|
|
|
|
// Protocol Buffers - Google's data interchange format
|
|
|
|
|
// Copyright 2023 Google LLC. All rights reserved.
|
|
|
|
|
//
|
|
|
|
|
// Use of this source code is governed by a BSD-style
|
|
|
|
|
// license that can be found in the LICENSE file or at
|
|
|
|
|
// https://developers.google.com/open-source/licenses/bsd
|
|
|
|
|
|
|
|
|
|
#ifndef UPB_MINI_TABLE_FIELD_H_
|
|
|
|
|
#define UPB_MINI_TABLE_FIELD_H_
|
|
|
|
|
|
|
|
|
|
#include "upb/mini_table/internal/field.h"
|
|
|
|
|
#include "upb/mini_table/internal/message.h"
|
|
|
|
|
#include "upb/mini_table/internal/sub.h"
|
|
|
|
|
|
|
|
|
|
// Must be last.
|
|
|
|
|
#include "upb/port/def.inc"
|
|
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
|
extern "C" {
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
typedef struct upb_MiniTableField upb_MiniTableField;
|
|
|
|
|
|
|
|
|
|
UPB_API_INLINE upb_FieldType
|
|
|
|
|
upb_MiniTableField_Type(const upb_MiniTableField* field) {
|
|
|
|
|
if (field->mode & kUpb_LabelFlags_IsAlternate) {
|
|
|
|
|
if (field->UPB_PRIVATE(descriptortype) == kUpb_FieldType_Int32) {
|
|
|
|
|
return kUpb_FieldType_Enum;
|
|
|
|
|
} else if (field->UPB_PRIVATE(descriptortype) == kUpb_FieldType_Bytes) {
|
|
|
|
|
return kUpb_FieldType_String;
|
|
|
|
|
} else {
|
|
|
|
|
UPB_ASSERT(false);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return (upb_FieldType)field->UPB_PRIVATE(descriptortype);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
UPB_API_INLINE upb_CType upb_MiniTableField_CType(const upb_MiniTableField* f) {
|
|
|
|
|
switch (upb_MiniTableField_Type(f)) {
|
|
|
|
|
case kUpb_FieldType_Double:
|
|
|
|
|
return kUpb_CType_Double;
|
|
|
|
|
case kUpb_FieldType_Float:
|
|
|
|
|
return kUpb_CType_Float;
|
|
|
|
|
case kUpb_FieldType_Int64:
|
|
|
|
|
case kUpb_FieldType_SInt64:
|
|
|
|
|
case kUpb_FieldType_SFixed64:
|
|
|
|
|
return kUpb_CType_Int64;
|
|
|
|
|
case kUpb_FieldType_Int32:
|
|
|
|
|
case kUpb_FieldType_SFixed32:
|
|
|
|
|
case kUpb_FieldType_SInt32:
|
|
|
|
|
return kUpb_CType_Int32;
|
|
|
|
|
case kUpb_FieldType_UInt64:
|
|
|
|
|
case kUpb_FieldType_Fixed64:
|
|
|
|
|
return kUpb_CType_UInt64;
|
|
|
|
|
case kUpb_FieldType_UInt32:
|
|
|
|
|
case kUpb_FieldType_Fixed32:
|
|
|
|
|
return kUpb_CType_UInt32;
|
|
|
|
|
case kUpb_FieldType_Enum:
|
|
|
|
|
return kUpb_CType_Enum;
|
|
|
|
|
case kUpb_FieldType_Bool:
|
|
|
|
|
return kUpb_CType_Bool;
|
|
|
|
|
case kUpb_FieldType_String:
|
|
|
|
|
return kUpb_CType_String;
|
|
|
|
|
case kUpb_FieldType_Bytes:
|
|
|
|
|
return kUpb_CType_Bytes;
|
|
|
|
|
case kUpb_FieldType_Group:
|
|
|
|
|
case kUpb_FieldType_Message:
|
|
|
|
|
return kUpb_CType_Message;
|
|
|
|
|
}
|
|
|
|
|
UPB_UNREACHABLE();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
UPB_API_INLINE bool upb_MiniTableField_IsExtension(
|
Refactored message accessors to share a common set of functions instead of duplicating logic.
Prior to this CL, there were several different code paths for reading/writing message data. Generated code, MiniTable accessors, and reflection all performed direct manipulation of the bits and bytes in a message, but they all had distinct implementations that did not share much of any code. This divergence meant that they could easily have different behavior, bugs could creep into one but not another, and we would need three different sets of tests to get full test coverage. This also made it very difficult to change the internal representation in any way, since it would require updating many places in the code.
With this CL, the three different APIs for accessing message data now all share a common set of functions. The common functions all take a `upb_MiniTableField` as the canonical description of a field's type and layout. The lowest-level functions are very branchy, as they must test for every possible variation in the field type (field vs oneof, hasbit vs no-hasbit, different field sizes, whether a nonzero default value exists, extension vs. regular field), however these functions are declared inline and designed to be very optimizable when values are known at compile time.
In generated accessors, for example, we can declare constant `upb_MiniTableField` instances so that all values can constant-propagate, and we can get fully specialized code even though we are calling a generic function. On the other hand, when we use the generic functions from reflection, we get runtime branches since values are not known at compile time. But even the function is written to still be as efficient as possible even when used from reflection. For example, we use memcpy() calls with constant length so that the compiler can optimize these into inline loads/stores without having to make an out-of-line call to memcpy().
In this way, this CL should be a benefit to both correctness and performance. It will also make it easier to change the message representation, for example to optimize the encoder by giving hasbits to all fields.
Note that we have not completely consolidated all access in this CL:
1. Some functions outside of get/set such as clear and hazzers are not yet unified.
2. The encoder and decoder still touch the message without going through the common functions. The encoder and decoder require a bit more specialized code to get good performance when reading/writing fields en masse.
PiperOrigin-RevId: 490016095
2 years ago
|
|
|
const upb_MiniTableField* field) {
|
|
|
|
|
return field->mode & kUpb_LabelFlags_IsExtension;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
UPB_API_INLINE bool upb_MiniTableField_IsClosedEnum(
|
|
|
|
|
const upb_MiniTableField* field) {
|
|
|
|
|
return field->UPB_PRIVATE(descriptortype) == kUpb_FieldType_Enum;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
UPB_API_INLINE bool upb_MiniTableField_HasPresence(
|
|
|
|
|
const upb_MiniTableField* field) {
|
|
|
|
|
if (upb_MiniTableField_IsExtension(field)) {
|
|
|
|
|
return !upb_IsRepeatedOrMap(field);
|
|
|
|
|
} else {
|
|
|
|
|
return field->presence != 0;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
|
} /* extern "C" */
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#include "upb/port/undef.inc"
|
|
|
|
|
|
|
|
|
|
#endif /* UPB_MINI_TABLE_FIELD_H_ */
|
