juliehockett updated this revision to Diff 137244.
juliehockett added a comment.
Adding hashing to reduce the size of USRs and updating tests.
https://reviews.llvm.org/D41102
Files:
CMakeLists.txt
clang-doc/BitcodeWriter.cpp
clang-doc/BitcodeWriter.h
clang-doc/CMakeLists.txt
clang-doc/ClangDoc.h
clang-doc/Mapper.cpp
clang-doc/Mapper.h
clang-doc/Representation.h
clang-doc/Serialize.cpp
clang-doc/Serialize.h
clang-doc/tool/CMakeLists.txt
clang-doc/tool/ClangDocMain.cpp
docs/clang-doc.rst
test/CMakeLists.txt
test/clang-doc/mapper-class-in-class.cpp
test/clang-doc/mapper-class-in-function.cpp
test/clang-doc/mapper-class.cpp
test/clang-doc/mapper-comments.cpp
test/clang-doc/mapper-enum.cpp
test/clang-doc/mapper-function.cpp
test/clang-doc/mapper-method.cpp
test/clang-doc/mapper-namespace.cpp
test/clang-doc/mapper-struct.cpp
test/clang-doc/mapper-union.cpp
Index: test/clang-doc/mapper-union.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-union.cpp
@@ -0,0 +1,28 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/0B8A6B938B939B77C6325CCCC8AA3E938BF9E2E8.bc --dump | FileCheck %s
+
+union D { int X; int Y; };
+
+// CHECK: <BLOCKINFO_BLOCK/>
+// CHECK-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-NEXT: </VersionBlock>
+// CHECK-NEXT: <RecordBlock NumWords=31 BlockCodeSize=4>
+ // CHECK-NEXT: <USR abbrevid=4 op0=40/> blob data = '0B8A6B938B939B77C6325CCCC8AA3E938BF9E2E8'
+ // CHECK-NEXT: <Name abbrevid=5 op0=1/> blob data = 'D'
+ // CHECK-NEXT: <TagType abbrevid=9 op0=2/>
+ // CHECK-NEXT: <MemberTypeBlock NumWords=6 BlockCodeSize=4>
+ // CHECK-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-NEXT: <Name abbrevid=5 op0=4/> blob data = 'D::X'
+ // CHECK-NEXT: <Access abbrevid=6 op0=3/>
+ // CHECK-NEXT: </MemberTypeBlock>
+ // CHECK-NEXT: <MemberTypeBlock NumWords=6 BlockCodeSize=4>
+ // CHECK-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-NEXT: <Name abbrevid=5 op0=4/> blob data = 'D::Y'
+ // CHECK-NEXT: <Access abbrevid=6 op0=3/>
+ // CHECK-NEXT: </MemberTypeBlock>
+// CHECK-NEXT: </RecordBlock>
Index: test/clang-doc/mapper-struct.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-struct.cpp
@@ -0,0 +1,22 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/06B5F6A19BA9F6A832E127C9968282B94619B210.bc --dump | FileCheck %s
+
+struct C { int i; };
+
+// CHECK: <BLOCKINFO_BLOCK/>
+// CHECK-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-NEXT: </VersionBlock>
+// CHECK-NEXT: <RecordBlock NumWords=22 BlockCodeSize=4>
+ // CHECK-NEXT: <USR abbrevid=4 op0=40/> blob data = '06B5F6A19BA9F6A832E127C9968282B94619B210'
+ // CHECK-NEXT: <Name abbrevid=5 op0=1/> blob data = 'C'
+ // CHECK-NEXT: <MemberTypeBlock NumWords=6 BlockCodeSize=4>
+ // CHECK-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-NEXT: <Name abbrevid=5 op0=4/> blob data = 'C::i'
+ // CHECK-NEXT: <Access abbrevid=6 op0=3/>
+ // CHECK-NEXT: </MemberTypeBlock>
+// CHECK-NEXT: </RecordBlock>
Index: test/clang-doc/mapper-namespace.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-namespace.cpp
@@ -0,0 +1,17 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/8D042EFFC98B373450BC6B5B90A330C25A150E9C.bc --dump | FileCheck %s
+
+namespace A {}
+
+// CHECK: <BLOCKINFO_BLOCK/>
+// CHECK-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-NEXT: </VersionBlock>
+// CHECK-NEXT: <NamespaceBlock NumWords=14 BlockCodeSize=4>
+ // CHECK-NEXT: <USR abbrevid=4 op0=40/> blob data = '8D042EFFC98B373450BC6B5B90A330C25A150E9C'
+ // CHECK-NEXT: <Name abbrevid=5 op0=1/> blob data = 'A'
+// CHECK-NEXT: </NamespaceBlock>
Index: test/clang-doc/mapper-method.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-method.cpp
@@ -0,0 +1,41 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/F0F9FC65FC90F54F690144A7AFB15DFC3D69B6E6.bc --dump | FileCheck %s --check-prefix CHECK-G-F
+// RUN: llvm-bcanalyzer %t/docs/bc/4202E8BF0ECB12AE354C8499C52725B0EE30AED5.bc --dump | FileCheck %s --check-prefix CHECK-G
+
+class G {
+public:
+ int Method(int param) { return param; }
+};
+
+// CHECK-G: <BLOCKINFO_BLOCK/>
+// CHECK-G-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-G-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-G-NEXT: </VersionBlock>
+// CHECK-G-NEXT: <RecordBlock NumWords=14 BlockCodeSize=4>
+ // CHECK-G-NEXT: <USR abbrevid=4 op0=40/> blob data = '4202E8BF0ECB12AE354C8499C52725B0EE30AED5'
+ // CHECK-G-NEXT: <Name abbrevid=5 op0=1/> blob data = 'G'
+ // CHECK-G-NEXT: <TagType abbrevid=9 op0=3/>
+// CHECK-G-NEXT: </RecordBlock>
+
+// CHECK-G-F: <BLOCKINFO_BLOCK/>
+// CHECK-G-F-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-G-F-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-G-F-NEXT: </VersionBlock>
+// CHECK-G-F-NEXT: <FunctionBlock NumWords=54 BlockCodeSize=4>
+ // CHECK-G-F-NEXT: <USR abbrevid=4 op0=40/> blob data = 'F0F9FC65FC90F54F690144A7AFB15DFC3D69B6E6'
+ // CHECK-G-F-NEXT: <Name abbrevid=5 op0=6/> blob data = 'Method'
+ // CHECK-G-F-NEXT: <Namespace abbrevid=6 op0=1 op1=40/> blob data = '4202E8BF0ECB12AE354C8499C52725B0EE30AED5'
+ // CHECK-G-F-NEXT: <IsMethod abbrevid=11 op0=1/>
+ // CHECK-G-F-NEXT: <Parent abbrevid=9 op0=1 op1=40/> blob data = '4202E8BF0ECB12AE354C8499C52725B0EE30AED5'
+ // CHECK-G-F-NEXT: <TypeBlock NumWords=4 BlockCodeSize=4>
+ // CHECK-G-F-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-G-F-NEXT: </TypeBlock>
+ // CHECK-G-F-NEXT: <FieldTypeBlock NumWords=7 BlockCodeSize=4>
+ // CHECK-G-F-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-G-F-NEXT: <Name abbrevid=5 op0=5/> blob data = 'param'
+ // CHECK-G-F-NEXT: </FieldTypeBlock>
+// CHECK-G-F-NEXT: </FunctionBlock>
Index: test/clang-doc/mapper-function.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-function.cpp
@@ -0,0 +1,24 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/A44B32CC3C087C9AF75DAF50DE193E85E7B2C16B.bc --dump | FileCheck %s
+
+int F(int param) { return param; }
+
+// CHECK: <BLOCKINFO_BLOCK/>
+// CHECK-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-NEXT: </VersionBlock>
+// CHECK-NEXT: <FunctionBlock NumWords=29 BlockCodeSize=4>
+ // CHECK-NEXT: <USR abbrevid=4 op0=40/> blob data = 'A44B32CC3C087C9AF75DAF50DE193E85E7B2C16B'
+ // CHECK-NEXT: <Name abbrevid=5 op0=1/> blob data = 'F'
+ // CHECK-NEXT: <TypeBlock NumWords=4 BlockCodeSize=4>
+ // CHECK-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-NEXT: </TypeBlock>
+ // CHECK-NEXT: <FieldTypeBlock NumWords=7 BlockCodeSize=4>
+ // CHECK-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-NEXT: <Name abbrevid=5 op0=5/> blob data = 'param'
+ // CHECK-NEXT: </FieldTypeBlock>
+// CHECK-NEXT: </FunctionBlock>
Index: test/clang-doc/mapper-enum.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-enum.cpp
@@ -0,0 +1,42 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/FC07BD34D5E77782C263FA944447929EA8753740.bc --dump | FileCheck %s --check-prefix CHECK-B
+// RUN: llvm-bcanalyzer %t/docs/bc/020E6C32A700C3170C009FCCD41671EDDBEAF575.bc --dump | FileCheck %s --check-prefix CHECK-C
+
+enum B { X, Y };
+
+// CHECK-B: <BLOCKINFO_BLOCK/>
+// CHECK-B-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-B-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-B-NEXT: </VersionBlock>
+// CHECK-B-NEXT: <EnumBlock NumWords=26 BlockCodeSize=4>
+ // CHECK-B-NEXT: <USR abbrevid=4 op0=40/> blob data = 'FC07BD34D5E77782C263FA944447929EA8753740'
+ // CHECK-B-NEXT: <Name abbrevid=5 op0=1/> blob data = 'B'
+ // CHECK-B-NEXT: <TypeBlock NumWords=4 BlockCodeSize=4>
+ // CHECK-B-NEXT: <Type abbrevid=4 op0=3 op1=1/> blob data = 'X'
+ // CHECK-B-NEXT: </TypeBlock>
+ // CHECK-B-NEXT: <TypeBlock NumWords=4 BlockCodeSize=4>
+ // CHECK-B-NEXT: <Type abbrevid=4 op0=3 op1=1/> blob data = 'Y'
+ // CHECK-B-NEXT: </TypeBlock>
+// CHECK-B-NEXT: </EnumBlock>
+
+enum class C { A, B };
+
+// CHECK-C: <BLOCKINFO_BLOCK/>
+// CHECK-C-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-C-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-C-NEXT: </VersionBlock>
+// CHECK-C-NEXT: <EnumBlock NumWords=26 BlockCodeSize=4>
+ // CHECK-C-NEXT: <USR abbrevid=4 op0=40/> blob data = '020E6C32A700C3170C009FCCD41671EDDBEAF575'
+ // CHECK-C-NEXT: <Name abbrevid=5 op0=1/> blob data = 'C'
+ // CHECK-C-NEXT: <Scoped abbrevid=9 op0=1/>
+ // CHECK-C-NEXT: <TypeBlock NumWords=4 BlockCodeSize=4>
+ // CHECK-C-NEXT: <Type abbrevid=4 op0=3 op1=4/> blob data = 'C::A'
+ // CHECK-C-NEXT: </TypeBlock>
+ // CHECK-C-NEXT: <TypeBlock NumWords=4 BlockCodeSize=4>
+ // CHECK-C-NEXT: <Type abbrevid=4 op0=3 op1=4/> blob data = 'C::B'
+ // CHECK-C-NEXT: </TypeBlock>
+// CHECK-C-NEXT: </EnumBlock>
Index: test/clang-doc/mapper-comments.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-comments.cpp
@@ -0,0 +1,171 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/7574630614A535710E5A6ABCFFF98BCA2D06A4CA.bc --dump | FileCheck %s
+
+/// \brief Brief description.
+///
+/// Extended description that
+/// continues onto the next line.
+///
+/// <ul> class="test">
+/// <li> Testing.
+/// </ul>
+///
+/// \verbatim
+/// The description continues.
+/// \endverbatim
+///
+/// \param [out] I is a parameter.
+/// \param J is a parameter.
+/// \return int
+int F(int I, int J);
+
+// CHECK: <BLOCKINFO_BLOCK/>
+// CHECK-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-NEXT: </VersionBlock>
+// CHECK-NEXT: <FunctionBlock NumWords=389 BlockCodeSize=4>
+ // CHECK-NEXT: <USR abbrevid=4 op0=40/> blob data = '7574630614A535710E5A6ABCFFF98BCA2D06A4CA'
+ // CHECK-NEXT: <Name abbrevid=5 op0=1/> blob data = 'F'
+ // CHECK-NEXT: <CommentBlock NumWords=351 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'FullComment'
+ // CHECK-NEXT: <CommentBlock NumWords=13 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=5 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=31 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=19/> blob data = 'BlockCommandComment'
+ // CHECK-NEXT: <Name abbrevid=6 op0=5/> blob data = 'brief'
+ // CHECK-NEXT: <CommentBlock NumWords=19 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=11 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=19/> blob data = ' Brief description.'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=37 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=13 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=26/> blob data = ' Extended description that'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=14 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=30/> blob data = ' continues onto the next line.'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=83 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=5 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=9 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=19/> blob data = 'HTMLStartTagComment'
+ // CHECK-NEXT: <Name abbrevid=6 op0=2/> blob data = 'ul'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=10 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=14/> blob data = ' class="test">'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=5 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=9 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=19/> blob data = 'HTMLStartTagComment'
+ // CHECK-NEXT: <Name abbrevid=6 op0=2/> blob data = 'li'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=9 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=9/> blob data = ' Testing.'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=5 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=9 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=17/> blob data = 'HTMLEndTagComment'
+ // CHECK-NEXT: <Name abbrevid=6 op0=2/> blob data = 'ul'
+ // CHECK-NEXT: <SelfClosing abbrevid=10 op0=1/>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=13 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=5 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=32 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=20/> blob data = 'VerbatimBlockComment'
+ // CHECK-NEXT: <Name abbrevid=6 op0=8/> blob data = 'verbatim'
+ // CHECK-NEXT: <CloseName abbrevid=9 op0=11/> blob data = 'endverbatim'
+ // CHECK-NEXT: <CommentBlock NumWords=16 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=24/> blob data = 'VerbatimBlockLineComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=27/> blob data = ' The description continues.'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=13 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=5 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=39 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=19/> blob data = 'ParamCommandComment'
+ // CHECK-NEXT: <Direction abbrevid=7 op0=5/> blob data = '[out]'
+ // CHECK-NEXT: <ParamName abbrevid=8 op0=1/> blob data = 'I'
+ // CHECK-NEXT: <Explicit abbrevid=11 op0=1/>
+ // CHECK-NEXT: <CommentBlock NumWords=25 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=10 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=16/> blob data = ' is a parameter.'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=5 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=38 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=19/> blob data = 'ParamCommandComment'
+ // CHECK-NEXT: <Direction abbrevid=7 op0=4/> blob data = '[in]'
+ // CHECK-NEXT: <ParamName abbrevid=8 op0=1/> blob data = 'J'
+ // CHECK-NEXT: <CommentBlock NumWords=25 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=10 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=16/> blob data = ' is a parameter.'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=5 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <CommentBlock NumWords=27 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=19/> blob data = 'BlockCommandComment'
+ // CHECK-NEXT: <Name abbrevid=6 op0=6/> blob data = 'return'
+ // CHECK-NEXT: <CommentBlock NumWords=15 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=16/> blob data = 'ParagraphComment'
+ // CHECK-NEXT: <CommentBlock NumWords=7 BlockCodeSize=4>
+ // CHECK-NEXT: <Kind abbrevid=4 op0=11/> blob data = 'TextComment'
+ // CHECK-NEXT: <Text abbrevid=5 op0=4/> blob data = ' int'
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: </CommentBlock>
+ // CHECK-NEXT: <TypeBlock NumWords=4 BlockCodeSize=4>
+ // CHECK-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-NEXT: </TypeBlock>
+ // CHECK-NEXT: <FieldTypeBlock NumWords=6 BlockCodeSize=4>
+ // CHECK-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-NEXT: <Name abbrevid=5 op0=1/> blob data = 'I'
+ // CHECK-NEXT: </FieldTypeBlock>
+ // CHECK-NEXT: <FieldTypeBlock NumWords=6 BlockCodeSize=4>
+ // CHECK-NEXT: <Type abbrevid=4 op0=4 op1=3/> blob data = 'int'
+ // CHECK-NEXT: <Name abbrevid=5 op0=1/> blob data = 'J'
+ // CHECK-NEXT: </FieldTypeBlock>
+// CHECK-NEXT: </FunctionBlock>
Index: test/clang-doc/mapper-class.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-class.cpp
@@ -0,0 +1,18 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/289584A8E0FF4178A794622A547AA622503967A1.bc --dump | FileCheck %s
+
+class E {};
+
+// CHECK: <BLOCKINFO_BLOCK/>
+// CHECK-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-NEXT: </VersionBlock>
+// CHECK-NEXT: <RecordBlock NumWords=14 BlockCodeSize=4>
+ // CHECK-NEXT: <USR abbrevid=4 op0=40/> blob data = '289584A8E0FF4178A794622A547AA622503967A1'
+ // CHECK-NEXT: <Name abbrevid=5 op0=1/> blob data = 'E'
+ // CHECK-NEXT: <TagType abbrevid=9 op0=3/>
+// CHECK-NEXT: </RecordBlock>
Index: test/clang-doc/mapper-class-in-function.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-class-in-function.cpp
@@ -0,0 +1,36 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/B6AC4C5C9F2EA3F2B3ECE1A33D349F4EE502B24E.bc --dump | FileCheck %s --check-prefix CHECK-H
+// RUN: llvm-bcanalyzer %t/docs/bc/FE4F139BB2A9041BA63F3D1267DE32EEBEF623BE.bc --dump | FileCheck %s --check-prefix CHECK-H-I
+
+void H() {
+ class I {};
+}
+
+// CHECK-H: <BLOCKINFO_BLOCK/>
+// CHECK-H-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-H-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-H-NEXT: </VersionBlock>
+// CHECK-H-NEXT: <FunctionBlock NumWords=20 BlockCodeSize=4>
+ // CHECK-H-NEXT: <USR abbrevid=4 op0=40/> blob data = 'B6AC4C5C9F2EA3F2B3ECE1A33D349F4EE502B24E'
+ // CHECK-H-NEXT: <Name abbrevid=5 op0=1/> blob data = 'H'
+ // CHECK-H-NEXT: <TypeBlock NumWords=4 BlockCodeSize=4>
+ // CHECK-H-NEXT: <Type abbrevid=4 op0=4 op1=4/> blob data = 'void'
+ // CHECK-H-NEXT: </TypeBlock>
+// CHECK-H-NEXT: </FunctionBlock>
+
+// CHECK-H-I: <BLOCKINFO_BLOCK/>
+// CHECK-H-I-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-H-I-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-H-I-NEXT: </VersionBlock>
+// CHECK-H-I-NEXT: <RecordBlock NumWords=26 BlockCodeSize=4>
+ // CHECK-H-I-NEXT: <USR abbrevid=4 op0=40/> blob data = 'FE4F139BB2A9041BA63F3D1267DE32EEBEF623BE'
+ // CHECK-H-I-NEXT: <Name abbrevid=5 op0=1/> blob data = 'I'
+ // CHECK-H-I-NEXT: <Namespace abbrevid=6 op0=2 op1=40/> blob data = 'B6AC4C5C9F2EA3F2B3ECE1A33D349F4EE502B24E'
+ // CHECK-H-I-NEXT: <TagType abbrevid=9 op0=3/>
+// CHECK-H-I-NEXT: </RecordBlock>
+
+
Index: test/clang-doc/mapper-class-in-class.cpp
===================================================================
--- /dev/null
+++ test/clang-doc/mapper-class-in-class.cpp
@@ -0,0 +1,33 @@
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo "" > %t/compile_flags.txt
+// RUN: cp "%s" "%t/test.cpp"
+// RUN: clang-doc --dump-mapper --omit-filenames -doxygen -p %t %t/test.cpp -output=%t/docs
+// RUN: llvm-bcanalyzer %t/docs/bc/641AB4A3D36399954ACDE29C7A8833032BF40472.bc --dump | FileCheck %s --check-prefix CHECK-X-Y
+// RUN: llvm-bcanalyzer %t/docs/bc/CA7C7935730B5EACD25F080E9C83FA087CCDC75E.bc --dump | FileCheck %s --check-prefix CHECK-X
+
+class X {
+ class Y {};
+};
+
+// CHECK-X: <BLOCKINFO_BLOCK/>
+// CHECK-X-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-X-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-X-NEXT: </VersionBlock>
+// CHECK-X-NEXT: <RecordBlock NumWords=14 BlockCodeSize=4>
+ // CHECK-X-NEXT: <USR abbrevid=4 op0=40/> blob data = 'CA7C7935730B5EACD25F080E9C83FA087CCDC75E'
+ // CHECK-X-NEXT: <Name abbrevid=5 op0=1/> blob data = 'X'
+ // CHECK-X-NEXT: <TagType abbrevid=9 op0=3/>
+// CHECK-X-NEXT: </RecordBlock>
+
+
+// CHECK-X-Y: <BLOCKINFO_BLOCK/>
+// CHECK-X-Y-NEXT: <VersionBlock NumWords=1 BlockCodeSize=4>
+ // CHECK-X-Y-NEXT: <Version abbrevid=4 op0=1/>
+// CHECK-X-Y-NEXT: </VersionBlock>
+// CHECK-X-Y-NEXT: <RecordBlock NumWords=26 BlockCodeSize=4>
+ // CHECK-X-Y-NEXT: <USR abbrevid=4 op0=40/> blob data = '641AB4A3D36399954ACDE29C7A8833032BF40472'
+ // CHECK-X-Y-NEXT: <Name abbrevid=5 op0=1/> blob data = 'Y'
+ // CHECK-X-Y-NEXT: <Namespace abbrevid=6 op0=1 op1=40/> blob data = 'CA7C7935730B5EACD25F080E9C83FA087CCDC75E'
+ // CHECK-X-Y-NEXT: <TagType abbrevid=9 op0=3/>
+// CHECK-X-Y-NEXT: </RecordBlock>
Index: test/CMakeLists.txt
===================================================================
--- test/CMakeLists.txt
+++ test/CMakeLists.txt
@@ -41,6 +41,7 @@
clang-apply-replacements
clang-change-namespace
clangd
+ clang-doc
clang-include-fixer
clang-move
clang-query
Index: docs/clang-doc.rst
===================================================================
--- /dev/null
+++ docs/clang-doc.rst
@@ -0,0 +1,62 @@
+===================
+Clang-Doc
+===================
+
+.. contents::
+
+:program:`clang-doc` is a tool for generating C and C++ documenation from
+source code and comments.
+
+The tool is in a very early development stage, so you might encounter bugs and
+crashes. Submitting reports with information about how to reproduce the issue
+to `the LLVM bugtracker <https://llvm.org/bugs>`_ will definitely help the
+project. If you have any ideas or suggestions, please to put a feature request
+there.
+
+Use
+=====
+
+:program:`clang-doc` is a `LibTooling
+<http://clang.llvm.org/docs/LibTooling.html>`_-based tool, and so requires a
+compile command database for your project (for an example of how to do this
+see `How To Setup Tooling For LLVM
+<http://clang.llvm.org/docs/HowToSetupToolingForLLVM.html>`_).
+
+The tool can be used on a single file or multiple files as defined in
+the compile commands database:
+
+.. code-block:: console
+
+ $ clang-doc /path/to/file.cpp -p /path/to/compile/commands
+
+This generates an intermediate representation of the declarations and their
+associated information in the specified TUs, serialized to LLVM bitcode.
+
+As currently implemented, the tool is only able to parse TUs that can be
+stored in-memory. Future additions will extend the current framework to use
+map-reduce frameworks to allow for use with large codebases.
+
+:program:`clang-doc` offers the following options:
+
+.. code-block:: console
+
+ $ clang-doc --help
+USAGE: clang-doc [options] <source0> [... <sourceN>]
+
+OPTIONS:
+
+Generic Options:
+
+ -help - Display available options (-help-hidden for more)
+ -help-list - Display list of available options (-help-list-hidden for more)
+ -version - Display the version of this program
+
+clang-doc options:
+
+ -doxygen - Use only doxygen-style comments to generate docs.
+ -dump - Dump intermediate results to bitcode file.
+ -extra-arg=<string> - Additional argument to append to the compiler command line
+ -extra-arg-before=<string> - Additional argument to prepend to the compiler command line
+ -omit-filenames - Omit filenames in output.
+ -output=<string> - Directory for outputting generated files.
+ -p=<string> - Build path
Index: clang-doc/tool/ClangDocMain.cpp
===================================================================
--- /dev/null
+++ clang-doc/tool/ClangDocMain.cpp
@@ -0,0 +1,116 @@
+//===-- ClangDocMain.cpp - ClangDoc -----------------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This tool for generating C and C++ documenation from source code
+// and comments. Generally, it runs a LibTooling FrontendAction on source files,
+// mapping each declaration in those files to its USR and serializing relevant
+// information into LLVM bitcode. It then runs a pass over the collected
+// declaration information, reducing by USR. There is an option to dump this
+// intermediate result to bitcode. Finally, it hands the reduced information
+// off to a generator, which does the final parsing from the intermediate
+// representation to the desired output format.
+//
+//===----------------------------------------------------------------------===//
+
+#include <string>
+#include "ClangDoc.h"
+#include "clang/AST/AST.h"
+#include "clang/AST/Decl.h"
+#include "clang/ASTMatchers/ASTMatchFinder.h"
+#include "clang/ASTMatchers/ASTMatchersInternal.h"
+#include "clang/Driver/Options.h"
+#include "clang/Frontend/FrontendActions.h"
+#include "clang/Tooling/CommonOptionsParser.h"
+#include "clang/Tooling/Execution.h"
+#include "clang/Tooling/StandaloneExecution.h"
+#include "clang/Tooling/Tooling.h"
+#include "llvm/ADT/APFloat.h"
+#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/Path.h"
+#include "llvm/Support/Process.h"
+#include "llvm/Support/Signals.h"
+#include "llvm/Support/raw_ostream.h"
+
+using namespace clang::ast_matchers;
+using namespace clang::tooling;
+using namespace clang;
+
+static llvm::cl::extrahelp CommonHelp(CommonOptionsParser::HelpMessage);
+static llvm::cl::OptionCategory ClangDocCategory("clang-doc options");
+
+static llvm::cl::opt<std::string> OutDirectory(
+ "output", llvm::cl::desc("Directory for outputting generated files."),
+ llvm::cl::init("docs"), llvm::cl::cat(ClangDocCategory));
+
+static llvm::cl::opt<bool> DumpMapperResult(
+ "dump-mapper", llvm::cl::desc("Dump mapper results to bitcode file."),
+ llvm::cl::init(false), llvm::cl::cat(ClangDocCategory));
+
+static llvm::cl::opt<bool> OmitFilenames(
+ "omit-filenames", llvm::cl::desc("Omit filenames in output."),
+ llvm::cl::init(false), llvm::cl::cat(ClangDocCategory));
+
+static llvm::cl::opt<bool> DoxygenOnly(
+ "doxygen",
+ llvm::cl::desc("Use only doxygen-style comments to generate docs."),
+ llvm::cl::init(false), llvm::cl::cat(ClangDocCategory));
+
+int main(int argc, const char **argv) {
+ llvm::sys::PrintStackTraceOnErrorSignal(argv[0]);
+ std::error_code OK;
+
+ auto Exec = clang::tooling::createExecutorFromCommandLineArgs(
+ argc, argv, ClangDocCategory);
+
+ if (!Exec) {
+ llvm::errs() << toString(Exec.takeError()) << "\n";
+ return 1;
+ }
+
+ ArgumentsAdjuster ArgAdjuster;
+ if (!DoxygenOnly)
+ ArgAdjuster = combineAdjusters(
+ getInsertArgumentAdjuster("-fparse-all-comments",
+ tooling::ArgumentInsertPosition::END),
+ ArgAdjuster);
+
+ // Mapping phase
+ llvm::outs() << "Mapping decls...\n";
+ auto Err = Exec->get()->execute(
+ llvm::make_unique<doc::MapperActionFactory>(
+ Exec->get()->getExecutionContext(), OmitFilenames),
+ ArgAdjuster);
+ if (Err) llvm::errs() << toString(std::move(Err)) << "\n";
+
+ if (DumpMapperResult) {
+ Exec->get()->getToolResults()->forEachResult([&](StringRef Key,
+ StringRef Value) {
+ SmallString<128> IRRootPath;
+ llvm::sys::path::native(OutDirectory, IRRootPath);
+ llvm::sys::path::append(IRRootPath, "bc");
+ std::error_code DirectoryStatus =
+ llvm::sys::fs::create_directories(IRRootPath);
+ if (DirectoryStatus != OK) {
+ llvm::errs() << "Unable to create documentation directories.\n";
+ return;
+ }
+ llvm::sys::path::append(IRRootPath, Key + ".bc");
+ std::error_code OutErrorInfo;
+ llvm::raw_fd_ostream OS(IRRootPath, OutErrorInfo, llvm::sys::fs::F_None);
+ if (OutErrorInfo != OK) {
+ llvm::errs() << "Error opening documentation file.\n";
+ return;
+ }
+ OS << Value;
+ OS.close();
+ });
+ }
+
+ return 0;
+}
Index: clang-doc/tool/CMakeLists.txt
===================================================================
--- /dev/null
+++ clang-doc/tool/CMakeLists.txt
@@ -0,0 +1,17 @@
+include_directories(${CMAKE_CURRENT_SOURCE_DIR}/..)
+
+add_clang_executable(clang-doc
+ ClangDocMain.cpp
+ )
+
+target_link_libraries(clang-doc
+ PRIVATE
+ clangAST
+ clangASTMatchers
+ clangBasic
+ clangFrontend
+ clangDoc
+ clangTooling
+ clangToolingCore
+ )
+
\ No newline at end of file
Index: clang-doc/Serialize.h
===================================================================
--- /dev/null
+++ clang-doc/Serialize.h
@@ -0,0 +1,53 @@
+//===-- Serializer.h - ClangDoc Serializer ----------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the serializing functions fro the clang-doc tool. Given
+// a particular declaration, it collects the appropriate information and returns
+// a serialized bitcode string for the declaration.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_SERIALIZE_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_SERIALIZE_H
+
+#include "Representation.h"
+#include "clang/AST/AST.h"
+#include "clang/AST/CommentVisitor.h"
+#include <string>
+#include <vector>
+
+using namespace clang::comments;
+
+namespace clang {
+namespace doc {
+namespace serialize {
+
+std::string emitInfo(const NamespaceDecl *D, const FullComment *FC,
+ int LineNumber, StringRef File, bool OmitFilenames);
+std::string emitInfo(const RecordDecl *D, const FullComment *FC, int LineNumber,
+ StringRef File, bool OmitFilenames);
+std::string emitInfo(const EnumDecl *D, const FullComment *FC, int LineNumber,
+ StringRef File, bool OmitFilenames);
+std::string emitInfo(const FunctionDecl *D, const FullComment *FC,
+ int LineNumber, StringRef File, bool OmitFilenames);
+std::string emitInfo(const CXXMethodDecl *D, const FullComment *FC,
+ int LineNumber, StringRef File, bool OmitFilenames);
+
+// Function to hash a given USR value for storage.
+// As USRs (Unified Symbol Resolution) could be large, especially for functions
+// with long type arguments, we use 160-bits SHA1(USR) values to
+// guarantee the uniqueness of symbols while using a relatively small amount of
+// memory (vs storing USRs directly).
+std::string hashUSR(llvm::StringRef USR);
+
+} // namespace serialize
+} // namespace doc
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_SERIALIZE_H
Index: clang-doc/Serialize.cpp
===================================================================
--- /dev/null
+++ clang-doc/Serialize.cpp
@@ -0,0 +1,337 @@
+//===-- Serializer.cpp - ClangDoc Serializer --------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "Serialize.h"
+#include "BitcodeWriter.h"
+#include "clang/AST/Comment.h"
+#include "clang/Index/USRGeneration.h"
+#include "llvm/ADT/Hashing.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/Support/SHA1.h"
+
+using clang::comments::FullComment;
+
+namespace clang {
+namespace doc {
+namespace serialize {
+
+std::string hashUSR(llvm::StringRef USR) {
+ auto Hash = llvm::SHA1::hash(arrayRefFromStringRef(USR));
+ return llvm::toHex(llvm::toStringRef(Hash));
+}
+
+class ClangDocCommentVisitor
+ : public ConstCommentVisitor<ClangDocCommentVisitor> {
+ public:
+ ClangDocCommentVisitor(CommentInfo &CI) : CurrentCI(CI) {}
+
+ void parseComment(const comments::Comment *C);
+
+ void visitTextComment(const TextComment *C);
+ void visitInlineCommandComment(const InlineCommandComment *C);
+ void visitHTMLStartTagComment(const HTMLStartTagComment *C);
+ void visitHTMLEndTagComment(const HTMLEndTagComment *C);
+ void visitBlockCommandComment(const BlockCommandComment *C);
+ void visitParamCommandComment(const ParamCommandComment *C);
+ void visitTParamCommandComment(const TParamCommandComment *C);
+ void visitVerbatimBlockComment(const VerbatimBlockComment *C);
+ void visitVerbatimBlockLineComment(const VerbatimBlockLineComment *C);
+ void visitVerbatimLineComment(const VerbatimLineComment *C);
+
+ private:
+ std::string getCommandName(unsigned CommandID) const;
+ bool isWhitespaceOnly(StringRef S) const;
+
+ CommentInfo &CurrentCI;
+};
+
+void ClangDocCommentVisitor::parseComment(const comments::Comment *C) {
+ CurrentCI.Kind = C->getCommentKindName();
+ ConstCommentVisitor<ClangDocCommentVisitor>::visit(C);
+ for (comments::Comment *Child :
+ llvm::make_range(C->child_begin(), C->child_end())) {
+ CurrentCI.Children.emplace_back(llvm::make_unique<CommentInfo>());
+ ClangDocCommentVisitor Visitor(*CurrentCI.Children.back());
+ Visitor.parseComment(Child);
+ }
+}
+
+void ClangDocCommentVisitor::visitTextComment(const TextComment *C) {
+ if (!isWhitespaceOnly(C->getText())) CurrentCI.Text = C->getText();
+}
+
+void ClangDocCommentVisitor::visitInlineCommandComment(
+ const InlineCommandComment *C) {
+ CurrentCI.Name = getCommandName(C->getCommandID());
+ for (unsigned I = 0, E = C->getNumArgs(); I != E; ++I)
+ CurrentCI.Args.push_back(C->getArgText(I));
+}
+
+void ClangDocCommentVisitor::visitHTMLStartTagComment(
+ const HTMLStartTagComment *C) {
+ CurrentCI.Name = C->getTagName();
+ CurrentCI.SelfClosing = C->isSelfClosing();
+ for (unsigned I = 0, E = C->getNumAttrs(); I < E; ++I) {
+ const HTMLStartTagComment::Attribute &Attr = C->getAttr(I);
+ CurrentCI.AttrKeys.push_back(Attr.Name);
+ CurrentCI.AttrValues.push_back(Attr.Value);
+ }
+}
+
+void ClangDocCommentVisitor::visitHTMLEndTagComment(
+ const HTMLEndTagComment *C) {
+ CurrentCI.Name = C->getTagName();
+ CurrentCI.SelfClosing = true;
+}
+
+void ClangDocCommentVisitor::visitBlockCommandComment(
+ const BlockCommandComment *C) {
+ CurrentCI.Name = getCommandName(C->getCommandID());
+ for (unsigned I = 0, E = C->getNumArgs(); I < E; ++I)
+ CurrentCI.Args.push_back(C->getArgText(I));
+}
+
+void ClangDocCommentVisitor::visitParamCommandComment(
+ const ParamCommandComment *C) {
+ CurrentCI.Direction =
+ ParamCommandComment::getDirectionAsString(C->getDirection());
+ CurrentCI.Explicit = C->isDirectionExplicit();
+ if (C->hasParamName()) CurrentCI.ParamName = C->getParamNameAsWritten();
+}
+
+void ClangDocCommentVisitor::visitTParamCommandComment(
+ const TParamCommandComment *C) {
+ if (C->hasParamName()) CurrentCI.ParamName = C->getParamNameAsWritten();
+}
+
+void ClangDocCommentVisitor::visitVerbatimBlockComment(
+ const VerbatimBlockComment *C) {
+ CurrentCI.Name = getCommandName(C->getCommandID());
+ CurrentCI.CloseName = C->getCloseName();
+}
+
+void ClangDocCommentVisitor::visitVerbatimBlockLineComment(
+ const VerbatimBlockLineComment *C) {
+ if (!isWhitespaceOnly(C->getText())) CurrentCI.Text = C->getText();
+}
+
+void ClangDocCommentVisitor::visitVerbatimLineComment(
+ const VerbatimLineComment *C) {
+ if (!isWhitespaceOnly(C->getText())) CurrentCI.Text = C->getText();
+}
+
+bool ClangDocCommentVisitor::isWhitespaceOnly(llvm::StringRef S) const {
+ return std::all_of(S.begin(), S.end(), isspace);
+}
+
+std::string ClangDocCommentVisitor::getCommandName(unsigned CommandID) const {
+ const CommandInfo *Info = CommandTraits::getBuiltinCommandInfo(CommandID);
+ if (Info) return Info->Name;
+ // TODO: Add parsing for \file command.
+ return "<not a builtin command>";
+}
+
+// Serializing functions.
+
+template <typename T>
+static std::string serialize(T &I, bool OmitFilenames) {
+ SmallString<2048> Buffer;
+ llvm::BitstreamWriter Stream(Buffer);
+ ClangDocBitcodeWriter Writer(Stream, OmitFilenames);
+ Writer.emitBlock(I);
+ return Buffer.str().str();
+}
+
+static void parseFullComment(const FullComment *C, CommentInfo &CI) {
+ ClangDocCommentVisitor Visitor(CI);
+ Visitor.parseComment(C);
+}
+
+static std::string getUSRForDecl(const Decl *D) {
+ llvm::SmallString<128> USR;
+ if (index::generateUSRForDecl(D, USR)) return "";
+ return hashUSR(USR);
+}
+
+static RecordDecl *getDeclForType(const QualType &T) {
+ auto *Ty = T->getAs<RecordType>();
+ if (!Ty) return nullptr;
+ return Ty->getDecl()->getDefinition();
+}
+
+static void parseFields(RecordInfo &I, const RecordDecl *D) {
+ for (const FieldDecl *F : D->fields()) {
+ // FIXME: Set Access to the appropriate value.
+ std::string Type;
+ InfoType RefType;
+ if (const auto *T = getDeclForType(F->getTypeSourceInfo()->getType())) {
+ Type = getUSRForDecl(T);
+ if (dyn_cast<EnumDecl>(T))
+ RefType = InfoType::IT_enum;
+ else if (dyn_cast<RecordDecl>(T))
+ RefType = InfoType::IT_record;
+ else
+ RefType = InfoType::IT_default;
+ } else {
+ Type = F->getTypeSourceInfo()->getType().getAsString();
+ RefType = InfoType::IT_default;
+ }
+ I.Members.emplace_back(Type, RefType, F->getQualifiedNameAsString());
+ }
+ // TODO: Populate type comment description from info description.
+}
+
+static void parseEnumerators(EnumInfo &I, const EnumDecl *D) {
+ for (const EnumConstantDecl *E : D->enumerators())
+ I.Members.emplace_back(E->getQualifiedNameAsString(), InfoType::IT_enum);
+ // TODO: Populate member comment description from info description.
+}
+
+static void parseParameters(FunctionInfo &I, const FunctionDecl *D) {
+ for (const ParmVarDecl *P : D->parameters()) {
+ std::string Type;
+ InfoType RefType;
+ if (const auto *T = getDeclForType(P->getOriginalType())) {
+ Type = getUSRForDecl(T);
+ if (dyn_cast<EnumDecl>(T))
+ RefType = InfoType::IT_enum;
+ else if (dyn_cast<RecordDecl>(T))
+ RefType = InfoType::IT_record;
+ else
+ RefType = InfoType::IT_default;
+ } else {
+ Type = P->getOriginalType().getAsString();
+ RefType = InfoType::IT_default;
+ }
+ I.Params.emplace_back(Type, RefType, P->getQualifiedNameAsString());
+ // TODO: Populate field comment description from info description.
+ }
+}
+
+static void parseBases(RecordInfo &I, const CXXRecordDecl *D) {
+ for (const CXXBaseSpecifier &B : D->bases()) {
+ if (B.isVirtual()) continue;
+ if (const auto *P = getDeclForType(B.getType()))
+ I.Parents.emplace_back(getUSRForDecl(P), InfoType::IT_record);
+ else
+ I.Parents.emplace_back(B.getType().getAsString(), InfoType::IT_default);
+ }
+ for (const CXXBaseSpecifier &B : D->vbases()) {
+ if (const auto *P = getDeclForType(B.getType()))
+ I.VirtualParents.emplace_back(getUSRForDecl(P), InfoType::IT_record);
+ else
+ I.VirtualParents.emplace_back(B.getType().getAsString(),
+ InfoType::IT_default);
+ }
+}
+
+template <typename T>
+static void populateParentNamespaces(
+ llvm::SmallVector<Reference, 4> &Namespaces, const T *D) {
+ const auto *DC = dyn_cast<DeclContext>(D);
+ while ((DC = DC->getParent())) {
+ if (const auto *N = dyn_cast<NamespaceDecl>(DC))
+ Namespaces.emplace_back(getUSRForDecl(N), InfoType::IT_namespace);
+ else if (const auto *N = dyn_cast<RecordDecl>(DC))
+ Namespaces.emplace_back(getUSRForDecl(N), InfoType::IT_record);
+ else if (const auto *N = dyn_cast<FunctionDecl>(DC))
+ Namespaces.emplace_back(getUSRForDecl(N), InfoType::IT_function);
+ else if (const auto *N = dyn_cast<EnumDecl>(DC))
+ Namespaces.emplace_back(getUSRForDecl(N), InfoType::IT_enum);
+ }
+}
+
+template <typename T>
+static void populateInfo(Info &I, const T *D, const FullComment *C) {
+ I.USR = getUSRForDecl(D);
+ I.Name = D->getNameAsString();
+ populateParentNamespaces(I.Namespace, D);
+ if (C) {
+ I.Description.emplace_back();
+ parseFullComment(C, I.Description.back());
+ }
+}
+
+template <typename T>
+static void populateSymbolInfo(SymbolInfo &I, const T *D, const FullComment *C,
+ int LineNumber, StringRef Filename) {
+ populateInfo(I, D, C);
+ if (D->isThisDeclarationADefinition())
+ I.DefLoc.emplace(LineNumber, Filename);
+ else
+ I.Loc.emplace_back(LineNumber, Filename);
+}
+
+static void populateFunctionInfo(FunctionInfo &I, const FunctionDecl *D,
+ const FullComment *FC, int LineNumber,
+ StringRef Filename) {
+ populateSymbolInfo(I, D, FC, LineNumber, Filename);
+ if (const auto *T = getDeclForType(D->getReturnType())) {
+ I.ReturnType.Type.USR = getUSRForDecl(T);
+ if (dyn_cast<EnumDecl>(T))
+ I.ReturnType.Type.RefType = InfoType::IT_enum;
+ else if (dyn_cast<RecordDecl>(T))
+ I.ReturnType.Type.RefType = InfoType::IT_record;
+ else
+ I.ReturnType.Type.RefType = InfoType::IT_default;
+ } else {
+ I.ReturnType.Type.USR = D->getReturnType().getAsString();
+ I.ReturnType.Type.RefType = InfoType::IT_default;
+ }
+ // TODO: Populate return type comment description from info description.
+ parseParameters(I, D);
+}
+
+std::string emitInfo(const NamespaceDecl *D, const FullComment *FC,
+ int LineNumber, llvm::StringRef File, bool OmitFilenames) {
+ NamespaceInfo I;
+ populateInfo(I, D, FC);
+ return serialize(I, OmitFilenames);
+}
+
+std::string emitInfo(const RecordDecl *D, const FullComment *FC, int LineNumber,
+ llvm::StringRef File, bool OmitFilenames) {
+ RecordInfo I;
+ populateSymbolInfo(I, D, FC, LineNumber, File);
+ I.TagType = D->getTagKind();
+ parseFields(I, D);
+ if (const auto *C = dyn_cast<CXXRecordDecl>(D)) parseBases(I, C);
+ return serialize(I, OmitFilenames);
+}
+
+std::string emitInfo(const FunctionDecl *D, const FullComment *FC,
+ int LineNumber, llvm::StringRef File, bool OmitFilenames) {
+ FunctionInfo I;
+ populateFunctionInfo(I, D, FC, LineNumber, File);
+ I.Access = clang::AccessSpecifier::AS_none;
+ return serialize(I, OmitFilenames);
+}
+
+std::string emitInfo(const CXXMethodDecl *D, const FullComment *FC,
+ int LineNumber, llvm::StringRef File, bool OmitFilenames) {
+ FunctionInfo I;
+ populateFunctionInfo(I, D, FC, LineNumber, File);
+ I.IsMethod = true;
+ I.Parent = Reference{getUSRForDecl(D->getParent()), InfoType::IT_record};
+ I.Access = D->getAccess();
+ return serialize(I, OmitFilenames);
+}
+
+std::string emitInfo(const EnumDecl *D, const FullComment *FC, int LineNumber,
+ llvm::StringRef File, bool OmitFilenames) {
+ EnumInfo I;
+ populateSymbolInfo(I, D, FC, LineNumber, File);
+ I.Scoped = D->isScoped();
+ parseEnumerators(I, D);
+ return serialize(I, OmitFilenames);
+}
+
+} // namespace serialize
+} // namespace doc
+} // namespace clang
Index: clang-doc/Representation.h
===================================================================
--- /dev/null
+++ clang-doc/Representation.h
@@ -0,0 +1,152 @@
+///===-- Representation.h - ClangDoc Represenation --------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the internal representations of different declaration
+// types for the clang-doc tool.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_REPRESENTATION_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_REPRESENTATION_H
+
+#include "clang/AST/Type.h"
+#include "clang/Basic/Specifiers.h"
+#include "llvm/ADT/Optional.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringExtras.h"
+#include <string>
+
+namespace clang {
+namespace doc {
+
+struct Info;
+enum class InfoType {
+ IT_namespace,
+ IT_record,
+ IT_function,
+ IT_enum,
+ IT_default
+};
+
+// A representation of a parsed comment.
+struct CommentInfo {
+ CommentInfo() = default;
+ CommentInfo(CommentInfo &&Other) : Children(std::move(Other.Children)) {}
+ SmallString<16> Kind;
+ SmallString<64> Text;
+ SmallString<16> Name;
+ SmallString<4> Direction;
+ SmallString<16> ParamName;
+ SmallString<16> CloseName;
+ bool SelfClosing = false;
+ bool Explicit = false;
+ llvm::SmallVector<SmallString<16>, 4> AttrKeys;
+ llvm::SmallVector<SmallString<16>, 4> AttrValues;
+ llvm::SmallVector<SmallString<16>, 4> Args;
+ std::vector<std::unique_ptr<CommentInfo>> Children;
+};
+
+struct Reference {
+ Reference() = default;
+ Reference(llvm::StringRef USR, InfoType IT) : USR(USR), RefType(IT) {}
+
+ SmallString<16> USR;
+ InfoType RefType = InfoType::IT_default;
+};
+
+// TODO: Pull the CommentInfo for a type out of the info's CommentInfo.
+// A base struct for TypeInfos
+struct TypeInfo {
+ TypeInfo() = default;
+ TypeInfo(llvm::StringRef Type, InfoType IT) : Type(Type, IT) {}
+
+ Reference Type;
+ std::vector<CommentInfo> Description;
+};
+
+// Info for field types.
+struct FieldTypeInfo : public TypeInfo {
+ FieldTypeInfo() = default;
+ FieldTypeInfo(llvm::StringRef Type, InfoType IT) : TypeInfo(Type, IT) {}
+ FieldTypeInfo(llvm::StringRef Type, InfoType IT, llvm::StringRef Name)
+ : TypeInfo(Type, IT), Name(Name) {}
+
+ SmallString<16> Name;
+};
+
+// Info for member types.
+struct MemberTypeInfo : public FieldTypeInfo {
+ MemberTypeInfo() = default;
+ MemberTypeInfo(llvm::StringRef Type, InfoType IT, llvm::StringRef Name)
+ : FieldTypeInfo(Type, IT, Name) {}
+
+ AccessSpecifier Access = clang::AccessSpecifier::AS_none;
+};
+
+struct Location {
+ Location() = default;
+ Location(int LineNumber, SmallString<16> Filename)
+ : LineNumber(LineNumber), Filename(std::move(Filename)) {}
+
+ int LineNumber;
+ SmallString<32> Filename;
+};
+
+/// A base struct for Infos.
+struct Info {
+ Info() = default;
+ Info(Info &&Other) : Description(std::move(Other.Description)) {}
+ virtual ~Info() = default;
+
+ SmallString<16> USR;
+ SmallString<16> Name;
+ llvm::SmallVector<Reference, 4> Namespace;
+ std::vector<CommentInfo> Description;
+};
+
+struct NamespaceInfo : public Info {};
+
+struct SymbolInfo : public Info {
+ llvm::Optional<Location> DefLoc;
+ llvm::SmallVector<Location, 2> Loc;
+};
+
+// TODO: Expand to allow for documenting templating and default args.
+// Info for functions.
+struct FunctionInfo : public SymbolInfo {
+ bool IsMethod = false;
+ Reference Parent;
+ TypeInfo ReturnType;
+ llvm::SmallVector<FieldTypeInfo, 4> Params;
+ AccessSpecifier Access = AccessSpecifier::AS_none;
+};
+
+// TODO: Expand to allow for documenting templating, inheritance access,
+// friend classes
+// Info for types.
+struct RecordInfo : public SymbolInfo {
+ TagTypeKind TagType = TagTypeKind::TTK_Struct;
+ llvm::SmallVector<MemberTypeInfo, 4> Members;
+ llvm::SmallVector<Reference, 4> Parents;
+ llvm::SmallVector<Reference, 4> VirtualParents;
+};
+
+// TODO: Expand to allow for documenting templating.
+// Info for types.
+struct EnumInfo : public SymbolInfo {
+ bool Scoped = false;
+ llvm::SmallVector<TypeInfo, 4> Members;
+};
+
+// TODO: Add functionality to include separate markdown pages.
+
+} // namespace doc
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_REPRESENTATION_H
Index: clang-doc/Mapper.h
===================================================================
--- /dev/null
+++ clang-doc/Mapper.h
@@ -0,0 +1,58 @@
+//===-- Mapper.h - ClangDoc Mapper ------------------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the Mapper piece of the clang-doc tool. It implements
+// a RecursiveASTVisitor to look at each declaration and populate the info
+// into the internal representation. Each seen declaration is serialized to
+// to bitcode and written out to the ExecutionContext as a KV pair where the
+// key is the declaration's USR and the value is the serialized bitcode.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_MAPPER_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_MAPPER_H
+
+#include "clang/AST/RecursiveASTVisitor.h"
+#include "clang/Tooling/Execution.h"
+
+using namespace clang::comments;
+using namespace clang::tooling;
+
+namespace clang {
+namespace doc {
+
+class MapASTVisitor : public clang::RecursiveASTVisitor<MapASTVisitor> {
+ public:
+ explicit MapASTVisitor(ASTContext *Ctx, ExecutionContext *ECtx,
+ bool OmitFilenames)
+ : ECtx(ECtx), OmitFilenames(OmitFilenames) {}
+
+ bool VisitNamespaceDecl(const NamespaceDecl *D);
+ bool VisitRecordDecl(const RecordDecl *D);
+ bool VisitEnumDecl(const EnumDecl *D);
+ bool VisitCXXMethodDecl(const CXXMethodDecl *D);
+ bool VisitFunctionDecl(const FunctionDecl *D);
+
+ private:
+ template <typename T>
+ bool mapDecl(const T *D);
+
+ int getLine(const NamedDecl *D, const ASTContext &Context) const;
+ StringRef getFile(const NamedDecl *D, const ASTContext &Context) const;
+ comments::FullComment *getComment(const NamedDecl *D,
+ const ASTContext &Context) const;
+
+ ExecutionContext *ECtx;
+ bool OmitFilenames;
+};
+
+} // namespace doc
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_MAPPER_H
Index: clang-doc/Mapper.cpp
===================================================================
--- /dev/null
+++ clang-doc/Mapper.cpp
@@ -0,0 +1,81 @@
+//===-- Mapper.cpp - ClangDoc Mapper ----------------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "Mapper.h"
+#include "BitcodeWriter.h"
+#include "Serialize.h"
+#include "clang/AST/Comment.h"
+#include "clang/Index/USRGeneration.h"
+
+using clang::comments::FullComment;
+
+namespace clang {
+namespace doc {
+
+template <typename T>
+bool MapASTVisitor::mapDecl(const T *D) {
+ // If we're looking a decl not in user files, skip this decl.
+ if (D->getASTContext().getSourceManager().isInSystemHeader(D->getLocation()))
+ return true;
+
+ llvm::SmallString<128> USR;
+ // If there is an error generating a USR for the decl, skip this decl.
+ if (index::generateUSRForDecl(D, USR)) return true;
+
+ ECtx->reportResult(
+ serialize::hashUSR(USR),
+ serialize::emitInfo(D, getComment(D, D->getASTContext()),
+ getLine(D, D->getASTContext()),
+ getFile(D, D->getASTContext()), OmitFilenames));
+ return true;
+}
+
+bool MapASTVisitor::VisitNamespaceDecl(const NamespaceDecl *D) {
+ return mapDecl(D);
+}
+
+bool MapASTVisitor::VisitRecordDecl(const RecordDecl *D) { return mapDecl(D); }
+
+bool MapASTVisitor::VisitEnumDecl(const EnumDecl *D) { return mapDecl(D); }
+
+bool MapASTVisitor::VisitCXXMethodDecl(const CXXMethodDecl *D) {
+ return mapDecl(D);
+}
+
+bool MapASTVisitor::VisitFunctionDecl(const FunctionDecl *D) {
+ // Don't visit CXXMethodDecls twice
+ if (dyn_cast<CXXMethodDecl>(D)) return true;
+ return mapDecl(D);
+}
+
+comments::FullComment *MapASTVisitor::getComment(
+ const NamedDecl *D, const ASTContext &Context) const {
+ RawComment *Comment = Context.getRawCommentForDeclNoCache(D);
+ // FIXME: Move setAttached to the initial comment parsing.
+ if (Comment) {
+ Comment->setAttached();
+ return Comment->parse(Context, nullptr, D);
+ }
+ return nullptr;
+}
+
+int MapASTVisitor::getLine(const NamedDecl *D,
+ const ASTContext &Context) const {
+ return Context.getSourceManager().getPresumedLoc(D->getLocStart()).getLine();
+}
+
+llvm::StringRef MapASTVisitor::getFile(const NamedDecl *D,
+ const ASTContext &Context) const {
+ return Context.getSourceManager()
+ .getPresumedLoc(D->getLocStart())
+ .getFilename();
+}
+
+} // namespace doc
+} // namespace clang
Index: clang-doc/ClangDoc.h
===================================================================
--- /dev/null
+++ clang-doc/ClangDoc.h
@@ -0,0 +1,77 @@
+//===-- ClangDoc.h - ClangDoc -----------------------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the main entry point for the clang-doc tool. It runs
+// the clang-doc mapper on a given set of source code files using a
+// FrontendActionFactory.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_CLANGDOC_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_CLANGDOC_H
+
+#include "Mapper.h"
+#include "clang/AST/AST.h"
+#include "clang/AST/ASTConsumer.h"
+#include "clang/AST/ASTContext.h"
+#include "clang/AST/RecursiveASTVisitor.h"
+#include "clang/Frontend/ASTConsumers.h"
+#include "clang/Frontend/CompilerInstance.h"
+#include "clang/Frontend/FrontendActions.h"
+#include "clang/Tooling/Tooling.h"
+
+namespace clang {
+namespace doc {
+
+class MapperActionFactory : public tooling::FrontendActionFactory {
+ public:
+ MapperActionFactory(tooling::ExecutionContext *ECtx, bool OmitFilenames)
+ : ECtx(ECtx), OmitFilenames(OmitFilenames) {}
+
+ clang::FrontendAction *create() override {
+ class ClangDocConsumer : public clang::ASTConsumer {
+ public:
+ ClangDocConsumer(ASTContext *Ctx, ExecutionContext *ECtx,
+ bool OmitFilenames)
+ : Mapper(Ctx, ECtx, OmitFilenames) {}
+ void HandleTranslationUnit(clang::ASTContext &Context) override {
+ Mapper.TraverseDecl(Context.getTranslationUnitDecl());
+ }
+
+ private:
+ MapASTVisitor Mapper;
+ };
+
+ class ClangDocAction : public clang::ASTFrontendAction {
+ public:
+ ClangDocAction(ExecutionContext *ECtx, bool &OmitFilenames)
+ : ECtx(ECtx), OmitFilenames(OmitFilenames) {}
+
+ std::unique_ptr<clang::ASTConsumer> CreateASTConsumer(
+ clang::CompilerInstance &Compiler, llvm::StringRef InFile) override {
+ return llvm::make_unique<ClangDocConsumer>(&Compiler.getASTContext(),
+ ECtx, OmitFilenames);
+ }
+
+ private:
+ ExecutionContext *ECtx;
+ bool OmitFilenames;
+ };
+ return new ClangDocAction(ECtx, OmitFilenames);
+ }
+
+ private:
+ tooling::ExecutionContext *ECtx;
+ bool OmitFilenames;
+};
+
+} // namespace doc
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_CLANGDOC_H
Index: clang-doc/CMakeLists.txt
===================================================================
--- /dev/null
+++ clang-doc/CMakeLists.txt
@@ -0,0 +1,22 @@
+set(LLVM_LINK_COMPONENTS
+ support
+ )
+
+add_clang_library(clangDoc
+ BitcodeWriter.cpp
+ Mapper.cpp
+ Serialize.cpp
+
+ LINK_LIBS
+ clangAnalysis
+ clangAST
+ clangASTMatchers
+ clangBasic
+ clangFrontend
+ clangIndex
+ clangLex
+ clangTooling
+ clangToolingCore
+ )
+
+add_subdirectory(tool)
Index: clang-doc/BitcodeWriter.h
===================================================================
--- /dev/null
+++ clang-doc/BitcodeWriter.h
@@ -0,0 +1,258 @@
+//===-- BitcodeWriter.h - ClangDoc Bitcode Writer --------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements a writer for serializing the clang-doc internal
+// representation to LLVM bitcode. The writer takes in a stream and emits the
+// generated bitcode to that stream.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_BITCODEWRITER_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_BITCODEWRITER_H
+
+#include "Representation.h"
+#include "clang/AST/AST.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Bitcode/BitstreamWriter.h"
+#include <initializer_list>
+#include <vector>
+
+namespace clang {
+namespace doc {
+
+// Current version number of clang-doc bitcode.
+// Should be bumped when removing or changing BlockIds, RecordIds, or
+// BitCodeConstants, though they can be added without breaking it.
+static const unsigned VersionNumber = 1;
+
+struct BitCodeConstants {
+ static constexpr unsigned RecordSize = 16U;
+ static constexpr unsigned SignatureBitSize = 8U;
+ static constexpr unsigned SubblockIDSize = 4U;
+ static constexpr unsigned BoolSize = 1U;
+ static constexpr unsigned IntSize = 16U;
+ static constexpr unsigned StringLengthSize = 16U;
+ static constexpr unsigned FilenameLengthSize = 16U;
+ static constexpr unsigned LineNumberSize = 16U;
+ static constexpr unsigned ReferenceTypeSize = 8U;
+ static constexpr unsigned USRLengthSize = 16U;
+};
+
+// New Ids need to be added to both the enum here and the relevant IdNameMap in
+// the implementation file.
+enum BlockId {
+ BI_VERSION_BLOCK_ID = llvm::bitc::FIRST_APPLICATION_BLOCKID,
+ BI_NAMESPACE_BLOCK_ID,
+ BI_ENUM_BLOCK_ID,
+ BI_TYPE_BLOCK_ID,
+ BI_FIELD_TYPE_BLOCK_ID,
+ BI_MEMBER_TYPE_BLOCK_ID,
+ BI_RECORD_BLOCK_ID,
+ BI_FUNCTION_BLOCK_ID,
+ BI_COMMENT_BLOCK_ID,
+ BI_FIRST = BI_VERSION_BLOCK_ID,
+ BI_LAST = BI_COMMENT_BLOCK_ID
+};
+
+// New Ids need to be added to the enum here, and to the relevant IdNameMap and
+// initialization list in the implementation file.
+#define INFORECORDS(X) X##_USR, X##_NAME, X##_NAMESPACE
+
+enum RecordId {
+ VERSION = 1,
+ INFORECORDS(FUNCTION),
+ FUNCTION_DEFLOCATION,
+ FUNCTION_LOCATION,
+ FUNCTION_PARENT,
+ FUNCTION_ACCESS,
+ FUNCTION_IS_METHOD,
+ COMMENT_KIND,
+ COMMENT_TEXT,
+ COMMENT_NAME,
+ COMMENT_DIRECTION,
+ COMMENT_PARAMNAME,
+ COMMENT_CLOSENAME,
+ COMMENT_SELFCLOSING,
+ COMMENT_EXPLICIT,
+ COMMENT_ATTRKEY,
+ COMMENT_ATTRVAL,
+ COMMENT_ARG,
+ TYPE_REF,
+ FIELD_TYPE_REF,
+ FIELD_TYPE_NAME,
+ MEMBER_TYPE_REF,
+ MEMBER_TYPE_NAME,
+ MEMBER_TYPE_ACCESS,
+ INFORECORDS(NAMESPACE),
+ INFORECORDS(ENUM),
+ ENUM_DEFLOCATION,
+ ENUM_LOCATION,
+ ENUM_SCOPED,
+ INFORECORDS(RECORD),
+ RECORD_DEFLOCATION,
+ RECORD_LOCATION,
+ RECORD_TAG_TYPE,
+ RECORD_PARENT,
+ RECORD_VPARENT,
+ RI_FIRST = VERSION,
+ RI_LAST = RECORD_VPARENT
+};
+
+static constexpr unsigned BlockIdCount = BI_LAST - BI_FIRST + 1;
+static constexpr unsigned RecordIdCount = RI_LAST - RI_FIRST + 1;
+
+#undef INFORECORDS
+
+template <typename Info>
+struct MapFromInfoToBlockId {
+ static const BlockId ID;
+};
+
+template <>
+struct MapFromInfoToBlockId<NamespaceInfo> {
+ static const BlockId ID = BI_NAMESPACE_BLOCK_ID;
+};
+
+template <>
+struct MapFromInfoToBlockId<EnumInfo> {
+ static const BlockId ID = BI_ENUM_BLOCK_ID;
+};
+
+template <>
+struct MapFromInfoToBlockId<RecordInfo> {
+ static const BlockId ID = BI_RECORD_BLOCK_ID;
+};
+
+template <>
+struct MapFromInfoToBlockId<FunctionInfo> {
+ static const BlockId ID = BI_FUNCTION_BLOCK_ID;
+};
+
+template <>
+struct MapFromInfoToBlockId<TypeInfo> {
+ static const BlockId ID = BI_TYPE_BLOCK_ID;
+};
+
+template <>
+struct MapFromInfoToBlockId<FieldTypeInfo> {
+ static const BlockId ID = BI_FIELD_TYPE_BLOCK_ID;
+};
+
+template <>
+struct MapFromInfoToBlockId<MemberTypeInfo> {
+ static const BlockId ID = BI_MEMBER_TYPE_BLOCK_ID;
+};
+
+template <>
+struct MapFromInfoToBlockId<CommentInfo> {
+ static const BlockId ID = BI_COMMENT_BLOCK_ID;
+};
+
+class ClangDocBitcodeWriter {
+ public:
+ ClangDocBitcodeWriter(llvm::BitstreamWriter &Stream,
+ bool OmitFilenames = false)
+ : Stream(Stream), OmitFilenames(OmitFilenames) {
+ emitHeader();
+ emitBlockInfoBlock();
+ emitVersionBlock();
+ }
+
+#ifndef NDEBUG // Don't want explicit dtor unless needed.
+ ~ClangDocBitcodeWriter() {
+ // Check that the static size is large-enough.
+ assert(Record.capacity() == BitCodeConstants::RecordSize);
+ }
+#endif
+
+ template <typename T>
+ void emitBlock(const T &I);
+
+ private:
+ class AbbreviationMap {
+ llvm::DenseMap<unsigned, unsigned> Abbrevs;
+
+ public:
+ AbbreviationMap() : Abbrevs(RecordIdCount) {}
+
+ void add(RecordId RID, unsigned AbbrevID);
+ unsigned get(RecordId RID) const;
+ };
+
+ class StreamSubBlockGuard {
+ llvm::BitstreamWriter &Stream;
+
+ public:
+ StreamSubBlockGuard(llvm::BitstreamWriter &Stream_, BlockId ID)
+ : Stream(Stream_) {
+ // NOTE: SubBlockIDSize could theoretically be calculated on the fly,
+ // based on the initialization list of records in each block.
+ Stream.EnterSubblock(ID, BitCodeConstants::SubblockIDSize);
+ }
+
+ StreamSubBlockGuard() = default;
+ StreamSubBlockGuard(const StreamSubBlockGuard &) = delete;
+ StreamSubBlockGuard &operator=(const StreamSubBlockGuard &) = delete;
+
+ ~StreamSubBlockGuard() { Stream.ExitBlock(); }
+ };
+
+ // Block emission of different info types.
+ void emitBlockContent(const NamespaceInfo &I);
+ void emitBlockContent(const RecordInfo &I);
+ void emitBlockContent(const FunctionInfo &I);
+ void emitBlockContent(const EnumInfo &I);
+ void emitBlockContent(const TypeInfo &B);
+ void emitBlockContent(const FieldTypeInfo &B);
+ void emitBlockContent(const MemberTypeInfo &B);
+ void emitBlockContent(const CommentInfo &B);
+
+ // Emission of validation and overview blocks.
+ void emitHeader();
+ void emitVersionBlock();
+ void emitRecordID(RecordId ID);
+ void emitBlockID(BlockId ID);
+ void emitBlockInfoBlock();
+ void emitBlockInfo(BlockId BID, const std::initializer_list<RecordId> &RIDs);
+
+ // Emission of individual record types.
+ void emitRecord(StringRef Str, RecordId ID);
+ void emitRecord(const Location &Loc, RecordId ID);
+ void emitRecord(const Reference &Ref, RecordId ID);
+ void emitRecord(bool Value, RecordId ID);
+ void emitRecord(int Value, RecordId ID);
+ void emitRecord(unsigned Value, RecordId ID);
+ bool prepRecordData(RecordId ID, bool ShouldEmit = true);
+
+ // Emission of appropriate abbreviation type.
+ void emitAbbrev(RecordId ID, BlockId Block);
+
+ // Static size is the maximum length of the block/record names we're pushing
+ // to this + 1. Longest is currently `MemberTypeBlock` at 15 chars.
+ SmallVector<uint32_t, BitCodeConstants::RecordSize> Record;
+ llvm::BitstreamWriter &Stream;
+ bool OmitFilenames;
+ AbbreviationMap Abbrevs;
+};
+
+/// \brief Entry point for writing an individual info to bitcode.
+///
+/// \param I The info to emit to bitcode.
+template <typename T>
+void ClangDocBitcodeWriter::emitBlock(const T &I) {
+ StreamSubBlockGuard Block(Stream, MapFromInfoToBlockId<T>::ID);
+ emitBlockContent(I);
+}
+
+} // namespace doc
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_DOC_BITCODEWRITER_H
Index: clang-doc/BitcodeWriter.cpp
===================================================================
--- /dev/null
+++ clang-doc/BitcodeWriter.cpp
@@ -0,0 +1,447 @@
+//===-- BitcodeWriter.cpp - ClangDoc Bitcode Writer ------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "BitcodeWriter.h"
+#include "llvm/ADT/IndexedMap.h"
+
+namespace clang {
+namespace doc {
+
+// Since id enums are not zero-indexed, we need to transform the given id into
+// its associated index.
+struct BlockIdToIndexFunctor {
+ using argument_type = unsigned;
+ unsigned operator()(unsigned ID) const { return ID - BI_FIRST; }
+};
+
+struct RecordIdToIndexFunctor {
+ using argument_type = unsigned;
+ unsigned operator()(unsigned ID) const { return ID - RI_FIRST; }
+};
+
+using AbbrevDsc = void (*)(std::shared_ptr<llvm::BitCodeAbbrev> &Abbrev);
+
+static void AbbrevGen(std::shared_ptr<llvm::BitCodeAbbrev> &Abbrev,
+ const std::initializer_list<llvm::BitCodeAbbrevOp> Ops) {
+ for (const auto &Op : Ops) Abbrev->Add(Op);
+}
+
+static void BoolAbbrev(std::shared_ptr<llvm::BitCodeAbbrev> &Abbrev) {
+ AbbrevGen(Abbrev,
+ {// 0. Boolean
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Fixed,
+ BitCodeConstants::BoolSize)});
+}
+
+static void IntAbbrev(std::shared_ptr<llvm::BitCodeAbbrev> &Abbrev) {
+ AbbrevGen(Abbrev,
+ {// 0. Fixed-size integer
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Fixed,
+ BitCodeConstants::IntSize)});
+}
+
+static void StringAbbrev(std::shared_ptr<llvm::BitCodeAbbrev> &Abbrev) {
+ AbbrevGen(Abbrev,
+ {// 0. Fixed-size integer (length of the following string)
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Fixed,
+ BitCodeConstants::StringLengthSize),
+ // 1. The string blob
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Blob)});
+}
+
+// Assumes that the file will not have more than 65535 lines.
+static void LocationAbbrev(std::shared_ptr<llvm::BitCodeAbbrev> &Abbrev) {
+ AbbrevGen(
+ Abbrev,
+ {// 0. Fixed-size integer (line number)
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Fixed,
+ BitCodeConstants::LineNumberSize),
+ // 1. Fixed-size integer (length of the following string (filename))
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Fixed,
+ BitCodeConstants::StringLengthSize),
+ // 2. The string blob
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Blob)});
+}
+
+static void ReferenceAbbrev(std::shared_ptr<llvm::BitCodeAbbrev> &Abbrev) {
+ AbbrevGen(Abbrev,
+ {// 0. Fixed-size integer (ref type)
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Fixed,
+ BitCodeConstants::USRLengthSize),
+ // 1. Fixed-size integer (length of the following string (USR))
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Fixed,
+ BitCodeConstants::ReferenceTypeSize),
+ // 2. The string blob
+ llvm::BitCodeAbbrevOp(llvm::BitCodeAbbrevOp::Blob)});
+}
+
+struct RecordIdDsc {
+ llvm::StringRef Name;
+ AbbrevDsc Abbrev = nullptr;
+
+ RecordIdDsc() = default;
+ RecordIdDsc(llvm::StringRef Name, AbbrevDsc Abbrev)
+ : Name(Name), Abbrev(Abbrev) {}
+
+ // Is this 'description' valid?
+ operator bool() const {
+ return Abbrev != nullptr && Name.data() != nullptr && !Name.empty();
+ }
+};
+
+static const llvm::IndexedMap<llvm::StringRef, BlockIdToIndexFunctor>
+ BlockIdNameMap = []() {
+ llvm::IndexedMap<llvm::StringRef, BlockIdToIndexFunctor> BlockIdNameMap;
+ BlockIdNameMap.resize(BlockIdCount);
+
+ // There is no init-list constructor for the IndexedMap, so have to
+ // improvise
+ static constexpr std::initializer_list<
+ std::pair<BlockId, const char *const>>
+ Inits = {{BI_VERSION_BLOCK_ID, "VersionBlock"},
+ {BI_NAMESPACE_BLOCK_ID, "NamespaceBlock"},
+ {BI_ENUM_BLOCK_ID, "EnumBlock"},
+ {BI_TYPE_BLOCK_ID, "TypeBlock"},
+ {BI_FIELD_TYPE_BLOCK_ID, "FieldTypeBlock"},
+ {BI_MEMBER_TYPE_BLOCK_ID, "MemberTypeBlock"},
+ {BI_RECORD_BLOCK_ID, "RecordBlock"},
+ {BI_FUNCTION_BLOCK_ID, "FunctionBlock"},
+ {BI_COMMENT_BLOCK_ID, "CommentBlock"}};
+ static_assert(Inits.size() == BlockIdCount,
+ "unexpected count of initializers");
+ for (const auto &Init : Inits) BlockIdNameMap[Init.first] = Init.second;
+ assert(BlockIdNameMap.size() == BlockIdCount);
+ return BlockIdNameMap;
+ }();
+
+static const llvm::IndexedMap<RecordIdDsc, RecordIdToIndexFunctor>
+ RecordIdNameMap = []() {
+ llvm::IndexedMap<RecordIdDsc, RecordIdToIndexFunctor> RecordIdNameMap;
+ RecordIdNameMap.resize(RecordIdCount);
+
+ // There is no init-list constructor for the IndexedMap, so have to
+ // improvise
+ static std::initializer_list<std::pair<RecordId, RecordIdDsc>> Inits = {
+ {VERSION, {"Version", &IntAbbrev}},
+ {COMMENT_KIND, {"Kind", &StringAbbrev}},
+ {COMMENT_TEXT, {"Text", &StringAbbrev}},
+ {COMMENT_NAME, {"Name", &StringAbbrev}},
+ {COMMENT_DIRECTION, {"Direction", &StringAbbrev}},
+ {COMMENT_PARAMNAME, {"ParamName", &StringAbbrev}},
+ {COMMENT_CLOSENAME, {"CloseName", &StringAbbrev}},
+ {COMMENT_SELFCLOSING, {"SelfClosing", &BoolAbbrev}},
+ {COMMENT_EXPLICIT, {"Explicit", &BoolAbbrev}},
+ {COMMENT_ATTRKEY, {"AttrKey", &StringAbbrev}},
+ {COMMENT_ATTRVAL, {"AttrVal", &StringAbbrev}},
+ {COMMENT_ARG, {"Arg", &StringAbbrev}},
+ {TYPE_REF, {"Type", &ReferenceAbbrev}},
+ {FIELD_TYPE_REF, {"Type", &ReferenceAbbrev}},
+ {FIELD_TYPE_NAME, {"Name", &StringAbbrev}},
+ {MEMBER_TYPE_REF, {"Type", &ReferenceAbbrev}},
+ {MEMBER_TYPE_NAME, {"Name", &StringAbbrev}},
+ {MEMBER_TYPE_ACCESS, {"Access", &IntAbbrev}},
+ {NAMESPACE_USR, {"USR", &StringAbbrev}},
+ {NAMESPACE_NAME, {"Name", &StringAbbrev}},
+ {NAMESPACE_NAMESPACE, {"Namespace", &ReferenceAbbrev}},
+ {ENUM_USR, {"USR", &StringAbbrev}},
+ {ENUM_NAME, {"Name", &StringAbbrev}},
+ {ENUM_NAMESPACE, {"Namespace", &ReferenceAbbrev}},
+ {ENUM_DEFLOCATION, {"DefLocation", &LocationAbbrev}},
+ {ENUM_LOCATION, {"Location", &LocationAbbrev}},
+ {ENUM_SCOPED, {"Scoped", &BoolAbbrev}},
+ {RECORD_USR, {"USR", &StringAbbrev}},
+ {RECORD_NAME, {"Name", &StringAbbrev}},
+ {RECORD_NAMESPACE, {"Namespace", &ReferenceAbbrev}},
+ {RECORD_DEFLOCATION, {"DefLocation", &LocationAbbrev}},
+ {RECORD_LOCATION, {"Location", &LocationAbbrev}},
+ {RECORD_TAG_TYPE, {"TagType", &IntAbbrev}},
+ {RECORD_PARENT, {"Parent", &ReferenceAbbrev}},
+ {RECORD_VPARENT, {"VParent", &ReferenceAbbrev}},
+ {FUNCTION_USR, {"USR", &StringAbbrev}},
+ {FUNCTION_NAME, {"Name", &StringAbbrev}},
+ {FUNCTION_NAMESPACE, {"Namespace", &ReferenceAbbrev}},
+ {FUNCTION_DEFLOCATION, {"DefLocation", &LocationAbbrev}},
+ {FUNCTION_LOCATION, {"Location", &LocationAbbrev}},
+ {FUNCTION_PARENT, {"Parent", &ReferenceAbbrev}},
+ {FUNCTION_ACCESS, {"Access", &IntAbbrev}},
+ {FUNCTION_IS_METHOD, {"IsMethod", &BoolAbbrev}}};
+ // assert(Inits.size() == RecordIdCount);
+ for (const auto &Init : Inits) {
+ RecordIdNameMap[Init.first] = Init.second;
+ assert((Init.second.Name.size() + 1) <= BitCodeConstants::RecordSize);
+ }
+ // assert(RecordIdNameMap.size() == RecordIdCount);
+ return RecordIdNameMap;
+ }();
+
+static const std::initializer_list<
+ std::pair<BlockId, std::initializer_list<RecordId>>>
+ RecordsByBlock{
+ // Version Block
+ {BI_VERSION_BLOCK_ID, {VERSION}},
+ // Comment Block
+ {BI_COMMENT_BLOCK_ID,
+ {COMMENT_KIND, COMMENT_TEXT, COMMENT_NAME, COMMENT_DIRECTION,
+ COMMENT_PARAMNAME, COMMENT_CLOSENAME, COMMENT_SELFCLOSING,
+ COMMENT_EXPLICIT, COMMENT_ATTRKEY, COMMENT_ATTRVAL, COMMENT_ARG}},
+ // Type Block
+ {BI_TYPE_BLOCK_ID, {TYPE_REF}},
+ // FieldType Block
+ {BI_FIELD_TYPE_BLOCK_ID, {FIELD_TYPE_REF, FIELD_TYPE_NAME}},
+ // MemberType Block
+ {BI_MEMBER_TYPE_BLOCK_ID,
+ {MEMBER_TYPE_REF, MEMBER_TYPE_NAME, MEMBER_TYPE_ACCESS}},
+ // Enum Block
+ {BI_ENUM_BLOCK_ID,
+ {ENUM_USR, ENUM_NAME, ENUM_NAMESPACE, ENUM_DEFLOCATION, ENUM_LOCATION,
+ ENUM_SCOPED}},
+ // Namespace Block
+ {BI_NAMESPACE_BLOCK_ID,
+ {NAMESPACE_USR, NAMESPACE_NAME, NAMESPACE_NAMESPACE}},
+ // Record Block
+ {BI_RECORD_BLOCK_ID,
+ {RECORD_USR, RECORD_NAME, RECORD_NAMESPACE, RECORD_DEFLOCATION,
+ RECORD_LOCATION, RECORD_TAG_TYPE, RECORD_PARENT, RECORD_VPARENT}},
+ // Function Block
+ {BI_FUNCTION_BLOCK_ID,
+ {FUNCTION_USR, FUNCTION_NAME, FUNCTION_NAMESPACE, FUNCTION_DEFLOCATION,
+ FUNCTION_LOCATION, FUNCTION_PARENT, FUNCTION_ACCESS,
+ FUNCTION_IS_METHOD}}};
+
+// AbbreviationMap
+
+void ClangDocBitcodeWriter::AbbreviationMap::add(RecordId RID,
+ unsigned AbbrevID) {
+ assert(RecordIdNameMap[RID] && "Unknown RecordId.");
+ assert(Abbrevs.find(RID) == Abbrevs.end() && "Abbreviation already added.");
+ Abbrevs[RID] = AbbrevID;
+}
+
+unsigned ClangDocBitcodeWriter::AbbreviationMap::get(RecordId RID) const {
+ assert(RecordIdNameMap[RID] && "Unknown RecordId.");
+ assert(Abbrevs.find(RID) != Abbrevs.end() && "Unknown abbreviation.");
+ return Abbrevs.lookup(RID);
+}
+
+// Validation and Overview Blocks
+
+/// \brief Emits the magic number header to check that its the right format,
+/// in this case, 'DOCS'.
+void ClangDocBitcodeWriter::emitHeader() {
+ for (char C : llvm::StringRef("DOCS"))
+ Stream.Emit((unsigned)C, BitCodeConstants::SignatureBitSize);
+}
+
+void ClangDocBitcodeWriter::emitVersionBlock() {
+ StreamSubBlockGuard Block(Stream, BI_VERSION_BLOCK_ID);
+ emitRecord(VersionNumber, VERSION);
+}
+
+/// \brief Emits a block ID and the block name to the BLOCKINFO block.
+void ClangDocBitcodeWriter::emitBlockID(BlockId BID) {
+ const auto &BlockIdName = BlockIdNameMap[BID];
+ assert(BlockIdName.data() && BlockIdName.size() && "Unknown BlockId.");
+
+ Record.clear();
+ Record.push_back(BID);
+ Stream.EmitRecord(llvm::bitc::BLOCKINFO_CODE_SETBID, Record);
+ Stream.EmitRecord(llvm::bitc::BLOCKINFO_CODE_BLOCKNAME,
+ ArrayRef<unsigned char>(BlockIdNameMap[BID].bytes_begin(),
+ BlockIdNameMap[BID].bytes_end()));
+}
+
+/// \brief Emits a record name to the BLOCKINFO block.
+void ClangDocBitcodeWriter::emitRecordID(RecordId ID) {
+ assert(RecordIdNameMap[ID] && "Unknown RecordId.");
+ prepRecordData(ID);
+ Record.append(RecordIdNameMap[ID].Name.begin(),
+ RecordIdNameMap[ID].Name.end());
+ Stream.EmitRecord(llvm::bitc::BLOCKINFO_CODE_SETRECORDNAME, Record);
+}
+
+// Abbreviations
+
+void ClangDocBitcodeWriter::emitAbbrev(RecordId ID, BlockId Block) {
+ assert(RecordIdNameMap[ID] && "Unknown abbreviation.");
+ auto Abbrev = std::make_shared<llvm::BitCodeAbbrev>();
+ Abbrev->Add(llvm::BitCodeAbbrevOp(ID));
+ RecordIdNameMap[ID].Abbrev(Abbrev);
+ Abbrevs.add(ID, Stream.EmitBlockInfoAbbrev(Block, std::move(Abbrev)));
+}
+
+// Records
+
+void ClangDocBitcodeWriter::emitRecord(llvm::StringRef Str, RecordId ID) {
+ assert(RecordIdNameMap[ID] && "Unknown RecordId.");
+ assert(RecordIdNameMap[ID].Abbrev == &StringAbbrev &&
+ "Abbrev type mismatch.");
+ if (!prepRecordData(ID, !Str.empty())) return;
+ assert(Str.size() < (1U << BitCodeConstants::StringLengthSize));
+ Record.push_back(Str.size());
+ Stream.EmitRecordWithBlob(Abbrevs.get(ID), Record, Str);
+}
+
+void ClangDocBitcodeWriter::emitRecord(const Location &Loc, RecordId ID) {
+ assert(RecordIdNameMap[ID] && "Unknown RecordId.");
+ assert(RecordIdNameMap[ID].Abbrev == &LocationAbbrev &&
+ "Abbrev type mismatch.");
+ if (!prepRecordData(ID, !OmitFilenames)) return;
+ // FIXME: Assert that the line number is of the appropriate size.
+ Record.push_back(Loc.LineNumber);
+ assert(Loc.Filename.size() < (1U << BitCodeConstants::StringLengthSize));
+ Record.push_back(Loc.Filename.size());
+ Stream.EmitRecordWithBlob(Abbrevs.get(ID), Record, Loc.Filename);
+}
+
+void ClangDocBitcodeWriter::emitRecord(const Reference &Ref, RecordId ID) {
+ assert(RecordIdNameMap[ID] && "Unknown RecordId.");
+ assert(RecordIdNameMap[ID].Abbrev == &ReferenceAbbrev &&
+ "Abbrev type mismatch.");
+ if (!prepRecordData(ID, !Ref.USR.empty())) return;
+ Record.push_back((int)Ref.RefType);
+ assert(Ref.USR.size() < (1U << BitCodeConstants::USRLengthSize));
+ Record.push_back(Ref.USR.size());
+ Stream.EmitRecordWithBlob(Abbrevs.get(ID), Record, Ref.USR);
+}
+
+void ClangDocBitcodeWriter::emitRecord(bool Val, RecordId ID) {
+ assert(RecordIdNameMap[ID] && "Unknown RecordId.");
+ assert(RecordIdNameMap[ID].Abbrev == &BoolAbbrev && "Abbrev type mismatch.");
+ if (!prepRecordData(ID, Val)) return;
+ Record.push_back(Val);
+ Stream.EmitRecordWithAbbrev(Abbrevs.get(ID), Record);
+}
+
+void ClangDocBitcodeWriter::emitRecord(int Val, RecordId ID) {
+ assert(RecordIdNameMap[ID] && "Unknown RecordId.");
+ assert(RecordIdNameMap[ID].Abbrev == &IntAbbrev && "Abbrev type mismatch.");
+ if (!prepRecordData(ID, Val)) return;
+ // FIXME: Assert that the integer is of the appropriate size.
+ Record.push_back(Val);
+ Stream.EmitRecordWithAbbrev(Abbrevs.get(ID), Record);
+}
+
+void ClangDocBitcodeWriter::emitRecord(unsigned Val, RecordId ID) {
+ assert(RecordIdNameMap[ID] && "Unknown RecordId.");
+ assert(RecordIdNameMap[ID].Abbrev == &IntAbbrev && "Abbrev type mismatch.");
+ if (!prepRecordData(ID, Val)) return;
+ assert(Val < (1U << BitCodeConstants::IntSize));
+ Record.push_back(Val);
+ Stream.EmitRecordWithAbbrev(Abbrevs.get(ID), Record);
+}
+
+bool ClangDocBitcodeWriter::prepRecordData(RecordId ID, bool ShouldEmit) {
+ assert(RecordIdNameMap[ID] && "Unknown RecordId.");
+ if (!ShouldEmit) return false;
+ Record.clear();
+ Record.push_back(ID);
+ return true;
+}
+
+// BlockInfo Block
+
+void ClangDocBitcodeWriter::emitBlockInfoBlock() {
+ Stream.EnterBlockInfoBlock();
+ for (const auto &Block : RecordsByBlock) {
+ assert(Block.second.size() < (1U << BitCodeConstants::SubblockIDSize));
+ emitBlockInfo(Block.first, Block.second);
+ }
+ Stream.ExitBlock();
+}
+
+void ClangDocBitcodeWriter::emitBlockInfo(
+ BlockId BID, const std::initializer_list<RecordId> &RIDs) {
+ assert(RIDs.size() < (1U << BitCodeConstants::SubblockIDSize));
+ emitBlockID(BID);
+ for (RecordId RID : RIDs) {
+ emitRecordID(RID);
+ emitAbbrev(RID, BID);
+ }
+}
+
+// Block emission
+
+void ClangDocBitcodeWriter::emitBlockContent(const TypeInfo &T) {
+ emitRecord(T.Type, TYPE_REF);
+ for (const auto &CI : T.Description) emitBlock(CI);
+}
+
+void ClangDocBitcodeWriter::emitBlockContent(const FieldTypeInfo &T) {
+ emitRecord(T.Type, FIELD_TYPE_REF);
+ emitRecord(T.Name, FIELD_TYPE_NAME);
+ for (const auto &CI : T.Description) emitBlock(CI);
+}
+
+void ClangDocBitcodeWriter::emitBlockContent(const MemberTypeInfo &T) {
+ emitRecord(T.Type, MEMBER_TYPE_REF);
+ emitRecord(T.Name, MEMBER_TYPE_NAME);
+ emitRecord(T.Access, MEMBER_TYPE_ACCESS);
+ for (const auto &CI : T.Description) emitBlock(CI);
+}
+
+void ClangDocBitcodeWriter::emitBlockContent(const CommentInfo &I) {
+ for (const auto &L :
+ std::initializer_list<std::pair<llvm::StringRef, RecordId>>{
+ {I.Kind, COMMENT_KIND},
+ {I.Text, COMMENT_TEXT},
+ {I.Name, COMMENT_NAME},
+ {I.Direction, COMMENT_DIRECTION},
+ {I.ParamName, COMMENT_PARAMNAME},
+ {I.CloseName, COMMENT_CLOSENAME}})
+ emitRecord(L.first, L.second);
+ emitRecord(I.SelfClosing, COMMENT_SELFCLOSING);
+ emitRecord(I.Explicit, COMMENT_EXPLICIT);
+ for (const auto &A : I.AttrKeys) emitRecord(A, COMMENT_ATTRKEY);
+ for (const auto &A : I.AttrValues) emitRecord(A, COMMENT_ATTRVAL);
+ for (const auto &A : I.Args) emitRecord(A, COMMENT_ARG);
+ for (const auto &C : I.Children) emitBlock(*C);
+}
+
+#define EMITINFO(X) \
+ emitRecord(I.USR, X##_USR); \
+ emitRecord(I.Name, X##_NAME); \
+ for (const auto &N : I.Namespace) emitRecord(N, X##_NAMESPACE); \
+ for (const auto &CI : I.Description) emitBlock(CI);
+
+void ClangDocBitcodeWriter::emitBlockContent(const NamespaceInfo &I) {
+ EMITINFO(NAMESPACE)
+}
+
+void ClangDocBitcodeWriter::emitBlockContent(const EnumInfo &I) {
+ EMITINFO(ENUM)
+ if (I.DefLoc) emitRecord(I.DefLoc.getValue(), ENUM_DEFLOCATION);
+ for (const auto &L : I.Loc) emitRecord(L, ENUM_LOCATION);
+ emitRecord(I.Scoped, ENUM_SCOPED);
+ for (const auto &N : I.Members) emitBlock(N);
+}
+
+void ClangDocBitcodeWriter::emitBlockContent(const RecordInfo &I) {
+ EMITINFO(RECORD)
+ if (I.DefLoc) emitRecord(I.DefLoc.getValue(), RECORD_DEFLOCATION);
+ for (const auto &L : I.Loc) emitRecord(L, RECORD_LOCATION);
+ emitRecord(I.TagType, RECORD_TAG_TYPE);
+ for (const auto &N : I.Members) emitBlock(N);
+ for (const auto &P : I.Parents) emitRecord(P, RECORD_PARENT);
+ for (const auto &P : I.VirtualParents) emitRecord(P, RECORD_VPARENT);
+}
+
+void ClangDocBitcodeWriter::emitBlockContent(const FunctionInfo &I) {
+ EMITINFO(FUNCTION)
+ emitRecord(I.IsMethod, FUNCTION_IS_METHOD);
+ if (I.DefLoc) emitRecord(I.DefLoc.getValue(), FUNCTION_DEFLOCATION);
+ for (const auto &L : I.Loc) emitRecord(L, FUNCTION_LOCATION);
+ emitRecord(I.Parent, FUNCTION_PARENT);
+ emitBlock(I.ReturnType);
+ for (const auto &N : I.Params) emitBlock(N);
+}
+
+#undef EMITINFO
+
+} // namespace doc
+} // namespace clang
Index: CMakeLists.txt
===================================================================
--- CMakeLists.txt
+++ CMakeLists.txt
@@ -7,6 +7,7 @@
endif()
add_subdirectory(change-namespace)
+add_subdirectory(clang-doc)
add_subdirectory(clang-query)
add_subdirectory(clang-move)
add_subdirectory(clangd)
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
