v8_presubmit.py 26.2 KB
Newer Older
1
#!/usr/bin/env python3
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
#
# Copyright 2012 the V8 project authors. All rights reserved.
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
#     * Redistributions of source code must retain the above copyright
#       notice, this list of conditions and the following disclaimer.
#     * Redistributions in binary form must reproduce the above
#       copyright notice, this list of conditions and the following
#       disclaimer in the documentation and/or other materials provided
#       with the distribution.
#     * Neither the name of Google Inc. nor the names of its
#       contributors may be used to endorse or promote products derived
#       from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

30 31
import hashlib
md5er = hashlib.md5
32 33 34


import json
35
import multiprocessing
36 37 38 39 40 41 42
import optparse
import os
from os.path import abspath, join, dirname, basename, exists
import pickle
import re
import subprocess
from subprocess import PIPE
43
import sys
44 45 46 47 48

from testrunner.local import statusfile
from testrunner.local import testsuite
from testrunner.local import utils

49 50
def decode(arg, encoding="utf-8"):
  return arg.decode(encoding)
51

52 53
def encode(arg, encoding="utf-8"):
  return arg.encode(encoding)
54

55 56 57 58 59
# Special LINT rules diverging from default and reason.
# build/header_guard: Our guards have the form "V8_FOO_H_", not "SRC_FOO_H_".
#   We now run our own header guard check in PRESUBMIT.py.
# build/include_what_you_use: Started giving false positives for variables
#   named "string" and "map" assuming that you needed to include STL headers.
60 61 62
# runtime/references: As of May 2020 the C++ style guide suggests using
#   references for out parameters, see
#   https://google.github.io/styleguide/cppguide.html#Inputs_and_Outputs.
63 64
# whitespace/braces: Doesn't handle {}-initialization for custom types
#   well; also should be subsumed by clang-format.
65 66 67 68 69 70

LINT_RULES = """
-build/header_guard
-build/include_what_you_use
-readability/fn_size
-readability/multiline_comment
71
-runtime/references
72
-whitespace/braces
73 74 75
-whitespace/comments
""".split()

76
LINT_OUTPUT_PATTERN = re.compile(r'^.+[:(]\d+[:)]')
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91
FLAGS_LINE = re.compile("//\s*Flags:.*--([A-z0-9-])+_[A-z0-9].*\n")
ASSERT_OPTIMIZED_PATTERN = re.compile("assertOptimized")
FLAGS_ENABLE_OPT = re.compile("//\s*Flags:.*--opt[^-].*\n")
ASSERT_UNOPTIMIZED_PATTERN = re.compile("assertUnoptimized")
FLAGS_NO_ALWAYS_OPT = re.compile("//\s*Flags:.*--no-?always-opt.*\n")

TOOLS_PATH = dirname(abspath(__file__))

def CppLintWorker(command):
  try:
    process = subprocess.Popen(command, stderr=subprocess.PIPE)
    process.wait()
    out_lines = ""
    error_count = -1
    while True:
92
      out_line = decode(process.stderr.readline())
93 94
      if out_line == '' and process.poll() != None:
        if error_count == -1:
95
          print("Failed to process %s" % command.pop())
96 97
          return 1
        break
98 99
      if out_line.strip() == 'Total errors found: 0':
        out_lines += "Done processing %s\n" % command.pop()
100
        error_count += 1
101 102 103 104 105
      else:
        m = LINT_OUTPUT_PATTERN.match(out_line)
        if m:
          out_lines += out_line
          error_count += 1
106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
    sys.stdout.write(out_lines)
    return error_count
  except KeyboardInterrupt:
    process.kill()
  except:
    print('Error running cpplint.py. Please make sure you have depot_tools' +
          ' in your $PATH. Lint check skipped.')
    process.kill()

def TorqueLintWorker(command):
  try:
    process = subprocess.Popen(command, stderr=subprocess.PIPE)
    process.wait()
    out_lines = ""
    error_count = 0
    while True:
122
      out_line = decode(process.stderr.readline())
123 124 125 126 127 128
      if out_line == '' and process.poll() != None:
        break
      out_lines += out_line
      error_count += 1
    sys.stdout.write(out_lines)
    if error_count != 0:
129
      sys.stdout.write(
130
          "warning: formatting and overwriting unformatted Torque files\n")
131 132 133 134 135 136 137
    return error_count
  except KeyboardInterrupt:
    process.kill()
  except:
    print('Error running format-torque.py')
    process.kill()

138
def JSLintWorker(command):
139 140 141 142 143 144 145 146 147 148 149 150 151
  def format_file(command):
    try:
      file_name = command[-1]
      with open(file_name, "r") as file_handle:
        contents = file_handle.read()

      process = subprocess.Popen(command, stdout=PIPE, stderr=subprocess.PIPE)
      output, err = process.communicate()
      rc = process.returncode
      if rc != 0:
        sys.stdout.write("error code " + str(rc) + " running clang-format.\n")
        return rc

152
      if decode(output) != contents:
153 154 155 156 157 158 159 160 161 162 163 164 165
        return 1

      return 0
    except KeyboardInterrupt:
      process.kill()
    except Exception:
      print('Error running clang-format. Please make sure you have depot_tools' +
            ' in your $PATH. Lint check skipped.')
      process.kill()

  rc = format_file(command)
  if rc == 1:
    # There are files that need to be formatted, let's format them in place.
166
    file_name = command[-1]
167 168 169
    sys.stdout.write("Formatting %s.\n" % (file_name))
    rc = format_file(command[:-1] + ["-i", file_name])
  return rc
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
class FileContentsCache(object):

  def __init__(self, sums_file_name):
    self.sums = {}
    self.sums_file_name = sums_file_name

  def Load(self):
    try:
      sums_file = None
      try:
        sums_file = open(self.sums_file_name, 'r')
        self.sums = pickle.load(sums_file)
      except:
        # Cannot parse pickle for any reason. Not much we can do about it.
        pass
    finally:
      if sums_file:
        sums_file.close()

  def Save(self):
    try:
      sums_file = open(self.sums_file_name, 'w')
      pickle.dump(self.sums, sums_file)
    except:
      # Failed to write pickle. Try to clean-up behind us.
      if sums_file:
        sums_file.close()
      try:
        os.unlink(self.sums_file_name)
      except:
        pass
    finally:
      sums_file.close()

  def FilterUnchangedFiles(self, files):
    changed_or_new = []
    for file in files:
      try:
        handle = open(file, "r")
210
        file_sum = md5er(encode(handle.read())).digest()
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
        if not file in self.sums or self.sums[file] != file_sum:
          changed_or_new.append(file)
          self.sums[file] = file_sum
      finally:
        handle.close()
    return changed_or_new

  def RemoveFile(self, file):
    if file in self.sums:
      self.sums.pop(file)


class SourceFileProcessor(object):
  """
  Utility class that can run through a directory structure, find all relevant
  files and invoke a custom check on the files.
  """

  def RunOnPath(self, path):
    """Runs processor on all files under the given path."""

    all_files = []
    for file in self.GetPathsToSearch():
      all_files += self.FindFilesIn(join(path, file))
    return self.ProcessFiles(all_files)

  def RunOnFiles(self, files):
    """Runs processor only on affected files."""

    # Helper for getting directory pieces.
    dirs = lambda f: dirname(f).split(os.sep)

    # Path offsets where to look (to be in sync with RunOnPath).
    # Normalize '.' to check for it with str.startswith.
    search_paths = [('' if p == '.' else p) for p in self.GetPathsToSearch()]

    all_files = [
      f.AbsoluteLocalPath()
      for f in files
      if (not self.IgnoreFile(f.LocalPath()) and
          self.IsRelevant(f.LocalPath()) and
          all(not self.IgnoreDir(d) for d in dirs(f.LocalPath())) and
          any(map(f.LocalPath().startswith, search_paths)))
    ]

    return self.ProcessFiles(all_files)

  def IgnoreDir(self, name):
    return (name.startswith('.') or
            name in ('buildtools', 'data', 'gmock', 'gtest', 'kraken',
                     'octane', 'sunspider', 'traces-arm64'))

  def IgnoreFile(self, name):
    return name.startswith('.')

  def FindFilesIn(self, path):
    result = []
    for (root, dirs, files) in os.walk(path):
      for ignored in [x for x in dirs if self.IgnoreDir(x)]:
        dirs.remove(ignored)
      for file in files:
        if not self.IgnoreFile(file) and self.IsRelevant(file):
          result.append(join(root, file))
    return result


277 278 279 280 281 282 283
class CacheableSourceFileProcessor(SourceFileProcessor):
  """Utility class that allows caching ProcessFiles() method calls.

  In order to use it, create a ProcessFilesWithoutCaching method that returns
  the files requiring intervention after processing the source files.
  """

284 285
  def __init__(self, use_cache, cache_file_path, file_type):
    self.use_cache = use_cache
286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
    self.cache_file_path = cache_file_path
    self.file_type = file_type

  def GetProcessorWorker(self):
    """Expected to return the worker function to run the formatter."""
    raise NotImplementedError

  def GetProcessorScript(self):
    """Expected to return a tuple
    (path to the format processor script, list of arguments)."""
    raise NotImplementedError

  def GetProcessorCommand(self):
    format_processor, options = self.GetProcessorScript()
    if not format_processor:
      print('Could not find the formatter for % files' % self.file_type)
      sys.exit(1)

    command = [sys.executable, format_processor]
    command.extend(options)

    return command

  def ProcessFiles(self, files):
310 311 312 313
    if self.use_cache:
      cache = FileContentsCache(self.cache_file_path)
      cache.Load()
      files = cache.FilterUnchangedFiles(files)
314 315

    if len(files) == 0:
316
      print('No changes in %s files detected. Skipping check' % self.file_type)
317 318 319 320 321 322
      return True

    files_requiring_changes = self.DetectFilesToChange(files)
    print (
      'Total %s files found that require formatting: %d' %
      (self.file_type, len(files_requiring_changes)))
323 324 325 326 327
    if self.use_cache:
      for file in files_requiring_changes:
        cache.RemoveFile(file)

      cache.Save()
328 329 330 331 332 333 334 335 336 337 338 339 340

    return files_requiring_changes == []

  def DetectFilesToChange(self, files):
    command = self.GetProcessorCommand()
    worker = self.GetProcessorWorker()

    commands = [command + [file] for file in files]
    count = multiprocessing.cpu_count()
    pool = multiprocessing.Pool(count)
    try:
      results = pool.map_async(worker, commands).get(timeout=240)
    except KeyboardInterrupt:
341
      print("\nCaught KeyboardInterrupt, terminating workers.")
342 343 344 345 346 347 348 349 350 351 352 353 354
      pool.terminate()
      pool.join()
      sys.exit(1)

    unformatted_files = []
    for index, errors in enumerate(results):
      if errors > 0:
        unformatted_files.append(files[index])

    return unformatted_files


class CppLintProcessor(CacheableSourceFileProcessor):
355 356 357 358
  """
  Lint files to check that they follow the google code style.
  """

359
  def __init__(self, use_cache=True):
360
    super(CppLintProcessor, self).__init__(
361
      use_cache=use_cache, cache_file_path='.cpplint-cache', file_type='C/C++')
362

363 364 365 366 367
  def IsRelevant(self, name):
    return name.endswith('.cc') or name.endswith('.h')

  def IgnoreDir(self, name):
    return (super(CppLintProcessor, self).IgnoreDir(name)
368
            or (name == 'third_party'))
369

370 371 372 373 374 375 376
  IGNORE_LINT = [
    'export-template.h',
    'flag-definitions.h',
    'gay-fixed.cc',
    'gay-precision.cc',
    'gay-shortest.cc',
  ]
377 378 379 380 381 382 383 384 385 386

  def IgnoreFile(self, name):
    return (super(CppLintProcessor, self).IgnoreFile(name)
              or (name in CppLintProcessor.IGNORE_LINT))

  def GetPathsToSearch(self):
    dirs = ['include', 'samples', 'src']
    test_dirs = ['cctest', 'common', 'fuzzer', 'inspector', 'unittests']
    return dirs + [join('test', dir) for dir in test_dirs]

387 388 389 390 391 392 393
  def GetProcessorWorker(self):
    return CppLintWorker

  def GetProcessorScript(self):
    filters = ','.join([n for n in LINT_RULES])
    arguments = ['--filter', filters]
    for path in [TOOLS_PATH] + os.environ["PATH"].split(os.pathsep):
394
      path = path.strip('"')
395
      cpplint = os.path.join(path, 'cpplint.py')
396
      if os.path.isfile(cpplint):
397
        return cpplint, arguments
398

399
    return None, arguments
400 401


402
class TorqueLintProcessor(CacheableSourceFileProcessor):
403 404 405 406
  """
  Check .tq files to verify they follow the Torque style guide.
  """

407
  def __init__(self, use_cache=True):
408 409 410
    super(TorqueLintProcessor, self).__init__(
      use_cache=use_cache, cache_file_path='.torquelint-cache',
      file_type='Torque')
411

412 413 414 415
  def IsRelevant(self, name):
    return name.endswith('.tq')

  def GetPathsToSearch(self):
416
    dirs = ['third_party', 'src']
417 418 419
    test_dirs = ['torque']
    return dirs + [join('test', dir) for dir in test_dirs]

420 421 422 423
  def GetProcessorWorker(self):
    return TorqueLintWorker

  def GetProcessorScript(self):
424 425
    torque_tools = os.path.join(TOOLS_PATH, "torque")
    torque_path = os.path.join(torque_tools, "format-torque.py")
426
    arguments = ["-il"]
427
    if os.path.isfile(torque_path):
428
      return torque_path, arguments
429

430
    return None, arguments
431

432 433 434 435 436 437 438 439 440 441 442 443 444
class JSLintProcessor(CacheableSourceFileProcessor):
  """
  Check .{m}js file to verify they follow the JS Style guide.
  """
  def __init__(self, use_cache=True):
    super(JSLintProcessor, self).__init__(
      use_cache=use_cache, cache_file_path='.jslint-cache',
      file_type='JavaScript')

  def IsRelevant(self, name):
    return name.endswith('.js') or name.endswith('.mjs')

  def GetPathsToSearch(self):
445
    return ['tools/system-analyzer', 'tools/heap-layout', 'tools/js']
446 447 448 449 450 451 452 453 454 455 456 457 458

  def GetProcessorWorker(self):
    return JSLintWorker

  def GetProcessorScript(self):
    for path in [TOOLS_PATH] + os.environ["PATH"].split(os.pathsep):
      path = path.strip('"')
      clang_format = os.path.join(path, 'clang_format.py')
      if os.path.isfile(clang_format):
        return clang_format, []

    return None, []

459
COPYRIGHT_HEADER_PATTERN = re.compile(
460
    r'Copyright [\d-]*20[0-2][0-9] the V8 project authors. All rights reserved.')
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

class SourceProcessor(SourceFileProcessor):
  """
  Check that all files include a copyright notice and no trailing whitespaces.
  """

  RELEVANT_EXTENSIONS = ['.js', '.cc', '.h', '.py', '.c', '.status', '.tq', '.g4']

  def __init__(self):
    self.runtime_function_call_pattern = self.CreateRuntimeFunctionCallMatcher()

  def CreateRuntimeFunctionCallMatcher(self):
    runtime_h_path = join(dirname(TOOLS_PATH), 'src/runtime/runtime.h')
    pattern = re.compile(r'\s+F\(([^,]*),.*\)')
    runtime_functions = []
    with open(runtime_h_path) as f:
      for line in f.readlines():
        m = pattern.match(line)
        if m:
          runtime_functions.append(m.group(1))
    if len(runtime_functions) < 250:
      print ("Runtime functions list is suspiciously short. "
             "Consider updating the presubmit script.")
      sys.exit(1)
    str = '(\%\s+(' + '|'.join(runtime_functions) + '))[\s\(]'
    return re.compile(str)

  # Overwriting the one in the parent class.
  def FindFilesIn(self, path):
    if os.path.exists(path+'/.git'):
      output = subprocess.Popen('git ls-files --full-name',
                                stdout=PIPE, cwd=path, shell=True)
      result = []
494
      for file in decode(output.stdout.read()).split():
495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552
        for dir_part in os.path.dirname(file).replace(os.sep, '/').split('/'):
          if self.IgnoreDir(dir_part):
            break
        else:
          if (self.IsRelevant(file) and os.path.exists(file)
              and not self.IgnoreFile(file)):
            result.append(join(path, file))
      if output.wait() == 0:
        return result
    return super(SourceProcessor, self).FindFilesIn(path)

  def IsRelevant(self, name):
    for ext in SourceProcessor.RELEVANT_EXTENSIONS:
      if name.endswith(ext):
        return True
    return False

  def GetPathsToSearch(self):
    return ['.']

  def IgnoreDir(self, name):
    return (super(SourceProcessor, self).IgnoreDir(name) or
            name in ('third_party', 'out', 'obj', 'DerivedSources'))

  IGNORE_COPYRIGHTS = ['box2d.js',
                       'cpplint.py',
                       'copy.js',
                       'corrections.js',
                       'crypto.js',
                       'daemon.py',
                       'earley-boyer.js',
                       'fannkuch.js',
                       'fasta.js',
                       'injected-script.cc',
                       'injected-script.h',
                       'libraries.cc',
                       'libraries-empty.cc',
                       'lua_binarytrees.js',
                       'meta-123.js',
                       'memops.js',
                       'poppler.js',
                       'primes.js',
                       'raytrace.js',
                       'regexp-pcre.js',
                       'resources-123.js',
                       'sqlite.js',
                       'sqlite-change-heap.js',
                       'sqlite-pointer-masking.js',
                       'sqlite-safe-heap.js',
                       'v8-debugger-script.h',
                       'v8-inspector-impl.cc',
                       'v8-inspector-impl.h',
                       'v8-runtime-agent-impl.cc',
                       'v8-runtime-agent-impl.h',
                       'gnuplot-4.6.3-emscripten.js',
                       'zlib.js']
  IGNORE_TABS = IGNORE_COPYRIGHTS + ['unicode-test.js', 'html-comments.js']

553 554 555 556
  IGNORE_COPYRIGHTS_DIRECTORIES = [
      "test/test262/local-tests",
      "test/mjsunit/wasm/bulk-memory-spec",
  ]
557 558 559 560 561 562 563 564 565 566 567 568 569 570

  def EndOfDeclaration(self, line):
    return line == "}" or line == "};"

  def StartOfDeclaration(self, line):
    return line.find("//") == 0 or \
           line.find("/*") == 0 or \
           line.find(") {") != -1

  def ProcessContents(self, name, contents):
    result = True
    base = basename(name)
    if not base in SourceProcessor.IGNORE_TABS:
      if '\t' in contents:
571
        print("%s contains tabs" % name)
572 573
        result = False
    if not base in SourceProcessor.IGNORE_COPYRIGHTS and \
574 575
        not any(ignore_dir in name for ignore_dir
                in SourceProcessor.IGNORE_COPYRIGHTS_DIRECTORIES):
576
      if not COPYRIGHT_HEADER_PATTERN.search(contents):
577
        print("%s is missing a correct copyright header." % name)
578 579 580 581 582 583 584 585 586 587 588 589
        result = False
    if ' \n' in contents or contents.endswith(' '):
      line = 0
      lines = []
      parts = contents.split(' \n')
      if not contents.endswith(' '):
        parts.pop()
      for part in parts:
        line += part.count('\n') + 1
        lines.append(str(line))
      linenumbers = ', '.join(lines)
      if len(lines) > 1:
590
        print("%s has trailing whitespaces in lines %s." % (name, linenumbers))
591
      else:
592
        print("%s has trailing whitespaces in line %s." % (name, linenumbers))
593 594
      result = False
    if not contents.endswith('\n') or contents.endswith('\n\n'):
595
      print("%s does not end with a single new line." % name)
596 597
      result = False
    # Sanitize flags for fuzzer.
598
    if (".js" in name or ".mjs" in name) and ("mjsunit" in name or "debugger" in name):
599 600
      match = FLAGS_LINE.search(contents)
      if match:
601
        print("%s Flags should use '-' (not '_')" % name)
602
        result = False
603 604
      if (not "mjsunit/mjsunit.js" in name and
          not "mjsunit/mjsunit_numfuzz.js" in name):
605 606
        if ASSERT_OPTIMIZED_PATTERN.search(contents) and \
            not FLAGS_ENABLE_OPT.search(contents):
607 608
          print("%s Flag --opt should be set if " \
                "assertOptimized() is used" % name)
609 610 611
          result = False
        if ASSERT_UNOPTIMIZED_PATTERN.search(contents) and \
            not FLAGS_NO_ALWAYS_OPT.search(contents):
612 613
          print("%s Flag --no-always-opt should be set if " \
                "assertUnoptimized() is used" % name)
614 615 616 617
          result = False

      match = self.runtime_function_call_pattern.search(contents)
      if match:
618
        print("%s has unexpected spaces in a runtime call '%s'" % (name, match.group(1)))
619 620 621 622 623 624 625 626
        result = False
    return result

  def ProcessFiles(self, files):
    success = True
    violations = 0
    for file in files:
      try:
627
        handle = open(file, "rb")
628
        contents = decode(handle.read(), "ISO-8859-1")
629
        if len(contents) > 0 and not self.ProcessContents(file, contents):
630 631 632 633
          success = False
          violations += 1
      finally:
        handle.close()
634
    print("Total violating files: %s" % violations)
635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733
    return success

def _CheckStatusFileForDuplicateKeys(filepath):
  comma_space_bracket = re.compile(", *]")
  lines = []
  with open(filepath) as f:
    for line in f.readlines():
      # Skip all-comment lines.
      if line.lstrip().startswith("#"): continue
      # Strip away comments at the end of the line.
      comment_start = line.find("#")
      if comment_start != -1:
        line = line[:comment_start]
      line = line.strip()
      # Strip away trailing commas within the line.
      line = comma_space_bracket.sub("]", line)
      if len(line) > 0:
        lines.append(line)

  # Strip away trailing commas at line ends. Ugh.
  for i in range(len(lines) - 1):
    if (lines[i].endswith(",") and len(lines[i + 1]) > 0 and
        lines[i + 1][0] in ("}", "]")):
      lines[i] = lines[i][:-1]

  contents = "\n".join(lines)
  # JSON wants double-quotes.
  contents = contents.replace("'", '"')
  # Fill in keywords (like PASS, SKIP).
  for key in statusfile.KEYWORDS:
    contents = re.sub(r"\b%s\b" % key, "\"%s\"" % key, contents)

  status = {"success": True}
  def check_pairs(pairs):
    keys = {}
    for key, value in pairs:
      if key in keys:
        print("%s: Error: duplicate key %s" % (filepath, key))
        status["success"] = False
      keys[key] = True

  json.loads(contents, object_pairs_hook=check_pairs)
  return status["success"]


class StatusFilesProcessor(SourceFileProcessor):
  """Checks status files for incorrect syntax and duplicate keys."""

  def IsRelevant(self, name):
    # Several changes to files under the test directories could impact status
    # files.
    return True

  def GetPathsToSearch(self):
    return ['test', 'tools/testrunner']

  def ProcessFiles(self, files):
    success = True
    for status_file_path in sorted(self._GetStatusFiles(files)):
      success &= statusfile.PresubmitCheck(status_file_path)
      success &= _CheckStatusFileForDuplicateKeys(status_file_path)
    return success

  def _GetStatusFiles(self, files):
    test_path = join(dirname(TOOLS_PATH), 'test')
    testrunner_path = join(TOOLS_PATH, 'testrunner')
    status_files = set()

    for file_path in files:
      if file_path.startswith(testrunner_path):
        for suitepath in os.listdir(test_path):
          suitename = os.path.basename(suitepath)
          status_file = os.path.join(
              test_path, suitename, suitename + ".status")
          if os.path.exists(status_file):
            status_files.add(status_file)
        return status_files

    for file_path in files:
      if file_path.startswith(test_path):
        # Strip off absolute path prefix pointing to test suites.
        pieces = file_path[len(test_path):].lstrip(os.sep).split(os.sep)
        if pieces:
          # Infer affected status file name. Only care for existing status
          # files. Some directories under "test" don't have any.
          if not os.path.isdir(join(test_path, pieces[0])):
            continue
          status_file = join(test_path, pieces[0], pieces[0] + ".status")
          if not os.path.exists(status_file):
            continue
          status_files.add(status_file)
    return status_files


def CheckDeps(workspace):
  checkdeps_py = join(workspace, 'buildtools', 'checkdeps', 'checkdeps.py')
  return subprocess.call([sys.executable, checkdeps_py, workspace]) == 0


734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757
def FindTests(workspace):
  scripts = []
  # TODO(almuthanna): unskip valid tests when they are properly migrated
  exclude = [
      'tools/clang',
      'tools/unittests/v8_presubmit_test.py',
      'tools/mb/mb_test.py',
      'tools/cppgc/gen_cmake_test.py',
      'tools/ignition/linux_perf_report_test.py',
      'tools/ignition/bytecode_dispatches_report_test.py',
      'tools/ignition/linux_perf_bytecode_annotate_test.py',
  ]
  scripts_without_excluded = []
  for root, dirs, files in os.walk(join(workspace, 'tools')):
    for f in files:
      if f.endswith('_test.py'):
        fullpath = os.path.join(root, f)
        scripts.append(fullpath)
  for script in scripts:
    if not any(exc_dir in script for exc_dir in exclude):
      scripts_without_excluded.append(script)
  return scripts_without_excluded


758 759
def PyTests(workspace):
  result = True
760
  for script in FindTests(workspace):
761
    print('Running ' + script)
762 763
    result &= subprocess.call(
        [sys.executable, script], stdout=subprocess.PIPE) == 0
764

765 766 767 768 769 770 771
  return result


def GetOptions():
  result = optparse.OptionParser()
  result.add_option('--no-lint', help="Do not run cpplint", default=False,
                    action="store_true")
772 773
  result.add_option('--no-linter-cache', help="Do not cache linter results",
                    default=False, action="store_true")
774

775 776 777 778 779 780 781 782
  return result


def Main():
  workspace = abspath(join(dirname(sys.argv[0]), '..'))
  parser = GetOptions()
  (options, args) = parser.parse_args()
  success = True
783
  print("Running checkdeps...")
784
  success &= CheckDeps(workspace)
785
  use_linter_cache = not options.no_linter_cache
786
  if not options.no_lint:
787
    print("Running C++ lint check...")
788 789
    success &= CppLintProcessor(use_cache=use_linter_cache).RunOnPath(workspace)

790 791 792
  print("Running Torque formatting check...")
  success &= TorqueLintProcessor(use_cache=use_linter_cache).RunOnPath(
    workspace)
793 794 795
  print("Running JavaScript formatting check...")
  success &= JSLintProcessor(use_cache=use_linter_cache).RunOnPath(
    workspace)
796 797
  print("Running copyright header, trailing whitespaces and " \
        "two empty lines between declarations check...")
798
  success &= SourceProcessor().RunOnPath(workspace)
799
  print("Running status-files check...")
800
  success &= StatusFilesProcessor().RunOnPath(workspace)
801
  print("Running python tests...")
802 803 804 805 806 807 808 809 810
  success &= PyTests(workspace)
  if success:
    return 0
  else:
    return 1


if __name__ == '__main__':
  sys.exit(Main())