|
|
|
// 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
|
|
|
|
|
|
|
|
#include "upb/reflection/message.h"
|
|
|
|
|
|
|
|
#include <stdint.h>
|
|
|
|
#include <string.h>
|
|
|
|
|
|
|
|
#include "upb/mem/arena.h"
|
|
|
|
#include "upb/message/accessors.h"
|
|
|
|
#include "upb/message/array.h"
|
|
|
|
#include "upb/message/internal/accessors.h"
|
|
|
|
#include "upb/message/internal/extension.h"
|
|
|
|
#include "upb/message/internal/message.h"
|
|
|
|
#include "upb/message/map.h"
|
|
|
|
#include "upb/message/message.h"
|
|
|
|
#include "upb/mini_table/field.h"
|
|
|
|
#include "upb/mini_table/internal/field.h"
|
|
|
|
#include "upb/reflection/def.h"
|
|
|
|
#include "upb/reflection/def_pool.h"
|
|
|
|
#include "upb/reflection/message_def.h"
|
|
|
|
#include "upb/reflection/oneof_def.h"
|
|
|
|
|
|
|
|
// Must be last.
|
|
|
|
#include "upb/port/def.inc"
|
|
|
|
|
|
|
|
bool upb_Message_HasFieldByDef(const upb_Message* msg, const upb_FieldDef* f) {
|
|
|
|
UPB_ASSERT(upb_FieldDef_HasPresence(f));
|
|
|
|
return upb_Message_HasField(msg, upb_FieldDef_MiniTable(f));
|
|
|
|
}
|
|
|
|
|
|
|
|
const upb_FieldDef* upb_Message_WhichOneof(const upb_Message* msg,
|
|
|
|
const upb_OneofDef* o) {
|
|
|
|
const upb_FieldDef* f = upb_OneofDef_Field(o, 0);
|
|
|
|
if (upb_OneofDef_IsSynthetic(o)) {
|
|
|
|
UPB_ASSERT(upb_OneofDef_FieldCount(o) == 1);
|
|
|
|
return upb_Message_HasFieldByDef(msg, f) ? f : NULL;
|
|
|
|
} else {
|
|
|
|
const upb_MiniTableField* field = upb_FieldDef_MiniTable(f);
|
|
|
|
uint32_t oneof_case = upb_Message_WhichOneofFieldNumber(msg, field);
|
|
|
|
f = oneof_case ? upb_OneofDef_LookupNumber(o, oneof_case) : NULL;
|
|
|
|
UPB_ASSERT((f != NULL) == (oneof_case != 0));
|
|
|
|
return f;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
upb_MessageValue upb_Message_GetFieldByDef(const upb_Message* msg,
|
|
|
|
const upb_FieldDef* f) {
|
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
|
|
|
upb_MessageValue default_val = upb_FieldDef_Default(f);
|
|
|
|
return upb_Message_GetField(msg, upb_FieldDef_MiniTable(f), default_val);
|
|
|
|
}
|
|
|
|
|
|
|
|
upb_MutableMessageValue upb_Message_Mutable(upb_Message* msg,
|
|
|
|
const upb_FieldDef* f,
|
|
|
|
upb_Arena* a) {
|
|
|
|
UPB_ASSERT(upb_FieldDef_IsSubMessage(f) || upb_FieldDef_IsRepeated(f));
|
|
|
|
if (upb_FieldDef_HasPresence(f) && !upb_Message_HasFieldByDef(msg, f)) {
|
|
|
|
// We need to skip the upb_Message_GetFieldByDef() call in this case.
|
|
|
|
goto make;
|
|
|
|
}
|
|
|
|
|
|
|
|
upb_MessageValue val = upb_Message_GetFieldByDef(msg, f);
|
|
|
|
if (val.array_val) {
|
|
|
|
return (upb_MutableMessageValue){.array = (upb_Array*)val.array_val};
|
|
|
|
}
|
|
|
|
|
|
|
|
upb_MutableMessageValue ret;
|
|
|
|
make:
|
|
|
|
if (!a) return (upb_MutableMessageValue){.array = NULL};
|
|
|
|
if (upb_FieldDef_IsMap(f)) {
|
|
|
|
const upb_MessageDef* entry = upb_FieldDef_MessageSubDef(f);
|
|
|
|
const upb_FieldDef* key =
|
|
|
|
upb_MessageDef_FindFieldByNumber(entry, kUpb_MapEntry_KeyFieldNumber);
|
|
|
|
const upb_FieldDef* value =
|
|
|
|
upb_MessageDef_FindFieldByNumber(entry, kUpb_MapEntry_ValueFieldNumber);
|
|
|
|
ret.map =
|
|
|
|
upb_Map_New(a, upb_FieldDef_CType(key), upb_FieldDef_CType(value));
|
|
|
|
} else if (upb_FieldDef_IsRepeated(f)) {
|
|
|
|
ret.array = upb_Array_New(a, upb_FieldDef_CType(f));
|
|
|
|
} else {
|
|
|
|
UPB_ASSERT(upb_FieldDef_IsSubMessage(f));
|
|
|
|
const upb_MessageDef* m = upb_FieldDef_MessageSubDef(f);
|
|
|
|
ret.msg = upb_Message_New(upb_MessageDef_MiniTable(m), a);
|
|
|
|
}
|
|
|
|
|
|
|
|
val.array_val = ret.array;
|
|
|
|
upb_Message_SetFieldByDef(msg, f, val, a);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool upb_Message_SetFieldByDef(upb_Message* msg, const upb_FieldDef* f,
|
|
|
|
upb_MessageValue val, upb_Arena* a) {
|
|
|
|
return upb_Message_SetField(msg, upb_FieldDef_MiniTable(f), val, a);
|
|
|
|
}
|
|
|
|
|
|
|
|
void upb_Message_ClearFieldByDef(upb_Message* msg, const upb_FieldDef* f) {
|
|
|
|
upb_Message_ClearField(msg, upb_FieldDef_MiniTable(f));
|
|
|
|
}
|
|
|
|
|
|
|
|
void upb_Message_ClearByDef(upb_Message* msg, const upb_MessageDef* m) {
|
|
|
|
upb_Message_Clear(msg, upb_MessageDef_MiniTable(m));
|
|
|
|
}
|
|
|
|
|
|
|
|
bool upb_Message_Next(const upb_Message* msg, const upb_MessageDef* m,
|
|
|
|
const upb_DefPool* ext_pool, const upb_FieldDef** out_f,
|
|
|
|
upb_MessageValue* out_val, size_t* iter) {
|
|
|
|
size_t i = *iter;
|
|
|
|
size_t n = upb_MessageDef_FieldCount(m);
|
|
|
|
UPB_UNUSED(ext_pool);
|
|
|
|
|
|
|
|
// Iterate over normal fields, returning the first one that is set.
|
|
|
|
while (++i < n) {
|
|
|
|
const upb_FieldDef* f = upb_MessageDef_Field(m, i);
|
|
|
|
const upb_MiniTableField* field = upb_FieldDef_MiniTable(f);
|
|
|
|
upb_MessageValue val = upb_Message_GetFieldByDef(msg, f);
|
|
|
|
|
|
|
|
// Skip field if unset or empty.
|
|
|
|
if (upb_MiniTableField_HasPresence(field)) {
|
|
|
|
if (!upb_Message_HasFieldByDef(msg, f)) continue;
|
|
|
|
} else {
|
|
|
|
switch (UPB_PRIVATE(_upb_MiniTableField_Mode)(field)) {
|
|
|
|
case kUpb_FieldMode_Map:
|
|
|
|
if (!val.map_val || upb_Map_Size(val.map_val) == 0) continue;
|
|
|
|
break;
|
|
|
|
case kUpb_FieldMode_Array:
|
|
|
|
if (!val.array_val || upb_Array_Size(val.array_val) == 0) continue;
|
|
|
|
break;
|
|
|
|
case kUpb_FieldMode_Scalar:
|
|
|
|
if (UPB_PRIVATE(_upb_MiniTableField_DataIsZero)(field, &val))
|
|
|
|
continue;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
*out_val = val;
|
|
|
|
*out_f = f;
|
|
|
|
*iter = i;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ext_pool) {
|
|
|
|
// Return any extensions that are set.
|
|
|
|
size_t count;
|
|
|
|
const upb_Extension* ext = _upb_Message_Getexts(msg, &count);
|
|
|
|
if (i - n < count) {
|
|
|
|
ext += count - 1 - (i - n);
|
|
|
|
memcpy(out_val, &ext->data, sizeof(*out_val));
|
|
|
|
*out_f = upb_DefPool_FindExtensionByMiniTable(ext_pool, ext->ext);
|
|
|
|
*iter = i;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
*iter = i;
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool _upb_Message_DiscardUnknown(upb_Message* msg, const upb_MessageDef* m,
|
|
|
|
int depth) {
|
|
|
|
size_t iter = kUpb_Message_Begin;
|
|
|
|
const upb_FieldDef* f;
|
|
|
|
upb_MessageValue val;
|
|
|
|
bool ret = true;
|
|
|
|
|
|
|
|
if (--depth == 0) return false;
|
|
|
|
|
|
|
|
_upb_Message_DiscardUnknown_shallow(msg);
|
|
|
|
|
|
|
|
while (upb_Message_Next(msg, m, NULL /*ext_pool*/, &f, &val, &iter)) {
|
|
|
|
const upb_MessageDef* subm = upb_FieldDef_MessageSubDef(f);
|
|
|
|
if (!subm) continue;
|
|
|
|
if (upb_FieldDef_IsMap(f)) {
|
|
|
|
const upb_FieldDef* val_f = upb_MessageDef_FindFieldByNumber(subm, 2);
|
|
|
|
const upb_MessageDef* val_m = upb_FieldDef_MessageSubDef(val_f);
|
|
|
|
upb_Map* map = (upb_Map*)val.map_val;
|
|
|
|
size_t iter = kUpb_Map_Begin;
|
|
|
|
|
|
|
|
if (!val_m) continue;
|
|
|
|
|
|
|
|
upb_MessageValue map_key, map_val;
|
|
|
|
while (upb_Map_Next(map, &map_key, &map_val, &iter)) {
|
|
|
|
if (!_upb_Message_DiscardUnknown((upb_Message*)map_val.msg_val, val_m,
|
|
|
|
depth)) {
|
|
|
|
ret = false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else if (upb_FieldDef_IsRepeated(f)) {
|
|
|
|
const upb_Array* arr = val.array_val;
|
|
|
|
size_t i, n = upb_Array_Size(arr);
|
|
|
|
for (i = 0; i < n; i++) {
|
|
|
|
upb_MessageValue elem = upb_Array_Get(arr, i);
|
|
|
|
if (!_upb_Message_DiscardUnknown((upb_Message*)elem.msg_val, subm,
|
|
|
|
depth)) {
|
|
|
|
ret = false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
if (!_upb_Message_DiscardUnknown((upb_Message*)val.msg_val, subm,
|
|
|
|
depth)) {
|
|
|
|
ret = false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool upb_Message_DiscardUnknown(upb_Message* msg, const upb_MessageDef* m,
|
|
|
|
int maxdepth) {
|
|
|
|
return _upb_Message_DiscardUnknown(msg, m, maxdepth);
|
|
|
|
}
|