HIVE-26713: StringExpr ArrayIndexOutOfBoundsException with LIKE '%xxx%'

ql/src/test/queries/clientpositive/like_control_characters.q

@@ -0,0 +1,15 @@
+set hive.mapred.mode=nonstrict;
+set hive.explain.user=false;
+set hive.vectorized.execution.enabled=true;
+
+create temporary table foo (col string) stored as orc;
+create temporary table bar (col binary) stored as orc;
+
+-- SORT_QUERY_RESULTS
+
+INSERT INTO bar select unhex('6162636465-166676869');
+INSERT INTO foo SELECT col FROM bar;
+
+explain select col, count(*) from foo where col like '%fg%' group by col;
+select col, count(*) from foo where col like '%fg%' group by col;
+

ql/src/test/results/clientpositive/llap/like_control_characters.q.out

@@ -0,0 +1,111 @@
+PREHOOK: query: create temporary table foo (col string) stored as orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@foo
+POSTHOOK: query: create temporary table foo (col string) stored as orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@foo
+PREHOOK: query: create temporary table bar (col binary) stored as orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@bar
+POSTHOOK: query: create temporary table bar (col binary) stored as orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@bar
+PREHOOK: query: INSERT INTO bar select unhex('6162636465-166676869')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@bar
+POSTHOOK: query: INSERT INTO bar select unhex('6162636465-166676869')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@bar
+POSTHOOK: Lineage: bar.col SIMPLE []
+PREHOOK: query: INSERT INTO foo SELECT col FROM bar
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bar
+PREHOOK: Output: default@foo
+POSTHOOK: query: INSERT INTO foo SELECT col FROM bar
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bar
+POSTHOOK: Output: default@foo
+POSTHOOK: Lineage: foo.col EXPRESSION [(bar)bar.FieldSchema(name:col, type:binary, comment:null), ]
+PREHOOK: query: explain select col, count(*) from foo where col like '%fg%' group by col
+PREHOOK: type: QUERY
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: explain select col, count(*) from foo where col like '%fg%' group by col
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: foo
+                  filterExpr: (col like '%fg%') (type: boolean)
+                  Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (col like '%fg%') (type: boolean)
+                    Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                    Group By Operator
+                      aggregations: count()
+                      keys: col (type: string)
+                      minReductionHashAggr: 0.99
+                      mode: hash
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: z
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: bigint)
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+        Reducer 2 
+            Execution mode: vectorized, llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: select col, count(*) from foo where col like '%fg%' group by col
+PREHOOK: type: QUERY
+PREHOOK: Input: default@foo
+#### A masked pattern was here ####
+POSTHOOK: query: select col, count(*) from foo where col like '%fg%' group by col
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@foo
+#### A masked pattern was here ####
+abcde�fghi	1

storage-api/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/StringExpr.java

@@ -342,7 +342,15 @@ public int find(byte[] input, int start, int len) {
           }
           s_tmp--;
         }
-        next += shift[input[next] & MAX_BYTE];
+
+        // if the character string contains control characters,
+        // overflow occurs.
+        int shiftIndex = input[next] & MAX_BYTE;
+        if (shiftIndex >= MAX_BYTE) {
+          next++;
+        } else {
+          next += shift[shiftIndex];
+        }
       }
       return -1;
     }

storage-api/src/test/org/apache/hadoop/hive/ql/exec/vector/expressions/TestStringExpr.java

@@ -20,6 +20,7 @@
 
 import org.junit.Test;
 
+import java.io.ByteArrayOutputStream;
 import java.nio.charset.StandardCharsets;
 
 import static org.junit.Assert.*;
@@ -49,6 +50,24 @@ public void test() throws Exception {
     assertEquals("Testing match at end of string", 24, find(pattern, input4));
   }
 
+  @Test
+  public void testControlCharacters() throws Exception {
+    StringExpr.Finder pattern = compile("pattern");
+    assertNotNull(pattern);
+
+    byte b = -1;
+    byte[] controlBytes1 = "abcedf".getBytes(StandardCharsets.UTF_8);
+    byte[] controlBytes2 = "pattern".getBytes(StandardCharsets.UTF_8);
+    ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
+    outputStream.write(controlBytes1);
+    outputStream.write(b);
+    outputStream.write(controlBytes2);
+    byte[] controlChar = outputStream.toByteArray();
+    outputStream.close();
+
+    assertEquals("Testing valid match", 7, pattern.find(controlChar, 0, controlChar.length));
+  }
+
   private StringExpr.Finder compile(String pattern) {
     return StringExpr.compile(pattern.getBytes(StandardCharsets.UTF_8));
   }