[llvm-rc] Add integer expressions parsing ability. [7/8]

This allows the ints to be written as integer expressions evaluating to
unsigned 16-bit/32-bit integers.

All the expressions may use the following operators: + - & | ~, and
parentheses. Minus token - can be also unary. There is no precedence of
the operators other than the unary operators binding stronger than their
binary counterparts.

Differential Revision: https://reviews.llvm.org/D37022

llvm-svn: 314477

test/tools/llvm-rc/parser-expr.test

@@ -0,0 +1,52 @@
+; RUN: llvm-rc /V %p/Inputs/parser-expr.rc | FileCheck %s
+
+; CHECK:  Language: 5, Sublanguage: 1
+; CHECK-NEXT:  Language: 3, Sublanguage: 2
+; CHECK-NEXT:  Language: 4294967293, Sublanguage: 4294967292
+; CHECK-NEXT:  Language: 0, Sublanguage: 1
+; CHECK-NEXT:  Language: 2, Sublanguage: 4
+; CHECK-NEXT:  Language: 3, Sublanguage: 5
+; CHECK-NEXT:  Language: 2, Sublanguage: 0
+; CHECK-NEXT:  Language: 4294967295, Sublanguage: 1
+; CHECK-NEXT:  Language: 1, Sublanguage: 4294967295
+; CHECK-NEXT:  Language: 4294967294, Sublanguage: 1
+; CHECK-NEXT:  Language: 1, Sublanguage: 4294967294
+; CHECK-NEXT:  Language: 2, Sublanguage: 1
+; CHECK-NEXT:  Language: 3, Sublanguage: 5
+; CHECK-NEXT:  Language: 0, Sublanguage: 13
+; CHECK-NEXT:  Language: 5, Sublanguage: 7
+
+
+; RUN: not llvm-rc /V %p/Inputs/parser-expr-bad-binary-1.rc 2>&1 | FileCheck %s --check-prefix BINARY1
+
+; BINARY1: llvm-rc: Error parsing file: expected '-', '~', integer or '(', got &
+
+
+; RUN: not llvm-rc /V %p/Inputs/parser-expr-bad-binary-2.rc 2>&1 | FileCheck %s --check-prefix BINARY2
+
+; BINARY2: llvm-rc: Error parsing file: expected '-', '~', integer or '(', got |
+
+
+; RUN: not llvm-rc /V %p/Inputs/parser-expr-bad-binary-3.rc 2>&1 | FileCheck %s --check-prefix BINARY3
+
+; BINARY3: llvm-rc: Error parsing file: expected '-', '~', integer or '(', got +
+
+
+; RUN: not llvm-rc /V %p/Inputs/parser-expr-bad-unary.rc 2>&1 | FileCheck %s --check-prefix UNARY
+
+; UNARY: llvm-rc: Error parsing file: expected ',', got ~
+
+
+; RUN: not llvm-rc /V %p/Inputs/parser-expr-unbalanced-1.rc 2>&1 | FileCheck %s --check-prefix UNBALANCED1
+
+; UNBALANCED1: llvm-rc: Error parsing file: expected ')', got ,
+
+
+; RUN: not llvm-rc /V %p/Inputs/parser-expr-unbalanced-2.rc 2>&1 | FileCheck %s --check-prefix UNBALANCED2
+
+; UNBALANCED2: llvm-rc: Error parsing file: expected ',', got )
+
+
+; RUN: not llvm-rc /V %p/Inputs/parser-expr-unbalanced-3.rc 2>&1 | FileCheck %s --check-prefix UNBALANCED3
+
+; UNBALANCED3: llvm-rc: Error parsing file: expected ',', got )

test/tools/llvm-rc/parser.test

@@ -106,12 +106,12 @@
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-eof.rc 2>&1 | FileCheck %s --check-prefix PEOF
 
-; PEOF:  llvm-rc: Error parsing file: expected integer, got <EOF>
+; PEOF:  llvm-rc: Error parsing file: expected '-', '~', integer or '(', got <EOF>
 
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-no-characteristics-arg.rc 2>&1 | FileCheck %s --check-prefix PCHARACTERISTICS1
 
-; PCHARACTERISTICS1:  llvm-rc: Error parsing file: expected integer, got BEGIN
+; PCHARACTERISTICS1:  llvm-rc: Error parsing file: expected '-', '~', integer or '(', got BEGIN
 
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-nonsense-token.rc 2>&1 | FileCheck %s --check-prefix PNONSENSE1
@@ -136,7 +136,7 @@
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-language-too-many-commas.rc 2>&1 | FileCheck %s --check-prefix PLANGUAGE2
 
-; PLANGUAGE2:  llvm-rc: Error parsing file: expected integer, got ,
+; PLANGUAGE2:  llvm-rc: Error parsing file: expected '-', '~', integer or '(', got ,
 
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-html-bad-string.rc 2>&1 | FileCheck %s --check-prefix PHTML1
@@ -171,7 +171,7 @@
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-menu-bad-id.rc 2>&1 | FileCheck %s --check-prefix PMENU1
 
-; PMENU1:  llvm-rc: Error parsing file: expected integer, got A
+; PMENU1:  llvm-rc: Error parsing file: expected '-', '~', integer or '(', got A
 
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-menu-bad-flag.rc 2>&1 | FileCheck %s --check-prefix PMENU2
@@ -211,7 +211,7 @@
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-dialog-unnecessary-string.rc 2>&1 | FileCheck %s --check-prefix PDIALOG5
 
-; PDIALOG5:  llvm-rc: Error parsing file: expected integer, got "This shouldn't be here"
+; PDIALOG5:  llvm-rc: Error parsing file: expected '-', '~', integer or '(', got "This shouldn't be here"
 
 
 ; RUN: not llvm-rc /V %p/Inputs/parser-versioninfo-wrong-fixed.rc 2>&1 | FileCheck %s --check-prefix PVERSIONINFO1

tools/llvm-rc/ResourceScriptParser.cpp

@@ -107,10 +107,102 @@ void RCParser::consume() {
   CurLoc++;
 }
 
-Expected<uint32_t> RCParser::readInt() {
-  if (!isNextTokenKind(Kind::Int))
-    return getExpectedError("integer");
-  return read().intValue();
+// An integer description might consist of a single integer or
+// an arithmetic expression evaluating to the integer. The expressions
+// can contain the following tokens: <int> ( ) + - | & ~. Their meaning
+// is the same as in C++.
+// The operators in the original RC implementation have the following
+// precedence:
+//   1) Unary operators (- ~),
+//   2) Binary operators (+ - & |), with no precedence.
+//
+// The following grammar is used to parse the expressions Exp1:
+//   Exp1 ::= Exp2 || Exp1 + Exp2 || Exp1 - Exp2 || Exp1 | Exp2 || Exp1 & Exp2
+//   Exp2 ::= -Exp2 || ~Exp2 || Int || (Exp1).
+// (More conveniently, Exp1 is a non-empty sequence of Exp2 expressions,
+// separated by binary operators.)
+//
+// Expressions of type Exp1 are read by parseIntExpr1(Inner) method, while Exp2
+// is read by parseIntExpr2().
+//
+// The original Microsoft tool handles multiple unary operators incorrectly.
+// For example, in 16-bit little-endian integers:
+//    1 => 01 00, -1 => ff ff, --1 => ff ff, ---1 => 01 00;
+//    1 => 01 00, ~1 => fe ff, ~~1 => fd ff, ~~~1 => fc ff.
+// Our implementation differs from the original one and handles these
+// operators correctly:
+//    1 => 01 00, -1 => ff ff, --1 => 01 00, ---1 => ff ff;
+//    1 => 01 00, ~1 => fe ff, ~~1 => 01 00, ~~~1 => fe ff.
+
+Expected<uint32_t> RCParser::readInt() { return parseIntExpr1(); }
+
+Expected<uint32_t> RCParser::parseIntExpr1() {
+  // Exp1 ::= Exp2 || Exp1 + Exp2 || Exp1 - Exp2 || Exp1 | Exp2 || Exp1 & Exp2.
+  ASSIGN_OR_RETURN(FirstResult, parseIntExpr2());
+  uint32_t Result = *FirstResult;
+
+  while (!isEof() && look().isBinaryOp()) {
+    auto OpToken = read();
+    ASSIGN_OR_RETURN(NextResult, parseIntExpr2());
+
+    switch (OpToken.kind()) {
+    case Kind::Plus:
+      Result += *NextResult;
+      break;
+
+    case Kind::Minus:
+      Result -= *NextResult;
+      break;
+
+    case Kind::Pipe:
+      Result |= *NextResult;
+      break;
+
+    case Kind::Amp:
+      Result &= *NextResult;
+      break;
+
+    default:
+      llvm_unreachable("Already processed all binary ops.");
+    }
+  }
+
+  return Result;
+}
+
+Expected<uint32_t> RCParser::parseIntExpr2() {
+  // Exp2 ::= -Exp2 || ~Exp2 || Int || (Exp1).
+  static const char ErrorMsg[] = "'-', '~', integer or '('";
+
+  if (isEof())
+    return getExpectedError(ErrorMsg);
+
+  switch (look().kind()) {
+  case Kind::Minus: {
+    consume();
+    ASSIGN_OR_RETURN(Result, parseIntExpr2());
+    return -(*Result);
+  }
+
+  case Kind::Tilde: {
+    consume();
+    ASSIGN_OR_RETURN(Result, parseIntExpr2());
+    return ~(*Result);
+  }
+
+  case Kind::Int:
+    return read().intValue();
+
+  case Kind::LeftParen: {
+    consume();
+    ASSIGN_OR_RETURN(Result, parseIntExpr1());
+    RETURN_IF_ERROR(consumeType(Kind::RightParen));
+    return *Result;
+  }
+
+  default:
+    return getExpectedError(ErrorMsg);
+  }
 }
 
 Expected<StringRef> RCParser::readString() {

tools/llvm-rc/ResourceScriptParser.h

@@ -77,12 +77,18 @@ private:
 
   // The following methods try to read a single token, check if it has the
   // correct type and then parse it.
+  // Each integer can be written as an arithmetic expression producing an
+  // unsigned 32-bit integer.
   Expected<uint32_t> readInt();            // Parse an integer.
   Expected<StringRef> readString();        // Parse a string.
   Expected<StringRef> readIdentifier();    // Parse an identifier.
   Expected<IntOrString> readIntOrString(); // Parse an integer or a string.
   Expected<IntOrString> readTypeOrName();  // Parse an integer or an identifier.
 
+  // Helper integer expression parsing methods.
+  Expected<uint32_t> parseIntExpr1();
+  Expected<uint32_t> parseIntExpr2();
+
   // Advance the state by one, discarding the current token.
   // If the discarded token had an incorrect type, fail.
   Error consumeType(Kind TokenKind);

tools/llvm-rc/ResourceScriptToken.cpp

@@ -60,6 +60,18 @@ StringRef RCToken::value() const { return TokenValue; }
 
 Kind RCToken::kind() const { return TokenKind; }
 
+bool RCToken::isBinaryOp() const {
+  switch (TokenKind) {
+  case Kind::Plus:
+  case Kind::Minus:
+  case Kind::Pipe:
+  case Kind::Amp:
+    return true;
+  default:
+    return false;
+  }
+}
+
 static Error getStringError(const Twine &message) {
   return make_error<StringError>("Error parsing file: " + message,
                                  inconvertibleErrorCode());

tools/llvm-rc/ResourceScriptToken.h

@@ -60,6 +60,9 @@ public:
   StringRef value() const;
   Kind kind() const;
 
+  // Check if a token describes a binary operator.
+  bool isBinaryOp() const;
+
 private:
   Kind TokenKind;
   StringRef TokenValue;