|
|
|
// 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_DECODE_H_
|
|
|
|
#define UPB_MINI_TABLE_DECODE_H_
|
|
|
|
|
|
|
|
#include "upb/base/status.h"
|
|
|
|
#include "upb/mem/arena.h"
|
|
|
|
#include "upb/mini_table/extension.h"
|
|
|
|
#include "upb/mini_table/field.h"
|
|
|
|
#include "upb/mini_table/message.h"
|
|
|
|
#include "upb/mini_table/sub.h"
|
|
|
|
|
|
|
|
// Export the newer headers, for legacy users. New users should include the
|
|
|
|
// more specific headers directly.
|
|
|
|
// IWYU pragma: begin_exports
|
|
|
|
#include "upb/mini_descriptor/build_enum.h"
|
|
|
|
#include "upb/mini_descriptor/link.h"
|
|
|
|
// IWYU pragma: end_exports
|
|
|
|
|
|
|
|
// Must be last.
|
|
|
|
#include "upb/port/def.inc"
|
|
|
|
|
|
|
|
typedef enum {
|
|
|
|
kUpb_MiniTablePlatform_32Bit,
|
|
|
|
kUpb_MiniTablePlatform_64Bit,
|
|
|
|
kUpb_MiniTablePlatform_Native =
|
|
|
|
UPB_SIZE(kUpb_MiniTablePlatform_32Bit, kUpb_MiniTablePlatform_64Bit),
|
|
|
|
} upb_MiniTablePlatform;
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
extern "C" {
|
|
|
|
#endif
|
|
|
|
|
|
|
|
// Builds a mini table from the data encoded in the buffer [data, len]. If any
|
|
|
|
// errors occur, returns NULL and sets a status message. In the success case,
|
|
|
|
// the caller must call upb_MiniTable_SetSub*() for all message or proto2 enum
|
|
|
|
// fields to link the table to the appropriate sub-tables.
|
|
|
|
upb_MiniTable* _upb_MiniTable_Build(const char* data, size_t len,
|
|
|
|
upb_MiniTablePlatform platform,
|
|
|
|
upb_Arena* arena, upb_Status* status);
|
|
|
|
|
|
|
|
UPB_API_INLINE upb_MiniTable* upb_MiniTable_Build(const char* data, size_t len,
|
|
|
|
upb_Arena* arena,
|
|
|
|
upb_Status* status) {
|
|
|
|
return _upb_MiniTable_Build(data, len, kUpb_MiniTablePlatform_Native, arena,
|
|
|
|
status);
|
|
|
|
}
|
|
|
|
|
|
|
|
// Initializes a MiniTableExtension buffer that has already been allocated.
|
|
|
|
// This is needed by upb_FileDef and upb_MessageDef, which allocate all of the
|
|
|
|
// extensions together in a single contiguous array.
|
|
|
|
const char* _upb_MiniTableExtension_Init(const char* data, size_t len,
|
|
|
|
upb_MiniTableExtension* ext,
|
|
|
|
const upb_MiniTable* extendee,
|
|
|
|
upb_MiniTableSub sub,
|
|
|
|
upb_MiniTablePlatform platform,
|
|
|
|
upb_Status* status);
|
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_API_INLINE const char* upb_MiniTableExtension_Init(
|
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 char* data, size_t len, upb_MiniTableExtension* ext,
|
|
|
|
const upb_MiniTable* extendee, upb_MiniTableSub sub, upb_Status* status) {
|
|
|
|
return _upb_MiniTableExtension_Init(data, len, ext, extendee, sub,
|
|
|
|
kUpb_MiniTablePlatform_Native, status);
|
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_API upb_MiniTableExtension* _upb_MiniTableExtension_Build(
|
|
|
|
const char* data, size_t len, const upb_MiniTable* extendee,
|
|
|
|
upb_MiniTableSub sub, upb_MiniTablePlatform platform, upb_Arena* arena,
|
|
|
|
upb_Status* status);
|
|
|
|
|
|
|
|
UPB_API_INLINE upb_MiniTableExtension* upb_MiniTableExtension_Build(
|
|
|
|
const char* data, size_t len, const upb_MiniTable* extendee,
|
|
|
|
upb_Arena* arena, upb_Status* status) {
|
|
|
|
upb_MiniTableSub sub;
|
|
|
|
sub.submsg = NULL;
|
|
|
|
return _upb_MiniTableExtension_Build(
|
|
|
|
data, len, extendee, sub, kUpb_MiniTablePlatform_Native, arena, status);
|
|
|
|
}
|
|
|
|
|
|
|
|
UPB_API_INLINE upb_MiniTableExtension* upb_MiniTableExtension_BuildMessage(
|
|
|
|
const char* data, size_t len, const upb_MiniTable* extendee,
|
|
|
|
upb_MiniTable* submsg, upb_Arena* arena, upb_Status* status) {
|
|
|
|
upb_MiniTableSub sub;
|
|
|
|
sub.submsg = submsg;
|
|
|
|
return _upb_MiniTableExtension_Build(
|
|
|
|
data, len, extendee, sub, kUpb_MiniTablePlatform_Native, arena, status);
|
|
|
|
}
|
|
|
|
|
|
|
|
UPB_API_INLINE upb_MiniTableExtension* upb_MiniTableExtension_BuildEnum(
|
|
|
|
const char* data, size_t len, const upb_MiniTable* extendee,
|
|
|
|
upb_MiniTableEnum* subenum, upb_Arena* arena, upb_Status* status) {
|
|
|
|
upb_MiniTableSub sub;
|
|
|
|
sub.subenum = subenum;
|
|
|
|
return _upb_MiniTableExtension_Build(
|
|
|
|
data, len, extendee, sub, kUpb_MiniTablePlatform_Native, arena, status);
|
|
|
|
}
|
|
|
|
|
|
|
|
// Like upb_MiniTable_Build(), but the user provides a buffer of layout data so
|
|
|
|
// it can be reused from call to call, avoiding repeated realloc()/free().
|
|
|
|
//
|
|
|
|
// The caller owns `*buf` both before and after the call, and must free() it
|
|
|
|
// when it is no longer in use. The function will realloc() `*buf` as
|
|
|
|
// necessary, updating `*size` accordingly.
|
|
|
|
upb_MiniTable* upb_MiniTable_BuildWithBuf(const char* data, size_t len,
|
|
|
|
upb_MiniTablePlatform platform,
|
|
|
|
upb_Arena* arena, void** buf,
|
|
|
|
size_t* buf_size, upb_Status* status);
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
} /* extern "C" */
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include "upb/port/undef.inc"
|
|
|
|
|
|
|
|
#endif /* UPB_MINI_TABLE_DECODE_H_ */
|