clang-format: [JS] nested and tagged template strings.

JavaScript template strings can be nested arbitrarily:

    foo = `text ${es.map(e => { return `<${e}>`; })} text`;

This change lexes nested template strings using a stack of lexer states to
correctly switch back to template string lexing on closing braces.

Also, reuse the same stack for the token-stashed logic.

Reviewers: djasper

Subscribers: cfe-commits, klimek

Differential Revision: https://reviews.llvm.org/D22431

llvm-svn: 279727

1 files changed, 19 insertions, 2 deletions

diff --git a/clang/lib/Format/FormatTokenLexer.h b/clang/lib/Format/FormatTokenLexer.h
index fa8c8882574..c47b0e725d3 100644
--- a/clang/lib/Format/FormatTokenLexer.h
+++ b/clang/lib/Format/FormatTokenLexer.h
@@ -23,9 +23,17 @@
 #include "clang/Format/Format.h"
 #include "llvm/Support/Regex.h"
 
+#include <stack>
+
 namespace clang {
 namespace format {
 
+enum LexerState {
+  NORMAL,
+  TEMPLATE_STRING,
+  TOKEN_STASHED,
+};
+
 class FormatTokenLexer {
 public:
   FormatTokenLexer(const SourceManager &SourceMgr, FileID ID,
@@ -53,7 +61,16 @@ private:
   // its text if successful.
   void tryParseJSRegexLiteral();
 
-  void tryParseTemplateString();
+  // Handles JavaScript template strings.
+  //
+  // JavaScript template strings use backticks ('`') as delimiters, and allow
+  // embedding expressions nested in ${expr-here}. Template strings can be
+  // nested recursively, i.e. expressions can contain template strings in turn.
+  //
+  // The code below parses starting from a backtick, up to a closing backtick or
+  // an opening ${. It also maintains a stack of lexing contexts to handle
+  // nested template parts by balancing curly braces.
+  void handleTemplateStrings();
 
   bool tryMerge_TMacro();
 
@@ -65,7 +82,7 @@ private:
 
   FormatToken *FormatTok;
   bool IsFirstToken;
-  bool GreaterStashed, LessStashed;
+  std::stack<LexerState> StateStack;
   unsigned Column;
   unsigned TrailingWhitespace;
   std::unique_ptr<Lexer> Lex;