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.

158 lines
6.8 KiB

/*
* Copyright (c) 2009-2021, 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_REFLECTION_DEF_BUILDER_INTERNAL_H_
#define UPB_REFLECTION_DEF_BUILDER_INTERNAL_H_
#include "upb/reflection/common.h"
#include "upb/reflection/def_pool_internal.h"
#include "upb/reflection/def_type.h"
// Must be last.
#include "upb/port/def.inc"
// We want to copy the options verbatim into the destination options proto.
// We use serialize+parse as our deep copy.
#define UPB_DEF_SET_OPTIONS(target, desc_type, options_type, proto) \
if (UPB_DESC(desc_type##_has_options)(proto)) { \
size_t size; \
char* pb = UPB_DESC(options_type##_serialize)( \
UPB_DESC(desc_type##_options)(proto), ctx->tmp_arena, &size); \
if (!pb) _upb_DefBuilder_OomErr(ctx); \
target = \
UPB_DESC(options_type##_parse)(pb, size, _upb_DefBuilder_Arena(ctx)); \
if (!target) _upb_DefBuilder_OomErr(ctx); \
} else { \
target = (const UPB_DESC(options_type)*)kUpbDefOptDefault; \
}
#ifdef __cplusplus
extern "C" {
#endif
struct upb_DefBuilder {
upb_DefPool* symtab;
upb_FileDef* file; // File we are building.
upb_Arena* arena; // Allocate defs here.
upb_Arena* tmp_arena; // For temporary allocations.
upb_Status* status; // Record errors here.
const upb_MiniTableFile* layout; // NULL if we should build layouts.
upb is self-hosting! This CL changes the upb compiler to no longer depend on C++ protobuf libraries. upb now uses its own reflection libraries to implement its code generator. # Key Benefits 1. upb can now use its own reflection libraries throughout the compiler. This makes upb more consistent and principled, and gives us more chances to dogfood our own C++ reflection API. This highlighted several parts of the C++ reflection API that were incomplete. 2. This CL removes code duplication that previously existed in the compiler. The upb reflection library has code to build MiniDescriptors and MiniTables out of descriptors, but prior to this CL the upb compiler could not use it. The upb compiler had a separate copy of this logic, and the compiler's copy of this logic was especially tricky and hard to maintain. This CL removes the separate copy of that logic. 3. This CL (mostly) removes upb's dependency on the C++ protobuf library. We still depend on `protoc` (the binary), but the runtime and compiler no longer link against C++'s libraries. This opens up the possibility of speeding up some builds significantly if we can use a prebuilt `protoc` binary. # Bootstrap Stages To bootstrap, we check in a copy of our generated code for `descriptor.proto` and `plugin.proto`. This allows the compiler to depend on the generated code for these two protos without creating a circular dependency. This code is checked in to the `stage0` directory. The bootstrapping process is divided into a few stages. All `cc_library()`, `upb_proto_library()`, and `cc_binary()` targets that would otherwise be circular participate in this staging process. That currently includes: * `//third_party/upb:descriptor_upb_proto` * `//third_party/upb:plugin_upb_proto` * `//third_party/upb:reflection` * `//third_party/upb:reflection_internal` * `//third_party/upbc:common` * `//third_party/upbc:file_layout` * `//third_party/upbc:plugin` * `//third_party/upbc:protoc-gen-upb` For each of these targets, we produce a rule for each stage (the logic for this is nicely encapsulated in Blaze/Bazel macros like `bootstrap_cc_library()` and `bootstrap_upb_proto_library()`, so the `BUILD` file remains readable). For example: * `//third_party/upb:descriptor_upb_proto_stage0` * `//third_party/upb:descriptor_upb_proto_stage1` * `//third_party/upb:descriptor_upb_proto` The stages are: 1. `stage0`: This uses the checked-in version of the generated code. The stage0 compiler is correct and outputs the same code as all other compilers, but it is unnecessarily slow because its protos were compiled in bootstrap mode. The stage0 compiler is used to generate protos for stage1. 2. `stage1`: The stage1 compiler is correct and fast, and therefore we use it in almost all cases (eg. `upb_proto_library()`). However its own protos were not generated using `upb_proto_library()`, so its `cc_library()` targets cannot be safely mixed with `upb_proto_library()`, as this would lead to duplicate symbols. 3. final (no stage): The final compiler is identical to the `stage1` compiler. The only difference is that its protos were built with `upb_proto_library()`. This doesn't matter very much for the compiler binary, but for the `cc_library()` targets like `//third_party/upb:reflection`, only the final targets can be safely linked in by other applications. # "Bootstrap Mode" Protos The checked-in generated code is generated in a special "bootstrap" mode that is a bit different than normal generated code. Bootstrap mode avoids depending on the internal representation of MiniTables or the messages, at the cost of slower runtime performance. Bootstrap mode only interacts with MiniTables and messages using public APIs such as `upb_MiniTable_Build()`, `upb_Message_GetInt32()`, etc. This is very important as it allows us to change the internal representation without needing to regenerate our bootstrap protos. This will make it far easier to write CLs that change the internal representation, because it avoids the awkward dance of trying to regenerate the bootstrap protos when the compiler itself is broken due to bootstrap protos being out of date. The bootstrap generated code does have two downsides: 1. The accessors are less efficient, because they look up MiniTable fields by number instead of hard-coding the MiniTableField into the generated code. 2. It requires runtime initialization of the MiniTables, which costs CPU cycles at startup, and also allocates memory which is never freed. Per google3 rules this is not really a leak, since this memory is still reachable via static variables, but it is undesirable in many contexts. We could fix this part by introducing the equivalent of `google::protobuf::ShutdownProtobufLibrary()`). These downsides are fine for the bootstrapping process, but they are reason enough not to enable bootstrap mode in general for all protos. # Bootstrapping Always Uses OSS Protos To enable smooth syncing between Google3 and OSS, we always use an OSS version of the checked in generated code for `stage0`, even in google3. This requires that the google3 code can be switched to reference the OSS proto names using a preprocessor define. We introduce the `UPB_DESC(xyz)` macro for this, which will expand into either `proto2_xyz` or `google_protobuf_xyz`. Any libraries used in `stage0` must use `UPB_DESC(xyz)` rather than refer to the symbol names directly. PiperOrigin-RevId: 501458451
2 years ago
upb_MiniTablePlatform platform; // Platform we are targeting.
int enum_count; // Count of enums built so far.
int msg_count; // Count of messages built so far.
int ext_count; // Count of extensions built so far.
jmp_buf err; // longjmp() on error.
};
extern const char* kUpbDefOptDefault;
// ctx->status has already been set elsewhere so just fail/longjmp()
UPB_NORETURN void _upb_DefBuilder_FailJmp(upb_DefBuilder* ctx);
UPB_NORETURN void _upb_DefBuilder_Errf(upb_DefBuilder* ctx, const char* fmt,
...) UPB_PRINTF(2, 3);
UPB_NORETURN void _upb_DefBuilder_OomErr(upb_DefBuilder* ctx);
const char* _upb_DefBuilder_MakeFullName(upb_DefBuilder* ctx,
const char* prefix,
upb_StringView name);
// Given a symbol and the base symbol inside which it is defined,
// find the symbol's definition.
const void* _upb_DefBuilder_ResolveAny(upb_DefBuilder* ctx,
const char* from_name_dbg,
const char* base, upb_StringView sym,
upb_deftype_t* type);
const void* _upb_DefBuilder_Resolve(upb_DefBuilder* ctx,
const char* from_name_dbg, const char* base,
upb_StringView sym, upb_deftype_t type);
char _upb_DefBuilder_ParseEscape(upb_DefBuilder* ctx, const upb_FieldDef* f,
const char** src, const char* end);
const char* _upb_DefBuilder_FullToShort(const char* fullname);
UPB_INLINE void* _upb_DefBuilder_Alloc(upb_DefBuilder* ctx, size_t bytes) {
if (bytes == 0) return NULL;
void* ret = upb_Arena_Malloc(ctx->arena, bytes);
if (!ret) _upb_DefBuilder_OomErr(ctx);
return ret;
}
// Adds a symbol |v| to the symtab, which must be a def pointer previously
// packed with pack_def(). The def's pointer to upb_FileDef* must be set before
// adding, so we know which entries to remove if building this file fails.
UPB_INLINE void _upb_DefBuilder_Add(upb_DefBuilder* ctx, const char* name,
upb_value v) {
upb_StringView sym = {.data = name, .size = strlen(name)};
bool ok = _upb_DefPool_InsertSym(ctx->symtab, sym, v, ctx->status);
if (!ok) _upb_DefBuilder_FailJmp(ctx);
}
UPB_INLINE upb_Arena* _upb_DefBuilder_Arena(const upb_DefBuilder* ctx) {
return ctx->arena;
}
UPB_INLINE upb_FileDef* _upb_DefBuilder_File(const upb_DefBuilder* ctx) {
return ctx->file;
}
// This version of CheckIdent() is only called by other, faster versions after
// they detect a parsing error.
void _upb_DefBuilder_CheckIdentSlow(upb_DefBuilder* ctx, upb_StringView name,
bool full);
// Verify a full identifier string. This is slightly more complicated than
// verifying a relative identifier string because we must track '.' chars.
UPB_INLINE void _upb_DefBuilder_CheckIdentFull(upb_DefBuilder* ctx,
upb_StringView name) {
bool good = name.size > 0;
bool start = true;
for (size_t i = 0; i < name.size; i++) {
const char c = name.data[i];
const char d = c | 0x20; // force lowercase
const bool is_alpha = (('a' <= d) & (d <= 'z')) | (c == '_');
const bool is_numer = ('0' <= c) & (c <= '9') & !start;
const bool is_dot = (c == '.') & !start;
good &= is_alpha | is_numer | is_dot;
start = is_dot;
}
if (!good) _upb_DefBuilder_CheckIdentSlow(ctx, name, true);
}
#ifdef __cplusplus
} /* extern "C" */
#endif
#include "upb/port/undef.inc"
#endif /* UPB_REFLECTION_DEF_BUILDER_INTERNAL_H_ */