Protocol Buffers - Google's data interchange format (grpc依赖) https://developers.google.com/protocol-buffers/
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

155 lines
5.4 KiB

// 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/message/message.h"
#include <math.h>
#include "upb/base/internal/log2.h"
#include "upb/message/internal/message.h"
// Must be last.
#include "upb/port/def.inc"
const float kUpb_FltInfinity = INFINITY;
const double kUpb_Infinity = INFINITY;
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 double kUpb_NaN = NAN;
5 years ago
static const size_t overhead = sizeof(upb_Message_InternalData);
upb_Message* upb_Message_New(const upb_MiniTable* mini_table,
upb_Arena* arena) {
return _upb_Message_New(mini_table, arena);
}
static bool realloc_internal(upb_Message* msg, size_t need, upb_Arena* arena) {
upb_Message_Internal* in = upb_Message_Getinternal(msg);
if (!in->internal) {
/* No internal data, allocate from scratch. */
size_t size = UPB_MAX(128, upb_Log2CeilingSize(need + overhead));
upb_Message_InternalData* internal = upb_Arena_Malloc(arena, size);
if (!internal) return false;
internal->size = size;
internal->unknown_end = overhead;
internal->ext_begin = size;
in->internal = internal;
} else if (in->internal->ext_begin - in->internal->unknown_end < need) {
/* Internal data is too small, reallocate. */
size_t new_size = upb_Log2CeilingSize(in->internal->size + need);
size_t ext_bytes = in->internal->size - in->internal->ext_begin;
size_t new_ext_begin = new_size - ext_bytes;
upb_Message_InternalData* internal =
upb_Arena_Realloc(arena, in->internal, in->internal->size, new_size);
if (!internal) return false;
if (ext_bytes) {
/* Need to move extension data to the end. */
char* ptr = (char*)internal;
memmove(ptr + new_ext_begin, ptr + internal->ext_begin, ext_bytes);
}
internal->ext_begin = new_ext_begin;
internal->size = new_size;
in->internal = internal;
}
UPB_ASSERT(in->internal->ext_begin - in->internal->unknown_end >= need);
return true;
}
bool _upb_Message_AddUnknown(upb_Message* msg, const char* data, size_t len,
upb_Arena* arena) {
if (!realloc_internal(msg, len, arena)) return false;
upb_Message_Internal* in = upb_Message_Getinternal(msg);
memcpy(UPB_PTR_AT(in->internal, in->internal->unknown_end, char), data, len);
in->internal->unknown_end += len;
return true;
5 years ago
}
void _upb_Message_DiscardUnknown_shallow(upb_Message* msg) {
upb_Message_Internal* in = upb_Message_Getinternal(msg);
if (in->internal) {
in->internal->unknown_end = overhead;
}
Fixes for PHP. (#286) - A new PHP-specific upb amalgamation. It contains everything related to upb_msg, but leaves out all of the old handlers-related interfaces and encoders/decoders. # Schema/Defs Changes - Changed `upb_fielddef_msgsubdef()` and `upb_fielddef_enumsubdef()` to return `NULL` instead of assert-failing if the field is not a message or enum. - Added `upb_msgdef_iswrapper()`, to test whether this is a wrapper well-known type. # Decoder - Decoder bugfix: when we parse a submessage inside a oneof, we need to clear out any previous data, so we don't misinterpret it as a pointer to an existing submessage. # JSON Decoder - Allowed well-known types at the top level to have their special processing. - Fixed a bug that could occur when parsing nested empty lists/objects, eg `[[]]`. - Made the "ignore unknown" option also be permissive about unknown enumerators by setting them to 0. # JSON Encoder - Allowed well-known types at the top level to have their special processing. - Removed all spaces after `:` and `,` characters, to match the old encoder and pass goldenfile tests. # Message / Reflection - Changed `upb_msg_hasoneof()` -> `upb_msg_whichoneof()`. The new function returns the `upb_fielddef*` of whichever oneof is set. - Implemented `upb_msg_clearfield()` and added/implemented `upb_msg_clear()`. - Added `upb_msg_discardunknown()`. Part of me thinks this should go in a util library instead of core reflection since it is a recursive algorithm. # Compiler - Always emit descriptors as an array instead of as a string, to avoid exceeding maximum string lengths. If this becomes a speed issue later we can go back to two separate paths.
5 years ago
}
const char* upb_Message_GetUnknown(const upb_Message* msg, size_t* len) {
const upb_Message_Internal* in = upb_Message_Getinternal(msg);
if (in->internal) {
*len = in->internal->unknown_end - overhead;
return (char*)(in->internal + 1);
} else {
*len = 0;
return NULL;
}
5 years ago
}
void upb_Message_DeleteUnknown(upb_Message* msg, const char* data, size_t len) {
upb_Message_Internal* in = upb_Message_Getinternal(msg);
const char* internal_unknown_end =
UPB_PTR_AT(in->internal, in->internal->unknown_end, char);
#ifndef NDEBUG
size_t full_unknown_size;
const char* full_unknown = upb_Message_GetUnknown(msg, &full_unknown_size);
UPB_ASSERT((uintptr_t)data >= (uintptr_t)full_unknown);
UPB_ASSERT((uintptr_t)data < (uintptr_t)(full_unknown + full_unknown_size));
UPB_ASSERT((uintptr_t)(data + len) > (uintptr_t)data);
UPB_ASSERT((uintptr_t)(data + len) <= (uintptr_t)internal_unknown_end);
#endif
if ((data + len) != internal_unknown_end) {
memmove((char*)data, data + len, internal_unknown_end - data - len);
}
in->internal->unknown_end -= len;
}
const upb_Message_Extension* _upb_Message_Getexts(const upb_Message* msg,
size_t* count) {
const upb_Message_Internal* in = upb_Message_Getinternal(msg);
if (in->internal) {
*count = (in->internal->size - in->internal->ext_begin) /
sizeof(upb_Message_Extension);
return UPB_PTR_AT(in->internal, in->internal->ext_begin, void);
} else {
*count = 0;
return NULL;
}
}
const upb_Message_Extension* _upb_Message_Getext(
const upb_Message* msg, const upb_MiniTableExtension* e) {
size_t n;
const upb_Message_Extension* ext = _upb_Message_Getexts(msg, &n);
/* For now we use linear search exclusively to find extensions. If this
* becomes an issue due to messages with lots of extensions, we can introduce
* a table of some sort. */
for (size_t i = 0; i < n; i++) {
if (ext[i].ext == e) {
return &ext[i];
}
}
return NULL;
}
upb_Message_Extension* _upb_Message_GetOrCreateExtension(
upb_Message* msg, const upb_MiniTableExtension* e, upb_Arena* arena) {
upb_Message_Extension* ext =
(upb_Message_Extension*)_upb_Message_Getext(msg, e);
if (ext) return ext;
if (!realloc_internal(msg, sizeof(upb_Message_Extension), arena)) return NULL;
upb_Message_Internal* in = upb_Message_Getinternal(msg);
in->internal->ext_begin -= sizeof(upb_Message_Extension);
ext = UPB_PTR_AT(in->internal, in->internal->ext_begin, void);
memset(ext, 0, sizeof(upb_Message_Extension));
ext->ext = e;
return ext;
}
size_t upb_Message_ExtensionCount(const upb_Message* msg) {
size_t count;
_upb_Message_Getexts(msg, &count);
return count;
}