|
|
|
|
# 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.
|
|
|
|
|
|
|
|
|
|
load(
|
|
|
|
|
"//bazel:build_defs.bzl",
|
|
|
|
|
"UPB_DEFAULT_COPTS",
|
|
|
|
|
"UPB_DEFAULT_CPPOPTS",
|
|
|
|
|
)
|
|
|
|
|
load(
|
|
|
|
|
"//bazel:upb_proto_library.bzl",
|
|
|
|
|
"upb_proto_library",
|
|
|
|
|
"upb_proto_library_copts",
|
|
|
|
|
"upb_proto_reflection_library",
|
|
|
|
|
)
|
|
|
|
|
load("@bazel_skylib//rules:common_settings.bzl", "bool_flag")
|
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
|
|
|
load(
|
|
|
|
|
"//upbc:bootstrap_compiler.bzl",
|
|
|
|
|
"bootstrap_cc_library",
|
|
|
|
|
"bootstrap_upb_proto_library",
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# begin:google_only
|
|
|
|
|
# load(
|
|
|
|
|
# "//third_party/bazel_rules/rules_kotlin/kotlin/native:native_interop_hint.bzl",
|
|
|
|
|
# "kt_native_interop_hint",
|
|
|
|
|
# )
|
|
|
|
|
# load("//tools/build_defs/license:license.bzl", "license")
|
|
|
|
|
# end:google_only
|
|
|
|
|
|
|
|
|
|
# begin:github_only
|
|
|
|
|
load(
|
|
|
|
|
"//bazel:amalgamation.bzl",
|
|
|
|
|
"upb_amalgamation",
|
|
|
|
|
)
|
|
|
|
|
# end:github_only
|
|
|
|
|
|
|
|
|
|
# begin:google_only
|
|
|
|
|
# package(default_applicable_licenses = ["//:license"])
|
|
|
|
|
#
|
|
|
|
|
# license(
|
|
|
|
|
# name = "license",
|
|
|
|
|
# package_name = "upb",
|
|
|
|
|
# )
|
|
|
|
|
# end:google_only
|
|
|
|
|
|
|
|
|
|
licenses(["notice"])
|
|
|
|
|
|
|
|
|
|
exports_files(["LICENSE"])
|
|
|
|
|
|
|
|
|
|
exports_files(
|
|
|
|
|
[
|
|
|
|
|
"BUILD",
|
|
|
|
|
"WORKSPACE",
|
|
|
|
|
],
|
|
|
|
|
visibility = ["//cmake:__pkg__"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
config_setting(
|
|
|
|
|
name = "windows",
|
|
|
|
|
constraint_values = ["@platforms//os:windows"],
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
bool_flag(
|
Added a codegen parameter for whether fasttables are generated or not.
Example:
$ CC=clang bazel build -c opt --copt=-g benchmarks:benchmark --//:fasttable_enabled=false
INFO: Build option --//:fasttable_enabled has changed, discarding analysis cache.
INFO: Analyzed target //benchmarks:benchmark (0 packages loaded, 913 targets configured).
INFO: Found 1 target...
Target //benchmarks:benchmark up-to-date:
bazel-bin/benchmarks/benchmark
INFO: Elapsed time: 0.760s, Critical Path: 0.58s
INFO: 7 processes: 1 internal, 6 linux-sandbox.
INFO: Build completed successfully, 7 total actions
$ bazel-bin/benchmarks/benchmark --benchmark_filter=BM_Parse_Upb
------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------
BM_Parse_Upb_FileDesc_WithArena 10985 ns 10984 ns 63567 651.857MB/s
BM_Parse_Upb_FileDesc_WithInitialBlock 10556 ns 10554 ns 66138 678.458MB/s
$ CC=clang bazel build -c opt --copt=-g benchmarks:benchmark --//:fasttable_enabled=true
INFO: Build option --//:fasttable_enabled has changed, discarding analysis cache.
INFO: Analyzed target //benchmarks:benchmark (0 packages loaded, 913 targets configured).
INFO: Found 1 target...
Target //benchmarks:benchmark up-to-date:
bazel-bin/benchmarks/benchmark
INFO: Elapsed time: 0.744s, Critical Path: 0.58s
INFO: 7 processes: 1 internal, 6 linux-sandbox.
INFO: Build completed successfully, 7 total actions
$ bazel-bin/benchmarks/benchmark --benchmark_filter=BM_Parse_Upb
------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------
BM_Parse_Upb_FileDesc_WithArena 3284 ns 3284 ns 213495 2.1293GB/s
BM_Parse_Upb_FileDesc_WithInitialBlock 2882 ns 2882 ns 243069 2.4262GB/s
Biggest unknown is whether this parameter should default to true or false.
4 years ago
|
|
|
name = "fasttable_enabled",
|
|
|
|
|
build_setting_default = False,
|
Added a codegen parameter for whether fasttables are generated or not.
Example:
$ CC=clang bazel build -c opt --copt=-g benchmarks:benchmark --//:fasttable_enabled=false
INFO: Build option --//:fasttable_enabled has changed, discarding analysis cache.
INFO: Analyzed target //benchmarks:benchmark (0 packages loaded, 913 targets configured).
INFO: Found 1 target...
Target //benchmarks:benchmark up-to-date:
bazel-bin/benchmarks/benchmark
INFO: Elapsed time: 0.760s, Critical Path: 0.58s
INFO: 7 processes: 1 internal, 6 linux-sandbox.
INFO: Build completed successfully, 7 total actions
$ bazel-bin/benchmarks/benchmark --benchmark_filter=BM_Parse_Upb
------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------
BM_Parse_Upb_FileDesc_WithArena 10985 ns 10984 ns 63567 651.857MB/s
BM_Parse_Upb_FileDesc_WithInitialBlock 10556 ns 10554 ns 66138 678.458MB/s
$ CC=clang bazel build -c opt --copt=-g benchmarks:benchmark --//:fasttable_enabled=true
INFO: Build option --//:fasttable_enabled has changed, discarding analysis cache.
INFO: Analyzed target //benchmarks:benchmark (0 packages loaded, 913 targets configured).
INFO: Found 1 target...
Target //benchmarks:benchmark up-to-date:
bazel-bin/benchmarks/benchmark
INFO: Elapsed time: 0.744s, Critical Path: 0.58s
INFO: 7 processes: 1 internal, 6 linux-sandbox.
INFO: Build completed successfully, 7 total actions
$ bazel-bin/benchmarks/benchmark --benchmark_filter=BM_Parse_Upb
------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------
BM_Parse_Upb_FileDesc_WithArena 3284 ns 3284 ns 213495 2.1293GB/s
BM_Parse_Upb_FileDesc_WithInitialBlock 2882 ns 2882 ns 243069 2.4262GB/s
Biggest unknown is whether this parameter should default to true or false.
4 years ago
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
config_setting(
|
|
|
|
|
name = "fasttable_enabled_setting",
|
|
|
|
|
flag_values = {"//:fasttable_enabled": "true"},
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
upb_proto_library_copts(
|
|
|
|
|
name = "upb_proto_library_copts__for_generated_code_only_do_not_use",
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Please update copy.bara.sky target = ":friends" if
|
|
|
|
|
# you make changes to this list.
|
|
|
|
|
package_group(
|
|
|
|
|
name = "friends",
|
|
|
|
|
packages = ["//..."],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Public C/C++ libraries #######################################################
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "port",
|
|
|
|
|
hdrs = [
|
Allow for fuse/free races in `upb_Arena`.
Implementation is by kfm@, I only added the portability code around it.
`upb_Arena` was designed to be only thread-compatible. However, fusing of arenas muddies the waters somewhat, because two distinct `upb_Arena` objects will end up sharing state when fused. This causes a `upb_Arena_Free(a)` to interfere with `upb_Arena_Fuse(b, c)` if `a` and `b` were previously fused.
It turns out that we can use atomics to fix this with about a 35% regression in fuse performance (see below). Arena create+free does not regress, thanks to special-case logic in Free().
`upb_Arena` is still a thread-compatible type, and it is still never safe to call `upb_Arena_xxx(a)` and `upb_Arena_yyy(a)` in parallel. However you can at least now call `upb_Arena_Free(a)` and `upb_Arena_Fuse(b, c)` in parallel, even if `a` and `b` were previously fused.
Note that `upb_Arena_Fuse(a, b)` and `upb_Arena_Fuse(c, d)` is still not allowed if `b` and `c` were previously fused. In practice this means that fuses must still be single-threaded within a single fused group.
Performance results:
```
name old cpu/op new cpu/op delta
BM_ArenaOneAlloc 18.6ns ± 1% 18.6ns ± 1% ~ (p=0.726 n=18+17)
BM_ArenaInitialBlockOneAlloc 6.28ns ± 1% 5.73ns ± 1% -8.68% (p=0.000 n=17+20)
BM_ArenaFuseUnbalanced/2 44.1ns ± 2% 60.4ns ± 1% +37.05% (p=0.000 n=18+19)
BM_ArenaFuseUnbalanced/8 370ns ± 2% 500ns ± 1% +35.12% (p=0.000 n=19+20)
BM_ArenaFuseUnbalanced/64 3.52µs ± 1% 4.71µs ± 1% +33.80% (p=0.000 n=18+19)
BM_ArenaFuseUnbalanced/128 7.20µs ± 1% 9.72µs ± 2% +34.93% (p=0.000 n=16+19)
BM_ArenaFuseBalanced/2 44.4ns ± 2% 61.4ns ± 1% +38.23% (p=0.000 n=20+17)
BM_ArenaFuseBalanced/8 373ns ± 2% 509ns ± 1% +36.57% (p=0.000 n=19+17)
BM_ArenaFuseBalanced/64 3.55µs ± 2% 4.79µs ± 1% +34.80% (p=0.000 n=19+19)
BM_ArenaFuseBalanced/128 7.26µs ± 1% 9.76µs ± 1% +34.45% (p=0.000 n=17+19)
BM_LoadAdsDescriptor_Upb<NoLayout> 5.66ms ± 1% 5.69ms ± 1% +0.57% (p=0.013 n=18+20)
BM_LoadAdsDescriptor_Upb<WithLayout> 6.30ms ± 1% 6.36ms ± 1% +0.90% (p=0.000 n=19+18)
BM_LoadAdsDescriptor_Proto2<NoLayout> 12.1ms ± 1% 12.1ms ± 1% ~ (p=0.118 n=18+18)
BM_LoadAdsDescriptor_Proto2<WithLayout> 12.2ms ± 1% 12.3ms ± 1% +0.50% (p=0.006 n=18+18)
BM_Parse_Upb_FileDesc<UseArena, Copy> 12.7µs ± 1% 12.7µs ± 1% ~ (p=0.194 n=20+19)
BM_Parse_Upb_FileDesc<UseArena, Alias> 11.6µs ± 1% 11.6µs ± 1% ~ (p=0.192 n=20+20)
BM_Parse_Upb_FileDesc<InitBlock, Copy> 12.5µs ± 1% 12.5µs ± 0% ~ (p=0.750 n=18+14)
BM_Parse_Upb_FileDesc<InitBlock, Alias> 11.4µs ± 1% 11.3µs ± 1% -0.34% (p=0.046 n=19+19)
BM_Parse_Proto2<FileDesc, NoArena, Copy> 25.4µs ± 1% 25.7µs ± 2% +1.37% (p=0.000 n=18+18)
BM_Parse_Proto2<FileDesc, UseArena, Copy> 12.1µs ± 2% 12.1µs ± 1% ~ (p=0.143 n=18+18)
BM_Parse_Proto2<FileDesc, InitBlock, Copy> 11.9µs ± 3% 11.9µs ± 1% ~ (p=0.076 n=17+19)
BM_Parse_Proto2<FileDescSV, InitBlock, Alias> 13.2µs ± 1% 13.2µs ± 1% ~ (p=0.053 n=19+19)
BM_SerializeDescriptor_Proto2 5.97µs ± 4% 5.90µs ± 4% ~ (p=0.093 n=17+19)
BM_SerializeDescriptor_Upb 10.4µs ± 1% 10.4µs ± 1% ~ (p=0.909 n=17+18)
name old time/op new time/op delta
BM_ArenaOneAlloc 18.7ns ± 2% 18.6ns ± 0% ~ (p=0.607 n=18+17)
BM_ArenaInitialBlockOneAlloc 6.29ns ± 1% 5.74ns ± 1% -8.71% (p=0.000 n=17+19)
BM_ArenaFuseUnbalanced/2 44.1ns ± 1% 60.6ns ± 1% +37.21% (p=0.000 n=17+19)
BM_ArenaFuseUnbalanced/8 371ns ± 2% 500ns ± 1% +35.02% (p=0.000 n=19+16)
BM_ArenaFuseUnbalanced/64 3.53µs ± 1% 4.72µs ± 1% +33.85% (p=0.000 n=18+19)
BM_ArenaFuseUnbalanced/128 7.22µs ± 1% 9.73µs ± 2% +34.87% (p=0.000 n=16+19)
BM_ArenaFuseBalanced/2 44.5ns ± 2% 61.5ns ± 1% +38.22% (p=0.000 n=20+17)
BM_ArenaFuseBalanced/8 373ns ± 2% 510ns ± 1% +36.58% (p=0.000 n=19+16)
BM_ArenaFuseBalanced/64 3.56µs ± 2% 4.80µs ± 1% +34.87% (p=0.000 n=19+19)
BM_ArenaFuseBalanced/128 7.27µs ± 1% 9.77µs ± 1% +34.40% (p=0.000 n=17+19)
BM_LoadAdsDescriptor_Upb<NoLayout> 5.67ms ± 1% 5.71ms ± 1% +0.60% (p=0.011 n=18+20)
BM_LoadAdsDescriptor_Upb<WithLayout> 6.32ms ± 1% 6.37ms ± 1% +0.87% (p=0.000 n=19+18)
BM_LoadAdsDescriptor_Proto2<NoLayout> 12.1ms ± 1% 12.2ms ± 1% ~ (p=0.126 n=18+19)
BM_LoadAdsDescriptor_Proto2<WithLayout> 12.2ms ± 1% 12.3ms ± 1% +0.51% (p=0.002 n=18+18)
BM_Parse_Upb_FileDesc<UseArena, Copy> 12.7µs ± 1% 12.7µs ± 1% ~ (p=0.149 n=20+19)
BM_Parse_Upb_FileDesc<UseArena, Alias> 11.6µs ± 1% 11.6µs ± 1% ~ (p=0.211 n=20+20)
BM_Parse_Upb_FileDesc<InitBlock, Copy> 12.5µs ± 1% 12.5µs ± 1% ~ (p=0.986 n=18+15)
BM_Parse_Upb_FileDesc<InitBlock, Alias> 11.4µs ± 1% 11.3µs ± 1% ~ (p=0.081 n=19+18)
BM_Parse_Proto2<FileDesc, NoArena, Copy> 25.4µs ± 1% 25.8µs ± 2% +1.41% (p=0.000 n=18+18)
BM_Parse_Proto2<FileDesc, UseArena, Copy> 12.1µs ± 2% 12.1µs ± 1% ~ (p=0.558 n=19+18)
BM_Parse_Proto2<FileDesc, InitBlock, Copy> 12.0µs ± 3% 11.9µs ± 1% ~ (p=0.165 n=17+19)
BM_Parse_Proto2<FileDescSV, InitBlock, Alias> 13.2µs ± 1% 13.2µs ± 1% ~ (p=0.070 n=19+19)
BM_SerializeDescriptor_Proto2 5.98µs ± 4% 5.92µs ± 3% ~ (p=0.138 n=17+19)
BM_SerializeDescriptor_Upb 10.4µs ± 1% 10.4µs ± 1% ~ (p=0.858 n=17+18)
```
PiperOrigin-RevId: 518573683
2 years ago
|
|
|
"upb/port/atomic.h",
|
|
|
|
|
"upb/port/vsnprintf_compat.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
textual_hdrs = [
|
|
|
|
|
"upb/port/def.inc",
|
|
|
|
|
"upb/port/undef.inc",
|
|
|
|
|
],
|
|
|
|
|
visibility = ["//:__subpackages__"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "upb",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/alloc.h",
|
|
|
|
|
"upb/arena.h",
|
|
|
|
|
"upb/array.h",
|
|
|
|
|
"upb/base/descriptor_constants.h",
|
|
|
|
|
"upb/base/status.h",
|
|
|
|
|
"upb/base/string_view.h",
|
|
|
|
|
"upb/collections/array.h",
|
|
|
|
|
"upb/decode.h",
|
|
|
|
|
"upb/encode.h",
|
|
|
|
|
"upb/extension_registry.h",
|
|
|
|
|
"upb/map.h",
|
|
|
|
|
"upb/mem/alloc.h",
|
|
|
|
|
"upb/mem/arena.h",
|
|
|
|
|
"upb/message/extension_internal.h",
|
|
|
|
|
"upb/message/message.h",
|
|
|
|
|
"upb/msg.h",
|
|
|
|
|
"upb/status.h",
|
|
|
|
|
"upb/string_view.h",
|
|
|
|
|
"upb/upb.h",
|
|
|
|
|
"upb/upb.hpp",
|
|
|
|
|
"upb/wire/common.h",
|
|
|
|
|
"upb/wire/decode.h",
|
|
|
|
|
"upb/wire/encode.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":fastdecode",
|
|
|
|
|
":hash",
|
|
|
|
|
":lex",
|
|
|
|
|
":mem",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":port",
|
|
|
|
|
":wire",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "base",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/base/status.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/base/descriptor_constants.h",
|
|
|
|
|
"upb/base/log2.h",
|
|
|
|
|
"upb/base/status.h",
|
|
|
|
|
"upb/base/string_view.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:__subpackages__"],
|
|
|
|
|
deps = [":port"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "message",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/message.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":mem",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":port",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
alias(
|
|
|
|
|
name = "mini_table",
|
|
|
|
|
actual = "//upb/mini_table",
|
|
|
|
|
visibility = ["//:friends"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
alias(
|
|
|
|
|
name = "mini_table_internal",
|
|
|
|
|
actual = "//upb/mini_table:internal",
|
|
|
|
|
visibility = ["//:friends"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "message_internal",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/message/message.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/extension_internal.h",
|
|
|
|
|
"upb/message/internal.h",
|
|
|
|
|
"upb/message/message.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":hash",
|
|
|
|
|
":mem",
|
|
|
|
|
":port",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "message_tagged_ptr",
|
|
|
|
|
hdrs = ["upb/message/tagged_ptr.h"],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:friends"],
|
|
|
|
|
deps = [
|
|
|
|
|
":port",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
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
|
|
|
cc_library(
|
|
|
|
|
name = "message_accessors_internal",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/accessors_internal.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:friends"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":mini_table_internal",
|
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
|
|
|
":port",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "message_accessors",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/message/accessors.c",
|
|
|
|
|
"upb/message/accessors_internal.h",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/accessors.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":mini_table",
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
":wire",
|
|
|
|
|
":wire_reader",
|
|
|
|
|
"//upb/mini_table:internal",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "message_promote",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/message/promote.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/promote.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":hash",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
":wire",
|
|
|
|
|
":wire_reader",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "message_copy",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/message/copy.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/copy.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "message_split64",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/accessors_split64.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":port",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "message_accessors_test",
|
|
|
|
|
srcs = ["upb/message/accessors_test.cc"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
"//upb/mini_descriptor",
|
|
|
|
|
"//upb/mini_descriptor:encode_internal",
|
|
|
|
|
"//upb/mini_descriptor:internal",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
"//upb/test:test_messages_proto2_upb_proto",
|
|
|
|
|
"//upb/test:test_messages_proto3_upb_proto",
|
|
|
|
|
"//upb/test:test_upb_proto",
|
|
|
|
|
"@com_google_absl//absl/container:flat_hash_set",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
"@com_google_protobuf//:protobuf",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "message_promote_test",
|
|
|
|
|
srcs = ["upb/message/promote_test.cc"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections",
|
|
|
|
|
":message_accessors",
|
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
|
|
|
":message_copy",
|
|
|
|
|
":message_promote",
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
"//upb/mini_descriptor:encode_internal",
|
|
|
|
|
"//upb/mini_descriptor:internal",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
"//upb/test:test_messages_proto2_upb_proto",
|
|
|
|
|
"//upb/test:test_messages_proto3_upb_proto",
|
|
|
|
|
"//upb/test:test_upb_proto",
|
|
|
|
|
"@com_google_absl//absl/container:flat_hash_set",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
"@com_google_protobuf//:protobuf",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "message_copy_test",
|
|
|
|
|
srcs = ["upb/message/copy_test.cc"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":message_copy",
|
|
|
|
|
":upb",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
"//upb/test:test_messages_proto2_upb_proto",
|
|
|
|
|
"//upb/test:test_messages_proto3_upb_proto",
|
|
|
|
|
"//upb/test:test_upb_proto",
|
|
|
|
|
"@com_google_absl//absl/container:flat_hash_set",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
"@com_google_protobuf//:protobuf",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "fastdecode",
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":hash",
|
|
|
|
|
":mem_internal",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":port",
|
|
|
|
|
":wire",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Common support routines used by generated code. This library has no
|
|
|
|
|
# implementation, but depends on :upb and exposes a few more hdrs.
|
|
|
|
|
#
|
|
|
|
|
# This is public only because we have no way of visibility-limiting it to
|
|
|
|
|
# upb_proto_library() only. This interface is not stable and by using it you
|
|
|
|
|
# give up any backward compatibility guarantees.
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "generated_code_support__only_for_generated_code_do_not_use__i_give_permission_to_break_me",
|
|
|
|
|
hdrs = ["upb/generated_code_support.h"],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
textual_hdrs = [
|
|
|
|
|
"upb/port/def.inc",
|
|
|
|
|
"upb/port/undef.inc",
|
|
|
|
|
],
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":message_accessors_internal",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":upb",
|
|
|
|
|
":wire_internal",
|
|
|
|
|
"//upb/mini_descriptor",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Common support code for C++ generated code.
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "generated_cpp_support__only_for_generated_code_do_not_use__i_give_permission_to_break_me",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/message.h",
|
|
|
|
|
"upb/port/def.inc",
|
|
|
|
|
"upb/port/undef.inc",
|
|
|
|
|
"upb/upb.hpp",
|
|
|
|
|
"upb/wire/decode.h",
|
|
|
|
|
"upb/wire/decode_fast.h",
|
|
|
|
|
"upb/wire/encode.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":hash",
|
|
|
|
|
":message_copy",
|
|
|
|
|
":upb",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "generated_reflection_support__only_for_generated_code_do_not_use__i_give_permission_to_break_me",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/port/def.inc",
|
|
|
|
|
"upb/port/undef.inc",
|
|
|
|
|
"upb/reflection/def.h",
|
|
|
|
|
"upb/reflection/def_pool_internal.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":reflection_internal",
|
|
|
|
|
"//upb/mini_descriptor",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
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
|
|
|
bootstrap_upb_proto_library(
|
|
|
|
|
name = "descriptor_upb_proto",
|
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
|
|
|
base_dir = "upb/reflection/",
|
|
|
|
|
# TODO(b/289127200): Export 'net/proto2/proto/descriptor.upb.h' and remove "-layering_check".
|
|
|
|
|
features = ["-layering_check"],
|
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
|
|
|
google3_src_files = ["net/proto2/proto/descriptor.proto"],
|
|
|
|
|
google3_src_rules = ["//net/proto2/proto:descriptor_proto_source"],
|
|
|
|
|
oss_src_files = ["google/protobuf/descriptor.proto"],
|
|
|
|
|
oss_src_rules = ["@com_google_protobuf//:descriptor_proto_srcs"],
|
|
|
|
|
oss_strip_prefix = "third_party/protobuf/github/bootstrap/src",
|
|
|
|
|
proto_lib_deps = ["@com_google_protobuf//:descriptor_proto"],
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
upb_proto_reflection_library(
|
|
|
|
|
name = "descriptor_upb_proto_reflection",
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = ["@com_google_protobuf//:descriptor_proto"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "collections",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/collections/array.h",
|
|
|
|
|
"upb/collections/map.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":mem",
|
|
|
|
|
":port",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "message_rep_internal",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/message/internal/map_entry.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":hash",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "collections_internal",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/collections/array.c",
|
|
|
|
|
"upb/collections/map.c",
|
|
|
|
|
"upb/collections/map_sorter.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/collections/array.h",
|
|
|
|
|
"upb/collections/array_internal.h",
|
|
|
|
|
"upb/collections/map.h",
|
|
|
|
|
"upb/collections/map_gencode_util.h",
|
|
|
|
|
"upb/collections/map_internal.h",
|
|
|
|
|
"upb/collections/map_sorter_internal.h",
|
|
|
|
|
"upb/collections/message_value.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:__subpackages__"],
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":hash",
|
|
|
|
|
":mem",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":message_rep_internal",
|
|
|
|
|
":message_tagged_ptr",
|
|
|
|
|
":port",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "collections_split64",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/collections/array_split64.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections",
|
|
|
|
|
":port",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# TODO(b/232091617): Once we can delete the deprecated forwarding headers
|
|
|
|
|
# (= everything in upb/) we can move this build target down into reflection/
|
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
|
|
|
bootstrap_cc_library(
|
|
|
|
|
name = "reflection",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/def.h",
|
|
|
|
|
"upb/def.hpp",
|
|
|
|
|
"upb/reflection.h",
|
|
|
|
|
"upb/reflection.hpp",
|
|
|
|
|
"upb/reflection/def.h",
|
|
|
|
|
"upb/reflection/def.hpp",
|
|
|
|
|
"upb/reflection/message.h",
|
|
|
|
|
"upb/reflection/message.hpp",
|
|
|
|
|
],
|
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
|
|
|
bootstrap_deps = [":reflection_internal"],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections",
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
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
|
|
|
bootstrap_cc_library(
|
|
|
|
|
name = "reflection_internal",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/reflection/def_builder.c",
|
|
|
|
|
"upb/reflection/def_pool.c",
|
|
|
|
|
"upb/reflection/def_type.c",
|
|
|
|
|
"upb/reflection/desc_state.c",
|
|
|
|
|
"upb/reflection/enum_def.c",
|
|
|
|
|
"upb/reflection/enum_reserved_range.c",
|
|
|
|
|
"upb/reflection/enum_value_def.c",
|
|
|
|
|
"upb/reflection/extension_range.c",
|
|
|
|
|
"upb/reflection/field_def.c",
|
|
|
|
|
"upb/reflection/file_def.c",
|
|
|
|
|
"upb/reflection/message.c",
|
|
|
|
|
"upb/reflection/message_def.c",
|
|
|
|
|
"upb/reflection/message_reserved_range.c",
|
|
|
|
|
"upb/reflection/method_def.c",
|
|
|
|
|
"upb/reflection/oneof_def.c",
|
|
|
|
|
"upb/reflection/service_def.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/reflection/common.h",
|
|
|
|
|
"upb/reflection/def.h",
|
|
|
|
|
"upb/reflection/def.hpp",
|
|
|
|
|
"upb/reflection/def_builder_internal.h",
|
|
|
|
|
"upb/reflection/def_pool.h",
|
|
|
|
|
"upb/reflection/def_pool_internal.h",
|
|
|
|
|
"upb/reflection/def_type.h",
|
|
|
|
|
"upb/reflection/desc_state_internal.h",
|
|
|
|
|
"upb/reflection/enum_def.h",
|
|
|
|
|
"upb/reflection/enum_def_internal.h",
|
|
|
|
|
"upb/reflection/enum_reserved_range.h",
|
|
|
|
|
"upb/reflection/enum_reserved_range_internal.h",
|
|
|
|
|
"upb/reflection/enum_value_def.h",
|
|
|
|
|
"upb/reflection/enum_value_def_internal.h",
|
|
|
|
|
"upb/reflection/extension_range.h",
|
|
|
|
|
"upb/reflection/extension_range_internal.h",
|
|
|
|
|
"upb/reflection/field_def.h",
|
|
|
|
|
"upb/reflection/field_def_internal.h",
|
|
|
|
|
"upb/reflection/file_def.h",
|
|
|
|
|
"upb/reflection/file_def_internal.h",
|
|
|
|
|
"upb/reflection/message.h",
|
|
|
|
|
"upb/reflection/message.hpp",
|
|
|
|
|
"upb/reflection/message_def.h",
|
|
|
|
|
"upb/reflection/message_def_internal.h",
|
|
|
|
|
"upb/reflection/message_reserved_range.h",
|
|
|
|
|
"upb/reflection/message_reserved_range_internal.h",
|
|
|
|
|
"upb/reflection/method_def.h",
|
|
|
|
|
"upb/reflection/method_def_internal.h",
|
|
|
|
|
"upb/reflection/oneof_def.h",
|
|
|
|
|
"upb/reflection/oneof_def_internal.h",
|
|
|
|
|
"upb/reflection/service_def.h",
|
|
|
|
|
"upb/reflection/service_def_internal.h",
|
|
|
|
|
],
|
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
|
|
|
bootstrap_deps = [":descriptor_upb_proto"],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections",
|
|
|
|
|
":hash",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
"//upb/mini_descriptor",
|
|
|
|
|
"//upb/mini_descriptor:encode_internal",
|
|
|
|
|
"//upb/mini_descriptor:internal",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "textformat",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/text/encode.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/text/encode.h",
|
|
|
|
|
"upb/text_encode.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":lex",
|
|
|
|
|
":port",
|
|
|
|
|
":reflection",
|
|
|
|
|
":wire",
|
|
|
|
|
":wire_reader",
|
|
|
|
|
":wire_types",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
alias(
|
|
|
|
|
name = "json",
|
|
|
|
|
actual = "//upb/json",
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Tests ########################################################################
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "def_builder_test",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/reflection/common.h",
|
|
|
|
|
"upb/reflection/def_builder_internal.h",
|
|
|
|
|
"upb/reflection/def_builder_test.cc",
|
|
|
|
|
"upb/reflection/def_type.h",
|
|
|
|
|
],
|
|
|
|
|
deps = [
|
|
|
|
|
":descriptor_upb_proto",
|
|
|
|
|
":hash",
|
|
|
|
|
":port",
|
|
|
|
|
":reflection",
|
|
|
|
|
":reflection_internal",
|
|
|
|
|
":upb",
|
|
|
|
|
"@com_google_absl//absl/strings",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "collections_test",
|
|
|
|
|
srcs = ["upb/collections/test.cc"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections",
|
|
|
|
|
":upb",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "message_test",
|
|
|
|
|
srcs = ["upb/message/test.cc"],
|
|
|
|
|
deps = [
|
|
|
|
|
":json",
|
|
|
|
|
":message_test_upb_proto",
|
|
|
|
|
":message_test_upb_proto_reflection",
|
|
|
|
|
":reflection",
|
|
|
|
|
":upb",
|
|
|
|
|
"//upb/json",
|
|
|
|
|
"//upb/test:fuzz_util",
|
|
|
|
|
"//upb/test:test_messages_proto3_upb_proto",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
proto_library(
|
|
|
|
|
name = "message_test_proto",
|
|
|
|
|
testonly = 1,
|
|
|
|
|
srcs = ["upb/message/test.proto"],
|
|
|
|
|
deps = ["@com_google_protobuf//src/google/protobuf:test_messages_proto3_proto"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
upb_proto_library(
|
|
|
|
|
name = "message_test_upb_proto",
|
|
|
|
|
testonly = 1,
|
|
|
|
|
deps = [":message_test_proto"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
upb_proto_reflection_library(
|
|
|
|
|
name = "message_test_upb_proto_reflection",
|
|
|
|
|
testonly = 1,
|
|
|
|
|
deps = [":message_test_proto"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "atoi_test",
|
|
|
|
|
srcs = ["upb/lex/atoi_test.cc"],
|
|
|
|
|
copts = UPB_DEFAULT_CPPOPTS,
|
|
|
|
|
deps = [
|
|
|
|
|
":lex",
|
|
|
|
|
"@com_google_absl//absl/strings",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "hash_test",
|
|
|
|
|
srcs = ["upb/hash/test.cc"],
|
|
|
|
|
copts = UPB_DEFAULT_CPPOPTS,
|
|
|
|
|
deps = [
|
|
|
|
|
":hash",
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Internal C/C++ libraries #####################################################
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "mem",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/mem/alloc.h",
|
|
|
|
|
"upb/mem/arena.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:__subpackages__"],
|
|
|
|
|
deps = [
|
|
|
|
|
":mem_internal",
|
|
|
|
|
":port",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "arena_test",
|
|
|
|
|
srcs = ["upb/mem/arena_test.cc"],
|
|
|
|
|
deps = [
|
|
|
|
|
":port",
|
|
|
|
|
":upb",
|
|
|
|
|
"@com_google_absl//absl/random",
|
|
|
|
|
"@com_google_absl//absl/random:distributions",
|
|
|
|
|
"@com_google_absl//absl/synchronization",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "mem_internal",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/mem/alloc.c",
|
|
|
|
|
"upb/mem/arena.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/mem/alloc.h",
|
|
|
|
|
"upb/mem/arena.h",
|
|
|
|
|
"upb/mem/arena_internal.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:__subpackages__"],
|
|
|
|
|
deps = [":port"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "wire",
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/wire/decode.h",
|
|
|
|
|
"upb/wire/encode.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":mem",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":port",
|
|
|
|
|
":wire_internal",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "wire_internal",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/wire/decode.c",
|
|
|
|
|
"upb/wire/decode_fast.c",
|
|
|
|
|
"upb/wire/encode.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/wire/common.h",
|
|
|
|
|
"upb/wire/common_internal.h",
|
|
|
|
|
"upb/wire/decode.h",
|
|
|
|
|
"upb/wire/decode_fast.h",
|
|
|
|
|
"upb/wire/decode_internal.h",
|
|
|
|
|
"upb/wire/encode.h",
|
|
|
|
|
"upb/wire/swap_internal.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:__subpackages__"],
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":mem_internal",
|
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
|
|
|
":message_accessors_internal",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":message_rep_internal",
|
|
|
|
|
":port",
|
|
|
|
|
":wire_reader",
|
|
|
|
|
":wire_types",
|
|
|
|
|
"//upb/mini_table",
|
|
|
|
|
"@utf8_range",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "wire_types",
|
|
|
|
|
hdrs = ["upb/wire/types.h"],
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "eps_copy_input_stream",
|
|
|
|
|
srcs = ["upb/wire/eps_copy_input_stream.c"],
|
|
|
|
|
hdrs = ["upb/wire/eps_copy_input_stream.h"],
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":mem",
|
|
|
|
|
":port",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "wire_reader",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/wire/reader.c",
|
|
|
|
|
"upb/wire/swap_internal.h",
|
|
|
|
|
],
|
|
|
|
|
hdrs = ["upb/wire/reader.h"],
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":port",
|
|
|
|
|
":wire_types",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_test(
|
|
|
|
|
name = "eps_copy_input_stream_test",
|
|
|
|
|
srcs = ["upb/wire/eps_copy_input_stream_test.cc"],
|
|
|
|
|
deps = [
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":upb",
|
|
|
|
|
"@com_google_googletest//:gtest_main",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "hash",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/hash/common.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/hash/common.h",
|
|
|
|
|
"upb/hash/int_table.h",
|
|
|
|
|
"upb/hash/str_table.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:__subpackages__"],
|
|
|
|
|
deps = [
|
|
|
|
|
":base",
|
|
|
|
|
":mem",
|
|
|
|
|
":port",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "lex",
|
|
|
|
|
srcs = [
|
|
|
|
|
"upb/lex/atoi.c",
|
|
|
|
|
"upb/lex/round_trip.c",
|
|
|
|
|
"upb/lex/strtod.c",
|
|
|
|
|
"upb/lex/unicode.c",
|
|
|
|
|
],
|
|
|
|
|
hdrs = [
|
|
|
|
|
"upb/lex/atoi.h",
|
|
|
|
|
"upb/lex/round_trip.h",
|
|
|
|
|
"upb/lex/strtod.h",
|
|
|
|
|
"upb/lex/unicode.h",
|
|
|
|
|
],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
visibility = ["//:__subpackages__"],
|
|
|
|
|
deps = [":port"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_binary(
|
|
|
|
|
name = "libupb.so",
|
|
|
|
|
srcs = ["upb/upb_so.c"],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS + ["-DUPB_BUILD_API"],
|
|
|
|
|
linkshared = 1,
|
|
|
|
|
linkstatic = 1,
|
|
|
|
|
visibility = ["//visibility:public"],
|
|
|
|
|
deps = [
|
|
|
|
|
":collections",
|
|
|
|
|
":collections_split64",
|
|
|
|
|
":mem",
|
|
|
|
|
":message",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":message_split64",
|
|
|
|
|
":mini_table",
|
|
|
|
|
":port",
|
|
|
|
|
"//upb/mini_descriptor",
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Amalgamation #################################################################
|
|
|
|
|
|
|
|
|
|
# begin:github_only
|
|
|
|
|
|
|
|
|
|
upb_amalgamation(
|
|
|
|
|
name = "gen_amalgamation",
|
|
|
|
|
outs = [
|
|
|
|
|
"upb.c",
|
|
|
|
|
"upb.h",
|
|
|
|
|
],
|
|
|
|
|
libs = [
|
|
|
|
|
":base",
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":descriptor_upb_proto",
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":fastdecode",
|
|
|
|
|
":generated_code_support__only_for_generated_code_do_not_use__i_give_permission_to_break_me",
|
|
|
|
|
":hash",
|
|
|
|
|
":lex",
|
|
|
|
|
":mem_internal",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":message_rep_internal",
|
|
|
|
|
":message_tagged_ptr",
|
|
|
|
|
":port",
|
|
|
|
|
":reflection_internal",
|
|
|
|
|
":reflection",
|
|
|
|
|
":upb",
|
|
|
|
|
":wire_internal",
|
|
|
|
|
":wire_reader",
|
|
|
|
|
":wire_types",
|
|
|
|
|
"//upb/mini_descriptor:encode_internal",
|
|
|
|
|
"//upb/mini_descriptor:internal",
|
|
|
|
|
"//upb/mini_descriptor:mini_descriptor",
|
|
|
|
|
"//upb/mini_table:internal",
|
|
|
|
|
"//upb/mini_table:mini_table",
|
|
|
|
|
],
|
|
|
|
|
strip_import_prefix = ["src"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "amalgamation",
|
|
|
|
|
srcs = ["upb.c"],
|
|
|
|
|
hdrs = ["upb.h"],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
deps = ["@utf8_range"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
upb_amalgamation(
|
|
|
|
|
name = "gen_php_amalgamation",
|
|
|
|
|
outs = [
|
|
|
|
|
"php-upb.c",
|
|
|
|
|
"php-upb.h",
|
|
|
|
|
],
|
|
|
|
|
libs = [
|
|
|
|
|
":base",
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":descriptor_upb_proto_reflection",
|
|
|
|
|
":descriptor_upb_proto",
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":fastdecode",
|
|
|
|
|
":generated_code_support__only_for_generated_code_do_not_use__i_give_permission_to_break_me",
|
|
|
|
|
":hash",
|
|
|
|
|
":json",
|
|
|
|
|
":lex",
|
|
|
|
|
":mem_internal",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":message_rep_internal",
|
|
|
|
|
":message_tagged_ptr",
|
|
|
|
|
":port",
|
|
|
|
|
":reflection_internal",
|
|
|
|
|
":reflection",
|
|
|
|
|
":upb",
|
|
|
|
|
":wire_internal",
|
|
|
|
|
":wire_reader",
|
|
|
|
|
":wire_types",
|
|
|
|
|
"//upb/mini_descriptor:encode_internal",
|
|
|
|
|
"//upb/mini_descriptor:internal",
|
|
|
|
|
"//upb/mini_descriptor:mini_descriptor",
|
|
|
|
|
"//upb/mini_table:internal",
|
|
|
|
|
"//upb/mini_table:mini_table",
|
|
|
|
|
],
|
|
|
|
|
prefix = "php-",
|
|
|
|
|
strip_import_prefix = ["src"],
|
|
|
|
|
visibility = ["@com_google_protobuf//php:__subpackages__"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "php_amalgamation",
|
|
|
|
|
srcs = ["php-upb.c"],
|
|
|
|
|
hdrs = ["php-upb.h"],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
deps = ["@utf8_range"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
upb_amalgamation(
|
|
|
|
|
name = "gen_ruby_amalgamation",
|
|
|
|
|
outs = [
|
|
|
|
|
"ruby-upb.c",
|
|
|
|
|
"ruby-upb.h",
|
|
|
|
|
],
|
|
|
|
|
libs = [
|
|
|
|
|
":base",
|
|
|
|
|
":collections_internal",
|
|
|
|
|
":descriptor_upb_proto",
|
|
|
|
|
":eps_copy_input_stream",
|
|
|
|
|
":fastdecode",
|
|
|
|
|
":generated_code_support__only_for_generated_code_do_not_use__i_give_permission_to_break_me",
|
|
|
|
|
":hash",
|
|
|
|
|
":json",
|
|
|
|
|
":lex",
|
|
|
|
|
":mem_internal",
|
|
|
|
|
":message_accessors",
|
|
|
|
|
":message_internal",
|
|
|
|
|
":message_rep_internal",
|
|
|
|
|
":message_tagged_ptr",
|
|
|
|
|
":port",
|
|
|
|
|
":reflection_internal",
|
|
|
|
|
":reflection",
|
|
|
|
|
":upb",
|
|
|
|
|
":wire_internal",
|
|
|
|
|
":wire_reader",
|
|
|
|
|
":wire_types",
|
|
|
|
|
"//upb/mini_descriptor:encode_internal",
|
|
|
|
|
"//upb/mini_descriptor:internal",
|
|
|
|
|
"//upb/mini_descriptor:mini_descriptor",
|
|
|
|
|
"//upb/mini_table:internal",
|
|
|
|
|
"//upb/mini_table:mini_table",
|
|
|
|
|
],
|
|
|
|
|
prefix = "ruby-",
|
|
|
|
|
strip_import_prefix = ["src"],
|
|
|
|
|
visibility = ["@com_google_protobuf//ruby:__subpackages__"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
cc_library(
|
|
|
|
|
name = "ruby_amalgamation",
|
|
|
|
|
srcs = ["ruby-upb.c"],
|
|
|
|
|
hdrs = ["ruby-upb.h"],
|
|
|
|
|
copts = UPB_DEFAULT_COPTS,
|
|
|
|
|
deps = ["@utf8_range"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
exports_files(
|
|
|
|
|
[
|
|
|
|
|
"third_party/lunit/console.lua",
|
|
|
|
|
"third_party/lunit/lunit.lua",
|
|
|
|
|
],
|
|
|
|
|
visibility = ["//lua:__pkg__"],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
filegroup(
|
|
|
|
|
name = "source_files",
|
|
|
|
|
srcs = glob(
|
|
|
|
|
[
|
|
|
|
|
"upb/**/*.c",
|
|
|
|
|
"upb/**/*.h",
|
|
|
|
|
"upb/**/*.hpp",
|
|
|
|
|
"upb/**/*.inc",
|
|
|
|
|
],
|
|
|
|
|
exclude = [
|
|
|
|
|
"upb/**/conformance_upb.c",
|
|
|
|
|
"upb/reflection/stage0/**/*",
|
|
|
|
|
],
|
|
|
|
|
),
|
|
|
|
|
visibility = [
|
|
|
|
|
"//cmake:__pkg__",
|
|
|
|
|
"//python/dist:__pkg__",
|
|
|
|
|
]
|
|
|
|
|
)
|
|
|
|
|
# end:github_only
|
|
|
|
|
|
|
|
|
|
# begin:google_only
|
|
|
|
|
#
|
|
|
|
|
# py_binary(
|
|
|
|
|
# name = "update_check_runs",
|
|
|
|
|
# srcs = ["update_check_runs.py"],
|
|
|
|
|
# main = "update_check_runs.py",
|
|
|
|
|
# deps = [
|
|
|
|
|
# "//third_party/py/absl:app",
|
|
|
|
|
# "//third_party/py/absl/flags",
|
|
|
|
|
# ],
|
|
|
|
|
# )
|
|
|
|
|
#
|
|
|
|
|
# kt_native_interop_hint(
|
|
|
|
|
# name = "upb_kotlin_native_hint",
|
|
|
|
|
# compatible_with = ["//buildenv/target:non_prod"],
|
|
|
|
|
# headers_to_exclude = glob([
|
|
|
|
|
# "**/*.hpp",
|
|
|
|
|
# ]),
|
|
|
|
|
# kotlin_package = "upb",
|
|
|
|
|
# no_string_conversion = ["_upb_MiniTable_Build"],
|
|
|
|
|
# strict_enums = ["upb_FieldType"],
|
|
|
|
|
# visibility = ["//:__subpackages__"],
|
|
|
|
|
# )
|
|
|
|
|
#
|
|
|
|
|
# end:google_only
|
