|
|
|
/*
|
|
|
|
* Copyright (c) 2009-2022, Google LLC
|
|
|
|
* All rights reserved.
|
|
|
|
*
|
|
|
|
* Redistribution and use in source and binary forms, with or without
|
|
|
|
* modification, are permitted provided that the following conditions are met:
|
|
|
|
* * Redistributions of source code must retain the above copyright
|
|
|
|
* notice, this list of conditions and the following disclaimer.
|
|
|
|
* * Redistributions in binary form must reproduce the above copyright
|
|
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
|
|
* documentation and/or other materials provided with the distribution.
|
|
|
|
* * Neither the name of Google LLC nor the
|
|
|
|
* names of its contributors may be used to endorse or promote products
|
|
|
|
* derived from this software without specific prior written permission.
|
|
|
|
*
|
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
|
|
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL Google LLC BE LIABLE FOR ANY DIRECT,
|
|
|
|
* INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
|
|
|
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
|
|
|
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
|
|
|
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
|
|
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
|
|
|
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef UPB_MINI_TABLE_COMMON_H_
|
|
|
|
#define UPB_MINI_TABLE_COMMON_H_
|
|
|
|
|
|
|
|
#include "upb/mini_table/field_internal.h"
|
|
|
|
#include "upb/mini_table/message_internal.h"
|
|
|
|
#include "upb/mini_table/sub_internal.h"
|
|
|
|
|
|
|
|
// Must be last.
|
|
|
|
#include "upb/port/def.inc"
|
|
|
|
|
|
|
|
typedef enum {
|
|
|
|
kUpb_FieldModifier_IsRepeated = 1 << 0,
|
|
|
|
kUpb_FieldModifier_IsPacked = 1 << 1,
|
|
|
|
kUpb_FieldModifier_IsClosedEnum = 1 << 2,
|
|
|
|
kUpb_FieldModifier_IsProto3Singular = 1 << 3,
|
|
|
|
kUpb_FieldModifier_IsRequired = 1 << 4,
|
|
|
|
} kUpb_FieldModifier;
|
|
|
|
|
|
|
|
typedef enum {
|
|
|
|
kUpb_MessageModifier_ValidateUtf8 = 1 << 0,
|
|
|
|
kUpb_MessageModifier_DefaultIsPacked = 1 << 1,
|
|
|
|
kUpb_MessageModifier_IsExtendable = 1 << 2,
|
|
|
|
} kUpb_MessageModifier;
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
extern "C" {
|
|
|
|
#endif
|
|
|
|
|
|
|
|
UPB_API const upb_MiniTableField* upb_MiniTable_FindFieldByNumber(
|
|
|
|
const upb_MiniTable* table, uint32_t number);
|
|
|
|
|
|
|
|
UPB_API_INLINE const upb_MiniTableField* upb_MiniTable_GetFieldByIndex(
|
|
|
|
const upb_MiniTable* t, uint32_t index) {
|
|
|
|
return &t->fields[index];
|
|
|
|
}
|
|
|
|
|
|
|
|
UPB_API upb_FieldType upb_MiniTableField_Type(const upb_MiniTableField* field);
|
|
|
|
|
|
|
|
UPB_API_INLINE upb_CType upb_MiniTableField_CType(const upb_MiniTableField* f) {
|
|
|
|
switch (f->UPB_PRIVATE(descriptortype)) {
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Returns the MiniTable for this message field. If the field is unlinked,
|
|
|
|
// returns NULL.
|
|
|
|
UPB_API_INLINE const upb_MiniTable* upb_MiniTable_GetSubMessageTable(
|
|
|
|
const upb_MiniTable* mini_table, const upb_MiniTableField* field) {
|
|
|
|
UPB_ASSERT(upb_MiniTableField_CType(field) == kUpb_CType_Message);
|
Added a new dynamic tree shaking model to upb, with the intention of removing the old model once YouTube has migrated.
The `kUpb_DecodeOption_ExperimentalAllowUnlinked` flag to the decoder will enable the new behavior. When that flag is not passed, tree shaking with the old model will still be possible.
"Dynamic tree shaking" in upb is a feature that allows messages to be parsed even if the MiniTables have not been fully linked. Unlinked sub-message fields can be parsed by preserving their data in the unknown fields. If the application later discovers that the message field is actually needed, the MiniTable can be patched to properly link that field, and existing message instances can "promote" the data from the unknown fields to an actual message of the correct type.
Before this change, dynamic tree shaking stored unparsed message data in the unknown fields of the *parent*. In effect, we were treating the field as if it did not exist at all. This meant that parsing an unlinked field did not affect the hasbits or oneof cases of the parent, nor did it create a `upb_Array` or `upb_Map` for array/map fields. Only when a message was linked and promoted did any of these things occur.
While this model had some amount of conceptual simplicity, it caused significant problems with oneofs. When multiple fields inside a single oneof are parsed from the wire, order matters, because later oneof fields must overwrite earlier ones. Dynamic tree shaking can mean that some fields in a oneof are linked while others are not. It is essential that we preserve this ordering semantic even when dynamic tree shaking is being used, but it is difficult to do if the oneof's data can be split between linked fields (which have been reified into parsed field data) and unlinked fields (whose data lives in the unknown fields of the parent).
To solve this problem, this CL changes the representation for unlinked fields. Instead of being placed in the parent's unknown fields, we create an actual message instance for each unlinked message we parse, but we use a placeholder "empty message" MiniTable as the message's type. All of the message's data will therefore be placed into the "empty message's" unknown fields. But unlike before, this "empty message" is actually present according to the hasbits, oneof case, and `upb_Array`/`upb_Map` of the parent. This means that all of the oneof presence logic works as normal.
Since the MiniTable can be patched at any time, we need a bit in the message instance itself to signal whether a pointer to a sub-message is an "empty message" or not. When dynamic tree shaking is in use, all users must be capable of recognizing an empty message and acting accordingly (promoting, etc) even if the MiniTable itself says that the field is linked.
Because dynamic tree shaking imposes this extra requirement on users, we require that users pass an extra option to the decoder to allow parsing of unlinked sub-messages. Many existing users of upb (Ruby, PHP, Python, etc) will always have fully-linked MiniTables, so there is no reason for them to add extra logic to handle empty messages. By omitting the `kUpb_DecodeOption_ExperimentalAllowUnlinked` option, they will be relieved of the duty to check the tagged pointer that would indicate an empty, unlinked message.
For existing users of dynamic tree shaking, there are three main changes:
1. The APIs in message/promote.h have changed, and users will need to update to the new interfaces.
2. The model for maps has changed slightly. Before, we required that map entries always had their values linked; for dynamic tree shaking to apply to maps, we required that the *entry* was left unlinked, not the entry's value. In the new model, that is reversed: map entries must always be linked, but a map entry's value can be unlinked.
3. The presence model for unlinked fields has changed. Unlinked fields will now register as "present" from the perspective of hasbits, oneof cases, and array/map entries. Users must test the tagged pointer to know if a message is of the correct, linked type or whether it is a placeholder "empty" message. There is a new function `upb_Message_GetTaggedMessagePtr()`, as well as a new accessor `upb_MessageValue.tagged_msg_val` that can be used to read and test the tagged pointer directly.
PiperOrigin-RevId: 535288031
2 years ago
|
|
|
const upb_MiniTable* ret =
|
|
|
|
mini_table->subs[field->UPB_PRIVATE(submsg_index)].submsg;
|
|
|
|
UPB_ASSUME(ret);
|
|
|
|
return ret == &_kUpb_MiniTable_Empty ? NULL : ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Returns the MiniTableEnum for this enum field. If the field is unlinked,
|
|
|
|
// returns NULL.
|
|
|
|
UPB_API_INLINE const upb_MiniTableEnum* upb_MiniTable_GetSubEnumTable(
|
|
|
|
const upb_MiniTable* mini_table, const upb_MiniTableField* field) {
|
|
|
|
UPB_ASSERT(upb_MiniTableField_CType(field) == kUpb_CType_Enum);
|
|
|
|
return mini_table->subs[field->UPB_PRIVATE(submsg_index)].subenum;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Returns true if this MiniTable field is linked to a MiniTable for the
|
|
|
|
// sub-message.
|
|
|
|
UPB_API_INLINE bool upb_MiniTable_MessageFieldIsLinked(
|
|
|
|
const upb_MiniTable* mini_table, const upb_MiniTableField* field) {
|
|
|
|
return upb_MiniTable_GetSubMessageTable(mini_table, field) != NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
// If this field is in a oneof, returns the first field in the oneof.
|
|
|
|
//
|
|
|
|
// Otherwise returns NULL.
|
|
|
|
//
|
|
|
|
// Usage:
|
|
|
|
// const upb_MiniTableField* field = upb_MiniTable_GetOneof(m, f);
|
|
|
|
// do {
|
|
|
|
// ..
|
|
|
|
// } while (upb_MiniTable_NextOneofField(m, &field);
|
|
|
|
//
|
|
|
|
const upb_MiniTableField* upb_MiniTable_GetOneof(const upb_MiniTable* m,
|
|
|
|
const upb_MiniTableField* f);
|
|
|
|
|
|
|
|
// Iterates to the next field in the oneof. If this is the last field in the
|
|
|
|
// oneof, returns false. The ordering of fields in the oneof is not
|
|
|
|
// guaranteed.
|
|
|
|
// REQUIRES: |f| is the field initialized by upb_MiniTable_GetOneof and updated
|
|
|
|
// by prior upb_MiniTable_NextOneofField calls.
|
|
|
|
bool upb_MiniTable_NextOneofField(const upb_MiniTable* m,
|
|
|
|
const upb_MiniTableField** f);
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
} /* extern "C" */
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include "upb/port/undef.inc"
|
|
|
|
|
|
|
|
#endif /* UPB_MINI_TABLE_COMMON_H_ */
|