GH-48151: [C++][Parquet] Fix arrow-ipc-message-internal-test & arrow-acero-hash-join-node-test failures

Author: Vishwanatha-HD

cpp/src/arrow/acero/hash_join.cc

@@ -29,6 +29,7 @@
 #include "arrow/acero/task_util.h"
 #include "arrow/compute/row/encode_internal.h"
 #include "arrow/compute/row/row_encoder_internal.h"
+#include "arrow/util/endian.h"
 #include "arrow/util/logging_internal.h"
 #include "arrow/util/tracing_internal.h"
 
@@ -306,19 +307,40 @@ class HashJoinBasicImpl : public HashJoinImpl {
 
     size_t num_probed_rows = match.size() + no_match.size();
     if (mask.is_scalar()) {
+#if ARROW_LITTLE_ENDIAN
       const auto& mask_scalar = mask.scalar_as<BooleanScalar>();
       if (mask_scalar.is_valid && mask_scalar.value) {
         // All rows passed, nothing left to do
         return Status::OK();
-      } else {
-        // Nothing passed, no_match becomes everything
-        no_match.resize(num_probed_rows);
-        std::iota(no_match.begin(), no_match.end(), 0);
-        match_left.clear();
-        match_right.clear();
-        match.clear();
-        return Status::OK();
       }
+#else
+      // Check if the scalar is a BooleanScalar before casting
+      if (mask.scalar()->type->id() == Type::BOOL) {
+        const auto& mask_scalar = mask.scalar_as<BooleanScalar>();
+        if (mask_scalar.is_valid && mask_scalar.value) {
+          // All rows passed, nothing left to do
+          return Status::OK();
+        } else {
+          // Nothing passed, no_match becomes everything
+          no_match.resize(num_probed_rows);
+          std::iota(no_match.begin(), no_match.end(), 0);
+          match_left.clear();
+          match_right.clear();
+          match.clear();
+          return Status::OK();
+        }
+      }
+#endif
+      // On Little-endian systems: Nothing passed, no_match becomes everything
+      // On Big-endian systems:
+      // If it's not a BooleanScalar (e.g., NullScalar), treat as false
+      // This handles cases like literal(NullScalar()) in filter expressions
+      no_match.resize(num_probed_rows);
+      std::iota(no_match.begin(), no_match.end(), 0);
+      match_left.clear();
+      match_right.clear();
+      match.clear();
+      return Status::OK();
     }
     ARROW_DCHECK_EQ(mask.array()->offset, 0);
     ARROW_DCHECK_EQ(mask.array()->length, static_cast<int64_t>(match_left.size()));

cpp/src/arrow/ipc/message_internal_test.cc

@@ -24,6 +24,7 @@
 #include "arrow/ipc/metadata_internal.h"
 #include "arrow/ipc/options.h"
 #include "arrow/testing/gtest_util.h"
+#include "arrow/util/endian.h"
 #include "arrow/util/key_value_metadata.h"
 
 namespace arrow::ipc::internal {
@@ -55,6 +56,7 @@ TEST(TestMessageInternal, TestByteIdentical) {
   ASSERT_OK(
       WriteSchemaMessage(*schema, mapper, IpcWriteOptions::Defaults(), &out_buffer));
 
+#if ARROW_LITTLE_ENDIAN
   // This is example output from macOS+ARM+LLVM
   const uint8_t expected[] = {
       0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0A, 0x00, 0x0E, 0x00, 0x06, 0x00, 0x05, 0x00,
@@ -74,6 +76,29 @@ TEST(TestMessageInternal, TestByteIdentical) {
       0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x66, 0x30, 0x00, 0x00, 0x08, 0x00,
       0x0C, 0x00, 0x08, 0x00, 0x07, 0x00, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01,
       0x40, 0x00, 0x00, 0x00};
+#else
+  // On Big-endian systems, FlatBuffer serialization can produce slightly different
+  // output across different platforms and toolchains.
+  // This is example output from Linux+s390x+GCC, which is a 232 byte structure
+  const uint8_t expected[] = {
+      0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0A, 0x00, 0x0E, 0x00, 0x06, 0x00, 0x05, 0x00,
+      0x08, 0x00, 0x0A, 0x00, 0x00, 0x00, 0x00, 0x01, 0x04, 0x00, 0x10, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x0A, 0x00, 0x10, 0x00, 0x06, 0x00, 0x08, 0x00, 0x0C, 0x00, 0x0A, 0x00,
+      0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x6C, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00,
+      0x02, 0x00, 0x00, 0x00, 0x38, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0xD8, 0xFF,
+      0xFF, 0xFF, 0x18, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x00,
+      0x6B, 0x65, 0x79, 0x5F, 0x32, 0x5F, 0x76, 0x61, 0x6C, 0x75, 0x65, 0x00, 0x05, 0x00,
+      0x00, 0x00, 0x6B, 0x65, 0x79, 0x5F, 0x32, 0x00, 0x00, 0x00, 0x08, 0x00, 0x0C, 0x00,
+      0x04, 0x00, 0x08, 0x00, 0x08, 0x00, 0x00, 0x00, 0x18, 0x00, 0x00, 0x00, 0x04, 0x00,
+      0x00, 0x00, 0x0B, 0x00, 0x00, 0x00, 0x6B, 0x65, 0x79, 0x5F, 0x31, 0x5F, 0x76, 0x61,
+      0x6C, 0x75, 0x65, 0x00, 0x05, 0x00, 0x00, 0x00, 0x6B, 0x65, 0x79, 0x5F, 0x31, 0x00,
+      0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x14, 0x00, 0x00, 0x00, 0x10, 0x00, 0x14, 0x00,
+      0x08, 0x00, 0x06, 0x00, 0x07, 0x00, 0x0C, 0x00, 0x00, 0x00, 0x10, 0x00, 0x10, 0x00,
+      0x00, 0x00, 0x00, 0x00, 0x01, 0x02, 0x10, 0x00, 0x00, 0x00, 0x1C, 0x00, 0x00, 0x00,
+      0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x66, 0x30,
+      0x00, 0x00, 0x08, 0x00, 0x0C, 0x00, 0x08, 0x00, 0x07, 0x00, 0x08, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x01, 0x40, 0x00, 0x00, 0x00};
+#endif
   Buffer expected_buffer(expected, sizeof(expected));
 
   AssertBufferEqual(expected_buffer, *out_buffer);