Skip to content

AVRO-4136: [c] json encoding of byte[] containing 0x00 #3375

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
martin-g merged 1 commit into from
Oct 24, 2025
Merged

AVRO-4136: [c] json encoding of byte[] containing 0x00 #3375

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions lang/c/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,13 +179,13 @@ set(CODEC_LIBRARIES ${ZLIB_LIBRARIES} ${LZMA_LIBRARIES} ${SNAPPY_LIBRARIES})
set(CODEC_PKG "${ZLIB_PKG} ${LZMA_PKG} ${SNAPPY_PKG}")

# Jansson JSON library
pkg_check_modules(JANSSON jansson>=2.3)
pkg_check_modules(JANSSON jansson>=2.7)
if (JANSSON_FOUND)
set(JANSSON_PKG libjansson)
include_directories(${JANSSON_INCLUDE_DIRS})
link_directories(${JANSSON_LIBRARY_DIRS})
else (JANSSON_FOUND)
message(FATAL_ERROR "libjansson >=2.3 not found")
message(FATAL_ERROR "libjansson >=2.7 not found")
endif (JANSSON_FOUND)


Expand Down
11 changes: 5 additions & 6 deletions lang/c/src/value-json.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,8 @@
#include "jansson.h"

/*
* Converts a binary buffer into a NUL-terminated JSON UTF-8 string.
* Converts a binary buffer into a JSON UTF-8 string which is NOT
* terminated with a null byte ('\0').
* Avro bytes and fixed values are encoded in JSON as a string, and JSON
* strings must be in UTF-8. For these Avro types, the JSON string is
* restricted to the characters U+0000..U+00FF, which corresponds to the
Expand All @@ -51,7 +52,7 @@ encode_utf8_bytes(const void *src, size_t src_len,
// the range 0x80..0xff will take up two.
const uint8_t *src8 = (const uint8_t *) src;

size_t utf8_len = src_len + 1; // +1 for NUL terminator
size_t utf8_len = src_len;
size_t i;
for (i = 0; i < src_len; i++) {
if (src8[i] & 0x80) {
Expand All @@ -76,8 +77,6 @@ encode_utf8_bytes(const void *src, size_t src_len,
}
}

*curr = '\0';

// And we're good.
*dest = dest8;
*dest_len = utf8_len;
Expand Down Expand Up @@ -127,7 +126,7 @@ avro_value_to_json_t(const avro_value_t *value)
return NULL;
}

json_t *result = json_string_nocheck((const char *) encoded);
json_t *result = json_stringn_nocheck((const char *) encoded, encoded_size);
avro_free(encoded, encoded_size);
if (result == NULL) {
avro_set_error("Cannot allocate JSON bytes");
Expand Down Expand Up @@ -242,7 +241,7 @@ avro_value_to_json_t(const avro_value_t *value)
return NULL;
}

json_t *result = json_string_nocheck((const char *) encoded);
json_t *result = json_stringn_nocheck((const char *) encoded, encoded_size);
avro_free(encoded, encoded_size);
if (result == NULL) {
avro_set_error("Cannot allocate JSON fixed");
Expand Down
8 changes: 4 additions & 4 deletions lang/c/tests/test_avro_data.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,14 +181,14 @@ static int test_string(void)

static int test_bytes(void)
{
char bytes[] = { 0xDE, 0xAD, 0xBE, 0xEF };
char bytes[] = { 0xDE, 0xAD, 0x00, 0xBE, 0xEF };
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, "\"\\u00de\\u00ad\\u00be\\u00ef\"");
test_json(datum, "\"\\u00de\\u00ad\\u0000\\u00be\\u00ef\"");
avro_datum_decref(datum);
avro_schema_decref(writer_schema);

Expand Down Expand Up @@ -613,14 +613,14 @@ static int test_union(void)

static int test_fixed(void)
{
char bytes[] = { 0xD, 0xA, 0xD, 0xA, 0xB, 0xA, 0xB, 0xA };
char bytes[] = { 0xD, 0xA, 0xD, 0xA, 0xB, 0x0, 0xB, 0xA };
avro_schema_t schema = avro_schema_fixed("msg", sizeof(bytes));
avro_datum_t datum;
avro_datum_t expected_datum;

datum = avro_givefixed(schema, bytes, sizeof(bytes), NULL);
write_read_check(schema, datum, NULL, NULL, "fixed");
test_json(datum, "\"\\r\\n\\r\\n\\u000b\\n\\u000b\\n\"");
test_json(datum, "\"\\r\\n\\r\\n\\u000b\\u0000\\u000b\\n\"");
avro_datum_decref(datum);

datum = avro_givefixed(schema, NULL, sizeof(bytes), NULL);
Expand Down