[clang-scan-deps] Improve string/character literal skipping

The existing string/character literal skipping code in the
dependency directives source minimizer has two issues:

- It doesn't stop the scanning when a newline is reached before the terminating character,
unlike the lexer which considers the token to be done (even if it's invalid) at the end of the line.

- It doesn't support whitespace between '\' and the newline when looking if the '\' is used as a line continuation character.

This commit fixes both issues.

Differential Revision: https://reviews.llvm.org/D68436

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@374127 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 29 insertions, 11 deletions

diff --git a/lib/Lex/DependencyDirectivesSourceMinimizer.cpp b/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
index 2ffbcfb7e6..f063ed711c 100644
--- a/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
+++ b/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
@@ -185,17 +185,6 @@ static void skipRawString(const char *&First, const char *const End) {
   }
 }
 
-static void skipString(const char *&First, const char *const End) {
-  assert(*First == '\'' || *First == '"' || *First == '<');
-  const char Terminator = *First == '<' ? '>' : *First;
-  for (++First; First != End && *First != Terminator; ++First)
-    if (*First == '\\')
-      if (++First == End)
-        return;
-  if (First != End)
-    ++First; // Finish off the string.
-}
-
 // 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)
@@ -206,6 +195,35 @@ static unsigned isEOL(const char *First, const char *const End) {
   return !!isVerticalWhitespace(First[0]);
 }
 
+static void skipString(const char *&First, const char *const End) {
+  assert(*First == '\'' || *First == '"' || *First == '<');
+  const char Terminator = *First == '<' ? '>' : *First;
+  for (++First; First != End && *First != Terminator; ++First) {
+    // String and character literals don't extend past the end of the line.
+    if (isVerticalWhitespace(*First))
+      return;
+    if (*First != '\\')
+      continue;
+    // Skip past backslash to the next character. This ensures that the
+    // character right after it is skipped as well, which matters if it's
+    // the terminator.
+    if (++First == End)
+      return;
+    if (!isWhitespace(*First))
+      continue;
+    // Whitespace after the backslash might indicate a line continuation.
+    const char *FirstAfterBackslashPastSpace = First;
+    skipOverSpaces(FirstAfterBackslashPastSpace, End);
+    if (unsigned NLSize = isEOL(FirstAfterBackslashPastSpace, End)) {
+      // Advance the character pointer to the next line for the next
+      // iteration.
+      First = FirstAfterBackslashPastSpace + NLSize - 1;
+    }
+  }
+  if (First != End)
+    ++First; // Finish off the string.
+}
+
 // Returns the length of the skipped newline
 static unsigned skipNewline(const char *&First, const char *End) {
   if (First == End)