[clang] Make source locations space usage diagnostics numbers easier to read

Instead of write "12345678B", write "12345678B (12.34MB)".

Author: bricknerb

clang/include/clang/Basic/DiagnosticCommonKinds.td

@@ -389,13 +389,14 @@ def remark_sloc_usage : Remark<
   "source manager location address space usage:">,
   InGroup<DiagGroup<"sloc-usage">>, DefaultRemark, ShowInSystemHeader;
 def note_total_sloc_usage : Note<
-  "%0B in local locations, %1B in locations loaded from AST files, for a total "
-  "of %2B (%3%% of available space)">;
+  "%0B (%1B) in local locations, %2B (%3B) "
+  "in locations loaded from AST files, for a total of %4B (%5B) "
+  "(%6%% of available space)">;
 def note_file_sloc_usage : Note<
-  "file entered %0 time%s0 using %1B of space"
-  "%plural{0:|: plus %2B for macro expansions}2">;
+  "file entered %0 time%s0 using %1B (%2B) of space"
+  "%plural{0:|: plus %3B (%4B) for macro expansions}3">;
 def note_file_misc_sloc_usage : Note<
-  "%0 additional files entered using a total of %1B of space">;
+  "%0 additional files entered using a total of %1B (%2B) of space">;
 
 // Modules
 def err_module_format_unhandled : Error<

clang/lib/Basic/SourceManager.cpp

@@ -2227,6 +2227,28 @@ LLVM_DUMP_METHOD void SourceManager::dump() const {
   }
 }
 
+static std::string NumberToHumanString(uint64_t number) {
+  static constexpr std::array<std::pair<uint64_t, char>, 4> Units = {
+      {{1'000'000'000'000UL, 'T'},
+       {1'000'000'000UL, 'G'},
+       {1'000'000UL, 'M'},
+       {1'000UL, 'k'}}};
+
+  std::string human_string;
+  llvm::raw_string_ostream human_string_stream(human_string);
+  for (const auto &[UnitSize, UnitSign] : Units) {
+    if (number >= UnitSize) {
+      human_string_stream << llvm::format(
+          "%.2f%c", number / static_cast<double>(UnitSize), UnitSign);
+      break;
+    }
+  }
+  if (human_string.empty()) {
+    human_string_stream << number;
+  }
+  return human_string;
+}
+
 void SourceManager::noteSLocAddressSpaceUsage(
     DiagnosticsEngine &Diag, std::optional<unsigned> MaxNotes) const {
   struct Info {
@@ -2296,22 +2318,27 @@ void SourceManager::noteSLocAddressSpaceUsage(
   int UsagePercent = static_cast<int>(100.0 * double(LocalUsage + LoadedUsage) /
                                       MaxLoadedOffset);
   Diag.Report(SourceLocation(), diag::note_total_sloc_usage)
-    << LocalUsage << LoadedUsage << (LocalUsage + LoadedUsage) << UsagePercent;
+      << LocalUsage << NumberToHumanString(LocalUsage) << LoadedUsage
+      << NumberToHumanString(LoadedUsage) << (LocalUsage + LoadedUsage)
+      << NumberToHumanString(LocalUsage + LoadedUsage) << UsagePercent;
 
   // Produce notes on sloc address space usage for each file with a high usage.
   uint64_t ReportedSize = 0;
   for (auto &[Entry, FileInfo] :
        llvm::make_range(SortedUsage.begin(), SortedEnd)) {
     Diag.Report(FileInfo.Loc, diag::note_file_sloc_usage)
         << FileInfo.Inclusions << FileInfo.DirectSize
-        << (FileInfo.TotalSize - FileInfo.DirectSize);
+        << NumberToHumanString(FileInfo.DirectSize)
+        << (FileInfo.TotalSize - FileInfo.DirectSize)
+        << NumberToHumanString(FileInfo.TotalSize - FileInfo.DirectSize);
     ReportedSize += FileInfo.TotalSize;
   }
 
   // Describe any remaining usage not reported in the per-file usage.
   if (ReportedSize != CountedSize) {
     Diag.Report(SourceLocation(), diag::note_file_misc_sloc_usage)
-        << (SortedUsage.end() - SortedEnd) << CountedSize - ReportedSize;
+        << (SortedUsage.end() - SortedEnd) << CountedSize - ReportedSize
+        << NumberToHumanString(CountedSize - ReportedSize);
   }
 }
 

clang/test/Lexer/SourceLocationsOverflow.c

@@ -3,17 +3,17 @@
 // CHECK-NEXT: inc1.h{{.*}}: fatal error: translation unit is too large for Clang to process: ran out of source locations
 // CHECK-NEXT: #include "inc2.h"
 // CHECK-NEXT:          ^
-// CHECK-NEXT: note: 214{{.......}}B in local locations, 0B in locations loaded from AST files, for a total of 214{{.......}}B (99% of available space)
-// CHECK-NEXT: {{.*}}inc2.h:1:1: note: file entered 214{{..}} times using 214{{.......}}B of space
+// CHECK-NEXT: note: 214{{.......}}B (2.15GB) in local locations, 0B (0B) in locations loaded from AST files, for a total of 214{{.......}}B (2.15GB) (99% of available space)
+// CHECK-NEXT: {{.*}}inc2.h:1:1: note: file entered 214{{..}} times using 214{{.......}}B (2.15GB) of space
 // CHECK-NEXT: /*.................................................................................................
 // CHECK-NEXT: ^
-// CHECK-NEXT: {{.*}}inc1.h:1:1: note: file entered 15 times using 39{{....}}B of space
+// CHECK-NEXT: {{.*}}inc1.h:1:1: note: file entered 15 times using 39{{....}}B (396.92kB) of space
 // CHECK-NEXT: #include "inc2.h"
 // CHECK-NEXT: ^
-// CHECK-NEXT: <built-in>:1:1: note: file entered {{.*}} times using {{.*}}B of space
+// CHECK-NEXT: <built-in>:1:1: note: file entered {{.*}} times using {{.*}}B ({{.*}}B) of space
 // CHECK-NEXT: # {{.*}}
 // CHECK-NEXT: ^
-// CHECK-NEXT: {{.*}}SourceLocationsOverflow.c:1:1: note: file entered 1 time using {{.*}}B of space
+// CHECK-NEXT: {{.*}}SourceLocationsOverflow.c:1:1: note: file entered 1 time using {{.*}}B ({{.*}}B) of space
 // CHECK-NEXT: // RUN: not %clang %s -S -o - 2>&1 | FileCheck %s
 // CHECK-NEXT: ^
 // CHECK-NEXT: 1 error generated.

clang/test/Misc/sloc-usage.cpp

@@ -9,6 +9,6 @@ bool b = EQUALS(k, k);
 
 #pragma clang __debug sloc_usage // expected-remark {{address space usage}}
 // expected-note@* {{(0% of available space)}}
-// (this file)     expected-note-re@1 {{file entered 1 time using {{.*}}B of space plus 51B for macro expansions}}
-// (included file) expected-note-re@Inputs/include.h:1 {{file entered 3 times using {{.*}}B of space{{$}}}}
+// (this file)     expected-note-re@1 {{file entered 1 time using {{.*}}B ({{.*}}B) of space plus 51B (51B) for macro expansions}}
+// (included file) expected-note-re@Inputs/include.h:1 {{file entered 3 times using {{.*}}B ({{.*}}B) of space{{$}}}}
 // (builtins file) expected-note@* {{file entered}}