Comment AST: TableGen'ize all command lists in CommentCommandTraits.cpp.

Now we have a list of all commands.  This is a good thing in itself, but it
also enables us to easily implement typo correction for command names.

With this change we have objects that contain information about each command,
so it makes sense to resolve command name just once during lexing (currently we
store command names as strings and do a linear search every time some property
value is needed).  Thus comment token and AST nodes were changed to contain a
command ID -- index into a tables of builtin and registered commands.  Unknown
commands are registered during parsing and thus are also uniformly assigned an
ID.  Using an ID instead of a StringRef is also a nice memory optimization
since ID is a small integer that fits into a common bitfield in Comment class.

This change implies that to get any information about a command (even a command
name) we need a CommandTraits object to resolve the command ID to CommandInfo*.
Currently a fresh temporary CommandTraits object is created whenever it is
needed since it does not have any state.  But with this change it has state --
new commands can be registered, so a CommandTraits object was added to
ASTContext.

Also, in libclang CXComment has to be expanded to include a CXTranslationUnit
so that all functions working on comment AST nodes can get a CommandTraits
object.  This breaks binary compatibility of CXComment APIs.

Now clang_FullComment_getAsXML(CXTranslationUnit TU, CXComment CXC) doesn't
need TU parameter anymore, so it was removed.  This is a source-incompatible
change for this C API.



git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@163540 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 39 insertions, 101 deletions

diff --git a/lib/AST/CommentCommandTraits.cpp b/lib/AST/CommentCommandTraits.cpp
index dc7a0bd175..26e2dee3a2 100644
--- a/lib/AST/CommentCommandTraits.cpp
+++ b/lib/AST/CommentCommandTraits.cpp
@@ -8,125 +8,63 @@
 //===----------------------------------------------------------------------===//
 
 #include "clang/AST/CommentCommandTraits.h"
-#include "llvm/ADT/StringSwitch.h"
+#include "llvm/ADT/STLExtras.h"
 
 namespace clang {
 namespace comments {
 
-// TODO: tablegen
+#include "clang/AST/CommentCommandInfo.inc"
 
-bool CommandTraits::isVerbatimBlockCommand(StringRef StartName,
-                                           StringRef &EndName) const {
-  const char *Result = llvm::StringSwitch<const char *>(StartName)
-    .Case("code", "endcode")
-    .Case("verbatim", "endverbatim")
-    .Case("htmlonly", "endhtmlonly")
-    .Case("latexonly", "endlatexonly")
-    .Case("xmlonly", "endxmlonly")
-    .Case("manonly", "endmanonly")
-    .Case("rtfonly", "endrtfonly")
+CommandTraits::CommandTraits(llvm::BumpPtrAllocator &Allocator) :
+    NextID(llvm::array_lengthof(Commands)), Allocator(Allocator)
+{ }
 
-    .Case("dot", "enddot")
-    .Case("msc", "endmsc")
-
-    .Case("f$", "f$") // Inline LaTeX formula
-    .Case("f[", "f]") // Displayed LaTeX formula
-    .Case("f{", "f}") // LaTeX environment
-
-    .Default(NULL);
-
-  if (Result) {
-    EndName = Result;
-    return true;
-  }
-
-  for (VerbatimBlockCommandVector::const_iterator
-           I = VerbatimBlockCommands.begin(),
-           E = VerbatimBlockCommands.end();
-       I != E; ++I)
-    if (I->StartName == StartName) {
-      EndName = I->EndName;
-      return true;
-    }
-
-  return false;
+const CommandInfo *CommandTraits::getCommandInfoOrNULL(StringRef Name) const {
+  if (const CommandInfo *Info = getBuiltinCommandInfo(Name))
+    return Info;
+  return getRegisteredCommandInfo(Name);
 }
 
-bool CommandTraits::isVerbatimLineCommand(StringRef Name) const {
-  bool Result = isDeclarationCommand(Name) || llvm::StringSwitch<bool>(Name)
-  .Case("defgroup", true)
-  .Case("ingroup", true)
-  .Case("addtogroup", true)
-  .Case("weakgroup", true)
-  .Case("name", true)
-
-  .Case("section", true)
-  .Case("subsection", true)
-  .Case("subsubsection", true)
-  .Case("paragraph", true)
-
-  .Case("mainpage", true)
-  .Case("subpage", true)
-  .Case("ref", true)
+const CommandInfo *CommandTraits::getCommandInfo(unsigned CommandID) const {
+  if (const CommandInfo *Info = getBuiltinCommandInfo(CommandID))
+    return Info;
+  return getRegisteredCommandInfo(CommandID);
+}
 
-  .Default(false);
+const CommandInfo *CommandTraits::registerUnknownCommand(StringRef CommandName) {
+  char *Name = Allocator.Allocate<char>(CommandName.size());
+  memcpy(Name, CommandName.data(), CommandName.size());
+  Name[CommandName.size() + 1] = '\0';
 
-  if (Result)
-    return true;
+  // Value-initialize (=zero-initialize in this case) a new CommandInfo.
+  CommandInfo *Info = new (Allocator) CommandInfo();
+  Info->Name = Name;
+  Info->ID = NextID++;
 
-  for (VerbatimLineCommandVector::const_iterator
-           I = VerbatimLineCommands.begin(),
-           E = VerbatimLineCommands.end();
-       I != E; ++I)
-    if (I->Name == Name)
-      return true;
+  RegisteredCommands.push_back(Info);
 
-  return false;
+  return Info;
 }
 
-bool CommandTraits::isDeclarationCommand(StringRef Name) const {
-  return llvm::StringSwitch<bool>(Name)
-      // Doxygen commands.
-      .Case("fn", true)
-      .Case("var", true)
-      .Case("property", true)
-      .Case("typedef", true)
-
-      .Case("overload", true)
-
-      // HeaderDoc commands.
-      .Case("class", true)
-      .Case("interface", true)
-      .Case("protocol", true)
-      .Case("category", true)
-      .Case("template", true)
-      .Case("function", true)
-      .Case("method", true)
-      .Case("callback", true)
-      .Case("var", true)
-      .Case("const", true)
-      .Case("constant", true)
-      .Case("property", true)
-      .Case("struct", true)
-      .Case("union", true)
-      .Case("typedef", true)
-      .Case("enum", true)
-
-      .Default(false);
+const CommandInfo *CommandTraits::getBuiltinCommandInfo(
+                                                  unsigned CommandID) {
+  if (CommandID < llvm::array_lengthof(Commands))
+    return &Commands[CommandID];
+  return NULL;
 }
 
-void CommandTraits::addVerbatimBlockCommand(StringRef StartName,
-                                            StringRef EndName) {
-  VerbatimBlockCommand VBC;
-  VBC.StartName = StartName;
-  VBC.EndName = EndName;
-  VerbatimBlockCommands.push_back(VBC);
+const CommandInfo *CommandTraits::getRegisteredCommandInfo(
+                                                  StringRef Name) const {
+  for (unsigned i = 0, e = RegisteredCommands.size(); i != e; ++i) {
+    if (RegisteredCommands[i]->Name == Name)
+      return RegisteredCommands[i];
+  }
+  return NULL;
 }
 
-void CommandTraits::addVerbatimLineCommand(StringRef Name) {
-  VerbatimLineCommand VLC;
-  VLC.Name = Name;
-  VerbatimLineCommands.push_back(VLC);
+const CommandInfo *CommandTraits::getRegisteredCommandInfo(
+                                                  unsigned CommandID) const {
+  return RegisteredCommands[CommandID - llvm::array_lengthof(Commands)];
 }
 
 } // end namespace comments