[clang-tools-extra] [llvm] [llvm] add support for mustache templating language (PR #105893)

[Nicolas van Kempen via llvm-commits]

================
@@ -0,0 +1,788 @@
+//===-- Mustache.cpp ------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+#include "llvm/Support/Mustache.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/raw_ostream.h"
+#include <sstream>
+
+using namespace llvm;
+using namespace llvm::mustache;
+
+namespace {
+
+using Accessor = SmallVector<std::string>;
+
+static bool isFalsey(const json::Value &V) {
+  return V.getAsNull() || (V.getAsBoolean() && !V.getAsBoolean().value()) ||
+         (V.getAsArray() && V.getAsArray()->empty());
+}
+
+static Accessor splitMustacheString(StringRef Str) {
+  // We split the mustache string into an accessor.
+  // For example:
+  //    "a.b.c" would be split into {"a", "b", "c"}
+  // We make an exception for a single dot which
+  // refers to the current context.
+  Accessor Tokens;
+  if (Str == ".") {
+    Tokens.emplace_back(Str);
+    return Tokens;
+  }
+  while (!Str.empty()) {
+    StringRef Part;
+    std::tie(Part, Str) = Str.split(".");
+    Tokens.emplace_back(Part.trim());
+  }
+  return Tokens;
+}
+
+} // namespace
+
+namespace llvm::mustache {
+
+class Token {
+public:
+  enum class Type {
+    Text,
+    Variable,
+    Partial,
+    SectionOpen,
+    SectionClose,
+    InvertSectionOpen,
+    UnescapeVariable,
+    Comment,
+  };
+
+  Token(std::string Str);
+
+  Token(std::string RawBody, std::string TokenBody, char Identifier);
+
+  StringRef getTokenBody() const { return TokenBody; };
+
+  StringRef getRawBody() const { return RawBody; };
+
+  std::string takeTokenBody() { return std::move(TokenBody); }
+
+  std::string takeRawBody() { return std::move(RawBody); }
+
+  void setTokenBody(std::string NewBody) { TokenBody = std::move(NewBody); };
+
+  Accessor getAccessor() const { return Accessor; };
+
+  Type getType() const { return TokenType; };
+
+  void setIndentation(size_t NewIndentation) { Indentation = NewIndentation; };
+
+  size_t getIndentation() const { return Indentation; };
+
+  static Type getTokenType(char Identifier);
----------------
nicovank wrote:

Same here, IMO implementation in declaration is more readable within `.cpp` files, but this is definitely preference-prone so I won't fight if you or others think differently.

https://github.com/llvm/llvm-project/pull/105893