public bool NextDoc() { if (freq.Eof()) { if (p.lastDocCode != -1) { // Return last doc docID = p.lastDocID; if (!field.omitTermFreqAndPositions) { termFreq = p.docFreq; } p.lastDocCode = -1; return(true); } // EOF else { return(false); } } int code = freq.ReadVInt(); if (field.omitTermFreqAndPositions) { docID += code; } else { docID += Number.URShift(code, 1); if ((code & 1) != 0) { termFreq = 1; } else { termFreq = freq.ReadVInt(); } } System.Diagnostics.Debug.Assert(docID != p.lastDocID); return(true); }
/* Walk through all unique text tokens (Posting * instances) found in this field and serialize them * into a single RAM segment. */ internal void AppendPostings(FreqProxTermsWriterPerField[] fields, FormatPostingsFieldsConsumer consumer) { int numFields = fields.Length; FreqProxFieldMergeState[] mergeStates = new FreqProxFieldMergeState[numFields]; for (int i = 0; i < numFields; i++) { FreqProxFieldMergeState fms = mergeStates[i] = new FreqProxFieldMergeState(fields[i]); System.Diagnostics.Debug.Assert(fms.field.fieldInfo == fields [0].fieldInfo); // Should always be true bool result = fms.NextTerm(); System.Diagnostics.Debug.Assert(result); } FormatPostingsTermsConsumer termsConsumer = consumer.AddField(fields[0].fieldInfo); FreqProxFieldMergeState[] termStates = new FreqProxFieldMergeState[numFields]; bool currentFieldOmitTermFreqAndPositions = fields[0].fieldInfo.omitTermFreqAndPositions; while (numFields > 0) { // Get the next term to merge termStates[0] = mergeStates[0]; int numToMerge = 1; for (int i = 1; i < numFields; i++) { char[] text = mergeStates[i].text; int textOffset = mergeStates[i].textOffset; int cmp = compareText(text, textOffset, termStates[0].text, termStates[0].textOffset); if (cmp < 0) { termStates[0] = mergeStates[i]; numToMerge = 1; } else if (cmp == 0) { termStates[numToMerge++] = mergeStates[i]; } } FormatPostingsDocsConsumer docConsumer = termsConsumer.AddTerm(termStates[0].text, termStates[0].textOffset); // Now termStates has numToMerge FieldMergeStates // which all share the same term. Now we must // interleave the docID streams. while (numToMerge > 0) { FreqProxFieldMergeState minState = termStates[0]; for (int i = 1; i < numToMerge; i++) { if (termStates[i].docID < minState.docID) { minState = termStates[i]; } } int termDocFreq = minState.termFreq; FormatPostingsPositionsConsumer posConsumer = docConsumer.AddDoc(minState.docID, termDocFreq); ByteSliceReader prox = minState.prox; // Carefully copy over the prox + payload info, // changing the format to match Lucene's segment // format. if (!currentFieldOmitTermFreqAndPositions) { // omitTermFreqAndPositions == false so we do write positions & // payload int position = 0; for (int j = 0; j < termDocFreq; j++) { int code = prox.ReadVInt(); position += (code >> 1); int payloadLength; if ((code & 1) != 0) { // This position has a payload payloadLength = prox.ReadVInt(); if (payloadBuffer == null || payloadBuffer.Length < payloadLength) { payloadBuffer = new byte[payloadLength]; } prox.ReadBytes(payloadBuffer, 0, payloadLength); } else { payloadLength = 0; } posConsumer.AddPosition(position, payloadBuffer, 0, payloadLength); } //End for posConsumer.Finish(); } if (!minState.NextDoc()) { // Remove from termStates int upto = 0; for (int i = 0; i < numToMerge; i++) { if (termStates[i] != minState) { termStates[upto++] = termStates[i]; } } numToMerge--; System.Diagnostics.Debug.Assert(upto == numToMerge); // Advance this state to the next term if (!minState.NextTerm()) { // OK, no more terms, so remove from mergeStates // as well upto = 0; for (int i = 0; i < numFields; i++) { if (mergeStates[i] != minState) { mergeStates[upto++] = mergeStates[i]; } } numFields--; System.Diagnostics.Debug.Assert(upto == numFields); } } } docConsumer.Finish(); } termsConsumer.Finish(); }