[clang] [clang][ASTMatcher] Add `matches` for `StringLiteral` which matches literals on given `RegExp` (PR #102152)

[via cfe-commits]

https://github.com/Gitspike updated https://github.com/llvm/llvm-project/pull/102152

>From c74cea916b5efe739de8a4dc6f63d583f5a46da3 Mon Sep 17 00:00:00 2001
From: hehouhua <hehouhua at feysh.com>
Date: Wed, 7 Aug 2024 11:55:30 +0800
Subject: [PATCH] [clang][ASTMatcher] Add matches for StringLiteral which
 matches literals on given RegExp

Add Matcher matchesString.
---
 clang/docs/LibASTMatchersReference.html       | 14 +++++++++++
 clang/docs/ReleaseNotes.rst                   |  2 ++
 clang/include/clang/ASTMatchers/ASTMatchers.h | 24 +++++++++++++++++++
 clang/lib/ASTMatchers/Dynamic/Registry.cpp    |  1 +
 .../ASTMatchers/ASTMatchersNarrowingTest.cpp  |  6 +++++
 5 files changed, 47 insertions(+)

diff --git a/clang/docs/LibASTMatchersReference.html b/clang/docs/LibASTMatchersReference.html
index a16b9c44ef0eab..77b789b1ec4b94 100644
--- a/clang/docs/LibASTMatchersReference.html
+++ b/clang/docs/LibASTMatchersReference.html
@@ -5582,6 +5582,20 @@ <h2 id="narrowing-matchers">Narrowing Matchers</h2>
 </pre></td></tr>
 
 
+<tr><td>Matcher<<a href="https://clang.llvm.org/doxygen/classclang_1_1StringLiteral.html">StringLiteral</a>></td><td class="name" onclick="toggle('matchesString0')"><a name="matchesString0A">matchesString</a></td><td>StringRef RegExp, Regex::RegexFlags Flags = NoFlags</td></tr>
+<tr><td colspan="4" class="doc" id="matchesString0"><pre>Matches string literals that contain a substring matched by the given RegExp
+
+Example matches "foo" and "foobar" but not "bar"
+  (matcher = stringLiteral(matchesString("foo.*")))
+  const char* a = "foo";
+  const char* b = "foobar";
+  const char* c = "bar";
+
+Usable as: Matcher<StringLiteral>
+</pre></td></tr>
+
+
+
 <tr><td>Matcher<<a href="https://clang.llvm.org/doxygen/classclang_1_1StringLiteral.html">StringLiteral</a>></td><td class="name" onclick="toggle('hasSize1')"><a name="hasSize1Anchor">hasSize</a></td><td>unsigned N</td></tr>
 <tr><td colspan="4" class="doc" id="hasSize1"><pre>Matches nodes that have the specified size.
 
diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index 54decb5dbf230d..353e1de6de3648 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -284,6 +284,8 @@ AST Matchers
 - Fixed an issue with the `hasName` and `hasAnyName` matcher when matching
   inline namespaces with an enclosing namespace of the same name.
 
+Add `matchesString` for `StringLiteral` which matches literals on given `RegExp`.
+
 clang-format
 ------------
 
diff --git a/clang/include/clang/ASTMatchers/ASTMatchers.h b/clang/include/clang/ASTMatchers/ASTMatchers.h
index ca44c3ee085654..bff415294c4561 100644
--- a/clang/include/clang/ASTMatchers/ASTMatchers.h
+++ b/clang/include/clang/ASTMatchers/ASTMatchers.h
@@ -3116,6 +3116,30 @@ AST_MATCHER_REGEX(NamedDecl, matchesName, RegExp) {
   return RegExp->match(FullNameString);
 }
 
+/// Matches string literals that contain a substring matched by the given RegExp.
+///
+/// Example matches "foo" and "foobar" but not "bar"
+///   (matcher = stringLiteral(matchesString("foo.*")))
+/// \code
+///   const char* a = "foo";
+///   const char* b = "foobar";
+///   const char* c = "bar";
+/// \endcode
+///
+/// Usable as: Matcher<StringLiteral>
+AST_MATCHER_REGEX(StringLiteral, matchesString, RegExp) {
+  constexpr unsigned StringLength = 64;
+  SmallString<StringLength> Str;
+  llvm::raw_svector_ostream OS(Str);
+  Node.outputString(OS);
+  StringRef OSRef = OS.str();
+  if (OSRef.size() < 2U) {
+    return false;
+  }
+  OSRef = OSRef.substr(1, OSRef.size() - 2);
+  return RegExp->match(OSRef);
+}
+
 /// Matches overloaded operator names.
 ///
 /// Matches overloaded operator names specified in strings without the
diff --git a/clang/lib/ASTMatchers/Dynamic/Registry.cpp b/clang/lib/ASTMatchers/Dynamic/Registry.cpp
index 2c75e6beb74301..a3a2515d86be70 100644
--- a/clang/lib/ASTMatchers/Dynamic/Registry.cpp
+++ b/clang/lib/ASTMatchers/Dynamic/Registry.cpp
@@ -125,6 +125,7 @@ RegistryMaps::RegistryMaps() {
   REGISTER_MATCHER_OVERLOAD(equals);
 
   REGISTER_REGEX_MATCHER(isExpansionInFileMatching);
+  REGISTER_REGEX_MATCHER(matchesString);
   REGISTER_REGEX_MATCHER(matchesName);
   REGISTER_REGEX_MATCHER(matchesSelector);
 
diff --git a/clang/unittests/ASTMatchers/ASTMatchersNarrowingTest.cpp b/clang/unittests/ASTMatchers/ASTMatchersNarrowingTest.cpp
index 611e1f9ba5327c..25106d38826a8d 100644
--- a/clang/unittests/ASTMatchers/ASTMatchersNarrowingTest.cpp
+++ b/clang/unittests/ASTMatchers/ASTMatchersNarrowingTest.cpp
@@ -2503,6 +2503,12 @@ TEST_P(ASTMatchersTest, IsDelegatingConstructor) {
       cxxConstructorDecl(isDelegatingConstructor(), parameterCountIs(1))));
 }
 
+TEST_P(ASTMatchersTest, matchesString) {
+  StatementMatcher Literal = stringLiteral(matchesString("foo.*"));
+  EXPECT_TRUE(matches("const char* a = \"foo\";", Literal));
+  EXPECT_TRUE(matches("const char* b = \"foobar\";", Literal));
+}
+
 TEST_P(ASTMatchersTest, HasSize) {
   StatementMatcher Literal = stringLiteral(hasSize(4));
   EXPECT_TRUE(matches("const char *s = \"abcd\";", Literal));