|
|
|
// 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_MESSAGE_PROMOTE_H_
|
|
|
|
#define UPB_MESSAGE_PROMOTE_H_
|
|
|
|
|
|
|
|
#include "upb/message/array.h"
|
|
|
|
#include "upb/message/internal/extension.h"
|
|
|
|
#include "upb/message/map.h"
|
|
|
|
#include "upb/wire/decode.h"
|
|
|
|
|
|
|
|
// Must be last.
|
|
|
|
#include "upb/port/def.inc"
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
extern "C" {
|
|
|
|
#endif
|
|
|
|
|
|
|
|
typedef enum {
|
|
|
|
kUpb_GetExtension_Ok,
|
|
|
|
kUpb_GetExtension_NotPresent,
|
|
|
|
kUpb_GetExtension_ParseError,
|
|
|
|
kUpb_GetExtension_OutOfMemory,
|
|
|
|
} upb_GetExtension_Status;
|
|
|
|
|
|
|
|
typedef enum {
|
|
|
|
kUpb_GetExtensionAsBytes_Ok,
|
|
|
|
kUpb_GetExtensionAsBytes_NotPresent,
|
|
|
|
kUpb_GetExtensionAsBytes_EncodeError,
|
|
|
|
} upb_GetExtensionAsBytes_Status;
|
|
|
|
|
|
|
|
// Returns a message extension or promotes an unknown field to
|
|
|
|
// an extension.
|
|
|
|
//
|
|
|
|
// TODO: Only supports extension fields that are messages,
|
|
|
|
// expand support to include non-message types.
|
|
|
|
upb_GetExtension_Status upb_MiniTable_GetOrPromoteExtension(
|
|
|
|
upb_Message* msg, const upb_MiniTableExtension* ext_table,
|
|
|
|
int decode_options, upb_Arena* arena,
|
|
|
|
const upb_Message_Extension** extension);
|
|
|
|
|
|
|
|
typedef enum {
|
|
|
|
kUpb_FindUnknown_Ok,
|
|
|
|
kUpb_FindUnknown_NotPresent,
|
|
|
|
kUpb_FindUnknown_ParseError,
|
|
|
|
} upb_FindUnknown_Status;
|
|
|
|
|
|
|
|
typedef struct {
|
|
|
|
upb_FindUnknown_Status status;
|
|
|
|
// Start of unknown field data in message arena.
|
|
|
|
const char* ptr;
|
|
|
|
// Size of unknown field data.
|
|
|
|
size_t len;
|
|
|
|
} upb_FindUnknownRet;
|
|
|
|
|
|
|
|
// Finds first occurrence of unknown data by tag id in message.
|
|
|
|
// A depth_limit of zero means to just use the upb default depth limit.
|
|
|
|
upb_FindUnknownRet upb_Message_FindUnknown(const upb_Message* msg,
|
|
|
|
uint32_t field_number,
|
|
|
|
int depth_limit);
|
|
|
|
|
|
|
|
typedef enum {
|
|
|
|
kUpb_UnknownToMessage_Ok,
|
|
|
|
kUpb_UnknownToMessage_ParseError,
|
|
|
|
kUpb_UnknownToMessage_OutOfMemory,
|
|
|
|
kUpb_UnknownToMessage_NotFound,
|
|
|
|
} upb_UnknownToMessage_Status;
|
|
|
|
|
|
|
|
typedef struct {
|
|
|
|
upb_UnknownToMessage_Status status;
|
|
|
|
upb_Message* message;
|
|
|
|
} upb_UnknownToMessageRet;
|
|
|
|
|
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
|
|
|
// Promotes an "empty" non-repeated message field in `parent` to a message of
|
|
|
|
// the correct type.
|
|
|
|
//
|
|
|
|
// Preconditions:
|
|
|
|
//
|
|
|
|
// 1. The message field must currently be in the "empty" state (this must have
|
|
|
|
// been previously verified by the caller by calling
|
|
|
|
// `upb_Message_GetTaggedMessagePtr()` and observing that the message is
|
|
|
|
// indeed empty).
|
|
|
|
//
|
|
|
|
// 2. This `field` must have previously been linked.
|
|
|
|
//
|
|
|
|
// If the promotion succeeds, `parent` will have its data for `field` replaced
|
|
|
|
// by the promoted message, which is also returned in `*promoted`. If the
|
|
|
|
// return value indicates an error status, `parent` and `promoted` are
|
|
|
|
// unchanged.
|
|
|
|
upb_DecodeStatus upb_Message_PromoteMessage(upb_Message* parent,
|
|
|
|
const upb_MiniTable* mini_table,
|
|
|
|
const upb_MiniTableField* field,
|
|
|
|
int decode_options,
|
|
|
|
upb_Arena* arena,
|
|
|
|
upb_Message** promoted);
|
|
|
|
|
|
|
|
// Promotes any "empty" messages in this array to a message of the correct type
|
|
|
|
// `mini_table`. This function should only be called for arrays of messages.
|
|
|
|
//
|
|
|
|
// If the return value indicates an error status, some but not all elements may
|
|
|
|
// have been promoted, but the array itself will not be corrupted.
|
|
|
|
upb_DecodeStatus upb_Array_PromoteMessages(upb_Array* arr,
|
|
|
|
const upb_MiniTable* mini_table,
|
|
|
|
int decode_options,
|
|
|
|
upb_Arena* arena);
|
|
|
|
|
|
|
|
// Promotes any "empty" entries in this map to a message of the correct type
|
|
|
|
// `mini_table`. This function should only be called for maps that have a
|
|
|
|
// message type as the map value.
|
|
|
|
//
|
|
|
|
// If the return value indicates an error status, some but not all elements may
|
|
|
|
// have been promoted, but the map itself will not be corrupted.
|
|
|
|
upb_DecodeStatus upb_Map_PromoteMessages(upb_Map* map,
|
|
|
|
const upb_MiniTable* mini_table,
|
|
|
|
int decode_options, upb_Arena* arena);
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
|
|
// OLD promotion interfaces, will be removed!
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
|
|
|
|
|
|
// Promotes unknown data inside message to a upb_Message parsing the unknown.
|
|
|
|
//
|
|
|
|
// The unknown data is removed from message after field value is set
|
|
|
|
// using upb_Message_SetMessage.
|
|
|
|
//
|
|
|
|
// WARNING!: See b/267655898
|
|
|
|
upb_UnknownToMessageRet upb_MiniTable_PromoteUnknownToMessage(
|
|
|
|
upb_Message* msg, const upb_MiniTable* mini_table,
|
|
|
|
const upb_MiniTableField* field, const upb_MiniTable* sub_mini_table,
|
|
|
|
int decode_options, upb_Arena* arena);
|
|
|
|
|
|
|
|
// Promotes all unknown data that matches field tag id to repeated messages
|
|
|
|
// in upb_Array.
|
|
|
|
//
|
|
|
|
// The unknown data is removed from message after upb_Array is populated.
|
|
|
|
// Since repeated messages can't be packed we remove each unknown that
|
|
|
|
// contains the target tag id.
|
|
|
|
upb_UnknownToMessage_Status upb_MiniTable_PromoteUnknownToMessageArray(
|
|
|
|
upb_Message* msg, const upb_MiniTableField* field,
|
|
|
|
const upb_MiniTable* mini_table, int decode_options, upb_Arena* arena);
|
|
|
|
|
|
|
|
// Promotes all unknown data that matches field tag id to upb_Map.
|
|
|
|
//
|
|
|
|
// The unknown data is removed from message after upb_Map is populated.
|
|
|
|
// Since repeated messages can't be packed we remove each unknown that
|
|
|
|
// contains the target tag id.
|
|
|
|
upb_UnknownToMessage_Status upb_MiniTable_PromoteUnknownToMap(
|
|
|
|
upb_Message* msg, const upb_MiniTable* mini_table,
|
|
|
|
const upb_MiniTableField* field, int decode_options, upb_Arena* arena);
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
} /* extern "C" */
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include "upb/port/undef.inc"
|
|
|
|
|
|
|
|
#endif // UPB_MESSAGE_PROMOTE_H_
|