending.size()-count;
int end = pending.size();
int nextBlockStart = start;
int nextFloorLeadLabel = -1;
for (int i=start; i<end; i++) {
PendingEntry ent = pending.get(i);
int suffixLeadLabel;
if (ent.isTerm) {
PendingTerm term = (PendingTerm) ent;
if (term.termBytes.length == prefixLength) {
suffixLeadLabel = -1;
} else {
suffixLeadLabel = term.termBytes[prefixLength] & 0xff;
}
} else {
PendingBlock block = (PendingBlock) ent;
suffixLeadLabel = block.prefix.bytes[block.prefix.offset + prefixLength] & 0xff;
}
if (suffixLeadLabel != lastSuffixLeadLabel) {
int itemsInBlock = i - nextBlockStart;
if (itemsInBlock >= minItemsInBlock && end-nextBlockStart > maxItemsInBlock) {
boolean isFloor = itemsInBlock < count;
newBlocks.add(writeBlock(prefixLength, isFloor, nextFloorLeadLabel, nextBlockStart, i, hasTerms, hasPrefixTerms, hasSubBlocks));
hasTerms = false;
hasSubBlocks = false;
hasPrefixTerms = false;
nextFloorLeadLabel = suffixLeadLabel;
nextBlockStart = i;
}
lastSuffixLeadLabel = suffixLeadLabel;
}
if (ent.isTerm) {
hasTerms = true;
hasPrefixTerms |= ((PendingTerm) ent).prefixTerm != null;
} else {
hasSubBlocks = true;
}
}
if (nextBlockStart < end) {
int itemsInBlock = end - nextBlockStart;
boolean isFloor = itemsInBlock < count;
newBlocks.add(writeBlock(prefixLength, isFloor, nextFloorLeadLabel, nextBlockStart, end, hasTerms, hasPrefixTerms, hasSubBlocks));
}
PendingBlock firstBlock = newBlocks.get(0);
firstBlock.compileIndex(newBlocks, scratchBytes, scratchIntsRef);
pending.subList(pending.size()-count, pending.size()).clear();
pending.add(firstBlock);
newBlocks.clear();
}hasTerms表示将要合并的项中是否含有Term（因为特殊情况下，合并的项只有子block）。
hasPrefixTerms表示是否有词的前缀，假设一直为false。
hasSubBlocks和hasTerms对应，表示将要合并的项中是否含有子block。
start和end的规定了需要合并的Term或Block在待处理的pending列表中的范围。
writeBlocks函数接下来遍历pending列表中每个待处理的Term或者Block，suffixLeadLabel保存了树中某个节点下的各个Term的byte，lastSuffixLeadLabel则是对应的最后一个不同的byte，检查所有项中是否有Term和子block，并对hasTerms和hasSubBlocks进行相应的设置。如果pending中的Term或block太多，大于minItemsInBlock和maxItemsInBlock计算出来的阈值，就会调用writeBlock写成一个block，最后也会写一次。
writeBlocks函数接下来通过compileIndex函数将一个block的信息写入FST结构中（保存在其成员变量index中），FST是有限状态机的缩写，其实就是将一棵树的信息保存在其自身的结构中，而这颗树是由所有Term的每个byte形成的，后面来看。
writeBlocks函数最后清空被保存的一部分pending列表，并添加刚刚创建的block到pending列表中。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->writeBlock
第一种情况
private PendingBlock writeBlock(int prefixLength, boolean isFloor, int floorLeadLabel, int start, int end, boolean hasTerms, boolean hasPrefixTerms, boolean hasSubBlocks) throws IOException {
long startFP = termsOut.getFilePointer();
boolean hasFloorLeadLabel = isFloor && floorLeadLabel != -1;
final BytesRef prefix = new BytesRef(prefixLength + (hasFloorLeadLabel ? 1 : 0));
System.arraycopy(lastTerm.get().bytes, 0, prefix.bytes, 0, prefixLength);
prefix.length = prefixLength;
int numEntries = end - start;
int code = numEntries << 1;
if (end == pending.size()) {
code |= 1;
}
termsOut.writeVInt(code);
boolean isLeafBlock = hasSubBlocks == false && hasPrefixTerms == false;
final List<FST<BytesRef>> subIndices;
boolean absolute = true;
if (isLeafBlock) {
subIndices = null;
for (int i=start;i<end;i++) {
PendingEntry ent = pending.get(i);
PendingTerm term = (PendingTerm) ent;
BlockTermState state = term.state;
final int suffix = term.termBytes.length - prefixLength;
suffixWriter.writeVInt(suffix);
suffixWriter.writeBytes(term.termBytes, prefixLength, suffix);
statsWriter.writeVInt(state.docFreq);
if (fieldInfo.getIndexOptions() != IndexOptions.DOCS) {
statsWriter.writeVLong(state.totalTermFreq - state.docFreq);
}
postingsWriter.encodeTerm(longs, bytesWriter, fieldInfo, state, absolute);
for (int pos = 0; pos < longsSize; pos++) {
metaWriter.writeVLong(longs[pos]);
}
bytesWriter.writeTo(metaWriter);
bytesWriter.reset();
absolute = false;
}
} else {
...
}
termsOut.writeVInt((int) (suffixWriter.getFilePointer() << 1) | (isLeafBlock ? 1:0));
suffixWriter.writeTo(termsOut);
suffixWriter.reset();
termsOut.writeVInt((int) statsWriter.getFilePointer());
statsWriter.writeTo(termsOut);
statsWriter.reset();
termsOut.writeVInt((int) metaWriter.getFilePointer());
metaWriter.writeTo(termsOut);
metaWriter.reset();
if (hasFloorLeadLabel) {
prefix.bytes[prefix.length++] = (byte) floorLeadLabel;
}
return new PendingBlock(prefix, startFP, hasTerms, isFloor, floorLeadLabel, subIndices);
}termsOut封装了.tim文件的输出流，其实是FSIndexOutput，其getFilePointer函数返回的startFP保存了该文件可以插入的指针。
writeBlock函数首先提取相同的前缀，例如需要写为一个block的Term有aaa，aab，aac，则相同的前缀为aa，保存在类型为BytesRef的prefix中，BytesRef用于封装一个byte数组。
numEntries保存了本次需要写入多少个Term或者Block，code封装了numEntries的信息，并在最后一个bit表示后面是否还有。然后将code写入.tim文件中。
isLeafBlock表示是否是叶子节点。bytesWriter、suffixWriter、statsWriter、metaWriter在内存中模拟文件。
writeBlock函数接下来遍历需要写入的Term或者Block，suffix表示最后取出的不同字幕的长度，例如aaa，aab，aac则suffix为1，首先写入该长度suffix，最终写入suffixWriter中的为a、b、c。再往下往statsWriter中写入词频和文档频率。
再往下postingsWriter是Lucene50PostingsWriter，encodeTerm函数在longs中保存了.doc、.pos和.pay中文件指针的偏移，然后singletonDocID、lastPosBlockOffset、skipOffset等信息保存在bytesWriter中，再将longs的指针写入metaWriter中，最后把其余信息写入bytesWriter中。
再往下调用bytesWriter、suffixWriter、statsWriter、metaWriter的writeTo函数将内存中的数据写入.tim文件中。
writeBlock函数最后创建PendingBlock并返回，PendingBlock封装了本次写入的各个Term或者子Block的信息。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->writeBlock
第二种情况
private PendingBlock writeBlock(int prefixLength, boolean isFloor, int floorLeadLabel, int start, int end, boolean hasTerms, boolean hasPrefixTerms, boolean hasSubBlocks) throws IOException {
long startFP = termsOut.getFilePointer();
boolean hasFloorLeadLabel = isFloor && floorLeadLabel != -1;
final BytesRef prefix = new BytesRef(prefixLength + (hasFloorLeadLabel ? 1 : 0));
System.arraycopy(lastTerm.get().bytes, 0, prefix.bytes, 0, prefixLength);
prefix.length = prefixLength;
int numEntries = end - start;
int code = numEntries << 1;
if (end == pending.size()) {
code |= 1;
}
termsOut.writeVInt(code);
boolean isLeafBlock = hasSubBlocks == false && hasPrefixTerms == false;
final List<FST<BytesRef>> subIndices;
boolean absolute = true;
if (isLeafBlock) {
...
} else {
subIndices = new ArrayList<>();
boolean sawAutoPrefixTerm = false;
for (int i=start;i<end;i++) {
PendingEntry ent = pending.get(i);
if (ent.isTerm) {
PendingTerm term = (PendingTerm) ent;
BlockTermState state = term.state;
final int suffix = term.termBytes.length - prefixLength;
if (minItemsInAutoPrefix == 0) {
suffixWriter.writeVInt(suffix << 1);
suffixWriter.writeBytes(term.termBytes, prefixLength, suffix);
} else {
code = suffix<<2;
int floorLeadEnd = -1;
if (term.prefixTerm != null) {
sawAutoPrefixTerm = true;
PrefixTerm prefixTerm = term.prefixTerm;
floorLeadEnd = prefixTerm.floorLeadEnd;
if (prefixTerm.floorLeadStart == -2) {
code |= 2;
} else {
code |= 3;
}
}
suffixWriter.writeVInt(code);
suffixWriter.writeBytes(term.termBytes, prefixLength, suffix);
if (floorLeadEnd != -1) {
suffixWriter.writeByte((byte) floorLeadEnd);
}
}
statsWriter.writeVInt(state.docFreq);
if (fieldInfo.getIndexOptions() != IndexOptions.DOCS) {
statsWriter.writeVLong(state.totalTermFreq - state.docFreq);
}
postingsWriter.encodeTerm(longs, bytesWriter, fieldInfo, state, absolute);
for (int pos = 0; pos < longsSize; pos++) {
metaWriter.writeVLong(longs[pos]);
}
bytesWriter.writeTo(metaWriter);
bytesWriter.reset();
absolute = false;
} else {
PendingBlock block = (PendingBlock) ent;
final int suffix = block.prefix.length - prefixLength;
if (minItemsInAutoPrefix == 0) {
suffixWriter.writeVInt((suffix<<1)|1);
} else {
suffixWriter.writeVInt((suffix<<2)|1);
}
suffixWriter.writeBytes(block.prefix.bytes, prefixLength, suffix);
suffixWriter.writeVLong(startFP - block.fp);
subIndices.add(block.index);
}
}
}
termsOut.writeVInt((int) (suffixWriter.getFilePointer() << 1) | (isLeafBlock ? 1:0));
suffixWriter.writeTo(termsOut);
suffixWriter.reset();
termsOut.writeVInt((int) statsWriter.getFilePointer());
statsWriter.writeTo(termsOut);
statsWriter.reset();
termsOut.writeVInt((int) metaWriter.getFilePointer());
metaWriter.writeTo(termsOut);
metaWriter.reset();
if (hasFloorLeadLabel) {
prefix.bytes[prefix.length++] = (byte) floorLeadLabel;
}
return new PendingBlock(prefix, startFP, hasTerms, isFloor, floorLeadLabel, subIndices);
}第二种情况表示要写入的不是叶子节点，如果是Term，和第一部分一样，如果是一个子block，写入子block的相应信息，最后创建的PendingBlock需要封装每个Block对应的FST结构，即subIndices。
writeBlocks函数调用完writeBlock函数后将pending列表中的Term或者Block写入.tim文件中，接下来要通过PendingBlock的compileIndex函数针对刚刚写入.tim文件中的Term创建索引信息，最后要将这些信息写入.tip文件中，用于查找。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex
public void compileIndex(List<PendingBlock> blocks, RAMOutputStream scratchBytes, IntsRefBuilder scratchIntsRef) throws IOException {
scratchBytes.writeVLong(encodeOutput(fp, hasTerms, isFloor));
if (isFloor) {
scratchBytes.writeVInt(blocks.size()-1);
for (int i=1;i<blocks.size();i++) {
PendingBlock sub = blocks.get(i);
scratchBytes.writeByte((byte) sub.floorLeadByte);
scratchBytes.writeVLong((sub.fp - fp) << 1 | (sub.hasTerms ? 1 : 0));
}
}
final ByteSequenceOutputs outputs = ByteSequenceOutputs.getSingleton();
final Builder<BytesRef> indexBuilder = new Builder<>(FST.INPUT_TYPE.BYTE1,
0, 0, true, false, Integer.MAX_VALUE,
outputs, false,
PackedInts.COMPACT, true, 15);
final byte[] bytes = new byte[(int) scratchBytes.getFilePointer()];
scratchBytes.writeTo(bytes, 0);
indexBuilder.add(Util.toIntsRef(prefix, scratchIntsRef), new BytesRef(bytes, 0, bytes.length));
scratchBytes.reset();
for(PendingBlock block : blocks) {
if (block.subIndices != null) {
for(FST<BytesRef> subIndex : block.subIndices) {
append(indexBuilder, subIndex, scratchIntsRef);
}
block.subIndices = null;
}
}
index = indexBuilder.finish();
}fp是对应.tim文件的指针，encodeOutput函数将fp、hasTerms和isFloor信息封装到一个长整型中，然后将该长整型存入scratchBytes中。compileIndex函数接下来创建Builder，用于构造索引树，再往下将scratchBytes中的数据存入byte数组bytes中。
compileIndex最核心的部分是通过Builder的add函数依次将Term或者Term的部分前缀添加到一颗树中，由frontier数组维护，进而添加到FST中。compileIndex最后通过Builder的finish函数将add添加后的FST树中的信息写入缓存中，后续添加到.tip文件里。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::Builder
public Builder(FST.INPUT_TYPE inputType, int minSuffixCount1, int minSuffixCount2, boolean doShareSuffix, boolean doShareNonSingletonNodes, int shareMaxTailLength, Outputs<T> outputs, boolean doPackFST, float acceptableOverheadRatio, boolean allowArrayArcs, int bytesPageBits) {
this.minSuffixCount1 = minSuffixCount1;
this.minSuffixCount2 = minSuffixCount2;
this.doShareNonSingletonNodes = doShareNonSingletonNodes;
this.shareMaxTailLength = shareMaxTailLength;
this.doPackFST = doPackFST;
this.acceptableOverheadRatio = acceptableOverheadRatio;
this.allowArrayArcs = allowArrayArcs;
fst = new FST<>(inputType, outputs, doPackFST, acceptableOverheadRatio, bytesPageBits);
bytes = fst.bytes;
if (doShareSuffix) {
dedupHash = new NodeHash<>(fst, bytes.getReverseReader(false));
} else {
dedupHash = null;
}
NO_OUTPUT = outputs.getNoOutput();
final UnCompiledNode<T>[] f = (UnCompiledNode<T>[]) new UnCompiledNode[10];
frontier = f;
for(int idx=0;idx<frontier.length;idx++) {
frontier[idx] = new UnCompiledNode<>(this, idx);
}
}Builder的构造函数主要是创建了一个FST，并初始化frontier数组，frontier数组中的每个元素UnCompiledNode代表树中的每个节点。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::add
public void add(IntsRef input, T output) throws IOException {
...
int pos1 = 0;
int pos2 = input.offset;
final int pos1Stop = Math.min(lastInput.length(), input.length);
while(true) {
frontier[pos1].inputCount++;
if (pos1 >= pos1Stop || lastInput.intAt(pos1) != input.ints[pos2]) {
break;
}
pos1++;
pos2++;
}
final int prefixLenPlus1 = pos1+1;
if (frontier.length < input.length+1) {
final UnCompiledNode<T>[] next = ArrayUtil.grow(frontier, input.length+1);
for(int idx=frontier.length;idx<next.length;idx++) {
next[idx] = new UnCompiledNode<>(this, idx);
}
frontier = next;
}
freezeTail(prefixLenPlus1);
for(int idx=prefixLenPlus1;idx<=input.length;idx++) {
frontier[idx-1].addArc(input.ints[input.offset + idx - 1],
frontier[idx]);
frontier[idx].inputCount++;
}
final UnCompiledNode<T> lastNode = frontier[input.length];
if (lastInput.length() != input.length || prefixLenPlus1 != input.length + 1) {
lastNode.isFinal = true;
lastNode.output = NO_OUTPUT;
}
for(int idx=1;idx<prefixLenPlus1;idx++) {
final UnCompiledNode<T> node = frontier[idx];
final UnCompiledNode<T> parentNode = frontier[idx-1];
final T lastOutput = parentNode.getLastOutput(input.ints[input.offset + idx - 1]);
final T commonOutputPrefix;
final T wordSuffix;
if (lastOutput != NO_OUTPUT) {
commonOutputPrefix = fst.outputs.common(output, lastOutput);
wordSuffix = fst.outputs.subtract(lastOutput, commonOutputPrefix);
parentNode.setLastOutput(input.ints[input.offset + idx - 1], commonOutputPrefix);
node.prependOutput(wordSuffix);
} else {
commonOutputPrefix = wordSuffix = NO_OUTPUT;
}
output = fst.outputs.subtract(output, commonOutputPrefix);
}
if (lastInput.length() == input.length && prefixLenPlus1 == 1+input.length) {
lastNode.output = fst.outputs.merge(lastNode.output, output);
} else {
frontier[prefixLenPlus1-1].setLastOutput(input.ints[input.offset + prefixLenPlus1-1], output);
}
lastInput.copyInts(input);
}add函数首先计算和上一个字符串的共同前缀，prefixLenPlus1表示FST数中的相同前缀的长度，如果存在，后面就需要进行相应的合并。接下来通过for循环调用addArc函数依次添加input即Term中的每个byte至frontier中，形成一个FST树，由frontier数组维护，然后设置frontier数组中的最后一个UnCompiledNode，将isFinal标志位设为true。add函数最后将output中的数据（文件指针等信息）存入本次frontier数组中最前面的一个UnCompiledNode中，并设置lastInput为本次的input。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::add->freezeTail
private void freezeTail(int prefixLenPlus1) throws IOException {
final int downTo = Math.max(1, prefixLenPlus1);
for(int idx=lastInput.length(); idx >= downTo; idx--) {
boolean doPrune = false;
boolean doCompile = false;
final UnCompiledNode<T> node = frontier[idx];
final UnCompiledNode<T> parent = frontier[idx-1];
if (node.inputCount < minSuffixCount1) {
doPrune = true;
doCompile = true;
} else if (idx > prefixLenPlus1) {
if (parent.inputCount < minSuffixCount2 || (minSuffixCount2 == 1 && parent.inputCount == 1 && idx > 1)) {
doPrune = true;
} else {
doPrune = false;
}
doCompile = true;
} else {
doCompile = minSuffixCount2 == 0;
}
if (node.inputCount < minSuffixCount2 || (minSuffixCount2 == 1 && node.inputCount == 1 && idx > 1)) {
for(int arcIdx=0;arcIdx<node.numArcs;arcIdx++) {
final UnCompiledNode<T> target = (UnCompiledNode<T>) node.arcs[arcIdx].target;
target.clear();
}
node.numArcs = 0;
}
if (doPrune) {
node.clear();
parent.deleteLast(lastInput.intAt(idx-1), node);
} else {
if (minSuffixCount2 != 0) {
compileAllTargets(node, lastInput.length()-idx);
}
final T nextFinalOutput = node.output;
final boolean isFinal = node.isFinal || node.numArcs == 0;
if (doCompile) {
parent.replaceLast(lastInput.intAt(idx-1),
compileNode(node, 1+lastInput.length()-idx),
nextFinalOutput,
isFinal);
} else {
parent.replaceLast(lastInput.intAt(idx-1),
node,
nextFinalOutput,
isFinal);
frontier[idx] = new UnCompiledNode<>(this, idx);
}
}
}
}freezeTail函数的核心功能是将不会再变化的节点通过compileNode函数添加到FST结构中。
replaceLast函数设置父节点对应的参数，例如其子节点在bytes中的位置target，是否为最后一个节点isFinal等等。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::add->freezeTail->compileNode
private CompiledNode compileNode(UnCompiledNode<T> nodeIn, int tailLength) throws IOException {
final long node;
long bytesPosStart = bytes.getPosition();
if (dedupHash != null && (doShareNonSingletonNodes || nodeIn.numArcs <= 1) && tailLength <= shareMaxTailLength) {
if (nodeIn.numArcs == 0) {
node = fst.addNode(this, nodeIn);
lastFrozenNode = node;
} else {
node = dedupHash.add(this, nodeIn);
}
} else {
node = fst.addNode(this, nodeIn);
}
long bytesPosEnd = bytes.getPosition();
if (bytesPosEnd != bytesPosStart) {
lastFrozenNode = node;
}
nodeIn.clear();
final CompiledNode fn = new CompiledNode();
fn.node = node;
return fn;
}compileNode的核心部分是调用FST的addNode函数添加节点。dedupHash是一个hash缓存，这里不管它。如果bytesPosEnd不等于bytesPosStart，表示有节点写入bytes中了，设置lastFrozenNode为当前node（其实是bytes中的缓存指针位置）。compileNode函数最后创建CompiledNode，设置其中的node并返回。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::add->freezeTail->compileNode->FST::addNode
long addNode(Builder<T> builder, Builder.UnCompiledNode<T> nodeIn) throws IOException {
T NO_OUTPUT = outputs.getNoOutput();
if (nodeIn.numArcs == 0) {
if (nodeIn.isFinal) {
return FINAL_END_NODE;
} else {
return NON_FINAL_END_NODE;
}
}
final long startAddress = builder.bytes.getPosition();
final boolean doFixedArray = shouldExpand(builder, nodeIn);
if (doFixedArray) {
if (builder.reusedBytesPerArc.length < nodeIn.numArcs) {
builder.reusedBytesPerArc = new int[ArrayUtil.oversize(nodeIn.numArcs, 1)];
}
}
builder.arcCount += nodeIn.numArcs;
final int lastArc = nodeIn.numArcs-1;
long lastArcStart = builder.bytes.getPosition();
int maxBytesPerArc = 0;
for(int arcIdx=0;arcIdx<nodeIn.numArcs;arcIdx++) {
final Builder.Arc<T> arc = nodeIn.arcs[arcIdx];
final Builder.CompiledNode target = (Builder.CompiledNode) arc.target;
int flags = 0;
if (arcIdx == lastArc) {
flags += BIT_LAST_ARC;
}
if (builder.lastFrozenNode == target.node && !doFixedArray) {
flags += BIT_TARGET_NEXT;
}
if (arc.isFinal) {
flags += BIT_FINAL_ARC;
if (arc.nextFinalOutput != NO_OUTPUT) {
flags += BIT_ARC_HAS_FINAL_OUTPUT;
}
} else {
}
boolean targetHasArcs = target.node > 0;
if (!targetHasArcs) {
flags += BIT_STOP_NODE;
} else if (inCounts != null) {
inCounts.set((int) target.node, inCounts.get((int) target.node) + 1);
}
if (arc.output != NO_OUTPUT) {
flags += BIT_ARC_HAS_OUTPUT;
}
builder.bytes.writeByte((byte) flags);
writeLabel(builder.bytes, arc.label);
if (arc.output != NO_OUTPUT) {
outputs.write(arc.output, builder.bytes);
}
if (arc.nextFinalOutput != NO_OUTPUT) {
outputs.writeFinalOutput(arc.nextFinalOutput, builder.bytes);
}
if (targetHasArcs && (flags & BIT_TARGET_NEXT) == 0) {
builder.bytes.writeVLong(target.node);
}
}
final long thisNodeAddress = builder.bytes.getPosition()-1;
builder.bytes.reverse(startAddress, thisNodeAddress);
builder.nodeCount++;
final long node;
node = thisNodeAddress;
return node;
}首先判断如果是最后的节点，直接返回。接下来累加numArcs至arcCount中，统计节点arc个数。addNode函数接下来计算并设置标志位flags，然后将flags和label写入bytes中，label就是Term中的某个字母或者byte。addNode函数最后返回bytes即BytesStore中的位置。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::add->freezeTail->compileNode->NodeHash::addNode
public long add(Builder<T> builder, Builder.UnCompiledNode<T> nodeIn) throws IOException {
final long h = hash(nodeIn);
long pos = h & mask;
int c = 0;
while(true) {
final long v = table.get(pos);
if (v == 0) {
final long node = fst.addNode(builder, nodeIn);
count++;
table.set(pos, node);
if (count > 2*table.size()/3) {
rehash();
}
return node;
} else if (nodesEqual(nodeIn, v)) {
return v;
}
pos = (pos + (++c)) & mask;
}
}dedupHash的add函数首先通过hash函数获得该node的hash值，遍历node内的每个arc，计算hash值。
该函数内部也是使用了FST的addNode函数添加节点，并在必要的时候通过rehash扩展hash数组。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::add->UnCompiledNode::addArc
public void addArc(int label, Node target) {
if (numArcs == arcs.length) {
final Arc<T>[] newArcs = ArrayUtil.grow(arcs, numArcs+1);
for(int arcIdx=numArcs;arcIdx<newArcs.length;arcIdx++) {
newArcs[arcIdx] = new Arc<>();
}
arcs = newArcs;
}
final Arc<T> arc = arcs[numArcs++];
arc.label = label;
arc.target = target;
arc.output = arc.nextFinalOutput = owner.NO_OUTPUT;
arc.isFinal = false;
}addArc用来将一个Term里的字母或者byte添加到该节点UnCompiledNode的arcs数组中，开头的if语句用来扩充arcs数组，然后按照顺序获取arcs数组中的Arc，并存入label，传入的参数target指向下一个UnCompiledNode节点。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::finish
public FST<T> finish() throws IOException {
final UnCompiledNode<T> root = frontier[0];
freezeTail(0);
if (root.inputCount < minSuffixCount1 || root.inputCount < minSuffixCount2 || root.numArcs == 0) {
if (fst.emptyOutput == null) {
return null;
} else if (minSuffixCount1 > 0 || minSuffixCount2 > 0) {
return null;
}
} else {
if (minSuffixCount2 != 0) {
compileAllTargets(root, lastInput.length());
}
}
fst.finish(compileNode(root, lastInput.length()).node);
if (doPackFST) {
return fst.pack(this, 3, Math.max(10, (int) (getNodeCount()/4)), acceptableOverheadRatio);
} else {
return fst;
}
}finish函数开头的freezeTail函数传入的参数0，代表要处理frontier数组维护的所有节点，compileNode函数最后向bytes中写入根节点。最后的finish函数将FST的信息缓存到成员变量blocks中去，blocks是一个byte数组列表。
BlockTreeTermsWriter::write->TermsWriter::write->pushTerm->writeBlocks->PendingBlock::compileIndex->Builder::finish->FST::finish
void finish(long newStartNode) throws IOException {
startNode = newStartNode;
bytes.finish();
cacheRootArcs();
}
public void finish() {
if (current != null) {
byte[] lastBuffer = new byte[nextWrite];
System.arraycopy(current, 0, lastBuffer, 0, nextWrite);
blocks.set(blocks.size()-1, lastBuffer);
current = null;
}
}回到BlockTreeTermsWriter的write函数中，接下来通过TermsWriter的finish函数将FST中的信息写入.tip文件中。
BlockTreeTermsWriter::write->TermsWriter::write->finish
public void finish() throws IOException {
if (numTerms > 0) {
pushTerm(new BytesRef());
pushTerm(new BytesRef());
writeBlocks(0, pending.size());
final PendingBlock root = (PendingBlock) pending.get(0);
indexStartFP = indexOut.getFilePointer();
root.index.save(indexOut);
BytesRef minTerm = new BytesRef(firstPendingTerm.termBytes);
BytesRef maxTerm = new BytesRef(lastPendingTerm.termBytes);
fields.add(new FieldMetaData(fieldInfo,
((PendingBlock) pending.get(0)).index.getEmptyOutput(),
numTerms,
indexStartFP,
sumTotalTermFreq,
sumDocFreq,
docsSeen.cardinality(),
longsSize,
minTerm, maxTerm));
} else {
}
}root.index.save(indexOut)就是将信息写入.tip文件中。
总结
总接一下本章的大体流程。
BlockTreeTermWrite的调用TermsWriter的write函数处理每个域中的每个Term，然后通过finish函数将信息写入.tip文件。
TermsWriter的write函数针对每个Term，调用pushTerm函数将Term的信息写入.tim文件和FST中，然后将每个Term添加到待处理列表pending中。
pushTerm函数通过计算选择适当的时候调用writeBlocks函数将pending中多个Term写成一个Block。
writeBlocks在pending列表中选择相应的Term或者子Block，然后调用writeBlock函数写入相应的信息，然后调用compileIndex函数建立索引，最后删除在pending列表中已被处理的Term或者Block。
writeBlock函数向各个文件.doc、.pos和.pay写入对应Term或者Block的信息。
compileIndex函数通过Builder的add函数添加节点（每个Term的每个字母或者byte）到frontier数组中，frontier数组维护了UnCompiledNode节点，构成一棵树，compileIndex内部通过freezeTail函数将树中不会变动的节点通过compileNode函数写入FST结构中。
BlockTreeTermWrite最后在finish函数中将FST中的信息写入.tip文件中
