cpython/Objects/stringlib/split.h at android-testPyObjectPrintOSError · mhsmith/cpython · GitHub

History

390 lines (346 loc) · 11 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

/* stringlib: split implementation */

#ifndef STRINGLIB_FASTSEARCH_H

#error must include "stringlib/fastsearch.h" before including this module

#endif

/* Overallocate the initial list to reduce the number of reallocs for small

split sizes. Eg, "A A A A A A A A A A".split() (10 elements) has three

resizes, to sizes 4, 8, then 16. Most observed string splits are for human

text (roughly 11 words per line) and field delimited data (usually 1-10

fields). For large strings the split algorithms are bandwidth limited

so increasing the preallocation likely will not improve things.*/

#define MAX_PREALLOC 12

/* 5 splits gives 6 elements */

#define PREALLOC_SIZE(maxsplit) \

(maxsplit >= MAX_PREALLOC ? MAX_PREALLOC : maxsplit+1)

#define SPLIT_APPEND(data, left, right) \

sub = STRINGLIB_NEW((data) + (left), \

(right) - (left)); \

if (sub == NULL) \

goto onError; \

if (PyList_Append(list, sub)) { \

Py_DECREF(sub); \

goto onError; \

} \

else \

Py_DECREF(sub);

#define SPLIT_ADD(data, left, right) { \

sub = STRINGLIB_NEW((data) + (left), \

(right) - (left)); \

if (sub == NULL) \

goto onError; \

if (count < MAX_PREALLOC) { \

PyList_SET_ITEM(list, count, sub); \

} else { \

if (PyList_Append(list, sub)) { \

Py_DECREF(sub); \

goto onError; \

} \

else \

Py_DECREF(sub); \

} \

count++; }

/* Always force the list to the expected size. */

#define FIX_PREALLOC_SIZE(list) Py_SET_SIZE(list, count)

Py_LOCAL_INLINE(PyObject *)

STRINGLIB(split_whitespace)(PyObject* str_obj,

const STRINGLIB_CHAR* str, Py_ssize_t str_len,

Py_ssize_t maxcount)

{

Py_ssize_t i, j, count=0;

PyObject *list = PyList_New(PREALLOC_SIZE(maxcount));

PyObject *sub;

if (list == NULL)

return NULL;

i = j = 0;

while (maxcount-- > 0) {

while (i < str_len && STRINGLIB_ISSPACE(str[i]))

i++;

if (i == str_len) break;

j = i; i++;

while (i < str_len && !STRINGLIB_ISSPACE(str[i]))

i++;

#if !STRINGLIB_MUTABLE

if (j == 0 && i == str_len && STRINGLIB_CHECK_EXACT(str_obj)) {

/* No whitespace in str_obj, so just use it as list[0] */

Py_INCREF(str_obj);

PyList_SET_ITEM(list, 0, (PyObject *)str_obj);

count++;

break;

}

#endif

SPLIT_ADD(str, j, i);

}

if (i < str_len) {

/* Only occurs when maxcount was reached */

/* Skip any remaining whitespace and copy to end of string */

while (i < str_len && STRINGLIB_ISSPACE(str[i]))

i++;

if (i != str_len)

SPLIT_ADD(str, i, str_len);

}

FIX_PREALLOC_SIZE(list);

return list;

onError:

Py_DECREF(list);

return NULL;

}

Py_LOCAL_INLINE(PyObject *)

STRINGLIB(split_char)(PyObject* str_obj,

const STRINGLIB_CHAR* str, Py_ssize_t str_len,

const STRINGLIB_CHAR ch,

Py_ssize_t maxcount)

{

Py_ssize_t i, j, count=0;

PyObject *list = PyList_New(PREALLOC_SIZE(maxcount));

PyObject *sub;

if (list == NULL)

return NULL;

i = j = 0;

while ((j < str_len) && (maxcount-- > 0)) {

for(; j < str_len; j++) {

/* I found that using memchr makes no difference */

if (str[j] == ch) {

SPLIT_ADD(str, i, j);

i = j = j + 1;

break;

}

#if !STRINGLIB_MUTABLE

if (count == 0 && STRINGLIB_CHECK_EXACT(str_obj)) {

/* ch not in str_obj, so just use str_obj as list[0] */

Py_INCREF(str_obj);

PyList_SET_ITEM(list, 0, (PyObject *)str_obj);

count++;

} else

#endif

if (i <= str_len) {

SPLIT_ADD(str, i, str_len);

}

FIX_PREALLOC_SIZE(list);

return list;

onError:

Py_DECREF(list);

return NULL;

}

Py_LOCAL_INLINE(PyObject *)

STRINGLIB(split)(PyObject* str_obj,

const STRINGLIB_CHAR* str, Py_ssize_t str_len,

const STRINGLIB_CHAR* sep, Py_ssize_t sep_len,

Py_ssize_t maxcount)

{

Py_ssize_t i, j, pos, count=0;

PyObject *list, *sub;

if (sep_len == 0) {

PyErr_SetString(PyExc_ValueError, "empty separator");

return NULL;

}

else if (sep_len == 1)

return STRINGLIB(split_char)(str_obj, str, str_len, sep[0], maxcount);

list = PyList_New(PREALLOC_SIZE(maxcount));

if (list == NULL)

return NULL;

i = j = 0;

while (maxcount-- > 0) {

pos = FASTSEARCH(str+i, str_len-i, sep, sep_len, -1, FAST_SEARCH);

if (pos < 0)

break;

j = i + pos;

SPLIT_ADD(str, i, j);

i = j + sep_len;

}

#if !STRINGLIB_MUTABLE

if (count == 0 && STRINGLIB_CHECK_EXACT(str_obj)) {

/* No match in str_obj, so just use it as list[0] */

Py_INCREF(str_obj);

PyList_SET_ITEM(list, 0, (PyObject *)str_obj);

count++;

} else

#endif

{

SPLIT_ADD(str, i, str_len);

}

FIX_PREALLOC_SIZE(list);

return list;

onError:

Py_DECREF(list);

return NULL;

}

Py_LOCAL_INLINE(PyObject *)

STRINGLIB(rsplit_whitespace)(PyObject* str_obj,

const STRINGLIB_CHAR* str, Py_ssize_t str_len,

Py_ssize_t maxcount)

{

Py_ssize_t i, j, count=0;

PyObject *list = PyList_New(PREALLOC_SIZE(maxcount));

PyObject *sub;

if (list == NULL)

return NULL;

i = j = str_len - 1;

while (maxcount-- > 0) {

while (i >= 0 && STRINGLIB_ISSPACE(str[i]))

i--;

if (i < 0) break;

j = i; i--;

while (i >= 0 && !STRINGLIB_ISSPACE(str[i]))

i--;

#if !STRINGLIB_MUTABLE

if (j == str_len - 1 && i < 0 && STRINGLIB_CHECK_EXACT(str_obj)) {

/* No whitespace in str_obj, so just use it as list[0] */

Py_INCREF(str_obj);

PyList_SET_ITEM(list, 0, (PyObject *)str_obj);

count++;

break;

}

#endif

SPLIT_ADD(str, i + 1, j + 1);

}

if (i >= 0) {

/* Only occurs when maxcount was reached */

/* Skip any remaining whitespace and copy to beginning of string */

while (i >= 0 && STRINGLIB_ISSPACE(str[i]))

i--;

if (i >= 0)

SPLIT_ADD(str, 0, i + 1);

}

FIX_PREALLOC_SIZE(list);

if (PyList_Reverse(list) < 0)

goto onError;

return list;

onError:

Py_DECREF(list);

return NULL;

}

Py_LOCAL_INLINE(PyObject *)

STRINGLIB(rsplit_char)(PyObject* str_obj,

const STRINGLIB_CHAR* str, Py_ssize_t str_len,

const STRINGLIB_CHAR ch,

Py_ssize_t maxcount)

{

Py_ssize_t i, j, count=0;

PyObject *list = PyList_New(PREALLOC_SIZE(maxcount));

PyObject *sub;

if (list == NULL)

return NULL;

i = j = str_len - 1;

while ((i >= 0) && (maxcount-- > 0)) {

for(; i >= 0; i--) {

if (str[i] == ch) {

SPLIT_ADD(str, i + 1, j + 1);

j = i = i - 1;

break;

}

#if !STRINGLIB_MUTABLE

if (count == 0 && STRINGLIB_CHECK_EXACT(str_obj)) {

/* ch not in str_obj, so just use str_obj as list[0] */

Py_INCREF(str_obj);

PyList_SET_ITEM(list, 0, (PyObject *)str_obj);

count++;

} else

#endif

if (j >= -1) {

SPLIT_ADD(str, 0, j + 1);

}

FIX_PREALLOC_SIZE(list);

if (PyList_Reverse(list) < 0)

goto onError;

return list;

onError:

Py_DECREF(list);

return NULL;

}

Py_LOCAL_INLINE(PyObject *)

STRINGLIB(rsplit)(PyObject* str_obj,

const STRINGLIB_CHAR* str, Py_ssize_t str_len,

const STRINGLIB_CHAR* sep, Py_ssize_t sep_len,

Py_ssize_t maxcount)

{

Py_ssize_t j, pos, count=0;

PyObject *list, *sub;

if (sep_len == 0) {

PyErr_SetString(PyExc_ValueError, "empty separator");

return NULL;

}

else if (sep_len == 1)

return STRINGLIB(rsplit_char)(str_obj, str, str_len, sep[0], maxcount);

list = PyList_New(PREALLOC_SIZE(maxcount));

if (list == NULL)

return NULL;

j = str_len;

while (maxcount-- > 0) {

pos = FASTSEARCH(str, j, sep, sep_len, -1, FAST_RSEARCH);

if (pos < 0)

break;

SPLIT_ADD(str, pos + sep_len, j);

j = pos;

}

#if !STRINGLIB_MUTABLE

if (count == 0 && STRINGLIB_CHECK_EXACT(str_obj)) {

/* No match in str_obj, so just use it as list[0] */

Py_INCREF(str_obj);

PyList_SET_ITEM(list, 0, (PyObject *)str_obj);

count++;

} else

#endif

{

SPLIT_ADD(str, 0, j);

}

FIX_PREALLOC_SIZE(list);

if (PyList_Reverse(list) < 0)

goto onError;

return list;

onError:

Py_DECREF(list);

return NULL;

}

Py_LOCAL_INLINE(PyObject *)

STRINGLIB(splitlines)(PyObject* str_obj,

const STRINGLIB_CHAR* str, Py_ssize_t str_len,

int keepends)

{

/* This does not use the preallocated list because splitlines is

usually run with hundreds of newlines. The overhead of

switching between PyList_SET_ITEM and append causes about a

2-3% slowdown for that common case. A smarter implementation

could move the if check out, so the SET_ITEMs are done first

and the appends only done when the prealloc buffer is full.

That's too much work for little gain.*/

Py_ssize_t i;

Py_ssize_t j;

PyObject *list = PyList_New(0);

PyObject *sub;

if (list == NULL)

return NULL;

for (i = j = 0; i < str_len; ) {

Py_ssize_t eol;

/* Find a line and append it */

while (i < str_len && !STRINGLIB_ISLINEBREAK(str[i]))

i++;

/* Skip the line break reading CRLF as one line break */

eol = i;

if (i < str_len) {

if (str[i] == '\r' && i + 1 < str_len && str[i+1] == '\n')

i += 2;

else

i++;

if (keepends)

eol = i;

}

#if !STRINGLIB_MUTABLE

if (j == 0 && eol == str_len && STRINGLIB_CHECK_EXACT(str_obj)) {

/* No linebreak in str_obj, so just use it as list[0] */

if (PyList_Append(list, str_obj))

goto onError;

break;

}

#endif

SPLIT_APPEND(str, j, eol);

j = i;

}

return list;

onError:

Py_DECREF(list);

return NULL;

}

cpython/Objects/stringlib/split.h at android-testPyObjectPrintOSError · mhsmith/cpython · GitHub

Expand file tree

Breadcrumbs

split.h

Latest commit

History

Breadcrumbs

split.h

File metadata and controls