wjones127 commented on code in PR #174:
URL: https://github.com/apache/arrow-nanoarrow/pull/174#discussion_r1151193559
##########
src/nanoarrow/nanoarrow_types.h:
##########
@@ -503,7 +503,8 @@ struct ArrowArrayView {
///
/// If storage_type is a union type, a 256-byte ArrowMalloc()ed buffer
/// such that child_index == union_type_id_map[type_id] and
- /// type_id == union_type_id_map[128 + child_index]
+ /// type_id == union_type_id_map[128 + child_index]. This value may be
+ /// NULL in the case where child_id == type_id.
Review Comment:
Is that part of the Arrow format? I couldn't find such a detail.
##########
src/nanoarrow/array.c:
##########
@@ -648,15 +663,25 @@ ArrowErrorCode ArrowArrayViewSetArray(struct
ArrowArrayView* array_view,
}
if (array_view->n_children != array->n_children) {
+ ArrowErrorSet(error, "Expected %ld children but found %ld children",
+ (long)array_view->n_children, (long)array->n_children);
return EINVAL;
}
// Check child sizes and calculate sizes that depend on data in the array
buffers
+ int64_t first_offset;
int64_t last_offset;
switch (array_view->storage_type) {
case NANOARROW_TYPE_STRING:
case NANOARROW_TYPE_BINARY:
if (array_view->buffer_views[1].size_bytes != 0) {
+ first_offset = array_view->buffer_views[1].data.as_int32[0];
+ if (first_offset < 0) {
+ ArrowErrorSet(error, "Expected first offset >0 but found %ld",
Review Comment:
```suggestion
ArrowErrorSet(error, "Expected first offset >=0 but found %ld",
```
##########
src/nanoarrow/array.c:
##########
@@ -665,6 +690,13 @@ ArrowErrorCode ArrowArrayViewSetArray(struct
ArrowArrayView* array_view,
case NANOARROW_TYPE_LARGE_STRING:
case NANOARROW_TYPE_LARGE_BINARY:
if (array_view->buffer_views[1].size_bytes != 0) {
+ first_offset = array_view->buffer_views[1].data.as_int64[0];
+ if (first_offset < 0) {
+ ArrowErrorSet(error, "Expected first offset >0 but found %ld",
Review Comment:
And similarly in other places
##########
src/nanoarrow/array.c:
##########
@@ -758,3 +804,138 @@ ArrowErrorCode ArrowArrayViewSetArray(struct
ArrowArrayView* array_view,
return NANOARROW_OK;
}
+
+static int ArrowAssertIncreasingInt32(struct ArrowBufferView view,
+ struct ArrowError* error) {
+ if (view.size_bytes <= (int64_t)sizeof(int32_t)) {
+ return NANOARROW_OK;
+ }
+
+ for (int64_t i = 1; i < view.size_bytes / (int64_t)sizeof(int32_t); i++) {
+ int32_t diff = view.data.as_int32[i] - view.data.as_int32[i - 1];
+ if (diff < 0) {
+ ArrowErrorSet(error,
+ "Expected element size >0 but found element size %ld at
position %ld",
+ (long)diff, (long)i);
+ return EINVAL;
+ }
+ }
+
+ return NANOARROW_OK;
+}
+
+static int ArrowAssertIncreasingInt64(struct ArrowBufferView view,
+ struct ArrowError* error) {
+ if (view.size_bytes <= (int64_t)sizeof(int64_t)) {
+ return NANOARROW_OK;
+ }
+
+ for (int64_t i = 1; i < view.size_bytes / (int64_t)sizeof(int64_t); i++) {
+ int64_t diff = view.data.as_int64[i] - view.data.as_int64[i - 1];
+ if (diff < 0) {
+ ArrowErrorSet(error,
+ "Expected element size >0 but found element size %ld at
position %ld",
+ (long)diff, (long)i);
+ return EINVAL;
+ }
+ }
+
+ return NANOARROW_OK;
+}
+
+static int ArrowAssertRangeInt8(struct ArrowBufferView view, int8_t min_value,
+ int8_t max_value, struct ArrowError* error) {
+ for (int64_t i = 0; i < view.size_bytes; i++) {
+ if (view.data.as_int8[i] < min_value || view.data.as_int8[i] > max_value) {
+ ArrowErrorSet(
+ error,
+ "Expected buffer value between %d and %d but found value %d at
position %ld",
+ (int)min_value, (int)max_value, (int)view.data.as_int8[i], (long)i);
+ return EINVAL;
+ }
+ }
+
+ return NANOARROW_OK;
+}
+
+static int ArrowAssertInt8In(struct ArrowBufferView view, const int8_t* values,
+ int64_t n_values, struct ArrowError* error) {
+ for (int64_t i = 0; i < view.size_bytes; i++) {
+ int item_found = 0;
Review Comment:
Question: why `int` over `bool`?
##########
src/nanoarrow/array.c:
##########
@@ -665,6 +690,13 @@ ArrowErrorCode ArrowArrayViewSetArray(struct
ArrowArrayView* array_view,
case NANOARROW_TYPE_LARGE_STRING:
case NANOARROW_TYPE_LARGE_BINARY:
if (array_view->buffer_views[1].size_bytes != 0) {
+ first_offset = array_view->buffer_views[1].data.as_int64[0];
+ if (first_offset < 0) {
+ ArrowErrorSet(error, "Expected first offset >0 but found %ld",
Review Comment:
```suggestion
ArrowErrorSet(error, "Expected first offset >=0 but found %ld",
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
