[TableGen] Add !select operator to select records

This operator is like `!select<T>(regex)`, which produces a list of
records whose type is `T` and record names match regular expression
`regex`.

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
                : !mul         !ne          !not         !or          !range
-               : !repr        !setdagarg   !setdagname  !setdagop    !shl
-               : !size        !sra         !srl         !strconcat   !sub
-               : !subst       !substr      !tail        !tolower     !toupper
-               : !xor
+               : !repr        !select      !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 +1920,10 @@ and non-0 as true.
     Represents *value* as a string. String format for the value is not
     guaranteed to be stable. Intended for debugging purposes only.
 
+``!select<``\ *type*\ ``>(``\ *regex*\ ``)``
+    This operator produces a list of records whose type is *type* and record
+    names match regular expression *regex*.
+
 ``!setdagarg(``\ *dag*\ ``,``\ *key*\ ``,``\ *arg*\ ``)``
     This operator produces a DAG node with the same operator and arguments as
     *dag*, but replacing the value of the argument specified by the *key* with

llvm/include/llvm/TableGen/Record.h

@@ -316,6 +316,7 @@ class Init {
     IK_FoldOpInit,
     IK_IsAOpInit,
     IK_ExistsOpInit,
+    IK_SelectOpInit,
     IK_AnonymousNameInit,
     IK_StringInit,
     IK_VarInit,
@@ -1191,6 +1192,38 @@ class ExistsOpInit final : public TypedInit, public FoldingSetNode {
   std::string getAsString() const override;
 };
 
+/// !select<type>(regex) - Produces a list of records whose type is `type` and
+/// record names match regular expression `regex`.
+class SelectOpInit final : public TypedInit, public FoldingSetNode {
+private:
+  const RecTy *Type;
+  const Init *Regex;
+
+  SelectOpInit(const RecTy *Type, const Init *Regex)
+      : TypedInit(IK_SelectOpInit, IntRecTy::get(Type->getRecordKeeper())),
+        Type(Type), Regex(Regex) {}
+
+public:
+  SelectOpInit(const SelectOpInit &) = delete;
+  SelectOpInit &operator=(const SelectOpInit &) = delete;
+
+  static bool classof(const Init *I) { return I->getKind() == IK_SelectOpInit; }
+
+  static const SelectOpInit *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

@@ -25,6 +25,7 @@
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/MathExtras.h"
+#include "llvm/Support/Regex.h"
 #include "llvm/Support/SMLoc.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/TableGen/Error.h"
@@ -83,6 +84,7 @@ struct RecordKeeperImpl {
   FoldingSet<FoldOpInit> TheFoldOpInitPool;
   FoldingSet<IsAOpInit> TheIsAOpInitPool;
   FoldingSet<ExistsOpInit> TheExistsOpInitPool;
+  FoldingSet<SelectOpInit> TheSelectOpInitPool;
   DenseMap<std::pair<const RecTy *, const Init *>, VarInit *> TheVarInitPool;
   DenseMap<std::pair<const TypedInit *, unsigned>, VarBitInit *>
       TheVarBitInitPool;
@@ -2199,6 +2201,66 @@ std::string ExistsOpInit::getAsString() const {
       .str();
 }
 
+static void ProfileSelectOpInit(FoldingSetNodeID &ID, const RecTy *Type,
+                                const Init *Regex) {
+  ID.AddPointer(Type);
+  ID.AddPointer(Regex);
+}
+
+const SelectOpInit *SelectOpInit::get(const RecTy *Type, const Init *Regex) {
+  FoldingSetNodeID ID;
+  ProfileSelectOpInit(ID, Type, Regex);
+
+  detail::RecordKeeperImpl &RK = Regex->getRecordKeeper().getImpl();
+  void *IP = nullptr;
+  if (const SelectOpInit *I =
+          RK.TheSelectOpInitPool.FindNodeOrInsertPos(ID, IP))
+    return I;
+
+  SelectOpInit *I = new (RK.Allocator) SelectOpInit(Type, Regex);
+  RK.TheSelectOpInitPool.InsertNode(I, IP);
+  return I;
+}
+
+void SelectOpInit::Profile(FoldingSetNodeID &ID) const {
+  ProfileSelectOpInit(ID, Type, Regex);
+}
+
+const Init *SelectOpInit::Fold() const {
+  if (const auto *RegexInit = dyn_cast<StringInit>(Regex)) {
+    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);
+  }
+  return this;
+}
+
+const Init *SelectOpInit::resolveReferences(Resolver &R) const {
+  const Init *NewRegex = Regex->resolveReferences(R);
+  if (Regex != NewRegex)
+    return get(Type, NewRegex)->Fold();
+  return this;
+}
+
+const Init *SelectOpInit::getBit(unsigned Bit) const {
+  return VarBitInit::get(this, Bit);
+}
+
+std::string SelectOpInit::getAsString() const {
+  return (Twine("!select<") + Type->getAsString() + ">(" +
+          Regex->getAsString() + ")")
+      .str();
+}
+
 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

@@ -644,6 +644,7 @@ tgtok::TokKind TGLexer::LexExclaim() {
           .Case("tolower", tgtok::XToLower)
           .Case("toupper", tgtok::XToUpper)
           .Case("repr", tgtok::XRepr)
+          .Case("select", tgtok::XSelect)
           .Default(tgtok::Error);
 
   return Kind != tgtok::Error ? Kind

llvm/lib/TableGen/TGLexer.h

@@ -158,7 +158,8 @@ enum TokKind {
   XSetDagArg,
   XSetDagName,
   XRepr,
-  BANG_OPERATOR_LAST = XRepr,
+  XSelect,
+  BANG_OPERATOR_LAST = XSelect,
 
   // String valued tokens.
   STRING_VALUE_FIRST,

llvm/lib/TableGen/TGParser.cpp

@@ -1455,6 +1455,44 @@ const Init *TGParser::ParseOperation(Record *CurRec, const RecTy *ItemType) {
     return (ExistsOpInit::get(Type, Expr))->Fold(CurRec);
   }
 
+  case tgtok::XSelect: {
+    // Value ::= !select '<' 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 !select");
+      return nullptr;
+    }
+
+    SMLoc RegexLoc = Lex.getLoc();
+    const Init *Regex = ParseValue(CurRec);
+    if (!Regex)
+      return nullptr;
+
+    const auto *RegexType = dyn_cast<TypedInit>(Regex);
+    if (!RegexType) {
+      Error(RegexLoc, "expected string type argument in !select operator");
+      return nullptr;
+    }
+
+    const auto *SType = dyn_cast<StringRecTy>(RegexType->getType());
+    if (!SType) {
+      Error(RegexLoc, "expected string type argument in !select operator");
+      return nullptr;
+    }
+
+    if (!consume(tgtok::r_paren)) {
+      TokError("expected ')' in !select");
+      return nullptr;
+    }
+
+    return (SelectOpInit::get(Type, Regex))->Fold();
+  }
+
   case tgtok::XConcat:
   case tgtok::XADD:
   case tgtok::XSUB:

llvm/test/TableGen/select.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 select_A {
+  list<A> selected = !select<A>(".*");
+}
+
+def select_A_x0 {
+  list<A> selected = !select<A>(".*0");
+}
+
+def select_A_x1 {
+  list<A> selected = !select<A>(".*1");
+}
+
+def select_B {
+  list<B> selected = !select<B>(".*");
+}
+
+// CHECK-LABEL: def select_A {
+// CHECK-NEXT:    list<A> selected = [a0, a1, b0, b1];
+// CHECK-NEXT:  }
+
+// CHECK-LABEL: def select_A_x0 {
+// CHECK-NEXT:    list<A> selected = [a0, b0];
+// CHECK-NEXT:  }
+
+// CHECK-LABEL: def select_A_x1 {
+// CHECK-NEXT:    list<A> selected = [a1, b1];
+// CHECK-NEXT:  }
+
+// CHECK-LABEL: def select_B {
+// CHECK-NEXT:    list<B> selected = [b0, b1];
+// CHECK-NEXT:  }
+
+#ifdef ERROR1
+defvar error1 = !select<A>(123)
+// ERROR1: error: expected string type argument in !select operator
+#endif
+
+#ifdef ERROR2
+defvar error2 = !select<1>("")
+// ERROR2: error: Unknown token when expecting a type
+#endif
+
+#ifdef ERROR3
+defvar error3 = !select<A>("([)]")
+// ERROR3: error: invalid regex '([)]'
+#endif