[FileCheck] Improve printing variables with escapes

Firstly fix FileCheck printing string variables
double-escaped (first regex, then C-style).

This is confusing because it is not clear if the printed
value is the literal value or exactly how it is escaped, without
looking at FileCheck's source code.

Secondly, only escape when doing so makes it easier to read the value
(when the string contains tabs, newlines or non-printable characters).
When the variable value is escaped, make a note of it in the output too,
in order to avoid confusion.

The common case that is motivating this change is variables that contain
windows style paths with backslashes. These were printed as
`"C:\\\\Program Files\\\\MyApp\\\\file.txt"`.
Now prefer to print them as `"C:\Program Files\MyApp\file.txt"`.
Printing the value literally also makes it easier to search for
variables in the output, since the user can just copy-paste it.

Author: Maetveis

llvm/lib/FileCheck/FileCheck.cpp

@@ -264,7 +264,7 @@ BinaryOperation::getImplicitFormat(const SourceMgr &SM) const {
                                                          : *RightFormat;
 }
 
-Expected<std::string> NumericSubstitution::getResult() const {
+Expected<std::string> NumericSubstitution::getResultRegex() const {
   assert(ExpressionPointer->getAST() != nullptr &&
          "Substituting empty expression");
   Expected<APInt> EvaluatedValue = ExpressionPointer->getAST()->eval();
@@ -274,14 +274,55 @@ Expected<std::string> NumericSubstitution::getResult() const {
   return Format.getMatchingString(*EvaluatedValue);
 }
 
-Expected<std::string> StringSubstitution::getResult() const {
+Expected<std::string> NumericSubstitution::getResultForDiagnostics() const {
+  // The "regex" returned by getResultRegex() is just a numeric value
+  // like '42', '0x2A', '-17', 'DEADBEEF' etc. This is already suitable for use in diagnostics.
+  Expected<std::string> Literal = getResultRegex();
+  if (!Literal)
+    return Literal;
+
+  return "\"" + std::move(*Literal) + "\"";
+}
+
+Expected<std::string> StringSubstitution::getResultRegex() const {
   // Look up the value and escape it so that we can put it into the regex.
   Expected<StringRef> VarVal = Context->getPatternVarValue(FromStr);
   if (!VarVal)
     return VarVal.takeError();
   return Regex::escape(*VarVal);
 }
 
+Expected<std::string> StringSubstitution::getResultForDiagnostics() const {
+    Expected<StringRef> VarVal = Context->getPatternVarValue(FromStr);
+    if (!VarVal)
+      return VarVal.takeError();
+
+    std::string Result;
+    Result.reserve(VarVal->size() + 2);
+    raw_string_ostream OS(Result);
+
+    OS << '"';
+    // Escape the string if it contains any characters that
+    // make it hard to read, such as tabs, newlines, quotes, and non-printable characters.
+    // Note that we do not include backslashes in this set, because they are
+    // common in Windows paths and escaping them would make the output
+    // harder to read.
+    // However, when we do escape, backslashes are escaped as well,
+    // otherwise the output would be ambiguous.
+    const bool NeedsEscaping = llvm::any_of(*VarVal, [](char C) {
+      return C == '\t' || C == '\n' || C == '"' || !isPrint(C);
+    });
+    if (NeedsEscaping)
+      OS.write_escaped(*VarVal);
+    else
+      OS << *VarVal;
+    OS << '"';
+    if (NeedsEscaping)
+      OS << " (escaped value)";
+    
+    return Result;
+}
+
 bool Pattern::isValidVarNameStart(char C) { return C == '_' || isAlpha(C); }
 
 Expected<Pattern::VariableProperties>
@@ -1106,7 +1147,7 @@ Pattern::MatchResult Pattern::match(StringRef Buffer,
     Error Errs = Error::success();
     for (const auto &Substitution : Substitutions) {
       // Substitute and check for failure (e.g. use of undefined variable).
-      Expected<std::string> Value = Substitution->getResult();
+      Expected<std::string> Value = Substitution->getResultRegex();
       if (!Value) {
         // Convert to an ErrorDiagnostic to get location information. This is
         // done here rather than printMatch/printNoMatch since now we know which
@@ -1210,16 +1251,16 @@ void Pattern::printSubstitutions(const SourceMgr &SM, StringRef Buffer,
       SmallString<256> Msg;
       raw_svector_ostream OS(Msg);
 
-      Expected<std::string> MatchedValue = Substitution->getResult();
+      Expected<std::string> MatchedValue = Substitution->getResultForDiagnostics();
       // Substitution failures are handled in printNoMatch().
       if (!MatchedValue) {
         consumeError(MatchedValue.takeError());
         continue;
       }
 
       OS << "with \"";
-      OS.write_escaped(Substitution->getFromString()) << "\" equal to \"";
-      OS.write_escaped(*MatchedValue) << "\"";
+      OS.write_escaped(Substitution->getFromString()) << "\" equal to ";
+      OS << *MatchedValue;
 
       // We report only the start of the match/search range to suggest we are
       // reporting the substitutions as set at the start of the match/search.

llvm/lib/FileCheck/FileCheckImpl.h

@@ -366,9 +366,14 @@ class Substitution {
   /// \returns the index where the substitution is to be performed in RegExStr.
   size_t getIndex() const { return InsertIdx; }
 
-  /// \returns a string containing the result of the substitution represented
+  /// \returns a regular expression string that matches the result of the substitution represented
   /// by this class instance or an error if substitution failed.
-  virtual Expected<std::string> getResult() const = 0;
+  virtual Expected<std::string> getResultRegex() const = 0;
+
+  /// \returns a string containing the result of the substitution represented
+  /// by this class instance in a form suitable for diagnostics, or an error if
+  /// substitution failed.
+  virtual Expected<std::string> getResultForDiagnostics() const = 0;
 };
 
 class StringSubstitution : public Substitution {
@@ -379,7 +384,11 @@ class StringSubstitution : public Substitution {
 
   /// \returns the text that the string variable in this substitution matched
   /// when defined, or an error if the variable is undefined.
-  Expected<std::string> getResult() const override;
+  Expected<std::string> getResultRegex() const override;
+
+  /// \returns the text that the string variable in this substitution matched
+  /// when defined, in a form suitable for diagnostics, or an error if the variable is undefined.
+  Expected<std::string> getResultForDiagnostics() const override;
 };
 
 class NumericSubstitution : public Substitution {
@@ -397,7 +406,11 @@ class NumericSubstitution : public Substitution {
 
   /// \returns a string containing the result of evaluating the expression in
   /// this substitution, or an error if evaluation failed.
-  Expected<std::string> getResult() const override;
+  Expected<std::string> getResultRegex() const override;
+
+  /// \returns a string containing the result of evaluating the expression in
+  /// this substitution, in a form suitable for diagnostics, or an error if evaluation failed.
+  Expected<std::string> getResultForDiagnostics() const override;
 };
 
 //===----------------------------------------------------------------------===//

llvm/test/FileCheck/var-escape.txt

@@ -14,9 +14,9 @@ VARS-NEXT: [[WINPATH]] [[NOT_ESCAPED]] [[ESCAPED]] [[#$NUMERIC + 0]]
 ; RUN:   -dump-input=never --strict-whitespace --check-prefix=VARS --input-file=%t.1 %s 2>&1 \
 ; RUN: | FileCheck %s
 
-CHECK: with "WINPATH" equal to "A:\\\\windows\\\\style\\\\path"
-CHECK: with "NOT_ESCAPED" equal to "shouldn't be escaped \\[a-Z\\]\\\\\\+\\$"
-CHECK: with "ESCAPED" equal to "\\\\ \014\013 needs\to \"be\" escaped\\\000"
+CHECK: with "WINPATH" equal to "A:\windows\style\path"
+CHECK: with "NOT_ESCAPED" equal to "shouldn't be escaped [a-Z]\+$"
+CHECK: with "ESCAPED" equal to "\\ \014\013 needs\to \"be\" escaped\000" (escaped value)
 CHECK: with "$NUMERIC + 0" equal to "DEADBEEF"
 
 ; Test escaping of the name of a numeric substitution, which might contain