[clangd] Support utf-8 offsets (rather than utf-16) as a protocol extension

Summary:
Still some pieces to go here: unit tests for new SourceCode functionality and
a command-line flag to force utf-8 mode. But wanted to get early feedback.

Reviewers: hokein

Subscribers: ilya-biryukov, ioeric, MaskRay, jkorous, arphaman, kadircet, jdoerfert, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D58275

llvm-svn: 357102

2 files changed, 8 insertions, 3 deletions

diff --git a/clang-tools-extra/clangd/index/IndexAction.cpp b/clang-tools-extra/clangd/index/IndexAction.cpp
index 61db161bd5b..bda2cf44a58 100644
--- a/clang-tools-extra/clangd/index/IndexAction.cpp
+++ b/clang-tools-extra/clangd/index/IndexAction.cpp
@@ -9,7 +9,6 @@
 #include "IndexAction.h"
 #include "index/SymbolOrigin.h"
 #include "clang/Frontend/CompilerInstance.h"
-#include "clang/Index/IndexDataConsumer.h"
 #include "clang/Index/IndexingAction.h"
 #include "clang/Tooling/Tooling.h"
 
diff --git a/clang-tools-extra/clangd/index/SymbolLocation.h b/clang-tools-extra/clangd/index/SymbolLocation.h
index f1b7ffd5e0b..9b503546a9f 100644
--- a/clang-tools-extra/clangd/index/SymbolLocation.h
+++ b/clang-tools-extra/clangd/index/SymbolLocation.h
@@ -20,6 +20,13 @@ struct SymbolLocation {
   // Specify a position (Line, Column) of symbol. Using Line/Column allows us to
   // build LSP responses without reading the file content.
   //
+  // clangd uses the following definitions, which differ slightly from LSP:
+  //  - Line is the number of newline characters (\n) before the point.
+  //  - Column is (by default) the number of UTF-16 code between the last \n
+  //    (or start of file) and the point.
+  //    If the `offsetEncoding` protocol extension is used to negotiate UTF-8,
+  //    then it is instead the number of *bytes* since the last \n.
+  //
   // Position is encoded into 32 bits to save space.
   // If Line/Column overflow, the value will be their maximum value.
   struct Position {
@@ -37,8 +44,7 @@ struct SymbolLocation {
     static constexpr uint32_t MaxColumn = (1 << 12) - 1;
 
   private:
-    uint32_t Line : 20; // 0-based
-    // Using UTF-16 code units.
+    uint32_t Line : 20;   // 0-based
     uint32_t Column : 12; // 0-based
   };