note/src/parser/NoteParser.cpp at dev · vixcpp/note · GitHub

History

534 lines (435 loc) · 11.6 KB

Raw

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

/**

* @file NoteParser.cpp

* @author Gaspard Kirira

* https://github.com/vixcpp/note

* Use of this source code is governed by a MIT license

* that can be found in the LICENSE file.

* Vix Note

#include <vix/note/parser/NoteParser.hpp>

#include <cstddef>

#include <optional>

#include <sstream>

#include <string>

#include <string_view>

#include <utility>

#include <vector>

namespace vix::note

{

namespace

{

struct CellMetadata

{

std::string id;

std::string title;

NoteCellKind kind = NoteCellKind::Unknown;

std::string typeId;

};

std::string trim_copy(std::string_view value)

{

std::size_t begin = 0;

while (begin < value.size() &&

(value[begin] == ' ' ||

value[begin] == '\t' ||

value[begin] == '\n' ||

value[begin] == '\r'))

{

++begin;

}

std::size_t end = value.size();

while (end > begin &&

(value[end - 1] == ' ' ||

value[end - 1] == '\t' ||

value[end - 1] == '\n' ||

value[end - 1] == '\r'))

{

--end;

}

return std::string(value.substr(begin, end - begin));

}

bool starts_with(std::string_view value, std::string_view prefix)

{

return value.size() >= prefix.size() &&

value.substr(0, prefix.size()) == prefix;

}

bool ends_with(std::string_view value, std::string_view suffix)

{

return value.size() >= suffix.size() &&

value.substr(value.size() - suffix.size()) == suffix;

}

std::string lower_copy(std::string value)

{

for (char &c : value)

{

if (c >= 'A' && c <= 'Z')

{

c = static_cast<char>(c - 'A' + 'a');

}

return value;

}

bool is_fence_line(std::string_view line, std::string &language)

{

const std::string trimmed = trim_copy(line);

if (!starts_with(trimmed, "```"))

{

return false;

}

language = trim_copy(std::string_view(trimmed).substr(3));

return true;

}

std::string language_to_cell_type_id(const std::string &language)

{

return normalize_cell_type_id(lower_copy(trim_copy(language)));

}

std::string extract_quoted_attribute(

std::string_view value,

std::string_view name)

{

const std::string text(value);

const std::string pattern =

std::string(name) + "=\"";

const std::size_t begin =

text.find(pattern);

if (begin == std::string::npos)

{

return {};

}

const std::size_t valueBegin =

begin + pattern.size();

const std::size_t valueEnd =

text.find('"', valueBegin);

if (valueEnd == std::string::npos)

{

return {};

}

return text.substr(

valueBegin,

valueEnd - valueBegin);

}

bool parse_cell_metadata_comment(

std::string_view line,

CellMetadata &metadata)

{

metadata = CellMetadata{};

const std::string trimmed =

trim_copy(line);

if (!starts_with(trimmed, "<!--") ||

!ends_with(trimmed, "-->"))

{

return false;

}

if (trimmed.find("vixnote:cell") == std::string::npos)

{

return false;

}

metadata.id =

extract_quoted_attribute(trimmed, "id");

metadata.title =

extract_quoted_attribute(trimmed, "title");

const std::string kind =

extract_quoted_attribute(trimmed, "kind");

if (!kind.empty())

{

metadata.typeId = normalize_cell_type_id(kind);

metadata.kind = builtin_kind_from_type_id(metadata.typeId);

}

return true;

}

std::string make_cell_id(std::size_t index)

{

return "cell-" + std::to_string(index);

}

bool contains_non_whitespace(std::string_view value)

{

for (char c : value)

{

if (c != ' ' && c != '\t' && c != '\n' && c != '\r')

{

return true;

}

return false;

}

void append_line(std::string &target, const std::string &line)

{

target += line;

target += '\n';

}

void remove_final_newline(std::string &value)

{

while (!value.empty() &&

(value.back() == '\n' ||

value.back() == '\r' ||

value.back() == ' ' ||

value.back() == '\t'))

{

value.pop_back();

}

void trim_outer_whitespace(std::string &value)

{

while (!value.empty() &&

(value.front() == '\n' ||

value.front() == '\r' ||

value.front() == ' ' ||

value.front() == '\t'))

{

value.erase(value.begin());

}

while (!value.empty() &&

(value.back() == '\n' ||

value.back() == '\r' ||

value.back() == ' ' ||

value.back() == '\t'))

{

value.pop_back();

}

std::string infer_title_from_markdown(std::string_view markdown)

{

std::istringstream in{std::string(markdown)};

std::string line;

while (std::getline(in, line))

{

const std::string trimmed = trim_copy(line);

if (!starts_with(trimmed, "# "))

{

continue;

}

return trim_copy(std::string_view(trimmed).substr(2));

}

return {};

}

void assign_id_if_needed(

NoteCell &cell,

const NoteParseOptions &options,

std::size_t cellIndex)

{

if (!options.assignCellIds || !cell.id().empty())

{

return;

}

cell.set_id(make_cell_id(cellIndex));

}

void apply_pending_metadata(

NoteCell &cell,

std::optional<CellMetadata> &pendingMetadata)

{

if (!pendingMetadata)

{

return;

}

if (!pendingMetadata->id.empty())

{

cell.set_id(pendingMetadata->id);

}

if (!pendingMetadata->title.empty())

{

cell.set_title(pendingMetadata->title);

}

if (!pendingMetadata->typeId.empty())

{

cell.set_type_id(pendingMetadata->typeId);

}

pendingMetadata.reset();

}

void append_markdown_cell(

NoteDocument &document,

std::string &markdown,

const NoteParseOptions &options,

std::optional<CellMetadata> &pendingMetadata)

{

if (!contains_non_whitespace(markdown))

{

markdown.clear();

return;

}

trim_outer_whitespace(markdown);

NoteCell cell = NoteCell::markdown(std::move(markdown));

apply_pending_metadata(cell, pendingMetadata);

assign_id_if_needed(cell, options, document.cell_count() + 1);

document.add_cell(std::move(cell));

markdown.clear();

}

void append_code_cell(

NoteDocument &document,

std::string typeId,

std::string source,

const NoteParseOptions &options,

std::optional<CellMetadata> &pendingMetadata)

{

remove_final_newline(source);

NoteCell cell({}, std::move(typeId), std::move(source));

apply_pending_metadata(cell, pendingMetadata);

assign_id_if_needed(cell, options, document.cell_count() + 1);

document.add_cell(std::move(cell));

}

bool NoteParseResult::has_diagnostics() const noexcept

{

return !diagnostics.empty();

}

NoteParser::NoteParser() = default;

NoteParser::NoteParser(NoteParseOptions options)

: options_(options)

{

}

const NoteParseOptions &NoteParser::options() const noexcept

{

return options_;

}

void NoteParser::set_options(NoteParseOptions options) noexcept

{

options_ = options;

}

NoteParseResult NoteParser::parse(std::string_view source) const

{

NoteParseResult result;

NoteDocument document;

std::string markdownBuffer;

std::string codeBuffer;

std::string fenceLanguage;

bool inFence = false;

std::string fenceTypeId;

std::size_t fenceStartLine = 0;

std::size_t lineNumber = 0;

std::optional<CellMetadata> pendingMetadata;

std::istringstream in{std::string(source)};

std::string line;

while (std::getline(in, line))

{

++lineNumber;

std::string language;

CellMetadata metadata;

if (!inFence &&

options_.readCellMetadata &&

parse_cell_metadata_comment(line, metadata))

{

append_markdown_cell(

document,

markdownBuffer,

options_,

pendingMetadata);

pendingMetadata = std::move(metadata);

continue;

}

if (!inFence && is_fence_line(line, language))

{

append_markdown_cell(

document,

markdownBuffer,

options_,

pendingMetadata);

inFence = true;

fenceLanguage = language;

fenceTypeId = language_to_cell_type_id(language);

fenceStartLine = lineNumber;

codeBuffer.clear();

continue;

}

if (inFence && is_fence_line(line, language))

{

const bool hasExplicitCellType =

pendingMetadata && !pendingMetadata->typeId.empty();

const bool shouldCreateCell =

!fenceTypeId.empty() &&

fenceTypeId != "markdown" &&

(is_builtin_cell_type(fenceTypeId) || hasExplicitCellType);

if (!shouldCreateCell)

{

std::string fencedMarkdown;

fencedMarkdown += "```";

fencedMarkdown += fenceLanguage;

fencedMarkdown += '\n';

fencedMarkdown += codeBuffer;

fencedMarkdown += "```";

append_line(markdownBuffer, fencedMarkdown);

}

else

{

append_code_cell(

document,

fenceTypeId,

std::move(codeBuffer),

options_,

pendingMetadata);

codeBuffer.clear();

}

inFence = false;

fenceLanguage.clear();

fenceTypeId.clear();

fenceStartLine = 0;

continue;

}

if (inFence)

{

append_line(codeBuffer, line);

}

else

{

append_line(markdownBuffer, line);

}

if (inFence)

{

result.ok = false;

result.document = std::move(document);

result.error =

"unterminated fenced cell starting at line " +

std::to_string(fenceStartLine);

return result;

}

append_markdown_cell(

document,

markdownBuffer,

options_,

pendingMetadata);

if (options_.inferTitle && !document.has_title())

{

for (const auto &cell : document.cells())

{

if (cell.kind() != NoteCellKind::Markdown)

{

continue;

}

const std::string title =

infer_title_from_markdown(cell.source());

if (!title.empty())

{

document.set_title(title);

break;

}

result.ok = true;

result.document = std::move(document);

return result;

}

NoteDocument NoteParser::parse_or_throw(std::string_view source) const

{

NoteParseResult result = parse(source);

if (!result.ok)

{

throw NoteError(

NoteErrorCode::Parse,

result.error.empty() ? "failed to parse note document" : result.error);

}

return std::move(result.document);

}

NoteParseResult parse_note(std::string_view source)

{

return NoteParser().parse(source);

}

NoteDocument parse_note_or_throw(std::string_view source)

{

return NoteParser().parse_or_throw(source);

}

note/src/parser/NoteParser.cpp at dev · vixcpp/note · GitHub

Uh oh!

Expand file tree

Breadcrumbs

NoteParser.cpp

Latest commit

History

Breadcrumbs

NoteParser.cpp

File metadata and controls