[PATCH] D126651: [clang-diff] Fix getStmtValue when dealing with wide chars

[Kaining Zhong via Phabricator via cfe-commits]

PRESIDENT810 updated this revision to Diff 433375.
PRESIDENT810 added a comment.

Refactored some code and add support of U16 & U32 characters, as well as tests for them.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D126651/new/

https://reviews.llvm.org/D126651

Files:
  clang/lib/Tooling/ASTDiff/ASTDiff.cpp
  clang/test/Tooling/clang-diff-ast.cpp


Index: clang/test/Tooling/clang-diff-ast.cpp
===================================================================
--- clang/test/Tooling/clang-diff-ast.cpp
+++ clang/test/Tooling/clang-diff-ast.cpp
@@ -51,6 +51,30 @@
     return 0;
   }
 
+  const wchar_t *fooWide(int i) {
+    if (i == 0)
+      // CHECK: StringLiteral: foo(
+      return L"foo";
+    // CHECK-NOT: ImplicitCastExpr
+    return 0;
+  }
+
+  const char16_t *fooU16(int i) {
+    if (i == 0)
+      // CHECK: StringLiteral: foo(
+      return u"foo";
+    // CHECK-NOT: ImplicitCastExpr
+    return 0;
+  }
+
+  const char32_t *fooU32(int i) {
+    if (i == 0)
+      // CHECK: StringLiteral: foo(
+      return U"foo";
+    // CHECK-NOT: ImplicitCastExpr
+    return 0;
+  }
+
   // CHECK: AccessSpecDecl: public(
 public:
   int not_initialized;
Index: clang/lib/Tooling/ASTDiff/ASTDiff.cpp
===================================================================
--- clang/lib/Tooling/ASTDiff/ASTDiff.cpp
+++ clang/lib/Tooling/ASTDiff/ASTDiff.cpp
@@ -16,6 +16,7 @@
 #include "clang/Basic/SourceManager.h"
 #include "clang/Lex/Lexer.h"
 #include "llvm/ADT/PriorityQueue.h"
+#include "llvm/Support/ConvertUTF.h"
 
 #include <limits>
 #include <memory>
@@ -463,8 +464,39 @@
   }
   if (auto *D = dyn_cast<DeclRefExpr>(S))
     return getRelativeName(D->getDecl(), getEnclosingDeclContext(AST, S));
-  if (auto *String = dyn_cast<StringLiteral>(S))
+  if (auto *String = dyn_cast<StringLiteral>(S)) {
+    if (String->isWide()) {
+      unsigned int wsize = String->getByteLength() / String->getCharByteWidth();
+      const auto *temp =
+          reinterpret_cast<const wchar_t *>(String->getBytes().data());
+      std::wstring wstr(temp, wsize);
+      std::string str;
+      if (!convertWideToUTF8(wstr, str))
+        return "";
+      return str;
+    }
+    if (String->isUTF16()) {
+      unsigned int usize = String->getByteLength() / String->getCharByteWidth();
+      const auto *temp =
+          reinterpret_cast<const unsigned short *>(String->getBytes().data());
+      ArrayRef<UTF16> u16str(temp, usize);
+      std::string str;
+      if (!convertUTF16ToUTF8String(u16str, str))
+        return "";
+      return str;
+    }
+    if (String->isUTF32()) {
+      unsigned int usize = String->getByteLength() / String->getCharByteWidth();
+      const auto *temp =
+          reinterpret_cast<const unsigned int *>(String->getBytes().data());
+      ArrayRef<UTF32> u32str(temp, usize);
+      std::string str;
+      if (!convertUTF32ToUTF8String(u32str, str))
+        return "";
+      return str;
+    }
     return std::string(String->getString());
+  }
   if (auto *B = dyn_cast<CXXBoolLiteralExpr>(S))
     return B->getValue() ? "true" : "false";
   return "";


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D126651.433375.patch
Type: text/x-patch
Size: 2748 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220601/b55c0fdf/attachment-0001.bin>