diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/0xtools/argparse.py | 2383 | ||||
| -rw-r--r-- | lib/0xtools/psnproc.py | 603 | ||||
| -rw-r--r-- | lib/0xtools/psnreport.py | 201 |
3 files changed, 3187 insertions, 0 deletions
diff --git a/lib/0xtools/argparse.py b/lib/0xtools/argparse.py new file mode 100644 index 0000000..cccc9ac --- /dev/null +++ b/lib/0xtools/argparse.py @@ -0,0 +1,2383 @@ +# Author: Steven J. Bethard <steven.bethard@gmail.com>. +# Maintainer: Thomas Waldmann <tw@waldmann-edv.de> + +# argparse is (c) 2006-2009 Steven J. Bethard <steven.bethard@gmail.com>. +# +# The argparse module was contributed to Python as of Python 2.7 and thus +# was licensed under the Python license. Same license applies to all files in +# the argparse package project. +# +# For details about the Python License, please see doc/Python-License.txt. +# +# History +# ------- +# +# Before (and including) argparse 1.1, the argparse package was licensed under +# Apache License v2.0. +# +# After argparse 1.1, all project files from the argparse project were deleted +# due to license compatibility issues between Apache License 2.0 and GNU GPL v2. +# +# The project repository then had a clean start with some files taken from +# Python 2.7.1, so definitely all files are under Python License now. + + +"""Command-line parsing library + +This module is an optparse-inspired command-line parsing library that: + + - handles both optional and positional arguments + - produces highly informative usage messages + - supports parsers that dispatch to sub-parsers + +The following is a simple usage example that sums integers from the +command-line and writes the result to a file:: + + parser = argparse.ArgumentParser( + description='sum the integers at the command line') + parser.add_argument( + 'integers', metavar='int', nargs='+', type=int, + help='an integer to be summed') + parser.add_argument( + '--log', default=sys.stdout, type=argparse.FileType('w'), + help='the file where the sum should be written') + args = parser.parse_args() + args.log.write('%s' % sum(args.integers)) + args.log.close() + +The module contains the following public classes: + + - ArgumentParser -- The main entry point for command-line parsing. As the + example above shows, the add_argument() method is used to populate + the parser with actions for optional and positional arguments. Then + the parse_args() method is invoked to convert the args at the + command-line into an object with attributes. + + - ArgumentError -- The exception raised by ArgumentParser objects when + there are errors with the parser's actions. Errors raised while + parsing the command-line are caught by ArgumentParser and emitted + as command-line messages. + + - FileType -- A factory for defining types of files to be created. As the + example above shows, instances of FileType are typically passed as + the type= argument of add_argument() calls. + + - Action -- The base class for parser actions. Typically actions are + selected by passing strings like 'store_true' or 'append_const' to + the action= argument of add_argument(). However, for greater + customization of ArgumentParser actions, subclasses of Action may + be defined and passed as the action= argument. + + - HelpFormatter, RawDescriptionHelpFormatter, RawTextHelpFormatter, + ArgumentDefaultsHelpFormatter -- Formatter classes which + may be passed as the formatter_class= argument to the + ArgumentParser constructor. HelpFormatter is the default, + RawDescriptionHelpFormatter and RawTextHelpFormatter tell the parser + not to change the formatting for help text, and + ArgumentDefaultsHelpFormatter adds information about argument defaults + to the help. + +All other classes in this module are considered implementation details. +(Also note that HelpFormatter and RawDescriptionHelpFormatter are only +considered public as object names -- the API of the formatter objects is +still considered an implementation detail.) +""" + +__version__ = '1.1' +__all__ = [ + 'ArgumentParser', + 'ArgumentError', + 'ArgumentTypeError', + 'FileType', + 'HelpFormatter', + 'ArgumentDefaultsHelpFormatter', + 'RawDescriptionHelpFormatter', + 'RawTextHelpFormatter', + 'Namespace', + 'Action', + 'ONE_OR_MORE', + 'OPTIONAL', + 'PARSER', + 'REMAINDER', + 'SUPPRESS', + 'ZERO_OR_MORE', +] + + +import collections as _collections +import copy as _copy +import os as _os +import re as _re +import sys as _sys +import textwrap as _textwrap + +from gettext import gettext as _ + + +def _callable(obj): + return hasattr(obj, '__call__') or hasattr(obj, '__bases__') + + +SUPPRESS = '==SUPPRESS==' + +OPTIONAL = '?' +ZERO_OR_MORE = '*' +ONE_OR_MORE = '+' +PARSER = 'A...' +REMAINDER = '...' +_UNRECOGNIZED_ARGS_ATTR = '_unrecognized_args' + +# ============================= +# Utility functions and classes +# ============================= + +class _AttributeHolder(object): + """Abstract base class that provides __repr__. + + The __repr__ method returns a string in the format:: + ClassName(attr=name, attr=name, ...) + The attributes are determined either by a class-level attribute, + '_kwarg_names', or by inspecting the instance __dict__. + """ + + def __repr__(self): + type_name = type(self).__name__ + arg_strings = [] + for arg in self._get_args(): + arg_strings.append(repr(arg)) + for name, value in self._get_kwargs(): + arg_strings.append('%s=%r' % (name, value)) + return '%s(%s)' % (type_name, ', '.join(arg_strings)) + + def _get_kwargs(self): + return sorted(self.__dict__.items()) + + def _get_args(self): + return [] + + +def _ensure_value(namespace, name, value): + if getattr(namespace, name, None) is None: + setattr(namespace, name, value) + return getattr(namespace, name) + + +# =============== +# Formatting Help +# =============== + +class HelpFormatter(object): + """Formatter for generating usage messages and argument help strings. + + Only the name of this class is considered a public API. All the methods + provided by the class are considered an implementation detail. + """ + + def __init__(self, + prog, + indent_increment=2, + max_help_position=24, + width=None): + + # default setting for width + if width is None: + try: + width = int(_os.environ['COLUMNS']) + except (KeyError, ValueError): + width = 80 + width -= 2 + + self._prog = prog + self._indent_increment = indent_increment + self._max_help_position = max_help_position + self._width = width + + self._current_indent = 0 + self._level = 0 + self._action_max_length = 0 + + self._root_section = self._Section(self, None) + self._current_section = self._root_section + + self._whitespace_matcher = _re.compile(r'\s+') + self._long_break_matcher = _re.compile(r'\n\n\n+') + + # =============================== + # Section and indentation methods + # =============================== + def _indent(self): + self._current_indent += self._indent_increment + self._level += 1 + + def _dedent(self): + self._current_indent -= self._indent_increment + assert self._current_indent >= 0, 'Indent decreased below 0.' + self._level -= 1 + + class _Section(object): + + def __init__(self, formatter, parent, heading=None): + self.formatter = formatter + self.parent = parent + self.heading = heading + self.items = [] + + def format_help(self): + # format the indented section + if self.parent is not None: + self.formatter._indent() + join = self.formatter._join_parts + for func, args in self.items: + func(*args) + item_help = join([func(*args) for func, args in self.items]) + if self.parent is not None: + self.formatter._dedent() + + # return nothing if the section was empty + if not item_help: + return '' + + # add the heading if the section was non-empty + if self.heading is not SUPPRESS and self.heading is not None: + current_indent = self.formatter._current_indent + heading = '%*s%s:\n' % (current_indent, '', self.heading) + else: + heading = '' + + # join the section-initial newline, the heading and the help + return join(['\n', heading, item_help, '\n']) + + def _add_item(self, func, args): + self._current_section.items.append((func, args)) + + # ======================== + # Message building methods + # ======================== + def start_section(self, heading): + self._indent() + section = self._Section(self, self._current_section, heading) + self._add_item(section.format_help, []) + self._current_section = section + + def end_section(self): + self._current_section = self._current_section.parent + self._dedent() + + def add_text(self, text): + if text is not SUPPRESS and text is not None: + self._add_item(self._format_text, [text]) + + def add_usage(self, usage, actions, groups, prefix=None): + if usage is not SUPPRESS: + args = usage, actions, groups, prefix + self._add_item(self._format_usage, args) + + def add_argument(self, action): + if action.help is not SUPPRESS: + + # find all invocations + get_invocation = self._format_action_invocation + invocations = [get_invocation(action)] + for subaction in self._iter_indented_subactions(action): + invocations.append(get_invocation(subaction)) + + # update the maximum item length + invocation_length = max([len(s) for s in invocations]) + action_length = invocation_length + self._current_indent + self._action_max_length = max(self._action_max_length, + action_length) + + # add the item to the list + self._add_item(self._format_action, [action]) + + def add_arguments(self, actions): + for action in actions: + self.add_argument(action) + + # ======================= + # Help-formatting methods + # ======================= + def format_help(self): + help = self._root_section.format_help() + if help: + help = self._long_break_matcher.sub('\n\n', help) + help = help.strip('\n') + '\n' + return help + + def _join_parts(self, part_strings): + return ''.join([part + for part in part_strings + if part and part is not SUPPRESS]) + + def _format_usage(self, usage, actions, groups, prefix): + if prefix is None: + prefix = _('usage: ') + + # if usage is specified, use that + if usage is not None: + usage = usage % dict(prog=self._prog) + + # if no optionals or positionals are available, usage is just prog + elif usage is None and not actions: + usage = '%(prog)s' % dict(prog=self._prog) + + # if optionals and positionals are available, calculate usage + elif usage is None: + prog = '%(prog)s' % dict(prog=self._prog) + + # split optionals from positionals + optionals = [] + positionals = [] + for action in actions: + if action.option_strings: + optionals.append(action) + else: + positionals.append(action) + + # build full usage string + format = self._format_actions_usage + action_usage = format(optionals + positionals, groups) + usage = ' '.join([s for s in [prog, action_usage] if s]) + + # wrap the usage parts if it's too long + text_width = self._width - self._current_indent + if len(prefix) + len(usage) > text_width: + + # break usage into wrappable parts + part_regexp = r'\(.*?\)+|\[.*?\]+|\S+' + opt_usage = format(optionals, groups) + pos_usage = format(positionals, groups) + opt_parts = _re.findall(part_regexp, opt_usage) + pos_parts = _re.findall(part_regexp, pos_usage) + assert ' '.join(opt_parts) == opt_usage + assert ' '.join(pos_parts) == pos_usage + + # helper for wrapping lines + def get_lines(parts, indent, prefix=None): + lines = [] + line = [] + if prefix is not None: + line_len = len(prefix) - 1 + else: + line_len = len(indent) - 1 + for part in parts: + if line_len + 1 + len(part) > text_width: + lines.append(indent + ' '.join(line)) + line = [] + line_len = len(indent) - 1 + line.append(part) + line_len += len(part) + 1 + if line: + lines.append(indent + ' '.join(line)) + if prefix is not None: + lines[0] = lines[0][len(indent):] + return lines + + # if prog is short, follow it with optionals or positionals + if len(prefix) + len(prog) <= 0.75 * text_width: + indent = ' ' * (len(prefix) + len(prog) + 1) + if opt_parts: + lines = get_lines([prog] + opt_parts, indent, prefix) + lines.extend(get_lines(pos_parts, indent)) + elif pos_parts: + lines = get_lines([prog] + pos_parts, indent, prefix) + else: + lines = [prog] + + # if prog is long, put it on its own line + else: + indent = ' ' * len(prefix) + parts = opt_parts + pos_parts + lines = get_lines(parts, indent) + if len(lines) > 1: + lines = [] + lines.extend(get_lines(opt_parts, indent)) + lines.extend(get_lines(pos_parts, indent)) + lines = [prog] + lines + + # join lines into usage + usage = '\n'.join(lines) + + # prefix with 'usage:' + return '%s%s\n\n' % (prefix, usage) + + def _format_actions_usage(self, actions, groups): + # find group indices and identify actions in groups + group_actions = set() + inserts = {} + for group in groups: + try: + start = actions.index(group._group_actions[0]) + except ValueError: + continue + else: + end = start + len(group._group_actions) + if actions[start:end] == group._group_actions: + for action in group._group_actions: + group_actions.add(action) + if not group.required: + if start in inserts: + inserts[start] += ' [' + else: + inserts[start] = '[' + inserts[end] = ']' + else: + if start in inserts: + inserts[start] += ' (' + else: + inserts[start] = '(' + inserts[end] = ')' + for i in range(start + 1, end): + inserts[i] = '|' + + # collect all actions format strings + parts = [] + for i, action in enumerate(actions): + + # suppressed arguments are marked with None + # remove | separators for suppressed arguments + if action.help is SUPPRESS: + parts.append(None) + if inserts.get(i) == '|': + inserts.pop(i) + elif inserts.get(i + 1) == '|': + inserts.pop(i + 1) + + # produce all arg strings + elif not action.option_strings: + part = self._format_args(action, action.dest) + + # if it's in a group, strip the outer [] + if action in group_actions: + if part[0] == '[' and part[-1] == ']': + part = part[1:-1] + + # add the action string to the list + parts.append(part) + + # produce the first way to invoke the option in brackets + else: + option_string = action.option_strings[0] + + # if the Optional doesn't take a value, format is: + # -s or --long + if action.nargs == 0: + part = '%s' % option_string + + # if the Optional takes a value, format is: + # -s ARGS or --long ARGS + else: + default = action.dest.upper() + args_string = self._format_args(action, default) + part = '%s %s' % (option_string, args_string) + + # make it look optional if it's not required or in a group + if not action.required and action not in group_actions: + part = '[%s]' % part + + # add the action string to the list + parts.append(part) + + # insert things at the necessary indices + for i in sorted(inserts, reverse=True): + parts[i:i] = [inserts[i]] + + # join all the action items with spaces + text = ' '.join([item for item in parts if item is not None]) + + # clean up separators for mutually exclusive groups + open = r'[\[(]' + close = r'[\])]' + text = _re.sub(r'(%s) ' % open, r'\1', text) + text = _re.sub(r' (%s)' % close, r'\1', text) + text = _re.sub(r'%s *%s' % (open, close), r'', text) + text = _re.sub(r'\(([^|]*)\)', r'\1', text) + text = text.strip() + + # return the text + return text + + def _format_text(self, text): + if '%(prog)' in text: + text = text % dict(prog=self._prog) + text_width = self._width - self._current_indent + indent = ' ' * self._current_indent + return self._fill_text(text, text_width, indent) + '\n\n' + + def _format_action(self, action): + # determine the required width and the entry label + help_position = min(self._action_max_length + 2, + self._max_help_position) + help_width = self._width - help_position + action_width = help_position - self._current_indent - 2 + action_header = self._format_action_invocation(action) + + # ho nelp; start on same line and add a final newline + if not action.help: + tup = self._current_indent, '', action_header + action_header = '%*s%s\n' % tup + + # short action name; start on the same line and pad two spaces + elif len(action_header) <= action_width: + tup = self._current_indent, '', action_width, action_header + action_header = '%*s%-*s ' % tup + indent_first = 0 + + # long action name; start on the next line + else: + tup = self._current_indent, '', action_header + action_header = '%*s%s\n' % tup + indent_first = help_position + + # collect the pieces of the action help + parts = [action_header] + + # if there was help for the action, add lines of help text + if action.help: + help_text = self._expand_help(action) + help_lines = self._split_lines(help_text, help_width) + parts.append('%*s%s\n' % (indent_first, '', help_lines[0])) + for line in help_lines[1:]: + parts.append('%*s%s\n' % (help_position, '', line)) + + # or add a newline if the description doesn't end with one + elif not action_header.endswith('\n'): + parts.append('\n') + + # if there are any sub-actions, add their help as well + for subaction in self._iter_indented_subactions(action): + parts.append(self._format_action(subaction)) + + # return a single string + return self._join_parts(parts) + + def _format_action_invocation(self, action): + if not action.option_strings: + metavar, = self._metavar_formatter(action, action.dest)(1) + return metavar + + else: + parts = [] + + # if the Optional doesn't take a value, format is: + # -s, --long + if action.nargs == 0: + parts.extend(action.option_strings) + + # if the Optional takes a value, format is: + # -s ARGS, --long ARGS + else: + default = action.dest.upper() + args_string = self._format_args(action, default) + for option_string in action.option_strings: + parts.append('%s %s' % (option_string, args_string)) + + return ', '.join(parts) + + def _metavar_formatter(self, action, default_metavar): + if action.metavar is not None: + result = action.metavar + elif action.choices is not None: + choice_strs = [str(choice) for choice in action.choices] + result = '{%s}' % ','.join(choice_strs) + else: + result = default_metavar + + def format(tuple_size): + if isinstance(result, tuple): + return result + else: + return (result, ) * tuple_size + return format + + def _format_args(self, action, default_metavar): + get_metavar = self._metavar_formatter(action, default_metavar) + if action.nargs is None: + result = '%s' % get_metavar(1) + elif action.nargs == OPTIONAL: + result = '[%s]' % get_metavar(1) + elif action.nargs == ZERO_OR_MORE: + result = '[%s [%s ...]]' % get_metavar(2) + elif action.nargs == ONE_OR_MORE: + result = '%s [%s ...]' % get_metavar(2) + elif action.nargs == REMAINDER: + result = '...' + elif action.nargs == PARSER: + result = '%s ...' % get_metavar(1) + else: + formats = ['%s' for _ in range(action.nargs)] + result = ' '.join(formats) % get_metavar(action.nargs) + return result + + def _expand_help(self, action): + params = dict(vars(action), prog=self._prog) + for name in list(params): + if params[name] is SUPPRESS: + del params[name] + for name in list(params): + if hasattr(params[name], '__name__'): + params[name] = params[name].__name__ + if params.get('choices') is not None: + choices_str = ', '.join([str(c) for c in params['choices']]) + params['choices'] = choices_str + return self._get_help_string(action) % params + + def _iter_indented_subactions(self, action): + try: + get_subactions = action._get_subactions + except AttributeError: + pass + else: + self._indent() + for subaction in get_subactions(): + yield subaction + self._dedent() + + def _split_lines(self, text, width): + text = self._whitespace_matcher.sub(' ', text).strip() + return _textwrap.wrap(text, width) + + def _fill_text(self, text, width, indent): + text = self._whitespace_matcher.sub(' ', text).strip() + return _textwrap.fill(text, width, initial_indent=indent, + subsequent_indent=indent) + + def _get_help_string(self, action): + return action.help + + +class RawDescriptionHelpFormatter(HelpFormatter): + """Help message formatter which retains any formatting in descriptions. + + Only the name of this class is considered a public API. All the methods + provided by the class are considered an implementation detail. + """ + + def _fill_text(self, text, width, indent): + return ''.join([indent + line for line in text.splitlines(True)]) + + +class RawTextHelpFormatter(RawDescriptionHelpFormatter): + """Help message formatter which retains formatting of all help text. + + Only the name of this class is considered a public API. All the methods + provided by the class are considered an implementation detail. + """ + + def _split_lines(self, text, width): + return text.splitlines() + + +class ArgumentDefaultsHelpFormatter(HelpFormatter): + """Help message formatter which adds default values to argument help. + + Only the name of this class is considered a public API. All the methods + provided by the class are considered an implementation detail. + """ + + def _get_help_string(self, action): + help = action.help + if '%(default)' not in action.help: + if action.default is not SUPPRESS: + defaulting_nargs = [OPTIONAL, ZERO_OR_MORE] + if action.option_strings or action.nargs in defaulting_nargs: + help += ' (default: %(default)s)' + return help + + +# ===================== +# Options and Arguments +# ===================== + +def _get_action_name(argument): + if argument is None: + return None + elif argument.option_strings: + return '/'.join(argument.option_strings) + elif argument.metavar not in (None, SUPPRESS): + return argument.metavar + elif argument.dest not in (None, SUPPRESS): + return argument.dest + else: + return None + + +class ArgumentError(Exception): + """An error from creating or using an argument (optional or positional). + + The string value of this exception is the message, augmented with + information about the argument that caused it. + """ + + def __init__(self, argument, message): + self.argument_name = _get_action_name(argument) + self.message = message + + def __str__(self): + if self.argument_name is None: + format = '%(message)s' + else: + format = 'argument %(argument_name)s: %(message)s' + return format % dict(message=self.message, + argument_name=self.argument_name) + + +class ArgumentTypeError(Exception): + """An error from trying to convert a command line string to a type.""" + pass + + +# ============== +# Action classes +# ============== + +class Action(_AttributeHolder): + """Information about how to convert command line strings to Python objects. + + Action objects are used by an ArgumentParser to represent the information + needed to parse a single argument from one or more strings from the + command line. The keyword arguments to the Action constructor are also + all attributes of Action instances. + + Keyword Arguments: + + - option_strings -- A list of command-line option strings which + should be associated with this action. + + - dest -- The name of the attribute to hold the created object(s) + + - nargs -- The number of command-line arguments that should be + consumed. By default, one argument will be consumed and a single + value will be produced. Other values include: + - N (an integer) consumes N arguments (and produces a list) + - '?' consumes zero or one arguments + - '*' consumes zero or more arguments (and produces a list) + - '+' consumes one or more arguments (and produces a list) + Note that the difference between the default and nargs=1 is that + with the default, a single value will be produced, while with + nargs=1, a list containing a single value will be produced. + + - const -- The value to be produced if the option is specified and the + option uses an action that takes no values. + + - default -- The value to be produced if the option is not specified. + + - type -- A callable that accepts a single string argument, and + returns the converted value. The standard Python types str, int, + float, and complex are useful examples of such callables. If None, + str is used. + + - choices -- A container of values that should be allowed. If not None, + after a command-line argument has been converted to the appropriate + type, an exception will be raised if it is not a member of this + collection. + + - required -- True if the action must always be specified at the + command line. This is only meaningful for optional command-line + arguments. + + - help -- The help string describing the argument. + + - metavar -- The name to be used for the option's argument with the + help string. If None, the 'dest' value will be used as the name. + """ + + def __init__(self, + option_strings, + dest, + nargs=None, + const=None, + default=None, + type=None, + choices=None, + required=False, + help=None, + metavar=None): + self.option_strings = option_strings + self.dest = dest + self.nargs = nargs + self.const = const + self.default = default + self.type = type + self.choices = choices + self.required = required + self.help = help + self.metavar = metavar + + def _get_kwargs(self): + names = [ + 'option_strings', + 'dest', + 'nargs', + 'const', + 'default', + 'type', + 'choices', + 'help', + 'metavar', + ] + return [(name, getattr(self, name)) for name in names] + + def __call__(self, parser, namespace, values, option_string=None): + raise NotImplementedError(_('.__call__() not defined')) + + +class _StoreAction(Action): + + def __init__(self, + option_strings, + dest, + nargs=None, + const=None, + default=None, + type=None, + choices=None, + required=False, + help=None, + metavar=None): + if nargs == 0: + raise ValueError('nargs for store actions must be > 0; if you ' + 'have nothing to store, actions such as store ' + 'true or store const may be more appropriate') + if const is not None and nargs != OPTIONAL: + raise ValueError('nargs must be %r to supply const' % OPTIONAL) + super(_StoreAction, self).__init__( + option_strings=option_strings, + dest=dest, + nargs=nargs, + const=const, + default=default, + type=type, + choices=choices, + required=required, + help=help, + metavar=metavar) + + def __call__(self, parser, namespace, values, option_string=None): + setattr(namespace, self.dest, values) + + +class _StoreConstAction(Action): + + def __init__(self, + option_strings, + dest, + const, + default=None, + required=False, + help=None, + metavar=None): + super(_StoreConstAction, self).__init__( + option_strings=option_strings, + dest=dest, + nargs=0, + const=const, + default=default, + required=required, + help=help) + + def __call__(self, parser, namespace, values, option_string=None): + setattr(namespace, self.dest, self.const) + + +class _StoreTrueAction(_StoreConstAction): + + def __init__(self, + option_strings, + dest, + default=False, + required=False, + help=None): + super(_StoreTrueAction, self).__init__( + option_strings=option_strings, + dest=dest, + const=True, + default=default, + required=required, + help=help) + + +class _StoreFalseAction(_StoreConstAction): + + def __init__(self, + option_strings, + dest, + default=True, + required=False, + help=None): + super(_StoreFalseAction, self).__init__( + option_strings=option_strings, + dest=dest, + const=False, + default=default, + required=required, + help=help) + + +class _AppendAction(Action): + + def __init__(self, + option_strings, + dest, + nargs=None, + const=None, + default=None, + type=None, + choices=None, + required=False, + help=None, + metavar=None): + if nargs == 0: + raise ValueError('nargs for append actions must be > 0; if arg ' + 'strings are not supplying the value to append, ' + 'the append const action may be more appropriate') + if const is not None and nargs != OPTIONAL: + raise ValueError('nargs must be %r to supply const' % OPTIONAL) + super(_AppendAction, self).__init__( + option_strings=option_strings, + dest=dest, + nargs=nargs, + const=const, + default=default, + type=type, + choices=choices, + required=required, + help=help, + metavar=metavar) + + def __call__(self, parser, namespace, values, option_string=None): + items = _copy.copy(_ensure_value(namespace, self.dest, [])) + items.append(values) + setattr(namespace, self.dest, items) + + +class _AppendConstAction(Action): + + def __init__(self, + option_strings, + dest, + const, + default=None, + required=False, + help=None, + metavar=None): + super(_AppendConstAction, self).__init__( + option_strings=option_strings, + dest=dest, + nargs=0, + const=const, + default=default, + required=required, + help=help, + metavar=metavar) + + def __call__(self, parser, namespace, values, option_string=None): + items = _copy.copy(_ensure_value(namespace, self.dest, [])) + items.append(self.const) + setattr(namespace, self.dest, items) + + +class _CountAction(Action): + + def __init__(self, + option_strings, + dest, + default=None, + required=False, + help=None): + super(_CountAction, self).__init__( + option_strings=option_strings, + dest=dest, + nargs=0, + default=default, + required=required, + help=help) + + def __call__(self, parser, namespace, values, option_string=None): + new_count = _ensure_value(namespace, self.dest, 0) + 1 + setattr(namespace, self.dest, new_count) + + +class _HelpAction(Action): + + def __init__(self, + option_strings, + dest=SUPPRESS, + default=SUPPRESS, + help=None): + super(_HelpAction, self).__init__( + option_strings=option_strings, + dest=dest, + default=default, + nargs=0, + help=help) + + def __call__(self, parser, namespace, values, option_string=None): + parser.print_help() + parser.exit() + + +class _VersionAction(Action): + + def __init__(self, + option_strings, + version=None, + dest=SUPPRESS, + default=SUPPRESS, + help="show program's version number and exit"): + super(_VersionAction, self).__init__( + option_strings=option_strings, + dest=dest, + default=default, + nargs=0, + help=help) + self.version = version + + def __call__(self, parser, namespace, values, option_string=None): + version = self.version + if version is None: + version = parser.version + formatter = parser._get_formatter() + formatter.add_text(version) + parser.exit(message=formatter.format_help()) + + +class _SubParsersAction(Action): + + class _ChoicesPseudoAction(Action): + + def __init__(self, name, help): + sup = super(_SubParsersAction._ChoicesPseudoAction, self) + sup.__init__(option_strings=[], dest=name, help=help) + + def __init__(self, + option_strings, + prog, + parser_class, + dest=SUPPRESS, + help=None, + metavar=None): + + self._prog_prefix = prog + self._parser_class = parser_class + self._name_parser_map = _collections.OrderedDict() + self._choices_actions = [] + + super(_SubParsersAction, self).__init__( + option_strings=option_strings, + dest=dest, + nargs=PARSER, + choices=self._name_parser_map, + help=help, + metavar=metavar) + + def add_parser(self, name, **kwargs): + # set prog from the existing prefix + if kwargs.get('prog') is None: + kwargs['prog'] = '%s %s' % (self._prog_prefix, name) + + # create a pseudo-action to hold the choice help + if 'help' in kwargs: + help = kwargs.pop('help') + choice_action = self._ChoicesPseudoAction(name, help) + self._choices_actions.append(choice_action) + + # create the parser and add it to the map + parser = self._parser_class(**kwargs) + self._name_parser_map[name] = parser + return parser + + def _get_subactions(self): + return self._choices_actions + + def __call__(self, parser, namespace, values, option_string=None): + parser_name = values[0] + arg_strings = values[1:] + + # set the parser name if requested + if self.dest is not SUPPRESS: + setattr(namespace, self.dest, parser_name) + + # select the parser + try: + parser = self._name_parser_map[parser_name] + except KeyError: + tup = parser_name, ', '.join(self._name_parser_map) + msg = _('unknown parser %r (choices: %s)') % tup + raise ArgumentError(self, msg) + + # parse all the remaining options into the namespace + # store any unrecognized options on the object, so that the top + # level parser can decide what to do with them + namespace, arg_strings = parser.parse_known_args(arg_strings, namespace) + if arg_strings: + vars(namespace).setdefault(_UNRECOGNIZED_ARGS_ATTR, []) + getattr(namespace, _UNRECOGNIZED_ARGS_ATTR).extend(arg_strings) + + +# ============== +# Type classes +# ============== + +class FileType(object): + """Factory for creating file object types + + Instances of FileType are typically passed as type= arguments to the + ArgumentParser add_argument() method. + + Keyword Arguments: + - mode -- A string indicating how the file is to be opened. Accepts the + same values as the builtin open() function. + - bufsize -- The file's desired buffer size. Accepts the same values as + the builtin open() function. + """ + + def __init__(self, mode='r', bufsize=-1): + self._mode = mode + self._bufsize = bufsize + + def __call__(self, string): + # the special argument "-" means sys.std{in,out} + if string == '-': + if 'r' in self._mode: + return _sys.stdin + elif 'w' in self._mode: + return _sys.stdout + else: + msg = _('argument "-" with mode %r') % self._mode + raise ValueError(msg) + + # all other arguments are used as file names + try: + return open(string, self._mode, self._bufsize) + except IOError as e: + message = _("can't open '%s': %s") + raise ArgumentTypeError(message % (string, e)) + + def __repr__(self): + args = self._mode, self._bufsize + args_str = ', '.join(repr(arg) for arg in args if arg != -1) + return '%s(%s)' % (type(self).__name__, args_str) + +# =========================== +# Optional and Positional Parsing +# =========================== + +class Namespace(_AttributeHolder): + """Simple object for storing attributes. + + Implements equality by attribute names and values, and provides a simple + string representation. + """ + + def __init__(self, **kwargs): + for name in kwargs: + setattr(self, name, kwargs[name]) + + __hash__ = None + + def __eq__(self, other): + return vars(self) == vars(other) + + def __ne__(self, other): + return not (self == other) + + def __contains__(self, key): + return key in self.__dict__ + + +class _ActionsContainer(object): + + def __init__(self, + description, + prefix_chars, + argument_default, + conflict_handler): + super(_ActionsContainer, self).__init__() + + self.description = description + self.argument_default = argument_default + self.prefix_chars = prefix_chars + self.conflict_handler = conflict_handler + + # set up registries + self._registries = {} + + # register actions + self.register('action', None, _StoreAction) + self.register('action', 'store', _StoreAction) + self.register('action', 'store_const', _StoreConstAction) + self.register('action', 'store_true', _StoreTrueAction) + self.register('action', 'store_false', _StoreFalseAction) + self.register('action', 'append', _AppendAction) + self.register('action', 'append_const', _AppendConstAction) + self.register('action', 'count', _CountAction) + self.register('action', 'help', _HelpAction) + self.register('action', 'version', _VersionAction) + self.register('action', 'parsers', _SubParsersAction) + + # raise an exception if the conflict handler is invalid + self._get_handler() + + # action storage + self._actions = [] + self._option_string_actions = {} + + # groups + self._action_groups = [] + self._mutually_exclusive_groups = [] + + # defaults storage + self._defaults = {} + + # determines whether an "option" looks like a negative number + self._negative_number_matcher = _re.compile(r'^-\d+$|^-\d*\.\d+$') + + # whether or not there are any optionals that look like negative + # numbers -- uses a list so it can be shared and edited + self._has_negative_number_optionals = [] + + # ==================== + # Registration methods + # ==================== + def register(self, registry_name, value, object): + registry = self._registries.setdefault(registry_name, {}) + registry[value] = object + + def _registry_get(self, registry_name, value, default=None): + return self._registries[registry_name].get(value, default) + + # ================================== + # Namespace default accessor methods + # ================================== + def set_defaults(self, **kwargs): + self._defaults.update(kwargs) + + # if these defaults match any existing arguments, replace + # the previous default on the object with the new one + for action in self._actions: + if action.dest in kwargs: + action.default = kwargs[action.dest] + + def get_default(self, dest): + for action in self._actions: + if action.dest == dest and action.default is not None: + return action.default + return self._defaults.get(dest, None) + + + # ======================= + # Adding argument actions + # ======================= + def add_argument(self, *args, **kwargs): + """ + add_argument(dest, ..., name=value, ...) + add_argument(option_string, option_string, ..., name=value, ...) + """ + + # if no positional args are supplied or only one is supplied and + # it doesn't look like an option string, parse a positional + # argument + chars = self.prefix_chars + if not args or len(args) == 1 and args[0][0] not in chars: + if args and 'dest' in kwargs: + raise ValueError('dest supplied twice for positional argument') + kwargs = self._get_positional_kwargs(*args, **kwargs) + + # otherwise, we're adding an optional argument + else: + kwargs = self._get_optional_kwargs(*args, **kwargs) + + # if no default was supplied, use the parser-level default + if 'default' not in kwargs: + dest = kwargs['dest'] + if dest in self._defaults: + kwargs['default'] = self._defaults[dest] + elif self.argument_default is not None: + kwargs['default'] = self.argument_default + + # create the action object, and add it to the parser + action_class = self._pop_action_class(kwargs) + if not _callable(action_class): + raise ValueError('unknown action "%s"' % (action_class,)) + action = action_class(**kwargs) + + # raise an error if the action type is not callable + type_func = self._registry_get('type', action.type, action.type) + if not _callable(type_func): + raise ValueError('%r is not callable' % (type_func,)) + + # raise an error if the metavar does not match the type + if hasattr(self, "_get_formatter"): + try: + self._get_formatter()._format_args(action, None) + except TypeError: + raise ValueError("length of metavar tuple does not match nargs") + + return self._add_action(action) + + def add_argument_group(self, *args, **kwargs): + group = _ArgumentGroup(self, *args, **kwargs) + self._action_groups.append(group) + return group + + def add_mutually_exclusive_group(self, **kwargs): + group = _MutuallyExclusiveGroup(self, **kwargs) + self._mutually_exclusive_groups.append(group) + return group + + def _add_action(self, action): + # resolve any conflicts + self._check_conflict(action) + + # add to actions list + self._actions.append(action) + action.container = self + + # index the action by any option strings it has + for option_string in action.option_strings: + self._option_string_actions[option_string] = action + + # set the flag if any option strings look like negative numbers + for option_string in action.option_strings: + if self._negative_number_matcher.match(option_string): + if not self._has_negative_number_optionals: + self._has_negative_number_optionals.append(True) + + # return the created action + return action + + def _remove_action(self, action): + self._actions.remove(action) + + def _add_container_actions(self, container): + # collect groups by titles + title_group_map = {} + for group in self._action_groups: + if group.title in title_group_map: + msg = _('cannot merge actions - two groups are named %r') + raise ValueError(msg % (group.title)) + title_group_map[group.title] = group + + # map each action to its group + group_map = {} + for group in container._action_groups: + + # if a group with the title exists, use that, otherwise + # create a new group matching the container's group + if group.title not in title_group_map: + title_group_map[group.title] = self.add_argument_group( + title=group.title, + description=group.description, + conflict_handler=group.conflict_handler) + + # map the actions to their new group + for action in group._group_actions: + group_map[action] = title_group_map[group.title] + + # add container's mutually exclusive groups + # NOTE: if add_mutually_exclusive_group ever gains title= and + # description= then this code will need to be expanded as above + for group in container._mutually_exclusive_groups: + mutex_group = self.add_mutually_exclusive_group( + required=group.required) + + # map the actions to their new mutex group + for action in group._group_actions: + group_map[action] = mutex_group + + # add all actions to this container or their group + for action in container._actions: + group_map.get(action, self)._add_action(action) + + def _get_positional_kwargs(self, dest, **kwargs): + # make sure required is not specified + if 'required' in kwargs: + msg = _("'required' is an invalid argument for positionals") + raise TypeError(msg) + + # mark positional arguments as required if at least one is + # always required + if kwargs.get('nargs') not in [OPTIONAL, ZERO_OR_MORE]: + kwargs['required'] = True + if kwargs.get('nargs') == ZERO_OR_MORE and 'default' not in kwargs: + kwargs['required'] = True + + # return the keyword arguments with no option strings + return dict(kwargs, dest=dest, option_strings=[]) + + def _get_optional_kwargs(self, *args, **kwargs): + # determine short and long option strings + option_strings = [] + long_option_strings = [] + for option_string in args: + # error on strings that don't start with an appropriate prefix + if not option_string[0] in self.prefix_chars: + msg = _('invalid option string %r: ' + 'must start with a character %r') + tup = option_string, self.prefix_chars + raise ValueError(msg % tup) + + # strings starting with two prefix characters are long options + option_strings.append(option_string) + if option_string[0] in self.prefix_chars: + if len(option_string) > 1: + if option_string[1] in self.prefix_chars: + long_option_strings.append(option_string) + + # infer destination, '--foo-bar' -> 'foo_bar' and '-x' -> 'x' + dest = kwargs.pop('dest', None) + if dest is None: + if long_option_strings: + dest_option_string = long_option_strings[0] + else: + dest_option_string = option_strings[0] + dest = dest_option_string.lstrip(self.prefix_chars) + if not dest: + msg = _('dest= is required for options like %r') + raise ValueError(msg % option_string) + dest = dest.replace('-', '_') + + # return the updated keyword arguments + return dict(kwargs, dest=dest, option_strings=option_strings) + + def _pop_action_class(self, kwargs, default=None): + action = kwargs.pop('action', default) + return self._registry_get('action', action, action) + + def _get_handler(self): + # determine function from conflict handler string + handler_func_name = '_handle_conflict_%s' % self.conflict_handler + try: + return getattr(self, handler_func_name) + except AttributeError: + msg = _('invalid conflict_resolution value: %r') + raise ValueError(msg % self.conflict_handler) + + def _check_conflict(self, action): + + # find all options that conflict with this option + confl_optionals = [] + for option_string in action.option_strings: + if option_string in self._option_string_actions: + confl_optional = self._option_string_actions[option_string] + confl_optionals.append((option_string, confl_optional)) + + # resolve any conflicts + if confl_optionals: + conflict_handler = self._get_handler() + conflict_handler(action, confl_optionals) + + def _handle_conflict_error(self, action, conflicting_actions): + message = _('conflicting option string(s): %s') + conflict_string = ', '.join([option_string + for option_string, action + in conflicting_actions]) + raise ArgumentError(action, message % conflict_string) + + def _handle_conflict_resolve(self, action, conflicting_actions): + + # remove all conflicting options + for option_string, action in conflicting_actions: + + # remove the conflicting option + action.option_strings.remove(option_string) + self._option_string_actions.pop(option_string, None) + + # if the option now has no option string, remove it from the + # container holding it + if not action.option_strings: + action.container._remove_action(action) + + +class _ArgumentGroup(_ActionsContainer): + + def __init__(self, container, title=None, description=None, **kwargs): + # add any missing keyword arguments by checking the container + update = kwargs.setdefault + update('conflict_handler', container.conflict_handler) + update('prefix_chars', container.prefix_chars) + update('argument_default', container.argument_default) + super_init = super(_ArgumentGroup, self).__init__ + super_init(description=description, **kwargs) + + # group attributes + self.title = title + self._group_actions = [] + + # share most attributes with the container + self._registries = container._registries + self._actions = container._actions + self._option_string_actions = container._option_string_actions + self._defaults = container._defaults + self._has_negative_number_optionals = \ + container._has_negative_number_optionals + self._mutually_exclusive_groups = container._mutually_exclusive_groups + + def _add_action(self, action): + action = super(_ArgumentGroup, self)._add_action(action) + self._group_actions.append(action) + return action + + def _remove_action(self, action): + super(_ArgumentGroup, self)._remove_action(action) + self._group_actions.remove(action) + + +class _MutuallyExclusiveGroup(_ArgumentGroup): + + def __init__(self, container, required=False): + super(_MutuallyExclusiveGroup, self).__init__(container) + self.required = required + self._container = container + + def _add_action(self, action): + if action.required: + msg = _('mutually exclusive arguments must be optional') + raise ValueError(msg) + action = self._container._add_action(action) + self._group_actions.append(action) + return action + + def _remove_action(self, action): + self._container._remove_action(action) + self._group_actions.remove(action) + + +class ArgumentParser(_AttributeHolder, _ActionsContainer): + """Object for parsing command line strings into Python objects. + + Keyword Arguments: + - prog -- The name of the program (default: sys.argv[0]) + - usage -- A usage message (default: auto-generated from arguments) + - description -- A description of what the program does + - epilog -- Text following the argument descriptions + - parents -- Parsers whose arguments should be copied into this one + - formatter_class -- HelpFormatter class for printing help messages + - prefix_chars -- Characters that prefix optional arguments + - fromfile_prefix_chars -- Characters that prefix files containing + additional arguments + - argument_default -- The default value for all arguments + - conflict_handler -- String indicating how to handle conflicts + - add_help -- Add a -h/-help option + """ + + def __init__(self, + prog=None, + usage=None, + description=None, + epilog=None, + version=None, + parents=[], + formatter_class=HelpFormatter, + prefix_chars='-', + fromfile_prefix_chars=None, + argument_default=None, + conflict_handler='error', + add_help=True): + + if version is not None: + import warnings + warnings.warn( + """The "version" argument to ArgumentParser is deprecated. """ + """Please use """ + """"add_argument(..., action='version', version="N", ...)" """ + """instead""", DeprecationWarning) + + superinit = super(ArgumentParser, self).__init__ + superinit(description=description, + prefix_chars=prefix_chars, + argument_default=argument_default, + conflict_handler=conflict_handler) + + # default setting for prog + if prog is None: + prog = _os.path.basename(_sys.argv[0]) + + self.prog = prog + self.usage = usage + self.epilog = epilog + self.version = version + self.formatter_class = formatter_class + self.fromfile_prefix_chars = fromfile_prefix_chars + self.add_help = add_help + + add_group = self.add_argument_group + self._positionals = add_group(_('positional arguments')) + self._optionals = add_group(_('optional arguments')) + self._subparsers = None + + # register types + def identity(string): + return string + self.register('type', None, identity) + + # add help and version arguments if necessary + # (using explicit default to override global argument_default) + default_prefix = '-' if '-' in prefix_chars else prefix_chars[0] + if self.add_help: + self.add_argument( + default_prefix+'h', default_prefix*2+'help', + action='help', default=SUPPRESS, + help=_('show this help message and exit')) + if self.version: + self.add_argument( + default_prefix+'v', default_prefix*2+'version', + action='version', default=SUPPRESS, + version=self.version, + help=_("show program's version number and exit")) + + # add parent arguments and defaults + for parent in parents: + self._add_container_actions(parent) + try: + defaults = parent._defaults + except AttributeError: + pass + else: + self._defaults.update(defaults) + + # ======================= + # Pretty __repr__ methods + # ======================= + def _get_kwargs(self): + names = [ + 'prog', + 'usage', + 'description', + 'version', + 'formatter_class', + 'conflict_handler', + 'add_help', + ] + return [(name, getattr(self, name)) for name in names] + + # ================================== + # Optional/Positional adding methods + # ================================== + def add_subparsers(self, **kwargs): + if self._subparsers is not None: + self.error(_('cannot have multiple subparser arguments')) + + # add the parser class to the arguments if it's not present + kwargs.setdefault('parser_class', type(self)) + + if 'title' in kwargs or 'description' in kwargs: + title = _(kwargs.pop('title', 'subcommands')) + description = _(kwargs.pop('description', None)) + self._subparsers = self.add_argument_group(title, description) + else: + self._subparsers = self._positionals + + # prog defaults to the usage message of this parser, skipping + # optional arguments and with no "usage:" prefix + if kwargs.get('prog') is None: + formatter = self._get_formatter() + positionals = self._get_positional_actions() + groups = self._mutually_exclusive_groups + formatter.add_usage(self.usage, positionals, groups, '') + kwargs['prog'] = formatter.format_help().strip() + + # create the parsers action and add it to the positionals list + parsers_class = self._pop_action_class(kwargs, 'parsers') + action = parsers_class(option_strings=[], **kwargs) + self._subparsers._add_action(action) + + # return the created parsers action + return action + + def _add_action(self, action): + if action.option_strings: + self._optionals._add_action(action) + else: + self._positionals._add_action(action) + return action + + def _get_optional_actions(self): + return [action + for action in self._actions + if action.option_strings] + + def _get_positional_actions(self): + return [action + for action in self._actions + if not action.option_strings] + + # ===================================== + # Command line argument parsing methods + # ===================================== + def parse_args(self, args=None, namespace=None): + args, argv = self.parse_known_args(args, namespace) + if argv: + msg = _('unrecognized arguments: %s') + self.error(msg % ' '.join(argv)) + return args + + def parse_known_args(self, args=None, namespace=None): + if args is None: + # args default to the system args + args = _sys.argv[1:] + else: + # make sure that args are mutable + args = list(args) + + # default Namespace built from parser defaults + if namespace is None: + namespace = Namespace() + + # add any action defaults that aren't present + for action in self._actions: + if action.dest is not SUPPRESS: + if not hasattr(namespace, action.dest): + if action.default is not SUPPRESS: + setattr(namespace, action.dest, action.default) + + # add any parser defaults that aren't present + for dest in self._defaults: + if not hasattr(namespace, dest): + setattr(namespace, dest, self._defaults[dest]) + + # parse the arguments and exit if there are any errors + try: + namespace, args = self._parse_known_args(args, namespace) + if hasattr(namespace, _UNRECOGNIZED_ARGS_ATTR): + args.extend(getattr(namespace, _UNRECOGNIZED_ARGS_ATTR)) + delattr(namespace, _UNRECOGNIZED_ARGS_ATTR) + return namespace, args + except ArgumentError: + err = _sys.exc_info()[1] + self.error(str(err)) + + def _parse_known_args(self, arg_strings, namespace): + # replace arg strings that are file references + if self.fromfile_prefix_chars is not None: + arg_strings = self._read_args_from_files(arg_strings) + + # map all mutually exclusive arguments to the other arguments + # they can't occur with + action_conflicts = {} + for mutex_group in self._mutually_exclusive_groups: + group_actions = mutex_group._group_actions + for i, mutex_action in enumerate(mutex_group._group_actions): + conflicts = action_conflicts.setdefault(mutex_action, []) + conflicts.extend(group_actions[:i]) + conflicts.extend(group_actions[i + 1:]) + + # find all option indices, and determine the arg_string_pattern + # which has an 'O' if there is an option at an index, + # an 'A' if there is an argument, or a '-' if there is a '--' + option_string_indices = {} + arg_string_pattern_parts = [] + arg_strings_iter = iter(arg_strings) + for i, arg_string in enumerate(arg_strings_iter): + + # all args after -- are non-options + if arg_string == '--': + arg_string_pattern_parts.append('-') + for arg_string in arg_strings_iter: + arg_string_pattern_parts.append('A') + + # otherwise, add the arg to the arg strings + # and note the index if it was an option + else: + option_tuple = self._parse_optional(arg_string) + if option_tuple is None: + pattern = 'A' + else: + option_string_indices[i] = option_tuple + pattern = 'O' + arg_string_pattern_parts.append(pattern) + + # join the pieces together to form the pattern + arg_strings_pattern = ''.join(arg_string_pattern_parts) + + # converts arg strings to the appropriate and then takes the action + seen_actions = set() + seen_non_default_actions = set() + + def take_action(action, argument_strings, option_string=None): + seen_actions.add(action) + argument_values = self._get_values(action, argument_strings) + + # error if this argument is not allowed with other previously + # seen arguments, assuming that actions that use the default + # value don't really count as "present" + if argument_values is not action.default: + seen_non_default_actions.add(action) + for conflict_action in action_conflicts.get(action, []): + if conflict_action in seen_non_default_actions: + msg = _('not allowed with argument %s') + action_name = _get_action_name(conflict_action) + raise ArgumentError(action, msg % action_name) + + # take the action if we didn't receive a SUPPRESS value + # (e.g. from a default) + if argument_values is not SUPPRESS: + action(self, namespace, argument_values, option_string) + + # function to convert arg_strings into an optional action + def consume_optional(start_index): + + # get the optional identified at this index + option_tuple = option_string_indices[start_index] + action, option_string, explicit_arg = option_tuple + + # identify additional optionals in the same arg string + # (e.g. -xyz is the same as -x -y -z if no args are required) + match_argument = self._match_argument + action_tuples = [] + while True: + + # if we found no optional action, skip it + if action is None: + extras.append(arg_strings[start_index]) + return start_index + 1 + + # if there is an explicit argument, try to match the + # optional's string arguments to only this + if explicit_arg is not None: + arg_count = match_argument(action, 'A') + + # if the action is a single-dash option and takes no + # arguments, try to parse more single-dash options out + # of the tail of the option string + chars = self.prefix_chars + if arg_count == 0 and option_string[1] not in chars: + action_tuples.append((action, [], option_string)) + char = option_string[0] + option_string = char + explicit_arg[0] + new_explicit_arg = explicit_arg[1:] or None + optionals_map = self._option_string_actions + if option_string in optionals_map: + action = optionals_map[option_string] + explicit_arg = new_explicit_arg + else: + msg = _('ignored explicit argument %r') + raise ArgumentError(action, msg % explicit_arg) + + # if the action expect exactly one argument, we've + # successfully matched the option; exit the loop + elif arg_count == 1: + stop = start_index + 1 + args = [explicit_arg] + action_tuples.append((action, args, option_string)) + break + + # error if a double-dash option did not use the + # explicit argument + else: + msg = _('ignored explicit argument %r') + raise ArgumentError(action, msg % explicit_arg) + + # if there is no explicit argument, try to match the + # optional's string arguments with the following strings + # if successful, exit the loop + else: + start = start_index + 1 + selected_patterns = arg_strings_pattern[start:] + arg_count = match_argument(action, selected_patterns) + stop = start + arg_count + args = arg_strings[start:stop] + action_tuples.append((action, args, option_string)) + break + + # add the Optional to the list and return the index at which + # the Optional's string args stopped + assert action_tuples + for action, args, option_string in action_tuples: + take_action(action, args, option_string) + return stop + + # the list of Positionals left to be parsed; this is modified + # by consume_positionals() + positionals = self._get_positional_actions() + + # function to convert arg_strings into positional actions + def consume_positionals(start_index): + # match as many Positionals as possible + match_partial = self._match_arguments_partial + selected_pattern = arg_strings_pattern[start_index:] + arg_counts = match_partial(positionals, selected_pattern) + + # slice off the appropriate arg strings for each Positional + # and add the Positional and its args to the list + for action, arg_count in zip(positionals, arg_counts): + args = arg_strings[start_index: start_index + arg_count] + start_index += arg_count + take_action(action, args) + + # slice off the Positionals that we just parsed and return the + # index at which the Positionals' string args stopped + positionals[:] = positionals[len(arg_counts):] + return start_index + + # consume Positionals and Optionals alternately, until we have + # passed the last option string + extras = [] + start_index = 0 + if option_string_indices: + max_option_string_index = max(option_string_indices) + else: + max_option_string_index = -1 + while start_index <= max_option_string_index: + + # consume any Positionals preceding the next option + next_option_string_index = min([ + index + for index in option_string_indices + if index >= start_index]) + if start_index != next_option_string_index: + positionals_end_index = consume_positionals(start_index) + + # only try to parse the next optional if we didn't consume + # the option string during the positionals parsing + if positionals_end_index > start_index: + start_index = positionals_end_index + continue + else: + start_index = positionals_end_index + + # if we consumed all the positionals we could and we're not + # at the index of an option string, there were extra arguments + if start_index not in option_string_indices: + strings = arg_strings[start_index:next_option_string_index] + extras.extend(strings) + start_index = next_option_string_index + + # consume the next optional and any arguments for it + start_index = consume_optional(start_index) + + # consume any positionals following the last Optional + stop_index = consume_positionals(start_index) + + # if we didn't consume all the argument strings, there were extras + extras.extend(arg_strings[stop_index:]) + + # if we didn't use all the Positional objects, there were too few + # arg strings supplied. + if positionals: + self.error(_('too few arguments')) + + # make sure all required actions were present, and convert defaults. + for action in self._actions: + if action not in seen_actions: + if action.required: + name = _get_action_name(action) + self.error(_('argument %s is required') % name) + else: + # Convert action default now instead of doing it before + # parsing arguments to avoid calling convert functions + # twice (which may fail) if the argument was given, but + # only if it was defined already in the namespace + if (action.default is not None and + isinstance(action.default, basestring) and + hasattr(namespace, action.dest) and + action.default is getattr(namespace, action.dest)): + setattr(namespace, action.dest, + self._get_value(action, action.default)) + + # make sure all required groups had one option present + for group in self._mutually_exclusive_groups: + if group.required: + for action in group._group_actions: + if action in seen_non_default_actions: + break + + # if no actions were used, report the error + else: + names = [_get_action_name(action) + for action in group._group_actions + if action.help is not SUPPRESS] + msg = _('one of the arguments %s is required') + self.error(msg % ' '.join(names)) + + # return the updated namespace and the extra arguments + return namespace, extras + + def _read_args_from_files(self, arg_strings): + # expand arguments referencing files + new_arg_strings = [] + for arg_string in arg_strings: + + # for regular arguments, just add them back into the list + if not arg_string or arg_string[0] not in self.fromfile_prefix_chars: + new_arg_strings.append(arg_string) + + # replace arguments referencing files with the file content + else: + try: + args_file = open(arg_string[1:]) + try: + arg_strings = [] + for arg_line in args_file.read().splitlines(): + for arg in self.convert_arg_line_to_args(arg_line): + arg_strings.append(arg) + arg_strings = self._read_args_from_files(arg_strings) + new_arg_strings.extend(arg_strings) + finally: + args_file.close() + except IOError: + err = _sys.exc_info()[1] + self.error(str(err)) + + # return the modified argument list + return new_arg_strings + + def convert_arg_line_to_args(self, arg_line): + return [arg_line] + + def _match_argument(self, action, arg_strings_pattern): + # match the pattern for this action to the arg strings + nargs_pattern = self._get_nargs_pattern(action) + match = _re.match(nargs_pattern, arg_strings_pattern) + + # raise an exception if we weren't able to find a match + if match is None: + nargs_errors = { + None: _('expected one argument'), + OPTIONAL: _('expected at most one argument'), + ONE_OR_MORE: _('expected at least one argument'), + } + default = _('expected %s argument(s)') % action.nargs + msg = nargs_errors.get(action.nargs, default) + raise ArgumentError(action, msg) + + # return the number of arguments matched + return len(match.group(1)) + + def _match_arguments_partial(self, actions, arg_strings_pattern): + # progressively shorten the actions list by slicing off the + # final actions until we find a match + result = [] + for i in range(len(actions), 0, -1): + actions_slice = actions[:i] + pattern = ''.join([self._get_nargs_pattern(action) + for action in actions_slice]) + match = _re.match(pattern, arg_strings_pattern) + if match is not None: + result.extend([len(string) for string in match.groups()]) + break + + # return the list of arg string counts + return result + + def _parse_optional(self, arg_string): + # if it's an empty string, it was meant to be a positional + if not arg_string: + return None + + # if it doesn't start with a prefix, it was meant to be positional + if not arg_string[0] in self.prefix_chars: + return None + + # if the option string is present in the parser, return the action + if arg_string in self._option_string_actions: + action = self._option_string_actions[arg_string] + return action, arg_string, None + + # if it's just a single character, it was meant to be positional + if len(arg_string) == 1: + return None + + # if the option string before the "=" is present, return the action + if '=' in arg_string: + option_string, explicit_arg = arg_string.split('=', 1) + if option_string in self._option_string_actions: + action = self._option_string_actions[option_string] + return action, option_string, explicit_arg + + # search through all possible prefixes of the option string + # and all actions in the parser for possible interpretations + option_tuples = self._get_option_tuples(arg_string) + + # if multiple actions match, the option string was ambiguous + if len(option_tuples) > 1: + options = ', '.join([option_string + for action, option_string, explicit_arg in option_tuples]) + tup = arg_string, options + self.error(_('ambiguous option: %s could match %s') % tup) + + # if exactly one action matched, this segmentation is good, + # so return the parsed action + elif len(option_tuples) == 1: + option_tuple, = option_tuples + return option_tuple + + # if it was not found as an option, but it looks like a negative + # number, it was meant to be positional + # unless there are negative-number-like options + if self._negative_number_matcher.match(arg_string): + if not self._has_negative_number_optionals: + return None + + # if it contains a space, it was meant to be a positional + if ' ' in arg_string: + return None + + # it was meant to be an optional but there is no such option + # in this parser (though it might be a valid option in a subparser) + return None, arg_string, None + + def _get_option_tuples(self, option_string): + result = [] + + # option strings starting with two prefix characters are only + # split at the '=' + chars = self.prefix_chars + if option_string[0] in chars and option_string[1] in chars: + if '=' in option_string: + option_prefix, explicit_arg = option_string.split('=', 1) + else: + option_prefix = option_string + explicit_arg = None + for option_string in self._option_string_actions: + if option_string.startswith(option_prefix): + action = self._option_string_actions[option_string] + tup = action, option_string, explicit_arg + result.append(tup) + + # single character options can be concatenated with their arguments + # but multiple character options always have to have their argument + # separate + elif option_string[0] in chars and option_string[1] not in chars: + option_prefix = option_string + explicit_arg = None + short_option_prefix = option_string[:2] + short_explicit_arg = option_string[2:] + + for option_string in self._option_string_actions: + if option_string == short_option_prefix: + action = self._option_string_actions[option_string] + tup = action, option_string, short_explicit_arg + result.append(tup) + elif option_string.startswith(option_prefix): + action = self._option_string_actions[option_string] + tup = action, option_string, explicit_arg + result.append(tup) + + # shouldn't ever get here + else: + self.error(_('unexpected option string: %s') % option_string) + + # return the collected option tuples + return result + + def _get_nargs_pattern(self, action): + # in all examples below, we have to allow for '--' args + # which are represented as '-' in the pattern + nargs = action.nargs + + # the default (None) is assumed to be a single argument + if nargs is None: + nargs_pattern = '(-*A-*)' + + # allow zero or one arguments + elif nargs == OPTIONAL: + nargs_pattern = '(-*A?-*)' + + # allow zero or more arguments + elif nargs == ZERO_OR_MORE: + nargs_pattern = '(-*[A-]*)' + + # allow one or more arguments + elif nargs == ONE_OR_MORE: + nargs_pattern = '(-*A[A-]*)' + + # allow any number of options or arguments + elif nargs == REMAINDER: + nargs_pattern = '([-AO]*)' + + # allow one argument followed by any number of options or arguments + elif nargs == PARSER: + nargs_pattern = '(-*A[-AO]*)' + + # all others should be integers + else: + nargs_pattern = '(-*%s-*)' % '-*'.join('A' * nargs) + + # if this is an optional action, -- is not allowed + if action.option_strings: + nargs_pattern = nargs_pattern.replace('-*', '') + nargs_pattern = nargs_pattern.replace('-', '') + + # return the pattern + return nargs_pattern + + # ======================== + # Value conversion methods + # ======================== + def _get_values(self, action, arg_strings): + # for everything but PARSER, REMAINDER args, strip out first '--' + if action.nargs not in [PARSER, REMAINDER]: + try: + arg_strings.remove('--') + except ValueError: + pass + + # optional argument produces a default when not present + if not arg_strings and action.nargs == OPTIONAL: + if action.option_strings: + value = action.const + else: + value = action.default + if isinstance(value, basestring): + value = self._get_value(action, value) + self._check_value(action, value) + + # when nargs='*' on a positional, if there were no command-line + # args, use the default if it is anything other than None + elif (not arg_strings and action.nargs == ZERO_OR_MORE and + not action.option_strings): + if action.default is not None: + value = action.default + else: + value = arg_strings + self._check_value(action, value) + + # single argument or optional argument produces a single value + elif len(arg_strings) == 1 and action.nargs in [None, OPTIONAL]: + arg_string, = arg_strings + value = self._get_value(action, arg_string) + self._check_value(action, value) + + # REMAINDER arguments convert all values, checking none + elif action.nargs == REMAINDER: + value = [self._get_value(action, v) for v in arg_strings] + + # PARSER arguments convert all values, but check only the first + elif action.nargs == PARSER: + value = [self._get_value(action, v) for v in arg_strings] + self._check_value(action, value[0]) + + # all other types of nargs produce a list + else: + value = [self._get_value(action, v) for v in arg_strings] + for v in value: + self._check_value(action, v) + + # return the converted value + return value + + def _get_value(self, action, arg_string): + type_func = self._registry_get('type', action.type, action.type) + if not _callable(type_func): + msg = _('%r is not callable') + raise ArgumentError(action, msg % type_func) + + # convert the value to the appropriate type + try: + result = type_func(arg_string) + + # ArgumentTypeErrors indicate errors + except ArgumentTypeError: + name = getattr(action.type, '__name__', repr(action.type)) + msg = str(_sys.exc_info()[1]) + raise ArgumentError(action, msg) + + # TypeErrors or ValueErrors also indicate errors + except (TypeError, ValueError): + name = getattr(action.type, '__name__', repr(action.type)) + msg = _('invalid %s value: %r') + raise ArgumentError(action, msg % (name, arg_string)) + + # return the converted value + return result + + def _check_value(self, action, value): + # converted value must be one of the choices (if specified) + if action.choices is not None and value not in action.choices: + tup = value, ', '.join(map(repr, action.choices)) + msg = _('invalid choice: %r (choose from %s)') % tup + raise ArgumentError(action, msg) + + # ======================= + # Help-formatting methods + # ======================= + def format_usage(self): + formatter = self._get_formatter() + formatter.add_usage(self.usage, self._actions, + self._mutually_exclusive_groups) + return formatter.format_help() + + def format_help(self): + formatter = self._get_formatter() + + # usage + formatter.add_usage(self.usage, self._actions, + self._mutually_exclusive_groups) + + # description + formatter.add_text(self.description) + + # positionals, optionals and user-defined groups + for action_group in self._action_groups: + formatter.start_section(action_group.title) + formatter.add_text(action_group.description) + formatter.add_arguments(action_group._group_actions) + formatter.end_section() + + # epilog + formatter.add_text(self.epilog) + + # determine help from format above + return formatter.format_help() + + def format_version(self): + import warnings + warnings.warn( + 'The format_version method is deprecated -- the "version" ' + 'argument to ArgumentParser is no longer supported.', + DeprecationWarning) + formatter = self._get_formatter() + formatter.add_text(self.version) + return formatter.format_help() + + def _get_formatter(self): + return self.formatter_class(prog=self.prog) + + # ===================== + # Help-printing methods + # ===================== + def print_usage(self, file=None): + if file is None: + file = _sys.stdout + self._print_message(self.format_usage(), file) + + def print_help(self, file=None): + if file is None: + file = _sys.stdout + self._print_message(self.format_help(), file) + + def print_version(self, file=None): + import warnings + warnings.warn( + 'The print_version method is deprecated -- the "version" ' + 'argument to ArgumentParser is no longer supported.', + DeprecationWarning) + self._print_message(self.format_version(), file) + + def _print_message(self, message, file=None): + if message: + if file is None: + file = _sys.stderr + file.write(message) + + # =============== + # Exiting methods + # =============== + def exit(self, status=0, message=None): + if message: + self._print_message(message, _sys.stderr) + _sys.exit(status) + + def error(self, message): + """error(message: string) + + Prints a usage message incorporating the message to stderr and + exits. + + If you override this in a subclass, it should not return -- it + should either exit or raise an exception. + """ + self.print_usage(_sys.stderr) + self.exit(2, _('%s: error: %s\n') % (self.prog, message)) diff --git a/lib/0xtools/psnproc.py b/lib/0xtools/psnproc.py new file mode 100644 index 0000000..fe3c624 --- /dev/null +++ b/lib/0xtools/psnproc.py @@ -0,0 +1,603 @@ +# psn -- Linux Process Snapper by Tanel Poder [https://0x.tools] +# Copyright 2019-2021 Tanel Poder +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License along +# with this program; if not, write to the Free Software Foundation, Inc., +# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. +# +# SPDX-License-Identifier: GPL-2.0-or-later + +# structures defining /proc +import os, os.path +import re +import platform + +system_timer_hz = os.sysconf('SC_CLK_TCK') + +class ProcSource: + def __init__(self, name, path, available_columns, stored_column_names, task_level=False, read_samples=lambda f: [f.read()], parse_sample=lambda self, sample: sample.split()): + self.name = name + self.path = path + self.available_columns = available_columns + self.task_level = task_level + self.read_samples = read_samples + self.parse_sample = parse_sample + + self.set_stored_columns(stored_column_names) + + + + def set_stored_columns(self, stored_column_names): + col_name_i, schema_type_i, source_i, transform_i = range(4) + self.stored_column_names = stored_column_names or [c[0] for c in self.available_columns] + + # find schema columns + sample_cols = [('event_time', str), ('pid', int), ('task', int)] + source_cols = [c for c in self.available_columns if c[col_name_i] in self.stored_column_names and c[col_name_i] not in dict(sample_cols) and c[1] is not None] + self.schema_columns = sample_cols + source_cols + + column_indexes = dict([(c[col_name_i], c[source_i]) for c in self.available_columns]) + + schema_extract_idx = [column_indexes[c[col_name_i]] for c in source_cols] + schema_extract_convert = [c[schema_type_i] if len(c) == 3 else c[transform_i] for c in source_cols] + self.schema_extract = list(zip(schema_extract_idx, schema_extract_convert)) + + self.insert_sql = "INSERT INTO '%s' VALUES (%s)" % (self.name, ','.join(['?' for i in self.schema_columns])) + + + # knowing the bit length, we can decide if it's a large positive number or just a (small or large) negative one + def hex_to_signed_int(self, hex_str, bit_length): + unsigned_int = int(hex_str, 16) + + if unsigned_int >= 2**(bit_length - 1): + return unsigned_int - 2**bit_length + return unsigned_int + + + def sample(self, event_time, pid, task): + sample_path = self.path % (pid, task) if self.task_level else self.path % pid + + with open(sample_path) as f: + full_sample = None + raw_samples = self.read_samples(f) + + def create_row_sample(raw_sample): + full_sample = self.parse_sample(self, raw_sample) + + # some syscall-specific code pushed down to general sampling function + # call readlink() to get the file name for system calls that have a file descriptor as arg0 + filename = '' + if self.name == 'syscall': + # special case: kernel threads show all-zero "syscall" on newer kernels like 4.x + # otherwise it incorrectly looks like that kernel is in a "read" syscall (id=0 on x86_64) + if full_sample[0] == '-1' or full_sample == ['0', '0x0', '0x0', '0x0', '0x0', '0x0', '0x0', '0x0', '0x0']: + full_sample = ['kernel_thread', '0x0', '0x0', '0x0', '0x0', '0x0', '0x0', '0x0', '0x0'] + + try: + syscall_id = full_sample[0] # get string version of syscall number or "running" or "-1" + except (ValueError, IndexError) as e: + print('problem extracting syscall id', self.name, 'sample:') + printr(full_sample) + print + raise + + if syscall_id in syscalls_with_fd_arg: + try: + arg0 = int(full_sample[1], 16) + # a hacky way for avoiding reading false file descriptors for kernel threads on older kernels + # (like 2.6.32) that show "syscall 0x0" for kernel threads + some random false arguments. + # TODO refactor this and kernel_thread translation above + if arg0 <= 65536: + filename = os.readlink("/proc/%s/fd/%s" % (pid, arg0)) + " " + special_fds.get(arg0, '') + else: + filename = 'fd over 65536' + + except (OSError) as e: + # file has been closed or process has disappeared + #print 'problem with translating fd to name /proc/%s/fd/%s' % (pid, arg0), 'sample:' + #print full_sample + #print + filename = '-' + + elif syscall_id in syscalls_with_sint_arg: + waitpid = self.hex_to_signed_int(full_sample[1], 32) + if waitpid == -1: + filename = 'pid:[child]' + else: + filename = 'pid:[' + str(waitpid) + ']' + + full_sample += (filename,) + + r = [event_time, pid, task] + [convert(full_sample[idx]) for idx, convert in self.schema_extract] + return r + + try: + return [create_row_sample(rs) for rs in raw_samples] + except (ValueError, IndexError) as e: + print('problem parsing', self.name, 'sample:') + print(raw_samples) + print + raise + + +### stat ### +# process_state_name = { +# 'R': 'Running (ON CPU)', +# 'S': 'Sleeping (Interruptible)', +# 'D': 'Disk (Uninterruptible)', +# 'Z': 'Zombie', +# 'T': 'Traced/Stopped', +# 'W': 'Paging' +# } + +# https://github.com/torvalds/linux/blob/master/fs/proc/array.c +# State W (paging) is not used in kernels 2.6.x onwards +process_state_name = { + 'R': 'Running (ON CPU)', #/* 0x00 */ + 'S': 'Sleep (Interruptible)', #/* 0x01 */ + 'D': 'Disk (Uninterruptible)', #/* 0x02 */ + 'T': '(stopped)', #/* 0x04 */ + 't': '(tracing stop)', #/* 0x08 */ + 'X': '(dead)', #/* 0x10 */ + 'Z': '(zombie)', #/* 0x20 */ + 'P': '(parked)', #/* 0x40 */ + #/* states beyond TASK_REPORT: */ + 'I': '(idle)', #/* 0x80 */ +} + +def parse_stat_sample(proc_source, sample): + tokens = raw_tokens = sample.split() + + # stitch together comm field of the form (word word) + if raw_tokens[1][0] == '(' and raw_tokens[1][-1] != ')': + tokens = raw_tokens[:2] + raw_tokens = raw_tokens[2:] + while tokens[-1][-1] != ')': + tokens[-1] += ' ' + raw_tokens.pop(0) + tokens.extend(raw_tokens) + + return tokens + + +trim_comm = re.compile(r'\d+') + + +stat = ProcSource('stat', '/proc/%s/task/%s/stat', [ + ('pid', int, 0), + ('comm', str, 1, lambda c: re.sub(trim_comm, '*', c)), + ('comm2', str, 1), + ('state_id', str, 2), + ('state', str, 2, lambda state_id: process_state_name.get(state_id, state_id)), + ('ppid', int, 3), + ('pgrp', int, 4), + ('session', int, 5), + ('tty_nr', int, 6), + ('tpgid', int, 7), + ('flags', None, 8), + ('minflt', int, 9), + ('cminflt', int, 10), + ('majflt', int, 11), + ('cmajflt', int, 12), + ('utime', int, 13), + ('stime', int, 14), + ('cutime', int, 15), + ('cstime', int, 16), + ('utime_sec', int, 13, lambda v: int(v) / system_timer_hz), + ('stime_sec', int, 14, lambda v: int(v) / system_timer_hz), + ('cutime_sec', int, 15, lambda v: int(v) / system_timer_hz), + ('cstime_sec', int, 16, lambda v: int(v) / system_timer_hz), + ('priority', int, 17), + ('nice', int, 18), + ('num_threads', int, 19), + ('itrealvalue', None, 20), + ('starttime', int, 21), + ('vsize', int, 22), + ('rss', int, 23), + ('rsslim', str, 24), + ('startcode', None, 25), + ('endcode', None, 26), + ('startstack', None, 27), + ('kstkesp', None, 28), + ('kstkeip', None, 29), + ('signal', None, 30), + ('blocked', None, 31), + ('sigignore', None, 32), + ('sigcatch', None, 33), + ('wchan', None, 34), + ('nswap', None, 35), + ('cnswap', None, 36), + ('exit_signal', int, 37), + ('processor', int, 38), + ('rt_priority', int, 39), + ('policy', None, 40), + ('delayacct_blkio_ticks', int, 41), + ('guest_time', int, 42), + ('cgust_time', int, 43), + ('start_data', None, 44), + ('end_data', None, 45), + ('start_brk', None, 46), + ('arg_start', None, 47), + ('arg_end', None, 48), + ('env_start', None, 49), + ('env_end', None, 50), + ('exit_code', int, 51), +], None, +task_level=True, +parse_sample=parse_stat_sample) + + + +### status ### +def parse_status_sample(proc_source, sample): + lines = sample.split('\n') + + sample_values = [] + + for line in [l for l in lines if l]: + line_tokens = line.split() + n, v = line_tokens[0][:-1].lower(), ' '.join(line_tokens[1:]) + n_kb = n + '_kb' + + # missing values take default parse function value: assume no order change, and that available_columns contains all possible field names + while len(sample_values) < len(proc_source.available_columns) and proc_source.available_columns[len(sample_values)][0] not in (n, n_kb): + parse_fn = proc_source.available_columns[len(sample_values)][1] + sample_values.append(parse_fn()) + + if len(sample_values) < len(proc_source.available_columns): + sample_values.append(v) + + return sample_values + + +status = ProcSource('status', '/proc/%s/status', [ + ('name', str, 0), + ('umask', str, 1), + ('state', str, 2), # remove duplicate with stat + ('tgid', int, 3), + ('ngid', int, 4), + ('pid', int, 5), + ('ppid', int, 6), # remove duplicate with stat + ('tracerpid', int, 7), + ('uid', int, 8, lambda v: int(v.split()[0])), + ('gid', int, 9, lambda v: int(v.split()[0])), + ('fdsize', int, 10), + ('groups', str, 11), + ('nstgid', str, 12), + ('nspid', str, 13), + ('nspgid', str, 14), + ('nssid', str, 15), + ('vmpeak_kb', int, 16, lambda v: int(v.split()[0])), + ('vmsize_kb', int, 17, lambda v: int(v.split()[0])), + ('vmlck_kb', int, 18, lambda v: int(v.split()[0])), + ('vmpin_kb', int, 19, lambda v: int(v.split()[0])), + ('vmhwm_kb', int, 20, lambda v: int(v.split()[0])), + ('vmrss_kb', int, 21, lambda v: int(v.split()[0])), + ('rssanon_kb', int, 22, lambda v: int(v.split()[0])), + ('rssfile_kb', int, 23, lambda v: int(v.split()[0])), + ('rssshmem_kb', int, 24, lambda v: int(v.split()[0])), + ('vmdata_kb', int, 25, lambda v: int(v.split()[0])), + ('vmstk_kb', int, 26, lambda v: int(v.split()[0])), + ('vmexe_kb', int, 27, lambda v: int(v.split()[0])), + ('vmlib_kb', int, 28, lambda v: int(v.split()[0])), + ('vmpte_kb', int, 29, lambda v: int(v.split()[0])), + ('vmpmd_kb', int, 30, lambda v: int(v.split()[0])), + ('vmswap_kb', int, 31, lambda v: int(v.split()[0])), + ('hugetlbpages_kb', int, 32, lambda v: int(v.split()[0])), + ('threads', int, 33), + ('sigq', str, 34), + ('sigpnd', str, 35), + ('shdpnd', str, 36), + ('sigblk', str, 37), + ('sigign', str, 38), + ('sigcgt', str, 39), + ('capinh', str, 40), + ('capprm', str, 41), + ('capeff', str, 42), + ('capbnd', str, 43), + ('capamb', str, 44), + ('seccomp', int, 45), + ('cpus_allowed', str, 46), + ('cpus_allowed_list', str, 47), + ('mems_allowed', str, 48), + ('mems_allowed_list', str, 49), + ('voluntary_ctxt_switches', int, 50), + ('nonvoluntary_ctxt_switches', int, 51) +], None, task_level=False, parse_sample=parse_status_sample) + + +### syscall ### +def extract_system_call_ids(unistd_64_fh): + syscall_id_to_name = {'running': '[running]', '-1': '[kernel_direct]', 'kernel_thread':'[kernel_thread]'} + + # examples from a unistd.h file + # #define __NR_mount 40 + # #define __NR3264_truncate 45 + + for name_prefix in ['__NR_', '__NR3264_']: + for line in unistd_64_fh.readlines(): + tokens = line.split() + if tokens and len(tokens) == 3 and tokens[0] == '#define': + _, s_name, s_id = tokens + if s_name.startswith(name_prefix): + s_name = s_name[len(name_prefix):] + syscall_id_to_name[s_id] = s_name + + return syscall_id_to_name + +# currently assuming all platforms are x86_64 +def get_system_call_names(): + psn_dir=os.path.dirname(os.path.realpath(__file__)) + kernel_ver=platform.release().split('-')[0] + + # this probably needds to be improved for better platform support + if platform.machine() == 'aarch64': + unistd_64_paths = ['/usr/include/asm-generic/unistd.h'] + else: + unistd_64_paths = ['/usr/include/asm/unistd_64.h', '/usr/include/x86_64-linux-gnu/asm/unistd_64.h', '/usr/include/asm-x86_64/unistd.h', '/usr/include/asm/unistd.h', psn_dir+'/syscall_64_'+kernel_ver+'.h', psn_dir+'/syscall_64.h'] + + for path in unistd_64_paths: + try: + with open(path) as f: + return extract_system_call_ids(f) + except IOError as e: + pass + + raise Exception('unistd_64.h not found in' + ' or '.join(unistd_64_paths) + '.\n You may need to "yum install kernel-headers" or "apt-get install libc6-dev"\n until this dependency is removed in a newer pSnapper version') + + +syscall_id_to_name = get_system_call_names() + +# define syscalls for which we can look up filename from fd argument +# before the change for Python 3 +#syscall_name_to_id = dict((y,x) for x,y in syscall_id_to_name.iteritems()) +syscall_name_to_id = dict((y,x) for x,y in syscall_id_to_name.items()) + +syscalls_with_fd_arg = set([ + syscall_name_to_id.get('read' , 'N/A') + , syscall_name_to_id.get('write' , 'N/A') + , syscall_name_to_id.get('pread64' , 'N/A') + , syscall_name_to_id.get('pwrite64' , 'N/A') + , syscall_name_to_id.get('fsync' , 'N/A') + , syscall_name_to_id.get('fdatasync' , 'N/A') + , syscall_name_to_id.get('recvfrom' , 'N/A') + , syscall_name_to_id.get('sendto' , 'N/A') + , syscall_name_to_id.get('recvmsg' , 'N/A') + , syscall_name_to_id.get('sendmsg' , 'N/A') + , syscall_name_to_id.get('epoll_wait' , 'N/A') + , syscall_name_to_id.get('ioctl' , 'N/A') + , syscall_name_to_id.get('accept' , 'N/A') + , syscall_name_to_id.get('accept4' , 'N/A') + , syscall_name_to_id.get('getdents' , 'N/A') + , syscall_name_to_id.get('getdents64' , 'N/A') + , syscall_name_to_id.get('unlinkat' , 'N/A') + , syscall_name_to_id.get('fstat' , 'N/A') + , syscall_name_to_id.get('fstatfs' , 'N/A') + , syscall_name_to_id.get('newfstatat' , 'N/A') +# , syscall_name_to_id.get('openat' , 'N/A') +# , syscall_name_to_id.get('openat2' , 'N/A') + , syscall_name_to_id.get('readv' , 'N/A') + , syscall_name_to_id.get('writev' , 'N/A') + , syscall_name_to_id.get('preadv' , 'N/A') + , syscall_name_to_id.get('pwritev' , 'N/A') + , syscall_name_to_id.get('preadv2' , 'N/A') + , syscall_name_to_id.get('pwritev2' , 'N/A') + , syscall_name_to_id.get('splice' , 'N/A') +]) + +special_fds = { 0:'(stdin) ', 1:'(stdout)', 2:'(stderr)' } + +syscalls_with_sint_arg = set([ + syscall_name_to_id.get('wait4' , 'N/A') # arg0 is pid_t + , syscall_name_to_id.get('waitpid' , 'N/A') +]) + +def parse_syscall_sample(proc_source, sample): + tokens = sample.split() + if tokens[0] == 'running': + return (tokens[0], '', '', '', '', '', '', None, None) + else: + return tokens + + +trim_socket = re.compile(r'\d+') + +syscall = ProcSource('syscall', '/proc/%s/task/%s/syscall', [ + ('syscall_id', int, 0, lambda sn: -2 if sn == 'running' else int(sn)), + ('syscall', str, 0, lambda sn: syscall_id_to_name[sn]), # convert syscall_id via unistd_64.h into call name + ('arg0', str, 1), + ('arg1', str, 2), + ('arg2', str, 3), + ('arg3', str, 4), + ('arg4', str, 5), + ('arg5', str, 6), + ('esp', None, 7), # stack pointer + ('eip', None, 8), # program counter/instruction pointer + ('filename', str, 9, lambda fn: re.sub(trim_socket, '*', fn) if fn.split(':')[0] in ['socket','pipe'] else fn), + ('filename2', str, 9), + ('filenamesum',str, 9, lambda fn: re.sub(trim_socket, '*', fn)), + ('basename', str, 9, lambda fn: re.sub(trim_socket, '*', fn) if fn.split(':')[0] in ['socket','pipe'] else os.path.basename(fn)), # filename if syscall has fd as arg0 + ('dirname', str, 9, lambda fn: re.sub(trim_socket, '*', fn) if fn.split(':')[0] in ['socket','pipe'] else os.path.dirname(fn)), # filename if syscall has fd as arg0 +], None, +task_level=True, parse_sample=parse_syscall_sample) + + +### get file name from file descriptor ### +#filename = ProcSource('fd', '/proc/%s/task/%s/fd', [('wchan', str, 0)], ['wchan'], task_level=True) + +### process cmdline args ### +def parse_cmdline_sample(proc_source,sample): + # the cmdline entry may have spaces in it and happens to have a \000 in the end + # the split [] hack is due to postgres having some extra spaces in its cmdlines + return [sample.split('\000')[0].strip()] + +cmdline = ProcSource('cmdline', '/proc/%s/task/%s/cmdline', [('cmdline', str, 0)], ['cmdline'], task_level=True, parse_sample=parse_cmdline_sample) + +### wchan ### +wchan = ProcSource('wchan', '/proc/%s/task/%s/wchan', [('wchan', str, 0)], ['wchan'], task_level=True) + + +### io ### +def parse_io_sample(proc_source, sample): + return [line.split()[1] if line else '' for line in sample.split('\n')] + +io = ProcSource('io', '/proc/%s/task/%s/io', [ + ('rchar', int, 0), + ('wchar', int, 1), + ('syscr', int, 2), + ('syscw', int, 3), + ('read_bytes', int, 4), + ('write_bytes', int, 5), + ('cancelled_write_bytes', int, 6), +], None, +task_level=True, +parse_sample=parse_io_sample) + + + +### net/dev ### (not accounted at process level) +def read_net_samples(fh): + return fh.readlines()[2:] + + +def parse_net_sample(proc_source, sample): + fields = sample.split() + fields[0] = fields[0][:-1] + return fields + + +net = ProcSource('net', '/proc/%s/task/%s/net/dev', [ + ('iface', str, 0), + ('rx_bytes', str, 1), + ('rx_packets', str, 2), + ('rx_errs', str, 3), + ('rx_drop', str, 4), + ('rx_fifo', str, 5), + ('rx_frame', str, 6), + ('rx_compressed', str, 7), + ('rx_multicast', str, 8), + ('tx_bytes', str, 9), + ('tx_packets', str, 10), + ('tx_errs', str, 11), + ('tx_drop', str, 12), + ('tx_fifo', str, 13), + ('tx_colls', str, 14), + ('tx_carrier', str, 15), + ('tx_compressed', str, 16), +], None, +read_samples=read_net_samples, +parse_sample=parse_net_sample) + + + +### stack ### +def read_stack_samples(fh): + result = '' + + # reverse stack and ignore the (reversed) top frame 0xfffffffffffff + # | | + # v v + for x in fh.readlines()[::-1][1:]: + func = x.split(' ')[1].split('+')[0] + if func not in ['entry_SYSCALL_64_after_hwframe','do_syscall_64','el0t_64_sync_handler', + 'el0_svc', 'do_el0_svc', 'el0_svc_common.constprop.0', 'invoke_syscall.constprop.0' ]: + if result: # skip writing the 1st "->" + result += '->' + result += func + '()' + + return [result or '-'] + + +stack = ProcSource('stack', '/proc/%s/task/%s/stack', [ + ('kstack', str, 0), +], None, +task_level=True, +read_samples=read_stack_samples) + + + +### smaps ### +def read_smaps_samples(fh): + samples = [] + current_sample = '' + for line in fh.readlines(): + current_sample += line + if line[:7] == 'VmFlags': + samples.append(current_sample) + current_sample = '' + return samples + + +def parse_smaps_sample(proc_source, sample): + sample_values = [] + sample_lines = [l for l in sample.split('\n') if l != ''] + + header_tokens = sample_lines[0].split() + sample_values.extend(header_tokens[:5]) + sample_values.append(' '.join(header_tokens[5:])) + + for line in sample_lines[1:-1]: + n, kb, _ = line.split() + n = n[:-1].lower() + '_kb' + + # missing values take default parse function value: assume no order change, and that available_columns contains all possible field names + while len(sample_values) < len(proc_source.available_columns) and n != proc_source.available_columns[len(sample_values)][0]: + parse_fn = proc_source.available_columns[len(sample_values)][1] + sample_values.append(parse_fn()) + + if len(sample_values) < len(proc_source.available_columns): + sample_values.append(kb) + + while len(sample_values) < len(proc_source.available_columns) - 1: + parse_fn = proc_source.available_columns[len(sample_values)][1] + sample_values.append(parse_fn()) + + sample_values.append(' '.join(sample_lines[-1].split()[1:])) + return sample_values + + +smaps = ProcSource('smaps', '/proc/%s/smaps', [ + ('address_range', str, 0), + ('perms', str, 1), + ('offset', str, 2), + ('dev', str, 3), + ('inode', int, 4), + ('pathname', str, 5), + ('size_kb', int, 6), + ('rss_kb', int, 7), + ('pss_kb', int, 8), + ('shared_clean_kb', int, 9), + ('shared_dirty_kb', int, 10), + ('private_clean_kb', int, 11), + ('private_dirty_kb', int, 12), + ('referenced_kb', int, 13), + ('anonymous_kb', int, 14), + ('anonhugepages_kb', int, 15), + ('shmempmdmapped_kb', int, 16), + ('shared_hugetld_kb', int, 17), + ('private_hugetld_kb', int, 18), + ('swap_kb', int, 19), + ('swappss_kb', int, 20), + ('kernelpagesize_kb', int, 21), + ('mmupagesize_kb', int, 22), + ('locked_kb', int, 23), + ('vmflags', str, 24), +], None, +task_level=False, +read_samples=read_smaps_samples, +parse_sample=parse_smaps_sample) + + + + +all_sources = [stat, status, syscall, wchan, io, smaps, stack, cmdline] + diff --git a/lib/0xtools/psnreport.py b/lib/0xtools/psnreport.py new file mode 100644 index 0000000..b5f6bbf --- /dev/null +++ b/lib/0xtools/psnreport.py @@ -0,0 +1,201 @@ +# psn -- Linux Process Snapper by Tanel Poder [https://0x.tools] +# Copyright 2019-2021 Tanel Poder +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License along +# with this program; if not, write to the Free Software Foundation, Inc., +# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. +# +# SPDX-License-Identifier: GPL-2.0-or-later + +# query/report code + +from itertools import groupby +from datetime import datetime + +import psnproc as proc +import logging + +def flatten(li): + return [item for sublist in li for item in sublist] + + +### ASCII table output ### +def output_table_report(report, dataset): + max_field_width = 500 + header_fmts, field_fmts = [], [] + total_field_width = 0 + total_field_width_without_kstack = 0 + + if dataset: + col_idx = 0 + for source, cols, expr, token in report.full_projection(): + if token in ('pid', 'task', 'samples'): + col_type = int + elif token == 'event_time': + col_type = str + elif token == 'avg_threads': + col_type = float + elif cols: + col = [c for c in source.available_columns if c[0] == cols[0]][0] + col_type = col[1] + else: + col_type = str + + if col_type in (str, int, int): + max_field_length = max([len(str(row[col_idx])) for row in dataset]) + elif col_idx == float: + max_field_length = max([len(str(int(row[col_idx]))) for row in dataset]) + 3 # arbitrary! + + field_width = min(max_field_width, max(len(token), max_field_length)) + + # left-align strings both in header and data + if col_type == str: + header_fmts.append('%%-%s.%ss' % (field_width, field_width)) + else: + header_fmts.append('%%%s.%ss' % (field_width, field_width)) + + if col_type == str: + field_fmts.append('%%-%s.%ss' % (field_width, field_width)) + elif col_type in (int, int): + field_fmts.append('%%%sd' % field_width) + elif col_type == float: + field_fmts.append('%%%s.%sf' % (field_width, 2)) # arbitrary + + total_field_width += field_width + total_field_width_without_kstack += field_width if token != 'kstack' else 0 + col_idx += 1 + + report_width = total_field_width + (3 * (len(header_fmts) -1)) + 2 + hr = '-' * report_width + title_pad = report_width - len(report.name) - 2 + #title = '=== ' + report.name + ' ' + '=' * (title_pad - 29) + ' [' + datetime.now().strftime("%Y-%m-%d %H:%M:%S") + '] ===' + title = '=== ' + report.name + ' ' + '=' * (title_pad - 3) + header_fmt = ' ' + ' | '.join(header_fmts) + ' ' + field_fmt = ' ' + ' | '.join(field_fmts) + ' ' + + print("") + print(title) + print("") + if dataset: + print(header_fmt % tuple([c[3] for c in report.full_projection()])) + print(hr) + for row in dataset: + print(field_fmt % row) + else: + print('query returned no rows') + print("") + print("") + + + +class Report: + def __init__(self, name, projection, dimensions=[], where=[], order=[], output_fn=output_table_report): + def reify_column_token(col_token): + if col_token == 'samples': + return (None, [], 'COUNT(1)', col_token) + elif col_token == 'avg_threads': + return (None, [], 'CAST(COUNT(1) AS REAL) / %(num_sample_events)s', col_token) + elif col_token in ('pid', 'task', 'event_time'): + return ('first_source', [col_token], col_token, col_token) + + for t in proc.all_sources: + for c in t.schema_columns: + if col_token.lower() == c[0].lower(): + return (t, [c[0]], c[0], c[0]) + + raise Exception('projection/dimension column %s not found.\nUse psn --list to see all available columns' % col_token) + + def process_filter_sql(filter_sql): + idle_filter = "stat.state_id IN ('S', 'Z', 'I', 'P')" + + if filter_sql == 'active': + return (proc.stat, ['state_id'], 'not(%s)' % idle_filter, filter_sql) + elif filter_sql == 'idle': + return (proc.stat, ['state_id'], idle_filter, filter_sql) + else: + raise Exception('arbitrary filtering not implemented') + + self.name = name + self.projection = [reify_column_token(t) for t in projection if t] + self.dimensions = [reify_column_token(t) for t in dimensions if t] + self.order = [reify_column_token(t) for t in order if t] + self.where = [process_filter_sql(t) for t in where if t] + self.output_fn = output_fn + + # columns without a specific source are assigned the first source + first_source = [c[0] for c in (self.projection + self.dimensions + self.order + self.where) if c[0] and c[0] != 'first_source'][0] + self.projection = [(first_source if c[0] == 'first_source' else c[0], c[1], c[2], c[3]) for c in self.projection] + self.dimensions = [(first_source if c[0] == 'first_source' else c[0], c[1], c[2], c[3]) for c in self.dimensions] + self.order = [(first_source if c[0] == 'first_source' else c[0], c[1], c[2], c[3]) for c in self.order] + self.where = [(first_source if c[0] == 'first_source' else c[0], c[1], c[2], c[3]) for c in self.where] + + self.sources = {} # source -> [cols] + for d in [self.projection, self.dimensions, self.order, self.where]: + for source, column_names, expr, token in d: + source_columns = self.sources.get(source, ['pid', 'task', 'event_time']) + source_columns.extend(column_names) + self.sources[source] = source_columns + if None in self.sources: + del self.sources[None] + + + def full_projection(self): + return self.projection + [c for c in self.dimensions if c not in self.projection] + + + def query(self): + def render_col(c): + return '%s.%s' % (c[0].name, c[2]) if c[0] else c[2] + + # build join conditions + first_source_name = list(self.sources.keys())[0].name + join_where = flatten([['%s.%s = %s.%s' % (s.name, c, first_source_name, c) for c in ['pid', 'task', 'event_time']] for s in list(self.sources.keys())[1:]]) + + attr = { + 'projection': '\t' + ',\n\t'.join([render_col(c) for c in self.full_projection()]), + 'tables': '\t' + ',\n\t'.join([s.name for s in self.sources]), + 'where': '\t' + ' AND\n\t'.join([c[2] for c in self.where] + join_where), + 'dimensions': '\t' + ',\n\t'.join([render_col(c) for c in self.dimensions]), + 'order': '\t' + ',\n\t'.join([render_col(c) + ' DESC' for c in self.order]), + 'num_sample_events': '(SELECT COUNT(DISTINCT(event_time)) FROM %s)' % first_source_name + } + + logging.debug('attr where=%s#end' % attr['where']) + + sql = 'SELECT\n%(projection)s\nFROM\n%(tables)s' % attr + # tanel changed from self.where to attr['where'] + # TODO think through the logic of using self.where vs attr.where (in the context of allowing pid/tid to be not part of group by) + if attr['where'].strip(): + sql += '\nWHERE\n%(where)s' % attr + if attr['dimensions']: + sql += '\nGROUP BY\n%(dimensions)s' % attr + if attr['order']: + sql += '\nORDER BY\n%(order)s' % attr + + # final substitution allows things like avg_threads to work + return sql % attr + + + def dataset(self, conn): + logging.debug(self.query()) + r = conn.execute(self.query()).fetchall() + logging.debug('Done') + return r + + def output_report(self, conn): + self.output_fn(self, self.dataset(conn)) + + + + + |