[mlir] Refactor the Parser library in preparation for an MLIR binary format

The current Parser library is solely focused on providing API for
the textual MLIR format, but MLIR will soon also provide a binary
format. This commit renames the current Parser library to AsmParser to
better correspond to what the library is actually intended for. A new
Parser library is added which will act as a unified parser interface
between both text and binary formats. Most parser clients are
unaffected, given that the unified interface is essentially the same as
the current interface. Only clients that rely on utilizing the
AsmParserState, or those that want to parse Attributes/Types need to be
updated to point to the AsmParser library.

Differential Revision: https://reviews.llvm.org/D129605

Author: River707

mlir/include/mlir/AsmParser/AsmParser.h

@@ -0,0 +1,90 @@
+//===- AsmParser.h - MLIR AsmParser Library Interface -----------*- 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
+//
+//===----------------------------------------------------------------------===//
+//
+// This file is contains the interface to the MLIR assembly parser library.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_ASMPARSER_ASMPARSER_H
+#define MLIR_ASMPARSER_ASMPARSER_H
+
+#include "mlir/IR/AsmState.h"
+#include <cstddef>
+
+namespace llvm {
+class SourceMgr;
+class StringRef;
+} // namespace llvm
+
+namespace mlir {
+class AsmParserState;
+class AsmParserCodeCompleteContext;
+
+/// This parses the file specified by the indicated SourceMgr and appends parsed
+/// operations to the given block. If the block is non-empty, the operations are
+/// placed before the current terminator. If parsing is successful, success is
+/// returned. Otherwise, an error message is emitted through the error handler
+/// registered in the context, and failure is returned. If `sourceFileLoc` is
+/// non-null, it is populated with a file location representing the start of the
+/// source file that is being parsed. If `asmState` is non-null, it is populated
+/// with detailed information about the parsed IR (including exact locations for
+/// SSA uses and definitions). `asmState` should only be provided if this
+/// detailed information is desired. If `codeCompleteContext` is non-null, it is
+/// used to signal tracking of a code completion event (generally only ever
+/// useful for LSP or other high level language tooling).
+LogicalResult
+parseAsmSourceFile(const llvm::SourceMgr &sourceMgr, Block *block,
+                   const ParserConfig &config,
+                   AsmParserState *asmState = nullptr,
+                   AsmParserCodeCompleteContext *codeCompleteContext = nullptr);
+
+/// This parses a single MLIR attribute to an MLIR context if it was valid.  If
+/// not, an error message is emitted through a new SourceMgrDiagnosticHandler
+/// constructed from a new SourceMgr with a single a MemoryBuffer wrapping
+/// `attrStr`. If the passed `attrStr` has additional tokens that were not part
+/// of the type, an error is emitted.
+// TODO: Improve diagnostic reporting.
+Attribute parseAttribute(llvm::StringRef attrStr, MLIRContext *context);
+Attribute parseAttribute(llvm::StringRef attrStr, Type type);
+
+/// This parses a single MLIR attribute to an MLIR context if it was valid.  If
+/// not, an error message is emitted through a new SourceMgrDiagnosticHandler
+/// constructed from a new SourceMgr with a single a MemoryBuffer wrapping
+/// `attrStr`. The number of characters of `attrStr` parsed in the process is
+/// returned in `numRead`.
+Attribute parseAttribute(llvm::StringRef attrStr, MLIRContext *context,
+                         size_t &numRead);
+Attribute parseAttribute(llvm::StringRef attrStr, Type type, size_t &numRead);
+
+/// This parses a single MLIR type to an MLIR context if it was valid.  If not,
+/// an error message is emitted through a new SourceMgrDiagnosticHandler
+/// constructed from a new SourceMgr with a single a MemoryBuffer wrapping
+/// `typeStr`. If the passed `typeStr` has additional tokens that were not part
+/// of the type, an error is emitted.
+// TODO: Improve diagnostic reporting.
+Type parseType(llvm::StringRef typeStr, MLIRContext *context);
+
+/// This parses a single MLIR type to an MLIR context if it was valid.  If not,
+/// an error message is emitted through a new SourceMgrDiagnosticHandler
+/// constructed from a new SourceMgr with a single a MemoryBuffer wrapping
+/// `typeStr`. The number of characters of `typeStr` parsed in the process is
+/// returned in `numRead`.
+Type parseType(llvm::StringRef typeStr, MLIRContext *context, size_t &numRead);
+
+/// This parses a single IntegerSet to an MLIR context if it was valid. If not,
+/// an error message is emitted through a new SourceMgrDiagnosticHandler
+/// constructed from a new SourceMgr with a single MemoryBuffer wrapping
+/// `str`. If the passed `str` has additional tokens that were not part of the
+/// IntegerSet, a failure is returned. Diagnostics are printed on failure if
+/// `printDiagnosticInfo` is true.
+IntegerSet parseIntegerSet(llvm::StringRef str, MLIRContext *context,
+                           bool printDiagnosticInfo = true);
+
+} // namespace mlir
+
+#endif // MLIR_ASMPARSER_ASMPARSER_H

mlir/include/mlir/Parser/AsmParserState.h renamed to mlir/include/mlir/AsmParser/AsmParserState.h

@@ -6,8 +6,8 @@
 //
 //===----------------------------------------------------------------------===//
 
-#ifndef MLIR_PARSER_ASMPARSERSTATE_H
-#define MLIR_PARSER_ASMPARSERSTATE_H
+#ifndef MLIR_ASMPARSER_ASMPARSERSTATE_H
+#define MLIR_ASMPARSER_ASMPARSERSTATE_H
 
 #include "mlir/Support/LLVM.h"
 #include "llvm/ADT/ArrayRef.h"
@@ -179,4 +179,4 @@ class AsmParserState {
 
 } // namespace mlir
 
-#endif // MLIR_PARSER_ASMPARSERSTATE_H
+#endif // MLIR_ASMPARSER_ASMPARSERSTATE_H

mlir/include/mlir/Parser/CodeComplete.h renamed to mlir/include/mlir/AsmParser/CodeComplete.h

@@ -6,8 +6,8 @@
 //
 //===----------------------------------------------------------------------===//
 
-#ifndef MLIR_PARSER_CODECOMPLETE_H
-#define MLIR_PARSER_CODECOMPLETE_H
+#ifndef MLIR_ASMPARSER_CODECOMPLETE_H
+#define MLIR_ASMPARSER_CODECOMPLETE_H
 
 #include "mlir/Support/LLVM.h"
 #include "llvm/ADT/StringMap.h"
@@ -75,4 +75,4 @@ class AsmParserCodeCompleteContext {
 };
 } // namespace mlir
 
-#endif // MLIR_PARSER_CODECOMPLETE_H
+#endif // MLIR_ASMPARSER_CODECOMPLETE_H

mlir/include/mlir/IR/AsmState.h

@@ -290,7 +290,7 @@ class AsmResourcePrinter {
 //===----------------------------------------------------------------------===//
 
 /// This class represents a configuration for the MLIR assembly parser. It
-/// contains all of the necessary state to parse a textual MLIR source file.
+/// contains all of the necessary state to parse a MLIR source file.
 class ParserConfig {
 public:
   ParserConfig(MLIRContext *context) : context(context) {

mlir/include/mlir/Parser/Parser.h

@@ -6,7 +6,7 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file is contains the interface to the MLIR parser library.
+// This file is contains a unified interface for parsing serialized MLIR.
 //
 //===----------------------------------------------------------------------===//
 
@@ -15,7 +15,7 @@
 
 #include "mlir/IR/AsmState.h"
 #include "mlir/IR/Builders.h"
-#include "mlir/IR/BuiltinOps.h"
+#include "mlir/IR/OwningOpRef.h"
 #include <cstddef>
 
 namespace llvm {
@@ -25,9 +25,6 @@ class StringRef;
 } // namespace llvm
 
 namespace mlir {
-class AsmParserState;
-class AsmParserCodeCompleteContext;
-
 namespace detail {
 
 /// Given a block containing operations that have just been parsed, if the block
@@ -81,16 +78,10 @@ inline OwningOpRef<ContainerOpT> constructContainerOpForParserIfNecessary(
 /// returned. Otherwise, an error message is emitted through the error handler
 /// registered in the context, and failure is returned. If `sourceFileLoc` is
 /// non-null, it is populated with a file location representing the start of the
-/// source file that is being parsed. If `asmState` is non-null, it is populated
-/// with detailed information about the parsed IR (including exact locations for
-/// SSA uses and definitions). `asmState` should only be provided if this
-/// detailed information is desired. If `codeCompleteContext` is non-null, it is
-/// used to signal tracking of a code completion event (generally only ever
-/// useful for LSP or other high level language tooling).
-LogicalResult parseSourceFile(
-    const llvm::SourceMgr &sourceMgr, Block *block, const ParserConfig &config,
-    LocationAttr *sourceFileLoc = nullptr, AsmParserState *asmState = nullptr,
-    AsmParserCodeCompleteContext *codeCompleteContext = nullptr);
+/// source file that is being parsed.
+LogicalResult parseSourceFile(const llvm::SourceMgr &sourceMgr, Block *block,
+                              const ParserConfig &config,
+                              LocationAttr *sourceFileLoc = nullptr);
 
 /// This parses the file specified by the indicated filename and appends parsed
 /// operations to the given block. If the block is non-empty, the operations are
@@ -109,15 +100,11 @@ LogicalResult parseSourceFile(llvm::StringRef filename, Block *block,
 /// parsing is successful, success is returned. Otherwise, an error message is
 /// emitted through the error handler registered in the context, and failure is
 /// returned. If `sourceFileLoc` is non-null, it is populated with a file
-/// location representing the start of the source file that is being parsed. If
-/// `asmState` is non-null, it is populated with detailed information about the
-/// parsed IR (including exact locations for SSA uses and definitions).
-/// `asmState` should only be provided if this detailed information is desired.
+/// location representing the start of the source file that is being parsed.
 LogicalResult parseSourceFile(llvm::StringRef filename,
                               llvm::SourceMgr &sourceMgr, Block *block,
                               const ParserConfig &config,
-                              LocationAttr *sourceFileLoc = nullptr,
-                              AsmParserState *asmState = nullptr);
+                              LocationAttr *sourceFileLoc = nullptr);
 
 /// This parses the IR string and appends parsed operations to the given block.
 /// If the block is non-empty, the operations are placed before the current
@@ -208,48 +195,6 @@ inline OwningOpRef<ContainerOpT> parseSourceString(llvm::StringRef sourceStr,
       &block, config.getContext(), sourceFileLoc);
 }
 
-/// This parses a single MLIR attribute to an MLIR context if it was valid.  If
-/// not, an error message is emitted through a new SourceMgrDiagnosticHandler
-/// constructed from a new SourceMgr with a single a MemoryBuffer wrapping
-/// `attrStr`. If the passed `attrStr` has additional tokens that were not part
-/// of the type, an error is emitted.
-// TODO: Improve diagnostic reporting.
-Attribute parseAttribute(llvm::StringRef attrStr, MLIRContext *context);
-Attribute parseAttribute(llvm::StringRef attrStr, Type type);
-
-/// This parses a single MLIR attribute to an MLIR context if it was valid.  If
-/// not, an error message is emitted through a new SourceMgrDiagnosticHandler
-/// constructed from a new SourceMgr with a single a MemoryBuffer wrapping
-/// `attrStr`. The number of characters of `attrStr` parsed in the process is
-/// returned in `numRead`.
-Attribute parseAttribute(llvm::StringRef attrStr, MLIRContext *context,
-                         size_t &numRead);
-Attribute parseAttribute(llvm::StringRef attrStr, Type type, size_t &numRead);
-
-/// This parses a single MLIR type to an MLIR context if it was valid.  If not,
-/// an error message is emitted through a new SourceMgrDiagnosticHandler
-/// constructed from a new SourceMgr with a single a MemoryBuffer wrapping
-/// `typeStr`. If the passed `typeStr` has additional tokens that were not part
-/// of the type, an error is emitted.
-// TODO: Improve diagnostic reporting.
-Type parseType(llvm::StringRef typeStr, MLIRContext *context);
-
-/// This parses a single MLIR type to an MLIR context if it was valid.  If not,
-/// an error message is emitted through a new SourceMgrDiagnosticHandler
-/// constructed from a new SourceMgr with a single a MemoryBuffer wrapping
-/// `typeStr`. The number of characters of `typeStr` parsed in the process is
-/// returned in `numRead`.
-Type parseType(llvm::StringRef typeStr, MLIRContext *context, size_t &numRead);
-
-/// This parses a single IntegerSet to an MLIR context if it was valid. If not,
-/// an error message is emitted through a new SourceMgrDiagnosticHandler
-/// constructed from a new SourceMgr with a single MemoryBuffer wrapping
-/// `str`. If the passed `str` has additional tokens that were not part of the
-/// IntegerSet, a failure is returned. Diagnostics are printed on failure if
-/// `printDiagnosticInfo` is true.
-IntegerSet parseIntegerSet(llvm::StringRef str, MLIRContext *context,
-                           bool printDiagnosticInfo = true);
-
 } // namespace mlir
 
 #endif // MLIR_PARSER_PARSER_H

mlir/lib/Parser/AffineParser.cpp renamed to mlir/lib/AsmParser/AffineParser.cpp

@@ -6,13 +6,13 @@
 //
 //===----------------------------------------------------------------------===//
 
-#ifndef MLIR_LIB_PARSER_ASMPARSERIMPL_H
-#define MLIR_LIB_PARSER_ASMPARSERIMPL_H
+#ifndef MLIR_LIB_ASMPARSER_ASMPARSERIMPL_H
+#define MLIR_LIB_ASMPARSER_ASMPARSERIMPL_H
 
 #include "Parser.h"
+#include "mlir/AsmParser/AsmParserState.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/OpImplementation.h"
-#include "mlir/Parser/AsmParserState.h"
 
 namespace mlir {
 namespace detail {
@@ -566,4 +566,4 @@ class AsmParserImpl : public BaseT {
 } // namespace detail
 } // namespace mlir
 
-#endif // MLIR_LIB_PARSER_ASMPARSERIMPL_H
+#endif // MLIR_LIB_ASMPARSER_ASMPARSERIMPL_H

mlir/lib/Parser/AsmParserImpl.h renamed to mlir/lib/AsmParser/AsmParserImpl.h

@@ -6,7 +6,7 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "mlir/Parser/AsmParserState.h"
+#include "mlir/AsmParser/AsmParserState.h"
 #include "mlir/IR/Operation.h"
 #include "mlir/IR/SymbolTable.h"
 #include "llvm/ADT/StringExtras.h"

mlir/lib/Parser/AsmParserState.cpp renamed to mlir/lib/AsmParser/AsmParserState.cpp

@@ -13,12 +13,12 @@
 #include "Parser.h"
 
 #include "AsmParserImpl.h"
+#include "mlir/AsmParser/AsmParserState.h"
 #include "mlir/IR/AffineMap.h"
 #include "mlir/IR/BuiltinTypes.h"
 #include "mlir/IR/Dialect.h"
 #include "mlir/IR/DialectImplementation.h"
 #include "mlir/IR/IntegerSet.h"
-#include "mlir/Parser/AsmParserState.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/Support/Endian.h"
 

mlir/lib/Parser/AttributeParser.cpp renamed to mlir/lib/AsmParser/AttributeParser.cpp

@@ -0,0 +1,17 @@
+add_mlir_library(MLIRAsmParser
+  AffineParser.cpp
+  AsmParserState.cpp
+  AttributeParser.cpp
+  DialectSymbolParser.cpp
+  Lexer.cpp
+  LocationParser.cpp
+  Parser.cpp
+  Token.cpp
+  TypeParser.cpp
+
+  ADDITIONAL_HEADER_DIRS
+  ${MLIR_MAIN_INCLUDE_DIR}/mlir/Parser
+
+  LINK_LIBS PUBLIC
+  MLIRIR
+  )