[clang] e3702f6 - [clang-format] TableGen multi line string support. (#78032)
via cfe-commits
cfe-commits at lists.llvm.org
Wed Jan 17 04:20:39 PST 2024
Author: Hirofumi Nakamura
Date: 2024-01-17T21:20:35+09:00
New Revision: e3702f6225fe4438ccffcac3f612e902c7b3db22
URL: https://github.com/llvm/llvm-project/commit/e3702f6225fe4438ccffcac3f612e902c7b3db22
DIFF: https://github.com/llvm/llvm-project/commit/e3702f6225fe4438ccffcac3f612e902c7b3db22.diff
LOG: [clang-format] TableGen multi line string support. (#78032)
Support the handling of TableGen's multiline string (code) literal.
That has the form,
[{ this is the string possibly with multi line... }]
Added:
Modified:
clang/lib/Format/ContinuationIndenter.cpp
clang/lib/Format/FormatToken.h
clang/lib/Format/FormatTokenLexer.cpp
clang/lib/Format/FormatTokenLexer.h
clang/unittests/Format/TokenAnnotatorTest.cpp
Removed:
################################################################################
diff --git a/clang/lib/Format/ContinuationIndenter.cpp b/clang/lib/Format/ContinuationIndenter.cpp
index 102504182c4505..e6eaaa9ab45706 100644
--- a/clang/lib/Format/ContinuationIndenter.cpp
+++ b/clang/lib/Format/ContinuationIndenter.cpp
@@ -1591,6 +1591,9 @@ unsigned ContinuationIndenter::moveStateToNextToken(LineState &State,
State.StartOfStringLiteral = State.Column + 1;
if (Current.is(TT_CSharpStringLiteral) && State.StartOfStringLiteral == 0) {
State.StartOfStringLiteral = State.Column + 1;
+ } else if (Current.is(TT_TableGenMultiLineString) &&
+ State.StartOfStringLiteral == 0) {
+ State.StartOfStringLiteral = State.Column + 1;
} else if (Current.isStringLiteral() && State.StartOfStringLiteral == 0) {
State.StartOfStringLiteral = State.Column;
} else if (!Current.isOneOf(tok::comment, tok::identifier, tok::hash) &&
diff --git a/clang/lib/Format/FormatToken.h b/clang/lib/Format/FormatToken.h
index d5ef627f1348d3..dede89f2600150 100644
--- a/clang/lib/Format/FormatToken.h
+++ b/clang/lib/Format/FormatToken.h
@@ -148,6 +148,7 @@ namespace format {
TYPE(StructLBrace) \
TYPE(StructRBrace) \
TYPE(StructuredBindingLSquare) \
+ TYPE(TableGenMultiLineString) \
TYPE(TemplateCloser) \
TYPE(TemplateOpener) \
TYPE(TemplateString) \
diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp
index a1fd6dd6effe6c..25ac9be57c81a9 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -93,6 +93,8 @@ ArrayRef<FormatToken *> FormatTokenLexer::lex() {
// string literals are correctly identified.
handleCSharpVerbatimAndInterpolatedStrings();
}
+ if (Style.isTableGen())
+ handleTableGenMultilineString();
if (Tokens.back()->NewlinesBefore > 0 || Tokens.back()->IsMultiline)
FirstInLineIndex = Tokens.size() - 1;
} while (Tokens.back()->isNot(tok::eof));
@@ -272,6 +274,14 @@ void FormatTokenLexer::tryMergePreviousTokens() {
return;
}
}
+ // TableGen's Multi line string starts with [{
+ if (Style.isTableGen() && tryMergeTokens({tok::l_square, tok::l_brace},
+ TT_TableGenMultiLineString)) {
+ // Set again with finalizing. This must never be annotated as other types.
+ Tokens.back()->setFinalizedType(TT_TableGenMultiLineString);
+ Tokens.back()->Tok.setKind(tok::string_literal);
+ return;
+ }
}
bool FormatTokenLexer::tryMergeNSStringLiteral() {
@@ -763,6 +773,37 @@ void FormatTokenLexer::handleCSharpVerbatimAndInterpolatedStrings() {
resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset + 1)));
}
+void FormatTokenLexer::handleTableGenMultilineString() {
+ FormatToken *MultiLineString = Tokens.back();
+ if (MultiLineString->isNot(TT_TableGenMultiLineString))
+ return;
+
+ auto OpenOffset = Lex->getCurrentBufferOffset() - 2 /* "[{" */;
+ // "}]" is the end of multi line string.
+ auto CloseOffset = Lex->getBuffer().find("}]", OpenOffset);
+ if (CloseOffset == StringRef::npos)
+ return;
+ auto Text = Lex->getBuffer().substr(OpenOffset, CloseOffset + 2);
+ MultiLineString->TokenText = Text;
+ resetLexer(SourceMgr.getFileOffset(
+ Lex->getSourceLocation(Lex->getBufferLocation() - 2 + Text.size())));
+ auto FirstLineText = Text;
+ auto FirstBreak = Text.find('\n');
+ // Set ColumnWidth and LastLineColumnWidth when it has multiple lines.
+ if (FirstBreak != StringRef::npos) {
+ MultiLineString->IsMultiline = true;
+ FirstLineText = Text.substr(0, FirstBreak + 1);
+ // LastLineColumnWidth holds the width of the last line.
+ auto LastBreak = Text.rfind('\n');
+ MultiLineString->LastLineColumnWidth = encoding::columnWidthWithTabs(
+ Text.substr(LastBreak + 1), MultiLineString->OriginalColumn,
+ Style.TabWidth, Encoding);
+ }
+ // ColumnWidth holds only the width of the first line.
+ MultiLineString->ColumnWidth = encoding::columnWidthWithTabs(
+ FirstLineText, MultiLineString->OriginalColumn, Style.TabWidth, Encoding);
+}
+
void FormatTokenLexer::handleTemplateStrings() {
FormatToken *BacktickToken = Tokens.back();
diff --git a/clang/lib/Format/FormatTokenLexer.h b/clang/lib/Format/FormatTokenLexer.h
index bb6a8ab69c1be1..1dec6bbc41514c 100644
--- a/clang/lib/Format/FormatTokenLexer.h
+++ b/clang/lib/Format/FormatTokenLexer.h
@@ -95,6 +95,9 @@ class FormatTokenLexer {
void handleCSharpVerbatimAndInterpolatedStrings();
+ // Handles TableGen multiline strings. It has the form [{ ... }].
+ void handleTableGenMultilineString();
+
void tryParsePythonComment();
bool tryMerge_TMacro();
diff --git a/clang/unittests/Format/TokenAnnotatorTest.cpp b/clang/unittests/Format/TokenAnnotatorTest.cpp
index 92f57a77cdaf01..117d8fe8f7dc12 100644
--- a/clang/unittests/Format/TokenAnnotatorTest.cpp
+++ b/clang/unittests/Format/TokenAnnotatorTest.cpp
@@ -2193,6 +2193,22 @@ TEST_F(TokenAnnotatorTest, UnderstandTableGenTokens) {
ASSERT_TRUE(Keywords.isTableGenDefinition(*Tokens[0]));
ASSERT_TRUE(Tokens[0]->is(Keywords.kw_def));
ASSERT_TRUE(Tokens[1]->is(TT_StartOfName));
+
+ // Code, the multiline string token.
+ Tokens = Annotate("[{ code is multiline string }]");
+ ASSERT_EQ(Tokens.size(), 2u) << Tokens;
+ EXPECT_TOKEN(Tokens[0], tok::string_literal, TT_TableGenMultiLineString);
+ EXPECT_FALSE(Tokens[0]->IsMultiline);
+ // Case with multiple lines.
+ Tokens = Annotate("[{ It can break\n"
+ " across lines and the line breaks\n"
+ " are retained in \n"
+ " the string. }]");
+ ASSERT_EQ(Tokens.size(), 2u) << Tokens;
+ EXPECT_TOKEN(Tokens[0], tok::string_literal, TT_TableGenMultiLineString);
+ EXPECT_EQ(Tokens[0]->ColumnWidth, sizeof("[{ It can break\n") - 1);
+ EXPECT_TRUE(Tokens[0]->IsMultiline);
+ EXPECT_EQ(Tokens[0]->LastLineColumnWidth, sizeof(" the string. }]") - 1);
}
TEST_F(TokenAnnotatorTest, UnderstandConstructors) {
More information about the cfe-commits
mailing list