[PATCH] D68052: [clang-scan-deps] Allow continuation line backslashes followed by whitespace in the dependency source minimizer

[Alex Lorenz via Phabricator via cfe-commits]

arphaman created this revision.
arphaman added reviewers: dexonsmith, Bigcheese, kousikk, aganea.
Herald added subscribers: ributzka, tschuett, jkorous.
Herald added a project: clang.

Clang allows continuations that have whitespace between the backslash and the 
newline. This patch ensures that the dependency source minimizer can handle the 
whitespace between the backslash and the newline when looking for a line 
continuation.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D68052

Files:
  clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
  clang/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp


Index: clang/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
===================================================================
--- clang/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
+++ clang/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
@@ -157,19 +157,19 @@
 
   ASSERT_FALSE(minimizeSourceToDependencyDirectives(
       "#define MACRO(\t)\tcon \t tent\t", Out));
-  EXPECT_STREQ("#define MACRO() con \t tent\t\n", Out.data());
+  EXPECT_STREQ("#define MACRO() con \t tent\n", Out.data());
 
   ASSERT_FALSE(minimizeSourceToDependencyDirectives(
       "#define MACRO(\f)\fcon \f tent\f", Out));
-  EXPECT_STREQ("#define MACRO() con \f tent\f\n", Out.data());
+  EXPECT_STREQ("#define MACRO() con \f tent\n", Out.data());
 
   ASSERT_FALSE(minimizeSourceToDependencyDirectives(
       "#define MACRO(\v)\vcon \v tent\v", Out));
-  EXPECT_STREQ("#define MACRO() con \v tent\v\n", Out.data());
+  EXPECT_STREQ("#define MACRO() con \v tent\n", Out.data());
 
   ASSERT_FALSE(minimizeSourceToDependencyDirectives(
       "#define MACRO \t\v\f\v\t con\f\t\vtent\v\f \v", Out));
-  EXPECT_STREQ("#define MACRO con\f\t\vtent\v\n", Out.data());
+  EXPECT_STREQ("#define MACRO con\f\t\vtent\n", Out.data());
 }
 
 TEST(MinimizeSourceToDependencyDirectivesTest, DefineMultilineArgs) {
@@ -476,6 +476,17 @@
   EXPECT_STREQ("#define GUA RD\n", Out.data());
 }
 
+TEST(MinimizeSourceToDependencyDirectivesTest,
+     WhitespaceAfterLineContinuationSlash) {
+  SmallVector<char, 128> Out;
+
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives("#define A 1 + \\  \n"
+                                                    "2 + \\\t\n"
+                                                    "3\n",
+                                                    Out));
+  EXPECT_STREQ("#define A 1 + 2 + 3\n", Out.data());
+}
+
 TEST(MinimizeSourceToDependencyDirectivesTest, PoundWarningAndError) {
   SmallVector<char, 128> Out;
 
Index: clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
===================================================================
--- clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
+++ clang/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
@@ -244,7 +244,8 @@
   }
 }
 
-static const char *reverseOverSpaces(const char *First, const char *Last) {
+static const char *reverseOverSpacesUntilFirstSpace(const char *First,
+                                                    const char *Last) {
   assert(First <= Last);
   const char *PrevLast = Last;
   while (First != Last && isHorizontalWhitespace(Last[-1])) {
@@ -254,6 +255,13 @@
   return PrevLast;
 }
 
+static const char *reverseOverSpaces(const char *First, const char *Last) {
+  assert(First <= Last);
+  while (First != Last && isHorizontalWhitespace(Last[-1]))
+    --Last;
+  return Last;
+}
+
 static void skipLineComment(const char *&First, const char *const End) {
   assert(First[0] == '/' && First[1] == '/');
   First += 2;
@@ -385,7 +393,7 @@
       }
 
       // Deal with "//..." and "/*...*/".
-      append(First, reverseOverSpaces(First, Last));
+      append(First, reverseOverSpacesUntilFirstSpace(First, Last));
       First = Last;
 
       if (Last[1] == '/') {
@@ -400,15 +408,20 @@
     } while (Last != End && !isVerticalWhitespace(*Last));
 
     // Print out the string.
-    if (Last == End || Last == First || Last[-1] != '\\') {
-      append(First, reverseOverSpaces(First, Last));
+    const char *LastBeforeTrailingSpace = reverseOverSpaces(First, Last);
+    if (Last == End || LastBeforeTrailingSpace == First ||
+        LastBeforeTrailingSpace[-1] != '\\') {
+      append(First, LastBeforeTrailingSpace);
       First = Last;
       skipNewline(First, End);
       return;
     }
 
-    // Print up to the backslash, backing up over spaces.
-    append(First, reverseOverSpaces(First, Last - 1));
+    // Print up to the backslash, backing up over spaces. Preserve at least one
+    // space, as the space matters when tokens are separated by a line
+    // continuation.
+    append(First, reverseOverSpacesUntilFirstSpace(
+                      First, LastBeforeTrailingSpace - 1));
 
     First = Last;
     skipNewline(First, End);

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