================ @@ -151,16 +151,91 @@ bool needsLeadingEscape(char C, llvm::StringRef Before, llvm::StringRef After, } } +/// \brief Tests whether \p C should be backslash-escaped in markdown. +/// +/// The MarkupContent LSP specification defines that `markdown` content needs to +/// follow GFM (GitHub Flavored Markdown) rules. And we can assume that markdown +/// is rendered on the client side. This means we do not need to escape any +/// markdown constructs. +/// The only exception is when the client does not support HTML rendering in +/// markdown. In that case, we need to escape HTML tags and HTML entities. +/// +/// **FIXME:** handle the case when the client does support HTML rendering in +/// markdown. For this, the LSP server needs to check the +/// [supportsHtml +/// capability](https://github.com/microsoft/language-server-protocol/issues/1344) +/// of the client. +/// +/// \param C The character to check. +/// \param After The string that follows \p C . +// This is used to determine if \p C is part of a tag or an entity reference. +/// \returns true if \p C should be escaped, false otherwise. +bool needsLeadingEscapeMarkdown(char C, llvm::StringRef After) { + switch (C) { + case '<': // HTML tag (or autolink, which we choose not to escape) + return looksLikeTag(After); + case '&': { // HTML entity reference + auto End = After.find(';'); + if (End == llvm::StringRef::npos) + return false; + llvm::StringRef Content = After.substr(0, End); + if (Content.consume_front("#")) { + if (Content.consume_front("x") || Content.consume_front("X")) + return llvm::all_of(Content, llvm::isHexDigit); + return llvm::all_of(Content, llvm::isDigit); + } + return llvm::all_of(Content, llvm::isAlpha); + } + default: + return false; + } +} + +bool needsLeadingEscape(char C, llvm::StringRef Before, llvm::StringRef After, + bool StartsLine, bool EscapeMarkdown) { + if (EscapeMarkdown) + return needsLeadingEscapePlaintext(C, Before, After, StartsLine); + return needsLeadingEscapeMarkdown(C, After); +} + /// Escape a markdown text block. Ensures the punctuation will not introduce /// any of the markdown constructs. -std::string renderText(llvm::StringRef Input, bool StartsLine) { +std::string renderText(llvm::StringRef Input, bool StartsLine, + bool EscapeMarkdown = false) { ---------------- emaxx-google wrote:
nit: I'd recommend not using the default parameter value here, since it's easy to forget passing it accidentally and also hard to spot the difference between "escaped" and non-escaped branches. https://github.com/llvm/llvm-project/pull/140498 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
