[clang-scan-deps] Minimizer: Correctly handle multi-line content with CR+LF line endings

Previously, an #error directive with quoted, multi-line content, along with CR+LF line endings wasn't handled correctly.

Differential Revision: https://reviews.llvm.org/D66556

llvm-svn: 369986

Author: aganea

clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp

@@ -196,33 +196,51 @@ static void skipString(const char *&First, const char *const End) {
     ++First; // Finish off the string.
 }
 
-static void skipNewline(const char *&First, const char *End) {
-  assert(isVerticalWhitespace(*First));
-  ++First;
+// Returns the length of EOL, either 0 (no end-of-line), 1 (\n) or 2 (\r\n)
+static unsigned isEOL(const char *First, const char *const End) {
   if (First == End)
-    return;
+    return 0;
+  if (End - First > 1 && isVerticalWhitespace(First[0]) &&
+      isVerticalWhitespace(First[1]) && First[0] != First[1])
+    return 2;
+  return !!isVerticalWhitespace(First[0]);
+}
 
-  // Check for "\n\r" and "\r\n".
-  if (LLVM_UNLIKELY(isVerticalWhitespace(*First) && First[-1] != First[0]))
-    ++First;
+// Returns the length of the skipped newline
+static unsigned skipNewline(const char *&First, const char *End) {
+  if (First == End)
+    return 0;
+  assert(isVerticalWhitespace(*First));
+  unsigned Len = isEOL(First, End);
+  assert(Len && "expected newline");
+  First += Len;
+  return Len;
+}
+
+static bool wasLineContinuation(const char *First, unsigned EOLLen) {
+  return *(First - (int)EOLLen - 1) == '\\';
 }
 
 static void skipToNewlineRaw(const char *&First, const char *const End) {
   for (;;) {
     if (First == End)
       return;
 
-    if (isVerticalWhitespace(*First))
+    unsigned Len = isEOL(First, End);
+    if (Len)
       return;
 
-    while (!isVerticalWhitespace(*First))
+    do {
       if (++First == End)
         return;
+      Len = isEOL(First, End);
+    } while (!Len);
 
     if (First[-1] != '\\')
       return;
 
-    ++First; // Keep going...
+    First += Len;
+    // Keep skipping lines...
   }
 }
 
@@ -277,7 +295,7 @@ static bool isQuoteCppDigitSeparator(const char *const Start,
 }
 
 static void skipLine(const char *&First, const char *const End) {
-  do {
+  for (;;) {
     assert(First <= End);
     if (First == End)
       return;
@@ -322,9 +340,10 @@ static void skipLine(const char *&First, const char *const End) {
       return;
 
     // Skip over the newline.
-    assert(isVerticalWhitespace(*First));
-    skipNewline(First, End);
-  } while (First[-2] == '\\'); // Continue past line-continuations.
+    unsigned Len = skipNewline(First, End);
+    if (!wasLineContinuation(First, Len)) // Continue past line-continuations.
+      break;
+  }
 }
 
 static void skipDirective(StringRef Name, const char *&First,
@@ -379,6 +398,8 @@ void Minimizer::printToNewline(const char *&First, const char *const End) {
     // Print out the string.
     if (Last == End || Last == First || Last[-1] != '\\') {
       append(First, reverseOverSpaces(First, Last));
+      First = Last;
+      skipNewline(First, End);
       return;
     }
 

clang/test/Lexer/minimize_source_to_dependency_directives_invalid_error.c

@@ -0,0 +1,16 @@
+// Test CF+LF are properly handled along with quoted, multi-line #error
+// RUN: cat %s | unix2dos | %clang_cc1 -DOTHER -print-dependency-directives-minimized-source 2>&1 | FileCheck %s
+
+#ifndef TEST
+#error "message \
+   more message \
+   even more"
+#endif
+
+#ifdef OTHER
+#include <string>
+#endif
+
+// CHECK:      #ifdef OTHER
+// CHECK-NEXT: #include <string>
+// CHECK-NEXT: #endif