def main():
    args = _parse_args()
    test_paths = [
        test for pattern in args.tests for test in glob.glob(pattern)
    ]
    for test_path in test_paths:
        sys.stderr.write('Test: {}\n'.format(test_path))

        # Call this per test. By default each warning will only be written once
        # per source location. Reset the warning filter so that now each warning
        # will be written once per source location per test.
        _configure_warnings(args)

        if not os.path.isfile(test_path):
            raise Error('could not find test file: {}'.format(test_path))

        with open(test_path) as f:
            input_lines = [l.rstrip() for l in f]

        run_lines = common.find_run_lines(test_path, input_lines)
        run_infos = _get_run_infos(run_lines, args)
        common_prefix, prefix_pad = _get_useful_prefix_info(run_infos)
        block_infos = _get_block_infos(run_infos, test_path, args,
                                       common_prefix)
        _write_output(test_path, input_lines, run_infos, block_infos, args,
                      common_prefix, prefix_pad)

    return 0
Esempio n. 2
0
def main():
    args = config()
    script_name = os.path.basename(__file__)
    autogenerated_note = (ADVERT + 'utils/' + script_name)

    for filename in args.tests:
        with open(filename) as f:
            input_lines = [l.rstrip() for l in f]

        first_line = input_lines[0] if input_lines else ""
        if 'autogenerated' in first_line and script_name not in first_line:
            common.warn(
                "Skipping test which wasn't autogenerated by " + script_name,
                filename)
            continue

        if args.update_only:
            if not first_line or 'autogenerated' not in first_line:
                common.warn("Skipping test which isn't autogenerated: " +
                            filename)
                continue

        # Extract RUN lines.
        run_lines = common.find_run_lines(filename, input_lines)

        # Build a list of clang command lines and check prefixes from RUN lines.
        run_list = []
        line2spell_and_mangled_list = collections.defaultdict(list)
        for l in run_lines:
            commands = [cmd.strip() for cmd in l.split('|')]

            triple_in_cmd = None
            m = common.TRIPLE_ARG_RE.search(commands[0])
            if m:
                triple_in_cmd = m.groups()[0]

            # Apply %clang substitution rule, replace %s by `filename`, and append args.clang_args
            clang_args = shlex.split(commands[0])
            if clang_args[0] not in SUBST:
                print('WARNING: Skipping non-clang RUN line: ' + l,
                      file=sys.stderr)
                continue
            clang_args[0:1] = SUBST[clang_args[0]]
            clang_args = [filename if i == '%s' else i
                          for i in clang_args] + args.clang_args

            # Permit piping the output through opt
            if not (len(commands) == 2 or
                    (len(commands) == 3 and commands[1].startswith('opt'))):
                print('WARNING: Skipping non-clang RUN line: ' + l,
                      file=sys.stderr)

            # Extract -check-prefix in FileCheck args
            filecheck_cmd = commands[-1]
            common.verify_filecheck_prefixes(filecheck_cmd)
            if not filecheck_cmd.startswith('FileCheck '):
                print('WARNING: Skipping non-FileChecked RUN line: ' + l,
                      file=sys.stderr)
                continue
            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']
            run_list.append(
                (check_prefixes, clang_args, commands[1:-1], triple_in_cmd))

        # Strip CHECK lines which are in `prefix_set`, update test file.
        prefix_set = set([prefix for p in run_list for prefix in p[0]])
        input_lines = []
        with open(filename, 'r+') as f:
            for line in f:
                m = common.CHECK_RE.match(line)
                if not (m and m.group(1) in prefix_set) and line != '//\n':
                    input_lines.append(line)
            f.seek(0)
            f.writelines(input_lines)
            f.truncate()

        # Execute clang, generate LLVM IR, and extract functions.
        func_dict = {}
        for p in run_list:
            prefixes = p[0]
            for prefix in prefixes:
                func_dict.update({prefix: dict()})
        for prefixes, clang_args, extra_commands, triple_in_cmd in run_list:
            common.debug('Extracted clang cmd: clang {}'.format(clang_args))
            common.debug('Extracted FileCheck prefixes: {}'.format(prefixes))

            get_function_body(args, filename, clang_args, extra_commands,
                              prefixes, triple_in_cmd, func_dict)

            # Invoke clang -Xclang -ast-dump=json to get mapping from start lines to
            # mangled names. Forward all clang args for now.
            for k, v in get_line2spell_and_mangled(args, clang_args).items():
                line2spell_and_mangled_list[k].append(v)

        output_lines = [autogenerated_note]
        for idx, line in enumerate(input_lines):
            # Discard any previous script advertising.
            if line.startswith(ADVERT):
                continue
            if idx in line2spell_and_mangled_list:
                added = set()
                for spell, mangled in line2spell_and_mangled_list[idx]:
                    # One line may contain multiple function declarations.
                    # Skip if the mangled name has been added before.
                    # The line number may come from an included file,
                    # we simply require the spelling name to appear on the line
                    # to exclude functions from other files.
                    if mangled in added or spell not in line:
                        continue
                    if args.functions is None or any(
                            re.search(regex, spell)
                            for regex in args.functions):
                        if added:
                            output_lines.append('//')
                        added.add(mangled)
                        common.add_ir_checks(output_lines, '//', run_list,
                                             func_dict, mangled, False,
                                             args.function_signature)
            output_lines.append(line.rstrip('\n'))

        # Update the test file.
        with open(filename, 'w') as f:
            for line in output_lines:
                f.write(line + '\n')

    return 0
Esempio n. 3
0
def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        '--llc-binary',
        default='llc',
        help='The "llc" binary to use to generate the test case')
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument(
        '--extra_scrub',
        action='store_true',
        help=
        'Always use additional regex to further reduce diffs between various subtargets'
    )
    parser.add_argument(
        '--x86_scrub_rip',
        action='store_true',
        default=True,
        help=
        'Use more regex for x86 matching to reduce diffs between various subtargets'
    )
    parser.add_argument('--no_x86_scrub_rip',
                        action='store_false',
                        dest='x86_scrub_rip')
    parser.add_argument('tests', nargs='+')
    args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)

    test_paths = [
        test for pattern in args.tests for test in glob.glob(pattern)
    ]
    for test in test_paths:
        with open(test) as f:
            input_lines = [l.rstrip() for l in f]

        first_line = input_lines[0] if input_lines else ""
        if 'autogenerated' in first_line and script_name not in first_line:
            common.warn(
                "Skipping test which wasn't autogenerated by " + script_name,
                test)
            continue

        if args.update_only:
            if not first_line or 'autogenerated' not in first_line:
                common.warn("Skipping test which isn't autogenerated: " + test)
                continue

        triple_in_ir = None
        for l in input_lines:
            m = common.TRIPLE_IR_RE.match(l)
            if m:
                triple_in_ir = m.groups()[0]
                break

        run_lines = common.find_run_lines(test, input_lines)
        run_list = []
        for l in run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            commands = [cmd.strip() for cmd in l.split('|', 1)]
            llc_cmd = commands[0]
            llc_tool = llc_cmd.split(' ')[0]

            triple_in_cmd = None
            m = common.TRIPLE_ARG_RE.search(llc_cmd)
            if m:
                triple_in_cmd = m.groups()[0]

            march_in_cmd = None
            m = common.MARCH_ARG_RE.search(llc_cmd)
            if m:
                march_in_cmd = m.groups()[0]

            filecheck_cmd = ''
            if len(commands) > 1:
                filecheck_cmd = commands[1]
            common.verify_filecheck_prefixes(filecheck_cmd)
            if llc_tool != 'llc':
                common.warn('Skipping non-llc RUN line: ' + l)
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            llc_cmd_args = llc_cmd[len(llc_tool):].strip()
            llc_cmd_args = llc_cmd_args.replace('< %s',
                                                '').replace('%s', '').strip()
            if test.endswith('.mir'):
                llc_cmd_args += ' -x mir'
            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            run_list.append(
                (check_prefixes, llc_cmd_args, triple_in_cmd, march_in_cmd))

        if test.endswith('.mir'):
            comment_sym = '#'
            check_indent = '  '
        else:
            comment_sym = ';'
            check_indent = ''
        autogenerated_note = (comment_sym + ADVERT + 'utils/' + script_name)

        func_dict = {}
        for p in run_list:
            prefixes = p[0]
            for prefix in prefixes:
                func_dict.update({prefix: dict()})
        for prefixes, llc_args, triple_in_cmd, march_in_cmd in run_list:
            common.debug('Extracted LLC cmd:', llc_tool, llc_args)
            common.debug('Extracted FileCheck prefixes:', str(prefixes))

            raw_tool_output = common.invoke_tool(args.llc_binary, llc_args,
                                                 test)
            triple = triple_in_cmd or triple_in_ir
            if not triple:
                triple = asm.get_triple_from_march(march_in_cmd)

            asm.build_function_body_dictionary_for_triple(
                args, raw_tool_output, triple, prefixes, func_dict)

        is_in_function = False
        is_in_function_start = False
        func_name = None
        prefix_set = set([prefix for p in run_list for prefix in p[0]])
        common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
        output_lines = []
        output_lines.append(autogenerated_note)

        for input_line in input_lines:
            if is_in_function_start:
                if input_line == '':
                    continue
                if input_line.lstrip().startswith(';'):
                    m = common.CHECK_RE.match(input_line)
                    if not m or m.group(1) not in prefix_set:
                        output_lines.append(input_line)
                        continue

                # Print out the various check lines here.
                asm.add_asm_checks(output_lines, check_indent + ';', run_list,
                                   func_dict, func_name)
                is_in_function_start = False

            if is_in_function:
                if common.should_add_line_to_output(input_line, prefix_set):
                    # This input line of the function body will go as-is into the output.
                    output_lines.append(input_line)
                else:
                    continue
                if input_line.strip() == '}':
                    is_in_function = False
                continue

            # Discard any previous script advertising.
            if input_line.startswith(comment_sym + ADVERT):
                continue

            # If it's outside a function, it just gets copied to the output.
            output_lines.append(input_line)

            m = common.IR_FUNCTION_RE.match(input_line)
            if not m:
                continue
            func_name = m.group(1)
            if args.function is not None and func_name != args.function:
                # When filtering on a specific function, skip all others.
                continue
            is_in_function = is_in_function_start = True

        common.debug('Writing %d lines to %s...' % (len(output_lines), test))

        with open(test, 'wb') as f:
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])
def main():
    from argparse import RawTextHelpFormatter
    parser = argparse.ArgumentParser(description=__doc__,
                                     formatter_class=RawTextHelpFormatter)
    parser.add_argument('--opt-binary',
                        default='opt',
                        help='The opt binary used to generate the test case')
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument('tests', nargs='+')
    args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)
    autogenerated_note = (ADVERT + 'utils/' + script_name)

    opt_basename = os.path.basename(args.opt_binary)
    if (opt_basename != "opt"):
        common.error('Unexpected opt name: ' + opt_basename)
        sys.exit(1)

    test_paths = [
        test for pattern in args.tests for test in glob.glob(pattern)
    ]
    for test in test_paths:
        with open(test) as f:
            input_lines = [l.rstrip() for l in f]

        first_line = input_lines[0] if input_lines else ""
        if 'autogenerated' in first_line and script_name not in first_line:
            common.warn("Skipping test which wasn't autogenerated by " +
                        script_name + ": " + test)
            continue

        if args.update_only:
            if not first_line or 'autogenerated' not in first_line:
                common.warn("Skipping test which isn't autogenerated: " + test)
                continue

        run_lines = common.find_run_lines(test, input_lines)
        prefix_list = []
        for l in run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            (tool_cmd,
             filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)])
            common.verify_filecheck_prefixes(filecheck_cmd)

            if not tool_cmd.startswith(opt_basename + ' '):
                common.warn('WSkipping non-%s RUN line: %s' %
                            (opt_basename, l))
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            tool_cmd_args = tool_cmd[len(opt_basename):].strip()
            tool_cmd_args = tool_cmd_args.replace('< %s',
                                                  '').replace('%s',
                                                              '').strip()

            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            prefix_list.append((check_prefixes, tool_cmd_args))

        func_dict = {}
        func_order = {}
        for prefixes, _ in prefix_list:
            for prefix in prefixes:
                func_dict.update({prefix: dict()})
                func_order.update({prefix: []})
        for prefixes, opt_args in prefix_list:
            common.debug('Extracted opt cmd:',
                         opt_basename,
                         opt_args,
                         file=sys.stderr)
            common.debug('Extracted FileCheck prefixes:',
                         str(prefixes),
                         file=sys.stderr)

            raw_tool_outputs = common.invoke_tool(args.opt_binary, opt_args,
                                                  test)

            # Split analysis outputs by "Printing analysis " declarations.
            for raw_tool_output in re.split(r'Printing analysis ',
                                            raw_tool_outputs):
                common.build_function_body_dictionary(
                    common.ANALYZE_FUNCTION_RE, common.scrub_body, [],
                    raw_tool_output, prefixes, func_dict, func_order,
                    args.verbose, False, False)

        is_in_function = False
        is_in_function_start = False
        prefix_set = set(
            [prefix for prefixes, _ in prefix_list for prefix in prefixes])
        common.debug('Rewriting FileCheck prefixes:',
                     str(prefix_set),
                     file=sys.stderr)
        output_lines = []
        output_lines.append(autogenerated_note)

        for input_line in input_lines:
            if is_in_function_start:
                if input_line == '':
                    continue
                if input_line.lstrip().startswith(';'):
                    m = common.CHECK_RE.match(input_line)
                    if not m or m.group(1) not in prefix_set:
                        output_lines.append(input_line)
                        continue

                # Print out the various check lines here.
                common.add_analyze_checks(output_lines, ';', prefix_list,
                                          func_dict, func_name)
                is_in_function_start = False

            if is_in_function:
                if common.should_add_line_to_output(input_line, prefix_set):
                    # This input line of the function body will go as-is into the output.
                    # Except make leading whitespace uniform: 2 spaces.
                    input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub(
                        r'  ', input_line)
                    output_lines.append(input_line)
                else:
                    continue
                if input_line.strip() == '}':
                    is_in_function = False
                continue

            # Discard any previous script advertising.
            if input_line.startswith(ADVERT):
                continue

            # If it's outside a function, it just gets copied to the output.
            output_lines.append(input_line)

            m = common.IR_FUNCTION_RE.match(input_line)
            if not m:
                continue
            func_name = m.group(1)
            if args.function is not None and func_name != args.function:
                # When filtering on a specific function, skip all others.
                continue
            is_in_function = is_in_function_start = True

        common.debug('Writing %d lines to %s...' % (len(output_lines), test))

        with open(test, 'wb') as f:
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])
Esempio n. 5
0
def main():
  from argparse import RawTextHelpFormatter
  parser = argparse.ArgumentParser(description=__doc__, formatter_class=RawTextHelpFormatter)
  parser.add_argument('--opt-binary', default='opt',
                      help='The opt binary used to generate the test case')
  parser.add_argument(
      '--function', help='The function in the test file to update')
  parser.add_argument('-p', '--preserve-names', action='store_true',
                      help='Do not scrub IR names')
  parser.add_argument('--function-signature', action='store_true',
                      help='Keep function signature information around for the check line')
  parser.add_argument('--scrub-attributes', action='store_true',
                      help='Remove attribute annotations (#0) from the end of check line')
  parser.add_argument('--enable', action='store_true', dest='enabled', default=True,
                      help='Activate CHECK line generation from this point forward')
  parser.add_argument('--disable', action='store_false', dest='enabled',
                      help='Deactivate CHECK line generation from this point forward')
  parser.add_argument('tests', nargs='+')
  args = common.parse_commandline_args(parser)

  script_name = os.path.basename(__file__)
  autogenerated_note = (ADVERT + 'utils/' + script_name)

  opt_basename = os.path.basename(args.opt_binary)
  if not re.match(r'^opt(-\d+)?$', opt_basename):
    common.error('Unexpected opt name: ' + opt_basename)
    sys.exit(1)
  opt_basename = 'opt'

  for test in args.tests:
    if not glob.glob(test):
      common.warn("Test file pattern '%s' was not found. Ignoring it." % (test,))
      continue

  # On Windows we must expand the patterns ourselves.
  test_paths = [test for pattern in args.tests for test in glob.glob(pattern)]
  for test in test_paths:
    argv = sys.argv[:]
    args = parser.parse_args()
    with open(test) as f:
      input_lines = [l.rstrip() for l in f]

    first_line = input_lines[0] if input_lines else ""
    if 'autogenerated' in first_line and script_name not in first_line:
      common.warn("Skipping test which wasn't autogenerated by " + script_name, test)
      continue
    if first_line and 'autogenerated' in first_line:
      args, argv = common.check_for_command(first_line, parser, args, argv)
    test_autogenerated_note = autogenerated_note + common.get_autogennote_suffix(parser, args)

    if args.update_only:
      if not first_line or 'autogenerated' not in first_line:
        common.warn("Skipping test which isn't autogenerated: " + test)
        continue

    run_lines = common.find_run_lines(test, input_lines)

    # If requested we scrub trailing attribute annotations, e.g., '#0', together with whitespaces
    if args.scrub_attributes:
      common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_AND_ATTRIBUTES_RE
    else:
      common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_RE

    prefix_list = []
    for l in run_lines:
      if '|' not in l:
        common.warn('Skipping unparseable RUN line: ' + l)
        continue

      (tool_cmd, filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)])
      common.verify_filecheck_prefixes(filecheck_cmd)
      if not tool_cmd.startswith(opt_basename + ' '):
        common.warn('Skipping non-%s RUN line: %s' % (opt_basename, l))
        continue

      if not filecheck_cmd.startswith('FileCheck '):
        common.warn('Skipping non-FileChecked RUN line: ' + l)
        continue

      tool_cmd_args = tool_cmd[len(opt_basename):].strip()
      tool_cmd_args = tool_cmd_args.replace('< %s', '').replace('%s', '').strip()

      check_prefixes = [item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                               for item in m.group(1).split(',')]
      if not check_prefixes:
        check_prefixes = ['CHECK']

      # FIXME: We should use multiple check prefixes to common check lines. For
      # now, we just ignore all but the last.
      prefix_list.append((check_prefixes, tool_cmd_args))

    func_dict = {}
    for prefixes, _ in prefix_list:
      for prefix in prefixes:
        func_dict.update({prefix: dict()})
    for prefixes, opt_args in prefix_list:
      common.debug('Extracted opt cmd: ' + opt_basename + ' ' + opt_args)
      common.debug('Extracted FileCheck prefixes: ' + str(prefixes))

      raw_tool_output = common.invoke_tool(args.opt_binary, opt_args, test)
      common.build_function_body_dictionary(
              common.OPT_FUNCTION_RE, common.scrub_body, [],
              raw_tool_output, prefixes, func_dict, args.verbose,
              args.function_signature)

    is_in_function = False
    is_in_function_start = False
    prefix_set = set([prefix for prefixes, _ in prefix_list for prefix in prefixes])
    common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
    output_lines = []
    output_lines.append(test_autogenerated_note)

    for input_line in input_lines:
      # Discard any previous script advertising.
      if input_line.startswith(ADVERT):
        continue

      args, argv = common.check_for_command(input_line, parser, args, argv)
      if not args.enabled:
          output_lines.append(input_line)
          continue
      if is_in_function_start:
        if input_line == '':
          continue
        if input_line.lstrip().startswith(';'):
          m = common.CHECK_RE.match(input_line)
          if not m or m.group(1) not in prefix_set:
            output_lines.append(input_line)
            continue

        # Print out the various check lines here.
        common.add_ir_checks(output_lines, ';', prefix_list, func_dict,
                             func_name, args.preserve_names, args.function_signature)
        is_in_function_start = False

      if is_in_function:
        if common.should_add_line_to_output(input_line, prefix_set):
          # This input line of the function body will go as-is into the output.
          # Except make leading whitespace uniform: 2 spaces.
          input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub(r'  ', input_line)
          output_lines.append(input_line)
        else:
          continue
        if input_line.strip() == '}':
          is_in_function = False
        continue

      # If it's outside a function, it just gets copied to the output.
      output_lines.append(input_line)

      m = IR_FUNCTION_RE.match(input_line)
      if not m:
        continue
      func_name = m.group(1)
      if args.function is not None and func_name != args.function:
        # When filtering on a specific function, skip all others.
        continue
      is_in_function = is_in_function_start = True

    common.debug('Writing %d lines to %s...' % (len(output_lines), test))

    with open(test, 'wb') as f:
      f.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines])
def update_test_file(args, test):
    with open(test) as fd:
        input_lines = [l.rstrip() for l in fd]

    script_name = os.path.basename(__file__)
    first_line = input_lines[0] if input_lines else ""
    if 'autogenerated' in first_line and script_name not in first_line:
        common.warn("Skipping test which wasn't autogenerated by " +
                    script_name + ": " + test)
        return

    if args.update_only:
        if not first_line or 'autogenerated' not in first_line:
            common.warn("Skipping test which isn't autogenerated: " + test)
            return

    triple_in_ir = find_triple_in_ir(input_lines, args.verbose)
    run_lines = common.find_run_lines(test, input_lines)
    run_list, common_prefixes = build_run_list(test, run_lines, args.verbose)

    simple_functions = find_functions_with_one_bb(input_lines, args.verbose)

    func_dict = {}
    for run in run_list:
        for prefix in run.prefixes:
            func_dict.update({prefix: dict()})
    for prefixes, llc_args, triple_in_cmd in run_list:
        log('Extracted LLC cmd: llc {}'.format(llc_args), args.verbose)
        log('Extracted FileCheck prefixes: {}'.format(prefixes), args.verbose)

        raw_tool_output = args.llc(llc_args, test)
        if not triple_in_cmd and not triple_in_ir:
            common.warn('No triple found: skipping file', test_file=test)
            return

        build_function_body_dictionary(test, raw_tool_output, triple_in_cmd
                                       or triple_in_ir, prefixes, func_dict,
                                       args.verbose)

    state = 'toplevel'
    func_name = None
    prefix_set = set([prefix for run in run_list for prefix in run.prefixes])
    log('Rewriting FileCheck prefixes: {}'.format(prefix_set), args.verbose)

    if args.remove_common_prefixes:
        prefix_set.update(common_prefixes)
    elif common_prefixes:
        common.warn('Ignoring common prefixes: {}'.format(common_prefixes),
                    test_file=test)

    comment_char = '#' if test.endswith('.mir') else ';'
    autogenerated_note = ('{} NOTE: Assertions have been autogenerated by '
                          'utils/{}'.format(comment_char, script_name))
    output_lines = []
    output_lines.append(autogenerated_note)

    for input_line in input_lines:
        if input_line == autogenerated_note:
            continue

        if state == 'toplevel':
            m = IR_FUNC_NAME_RE.match(input_line)
            if m:
                state = 'ir function prefix'
                func_name = m.group('func')
            if input_line.rstrip('| \r\n') == '---':
                state = 'document'
            output_lines.append(input_line)
        elif state == 'document':
            m = MIR_FUNC_NAME_RE.match(input_line)
            if m:
                state = 'mir function metadata'
                func_name = m.group('func')
            if input_line.strip() == '...':
                state = 'toplevel'
                func_name = None
            if should_add_line_to_output(input_line, prefix_set):
                output_lines.append(input_line)
        elif state == 'mir function metadata':
            if should_add_line_to_output(input_line, prefix_set):
                output_lines.append(input_line)
            m = MIR_BODY_BEGIN_RE.match(input_line)
            if m:
                if func_name in simple_functions:
                    # If there's only one block, put the checks inside it
                    state = 'mir function prefix'
                    continue
                state = 'mir function body'
                add_checks_for_function(test,
                                        output_lines,
                                        run_list,
                                        func_dict,
                                        func_name,
                                        single_bb=False,
                                        verbose=args.verbose)
        elif state == 'mir function prefix':
            m = MIR_PREFIX_DATA_RE.match(input_line)
            if not m:
                state = 'mir function body'
                add_checks_for_function(test,
                                        output_lines,
                                        run_list,
                                        func_dict,
                                        func_name,
                                        single_bb=True,
                                        verbose=args.verbose)

            if should_add_line_to_output(input_line, prefix_set):
                output_lines.append(input_line)
        elif state == 'mir function body':
            if input_line.strip() == '...':
                state = 'toplevel'
                func_name = None
            if should_add_line_to_output(input_line, prefix_set):
                output_lines.append(input_line)
        elif state == 'ir function prefix':
            m = IR_PREFIX_DATA_RE.match(input_line)
            if not m:
                state = 'ir function body'
                add_checks_for_function(test,
                                        output_lines,
                                        run_list,
                                        func_dict,
                                        func_name,
                                        single_bb=False,
                                        verbose=args.verbose)

            if should_add_line_to_output(input_line, prefix_set):
                output_lines.append(input_line)
        elif state == 'ir function body':
            if input_line.strip() == '}':
                state = 'toplevel'
                func_name = None
            if should_add_line_to_output(input_line, prefix_set):
                output_lines.append(input_line)

    log('Writing {} lines to {}...'.format(len(output_lines), test),
        args.verbose)

    with open(test, 'wb') as fd:
        fd.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines])