[YAML] Add support for non-printable characters

LLVM IR function names which disable mangling start with '\01'
(https://www.llvm.org/docs/LangRef.html#identifiers).

When an identifier like "\01@abc@" gets dumped to MIR, it is quoted, but
only with single quotes.

http://www.yaml.org/spec/1.2/spec.html#id2770814:

"The allowed character range explicitly excludes the C0 control block
allowed), the surrogate block #xD800-#xDFFF, #xFFFE, and #xFFFF."

http://www.yaml.org/spec/1.2/spec.html#id2776092:

"All non-printable characters must be escaped.
[...]
Note that escape sequences are only interpreted in double-quoted scalars."

This patch adds support for printing escaped non-printable characters
between double quotes if needed.

Should also fix PR31743.

Differential Revision: https://reviews.llvm.org/D41290

llvm-svn: 320996

1 files changed, 90 insertions, 4 deletions

diff --git a/llvm/unittests/Support/YAMLIOTest.cpp b/llvm/unittests/Support/YAMLIOTest.cpp
index 120773a0c8d..9caff85a596 100644
--- a/llvm/unittests/Support/YAMLIOTest.cpp
+++ b/llvm/unittests/Support/YAMLIOTest.cpp
@@ -860,7 +860,7 @@ namespace yaml {
           return "malformed by";
       }
     }
-    static bool mustQuote(StringRef) { return true; }
+    static QuotingType mustQuote(StringRef) { return QuotingType::Single; }
   };
 }
 }
@@ -1064,7 +1064,7 @@ namespace yaml {
       return StringRef();
     }
 
-    static bool mustQuote(StringRef) { return false; }
+    static QuotingType mustQuote(StringRef) { return QuotingType::None; }
   };
 
   template <> struct ScalarTraits<MyString> {
@@ -1075,7 +1075,9 @@ namespace yaml {
     static StringRef input(StringRef S, void *Ctx, MyString &V) {
       return Impl::input(S, Ctx, V.value);
     }
-    static bool mustQuote(StringRef S) { return Impl::mustQuote(S); }
+    static QuotingType mustQuote(StringRef S) {
+      return Impl::mustQuote(S);
+    }
   };
 }
 }
@@ -2232,7 +2234,7 @@ struct ScalarTraits<FlowSeq> {
     return "";
   }
 
-  static bool mustQuote(StringRef S) { return false; }
+  static QuotingType mustQuote(StringRef S) { return QuotingType::None; }
 };
 }
 }
@@ -2455,3 +2457,87 @@ TEST(YAMLIO, InvalidInput) {
   yin >> Data;
   EXPECT_TRUE((bool)yin.error());
 }
+
+TEST(YAMLIO, TestEscapedSingleQuote) {
+  std::string Id = "@abc@";
+
+  std::string out;
+  llvm::raw_string_ostream ostr(out);
+  Output xout(ostr, nullptr, 0);
+
+  llvm::yaml::EmptyContext Ctx;
+  yamlize(xout, Id, true, Ctx);
+
+  ostr.flush();
+  EXPECT_EQ("'@abc@'", out);
+}
+
+TEST(YAMLIO, TestEscapedNoQuote) {
+  std::string Id = "abc/";
+
+  std::string out;
+  llvm::raw_string_ostream ostr(out);
+  Output xout(ostr, nullptr, 0);
+
+  llvm::yaml::EmptyContext Ctx;
+  yamlize(xout, Id, true, Ctx);
+
+  ostr.flush();
+  EXPECT_EQ("abc/", out);
+}
+
+TEST(YAMLIO, TestEscapedDoubleQuoteNonPrintable) {
+  std::string Id = "\01@abc@";
+
+  std::string out;
+  llvm::raw_string_ostream ostr(out);
+  Output xout(ostr, nullptr, 0);
+
+  llvm::yaml::EmptyContext Ctx;
+  yamlize(xout, Id, true, Ctx);
+
+  ostr.flush();
+  EXPECT_EQ("\"\\x01@abc@\"", out);
+}
+
+TEST(YAMLIO, TestEscapedDoubleQuoteInsideSingleQuote) {
+  std::string Id = "abc\"fdf";
+
+  std::string out;
+  llvm::raw_string_ostream ostr(out);
+  Output xout(ostr, nullptr, 0);
+
+  llvm::yaml::EmptyContext Ctx;
+  yamlize(xout, Id, true, Ctx);
+
+  ostr.flush();
+  EXPECT_EQ("'abc\"fdf'", out);
+}
+
+TEST(YAMLIO, TestEscapedDoubleQuoteInsideDoubleQuote) {
+  std::string Id = "\01bc\"fdf";
+
+  std::string out;
+  llvm::raw_string_ostream ostr(out);
+  Output xout(ostr, nullptr, 0);
+
+  llvm::yaml::EmptyContext Ctx;
+  yamlize(xout, Id, true, Ctx);
+
+  ostr.flush();
+  EXPECT_EQ("\"\\x01bc\\\"fdf\"", out);
+}
+
+TEST(YAMLIO, TestEscapedSingleQuoteInsideSingleQuote) {
+  std::string Id = "abc'fdf";
+
+  std::string out;
+  llvm::raw_string_ostream ostr(out);
+  Output xout(ostr, nullptr, 0);
+
+  llvm::yaml::EmptyContext Ctx;
+  yamlize(xout, Id, true, Ctx);
+
+  ostr.flush();
+  EXPECT_EQ("'abc''fdf'", out);
+}