Restrict GraphTokenStreamFiniteStrings#articulationPointsRecurse recu…

…rsion depth (#12249)
apache · Jun 12, 2023 · 41baf23 · 41baf23
1 parent ef35e6e
commit 41baf23
Show file tree

Hide file tree

Showing 3 changed files with 34 additions and 1 deletion.
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
@@ -190,6 +190,8 @@ Bug Fixes
 * GITHUB#12352: [Tessellator] Improve the checks that validate the diagonal between two polygon nodes so
   the resulting polygons are valid counter clockwise polygons. (Ignacio Vera)
 
+* LUCENE-10181: Restrict GraphTokenStreamFiniteStrings#articulationPointsRecurse recursion depth. (Chris Fournier)
+
 Other
 ---------------------
 (No changes)

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
@@ -45,6 +45,8 @@
  * 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 AttributeSource[] tokens = new AttributeSource[4];
   private final Automaton det;
@@ -271,7 +273,12 @@ private static void articulationPointsRecurse(
       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.TokenStream;
 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
@@ -660,4 +661,27 @@ public void testMultipleSidePathsWithGaps() throws Exception {
         it.next(), new String[] {"king", "alfred", "saxons", "ruled"}, new int[] {1, 1, 3, 1});
     assertFalse(it.hasNext());
   }
+
+  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);
+  }
 }