llvm-dwarfdump: Improve/fix pretty printing of array dimensions

This is to address post-commit feedback from Paul Robinson on r348954.

The original commit misinterprets count and upper bound as the same thing (I thought I saw GCC producing an upper bound the same as Clang's count, but GCC correctly produces an upper bound that's one less than the count (in C, that is, where arrays are zero indexed)).

I want to preserve the C-like output for the common case, so in the absence of a lower bound the count (or one greater than the upper bound) is rendered between []. In the trickier cases, where a lower bound is specified, a half-open range is used (eg: lower bound 1, count 2 would be "[1, 3)" and an unknown parts use a '?' (eg: "[1, ?)" or "[?, 7)" or "[?, ? + 3)").

Reviewers: aprantl, probinson, JDevlieghere

Differential Revision: https://reviews.llvm.org/D55721

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@349670 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 65 insertions, 24 deletions

diff --git a/lib/BinaryFormat/Dwarf.cpp b/lib/BinaryFormat/Dwarf.cpp
index fe8ce2bd7aa..46f8056774b 100644
--- a/lib/BinaryFormat/Dwarf.cpp
+++ b/lib/BinaryFormat/Dwarf.cpp
@@ -301,7 +301,7 @@ StringRef llvm::dwarf::LanguageString(unsigned Language) {
   switch (Language) {
   default:
     return StringRef();
-#define HANDLE_DW_LANG(ID, NAME, VERSION, VENDOR)                              \
+#define HANDLE_DW_LANG(ID, NAME, LOWER_BOUND, VERSION, VENDOR)                 \
   case DW_LANG_##NAME:                                                         \
     return "DW_LANG_" #NAME;
 #include "llvm/BinaryFormat/Dwarf.def"
@@ -310,7 +310,7 @@ StringRef llvm::dwarf::LanguageString(unsigned Language) {
 
 unsigned llvm::dwarf::getLanguage(StringRef LanguageString) {
   return StringSwitch<unsigned>(LanguageString)
-#define HANDLE_DW_LANG(ID, NAME, VERSION, VENDOR)                              \
+#define HANDLE_DW_LANG(ID, NAME, LOWER_BOUND, VERSION, VENDOR)                 \
   .Case("DW_LANG_" #NAME, DW_LANG_##NAME)
 #include "llvm/BinaryFormat/Dwarf.def"
       .Default(0);
@@ -320,7 +320,7 @@ unsigned llvm::dwarf::LanguageVersion(dwarf::SourceLanguage Lang) {
   switch (Lang) {
   default:
     return 0;
-#define HANDLE_DW_LANG(ID, NAME, VERSION, VENDOR)                              \
+#define HANDLE_DW_LANG(ID, NAME, LOWER_BOUND, VERSION, VENDOR)                 \
   case DW_LANG_##NAME:                                                         \
     return VERSION;
 #include "llvm/BinaryFormat/Dwarf.def"
@@ -331,13 +331,24 @@ unsigned llvm::dwarf::LanguageVendor(dwarf::SourceLanguage Lang) {
   switch (Lang) {
   default:
     return 0;
-#define HANDLE_DW_LANG(ID, NAME, VERSION, VENDOR)                              \
+#define HANDLE_DW_LANG(ID, NAME, LOWER_BOUND, VERSION, VENDOR)                 \
   case DW_LANG_##NAME:                                                         \
     return DWARF_VENDOR_##VENDOR;
 #include "llvm/BinaryFormat/Dwarf.def"
   }
 }
 
+Optional<unsigned> llvm::dwarf::LanguageLowerBound(dwarf::SourceLanguage Lang) {
+  switch (Lang) {
+  default:
+    return None;
+#define HANDLE_DW_LANG(ID, NAME, LOWER_BOUND, VERSION, VENDOR)                 \
+  case DW_LANG_##NAME:                                                         \
+    return LOWER_BOUND;
+#include "llvm/BinaryFormat/Dwarf.def"
+  }
+}
+
 StringRef llvm::dwarf::CaseString(unsigned Case) {
   switch (Case) {
   case DW_ID_case_sensitive:
diff --git a/lib/DebugInfo/DWARF/DWARFDie.cpp b/lib/DebugInfo/DWARF/DWARFDie.cpp
index 551e292fb03..e6018d9cf22 100644
--- a/lib/DebugInfo/DWARF/DWARFDie.cpp
+++ b/lib/DebugInfo/DWARF/DWARFDie.cpp
@@ -154,6 +154,52 @@ static void dumpTypeTagName(raw_ostream &OS, dwarf::Tag T) {
   OS << TagStr.substr(7, TagStr.size() - 12) << " ";
 }
 
+static void dumpArrayType(raw_ostream &OS, const DWARFDie &D) {
+  Optional<uint64_t> Bound;
+  for (const DWARFDie &C : D.children())
+    if (C.getTag() == DW_TAG_subrange_type) {
+      Optional<uint64_t> LB;
+      Optional<uint64_t> Count;
+      Optional<uint64_t> UB;
+      Optional<unsigned> DefaultLB;
+      if (Optional<DWARFFormValue> L = C.find(DW_AT_lower_bound))
+        LB = L->getAsUnsignedConstant();
+      if (Optional<DWARFFormValue> CountV = C.find(DW_AT_count))
+        Count = CountV->getAsUnsignedConstant();
+      if (Optional<DWARFFormValue> UpperV = C.find(DW_AT_upper_bound))
+        UB = UpperV->getAsUnsignedConstant();
+      if (Optional<DWARFFormValue> LV =
+              D.getDwarfUnit()->getUnitDIE().find(DW_AT_language))
+        if (Optional<uint64_t> LC = LV->getAsUnsignedConstant())
+          if ((DefaultLB =
+                   LanguageLowerBound(static_cast<dwarf::SourceLanguage>(*LC))))
+            if (LB && *LB == *DefaultLB)
+              LB = None;
+      if (!LB && !Count && !UB)
+        OS << "[]";
+      else if (!LB && (Count || UB) && DefaultLB)
+        OS << '[' << (Count ? *Count : *UB - *DefaultLB + 1) << ']';
+      else {
+        OS << "[[";
+        if (LB)
+          OS << *LB;
+        else
+          OS << '?';
+        OS << ", ";
+        if (Count)
+          if (LB)
+            OS << *LB + *Count;
+          else
+            OS << "? + " << *Count;
+        else if (UB)
+          OS << *UB + 1;
+        else
+          OS << '?';
+        OS << ")]";
+      }
+    }
+}
+
 /// Recursively dump the DIE type name when applicable.
 static void dumpTypeName(raw_ostream &OS, const DWARFDie &D) {
   if (!D.isValid())
@@ -201,24 +247,7 @@ static void dumpTypeName(raw_ostream &OS, const DWARFDie &D) {
     break;
   }
   case DW_TAG_array_type: {
-    Optional<uint64_t> Bound;
-    for (const DWARFDie &C : D.children())
-      if (C.getTag() == DW_TAG_subrange_type) {
-        OS << '[';
-        uint64_t LowerBound = 0;
-        if (Optional<DWARFFormValue> L = C.find(DW_AT_lower_bound))
-          if (Optional<uint64_t> LB = L->getAsUnsignedConstant()) {
-            LowerBound = *LB;
-            OS << LowerBound << '-';
-          }
-        if (Optional<DWARFFormValue> CountV = C.find(DW_AT_count)) {
-          if (Optional<uint64_t> C = CountV->getAsUnsignedConstant())
-            OS << (*C + LowerBound);
-        } else if (Optional<DWARFFormValue> UpperV = C.find(DW_AT_upper_bound))
-          if (Optional<uint64_t> U = UpperV->getAsUnsignedConstant())
-            OS << *U;
-        OS << ']';
-      }
+    dumpArrayType(OS, D);
     break;
   }
   case DW_TAG_pointer_type:
diff --git a/lib/IR/DebugInfo.cpp b/lib/IR/DebugInfo.cpp
index d1ff5457178..9fa31773b59 100644
--- a/lib/IR/DebugInfo.cpp
+++ b/lib/IR/DebugInfo.cpp
@@ -697,8 +697,9 @@ void Instruction::applyMergedLocation(const DILocation *LocA,
 
 static unsigned map_from_llvmDWARFsourcelanguage(LLVMDWARFSourceLanguage lang) {
   switch (lang) {
-#define HANDLE_DW_LANG(ID, NAME, VERSION, VENDOR) \
-case LLVMDWARFSourceLanguage##NAME: return ID;
+#define HANDLE_DW_LANG(ID, NAME, LOWER_BOUND, VERSION, VENDOR)                 \
+  case LLVMDWARFSourceLanguage##NAME:                                          \
+    return ID;
 #include "llvm/BinaryFormat/Dwarf.def"
 #undef HANDLE_DW_LANG
   }