Support for llvm-bcanalyzer dumping of record array strings.

[tejohnson]

Summary

Adds support for automatically detecting and printing strings
represented by Array abbrev operands, analogous to the string dumping
performed for Blob abbrev operands.

Enhanced the ThinLTO combined index test to check for the appropriate
module and function strings.

[tejohnson]

• Fix test failures by guarding call to getEncoding.

[mehdi_amini]

tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp

518 ↗

(On Diff #36856)

I don't understand this assert? The position of an array is supposed to be always second to last? What has to follow?

521 ↗

(On Diff #36856)

I don't know why is this loop going to the end of the record?

[mehdi_amini]

LGTM!
Thanks for the pointer to the doc ;)

llvm/trunk/test/tools/gold/X86/thinlto.ll

 ; RUN: llvm-as -function-summary %s -o %t.o
 ; RUN: llvm-as -function-summary %p/Inputs/thinlto.ll -o %t2.o
 
 ; RUN: %gold -plugin %llvmshlibdir/LLVMgold.so \
 ; RUN:    --plugin-opt=thinlto \
 ; RUN:    -shared %t.o %t2.o -o %t3
 ; RUN: llvm-bcanalyzer -dump %t3.thinlto.bc | FileCheck %s --check-prefix=COMBINED
 ; RUN: not test -e %t3
 
 ; COMBINED: <MODULE_STRTAB_BLOCK
-; COMBINED-NEXT: <ENTRY
-; COMBINED-NEXT: <ENTRY
+; COMBINED-NEXT: <ENTRY {{.*}} record string = '{{.*}}/test/tools/gold/X86/Output/thinlto.ll.tmp{{.*}}.o'
+; COMBINED-NEXT: <ENTRY {{.*}} record string = '{{.*}}/test/tools/gold/X86/Output/thinlto.ll.tmp{{.*}}.o'
 ; COMBINED-NEXT: </MODULE_STRTAB_BLOCK
 ; COMBINED-NEXT: <FUNCTION_SUMMARY_BLOCK
 ; COMBINED-NEXT: <COMBINED_ENTRY
 ; COMBINED-NEXT: <COMBINED_ENTRY
 ; COMBINED-NEXT: </FUNCTION_SUMMARY_BLOCK
+; COMBINED-NEXT: <VALUE_SYMTAB
+; COMBINED-NEXT: <COMBINED_FNENTRY {{.*}} record string = '{{f|g}}'
+; COMBINED-NEXT: <COMBINED_FNENTRY {{.*}} record string = '{{f|g}}'
+; COMBINED-NEXT: </VALUE_SYMTAB
 
 define void @f() {
 entry:
   ret void
 }

llvm/trunk/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp

if (Dump) {
                         CurStreamType))
         outs() << CodeName;
       else
         outs() << "UnknownCode" << Code;
       if (NonSymbolic &&
           GetCodeName(Code, BlockID, *Stream.getBitStreamReader(),
                       CurStreamType))
         outs() << " codeid=" << Code;
-      if (Entry.ID != bitc::UNABBREV_RECORD)
+      const BitCodeAbbrev *Abbv = nullptr;
+      if (Entry.ID != bitc::UNABBREV_RECORD) {
+        Abbv = Stream.getAbbrev(Entry.ID);
         outs() << " abbrevid=" << Entry.ID;
+      }
 
       for (unsigned i = 0, e = Record.size(); i != e; ++i)
         outs() << " op" << i << "=" << (int64_t)Record[i];
 
       outs() << "/>";
 
+      if (Abbv) {
+        for (unsigned i = 1, e = Abbv->getNumOperandInfos(); i != e; ++i) {
+          const BitCodeAbbrevOp &Op = Abbv->getOperandInfo(i);
+          if (!Op.isEncoding() || Op.getEncoding() != BitCodeAbbrevOp::Array)
+            continue;
+          assert(i + 2 == e && "Array op not second to last");
+          std::string Str;
+          bool ArrayIsPrintable = true;
+          for (unsigned j = i - 1, je = Record.size(); j != je; ++j) {
+            if (!isprint(static_cast<unsigned char>(Record[j]))) {
+              ArrayIsPrintable = false;
+              break;
+            }
+            Str += (char)Record[j];
+          }
+          if (ArrayIsPrintable) outs() << " record string = '" << Str << "'";
+          break;
+        }
+      }
+
       if (Blob.data()) {
         outs() << " blob data = ";
         if (ShowBinaryBlobs) {
           outs() << "'";
           outs().write_escaped(Blob, /*hex=*/true) << "'";
         } else {
           bool BlobIsPrintable = true;
           for (unsigned i = 0, e = Blob.size(); i != e; ++i)