[clang-format] Improve detection of ObjC for-in statements

Summary:
Previously, clang-format would detect the following as an
Objective-C for-in statement:

  for (int x = in.value(); ...) {}

because the logic only decided a for-loop was definitely *not*
an Objective-C for-in loop after it saw a semicolon or a colon.

To fix this, I delayed the decision of whether this was a for-in
statement until after we found the matching right-paren, at which
point we know if we've seen a semicolon or not.

Test Plan: New tests added. Ran tests with:
  make -j12 FormatTests && ./tools/clang/unittests/Format/FormatTests

Reviewers: krasimir, jolesiak

Reviewed By: jolesiak

Subscribers: djasper, cfe-commits, klimek

Differential Revision: https://reviews.llvm.org/D43904

llvm-svn: 326815

clang/lib/Format/TokenAnnotator.cpp

@@ -216,6 +216,7 @@ private:
     bool HasMultipleParametersOnALine = false;
     bool MightBeObjCForRangeLoop =
         Left->Previous && Left->Previous->is(tok::kw_for);
+    FormatToken *PossibleObjCForInToken = nullptr;
     while (CurrentToken) {
       // LookForDecls is set when "if (" has been seen. Check for
       // 'identifier' '*' 'identifier' followed by not '=' -- this
@@ -301,10 +302,17 @@ private:
            CurrentToken->Previous->isSimpleTypeSpecifier()) &&
           !CurrentToken->is(tok::l_brace))
         Contexts.back().IsExpression = false;
-      if (CurrentToken->isOneOf(tok::semi, tok::colon))
+      if (CurrentToken->isOneOf(tok::semi, tok::colon)) {
         MightBeObjCForRangeLoop = false;
-      if (MightBeObjCForRangeLoop && CurrentToken->is(Keywords.kw_in))
-        CurrentToken->Type = TT_ObjCForIn;
+        if (PossibleObjCForInToken) {
+          PossibleObjCForInToken->Type = TT_Unknown;
+          PossibleObjCForInToken = nullptr;
+        }
+      }
+      if (MightBeObjCForRangeLoop && CurrentToken->is(Keywords.kw_in)) {
+        PossibleObjCForInToken = CurrentToken;
+        PossibleObjCForInToken->Type = TT_ObjCForIn;
+      }
       // When we discover a 'new', we set CanBeExpression to 'false' in order to
       // parse the type correctly. Reset that after a comma.
       if (CurrentToken->is(tok::comma))

clang/unittests/Format/FormatTest.cpp

@@ -742,6 +742,12 @@ TEST_F(FormatTest, FormatsForLoop) {
                "     aaaaaaaaaaaaaaaaaaaaaaaaaaa != bbbbbbbbbbbbbbbbbbbbbbb;\n"
                "     ++aaaaaaaaaaaaaaaaaaaaaaaaaaa) {");
 
+  // These should not be formatted as Objective-C for-in loops.
+  verifyFormat("for (Foo *x = 0; x != in; x++) {\n}");
+  verifyFormat("Foo *x;\nfor (x = 0; x != in; x++) {\n}");
+  verifyFormat("Foo *x;\nfor (x in y) {\n}");
+  verifyFormat("for (const Foo<Bar> &baz = in.value(); !baz.at_end(); ++baz) {\n}");
+
   FormatStyle NoBinPacking = getLLVMStyle();
   NoBinPacking.BinPackParameters = false;
   verifyFormat("for (int aaaaaaaaaaa = 1;\n"
@@ -12082,6 +12088,31 @@ TEST_F(FormatTest, FileAndCode) {
   EXPECT_EQ(FormatStyle::LK_ObjC, guessLanguage("foo", "@interface Foo\n@end\n"));
 }
 
+TEST_F(FormatTest, GuessLanguageWithForIn) {
+  EXPECT_EQ(FormatStyle::LK_Cpp,
+            guessLanguage("foo.h", "for (Foo *x = 0; x != in; x++) {}"));
+  EXPECT_EQ(FormatStyle::LK_ObjC,
+            guessLanguage("foo.h", "for (Foo *x in bar) {}"));
+  EXPECT_EQ(FormatStyle::LK_ObjC,
+            guessLanguage("foo.h", "for (Foo *x in [bar baz]) {}"));
+  EXPECT_EQ(FormatStyle::LK_ObjC,
+            guessLanguage("foo.h", "for (Foo *x in [bar baz:blech]) {}"));
+  EXPECT_EQ(
+      FormatStyle::LK_ObjC,
+      guessLanguage("foo.h", "for (Foo *x in [bar baz:blech, 1, 2, 3, 0]) {}"));
+  EXPECT_EQ(FormatStyle::LK_ObjC,
+            guessLanguage("foo.h", "for (Foo *x in [bar baz:^{[uh oh];}]) {}"));
+  EXPECT_EQ(FormatStyle::LK_Cpp,
+            guessLanguage("foo.h", "Foo *x; for (x = 0; x != in; x++) {}"));
+  EXPECT_EQ(FormatStyle::LK_ObjC,
+            guessLanguage("foo.h", "Foo *x; for (x in y) {}"));
+  EXPECT_EQ(
+      FormatStyle::LK_Cpp,
+      guessLanguage(
+          "foo.h",
+          "for (const Foo<Bar>& baz = in.value(); !baz.at_end(); ++baz) {}"));
+}
+
 } // end namespace
 } // end namespace format
 } // end namespace clang

clang/unittests/Format/FormatTestObjC.cpp

@@ -893,6 +893,13 @@ TEST_F(FormatTestObjC, ObjCForIn) {
                "    foo(n);\n"
                "  }\n"
                "}");
+  verifyFormat("for (Foo *x in bar) {\n}");
+  verifyFormat("for (Foo *x in [bar baz]) {\n}");
+  verifyFormat("for (Foo *x in [bar baz:blech]) {\n}");
+  verifyFormat("for (Foo *x in [bar baz:blech, 1, 2, 3, 0]) {\n}");
+  verifyFormat("for (Foo *x in [bar baz:^{\n"
+               "       [uh oh];\n"
+               "     }]) {\n}");
 }
 
 TEST_F(FormatTestObjC, ObjCLiterals) {