milvus-io / milvus

    r'(?:.*stream\s*&\s*' + _RE_PATTERN_IDENT + r')')

def CheckLanguage(filename, clean_lines, linenum, file_extension,

                  include_state, nesting_state, error):

  """Checks rules from the 'C++ language rules' section of cppguide.html.

  Some of these rules are hard to test (function overloading, using

  uint32 inappropriately), but we do the best we can.

  Args:

    filename: The name of the current file.

    clean_lines: A CleansedLines instance containing the file.

    linenum: The number of the line to check.

    file_extension: The extension (without the dot) of the filename.

    include_state: An _IncludeState instance in which the headers are inserted.

    nesting_state: A NestingState instance which maintains information about

                   the current stack of nested blocks being parsed.

    error: The function to call with any errors found.

  """

  # If the line is empty or consists of entirely a comment, no need to

  # check it.

  line = clean_lines.elided[linenum]

  if not line:

    return

  match = _RE_PATTERN_INCLUDE.search(line)

  if match:

    CheckIncludeLine(filename, clean_lines, linenum, include_state, error)

    return

  # Reset include state across preprocessor directives.  This is meant

  # to silence warnings for conditional includes.

  match = Match(r'^\s*#\s*(if|ifdef|ifndef|elif|else|endif)\b', line)

  if match:

    include_state.ResetSection(match.group(1))

  # Perform other checks now that we are sure that this is not an include line

  CheckCasts(filename, clean_lines, linenum, error)

  CheckGlobalStatic(filename, clean_lines, linenum, error)

  CheckPrintf(filename, clean_lines, linenum, error)

  if file_extension in GetHeaderExtensions():

    # TODO(unknown): check that 1-arg constructors are explicit.

    #                How to tell it's a constructor?

    #                (handled in CheckForNonStandardConstructs for now)

    # TODO(unknown): check that classes declare or disable copy/assign

    #                (level 1 error)

    pass

  # Check if people are using the verboten C basic types.  The only exception

  # we regularly allow is "unsigned short port" for port.

  if Search(r'\bshort port\b', line):

    if not Search(r'\bunsigned short port\b', line):

      error(filename, linenum, 'runtime/int', 4,

            'Use "unsigned short" for ports, not "short"')

  else:

    match = Search(r'\b(short|long(?! +double)|long long)\b', line)

    if match:

      error(filename, linenum, 'runtime/int', 4,

            'Use int16/int64/etc, rather than the C type %s' % match.group(1))

  # Check if some verboten operator overloading is going on

  # TODO(unknown): catch out-of-line unary operator&:

  #   class X {};

  #   int operator&(const X& x) { return 42; }  // unary operator&

  # The trick is it's hard to tell apart from binary operator&:

  #   class Y { int operator&(const Y& x) { return 23; } }; // binary operator&

  if Search(r'\boperator\s*&\s*\(\s*\)', line):

    error(filename, linenum, 'runtime/operator', 4,

          'Unary operator& is dangerous.  Do not use it.')

  # Check for suspicious usage of "if" like

  # } if (a == b) {

  if Search(r'\}\s*if\s*\(', line):

    error(filename, linenum, 'readability/braces', 4,

          'Did you mean "else if"? If not, start a new line for "if".')

  # Check for potential format string bugs like printf(foo).

  # We constrain the pattern not to pick things like DocidForPrintf(foo).

  # Not perfect but it can catch printf(foo.c_str()) and printf(foo->c_str())

  # TODO(unknown): Catch the following case. Need to change the calling

  # convention of the whole function to process multiple line to handle it.

  #   printf(

  #       boy_this_is_a_really_long_variable_that_cannot_fit_on_the_prev_line);

  printf_args = _GetTextInside(line, r'(?i)\b(string)?printf\s*\(')

  if printf_args:

    match = Match(r'([\w.\->()]+)$', printf_args)

    if match and match.group(1) != '__VA_ARGS__':

      function_name = re.search(r'\b((?:string)?printf)\s*\(',

                                line, re.I).group(1)

      error(filename, linenum, 'runtime/printf', 4,

            'Potential format string bug. Do %s("%%s", %s) instead.'

            % (function_name, match.group(1)))

  # Check for potential memset bugs like memset(buf, sizeof(buf), 0).

  match = Search(r'memset\s*\(([^,]*),\s*([^,]*),\s*0\s*\)', line)

  if match and not Match(r"^''|-?[0-9]+|0x[0-9A-Fa-f]$", match.group(2)):

    error(filename, linenum, 'runtime/memset', 4,

          'Did you mean "memset(%s, 0, %s)"?'

          % (match.group(1), match.group(2)))

  if Search(r'\busing namespace\b', line):

    if Search(r'\bliterals\b', line):

      error(filename, linenum, 'build/namespaces_literals', 5,

            'Do not use namespace using-directives.  '

            'Use using-declarations instead.')

    else:

      error(filename, linenum, 'build/namespaces', 5,

            'Do not use namespace using-directives.  '

            'Use using-declarations instead.')

  # Detect variable-length arrays.

  match = Match(r'\s*(.+::)?(\w+) [a-z]\w*\[(.+)];', line)

  if (match and match.group(2) != 'return' and match.group(2) != 'delete' and

      match.group(3).find(']') == -1):

    # Split the size using space and arithmetic operators as delimiters.

    # If any of the resulting tokens are not compile time constants then

    # report the error.

    tokens = re.split(r'\s|\+|\-|\*|\/|<<|>>]', match.group(3))

    is_const = True

    skip_next = False

    for tok in tokens:

      if skip_next:

        skip_next = False

        continue

      if Search(r'sizeof\(.+\)', tok): continue

      if Search(r'arraysize\(\w+\)', tok): continue

      tok = tok.lstrip('(')

      tok = tok.rstrip(')')

      if not tok: continue

      if Match(r'\d+', tok): continue

      if Match(r'0[xX][0-9a-fA-F]+', tok): continue

      if Match(r'k[A-Z0-9]\w*', tok): continue

      if Match(r'(.+::)?k[A-Z0-9]\w*', tok): continue

      if Match(r'(.+::)?[A-Z][A-Z0-9_]*', tok): continue

      # A catch all for tricky sizeof cases, including 'sizeof expression',

      # 'sizeof(*type)', 'sizeof(const type)', 'sizeof(struct StructName)'

      # requires skipping the next token because we split on ' ' and '*'.

      if tok.startswith('sizeof'):

        skip_next = True

        continue

      is_const = False

      break

    if not is_const:

      error(filename, linenum, 'runtime/arrays', 1,

            'Do not use variable-length arrays.  Use an appropriately named '

            "('k' followed by CamelCase) compile-time constant for the size.")

  # Check for use of unnamed namespaces in header files.  Registration

  # macros are typically OK, so we allow use of "namespace {" on lines

  # that end with backslashes.

  if (file_extension in GetHeaderExtensions()

      and Search(r'\bnamespace\s*{', line)

      and line[-1] != '\\'):

    error(filename, linenum, 'build/namespaces', 4,

          'Do not use unnamed namespaces in header files.  See '

          'https://google-styleguide.googlecode.com/svn/trunk/cppguide.xml#Namespaces'

          ' for more information.')

    r'(?:.*stream\s*&\s*' + _RE_PATTERN_IDENT + r')')

def CheckLanguage(filename, clean_lines, linenum, file_extension,

                  include_state, nesting_state, error):

  """Checks rules from the 'C++ language rules' section of cppguide.html.

  Some of these rules are hard to test (function overloading, using

  uint32 inappropriately), but we do the best we can.

  Args:

    filename: The name of the current file.

    clean_lines: A CleansedLines instance containing the file.

    linenum: The number of the line to check.

    file_extension: The extension (without the dot) of the filename.

    include_state: An _IncludeState instance in which the headers are inserted.

    nesting_state: A NestingState instance which maintains information about

                   the current stack of nested blocks being parsed.

    error: The function to call with any errors found.

  """

  # If the line is empty or consists of entirely a comment, no need to

  # check it.

  line = clean_lines.elided[linenum]

  if not line:

    return

  match = _RE_PATTERN_INCLUDE.search(line)

  if match:

    CheckIncludeLine(filename, clean_lines, linenum, include_state, error)

    return

  # Reset include state across preprocessor directives.  This is meant

  # to silence warnings for conditional includes.

  match = Match(r'^\s*#\s*(if|ifdef|ifndef|elif|else|endif)\b', line)

  if match:

    include_state.ResetSection(match.group(1))

  # Perform other checks now that we are sure that this is not an include line

  CheckCasts(filename, clean_lines, linenum, error)

  CheckGlobalStatic(filename, clean_lines, linenum, error)

  CheckPrintf(filename, clean_lines, linenum, error)

  if file_extension in GetHeaderExtensions():

    # TODO(unknown): check that 1-arg constructors are explicit.

    #                How to tell it's a constructor?

    #                (handled in CheckForNonStandardConstructs for now)

    # TODO(unknown): check that classes declare or disable copy/assign

    #                (level 1 error)

    pass

  # Check if people are using the verboten C basic types.  The only exception

  # we regularly allow is "unsigned short port" for port.

  if Search(r'\bshort port\b', line):

    if not Search(r'\bunsigned short port\b', line):

      error(filename, linenum, 'runtime/int', 4,

            'Use "unsigned short" for ports, not "short"')

  else:

    match = Search(r'\b(short|long(?! +double)|long long)\b', line)

    if match:

      error(filename, linenum, 'runtime/int', 4,

            'Use int16/int64/etc, rather than the C type %s' % match.group(1))

  # Check if some verboten operator overloading is going on

  # TODO(unknown): catch out-of-line unary operator&:

  #   class X {};

  #   int operator&(const X& x) { return 42; }  // unary operator&

  # The trick is it's hard to tell apart from binary operator&:

  #   class Y { int operator&(const Y& x) { return 23; } }; // binary operator&

  if Search(r'\boperator\s*&\s*\(\s*\)', line):

    error(filename, linenum, 'runtime/operator', 4,

          'Unary operator& is dangerous.  Do not use it.')

  # Check for suspicious usage of "if" like

  # } if (a == b) {

  if Search(r'\}\s*if\s*\(', line):

    error(filename, linenum, 'readability/braces', 4,

          'Did you mean "else if"? If not, start a new line for "if".')

  # Check for potential format string bugs like printf(foo).

  # We constrain the pattern not to pick things like DocidForPrintf(foo).

  # Not perfect but it can catch printf(foo.c_str()) and printf(foo->c_str())

  # TODO(unknown): Catch the following case. Need to change the calling

  # convention of the whole function to process multiple line to handle it.

  #   printf(

  #       boy_this_is_a_really_long_variable_that_cannot_fit_on_the_prev_line);

  printf_args = _GetTextInside(line, r'(?i)\b(string)?printf\s*\(')

  if printf_args:

    match = Match(r'([\w.\->()]+)$', printf_args)

    if match and match.group(1) != '__VA_ARGS__':

      function_name = re.search(r'\b((?:string)?printf)\s*\(',

                                line, re.I).group(1)

      error(filename, linenum, 'runtime/printf', 4,

            'Potential format string bug. Do %s("%%s", %s) instead.'

            % (function_name, match.group(1)))

  # Check for potential memset bugs like memset(buf, sizeof(buf), 0).

  match = Search(r'memset\s*\(([^,]*),\s*([^,]*),\s*0\s*\)', line)

  if match and not Match(r"^''|-?[0-9]+|0x[0-9A-Fa-f]$", match.group(2)):

    error(filename, linenum, 'runtime/memset', 4,

          'Did you mean "memset(%s, 0, %s)"?'

          % (match.group(1), match.group(2)))

  if Search(r'\busing namespace\b', line):

    if Search(r'\bliterals\b', line):

      error(filename, linenum, 'build/namespaces_literals', 5,

            'Do not use namespace using-directives.  '

            'Use using-declarations instead.')

    else:

      error(filename, linenum, 'build/namespaces', 5,

            'Do not use namespace using-directives.  '

            'Use using-declarations instead.')

  # Detect variable-length arrays.

  match = Match(r'\s*(.+::)?(\w+) [a-z]\w*\[(.+)];', line)

  if (match and match.group(2) != 'return' and match.group(2) != 'delete' and

      match.group(3).find(']') == -1):

    # Split the size using space and arithmetic operators as delimiters.

    # If any of the resulting tokens are not compile time constants then

    # report the error.

    tokens = re.split(r'\s|\+|\-|\*|\/|<<|>>]', match.group(3))

    is_const = True

    skip_next = False

    for tok in tokens:

      if skip_next:

        skip_next = False

        continue

      if Search(r'sizeof\(.+\)', tok): continue

      if Search(r'arraysize\(\w+\)', tok): continue

      tok = tok.lstrip('(')

      tok = tok.rstrip(')')

      if not tok: continue

      if Match(r'\d+', tok): continue

      if Match(r'0[xX][0-9a-fA-F]+', tok): continue

      if Match(r'k[A-Z0-9]\w*', tok): continue

      if Match(r'(.+::)?k[A-Z0-9]\w*', tok): continue

      if Match(r'(.+::)?[A-Z][A-Z0-9_]*', tok): continue

      # A catch all for tricky sizeof cases, including 'sizeof expression',

      # 'sizeof(*type)', 'sizeof(const type)', 'sizeof(struct StructName)'

      # requires skipping the next token because we split on ' ' and '*'.

      if tok.startswith('sizeof'):

        skip_next = True

        continue

      is_const = False

      break

    if not is_const:

      error(filename, linenum, 'runtime/arrays', 1,

            'Do not use variable-length arrays.  Use an appropriately named '

            "('k' followed by CamelCase) compile-time constant for the size.")

  # Check for use of unnamed namespaces in header files.  Registration

  # macros are typically OK, so we allow use of "namespace {" on lines

  # that end with backslashes.

  if (file_extension in GetHeaderExtensions()

      and Search(r'\bnamespace\s*{', line)

      and line[-1] != '\\'):

    error(filename, linenum, 'build/namespaces', 4,

          'Do not use unnamed namespaces in header files.  See '

          'https://google-styleguide.googlecode.com/svn/trunk/cppguide.xml#Namespaces'

          ' for more information.')