Replace TableGen range piece punctuator with '...'

The TableGen range piece punctuator is currently '-' (e.g., {0-9}),
which interacts oddly with the fact that an integer literal's sign
is part of the literal. This patch replaces the '-' with the new
punctuator '...'. The '-' punctuator is deprecated.

Differential Revision: https://reviews.llvm.org/D85585

Change-Id: I3d53d14e23f878b142d8f84590dd465a0fb6c09c

docs/ReleaseNotes.rst

@@ -65,6 +65,14 @@ Changes to the LLVM IR
 Changes to building LLVM
 ------------------------
 
+Changes to TableGen
+-------------------
+
+* The syntax for specifying an integer range in a range list has changed.
+  The old syntax used a hyphen in the range (e.g., ``{0-9}``). The new syntax
+  uses the "`...`" range punctuator (e.g., ``{0...9}``). The hyphen syntax
+  is deprecated. The "TableGen Language Reference" document has been updated.
+
 Changes to the ARM Backend
 --------------------------
 

docs/TableGen/ProgRef.rst

@@ -321,7 +321,7 @@ to an entity of type ``bits<4>``.
               :| "." `TokIdentifier`
    RangeList: `RangePiece` ("," `RangePiece`)*
    RangePiece: `TokInteger`
-             :| `TokInteger` ".." `TokInteger`
+             :| `TokInteger` "..." `TokInteger`
              :| `TokInteger` "-" `TokInteger`
              :| `TokInteger` `TokInteger`
 

lib/TableGen/TGLexer.cpp

@@ -161,7 +161,6 @@ tgtok::TokKind TGLexer::LexToken(bool FileOrLineStart) {
 
   case ':': return tgtok::colon;
   case ';': return tgtok::semi;
-  case '.': return tgtok::period;
   case ',': return tgtok::comma;
   case '<': return tgtok::less;
   case '>': return tgtok::greater;
@@ -181,6 +180,19 @@ tgtok::TokKind TGLexer::LexToken(bool FileOrLineStart) {
 
     return tgtok::paste;
 
+  // The period is a separate case so we can recognize the "..."
+  // range punctuator.
+  case '.':
+    if (peekNextChar(0) == '.') {
+      ++CurPtr; // Eat second dot.
+      if (peekNextChar(0) == '.') {
+        ++CurPtr; // Eat third dot.
+        return tgtok::dotdotdot;
+      }
+      return ReturnError(TokStart, "Invalid '..' punctuation");
+    }
+    return tgtok::dot;
+
   case '\r':
     PrintFatalError("getNextChar() must never return '\r'");
     return tgtok::Error;

lib/TableGen/TGLexer.h

@@ -40,9 +40,10 @@ namespace tgtok {
     l_paren, r_paren,   // ( )
     less, greater,      // < >
     colon, semi,        // : ;
-    comma, period,      // , .
+    comma, dot,         // , .
     equal, question,    // = ?
     paste,              // #
+    dotdotdot,          // ...
 
     // Keywords. ('ElseKW' is named to distinguish it from the existing 'Else'
     // that means the preprocessor #else.)

lib/TableGen/TGParser.cpp

@@ -671,8 +671,10 @@ ParseSubMultiClassReference(MultiClass *CurMC) {
 
 /// ParseRangePiece - Parse a bit/value range.
 ///   RangePiece ::= INTVAL
+///   RangePiece ::= INTVAL '...' INTVAL
 ///   RangePiece ::= INTVAL '-' INTVAL
-///   RangePiece ::= INTVAL INTVAL
+///   RangePiece ::= INTVAL INTVAL 
+// The last two forms are deprecated.
 bool TGParser::ParseRangePiece(SmallVectorImpl<unsigned> &Ranges,
                                TypedInit *FirstItem) {
   Init *CurVal = FirstItem;
@@ -693,6 +695,8 @@ bool TGParser::ParseRangePiece(SmallVectorImpl<unsigned> &Ranges,
   default:
     Ranges.push_back(Start);
     return false;
+
+  case tgtok::dotdotdot:
   case tgtok::minus: {
     Lex.Lex(); // eat
 
@@ -2167,7 +2171,7 @@ Init *TGParser::ParseValue(Record *CurRec, RecTy *ItemType, IDParseMode Mode) {
       }
       break;
     }
-    case tgtok::period: {
+    case tgtok::dot: {
       if (Lex.Lex() != tgtok::Id) {  // eat the .
         TokError("expected field identifier after '.'");
         return nullptr;

test/TableGen/range-lists.td

@@ -0,0 +1,80 @@
+// RUN: llvm-tblgen %s | FileCheck %s
+// XFAIL: vg_leak
+
+// This file has tests for range lists and range pieces.
+
+// These are tests for bits ranges.
+
+def bit_range_hyphen {
+  bits<16> field1;
+  let field1{15, 14, 13, 12} = {1, 0, 1, 0};
+  let field1{11-8} = {1, 0, 1, 1};
+  let field1{+7-4} = {1, 1, 0, 0};
+  let field1{+3-+0} = {1, 1, 0, 1};
+  bit hyphen_field1_ok = !eq(field1, 0xABCD);
+}
+
+def bit_range_dotdotdot {
+  bits<16> field1;
+  let field1{15, 14, 13, 12} = {1, 0, 1, 0};
+  let field1{11...8} = {1, 0, 1, 1};
+  let field1{+7...4} = {1, 1, 0, 0};
+  let field1{+3...+0} = {1, 1, 0, 1};
+  bit dotdotdot_field1_ok = !eq(field1, 0xABCD);
+}
+
+if !eq(bit_range_hyphen.field1, bit_range_dotdotdot.field1) then
+  def bit_range_ok {}
+else
+  def bit_range_not_ok {}
+
+// These are tests for lists.
+
+def list_range_hyphen {
+  list<string> field1 = ["foo", "bar", "baz", "snork", "quux", "quuux",
+                         "bazola", "ztesch", "bletch", "flarp"];
+  list<string> subfielda = field1[0, 1, 2, 3];
+  list<string> subfieldb = field1[4-5];
+  list<string> subfieldc = field1[+6-7];
+  list<string> subfieldd = field1[+8-+9];
+  bit hyphen_subfields_ok = !and(!eq(subfieldb[0], "quux"),
+                                 !eq(subfieldd[1], "flarp"));
+}
+
+def list_range_dotdotdot {
+  list<string> field1 = ["foo", "bar", "baz", "snork", "quux", "quuux",
+                         "bazola", "ztesch", "bletch", "flarp"];
+  list<string> subfielda = field1[0, 1, 2, 3];
+  list<string> subfieldb = field1[4...5];
+  list<string> subfieldc = field1[+6...7];
+  list<string> subfieldd = field1[+8...+9];
+  bit dotdotdot_subfields_ok = !and(!eq(subfieldb[0], "quux"),
+                                    !eq(subfieldd[1], "flarp"));
+}
+
+if !eq(!head(list_range_hyphen.subfieldd),
+       !head(list_range_dotdotdot.subfieldd)) then
+  def list_range_ok {}
+else
+  def list_range_not_ok {}
+
+// This is a test of foreach.
+
+foreach i = {0-3} in 
+  foreach j = {4...5} in
+    def eachrec#i#j {
+      int fi = i;
+      int fj = j;
+    }
+
+//CHECK: bit dotdotdot_field1_ok = 1
+//CHECK: bit hyphen_field1_ok = 1
+//CHECK: def bit_range_ok {
+
+//CHECK: def eachrec04 {
+//CHECK: def eachrec35 {
+
+//CHECK: bit dotdotdot_subfields_ok = 1
+//CHECK: bit hyphen_subfields_ok = 1
+//CHECK: def list_range_ok {
+