1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
|
//===-- 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/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include <cctype>
#include <optional>
#include <sstream>
#define DEBUG_TYPE "mustache"
using namespace llvm;
using namespace llvm::mustache;
namespace {
using Accessor = ArrayRef<StringRef>;
static bool isFalsey(const json::Value &V) {
return V.getAsNull() || (V.getAsBoolean() && !V.getAsBoolean().value()) ||
(V.getAsArray() && V.getAsArray()->empty());
}
static bool isContextFalsey(const json::Value *V) {
// A missing context (represented by a nullptr) is defined as falsey.
if (!V)
return true;
return isFalsey(*V);
}
static Accessor splitMustacheString(StringRef Str, MustacheContext &Ctx) {
// 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.
SmallVector<StringRef> Tokens;
if (Str == ".") {
// "." is a special accessor that refers to the current context.
// It's a literal, so it doesn't need to be saved.
Tokens.push_back(".");
} else {
while (!Str.empty()) {
StringRef Part;
std::tie(Part, Str) = Str.split('.');
// Each part of the accessor needs to be saved to the arena
// to ensure it has a stable address.
Tokens.push_back(Ctx.Saver.save(Part.trim()));
}
}
// Now, allocate memory for the array of StringRefs in the arena.
StringRef *ArenaTokens = Ctx.Allocator.Allocate<StringRef>(Tokens.size());
// Copy the StringRefs from the stack vector to the arena.
std::copy(Tokens.begin(), Tokens.end(), ArenaTokens);
// Return an ArrayRef pointing to the stable arena memory.
return ArrayRef<StringRef>(ArenaTokens, Tokens.size());
}
} // namespace
namespace llvm::mustache {
class MustacheOutputStream : public raw_ostream {
public:
MustacheOutputStream() = default;
~MustacheOutputStream() override = default;
virtual void suspendIndentation() {}
virtual void resumeIndentation() {}
private:
void anchor() override;
};
void MustacheOutputStream::anchor() {}
class RawMustacheOutputStream : public MustacheOutputStream {
public:
RawMustacheOutputStream(raw_ostream &OS) : OS(OS) { SetUnbuffered(); }
private:
raw_ostream &OS;
void write_impl(const char *Ptr, size_t Size) override {
OS.write(Ptr, Size);
}
uint64_t current_pos() const override { return OS.tell(); }
};
class Token {
public:
enum class Type {
Text,
Variable,
Partial,
SectionOpen,
SectionClose,
InvertSectionOpen,
UnescapeVariable,
Comment,
SetDelimiter,
};
Token(StringRef Str)
: TokenType(Type::Text), RawBody(Str), TokenBody(RawBody),
AccessorValue({}), Indentation(0) {};
Token(StringRef RawBody, StringRef TokenBody, char Identifier,
MustacheContext &Ctx)
: RawBody(RawBody), TokenBody(TokenBody), Indentation(0) {
TokenType = getTokenType(Identifier);
if (TokenType == Type::Comment)
return;
StringRef AccessorStr(this->TokenBody);
if (TokenType != Type::Variable)
AccessorStr = AccessorStr.substr(1);
AccessorValue = splitMustacheString(StringRef(AccessorStr).trim(), Ctx);
}
ArrayRef<StringRef> getAccessor() const { return AccessorValue; }
Type getType() const { return TokenType; }
void setIndentation(size_t NewIndentation) { Indentation = NewIndentation; }
size_t getIndentation() const { return Indentation; }
static Type 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;
case '=':
return Type::SetDelimiter;
default:
return Type::Variable;
}
}
Type TokenType;
// RawBody is the original string that was tokenized.
StringRef RawBody;
// TokenBody is the original string with the identifier removed.
StringRef TokenBody;
ArrayRef<StringRef> AccessorValue;
size_t Indentation;
};
using EscapeMap = DenseMap<char, std::string>;
class ASTNode : public ilist_node<ASTNode> {
public:
enum Type {
Root,
Text,
Partial,
Variable,
UnescapeVariable,
Section,
InvertSection,
};
ASTNode(MustacheContext &Ctx)
: Ctx(Ctx), Ty(Type::Root), Parent(nullptr), ParentContext(nullptr) {}
ASTNode(MustacheContext &Ctx, StringRef Body, ASTNode *Parent)
: Ctx(Ctx), Ty(Type::Text), Body(Body), Parent(Parent),
ParentContext(nullptr) {}
// Constructor for Section/InvertSection/Variable/UnescapeVariable Nodes
ASTNode(MustacheContext &Ctx, Type Ty, ArrayRef<StringRef> Accessor,
ASTNode *Parent)
: Ctx(Ctx), Ty(Ty), Parent(Parent), AccessorValue(Accessor),
ParentContext(nullptr) {}
void addChild(AstPtr Child) { Children.push_back(Child); };
void setRawBody(StringRef NewBody) { RawBody = NewBody; };
void setIndentation(size_t NewIndentation) { Indentation = NewIndentation; };
void render(const llvm::json::Value &Data, MustacheOutputStream &OS);
private:
void renderLambdas(const llvm::json::Value &Contexts,
MustacheOutputStream &OS, Lambda &L);
void renderSectionLambdas(const llvm::json::Value &Contexts,
MustacheOutputStream &OS, SectionLambda &L);
void renderPartial(const llvm::json::Value &Contexts,
MustacheOutputStream &OS, ASTNode *Partial);
void renderChild(const llvm::json::Value &Context, MustacheOutputStream &OS);
const llvm::json::Value *findContext();
void renderRoot(const json::Value &CurrentCtx, MustacheOutputStream &OS);
void renderText(MustacheOutputStream &OS);
void renderPartial(const json::Value &CurrentCtx, MustacheOutputStream &OS);
void renderVariable(const json::Value &CurrentCtx, MustacheOutputStream &OS);
void renderUnescapeVariable(const json::Value &CurrentCtx,
MustacheOutputStream &OS);
void renderSection(const json::Value &CurrentCtx, MustacheOutputStream &OS);
void renderInvertSection(const json::Value &CurrentCtx,
MustacheOutputStream &OS);
MustacheContext &Ctx;
Type Ty;
size_t Indentation = 0;
StringRef RawBody;
StringRef Body;
ASTNode *Parent;
ASTNodeList Children;
const ArrayRef<StringRef> AccessorValue;
const llvm::json::Value *ParentContext;
};
// A wrapper for arena allocator for ASTNodes
static AstPtr createRootNode(MustacheContext &Ctx) {
return new (Ctx.Allocator.Allocate<ASTNode>()) ASTNode(Ctx);
}
static AstPtr createNode(MustacheContext &Ctx, ASTNode::Type T,
ArrayRef<StringRef> A, ASTNode *Parent) {
return new (Ctx.Allocator.Allocate<ASTNode>()) ASTNode(Ctx, T, A, Parent);
}
static AstPtr createTextNode(MustacheContext &Ctx, StringRef Body,
ASTNode *Parent) {
return new (Ctx.Allocator.Allocate<ASTNode>()) ASTNode(Ctx, Body, Parent);
}
// 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}}"
static bool hasTextBehind(size_t Idx, const ArrayRef<Token> &Tokens) {
if (Idx == 0)
return true;
size_t PrevIdx = Idx - 1;
if (Tokens[PrevIdx].getType() != Token::Type::Text)
return true;
const Token &PrevToken = Tokens[PrevIdx];
StringRef TokenBody = StringRef(PrevToken.RawBody).rtrim(" \r\t\v");
return !TokenBody.ends_with("\n") && !(TokenBody.empty() && Idx == 1);
}
// Function to check if there's no meaningful text ahead.
// We determine if a token has text ahead if the left of previous
// token does not start with a newline.
static bool hasTextAhead(size_t Idx, const ArrayRef<Token> &Tokens) {
if (Idx >= Tokens.size() - 1)
return true;
size_t NextIdx = Idx + 1;
if (Tokens[NextIdx].getType() != Token::Type::Text)
return true;
const Token &NextToken = Tokens[NextIdx];
StringRef TokenBody = StringRef(NextToken.RawBody).ltrim(" ");
return !TokenBody.starts_with("\r\n") && !TokenBody.starts_with("\n");
}
static bool requiresCleanUp(Token::Type T) {
// We must clean up all the tokens that could contain child nodes.
return T == Token::Type::SectionOpen || T == Token::Type::InvertSectionOpen ||
T == Token::Type::SectionClose || T == Token::Type::Comment ||
T == Token::Type::Partial || T == Token::Type::SetDelimiter;
}
// Adjust next token body if there is no text ahead.
// For example:
// The template string
// "{{! Comment }} \nLine 2"
// would be considered as no text ahead and should be rendered as
// " Line 2"
static void stripTokenAhead(SmallVectorImpl<Token> &Tokens, size_t Idx) {
Token &NextToken = Tokens[Idx + 1];
StringRef NextTokenBody = NextToken.TokenBody;
// Cut off the leading newline which could be \n or \r\n.
if (NextTokenBody.starts_with("\r\n"))
NextToken.TokenBody = NextTokenBody.substr(2);
else if (NextTokenBody.starts_with("\n"))
NextToken.TokenBody = NextTokenBody.substr(1);
}
// Adjust previous token body if there no text behind.
// For example:
// The template string
// " \t{{#section}}A{{/section}}"
// would be considered as having no text ahead and would be render as:
// "A"
void stripTokenBefore(SmallVectorImpl<Token> &Tokens, size_t Idx,
Token &CurrentToken, Token::Type CurrentType) {
Token &PrevToken = Tokens[Idx - 1];
StringRef PrevTokenBody = PrevToken.TokenBody;
StringRef Unindented = PrevTokenBody.rtrim(" \r\t\v");
size_t Indentation = PrevTokenBody.size() - Unindented.size();
PrevToken.TokenBody = Unindented;
CurrentToken.setIndentation(Indentation);
}
struct Tag {
enum class Kind {
None,
Normal, // {{...}}
Triple, // {{{...}}}
};
Kind TagKind = Kind::None;
StringRef Content; // The content between the delimiters.
StringRef FullMatch; // The entire tag, including delimiters.
size_t StartPosition = StringRef::npos;
};
[[maybe_unused]] static const char *tagKindToString(Tag::Kind K) {
switch (K) {
case Tag::Kind::None:
return "None";
case Tag::Kind::Normal:
return "Normal";
case Tag::Kind::Triple:
return "Triple";
}
llvm_unreachable("Unknown Tag::Kind");
}
[[maybe_unused]] static const char *jsonKindToString(json::Value::Kind K) {
switch (K) {
case json::Value::Kind::Null:
return "JSON_KIND_NULL";
case json::Value::Kind::Boolean:
return "JSON_KIND_BOOLEAN";
case json::Value::Kind::Number:
return "JSON_KIND_NUMBER";
case json::Value::Kind::String:
return "JSON_KIND_STRING";
case json::Value::Kind::Array:
return "JSON_KIND_ARRAY";
case json::Value::Kind::Object:
return "JSON_KIND_OBJECT";
}
llvm_unreachable("Unknown json::Value::Kind");
}
static Tag findNextTag(StringRef Template, size_t StartPos, StringRef Open,
StringRef Close) {
const StringLiteral TripleOpen("{{{");
const StringLiteral TripleClose("}}}");
size_t NormalOpenPos = Template.find(Open, StartPos);
size_t TripleOpenPos = Template.find(TripleOpen, StartPos);
Tag Result;
// Determine which tag comes first.
if (TripleOpenPos != StringRef::npos &&
(NormalOpenPos == StringRef::npos || TripleOpenPos <= NormalOpenPos)) {
// Found a triple mustache tag.
size_t EndPos =
Template.find(TripleClose, TripleOpenPos + TripleOpen.size());
if (EndPos == StringRef::npos)
return Result; // No closing tag found.
Result.TagKind = Tag::Kind::Triple;
Result.StartPosition = TripleOpenPos;
size_t ContentStart = TripleOpenPos + TripleOpen.size();
Result.Content = Template.substr(ContentStart, EndPos - ContentStart);
Result.FullMatch = Template.substr(
TripleOpenPos, (EndPos + TripleClose.size()) - TripleOpenPos);
} else if (NormalOpenPos != StringRef::npos) {
// Found a normal mustache tag.
size_t EndPos = Template.find(Close, NormalOpenPos + Open.size());
if (EndPos == StringRef::npos)
return Result; // No closing tag found.
Result.TagKind = Tag::Kind::Normal;
Result.StartPosition = NormalOpenPos;
size_t ContentStart = NormalOpenPos + Open.size();
Result.Content = Template.substr(ContentStart, EndPos - ContentStart);
Result.FullMatch =
Template.substr(NormalOpenPos, (EndPos + Close.size()) - NormalOpenPos);
}
return Result;
}
static std::optional<std::pair<StringRef, StringRef>>
processTag(const Tag &T, SmallVectorImpl<Token> &Tokens, MustacheContext &Ctx) {
LLVM_DEBUG(dbgs() << "[Tag] " << T.FullMatch << ", Content: " << T.Content
<< ", Kind: " << tagKindToString(T.TagKind) << "\n");
if (T.TagKind == Tag::Kind::Triple) {
Tokens.emplace_back(T.FullMatch, Ctx.Saver.save("&" + T.Content), '&', Ctx);
return std::nullopt;
}
StringRef Interpolated = T.Content;
if (!Interpolated.trim().starts_with("=")) {
char Front = Interpolated.empty() ? ' ' : Interpolated.trim().front();
Tokens.emplace_back(T.FullMatch, Interpolated, Front, Ctx);
return std::nullopt;
}
Tokens.emplace_back(T.FullMatch, Interpolated, '=', Ctx);
StringRef DelimSpec = Interpolated.trim();
DelimSpec = DelimSpec.drop_front(1);
DelimSpec = DelimSpec.take_until([](char C) { return C == '='; });
DelimSpec = DelimSpec.trim();
std::pair<StringRef, StringRef> Ret = DelimSpec.split(' ');
LLVM_DEBUG(dbgs() << "[Set Delimiter] NewOpen: " << Ret.first
<< ", NewClose: " << Ret.second << "\n");
return Ret;
}
// Simple tokenizer that splits the template into tokens.
// The mustache spec allows {{{ }}} to unescape variables,
// but we don't support that here. An unescape variable
// is represented only by {{& variable}}.
static SmallVector<Token> tokenize(StringRef Template, MustacheContext &Ctx) {
LLVM_DEBUG(dbgs() << "[Tokenize Template] \"" << Template << "\"\n");
SmallVector<Token> Tokens;
SmallString<8> Open("{{");
SmallString<8> Close("}}");
size_t Start = 0;
while (Start < Template.size()) {
LLVM_DEBUG(dbgs() << "[Tokenize Loop] Start:" << Start << ", Open:'" << Open
<< "', Close:'" << Close << "'\n");
Tag T = findNextTag(Template, Start, Open, Close);
if (T.TagKind == Tag::Kind::None) {
// No more tags, the rest is text.
Tokens.emplace_back(Template.substr(Start));
break;
}
// Add the text before the tag.
if (T.StartPosition > Start) {
StringRef Text = Template.substr(Start, T.StartPosition - Start);
Tokens.emplace_back(Text);
}
if (auto NewDelims = processTag(T, Tokens, Ctx)) {
std::tie(Open, Close) = *NewDelims;
}
// Move past the tag.
Start = T.StartPosition + T.FullMatch.size();
}
// Fix up white spaces for:
// - open sections
// - inverted sections
// - close sections
// - comments
//
// This loop attempts to find standalone tokens and tries to trim out
// the surrounding whitespace.
// For example:
// if you have the template string
// {{#section}} \n Example \n{{/section}}
// The output should would be
// For example:
// \n Example \n
size_t LastIdx = Tokens.size() - 1;
for (size_t Idx = 0, End = Tokens.size(); Idx < End; ++Idx) {
Token &CurrentToken = Tokens[Idx];
Token::Type CurrentType = CurrentToken.getType();
// Check if token type requires cleanup.
bool RequiresCleanUp = requiresCleanUp(CurrentType);
if (!RequiresCleanUp)
continue;
// We adjust the token body if there's no text behind or ahead.
// A token is considered to have no text ahead if the right of the previous
// token is a newline followed by spaces.
// A token is considered to have no text behind if the left of the next
// token is spaces followed by a newline.
// eg.
// "Line 1\n {{#section}} \n Line 2 \n {{/section}} \n Line 3"
bool HasTextBehind = hasTextBehind(Idx, Tokens);
bool HasTextAhead = hasTextAhead(Idx, Tokens);
if ((!HasTextAhead && !HasTextBehind) || (!HasTextAhead && Idx == 0))
stripTokenAhead(Tokens, Idx);
if ((!HasTextBehind && !HasTextAhead) || (!HasTextBehind && Idx == LastIdx))
stripTokenBefore(Tokens, Idx, CurrentToken, CurrentType);
}
return Tokens;
}
// Custom stream to escape strings.
class EscapeStringStream : public MustacheOutputStream {
public:
explicit EscapeStringStream(llvm::raw_ostream &WrappedStream,
EscapeMap &Escape)
: Escape(Escape), EscapeChars(Escape.keys().begin(), Escape.keys().end()),
WrappedStream(WrappedStream) {
SetUnbuffered();
}
protected:
void write_impl(const char *Ptr, size_t Size) override {
StringRef Data(Ptr, Size);
size_t Start = 0;
while (Start < Size) {
// Find the next character that needs to be escaped.
size_t Next = Data.find_first_of(EscapeChars.str(), Start);
// If no escapable characters are found, write the rest of the string.
if (Next == StringRef::npos) {
WrappedStream << Data.substr(Start);
return;
}
// Write the chunk of text before the escapable character.
if (Next > Start)
WrappedStream << Data.substr(Start, Next - Start);
// Look up and write the escaped version of the character.
WrappedStream << Escape[Data[Next]];
Start = Next + 1;
}
}
uint64_t current_pos() const override { return WrappedStream.tell(); }
private:
EscapeMap &Escape;
SmallString<8> EscapeChars;
llvm::raw_ostream &WrappedStream;
};
// Custom stream to add indentation used to for rendering partials.
class AddIndentationStringStream : public MustacheOutputStream {
public:
explicit AddIndentationStringStream(raw_ostream &WrappedStream,
size_t Indentation)
: Indentation(Indentation), WrappedStream(WrappedStream),
NeedsIndent(true), IsSuspended(false) {
SetUnbuffered();
}
void suspendIndentation() override { IsSuspended = true; }
void resumeIndentation() override { IsSuspended = false; }
protected:
void write_impl(const char *Ptr, size_t Size) override {
llvm::StringRef Data(Ptr, Size);
SmallString<0> Indent;
Indent.resize(Indentation, ' ');
for (char C : Data) {
LLVM_DEBUG(dbgs() << "[Indentation Stream] NeedsIndent:" << NeedsIndent
<< ", C:'" << C << "', Indentation:" << Indentation
<< "\n");
if (NeedsIndent && C != '\n') {
WrappedStream << Indent;
NeedsIndent = false;
}
WrappedStream << C;
if (C == '\n' && !IsSuspended)
NeedsIndent = true;
}
}
uint64_t current_pos() const override { return WrappedStream.tell(); }
private:
size_t Indentation;
raw_ostream &WrappedStream;
bool NeedsIndent;
bool IsSuspended;
};
class Parser {
public:
Parser(StringRef TemplateStr, MustacheContext &Ctx)
: Ctx(Ctx), TemplateStr(TemplateStr) {}
AstPtr parse();
private:
void parseMustache(ASTNode *Parent);
void parseSection(ASTNode *Parent, ASTNode::Type Ty, const Accessor &A);
MustacheContext &Ctx;
SmallVector<Token> Tokens;
size_t CurrentPtr;
StringRef TemplateStr;
};
void Parser::parseSection(ASTNode *Parent, ASTNode::Type Ty,
const Accessor &A) {
AstPtr CurrentNode = createNode(Ctx, Ty, A, Parent);
size_t Start = CurrentPtr;
parseMustache(CurrentNode);
const size_t End = CurrentPtr - 1;
SmallString<128> RawBody;
for (std::size_t I = Start; I < End; I++)
RawBody += Tokens[I].RawBody;
CurrentNode->setRawBody(Ctx.Saver.save(StringRef(RawBody)));
Parent->addChild(CurrentNode);
}
AstPtr Parser::parse() {
Tokens = tokenize(TemplateStr, Ctx);
CurrentPtr = 0;
AstPtr RootNode = createRootNode(Ctx);
parseMustache(RootNode);
return RootNode;
}
void Parser::parseMustache(ASTNode *Parent) {
while (CurrentPtr < Tokens.size()) {
Token CurrentToken = Tokens[CurrentPtr];
CurrentPtr++;
ArrayRef<StringRef> A = CurrentToken.getAccessor();
AstPtr CurrentNode;
switch (CurrentToken.getType()) {
case Token::Type::Text: {
CurrentNode = createTextNode(Ctx, CurrentToken.TokenBody, Parent);
Parent->addChild(CurrentNode);
break;
}
case Token::Type::Variable: {
CurrentNode = createNode(Ctx, ASTNode::Variable, A, Parent);
Parent->addChild(CurrentNode);
break;
}
case Token::Type::UnescapeVariable: {
CurrentNode = createNode(Ctx, ASTNode::UnescapeVariable, A, Parent);
Parent->addChild(CurrentNode);
break;
}
case Token::Type::Partial: {
CurrentNode = createNode(Ctx, ASTNode::Partial, A, Parent);
CurrentNode->setIndentation(CurrentToken.getIndentation());
Parent->addChild(CurrentNode);
break;
}
case Token::Type::SectionOpen: {
parseSection(Parent, ASTNode::Section, A);
break;
}
case Token::Type::InvertSectionOpen: {
parseSection(Parent, ASTNode::InvertSection, A);
break;
}
case Token::Type::Comment:
case Token::Type::SetDelimiter:
break;
case Token::Type::SectionClose:
return;
}
}
}
static void toMustacheString(const json::Value &Data, raw_ostream &OS) {
LLVM_DEBUG(dbgs() << "[To Mustache String] Kind: "
<< jsonKindToString(Data.kind()) << ", Data: " << Data
<< "\n");
switch (Data.kind()) {
case json::Value::Null:
return;
case json::Value::Number: {
auto Num = *Data.getAsNumber();
std::ostringstream SS;
SS << Num;
OS << SS.str();
return;
}
case json::Value::String: {
OS << *Data.getAsString();
return;
}
case json::Value::Array: {
auto Arr = *Data.getAsArray();
if (Arr.empty())
return;
[[fallthrough]];
}
case json::Value::Object:
case json::Value::Boolean: {
llvm::json::OStream JOS(OS, 2);
JOS.value(Data);
break;
}
}
}
void ASTNode::renderRoot(const json::Value &CurrentCtx,
MustacheOutputStream &OS) {
renderChild(CurrentCtx, OS);
}
void ASTNode::renderText(MustacheOutputStream &OS) { OS << Body; }
void ASTNode::renderPartial(const json::Value &CurrentCtx,
MustacheOutputStream &OS) {
LLVM_DEBUG(dbgs() << "[Render Partial] Accessor:" << AccessorValue[0]
<< ", Indentation:" << Indentation << "\n");
auto Partial = Ctx.Partials.find(AccessorValue[0]);
if (Partial != Ctx.Partials.end())
renderPartial(CurrentCtx, OS, Partial->getValue());
}
void ASTNode::renderVariable(const json::Value &CurrentCtx,
MustacheOutputStream &OS) {
auto Lambda = Ctx.Lambdas.find(AccessorValue[0]);
if (Lambda != Ctx.Lambdas.end()) {
renderLambdas(CurrentCtx, OS, Lambda->getValue());
} else if (const json::Value *ContextPtr = findContext()) {
EscapeStringStream ES(OS, Ctx.Escapes);
toMustacheString(*ContextPtr, ES);
}
}
void ASTNode::renderUnescapeVariable(const json::Value &CurrentCtx,
MustacheOutputStream &OS) {
LLVM_DEBUG(dbgs() << "[Render UnescapeVariable] Accessor:" << AccessorValue[0]
<< "\n");
auto Lambda = Ctx.Lambdas.find(AccessorValue[0]);
if (Lambda != Ctx.Lambdas.end()) {
renderLambdas(CurrentCtx, OS, Lambda->getValue());
} else if (const json::Value *ContextPtr = findContext()) {
OS.suspendIndentation();
toMustacheString(*ContextPtr, OS);
OS.resumeIndentation();
}
}
void ASTNode::renderSection(const json::Value &CurrentCtx,
MustacheOutputStream &OS) {
auto SectionLambda = Ctx.SectionLambdas.find(AccessorValue[0]);
if (SectionLambda != Ctx.SectionLambdas.end()) {
renderSectionLambdas(CurrentCtx, OS, SectionLambda->getValue());
return;
}
const json::Value *ContextPtr = findContext();
if (isContextFalsey(ContextPtr))
return;
if (const json::Array *Arr = ContextPtr->getAsArray()) {
for (const json::Value &V : *Arr)
renderChild(V, OS);
return;
}
renderChild(*ContextPtr, OS);
}
void ASTNode::renderInvertSection(const json::Value &CurrentCtx,
MustacheOutputStream &OS) {
bool IsLambda = Ctx.SectionLambdas.contains(AccessorValue[0]);
const json::Value *ContextPtr = findContext();
if (isContextFalsey(ContextPtr) && !IsLambda) {
renderChild(CurrentCtx, OS);
}
}
void ASTNode::render(const llvm::json::Value &Data, MustacheOutputStream &OS) {
if (Ty != Root && Ty != Text && AccessorValue.empty())
return;
// Set the parent context to the incoming context so that we
// can walk up the context tree correctly in findContext().
ParentContext = &Data;
switch (Ty) {
case Root:
renderRoot(Data, OS);
return;
case Text:
renderText(OS);
return;
case Partial:
renderPartial(Data, OS);
return;
case Variable:
renderVariable(Data, OS);
return;
case UnescapeVariable:
renderUnescapeVariable(Data, OS);
return;
case Section:
renderSection(Data, OS);
return;
case InvertSection:
renderInvertSection(Data, OS);
return;
}
llvm_unreachable("Invalid ASTNode type");
}
const json::Value *ASTNode::findContext() {
// The mustache spec allows for dot notation to access nested values
// a single dot refers to the current context.
// We attempt to find the JSON context in the current node, if it is not
// found, then we traverse the parent nodes to find the context until we
// reach the root node or the context is found.
if (AccessorValue.empty())
return nullptr;
if (AccessorValue[0] == ".")
return ParentContext;
const json::Object *CurrentContext = ParentContext->getAsObject();
StringRef CurrentAccessor = AccessorValue[0];
ASTNode *CurrentParent = Parent;
while (!CurrentContext || !CurrentContext->get(CurrentAccessor)) {
if (CurrentParent->Ty != Root) {
CurrentContext = CurrentParent->ParentContext->getAsObject();
CurrentParent = CurrentParent->Parent;
continue;
}
return nullptr;
}
const json::Value *Context = nullptr;
for (auto [Idx, Acc] : enumerate(AccessorValue)) {
const json::Value *CurrentValue = CurrentContext->get(Acc);
if (!CurrentValue)
return nullptr;
if (Idx < AccessorValue.size() - 1) {
CurrentContext = CurrentValue->getAsObject();
if (!CurrentContext)
return nullptr;
} else {
Context = CurrentValue;
}
}
return Context;
}
void ASTNode::renderChild(const json::Value &Contexts,
MustacheOutputStream &OS) {
for (ASTNode &Child : Children)
Child.render(Contexts, OS);
}
void ASTNode::renderPartial(const json::Value &Contexts,
MustacheOutputStream &OS, ASTNode *Partial) {
LLVM_DEBUG(dbgs() << "[Render Partial Indentation] Indentation: " << Indentation << "\n");
AddIndentationStringStream IS(OS, Indentation);
Partial->render(Contexts, IS);
}
void ASTNode::renderLambdas(const llvm::json::Value &Contexts,
MustacheOutputStream &OS, Lambda &L) {
json::Value LambdaResult = L();
std::string LambdaStr;
raw_string_ostream Output(LambdaStr);
toMustacheString(LambdaResult, Output);
Parser P(LambdaStr, Ctx);
AstPtr LambdaNode = P.parse();
EscapeStringStream ES(OS, Ctx.Escapes);
if (Ty == Variable) {
LambdaNode->render(Contexts, ES);
return;
}
LambdaNode->render(Contexts, OS);
}
void ASTNode::renderSectionLambdas(const llvm::json::Value &Contexts,
MustacheOutputStream &OS, SectionLambda &L) {
json::Value Return = L(RawBody.str());
if (isFalsey(Return))
return;
std::string LambdaStr;
raw_string_ostream Output(LambdaStr);
toMustacheString(Return, Output);
Parser P(LambdaStr, Ctx);
AstPtr LambdaNode = P.parse();
LambdaNode->render(Contexts, OS);
}
void Template::render(const llvm::json::Value &Data, llvm::raw_ostream &OS) {
RawMustacheOutputStream MOS(OS);
Tree->render(Data, MOS);
}
void Template::registerPartial(std::string Name, std::string Partial) {
StringRef SavedPartial = Ctx.Saver.save(Partial);
Parser P(SavedPartial, Ctx);
AstPtr PartialTree = P.parse();
Ctx.Partials.insert(std::make_pair(Name, PartialTree));
}
void Template::registerLambda(std::string Name, Lambda L) {
Ctx.Lambdas[Name] = L;
}
void Template::registerLambda(std::string Name, SectionLambda L) {
Ctx.SectionLambdas[Name] = L;
}
void Template::overrideEscapeCharacters(EscapeMap E) {
Ctx.Escapes = std::move(E);
}
Template::Template(StringRef TemplateStr, MustacheContext &Ctx) : Ctx(Ctx) {
Parser P(TemplateStr, Ctx);
Tree = P.parse();
// The default behavior is to escape html entities.
const EscapeMap HtmlEntities = {{'&', "&"},
{'<', "<"},
{'>', ">"},
{'"', """},
{'\'', "'"}};
overrideEscapeCharacters(HtmlEntities);
}
Template::Template(Template &&Other) noexcept
: Ctx(Other.Ctx), Tree(Other.Tree) {
Other.Tree = nullptr;
}
Template::~Template() = default;
} // namespace llvm::mustache
#undef DEBUG_TYPE
|