Github user mikemccand commented on a diff in the pull request:
https://github.com/apache/lucene-solr/pull/129#discussion_r94217475
--- Diff:
lucene/core/src/java/org/apache/lucene/util/graph/GraphTokenStreamFiniteStrings.java
---
@@ -0,0 +1,237 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.lucene.util.graph;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.BytesTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
+import
org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute;
+import org.apache.lucene.analysis.tokenattributes.TermToBytesRefAttribute;
+import org.apache.lucene.util.BytesRef;
+import org.apache.lucene.util.IntsRef;
+import org.apache.lucene.util.automaton.Automaton;
+import org.apache.lucene.util.automaton.FiniteStringsIterator;
+import org.apache.lucene.util.automaton.Operations;
+
+import static
org.apache.lucene.util.automaton.Operations.DEFAULT_MAX_DETERMINIZED_STATES;
+
+/**
+ * Creates a list of {@link TokenStream} where each stream is the tokens
that make up a finite string in graph token stream. To do this,
+ * the graph token stream is converted to an {@link Automaton} and from
there we use a {@link FiniteStringsIterator} to collect the various
+ * token streams for each finite string.
+ */
+public class GraphTokenStreamFiniteStrings {
+ /* TODO:
+ Most of this is a combination of code from TermAutomatonQuery and
TokenStreamToTermAutomatonQuery. Would be
+ good to make this so it could be shared. */
+ private final Automaton.Builder builder;
+ Automaton det;
+ private final Map<BytesRef, Integer> termToID = new HashMap<>();
+ private final Map<Integer, BytesRef> idToTerm = new HashMap<>();
+ private final Map<Integer, Integer> idToInc = new HashMap<>();
+
+ public GraphTokenStreamFiniteStrings() {
+ this.builder = new Automaton.Builder();
+ }
+
+ private static class BytesRefArrayTokenStream extends TokenStream {
+ private final BytesTermAttribute termAtt =
addAttribute(BytesTermAttribute.class);
+ private final PositionIncrementAttribute posIncAtt =
addAttribute(PositionIncrementAttribute.class);
+
+ private final BytesRef[] terms;
+ private final int[] increments;
+ private int offset;
+
+ BytesRefArrayTokenStream(BytesRef[] terms, int[] increments) {
+ this.terms = terms;
+ this.increments = increments;
+ assert terms.length == increments.length;
+ offset = 0;
+ }
+
+ @Override
+ public boolean incrementToken() throws IOException {
+ if (offset < terms.length) {
+ clearAttributes();
+ termAtt.setBytesRef(terms[offset]);
+ posIncAtt.setPositionIncrement(increments[offset]);
+ offset = offset + 1;
+ return true;
+ }
+
+ return false;
+ }
+ }
+
+ /**
+ * Gets the list of finite string token streams from the given input
graph token stream.
+ */
+ public List<TokenStream> getTokenStreams(final TokenStream in) throws
IOException {
+ // build automation
+ build(in);
+
+ List<TokenStream> tokenStreams = new ArrayList<>();
+ final FiniteStringsIterator finiteStrings = new
FiniteStringsIterator(det);
+ for (IntsRef string; (string = finiteStrings.next()) != null; ) {
+ final BytesRef[] tokens = new BytesRef[string.length];
+ final int[] increments = new int[string.length];
+ for (int idx = string.offset, len = string.offset + string.length;
idx < len; idx++) {
+ int id = string.ints[idx];
+ int offset = idx - string.offset;
+ tokens[offset] = idToTerm.get(id);
+ if (idToInc.containsKey(id)) {
+ increments[offset] = idToInc.get(id);
+ } else {
+ increments[offset] = 1;
+ }
+ }
+
+ tokenStreams.add(new BytesRefArrayTokenStream(tokens, increments));
+ }
+
+ return tokenStreams;
+ }
+
+ private void build(final TokenStream in) throws IOException {
+ if (det != null) {
+ throw new IllegalStateException("Automation already built");
+ }
+
+ final TermToBytesRefAttribute termBytesAtt =
in.addAttribute(TermToBytesRefAttribute.class);
+ final PositionIncrementAttribute posIncAtt =
in.addAttribute(PositionIncrementAttribute.class);
+ final PositionLengthAttribute posLengthAtt =
in.addAttribute(PositionLengthAttribute.class);
+ final OffsetAttribute offsetAtt =
in.addAttribute(OffsetAttribute.class);
+
+ in.reset();
+
+ int pos = -1;
+ int lastIncr = 1;
+ int maxOffset = 0;
+ int maxPos = -1;
+ int state = -1;
+ while (in.incrementToken()) {
+ int posInc = posIncAtt.getPositionIncrement();
+
+ // always use inc 1 while building, but save original increment
+ int fakePosInc = posInc > 1 ? 1 : posInc;
+
+ assert pos > -1 || fakePosInc > 0;
--- End diff --
Can we upgrade this to a real `if`? I.e. we need a well-formed
`TokenStream` input ... it cannot have `posInc=0` on its first token.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
