================
@@ -0,0 +1,730 @@
+//===-- 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/Support/Error.h"
+#include "llvm/Support/raw_ostream.h"
+#include <sstream>
+
+using namespace llvm;
+using namespace llvm::json;
+
+namespace llvm {
+namespace mustache {
+namespace {
+
+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; };
+
+ 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);
+
+private:
+ Type TokenType;
+ // RawBody is the original string that was tokenized
+ std::string RawBody;
+ // TokenBody is the original string with the identifier removed
+ std::string TokenBody;
+ Accessor Accessor;
+ size_t Indentation;
+};
+
+class ASTNode {
+public:
+ enum Type {
+ Root,
+ Text,
+ Partial,
+ Variable,
+ UnescapeVariable,
+ Section,
+ InvertSection,
+ };
+
+ ASTNode() : T(Type::Root), ParentContext(nullptr) {};
+
+ ASTNode(StringRef Body, ASTNode *Parent)
+ : T(Type::Text), Body(Body), Parent(Parent), ParentContext(nullptr) {};
+
+ // Constructor for Section/InvertSection/Variable/UnescapeVariable
+ ASTNode(Type T, Accessor Accessor, ASTNode *Parent)
+ : T(T), Parent(Parent), Children({}), Accessor(Accessor),
+ ParentContext(nullptr) {};
+
+ void addChild(ASTNode *Child) { Children.emplace_back(Child); };
+
+ void setRawBody(std::string NewBody) { RawBody = std::move(NewBody); };
+
+ void setIndentation(size_t NewIndentation) { Indentation = NewIndentation; };
+
+ void render(const llvm::json::Value &Data, llvm::raw_ostream &OS);
+
+ void setUpNode(llvm::BumpPtrAllocator &Alloc, StringMap<ASTNode *> &Partials,
+ StringMap<Lambda> &Lambdas,
+ StringMap<SectionLambda> &SectionLambdas,
+ DenseMap<char, std::string> &Escapes);
+
+private:
+ void renderLambdas(const llvm::json::Value &Contexts, llvm::raw_ostream &OS,
+ Lambda &L);
+
+ void renderSectionLambdas(const llvm::json::Value &Contexts,
+ llvm::raw_ostream &OS, SectionLambda &L);
+
+ void renderPartial(const llvm::json::Value &Contexts, llvm::raw_ostream &OS,
+ ASTNode *Partial);
+
+ void renderChild(const llvm::json::Value &Context, llvm::raw_ostream &OS);
+
+ const llvm::json::Value *findContext();
+
+ llvm::BumpPtrAllocator *Allocator;
+ StringMap<ASTNode *> *Partials;
+ StringMap<Lambda> *Lambdas;
+ StringMap<SectionLambda> *SectionLambdas;
+ DenseMap<char, std::string> *Escapes;
+ Type T;
+ size_t Indentation = 0;
+ std::string RawBody;
+ std::string Body;
+ ASTNode *Parent;
+ // TODO: switch implementation to SmallVector<T>
+ std::vector<ASTNode *> Children;
+ const Accessor Accessor;
+ const llvm::json::Value *ParentContext;
+};
+
+// Custom stream to escape strings
+class EscapeStringStream : public raw_ostream {
+public:
+ explicit EscapeStringStream(llvm::raw_ostream &WrappedStream,
+ DenseMap<char, std::string> &Escape)
+ : Escape(Escape), WrappedStream(WrappedStream) {
+ SetUnbuffered();
+ }
+
+protected:
+ void write_impl(const char *Ptr, size_t Size) override {
+ llvm::StringRef Data(Ptr, Size);
+ for (char C : Data) {
+ auto It = Escape.find(C);
+ if (It != Escape.end())
+ WrappedStream << It->getSecond();
+ else
+ WrappedStream << C;
+ }
+ }
+
+ uint64_t current_pos() const override { return WrappedStream.tell(); }
+
+private:
+ DenseMap<char, std::string> &Escape;
+ llvm::raw_ostream &WrappedStream;
+};
+
+// Custom stream to add indentation used to for rendering partials
+class AddIndentationStringStream : public raw_ostream {
+public:
+ explicit AddIndentationStringStream(llvm::raw_ostream &WrappedStream,
+ size_t Indentation)
+ : Indentation(Indentation), WrappedStream(WrappedStream) {
+ SetUnbuffered();
+ }
+
+protected:
+ void write_impl(const char *Ptr, size_t Size) override {
+ llvm::StringRef Data(Ptr, Size);
+ std::string Indent(Indentation, ' ');
+ for (char C : Data) {
+ WrappedStream << C;
+ if (C == '\n')
+ WrappedStream << Indent;
+ }
+ }
+
+ uint64_t current_pos() const override { return WrappedStream.tell(); }
+
+private:
+ size_t Indentation;
+ llvm::raw_ostream &WrappedStream;
+};
+
+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;
+ }
+ StringRef Ref(Str);
+ while (!Ref.empty()) {
+ StringRef Part;
+ std::tie(Part, Ref) = Ref.split(".");
+ Tokens.emplace_back(Part.trim());
+ }
+ return Tokens;
+}
+
+Token::Token(std::string RawBody, std::string TokenBody, char Identifier)
+ : RawBody(std::move(RawBody)), TokenBody(std::move(TokenBody)),
+ Indentation(0) {
+ TokenType = getTokenType(Identifier);
+ if (TokenType == Type::Comment)
+ return;
+
+ std::string AccessorStr =
+ TokenType == Type::Variable ? this->TokenBody :
this->TokenBody.substr(1);
+
+ Accessor = splitMustacheString(StringRef(AccessorStr).trim());
+}
+
+Token::Token(std::string Str)
+ : TokenType(Type::Text), RawBody(std::move(Str)), Accessor({}),
+ TokenBody(RawBody), Indentation(0) {}
+
+Token::Type Token::getTokenType(char Identifier) {
+ switch (Identifier) {
+ case '#':
+ return Type::SectionOpen;
+ case '/':
+ return Type::SectionClose;
+ case '^':
+ return Type::InvertSectionOpen;
+ case '!':
+ return Type::Comment;
+ case '>':
+ return Type::Partial;
+ case '&':
+ return Type::UnescapeVariable;
+ default:
+ return Type::Variable;
+ }
+}
+
+// Function to check if there is meaningful text behind.
+// We determine if a token has meaningful text behind
+// if the right of previous token contains anything that is
+// not a newline
+// For example:
+// "Stuff {{#Section}}" (returns true)
+// vs
+// "{{#Section}} \n" (returns false)
+// We make an exception for when previous token is empty
+// and the current token is the second token
+// For example: "{{#Section}}"
----------------
ilovepi wrote:
```suggestion
// Function to check if there is meaningful text behind.
// We determine if a token has meaningful text behind
// if the right of previous token contains anything that is
// not a newline.
// For example:
// "Stuff {{#Section}}" (returns true)
// vs
// "{{#Section}} \n" (returns false)
// We make an exception for when previous token is empty
// and the current token is the second token.
// For example: "{{#Section}}"
```
https://github.com/llvm/llvm-project/pull/105893
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
