mprobst updated this revision to Diff 64803.
mprobst added a comment.
- Use a stack to parse nested template strings.
- move docs
https://reviews.llvm.org/D22431
Files:
lib/Format/FormatTokenLexer.cpp
lib/Format/FormatTokenLexer.h
lib/Format/TokenAnnotator.cpp
unittests/Format/FormatTestJS.cpp
Index: unittests/Format/FormatTestJS.cpp
===================================================================
--- unittests/Format/FormatTestJS.cpp
+++ unittests/Format/FormatTestJS.cpp
@@ -1122,7 +1122,7 @@
TEST_F(FormatTestJS, TemplateStrings) {
// Keeps any whitespace/indentation within the template string.
verifyFormat("var x = `hello\n"
- " ${ name }\n"
+ " ${name}\n"
" !`;",
"var x = `hello\n"
" ${ name }\n"
@@ -1208,6 +1208,16 @@
"var y;");
}
+TEST_F(FormatTestJS, NestedTemplateStrings) {
+ verifyFormat(
+ "var x = `<ul>${xs.map(x => `<li>${x}</li>`).join('\\n')}</ul>`;");
+ verifyFormat("var x = `he${({text: 'll'}.text)}o`;");
+}
+
+TEST_F(FormatTestJS, TaggedTemplateStrings) {
+ verifyFormat("var x = html`<ul>`;");
+}
+
TEST_F(FormatTestJS, CastSyntax) {
verifyFormat("var x = <type>foo;");
verifyFormat("var x = foo as type;");
Index: lib/Format/TokenAnnotator.cpp
===================================================================
--- lib/Format/TokenAnnotator.cpp
+++ lib/Format/TokenAnnotator.cpp
@@ -858,7 +858,7 @@
if (!CurrentToken->isOneOf(TT_LambdaLSquare, TT_ForEachMacro,
TT_FunctionLBrace, TT_ImplicitStringLiteral,
TT_InlineASMBrace, TT_JsFatArrow, TT_LambdaArrow,
- TT_RegexLiteral))
+ TT_RegexLiteral, TT_TemplateString))
CurrentToken->Type = TT_Unknown;
CurrentToken->Role.reset();
CurrentToken->MatchingParen = nullptr;
@@ -1816,6 +1816,9 @@
return 100;
if (Left.is(TT_JsTypeColon))
return 35;
+ if ((Left.is(TT_TemplateString) && Left.TokenText.endswith("${")) ||
+ (Right.is(TT_TemplateString) && Right.TokenText.startswith("}")))
+ return 100;
}
if (Left.is(tok::comma) || (Right.is(tok::identifier) && Right.Next &&
@@ -2113,6 +2116,11 @@
} else if (Style.Language == FormatStyle::LK_JavaScript) {
if (Left.is(TT_JsFatArrow))
return true;
+ if ((Left.is(TT_TemplateString) && Left.TokenText.endswith("${")) ||
+ (Right.is(TT_TemplateString) && Right.TokenText.startswith("}")))
+ return false;
+ if (Left.is(tok::identifier) && Right.is(TT_TemplateString))
+ return false;
if (Right.is(tok::star) &&
Left.isOneOf(Keywords.kw_function, Keywords.kw_yield))
return false;
Index: lib/Format/FormatTokenLexer.h
===================================================================
--- lib/Format/FormatTokenLexer.h
+++ lib/Format/FormatTokenLexer.h
@@ -23,9 +23,16 @@
#include "clang/Format/Format.h"
#include "llvm/Support/Regex.h"
+#include <stack>
+
namespace clang {
namespace format {
+enum LexerState {
+ NORMAL,
+ TEMPLATE_STRING,
+};
+
class FormatTokenLexer {
public:
FormatTokenLexer(const SourceManager &SourceMgr, FileID ID,
@@ -53,7 +60,16 @@
// 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 turns.
+ //
+ // 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();
@@ -66,6 +82,7 @@
FormatToken *FormatTok;
bool IsFirstToken;
bool GreaterStashed, LessStashed;
+ std::stack<LexerState> StateStack;
unsigned Column;
unsigned TrailingWhitespace;
std::unique_ptr<Lexer> Lex;
Index: lib/Format/FormatTokenLexer.cpp
===================================================================
--- lib/Format/FormatTokenLexer.cpp
+++ lib/Format/FormatTokenLexer.cpp
@@ -27,8 +27,8 @@
const FormatStyle &Style,
encoding::Encoding Encoding)
: FormatTok(nullptr), IsFirstToken(true), GreaterStashed(false),
- LessStashed(false), Column(0), TrailingWhitespace(0),
- SourceMgr(SourceMgr), ID(ID), Style(Style),
+ LessStashed(false), StateStack({LexerState::NORMAL}), Column(0),
+ TrailingWhitespace(0), SourceMgr(SourceMgr), ID(ID), Style(Style),
IdentTable(getFormattingLangOpts(Style)), Keywords(IdentTable),
Encoding(Encoding), FirstInLineIndex(0), FormattingDisabled(false),
MacroBlockBeginRegex(Style.MacroBlockBegin),
@@ -49,7 +49,7 @@
Tokens.push_back(getNextToken());
if (Style.Language == FormatStyle::LK_JavaScript) {
tryParseJSRegexLiteral();
- tryParseTemplateString();
+ handleTemplateStrings();
}
tryMergePreviousTokens();
if (Tokens.back()->NewlinesBefore > 0 || Tokens.back()->IsMultiline)
@@ -228,17 +228,42 @@
resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset)));
}
-void FormatTokenLexer::tryParseTemplateString() {
+void FormatTokenLexer::handleTemplateStrings() {
FormatToken *BacktickToken = Tokens.back();
- if (!BacktickToken->is(tok::unknown) || BacktickToken->TokenText != "`")
+
+ if (BacktickToken->is(tok::l_brace)) {
+ StateStack.push(LexerState::NORMAL);
return;
+ }
+ if (BacktickToken->is(tok::r_brace)) {
+ StateStack.pop();
+ if (StateStack.top() != LexerState::TEMPLATE_STRING)
+ return;
+ // If back in TEMPLATE_STRING, fallthrough and continue parsing the
+ } else if (BacktickToken->is(tok::unknown) &&
+ BacktickToken->TokenText == "`") {
+ StateStack.push(LexerState::TEMPLATE_STRING);
+ } else {
+ return; // Not actually a template
+ }
// 'Manually' lex ahead in the current file buffer.
const char *Offset = Lex->getBufferLocation();
const char *TmplBegin = Offset - BacktickToken->TokenText.size(); // at "`"
- for (; Offset != Lex->getBuffer().end() && *Offset != '`'; ++Offset) {
+ for (; Offset != Lex->getBuffer().end(); ++Offset) {
+ if (*Offset == '`') {
+ StateStack.pop();
+ break;
+ }
if (*Offset == '\\')
++Offset; // Skip the escaped character.
+ if (Offset + 1 < Lex->getBuffer().end() && *Offset == '$' &&
+ Offset[1] == '{') {
+ // '${' introduces an expression interpolation in the template string.
+ StateStack.push(LexerState::NORMAL);
+ ++Offset;
+ break;
+ }
}
StringRef LiteralText(TmplBegin, Offset - TmplBegin + 1);
@@ -262,7 +287,10 @@
Style.TabWidth, Encoding);
}
- resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset + 1)));
+ SourceLocation loc = Offset < Lex->getBuffer().end()
+ ? Lex->getSourceLocation(Offset + 1)
+ : SourceMgr.getLocForEndOfFile(ID);
+ resetLexer(SourceMgr.getFileOffset(loc));
}
bool FormatTokenLexer::tryMerge_TMacro() {
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
