cpython/Tools/scripts/pindent.py at master · python-emscripten/cpython · GitHub

Repository navigation

History

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

#! /usr/bin/env python3

# This file contains a class and a main program that perform three

# related (though complimentary) formatting operations on Python

# programs. When called as "pindent -c", it takes a valid Python

# program as input and outputs a version augmented with block-closing

# comments. When called as "pindent -d", it assumes its input is a

# Python program with block-closing comments and outputs a commentless

# version. When called as "pindent -r" it assumes its input is a

# Python program with block-closing comments but with its indentation

# messed up, and outputs a properly indented version.

# A "block-closing comment" is a comment of the form '# end <keyword>'

# where <keyword> is the keyword that opened the block. If the

# opening keyword is 'def' or 'class', the function or class name may

# be repeated in the block-closing comment as well. Here is an

# example of a program fully augmented with block-closing comments:

# def foobar(a, b):

# if a == b:

# a = a+1

# elif a < b:

# b = b-1

# if b > a: a = a-1

# # end if

# else:

# print 'oops!'

# # end if

# # end def foobar

# Note that only the last part of an if...elif...else... block needs a

# block-closing comment; the same is true for other compound

# statements (e.g. try...except). Also note that "short-form" blocks

# like the second 'if' in the example must be closed as well;

# otherwise the 'else' in the example would be ambiguous (remember

# that indentation is not significant when interpreting block-closing

# comments).

# The operations are idempotent (i.e. applied to their own output

# they yield an identical result). Running first "pindent -c" and

# then "pindent -r" on a valid Python program produces a program that

# is semantically identical to the input (though its indentation may

# be different). Running "pindent -e" on that output produces a

# program that only differs from the original in indentation.

# Other options:

# -s stepsize: set the indentation step size (default 8)

# -t tabsize : set the number of spaces a tab character is worth (default 8)

# -e : expand TABs into spaces

# file ... : input file(s) (default standard input)

# The results always go to standard output

# Caveats:

# - comments ending in a backslash will be mistaken for continued lines

# - continuations using backslash are always left unchanged

# - continuations inside parentheses are not extra indented by -r

# but must be indented for -c to work correctly (this breaks

# idempotency!)

# - continued lines inside triple-quoted strings are totally garbled

# Secret feature:

# - On input, a block may also be closed with an "end statement" --

# this is a block-closing comment without the '#' sign.

# Possible improvements:

# - check syntax based on transitions in 'next' table

# - better error reporting

# - better error recovery

# - check identifier after class/def

# The following wishes need a more complete tokenization of the source:

# - Don't get fooled by comments ending in backslash

# - reindent continuation lines indicated by backslash

# - handle continuation lines inside parentheses/braces/brackets

# - handle triple quoted strings spanning lines

# - realign comments

# - optionally do much more thorough reformatting, a la C indent

# Defaults

STEPSIZE = 8

TABSIZE = 8

EXPANDTABS = False

import io

import re

import sys

next = {}

next['if'] = next['elif'] = 'elif', 'else', 'end'

next['while'] = next['for'] = 'else', 'end'

next['try'] = 'except', 'finally'

next['except'] = 'except', 'else', 'finally', 'end'

next['else'] = next['finally'] = next['with'] = \

next['def'] = next['class'] = 'end'

next['end'] = ()

start = 'if', 'while', 'for', 'try', 'with', 'def', 'class'

class PythonIndenter:

def __init__(self, fpi = sys.stdin, fpo = sys.stdout,

indentsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

self.fpi = fpi

self.fpo = fpo

self.indentsize = indentsize

self.tabsize = tabsize

self.lineno = 0

self.expandtabs = expandtabs

self._write = fpo.write

self.kwprog = re.compile(

r'^(?:\s|\\\n)*(?P<kw>[a-z]+)'

r'((?:\s|\\\n)+(?P<id>[a-zA-Z_]\w*))?'

r'[^\w]')

self.endprog = re.compile(

r'^(?:\s|\\\n)*#?\s*end\s+(?P<kw>[a-z]+)'

r'(\s+(?P<id>[a-zA-Z_]\w*))?'

r'[^\w]')

self.wsprog = re.compile(r'^[ \t]*')

# end def __init__

def write(self, line):

if self.expandtabs:

self._write(line.expandtabs(self.tabsize))

else:

self._write(line)

# end if

# end def write

def readline(self):

line = self.fpi.readline()

if line: self.lineno += 1

# end if

return line

# end def readline

def error(self, fmt, *args):

if args: fmt = fmt % args

# end if

sys.stderr.write('Error at line %d: %s\n' % (self.lineno, fmt))

self.write('### %s ###\n' % fmt)

# end def error

def getline(self):

line = self.readline()

while line[-2:] == '\\\n':

line2 = self.readline()

if not line2: break

# end if

line += line2

# end while

return line

# end def getline

def putline(self, line, indent):

tabs, spaces = divmod(indent*self.indentsize, self.tabsize)

i = self.wsprog.match(line).end()

line = line[i:]

if line[:1] not in ('\n', '\r', ''):

line = '\t'*tabs + ' '*spaces + line

# end if

self.write(line)

# end def putline

def reformat(self):

stack = []

while True:

line = self.getline()

if not line: break # EOF

# end if

m = self.endprog.match(line)

if m:

kw = 'end'

kw2 = m.group('kw')

if not stack:

self.error('unexpected end')

elif stack.pop()[0] != kw2:

self.error('unmatched end')

# end if

self.putline(line, len(stack))

continue

# end if

m = self.kwprog.match(line)

if m:

kw = m.group('kw')

if kw in start:

self.putline(line, len(stack))

stack.append((kw, kw))

continue

# end if

if kw in next and stack:

self.putline(line, len(stack)-1)

kwa, kwb = stack[-1]

stack[-1] = kwa, kw

continue

# end if

self.putline(line, len(stack))

# end while

if stack:

self.error('unterminated keywords')

for kwa, kwb in stack:

self.write('\t%s\n' % kwa)

# end for

# end if

# end def reformat

def delete(self):

begin_counter = 0

end_counter = 0

while True:

line = self.getline()

if not line: break # EOF

# end if

m = self.endprog.match(line)

if m:

end_counter += 1

continue

# end if

m = self.kwprog.match(line)

if m:

kw = m.group('kw')

if kw in start:

begin_counter += 1

# end if

self.write(line)

# end while

if begin_counter - end_counter < 0:

sys.stderr.write('Warning: input contained more end tags than expected\n')

elif begin_counter - end_counter > 0:

sys.stderr.write('Warning: input contained less end tags than expected\n')

# end if

# end def delete

def complete(self):

stack = []

todo = []

currentws = thisid = firstkw = lastkw = topid = ''

while True:

line = self.getline()

i = self.wsprog.match(line).end()

m = self.endprog.match(line)

if m:

thiskw = 'end'

endkw = m.group('kw')

thisid = m.group('id')

else:

m = self.kwprog.match(line)

if m:

thiskw = m.group('kw')

if thiskw not in next:

thiskw = ''

# end if

if thiskw in ('def', 'class'):

thisid = m.group('id')

else:

thisid = ''

# end if

elif line[i:i+1] in ('\n', '#'):

todo.append(line)

continue

else:

thiskw = ''

# end if

indentws = line[:i]

indent = len(indentws.expandtabs(self.tabsize))

current = len(currentws.expandtabs(self.tabsize))

while indent < current:

if firstkw:

if topid:

s = '# end %s %s\n' % (

firstkw, topid)

else:

s = '# end %s\n' % firstkw

# end if

self.write(currentws + s)

firstkw = lastkw = ''

# end if

currentws, firstkw, lastkw, topid = stack.pop()

current = len(currentws.expandtabs(self.tabsize))

# end while

if indent == current and firstkw:

if thiskw == 'end':

if endkw != firstkw:

self.error('mismatched end')

# end if

firstkw = lastkw = ''

elif not thiskw or thiskw in start:

if topid:

s = '# end %s %s\n' % (

firstkw, topid)

else:

s = '# end %s\n' % firstkw

# end if

self.write(currentws + s)

firstkw = lastkw = topid = ''

# end if

if indent > current:

stack.append((currentws, firstkw, lastkw, topid))

if thiskw and thiskw not in start:

# error

thiskw = ''

# end if

currentws, firstkw, lastkw, topid = \

indentws, thiskw, thiskw, thisid

# end if

if thiskw:

if thiskw in start:

firstkw = lastkw = thiskw

topid = thisid

else:

lastkw = thiskw

# end if

for l in todo: self.write(l)

# end for

todo = []

if not line: break

# end if

self.write(line)

# end while

# end def complete

# end class PythonIndenter

# Simplified user interface

# - xxx_filter(input, output): read and write file objects

# - xxx_string(s): take and return string object

# - xxx_file(filename): process file in place, return true iff changed

def complete_filter(input = sys.stdin, output = sys.stdout,

stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)

pi.complete()

# end def complete_filter

def delete_filter(input= sys.stdin, output = sys.stdout,

stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)

pi.delete()

# end def delete_filter

def reformat_filter(input = sys.stdin, output = sys.stdout,

stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)

pi.reformat()

# end def reformat_filter

def complete_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

input = io.StringIO(source)

output = io.StringIO()

pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)

pi.complete()

return output.getvalue()

# end def complete_string

def delete_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

input = io.StringIO(source)

output = io.StringIO()

pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)

pi.delete()

return output.getvalue()

# end def delete_string

def reformat_string(source, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

input = io.StringIO(source)

output = io.StringIO()

pi = PythonIndenter(input, output, stepsize, tabsize, expandtabs)

pi.reformat()

return output.getvalue()

# end def reformat_string

def make_backup(filename):

import os, os.path

backup = filename + '~'

if os.path.lexists(backup):

try:

os.remove(backup)

except OSError:

print("Can't remove backup %r" % (backup,), file=sys.stderr)

# end try

# end if

try:

os.rename(filename, backup)

except OSError:

print("Can't rename %r to %r" % (filename, backup), file=sys.stderr)

# end try

# end def make_backup

def complete_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

with open(filename, 'r') as f:

source = f.read()

# end with

result = complete_string(source, stepsize, tabsize, expandtabs)

if source == result: return 0

# end if

make_backup(filename)

with open(filename, 'w') as f:

f.write(result)

# end with

return 1

# end def complete_file

def delete_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

with open(filename, 'r') as f:

source = f.read()

# end with

result = delete_string(source, stepsize, tabsize, expandtabs)

if source == result: return 0

# end if

make_backup(filename)

with open(filename, 'w') as f:

f.write(result)

# end with

return 1

# end def delete_file

def reformat_file(filename, stepsize = STEPSIZE, tabsize = TABSIZE, expandtabs = EXPANDTABS):

with open(filename, 'r') as f:

source = f.read()

# end with

result = reformat_string(source, stepsize, tabsize, expandtabs)

if source == result: return 0

# end if

make_backup(filename)

with open(filename, 'w') as f:

f.write(result)

# end with

return 1

# end def reformat_file

# Test program when called as a script

usage = """

usage: pindent (-c|-d|-r) [-s stepsize] [-t tabsize] [-e] [file] ...

-c : complete a correctly indented program (add #end directives)

-d : delete #end directives

-r : reformat a completed program (use #end directives)

-s stepsize: indentation step (default %(STEPSIZE)d)

-t tabsize : the worth in spaces of a tab (default %(TABSIZE)d)

-e : expand TABs into spaces (default OFF)

[file] ... : files are changed in place, with backups in file~

If no files are specified or a single - is given,

the program acts as a filter (reads stdin, writes stdout).

""" % vars()

def error_both(op1, op2):

sys.stderr.write('Error: You can not specify both '+op1+' and -'+op2[0]+' at the same time\n')

sys.stderr.write(usage)

sys.exit(2)

# end def error_both

def test():

import getopt

try:

opts, args = getopt.getopt(sys.argv[1:], 'cdrs:t:e')

except getopt.error as msg:

sys.stderr.write('Error: %s\n' % msg)

sys.stderr.write(usage)

sys.exit(2)

# end try

action = None

stepsize = STEPSIZE

tabsize = TABSIZE

expandtabs = EXPANDTABS

for o, a in opts:

if o == '-c':

if action: error_both(o, action)

# end if

action = 'complete'

elif o == '-d':

if action: error_both(o, action)

# end if

action = 'delete'

elif o == '-r':

if action: error_both(o, action)

# end if

action = 'reformat'

elif o == '-s':

stepsize = int(a)

elif o == '-t':

tabsize = int(a)

elif o == '-e':

expandtabs = True

# end if

# end for

if not action:

sys.stderr.write(

'You must specify -c(omplete), -d(elete) or -r(eformat)\n')

sys.stderr.write(usage)

sys.exit(2)

# end if

if not args or args == ['-']:

action = eval(action + '_filter')

action(sys.stdin, sys.stdout, stepsize, tabsize, expandtabs)

else:

action = eval(action + '_file')

for filename in args:

action(filename, stepsize, tabsize, expandtabs)

# end for

# end if

# end def test

if __name__ == '__main__':

test()

# end if

cpython/Tools/scripts/pindent.py at master · python-emscripten/cpython · GitHub

Repository navigation

Expand file tree

Breadcrumbs

pindent.py

Latest commit

History

Breadcrumbs

pindent.py

File metadata and controls