clang-format: Basic support for Java.

llvm-svn: 217759

clang/include/clang/Format/Format.h

@@ -47,6 +47,8 @@ struct FormatStyle {
     LK_None,
     /// Should be used for C, C++, ObjectiveC, ObjectiveC++.
     LK_Cpp,
+    /// Should be used for Java.
+    LK_Java,
     /// Should be used for JavaScript.
     LK_JavaScript,
     /// Should be used for Protocol Buffers

clang/lib/Format/Format.cpp

@@ -41,6 +41,7 @@ namespace yaml {
 template <> struct ScalarEnumerationTraits<FormatStyle::LanguageKind> {
   static void enumeration(IO &IO, FormatStyle::LanguageKind &Value) {
     IO.enumCase(Value, "Cpp", FormatStyle::LK_Cpp);
+    IO.enumCase(Value, "Java", FormatStyle::LK_Java);
     IO.enumCase(Value, "JavaScript", FormatStyle::LK_JavaScript);
     IO.enumCase(Value, "Proto", FormatStyle::LK_Proto);
   }
@@ -405,7 +406,11 @@ FormatStyle getGoogleStyle(FormatStyle::LanguageKind Language) {
   GoogleStyle.PenaltyReturnTypeOnItsOwnLine = 200;
   GoogleStyle.PenaltyBreakBeforeFirstCallParameter = 1;
 
-  if (Language == FormatStyle::LK_JavaScript) {
+  if (Language == FormatStyle::LK_Java) {
+    GoogleStyle.BreakBeforeBinaryOperators = FormatStyle::BOS_NonAssignment;
+    GoogleStyle.ColumnLimit = 100;
+    GoogleStyle.SpaceAfterCStyleCast = true;
+  } else if (Language == FormatStyle::LK_JavaScript) {
     GoogleStyle.BreakBeforeTernaryOperators = false;
     GoogleStyle.MaxEmptyLinesToKeep = 3;
     GoogleStyle.SpacesInContainerLiterals = false;
@@ -1031,6 +1036,8 @@ private:
   /// For example, 'public:' labels in classes are offset by 1 or 2
   /// characters to the left from their level.
   int getIndentOffset(const FormatToken &RootToken) {
+    if (Style.Language == FormatStyle::LK_Java)
+      return 0;
     if (RootToken.isAccessSpecifier(false) || RootToken.isObjCAccessSpecifier())
       return Style.AccessModifierOffset;
     return 0;
@@ -1754,6 +1761,8 @@ static StringRef getLanguageName(FormatStyle::LanguageKind Language) {
   switch (Language) {
   case FormatStyle::LK_Cpp:
     return "C++";
+  case FormatStyle::LK_Java:
+    return "Java";
   case FormatStyle::LK_JavaScript:
     return "JavaScript";
   case FormatStyle::LK_Proto:
@@ -2120,7 +2129,9 @@ const char *StyleOptionHelpDescription =
     "  -style=\"{BasedOnStyle: llvm, IndentWidth: 8}\"";
 
 static FormatStyle::LanguageKind getLanguageByFileName(StringRef FileName) {
-  if (FileName.endswith_lower(".js")) {
+  if (FileName.endswith(".java")) {
+    return FormatStyle::LK_Java;
+  } else if (FileName.endswith_lower(".js")) {
     return FormatStyle::LK_JavaScript;
   } else if (FileName.endswith_lower(".proto") ||
              FileName.endswith_lower(".protodevel")) {

clang/lib/Format/UnwrappedLineParser.cpp

@@ -685,7 +685,10 @@ void UnwrappedLineParser::parseStructuralElement() {
   case tok::kw_public:
   case tok::kw_protected:
   case tok::kw_private:
-    parseAccessSpecifier();
+    if (Style.Language == FormatStyle::LK_Java)
+      nextToken();
+    else
+      parseAccessSpecifier();
     return;
   case tok::kw_if:
     parseIfThenElse();
@@ -1405,6 +1408,9 @@ void UnwrappedLineParser::parseRecord() {
   // We fall through to parsing a structural element afterwards, so
   // class A {} n, m;
   // will end up in one unwrapped line.
+  // This does not apply for Java.
+  if (Style.Language == FormatStyle::LK_Java)
+    addUnwrappedLine();
 }
 
 void UnwrappedLineParser::parseObjCProtocolList() {

clang/unittests/Format/CMakeLists.txt

@@ -4,6 +4,7 @@ set(LLVM_LINK_COMPONENTS
 
 add_clang_unittest(FormatTests
   FormatTest.cpp
+  FormatTestJava.cpp
   FormatTestJS.cpp
   FormatTestProto.cpp
   )

clang/unittests/Format/FormatTestJava.cpp

@@ -0,0 +1,69 @@
+//===- unittest/Format/FormatTestJava.cpp - Formatting tests for Java -----===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "FormatTestUtils.h"
+#include "clang/Format/Format.h"
+#include "llvm/Support/Debug.h"
+#include "gtest/gtest.h"
+
+#define DEBUG_TYPE "format-test"
+
+namespace clang {
+namespace format {
+
+class FormatTestJava : public ::testing::Test {
+protected:
+  static std::string format(llvm::StringRef Code, unsigned Offset,
+                            unsigned Length, const FormatStyle &Style) {
+    DEBUG(llvm::errs() << "---\n");
+    DEBUG(llvm::errs() << Code << "\n\n");
+    std::vector<tooling::Range> Ranges(1, tooling::Range(Offset, Length));
+    tooling::Replacements Replaces = reformat(Style, Code, Ranges);
+    std::string Result = applyAllReplacements(Code, Replaces);
+    EXPECT_NE("", Result);
+    DEBUG(llvm::errs() << "\n" << Result << "\n\n");
+    return Result;
+  }
+
+  static std::string format(
+      llvm::StringRef Code,
+      const FormatStyle &Style = getGoogleStyle(FormatStyle::LK_Java)) {
+    return format(Code, 0, Code.size(), Style);
+  }
+
+  static FormatStyle getGoogleJSStyleWithColumns(unsigned ColumnLimit) {
+    FormatStyle Style = getGoogleStyle(FormatStyle::LK_Java);
+    Style.ColumnLimit = ColumnLimit;
+    return Style;
+  }
+
+  static void verifyFormat(
+      llvm::StringRef Code,
+      const FormatStyle &Style = getGoogleStyle(FormatStyle::LK_Java)) {
+    EXPECT_EQ(Code.str(), format(test::messUp(Code), Style));
+  }
+};
+
+TEST_F(FormatTestJava, ClassDeclarations) {
+  verifyFormat("public class SomeClass {\n"
+               "  private int a;\n"
+               "  private int b;\n"
+               "}");
+  verifyFormat("public class A {\n"
+               "  class B {\n"
+               "    int i;\n"
+               "  }\n"
+               "  class C {\n"
+               "    int j;\n"
+               "  }\n"
+               "}");
+}
+
+} // end namespace tooling
+} // end namespace clang