From 89fb9db03478b793be7188c5683c6560c2eff115 Mon Sep 17 00:00:00 2001
From: Steven Aerts <steven.aerts@gmail.com>
Date: Fri, 24 Oct 2025 12:46:57 +0000
Subject: [PATCH] AVRO-4193 support for empty bytes

When avro-c tries to encode an empty byte array it will avro_malloc(0)
which on some architectures will return NULL.  Make sure this is not
interpreted as an error or or dereferenced causing a segfault.
---
 lang/c/src/datum.c            |  4 +--
 lang/c/src/value-json.c       |  4 +--
 lang/c/tests/test_avro_data.c | 53 +++++++++++++++++++++++++++--------
 3 files changed, 46 insertions(+), 15 deletions(-)

diff --git a/lang/c/src/datum.c b/lang/c/src/datum.c
index 5307c7a8385..0dc201b9613 100644
--- a/lang/c/src/datum.c
+++ b/lang/c/src/datum.c
@@ -156,7 +156,7 @@ static avro_datum_t avro_bytes_private(char *bytes, int64_t size,
 avro_datum_t avro_bytes(const char *bytes, int64_t size)
 {
 	char *bytes_copy = (char *) avro_malloc(size);
-	if (!bytes_copy) {
+	if (!bytes_copy && size) {
 		avro_set_error("Cannot copy bytes content");
 		return NULL;
 	}
@@ -197,7 +197,7 @@ int avro_bytes_set(avro_datum_t datum, const char *bytes, const int64_t size)
 {
 	int rval;
 	char *bytes_copy = (char *) avro_malloc(size);
-	if (!bytes_copy) {
+	if (!bytes_copy && size) {
 		avro_set_error("Cannot copy bytes content");
 		return ENOMEM;
 	}
diff --git a/lang/c/src/value-json.c b/lang/c/src/value-json.c
index 7927c14dd84..6b505a9ce41 100644
--- a/lang/c/src/value-json.c
+++ b/lang/c/src/value-json.c
@@ -62,7 +62,7 @@ encode_utf8_bytes(const void *src, size_t src_len,
 
 	// Allocate a new buffer for the UTF-8 string and fill it in.
 	uint8_t  *dest8 = (uint8_t *) avro_malloc(utf8_len);
-	if (dest8 == NULL) {
+	if (dest8 == NULL && utf8_len) {
 		avro_set_error("Cannot allocate JSON bytes buffer");
 		return ENOMEM;
 	}
@@ -126,7 +126,7 @@ avro_value_to_json_t(const avro_value_t *value)
 				return NULL;
 			}
 
-			json_t  *result = json_stringn_nocheck((const char *) encoded, encoded_size);
+			json_t  *result = json_stringn_nocheck((const char *) encoded ? encoded : "", encoded_size);
 			avro_free(encoded, encoded_size);
 			if (result == NULL) {
 				avro_set_error("Cannot allocate JSON bytes");
diff --git a/lang/c/tests/test_avro_data.c b/lang/c/tests/test_avro_data.c
index 3a26c67e242..ac7c637929f 100644
--- a/lang/c/tests/test_avro_data.c
+++ b/lang/c/tests/test_avro_data.c
@@ -40,18 +40,20 @@ test_allocator(void *ud, void *ptr, size_t osize, size_t nsize)
 	AVRO_UNUSED(osize);
 
 	if (nsize == 0) {
-		size_t  *size = ((size_t *) ptr) - 1;
-		if (osize != *size) {
-			fprintf(stderr,
-				"Error freeing %p:\n"
-				"Size passed to avro_free (%" PRIsz ") "
-				"doesn't match size passed to "
-				"avro_malloc (%" PRIsz ")\n",
-				ptr, osize, *size);
-			abort();
-			//exit(EXIT_FAILURE);
+		if (ptr) {
+			size_t  *size = ((size_t *) ptr) - 1;
+			if (osize != *size) {
+				fprintf(stderr,
+					"Error freeing %p:\n"
+					"Size passed to avro_free (%" PRIsz ") "
+					"doesn't match size passed to "
+					"avro_malloc (%" PRIsz ")\n",
+					ptr, osize, *size);
+				abort();
+				//exit(EXIT_FAILURE);
+			}
+			free(size);
 		}
-		free(size);
 		return NULL;
 	} else {
 		size_t  real_size = nsize + sizeof(size_t);
@@ -214,6 +216,34 @@ static int test_bytes(void)
 	return 0;
 }
 
+static int test_empty_bytes(void)
+{
+	char bytes[] = { };
+	avro_schema_t writer_schema = avro_schema_bytes();
+	avro_datum_t datum;
+	avro_datum_t expected_datum;
+
+	datum = avro_givebytes(bytes, sizeof(bytes), NULL);
+	write_read_check(writer_schema, datum, NULL, NULL, "bytes");
+	test_json(datum, "\"\"");
+	avro_datum_decref(datum);
+	avro_schema_decref(writer_schema);
+
+	datum = avro_givebytes(NULL, 0, NULL);
+	avro_givebytes_set(datum, bytes, sizeof(bytes), NULL);
+	expected_datum = avro_givebytes(bytes, sizeof(bytes), NULL);
+	if (!avro_datum_equal(datum, expected_datum)) {
+		fprintf(stderr,
+		        "Expected equal bytes instances.\n");
+		exit(EXIT_FAILURE);
+	}
+	avro_datum_decref(datum);
+	avro_datum_decref(expected_datum);
+
+	avro_schema_decref(writer_schema);
+	return 0;
+}
+
 static int test_int32(void)
 {
 	int i;
@@ -657,6 +687,7 @@ int main(void)
 		{
 		"string", test_string}, {
 		"bytes", test_bytes}, {
+		"empty_bytes", test_empty_bytes}, {
 		"int", test_int32}, {
 		"long", test_int64}, {
 		"float", test_float}, {