[clang] Adjust TextDiagnostic style ranges for interesting source region

Author: tbaederr

clang/lib/Frontend/TextDiagnostic.cpp

@@ -349,14 +349,13 @@ struct SourceColumnMap {
 
 /// When the source code line we want to print is too long for
 /// the terminal, select the "interesting" region.
-static void selectInterestingSourceRegion(std::string &SourceLine,
-                                          std::string &CaretLine,
-                                          std::string &FixItInsertionLine,
-                                          Columns NonGutterColumns,
-                                          const SourceColumnMap &Map) {
-  Columns CaretColumns = Columns(CaretLine.size());
-  Columns FixItColumns =
-      Columns(llvm::sys::locale::columnWidth(FixItInsertionLine));
+static void selectInterestingSourceRegion(
+    std::string &SourceLine, std::string &CaretLine,
+    std::string &FixItInsertionLine, Columns NonGutterColumns,
+    const SourceColumnMap &Map,
+    SmallVector<clang::TextDiagnostic::StyleRange> &Styles) {
+  Columns CaretColumns = CaretLine.size();
+  Columns FixItColumns = llvm::sys::locale::columnWidth(FixItInsertionLine);
   Columns MaxColumns =
       std::max({Map.columns().V, CaretColumns.V, FixItColumns.V});
   // if the number of columns is less than the desired number we're done
@@ -369,13 +368,11 @@ static void selectInterestingSourceRegion(std::string &SourceLine,
   // Find the slice that we need to display the full caret line
   // correctly.
   Columns CaretStart = 0, CaretEnd = CaretLine.size();
-  for (; CaretStart != CaretEnd; CaretStart = CaretStart.next())
-    if (!isWhitespace(CaretLine[CaretStart.V]))
-      break;
+  while (CaretStart != CaretEnd && isWhitespace(CaretLine[CaretStart.V]))
+    CaretStart = CaretStart.next();
 
-  for (; CaretEnd != CaretStart; CaretEnd = CaretEnd.prev())
-    if (!isWhitespace(CaretLine[CaretEnd.V - 1]))
-      break;
+  while (CaretEnd != CaretStart && isWhitespace(CaretLine[CaretEnd.V]))
+    CaretEnd = CaretEnd.prev();
 
   // caret has already been inserted into CaretLine so the above whitespace
   // check is guaranteed to include the caret
@@ -521,8 +518,41 @@ static void selectInterestingSourceRegion(std::string &SourceLine,
   if (BackColumnsRemoved > Columns(BackEllipse.size()))
     SourceLine.replace(SourceEnd.V, std::string::npos, BackEllipse);
 
+  // Since we've modified the SourceLine, we also need to adjust the line's
+  // highlighting information. In particular, if we've removed
+  // from the front of the line, we need to move the style ranges to the
+  // left and remove unneeded ranges.
+  Columns FrontDiff = FrontColumnsRemoved > FrontEllipse.size()
+                          ? FrontColumnsRemoved - FrontEllipse.size()
+                          : 0;
+  Columns CodeStart = FrontColumnsRemoved > FrontEllipse.size()
+                          ? FrontEllipse.size()
+                          : FrontColumnsRemoved;
+  Bytes CodeEnd = Map.columnToByte(CodeStart + ColumnsKept);
+
+  for (auto &R : Styles) {
+    // Style ranges too far left. Just move them where they don't bother.
+    if (R.End < static_cast<unsigned>(FrontDiff.V)) {
+      R.Start = R.End = std::numeric_limits<int>::max();
+      continue;
+    }
+    // Move them left. (Note that this can wrap R.Start, but that doesn't
+    // matter).
+    R.Start -= FrontDiff.V;
+    R.End -= FrontDiff.V;
+
+    // If the range overlaps the end of the code, don't leak into the back
+    // ellipse.
+    if (R.Start < static_cast<unsigned>(CodeEnd.V) &&
+        R.End > static_cast<unsigned>(CodeEnd.V))
+      R.End = CodeEnd.V;
+    // Don't leak into the ellipse at the end.
+    if (R.Start >= static_cast<unsigned>(CodeEnd.V))
+      R.Start = R.End = std::numeric_limits<int>::max();
+  }
+
   // If that's enough then we're done
-  if (FrontColumnsRemoved + ColumnsKept <= Columns(NonGutterColumns))
+  if (FrontColumnsRemoved + ColumnsKept <= NonGutterColumns)
     return;
 
   // Otherwise remove the front as well
@@ -1391,6 +1421,12 @@ void TextDiagnostic::emitSnippetAndCaret(
       OS.indent(MaxLineNoDisplayWidth + 2) << "| ";
   };
 
+  Columns MessageLength = DiagOpts.MessageLength;
+
+  // If we don't have enough columns available, just abort now.
+  if (MessageLength != 0 && MessageLength <= Columns(MaxLineNoDisplayWidth + 4))
+    return;
+
   // Prepare source highlighting information for the lines we're about to
   // emit, starting from the first line.
   std::unique_ptr<SmallVector<StyleRange>[]> SourceStyles =
@@ -1450,10 +1486,10 @@ void TextDiagnostic::emitSnippetAndCaret(
 
     // If the source line is too long for our terminal, select only the
     // "interesting" source region within that line.
-    Columns MessageLength = DiagOpts.MessageLength;
-    if (MessageLength.V != 0)
+    if (MessageLength != 0)
       selectInterestingSourceRegion(SourceLine, CaretLine, FixItInsertionLine,
-                                    MessageLength, SourceColMap);
+                                    MessageLength, SourceColMap,
+                                    SourceStyles[LineNo - Lines.first]);
 
     // If we are in -fdiagnostics-print-source-range-info mode, we are trying
     // to produce easily machine parsable output.  Add a space before the
@@ -1508,8 +1544,9 @@ void TextDiagnostic::emitSnippet(StringRef SourceLine,
   // Print the source line one character at a time.
   bool PrintReversed = false;
   std::optional<llvm::raw_ostream::Colors> CurrentColor;
-  size_t I = 0;
+  size_t I = 0; // Bytes.
   while (I < SourceLine.size()) {
+    // llvm::errs() << "I: " <<I << '\n';
     auto [Str, WasPrintable] =
         printableTextForNextCharacter(SourceLine, &I, DiagOpts.TabStop);
 

clang/test/Frontend/diags-interesting-source-region-colors.cpp

@@ -0,0 +1,28 @@
+// RUN: not %clang_cc1 %s -fmessage-length=40 -fcolor-diagnostics -fno-show-source-location -Wunused-value -o - 2>&1 | FileCheck %s
+
+
+int main() {
+  1 +                                                        + if;
+  // CHECK: expected expression
+  // CHECK-NEXT: ...+ [[MAGENTA:.\[0;34m]]if[[RESET:.\[0m]];
+
+
+  a + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1;
+  // CHECK: use of undeclared identifier
+  // CHECK-NEXT: a + [[GREEN:.\[0;32m]]1[[RESET]] + [[GREEN]]1[[RESET]] + [[GREEN]]1[[RESET]] + [[GREEN]]1[[RESET]] + [[GREEN]]1[[RESET]] + [[GREEN]]1[[RESET]] + [[GREEN]]1[[RESET]] ...
+
+
+  /*😂😂😂*/ a + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 1;
+  // CHECK: use of undeclared identifier
+  // CHECK-NEXT: [[YELLOW:.\[0;33m]]/*😂😂😂*/[[RESET]] a + [[GREEN:.\[0;32m]]1[[RESET]] + [[GREEN]]1[[RESET]] + [[GREEN]]1[[RESET]] + [[GREEN]]1[[RESET]] ...
+
+
+
+  "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx";
+  // CHECK: [[GREEN:.\[0;32m]]"xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"[[RESET]];
+
+  "😂xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx";
+  // CHECK: [[GREEN:.\[0;32m]]"😂xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"[[RESET]];
+}
+
+