[PATCH] D66556: [clang-scan-deps] Minimizer: Correctly handle multi-line content with CR+LF line endings

[Alexandre Ganea via Phabricator via cfe-commits]

aganea created this revision.
aganea added reviewers: arphaman, dexonsmith, Bigcheese.
aganea added a project: clang.
Herald added a subscriber: tschuett.

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


Repository:
  rC Clang

https://reviews.llvm.org/D66556

Files:
  lib/Lex/DependencyDirectivesSourceMinimizer.cpp
  test/Lexer/minimize_source_to_dependency_directives_include.c


Index: test/Lexer/minimize_source_to_dependency_directives_include.c
===================================================================
--- test/Lexer/minimize_source_to_dependency_directives_include.c
+++ test/Lexer/minimize_source_to_dependency_directives_include.c
@@ -0,0 +1,8 @@
+// Test double slashes in #include directive along with angle brackets. Previously, this was interpreted as comments.
+// RUN: %clang_cc1 -DTEST -print-dependency-directives-minimized-source %s 2>&1 | FileCheck %s
+
+#include "a//b.h"
+#include <a//b.h>
+
+// CHECK: #include "a//b.h"
+// CHECK: #include <a//b.h>
Index: lib/Lex/DependencyDirectivesSourceMinimizer.cpp
===================================================================
--- lib/Lex/DependencyDirectivesSourceMinimizer.cpp
+++ lib/Lex/DependencyDirectivesSourceMinimizer.cpp
@@ -196,15 +196,27 @@
     ++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) {
+  assert(isVerticalWhitespace(*First));
+  unsigned Len = isEOL(First, End);
+  assert(Len);
+  First += Len;
+  return Len;
+}
+
+static bool wasLineContinuation(const char *First, unsigned Len) {
+  return *(First - (int)Len - 1) == '\\';
 }
 
 static void skipToNewlineRaw(const char *&First, const char *const End) {
@@ -212,17 +224,22 @@
     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);
+
+    First += Len;
 
-    if (First[-1] != '\\')
+    if (!wasLineContinuation(First, Len))
       return;
 
-    ++First; // Keep going...
+    // Keep skipping lines...
   }
 }
 
@@ -277,7 +294,7 @@
 }
 
 static void skipLine(const char *&First, const char *const End) {
-  do {
+  for (;;) {
     assert(First <= End);
     if (First == End)
       return;
@@ -322,9 +339,10 @@
       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 +397,8 @@
     // Print out the string.
     if (Last == End || Last == First || Last[-1] != '\\') {
       append(First, reverseOverSpaces(First, Last));
+      First = Last;
+      skipNewline(First, End);
       return;
     }
 

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits