[clang-format] Handle Java text blocks #141334
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-clang-format Author: Owen Pan (owenca) ChangesFix #61954 Full diff: https://github.com/llvm/llvm-project/pull/141334.diff 3 Files Affected:
diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp
index 864486a9b878d..31c3613c8b083 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -694,6 +694,49 @@ bool FormatTokenLexer::canPrecedeRegexLiteral(FormatToken *Prev) {
return true;
}
+void FormatTokenLexer::tryParseJavaTextBlock() {
+ if (FormatTok->TokenText != "\"\"")
+ return;
+
+ const auto *Str = Lex->getBufferLocation();
+ const auto *End = Lex->getBuffer().end();
+
+ if (Str == End || *Str != '\"')
+ return;
+
+ // Skip the `"""` that begins a text block.
+ const auto *S = Str + 1;
+
+ // From docs.oracle.com/en/java/javase/15/text-blocks/#text-block-syntax:
+ // A text block begins with three double-quote characters followed by a line
+ // terminator.
+ while (S < End && *S != '\n') {
+ if (!isblank(*S))
+ return;
+ ++S;
+ }
+
+ // Find the `"""` that ends the text block.
+ for (int Count = 0; Count < 3; ++S) {
+ if (S == End)
+ return;
+
+ switch (*S) {
+ case '\\':
+ Count = -1;
+ break;
+ case '\"':
+ ++Count;
+ break;
+ default:
+ Count = 0;
+ }
+ }
+
+ // Skip the text block.
+ resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(S)));
+}
+
// Tries to parse a JavaScript Regex literal starting at the current token,
// if that begins with a slash and is in a location where JavaScript allows
// regex literals. Changes the current token to a regex literal and updates
@@ -1374,6 +1417,8 @@ FormatToken *FormatTokenLexer::getNextToken() {
FormatTok->TokenText = FormatTok->TokenText.substr(0, 1);
++Column;
StateStack.push(LexerState::TOKEN_STASHED);
+ } else if (Style.isJava() && FormatTok->is(tok::string_literal)) {
+ tryParseJavaTextBlock();
}
if (Style.isVerilog() && Tokens.size() > 0 &&
diff --git a/clang/lib/Format/FormatTokenLexer.h b/clang/lib/Format/FormatTokenLexer.h
index 105847b126e20..026383db1fe6c 100644
--- a/clang/lib/Format/FormatTokenLexer.h
+++ b/clang/lib/Format/FormatTokenLexer.h
@@ -72,6 +72,8 @@ class FormatTokenLexer {
bool canPrecedeRegexLiteral(FormatToken *Prev);
+ void tryParseJavaTextBlock();
+
// Tries to parse a JavaScript Regex literal starting at the current token,
// if that begins with a slash and is in a location where JavaScript allows
// regex literals. Changes the current token to a regex literal and updates
diff --git a/clang/unittests/Format/FormatTestJava.cpp b/clang/unittests/Format/FormatTestJava.cpp
index e01c1d6d7e684..35ee257d015d3 100644
--- a/clang/unittests/Format/FormatTestJava.cpp
+++ b/clang/unittests/Format/FormatTestJava.cpp
@@ -791,6 +791,58 @@ TEST_F(FormatTestJava, AlignCaseArrows) {
Style);
}
+TEST_F(FormatTestJava, TextBlock) {
+ verifyNoChange("String myStr = \"\"\"\n"
+ "hello\n"
+ "there\n"
+ "\"\"\";");
+
+ verifyNoChange("String tb = \"\"\"\n"
+ " the new\"\"\";");
+
+ verifyNoChange("System.out.println(\"\"\"\n"
+ " This is the first line\n"
+ " This is the second line\n"
+ " \"\"\");");
+
+ verifyNoChange("void writeHTML() {\n"
+ " String html = \"\"\" \n"
+ " <html>\n"
+ " <p>Hello World.</p>\n"
+ " </html>\n"
+ "\"\"\";\n"
+ " writeOutput(html);\n"
+ "}");
+
+ verifyNoChange("String colors = \"\"\"\t\n"
+ " red\n"
+ " green\n"
+ " blue\"\"\".indent(4);");
+
+ verifyNoChange("String code = \"\"\"\n"
+ " String source = \\\"\"\"\n"
+ " String message = \"Hello, World!\";\n"
+ " System.out.println(message);\n"
+ " \\\"\"\";\n"
+ " \"\"\";");
+
+ verifyNoChange(
+ "class Outer {\n"
+ " void printPoetry() {\n"
+ " String lilacs = \"\"\"\n"
+ "Passing the apple-tree blows of white and pink in the orchards\n"
+ "\"\"\";\n"
+ " System.out.println(lilacs);\n"
+ " }\n"
+ "}");
+
+ verifyNoChange("String name = \"\"\"\n"
+ " red\n"
+ " green\n"
+ " blue\\\n"
+ " \"\"\";");
+}
+
} // namespace
} // namespace test
} // namespace format
|
HazardyKnusperkeks
approved these changes
May 24, 2025
github-project-automation
bot
moved this from Needs Triage
to Needs Merge
in LLVM Release Status
mydeveloperday
approved these changes
May 24, 2025
HazardyKnusperkeks
approved these changes
May 25, 2025
github-project-automation
bot
moved this from Needs Backport PR
to Needs Merge
in LLVM Release Status
github-project-automation
bot
moved this from Needs Merge
to Done
in LLVM Release Status
|
/cherry-pick b7f5950 |
|
/pull-request #141433 |
swift-ci
pushed a commit
to swiftlang/llvm-project
that referenced
this pull request
May 27, 2025
Fix llvm#61954 (cherry picked from commit b7f5950)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fix #61954