1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 20:23:11 +01:00
llvm-mirror/lib/TableGen/JSONBackend.cpp

189 lines
5.8 KiB
C++
Raw Normal View History

[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
//===- JSONBackend.cpp - Generate a JSON dump of all records. -*- C++ -*-=====//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
//
//===----------------------------------------------------------------------===//
//
// This TableGen back end generates a machine-readable representation
// of all the classes and records defined by the input, in JSON format.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/BitVector.h"
#include "llvm/Support/Debug.h"
#include "llvm/TableGen/Error.h"
#include "llvm/TableGen/Record.h"
#include "llvm/TableGen/TableGenBackend.h"
#include "llvm/Support/JSON.h"
#define DEBUG_TYPE "json-emitter"
using namespace llvm;
namespace {
class JSONEmitter {
private:
RecordKeeper &Records;
json::Value translateInit(const Init &I);
json::Array listSuperclasses(const Record &R);
public:
JSONEmitter(RecordKeeper &R);
void run(raw_ostream &OS);
};
} // end anonymous namespace
JSONEmitter::JSONEmitter(RecordKeeper &R) : Records(R) {}
json::Value JSONEmitter::translateInit(const Init &I) {
// Init subclasses that we return as JSON primitive values of one
// kind or another.
if (isa<UnsetInit>(&I)) {
return nullptr;
} else if (auto *Bit = dyn_cast<BitInit>(&I)) {
return Bit->getValue() ? 1 : 0;
} else if (auto *Bits = dyn_cast<BitsInit>(&I)) {
json::Array array;
for (unsigned i = 0, limit = Bits->getNumBits(); i < limit; i++)
array.push_back(translateInit(*Bits->getBit(i)));
return std::move(array);
[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
} else if (auto *Int = dyn_cast<IntInit>(&I)) {
return Int->getValue();
} else if (auto *Str = dyn_cast<StringInit>(&I)) {
return Str->getValue();
} else if (auto *Code = dyn_cast<CodeInit>(&I)) {
return Code->getValue();
} else if (auto *List = dyn_cast<ListInit>(&I)) {
json::Array array;
for (auto val : *List)
array.push_back(translateInit(*val));
return std::move(array);
[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
}
// Init subclasses that we return as JSON objects containing a
// 'kind' discriminator. For these, we also provide the same
// translation back into TableGen input syntax that -print-records
// would give.
json::Object obj;
obj["printable"] = I.getAsString();
if (auto *Def = dyn_cast<DefInit>(&I)) {
obj["kind"] = "def";
obj["def"] = Def->getDef()->getName();
return std::move(obj);
[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
} else if (auto *Var = dyn_cast<VarInit>(&I)) {
obj["kind"] = "var";
obj["var"] = Var->getName();
return std::move(obj);
[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
} else if (auto *VarBit = dyn_cast<VarBitInit>(&I)) {
if (auto *Var = dyn_cast<VarInit>(VarBit->getBitVar())) {
obj["kind"] = "varbit";
obj["var"] = Var->getName();
obj["index"] = VarBit->getBitNum();
return std::move(obj);
[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
}
} else if (auto *Dag = dyn_cast<DagInit>(&I)) {
obj["kind"] = "dag";
obj["operator"] = translateInit(*Dag->getOperator());
if (auto name = Dag->getName())
obj["name"] = name->getAsUnquotedString();
json::Array args;
for (unsigned i = 0, limit = Dag->getNumArgs(); i < limit; ++i) {
json::Array arg;
arg.push_back(translateInit(*Dag->getArg(i)));
if (auto argname = Dag->getArgName(i))
arg.push_back(argname->getAsUnquotedString());
else
arg.push_back(nullptr);
args.push_back(std::move(arg));
}
obj["args"] = std::move(args);
return std::move(obj);
[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
}
// Final fallback: anything that gets past here is simply given a
// kind field of 'complex', and the only other field is the standard
// 'printable' representation.
assert(!I.isConcrete());
obj["kind"] = "complex";
return std::move(obj);
[TableGen] Add a general-purpose JSON backend. The aim of this backend is to output everything TableGen knows about the record set, similarly to the default -print-records backend. But where -print-records produces output in TableGen's input syntax (convenient for humans to read), this backend produces it as structured JSON data, which is convenient for loading into standard scripting languages such as Python, in order to extract information from the data set in an automated way. The output data contains a JSON representation of the variable definitions in output 'def' records, and a few pieces of metadata such as which of those definitions are tagged with the 'field' prefix and which defs are derived from which classes. It doesn't dump out absolutely every piece of knowledge it _could_ produce, such as type information and complicated arithmetic operator nodes in abstract superclasses; the main aim is to allow consumers of this JSON dump to essentially act as new backends, and backends don't generally need to depend on that kind of data. The new backend is implemented as an EmitJSON() function similar to all of llvm-tblgen's other EmitFoo functions, except that it lives in lib/TableGen instead of utils/TableGen on the basis that I'm expecting to add it to clang-tblgen too in a future patch. To test it, I've written a Python script that loads the JSON output and tests properties of it based on comments in the .td source - more or less like FileCheck, except that the CHECK: lines have Python expressions after them instead of textual pattern matches. Reviewers: nhaehnle Reviewed By: nhaehnle Subscribers: arichardson, labath, mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D46054 llvm-svn: 336771
2018-07-11 10:40:19 +02:00
}
void JSONEmitter::run(raw_ostream &OS) {
json::Object root;
root["!tablegen_json_version"] = 1;
// Prepare the arrays that will list the instances of every class.
// We mostly fill those in by iterating over the superclasses of
// each def, but we also want to ensure we store an empty list for a
// class with no instances at all, so we do a preliminary iteration
// over the classes, invoking std::map::operator[] to default-
// construct the array for each one.
std::map<std::string, json::Array> instance_lists;
for (const auto &C : Records.getClasses()) {
auto &Name = C.second->getNameInitAsString();
(void)instance_lists[Name];
}
// Main iteration over the defs.
for (const auto &D : Records.getDefs()) {
auto &Name = D.second->getNameInitAsString();
auto &Def = *D.second;
json::Object obj;
json::Array fields;
for (const RecordVal &RV : Def.getValues()) {
if (!Def.isTemplateArg(RV.getNameInit())) {
auto Name = RV.getNameInitAsString();
if (RV.getPrefix())
fields.push_back(Name);
obj[Name] = translateInit(*RV.getValue());
}
}
obj["!fields"] = std::move(fields);
json::Array superclasses;
for (const auto &SuperPair : Def.getSuperClasses())
superclasses.push_back(SuperPair.first->getNameInitAsString());
obj["!superclasses"] = std::move(superclasses);
obj["!name"] = Name;
obj["!anonymous"] = Def.isAnonymous();
root[Name] = std::move(obj);
// Add this def to the instance list for each of its superclasses.
for (const auto &SuperPair : Def.getSuperClasses()) {
auto SuperName = SuperPair.first->getNameInitAsString();
instance_lists[SuperName].push_back(Name);
}
}
// Make a JSON object from the std::map of instance lists.
json::Object instanceof;
for (auto kv: instance_lists)
instanceof[kv.first] = std::move(kv.second);
root["!instanceof"] = std::move(instanceof);
// Done. Write the output.
OS << json::Value(std::move(root)) << "\n";
}
namespace llvm {
void EmitJSON(RecordKeeper &RK, raw_ostream &OS) { JSONEmitter(RK).run(OS); }
} // end namespace llvm