backport apache#12249

searchly · Sep 24, 2024 · 163b059 · 163b059
1 parent f2ed5d9
commit 163b059
Show file tree

Hide file tree

Showing 4 changed files with 45 additions and 5 deletions.
diff --git a/lucene/core/src/java/org/apache/lucene/util/graph/GraphTokenStreamFiniteStrings.java b/lucene/core/src/java/org/apache/lucene/util/graph/GraphTokenStreamFiniteStrings.java
@@ -48,6 +48,10 @@
  * This class also provides helpers to explore the different paths of the {@link Automaton}.
  */
 public final class GraphTokenStreamFiniteStrings {
+
+  /** Maximum level of recursion allowed in recursive operations. */
+  private static final int MAX_RECURSION_LEVEL = 1000;
+
   private final Map<Integer, BytesRef> idToTerm = new HashMap<>();
   private final Map<Integer, Integer> idToInc = new HashMap<>();
   private final Automaton det;
@@ -262,8 +266,15 @@ private int getTermID(int incr, int prevIncr, BytesRef term) {
     return id;
   }
 
-  private static void articulationPointsRecurse(Automaton a, int state, int d, int[] depth, int[] low, int[] parent,
-                                                BitSet visited, List<Integer> points) {
+  private static void articulationPointsRecurse(
+          Automaton a,
+          int state,
+          int d,
+          int[] depth,
+          int[] low,
+          int[] parent,
+          BitSet visited,
+          List<Integer> points) {
     visited.set(state);
     depth[state] = d;
     low[state] = d;
@@ -275,7 +286,12 @@ private static void articulationPointsRecurse(Automaton a, int state, int d, int
       a.getNextTransition(t);
       if (visited.get(t.dest) == false) {
         parent[t.dest] = state;
-        articulationPointsRecurse(a, t.dest, d + 1, depth, low, parent, visited, points);
+        if (d < MAX_RECURSION_LEVEL) {
+          articulationPointsRecurse(a, t.dest, d + 1, depth, low, parent, visited, points);
+        } else {
+          throw new IllegalArgumentException(
+                  "Exceeded maximum recursion level during graph analysis");
+        }
         childCount++;
         if (low[t.dest] >= depth[state]) {
           isArticulation = true;

diff --git a/lucene/core/src/test/org/apache/lucene/util/graph/TestGraphTokenStreamFiniteStrings.java b/lucene/core/src/test/org/apache/lucene/util/graph/TestGraphTokenStreamFiniteStrings.java
@@ -16,6 +16,7 @@
  */
 package org.apache.lucene.util.graph;
 
+import java.util.ArrayList;
 import java.util.Iterator;
 
 import org.apache.lucene.analysis.CannedTokenStream;
@@ -596,4 +597,27 @@ public void testMultipleSidePaths() throws Exception {
     terms = graph.getTerms("field", 7);
     assertArrayEquals(terms, new Term[] {new Term("field", "network")});
   }
+
+  public void testLongTokenStreamStackOverflowError() throws Exception {
+
+    ArrayList<Token> tokens =
+            new ArrayList<Token>() {
+              {
+                add(token("fast", 1, 1));
+                add(token("wi", 1, 1));
+                add(token("wifi", 0, 2));
+                add(token("fi", 1, 1));
+              }
+            };
+
+    // Add in too many tokens to get a high depth graph
+    for (int i = 0; i < 1024 + 1; i++) {
+      tokens.add(token("network", 1, 1));
+    }
+
+    TokenStream ts = new CannedTokenStream(tokens.toArray(new Token[0]));
+    GraphTokenStreamFiniteStrings graph = new GraphTokenStreamFiniteStrings(ts);
+
+    assertThrows(IllegalArgumentException.class, graph::articulationPoints);
+  }
 }
diff --git a/lucene/ivy-versions.properties b/lucene/ivy-versions.properties
@@ -82,7 +82,7 @@ io.prometheus.version = 0.2.0
 /javax.activation/activation = 1.1.1
 /javax.servlet/javax.servlet-api = 3.1.0
 /joda-time/joda-time = 2.2
-/junit/junit = 4.12
+/junit/junit = 4.13.2
 
 /mecab/mecab-ipadic = 2.7.0-20070801
 /mecab/mecab-ko-dic = 2.0.3-20170922

diff --git a/lucene/version.properties b/lucene/version.properties
@@ -2,7 +2,7 @@
 
 # RELEASE MANAGER must change this file after creating a release and
 # enter new base version (format "x.y.z", no prefix/appendix): 
-version.base=7.7.3
+version.base=7.7.3.1
 
 # Other version property defaults, don't change:
 version.suffix=SNAPSHOT