Add .rc scripts tokenizer.

This extends the shell of llvm-rc tool with the ability of tokenization
of the input files. Currently, ASCII and ASCII-compatible UTF-8 files
are supported.

Thanks to Nico Weber (thakis) for his original work in this area.

Differential Revision: https://reviews.llvm.org/D35957

llvm-svn: 310621

test/tools/llvm-rc/tokenizer.test

@@ -0,0 +1,35 @@
+; RUN: llvm-rc /V %p/Inputs/tokens.rc | FileCheck %s
+
+; CHECK:  Int: 1; int value = 1
+; CHECK-NEXT:  Plus: +
+; CHECK-NEXT:  Int: 2; int value = 2
+; CHECK-NEXT:  Minus: -
+; CHECK-NEXT:  Int: 3214L; int value = 3214
+; CHECK-NEXT:  Amp: &
+; CHECK-NEXT:  Int: 0x120894; int value = 1181844
+; CHECK-NEXT:  Int: 032173; int value = 13435
+; CHECK-NEXT:  Int: 2; int value = 2
+; CHECK-NEXT:  Pipe: |
+; CHECK-NEXT:  Amp: &
+; CHECK-NEXT:  Tilde: ~
+; CHECK-NEXT:  Plus: +
+; CHECK-NEXT:  LeftParen: (
+; CHECK-NEXT:  Minus: -
+; CHECK-NEXT:  Int: 7; int value = 7
+; CHECK-NEXT:  RightParen: )
+; CHECK-NEXT:  BlockBegin: {
+; CHECK-NEXT:  Int: 0xabcdef; int value = 11259375
+; CHECK-NEXT:  Int: 0xABCDEFl; int value = 11259375
+; CHECK-NEXT:  BlockEnd: }
+; CHECK-NEXT:  BlockBegin: Begin
+; CHECK-NEXT:  BlockEnd: End
+; CHECK-NEXT:  Identifier: He11o
+; CHECK-NEXT:  Identifier: LLVM
+; CHECK-NEXT:  String: "RC string test."
+; CHECK-NEXT:  Comma: ,
+; CHECK-NEXT:  String: L"Another RC string test.'&{"
+; CHECK-NEXT:  Comma: ,
+; CHECK-NEXT:  Int: 42; int value = 42
+; CHECK-NEXT:  Comma: ,
+; CHECK-NEXT:  Int: 100; int value = 100
+; CHECK-NEXT:  String: ":))"

tools/llvm-rc/CMakeLists.txt

@@ -10,4 +10,5 @@ add_public_tablegen_target(RcTableGen)
 
 add_llvm_tool(llvm-rc
   llvm-rc.cpp
+  ResourceScriptToken.cpp
   )

tools/llvm-rc/ResourceScriptToken.cpp

@@ -0,0 +1,296 @@
+//===-- ResourceScriptToken.cpp ---------------------------------*- C++-*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===---------------------------------------------------------------------===//
+//
+// This file implements an interface defined in ResourceScriptToken.h.
+// In particular, it defines an .rc script tokenizer.
+//
+//===---------------------------------------------------------------------===//
+
+#include "ResourceScriptToken.h"
+#include "llvm/Support/raw_ostream.h"
+
+#include <algorithm>
+#include <cassert>
+#include <cctype>
+#include <cstdlib>
+#include <utility>
+
+using namespace llvm;
+
+using Kind = RCToken::Kind;
+
+// Checks if Representation is a correct description of an RC integer.
+// It should be a 32-bit unsigned integer, either decimal, octal (0[0-7]+),
+// or hexadecimal (0x[0-9a-f]+). It might be followed by a single 'L'
+// character (that is the difference between our representation and
+// StringRef's one). If Representation is correct, 'true' is returned and
+// the return value is put back in Num.
+static bool rcGetAsInteger(StringRef Representation, uint32_t &Num) {
+  size_t Length = Representation.size();
+  if (Length == 0)
+    return false;
+  // Strip the last 'L' if unnecessary.
+  if (std::toupper(Representation.back()) == 'L')
+    Representation = Representation.drop_back(1);
+
+  return !Representation.getAsInteger<uint32_t>(0, Num);
+}
+
+RCToken::RCToken(RCToken::Kind RCTokenKind, StringRef Value)
+    : TokenKind(RCTokenKind), TokenValue(Value) {}
+
+uint32_t RCToken::intValue() const {
+  assert(TokenKind == Kind::Int);
+  // We assume that the token already is a correct integer (checked by
+  // rcGetAsInteger).
+  uint32_t Result;
+  bool IsSuccess = rcGetAsInteger(TokenValue, Result);
+  assert(IsSuccess);
+  (void)IsSuccess;  // Silence the compiler warning when -DNDEBUG flag is on.
+  return Result;
+}
+
+StringRef RCToken::value() const { return TokenValue; }
+
+Kind RCToken::kind() const { return TokenKind; }
+
+static Error getStringError(const Twine &message) {
+  return make_error<StringError>("Error parsing file: " + message,
+                                 inconvertibleErrorCode());
+}
+
+namespace {
+
+class Tokenizer {
+public:
+  Tokenizer(StringRef Input) : Data(Input), DataLength(Input.size()) {}
+
+  Expected<std::vector<RCToken>> run();
+
+private:
+  // All 'advancing' methods return boolean values; if they're equal to false,
+  // the stream has ended or failed.
+  bool advance(size_t Amount = 1);
+  bool skipWhitespaces();
+
+  // Consumes a token. If any problem occurred, a non-empty Error is returned.
+  Error consumeToken(const Kind TokenKind);
+
+  // Check if tokenizer is about to read FollowingChars.
+  bool willNowRead(StringRef FollowingChars) const;
+
+  // Check if tokenizer can start reading an identifier at current position.
+  // The original tool did non specify the rules to determine what is a correct
+  // identifier. We assume they should follow the C convention:
+  // [a-zA-z_][a-zA-Z0-9_]*.
+  bool canStartIdentifier() const;
+  // Check if tokenizer can continue reading an identifier.
+  bool canContinueIdentifier() const;
+
+  // Check if tokenizer can start reading an integer.
+  // A correct integer always starts with a 0-9 digit,
+  // can contain characters 0-9A-Fa-f (digits),
+  // Ll (marking the integer is 32-bit), Xx (marking the representation
+  // is hexadecimal). As some kind of separator should come after the
+  // integer, we can consume the integer until a non-alphanumeric
+  // character.
+  bool canStartInt() const;
+  bool canContinueInt() const;
+
+  bool canStartString() const;
+
+  bool streamEof() const;
+
+  // Classify the token that is about to be read from the current position.
+  Kind classifyCurrentToken() const;
+
+  // Process the Kind::Identifier token - check if it is
+  // an identifier describing a block start or end.
+  void processIdentifier(RCToken &token) const;
+
+  StringRef Data;
+  size_t DataLength, Pos;
+};
+
+Expected<std::vector<RCToken>> Tokenizer::run() {
+  Pos = 0;
+  std::vector<RCToken> Result;
+
+  // Consume an optional UTF-8 Byte Order Mark.
+  if (willNowRead("\xef\xbb\xbf"))
+    advance(3);
+
+  while (!streamEof()) {
+    if (!skipWhitespaces())
+      break;
+
+    Kind TokenKind = classifyCurrentToken();
+    if (TokenKind == Kind::Invalid)
+      return getStringError("Invalid token found at position " + Twine(Pos));
+
+    const size_t TokenStart = Pos;
+    if (Error TokenError = consumeToken(TokenKind))
+      return std::move(TokenError);
+
+    RCToken Token(TokenKind, Data.take_front(Pos).drop_front(TokenStart));
+    if (TokenKind == Kind::Identifier) {
+      processIdentifier(Token);
+    } else if (TokenKind == Kind::Int) {
+      uint32_t TokenInt;
+      if (!rcGetAsInteger(Token.value(), TokenInt)) {
+        // The integer has incorrect format or cannot be represented in
+        // a 32-bit integer.
+        return getStringError("Integer invalid or too large: " +
+                              Token.value().str());
+      }
+    }
+
+    Result.push_back(Token);
+  }
+
+  return Result;
+}
+
+bool Tokenizer::advance(size_t Amount) {
+  Pos += Amount;
+  return !streamEof();
+}
+
+bool Tokenizer::skipWhitespaces() {
+  while (!streamEof() && std::isspace(Data[Pos]))
+    advance();
+  return !streamEof();
+}
+
+Error Tokenizer::consumeToken(const Kind TokenKind) {
+  switch (TokenKind) {
+  // One-character token consumption.
+#define TOKEN(Name)
+#define SHORT_TOKEN(Name, Ch) case Kind::Name:
+#include "ResourceScriptTokenList.h"
+#undef TOKEN
+#undef SHORT_TOKEN
+    advance();
+    return Error::success();
+
+  case Kind::Identifier:
+    while (!streamEof() && canContinueIdentifier())
+      advance();
+    return Error::success();
+
+  case Kind::Int:
+    while (!streamEof() && canContinueInt())
+      advance();
+    return Error::success();
+
+  case Kind::String:
+    // Consume the preceding 'L', if there is any.
+    if (std::toupper(Data[Pos]) == 'L')
+      advance();
+    // Consume the double-quote.
+    advance();
+
+    // Consume the characters until the end of the file, line or string.
+    while (true) {
+      if (streamEof()) {
+        return getStringError("Unterminated string literal.");
+      } else if (Data[Pos] == '"') {
+        // Consume the ending double-quote.
+        advance();
+        return Error::success();
+      } else if (Data[Pos] == '\n') {
+        return getStringError("String literal not terminated in the line.");
+      }
+
+      advance();
+    }
+
+  case Kind::Invalid:
+    assert(false && "Cannot consume an invalid token.");
+  }
+}
+
+bool Tokenizer::willNowRead(StringRef FollowingChars) const {
+  return Data.drop_front(Pos).startswith(FollowingChars);
+}
+
+bool Tokenizer::canStartIdentifier() const {
+  assert(!streamEof());
+
+  const char CurChar = Data[Pos];
+  return std::isalpha(CurChar) || CurChar == '_';
+}
+
+bool Tokenizer::canContinueIdentifier() const {
+  assert(!streamEof());
+  const char CurChar = Data[Pos];
+  return std::isalnum(CurChar) || CurChar == '_';
+}
+
+bool Tokenizer::canStartInt() const {
+  assert(!streamEof());
+  return std::isdigit(Data[Pos]);
+}
+
+bool Tokenizer::canContinueInt() const {
+  assert(!streamEof());
+  return std::isalnum(Data[Pos]);
+}
+
+bool Tokenizer::canStartString() const {
+  return willNowRead("\"") || willNowRead("L\"") || willNowRead("l\"");
+}
+
+bool Tokenizer::streamEof() const { return Pos == DataLength; }
+
+Kind Tokenizer::classifyCurrentToken() const {
+  if (canStartInt())
+    return Kind::Int;
+  if (canStartString())
+    return Kind::String;
+  // BEGIN and END are at this point of lexing recognized as identifiers.
+  if (canStartIdentifier())
+    return Kind::Identifier;
+
+  const char CurChar = Data[Pos];
+
+  switch (CurChar) {
+  // One-character token classification.
+#define TOKEN(Name)
+#define SHORT_TOKEN(Name, Ch)                                                  \
+  case Ch:                                                                     \
+    return Kind::Name;
+#include "ResourceScriptTokenList.h"
+#undef TOKEN
+#undef SHORT_TOKEN
+
+  default:
+    return Kind::Invalid;
+  }
+}
+
+void Tokenizer::processIdentifier(RCToken &Token) const {
+  assert(Token.kind() == Kind::Identifier);
+  StringRef Name = Token.value();
+
+  if (Name.equals_lower("begin"))
+    Token = RCToken(Kind::BlockBegin, Name);
+  else if (Name.equals_lower("end"))
+    Token = RCToken(Kind::BlockEnd, Name);
+}
+
+} // anonymous namespace
+
+namespace llvm {
+
+Expected<std::vector<RCToken>> tokenizeRC(StringRef Input) {
+  return Tokenizer(Input).run();
+}
+
+} // namespace llvm

tools/llvm-rc/ResourceScriptToken.h

@@ -0,0 +1,81 @@
+//===-- ResourceScriptToken.h -----------------------------------*- C++-*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===---------------------------------------------------------------------===//
+//
+// This declares the .rc script tokens and defines an interface for tokenizing
+// the input data. The list of available tokens is located at
+// ResourceScriptTokenList.h.
+//
+// Note that the tokenizer does not support comments or preprocessor
+// directives. The preprocessor should do its work on the .rc file before
+// running llvm-rc.
+//
+// As for now, it is possible to parse ASCII files only (the behavior on
+// UTF files might be undefined). However, it already consumes UTF-8 BOM, if
+// there is any. Thus, ASCII-compatible UTF-8 files are tokenized correctly.
+//
+// Ref: msdn.microsoft.com/en-us/library/windows/desktop/aa380599(v=vs.85).aspx
+//
+//===---------------------------------------------------------------------===//
+
+#ifndef LLVM_TOOLS_LLVMRC_RESOURCESCRIPTTOKEN_H
+#define LLVM_TOOLS_LLVMRC_RESOURCESCRIPTTOKEN_H
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/Error.h"
+
+#include <cstdint>
+#include <map>
+#include <string>
+#include <vector>
+
+namespace llvm {
+
+// A definition of a single resource script token. Each token has its kind
+// (declared in ResourceScriptTokenList) and holds a value - a reference
+// representation of the token.
+// RCToken does not claim ownership on its value. A memory buffer containing
+// the token value should be stored in a safe place and cannot be freed
+// nor reallocated.
+class RCToken {
+public:
+  enum class Kind {
+#define TOKEN(Name) Name,
+#define SHORT_TOKEN(Name, Ch) Name,
+#include "ResourceScriptTokenList.h"
+#undef TOKEN
+#undef SHORT_TOKEN
+  };
+
+  RCToken(RCToken::Kind RCTokenKind, StringRef Value);
+
+  // Get an integer value of the integer token.
+  uint32_t intValue() const;
+
+  StringRef value() const;
+  Kind kind() const;
+
+private:
+  Kind TokenKind;
+  StringRef TokenValue;
+};
+
+// Tokenize Input.
+// In case no error occured, the return value contains
+//   tokens in order they were in the input file.
+// In case of any error, the return value contains
+//   a textual representation of error.
+//
+// Tokens returned by this function hold only references to the parts
+// of the Input. Memory buffer containing Input cannot be freed,
+// modified or reallocated.
+Expected<std::vector<RCToken>> tokenizeRC(StringRef Input);
+
+} // namespace llvm
+
+#endif

tools/llvm-rc/ResourceScriptTokenList.h

@@ -0,0 +1,35 @@
+//===-- ResourceScriptTokenList.h -------------------------------*- C++-*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===---------------------------------------------------------------------===//
+//
+// This is a part of llvm-rc tokenizer. It lists all the possible tokens
+// that might occur in a correct .rc script.
+//
+//===---------------------------------------------------------------------===//
+
+
+// Long tokens. They might consist of more than one character.
+TOKEN(Invalid)      // Invalid token. Should not occur in a valid script.
+TOKEN(Int)          // Integer (decimal, octal or hexadecimal).
+TOKEN(String)       // String value.
+TOKEN(Identifier)   // Script identifier (resource name or type).
+
+// Short tokens. They usually consist of exactly one character.
+// The definitions are of the form SHORT_TOKEN(TokenName, TokenChar).
+// TokenChar is the one-character token representation occuring in the correct
+// .rc scripts.
+SHORT_TOKEN(BlockBegin, '{')   // Start of the script block; can also be BEGIN.
+SHORT_TOKEN(BlockEnd, '}')     // End of the block; can also be END.
+SHORT_TOKEN(Comma, ',')        // Comma - resource arguments separator.
+SHORT_TOKEN(Plus, '+')         // Addition operator.
+SHORT_TOKEN(Minus, '-')        // Subtraction operator.
+SHORT_TOKEN(Pipe, '|')         // Bitwise-OR operator.
+SHORT_TOKEN(Amp, '&')          // Bitwise-AND operator.
+SHORT_TOKEN(Tilde, '~')        // Bitwise-NOT operator.
+SHORT_TOKEN(LeftParen, '(')    // Left parenthesis in the script expressions.
+SHORT_TOKEN(RightParen, ')')   // Right parenthesis.

tools/llvm-rc/llvm-rc.cpp

@@ -1,4 +1,4 @@
-//===- llvm-rc.cpp - Compile .rc scripts into .res -------------*- C++ -*--===//
+//===-- llvm-rc.cpp - Compile .rc scripts into .res -------------*- C++ -*-===//
 //
 //                     The LLVM Compiler Infrastructure
 //
@@ -12,6 +12,8 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "ResourceScriptToken.h"
+
 #include "llvm/Option/Arg.h"
 #include "llvm/Option/ArgList.h"
 #include "llvm/Support/Error.h"
@@ -60,6 +62,12 @@ public:
 };
 
 static ExitOnError ExitOnErr;
+
+LLVM_ATTRIBUTE_NORETURN static void fatalError(Twine Message) {
+  errs() << Message << "\n";
+  exit(1);
+}
+
 } // anonymous namespace
 
 int main(int argc_, const char *argv_[]) {
@@ -81,8 +89,49 @@ int main(int argc_, const char *argv_[]) {
   opt::InputArgList InputArgs = T.ParseArgs(ArgsArr, MAI, MAC);
 
   // The tool prints nothing when invoked with no command-line arguments.
-  if (InputArgs.hasArg(OPT_HELP))
+  if (InputArgs.hasArg(OPT_HELP)) {
     T.PrintHelp(outs(), "rc", "Resource Converter", false);
+    return 0;
+  }
+
+  const bool BeVerbose = InputArgs.hasArg(OPT_VERBOSE);
+
+  std::vector<std::string> InArgsInfo = InputArgs.getAllArgValues(OPT_INPUT);
+  if (InArgsInfo.size() != 1) {
+    fatalError("Exactly one input file should be provided.");
+  }
+
+  // Read and tokenize the input file.
+  const Twine &Filename = InArgsInfo[0];
+  ErrorOr<std::unique_ptr<MemoryBuffer>> File = MemoryBuffer::getFile(Filename);
+  if (!File) {
+    fatalError("Error opening file '" + Filename +
+               "': " + File.getError().message());
+  }
+
+  std::unique_ptr<MemoryBuffer> FileContents = std::move(*File);
+  StringRef Contents = FileContents->getBuffer();
+
+  std::vector<RCToken> Tokens = ExitOnErr(tokenizeRC(Contents));
+
+  if (BeVerbose) {
+    const Twine TokenNames[] = {
+#define TOKEN(Name) #Name,
+#define SHORT_TOKEN(Name, Ch) #Name,
+#include "ResourceScriptTokenList.h"
+#undef TOKEN
+#undef SHORT_TOKEN
+    };
+
+    for (const RCToken &Token : Tokens) {
+      outs() << TokenNames[static_cast<int>(Token.kind())] << ": "
+             << Token.value();
+      if (Token.kind() == RCToken::Kind::Int)
+        outs() << "; int value = " << Token.intValue();
+
+      outs() << "\n";
+    }
+  }
 
   return 0;
 }