release/20.x: [clang-format] Handle Java text blocks (#141334) #141433
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
|
@HazardyKnusperkeks What do you think about merging this PR to the release branch? |
|
@llvm/pr-subscribers-clang-format Author: None (llvmbot) ChangesBackport b7f5950 Requested by: @owenca Full diff: https://github.com/llvm/llvm-project/pull/141433.diff 3 Files Affected:
diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp
index 16f0a76f3a954..d8ad3a1d52115 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/clang/lib/Format/FormatTokenLexer.cpp
@@ -636,6 +636,36 @@ bool FormatTokenLexer::canPrecedeRegexLiteral(FormatToken *Prev) {
return true;
}
+void FormatTokenLexer::tryParseJavaTextBlock() {
+ if (FormatTok->TokenText != "\"\"")
+ return;
+
+ const auto *S = Lex->getBufferLocation();
+ const auto *End = Lex->getBuffer().end();
+
+ if (S == End || *S != '\"')
+ return;
+
+ ++S; // Skip the `"""` that begins a text block.
+
+ // Find the `"""` that ends the text block.
+ for (int Count = 0; Count < 3 && S < End; ++S) {
+ switch (*S) {
+ case '\\':
+ Count = -1;
+ break;
+ case '\"':
+ ++Count;
+ break;
+ default:
+ Count = 0;
+ }
+ }
+
+ // Ignore the possibly invalid 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
@@ -1326,6 +1356,8 @@ 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 61474a3f9ada8..d9a25c8ef3538 100644
--- a/clang/lib/Format/FormatTokenLexer.h
+++ b/clang/lib/Format/FormatTokenLexer.h
@@ -71,6 +71,8 @@ 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 33998bc7ff858..d0a3b4eb96d69 100644
--- a/clang/unittests/Format/FormatTestJava.cpp
+++ b/clang/unittests/Format/FormatTestJava.cpp
@@ -789,6 +789,63 @@ 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 = \"\"\"\r\n"
+ " red\n"
+ " green\n"
+ " blue\\\n"
+ " \"\"\";");
+
+ verifyFormat("String name = \"\"\"Pat Q. Smith\"\"\";");
+
+ verifyNoChange("String name = \"\"\"\n"
+ " Pat Q. Smith");
+}
+
} // namespace
} // namespace test
} // namespace format
|
HazardyKnusperkeks
approved these changes
May 26, 2025
github-project-automation
bot
moved this from Needs Triage
to Needs Merge
in LLVM Release Status
Fix llvm#61954 (cherry picked from commit b7f5950)
github-project-automation
bot
moved this from Needs Merge
to Done
in LLVM Release Status
|
@owenca (or anyone else). If you would like to add a note about this fix in the release notes (completely optional). Please reply to this comment with a one or two sentence description of the fix. When you are done, please add the release:note label to this PR. |
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.
Backport b7f5950
Requested by: @owenca