cnpython/Lib/fileinput.py at cnpython · lp9102/cnpython · GitHub

History

427 lines (371 loc) · 14.2 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

"""Helper class to quickly write a loop over all standard input files.

Typical use is:

import fileinput

for line in fileinput.input():

process(line)

This iterates over the lines of all files listed in sys.argv[1:],

defaulting to sys.stdin if the list is empty. If a filename is '-' it

is also replaced by sys.stdin. To specify an alternative list of

filenames, pass it as the argument to input(). A single file name is

also allowed.

Functions filename(), lineno() return the filename and cumulative line

number of the line that has just been read; filelineno() returns its

line number in the current file; isfirstline() returns true iff the

line just read is the first line of its file; isstdin() returns true

iff the line was read from sys.stdin. Function nextfile() closes the

current file so that the next iteration will read the first line from

the next file (if any); lines not read from the file will not count

towards the cumulative line count; the filename is not changed until

after the first line of the next file has been read. Function close()

closes the sequence.

Before any lines have been read, filename() returns None and both line

numbers are zero; nextfile() has no effect. After all lines have been

read, filename() and the line number functions return the values

pertaining to the last line read; nextfile() has no effect.

All files are opened in text mode by default, you can override this by

setting the mode parameter to input() or FileInput.__init__().

If an I/O error occurs during opening or reading a file, the OSError

exception is raised.

If sys.stdin is used more than once, the second and further use will

return no lines, except perhaps for interactive use, or if it has been

explicitly reset (e.g. using sys.stdin.seek(0)).

Empty files are opened and immediately closed; the only time their

presence in the list of filenames is noticeable at all is when the

last file opened is empty.

It is possible that the last line of a file doesn't end in a newline

character; otherwise lines are returned including the trailing

newline.

Class FileInput is the implementation; its methods filename(),

lineno(), fileline(), isfirstline(), isstdin(), nextfile() and close()

correspond to the functions in the module. In addition it has a

readline() method which returns the next input line, and a

__getitem__() method which implements the sequence behavior. The

sequence must be accessed in strictly sequential order; sequence

access and readline() cannot be mixed.

Optional in-place filtering: if the keyword argument inplace=1 is

passed to input() or to the FileInput constructor, the file is moved

to a backup file and standard output is directed to the input file.

This makes it possible to write a filter that rewrites its input file

in place. If the keyword argument backup=".<some extension>" is also

given, it specifies the extension for the backup file, and the backup

file remains around; by default, the extension is ".bak" and it is

deleted when the output file is closed. In-place filtering is

disabled when standard input is read. XXX The current implementation

does not work for MS-DOS 8+3 filesystems.

XXX Possible additions:

- optional getopt argument processing

- isatty()

- read(), read(size), even readlines()

"""

import sys, os

__all__ = ["input", "close", "nextfile", "filename", "lineno", "filelineno",

"fileno", "isfirstline", "isstdin", "FileInput", "hook_compressed",

"hook_encoded"]

_state = None

def input(files=None, inplace=False, backup="", bufsize=0,

mode="r", openhook=None):

"""Return an instance of the FileInput class, which can be iterated.

The parameters are passed to the constructor of the FileInput class.

The returned instance, in addition to being an iterator,

keeps global state for the functions of this module,.

"""

global _state

if _state and _state._file:

raise RuntimeError("input() already active")

_state = FileInput(files, inplace, backup, bufsize, mode, openhook)

return _state

def close():

"""Close the sequence."""

global _state

state = _state

_state = None

if state:

state.close()

def nextfile():

"""

Close the current file so that the next iteration will read the first

line from the next file (if any); lines not read from the file will

not count towards the cumulative line count. The filename is not

changed until after the first line of the next file has been read.

Before the first line has been read, this function has no effect;

it cannot be used to skip the first file. After the last line of the

last file has been read, this function has no effect.

"""

if not _state:

raise RuntimeError("no active input()")

return _state.nextfile()

def filename():

"""

Return the name of the file currently being read.

Before the first line has been read, returns None.

"""

if not _state:

raise RuntimeError("no active input()")

return _state.filename()

def lineno():

"""

Return the cumulative line number of the line that has just been read.

Before the first line has been read, returns 0. After the last line

of the last file has been read, returns the line number of that line.

"""

if not _state:

raise RuntimeError("no active input()")

return _state.lineno()

def filelineno():

"""

Return the line number in the current file. Before the first line

has been read, returns 0. After the last line of the last file has

been read, returns the line number of that line within the file.

"""

if not _state:

raise RuntimeError("no active input()")

return _state.filelineno()

def fileno():

"""

Return the file number of the current file. When no file is currently

opened, returns -1.

"""

if not _state:

raise RuntimeError("no active input()")

return _state.fileno()

def isfirstline():

"""

Returns true the line just read is the first line of its file,

otherwise returns false.

"""

if not _state:

raise RuntimeError("no active input()")

return _state.isfirstline()

def isstdin():

"""

Returns true if the last line was read from sys.stdin,

otherwise returns false.

"""

if not _state:

raise RuntimeError("no active input()")

return _state.isstdin()

class FileInput:

"""FileInput([files[, inplace[, backup[, bufsize, [, mode[, openhook]]]]]])

Class FileInput is the implementation of the module; its methods

filename(), lineno(), fileline(), isfirstline(), isstdin(), fileno(),

nextfile() and close() correspond to the functions of the same name

in the module.

In addition it has a readline() method which returns the next

input line, and a __getitem__() method which implements the

sequence behavior. The sequence must be accessed in strictly

sequential order; random access and readline() cannot be mixed.

"""

def __init__(self, files=None, inplace=False, backup="", bufsize=0,

mode="r", openhook=None):

if isinstance(files, str):

files = (files,)

elif isinstance(files, os.PathLike):

files = (os.fspath(files), )

else:

if files is None:

files = sys.argv[1:]

if not files:

files = ('-',)

else:

files = tuple(files)

self._files = files

self._inplace = inplace

self._backup = backup

if bufsize:

import warnings

warnings.warn('bufsize is deprecated and ignored',

DeprecationWarning, stacklevel=2)

self._savestdout = None

self._output = None

self._filename = None

self._startlineno = 0

self._filelineno = 0

self._file = None

self._isstdin = False

self._backupfilename = None

# restrict mode argument to reading modes

if mode not in ('r', 'rU', 'U', 'rb'):

raise ValueError("FileInput opening mode must be one of "

"'r', 'rU', 'U' and 'rb'")

if 'U' in mode:

import warnings

warnings.warn("'U' mode is deprecated",

DeprecationWarning, 2)

self._mode = mode

if openhook:

if inplace:

raise ValueError("FileInput cannot use an opening hook in inplace mode")

if not callable(openhook):

raise ValueError("FileInput openhook must be callable")

self._openhook = openhook

def __del__(self):

self.close()

def close(self):

try:

self.nextfile()

finally:

self._files = ()

def __enter__(self):

return self

def __exit__(self, type, value, traceback):

self.close()

def __iter__(self):

return self

def __next__(self):

while True:

line = self._readline()

if line:

self._filelineno += 1

return line

if not self._file:

raise StopIteration

self.nextfile()

# repeat with next file

def __getitem__(self, i):

if i != self.lineno():

raise RuntimeError("accessing lines out of order")

try:

return self.__next__()

except StopIteration:

raise IndexError("end of input reached")

def nextfile(self):

savestdout = self._savestdout

self._savestdout = None

if savestdout:

sys.stdout = savestdout

output = self._output

self._output = None

try:

if output:

output.close()

finally:

file = self._file

self._file = None

try:

del self._readline # restore FileInput._readline

except AttributeError:

pass

try:

if file and not self._isstdin:

file.close()

finally:

backupfilename = self._backupfilename

self._backupfilename = None

if backupfilename and not self._backup:

try: os.unlink(backupfilename)

except OSError: pass

self._isstdin = False

def readline(self):

while True:

line = self._readline()

if line:

self._filelineno += 1

return line

if not self._file:

return line

self.nextfile()

# repeat with next file

def _readline(self):

if not self._files:

if 'b' in self._mode:

return b''

else:

return ''

self._filename = self._files[0]

self._files = self._files[1:]

self._startlineno = self.lineno()

self._filelineno = 0

self._file = None

self._isstdin = False

self._backupfilename = 0

if self._filename == '-':

self._filename = '<stdin>'

if 'b' in self._mode:

self._file = getattr(sys.stdin, 'buffer', sys.stdin)

else:

self._file = sys.stdin

self._isstdin = True

else:

if self._inplace:

self._backupfilename = (

os.fspath(self._filename) + (self._backup or ".bak"))

try:

os.unlink(self._backupfilename)

except OSError:

pass

# The next few lines may raise OSError

os.rename(self._filename, self._backupfilename)

self._file = open(self._backupfilename, self._mode)

try:

perm = os.fstat(self._file.fileno()).st_mode

except OSError:

self._output = open(self._filename, "w")

else:

mode = os.O_CREAT | os.O_WRONLY | os.O_TRUNC

if hasattr(os, 'O_BINARY'):

mode |= os.O_BINARY

fd = os.open(self._filename, mode, perm)

self._output = os.fdopen(fd, "w")

try:

if hasattr(os, 'chmod'):

os.chmod(self._filename, perm)

except OSError:

pass

self._savestdout = sys.stdout

sys.stdout = self._output

else:

# This may raise OSError

if self._openhook:

self._file = self._openhook(self._filename, self._mode)

else:

self._file = open(self._filename, self._mode)

self._readline = self._file.readline # hide FileInput._readline

return self._readline()

def filename(self):

return self._filename

def lineno(self):

return self._startlineno + self._filelineno

def filelineno(self):

return self._filelineno

def fileno(self):

if self._file:

try:

return self._file.fileno()

except ValueError:

return -1

else:

return -1

def isfirstline(self):

return self._filelineno == 1

def isstdin(self):

return self._isstdin

def hook_compressed(filename, mode):

ext = os.path.splitext(filename)[1]

if ext == '.gz':

import gzip

return gzip.open(filename, mode)

elif ext == '.bz2':

import bz2

return bz2.BZ2File(filename, mode)

else:

return open(filename, mode)

def hook_encoded(encoding, errors=None):

def openhook(filename, mode):

return open(filename, mode, encoding=encoding, errors=errors)

return openhook

def _test():

import getopt

inplace = False

backup = False

opts, args = getopt.getopt(sys.argv[1:], "ib:")

for o, a in opts:

if o == '-i': inplace = True

if o == '-b': backup = a

for line in input(args, inplace=inplace, backup=backup):

if line[-1:] == '\n': line = line[:-1]

if line[-1:] == '\r': line = line[:-1]

print("%d: %s[%d]%s %s" % (lineno(), filename(), filelineno(),

isfirstline() and "*" or "", line))

print("%d: %s[%d]" % (lineno(), filename(), filelineno()))

if __name__ == '__main__':

_test()

cnpython/Lib/fileinput.py at cnpython · lp9102/cnpython · GitHub

Expand file tree

Breadcrumbs

fileinput.py

Latest commit

History

Breadcrumbs

fileinput.py

File metadata and controls