[Mlir-commits] [mlir] mlir/Presburger: contribute a free-standing parser (PR #94916)

[Jay Foad]

================
@@ -0,0 +1,161 @@
+//===- Lexer.cpp - Presburger Lexer Implementation ------------------------===//
+//
+// 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 implements the lexer for the Presburger textual form.
+//
+//===----------------------------------------------------------------------===//
+
+#include "Lexer.h"
+#include "Token.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/ADT/StringSwitch.h"
+#include "llvm/ADT/Twine.h"
+#include "llvm/Support/SourceMgr.h"
+
+using namespace mlir::presburger;
+
+Lexer::Lexer(const llvm::SourceMgr &sourceMgr) : sourceMgr(sourceMgr) {
+  auto bufferID = sourceMgr.getMainFileID();
+  curBuffer = sourceMgr.getMemoryBuffer(bufferID)->getBuffer();
+  curPtr = curBuffer.begin();
+}
+
+/// emitError - Emit an error message and return an Token::error token.
+Token Lexer::emitError(const char *loc, const llvm::Twine &message) {
+  sourceMgr.PrintMessage(SMLoc::getFromPointer(loc), llvm::SourceMgr::DK_Error,
+                         message);
+  return formToken(Token::error, loc);
+}
+
+Token Lexer::lexToken() {
+  while (true) {
+    const char *tokStart = curPtr;
+
+    // Lex the next token.
+    switch (*curPtr++) {
+    default:
+      // Handle bare identifiers.
+      if (isalpha(curPtr[-1]))
+        return lexBareIdentifierOrKeyword(tokStart);
+
+      // Unknown character, emit an error.
+      return emitError(tokStart, "unexpected character");
+
+    case ' ':
+    case '\t':
+    case '\n':
+    case '\r':
+      // Handle whitespace.
+      continue;
+
+    case '_':
+      // Handle bare identifiers.
+      return lexBareIdentifierOrKeyword(tokStart);
+
+    case 0:
+      // This may either be a nul character in the source file or may be the EOF
+      // marker that llvm::MemoryBuffer guarantees will be there.
+      if (curPtr - 1 == curBuffer.end())
+        return formToken(Token::eof, tokStart);
+      continue;
----------------
jayfoad wrote:

This should probably be an unknown character error?

https://github.com/llvm/llvm-project/pull/94916