Removed vendorized packages.

This commit is contained in:
Kenneth Reitz
2010-09-13 16:06:14 -04:00
parent 89209b6bd3
commit 5b42824871
45 changed files with 0 additions and 11532 deletions
-1
View File
@@ -1 +0,0 @@
all = ['simplejson', 'typecheck', 'xlwt', 'opster']
-612
View File
@@ -1,612 +0,0 @@
# (c) Alexander Solovyov, 2009, under terms of the new BSD License
'''Command line arguments parser
'''
import sys, traceback, getopt, types, textwrap, inspect, os
from itertools import imap
__all__ = ['command', 'dispatch']
__version__ = '0.9.10'
__author__ = 'Alexander Solovyov'
__email__ = 'piranha@piranha.org.ua'
write = sys.stdout.write
err = sys.stderr.write
CMDTABLE = {}
# --------
# Public interface
# --------
def command(options=None, usage=None, name=None, shortlist=False, hide=False):
'''Decorator to mark function to be used for command line processing.
All arguments are optional:
- ``options``: options in format described in docs. If not supplied,
will be determined from function.
- ``usage``: usage string for function, replaces ``%name`` with name
of program or subcommand. In case if it's subcommand and ``%name``
is not present, usage is prepended by ``name``
- ``name``: used for multiple subcommands. Defaults to wrapped
function name
- ``shortlist``: if command should be included in shortlist. Used
only with multiple subcommands
- ``hide``: if command should be hidden from help listing. Used only
with multiple subcommands, overrides ``shortlist``
'''
def wrapper(func):
try:
options_ = list(guess_options(func))
except TypeError:
options_ = []
try:
options_ = options_ + list(options)
except TypeError:
pass
name_ = name or func.__name__.replace('_', '-')
if usage is None:
usage_ = guess_usage(func, options_)
else:
usage_ = usage
prefix = hide and '~' or (shortlist and '^' or '')
CMDTABLE[prefix + name_] = (func, options_, usage_)
def help_func(name=None):
return help_cmd(func, replace_name(usage_, sysname()), options_)
@wraps(func)
def inner(*args, **opts):
# look if we need to add 'help' option
try:
(True for option in reversed(options_)
if option[1] == 'help').next()
except StopIteration:
options_.append(('h', 'help', False, 'show help'))
argv = opts.pop('argv', sys.argv[1:])
if opts.pop('help', False):
return help_func()
if args or opts:
# no catcher here because this is call from Python
return call_cmd_regular(func, options_)(*args, **opts)
try:
opts, args = catcher(lambda: parse(argv, options_), help_func)
except Abort:
return -1
try:
if opts.pop('help', False):
return help_func()
return catcher(lambda: call_cmd(name_, func)(*args, **opts),
help_func)
except Abort:
return -1
return inner
return wrapper
def dispatch(args=None, cmdtable=None, globaloptions=None,
middleware=lambda x: x):
'''Dispatch command arguments based on subcommands.
- ``args``: list of arguments, default: ``sys.argv[1:]``
- ``cmdtable``: dict of commands in format described below.
If not supplied, will use functions decorated with ``@command``.
- ``globaloptions``: list of options which are applied to all
commands, will contain ``--help`` option at least.
- ``middleware``: global decorator for all commands.
cmdtable format description::
{'name': (function, options, usage)}
- ``name`` is the name used on command-line. Can contain aliases
(separate them with ``|``), pointer to a fact that this command
should be displayed in short help (start name with ``^``), or to
a fact that this command should be hidden (start name with ``~``)
- ``function`` is the actual callable
- ``options`` is options list in format described in docs
- ``usage`` is the short string of usage
'''
args = args or sys.argv[1:]
cmdtable = cmdtable or CMDTABLE
globaloptions = globaloptions or []
globaloptions.append(('h', 'help', False, 'display help'))
cmdtable['help'] = (help_(cmdtable, globaloptions), [], '[TOPIC]')
help_func = cmdtable['help'][0]
autocomplete(cmdtable, args)
try:
name, func, args, kwargs = catcher(
lambda: _dispatch(args, cmdtable, globaloptions),
help_func)
return catcher(
lambda: call_cmd(name, middleware(func))(*args, **kwargs),
help_func)
except Abort:
return -1
# --------
# Help
# --------
def help_(cmdtable, globalopts):
def help_inner(name=None):
'''Show help for a given help topic or a help overview
With no arguments, print a list of commands with short help messages.
Given a command name, print help for that command.
'''
def helplist():
hlp = {}
# determine if any command is marked for shortlist
shortlist = (name == 'shortlist' and
any(imap(lambda x: x.startswith('^'), cmdtable)))
for cmd, info in cmdtable.items():
if cmd.startswith('~'):
continue # do not display hidden commands
if shortlist and not cmd.startswith('^'):
continue # short help contains only marked commands
cmd = cmd.lstrip('^~')
doc = info[0].__doc__ or '(no help text available)'
hlp[cmd] = doc.splitlines()[0].rstrip()
hlplist = sorted(hlp)
maxlen = max(map(len, hlplist))
write('usage: %s <command> [options]\n' % sysname())
write('\ncommands:\n\n')
for cmd in hlplist:
doc = hlp[cmd]
if False: # verbose?
write(' %s:\n %s\n' % (cmd.replace('|', ', '), doc))
else:
write(' %-*s %s\n' % (maxlen, cmd.split('|', 1)[0],
doc))
if not cmdtable:
return err('No commands specified!\n')
if not name or name == 'shortlist':
return helplist()
aliases, (cmd, options, usage) = findcmd(name, cmdtable)
return help_cmd(cmd,
replace_name(usage, sysname() + ' ' + aliases[0]),
options + globalopts)
return help_inner
def help_cmd(func, usage, options):
'''show help for given command
- ``func``: function to generate help for (``func.__doc__`` is taken)
- ``usage``: usage string
- ``options``: options in usual format
>>> def test(*args, **opts):
... """that's a test command
...
... you can do nothing with this command"""
... pass
>>> opts = [('l', 'listen', 'localhost',
... 'ip to listen on'),
... ('p', 'port', 8000,
... 'port to listen on'),
... ('d', 'daemonize', False,
... 'daemonize process'),
... ('', 'pid-file', '',
... 'name of file to write process ID to')]
>>> help_cmd(test, 'test [-l HOST] [NAME]', opts)
test [-l HOST] [NAME]
<BLANKLINE>
that's a test command
<BLANKLINE>
you can do nothing with this command
<BLANKLINE>
options:
<BLANKLINE>
-l --listen ip to listen on (default: localhost)
-p --port port to listen on (default: 8000)
-d --daemonize daemonize process
--pid-file name of file to write process ID to
<BLANKLINE>
'''
write(usage + '\n')
doc = func.__doc__
if not doc:
doc = '(no help text available)'
write('\n' + doc.strip() + '\n\n')
if options:
write(''.join(help_options(options)))
def help_options(options):
yield 'options:\n\n'
output = []
for short, name, default, desc in options:
if hasattr(default, '__call__'):
default = default(None)
default = default and ' (default: %s)' % default or ''
output.append(('%2s%s' % (short and '-%s' % short,
name and ' --%s' % name),
'%s%s' % (desc, default)))
opts_len = max([len(first) for first, second in output if second] or [0])
for first, second in output:
if second:
# wrap description at 78 chars
second = textwrap.wrap(second, width=(78 - opts_len - 3))
pad = '\n' + ' ' * (opts_len + 3)
yield ' %-*s %s\n' % (opts_len, first, pad.join(second))
else:
yield '%s\n' % first
# --------
# Options parsing
# --------
def parse(args, options):
'''
>>> opts = [('l', 'listen', 'localhost',
... 'ip to listen on'),
... ('p', 'port', 8000,
... 'port to listen on'),
... ('d', 'daemonize', False,
... 'daemonize process'),
... ('', 'pid-file', '',
... 'name of file to write process ID to')]
>>> print parse(['-l', '0.0.0.0', '--pi', 'test', 'all'], opts)
({'pid_file': 'test', 'daemonize': False, 'port': 8000, 'listen': '0.0.0.0'}, ['all'])
'''
argmap, defmap, state = {}, {}, {}
shortlist, namelist, funlist = '', [], []
for short, name, default, comment in options:
if short and len(short) != 1:
raise FOError('Short option should be only a single'
' character: %s' % short)
if not name:
raise FOError(
'Long name should be defined for every option')
# change name to match Python styling
pyname = name.replace('-', '_')
argmap['-' + short] = argmap['--' + name] = pyname
defmap[pyname] = default
# copy defaults to state
if isinstance(default, list):
state[pyname] = default[:]
elif hasattr(default, '__call__'):
funlist.append(pyname)
state[pyname] = None
else:
state[pyname] = default
# getopt wants indication that it takes a parameter
if not (default is None or default is True or default is False):
if short: short += ':'
if name: name += '='
if short:
shortlist += short
if name:
namelist.append(name)
opts, args = getopt.gnu_getopt(args, shortlist, namelist)
# transfer result to state
for opt, val in opts:
name = argmap[opt]
t = type(defmap[name])
if t is types.FunctionType:
del funlist[funlist.index(name)]
state[name] = defmap[name](val)
elif t is types.ListType:
state[name].append(val)
elif t in (types.NoneType, types.BooleanType):
state[name] = not defmap[name]
else:
state[name] = t(val)
for name in funlist:
state[name] = defmap[name](None)
return state, args
# --------
# Subcommand system
# --------
def _dispatch(args, cmdtable, globalopts):
cmd, func, args, options = cmdparse(args, cmdtable, globalopts)
if options.pop('help', False):
return 'help', cmdtable['help'][0], [cmd], {}
elif not cmd:
return 'help', cmdtable['help'][0], ['shortlist'], {}
return cmd, func, args, options
def cmdparse(args, cmdtable, globalopts):
# command is the first non-option
cmd = None
for arg in args:
if not arg.startswith('-'):
cmd = arg
break
if cmd:
args.pop(args.index(cmd))
aliases, info = findcmd(cmd, cmdtable)
cmd = aliases[0]
possibleopts = list(info[1])
else:
possibleopts = []
possibleopts.extend(globalopts)
try:
options, args = parse(args, possibleopts)
except getopt.GetoptError, e:
raise ParseError(cmd, e)
return (cmd, cmd and info[0] or None, args, options)
def aliases_(cmdtable_key):
return cmdtable_key.lstrip("^~").split("|")
def findpossible(cmd, table):
"""
Return cmd -> (aliases, command table entry)
for each matching command.
"""
choice = {}
for e in table.keys():
aliases = aliases_(e)
found = None
if cmd in aliases:
found = cmd
else:
for a in aliases:
if a.startswith(cmd):
found = a
break
if found is not None:
choice[found] = (aliases, table[e])
return choice
def findcmd(cmd, table):
"""Return (aliases, command table entry) for command string."""
choice = findpossible(cmd, table)
if cmd in choice:
return choice[cmd]
if len(choice) > 1:
clist = choice.keys()
clist.sort()
raise AmbiguousCommand(cmd, clist)
if choice:
return choice.values()[0]
raise UnknownCommand(cmd)
# --------
# Helpers
# --------
def guess_options(func):
args, varargs, varkw, defaults = inspect.getargspec(func)
for name, option in zip(args[-len(defaults):], defaults):
try:
sname, default, hlp = option
yield (sname, name.replace('_', '-'), default, hlp)
except TypeError:
pass
def guess_usage(func, options):
usage = '%name '
if options:
usage += '[OPTIONS] '
args, varargs = inspect.getargspec(func)[:2]
argnum = len(args) - len(options)
if argnum > 0:
usage += args[0].upper()
if argnum > 1:
usage += 'S'
elif varargs:
usage += '[%s]' % varargs.upper()
return usage
def catcher(target, help_func):
'''Catches all exceptions and prints human-readable information on them
'''
try:
return target()
except UnknownCommand, e:
err("unknown command: '%s'\n" % e)
except AmbiguousCommand, e:
err("command '%s' is ambiguous:\n %s\n" %
(e.args[0], ' '.join(e.args[1])))
except ParseError, e:
err('%s: %s\n' % (e.args[0], e.args[1]))
help_func(e.args[0])
except getopt.GetoptError, e:
err('error: %s\n' % e)
help_func()
except FOError, e:
err('%s\n' % e)
except KeyboardInterrupt:
err('interrupted!\n')
except SystemExit:
raise
except:
err('unknown exception encountered')
raise
raise Abort
def call_cmd(name, func):
def inner(*args, **kwargs):
try:
return func(*args, **kwargs)
except TypeError:
if len(traceback.extract_tb(sys.exc_info()[2])) == 1:
raise ParseError(name, "invalid arguments")
raise
return inner
def call_cmd_regular(func, opts):
def inner(*args, **kwargs):
funcargs, _, varkw, defaults = inspect.getargspec(func)
if len(args) > len(funcargs):
raise TypeError('You have supplied more positional arguments'
' than applicable')
funckwargs = dict((lname.replace('-', '_'), default)
for _, lname, default, _ in opts)
if 'help' not in (defaults or ()) and not varkw:
funckwargs.pop('help', None)
funckwargs.update(kwargs)
return func(*args, **funckwargs)
return inner
def replace_name(usage, name):
if '%name' in usage:
return usage.replace('%name', name, 1)
return name + ' ' + usage
def sysname():
name = sys.argv[0]
if name.startswith('./'):
return name[2:]
return name
try:
from functools import wraps
except ImportError:
def wraps(wrapped, assigned=('__module__', '__name__', '__doc__'),
updated=('__dict__',)):
def inner(wrapper):
for attr in assigned:
setattr(wrapper, attr, getattr(wrapped, attr))
for attr in updated:
getattr(wrapper, attr).update(getattr(wrapped, attr, {}))
return wrapper
return inner
# --------
# Autocomplete system
# --------
# Borrowed from PIP
def autocomplete(cmdtable, args):
"""Command and option completion.
Enable by sourcing one of the completion shell scripts (bash or zsh).
"""
# Don't complete if user hasn't sourced bash_completion file.
if not os.environ.has_key('OPSTER_AUTO_COMPLETE'):
return
cwords = os.environ['COMP_WORDS'].split()[1:]
cword = int(os.environ['COMP_CWORD'])
try:
current = cwords[cword-1]
except IndexError:
current = ''
commands = []
for k in cmdtable.keys():
commands += aliases_(k)
# command
if cword == 1:
print ' '.join(filter(lambda x: x.startswith(current), commands))
# command options
elif cwords[0] in commands:
options = []
aliases, (cmd, opts, usage) = findcmd(cwords[0], cmdtable)
for (short, long, default, help) in opts:
options.append('-%s' % short)
options.append('--%s' % long)
options = [o for o in options if o.startswith(current)]
print ' '.join(filter(lambda x: x.startswith(current), options))
sys.exit(1)
COMPLETIONS = {
'bash':
"""
# opster bash completion start
_opster_completion()
{
COMPREPLY=( $( COMP_WORDS="${COMP_WORDS[*]}" \\
COMP_CWORD=$COMP_CWORD \\
OPSTER_AUTO_COMPLETE=1 $1 ) )
}
complete -o default -F _opster_completion %s
# opster bash completion end
""",
'zsh':
"""
# opster zsh completion start
function _opster_completion {
local words cword
read -Ac words
read -cn cword
reply=( $( COMP_WORDS="$words[*]" \\
COMP_CWORD=$(( cword-1 )) \\
OPSTER_AUTO_COMPLETE=1 $words[1] ) )
}
compctl -K _opster_completion %s
# opster zsh completion end
"""
}
@command(name='_completion', hide=True)
def completion(type=('t', 'bash', 'Completion type (bash or zsh)')):
"""Outputs completion script for bash or zsh."""
prog_name = os.path.split(sys.argv[0])[1]
print COMPLETIONS[type] % prog_name
# --------
# Exceptions
# --------
# Command exceptions
class CommandException(Exception):
'Base class for command exceptions'
class AmbiguousCommand(CommandException):
'Raised if command is ambiguous'
class UnknownCommand(CommandException):
'Raised if command is unknown'
class ParseError(CommandException):
'Raised on error in command line parsing'
class Abort(CommandException):
'Abort execution'
class FOError(CommandException):
'Raised on trouble with opster configuration'
-437
View File
@@ -1,437 +0,0 @@
r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of
JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data
interchange format.
:mod:`simplejson` exposes an API familiar to users of the standard library
:mod:`marshal` and :mod:`pickle` modules. It is the externally maintained
version of the :mod:`json` library contained in Python 2.6, but maintains
compatibility with Python 2.4 and Python 2.5 and (currently) has
significant performance advantages, even without using the optional C
extension for speedups.
Encoding basic Python object hierarchies::
>>> import simplejson as json
>>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}])
'["foo", {"bar": ["baz", null, 1.0, 2]}]'
>>> print json.dumps("\"foo\bar")
"\"foo\bar"
>>> print json.dumps(u'\u1234')
"\u1234"
>>> print json.dumps('\\')
"\\"
>>> print json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)
{"a": 0, "b": 0, "c": 0}
>>> from StringIO import StringIO
>>> io = StringIO()
>>> json.dump(['streaming API'], io)
>>> io.getvalue()
'["streaming API"]'
Compact encoding::
>>> import simplejson as json
>>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':'))
'[1,2,3,{"4":5,"6":7}]'
Pretty printing::
>>> import simplejson as json
>>> s = json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=' ')
>>> print '\n'.join([l.rstrip() for l in s.splitlines()])
{
"4": 5,
"6": 7
}
Decoding JSON::
>>> import simplejson as json
>>> obj = [u'foo', {u'bar': [u'baz', None, 1.0, 2]}]
>>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj
True
>>> json.loads('"\\"foo\\bar"') == u'"foo\x08ar'
True
>>> from StringIO import StringIO
>>> io = StringIO('["streaming API"]')
>>> json.load(io)[0] == 'streaming API'
True
Specializing JSON object decoding::
>>> import simplejson as json
>>> def as_complex(dct):
... if '__complex__' in dct:
... return complex(dct['real'], dct['imag'])
... return dct
...
>>> json.loads('{"__complex__": true, "real": 1, "imag": 2}',
... object_hook=as_complex)
(1+2j)
>>> from decimal import Decimal
>>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1')
True
Specializing JSON object encoding::
>>> import simplejson as json
>>> def encode_complex(obj):
... if isinstance(obj, complex):
... return [obj.real, obj.imag]
... raise TypeError(repr(o) + " is not JSON serializable")
...
>>> json.dumps(2 + 1j, default=encode_complex)
'[2.0, 1.0]'
>>> json.JSONEncoder(default=encode_complex).encode(2 + 1j)
'[2.0, 1.0]'
>>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j))
'[2.0, 1.0]'
Using simplejson.tool from the shell to validate and pretty-print::
$ echo '{"json":"obj"}' | python -m simplejson.tool
{
"json": "obj"
}
$ echo '{ 1.2:3.4}' | python -m simplejson.tool
Expecting property name: line 1 column 2 (char 2)
"""
__version__ = '2.1.1'
__all__ = [
'dump', 'dumps', 'load', 'loads',
'JSONDecoder', 'JSONDecodeError', 'JSONEncoder',
'OrderedDict',
]
__author__ = 'Bob Ippolito <bob@redivi.com>'
from decimal import Decimal
from decoder import JSONDecoder, JSONDecodeError
from encoder import JSONEncoder
def _import_OrderedDict():
import collections
try:
return collections.OrderedDict
except AttributeError:
import ordered_dict
return ordered_dict.OrderedDict
OrderedDict = _import_OrderedDict()
def _import_c_make_encoder():
try:
from simplejson._speedups import make_encoder
return make_encoder
except ImportError:
return None
_default_encoder = JSONEncoder(
skipkeys=False,
ensure_ascii=True,
check_circular=True,
allow_nan=True,
indent=None,
separators=None,
encoding='utf-8',
default=None,
use_decimal=False,
)
def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
allow_nan=True, cls=None, indent=None, separators=None,
encoding='utf-8', default=None, use_decimal=False, **kw):
"""Serialize ``obj`` as a JSON formatted stream to ``fp`` (a
``.write()``-supporting file-like object).
If ``skipkeys`` is true then ``dict`` keys that are not basic types
(``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
will be skipped instead of raising a ``TypeError``.
If ``ensure_ascii`` is false, then the some chunks written to ``fp``
may be ``unicode`` instances, subject to normal Python ``str`` to
``unicode`` coercion rules. Unless ``fp.write()`` explicitly
understands ``unicode`` (as in ``codecs.getwriter()``) this is likely
to cause an error.
If ``check_circular`` is false, then the circular reference check
for container types will be skipped and a circular reference will
result in an ``OverflowError`` (or worse).
If ``allow_nan`` is false, then it will be a ``ValueError`` to
serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``)
in strict compliance of the JSON specification, instead of using the
JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
If *indent* is a string, then JSON array elements and object members
will be pretty-printed with a newline followed by that string repeated
for each level of nesting. ``None`` (the default) selects the most compact
representation without any newlines. For backwards compatibility with
versions of simplejson earlier than 2.1.0, an integer is also accepted
and is converted to a string with that many spaces.
If ``separators`` is an ``(item_separator, dict_separator)`` tuple
then it will be used instead of the default ``(', ', ': ')`` separators.
``(',', ':')`` is the most compact JSON representation.
``encoding`` is the character encoding for str instances, default is UTF-8.
``default(obj)`` is a function that should return a serializable version
of obj or raise TypeError. The default simply raises TypeError.
If *use_decimal* is true (default: ``False``) then decimal.Decimal
will be natively serialized to JSON with full precision.
To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
``.default()`` method to serialize additional types), specify it with
the ``cls`` kwarg.
"""
# cached encoder
if (not skipkeys and ensure_ascii and
check_circular and allow_nan and
cls is None and indent is None and separators is None and
encoding == 'utf-8' and default is None and not kw):
iterable = _default_encoder.iterencode(obj)
else:
if cls is None:
cls = JSONEncoder
iterable = cls(skipkeys=skipkeys, ensure_ascii=ensure_ascii,
check_circular=check_circular, allow_nan=allow_nan, indent=indent,
separators=separators, encoding=encoding,
default=default, use_decimal=use_decimal, **kw).iterencode(obj)
# could accelerate with writelines in some versions of Python, at
# a debuggability cost
for chunk in iterable:
fp.write(chunk)
def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
allow_nan=True, cls=None, indent=None, separators=None,
encoding='utf-8', default=None, use_decimal=False, **kw):
"""Serialize ``obj`` to a JSON formatted ``str``.
If ``skipkeys`` is false then ``dict`` keys that are not basic types
(``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
will be skipped instead of raising a ``TypeError``.
If ``ensure_ascii`` is false, then the return value will be a
``unicode`` instance subject to normal Python ``str`` to ``unicode``
coercion rules instead of being escaped to an ASCII ``str``.
If ``check_circular`` is false, then the circular reference check
for container types will be skipped and a circular reference will
result in an ``OverflowError`` (or worse).
If ``allow_nan`` is false, then it will be a ``ValueError`` to
serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in
strict compliance of the JSON specification, instead of using the
JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
If ``indent`` is a string, then JSON array elements and object members
will be pretty-printed with a newline followed by that string repeated
for each level of nesting. ``None`` (the default) selects the most compact
representation without any newlines. For backwards compatibility with
versions of simplejson earlier than 2.1.0, an integer is also accepted
and is converted to a string with that many spaces.
If ``separators`` is an ``(item_separator, dict_separator)`` tuple
then it will be used instead of the default ``(', ', ': ')`` separators.
``(',', ':')`` is the most compact JSON representation.
``encoding`` is the character encoding for str instances, default is UTF-8.
``default(obj)`` is a function that should return a serializable version
of obj or raise TypeError. The default simply raises TypeError.
If *use_decimal* is true (default: ``False``) then decimal.Decimal
will be natively serialized to JSON with full precision.
To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
``.default()`` method to serialize additional types), specify it with
the ``cls`` kwarg.
"""
# cached encoder
if (not skipkeys and ensure_ascii and
check_circular and allow_nan and
cls is None and indent is None and separators is None and
encoding == 'utf-8' and default is None and not use_decimal
and not kw):
return _default_encoder.encode(obj)
if cls is None:
cls = JSONEncoder
return cls(
skipkeys=skipkeys, ensure_ascii=ensure_ascii,
check_circular=check_circular, allow_nan=allow_nan, indent=indent,
separators=separators, encoding=encoding, default=default,
use_decimal=use_decimal, **kw).encode(obj)
_default_decoder = JSONDecoder(encoding=None, object_hook=None,
object_pairs_hook=None)
def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
parse_int=None, parse_constant=None, object_pairs_hook=None,
use_decimal=False, **kw):
"""Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
a JSON document) to a Python object.
*encoding* determines the encoding used to interpret any
:class:`str` objects decoded by this instance (``'utf-8'`` by
default). It has no effect when decoding :class:`unicode` objects.
Note that currently only encodings that are a superset of ASCII work,
strings of other encodings should be passed in as :class:`unicode`.
*object_hook*, if specified, will be called with the result of every
JSON object decoded and its return value will be used in place of the
given :class:`dict`. This can be used to provide custom
deserializations (e.g. to support JSON-RPC class hinting).
*object_pairs_hook* is an optional function that will be called with
the result of any object literal decode with an ordered list of pairs.
The return value of *object_pairs_hook* will be used instead of the
:class:`dict`. This feature can be used to implement custom decoders
that rely on the order that the key and value pairs are decoded (for
example, :func:`collections.OrderedDict` will remember the order of
insertion). If *object_hook* is also defined, the *object_pairs_hook*
takes priority.
*parse_float*, if specified, will be called with the string of every
JSON float to be decoded. By default, this is equivalent to
``float(num_str)``. This can be used to use another datatype or parser
for JSON floats (e.g. :class:`decimal.Decimal`).
*parse_int*, if specified, will be called with the string of every
JSON int to be decoded. By default, this is equivalent to
``int(num_str)``. This can be used to use another datatype or parser
for JSON integers (e.g. :class:`float`).
*parse_constant*, if specified, will be called with one of the
following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
can be used to raise an exception if invalid JSON numbers are
encountered.
If *use_decimal* is true (default: ``False``) then it implies
parse_float=decimal.Decimal for parity with ``dump``.
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
kwarg.
"""
return loads(fp.read(),
encoding=encoding, cls=cls, object_hook=object_hook,
parse_float=parse_float, parse_int=parse_int,
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook,
use_decimal=use_decimal, **kw)
def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
parse_int=None, parse_constant=None, object_pairs_hook=None,
use_decimal=False, **kw):
"""Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON
document) to a Python object.
*encoding* determines the encoding used to interpret any
:class:`str` objects decoded by this instance (``'utf-8'`` by
default). It has no effect when decoding :class:`unicode` objects.
Note that currently only encodings that are a superset of ASCII work,
strings of other encodings should be passed in as :class:`unicode`.
*object_hook*, if specified, will be called with the result of every
JSON object decoded and its return value will be used in place of the
given :class:`dict`. This can be used to provide custom
deserializations (e.g. to support JSON-RPC class hinting).
*object_pairs_hook* is an optional function that will be called with
the result of any object literal decode with an ordered list of pairs.
The return value of *object_pairs_hook* will be used instead of the
:class:`dict`. This feature can be used to implement custom decoders
that rely on the order that the key and value pairs are decoded (for
example, :func:`collections.OrderedDict` will remember the order of
insertion). If *object_hook* is also defined, the *object_pairs_hook*
takes priority.
*parse_float*, if specified, will be called with the string of every
JSON float to be decoded. By default, this is equivalent to
``float(num_str)``. This can be used to use another datatype or parser
for JSON floats (e.g. :class:`decimal.Decimal`).
*parse_int*, if specified, will be called with the string of every
JSON int to be decoded. By default, this is equivalent to
``int(num_str)``. This can be used to use another datatype or parser
for JSON integers (e.g. :class:`float`).
*parse_constant*, if specified, will be called with one of the
following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
can be used to raise an exception if invalid JSON numbers are
encountered.
If *use_decimal* is true (default: ``False``) then it implies
parse_float=decimal.Decimal for parity with ``dump``.
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
kwarg.
"""
if (cls is None and encoding is None and object_hook is None and
parse_int is None and parse_float is None and
parse_constant is None and object_pairs_hook is None
and not use_decimal and not kw):
return _default_decoder.decode(s)
if cls is None:
cls = JSONDecoder
if object_hook is not None:
kw['object_hook'] = object_hook
if object_pairs_hook is not None:
kw['object_pairs_hook'] = object_pairs_hook
if parse_float is not None:
kw['parse_float'] = parse_float
if parse_int is not None:
kw['parse_int'] = parse_int
if parse_constant is not None:
kw['parse_constant'] = parse_constant
if use_decimal:
if parse_float is not None:
raise TypeError("use_decimal=True implies parse_float=Decimal")
kw['parse_float'] = Decimal
return cls(encoding=encoding, **kw).decode(s)
def _toggle_speedups(enabled):
import simplejson.decoder as dec
import simplejson.encoder as enc
import simplejson.scanner as scan
c_make_encoder = _import_c_make_encoder()
if enabled:
dec.scanstring = dec.c_scanstring or dec.py_scanstring
enc.c_make_encoder = c_make_encoder
enc.encode_basestring_ascii = (enc.c_encode_basestring_ascii or
enc.py_encode_basestring_ascii)
scan.make_scanner = scan.c_make_scanner or scan.py_make_scanner
else:
dec.scanstring = dec.py_scanstring
enc.c_make_encoder = None
enc.encode_basestring_ascii = enc.py_encode_basestring_ascii
scan.make_scanner = scan.py_make_scanner
dec.make_scanner = scan.make_scanner
global _default_decoder
_default_decoder = JSONDecoder(
encoding=None,
object_hook=None,
object_pairs_hook=None,
)
global _default_encoder
_default_encoder = JSONEncoder(
skipkeys=False,
ensure_ascii=True,
check_circular=True,
allow_nan=True,
indent=None,
separators=None,
encoding='utf-8',
default=None,
)
File diff suppressed because it is too large Load Diff
-421
View File
@@ -1,421 +0,0 @@
"""Implementation of JSONDecoder
"""
import re
import sys
import struct
from simplejson.scanner import make_scanner
def _import_c_scanstring():
try:
from simplejson._speedups import scanstring
return scanstring
except ImportError:
return None
c_scanstring = _import_c_scanstring()
__all__ = ['JSONDecoder']
FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
def _floatconstants():
_BYTES = '7FF80000000000007FF0000000000000'.decode('hex')
# The struct module in Python 2.4 would get frexp() out of range here
# when an endian is specified in the format string. Fixed in Python 2.5+
if sys.byteorder != 'big':
_BYTES = _BYTES[:8][::-1] + _BYTES[8:][::-1]
nan, inf = struct.unpack('dd', _BYTES)
return nan, inf, -inf
NaN, PosInf, NegInf = _floatconstants()
class JSONDecodeError(ValueError):
"""Subclass of ValueError with the following additional properties:
msg: The unformatted error message
doc: The JSON document being parsed
pos: The start index of doc where parsing failed
end: The end index of doc where parsing failed (may be None)
lineno: The line corresponding to pos
colno: The column corresponding to pos
endlineno: The line corresponding to end (may be None)
endcolno: The column corresponding to end (may be None)
"""
def __init__(self, msg, doc, pos, end=None):
ValueError.__init__(self, errmsg(msg, doc, pos, end=end))
self.msg = msg
self.doc = doc
self.pos = pos
self.end = end
self.lineno, self.colno = linecol(doc, pos)
if end is not None:
self.endlineno, self.endcolno = linecol(doc, pos)
else:
self.endlineno, self.endcolno = None, None
def linecol(doc, pos):
lineno = doc.count('\n', 0, pos) + 1
if lineno == 1:
colno = pos
else:
colno = pos - doc.rindex('\n', 0, pos)
return lineno, colno
def errmsg(msg, doc, pos, end=None):
# Note that this function is called from _speedups
lineno, colno = linecol(doc, pos)
if end is None:
#fmt = '{0}: line {1} column {2} (char {3})'
#return fmt.format(msg, lineno, colno, pos)
fmt = '%s: line %d column %d (char %d)'
return fmt % (msg, lineno, colno, pos)
endlineno, endcolno = linecol(doc, end)
#fmt = '{0}: line {1} column {2} - line {3} column {4} (char {5} - {6})'
#return fmt.format(msg, lineno, colno, endlineno, endcolno, pos, end)
fmt = '%s: line %d column %d - line %d column %d (char %d - %d)'
return fmt % (msg, lineno, colno, endlineno, endcolno, pos, end)
_CONSTANTS = {
'-Infinity': NegInf,
'Infinity': PosInf,
'NaN': NaN,
}
STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
BACKSLASH = {
'"': u'"', '\\': u'\\', '/': u'/',
'b': u'\b', 'f': u'\f', 'n': u'\n', 'r': u'\r', 't': u'\t',
}
DEFAULT_ENCODING = "utf-8"
def py_scanstring(s, end, encoding=None, strict=True,
_b=BACKSLASH, _m=STRINGCHUNK.match):
"""Scan the string s for a JSON string. End is the index of the
character in s after the quote that started the JSON string.
Unescapes all valid JSON string escape sequences and raises ValueError
on attempt to decode an invalid string. If strict is False then literal
control characters are allowed in the string.
Returns a tuple of the decoded string and the index of the character in s
after the end quote."""
if encoding is None:
encoding = DEFAULT_ENCODING
chunks = []
_append = chunks.append
begin = end - 1
while 1:
chunk = _m(s, end)
if chunk is None:
raise JSONDecodeError(
"Unterminated string starting at", s, begin)
end = chunk.end()
content, terminator = chunk.groups()
# Content is contains zero or more unescaped string characters
if content:
if not isinstance(content, unicode):
content = unicode(content, encoding)
_append(content)
# Terminator is the end of string, a literal control character,
# or a backslash denoting that an escape sequence follows
if terminator == '"':
break
elif terminator != '\\':
if strict:
msg = "Invalid control character %r at" % (terminator,)
#msg = "Invalid control character {0!r} at".format(terminator)
raise JSONDecodeError(msg, s, end)
else:
_append(terminator)
continue
try:
esc = s[end]
except IndexError:
raise JSONDecodeError(
"Unterminated string starting at", s, begin)
# If not a unicode escape sequence, must be in the lookup table
if esc != 'u':
try:
char = _b[esc]
except KeyError:
msg = "Invalid \\escape: " + repr(esc)
raise JSONDecodeError(msg, s, end)
end += 1
else:
# Unicode escape sequence
esc = s[end + 1:end + 5]
next_end = end + 5
if len(esc) != 4:
msg = "Invalid \\uXXXX escape"
raise JSONDecodeError(msg, s, end)
uni = int(esc, 16)
# Check for surrogate pair on UCS-4 systems
if 0xd800 <= uni <= 0xdbff and sys.maxunicode > 65535:
msg = "Invalid \\uXXXX\\uXXXX surrogate pair"
if not s[end + 5:end + 7] == '\\u':
raise JSONDecodeError(msg, s, end)
esc2 = s[end + 7:end + 11]
if len(esc2) != 4:
raise JSONDecodeError(msg, s, end)
uni2 = int(esc2, 16)
uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
next_end += 6
char = unichr(uni)
end = next_end
# Append the unescaped character
_append(char)
return u''.join(chunks), end
# Use speedup if available
scanstring = c_scanstring or py_scanstring
WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)
WHITESPACE_STR = ' \t\n\r'
def JSONObject((s, end), encoding, strict, scan_once, object_hook,
object_pairs_hook, memo=None,
_w=WHITESPACE.match, _ws=WHITESPACE_STR):
# Backwards compatibility
if memo is None:
memo = {}
memo_get = memo.setdefault
pairs = []
# Use a slice to prevent IndexError from being raised, the following
# check will raise a more specific ValueError if the string is empty
nextchar = s[end:end + 1]
# Normally we expect nextchar == '"'
if nextchar != '"':
if nextchar in _ws:
end = _w(s, end).end()
nextchar = s[end:end + 1]
# Trivial empty object
if nextchar == '}':
if object_pairs_hook is not None:
result = object_pairs_hook(pairs)
return result, end
pairs = {}
if object_hook is not None:
pairs = object_hook(pairs)
return pairs, end + 1
elif nextchar != '"':
raise JSONDecodeError("Expecting property name", s, end)
end += 1
while True:
key, end = scanstring(s, end, encoding, strict)
key = memo_get(key, key)
# To skip some function call overhead we optimize the fast paths where
# the JSON key separator is ": " or just ":".
if s[end:end + 1] != ':':
end = _w(s, end).end()
if s[end:end + 1] != ':':
raise JSONDecodeError("Expecting : delimiter", s, end)
end += 1
try:
if s[end] in _ws:
end += 1
if s[end] in _ws:
end = _w(s, end + 1).end()
except IndexError:
pass
try:
value, end = scan_once(s, end)
except StopIteration:
raise JSONDecodeError("Expecting object", s, end)
pairs.append((key, value))
try:
nextchar = s[end]
if nextchar in _ws:
end = _w(s, end + 1).end()
nextchar = s[end]
except IndexError:
nextchar = ''
end += 1
if nextchar == '}':
break
elif nextchar != ',':
raise JSONDecodeError("Expecting , delimiter", s, end - 1)
try:
nextchar = s[end]
if nextchar in _ws:
end += 1
nextchar = s[end]
if nextchar in _ws:
end = _w(s, end + 1).end()
nextchar = s[end]
except IndexError:
nextchar = ''
end += 1
if nextchar != '"':
raise JSONDecodeError("Expecting property name", s, end - 1)
if object_pairs_hook is not None:
result = object_pairs_hook(pairs)
return result, end
pairs = dict(pairs)
if object_hook is not None:
pairs = object_hook(pairs)
return pairs, end
def JSONArray((s, end), scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
values = []
nextchar = s[end:end + 1]
if nextchar in _ws:
end = _w(s, end + 1).end()
nextchar = s[end:end + 1]
# Look-ahead for trivial empty array
if nextchar == ']':
return values, end + 1
_append = values.append
while True:
try:
value, end = scan_once(s, end)
except StopIteration:
raise JSONDecodeError("Expecting object", s, end)
_append(value)
nextchar = s[end:end + 1]
if nextchar in _ws:
end = _w(s, end + 1).end()
nextchar = s[end:end + 1]
end += 1
if nextchar == ']':
break
elif nextchar != ',':
raise JSONDecodeError("Expecting , delimiter", s, end)
try:
if s[end] in _ws:
end += 1
if s[end] in _ws:
end = _w(s, end + 1).end()
except IndexError:
pass
return values, end
class JSONDecoder(object):
"""Simple JSON <http://json.org> decoder
Performs the following translations in decoding by default:
+---------------+-------------------+
| JSON | Python |
+===============+===================+
| object | dict |
+---------------+-------------------+
| array | list |
+---------------+-------------------+
| string | unicode |
+---------------+-------------------+
| number (int) | int, long |
+---------------+-------------------+
| number (real) | float |
+---------------+-------------------+
| true | True |
+---------------+-------------------+
| false | False |
+---------------+-------------------+
| null | None |
+---------------+-------------------+
It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as
their corresponding ``float`` values, which is outside the JSON spec.
"""
def __init__(self, encoding=None, object_hook=None, parse_float=None,
parse_int=None, parse_constant=None, strict=True,
object_pairs_hook=None):
"""
*encoding* determines the encoding used to interpret any
:class:`str` objects decoded by this instance (``'utf-8'`` by
default). It has no effect when decoding :class:`unicode` objects.
Note that currently only encodings that are a superset of ASCII work,
strings of other encodings should be passed in as :class:`unicode`.
*object_hook*, if specified, will be called with the result of every
JSON object decoded and its return value will be used in place of the
given :class:`dict`. This can be used to provide custom
deserializations (e.g. to support JSON-RPC class hinting).
*object_pairs_hook* is an optional function that will be called with
the result of any object literal decode with an ordered list of pairs.
The return value of *object_pairs_hook* will be used instead of the
:class:`dict`. This feature can be used to implement custom decoders
that rely on the order that the key and value pairs are decoded (for
example, :func:`collections.OrderedDict` will remember the order of
insertion). If *object_hook* is also defined, the *object_pairs_hook*
takes priority.
*parse_float*, if specified, will be called with the string of every
JSON float to be decoded. By default, this is equivalent to
``float(num_str)``. This can be used to use another datatype or parser
for JSON floats (e.g. :class:`decimal.Decimal`).
*parse_int*, if specified, will be called with the string of every
JSON int to be decoded. By default, this is equivalent to
``int(num_str)``. This can be used to use another datatype or parser
for JSON integers (e.g. :class:`float`).
*parse_constant*, if specified, will be called with one of the
following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
can be used to raise an exception if invalid JSON numbers are
encountered.
*strict* controls the parser's behavior when it encounters an
invalid control character in a string. The default setting of
``True`` means that unescaped control characters are parse errors, if
``False`` then control characters will be allowed in strings.
"""
self.encoding = encoding
self.object_hook = object_hook
self.object_pairs_hook = object_pairs_hook
self.parse_float = parse_float or float
self.parse_int = parse_int or int
self.parse_constant = parse_constant or _CONSTANTS.__getitem__
self.strict = strict
self.parse_object = JSONObject
self.parse_array = JSONArray
self.parse_string = scanstring
self.memo = {}
self.scan_once = make_scanner(self)
def decode(self, s, _w=WHITESPACE.match):
"""Return the Python representation of ``s`` (a ``str`` or ``unicode``
instance containing a JSON document)
"""
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
end = _w(s, end).end()
if end != len(s):
raise JSONDecodeError("Extra data", s, end, len(s))
return obj
def raw_decode(self, s, idx=0):
"""Decode a JSON document from ``s`` (a ``str`` or ``unicode``
beginning with a JSON document) and return a 2-tuple of the Python
representation and the index in ``s`` where the document ended.
This can be used to decode a JSON document from a string that may
have extraneous data at the end.
"""
try:
obj, end = self.scan_once(s, idx)
except StopIteration:
raise JSONDecodeError("No JSON object could be decoded", s, idx)
return obj, end
-501
View File
@@ -1,501 +0,0 @@
"""Implementation of JSONEncoder
"""
import re
from decimal import Decimal
def _import_speedups():
try:
from simplejson import _speedups
return _speedups.encode_basestring_ascii, _speedups.make_encoder
except ImportError:
return None, None
c_encode_basestring_ascii, c_make_encoder = _import_speedups()
from simplejson.decoder import PosInf
ESCAPE = re.compile(r'[\x00-\x1f\\"\b\f\n\r\t]')
ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])')
HAS_UTF8 = re.compile(r'[\x80-\xff]')
ESCAPE_DCT = {
'\\': '\\\\',
'"': '\\"',
'\b': '\\b',
'\f': '\\f',
'\n': '\\n',
'\r': '\\r',
'\t': '\\t',
}
for i in range(0x20):
#ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i))
ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))
FLOAT_REPR = repr
def encode_basestring(s):
"""Return a JSON representation of a Python string
"""
if isinstance(s, str) and HAS_UTF8.search(s) is not None:
s = s.decode('utf-8')
def replace(match):
return ESCAPE_DCT[match.group(0)]
return u'"' + ESCAPE.sub(replace, s) + u'"'
def py_encode_basestring_ascii(s):
"""Return an ASCII-only JSON representation of a Python string
"""
if isinstance(s, str) and HAS_UTF8.search(s) is not None:
s = s.decode('utf-8')
def replace(match):
s = match.group(0)
try:
return ESCAPE_DCT[s]
except KeyError:
n = ord(s)
if n < 0x10000:
#return '\\u{0:04x}'.format(n)
return '\\u%04x' % (n,)
else:
# surrogate pair
n -= 0x10000
s1 = 0xd800 | ((n >> 10) & 0x3ff)
s2 = 0xdc00 | (n & 0x3ff)
#return '\\u{0:04x}\\u{1:04x}'.format(s1, s2)
return '\\u%04x\\u%04x' % (s1, s2)
return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
encode_basestring_ascii = (
c_encode_basestring_ascii or py_encode_basestring_ascii)
class JSONEncoder(object):
"""Extensible JSON <http://json.org> encoder for Python data structures.
Supports the following objects and types by default:
+-------------------+---------------+
| Python | JSON |
+===================+===============+
| dict | object |
+-------------------+---------------+
| list, tuple | array |
+-------------------+---------------+
| str, unicode | string |
+-------------------+---------------+
| int, long, float | number |
+-------------------+---------------+
| True | true |
+-------------------+---------------+
| False | false |
+-------------------+---------------+
| None | null |
+-------------------+---------------+
To extend this to recognize other objects, subclass and implement a
``.default()`` method with another method that returns a serializable
object for ``o`` if possible, otherwise it should call the superclass
implementation (to raise ``TypeError``).
"""
item_separator = ', '
key_separator = ': '
def __init__(self, skipkeys=False, ensure_ascii=True,
check_circular=True, allow_nan=True, sort_keys=False,
indent=None, separators=None, encoding='utf-8', default=None,
use_decimal=False):
"""Constructor for JSONEncoder, with sensible defaults.
If skipkeys is false, then it is a TypeError to attempt
encoding of keys that are not str, int, long, float or None. If
skipkeys is True, such items are simply skipped.
If ensure_ascii is true, the output is guaranteed to be str
objects with all incoming unicode characters escaped. If
ensure_ascii is false, the output will be unicode object.
If check_circular is true, then lists, dicts, and custom encoded
objects will be checked for circular references during encoding to
prevent an infinite recursion (which would cause an OverflowError).
Otherwise, no such check takes place.
If allow_nan is true, then NaN, Infinity, and -Infinity will be
encoded as such. This behavior is not JSON specification compliant,
but is consistent with most JavaScript based encoders and decoders.
Otherwise, it will be a ValueError to encode such floats.
If sort_keys is true, then the output of dictionaries will be
sorted by key; this is useful for regression tests to ensure
that JSON serializations can be compared on a day-to-day basis.
If indent is a string, then JSON array elements and object members
will be pretty-printed with a newline followed by that string repeated
for each level of nesting. ``None`` (the default) selects the most compact
representation without any newlines. For backwards compatibility with
versions of simplejson earlier than 2.1.0, an integer is also accepted
and is converted to a string with that many spaces.
If specified, separators should be a (item_separator, key_separator)
tuple. The default is (', ', ': '). To get the most compact JSON
representation you should specify (',', ':') to eliminate whitespace.
If specified, default is a function that gets called for objects
that can't otherwise be serialized. It should return a JSON encodable
version of the object or raise a ``TypeError``.
If encoding is not None, then all input strings will be
transformed into unicode using that encoding prior to JSON-encoding.
The default is UTF-8.
If use_decimal is true (not the default), ``decimal.Decimal`` will
be supported directly by the encoder. For the inverse, decode JSON
with ``parse_float=decimal.Decimal``.
"""
self.skipkeys = skipkeys
self.ensure_ascii = ensure_ascii
self.check_circular = check_circular
self.allow_nan = allow_nan
self.sort_keys = sort_keys
self.use_decimal = use_decimal
if isinstance(indent, (int, long)):
indent = ' ' * indent
self.indent = indent
if separators is not None:
self.item_separator, self.key_separator = separators
if default is not None:
self.default = default
self.encoding = encoding
def default(self, o):
"""Implement this method in a subclass such that it returns
a serializable object for ``o``, or calls the base implementation
(to raise a ``TypeError``).
For example, to support arbitrary iterators, you could
implement default like this::
def default(self, o):
try:
iterable = iter(o)
except TypeError:
pass
else:
return list(iterable)
return JSONEncoder.default(self, o)
"""
raise TypeError(repr(o) + " is not JSON serializable")
def encode(self, o):
"""Return a JSON string representation of a Python data structure.
>>> from simplejson import JSONEncoder
>>> JSONEncoder().encode({"foo": ["bar", "baz"]})
'{"foo": ["bar", "baz"]}'
"""
# This is for extremely simple cases and benchmarks.
if isinstance(o, basestring):
if isinstance(o, str):
_encoding = self.encoding
if (_encoding is not None
and not (_encoding == 'utf-8')):
o = o.decode(_encoding)
if self.ensure_ascii:
return encode_basestring_ascii(o)
else:
return encode_basestring(o)
# This doesn't pass the iterator directly to ''.join() because the
# exceptions aren't as detailed. The list call should be roughly
# equivalent to the PySequence_Fast that ''.join() would do.
chunks = self.iterencode(o, _one_shot=True)
if not isinstance(chunks, (list, tuple)):
chunks = list(chunks)
if self.ensure_ascii:
return ''.join(chunks)
else:
return u''.join(chunks)
def iterencode(self, o, _one_shot=False):
"""Encode the given object and yield each string
representation as available.
For example::
for chunk in JSONEncoder().iterencode(bigobject):
mysocket.write(chunk)
"""
if self.check_circular:
markers = {}
else:
markers = None
if self.ensure_ascii:
_encoder = encode_basestring_ascii
else:
_encoder = encode_basestring
if self.encoding != 'utf-8':
def _encoder(o, _orig_encoder=_encoder, _encoding=self.encoding):
if isinstance(o, str):
o = o.decode(_encoding)
return _orig_encoder(o)
def floatstr(o, allow_nan=self.allow_nan,
_repr=FLOAT_REPR, _inf=PosInf, _neginf=-PosInf):
# Check for specials. Note that this type of test is processor
# and/or platform-specific, so do tests which don't depend on
# the internals.
if o != o:
text = 'NaN'
elif o == _inf:
text = 'Infinity'
elif o == _neginf:
text = '-Infinity'
else:
return _repr(o)
if not allow_nan:
raise ValueError(
"Out of range float values are not JSON compliant: " +
repr(o))
return text
key_memo = {}
if (_one_shot and c_make_encoder is not None
and not self.indent and not self.sort_keys):
_iterencode = c_make_encoder(
markers, self.default, _encoder, self.indent,
self.key_separator, self.item_separator, self.sort_keys,
self.skipkeys, self.allow_nan, key_memo, self.use_decimal)
else:
_iterencode = _make_iterencode(
markers, self.default, _encoder, self.indent, floatstr,
self.key_separator, self.item_separator, self.sort_keys,
self.skipkeys, _one_shot, self.use_decimal)
try:
return _iterencode(o, 0)
finally:
key_memo.clear()
class JSONEncoderForHTML(JSONEncoder):
"""An encoder that produces JSON safe to embed in HTML.
To embed JSON content in, say, a script tag on a web page, the
characters &, < and > should be escaped. They cannot be escaped
with the usual entities (e.g. &amp;) because they are not expanded
within <script> tags.
"""
def encode(self, o):
# Override JSONEncoder.encode because it has hacks for
# performance that make things more complicated.
chunks = self.iterencode(o, True)
if self.ensure_ascii:
return ''.join(chunks)
else:
return u''.join(chunks)
def iterencode(self, o, _one_shot=False):
chunks = super(JSONEncoderForHTML, self).iterencode(o, _one_shot)
for chunk in chunks:
chunk = chunk.replace('&', '\\u0026')
chunk = chunk.replace('<', '\\u003c')
chunk = chunk.replace('>', '\\u003e')
yield chunk
def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
_key_separator, _item_separator, _sort_keys, _skipkeys, _one_shot,
_use_decimal,
## HACK: hand-optimized bytecode; turn globals into locals
False=False,
True=True,
ValueError=ValueError,
basestring=basestring,
Decimal=Decimal,
dict=dict,
float=float,
id=id,
int=int,
isinstance=isinstance,
list=list,
long=long,
str=str,
tuple=tuple,
):
def _iterencode_list(lst, _current_indent_level):
if not lst:
yield '[]'
return
if markers is not None:
markerid = id(lst)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = lst
buf = '['
if _indent is not None:
_current_indent_level += 1
newline_indent = '\n' + (_indent * _current_indent_level)
separator = _item_separator + newline_indent
buf += newline_indent
else:
newline_indent = None
separator = _item_separator
first = True
for value in lst:
if first:
first = False
else:
buf = separator
if isinstance(value, basestring):
yield buf + _encoder(value)
elif value is None:
yield buf + 'null'
elif value is True:
yield buf + 'true'
elif value is False:
yield buf + 'false'
elif isinstance(value, (int, long)):
yield buf + str(value)
elif isinstance(value, float):
yield buf + _floatstr(value)
elif _use_decimal and isinstance(value, Decimal):
yield buf + str(value)
else:
yield buf
if isinstance(value, (list, tuple)):
chunks = _iterencode_list(value, _current_indent_level)
elif isinstance(value, dict):
chunks = _iterencode_dict(value, _current_indent_level)
else:
chunks = _iterencode(value, _current_indent_level)
for chunk in chunks:
yield chunk
if newline_indent is not None:
_current_indent_level -= 1
yield '\n' + (_indent * _current_indent_level)
yield ']'
if markers is not None:
del markers[markerid]
def _iterencode_dict(dct, _current_indent_level):
if not dct:
yield '{}'
return
if markers is not None:
markerid = id(dct)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = dct
yield '{'
if _indent is not None:
_current_indent_level += 1
newline_indent = '\n' + (_indent * _current_indent_level)
item_separator = _item_separator + newline_indent
yield newline_indent
else:
newline_indent = None
item_separator = _item_separator
first = True
if _sort_keys:
items = dct.items()
items.sort(key=lambda kv: kv[0])
else:
items = dct.iteritems()
for key, value in items:
if isinstance(key, basestring):
pass
# JavaScript is weakly typed for these, so it makes sense to
# also allow them. Many encoders seem to do something like this.
elif isinstance(key, float):
key = _floatstr(key)
elif key is True:
key = 'true'
elif key is False:
key = 'false'
elif key is None:
key = 'null'
elif isinstance(key, (int, long)):
key = str(key)
elif _skipkeys:
continue
else:
raise TypeError("key " + repr(key) + " is not a string")
if first:
first = False
else:
yield item_separator
yield _encoder(key)
yield _key_separator
if isinstance(value, basestring):
yield _encoder(value)
elif value is None:
yield 'null'
elif value is True:
yield 'true'
elif value is False:
yield 'false'
elif isinstance(value, (int, long)):
yield str(value)
elif isinstance(value, float):
yield _floatstr(value)
elif _use_decimal and isinstance(value, Decimal):
yield str(value)
else:
if isinstance(value, (list, tuple)):
chunks = _iterencode_list(value, _current_indent_level)
elif isinstance(value, dict):
chunks = _iterencode_dict(value, _current_indent_level)
else:
chunks = _iterencode(value, _current_indent_level)
for chunk in chunks:
yield chunk
if newline_indent is not None:
_current_indent_level -= 1
yield '\n' + (_indent * _current_indent_level)
yield '}'
if markers is not None:
del markers[markerid]
def _iterencode(o, _current_indent_level):
if isinstance(o, basestring):
yield _encoder(o)
elif o is None:
yield 'null'
elif o is True:
yield 'true'
elif o is False:
yield 'false'
elif isinstance(o, (int, long)):
yield str(o)
elif isinstance(o, float):
yield _floatstr(o)
elif isinstance(o, (list, tuple)):
for chunk in _iterencode_list(o, _current_indent_level):
yield chunk
elif isinstance(o, dict):
for chunk in _iterencode_dict(o, _current_indent_level):
yield chunk
elif _use_decimal and isinstance(o, Decimal):
yield str(o)
else:
if markers is not None:
markerid = id(o)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = o
o = _default(o)
for chunk in _iterencode(o, _current_indent_level):
yield chunk
if markers is not None:
del markers[markerid]
return _iterencode
-119
View File
@@ -1,119 +0,0 @@
"""Drop-in replacement for collections.OrderedDict by Raymond Hettinger
http://code.activestate.com/recipes/576693/
"""
from UserDict import DictMixin
# Modified from original to support Python 2.4, see
# http://code.google.com/p/simplejson/issues/detail?id=53
try:
all
except NameError:
def all(seq):
for elem in seq:
if not elem:
return False
return True
class OrderedDict(dict, DictMixin):
def __init__(self, *args, **kwds):
if len(args) > 1:
raise TypeError('expected at most 1 arguments, got %d' % len(args))
try:
self.__end
except AttributeError:
self.clear()
self.update(*args, **kwds)
def clear(self):
self.__end = end = []
end += [None, end, end] # sentinel node for doubly linked list
self.__map = {} # key --> [key, prev, next]
dict.clear(self)
def __setitem__(self, key, value):
if key not in self:
end = self.__end
curr = end[1]
curr[2] = end[1] = self.__map[key] = [key, curr, end]
dict.__setitem__(self, key, value)
def __delitem__(self, key):
dict.__delitem__(self, key)
key, prev, next = self.__map.pop(key)
prev[2] = next
next[1] = prev
def __iter__(self):
end = self.__end
curr = end[2]
while curr is not end:
yield curr[0]
curr = curr[2]
def __reversed__(self):
end = self.__end
curr = end[1]
while curr is not end:
yield curr[0]
curr = curr[1]
def popitem(self, last=True):
if not self:
raise KeyError('dictionary is empty')
# Modified from original to support Python 2.4, see
# http://code.google.com/p/simplejson/issues/detail?id=53
if last:
key = reversed(self).next()
else:
key = iter(self).next()
value = self.pop(key)
return key, value
def __reduce__(self):
items = [[k, self[k]] for k in self]
tmp = self.__map, self.__end
del self.__map, self.__end
inst_dict = vars(self).copy()
self.__map, self.__end = tmp
if inst_dict:
return (self.__class__, (items,), inst_dict)
return self.__class__, (items,)
def keys(self):
return list(self)
setdefault = DictMixin.setdefault
update = DictMixin.update
pop = DictMixin.pop
values = DictMixin.values
items = DictMixin.items
iterkeys = DictMixin.iterkeys
itervalues = DictMixin.itervalues
iteritems = DictMixin.iteritems
def __repr__(self):
if not self:
return '%s()' % (self.__class__.__name__,)
return '%s(%r)' % (self.__class__.__name__, self.items())
def copy(self):
return self.__class__(self)
@classmethod
def fromkeys(cls, iterable, value=None):
d = cls()
for key in iterable:
d[key] = value
return d
def __eq__(self, other):
if isinstance(other, OrderedDict):
return len(self)==len(other) and \
all(p==q for p, q in zip(self.items(), other.items()))
return dict.__eq__(self, other)
def __ne__(self, other):
return not self == other
-77
View File
@@ -1,77 +0,0 @@
"""JSON token scanner
"""
import re
def _import_c_make_scanner():
try:
from simplejson._speedups import make_scanner
return make_scanner
except ImportError:
return None
c_make_scanner = _import_c_make_scanner()
__all__ = ['make_scanner']
NUMBER_RE = re.compile(
r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?',
(re.VERBOSE | re.MULTILINE | re.DOTALL))
def py_make_scanner(context):
parse_object = context.parse_object
parse_array = context.parse_array
parse_string = context.parse_string
match_number = NUMBER_RE.match
encoding = context.encoding
strict = context.strict
parse_float = context.parse_float
parse_int = context.parse_int
parse_constant = context.parse_constant
object_hook = context.object_hook
object_pairs_hook = context.object_pairs_hook
memo = context.memo
def _scan_once(string, idx):
try:
nextchar = string[idx]
except IndexError:
raise StopIteration
if nextchar == '"':
return parse_string(string, idx + 1, encoding, strict)
elif nextchar == '{':
return parse_object((string, idx + 1), encoding, strict,
_scan_once, object_hook, object_pairs_hook, memo)
elif nextchar == '[':
return parse_array((string, idx + 1), _scan_once)
elif nextchar == 'n' and string[idx:idx + 4] == 'null':
return None, idx + 4
elif nextchar == 't' and string[idx:idx + 4] == 'true':
return True, idx + 4
elif nextchar == 'f' and string[idx:idx + 5] == 'false':
return False, idx + 5
m = match_number(string, idx)
if m is not None:
integer, frac, exp = m.groups()
if frac or exp:
res = parse_float(integer + (frac or '') + (exp or ''))
else:
res = parse_int(integer)
return res, m.end()
elif nextchar == 'N' and string[idx:idx + 3] == 'NaN':
return parse_constant('NaN'), idx + 3
elif nextchar == 'I' and string[idx:idx + 8] == 'Infinity':
return parse_constant('Infinity'), idx + 8
elif nextchar == '-' and string[idx:idx + 9] == '-Infinity':
return parse_constant('-Infinity'), idx + 9
else:
raise StopIteration
def scan_once(string, idx):
try:
return _scan_once(string, idx)
finally:
memo.clear()
return scan_once
make_scanner = c_make_scanner or py_make_scanner
@@ -1,63 +0,0 @@
import unittest
import doctest
class OptionalExtensionTestSuite(unittest.TestSuite):
def run(self, result):
import simplejson
run = unittest.TestSuite.run
run(self, result)
simplejson._toggle_speedups(False)
run(self, result)
simplejson._toggle_speedups(True)
return result
def additional_tests(suite=None):
import simplejson
import simplejson.encoder
import simplejson.decoder
if suite is None:
suite = unittest.TestSuite()
for mod in (simplejson, simplejson.encoder, simplejson.decoder):
suite.addTest(doctest.DocTestSuite(mod))
suite.addTest(doctest.DocFileSuite('../../index.rst'))
return suite
def all_tests_suite():
suite = unittest.TestLoader().loadTestsFromNames([
'simplejson.tests.test_check_circular',
'simplejson.tests.test_decode',
'simplejson.tests.test_default',
'simplejson.tests.test_dump',
'simplejson.tests.test_encode_basestring_ascii',
'simplejson.tests.test_encode_for_html',
'simplejson.tests.test_fail',
'simplejson.tests.test_float',
'simplejson.tests.test_indent',
'simplejson.tests.test_pass1',
'simplejson.tests.test_pass2',
'simplejson.tests.test_pass3',
'simplejson.tests.test_recursion',
'simplejson.tests.test_scanstring',
'simplejson.tests.test_separators',
'simplejson.tests.test_speedups',
'simplejson.tests.test_unicode',
'simplejson.tests.test_decimal',
])
suite = additional_tests(suite)
return OptionalExtensionTestSuite([suite])
def main():
runner = unittest.TextTestRunner()
suite = all_tests_suite()
runner.run(suite)
if __name__ == '__main__':
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
main()
@@ -1,30 +0,0 @@
from unittest import TestCase
import simplejson as json
def default_iterable(obj):
return list(obj)
class TestCheckCircular(TestCase):
def test_circular_dict(self):
dct = {}
dct['a'] = dct
self.assertRaises(ValueError, json.dumps, dct)
def test_circular_list(self):
lst = []
lst.append(lst)
self.assertRaises(ValueError, json.dumps, lst)
def test_circular_composite(self):
dct2 = {}
dct2['a'] = []
dct2['a'].append(dct2)
self.assertRaises(ValueError, json.dumps, dct2)
def test_circular_default(self):
json.dumps([set()], default=default_iterable)
self.assertRaises(TypeError, json.dumps, [set()])
def test_circular_off_default(self):
json.dumps([set()], default=default_iterable, check_circular=False)
self.assertRaises(TypeError, json.dumps, [set()], check_circular=False)
@@ -1,33 +0,0 @@
from decimal import Decimal
from unittest import TestCase
import simplejson as json
class TestDecimal(TestCase):
NUMS = "1.0", "10.00", "1.1", "1234567890.1234567890", "500"
def test_decimal_encode(self):
for d in map(Decimal, self.NUMS):
self.assertEquals(json.dumps(d, use_decimal=True), str(d))
def test_decimal_decode(self):
for s in self.NUMS:
self.assertEquals(json.loads(s, parse_float=Decimal), Decimal(s))
def test_decimal_roundtrip(self):
for d in map(Decimal, self.NUMS):
# The type might not be the same (int and Decimal) but they
# should still compare equal.
self.assertEquals(
json.loads(
json.dumps(d, use_decimal=True), parse_float=Decimal),
d)
self.assertEquals(
json.loads(
json.dumps([d], use_decimal=True), parse_float=Decimal),
[d])
def test_decimal_defaults(self):
d = Decimal(1)
# use_decimal=False is the default
self.assertRaises(TypeError, json.dumps, d, use_decimal=False)
self.assertRaises(TypeError, json.dumps, d)
@@ -1,73 +0,0 @@
import decimal
from unittest import TestCase
from StringIO import StringIO
import simplejson as json
from simplejson import OrderedDict
class TestDecode(TestCase):
if not hasattr(TestCase, 'assertIs'):
def assertIs(self, a, b):
self.assertTrue(a is b, '%r is %r' % (a, b))
def test_decimal(self):
rval = json.loads('1.1', parse_float=decimal.Decimal)
self.assertTrue(isinstance(rval, decimal.Decimal))
self.assertEquals(rval, decimal.Decimal('1.1'))
def test_float(self):
rval = json.loads('1', parse_int=float)
self.assertTrue(isinstance(rval, float))
self.assertEquals(rval, 1.0)
def test_decoder_optimizations(self):
# Several optimizations were made that skip over calls to
# the whitespace regex, so this test is designed to try and
# exercise the uncommon cases. The array cases are already covered.
rval = json.loads('{ "key" : "value" , "k":"v" }')
self.assertEquals(rval, {"key":"value", "k":"v"})
def test_empty_objects(self):
s = '{}'
self.assertEqual(json.loads(s), eval(s))
s = '[]'
self.assertEqual(json.loads(s), eval(s))
s = '""'
self.assertEqual(json.loads(s), eval(s))
def test_object_pairs_hook(self):
s = '{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
p = [("xkd", 1), ("kcw", 2), ("art", 3), ("hxm", 4),
("qrt", 5), ("pad", 6), ("hoy", 7)]
self.assertEqual(json.loads(s), eval(s))
self.assertEqual(json.loads(s, object_pairs_hook=lambda x: x), p)
self.assertEqual(json.load(StringIO(s),
object_pairs_hook=lambda x: x), p)
od = json.loads(s, object_pairs_hook=OrderedDict)
self.assertEqual(od, OrderedDict(p))
self.assertEqual(type(od), OrderedDict)
# the object_pairs_hook takes priority over the object_hook
self.assertEqual(json.loads(s,
object_pairs_hook=OrderedDict,
object_hook=lambda x: None),
OrderedDict(p))
def check_keys_reuse(self, source, loads):
rval = loads(source)
(a, b), (c, d) = sorted(rval[0]), sorted(rval[1])
self.assertIs(a, c)
self.assertIs(b, d)
def test_keys_reuse_str(self):
s = u'[{"a_key": 1, "b_\xe9": 2}, {"a_key": 3, "b_\xe9": 4}]'.encode('utf8')
self.check_keys_reuse(s, json.loads)
def test_keys_reuse_unicode(self):
s = u'[{"a_key": 1, "b_\xe9": 2}, {"a_key": 3, "b_\xe9": 4}]'
self.check_keys_reuse(s, json.loads)
def test_empty_strings(self):
self.assertEqual(json.loads('""'), "")
self.assertEqual(json.loads(u'""'), u"")
self.assertEqual(json.loads('[""]'), [""])
self.assertEqual(json.loads(u'[""]'), [u""])
@@ -1,9 +0,0 @@
from unittest import TestCase
import simplejson as json
class TestDefault(TestCase):
def test_default(self):
self.assertEquals(
json.dumps(type, default=repr),
json.dumps(repr(type)))
@@ -1,27 +0,0 @@
from unittest import TestCase
from cStringIO import StringIO
import simplejson as json
class TestDump(TestCase):
def test_dump(self):
sio = StringIO()
json.dump({}, sio)
self.assertEquals(sio.getvalue(), '{}')
def test_dumps(self):
self.assertEquals(json.dumps({}), '{}')
def test_encode_truefalse(self):
self.assertEquals(json.dumps(
{True: False, False: True}, sort_keys=True),
'{"false": true, "true": false}')
self.assertEquals(json.dumps(
{2: 3.0, 4.0: 5L, False: 1, 6L: True, "7": 0}, sort_keys=True),
'{"false": 1, "2": 3.0, "4.0": 5, "6": true, "7": 0}')
def test_ordered_dict(self):
# http://bugs.python.org/issue6105
items = [('one', 1), ('two', 2), ('three', 3), ('four', 4), ('five', 5)]
s = json.dumps(json.OrderedDict(items))
self.assertEqual(s, '{"one": 1, "two": 2, "three": 3, "four": 4, "five": 5}')
@@ -1,41 +0,0 @@
from unittest import TestCase
import simplejson.encoder
CASES = [
(u'/\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\x08\x0c\n\r\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?', '"/\\\\\\"\\ucafe\\ubabe\\uab98\\ufcde\\ubcda\\uef4a\\b\\f\\n\\r\\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?"'),
(u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
(u'controls', '"controls"'),
(u'\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
(u'{"object with 1 member":["array with 1 element"]}', '"{\\"object with 1 member\\":[\\"array with 1 element\\"]}"'),
(u' s p a c e d ', '" s p a c e d "'),
(u'\U0001d120', '"\\ud834\\udd20"'),
(u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
('\xce\xb1\xce\xa9', '"\\u03b1\\u03a9"'),
(u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
('\xce\xb1\xce\xa9', '"\\u03b1\\u03a9"'),
(u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
(u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
(u"`1~!@#$%^&*()_+-={':[,]}|;.</>?", '"`1~!@#$%^&*()_+-={\':[,]}|;.</>?"'),
(u'\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
(u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
]
class TestEncodeBaseStringAscii(TestCase):
def test_py_encode_basestring_ascii(self):
self._test_encode_basestring_ascii(simplejson.encoder.py_encode_basestring_ascii)
def test_c_encode_basestring_ascii(self):
if not simplejson.encoder.c_encode_basestring_ascii:
return
self._test_encode_basestring_ascii(simplejson.encoder.c_encode_basestring_ascii)
def _test_encode_basestring_ascii(self, encode_basestring_ascii):
fname = encode_basestring_ascii.__name__
for input_string, expect in CASES:
result = encode_basestring_ascii(input_string)
#self.assertEquals(result, expect,
# '{0!r} != {1!r} for {2}({3!r})'.format(
# result, expect, fname, input_string))
self.assertEquals(result, expect,
'%r != %r for %s(%r)' % (result, expect, fname, input_string))
@@ -1,32 +0,0 @@
import unittest
import simplejson.decoder
import simplejson.encoder
class TestEncodeForHTML(unittest.TestCase):
def setUp(self):
self.decoder = simplejson.decoder.JSONDecoder()
self.encoder = simplejson.encoder.JSONEncoderForHTML()
def test_basic_encode(self):
self.assertEqual(r'"\u0026"', self.encoder.encode('&'))
self.assertEqual(r'"\u003c"', self.encoder.encode('<'))
self.assertEqual(r'"\u003e"', self.encoder.encode('>'))
def test_basic_roundtrip(self):
for char in '&<>':
self.assertEqual(
char, self.decoder.decode(
self.encoder.encode(char)))
def test_prevent_script_breakout(self):
bad_string = '</script><script>alert("gotcha")</script>'
self.assertEqual(
r'"\u003c/script\u003e\u003cscript\u003e'
r'alert(\"gotcha\")\u003c/script\u003e"',
self.encoder.encode(bad_string))
self.assertEqual(
bad_string, self.decoder.decode(
self.encoder.encode(bad_string)))
@@ -1,91 +0,0 @@
from unittest import TestCase
import simplejson as json
# Fri Dec 30 18:57:26 2005
JSONDOCS = [
# http://json.org/JSON_checker/test/fail1.json
'"A JSON payload should be an object or array, not a string."',
# http://json.org/JSON_checker/test/fail2.json
'["Unclosed array"',
# http://json.org/JSON_checker/test/fail3.json
'{unquoted_key: "keys must be quoted}',
# http://json.org/JSON_checker/test/fail4.json
'["extra comma",]',
# http://json.org/JSON_checker/test/fail5.json
'["double extra comma",,]',
# http://json.org/JSON_checker/test/fail6.json
'[ , "<-- missing value"]',
# http://json.org/JSON_checker/test/fail7.json
'["Comma after the close"],',
# http://json.org/JSON_checker/test/fail8.json
'["Extra close"]]',
# http://json.org/JSON_checker/test/fail9.json
'{"Extra comma": true,}',
# http://json.org/JSON_checker/test/fail10.json
'{"Extra value after close": true} "misplaced quoted value"',
# http://json.org/JSON_checker/test/fail11.json
'{"Illegal expression": 1 + 2}',
# http://json.org/JSON_checker/test/fail12.json
'{"Illegal invocation": alert()}',
# http://json.org/JSON_checker/test/fail13.json
'{"Numbers cannot have leading zeroes": 013}',
# http://json.org/JSON_checker/test/fail14.json
'{"Numbers cannot be hex": 0x14}',
# http://json.org/JSON_checker/test/fail15.json
'["Illegal backslash escape: \\x15"]',
# http://json.org/JSON_checker/test/fail16.json
'["Illegal backslash escape: \\\'"]',
# http://json.org/JSON_checker/test/fail17.json
'["Illegal backslash escape: \\017"]',
# http://json.org/JSON_checker/test/fail18.json
'[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]',
# http://json.org/JSON_checker/test/fail19.json
'{"Missing colon" null}',
# http://json.org/JSON_checker/test/fail20.json
'{"Double colon":: null}',
# http://json.org/JSON_checker/test/fail21.json
'{"Comma instead of colon", null}',
# http://json.org/JSON_checker/test/fail22.json
'["Colon instead of comma": false]',
# http://json.org/JSON_checker/test/fail23.json
'["Bad value", truth]',
# http://json.org/JSON_checker/test/fail24.json
"['single quote']",
# http://code.google.com/p/simplejson/issues/detail?id=3
u'["A\u001FZ control characters in string"]',
]
SKIPS = {
1: "why not have a string payload?",
18: "spec doesn't specify any nesting limitations",
}
class TestFail(TestCase):
def test_failures(self):
for idx, doc in enumerate(JSONDOCS):
idx = idx + 1
if idx in SKIPS:
json.loads(doc)
continue
try:
json.loads(doc)
except json.JSONDecodeError:
pass
else:
#self.fail("Expected failure for fail{0}.json: {1!r}".format(idx, doc))
self.fail("Expected failure for fail%d.json: %r" % (idx, doc))
def test_array_decoder_issue46(self):
# http://code.google.com/p/simplejson/issues/detail?id=46
for doc in [u'[,]', '[,]']:
try:
json.loads(doc)
except json.JSONDecodeError, e:
self.assertEquals(e.pos, 1)
self.assertEquals(e.lineno, 1)
self.assertEquals(e.colno, 1)
except Exception, e:
self.fail("Unexpected exception raised %r %s" % (e, e))
else:
self.fail("Unexpected success parsing '[,]'")
@@ -1,19 +0,0 @@
import math
from unittest import TestCase
import simplejson as json
class TestFloat(TestCase):
def test_floats(self):
for num in [1617161771.7650001, math.pi, math.pi**100,
math.pi**-100, 3.1]:
self.assertEquals(float(json.dumps(num)), num)
self.assertEquals(json.loads(json.dumps(num)), num)
self.assertEquals(json.loads(unicode(json.dumps(num))), num)
def test_ints(self):
for num in [1, 1L, 1<<32, 1<<64]:
self.assertEquals(json.dumps(num), str(num))
self.assertEquals(int(json.dumps(num)), num)
self.assertEquals(json.loads(json.dumps(num)), num)
self.assertEquals(json.loads(unicode(json.dumps(num))), num)
@@ -1,53 +0,0 @@
from unittest import TestCase
import simplejson as json
import textwrap
class TestIndent(TestCase):
def test_indent(self):
h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh',
'i-vhbjkhnth',
{'nifty': 87}, {'field': 'yes', 'morefield': False} ]
expect = textwrap.dedent("""\
[
\t[
\t\t"blorpie"
\t],
\t[
\t\t"whoops"
\t],
\t[],
\t"d-shtaeou",
\t"d-nthiouh",
\t"i-vhbjkhnth",
\t{
\t\t"nifty": 87
\t},
\t{
\t\t"field": "yes",
\t\t"morefield": false
\t}
]""")
d1 = json.dumps(h)
d2 = json.dumps(h, indent='\t', sort_keys=True, separators=(',', ': '))
d3 = json.dumps(h, indent=' ', sort_keys=True, separators=(',', ': '))
d4 = json.dumps(h, indent=2, sort_keys=True, separators=(',', ': '))
h1 = json.loads(d1)
h2 = json.loads(d2)
h3 = json.loads(d3)
h4 = json.loads(d4)
self.assertEquals(h1, h)
self.assertEquals(h2, h)
self.assertEquals(h3, h)
self.assertEquals(h4, h)
self.assertEquals(d3, expect.replace('\t', ' '))
self.assertEquals(d4, expect.replace('\t', ' '))
# NOTE: Python 2.4 textwrap.dedent converts tabs to spaces,
# so the following is expected to fail. Python 2.4 is not a
# supported platform in simplejson 2.1.0+.
self.assertEquals(d2, expect)
@@ -1,76 +0,0 @@
from unittest import TestCase
import simplejson as json
# from http://json.org/JSON_checker/test/pass1.json
JSON = r'''
[
"JSON Test Pattern pass1",
{"object with 1 member":["array with 1 element"]},
{},
[],
-42,
true,
false,
null,
{
"integer": 1234567890,
"real": -9876.543210,
"e": 0.123456789e-12,
"E": 1.234567890E+34,
"": 23456789012E666,
"zero": 0,
"one": 1,
"space": " ",
"quote": "\"",
"backslash": "\\",
"controls": "\b\f\n\r\t",
"slash": "/ & \/",
"alpha": "abcdefghijklmnopqrstuvwyz",
"ALPHA": "ABCDEFGHIJKLMNOPQRSTUVWYZ",
"digit": "0123456789",
"special": "`1~!@#$%^&*()_+-={':[,]}|;.</>?",
"hex": "\u0123\u4567\u89AB\uCDEF\uabcd\uef4A",
"true": true,
"false": false,
"null": null,
"array":[ ],
"object":{ },
"address": "50 St. James Street",
"url": "http://www.JSON.org/",
"comment": "// /* <!-- --",
"# -- --> */": " ",
" s p a c e d " :[1,2 , 3
,
4 , 5 , 6 ,7 ],
"compact": [1,2,3,4,5,6,7],
"jsontext": "{\"object with 1 member\":[\"array with 1 element\"]}",
"quotes": "&#34; \u0022 %22 0x22 034 &#x22;",
"\/\\\"\uCAFE\uBABE\uAB98\uFCDE\ubcda\uef4A\b\f\n\r\t`1~!@#$%^&*()_+-=[]{}|;:',./<>?"
: "A key can be any string"
},
0.5 ,98.6
,
99.44
,
1066
,"rosebud"]
'''
class TestPass1(TestCase):
def test_parse(self):
# test in/out equivalence and parsing
res = json.loads(JSON)
out = json.dumps(res)
self.assertEquals(res, json.loads(out))
try:
json.dumps(res, allow_nan=False)
except ValueError:
pass
else:
self.fail("23456789012E666 should be out of range")
@@ -1,14 +0,0 @@
from unittest import TestCase
import simplejson as json
# from http://json.org/JSON_checker/test/pass2.json
JSON = r'''
[[[[[[[[[[[[[[[[[[["Not too deep"]]]]]]]]]]]]]]]]]]]
'''
class TestPass2(TestCase):
def test_parse(self):
# test in/out equivalence and parsing
res = json.loads(JSON)
out = json.dumps(res)
self.assertEquals(res, json.loads(out))
@@ -1,20 +0,0 @@
from unittest import TestCase
import simplejson as json
# from http://json.org/JSON_checker/test/pass3.json
JSON = r'''
{
"JSON Test Pattern pass3": {
"The outermost value": "must be an object or array.",
"In this test": "It is an object."
}
}
'''
class TestPass3(TestCase):
def test_parse(self):
# test in/out equivalence and parsing
res = json.loads(JSON)
out = json.dumps(res)
self.assertEquals(res, json.loads(out))
@@ -1,67 +0,0 @@
from unittest import TestCase
import simplejson as json
class JSONTestObject:
pass
class RecursiveJSONEncoder(json.JSONEncoder):
recurse = False
def default(self, o):
if o is JSONTestObject:
if self.recurse:
return [JSONTestObject]
else:
return 'JSONTestObject'
return json.JSONEncoder.default(o)
class TestRecursion(TestCase):
def test_listrecursion(self):
x = []
x.append(x)
try:
json.dumps(x)
except ValueError:
pass
else:
self.fail("didn't raise ValueError on list recursion")
x = []
y = [x]
x.append(y)
try:
json.dumps(x)
except ValueError:
pass
else:
self.fail("didn't raise ValueError on alternating list recursion")
y = []
x = [y, y]
# ensure that the marker is cleared
json.dumps(x)
def test_dictrecursion(self):
x = {}
x["test"] = x
try:
json.dumps(x)
except ValueError:
pass
else:
self.fail("didn't raise ValueError on dict recursion")
x = {}
y = {"a": x, "b": x}
# ensure that the marker is cleared
json.dumps(x)
def test_defaultrecursion(self):
enc = RecursiveJSONEncoder()
self.assertEquals(enc.encode(JSONTestObject), '"JSONTestObject"')
enc.recurse = True
try:
enc.encode(JSONTestObject)
except ValueError:
pass
else:
self.fail("didn't raise ValueError on default recursion")
@@ -1,117 +0,0 @@
import sys
from unittest import TestCase
import simplejson as json
import simplejson.decoder
class TestScanString(TestCase):
def test_py_scanstring(self):
self._test_scanstring(simplejson.decoder.py_scanstring)
def test_c_scanstring(self):
if not simplejson.decoder.c_scanstring:
return
self._test_scanstring(simplejson.decoder.c_scanstring)
def _test_scanstring(self, scanstring):
self.assertEquals(
scanstring('"z\\ud834\\udd20x"', 1, None, True),
(u'z\U0001d120x', 16))
if sys.maxunicode == 65535:
self.assertEquals(
scanstring(u'"z\U0001d120x"', 1, None, True),
(u'z\U0001d120x', 6))
else:
self.assertEquals(
scanstring(u'"z\U0001d120x"', 1, None, True),
(u'z\U0001d120x', 5))
self.assertEquals(
scanstring('"\\u007b"', 1, None, True),
(u'{', 8))
self.assertEquals(
scanstring('"A JSON payload should be an object or array, not a string."', 1, None, True),
(u'A JSON payload should be an object or array, not a string.', 60))
self.assertEquals(
scanstring('["Unclosed array"', 2, None, True),
(u'Unclosed array', 17))
self.assertEquals(
scanstring('["extra comma",]', 2, None, True),
(u'extra comma', 14))
self.assertEquals(
scanstring('["double extra comma",,]', 2, None, True),
(u'double extra comma', 21))
self.assertEquals(
scanstring('["Comma after the close"],', 2, None, True),
(u'Comma after the close', 24))
self.assertEquals(
scanstring('["Extra close"]]', 2, None, True),
(u'Extra close', 14))
self.assertEquals(
scanstring('{"Extra comma": true,}', 2, None, True),
(u'Extra comma', 14))
self.assertEquals(
scanstring('{"Extra value after close": true} "misplaced quoted value"', 2, None, True),
(u'Extra value after close', 26))
self.assertEquals(
scanstring('{"Illegal expression": 1 + 2}', 2, None, True),
(u'Illegal expression', 21))
self.assertEquals(
scanstring('{"Illegal invocation": alert()}', 2, None, True),
(u'Illegal invocation', 21))
self.assertEquals(
scanstring('{"Numbers cannot have leading zeroes": 013}', 2, None, True),
(u'Numbers cannot have leading zeroes', 37))
self.assertEquals(
scanstring('{"Numbers cannot be hex": 0x14}', 2, None, True),
(u'Numbers cannot be hex', 24))
self.assertEquals(
scanstring('[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]', 21, None, True),
(u'Too deep', 30))
self.assertEquals(
scanstring('{"Missing colon" null}', 2, None, True),
(u'Missing colon', 16))
self.assertEquals(
scanstring('{"Double colon":: null}', 2, None, True),
(u'Double colon', 15))
self.assertEquals(
scanstring('{"Comma instead of colon", null}', 2, None, True),
(u'Comma instead of colon', 25))
self.assertEquals(
scanstring('["Colon instead of comma": false]', 2, None, True),
(u'Colon instead of comma', 25))
self.assertEquals(
scanstring('["Bad value", truth]', 2, None, True),
(u'Bad value', 12))
def test_issue3623(self):
self.assertRaises(ValueError, json.decoder.scanstring, "xxx", 1,
"xxx")
self.assertRaises(UnicodeDecodeError,
json.encoder.encode_basestring_ascii, "xx\xff")
def test_overflow(self):
# Python 2.5 does not have maxsize
maxsize = getattr(sys, 'maxsize', sys.maxint)
self.assertRaises(OverflowError, json.decoder.scanstring, "xxx",
maxsize + 1)
@@ -1,42 +0,0 @@
import textwrap
from unittest import TestCase
import simplejson as json
class TestSeparators(TestCase):
def test_separators(self):
h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth',
{'nifty': 87}, {'field': 'yes', 'morefield': False} ]
expect = textwrap.dedent("""\
[
[
"blorpie"
] ,
[
"whoops"
] ,
[] ,
"d-shtaeou" ,
"d-nthiouh" ,
"i-vhbjkhnth" ,
{
"nifty" : 87
} ,
{
"field" : "yes" ,
"morefield" : false
}
]""")
d1 = json.dumps(h)
d2 = json.dumps(h, indent=' ', sort_keys=True, separators=(' ,', ' : '))
h1 = json.loads(d1)
h2 = json.loads(d2)
self.assertEquals(h1, h)
self.assertEquals(h2, h)
self.assertEquals(d2, expect)
@@ -1,21 +0,0 @@
import decimal
from unittest import TestCase
from simplejson import decoder, encoder, scanner
def has_speedups():
return encoder.c_make_encoder is not None
class TestDecode(TestCase):
def test_make_scanner(self):
if not has_speedups():
return
self.assertRaises(AttributeError, scanner.c_make_scanner, 1)
def test_make_encoder(self):
if not has_speedups():
return
self.assertRaises(TypeError, encoder.c_make_encoder,
None,
"\xCD\x7D\x3D\x4E\x12\x4C\xF9\x79\xD7\x52\xBA\x82\xF2\x27\x4A\x7D\xA0\xCA\x75",
None)
@@ -1,99 +0,0 @@
from unittest import TestCase
import simplejson as json
class TestUnicode(TestCase):
def test_encoding1(self):
encoder = json.JSONEncoder(encoding='utf-8')
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
s = u.encode('utf-8')
ju = encoder.encode(u)
js = encoder.encode(s)
self.assertEquals(ju, js)
def test_encoding2(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
s = u.encode('utf-8')
ju = json.dumps(u, encoding='utf-8')
js = json.dumps(s, encoding='utf-8')
self.assertEquals(ju, js)
def test_encoding3(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = json.dumps(u)
self.assertEquals(j, '"\\u03b1\\u03a9"')
def test_encoding4(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = json.dumps([u])
self.assertEquals(j, '["\\u03b1\\u03a9"]')
def test_encoding5(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = json.dumps(u, ensure_ascii=False)
self.assertEquals(j, u'"' + u + u'"')
def test_encoding6(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = json.dumps([u], ensure_ascii=False)
self.assertEquals(j, u'["' + u + u'"]')
def test_big_unicode_encode(self):
u = u'\U0001d120'
self.assertEquals(json.dumps(u), '"\\ud834\\udd20"')
self.assertEquals(json.dumps(u, ensure_ascii=False), u'"\U0001d120"')
def test_big_unicode_decode(self):
u = u'z\U0001d120x'
self.assertEquals(json.loads('"' + u + '"'), u)
self.assertEquals(json.loads('"z\\ud834\\udd20x"'), u)
def test_unicode_decode(self):
for i in range(0, 0xd7ff):
u = unichr(i)
#s = '"\\u{0:04x}"'.format(i)
s = '"\\u%04x"' % (i,)
self.assertEquals(json.loads(s), u)
def test_object_pairs_hook_with_unicode(self):
s = u'{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
p = [(u"xkd", 1), (u"kcw", 2), (u"art", 3), (u"hxm", 4),
(u"qrt", 5), (u"pad", 6), (u"hoy", 7)]
self.assertEqual(json.loads(s), eval(s))
self.assertEqual(json.loads(s, object_pairs_hook=lambda x: x), p)
od = json.loads(s, object_pairs_hook=json.OrderedDict)
self.assertEqual(od, json.OrderedDict(p))
self.assertEqual(type(od), json.OrderedDict)
# the object_pairs_hook takes priority over the object_hook
self.assertEqual(json.loads(s,
object_pairs_hook=json.OrderedDict,
object_hook=lambda x: None),
json.OrderedDict(p))
def test_default_encoding(self):
self.assertEquals(json.loads(u'{"a": "\xe9"}'.encode('utf-8')),
{'a': u'\xe9'})
def test_unicode_preservation(self):
self.assertEquals(type(json.loads(u'""')), unicode)
self.assertEquals(type(json.loads(u'"a"')), unicode)
self.assertEquals(type(json.loads(u'["a"]')[0]), unicode)
def test_ensure_ascii_false_returns_unicode(self):
# http://code.google.com/p/simplejson/issues/detail?id=48
self.assertEquals(type(json.dumps([], ensure_ascii=False)), unicode)
self.assertEquals(type(json.dumps(0, ensure_ascii=False)), unicode)
self.assertEquals(type(json.dumps({}, ensure_ascii=False)), unicode)
self.assertEquals(type(json.dumps("", ensure_ascii=False)), unicode)
def test_ensure_ascii_false_bytestring_encoding(self):
# http://code.google.com/p/simplejson/issues/detail?id=48
doc1 = {u'quux': 'Arr\xc3\xaat sur images'}
doc2 = {u'quux': u'Arr\xeat sur images'}
doc_ascii = '{"quux": "Arr\\u00eat sur images"}'
doc_unicode = u'{"quux": "Arr\xeat sur images"}'
self.assertEquals(json.dumps(doc1), doc_ascii)
self.assertEquals(json.dumps(doc2), doc_ascii)
self.assertEquals(json.dumps(doc1, ensure_ascii=False), doc_unicode)
self.assertEquals(json.dumps(doc2, ensure_ascii=False), doc_unicode)
-39
View File
@@ -1,39 +0,0 @@
r"""Command-line tool to validate and pretty-print JSON
Usage::
$ echo '{"json":"obj"}' | python -m simplejson.tool
{
"json": "obj"
}
$ echo '{ 1.2:3.4}' | python -m simplejson.tool
Expecting property name: line 1 column 2 (char 2)
"""
import sys
import simplejson as json
def main():
if len(sys.argv) == 1:
infile = sys.stdin
outfile = sys.stdout
elif len(sys.argv) == 2:
infile = open(sys.argv[1], 'rb')
outfile = sys.stdout
elif len(sys.argv) == 3:
infile = open(sys.argv[1], 'rb')
outfile = open(sys.argv[2], 'wb')
else:
raise SystemExit(sys.argv[0] + " [infile [outfile]]")
try:
obj = json.load(infile,
object_pairs_hook=json.OrderedDict,
use_decimal=True)
except ValueError, e:
raise SystemExit(e)
json.dump(obj, outfile, sort_keys=True, indent=' ', use_decimal=True)
outfile.write('\n')
if __name__ == '__main__':
main()
-288
View File
@@ -1,288 +0,0 @@
from error import *
from tokens import *
from events import *
from nodes import *
from loader import *
from dumper import *
__version__ = '3.09'
try:
from cyaml import *
__with_libyaml__ = True
except ImportError:
__with_libyaml__ = False
def scan(stream, Loader=Loader):
"""
Scan a YAML stream and produce scanning tokens.
"""
loader = Loader(stream)
while loader.check_token():
yield loader.get_token()
def parse(stream, Loader=Loader):
"""
Parse a YAML stream and produce parsing events.
"""
loader = Loader(stream)
while loader.check_event():
yield loader.get_event()
def compose(stream, Loader=Loader):
"""
Parse the first YAML document in a stream
and produce the corresponding representation tree.
"""
loader = Loader(stream)
return loader.get_single_node()
def compose_all(stream, Loader=Loader):
"""
Parse all YAML documents in a stream
and produce corresponding representation trees.
"""
loader = Loader(stream)
while loader.check_node():
yield loader.get_node()
def load(stream, Loader=Loader):
"""
Parse the first YAML document in a stream
and produce the corresponding Python object.
"""
loader = Loader(stream)
return loader.get_single_data()
def load_all(stream, Loader=Loader):
"""
Parse all YAML documents in a stream
and produce corresponding Python objects.
"""
loader = Loader(stream)
while loader.check_data():
yield loader.get_data()
def safe_load(stream):
"""
Parse the first YAML document in a stream
and produce the corresponding Python object.
Resolve only basic YAML tags.
"""
return load(stream, SafeLoader)
def safe_load_all(stream):
"""
Parse all YAML documents in a stream
and produce corresponding Python objects.
Resolve only basic YAML tags.
"""
return load_all(stream, SafeLoader)
def emit(events, stream=None, Dumper=Dumper,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None):
"""
Emit YAML parsing events into a stream.
If stream is None, return the produced string instead.
"""
getvalue = None
if stream is None:
from StringIO import StringIO
stream = StringIO()
getvalue = stream.getvalue
dumper = Dumper(stream, canonical=canonical, indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break)
for event in events:
dumper.emit(event)
if getvalue:
return getvalue()
def serialize_all(nodes, stream=None, Dumper=Dumper,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding='utf-8', explicit_start=None, explicit_end=None,
version=None, tags=None):
"""
Serialize a sequence of representation trees into a YAML stream.
If stream is None, return the produced string instead.
"""
getvalue = None
if stream is None:
if encoding is None:
from StringIO import StringIO
else:
from cStringIO import StringIO
stream = StringIO()
getvalue = stream.getvalue
dumper = Dumper(stream, canonical=canonical, indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break,
encoding=encoding, version=version, tags=tags,
explicit_start=explicit_start, explicit_end=explicit_end)
dumper.open()
for node in nodes:
dumper.serialize(node)
dumper.close()
if getvalue:
return getvalue()
def serialize(node, stream=None, Dumper=Dumper, **kwds):
"""
Serialize a representation tree into a YAML stream.
If stream is None, return the produced string instead.
"""
return serialize_all([node], stream, Dumper=Dumper, **kwds)
def dump_all(documents, stream=None, Dumper=Dumper,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding='utf-8', explicit_start=None, explicit_end=None,
version=None, tags=None):
"""
Serialize a sequence of Python objects into a YAML stream.
If stream is None, return the produced string instead.
"""
getvalue = None
if stream is None:
if encoding is None:
from StringIO import StringIO
else:
from cStringIO import StringIO
stream = StringIO()
getvalue = stream.getvalue
dumper = Dumper(stream, default_style=default_style,
default_flow_style=default_flow_style,
canonical=canonical, indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break,
encoding=encoding, version=version, tags=tags,
explicit_start=explicit_start, explicit_end=explicit_end)
dumper.open()
for data in documents:
dumper.represent(data)
dumper.close()
if getvalue:
return getvalue()
def dump(data, stream=None, Dumper=Dumper, **kwds):
"""
Serialize a Python object into a YAML stream.
If stream is None, return the produced string instead.
"""
return dump_all([data], stream, Dumper=Dumper, **kwds)
def safe_dump_all(documents, stream=None, **kwds):
"""
Serialize a sequence of Python objects into a YAML stream.
Produce only basic YAML tags.
If stream is None, return the produced string instead.
"""
return dump_all(documents, stream, Dumper=SafeDumper, **kwds)
def safe_dump(data, stream=None, **kwds):
"""
Serialize a Python object into a YAML stream.
Produce only basic YAML tags.
If stream is None, return the produced string instead.
"""
return dump_all([data], stream, Dumper=SafeDumper, **kwds)
def add_implicit_resolver(tag, regexp, first=None,
Loader=Loader, Dumper=Dumper):
"""
Add an implicit scalar detector.
If an implicit scalar value matches the given regexp,
the corresponding tag is assigned to the scalar.
first is a sequence of possible initial characters or None.
"""
Loader.add_implicit_resolver(tag, regexp, first)
Dumper.add_implicit_resolver(tag, regexp, first)
def add_path_resolver(tag, path, kind=None, Loader=Loader, Dumper=Dumper):
"""
Add a path based resolver for the given tag.
A path is a list of keys that forms a path
to a node in the representation tree.
Keys can be string values, integers, or None.
"""
Loader.add_path_resolver(tag, path, kind)
Dumper.add_path_resolver(tag, path, kind)
def add_constructor(tag, constructor, Loader=Loader):
"""
Add a constructor for the given tag.
Constructor is a function that accepts a Loader instance
and a node object and produces the corresponding Python object.
"""
Loader.add_constructor(tag, constructor)
def add_multi_constructor(tag_prefix, multi_constructor, Loader=Loader):
"""
Add a multi-constructor for the given tag prefix.
Multi-constructor is called for a node if its tag starts with tag_prefix.
Multi-constructor accepts a Loader instance, a tag suffix,
and a node object and produces the corresponding Python object.
"""
Loader.add_multi_constructor(tag_prefix, multi_constructor)
def add_representer(data_type, representer, Dumper=Dumper):
"""
Add a representer for the given type.
Representer is a function accepting a Dumper instance
and an instance of the given data type
and producing the corresponding representation node.
"""
Dumper.add_representer(data_type, representer)
def add_multi_representer(data_type, multi_representer, Dumper=Dumper):
"""
Add a representer for the given type.
Multi-representer is a function accepting a Dumper instance
and an instance of the given data type or subtype
and producing the corresponding representation node.
"""
Dumper.add_multi_representer(data_type, multi_representer)
class YAMLObjectMetaclass(type):
"""
The metaclass for YAMLObject.
"""
def __init__(cls, name, bases, kwds):
super(YAMLObjectMetaclass, cls).__init__(name, bases, kwds)
if 'yaml_tag' in kwds and kwds['yaml_tag'] is not None:
cls.yaml_loader.add_constructor(cls.yaml_tag, cls.from_yaml)
cls.yaml_dumper.add_representer(cls, cls.to_yaml)
class YAMLObject(object):
"""
An object that can dump itself to a YAML stream
and load itself from a YAML stream.
"""
__metaclass__ = YAMLObjectMetaclass
__slots__ = () # no direct instantiation, so allow immutable subclasses
yaml_loader = Loader
yaml_dumper = Dumper
yaml_tag = None
yaml_flow_style = None
def from_yaml(cls, loader, node):
"""
Convert a representation node to a Python object.
"""
return loader.construct_yaml_object(node, cls)
from_yaml = classmethod(from_yaml)
def to_yaml(cls, dumper, data):
"""
Convert a Python object to a representation node.
"""
return dumper.represent_yaml_object(cls.yaml_tag, data, cls,
flow_style=cls.yaml_flow_style)
to_yaml = classmethod(to_yaml)
-139
View File
@@ -1,139 +0,0 @@
__all__ = ['Composer', 'ComposerError']
from error import MarkedYAMLError
from events import *
from nodes import *
class ComposerError(MarkedYAMLError):
pass
class Composer(object):
def __init__(self):
self.anchors = {}
def check_node(self):
# Drop the STREAM-START event.
if self.check_event(StreamStartEvent):
self.get_event()
# If there are more documents available?
return not self.check_event(StreamEndEvent)
def get_node(self):
# Get the root node of the next document.
if not self.check_event(StreamEndEvent):
return self.compose_document()
def get_single_node(self):
# Drop the STREAM-START event.
self.get_event()
# Compose a document if the stream is not empty.
document = None
if not self.check_event(StreamEndEvent):
document = self.compose_document()
# Ensure that the stream contains no more documents.
if not self.check_event(StreamEndEvent):
event = self.get_event()
raise ComposerError("expected a single document in the stream",
document.start_mark, "but found another document",
event.start_mark)
# Drop the STREAM-END event.
self.get_event()
return document
def compose_document(self):
# Drop the DOCUMENT-START event.
self.get_event()
# Compose the root node.
node = self.compose_node(None, None)
# Drop the DOCUMENT-END event.
self.get_event()
self.anchors = {}
return node
def compose_node(self, parent, index):
if self.check_event(AliasEvent):
event = self.get_event()
anchor = event.anchor
if anchor not in self.anchors:
raise ComposerError(None, None, "found undefined alias %r"
% anchor.encode('utf-8'), event.start_mark)
return self.anchors[anchor]
event = self.peek_event()
anchor = event.anchor
if anchor is not None:
if anchor in self.anchors:
raise ComposerError("found duplicate anchor %r; first occurence"
% anchor.encode('utf-8'), self.anchors[anchor].start_mark,
"second occurence", event.start_mark)
self.descend_resolver(parent, index)
if self.check_event(ScalarEvent):
node = self.compose_scalar_node(anchor)
elif self.check_event(SequenceStartEvent):
node = self.compose_sequence_node(anchor)
elif self.check_event(MappingStartEvent):
node = self.compose_mapping_node(anchor)
self.ascend_resolver()
return node
def compose_scalar_node(self, anchor):
event = self.get_event()
tag = event.tag
if tag is None or tag == u'!':
tag = self.resolve(ScalarNode, event.value, event.implicit)
node = ScalarNode(tag, event.value,
event.start_mark, event.end_mark, style=event.style)
if anchor is not None:
self.anchors[anchor] = node
return node
def compose_sequence_node(self, anchor):
start_event = self.get_event()
tag = start_event.tag
if tag is None or tag == u'!':
tag = self.resolve(SequenceNode, None, start_event.implicit)
node = SequenceNode(tag, [],
start_event.start_mark, None,
flow_style=start_event.flow_style)
if anchor is not None:
self.anchors[anchor] = node
index = 0
while not self.check_event(SequenceEndEvent):
node.value.append(self.compose_node(node, index))
index += 1
end_event = self.get_event()
node.end_mark = end_event.end_mark
return node
def compose_mapping_node(self, anchor):
start_event = self.get_event()
tag = start_event.tag
if tag is None or tag == u'!':
tag = self.resolve(MappingNode, None, start_event.implicit)
node = MappingNode(tag, [],
start_event.start_mark, None,
flow_style=start_event.flow_style)
if anchor is not None:
self.anchors[anchor] = node
while not self.check_event(MappingEndEvent):
#key_event = self.peek_event()
item_key = self.compose_node(node, None)
#if item_key in node.value:
# raise ComposerError("while composing a mapping", start_event.start_mark,
# "found duplicate key", key_event.start_mark)
item_value = self.compose_node(node, item_key)
#node.value[item_key] = item_value
node.value.append((item_key, item_value))
end_event = self.get_event()
node.end_mark = end_event.end_mark
return node
-684
View File
@@ -1,684 +0,0 @@
__all__ = ['BaseConstructor', 'SafeConstructor', 'Constructor',
'ConstructorError']
from error import *
from nodes import *
import datetime
try:
set
except NameError:
from sets import Set as set
import binascii, re, sys, types
class ConstructorError(MarkedYAMLError):
pass
class BaseConstructor(object):
yaml_constructors = {}
yaml_multi_constructors = {}
def __init__(self):
self.constructed_objects = {}
self.recursive_objects = {}
self.state_generators = []
self.deep_construct = False
def check_data(self):
# If there are more documents available?
return self.check_node()
def get_data(self):
# Construct and return the next document.
if self.check_node():
return self.construct_document(self.get_node())
def get_single_data(self):
# Ensure that the stream contains a single document and construct it.
node = self.get_single_node()
if node is not None:
return self.construct_document(node)
return None
def construct_document(self, node):
data = self.construct_object(node)
while self.state_generators:
state_generators = self.state_generators
self.state_generators = []
for generator in state_generators:
for dummy in generator:
pass
self.constructed_objects = {}
self.recursive_objects = {}
self.deep_construct = False
return data
def construct_object(self, node, deep=False):
if deep:
old_deep = self.deep_construct
self.deep_construct = True
if node in self.constructed_objects:
return self.constructed_objects[node]
if node in self.recursive_objects:
raise ConstructorError(None, None,
"found unconstructable recursive node", node.start_mark)
self.recursive_objects[node] = None
constructor = None
tag_suffix = None
if node.tag in self.yaml_constructors:
constructor = self.yaml_constructors[node.tag]
else:
for tag_prefix in self.yaml_multi_constructors:
if node.tag.startswith(tag_prefix):
tag_suffix = node.tag[len(tag_prefix):]
constructor = self.yaml_multi_constructors[tag_prefix]
break
else:
if None in self.yaml_multi_constructors:
tag_suffix = node.tag
constructor = self.yaml_multi_constructors[None]
elif None in self.yaml_constructors:
constructor = self.yaml_constructors[None]
elif isinstance(node, ScalarNode):
constructor = self.__class__.construct_scalar
elif isinstance(node, SequenceNode):
constructor = self.__class__.construct_sequence
elif isinstance(node, MappingNode):
constructor = self.__class__.construct_mapping
if tag_suffix is None:
data = constructor(self, node)
else:
data = constructor(self, tag_suffix, node)
if isinstance(data, types.GeneratorType):
generator = data
data = generator.next()
if self.deep_construct:
for dummy in generator:
pass
else:
self.state_generators.append(generator)
self.constructed_objects[node] = data
del self.recursive_objects[node]
if deep:
self.deep_construct = old_deep
return data
def construct_scalar(self, node):
if not isinstance(node, ScalarNode):
raise ConstructorError(None, None,
"expected a scalar node, but found %s" % node.id,
node.start_mark)
return node.value
def construct_sequence(self, node, deep=False):
if not isinstance(node, SequenceNode):
raise ConstructorError(None, None,
"expected a sequence node, but found %s" % node.id,
node.start_mark)
return [self.construct_object(child, deep=deep)
for child in node.value]
def construct_mapping(self, node, deep=False):
if not isinstance(node, MappingNode):
raise ConstructorError(None, None,
"expected a mapping node, but found %s" % node.id,
node.start_mark)
mapping = {}
for key_node, value_node in node.value:
key = self.construct_object(key_node, deep=deep)
try:
hash(key)
except TypeError, exc:
raise ConstructorError("while constructing a mapping", node.start_mark,
"found unacceptable key (%s)" % exc, key_node.start_mark)
value = self.construct_object(value_node, deep=deep)
mapping[key] = value
return mapping
def construct_pairs(self, node, deep=False):
if not isinstance(node, MappingNode):
raise ConstructorError(None, None,
"expected a mapping node, but found %s" % node.id,
node.start_mark)
pairs = []
for key_node, value_node in node.value:
key = self.construct_object(key_node, deep=deep)
value = self.construct_object(value_node, deep=deep)
pairs.append((key, value))
return pairs
def add_constructor(cls, tag, constructor):
if not 'yaml_constructors' in cls.__dict__:
cls.yaml_constructors = cls.yaml_constructors.copy()
cls.yaml_constructors[tag] = constructor
add_constructor = classmethod(add_constructor)
def add_multi_constructor(cls, tag_prefix, multi_constructor):
if not 'yaml_multi_constructors' in cls.__dict__:
cls.yaml_multi_constructors = cls.yaml_multi_constructors.copy()
cls.yaml_multi_constructors[tag_prefix] = multi_constructor
add_multi_constructor = classmethod(add_multi_constructor)
class SafeConstructor(BaseConstructor):
def construct_scalar(self, node):
if isinstance(node, MappingNode):
for key_node, value_node in node.value:
if key_node.tag == u'tag:yaml.org,2002:value':
return self.construct_scalar(value_node)
return BaseConstructor.construct_scalar(self, node)
def flatten_mapping(self, node):
merge = []
index = 0
while index < len(node.value):
key_node, value_node = node.value[index]
if key_node.tag == u'tag:yaml.org,2002:merge':
del node.value[index]
if isinstance(value_node, MappingNode):
self.flatten_mapping(value_node)
merge.extend(value_node.value)
elif isinstance(value_node, SequenceNode):
submerge = []
for subnode in value_node.value:
if not isinstance(subnode, MappingNode):
raise ConstructorError("while constructing a mapping",
node.start_mark,
"expected a mapping for merging, but found %s"
% subnode.id, subnode.start_mark)
self.flatten_mapping(subnode)
submerge.append(subnode.value)
submerge.reverse()
for value in submerge:
merge.extend(value)
else:
raise ConstructorError("while constructing a mapping", node.start_mark,
"expected a mapping or list of mappings for merging, but found %s"
% value_node.id, value_node.start_mark)
elif key_node.tag == u'tag:yaml.org,2002:value':
key_node.tag = u'tag:yaml.org,2002:str'
index += 1
else:
index += 1
if merge:
node.value = merge + node.value
def construct_mapping(self, node, deep=False):
if isinstance(node, MappingNode):
self.flatten_mapping(node)
return BaseConstructor.construct_mapping(self, node, deep=deep)
def construct_yaml_null(self, node):
self.construct_scalar(node)
return None
bool_values = {
u'yes': True,
u'no': False,
u'true': True,
u'false': False,
u'on': True,
u'off': False,
}
def construct_yaml_bool(self, node):
value = self.construct_scalar(node)
return self.bool_values[value.lower()]
def construct_yaml_int(self, node):
value = str(self.construct_scalar(node))
value = value.replace('_', '')
sign = +1
if value[0] == '-':
sign = -1
if value[0] in '+-':
value = value[1:]
if value == '0':
return 0
elif value.startswith('0b'):
return sign*int(value[2:], 2)
elif value.startswith('0x'):
return sign*int(value[2:], 16)
elif value[0] == '0':
return sign*int(value, 8)
elif ':' in value:
digits = [int(part) for part in value.split(':')]
digits.reverse()
base = 1
value = 0
for digit in digits:
value += digit*base
base *= 60
return sign*value
else:
return sign*int(value)
inf_value = 1e300
while inf_value != inf_value*inf_value:
inf_value *= inf_value
nan_value = -inf_value/inf_value # Trying to make a quiet NaN (like C99).
def construct_yaml_float(self, node):
value = str(self.construct_scalar(node))
value = value.replace('_', '').lower()
sign = +1
if value[0] == '-':
sign = -1
if value[0] in '+-':
value = value[1:]
if value == '.inf':
return sign*self.inf_value
elif value == '.nan':
return self.nan_value
elif ':' in value:
digits = [float(part) for part in value.split(':')]
digits.reverse()
base = 1
value = 0.0
for digit in digits:
value += digit*base
base *= 60
return sign*value
else:
return sign*float(value)
def construct_yaml_binary(self, node):
value = self.construct_scalar(node)
try:
return str(value).decode('base64')
except (binascii.Error, UnicodeEncodeError), exc:
raise ConstructorError(None, None,
"failed to decode base64 data: %s" % exc, node.start_mark)
timestamp_regexp = re.compile(
ur'''^(?P<year>[0-9][0-9][0-9][0-9])
-(?P<month>[0-9][0-9]?)
-(?P<day>[0-9][0-9]?)
(?:(?:[Tt]|[ \t]+)
(?P<hour>[0-9][0-9]?)
:(?P<minute>[0-9][0-9])
:(?P<second>[0-9][0-9])
(?:\.(?P<fraction>[0-9]*))?
(?:[ \t]*(?P<tz>Z|(?P<tz_sign>[-+])(?P<tz_hour>[0-9][0-9]?)
(?::(?P<tz_minute>[0-9][0-9]))?))?)?$''', re.X)
def construct_yaml_timestamp(self, node):
value = self.construct_scalar(node)
match = self.timestamp_regexp.match(node.value)
values = match.groupdict()
year = int(values['year'])
month = int(values['month'])
day = int(values['day'])
if not values['hour']:
return datetime.date(year, month, day)
hour = int(values['hour'])
minute = int(values['minute'])
second = int(values['second'])
fraction = 0
if values['fraction']:
fraction = values['fraction'][:6]
while len(fraction) < 6:
fraction += '0'
fraction = int(fraction)
delta = None
if values['tz_sign']:
tz_hour = int(values['tz_hour'])
tz_minute = int(values['tz_minute'] or 0)
delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute)
if values['tz_sign'] == '-':
delta = -delta
data = datetime.datetime(year, month, day, hour, minute, second, fraction)
if delta:
data -= delta
return data
def construct_yaml_omap(self, node):
# Note: we do not check for duplicate keys, because it's too
# CPU-expensive.
omap = []
yield omap
if not isinstance(node, SequenceNode):
raise ConstructorError("while constructing an ordered map", node.start_mark,
"expected a sequence, but found %s" % node.id, node.start_mark)
for subnode in node.value:
if not isinstance(subnode, MappingNode):
raise ConstructorError("while constructing an ordered map", node.start_mark,
"expected a mapping of length 1, but found %s" % subnode.id,
subnode.start_mark)
if len(subnode.value) != 1:
raise ConstructorError("while constructing an ordered map", node.start_mark,
"expected a single mapping item, but found %d items" % len(subnode.value),
subnode.start_mark)
key_node, value_node = subnode.value[0]
key = self.construct_object(key_node)
value = self.construct_object(value_node)
omap.append((key, value))
def construct_yaml_pairs(self, node):
# Note: the same code as `construct_yaml_omap`.
pairs = []
yield pairs
if not isinstance(node, SequenceNode):
raise ConstructorError("while constructing pairs", node.start_mark,
"expected a sequence, but found %s" % node.id, node.start_mark)
for subnode in node.value:
if not isinstance(subnode, MappingNode):
raise ConstructorError("while constructing pairs", node.start_mark,
"expected a mapping of length 1, but found %s" % subnode.id,
subnode.start_mark)
if len(subnode.value) != 1:
raise ConstructorError("while constructing pairs", node.start_mark,
"expected a single mapping item, but found %d items" % len(subnode.value),
subnode.start_mark)
key_node, value_node = subnode.value[0]
key = self.construct_object(key_node)
value = self.construct_object(value_node)
pairs.append((key, value))
def construct_yaml_set(self, node):
data = set()
yield data
value = self.construct_mapping(node)
data.update(value)
def construct_yaml_str(self, node):
value = self.construct_scalar(node)
try:
return value.encode('ascii')
except UnicodeEncodeError:
return value
def construct_yaml_seq(self, node):
data = []
yield data
data.extend(self.construct_sequence(node))
def construct_yaml_map(self, node):
data = {}
yield data
value = self.construct_mapping(node)
data.update(value)
def construct_yaml_object(self, node, cls):
data = cls.__new__(cls)
yield data
if hasattr(data, '__setstate__'):
state = self.construct_mapping(node, deep=True)
data.__setstate__(state)
else:
state = self.construct_mapping(node)
data.__dict__.update(state)
def construct_undefined(self, node):
raise ConstructorError(None, None,
"could not determine a constructor for the tag %r" % node.tag.encode('utf-8'),
node.start_mark)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:null',
SafeConstructor.construct_yaml_null)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:bool',
SafeConstructor.construct_yaml_bool)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:int',
SafeConstructor.construct_yaml_int)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:float',
SafeConstructor.construct_yaml_float)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:binary',
SafeConstructor.construct_yaml_binary)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:timestamp',
SafeConstructor.construct_yaml_timestamp)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:omap',
SafeConstructor.construct_yaml_omap)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:pairs',
SafeConstructor.construct_yaml_pairs)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:set',
SafeConstructor.construct_yaml_set)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:str',
SafeConstructor.construct_yaml_str)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:seq',
SafeConstructor.construct_yaml_seq)
SafeConstructor.add_constructor(
u'tag:yaml.org,2002:map',
SafeConstructor.construct_yaml_map)
SafeConstructor.add_constructor(None,
SafeConstructor.construct_undefined)
class Constructor(SafeConstructor):
def construct_python_str(self, node):
return self.construct_scalar(node).encode('utf-8')
def construct_python_unicode(self, node):
return self.construct_scalar(node)
def construct_python_long(self, node):
return long(self.construct_yaml_int(node))
def construct_python_complex(self, node):
return complex(self.construct_scalar(node))
def construct_python_tuple(self, node):
return tuple(self.construct_sequence(node))
def find_python_module(self, name, mark):
if not name:
raise ConstructorError("while constructing a Python module", mark,
"expected non-empty name appended to the tag", mark)
try:
__import__(name)
except ImportError, exc:
raise ConstructorError("while constructing a Python module", mark,
"cannot find module %r (%s)" % (name.encode('utf-8'), exc), mark)
return sys.modules[name]
def find_python_name(self, name, mark):
if not name:
raise ConstructorError("while constructing a Python object", mark,
"expected non-empty name appended to the tag", mark)
if u'.' in name:
# Python 2.4 only
#module_name, object_name = name.rsplit('.', 1)
items = name.split('.')
object_name = items.pop()
module_name = '.'.join(items)
else:
module_name = '__builtin__'
object_name = name
try:
__import__(module_name)
except ImportError, exc:
raise ConstructorError("while constructing a Python object", mark,
"cannot find module %r (%s)" % (module_name.encode('utf-8'), exc), mark)
module = sys.modules[module_name]
if not hasattr(module, object_name):
raise ConstructorError("while constructing a Python object", mark,
"cannot find %r in the module %r" % (object_name.encode('utf-8'),
module.__name__), mark)
return getattr(module, object_name)
def construct_python_name(self, suffix, node):
value = self.construct_scalar(node)
if value:
raise ConstructorError("while constructing a Python name", node.start_mark,
"expected the empty value, but found %r" % value.encode('utf-8'),
node.start_mark)
return self.find_python_name(suffix, node.start_mark)
def construct_python_module(self, suffix, node):
value = self.construct_scalar(node)
if value:
raise ConstructorError("while constructing a Python module", node.start_mark,
"expected the empty value, but found %r" % value.encode('utf-8'),
node.start_mark)
return self.find_python_module(suffix, node.start_mark)
class classobj: pass
def make_python_instance(self, suffix, node,
args=None, kwds=None, newobj=False):
if not args:
args = []
if not kwds:
kwds = {}
cls = self.find_python_name(suffix, node.start_mark)
if newobj and isinstance(cls, type(self.classobj)) \
and not args and not kwds:
instance = self.classobj()
instance.__class__ = cls
return instance
elif newobj and isinstance(cls, type):
return cls.__new__(cls, *args, **kwds)
else:
return cls(*args, **kwds)
def set_python_instance_state(self, instance, state):
if hasattr(instance, '__setstate__'):
instance.__setstate__(state)
else:
slotstate = {}
if isinstance(state, tuple) and len(state) == 2:
state, slotstate = state
if hasattr(instance, '__dict__'):
instance.__dict__.update(state)
elif state:
slotstate.update(state)
for key, value in slotstate.items():
setattr(object, key, value)
def construct_python_object(self, suffix, node):
# Format:
# !!python/object:module.name { ... state ... }
instance = self.make_python_instance(suffix, node, newobj=True)
yield instance
deep = hasattr(instance, '__setstate__')
state = self.construct_mapping(node, deep=deep)
self.set_python_instance_state(instance, state)
def construct_python_object_apply(self, suffix, node, newobj=False):
# Format:
# !!python/object/apply # (or !!python/object/new)
# args: [ ... arguments ... ]
# kwds: { ... keywords ... }
# state: ... state ...
# listitems: [ ... listitems ... ]
# dictitems: { ... dictitems ... }
# or short format:
# !!python/object/apply [ ... arguments ... ]
# The difference between !!python/object/apply and !!python/object/new
# is how an object is created, check make_python_instance for details.
if isinstance(node, SequenceNode):
args = self.construct_sequence(node, deep=True)
kwds = {}
state = {}
listitems = []
dictitems = {}
else:
value = self.construct_mapping(node, deep=True)
args = value.get('args', [])
kwds = value.get('kwds', {})
state = value.get('state', {})
listitems = value.get('listitems', [])
dictitems = value.get('dictitems', {})
instance = self.make_python_instance(suffix, node, args, kwds, newobj)
if state:
self.set_python_instance_state(instance, state)
if listitems:
instance.extend(listitems)
if dictitems:
for key in dictitems:
instance[key] = dictitems[key]
return instance
def construct_python_object_new(self, suffix, node):
return self.construct_python_object_apply(suffix, node, newobj=True)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/none',
Constructor.construct_yaml_null)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/bool',
Constructor.construct_yaml_bool)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/str',
Constructor.construct_python_str)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/unicode',
Constructor.construct_python_unicode)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/int',
Constructor.construct_yaml_int)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/long',
Constructor.construct_python_long)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/float',
Constructor.construct_yaml_float)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/complex',
Constructor.construct_python_complex)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/list',
Constructor.construct_yaml_seq)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/tuple',
Constructor.construct_python_tuple)
Constructor.add_constructor(
u'tag:yaml.org,2002:python/dict',
Constructor.construct_yaml_map)
Constructor.add_multi_constructor(
u'tag:yaml.org,2002:python/name:',
Constructor.construct_python_name)
Constructor.add_multi_constructor(
u'tag:yaml.org,2002:python/module:',
Constructor.construct_python_module)
Constructor.add_multi_constructor(
u'tag:yaml.org,2002:python/object:',
Constructor.construct_python_object)
Constructor.add_multi_constructor(
u'tag:yaml.org,2002:python/object/apply:',
Constructor.construct_python_object_apply)
Constructor.add_multi_constructor(
u'tag:yaml.org,2002:python/object/new:',
Constructor.construct_python_object_new)
-85
View File
@@ -1,85 +0,0 @@
__all__ = ['CBaseLoader', 'CSafeLoader', 'CLoader',
'CBaseDumper', 'CSafeDumper', 'CDumper']
from _yaml import CParser, CEmitter
from constructor import *
from serializer import *
from representer import *
from resolver import *
class CBaseLoader(CParser, BaseConstructor, BaseResolver):
def __init__(self, stream):
CParser.__init__(self, stream)
BaseConstructor.__init__(self)
BaseResolver.__init__(self)
class CSafeLoader(CParser, SafeConstructor, Resolver):
def __init__(self, stream):
CParser.__init__(self, stream)
SafeConstructor.__init__(self)
Resolver.__init__(self)
class CLoader(CParser, Constructor, Resolver):
def __init__(self, stream):
CParser.__init__(self, stream)
Constructor.__init__(self)
Resolver.__init__(self)
class CBaseDumper(CEmitter, BaseRepresenter, BaseResolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
CEmitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width, encoding=encoding,
allow_unicode=allow_unicode, line_break=line_break,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
Representer.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)
class CSafeDumper(CEmitter, SafeRepresenter, Resolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
CEmitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width, encoding=encoding,
allow_unicode=allow_unicode, line_break=line_break,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
SafeRepresenter.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)
class CDumper(CEmitter, Serializer, Representer, Resolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
CEmitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width, encoding=encoding,
allow_unicode=allow_unicode, line_break=line_break,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
Representer.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)
-62
View File
@@ -1,62 +0,0 @@
__all__ = ['BaseDumper', 'SafeDumper', 'Dumper']
from emitter import *
from serializer import *
from representer import *
from resolver import *
class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
Emitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break)
Serializer.__init__(self, encoding=encoding,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
Representer.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)
class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
Emitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break)
Serializer.__init__(self, encoding=encoding,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
SafeRepresenter.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)
class Dumper(Emitter, Serializer, Representer, Resolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
Emitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break)
Serializer.__init__(self, encoding=encoding,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
Representer.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)
File diff suppressed because it is too large Load Diff
-75
View File
@@ -1,75 +0,0 @@
__all__ = ['Mark', 'YAMLError', 'MarkedYAMLError']
class Mark(object):
def __init__(self, name, index, line, column, buffer, pointer):
self.name = name
self.index = index
self.line = line
self.column = column
self.buffer = buffer
self.pointer = pointer
def get_snippet(self, indent=4, max_length=75):
if self.buffer is None:
return None
head = ''
start = self.pointer
while start > 0 and self.buffer[start-1] not in u'\0\r\n\x85\u2028\u2029':
start -= 1
if self.pointer-start > max_length/2-1:
head = ' ... '
start += 5
break
tail = ''
end = self.pointer
while end < len(self.buffer) and self.buffer[end] not in u'\0\r\n\x85\u2028\u2029':
end += 1
if end-self.pointer > max_length/2-1:
tail = ' ... '
end -= 5
break
snippet = self.buffer[start:end].encode('utf-8')
return ' '*indent + head + snippet + tail + '\n' \
+ ' '*(indent+self.pointer-start+len(head)) + '^'
def __str__(self):
snippet = self.get_snippet()
where = " in \"%s\", line %d, column %d" \
% (self.name, self.line+1, self.column+1)
if snippet is not None:
where += ":\n"+snippet
return where
class YAMLError(Exception):
pass
class MarkedYAMLError(YAMLError):
def __init__(self, context=None, context_mark=None,
problem=None, problem_mark=None, note=None):
self.context = context
self.context_mark = context_mark
self.problem = problem
self.problem_mark = problem_mark
self.note = note
def __str__(self):
lines = []
if self.context is not None:
lines.append(self.context)
if self.context_mark is not None \
and (self.problem is None or self.problem_mark is None
or self.context_mark.name != self.problem_mark.name
or self.context_mark.line != self.problem_mark.line
or self.context_mark.column != self.problem_mark.column):
lines.append(str(self.context_mark))
if self.problem is not None:
lines.append(self.problem)
if self.problem_mark is not None:
lines.append(str(self.problem_mark))
if self.note is not None:
lines.append(self.note)
return '\n'.join(lines)
-86
View File
@@ -1,86 +0,0 @@
# Abstract classes.
class Event(object):
def __init__(self, start_mark=None, end_mark=None):
self.start_mark = start_mark
self.end_mark = end_mark
def __repr__(self):
attributes = [key for key in ['anchor', 'tag', 'implicit', 'value']
if hasattr(self, key)]
arguments = ', '.join(['%s=%r' % (key, getattr(self, key))
for key in attributes])
return '%s(%s)' % (self.__class__.__name__, arguments)
class NodeEvent(Event):
def __init__(self, anchor, start_mark=None, end_mark=None):
self.anchor = anchor
self.start_mark = start_mark
self.end_mark = end_mark
class CollectionStartEvent(NodeEvent):
def __init__(self, anchor, tag, implicit, start_mark=None, end_mark=None,
flow_style=None):
self.anchor = anchor
self.tag = tag
self.implicit = implicit
self.start_mark = start_mark
self.end_mark = end_mark
self.flow_style = flow_style
class CollectionEndEvent(Event):
pass
# Implementations.
class StreamStartEvent(Event):
def __init__(self, start_mark=None, end_mark=None, encoding=None):
self.start_mark = start_mark
self.end_mark = end_mark
self.encoding = encoding
class StreamEndEvent(Event):
pass
class DocumentStartEvent(Event):
def __init__(self, start_mark=None, end_mark=None,
explicit=None, version=None, tags=None):
self.start_mark = start_mark
self.end_mark = end_mark
self.explicit = explicit
self.version = version
self.tags = tags
class DocumentEndEvent(Event):
def __init__(self, start_mark=None, end_mark=None,
explicit=None):
self.start_mark = start_mark
self.end_mark = end_mark
self.explicit = explicit
class AliasEvent(NodeEvent):
pass
class ScalarEvent(NodeEvent):
def __init__(self, anchor, tag, implicit, value,
start_mark=None, end_mark=None, style=None):
self.anchor = anchor
self.tag = tag
self.implicit = implicit
self.value = value
self.start_mark = start_mark
self.end_mark = end_mark
self.style = style
class SequenceStartEvent(CollectionStartEvent):
pass
class SequenceEndEvent(CollectionEndEvent):
pass
class MappingStartEvent(CollectionStartEvent):
pass
class MappingEndEvent(CollectionEndEvent):
pass
-40
View File
@@ -1,40 +0,0 @@
__all__ = ['BaseLoader', 'SafeLoader', 'Loader']
from reader import *
from scanner import *
from parser import *
from composer import *
from constructor import *
from resolver import *
class BaseLoader(Reader, Scanner, Parser, Composer, BaseConstructor, BaseResolver):
def __init__(self, stream):
Reader.__init__(self, stream)
Scanner.__init__(self)
Parser.__init__(self)
Composer.__init__(self)
BaseConstructor.__init__(self)
BaseResolver.__init__(self)
class SafeLoader(Reader, Scanner, Parser, Composer, SafeConstructor, Resolver):
def __init__(self, stream):
Reader.__init__(self, stream)
Scanner.__init__(self)
Parser.__init__(self)
Composer.__init__(self)
SafeConstructor.__init__(self)
Resolver.__init__(self)
class Loader(Reader, Scanner, Parser, Composer, Constructor, Resolver):
def __init__(self, stream):
Reader.__init__(self, stream)
Scanner.__init__(self)
Parser.__init__(self)
Composer.__init__(self)
Constructor.__init__(self)
Resolver.__init__(self)
-49
View File
@@ -1,49 +0,0 @@
class Node(object):
def __init__(self, tag, value, start_mark, end_mark):
self.tag = tag
self.value = value
self.start_mark = start_mark
self.end_mark = end_mark
def __repr__(self):
value = self.value
#if isinstance(value, list):
# if len(value) == 0:
# value = '<empty>'
# elif len(value) == 1:
# value = '<1 item>'
# else:
# value = '<%d items>' % len(value)
#else:
# if len(value) > 75:
# value = repr(value[:70]+u' ... ')
# else:
# value = repr(value)
value = repr(value)
return '%s(tag=%r, value=%s)' % (self.__class__.__name__, self.tag, value)
class ScalarNode(Node):
id = 'scalar'
def __init__(self, tag, value,
start_mark=None, end_mark=None, style=None):
self.tag = tag
self.value = value
self.start_mark = start_mark
self.end_mark = end_mark
self.style = style
class CollectionNode(Node):
def __init__(self, tag, value,
start_mark=None, end_mark=None, flow_style=None):
self.tag = tag
self.value = value
self.start_mark = start_mark
self.end_mark = end_mark
self.flow_style = flow_style
class SequenceNode(CollectionNode):
id = 'sequence'
class MappingNode(CollectionNode):
id = 'mapping'
-584
View File
@@ -1,584 +0,0 @@
# The following YAML grammar is LL(1) and is parsed by a recursive descent
# parser.
#
# stream ::= STREAM-START implicit_document? explicit_document* STREAM-END
# implicit_document ::= block_node DOCUMENT-END*
# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END*
# block_node_or_indentless_sequence ::=
# ALIAS
# | properties (block_content | indentless_block_sequence)?
# | block_content
# | indentless_block_sequence
# block_node ::= ALIAS
# | properties block_content?
# | block_content
# flow_node ::= ALIAS
# | properties flow_content?
# | flow_content
# properties ::= TAG ANCHOR? | ANCHOR TAG?
# block_content ::= block_collection | flow_collection | SCALAR
# flow_content ::= flow_collection | SCALAR
# block_collection ::= block_sequence | block_mapping
# flow_collection ::= flow_sequence | flow_mapping
# block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END
# indentless_sequence ::= (BLOCK-ENTRY block_node?)+
# block_mapping ::= BLOCK-MAPPING_START
# ((KEY block_node_or_indentless_sequence?)?
# (VALUE block_node_or_indentless_sequence?)?)*
# BLOCK-END
# flow_sequence ::= FLOW-SEQUENCE-START
# (flow_sequence_entry FLOW-ENTRY)*
# flow_sequence_entry?
# FLOW-SEQUENCE-END
# flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)?
# flow_mapping ::= FLOW-MAPPING-START
# (flow_mapping_entry FLOW-ENTRY)*
# flow_mapping_entry?
# FLOW-MAPPING-END
# flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)?
#
# FIRST sets:
#
# stream: { STREAM-START }
# explicit_document: { DIRECTIVE DOCUMENT-START }
# implicit_document: FIRST(block_node)
# block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START }
# flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START }
# block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR }
# flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR }
# block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START }
# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START }
# block_sequence: { BLOCK-SEQUENCE-START }
# block_mapping: { BLOCK-MAPPING-START }
# block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY }
# indentless_sequence: { ENTRY }
# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START }
# flow_sequence: { FLOW-SEQUENCE-START }
# flow_mapping: { FLOW-MAPPING-START }
# flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY }
# flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY }
__all__ = ['Parser', 'ParserError']
from error import MarkedYAMLError
from tokens import *
from events import *
from scanner import *
class ParserError(MarkedYAMLError):
pass
class Parser(object):
# Since writing a recursive-descendant parser is a straightforward task, we
# do not give many comments here.
DEFAULT_TAGS = {
u'!': u'!',
u'!!': u'tag:yaml.org,2002:',
}
def __init__(self):
self.current_event = None
self.yaml_version = None
self.tag_handles = {}
self.states = []
self.marks = []
self.state = self.parse_stream_start
def check_event(self, *choices):
# Check the type of the next event.
if self.current_event is None:
if self.state:
self.current_event = self.state()
if self.current_event is not None:
if not choices:
return True
for choice in choices:
if isinstance(self.current_event, choice):
return True
return False
def peek_event(self):
# Get the next event.
if self.current_event is None:
if self.state:
self.current_event = self.state()
return self.current_event
def get_event(self):
# Get the next event and proceed further.
if self.current_event is None:
if self.state:
self.current_event = self.state()
value = self.current_event
self.current_event = None
return value
# stream ::= STREAM-START implicit_document? explicit_document* STREAM-END
# implicit_document ::= block_node DOCUMENT-END*
# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END*
def parse_stream_start(self):
# Parse the stream start.
token = self.get_token()
event = StreamStartEvent(token.start_mark, token.end_mark,
encoding=token.encoding)
# Prepare the next state.
self.state = self.parse_implicit_document_start
return event
def parse_implicit_document_start(self):
# Parse an implicit document.
if not self.check_token(DirectiveToken, DocumentStartToken,
StreamEndToken):
self.tag_handles = self.DEFAULT_TAGS
token = self.peek_token()
start_mark = end_mark = token.start_mark
event = DocumentStartEvent(start_mark, end_mark,
explicit=False)
# Prepare the next state.
self.states.append(self.parse_document_end)
self.state = self.parse_block_node
return event
else:
return self.parse_document_start()
def parse_document_start(self):
# Parse any extra document end indicators.
while self.check_token(DocumentEndToken):
self.get_token()
# Parse an explicit document.
if not self.check_token(StreamEndToken):
token = self.peek_token()
start_mark = token.start_mark
version, tags = self.process_directives()
if not self.check_token(DocumentStartToken):
raise ParserError(None, None,
"expected '<document start>', but found %r"
% self.peek_token().id,
self.peek_token().start_mark)
token = self.get_token()
end_mark = token.end_mark
event = DocumentStartEvent(start_mark, end_mark,
explicit=True, version=version, tags=tags)
self.states.append(self.parse_document_end)
self.state = self.parse_document_content
else:
# Parse the end of the stream.
token = self.get_token()
event = StreamEndEvent(token.start_mark, token.end_mark)
assert not self.states
assert not self.marks
self.state = None
return event
def parse_document_end(self):
# Parse the document end.
token = self.peek_token()
start_mark = end_mark = token.start_mark
explicit = False
if self.check_token(DocumentEndToken):
token = self.get_token()
end_mark = token.end_mark
explicit = True
event = DocumentEndEvent(start_mark, end_mark,
explicit=explicit)
# Prepare the next state.
self.state = self.parse_document_start
return event
def parse_document_content(self):
if self.check_token(DirectiveToken,
DocumentStartToken, DocumentEndToken, StreamEndToken):
event = self.process_empty_scalar(self.peek_token().start_mark)
self.state = self.states.pop()
return event
else:
return self.parse_block_node()
def process_directives(self):
self.yaml_version = None
self.tag_handles = {}
while self.check_token(DirectiveToken):
token = self.get_token()
if token.name == u'YAML':
if self.yaml_version is not None:
raise ParserError(None, None,
"found duplicate YAML directive", token.start_mark)
major, minor = token.value
if major != 1:
raise ParserError(None, None,
"found incompatible YAML document (version 1.* is required)",
token.start_mark)
self.yaml_version = token.value
elif token.name == u'TAG':
handle, prefix = token.value
if handle in self.tag_handles:
raise ParserError(None, None,
"duplicate tag handle %r" % handle.encode('utf-8'),
token.start_mark)
self.tag_handles[handle] = prefix
if self.tag_handles:
value = self.yaml_version, self.tag_handles.copy()
else:
value = self.yaml_version, None
for key in self.DEFAULT_TAGS:
if key not in self.tag_handles:
self.tag_handles[key] = self.DEFAULT_TAGS[key]
return value
# block_node_or_indentless_sequence ::= ALIAS
# | properties (block_content | indentless_block_sequence)?
# | block_content
# | indentless_block_sequence
# block_node ::= ALIAS
# | properties block_content?
# | block_content
# flow_node ::= ALIAS
# | properties flow_content?
# | flow_content
# properties ::= TAG ANCHOR? | ANCHOR TAG?
# block_content ::= block_collection | flow_collection | SCALAR
# flow_content ::= flow_collection | SCALAR
# block_collection ::= block_sequence | block_mapping
# flow_collection ::= flow_sequence | flow_mapping
def parse_block_node(self):
return self.parse_node(block=True)
def parse_flow_node(self):
return self.parse_node()
def parse_block_node_or_indentless_sequence(self):
return self.parse_node(block=True, indentless_sequence=True)
def parse_node(self, block=False, indentless_sequence=False):
if self.check_token(AliasToken):
token = self.get_token()
event = AliasEvent(token.value, token.start_mark, token.end_mark)
self.state = self.states.pop()
else:
anchor = None
tag = None
start_mark = end_mark = tag_mark = None
if self.check_token(AnchorToken):
token = self.get_token()
start_mark = token.start_mark
end_mark = token.end_mark
anchor = token.value
if self.check_token(TagToken):
token = self.get_token()
tag_mark = token.start_mark
end_mark = token.end_mark
tag = token.value
elif self.check_token(TagToken):
token = self.get_token()
start_mark = tag_mark = token.start_mark
end_mark = token.end_mark
tag = token.value
if self.check_token(AnchorToken):
token = self.get_token()
end_mark = token.end_mark
anchor = token.value
if tag is not None:
handle, suffix = tag
if handle is not None:
if handle not in self.tag_handles:
raise ParserError("while parsing a node", start_mark,
"found undefined tag handle %r" % handle.encode('utf-8'),
tag_mark)
tag = self.tag_handles[handle]+suffix
else:
tag = suffix
#if tag == u'!':
# raise ParserError("while parsing a node", start_mark,
# "found non-specific tag '!'", tag_mark,
# "Please check 'http://pyyaml.org/wiki/YAMLNonSpecificTag' and share your opinion.")
if start_mark is None:
start_mark = end_mark = self.peek_token().start_mark
event = None
implicit = (tag is None or tag == u'!')
if indentless_sequence and self.check_token(BlockEntryToken):
end_mark = self.peek_token().end_mark
event = SequenceStartEvent(anchor, tag, implicit,
start_mark, end_mark)
self.state = self.parse_indentless_sequence_entry
else:
if self.check_token(ScalarToken):
token = self.get_token()
end_mark = token.end_mark
if (token.plain and tag is None) or tag == u'!':
implicit = (True, False)
elif tag is None:
implicit = (False, True)
else:
implicit = (False, False)
event = ScalarEvent(anchor, tag, implicit, token.value,
start_mark, end_mark, style=token.style)
self.state = self.states.pop()
elif self.check_token(FlowSequenceStartToken):
end_mark = self.peek_token().end_mark
event = SequenceStartEvent(anchor, tag, implicit,
start_mark, end_mark, flow_style=True)
self.state = self.parse_flow_sequence_first_entry
elif self.check_token(FlowMappingStartToken):
end_mark = self.peek_token().end_mark
event = MappingStartEvent(anchor, tag, implicit,
start_mark, end_mark, flow_style=True)
self.state = self.parse_flow_mapping_first_key
elif block and self.check_token(BlockSequenceStartToken):
end_mark = self.peek_token().start_mark
event = SequenceStartEvent(anchor, tag, implicit,
start_mark, end_mark, flow_style=False)
self.state = self.parse_block_sequence_first_entry
elif block and self.check_token(BlockMappingStartToken):
end_mark = self.peek_token().start_mark
event = MappingStartEvent(anchor, tag, implicit,
start_mark, end_mark, flow_style=False)
self.state = self.parse_block_mapping_first_key
elif anchor is not None or tag is not None:
# Empty scalars are allowed even if a tag or an anchor is
# specified.
event = ScalarEvent(anchor, tag, (implicit, False), u'',
start_mark, end_mark)
self.state = self.states.pop()
else:
if block:
node = 'block'
else:
node = 'flow'
token = self.peek_token()
raise ParserError("while parsing a %s node" % node, start_mark,
"expected the node content, but found %r" % token.id,
token.start_mark)
return event
# block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END
def parse_block_sequence_first_entry(self):
token = self.get_token()
self.marks.append(token.start_mark)
return self.parse_block_sequence_entry()
def parse_block_sequence_entry(self):
if self.check_token(BlockEntryToken):
token = self.get_token()
if not self.check_token(BlockEntryToken, BlockEndToken):
self.states.append(self.parse_block_sequence_entry)
return self.parse_block_node()
else:
self.state = self.parse_block_sequence_entry
return self.process_empty_scalar(token.end_mark)
if not self.check_token(BlockEndToken):
token = self.peek_token()
raise ParserError("while parsing a block collection", self.marks[-1],
"expected <block end>, but found %r" % token.id, token.start_mark)
token = self.get_token()
event = SequenceEndEvent(token.start_mark, token.end_mark)
self.state = self.states.pop()
self.marks.pop()
return event
# indentless_sequence ::= (BLOCK-ENTRY block_node?)+
def parse_indentless_sequence_entry(self):
if self.check_token(BlockEntryToken):
token = self.get_token()
if not self.check_token(BlockEntryToken,
KeyToken, ValueToken, BlockEndToken):
self.states.append(self.parse_indentless_sequence_entry)
return self.parse_block_node()
else:
self.state = self.parse_indentless_sequence_entry
return self.process_empty_scalar(token.end_mark)
token = self.peek_token()
event = SequenceEndEvent(token.start_mark, token.start_mark)
self.state = self.states.pop()
return event
# block_mapping ::= BLOCK-MAPPING_START
# ((KEY block_node_or_indentless_sequence?)?
# (VALUE block_node_or_indentless_sequence?)?)*
# BLOCK-END
def parse_block_mapping_first_key(self):
token = self.get_token()
self.marks.append(token.start_mark)
return self.parse_block_mapping_key()
def parse_block_mapping_key(self):
if self.check_token(KeyToken):
token = self.get_token()
if not self.check_token(KeyToken, ValueToken, BlockEndToken):
self.states.append(self.parse_block_mapping_value)
return self.parse_block_node_or_indentless_sequence()
else:
self.state = self.parse_block_mapping_value
return self.process_empty_scalar(token.end_mark)
if not self.check_token(BlockEndToken):
token = self.peek_token()
raise ParserError("while parsing a block mapping", self.marks[-1],
"expected <block end>, but found %r" % token.id, token.start_mark)
token = self.get_token()
event = MappingEndEvent(token.start_mark, token.end_mark)
self.state = self.states.pop()
self.marks.pop()
return event
def parse_block_mapping_value(self):
if self.check_token(ValueToken):
token = self.get_token()
if not self.check_token(KeyToken, ValueToken, BlockEndToken):
self.states.append(self.parse_block_mapping_key)
return self.parse_block_node_or_indentless_sequence()
else:
self.state = self.parse_block_mapping_key
return self.process_empty_scalar(token.end_mark)
else:
self.state = self.parse_block_mapping_key
token = self.peek_token()
return self.process_empty_scalar(token.start_mark)
# flow_sequence ::= FLOW-SEQUENCE-START
# (flow_sequence_entry FLOW-ENTRY)*
# flow_sequence_entry?
# FLOW-SEQUENCE-END
# flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)?
#
# Note that while production rules for both flow_sequence_entry and
# flow_mapping_entry are equal, their interpretations are different.
# For `flow_sequence_entry`, the part `KEY flow_node? (VALUE flow_node?)?`
# generate an inline mapping (set syntax).
def parse_flow_sequence_first_entry(self):
token = self.get_token()
self.marks.append(token.start_mark)
return self.parse_flow_sequence_entry(first=True)
def parse_flow_sequence_entry(self, first=False):
if not self.check_token(FlowSequenceEndToken):
if not first:
if self.check_token(FlowEntryToken):
self.get_token()
else:
token = self.peek_token()
raise ParserError("while parsing a flow sequence", self.marks[-1],
"expected ',' or ']', but got %r" % token.id, token.start_mark)
if self.check_token(KeyToken):
token = self.peek_token()
event = MappingStartEvent(None, None, True,
token.start_mark, token.end_mark,
flow_style=True)
self.state = self.parse_flow_sequence_entry_mapping_key
return event
elif not self.check_token(FlowSequenceEndToken):
self.states.append(self.parse_flow_sequence_entry)
return self.parse_flow_node()
token = self.get_token()
event = SequenceEndEvent(token.start_mark, token.end_mark)
self.state = self.states.pop()
self.marks.pop()
return event
def parse_flow_sequence_entry_mapping_key(self):
token = self.get_token()
if not self.check_token(ValueToken,
FlowEntryToken, FlowSequenceEndToken):
self.states.append(self.parse_flow_sequence_entry_mapping_value)
return self.parse_flow_node()
else:
self.state = self.parse_flow_sequence_entry_mapping_value
return self.process_empty_scalar(token.end_mark)
def parse_flow_sequence_entry_mapping_value(self):
if self.check_token(ValueToken):
token = self.get_token()
if not self.check_token(FlowEntryToken, FlowSequenceEndToken):
self.states.append(self.parse_flow_sequence_entry_mapping_end)
return self.parse_flow_node()
else:
self.state = self.parse_flow_sequence_entry_mapping_end
return self.process_empty_scalar(token.end_mark)
else:
self.state = self.parse_flow_sequence_entry_mapping_end
token = self.peek_token()
return self.process_empty_scalar(token.start_mark)
def parse_flow_sequence_entry_mapping_end(self):
self.state = self.parse_flow_sequence_entry
token = self.peek_token()
return MappingEndEvent(token.start_mark, token.start_mark)
# flow_mapping ::= FLOW-MAPPING-START
# (flow_mapping_entry FLOW-ENTRY)*
# flow_mapping_entry?
# FLOW-MAPPING-END
# flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)?
def parse_flow_mapping_first_key(self):
token = self.get_token()
self.marks.append(token.start_mark)
return self.parse_flow_mapping_key(first=True)
def parse_flow_mapping_key(self, first=False):
if not self.check_token(FlowMappingEndToken):
if not first:
if self.check_token(FlowEntryToken):
self.get_token()
else:
token = self.peek_token()
raise ParserError("while parsing a flow mapping", self.marks[-1],
"expected ',' or '}', but got %r" % token.id, token.start_mark)
if self.check_token(KeyToken):
token = self.get_token()
if not self.check_token(ValueToken,
FlowEntryToken, FlowMappingEndToken):
self.states.append(self.parse_flow_mapping_value)
return self.parse_flow_node()
else:
self.state = self.parse_flow_mapping_value
return self.process_empty_scalar(token.end_mark)
elif not self.check_token(FlowMappingEndToken):
self.states.append(self.parse_flow_mapping_empty_value)
return self.parse_flow_node()
token = self.get_token()
event = MappingEndEvent(token.start_mark, token.end_mark)
self.state = self.states.pop()
self.marks.pop()
return event
def parse_flow_mapping_value(self):
if self.check_token(ValueToken):
token = self.get_token()
if not self.check_token(FlowEntryToken, FlowMappingEndToken):
self.states.append(self.parse_flow_mapping_key)
return self.parse_flow_node()
else:
self.state = self.parse_flow_mapping_key
return self.process_empty_scalar(token.end_mark)
else:
self.state = self.parse_flow_mapping_key
token = self.peek_token()
return self.process_empty_scalar(token.start_mark)
def parse_flow_mapping_empty_value(self):
self.state = self.parse_flow_mapping_key
return self.process_empty_scalar(self.peek_token().start_mark)
def process_empty_scalar(self, mark):
return ScalarEvent(None, None, (True, False), u'', mark, mark)
-225
View File
@@ -1,225 +0,0 @@
# This module contains abstractions for the input stream. You don't have to
# looks further, there are no pretty code.
#
# We define two classes here.
#
# Mark(source, line, column)
# It's just a record and its only use is producing nice error messages.
# Parser does not use it for any other purposes.
#
# Reader(source, data)
# Reader determines the encoding of `data` and converts it to unicode.
# Reader provides the following methods and attributes:
# reader.peek(length=1) - return the next `length` characters
# reader.forward(length=1) - move the current position to `length` characters.
# reader.index - the number of the current character.
# reader.line, stream.column - the line and the column of the current character.
__all__ = ['Reader', 'ReaderError']
from error import YAMLError, Mark
import codecs, re
# Unfortunately, codec functions in Python 2.3 does not support the `finish`
# arguments, so we have to write our own wrappers.
try:
codecs.utf_8_decode('', 'strict', False)
from codecs import utf_8_decode, utf_16_le_decode, utf_16_be_decode
except TypeError:
def utf_16_le_decode(data, errors, finish=False):
if not finish and len(data) % 2 == 1:
data = data[:-1]
return codecs.utf_16_le_decode(data, errors)
def utf_16_be_decode(data, errors, finish=False):
if not finish and len(data) % 2 == 1:
data = data[:-1]
return codecs.utf_16_be_decode(data, errors)
def utf_8_decode(data, errors, finish=False):
if not finish:
# We are trying to remove a possible incomplete multibyte character
# from the suffix of the data.
# The first byte of a multi-byte sequence is in the range 0xc0 to 0xfd.
# All further bytes are in the range 0x80 to 0xbf.
# UTF-8 encoded UCS characters may be up to six bytes long.
count = 0
while count < 5 and count < len(data) \
and '\x80' <= data[-count-1] <= '\xBF':
count -= 1
if count < 5 and count < len(data) \
and '\xC0' <= data[-count-1] <= '\xFD':
data = data[:-count-1]
return codecs.utf_8_decode(data, errors)
class ReaderError(YAMLError):
def __init__(self, name, position, character, encoding, reason):
self.name = name
self.character = character
self.position = position
self.encoding = encoding
self.reason = reason
def __str__(self):
if isinstance(self.character, str):
return "'%s' codec can't decode byte #x%02x: %s\n" \
" in \"%s\", position %d" \
% (self.encoding, ord(self.character), self.reason,
self.name, self.position)
else:
return "unacceptable character #x%04x: %s\n" \
" in \"%s\", position %d" \
% (self.character, self.reason,
self.name, self.position)
class Reader(object):
# Reader:
# - determines the data encoding and converts it to unicode,
# - checks if characters are in allowed range,
# - adds '\0' to the end.
# Reader accepts
# - a `str` object,
# - a `unicode` object,
# - a file-like object with its `read` method returning `str`,
# - a file-like object with its `read` method returning `unicode`.
# Yeah, it's ugly and slow.
def __init__(self, stream):
self.name = None
self.stream = None
self.stream_pointer = 0
self.eof = True
self.buffer = u''
self.pointer = 0
self.raw_buffer = None
self.raw_decode = None
self.encoding = None
self.index = 0
self.line = 0
self.column = 0
if isinstance(stream, unicode):
self.name = "<unicode string>"
self.check_printable(stream)
self.buffer = stream+u'\0'
elif isinstance(stream, str):
self.name = "<string>"
self.raw_buffer = stream
self.determine_encoding()
else:
self.stream = stream
self.name = getattr(stream, 'name', "<file>")
self.eof = False
self.raw_buffer = ''
self.determine_encoding()
def peek(self, index=0):
try:
return self.buffer[self.pointer+index]
except IndexError:
self.update(index+1)
return self.buffer[self.pointer+index]
def prefix(self, length=1):
if self.pointer+length >= len(self.buffer):
self.update(length)
return self.buffer[self.pointer:self.pointer+length]
def forward(self, length=1):
if self.pointer+length+1 >= len(self.buffer):
self.update(length+1)
while length:
ch = self.buffer[self.pointer]
self.pointer += 1
self.index += 1
if ch in u'\n\x85\u2028\u2029' \
or (ch == u'\r' and self.buffer[self.pointer] != u'\n'):
self.line += 1
self.column = 0
elif ch != u'\uFEFF':
self.column += 1
length -= 1
def get_mark(self):
if self.stream is None:
return Mark(self.name, self.index, self.line, self.column,
self.buffer, self.pointer)
else:
return Mark(self.name, self.index, self.line, self.column,
None, None)
def determine_encoding(self):
while not self.eof and len(self.raw_buffer) < 2:
self.update_raw()
if not isinstance(self.raw_buffer, unicode):
if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
self.raw_decode = utf_16_le_decode
self.encoding = 'utf-16-le'
elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
self.raw_decode = utf_16_be_decode
self.encoding = 'utf-16-be'
else:
self.raw_decode = utf_8_decode
self.encoding = 'utf-8'
self.update(1)
NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]')
def check_printable(self, data):
match = self.NON_PRINTABLE.search(data)
if match:
character = match.group()
position = self.index+(len(self.buffer)-self.pointer)+match.start()
raise ReaderError(self.name, position, ord(character),
'unicode', "special characters are not allowed")
def update(self, length):
if self.raw_buffer is None:
return
self.buffer = self.buffer[self.pointer:]
self.pointer = 0
while len(self.buffer) < length:
if not self.eof:
self.update_raw()
if self.raw_decode is not None:
try:
data, converted = self.raw_decode(self.raw_buffer,
'strict', self.eof)
except UnicodeDecodeError, exc:
character = exc.object[exc.start]
if self.stream is not None:
position = self.stream_pointer-len(self.raw_buffer)+exc.start
else:
position = exc.start
raise ReaderError(self.name, position, character,
exc.encoding, exc.reason)
else:
data = self.raw_buffer
converted = len(data)
self.check_printable(data)
self.buffer += data
self.raw_buffer = self.raw_buffer[converted:]
if self.eof:
self.buffer += u'\0'
self.raw_buffer = None
break
def update_raw(self, size=1024):
data = self.stream.read(size)
if data:
self.raw_buffer += data
self.stream_pointer += len(data)
else:
self.eof = True
#try:
# import psyco
# psyco.bind(Reader)
#except ImportError:
# pass
-489
View File
@@ -1,489 +0,0 @@
__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer',
'RepresenterError']
from error import *
from nodes import *
import datetime
try:
set
except NameError:
from sets import Set as set
import sys, copy_reg, types
class RepresenterError(YAMLError):
pass
class BaseRepresenter(object):
yaml_representers = {}
yaml_multi_representers = {}
def __init__(self, default_style=None, default_flow_style=None):
self.default_style = default_style
self.default_flow_style = default_flow_style
self.represented_objects = {}
self.object_keeper = []
self.alias_key = None
def represent(self, data):
node = self.represent_data(data)
self.serialize(node)
self.represented_objects = {}
self.object_keeper = []
self.alias_key = None
def get_classobj_bases(self, cls):
bases = [cls]
for base in cls.__bases__:
bases.extend(self.get_classobj_bases(base))
return bases
def represent_data(self, data):
if self.ignore_aliases(data):
self.alias_key = None
else:
self.alias_key = id(data)
if self.alias_key is not None:
if self.alias_key in self.represented_objects:
node = self.represented_objects[self.alias_key]
#if node is None:
# raise RepresenterError("recursive objects are not allowed: %r" % data)
return node
#self.represented_objects[alias_key] = None
self.object_keeper.append(data)
data_types = type(data).__mro__
if type(data) is types.InstanceType:
data_types = self.get_classobj_bases(data.__class__)+list(data_types)
if data_types[0] in self.yaml_representers:
node = self.yaml_representers[data_types[0]](self, data)
else:
for data_type in data_types:
if data_type in self.yaml_multi_representers:
node = self.yaml_multi_representers[data_type](self, data)
break
else:
if None in self.yaml_multi_representers:
node = self.yaml_multi_representers[None](self, data)
elif None in self.yaml_representers:
node = self.yaml_representers[None](self, data)
else:
node = ScalarNode(None, unicode(data))
#if alias_key is not None:
# self.represented_objects[alias_key] = node
return node
def add_representer(cls, data_type, representer):
if not 'yaml_representers' in cls.__dict__:
cls.yaml_representers = cls.yaml_representers.copy()
cls.yaml_representers[data_type] = representer
add_representer = classmethod(add_representer)
def add_multi_representer(cls, data_type, representer):
if not 'yaml_multi_representers' in cls.__dict__:
cls.yaml_multi_representers = cls.yaml_multi_representers.copy()
cls.yaml_multi_representers[data_type] = representer
add_multi_representer = classmethod(add_multi_representer)
def represent_scalar(self, tag, value, style=None):
if style is None:
style = self.default_style
node = ScalarNode(tag, value, style=style)
if self.alias_key is not None:
self.represented_objects[self.alias_key] = node
return node
def represent_sequence(self, tag, sequence, flow_style=None):
value = []
node = SequenceNode(tag, value, flow_style=flow_style)
if self.alias_key is not None:
self.represented_objects[self.alias_key] = node
best_style = True
for item in sequence:
node_item = self.represent_data(item)
if not (isinstance(node_item, ScalarNode) and not node_item.style):
best_style = False
value.append(node_item)
if flow_style is None:
if self.default_flow_style is not None:
node.flow_style = self.default_flow_style
else:
node.flow_style = best_style
return node
def represent_mapping(self, tag, mapping, flow_style=None):
value = []
node = MappingNode(tag, value, flow_style=flow_style)
if self.alias_key is not None:
self.represented_objects[self.alias_key] = node
best_style = True
if hasattr(mapping, 'items'):
mapping = mapping.items()
mapping.sort()
for item_key, item_value in mapping:
node_key = self.represent_data(item_key)
node_value = self.represent_data(item_value)
if not (isinstance(node_key, ScalarNode) and not node_key.style):
best_style = False
if not (isinstance(node_value, ScalarNode) and not node_value.style):
best_style = False
value.append((node_key, node_value))
if flow_style is None:
if self.default_flow_style is not None:
node.flow_style = self.default_flow_style
else:
node.flow_style = best_style
return node
def ignore_aliases(self, data):
return False
class SafeRepresenter(BaseRepresenter):
def ignore_aliases(self, data):
if data in [None, ()]:
return True
if isinstance(data, (str, unicode, bool, int, float)):
return True
def represent_none(self, data):
return self.represent_scalar(u'tag:yaml.org,2002:null',
u'null')
def represent_str(self, data):
tag = None
style = None
try:
data = unicode(data, 'ascii')
tag = u'tag:yaml.org,2002:str'
except UnicodeDecodeError:
try:
data = unicode(data, 'utf-8')
tag = u'tag:yaml.org,2002:str'
except UnicodeDecodeError:
data = data.encode('base64')
tag = u'tag:yaml.org,2002:binary'
style = '|'
return self.represent_scalar(tag, data, style=style)
def represent_unicode(self, data):
return self.represent_scalar(u'tag:yaml.org,2002:str', data)
def represent_bool(self, data):
if data:
value = u'true'
else:
value = u'false'
return self.represent_scalar(u'tag:yaml.org,2002:bool', value)
def represent_int(self, data):
return self.represent_scalar(u'tag:yaml.org,2002:int', unicode(data))
def represent_long(self, data):
return self.represent_scalar(u'tag:yaml.org,2002:int', unicode(data))
inf_value = 1e300
while repr(inf_value) != repr(inf_value*inf_value):
inf_value *= inf_value
def represent_float(self, data):
if data != data or (data == 0.0 and data == 1.0):
value = u'.nan'
elif data == self.inf_value:
value = u'.inf'
elif data == -self.inf_value:
value = u'-.inf'
else:
value = unicode(repr(data)).lower()
# Note that in some cases `repr(data)` represents a float number
# without the decimal parts. For instance:
# >>> repr(1e17)
# '1e17'
# Unfortunately, this is not a valid float representation according
# to the definition of the `!!float` tag. We fix this by adding
# '.0' before the 'e' symbol.
if u'.' not in value and u'e' in value:
value = value.replace(u'e', u'.0e', 1)
return self.represent_scalar(u'tag:yaml.org,2002:float', value)
def represent_list(self, data):
#pairs = (len(data) > 0 and isinstance(data, list))
#if pairs:
# for item in data:
# if not isinstance(item, tuple) or len(item) != 2:
# pairs = False
# break
#if not pairs:
return self.represent_sequence(u'tag:yaml.org,2002:seq', data)
#value = []
#for item_key, item_value in data:
# value.append(self.represent_mapping(u'tag:yaml.org,2002:map',
# [(item_key, item_value)]))
#return SequenceNode(u'tag:yaml.org,2002:pairs', value)
def represent_dict(self, data):
return self.represent_mapping(u'tag:yaml.org,2002:map', data)
def represent_set(self, data):
value = {}
for key in data:
value[key] = None
return self.represent_mapping(u'tag:yaml.org,2002:set', value)
def represent_date(self, data):
value = unicode(data.isoformat())
return self.represent_scalar(u'tag:yaml.org,2002:timestamp', value)
def represent_datetime(self, data):
value = unicode(data.isoformat(' '))
return self.represent_scalar(u'tag:yaml.org,2002:timestamp', value)
def represent_yaml_object(self, tag, data, cls, flow_style=None):
if hasattr(data, '__getstate__'):
state = data.__getstate__()
else:
state = data.__dict__.copy()
return self.represent_mapping(tag, state, flow_style=flow_style)
def represent_undefined(self, data):
raise RepresenterError("cannot represent an object: %s" % data)
SafeRepresenter.add_representer(type(None),
SafeRepresenter.represent_none)
SafeRepresenter.add_representer(str,
SafeRepresenter.represent_str)
SafeRepresenter.add_representer(unicode,
SafeRepresenter.represent_unicode)
SafeRepresenter.add_representer(bool,
SafeRepresenter.represent_bool)
SafeRepresenter.add_representer(int,
SafeRepresenter.represent_int)
SafeRepresenter.add_representer(long,
SafeRepresenter.represent_long)
SafeRepresenter.add_representer(float,
SafeRepresenter.represent_float)
SafeRepresenter.add_representer(list,
SafeRepresenter.represent_list)
SafeRepresenter.add_representer(tuple,
SafeRepresenter.represent_list)
SafeRepresenter.add_representer(dict,
SafeRepresenter.represent_dict)
SafeRepresenter.add_representer(set,
SafeRepresenter.represent_set)
SafeRepresenter.add_representer(datetime.date,
SafeRepresenter.represent_date)
SafeRepresenter.add_representer(datetime.datetime,
SafeRepresenter.represent_datetime)
SafeRepresenter.add_representer(None,
SafeRepresenter.represent_undefined)
class Representer(SafeRepresenter):
def represent_str(self, data):
tag = None
style = None
try:
data = unicode(data, 'ascii')
tag = u'tag:yaml.org,2002:str'
except UnicodeDecodeError:
try:
data = unicode(data, 'utf-8')
tag = u'tag:yaml.org,2002:python/str'
except UnicodeDecodeError:
data = data.encode('base64')
tag = u'tag:yaml.org,2002:binary'
style = '|'
return self.represent_scalar(tag, data, style=style)
def represent_unicode(self, data):
tag = None
try:
data.encode('ascii')
tag = u'tag:yaml.org,2002:python/unicode'
except UnicodeEncodeError:
tag = u'tag:yaml.org,2002:str'
return self.represent_scalar(tag, data)
def represent_long(self, data):
tag = u'tag:yaml.org,2002:int'
if int(data) is not data:
tag = u'tag:yaml.org,2002:python/long'
return self.represent_scalar(tag, unicode(data))
def represent_complex(self, data):
if data.imag == 0.0:
data = u'%r' % data.real
elif data.real == 0.0:
data = u'%rj' % data.imag
elif data.imag > 0:
data = u'%r+%rj' % (data.real, data.imag)
else:
data = u'%r%rj' % (data.real, data.imag)
return self.represent_scalar(u'tag:yaml.org,2002:python/complex', data)
def represent_tuple(self, data):
return self.represent_sequence(u'tag:yaml.org,2002:python/tuple', data)
def represent_name(self, data):
name = u'%s.%s' % (data.__module__, data.__name__)
return self.represent_scalar(u'tag:yaml.org,2002:python/name:'+name, u'')
def represent_module(self, data):
return self.represent_scalar(
u'tag:yaml.org,2002:python/module:'+data.__name__, u'')
def represent_instance(self, data):
# For instances of classic classes, we use __getinitargs__ and
# __getstate__ to serialize the data.
# If data.__getinitargs__ exists, the object must be reconstructed by
# calling cls(**args), where args is a tuple returned by
# __getinitargs__. Otherwise, the cls.__init__ method should never be
# called and the class instance is created by instantiating a trivial
# class and assigning to the instance's __class__ variable.
# If data.__getstate__ exists, it returns the state of the object.
# Otherwise, the state of the object is data.__dict__.
# We produce either a !!python/object or !!python/object/new node.
# If data.__getinitargs__ does not exist and state is a dictionary, we
# produce a !!python/object node . Otherwise we produce a
# !!python/object/new node.
cls = data.__class__
class_name = u'%s.%s' % (cls.__module__, cls.__name__)
args = None
state = None
if hasattr(data, '__getinitargs__'):
args = list(data.__getinitargs__())
if hasattr(data, '__getstate__'):
state = data.__getstate__()
else:
state = data.__dict__
if args is None and isinstance(state, dict):
return self.represent_mapping(
u'tag:yaml.org,2002:python/object:'+class_name, state)
if isinstance(state, dict) and not state:
return self.represent_sequence(
u'tag:yaml.org,2002:python/object/new:'+class_name, args)
value = {}
if args:
value['args'] = args
value['state'] = state
return self.represent_mapping(
u'tag:yaml.org,2002:python/object/new:'+class_name, value)
def represent_object(self, data):
# We use __reduce__ API to save the data. data.__reduce__ returns
# a tuple of length 2-5:
# (function, args, state, listitems, dictitems)
# For reconstructing, we calls function(*args), then set its state,
# listitems, and dictitems if they are not None.
# A special case is when function.__name__ == '__newobj__'. In this
# case we create the object with args[0].__new__(*args).
# Another special case is when __reduce__ returns a string - we don't
# support it.
# We produce a !!python/object, !!python/object/new or
# !!python/object/apply node.
cls = type(data)
if cls in copy_reg.dispatch_table:
reduce = copy_reg.dispatch_table[cls](data)
elif hasattr(data, '__reduce_ex__'):
reduce = data.__reduce_ex__(2)
elif hasattr(data, '__reduce__'):
reduce = data.__reduce__()
else:
raise RepresenterError("cannot represent object: %r" % data)
reduce = (list(reduce)+[None]*5)[:5]
function, args, state, listitems, dictitems = reduce
args = list(args)
if state is None:
state = {}
if listitems is not None:
listitems = list(listitems)
if dictitems is not None:
dictitems = dict(dictitems)
if function.__name__ == '__newobj__':
function = args[0]
args = args[1:]
tag = u'tag:yaml.org,2002:python/object/new:'
newobj = True
else:
tag = u'tag:yaml.org,2002:python/object/apply:'
newobj = False
function_name = u'%s.%s' % (function.__module__, function.__name__)
if not args and not listitems and not dictitems \
and isinstance(state, dict) and newobj:
return self.represent_mapping(
u'tag:yaml.org,2002:python/object:'+function_name, state)
if not listitems and not dictitems \
and isinstance(state, dict) and not state:
return self.represent_sequence(tag+function_name, args)
value = {}
if args:
value['args'] = args
if state or not isinstance(state, dict):
value['state'] = state
if listitems:
value['listitems'] = listitems
if dictitems:
value['dictitems'] = dictitems
return self.represent_mapping(tag+function_name, value)
Representer.add_representer(str,
Representer.represent_str)
Representer.add_representer(unicode,
Representer.represent_unicode)
Representer.add_representer(long,
Representer.represent_long)
Representer.add_representer(complex,
Representer.represent_complex)
Representer.add_representer(tuple,
Representer.represent_tuple)
Representer.add_representer(type,
Representer.represent_name)
Representer.add_representer(types.ClassType,
Representer.represent_name)
Representer.add_representer(types.FunctionType,
Representer.represent_name)
Representer.add_representer(types.BuiltinFunctionType,
Representer.represent_name)
Representer.add_representer(types.ModuleType,
Representer.represent_module)
Representer.add_multi_representer(types.InstanceType,
Representer.represent_instance)
Representer.add_multi_representer(object,
Representer.represent_object)
-224
View File
@@ -1,224 +0,0 @@
__all__ = ['BaseResolver', 'Resolver']
from error import *
from nodes import *
import re
class ResolverError(YAMLError):
pass
class BaseResolver(object):
DEFAULT_SCALAR_TAG = u'tag:yaml.org,2002:str'
DEFAULT_SEQUENCE_TAG = u'tag:yaml.org,2002:seq'
DEFAULT_MAPPING_TAG = u'tag:yaml.org,2002:map'
yaml_implicit_resolvers = {}
yaml_path_resolvers = {}
def __init__(self):
self.resolver_exact_paths = []
self.resolver_prefix_paths = []
def add_implicit_resolver(cls, tag, regexp, first):
if not 'yaml_implicit_resolvers' in cls.__dict__:
cls.yaml_implicit_resolvers = cls.yaml_implicit_resolvers.copy()
if first is None:
first = [None]
for ch in first:
cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp))
add_implicit_resolver = classmethod(add_implicit_resolver)
def add_path_resolver(cls, tag, path, kind=None):
# Note: `add_path_resolver` is experimental. The API could be changed.
# `new_path` is a pattern that is matched against the path from the
# root to the node that is being considered. `node_path` elements are
# tuples `(node_check, index_check)`. `node_check` is a node class:
# `ScalarNode`, `SequenceNode`, `MappingNode` or `None`. `None`
# matches any kind of a node. `index_check` could be `None`, a boolean
# value, a string value, or a number. `None` and `False` match against
# any _value_ of sequence and mapping nodes. `True` matches against
# any _key_ of a mapping node. A string `index_check` matches against
# a mapping value that corresponds to a scalar key which content is
# equal to the `index_check` value. An integer `index_check` matches
# against a sequence value with the index equal to `index_check`.
if not 'yaml_path_resolvers' in cls.__dict__:
cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy()
new_path = []
for element in path:
if isinstance(element, (list, tuple)):
if len(element) == 2:
node_check, index_check = element
elif len(element) == 1:
node_check = element[0]
index_check = True
else:
raise ResolverError("Invalid path element: %s" % element)
else:
node_check = None
index_check = element
if node_check is str:
node_check = ScalarNode
elif node_check is list:
node_check = SequenceNode
elif node_check is dict:
node_check = MappingNode
elif node_check not in [ScalarNode, SequenceNode, MappingNode] \
and not isinstance(node_check, basestring) \
and node_check is not None:
raise ResolverError("Invalid node checker: %s" % node_check)
if not isinstance(index_check, (basestring, int)) \
and index_check is not None:
raise ResolverError("Invalid index checker: %s" % index_check)
new_path.append((node_check, index_check))
if kind is str:
kind = ScalarNode
elif kind is list:
kind = SequenceNode
elif kind is dict:
kind = MappingNode
elif kind not in [ScalarNode, SequenceNode, MappingNode] \
and kind is not None:
raise ResolverError("Invalid node kind: %s" % kind)
cls.yaml_path_resolvers[tuple(new_path), kind] = tag
add_path_resolver = classmethod(add_path_resolver)
def descend_resolver(self, current_node, current_index):
if not self.yaml_path_resolvers:
return
exact_paths = {}
prefix_paths = []
if current_node:
depth = len(self.resolver_prefix_paths)
for path, kind in self.resolver_prefix_paths[-1]:
if self.check_resolver_prefix(depth, path, kind,
current_node, current_index):
if len(path) > depth:
prefix_paths.append((path, kind))
else:
exact_paths[kind] = self.yaml_path_resolvers[path, kind]
else:
for path, kind in self.yaml_path_resolvers:
if not path:
exact_paths[kind] = self.yaml_path_resolvers[path, kind]
else:
prefix_paths.append((path, kind))
self.resolver_exact_paths.append(exact_paths)
self.resolver_prefix_paths.append(prefix_paths)
def ascend_resolver(self):
if not self.yaml_path_resolvers:
return
self.resolver_exact_paths.pop()
self.resolver_prefix_paths.pop()
def check_resolver_prefix(self, depth, path, kind,
current_node, current_index):
node_check, index_check = path[depth-1]
if isinstance(node_check, basestring):
if current_node.tag != node_check:
return
elif node_check is not None:
if not isinstance(current_node, node_check):
return
if index_check is True and current_index is not None:
return
if (index_check is False or index_check is None) \
and current_index is None:
return
if isinstance(index_check, basestring):
if not (isinstance(current_index, ScalarNode)
and index_check == current_index.value):
return
elif isinstance(index_check, int) and not isinstance(index_check, bool):
if index_check != current_index:
return
return True
def resolve(self, kind, value, implicit):
if kind is ScalarNode and implicit[0]:
if value == u'':
resolvers = self.yaml_implicit_resolvers.get(u'', [])
else:
resolvers = self.yaml_implicit_resolvers.get(value[0], [])
resolvers += self.yaml_implicit_resolvers.get(None, [])
for tag, regexp in resolvers:
if regexp.match(value):
return tag
implicit = implicit[1]
if self.yaml_path_resolvers:
exact_paths = self.resolver_exact_paths[-1]
if kind in exact_paths:
return exact_paths[kind]
if None in exact_paths:
return exact_paths[None]
if kind is ScalarNode:
return self.DEFAULT_SCALAR_TAG
elif kind is SequenceNode:
return self.DEFAULT_SEQUENCE_TAG
elif kind is MappingNode:
return self.DEFAULT_MAPPING_TAG
class Resolver(BaseResolver):
pass
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:bool',
re.compile(ur'''^(?:yes|Yes|YES|no|No|NO
|true|True|TRUE|false|False|FALSE
|on|On|ON|off|Off|OFF)$''', re.X),
list(u'yYnNtTfFoO'))
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:float',
re.compile(ur'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)?
|\.[0-9_]+(?:[eE][-+][0-9]+)?
|[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]*
|[-+]?\.(?:inf|Inf|INF)
|\.(?:nan|NaN|NAN))$''', re.X),
list(u'-+0123456789.'))
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:int',
re.compile(ur'''^(?:[-+]?0b[0-1_]+
|[-+]?0[0-7_]+
|[-+]?(?:0|[1-9][0-9_]*)
|[-+]?0x[0-9a-fA-F_]+
|[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X),
list(u'-+0123456789'))
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:merge',
re.compile(ur'^(?:<<)$'),
[u'<'])
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:null',
re.compile(ur'''^(?: ~
|null|Null|NULL
| )$''', re.X),
[u'~', u'n', u'N', u''])
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:timestamp',
re.compile(ur'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]
|[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]?
(?:[Tt]|[ \t]+)[0-9][0-9]?
:[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)?
(?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X),
list(u'0123456789'))
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:value',
re.compile(ur'^(?:=)$'),
[u'='])
# The following resolver is only for documentation purposes. It cannot work
# because plain scalars cannot start with '!', '&', or '*'.
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:yaml',
re.compile(ur'^(?:!|&|\*)$'),
list(u'!&*'))
File diff suppressed because it is too large Load Diff
-111
View File
@@ -1,111 +0,0 @@
__all__ = ['Serializer', 'SerializerError']
from error import YAMLError
from events import *
from nodes import *
class SerializerError(YAMLError):
pass
class Serializer(object):
ANCHOR_TEMPLATE = u'id%03d'
def __init__(self, encoding=None,
explicit_start=None, explicit_end=None, version=None, tags=None):
self.use_encoding = encoding
self.use_explicit_start = explicit_start
self.use_explicit_end = explicit_end
self.use_version = version
self.use_tags = tags
self.serialized_nodes = {}
self.anchors = {}
self.last_anchor_id = 0
self.closed = None
def open(self):
if self.closed is None:
self.emit(StreamStartEvent(encoding=self.use_encoding))
self.closed = False
elif self.closed:
raise SerializerError("serializer is closed")
else:
raise SerializerError("serializer is already opened")
def close(self):
if self.closed is None:
raise SerializerError("serializer is not opened")
elif not self.closed:
self.emit(StreamEndEvent())
self.closed = True
#def __del__(self):
# self.close()
def serialize(self, node):
if self.closed is None:
raise SerializerError("serializer is not opened")
elif self.closed:
raise SerializerError("serializer is closed")
self.emit(DocumentStartEvent(explicit=self.use_explicit_start,
version=self.use_version, tags=self.use_tags))
self.anchor_node(node)
self.serialize_node(node, None, None)
self.emit(DocumentEndEvent(explicit=self.use_explicit_end))
self.serialized_nodes = {}
self.anchors = {}
self.last_anchor_id = 0
def anchor_node(self, node):
if node in self.anchors:
if self.anchors[node] is None:
self.anchors[node] = self.generate_anchor(node)
else:
self.anchors[node] = None
if isinstance(node, SequenceNode):
for item in node.value:
self.anchor_node(item)
elif isinstance(node, MappingNode):
for key, value in node.value:
self.anchor_node(key)
self.anchor_node(value)
def generate_anchor(self, node):
self.last_anchor_id += 1
return self.ANCHOR_TEMPLATE % self.last_anchor_id
def serialize_node(self, node, parent, index):
alias = self.anchors[node]
if node in self.serialized_nodes:
self.emit(AliasEvent(alias))
else:
self.serialized_nodes[node] = True
self.descend_resolver(parent, index)
if isinstance(node, ScalarNode):
detected_tag = self.resolve(ScalarNode, node.value, (True, False))
default_tag = self.resolve(ScalarNode, node.value, (False, True))
implicit = (node.tag == detected_tag), (node.tag == default_tag)
self.emit(ScalarEvent(alias, node.tag, implicit, node.value,
style=node.style))
elif isinstance(node, SequenceNode):
implicit = (node.tag
== self.resolve(SequenceNode, node.value, True))
self.emit(SequenceStartEvent(alias, node.tag, implicit,
flow_style=node.flow_style))
index = 0
for item in node.value:
self.serialize_node(item, node, index)
index += 1
self.emit(SequenceEndEvent())
elif isinstance(node, MappingNode):
implicit = (node.tag
== self.resolve(MappingNode, node.value, True))
self.emit(MappingStartEvent(alias, node.tag, implicit,
flow_style=node.flow_style))
for key, value in node.value:
self.serialize_node(key, node, None)
self.serialize_node(value, node, key)
self.emit(MappingEndEvent())
self.ascend_resolver()
-104
View File
@@ -1,104 +0,0 @@
class Token(object):
def __init__(self, start_mark, end_mark):
self.start_mark = start_mark
self.end_mark = end_mark
def __repr__(self):
attributes = [key for key in self.__dict__
if not key.endswith('_mark')]
attributes.sort()
arguments = ', '.join(['%s=%r' % (key, getattr(self, key))
for key in attributes])
return '%s(%s)' % (self.__class__.__name__, arguments)
#class BOMToken(Token):
# id = '<byte order mark>'
class DirectiveToken(Token):
id = '<directive>'
def __init__(self, name, value, start_mark, end_mark):
self.name = name
self.value = value
self.start_mark = start_mark
self.end_mark = end_mark
class DocumentStartToken(Token):
id = '<document start>'
class DocumentEndToken(Token):
id = '<document end>'
class StreamStartToken(Token):
id = '<stream start>'
def __init__(self, start_mark=None, end_mark=None,
encoding=None):
self.start_mark = start_mark
self.end_mark = end_mark
self.encoding = encoding
class StreamEndToken(Token):
id = '<stream end>'
class BlockSequenceStartToken(Token):
id = '<block sequence start>'
class BlockMappingStartToken(Token):
id = '<block mapping start>'
class BlockEndToken(Token):
id = '<block end>'
class FlowSequenceStartToken(Token):
id = '['
class FlowMappingStartToken(Token):
id = '{'
class FlowSequenceEndToken(Token):
id = ']'
class FlowMappingEndToken(Token):
id = '}'
class KeyToken(Token):
id = '?'
class ValueToken(Token):
id = ':'
class BlockEntryToken(Token):
id = '-'
class FlowEntryToken(Token):
id = ','
class AliasToken(Token):
id = '<alias>'
def __init__(self, value, start_mark, end_mark):
self.value = value
self.start_mark = start_mark
self.end_mark = end_mark
class AnchorToken(Token):
id = '<anchor>'
def __init__(self, value, start_mark, end_mark):
self.value = value
self.start_mark = start_mark
self.end_mark = end_mark
class TagToken(Token):
id = '<tag>'
def __init__(self, value, start_mark, end_mark):
self.value = value
self.start_mark = start_mark
self.end_mark = end_mark
class ScalarToken(Token):
id = '<scalar>'
def __init__(self, value, plain, start_mark, end_mark, style=None):
self.value = value
self.plain = plain
self.start_mark = start_mark
self.end_mark = end_mark
self.style = style