[TableGen] Add !records operator to get defined records

The format is: `!records<T>([regex])`.

This operator produces a list of records whose type is `T`. If
`regex` is provided, only records whose name matches the regular
expression `regex` will be included. The format of `regex` is ERE
(Extended POSIX Regular Expressions).

Author: wangpc-pp

llvm/docs/TableGen/ProgRef.rst

@@ -226,10 +226,10 @@ TableGen provides "bang operators" that have a wide variety of uses:
                : !initialized !interleave  !isa         !le          !listconcat
                : !listflatten !listremove  !listsplat   !logtwo      !lt
                : !match       !mul         !ne          !not         !or
-               : !range       !repr        !setdagarg   !setdagname  !setdagop
-               : !shl         !size        !sra         !srl         !strconcat
-               : !sub         !subst       !substr      !tail        !tolower
-               : !toupper     !xor
+               : !range       !records     !repr        !setdagarg   !setdagname
+               : !setdagop    !shl         !size        !sra         !srl
+               : !strconcat   !sub         !subst       !substr      !tail
+               : !tolower     !toupper     !xor
 
 The ``!cond`` operator has a slightly different
 syntax compared to other bang operators, so it is defined separately:
@@ -1920,6 +1920,12 @@ and non-0 as true.
 ``!range(``\ *list*\ ``)``
     Equivalent to ``!range(0, !size(list))``.
 
+``!records<``\ *type*\ ``>([``\ *regex*\ ``])``
+    This operator produces a list of records whose type is *type*. If *regex*
+    is provided, only records whose name matches the regular expression *regex*
+    will be included. The format of *regex* is ERE (Extended POSIX Regular
+    Expressions).
+
 ``!repr(``\ *value*\ ``)``
     Represents *value* as a string. String format for the value is not
     guaranteed to be stable. Intended for debugging purposes only.

llvm/include/llvm/TableGen/Record.h

@@ -316,6 +316,7 @@ class Init {
     IK_FoldOpInit,
     IK_IsAOpInit,
     IK_ExistsOpInit,
+    IK_RecordsOpInit,
     IK_AnonymousNameInit,
     IK_StringInit,
     IK_VarInit,
@@ -1192,6 +1193,41 @@ class ExistsOpInit final : public TypedInit, public FoldingSetNode {
   std::string getAsString() const override;
 };
 
+/// !records<type>([regex]) - Produces a list of records whose type is `type`.
+/// If `regex` is provided, only records whose name matches the regular
+/// expression `regex` will be included.
+class RecordsOpInit final : public TypedInit, public FoldingSetNode {
+private:
+  const RecTy *Type;
+  const Init *Regex;
+
+  RecordsOpInit(const RecTy *Type, const Init *Regex)
+      : TypedInit(IK_RecordsOpInit, ListRecTy::get(Type)), Type(Type),
+        Regex(Regex) {}
+
+public:
+  RecordsOpInit(const RecordsOpInit &) = delete;
+  RecordsOpInit &operator=(const RecordsOpInit &) = delete;
+
+  static bool classof(const Init *I) {
+    return I->getKind() == IK_RecordsOpInit;
+  }
+
+  static const RecordsOpInit *get(const RecTy *Type, const Init *Regex);
+
+  void Profile(FoldingSetNodeID &ID) const;
+
+  const Init *Fold() const;
+
+  bool isComplete() const override { return false; }
+
+  const Init *resolveReferences(Resolver &R) const override;
+
+  const Init *getBit(unsigned Bit) const override;
+
+  std::string getAsString() const override;
+};
+
 /// 'Opcode' - Represent a reference to an entire variable object.
 class VarInit final : public TypedInit {
   const Init *VarName;

llvm/lib/TableGen/Record.cpp

@@ -84,6 +84,7 @@ struct RecordKeeperImpl {
   FoldingSet<FoldOpInit> TheFoldOpInitPool;
   FoldingSet<IsAOpInit> TheIsAOpInitPool;
   FoldingSet<ExistsOpInit> TheExistsOpInitPool;
+  FoldingSet<RecordsOpInit> TheRecordsOpInitPool;
   DenseMap<std::pair<const RecTy *, const Init *>, VarInit *> TheVarInitPool;
   DenseMap<std::pair<const TypedInit *, unsigned>, VarBitInit *>
       TheVarBitInitPool;
@@ -2222,6 +2223,65 @@ std::string ExistsOpInit::getAsString() const {
       .str();
 }
 
+static void ProfileRecordsOpInit(FoldingSetNodeID &ID, const RecTy *Type,
+                                 const Init *Regex) {
+  ID.AddPointer(Type);
+  ID.AddPointer(Regex);
+}
+
+const RecordsOpInit *RecordsOpInit::get(const RecTy *Type, const Init *Regex) {
+  FoldingSetNodeID ID;
+  ProfileRecordsOpInit(ID, Type, Regex);
+
+  detail::RecordKeeperImpl &RK = Regex->getRecordKeeper().getImpl();
+  void *IP = nullptr;
+  if (const RecordsOpInit *I =
+          RK.TheRecordsOpInitPool.FindNodeOrInsertPos(ID, IP))
+    return I;
+
+  RecordsOpInit *I = new (RK.Allocator) RecordsOpInit(Type, Regex);
+  RK.TheRecordsOpInitPool.InsertNode(I, IP);
+  return I;
+}
+
+void RecordsOpInit::Profile(FoldingSetNodeID &ID) const {
+  ProfileRecordsOpInit(ID, Type, Regex);
+}
+
+const Init *RecordsOpInit::Fold() const {
+  const auto *RegexInit = dyn_cast<StringInit>(Regex);
+  if (!RegexInit)
+    return this;
+
+  StringRef RegexStr = RegexInit->getValue();
+  llvm::Regex Matcher(RegexStr);
+  if (!Matcher.isValid())
+    PrintFatalError(Twine("invalid regex '") + RegexStr + Twine("'"));
+
+  const RecordKeeper &RK = Type->getRecordKeeper();
+  SmallVector<Init *, 8> Selected;
+  for (auto &Def : RK.getAllDerivedDefinitionsIfDefined(Type->getAsString()))
+    if (Matcher.match(Def->getName()))
+      Selected.push_back(Def->getDefInit());
+
+  return ListInit::get(Selected, Type);
+}
+
+const Init *RecordsOpInit::resolveReferences(Resolver &R) const {
+  const Init *NewRegex = Regex->resolveReferences(R);
+  if (Regex != NewRegex)
+    return get(Type, NewRegex)->Fold();
+  return this;
+}
+
+const Init *RecordsOpInit::getBit(unsigned Bit) const {
+  return VarBitInit::get(this, Bit);
+}
+
+std::string RecordsOpInit::getAsString() const {
+  return "!records<" + Type->getAsString() + ">(" + Regex->getAsString() + ")";
+}
+
 const RecTy *TypedInit::getFieldType(const StringInit *FieldName) const {
   if (const auto *RecordType = dyn_cast<RecordRecTy>(getType())) {
     for (const Record *Rec : RecordType->getClasses()) {

llvm/lib/TableGen/TGLexer.cpp

@@ -629,6 +629,7 @@ tgtok::TokKind TGLexer::LexExclaim() {
           .Case("listsplat", tgtok::XListSplat)
           .Case("listremove", tgtok::XListRemove)
           .Case("range", tgtok::XRange)
+          .Case("records", tgtok::XRecords)
           .Case("strconcat", tgtok::XStrConcat)
           .Case("initialized", tgtok::XInitialized)
           .Case("interleave", tgtok::XInterleave)

llvm/lib/TableGen/TGLexer.h

@@ -154,6 +154,7 @@ enum TokKind {
   XToLower,
   XToUpper,
   XRange,
+  XRecords,
   XGetDagArg,
   XGetDagName,
   XSetDagArg,

llvm/lib/TableGen/TGParser.cpp

@@ -1455,6 +1455,49 @@ const Init *TGParser::ParseOperation(Record *CurRec, const RecTy *ItemType) {
     return (ExistsOpInit::get(Type, Expr))->Fold(CurRec);
   }
 
+  case tgtok::XRecords: {
+    // Value ::= !records '<' Type '>' '(' Regex? ')'
+    Lex.Lex(); // eat the operation.
+
+    const RecTy *Type = ParseOperatorType();
+    if (!Type)
+      return nullptr;
+
+    if (!consume(tgtok::l_paren)) {
+      TokError("expected '(' after type of !records");
+      return nullptr;
+    }
+
+    // The Regex can be optional.
+    const Init *Regex;
+    if (Lex.getCode() != tgtok::r_paren) {
+      SMLoc RegexLoc = Lex.getLoc();
+      Regex = ParseValue(CurRec);
+
+      const auto *RegexType = dyn_cast<TypedInit>(Regex);
+      if (!RegexType) {
+        Error(RegexLoc, "expected string type argument in !records operator");
+        return nullptr;
+      }
+
+      const auto *SType = dyn_cast<StringRecTy>(RegexType->getType());
+      if (!SType) {
+        Error(RegexLoc, "expected string type argument in !records operator");
+        return nullptr;
+      }
+    } else {
+      // Use wildcard when Regex is not specified.
+      Regex = StringInit::get(Records, ".*");
+    }
+
+    if (!consume(tgtok::r_paren)) {
+      TokError("expected ')' in !records");
+      return nullptr;
+    }
+
+    return RecordsOpInit::get(Type, Regex)->Fold();
+  }
+
   case tgtok::XConcat:
   case tgtok::XMatch:
   case tgtok::XADD:

llvm/test/TableGen/records.td

@@ -0,0 +1,60 @@
+// RUN: llvm-tblgen %s | FileCheck %s
+// RUN: not llvm-tblgen -DERROR1 %s 2>&1 | FileCheck --check-prefix=ERROR1 %s
+// RUN: not llvm-tblgen -DERROR2 %s 2>&1 | FileCheck --check-prefix=ERROR2 %s
+// RUN: not llvm-tblgen -DERROR3 %s 2>&1 | FileCheck --check-prefix=ERROR3 %s
+// XFAIL: vg_leak
+
+class A;
+def a0 : A;
+def a1 : A;
+
+class B : A;
+def b0 : B;
+def b1 : B;
+
+def records_A {
+  list<A> records = !records<A>();
+}
+
+def records_A_x0 {
+  list<A> records = !records<A>(".*0");
+}
+
+def records_A_x1 {
+  list<A> records = !records<A>(".*1");
+}
+
+def records_B {
+  list<B> records = !records<B>();
+}
+
+// CHECK-LABEL: def records_A {
+// CHECK-NEXT:    list<A> records = [a0, a1, b0, b1];
+// CHECK-NEXT:  }
+
+// CHECK-LABEL: def records_A_x0 {
+// CHECK-NEXT:    list<A> records = [a0, b0];
+// CHECK-NEXT:  }
+
+// CHECK-LABEL: def records_A_x1 {
+// CHECK-NEXT:    list<A> records = [a1, b1];
+// CHECK-NEXT:  }
+
+// CHECK-LABEL: def records_B {
+// CHECK-NEXT:    list<B> records = [b0, b1];
+// CHECK-NEXT:  }
+
+#ifdef ERROR1
+defvar error1 = !records<A>(123)
+// ERROR1: error: expected string type argument in !records operator
+#endif
+
+#ifdef ERROR2
+defvar error2 = !records<1>("")
+// ERROR2: error: Unknown token when expecting a type
+#endif
+
+#ifdef ERROR3
+defvar error3 = !records<A>("([)]")
+// ERROR3: error: invalid regex '([)]'
+#endif