================ @@ -0,0 +1,157 @@ +//===----------------------------------------------------------------------===// +// +// 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 "Markdown.h" +#include "llvm/ADT/SmallVector.h" +#include "llvm/ADT/StringRef.h" +#include "llvm/Support/Allocator.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/raw_ostream.h" + +#define DEBUG_TYPE "clang-doc-markdown" + +namespace clang { +namespace doc { +namespace markdown { + +static MDNode makeText(llvm::StringRef S) { + return {NodeKind::NK_Text, S, {}}; +} + +// A line is a table separator if it only contains |, -, :, and spaces, +// and has at least one -. +static bool isSepRow(llvm::StringRef Line) { + return Line.contains('-') && + Line.find_first_not_of("|-: ") == llvm::StringRef::npos; +} + +static llvm::ArrayRef<MDNode> +allocateNodes(llvm::SmallVectorImpl<MDNode> &Nodes, + llvm::BumpPtrAllocator &Arena) { + if (Nodes.empty()) + return {}; + MDNode *Allocated = Arena.Allocate<MDNode>(Nodes.size()); + std::uninitialized_copy(Nodes.begin(), Nodes.end(), Allocated); + return llvm::ArrayRef<MDNode>(Allocated, Nodes.size()); +} + +llvm::ArrayRef<MDNode> parseMarkdown(llvm::StringRef ParagraphText, + llvm::BumpPtrAllocator &Arena) { + if (ParagraphText.trim().empty()) { + LLVM_DEBUG(llvm::dbgs() << "[md] empty input, returning nothing\n"); + return {}; + } + + llvm::SmallVector<llvm::StringRef, 16> Lines; + ParagraphText.split(Lines, '\n'); + + LLVM_DEBUG(llvm::dbgs() << "[md] parsing " << Lines.size() << " line(s)\n"); + + llvm::SmallVector<MDNode, 8> Nodes; + unsigned I = 0; + + while (I < Lines.size()) { + llvm::StringRef Line = Lines[I].trim(); + + if (Line.empty()) { + ++I; + continue; + } + + // Fenced code block: ``` or ~~~ + if (Line.starts_with("```") || Line.starts_with("~~~")) { + char Fence = Line[0]; + llvm::StringRef Lang = Line.drop_front(3).trim(); + LLVM_DEBUG(llvm::dbgs() + << "[md] fenced code block, lang='" << Lang << "'\n"); + llvm::SmallVector<MDNode, 4> CodeLines; + ++I; + while (I < Lines.size()) { + llvm::StringRef CodeLine = Lines[I].trim(); + if (CodeLine.size() >= 3 && + llvm::all_of(CodeLine.take_front(3), + [Fence](char C) { return C == Fence; })) { + LLVM_DEBUG(llvm::dbgs() + << "[md] closing fence found at line " << I << "\n"); + break; + } + CodeLines.push_back(makeText(Lines[I])); + ++I; + } + ++I; // skip closing fence ---------------- ilovepi wrote:
this is risky, as I beleive its legal to have text after the closigng fence on the same line. https://github.com/llvm/llvm-project/pull/201746 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
