summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKenneth Reitz <me@kennethreitz.com>2010-09-13 16:06:14 -0400
committerKenneth Reitz <me@kennethreitz.com>2010-09-13 16:06:14 -0400
commit5b42824871b357bcd6531845b2bb8ac5a4436572 (patch)
treef1a5b43181791e6c597bfa99879f0000cefe68ba
parent89209b6bd3041c946033570af3aa5087042bff87 (diff)
downloadtablib-5b42824871b357bcd6531845b2bb8ac5a4436572.tar.gz
Removed vendorized packages.
-rw-r--r--tablib/packages/__init__.py1
-rw-r--r--tablib/packages/opster.py612
-rw-r--r--tablib/packages/simplejson/__init__.py437
-rw-r--r--tablib/packages/simplejson/_speedups.c2561
-rw-r--r--tablib/packages/simplejson/decoder.py421
-rw-r--r--tablib/packages/simplejson/encoder.py501
-rw-r--r--tablib/packages/simplejson/ordered_dict.py119
-rw-r--r--tablib/packages/simplejson/scanner.py77
-rw-r--r--tablib/packages/simplejson/tests/__init__.py63
-rw-r--r--tablib/packages/simplejson/tests/test_check_circular.py30
-rw-r--r--tablib/packages/simplejson/tests/test_decimal.py33
-rw-r--r--tablib/packages/simplejson/tests/test_decode.py73
-rw-r--r--tablib/packages/simplejson/tests/test_default.py9
-rw-r--r--tablib/packages/simplejson/tests/test_dump.py27
-rw-r--r--tablib/packages/simplejson/tests/test_encode_basestring_ascii.py41
-rw-r--r--tablib/packages/simplejson/tests/test_encode_for_html.py32
-rw-r--r--tablib/packages/simplejson/tests/test_fail.py91
-rw-r--r--tablib/packages/simplejson/tests/test_float.py19
-rw-r--r--tablib/packages/simplejson/tests/test_indent.py53
-rw-r--r--tablib/packages/simplejson/tests/test_pass1.py76
-rw-r--r--tablib/packages/simplejson/tests/test_pass2.py14
-rw-r--r--tablib/packages/simplejson/tests/test_pass3.py20
-rw-r--r--tablib/packages/simplejson/tests/test_recursion.py67
-rw-r--r--tablib/packages/simplejson/tests/test_scanstring.py117
-rw-r--r--tablib/packages/simplejson/tests/test_separators.py42
-rw-r--r--tablib/packages/simplejson/tests/test_speedups.py21
-rw-r--r--tablib/packages/simplejson/tests/test_unicode.py99
-rw-r--r--tablib/packages/simplejson/tool.py39
-rw-r--r--tablib/packages/yaml/__init__.py288
-rw-r--r--tablib/packages/yaml/composer.py139
-rw-r--r--tablib/packages/yaml/constructor.py684
-rw-r--r--tablib/packages/yaml/cyaml.py85
-rw-r--r--tablib/packages/yaml/dumper.py62
-rw-r--r--tablib/packages/yaml/emitter.py1135
-rw-r--r--tablib/packages/yaml/error.py75
-rw-r--r--tablib/packages/yaml/events.py86
-rw-r--r--tablib/packages/yaml/loader.py40
-rw-r--r--tablib/packages/yaml/nodes.py49
-rw-r--r--tablib/packages/yaml/parser.py584
-rw-r--r--tablib/packages/yaml/reader.py225
-rw-r--r--tablib/packages/yaml/representer.py489
-rw-r--r--tablib/packages/yaml/resolver.py224
-rw-r--r--tablib/packages/yaml/scanner.py1457
-rw-r--r--tablib/packages/yaml/serializer.py111
-rw-r--r--tablib/packages/yaml/tokens.py104
45 files changed, 0 insertions, 11532 deletions
diff --git a/tablib/packages/__init__.py b/tablib/packages/__init__.py
deleted file mode 100644
index a38d74d..0000000
--- a/tablib/packages/__init__.py
+++ /dev/null
@@ -1 +0,0 @@
-all = ['simplejson', 'typecheck', 'xlwt', 'opster'] \ No newline at end of file
diff --git a/tablib/packages/opster.py b/tablib/packages/opster.py
deleted file mode 100644
index 5fe64be..0000000
--- a/tablib/packages/opster.py
+++ /dev/null
@@ -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'
diff --git a/tablib/packages/simplejson/__init__.py b/tablib/packages/simplejson/__init__.py
deleted file mode 100644
index dcfd541..0000000
--- a/tablib/packages/simplejson/__init__.py
+++ /dev/null
@@ -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,
- )
diff --git a/tablib/packages/simplejson/_speedups.c b/tablib/packages/simplejson/_speedups.c
deleted file mode 100644
index b06ba50..0000000
--- a/tablib/packages/simplejson/_speedups.c
+++ /dev/null
@@ -1,2561 +0,0 @@
-#include "Python.h"
-#include "structmember.h"
-#if PY_VERSION_HEX < 0x02070000 && !defined(PyOS_string_to_double)
-#define PyOS_string_to_double json_PyOS_string_to_double
-static double
-json_PyOS_string_to_double(const char *s, char **endptr, PyObject *overflow_exception);
-static double
-json_PyOS_string_to_double(const char *s, char **endptr, PyObject *overflow_exception) {
- double x;
- assert(endptr == NULL);
- assert(overflow_exception == NULL);
- PyFPE_START_PROTECT("json_PyOS_string_to_double", return -1.0;)
- x = PyOS_ascii_atof(s);
- PyFPE_END_PROTECT(x)
- return x;
-}
-#endif
-#if PY_VERSION_HEX < 0x02060000 && !defined(Py_TYPE)
-#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
-#endif
-#if PY_VERSION_HEX < 0x02050000 && !defined(PY_SSIZE_T_MIN)
-typedef int Py_ssize_t;
-#define PY_SSIZE_T_MAX INT_MAX
-#define PY_SSIZE_T_MIN INT_MIN
-#define PyInt_FromSsize_t PyInt_FromLong
-#define PyInt_AsSsize_t PyInt_AsLong
-#endif
-#ifndef Py_IS_FINITE
-#define Py_IS_FINITE(X) (!Py_IS_INFINITY(X) && !Py_IS_NAN(X))
-#endif
-
-#ifdef __GNUC__
-#define UNUSED __attribute__((__unused__))
-#else
-#define UNUSED
-#endif
-
-#define DEFAULT_ENCODING "utf-8"
-
-#define PyScanner_Check(op) PyObject_TypeCheck(op, &PyScannerType)
-#define PyScanner_CheckExact(op) (Py_TYPE(op) == &PyScannerType)
-#define PyEncoder_Check(op) PyObject_TypeCheck(op, &PyEncoderType)
-#define PyEncoder_CheckExact(op) (Py_TYPE(op) == &PyEncoderType)
-#define Decimal_Check(op) (PyObject_TypeCheck(op, DecimalTypePtr))
-
-static PyTypeObject PyScannerType;
-static PyTypeObject PyEncoderType;
-static PyTypeObject *DecimalTypePtr;
-
-typedef struct _PyScannerObject {
- PyObject_HEAD
- PyObject *encoding;
- PyObject *strict;
- PyObject *object_hook;
- PyObject *pairs_hook;
- PyObject *parse_float;
- PyObject *parse_int;
- PyObject *parse_constant;
- PyObject *memo;
-} PyScannerObject;
-
-static PyMemberDef scanner_members[] = {
- {"encoding", T_OBJECT, offsetof(PyScannerObject, encoding), READONLY, "encoding"},
- {"strict", T_OBJECT, offsetof(PyScannerObject, strict), READONLY, "strict"},
- {"object_hook", T_OBJECT, offsetof(PyScannerObject, object_hook), READONLY, "object_hook"},
- {"object_pairs_hook", T_OBJECT, offsetof(PyScannerObject, pairs_hook), READONLY, "object_pairs_hook"},
- {"parse_float", T_OBJECT, offsetof(PyScannerObject, parse_float), READONLY, "parse_float"},
- {"parse_int", T_OBJECT, offsetof(PyScannerObject, parse_int), READONLY, "parse_int"},
- {"parse_constant", T_OBJECT, offsetof(PyScannerObject, parse_constant), READONLY, "parse_constant"},
- {NULL}
-};
-
-typedef struct _PyEncoderObject {
- PyObject_HEAD
- PyObject *markers;
- PyObject *defaultfn;
- PyObject *encoder;
- PyObject *indent;
- PyObject *key_separator;
- PyObject *item_separator;
- PyObject *sort_keys;
- PyObject *skipkeys;
- PyObject *key_memo;
- int fast_encode;
- int allow_nan;
- int use_decimal;
-} PyEncoderObject;
-
-static PyMemberDef encoder_members[] = {
- {"markers", T_OBJECT, offsetof(PyEncoderObject, markers), READONLY, "markers"},
- {"default", T_OBJECT, offsetof(PyEncoderObject, defaultfn), READONLY, "default"},
- {"encoder", T_OBJECT, offsetof(PyEncoderObject, encoder), READONLY, "encoder"},
- {"indent", T_OBJECT, offsetof(PyEncoderObject, indent), READONLY, "indent"},
- {"key_separator", T_OBJECT, offsetof(PyEncoderObject, key_separator), READONLY, "key_separator"},
- {"item_separator", T_OBJECT, offsetof(PyEncoderObject, item_separator), READONLY, "item_separator"},
- {"sort_keys", T_OBJECT, offsetof(PyEncoderObject, sort_keys), READONLY, "sort_keys"},
- {"skipkeys", T_OBJECT, offsetof(PyEncoderObject, skipkeys), READONLY, "skipkeys"},
- {"key_memo", T_OBJECT, offsetof(PyEncoderObject, key_memo), READONLY, "key_memo"},
- {NULL}
-};
-
-static Py_ssize_t
-ascii_escape_char(Py_UNICODE c, char *output, Py_ssize_t chars);
-static PyObject *
-ascii_escape_unicode(PyObject *pystr);
-static PyObject *
-ascii_escape_str(PyObject *pystr);
-static PyObject *
-py_encode_basestring_ascii(PyObject* self UNUSED, PyObject *pystr);
-void init_speedups(void);
-static PyObject *
-scan_once_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr);
-static PyObject *
-scan_once_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr);
-static PyObject *
-_build_rval_index_tuple(PyObject *rval, Py_ssize_t idx);
-static PyObject *
-scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds);
-static int
-scanner_init(PyObject *self, PyObject *args, PyObject *kwds);
-static void
-scanner_dealloc(PyObject *self);
-static int
-scanner_clear(PyObject *self);
-static PyObject *
-encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds);
-static int
-encoder_init(PyObject *self, PyObject *args, PyObject *kwds);
-static void
-encoder_dealloc(PyObject *self);
-static int
-encoder_clear(PyObject *self);
-static int
-encoder_listencode_list(PyEncoderObject *s, PyObject *rval, PyObject *seq, Py_ssize_t indent_level);
-static int
-encoder_listencode_obj(PyEncoderObject *s, PyObject *rval, PyObject *obj, Py_ssize_t indent_level);
-static int
-encoder_listencode_dict(PyEncoderObject *s, PyObject *rval, PyObject *dct, Py_ssize_t indent_level);
-static PyObject *
-_encoded_const(PyObject *obj);
-static void
-raise_errmsg(char *msg, PyObject *s, Py_ssize_t end);
-static PyObject *
-encoder_encode_string(PyEncoderObject *s, PyObject *obj);
-static int
-_convertPyInt_AsSsize_t(PyObject *o, Py_ssize_t *size_ptr);
-static PyObject *
-_convertPyInt_FromSsize_t(Py_ssize_t *size_ptr);
-static PyObject *
-encoder_encode_float(PyEncoderObject *s, PyObject *obj);
-
-#define S_CHAR(c) (c >= ' ' && c <= '~' && c != '\\' && c != '"')
-#define IS_WHITESPACE(c) (((c) == ' ') || ((c) == '\t') || ((c) == '\n') || ((c) == '\r'))
-
-#define MIN_EXPANSION 6
-#ifdef Py_UNICODE_WIDE
-#define MAX_EXPANSION (2 * MIN_EXPANSION)
-#else
-#define MAX_EXPANSION MIN_EXPANSION
-#endif
-
-static int
-_convertPyInt_AsSsize_t(PyObject *o, Py_ssize_t *size_ptr)
-{
- /* PyObject to Py_ssize_t converter */
- *size_ptr = PyInt_AsSsize_t(o);
- if (*size_ptr == -1 && PyErr_Occurred())
- return 0;
- return 1;
-}
-
-static PyObject *
-_convertPyInt_FromSsize_t(Py_ssize_t *size_ptr)
-{
- /* Py_ssize_t to PyObject converter */
- return PyInt_FromSsize_t(*size_ptr);
-}
-
-static Py_ssize_t
-ascii_escape_char(Py_UNICODE c, char *output, Py_ssize_t chars)
-{
- /* Escape unicode code point c to ASCII escape sequences
- in char *output. output must have at least 12 bytes unused to
- accommodate an escaped surrogate pair "\uXXXX\uXXXX" */
- output[chars++] = '\\';
- switch (c) {
- case '\\': output[chars++] = (char)c; break;
- case '"': output[chars++] = (char)c; break;
- case '\b': output[chars++] = 'b'; break;
- case '\f': output[chars++] = 'f'; break;
- case '\n': output[chars++] = 'n'; break;
- case '\r': output[chars++] = 'r'; break;
- case '\t': output[chars++] = 't'; break;
- default:
-#ifdef Py_UNICODE_WIDE
- if (c >= 0x10000) {
- /* UTF-16 surrogate pair */
- Py_UNICODE v = c - 0x10000;
- c = 0xd800 | ((v >> 10) & 0x3ff);
- output[chars++] = 'u';
- output[chars++] = "0123456789abcdef"[(c >> 12) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 8) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 4) & 0xf];
- output[chars++] = "0123456789abcdef"[(c ) & 0xf];
- c = 0xdc00 | (v & 0x3ff);
- output[chars++] = '\\';
- }
-#endif
- output[chars++] = 'u';
- output[chars++] = "0123456789abcdef"[(c >> 12) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 8) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 4) & 0xf];
- output[chars++] = "0123456789abcdef"[(c ) & 0xf];
- }
- return chars;
-}
-
-static PyObject *
-ascii_escape_unicode(PyObject *pystr)
-{
- /* Take a PyUnicode pystr and return a new ASCII-only escaped PyString */
- Py_ssize_t i;
- Py_ssize_t input_chars;
- Py_ssize_t output_size;
- Py_ssize_t max_output_size;
- Py_ssize_t chars;
- PyObject *rval;
- char *output;
- Py_UNICODE *input_unicode;
-
- input_chars = PyUnicode_GET_SIZE(pystr);
- input_unicode = PyUnicode_AS_UNICODE(pystr);
-
- /* One char input can be up to 6 chars output, estimate 4 of these */
- output_size = 2 + (MIN_EXPANSION * 4) + input_chars;
- max_output_size = 2 + (input_chars * MAX_EXPANSION);
- rval = PyString_FromStringAndSize(NULL, output_size);
- if (rval == NULL) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- chars = 0;
- output[chars++] = '"';
- for (i = 0; i < input_chars; i++) {
- Py_UNICODE c = input_unicode[i];
- if (S_CHAR(c)) {
- output[chars++] = (char)c;
- }
- else {
- chars = ascii_escape_char(c, output, chars);
- }
- if (output_size - chars < (1 + MAX_EXPANSION)) {
- /* There's more than four, so let's resize by a lot */
- Py_ssize_t new_output_size = output_size * 2;
- /* This is an upper bound */
- if (new_output_size > max_output_size) {
- new_output_size = max_output_size;
- }
- /* Make sure that the output size changed before resizing */
- if (new_output_size != output_size) {
- output_size = new_output_size;
- if (_PyString_Resize(&rval, output_size) == -1) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- }
- }
- }
- output[chars++] = '"';
- if (_PyString_Resize(&rval, chars) == -1) {
- return NULL;
- }
- return rval;
-}
-
-static PyObject *
-ascii_escape_str(PyObject *pystr)
-{
- /* Take a PyString pystr and return a new ASCII-only escaped PyString */
- Py_ssize_t i;
- Py_ssize_t input_chars;
- Py_ssize_t output_size;
- Py_ssize_t chars;
- PyObject *rval;
- char *output;
- char *input_str;
-
- input_chars = PyString_GET_SIZE(pystr);
- input_str = PyString_AS_STRING(pystr);
-
- /* Fast path for a string that's already ASCII */
- for (i = 0; i < input_chars; i++) {
- Py_UNICODE c = (Py_UNICODE)(unsigned char)input_str[i];
- if (!S_CHAR(c)) {
- /* If we have to escape something, scan the string for unicode */
- Py_ssize_t j;
- for (j = i; j < input_chars; j++) {
- c = (Py_UNICODE)(unsigned char)input_str[j];
- if (c > 0x7f) {
- /* We hit a non-ASCII character, bail to unicode mode */
- PyObject *uni;
- uni = PyUnicode_DecodeUTF8(input_str, input_chars, "strict");
- if (uni == NULL) {
- return NULL;
- }
- rval = ascii_escape_unicode(uni);
- Py_DECREF(uni);
- return rval;
- }
- }
- break;
- }
- }
-
- if (i == input_chars) {
- /* Input is already ASCII */
- output_size = 2 + input_chars;
- }
- else {
- /* One char input can be up to 6 chars output, estimate 4 of these */
- output_size = 2 + (MIN_EXPANSION * 4) + input_chars;
- }
- rval = PyString_FromStringAndSize(NULL, output_size);
- if (rval == NULL) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- output[0] = '"';
-
- /* We know that everything up to i is ASCII already */
- chars = i + 1;
- memcpy(&output[1], input_str, i);
-
- for (; i < input_chars; i++) {
- Py_UNICODE c = (Py_UNICODE)(unsigned char)input_str[i];
- if (S_CHAR(c)) {
- output[chars++] = (char)c;
- }
- else {
- chars = ascii_escape_char(c, output, chars);
- }
- /* An ASCII char can't possibly expand to a surrogate! */
- if (output_size - chars < (1 + MIN_EXPANSION)) {
- /* There's more than four, so let's resize by a lot */
- output_size *= 2;
- if (output_size > 2 + (input_chars * MIN_EXPANSION)) {
- output_size = 2 + (input_chars * MIN_EXPANSION);
- }
- if (_PyString_Resize(&rval, output_size) == -1) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- }
- }
- output[chars++] = '"';
- if (_PyString_Resize(&rval, chars) == -1) {
- return NULL;
- }
- return rval;
-}
-
-static void
-raise_errmsg(char *msg, PyObject *s, Py_ssize_t end)
-{
- /* Use the Python function simplejson.decoder.errmsg to raise a nice
- looking ValueError exception */
- static PyObject *JSONDecodeError = NULL;
- PyObject *exc;
- if (JSONDecodeError == NULL) {
- PyObject *decoder = PyImport_ImportModule("simplejson.decoder");
- if (decoder == NULL)
- return;
- JSONDecodeError = PyObject_GetAttrString(decoder, "JSONDecodeError");
- Py_DECREF(decoder);
- if (JSONDecodeError == NULL)
- return;
- }
- exc = PyObject_CallFunction(JSONDecodeError, "(zOO&)", msg, s, _convertPyInt_FromSsize_t, &end);
- if (exc) {
- PyErr_SetObject(JSONDecodeError, exc);
- Py_DECREF(exc);
- }
-}
-
-static PyObject *
-join_list_unicode(PyObject *lst)
-{
- /* return u''.join(lst) */
- static PyObject *joinfn = NULL;
- if (joinfn == NULL) {
- PyObject *ustr = PyUnicode_FromUnicode(NULL, 0);
- if (ustr == NULL)
- return NULL;
-
- joinfn = PyObject_GetAttrString(ustr, "join");
- Py_DECREF(ustr);
- if (joinfn == NULL)
- return NULL;
- }
- return PyObject_CallFunctionObjArgs(joinfn, lst, NULL);
-}
-
-static PyObject *
-join_list_string(PyObject *lst)
-{
- /* return ''.join(lst) */
- static PyObject *joinfn = NULL;
- if (joinfn == NULL) {
- PyObject *ustr = PyString_FromStringAndSize(NULL, 0);
- if (ustr == NULL)
- return NULL;
-
- joinfn = PyObject_GetAttrString(ustr, "join");
- Py_DECREF(ustr);
- if (joinfn == NULL)
- return NULL;
- }
- return PyObject_CallFunctionObjArgs(joinfn, lst, NULL);
-}
-
-static PyObject *
-_build_rval_index_tuple(PyObject *rval, Py_ssize_t idx) {
- /* return (rval, idx) tuple, stealing reference to rval */
- PyObject *tpl;
- PyObject *pyidx;
- /*
- steal a reference to rval, returns (rval, idx)
- */
- if (rval == NULL) {
- return NULL;
- }
- pyidx = PyInt_FromSsize_t(idx);
- if (pyidx == NULL) {
- Py_DECREF(rval);
- return NULL;
- }
- tpl = PyTuple_New(2);
- if (tpl == NULL) {
- Py_DECREF(pyidx);
- Py_DECREF(rval);
- return NULL;
- }
- PyTuple_SET_ITEM(tpl, 0, rval);
- PyTuple_SET_ITEM(tpl, 1, pyidx);
- return tpl;
-}
-
-#define APPEND_OLD_CHUNK \
- if (chunk != NULL) { \
- if (chunks == NULL) { \
- chunks = PyList_New(0); \
- if (chunks == NULL) { \
- goto bail; \
- } \
- } \
- if (PyList_Append(chunks, chunk)) { \
- goto bail; \
- } \
- Py_CLEAR(chunk); \
- }
-
-static PyObject *
-scanstring_str(PyObject *pystr, Py_ssize_t end, char *encoding, int strict, Py_ssize_t *next_end_ptr)
-{
- /* Read the JSON string from PyString pystr.
- end is the index of the first character after the quote.
- encoding is the encoding of pystr (must be an ASCII superset)
- if strict is zero then literal control characters are allowed
- *next_end_ptr is a return-by-reference index of the character
- after the end quote
-
- Return value is a new PyString (if ASCII-only) or PyUnicode
- */
- PyObject *rval;
- Py_ssize_t len = PyString_GET_SIZE(pystr);
- Py_ssize_t begin = end - 1;
- Py_ssize_t next = begin;
- int has_unicode = 0;
- char *buf = PyString_AS_STRING(pystr);
- PyObject *chunks = NULL;
- PyObject *chunk = NULL;
-
- if (end < 0 || len <= end) {
- PyErr_SetString(PyExc_ValueError, "end is out of bounds");
- goto bail;
- }
- while (1) {
- /* Find the end of the string or the next escape */
- Py_UNICODE c = 0;
- for (next = end; next < len; next++) {
- c = (unsigned char)buf[next];
- if (c == '"' || c == '\\') {
- break;
- }
- else if (strict && c <= 0x1f) {
- raise_errmsg("Invalid control character at", pystr, next);
- goto bail;
- }
- else if (c > 0x7f) {
- has_unicode = 1;
- }
- }
- if (!(c == '"' || c == '\\')) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- /* Pick up this chunk if it's not zero length */
- if (next != end) {
- PyObject *strchunk;
- APPEND_OLD_CHUNK
- strchunk = PyString_FromStringAndSize(&buf[end], next - end);
- if (strchunk == NULL) {
- goto bail;
- }
- if (has_unicode) {
- chunk = PyUnicode_FromEncodedObject(strchunk, encoding, NULL);
- Py_DECREF(strchunk);
- if (chunk == NULL) {
- goto bail;
- }
- }
- else {
- chunk = strchunk;
- }
- }
- next++;
- if (c == '"') {
- end = next;
- break;
- }
- if (next == len) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- c = buf[next];
- if (c != 'u') {
- /* Non-unicode backslash escapes */
- end = next + 1;
- switch (c) {
- case '"': break;
- case '\\': break;
- case '/': break;
- case 'b': c = '\b'; break;
- case 'f': c = '\f'; break;
- case 'n': c = '\n'; break;
- case 'r': c = '\r'; break;
- case 't': c = '\t'; break;
- default: c = 0;
- }
- if (c == 0) {
- raise_errmsg("Invalid \\escape", pystr, end - 2);
- goto bail;
- }
- }
- else {
- c = 0;
- next++;
- end = next + 4;
- if (end >= len) {
- raise_errmsg("Invalid \\uXXXX escape", pystr, next - 1);
- goto bail;
- }
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- Py_UNICODE digit = buf[next];
- c <<= 4;
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
-#ifdef Py_UNICODE_WIDE
- /* Surrogate pair */
- if ((c & 0xfc00) == 0xd800) {
- Py_UNICODE c2 = 0;
- if (end + 6 >= len) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- if (buf[next++] != '\\' || buf[next++] != 'u') {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- end += 6;
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- c2 <<= 4;
- Py_UNICODE digit = buf[next];
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c2 |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c2 |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c2 |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
- if ((c2 & 0xfc00) != 0xdc00) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00));
- }
- else if ((c & 0xfc00) == 0xdc00) {
- raise_errmsg("Unpaired low surrogate", pystr, end - 5);
- goto bail;
- }
-#endif
- }
- if (c > 0x7f) {
- has_unicode = 1;
- }
- APPEND_OLD_CHUNK
- if (has_unicode) {
- chunk = PyUnicode_FromUnicode(&c, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
- else {
- char c_char = Py_CHARMASK(c);
- chunk = PyString_FromStringAndSize(&c_char, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
- }
-
- if (chunks == NULL) {
- if (chunk != NULL)
- rval = chunk;
- else
- rval = PyString_FromStringAndSize("", 0);
- }
- else {
- APPEND_OLD_CHUNK
- rval = join_list_string(chunks);
- if (rval == NULL) {
- goto bail;
- }
- Py_CLEAR(chunks);
- }
-
- *next_end_ptr = end;
- return rval;
-bail:
- *next_end_ptr = -1;
- Py_XDECREF(chunk);
- Py_XDECREF(chunks);
- return NULL;
-}
-
-
-static PyObject *
-scanstring_unicode(PyObject *pystr, Py_ssize_t end, int strict, Py_ssize_t *next_end_ptr)
-{
- /* Read the JSON string from PyUnicode pystr.
- end is the index of the first character after the quote.
- if strict is zero then literal control characters are allowed
- *next_end_ptr is a return-by-reference index of the character
- after the end quote
-
- Return value is a new PyUnicode
- */
- PyObject *rval;
- Py_ssize_t len = PyUnicode_GET_SIZE(pystr);
- Py_ssize_t begin = end - 1;
- Py_ssize_t next = begin;
- const Py_UNICODE *buf = PyUnicode_AS_UNICODE(pystr);
- PyObject *chunks = NULL;
- PyObject *chunk = NULL;
-
- if (end < 0 || len <= end) {
- PyErr_SetString(PyExc_ValueError, "end is out of bounds");
- goto bail;
- }
- while (1) {
- /* Find the end of the string or the next escape */
- Py_UNICODE c = 0;
- for (next = end; next < len; next++) {
- c = buf[next];
- if (c == '"' || c == '\\') {
- break;
- }
- else if (strict && c <= 0x1f) {
- raise_errmsg("Invalid control character at", pystr, next);
- goto bail;
- }
- }
- if (!(c == '"' || c == '\\')) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- /* Pick up this chunk if it's not zero length */
- if (next != end) {
- APPEND_OLD_CHUNK
- chunk = PyUnicode_FromUnicode(&buf[end], next - end);
- if (chunk == NULL) {
- goto bail;
- }
- }
- next++;
- if (c == '"') {
- end = next;
- break;
- }
- if (next == len) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- c = buf[next];
- if (c != 'u') {
- /* Non-unicode backslash escapes */
- end = next + 1;
- switch (c) {
- case '"': break;
- case '\\': break;
- case '/': break;
- case 'b': c = '\b'; break;
- case 'f': c = '\f'; break;
- case 'n': c = '\n'; break;
- case 'r': c = '\r'; break;
- case 't': c = '\t'; break;
- default: c = 0;
- }
- if (c == 0) {
- raise_errmsg("Invalid \\escape", pystr, end - 2);
- goto bail;
- }
- }
- else {
- c = 0;
- next++;
- end = next + 4;
- if (end >= len) {
- raise_errmsg("Invalid \\uXXXX escape", pystr, next - 1);
- goto bail;
- }
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- Py_UNICODE digit = buf[next];
- c <<= 4;
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
-#ifdef Py_UNICODE_WIDE
- /* Surrogate pair */
- if ((c & 0xfc00) == 0xd800) {
- Py_UNICODE c2 = 0;
- if (end + 6 >= len) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- if (buf[next++] != '\\' || buf[next++] != 'u') {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- end += 6;
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- c2 <<= 4;
- Py_UNICODE digit = buf[next];
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c2 |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c2 |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c2 |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
- if ((c2 & 0xfc00) != 0xdc00) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00));
- }
- else if ((c & 0xfc00) == 0xdc00) {
- raise_errmsg("Unpaired low surrogate", pystr, end - 5);
- goto bail;
- }
-#endif
- }
- APPEND_OLD_CHUNK
- chunk = PyUnicode_FromUnicode(&c, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
-
- if (chunks == NULL) {
- if (chunk != NULL)
- rval = chunk;
- else
- rval = PyUnicode_FromUnicode(NULL, 0);
- }
- else {
- APPEND_OLD_CHUNK
- rval = join_list_unicode(chunks);
- if (rval == NULL) {
- goto bail;
- }
- Py_CLEAR(chunks);
- }
- *next_end_ptr = end;
- return rval;
-bail:
- *next_end_ptr = -1;
- Py_XDECREF(chunk);
- Py_XDECREF(chunks);
- return NULL;
-}
-
-PyDoc_STRVAR(pydoc_scanstring,
- "scanstring(basestring, end, encoding, strict=True) -> (str, end)\n"
- "\n"
- "Scan the string s for a JSON string. End is the index of the\n"
- "character in s after the quote that started the JSON string.\n"
- "Unescapes all valid JSON string escape sequences and raises ValueError\n"
- "on attempt to decode an invalid string. If strict is False then literal\n"
- "control characters are allowed in the string.\n"
- "\n"
- "Returns a tuple of the decoded string and the index of the character in s\n"
- "after the end quote."
-);
-
-static PyObject *
-py_scanstring(PyObject* self UNUSED, PyObject *args)
-{
- PyObject *pystr;
- PyObject *rval;
- Py_ssize_t end;
- Py_ssize_t next_end = -1;
- char *encoding = NULL;
- int strict = 1;
- if (!PyArg_ParseTuple(args, "OO&|zi:scanstring", &pystr, _convertPyInt_AsSsize_t, &end, &encoding, &strict)) {
- return NULL;
- }
- if (encoding == NULL) {
- encoding = DEFAULT_ENCODING;
- }
- if (PyString_Check(pystr)) {
- rval = scanstring_str(pystr, end, encoding, strict, &next_end);
- }
- else if (PyUnicode_Check(pystr)) {
- rval = scanstring_unicode(pystr, end, strict, &next_end);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
- return _build_rval_index_tuple(rval, next_end);
-}
-
-PyDoc_STRVAR(pydoc_encode_basestring_ascii,
- "encode_basestring_ascii(basestring) -> str\n"
- "\n"
- "Return an ASCII-only JSON representation of a Python string"
-);
-
-static PyObject *
-py_encode_basestring_ascii(PyObject* self UNUSED, PyObject *pystr)
-{
- /* Return an ASCII-only JSON representation of a Python string */
- /* METH_O */
- if (PyString_Check(pystr)) {
- return ascii_escape_str(pystr);
- }
- else if (PyUnicode_Check(pystr)) {
- return ascii_escape_unicode(pystr);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
-}
-
-static void
-scanner_dealloc(PyObject *self)
-{
- /* Deallocate scanner object */
- scanner_clear(self);
- Py_TYPE(self)->tp_free(self);
-}
-
-static int
-scanner_traverse(PyObject *self, visitproc visit, void *arg)
-{
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- Py_VISIT(s->encoding);
- Py_VISIT(s->strict);
- Py_VISIT(s->object_hook);
- Py_VISIT(s->pairs_hook);
- Py_VISIT(s->parse_float);
- Py_VISIT(s->parse_int);
- Py_VISIT(s->parse_constant);
- Py_VISIT(s->memo);
- return 0;
-}
-
-static int
-scanner_clear(PyObject *self)
-{
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- Py_CLEAR(s->encoding);
- Py_CLEAR(s->strict);
- Py_CLEAR(s->object_hook);
- Py_CLEAR(s->pairs_hook);
- Py_CLEAR(s->parse_float);
- Py_CLEAR(s->parse_int);
- Py_CLEAR(s->parse_constant);
- Py_CLEAR(s->memo);
- return 0;
-}
-
-static PyObject *
-_parse_object_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON object from PyString pystr.
- idx is the index of the first character after the opening curly brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing curly brace.
-
- Returns a new PyObject (usually a dict, but object_hook or
- object_pairs_hook can change that)
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- PyObject *rval = NULL;
- PyObject *pairs = NULL;
- PyObject *item;
- PyObject *key = NULL;
- PyObject *val = NULL;
- char *encoding = PyString_AS_STRING(s->encoding);
- int strict = PyObject_IsTrue(s->strict);
- int has_pairs_hook = (s->pairs_hook != Py_None);
- Py_ssize_t next_idx;
- if (has_pairs_hook) {
- pairs = PyList_New(0);
- if (pairs == NULL)
- return NULL;
- }
- else {
- rval = PyDict_New();
- if (rval == NULL)
- return NULL;
- }
-
- /* skip whitespace after { */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the object is non-empty */
- if (idx <= end_idx && str[idx] != '}') {
- while (idx <= end_idx) {
- PyObject *memokey;
-
- /* read key */
- if (str[idx] != '"') {
- raise_errmsg("Expecting property name", pystr, idx);
- goto bail;
- }
- key = scanstring_str(pystr, idx + 1, encoding, strict, &next_idx);
- if (key == NULL)
- goto bail;
- memokey = PyDict_GetItem(s->memo, key);
- if (memokey != NULL) {
- Py_INCREF(memokey);
- Py_DECREF(key);
- key = memokey;
- }
- else {
- if (PyDict_SetItem(s->memo, key, key) < 0)
- goto bail;
- }
- idx = next_idx;
-
- /* skip whitespace between key and : delimiter, read :, skip whitespace */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- if (idx > end_idx || str[idx] != ':') {
- raise_errmsg("Expecting : delimiter", pystr, idx);
- goto bail;
- }
- idx++;
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* read any JSON data type */
- val = scan_once_str(s, pystr, idx, &next_idx);
- if (val == NULL)
- goto bail;
-
- if (has_pairs_hook) {
- item = PyTuple_Pack(2, key, val);
- if (item == NULL)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- if (PyList_Append(pairs, item) == -1) {
- Py_DECREF(item);
- goto bail;
- }
- Py_DECREF(item);
- }
- else {
- if (PyDict_SetItem(rval, key, val) < 0)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- }
- idx = next_idx;
-
- /* skip whitespace before } or , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the object is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == '}') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , delimiter */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
- /* verify that idx < end_idx, str[idx] should be '}' */
- if (idx > end_idx || str[idx] != '}') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
-
- /* if pairs_hook is not None: rval = object_pairs_hook(pairs) */
- if (s->pairs_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->pairs_hook, pairs, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(pairs);
- *next_idx_ptr = idx + 1;
- return val;
- }
-
- /* if object_hook is not None: rval = object_hook(rval) */
- if (s->object_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->object_hook, rval, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(rval);
- rval = val;
- val = NULL;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(rval);
- Py_XDECREF(key);
- Py_XDECREF(val);
- Py_XDECREF(pairs);
- return NULL;
-}
-
-static PyObject *
-_parse_object_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON object from PyUnicode pystr.
- idx is the index of the first character after the opening curly brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing curly brace.
-
- Returns a new PyObject (usually a dict, but object_hook can change that)
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- PyObject *rval = NULL;
- PyObject *pairs = NULL;
- PyObject *item;
- PyObject *key = NULL;
- PyObject *val = NULL;
- int strict = PyObject_IsTrue(s->strict);
- int has_pairs_hook = (s->pairs_hook != Py_None);
- Py_ssize_t next_idx;
-
- if (has_pairs_hook) {
- pairs = PyList_New(0);
- if (pairs == NULL)
- return NULL;
- }
- else {
- rval = PyDict_New();
- if (rval == NULL)
- return NULL;
- }
-
- /* skip whitespace after { */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the object is non-empty */
- if (idx <= end_idx && str[idx] != '}') {
- while (idx <= end_idx) {
- PyObject *memokey;
-
- /* read key */
- if (str[idx] != '"') {
- raise_errmsg("Expecting property name", pystr, idx);
- goto bail;
- }
- key = scanstring_unicode(pystr, idx + 1, strict, &next_idx);
- if (key == NULL)
- goto bail;
- memokey = PyDict_GetItem(s->memo, key);
- if (memokey != NULL) {
- Py_INCREF(memokey);
- Py_DECREF(key);
- key = memokey;
- }
- else {
- if (PyDict_SetItem(s->memo, key, key) < 0)
- goto bail;
- }
- idx = next_idx;
-
- /* skip whitespace between key and : delimiter, read :, skip whitespace */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- if (idx > end_idx || str[idx] != ':') {
- raise_errmsg("Expecting : delimiter", pystr, idx);
- goto bail;
- }
- idx++;
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* read any JSON term */
- val = scan_once_unicode(s, pystr, idx, &next_idx);
- if (val == NULL)
- goto bail;
-
- if (has_pairs_hook) {
- item = PyTuple_Pack(2, key, val);
- if (item == NULL)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- if (PyList_Append(pairs, item) == -1) {
- Py_DECREF(item);
- goto bail;
- }
- Py_DECREF(item);
- }
- else {
- if (PyDict_SetItem(rval, key, val) < 0)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- }
- idx = next_idx;
-
- /* skip whitespace before } or , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the object is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == '}') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , delimiter */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be '}' */
- if (idx > end_idx || str[idx] != '}') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
-
- /* if pairs_hook is not None: rval = object_pairs_hook(pairs) */
- if (s->pairs_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->pairs_hook, pairs, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(pairs);
- *next_idx_ptr = idx + 1;
- return val;
- }
-
- /* if object_hook is not None: rval = object_hook(rval) */
- if (s->object_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->object_hook, rval, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(rval);
- rval = val;
- val = NULL;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(rval);
- Py_XDECREF(key);
- Py_XDECREF(val);
- Py_XDECREF(pairs);
- return NULL;
-}
-
-static PyObject *
-_parse_array_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON array from PyString pystr.
- idx is the index of the first character after the opening brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing brace.
-
- Returns a new PyList
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- PyObject *val = NULL;
- PyObject *rval = PyList_New(0);
- Py_ssize_t next_idx;
- if (rval == NULL)
- return NULL;
-
- /* skip whitespace after [ */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the array is non-empty */
- if (idx <= end_idx && str[idx] != ']') {
- while (idx <= end_idx) {
-
- /* read any JSON term and de-tuplefy the (rval, idx) */
- val = scan_once_str(s, pystr, idx, &next_idx);
- if (val == NULL) {
- if (PyErr_ExceptionMatches(PyExc_StopIteration)) {
- PyErr_Clear();
- raise_errmsg("Expecting object", pystr, idx);
- }
- goto bail;
- }
-
- if (PyList_Append(rval, val) == -1)
- goto bail;
-
- Py_CLEAR(val);
- idx = next_idx;
-
- /* skip whitespace between term and , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the array is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == ']') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be ']' */
- if (idx > end_idx || str[idx] != ']') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(val);
- Py_DECREF(rval);
- return NULL;
-}
-
-static PyObject *
-_parse_array_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON array from PyString pystr.
- idx is the index of the first character after the opening brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing brace.
-
- Returns a new PyList
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- PyObject *val = NULL;
- PyObject *rval = PyList_New(0);
- Py_ssize_t next_idx;
- if (rval == NULL)
- return NULL;
-
- /* skip whitespace after [ */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the array is non-empty */
- if (idx <= end_idx && str[idx] != ']') {
- while (idx <= end_idx) {
-
- /* read any JSON term */
- val = scan_once_unicode(s, pystr, idx, &next_idx);
- if (val == NULL) {
- if (PyErr_ExceptionMatches(PyExc_StopIteration)) {
- PyErr_Clear();
- raise_errmsg("Expecting object", pystr, idx);
- }
- goto bail;
- }
-
- if (PyList_Append(rval, val) == -1)
- goto bail;
-
- Py_CLEAR(val);
- idx = next_idx;
-
- /* skip whitespace between term and , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the array is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == ']') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be ']' */
- if (idx > end_idx || str[idx] != ']') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(val);
- Py_DECREF(rval);
- return NULL;
-}
-
-static PyObject *
-_parse_constant(PyScannerObject *s, char *constant, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON constant from PyString pystr.
- constant is the constant string that was found
- ("NaN", "Infinity", "-Infinity").
- idx is the index of the first character of the constant
- *next_idx_ptr is a return-by-reference index to the first character after
- the constant.
-
- Returns the result of parse_constant
- */
- PyObject *cstr;
- PyObject *rval;
- /* constant is "NaN", "Infinity", or "-Infinity" */
- cstr = PyString_InternFromString(constant);
- if (cstr == NULL)
- return NULL;
-
- /* rval = parse_constant(constant) */
- rval = PyObject_CallFunctionObjArgs(s->parse_constant, cstr, NULL);
- idx += PyString_GET_SIZE(cstr);
- Py_DECREF(cstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-_match_number_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON number from PyString pystr.
- idx is the index of the first character of the number
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of that number:
- PyInt, PyLong, or PyFloat.
- May return other types if parse_int or parse_float are set
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- Py_ssize_t idx = start;
- int is_float = 0;
- PyObject *rval;
- PyObject *numstr;
-
- /* read a sign if it's there, make sure it's not the end of the string */
- if (str[idx] == '-') {
- idx++;
- if (idx > end_idx) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- }
-
- /* read as many integer digits as we find as long as it doesn't start with 0 */
- if (str[idx] >= '1' && str[idx] <= '9') {
- idx++;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
- /* if it starts with 0 we only expect one integer digit */
- else if (str[idx] == '0') {
- idx++;
- }
- /* no integer digits, error */
- else {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
-
- /* if the next char is '.' followed by a digit then read all float digits */
- if (idx < end_idx && str[idx] == '.' && str[idx + 1] >= '0' && str[idx + 1] <= '9') {
- is_float = 1;
- idx += 2;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
-
- /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */
- if (idx < end_idx && (str[idx] == 'e' || str[idx] == 'E')) {
-
- /* save the index of the 'e' or 'E' just in case we need to backtrack */
- Py_ssize_t e_start = idx;
- idx++;
-
- /* read an exponent sign if present */
- if (idx < end_idx && (str[idx] == '-' || str[idx] == '+')) idx++;
-
- /* read all digits */
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
-
- /* if we got a digit, then parse as float. if not, backtrack */
- if (str[idx - 1] >= '0' && str[idx - 1] <= '9') {
- is_float = 1;
- }
- else {
- idx = e_start;
- }
- }
-
- /* copy the section we determined to be a number */
- numstr = PyString_FromStringAndSize(&str[start], idx - start);
- if (numstr == NULL)
- return NULL;
- if (is_float) {
- /* parse as a float using a fast path if available, otherwise call user defined method */
- if (s->parse_float != (PyObject *)&PyFloat_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_float, numstr, NULL);
- }
- else {
- /* rval = PyFloat_FromDouble(PyOS_ascii_atof(PyString_AS_STRING(numstr))); */
- double d = PyOS_string_to_double(PyString_AS_STRING(numstr),
- NULL, NULL);
- if (d == -1.0 && PyErr_Occurred())
- return NULL;
- rval = PyFloat_FromDouble(d);
- }
- }
- else {
- /* parse as an int using a fast path if available, otherwise call user defined method */
- if (s->parse_int != (PyObject *)&PyInt_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_int, numstr, NULL);
- }
- else {
- rval = PyInt_FromString(PyString_AS_STRING(numstr), NULL, 10);
- }
- }
- Py_DECREF(numstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-_match_number_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON number from PyUnicode pystr.
- idx is the index of the first character of the number
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of that number:
- PyInt, PyLong, or PyFloat.
- May return other types if parse_int or parse_float are set
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- Py_ssize_t idx = start;
- int is_float = 0;
- PyObject *rval;
- PyObject *numstr;
-
- /* read a sign if it's there, make sure it's not the end of the string */
- if (str[idx] == '-') {
- idx++;
- if (idx > end_idx) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- }
-
- /* read as many integer digits as we find as long as it doesn't start with 0 */
- if (str[idx] >= '1' && str[idx] <= '9') {
- idx++;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
- /* if it starts with 0 we only expect one integer digit */
- else if (str[idx] == '0') {
- idx++;
- }
- /* no integer digits, error */
- else {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
-
- /* if the next char is '.' followed by a digit then read all float digits */
- if (idx < end_idx && str[idx] == '.' && str[idx + 1] >= '0' && str[idx + 1] <= '9') {
- is_float = 1;
- idx += 2;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
-
- /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */
- if (idx < end_idx && (str[idx] == 'e' || str[idx] == 'E')) {
- Py_ssize_t e_start = idx;
- idx++;
-
- /* read an exponent sign if present */
- if (idx < end_idx && (str[idx] == '-' || str[idx] == '+')) idx++;
-
- /* read all digits */
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
-
- /* if we got a digit, then parse as float. if not, backtrack */
- if (str[idx - 1] >= '0' && str[idx - 1] <= '9') {
- is_float = 1;
- }
- else {
- idx = e_start;
- }
- }
-
- /* copy the section we determined to be a number */
- numstr = PyUnicode_FromUnicode(&str[start], idx - start);
- if (numstr == NULL)
- return NULL;
- if (is_float) {
- /* parse as a float using a fast path if available, otherwise call user defined method */
- if (s->parse_float != (PyObject *)&PyFloat_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_float, numstr, NULL);
- }
- else {
- rval = PyFloat_FromString(numstr, NULL);
- }
- }
- else {
- /* no fast path for unicode -> int, just call */
- rval = PyObject_CallFunctionObjArgs(s->parse_int, numstr, NULL);
- }
- Py_DECREF(numstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-scan_once_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr)
-{
- /* Read one JSON term (of any kind) from PyString pystr.
- idx is the index of the first character of the term
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of the term.
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t length = PyString_GET_SIZE(pystr);
- if (idx >= length) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- switch (str[idx]) {
- case '"':
- /* string */
- return scanstring_str(pystr, idx + 1,
- PyString_AS_STRING(s->encoding),
- PyObject_IsTrue(s->strict),
- next_idx_ptr);
- case '{':
- /* object */
- return _parse_object_str(s, pystr, idx + 1, next_idx_ptr);
- case '[':
- /* array */
- return _parse_array_str(s, pystr, idx + 1, next_idx_ptr);
- case 'n':
- /* null */
- if ((idx + 3 < length) && str[idx + 1] == 'u' && str[idx + 2] == 'l' && str[idx + 3] == 'l') {
- Py_INCREF(Py_None);
- *next_idx_ptr = idx + 4;
- return Py_None;
- }
- break;
- case 't':
- /* true */
- if ((idx + 3 < length) && str[idx + 1] == 'r' && str[idx + 2] == 'u' && str[idx + 3] == 'e') {
- Py_INCREF(Py_True);
- *next_idx_ptr = idx + 4;
- return Py_True;
- }
- break;
- case 'f':
- /* false */
- if ((idx + 4 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'l' && str[idx + 3] == 's' && str[idx + 4] == 'e') {
- Py_INCREF(Py_False);
- *next_idx_ptr = idx + 5;
- return Py_False;
- }
- break;
- case 'N':
- /* NaN */
- if ((idx + 2 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'N') {
- return _parse_constant(s, "NaN", idx, next_idx_ptr);
- }
- break;
- case 'I':
- /* Infinity */
- if ((idx + 7 < length) && str[idx + 1] == 'n' && str[idx + 2] == 'f' && str[idx + 3] == 'i' && str[idx + 4] == 'n' && str[idx + 5] == 'i' && str[idx + 6] == 't' && str[idx + 7] == 'y') {
- return _parse_constant(s, "Infinity", idx, next_idx_ptr);
- }
- break;
- case '-':
- /* -Infinity */
- if ((idx + 8 < length) && str[idx + 1] == 'I' && str[idx + 2] == 'n' && str[idx + 3] == 'f' && str[idx + 4] == 'i' && str[idx + 5] == 'n' && str[idx + 6] == 'i' && str[idx + 7] == 't' && str[idx + 8] == 'y') {
- return _parse_constant(s, "-Infinity", idx, next_idx_ptr);
- }
- break;
- }
- /* Didn't find a string, object, array, or named constant. Look for a number. */
- return _match_number_str(s, pystr, idx, next_idx_ptr);
-}
-
-static PyObject *
-scan_once_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr)
-{
- /* Read one JSON term (of any kind) from PyUnicode pystr.
- idx is the index of the first character of the term
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of the term.
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t length = PyUnicode_GET_SIZE(pystr);
- if (idx >= length) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- switch (str[idx]) {
- case '"':
- /* string */
- return scanstring_unicode(pystr, idx + 1,
- PyObject_IsTrue(s->strict),
- next_idx_ptr);
- case '{':
- /* object */
- return _parse_object_unicode(s, pystr, idx + 1, next_idx_ptr);
- case '[':
- /* array */
- return _parse_array_unicode(s, pystr, idx + 1, next_idx_ptr);
- case 'n':
- /* null */
- if ((idx + 3 < length) && str[idx + 1] == 'u' && str[idx + 2] == 'l' && str[idx + 3] == 'l') {
- Py_INCREF(Py_None);
- *next_idx_ptr = idx + 4;
- return Py_None;
- }
- break;
- case 't':
- /* true */
- if ((idx + 3 < length) && str[idx + 1] == 'r' && str[idx + 2] == 'u' && str[idx + 3] == 'e') {
- Py_INCREF(Py_True);
- *next_idx_ptr = idx + 4;
- return Py_True;
- }
- break;
- case 'f':
- /* false */
- if ((idx + 4 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'l' && str[idx + 3] == 's' && str[idx + 4] == 'e') {
- Py_INCREF(Py_False);
- *next_idx_ptr = idx + 5;
- return Py_False;
- }
- break;
- case 'N':
- /* NaN */
- if ((idx + 2 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'N') {
- return _parse_constant(s, "NaN", idx, next_idx_ptr);
- }
- break;
- case 'I':
- /* Infinity */
- if ((idx + 7 < length) && str[idx + 1] == 'n' && str[idx + 2] == 'f' && str[idx + 3] == 'i' && str[idx + 4] == 'n' && str[idx + 5] == 'i' && str[idx + 6] == 't' && str[idx + 7] == 'y') {
- return _parse_constant(s, "Infinity", idx, next_idx_ptr);
- }
- break;
- case '-':
- /* -Infinity */
- if ((idx + 8 < length) && str[idx + 1] == 'I' && str[idx + 2] == 'n' && str[idx + 3] == 'f' && str[idx + 4] == 'i' && str[idx + 5] == 'n' && str[idx + 6] == 'i' && str[idx + 7] == 't' && str[idx + 8] == 'y') {
- return _parse_constant(s, "-Infinity", idx, next_idx_ptr);
- }
- break;
- }
- /* Didn't find a string, object, array, or named constant. Look for a number. */
- return _match_number_unicode(s, pystr, idx, next_idx_ptr);
-}
-
-static PyObject *
-scanner_call(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Python callable interface to scan_once_{str,unicode} */
- PyObject *pystr;
- PyObject *rval;
- Py_ssize_t idx;
- Py_ssize_t next_idx = -1;
- static char *kwlist[] = {"string", "idx", NULL};
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&:scan_once", kwlist, &pystr, _convertPyInt_AsSsize_t, &idx))
- return NULL;
-
- if (PyString_Check(pystr)) {
- rval = scan_once_str(s, pystr, idx, &next_idx);
- }
- else if (PyUnicode_Check(pystr)) {
- rval = scan_once_unicode(s, pystr, idx, &next_idx);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
- PyDict_Clear(s->memo);
- return _build_rval_index_tuple(rval, next_idx);
-}
-
-static PyObject *
-scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
-{
- PyScannerObject *s;
- s = (PyScannerObject *)type->tp_alloc(type, 0);
- if (s != NULL) {
- s->encoding = NULL;
- s->strict = NULL;
- s->object_hook = NULL;
- s->pairs_hook = NULL;
- s->parse_float = NULL;
- s->parse_int = NULL;
- s->parse_constant = NULL;
- }
- return (PyObject *)s;
-}
-
-static int
-scanner_init(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Initialize Scanner object */
- PyObject *ctx;
- static char *kwlist[] = {"context", NULL};
- PyScannerObject *s;
-
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
-
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "O:make_scanner", kwlist, &ctx))
- return -1;
-
- if (s->memo == NULL) {
- s->memo = PyDict_New();
- if (s->memo == NULL)
- goto bail;
- }
-
- /* PyString_AS_STRING is used on encoding */
- s->encoding = PyObject_GetAttrString(ctx, "encoding");
- if (s->encoding == NULL)
- goto bail;
- if (s->encoding == Py_None) {
- Py_DECREF(Py_None);
- s->encoding = PyString_InternFromString(DEFAULT_ENCODING);
- }
- else if (PyUnicode_Check(s->encoding)) {
- PyObject *tmp = PyUnicode_AsEncodedString(s->encoding, NULL, NULL);
- Py_DECREF(s->encoding);
- s->encoding = tmp;
- }
- if (s->encoding == NULL || !PyString_Check(s->encoding))
- goto bail;
-
- /* All of these will fail "gracefully" so we don't need to verify them */
- s->strict = PyObject_GetAttrString(ctx, "strict");
- if (s->strict == NULL)
- goto bail;
- s->object_hook = PyObject_GetAttrString(ctx, "object_hook");
- if (s->object_hook == NULL)
- goto bail;
- s->pairs_hook = PyObject_GetAttrString(ctx, "object_pairs_hook");
- if (s->pairs_hook == NULL)
- goto bail;
- s->parse_float = PyObject_GetAttrString(ctx, "parse_float");
- if (s->parse_float == NULL)
- goto bail;
- s->parse_int = PyObject_GetAttrString(ctx, "parse_int");
- if (s->parse_int == NULL)
- goto bail;
- s->parse_constant = PyObject_GetAttrString(ctx, "parse_constant");
- if (s->parse_constant == NULL)
- goto bail;
-
- return 0;
-
-bail:
- Py_CLEAR(s->encoding);
- Py_CLEAR(s->strict);
- Py_CLEAR(s->object_hook);
- Py_CLEAR(s->pairs_hook);
- Py_CLEAR(s->parse_float);
- Py_CLEAR(s->parse_int);
- Py_CLEAR(s->parse_constant);
- return -1;
-}
-
-PyDoc_STRVAR(scanner_doc, "JSON scanner object");
-
-static
-PyTypeObject PyScannerType = {
- PyObject_HEAD_INIT(NULL)
- 0, /* tp_internal */
- "simplejson._speedups.Scanner", /* tp_name */
- sizeof(PyScannerObject), /* tp_basicsize */
- 0, /* tp_itemsize */
- scanner_dealloc, /* tp_dealloc */
- 0, /* tp_print */
- 0, /* tp_getattr */
- 0, /* tp_setattr */
- 0, /* tp_compare */
- 0, /* tp_repr */
- 0, /* tp_as_number */
- 0, /* tp_as_sequence */
- 0, /* tp_as_mapping */
- 0, /* tp_hash */
- scanner_call, /* tp_call */
- 0, /* tp_str */
- 0,/* PyObject_GenericGetAttr, */ /* tp_getattro */
- 0,/* PyObject_GenericSetAttr, */ /* tp_setattro */
- 0, /* tp_as_buffer */
- Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */
- scanner_doc, /* tp_doc */
- scanner_traverse, /* tp_traverse */
- scanner_clear, /* tp_clear */
- 0, /* tp_richcompare */
- 0, /* tp_weaklistoffset */
- 0, /* tp_iter */
- 0, /* tp_iternext */
- 0, /* tp_methods */
- scanner_members, /* tp_members */
- 0, /* tp_getset */
- 0, /* tp_base */
- 0, /* tp_dict */
- 0, /* tp_descr_get */
- 0, /* tp_descr_set */
- 0, /* tp_dictoffset */
- scanner_init, /* tp_init */
- 0,/* PyType_GenericAlloc, */ /* tp_alloc */
- scanner_new, /* tp_new */
- 0,/* PyObject_GC_Del, */ /* tp_free */
-};
-
-static PyObject *
-encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
-{
- PyEncoderObject *s;
- s = (PyEncoderObject *)type->tp_alloc(type, 0);
- if (s != NULL) {
- s->markers = NULL;
- s->defaultfn = NULL;
- s->encoder = NULL;
- s->indent = NULL;
- s->key_separator = NULL;
- s->item_separator = NULL;
- s->sort_keys = NULL;
- s->skipkeys = NULL;
- s->key_memo = NULL;
- }
- return (PyObject *)s;
-}
-
-static int
-encoder_init(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* initialize Encoder object */
- static char *kwlist[] = {"markers", "default", "encoder", "indent", "key_separator", "item_separator", "sort_keys", "skipkeys", "allow_nan", "key_memo", "use_decimal", NULL};
-
- PyEncoderObject *s;
- PyObject *markers, *defaultfn, *encoder, *indent, *key_separator;
- PyObject *item_separator, *sort_keys, *skipkeys, *allow_nan, *key_memo, *use_decimal;
-
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
-
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OOOOOOOOOOO:make_encoder", kwlist,
- &markers, &defaultfn, &encoder, &indent, &key_separator, &item_separator,
- &sort_keys, &skipkeys, &allow_nan, &key_memo, &use_decimal))
- return -1;
-
- s->markers = markers;
- s->defaultfn = defaultfn;
- s->encoder = encoder;
- s->indent = indent;
- s->key_separator = key_separator;
- s->item_separator = item_separator;
- s->sort_keys = sort_keys;
- s->skipkeys = skipkeys;
- s->key_memo = key_memo;
- s->fast_encode = (PyCFunction_Check(s->encoder) && PyCFunction_GetFunction(s->encoder) == (PyCFunction)py_encode_basestring_ascii);
- s->allow_nan = PyObject_IsTrue(allow_nan);
- s->use_decimal = PyObject_IsTrue(use_decimal);
-
- Py_INCREF(s->markers);
- Py_INCREF(s->defaultfn);
- Py_INCREF(s->encoder);
- Py_INCREF(s->indent);
- Py_INCREF(s->key_separator);
- Py_INCREF(s->item_separator);
- Py_INCREF(s->sort_keys);
- Py_INCREF(s->skipkeys);
- Py_INCREF(s->key_memo);
- return 0;
-}
-
-static PyObject *
-encoder_call(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Python callable interface to encode_listencode_obj */
- static char *kwlist[] = {"obj", "_current_indent_level", NULL};
- PyObject *obj;
- PyObject *rval;
- Py_ssize_t indent_level;
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&:_iterencode", kwlist,
- &obj, _convertPyInt_AsSsize_t, &indent_level))
- return NULL;
- rval = PyList_New(0);
- if (rval == NULL)
- return NULL;
- if (encoder_listencode_obj(s, rval, obj, indent_level)) {
- Py_DECREF(rval);
- return NULL;
- }
- return rval;
-}
-
-static PyObject *
-_encoded_const(PyObject *obj)
-{
- /* Return the JSON string representation of None, True, False */
- if (obj == Py_None) {
- static PyObject *s_null = NULL;
- if (s_null == NULL) {
- s_null = PyString_InternFromString("null");
- }
- Py_INCREF(s_null);
- return s_null;
- }
- else if (obj == Py_True) {
- static PyObject *s_true = NULL;
- if (s_true == NULL) {
- s_true = PyString_InternFromString("true");
- }
- Py_INCREF(s_true);
- return s_true;
- }
- else if (obj == Py_False) {
- static PyObject *s_false = NULL;
- if (s_false == NULL) {
- s_false = PyString_InternFromString("false");
- }
- Py_INCREF(s_false);
- return s_false;
- }
- else {
- PyErr_SetString(PyExc_ValueError, "not a const");
- return NULL;
- }
-}
-
-static PyObject *
-encoder_encode_float(PyEncoderObject *s, PyObject *obj)
-{
- /* Return the JSON representation of a PyFloat */
- double i = PyFloat_AS_DOUBLE(obj);
- if (!Py_IS_FINITE(i)) {
- if (!s->allow_nan) {
- PyErr_SetString(PyExc_ValueError, "Out of range float values are not JSON compliant");
- return NULL;
- }
- if (i > 0) {
- return PyString_FromString("Infinity");
- }
- else if (i < 0) {
- return PyString_FromString("-Infinity");
- }
- else {
- return PyString_FromString("NaN");
- }
- }
- /* Use a better float format here? */
- return PyObject_Repr(obj);
-}
-
-static PyObject *
-encoder_encode_string(PyEncoderObject *s, PyObject *obj)
-{
- /* Return the JSON representation of a string */
- if (s->fast_encode)
- return py_encode_basestring_ascii(NULL, obj);
- else
- return PyObject_CallFunctionObjArgs(s->encoder, obj, NULL);
-}
-
-static int
-_steal_list_append(PyObject *lst, PyObject *stolen)
-{
- /* Append stolen and then decrement its reference count */
- int rval = PyList_Append(lst, stolen);
- Py_DECREF(stolen);
- return rval;
-}
-
-static int
-encoder_listencode_obj(PyEncoderObject *s, PyObject *rval, PyObject *obj, Py_ssize_t indent_level)
-{
- /* Encode Python object obj to a JSON term, rval is a PyList */
- PyObject *newobj;
- int rv;
-
- if (obj == Py_None || obj == Py_True || obj == Py_False) {
- PyObject *cstr = _encoded_const(obj);
- if (cstr == NULL)
- return -1;
- return _steal_list_append(rval, cstr);
- }
- else if (PyString_Check(obj) || PyUnicode_Check(obj))
- {
- PyObject *encoded = encoder_encode_string(s, obj);
- if (encoded == NULL)
- return -1;
- return _steal_list_append(rval, encoded);
- }
- else if (PyInt_Check(obj) || PyLong_Check(obj)) {
- PyObject *encoded = PyObject_Str(obj);
- if (encoded == NULL)
- return -1;
- return _steal_list_append(rval, encoded);
- }
- else if (PyFloat_Check(obj)) {
- PyObject *encoded = encoder_encode_float(s, obj);
- if (encoded == NULL)
- return -1;
- return _steal_list_append(rval, encoded);
- }
- else if (PyList_Check(obj) || PyTuple_Check(obj)) {
- return encoder_listencode_list(s, rval, obj, indent_level);
- }
- else if (PyDict_Check(obj)) {
- return encoder_listencode_dict(s, rval, obj, indent_level);
- }
- else if (s->use_decimal && Decimal_Check(obj)) {
- PyObject *encoded = PyObject_Str(obj);
- if (encoded == NULL)
- return -1;
- return _steal_list_append(rval, encoded);
- }
- else {
- PyObject *ident = NULL;
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(obj);
- if (ident == NULL)
- return -1;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- Py_DECREF(ident);
- return -1;
- }
- if (PyDict_SetItem(s->markers, ident, obj)) {
- Py_DECREF(ident);
- return -1;
- }
- }
- newobj = PyObject_CallFunctionObjArgs(s->defaultfn, obj, NULL);
- if (newobj == NULL) {
- Py_XDECREF(ident);
- return -1;
- }
- rv = encoder_listencode_obj(s, rval, newobj, indent_level);
- Py_DECREF(newobj);
- if (rv) {
- Py_XDECREF(ident);
- return -1;
- }
- if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident)) {
- Py_XDECREF(ident);
- return -1;
- }
- Py_XDECREF(ident);
- }
- return rv;
- }
-}
-
-static int
-encoder_listencode_dict(PyEncoderObject *s, PyObject *rval, PyObject *dct, Py_ssize_t indent_level)
-{
- /* Encode Python dict dct a JSON term, rval is a PyList */
- static PyObject *open_dict = NULL;
- static PyObject *close_dict = NULL;
- static PyObject *empty_dict = NULL;
- static PyObject *iteritems = NULL;
- PyObject *kstr = NULL;
- PyObject *ident = NULL;
- PyObject *key, *value;
- PyObject *iter = NULL;
- PyObject *item = NULL;
- PyObject *encoded = NULL;
- int skipkeys;
- Py_ssize_t idx;
-
- if (open_dict == NULL || close_dict == NULL || empty_dict == NULL || iteritems == NULL) {
- open_dict = PyString_InternFromString("{");
- close_dict = PyString_InternFromString("}");
- empty_dict = PyString_InternFromString("{}");
- iteritems = PyString_InternFromString("iteritems");
- if (open_dict == NULL || close_dict == NULL || empty_dict == NULL || iteritems == NULL)
- return -1;
- }
- if (PyDict_Size(dct) == 0)
- return PyList_Append(rval, empty_dict);
-
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(dct);
- if (ident == NULL)
- goto bail;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- goto bail;
- }
- if (PyDict_SetItem(s->markers, ident, dct)) {
- goto bail;
- }
- }
-
- if (PyList_Append(rval, open_dict))
- goto bail;
-
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level += 1;
- /*
- newline_indent = '\n' + (_indent * _current_indent_level)
- separator = _item_separator + newline_indent
- buf += newline_indent
- */
- }
-
- /* TODO: C speedup not implemented for sort_keys */
-
- skipkeys = PyObject_IsTrue(s->skipkeys);
- idx = 0;
- iter = PyObject_CallMethodObjArgs(dct, iteritems, NULL);
- if (iter == NULL)
- goto bail;
- while ((item = PyIter_Next(iter))) {
-
- key = PyTuple_GetItem(item, 0);
- if (key == NULL)
- goto bail;
- value = PyTuple_GetItem(item, 1);
- if (value == NULL)
- goto bail;
-
- encoded = PyDict_GetItem(s->key_memo, key);
- if (encoded != NULL) {
- Py_INCREF(encoded);
- }
- else if (PyString_Check(key) || PyUnicode_Check(key)) {
- Py_INCREF(key);
- kstr = key;
- }
- else if (PyFloat_Check(key)) {
- kstr = encoder_encode_float(s, key);
- if (kstr == NULL)
- goto bail;
- }
- else if (PyInt_Check(key) || PyLong_Check(key)) {
- kstr = PyObject_Str(key);
- if (kstr == NULL)
- goto bail;
- }
- else if (key == Py_True || key == Py_False || key == Py_None) {
- kstr = _encoded_const(key);
- if (kstr == NULL)
- goto bail;
- }
- else if (skipkeys) {
- Py_DECREF(item);
- continue;
- }
- else {
- /* TODO: include repr of key */
- PyErr_SetString(PyExc_ValueError, "keys must be a string");
- goto bail;
- }
-
- if (idx) {
- if (PyList_Append(rval, s->item_separator))
- goto bail;
- }
-
- if (encoded == NULL) {
- encoded = encoder_encode_string(s, kstr);
- Py_CLEAR(kstr);
- if (encoded == NULL)
- goto bail;
- if (PyDict_SetItem(s->key_memo, key, encoded))
- goto bail;
- }
- if (PyList_Append(rval, encoded)) {
- goto bail;
- }
- Py_CLEAR(encoded);
- if (PyList_Append(rval, s->key_separator))
- goto bail;
- if (encoder_listencode_obj(s, rval, value, indent_level))
- goto bail;
- Py_CLEAR(item);
- idx += 1;
- }
- Py_CLEAR(iter);
- if (PyErr_Occurred())
- goto bail;
- if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident))
- goto bail;
- Py_CLEAR(ident);
- }
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level -= 1;
- /*
- yield '\n' + (_indent * _current_indent_level)
- */
- }
- if (PyList_Append(rval, close_dict))
- goto bail;
- return 0;
-
-bail:
- Py_XDECREF(encoded);
- Py_XDECREF(item);
- Py_XDECREF(iter);
- Py_XDECREF(kstr);
- Py_XDECREF(ident);
- return -1;
-}
-
-
-static int
-encoder_listencode_list(PyEncoderObject *s, PyObject *rval, PyObject *seq, Py_ssize_t indent_level)
-{
- /* Encode Python list seq to a JSON term, rval is a PyList */
- static PyObject *open_array = NULL;
- static PyObject *close_array = NULL;
- static PyObject *empty_array = NULL;
- PyObject *ident = NULL;
- PyObject *iter = NULL;
- PyObject *obj = NULL;
- int is_true;
- int i = 0;
-
- if (open_array == NULL || close_array == NULL || empty_array == NULL) {
- open_array = PyString_InternFromString("[");
- close_array = PyString_InternFromString("]");
- empty_array = PyString_InternFromString("[]");
- if (open_array == NULL || close_array == NULL || empty_array == NULL)
- return -1;
- }
- ident = NULL;
- is_true = PyObject_IsTrue(seq);
- if (is_true == -1)
- return -1;
- else if (is_true == 0)
- return PyList_Append(rval, empty_array);
-
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(seq);
- if (ident == NULL)
- goto bail;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- goto bail;
- }
- if (PyDict_SetItem(s->markers, ident, seq)) {
- goto bail;
- }
- }
-
- iter = PyObject_GetIter(seq);
- if (iter == NULL)
- goto bail;
-
- if (PyList_Append(rval, open_array))
- goto bail;
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level += 1;
- /*
- newline_indent = '\n' + (_indent * _current_indent_level)
- separator = _item_separator + newline_indent
- buf += newline_indent
- */
- }
- while ((obj = PyIter_Next(iter))) {
- if (i) {
- if (PyList_Append(rval, s->item_separator))
- goto bail;
- }
- if (encoder_listencode_obj(s, rval, obj, indent_level))
- goto bail;
- i++;
- Py_CLEAR(obj);
- }
- Py_CLEAR(iter);
- if (PyErr_Occurred())
- goto bail;
- if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident))
- goto bail;
- Py_CLEAR(ident);
- }
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level -= 1;
- /*
- yield '\n' + (_indent * _current_indent_level)
- */
- }
- if (PyList_Append(rval, close_array))
- goto bail;
- return 0;
-
-bail:
- Py_XDECREF(obj);
- Py_XDECREF(iter);
- Py_XDECREF(ident);
- return -1;
-}
-
-static void
-encoder_dealloc(PyObject *self)
-{
- /* Deallocate Encoder */
- encoder_clear(self);
- Py_TYPE(self)->tp_free(self);
-}
-
-static int
-encoder_traverse(PyObject *self, visitproc visit, void *arg)
-{
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- Py_VISIT(s->markers);
- Py_VISIT(s->defaultfn);
- Py_VISIT(s->encoder);
- Py_VISIT(s->indent);
- Py_VISIT(s->key_separator);
- Py_VISIT(s->item_separator);
- Py_VISIT(s->sort_keys);
- Py_VISIT(s->skipkeys);
- Py_VISIT(s->key_memo);
- return 0;
-}
-
-static int
-encoder_clear(PyObject *self)
-{
- /* Deallocate Encoder */
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- Py_CLEAR(s->markers);
- Py_CLEAR(s->defaultfn);
- Py_CLEAR(s->encoder);
- Py_CLEAR(s->indent);
- Py_CLEAR(s->key_separator);
- Py_CLEAR(s->item_separator);
- Py_CLEAR(s->sort_keys);
- Py_CLEAR(s->skipkeys);
- Py_CLEAR(s->key_memo);
- return 0;
-}
-
-PyDoc_STRVAR(encoder_doc, "_iterencode(obj, _current_indent_level) -> iterable");
-
-static
-PyTypeObject PyEncoderType = {
- PyObject_HEAD_INIT(NULL)
- 0, /* tp_internal */
- "simplejson._speedups.Encoder", /* tp_name */
- sizeof(PyEncoderObject), /* tp_basicsize */
- 0, /* tp_itemsize */
- encoder_dealloc, /* tp_dealloc */
- 0, /* tp_print */
- 0, /* tp_getattr */
- 0, /* tp_setattr */
- 0, /* tp_compare */
- 0, /* tp_repr */
- 0, /* tp_as_number */
- 0, /* tp_as_sequence */
- 0, /* tp_as_mapping */
- 0, /* tp_hash */
- encoder_call, /* tp_call */
- 0, /* tp_str */
- 0, /* tp_getattro */
- 0, /* tp_setattro */
- 0, /* tp_as_buffer */
- Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */
- encoder_doc, /* tp_doc */
- encoder_traverse, /* tp_traverse */
- encoder_clear, /* tp_clear */
- 0, /* tp_richcompare */
- 0, /* tp_weaklistoffset */
- 0, /* tp_iter */
- 0, /* tp_iternext */
- 0, /* tp_methods */
- encoder_members, /* tp_members */
- 0, /* tp_getset */
- 0, /* tp_base */
- 0, /* tp_dict */
- 0, /* tp_descr_get */
- 0, /* tp_descr_set */
- 0, /* tp_dictoffset */
- encoder_init, /* tp_init */
- 0, /* tp_alloc */
- encoder_new, /* tp_new */
- 0, /* tp_free */
-};
-
-static PyMethodDef speedups_methods[] = {
- {"encode_basestring_ascii",
- (PyCFunction)py_encode_basestring_ascii,
- METH_O,
- pydoc_encode_basestring_ascii},
- {"scanstring",
- (PyCFunction)py_scanstring,
- METH_VARARGS,
- pydoc_scanstring},
- {NULL, NULL, 0, NULL}
-};
-
-PyDoc_STRVAR(module_doc,
-"simplejson speedups\n");
-
-void
-init_speedups(void)
-{
- PyObject *m, *decimal;
- PyScannerType.tp_new = PyType_GenericNew;
- if (PyType_Ready(&PyScannerType) < 0)
- return;
- PyEncoderType.tp_new = PyType_GenericNew;
- if (PyType_Ready(&PyEncoderType) < 0)
- return;
-
- decimal = PyImport_ImportModule("decimal");
- if (decimal == NULL)
- return;
- DecimalTypePtr = (PyTypeObject*)PyObject_GetAttrString(decimal, "Decimal");
- Py_DECREF(decimal);
- if (DecimalTypePtr == NULL)
- return;
-
- m = Py_InitModule3("_speedups", speedups_methods, module_doc);
- Py_INCREF((PyObject*)&PyScannerType);
- PyModule_AddObject(m, "make_scanner", (PyObject*)&PyScannerType);
- Py_INCREF((PyObject*)&PyEncoderType);
- PyModule_AddObject(m, "make_encoder", (PyObject*)&PyEncoderType);
-}
diff --git a/tablib/packages/simplejson/decoder.py b/tablib/packages/simplejson/decoder.py
deleted file mode 100644
index 4cf4015..0000000
--- a/tablib/packages/simplejson/decoder.py
+++ /dev/null
@@ -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
diff --git a/tablib/packages/simplejson/encoder.py b/tablib/packages/simplejson/encoder.py
deleted file mode 100644
index cab8456..0000000
--- a/tablib/packages/simplejson/encoder.py
+++ /dev/null
@@ -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
diff --git a/tablib/packages/simplejson/ordered_dict.py b/tablib/packages/simplejson/ordered_dict.py
deleted file mode 100644
index 87ad888..0000000
--- a/tablib/packages/simplejson/ordered_dict.py
+++ /dev/null
@@ -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
diff --git a/tablib/packages/simplejson/scanner.py b/tablib/packages/simplejson/scanner.py
deleted file mode 100644
index 54593a3..0000000
--- a/tablib/packages/simplejson/scanner.py
+++ /dev/null
@@ -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
diff --git a/tablib/packages/simplejson/tests/__init__.py b/tablib/packages/simplejson/tests/__init__.py
deleted file mode 100644
index 22d8465..0000000
--- a/tablib/packages/simplejson/tests/__init__.py
+++ /dev/null
@@ -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()
diff --git a/tablib/packages/simplejson/tests/test_check_circular.py b/tablib/packages/simplejson/tests/test_check_circular.py
deleted file mode 100644
index af6463d..0000000
--- a/tablib/packages/simplejson/tests/test_check_circular.py
+++ /dev/null
@@ -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)
diff --git a/tablib/packages/simplejson/tests/test_decimal.py b/tablib/packages/simplejson/tests/test_decimal.py
deleted file mode 100644
index a694c7e..0000000
--- a/tablib/packages/simplejson/tests/test_decimal.py
+++ /dev/null
@@ -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) \ No newline at end of file
diff --git a/tablib/packages/simplejson/tests/test_decode.py b/tablib/packages/simplejson/tests/test_decode.py
deleted file mode 100644
index a5a1c48..0000000
--- a/tablib/packages/simplejson/tests/test_decode.py
+++ /dev/null
@@ -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""])
diff --git a/tablib/packages/simplejson/tests/test_default.py b/tablib/packages/simplejson/tests/test_default.py
deleted file mode 100644
index 139e42b..0000000
--- a/tablib/packages/simplejson/tests/test_default.py
+++ /dev/null
@@ -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)))
diff --git a/tablib/packages/simplejson/tests/test_dump.py b/tablib/packages/simplejson/tests/test_dump.py
deleted file mode 100644
index 8b34004..0000000
--- a/tablib/packages/simplejson/tests/test_dump.py
+++ /dev/null
@@ -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}') \ No newline at end of file
diff --git a/tablib/packages/simplejson/tests/test_encode_basestring_ascii.py b/tablib/packages/simplejson/tests/test_encode_basestring_ascii.py
deleted file mode 100644
index b19631a..0000000
--- a/tablib/packages/simplejson/tests/test_encode_basestring_ascii.py
+++ /dev/null
@@ -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))
diff --git a/tablib/packages/simplejson/tests/test_encode_for_html.py b/tablib/packages/simplejson/tests/test_encode_for_html.py
deleted file mode 100644
index c2d5f80..0000000
--- a/tablib/packages/simplejson/tests/test_encode_for_html.py
+++ /dev/null
@@ -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)))
diff --git a/tablib/packages/simplejson/tests/test_fail.py b/tablib/packages/simplejson/tests/test_fail.py
deleted file mode 100644
index 646c0f4..0000000
--- a/tablib/packages/simplejson/tests/test_fail.py
+++ /dev/null
@@ -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 '[,]'") \ No newline at end of file
diff --git a/tablib/packages/simplejson/tests/test_float.py b/tablib/packages/simplejson/tests/test_float.py
deleted file mode 100644
index 94502c6..0000000
--- a/tablib/packages/simplejson/tests/test_float.py
+++ /dev/null
@@ -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)
diff --git a/tablib/packages/simplejson/tests/test_indent.py b/tablib/packages/simplejson/tests/test_indent.py
deleted file mode 100644
index 985831b..0000000
--- a/tablib/packages/simplejson/tests/test_indent.py
+++ /dev/null
@@ -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)
diff --git a/tablib/packages/simplejson/tests/test_pass1.py b/tablib/packages/simplejson/tests/test_pass1.py
deleted file mode 100644
index c3d6302..0000000
--- a/tablib/packages/simplejson/tests/test_pass1.py
+++ /dev/null
@@ -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")
diff --git a/tablib/packages/simplejson/tests/test_pass2.py b/tablib/packages/simplejson/tests/test_pass2.py
deleted file mode 100644
index de4ee00..0000000
--- a/tablib/packages/simplejson/tests/test_pass2.py
+++ /dev/null
@@ -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))
diff --git a/tablib/packages/simplejson/tests/test_pass3.py b/tablib/packages/simplejson/tests/test_pass3.py
deleted file mode 100644
index f591aba..0000000
--- a/tablib/packages/simplejson/tests/test_pass3.py
+++ /dev/null
@@ -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))
diff --git a/tablib/packages/simplejson/tests/test_recursion.py b/tablib/packages/simplejson/tests/test_recursion.py
deleted file mode 100644
index 97422a6..0000000
--- a/tablib/packages/simplejson/tests/test_recursion.py
+++ /dev/null
@@ -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")
diff --git a/tablib/packages/simplejson/tests/test_scanstring.py b/tablib/packages/simplejson/tests/test_scanstring.py
deleted file mode 100644
index a7fcd46..0000000
--- a/tablib/packages/simplejson/tests/test_scanstring.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/simplejson/tests/test_separators.py b/tablib/packages/simplejson/tests/test_separators.py
deleted file mode 100644
index cbda93c..0000000
--- a/tablib/packages/simplejson/tests/test_separators.py
+++ /dev/null
@@ -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)
diff --git a/tablib/packages/simplejson/tests/test_speedups.py b/tablib/packages/simplejson/tests/test_speedups.py
deleted file mode 100644
index 4bf0875..0000000
--- a/tablib/packages/simplejson/tests/test_speedups.py
+++ /dev/null
@@ -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)
diff --git a/tablib/packages/simplejson/tests/test_unicode.py b/tablib/packages/simplejson/tests/test_unicode.py
deleted file mode 100644
index f73e5bf..0000000
--- a/tablib/packages/simplejson/tests/test_unicode.py
+++ /dev/null
@@ -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)
diff --git a/tablib/packages/simplejson/tool.py b/tablib/packages/simplejson/tool.py
deleted file mode 100644
index 73370db..0000000
--- a/tablib/packages/simplejson/tool.py
+++ /dev/null
@@ -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()
diff --git a/tablib/packages/yaml/__init__.py b/tablib/packages/yaml/__init__.py
deleted file mode 100644
index c0fd1f3..0000000
--- a/tablib/packages/yaml/__init__.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/yaml/composer.py b/tablib/packages/yaml/composer.py
deleted file mode 100644
index 06e5ac7..0000000
--- a/tablib/packages/yaml/composer.py
+++ /dev/null
@@ -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
-
diff --git a/tablib/packages/yaml/constructor.py b/tablib/packages/yaml/constructor.py
deleted file mode 100644
index 420c434..0000000
--- a/tablib/packages/yaml/constructor.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/yaml/cyaml.py b/tablib/packages/yaml/cyaml.py
deleted file mode 100644
index 68dcd75..0000000
--- a/tablib/packages/yaml/cyaml.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/yaml/dumper.py b/tablib/packages/yaml/dumper.py
deleted file mode 100644
index f811d2c..0000000
--- a/tablib/packages/yaml/dumper.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/yaml/emitter.py b/tablib/packages/yaml/emitter.py
deleted file mode 100644
index 4cb2c8a..0000000
--- a/tablib/packages/yaml/emitter.py
+++ /dev/null
@@ -1,1135 +0,0 @@
-
-# Emitter expects events obeying the following grammar:
-# stream ::= STREAM-START document* STREAM-END
-# document ::= DOCUMENT-START node DOCUMENT-END
-# node ::= SCALAR | sequence | mapping
-# sequence ::= SEQUENCE-START node* SEQUENCE-END
-# mapping ::= MAPPING-START (node node)* MAPPING-END
-
-__all__ = ['Emitter', 'EmitterError']
-
-from error import YAMLError
-from events import *
-
-class EmitterError(YAMLError):
- pass
-
-class ScalarAnalysis(object):
- def __init__(self, scalar, empty, multiline,
- allow_flow_plain, allow_block_plain,
- allow_single_quoted, allow_double_quoted,
- allow_block):
- self.scalar = scalar
- self.empty = empty
- self.multiline = multiline
- self.allow_flow_plain = allow_flow_plain
- self.allow_block_plain = allow_block_plain
- self.allow_single_quoted = allow_single_quoted
- self.allow_double_quoted = allow_double_quoted
- self.allow_block = allow_block
-
-class Emitter(object):
-
- DEFAULT_TAG_PREFIXES = {
- u'!' : u'!',
- u'tag:yaml.org,2002:' : u'!!',
- }
-
- def __init__(self, stream, canonical=None, indent=None, width=None,
- allow_unicode=None, line_break=None):
-
- # The stream should have the methods `write` and possibly `flush`.
- self.stream = stream
-
- # Encoding can be overriden by STREAM-START.
- self.encoding = None
-
- # Emitter is a state machine with a stack of states to handle nested
- # structures.
- self.states = []
- self.state = self.expect_stream_start
-
- # Current event and the event queue.
- self.events = []
- self.event = None
-
- # The current indentation level and the stack of previous indents.
- self.indents = []
- self.indent = None
-
- # Flow level.
- self.flow_level = 0
-
- # Contexts.
- self.root_context = False
- self.sequence_context = False
- self.mapping_context = False
- self.simple_key_context = False
-
- # Characteristics of the last emitted character:
- # - current position.
- # - is it a whitespace?
- # - is it an indention character
- # (indentation space, '-', '?', or ':')?
- self.line = 0
- self.column = 0
- self.whitespace = True
- self.indention = True
-
- # Whether the document requires an explicit document indicator
- self.open_ended = False
-
- # Formatting details.
- self.canonical = canonical
- self.allow_unicode = allow_unicode
- self.best_indent = 2
- if indent and 1 < indent < 10:
- self.best_indent = indent
- self.best_width = 80
- if width and width > self.best_indent*2:
- self.best_width = width
- self.best_line_break = u'\n'
- if line_break in [u'\r', u'\n', u'\r\n']:
- self.best_line_break = line_break
-
- # Tag prefixes.
- self.tag_prefixes = None
-
- # Prepared anchor and tag.
- self.prepared_anchor = None
- self.prepared_tag = None
-
- # Scalar analysis and style.
- self.analysis = None
- self.style = None
-
- def emit(self, event):
- self.events.append(event)
- while not self.need_more_events():
- self.event = self.events.pop(0)
- self.state()
- self.event = None
-
- # In some cases, we wait for a few next events before emitting.
-
- def need_more_events(self):
- if not self.events:
- return True
- event = self.events[0]
- if isinstance(event, DocumentStartEvent):
- return self.need_events(1)
- elif isinstance(event, SequenceStartEvent):
- return self.need_events(2)
- elif isinstance(event, MappingStartEvent):
- return self.need_events(3)
- else:
- return False
-
- def need_events(self, count):
- level = 0
- for event in self.events[1:]:
- if isinstance(event, (DocumentStartEvent, CollectionStartEvent)):
- level += 1
- elif isinstance(event, (DocumentEndEvent, CollectionEndEvent)):
- level -= 1
- elif isinstance(event, StreamEndEvent):
- level = -1
- if level < 0:
- return False
- return (len(self.events) < count+1)
-
- def increase_indent(self, flow=False, indentless=False):
- self.indents.append(self.indent)
- if self.indent is None:
- if flow:
- self.indent = self.best_indent
- else:
- self.indent = 0
- elif not indentless:
- self.indent += self.best_indent
-
- # States.
-
- # Stream handlers.
-
- def expect_stream_start(self):
- if isinstance(self.event, StreamStartEvent):
- if self.event.encoding and not getattr(self.stream, 'encoding', None):
- self.encoding = self.event.encoding
- self.write_stream_start()
- self.state = self.expect_first_document_start
- else:
- raise EmitterError("expected StreamStartEvent, but got %s"
- % self.event)
-
- def expect_nothing(self):
- raise EmitterError("expected nothing, but got %s" % self.event)
-
- # Document handlers.
-
- def expect_first_document_start(self):
- return self.expect_document_start(first=True)
-
- def expect_document_start(self, first=False):
- if isinstance(self.event, DocumentStartEvent):
- if (self.event.version or self.event.tags) and self.open_ended:
- self.write_indicator(u'...', True)
- self.write_indent()
- if self.event.version:
- version_text = self.prepare_version(self.event.version)
- self.write_version_directive(version_text)
- self.tag_prefixes = self.DEFAULT_TAG_PREFIXES.copy()
- if self.event.tags:
- handles = self.event.tags.keys()
- handles.sort()
- for handle in handles:
- prefix = self.event.tags[handle]
- self.tag_prefixes[prefix] = handle
- handle_text = self.prepare_tag_handle(handle)
- prefix_text = self.prepare_tag_prefix(prefix)
- self.write_tag_directive(handle_text, prefix_text)
- implicit = (first and not self.event.explicit and not self.canonical
- and not self.event.version and not self.event.tags
- and not self.check_empty_document())
- if not implicit:
- self.write_indent()
- self.write_indicator(u'---', True)
- if self.canonical:
- self.write_indent()
- self.state = self.expect_document_root
- elif isinstance(self.event, StreamEndEvent):
- if self.open_ended:
- self.write_indicator(u'...', True)
- self.write_indent()
- self.write_stream_end()
- self.state = self.expect_nothing
- else:
- raise EmitterError("expected DocumentStartEvent, but got %s"
- % self.event)
-
- def expect_document_end(self):
- if isinstance(self.event, DocumentEndEvent):
- self.write_indent()
- if self.event.explicit:
- self.write_indicator(u'...', True)
- self.write_indent()
- self.flush_stream()
- self.state = self.expect_document_start
- else:
- raise EmitterError("expected DocumentEndEvent, but got %s"
- % self.event)
-
- def expect_document_root(self):
- self.states.append(self.expect_document_end)
- self.expect_node(root=True)
-
- # Node handlers.
-
- def expect_node(self, root=False, sequence=False, mapping=False,
- simple_key=False):
- self.root_context = root
- self.sequence_context = sequence
- self.mapping_context = mapping
- self.simple_key_context = simple_key
- if isinstance(self.event, AliasEvent):
- self.expect_alias()
- elif isinstance(self.event, (ScalarEvent, CollectionStartEvent)):
- self.process_anchor(u'&')
- self.process_tag()
- if isinstance(self.event, ScalarEvent):
- self.expect_scalar()
- elif isinstance(self.event, SequenceStartEvent):
- if self.flow_level or self.canonical or self.event.flow_style \
- or self.check_empty_sequence():
- self.expect_flow_sequence()
- else:
- self.expect_block_sequence()
- elif isinstance(self.event, MappingStartEvent):
- if self.flow_level or self.canonical or self.event.flow_style \
- or self.check_empty_mapping():
- self.expect_flow_mapping()
- else:
- self.expect_block_mapping()
- else:
- raise EmitterError("expected NodeEvent, but got %s" % self.event)
-
- def expect_alias(self):
- if self.event.anchor is None:
- raise EmitterError("anchor is not specified for alias")
- self.process_anchor(u'*')
- self.state = self.states.pop()
-
- def expect_scalar(self):
- self.increase_indent(flow=True)
- self.process_scalar()
- self.indent = self.indents.pop()
- self.state = self.states.pop()
-
- # Flow sequence handlers.
-
- def expect_flow_sequence(self):
- self.write_indicator(u'[', True, whitespace=True)
- self.flow_level += 1
- self.increase_indent(flow=True)
- self.state = self.expect_first_flow_sequence_item
-
- def expect_first_flow_sequence_item(self):
- if isinstance(self.event, SequenceEndEvent):
- self.indent = self.indents.pop()
- self.flow_level -= 1
- self.write_indicator(u']', False)
- self.state = self.states.pop()
- else:
- if self.canonical or self.column > self.best_width:
- self.write_indent()
- self.states.append(self.expect_flow_sequence_item)
- self.expect_node(sequence=True)
-
- def expect_flow_sequence_item(self):
- if isinstance(self.event, SequenceEndEvent):
- self.indent = self.indents.pop()
- self.flow_level -= 1
- if self.canonical:
- self.write_indicator(u',', False)
- self.write_indent()
- self.write_indicator(u']', False)
- self.state = self.states.pop()
- else:
- self.write_indicator(u',', False)
- if self.canonical or self.column > self.best_width:
- self.write_indent()
- self.states.append(self.expect_flow_sequence_item)
- self.expect_node(sequence=True)
-
- # Flow mapping handlers.
-
- def expect_flow_mapping(self):
- self.write_indicator(u'{', True, whitespace=True)
- self.flow_level += 1
- self.increase_indent(flow=True)
- self.state = self.expect_first_flow_mapping_key
-
- def expect_first_flow_mapping_key(self):
- if isinstance(self.event, MappingEndEvent):
- self.indent = self.indents.pop()
- self.flow_level -= 1
- self.write_indicator(u'}', False)
- self.state = self.states.pop()
- else:
- if self.canonical or self.column > self.best_width:
- self.write_indent()
- if not self.canonical and self.check_simple_key():
- self.states.append(self.expect_flow_mapping_simple_value)
- self.expect_node(mapping=True, simple_key=True)
- else:
- self.write_indicator(u'?', True)
- self.states.append(self.expect_flow_mapping_value)
- self.expect_node(mapping=True)
-
- def expect_flow_mapping_key(self):
- if isinstance(self.event, MappingEndEvent):
- self.indent = self.indents.pop()
- self.flow_level -= 1
- if self.canonical:
- self.write_indicator(u',', False)
- self.write_indent()
- self.write_indicator(u'}', False)
- self.state = self.states.pop()
- else:
- self.write_indicator(u',', False)
- if self.canonical or self.column > self.best_width:
- self.write_indent()
- if not self.canonical and self.check_simple_key():
- self.states.append(self.expect_flow_mapping_simple_value)
- self.expect_node(mapping=True, simple_key=True)
- else:
- self.write_indicator(u'?', True)
- self.states.append(self.expect_flow_mapping_value)
- self.expect_node(mapping=True)
-
- def expect_flow_mapping_simple_value(self):
- self.write_indicator(u':', False)
- self.states.append(self.expect_flow_mapping_key)
- self.expect_node(mapping=True)
-
- def expect_flow_mapping_value(self):
- if self.canonical or self.column > self.best_width:
- self.write_indent()
- self.write_indicator(u':', True)
- self.states.append(self.expect_flow_mapping_key)
- self.expect_node(mapping=True)
-
- # Block sequence handlers.
-
- def expect_block_sequence(self):
- indentless = (self.mapping_context and not self.indention)
- self.increase_indent(flow=False, indentless=indentless)
- self.state = self.expect_first_block_sequence_item
-
- def expect_first_block_sequence_item(self):
- return self.expect_block_sequence_item(first=True)
-
- def expect_block_sequence_item(self, first=False):
- if not first and isinstance(self.event, SequenceEndEvent):
- self.indent = self.indents.pop()
- self.state = self.states.pop()
- else:
- self.write_indent()
- self.write_indicator(u'-', True, indention=True)
- self.states.append(self.expect_block_sequence_item)
- self.expect_node(sequence=True)
-
- # Block mapping handlers.
-
- def expect_block_mapping(self):
- self.increase_indent(flow=False)
- self.state = self.expect_first_block_mapping_key
-
- def expect_first_block_mapping_key(self):
- return self.expect_block_mapping_key(first=True)
-
- def expect_block_mapping_key(self, first=False):
- if not first and isinstance(self.event, MappingEndEvent):
- self.indent = self.indents.pop()
- self.state = self.states.pop()
- else:
- self.write_indent()
- if self.check_simple_key():
- self.states.append(self.expect_block_mapping_simple_value)
- self.expect_node(mapping=True, simple_key=True)
- else:
- self.write_indicator(u'?', True, indention=True)
- self.states.append(self.expect_block_mapping_value)
- self.expect_node(mapping=True)
-
- def expect_block_mapping_simple_value(self):
- self.write_indicator(u':', False)
- self.states.append(self.expect_block_mapping_key)
- self.expect_node(mapping=True)
-
- def expect_block_mapping_value(self):
- self.write_indent()
- self.write_indicator(u':', True, indention=True)
- self.states.append(self.expect_block_mapping_key)
- self.expect_node(mapping=True)
-
- # Checkers.
-
- def check_empty_sequence(self):
- return (isinstance(self.event, SequenceStartEvent) and self.events
- and isinstance(self.events[0], SequenceEndEvent))
-
- def check_empty_mapping(self):
- return (isinstance(self.event, MappingStartEvent) and self.events
- and isinstance(self.events[0], MappingEndEvent))
-
- def check_empty_document(self):
- if not isinstance(self.event, DocumentStartEvent) or not self.events:
- return False
- event = self.events[0]
- return (isinstance(event, ScalarEvent) and event.anchor is None
- and event.tag is None and event.implicit and event.value == u'')
-
- def check_simple_key(self):
- length = 0
- if isinstance(self.event, NodeEvent) and self.event.anchor is not None:
- if self.prepared_anchor is None:
- self.prepared_anchor = self.prepare_anchor(self.event.anchor)
- length += len(self.prepared_anchor)
- if isinstance(self.event, (ScalarEvent, CollectionStartEvent)) \
- and self.event.tag is not None:
- if self.prepared_tag is None:
- self.prepared_tag = self.prepare_tag(self.event.tag)
- length += len(self.prepared_tag)
- if isinstance(self.event, ScalarEvent):
- if self.analysis is None:
- self.analysis = self.analyze_scalar(self.event.value)
- length += len(self.analysis.scalar)
- return (length < 128 and (isinstance(self.event, AliasEvent)
- or (isinstance(self.event, ScalarEvent)
- and not self.analysis.empty and not self.analysis.multiline)
- or self.check_empty_sequence() or self.check_empty_mapping()))
-
- # Anchor, Tag, and Scalar processors.
-
- def process_anchor(self, indicator):
- if self.event.anchor is None:
- self.prepared_anchor = None
- return
- if self.prepared_anchor is None:
- self.prepared_anchor = self.prepare_anchor(self.event.anchor)
- if self.prepared_anchor:
- self.write_indicator(indicator+self.prepared_anchor, True)
- self.prepared_anchor = None
-
- def process_tag(self):
- tag = self.event.tag
- if isinstance(self.event, ScalarEvent):
- if self.style is None:
- self.style = self.choose_scalar_style()
- if ((not self.canonical or tag is None) and
- ((self.style == '' and self.event.implicit[0])
- or (self.style != '' and self.event.implicit[1]))):
- self.prepared_tag = None
- return
- if self.event.implicit[0] and tag is None:
- tag = u'!'
- self.prepared_tag = None
- else:
- if (not self.canonical or tag is None) and self.event.implicit:
- self.prepared_tag = None
- return
- if tag is None:
- raise EmitterError("tag is not specified")
- if self.prepared_tag is None:
- self.prepared_tag = self.prepare_tag(tag)
- if self.prepared_tag:
- self.write_indicator(self.prepared_tag, True)
- self.prepared_tag = None
-
- def choose_scalar_style(self):
- if self.analysis is None:
- self.analysis = self.analyze_scalar(self.event.value)
- if self.event.style == '"' or self.canonical:
- return '"'
- if not self.event.style and self.event.implicit[0]:
- if (not (self.simple_key_context and
- (self.analysis.empty or self.analysis.multiline))
- and (self.flow_level and self.analysis.allow_flow_plain
- or (not self.flow_level and self.analysis.allow_block_plain))):
- return ''
- if self.event.style and self.event.style in '|>':
- if (not self.flow_level and not self.simple_key_context
- and self.analysis.allow_block):
- return self.event.style
- if not self.event.style or self.event.style == '\'':
- if (self.analysis.allow_single_quoted and
- not (self.simple_key_context and self.analysis.multiline)):
- return '\''
- return '"'
-
- def process_scalar(self):
- if self.analysis is None:
- self.analysis = self.analyze_scalar(self.event.value)
- if self.style is None:
- self.style = self.choose_scalar_style()
- split = (not self.simple_key_context)
- #if self.analysis.multiline and split \
- # and (not self.style or self.style in '\'\"'):
- # self.write_indent()
- if self.style == '"':
- self.write_double_quoted(self.analysis.scalar, split)
- elif self.style == '\'':
- self.write_single_quoted(self.analysis.scalar, split)
- elif self.style == '>':
- self.write_folded(self.analysis.scalar)
- elif self.style == '|':
- self.write_literal(self.analysis.scalar)
- else:
- self.write_plain(self.analysis.scalar, split)
- self.analysis = None
- self.style = None
-
- # Analyzers.
-
- def prepare_version(self, version):
- major, minor = version
- if major != 1:
- raise EmitterError("unsupported YAML version: %d.%d" % (major, minor))
- return u'%d.%d' % (major, minor)
-
- def prepare_tag_handle(self, handle):
- if not handle:
- raise EmitterError("tag handle must not be empty")
- if handle[0] != u'!' or handle[-1] != u'!':
- raise EmitterError("tag handle must start and end with '!': %r"
- % (handle.encode('utf-8')))
- for ch in handle[1:-1]:
- if not (u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \
- or ch in u'-_'):
- raise EmitterError("invalid character %r in the tag handle: %r"
- % (ch.encode('utf-8'), handle.encode('utf-8')))
- return handle
-
- def prepare_tag_prefix(self, prefix):
- if not prefix:
- raise EmitterError("tag prefix must not be empty")
- chunks = []
- start = end = 0
- if prefix[0] == u'!':
- end = 1
- while end < len(prefix):
- ch = prefix[end]
- if u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \
- or ch in u'-;/?!:@&=+$,_.~*\'()[]':
- end += 1
- else:
- if start < end:
- chunks.append(prefix[start:end])
- start = end = end+1
- data = ch.encode('utf-8')
- for ch in data:
- chunks.append(u'%%%02X' % ord(ch))
- if start < end:
- chunks.append(prefix[start:end])
- return u''.join(chunks)
-
- def prepare_tag(self, tag):
- if not tag:
- raise EmitterError("tag must not be empty")
- if tag == u'!':
- return tag
- handle = None
- suffix = tag
- prefixes = self.tag_prefixes.keys()
- prefixes.sort()
- for prefix in prefixes:
- if tag.startswith(prefix) \
- and (prefix == u'!' or len(prefix) < len(tag)):
- handle = self.tag_prefixes[prefix]
- suffix = tag[len(prefix):]
- chunks = []
- start = end = 0
- while end < len(suffix):
- ch = suffix[end]
- if u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \
- or ch in u'-;/?:@&=+$,_.~*\'()[]' \
- or (ch == u'!' and handle != u'!'):
- end += 1
- else:
- if start < end:
- chunks.append(suffix[start:end])
- start = end = end+1
- data = ch.encode('utf-8')
- for ch in data:
- chunks.append(u'%%%02X' % ord(ch))
- if start < end:
- chunks.append(suffix[start:end])
- suffix_text = u''.join(chunks)
- if handle:
- return u'%s%s' % (handle, suffix_text)
- else:
- return u'!<%s>' % suffix_text
-
- def prepare_anchor(self, anchor):
- if not anchor:
- raise EmitterError("anchor must not be empty")
- for ch in anchor:
- if not (u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \
- or ch in u'-_'):
- raise EmitterError("invalid character %r in the anchor: %r"
- % (ch.encode('utf-8'), anchor.encode('utf-8')))
- return anchor
-
- def analyze_scalar(self, scalar):
-
- # Empty scalar is a special case.
- if not scalar:
- return ScalarAnalysis(scalar=scalar, empty=True, multiline=False,
- allow_flow_plain=False, allow_block_plain=True,
- allow_single_quoted=True, allow_double_quoted=True,
- allow_block=False)
-
- # Indicators and special characters.
- block_indicators = False
- flow_indicators = False
- line_breaks = False
- special_characters = False
-
- # Important whitespace combinations.
- leading_space = False
- leading_break = False
- trailing_space = False
- trailing_break = False
- break_space = False
- space_break = False
-
- # Check document indicators.
- if scalar.startswith(u'---') or scalar.startswith(u'...'):
- block_indicators = True
- flow_indicators = True
-
- # First character or preceded by a whitespace.
- preceeded_by_whitespace = True
-
- # Last character or followed by a whitespace.
- followed_by_whitespace = (len(scalar) == 1 or
- scalar[1] in u'\0 \t\r\n\x85\u2028\u2029')
-
- # The previous character is a space.
- previous_space = False
-
- # The previous character is a break.
- previous_break = False
-
- index = 0
- while index < len(scalar):
- ch = scalar[index]
-
- # Check for indicators.
- if index == 0:
- # Leading indicators are special characters.
- if ch in u'#,[]{}&*!|>\'\"%@`':
- flow_indicators = True
- block_indicators = True
- if ch in u'?:':
- flow_indicators = True
- if followed_by_whitespace:
- block_indicators = True
- if ch == u'-' and followed_by_whitespace:
- flow_indicators = True
- block_indicators = True
- else:
- # Some indicators cannot appear within a scalar as well.
- if ch in u',?[]{}':
- flow_indicators = True
- if ch == u':':
- flow_indicators = True
- if followed_by_whitespace:
- block_indicators = True
- if ch == u'#' and preceeded_by_whitespace:
- flow_indicators = True
- block_indicators = True
-
- # Check for line breaks, special, and unicode characters.
- if ch in u'\n\x85\u2028\u2029':
- line_breaks = True
- if not (ch == u'\n' or u'\x20' <= ch <= u'\x7E'):
- if (ch == u'\x85' or u'\xA0' <= ch <= u'\uD7FF'
- or u'\uE000' <= ch <= u'\uFFFD') and ch != u'\uFEFF':
- unicode_characters = True
- if not self.allow_unicode:
- special_characters = True
- else:
- special_characters = True
-
- # Detect important whitespace combinations.
- if ch == u' ':
- if index == 0:
- leading_space = True
- if index == len(scalar)-1:
- trailing_space = True
- if previous_break:
- break_space = True
- previous_space = True
- previous_break = False
- elif ch in u'\n\x85\u2028\u2029':
- if index == 0:
- leading_break = True
- if index == len(scalar)-1:
- trailing_break = True
- if previous_space:
- space_break = True
- previous_space = False
- previous_break = True
- else:
- previous_space = False
- previous_break = False
-
- # Prepare for the next character.
- index += 1
- preceeded_by_whitespace = (ch in u'\0 \t\r\n\x85\u2028\u2029')
- followed_by_whitespace = (index+1 >= len(scalar) or
- scalar[index+1] in u'\0 \t\r\n\x85\u2028\u2029')
-
- # Let's decide what styles are allowed.
- allow_flow_plain = True
- allow_block_plain = True
- allow_single_quoted = True
- allow_double_quoted = True
- allow_block = True
-
- # Leading and trailing whitespaces are bad for plain scalars.
- if (leading_space or leading_break
- or trailing_space or trailing_break):
- allow_flow_plain = allow_block_plain = False
-
- # We do not permit trailing spaces for block scalars.
- if trailing_space:
- allow_block = False
-
- # Spaces at the beginning of a new line are only acceptable for block
- # scalars.
- if break_space:
- allow_flow_plain = allow_block_plain = allow_single_quoted = False
-
- # Spaces followed by breaks, as well as special character are only
- # allowed for double quoted scalars.
- if space_break or special_characters:
- allow_flow_plain = allow_block_plain = \
- allow_single_quoted = allow_block = False
-
- # Although the plain scalar writer supports breaks, we never emit
- # multiline plain scalars.
- if line_breaks:
- allow_flow_plain = allow_block_plain = False
-
- # Flow indicators are forbidden for flow plain scalars.
- if flow_indicators:
- allow_flow_plain = False
-
- # Block indicators are forbidden for block plain scalars.
- if block_indicators:
- allow_block_plain = False
-
- return ScalarAnalysis(scalar=scalar,
- empty=False, multiline=line_breaks,
- allow_flow_plain=allow_flow_plain,
- allow_block_plain=allow_block_plain,
- allow_single_quoted=allow_single_quoted,
- allow_double_quoted=allow_double_quoted,
- allow_block=allow_block)
-
- # Writers.
-
- def flush_stream(self):
- if hasattr(self.stream, 'flush'):
- self.stream.flush()
-
- def write_stream_start(self):
- # Write BOM if needed.
- if self.encoding and self.encoding.startswith('utf-16'):
- self.stream.write(u'\uFEFF'.encode(self.encoding))
-
- def write_stream_end(self):
- self.flush_stream()
-
- def write_indicator(self, indicator, need_whitespace,
- whitespace=False, indention=False):
- if self.whitespace or not need_whitespace:
- data = indicator
- else:
- data = u' '+indicator
- self.whitespace = whitespace
- self.indention = self.indention and indention
- self.column += len(data)
- self.open_ended = False
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
-
- def write_indent(self):
- indent = self.indent or 0
- if not self.indention or self.column > indent \
- or (self.column == indent and not self.whitespace):
- self.write_line_break()
- if self.column < indent:
- self.whitespace = True
- data = u' '*(indent-self.column)
- self.column = indent
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
-
- def write_line_break(self, data=None):
- if data is None:
- data = self.best_line_break
- self.whitespace = True
- self.indention = True
- self.line += 1
- self.column = 0
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
-
- def write_version_directive(self, version_text):
- data = u'%%YAML %s' % version_text
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- self.write_line_break()
-
- def write_tag_directive(self, handle_text, prefix_text):
- data = u'%%TAG %s %s' % (handle_text, prefix_text)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- self.write_line_break()
-
- # Scalar streams.
-
- def write_single_quoted(self, text, split=True):
- self.write_indicator(u'\'', True)
- spaces = False
- breaks = False
- start = end = 0
- while end <= len(text):
- ch = None
- if end < len(text):
- ch = text[end]
- if spaces:
- if ch is None or ch != u' ':
- if start+1 == end and self.column > self.best_width and split \
- and start != 0 and end != len(text):
- self.write_indent()
- else:
- data = text[start:end]
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- start = end
- elif breaks:
- if ch is None or ch not in u'\n\x85\u2028\u2029':
- if text[start] == u'\n':
- self.write_line_break()
- for br in text[start:end]:
- if br == u'\n':
- self.write_line_break()
- else:
- self.write_line_break(br)
- self.write_indent()
- start = end
- else:
- if ch is None or ch in u' \n\x85\u2028\u2029' or ch == u'\'':
- if start < end:
- data = text[start:end]
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- start = end
- if ch == u'\'':
- data = u'\'\''
- self.column += 2
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- start = end + 1
- if ch is not None:
- spaces = (ch == u' ')
- breaks = (ch in u'\n\x85\u2028\u2029')
- end += 1
- self.write_indicator(u'\'', False)
-
- ESCAPE_REPLACEMENTS = {
- u'\0': u'0',
- u'\x07': u'a',
- u'\x08': u'b',
- u'\x09': u't',
- u'\x0A': u'n',
- u'\x0B': u'v',
- u'\x0C': u'f',
- u'\x0D': u'r',
- u'\x1B': u'e',
- u'\"': u'\"',
- u'\\': u'\\',
- u'\x85': u'N',
- u'\xA0': u'_',
- u'\u2028': u'L',
- u'\u2029': u'P',
- }
-
- def write_double_quoted(self, text, split=True):
- self.write_indicator(u'"', True)
- start = end = 0
- while end <= len(text):
- ch = None
- if end < len(text):
- ch = text[end]
- if ch is None or ch in u'"\\\x85\u2028\u2029\uFEFF' \
- or not (u'\x20' <= ch <= u'\x7E'
- or (self.allow_unicode
- and (u'\xA0' <= ch <= u'\uD7FF'
- or u'\uE000' <= ch <= u'\uFFFD'))):
- if start < end:
- data = text[start:end]
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- start = end
- if ch is not None:
- if ch in self.ESCAPE_REPLACEMENTS:
- data = u'\\'+self.ESCAPE_REPLACEMENTS[ch]
- elif ch <= u'\xFF':
- data = u'\\x%02X' % ord(ch)
- elif ch <= u'\uFFFF':
- data = u'\\u%04X' % ord(ch)
- else:
- data = u'\\U%08X' % ord(ch)
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- start = end+1
- if 0 < end < len(text)-1 and (ch == u' ' or start >= end) \
- and self.column+(end-start) > self.best_width and split:
- data = text[start:end]+u'\\'
- if start < end:
- start = end
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- self.write_indent()
- self.whitespace = False
- self.indention = False
- if text[start] == u' ':
- data = u'\\'
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- end += 1
- self.write_indicator(u'"', False)
-
- def determine_block_hints(self, text):
- hints = u''
- if text:
- if text[0] in u' \n\x85\u2028\u2029':
- hints += unicode(self.best_indent)
- if text[-1] not in u'\n\x85\u2028\u2029':
- hints += u'-'
- elif len(text) == 1 or text[-2] in u'\n\x85\u2028\u2029':
- hints += u'+'
- return hints
-
- def write_folded(self, text):
- hints = self.determine_block_hints(text)
- self.write_indicator(u'>'+hints, True)
- if hints[-1:] == u'+':
- self.open_ended = True
- self.write_line_break()
- leading_space = True
- spaces = False
- breaks = True
- start = end = 0
- while end <= len(text):
- ch = None
- if end < len(text):
- ch = text[end]
- if breaks:
- if ch is None or ch not in u'\n\x85\u2028\u2029':
- if not leading_space and ch is not None and ch != u' ' \
- and text[start] == u'\n':
- self.write_line_break()
- leading_space = (ch == u' ')
- for br in text[start:end]:
- if br == u'\n':
- self.write_line_break()
- else:
- self.write_line_break(br)
- if ch is not None:
- self.write_indent()
- start = end
- elif spaces:
- if ch != u' ':
- if start+1 == end and self.column > self.best_width:
- self.write_indent()
- else:
- data = text[start:end]
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- start = end
- else:
- if ch is None or ch in u' \n\x85\u2028\u2029':
- data = text[start:end]
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- if ch is None:
- self.write_line_break()
- start = end
- if ch is not None:
- breaks = (ch in u'\n\x85\u2028\u2029')
- spaces = (ch == u' ')
- end += 1
-
- def write_literal(self, text):
- hints = self.determine_block_hints(text)
- self.write_indicator(u'|'+hints, True)
- if hints[-1:] == u'+':
- self.open_ended = True
- self.write_line_break()
- breaks = True
- start = end = 0
- while end <= len(text):
- ch = None
- if end < len(text):
- ch = text[end]
- if breaks:
- if ch is None or ch not in u'\n\x85\u2028\u2029':
- for br in text[start:end]:
- if br == u'\n':
- self.write_line_break()
- else:
- self.write_line_break(br)
- if ch is not None:
- self.write_indent()
- start = end
- else:
- if ch is None or ch in u'\n\x85\u2028\u2029':
- data = text[start:end]
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- if ch is None:
- self.write_line_break()
- start = end
- if ch is not None:
- breaks = (ch in u'\n\x85\u2028\u2029')
- end += 1
-
- def write_plain(self, text, split=True):
- if self.root_context:
- self.open_ended = True
- if not text:
- return
- if not self.whitespace:
- data = u' '
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- self.whitespace = False
- self.indention = False
- spaces = False
- breaks = False
- start = end = 0
- while end <= len(text):
- ch = None
- if end < len(text):
- ch = text[end]
- if spaces:
- if ch != u' ':
- if start+1 == end and self.column > self.best_width and split:
- self.write_indent()
- self.whitespace = False
- self.indention = False
- else:
- data = text[start:end]
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- start = end
- elif breaks:
- if ch not in u'\n\x85\u2028\u2029':
- if text[start] == u'\n':
- self.write_line_break()
- for br in text[start:end]:
- if br == u'\n':
- self.write_line_break()
- else:
- self.write_line_break(br)
- self.write_indent()
- self.whitespace = False
- self.indention = False
- start = end
- else:
- if ch is None or ch in u' \n\x85\u2028\u2029':
- data = text[start:end]
- self.column += len(data)
- if self.encoding:
- data = data.encode(self.encoding)
- self.stream.write(data)
- start = end
- if ch is not None:
- spaces = (ch == u' ')
- breaks = (ch in u'\n\x85\u2028\u2029')
- end += 1
-
diff --git a/tablib/packages/yaml/error.py b/tablib/packages/yaml/error.py
deleted file mode 100644
index 577686d..0000000
--- a/tablib/packages/yaml/error.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/yaml/events.py b/tablib/packages/yaml/events.py
deleted file mode 100644
index f79ad38..0000000
--- a/tablib/packages/yaml/events.py
+++ /dev/null
@@ -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
-
diff --git a/tablib/packages/yaml/loader.py b/tablib/packages/yaml/loader.py
deleted file mode 100644
index 293ff46..0000000
--- a/tablib/packages/yaml/loader.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/yaml/nodes.py b/tablib/packages/yaml/nodes.py
deleted file mode 100644
index c4f070c..0000000
--- a/tablib/packages/yaml/nodes.py
+++ /dev/null
@@ -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'
-
diff --git a/tablib/packages/yaml/parser.py b/tablib/packages/yaml/parser.py
deleted file mode 100644
index b6a7416..0000000
--- a/tablib/packages/yaml/parser.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/yaml/reader.py b/tablib/packages/yaml/reader.py
deleted file mode 100644
index 1e7a4db..0000000
--- a/tablib/packages/yaml/reader.py
+++ /dev/null
@@ -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
-
diff --git a/tablib/packages/yaml/representer.py b/tablib/packages/yaml/representer.py
deleted file mode 100644
index f5606ec..0000000
--- a/tablib/packages/yaml/representer.py
+++ /dev/null
@@ -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)
-
diff --git a/tablib/packages/yaml/resolver.py b/tablib/packages/yaml/resolver.py
deleted file mode 100644
index 6b5ab87..0000000
--- a/tablib/packages/yaml/resolver.py
+++ /dev/null
@@ -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'!&*'))
-
diff --git a/tablib/packages/yaml/scanner.py b/tablib/packages/yaml/scanner.py
deleted file mode 100644
index 5228fad..0000000
--- a/tablib/packages/yaml/scanner.py
+++ /dev/null
@@ -1,1457 +0,0 @@
-
-# Scanner produces tokens of the following types:
-# STREAM-START
-# STREAM-END
-# DIRECTIVE(name, value)
-# DOCUMENT-START
-# DOCUMENT-END
-# BLOCK-SEQUENCE-START
-# BLOCK-MAPPING-START
-# BLOCK-END
-# FLOW-SEQUENCE-START
-# FLOW-MAPPING-START
-# FLOW-SEQUENCE-END
-# FLOW-MAPPING-END
-# BLOCK-ENTRY
-# FLOW-ENTRY
-# KEY
-# VALUE
-# ALIAS(value)
-# ANCHOR(value)
-# TAG(value)
-# SCALAR(value, plain, style)
-#
-# Read comments in the Scanner code for more details.
-#
-
-__all__ = ['Scanner', 'ScannerError']
-
-from error import MarkedYAMLError
-from tokens import *
-
-class ScannerError(MarkedYAMLError):
- pass
-
-class SimpleKey(object):
- # See below simple keys treatment.
-
- def __init__(self, token_number, required, index, line, column, mark):
- self.token_number = token_number
- self.required = required
- self.index = index
- self.line = line
- self.column = column
- self.mark = mark
-
-class Scanner(object):
-
- def __init__(self):
- """Initialize the scanner."""
- # It is assumed that Scanner and Reader will have a common descendant.
- # Reader do the dirty work of checking for BOM and converting the
- # input data to Unicode. It also adds NUL to the end.
- #
- # Reader supports the following methods
- # self.peek(i=0) # peek the next i-th character
- # self.prefix(l=1) # peek the next l characters
- # self.forward(l=1) # read the next l characters and move the pointer.
-
- # Had we reached the end of the stream?
- self.done = False
-
- # The number of unclosed '{' and '['. `flow_level == 0` means block
- # context.
- self.flow_level = 0
-
- # List of processed tokens that are not yet emitted.
- self.tokens = []
-
- # Add the STREAM-START token.
- self.fetch_stream_start()
-
- # Number of tokens that were emitted through the `get_token` method.
- self.tokens_taken = 0
-
- # The current indentation level.
- self.indent = -1
-
- # Past indentation levels.
- self.indents = []
-
- # Variables related to simple keys treatment.
-
- # A simple key is a key that is not denoted by the '?' indicator.
- # Example of simple keys:
- # ---
- # block simple key: value
- # ? not a simple key:
- # : { flow simple key: value }
- # We emit the KEY token before all keys, so when we find a potential
- # simple key, we try to locate the corresponding ':' indicator.
- # Simple keys should be limited to a single line and 1024 characters.
-
- # Can a simple key start at the current position? A simple key may
- # start:
- # - at the beginning of the line, not counting indentation spaces
- # (in block context),
- # - after '{', '[', ',' (in the flow context),
- # - after '?', ':', '-' (in the block context).
- # In the block context, this flag also signifies if a block collection
- # may start at the current position.
- self.allow_simple_key = True
-
- # Keep track of possible simple keys. This is a dictionary. The key
- # is `flow_level`; there can be no more that one possible simple key
- # for each level. The value is a SimpleKey record:
- # (token_number, required, index, line, column, mark)
- # A simple key may start with ALIAS, ANCHOR, TAG, SCALAR(flow),
- # '[', or '{' tokens.
- self.possible_simple_keys = {}
-
- # Public methods.
-
- def check_token(self, *choices):
- # Check if the next token is one of the given types.
- while self.need_more_tokens():
- self.fetch_more_tokens()
- if self.tokens:
- if not choices:
- return True
- for choice in choices:
- if isinstance(self.tokens[0], choice):
- return True
- return False
-
- def peek_token(self):
- # Return the next token, but do not delete if from the queue.
- while self.need_more_tokens():
- self.fetch_more_tokens()
- if self.tokens:
- return self.tokens[0]
-
- def get_token(self):
- # Return the next token.
- while self.need_more_tokens():
- self.fetch_more_tokens()
- if self.tokens:
- self.tokens_taken += 1
- return self.tokens.pop(0)
-
- # Private methods.
-
- def need_more_tokens(self):
- if self.done:
- return False
- if not self.tokens:
- return True
- # The current token may be a potential simple key, so we
- # need to look further.
- self.stale_possible_simple_keys()
- if self.next_possible_simple_key() == self.tokens_taken:
- return True
-
- def fetch_more_tokens(self):
-
- # Eat whitespaces and comments until we reach the next token.
- self.scan_to_next_token()
-
- # Remove obsolete possible simple keys.
- self.stale_possible_simple_keys()
-
- # Compare the current indentation and column. It may add some tokens
- # and decrease the current indentation level.
- self.unwind_indent(self.column)
-
- # Peek the next character.
- ch = self.peek()
-
- # Is it the end of stream?
- if ch == u'\0':
- return self.fetch_stream_end()
-
- # Is it a directive?
- if ch == u'%' and self.check_directive():
- return self.fetch_directive()
-
- # Is it the document start?
- if ch == u'-' and self.check_document_start():
- return self.fetch_document_start()
-
- # Is it the document end?
- if ch == u'.' and self.check_document_end():
- return self.fetch_document_end()
-
- # TODO: support for BOM within a stream.
- #if ch == u'\uFEFF':
- # return self.fetch_bom() <-- issue BOMToken
-
- # Note: the order of the following checks is NOT significant.
-
- # Is it the flow sequence start indicator?
- if ch == u'[':
- return self.fetch_flow_sequence_start()
-
- # Is it the flow mapping start indicator?
- if ch == u'{':
- return self.fetch_flow_mapping_start()
-
- # Is it the flow sequence end indicator?
- if ch == u']':
- return self.fetch_flow_sequence_end()
-
- # Is it the flow mapping end indicator?
- if ch == u'}':
- return self.fetch_flow_mapping_end()
-
- # Is it the flow entry indicator?
- if ch == u',':
- return self.fetch_flow_entry()
-
- # Is it the block entry indicator?
- if ch == u'-' and self.check_block_entry():
- return self.fetch_block_entry()
-
- # Is it the key indicator?
- if ch == u'?' and self.check_key():
- return self.fetch_key()
-
- # Is it the value indicator?
- if ch == u':' and self.check_value():
- return self.fetch_value()
-
- # Is it an alias?
- if ch == u'*':
- return self.fetch_alias()
-
- # Is it an anchor?
- if ch == u'&':
- return self.fetch_anchor()
-
- # Is it a tag?
- if ch == u'!':
- return self.fetch_tag()
-
- # Is it a literal scalar?
- if ch == u'|' and not self.flow_level:
- return self.fetch_literal()
-
- # Is it a folded scalar?
- if ch == u'>' and not self.flow_level:
- return self.fetch_folded()
-
- # Is it a single quoted scalar?
- if ch == u'\'':
- return self.fetch_single()
-
- # Is it a double quoted scalar?
- if ch == u'\"':
- return self.fetch_double()
-
- # It must be a plain scalar then.
- if self.check_plain():
- return self.fetch_plain()
-
- # No? It's an error. Let's produce a nice error message.
- raise ScannerError("while scanning for the next token", None,
- "found character %r that cannot start any token"
- % ch.encode('utf-8'), self.get_mark())
-
- # Simple keys treatment.
-
- def next_possible_simple_key(self):
- # Return the number of the nearest possible simple key. Actually we
- # don't need to loop through the whole dictionary. We may replace it
- # with the following code:
- # if not self.possible_simple_keys:
- # return None
- # return self.possible_simple_keys[
- # min(self.possible_simple_keys.keys())].token_number
- min_token_number = None
- for level in self.possible_simple_keys:
- key = self.possible_simple_keys[level]
- if min_token_number is None or key.token_number < min_token_number:
- min_token_number = key.token_number
- return min_token_number
-
- def stale_possible_simple_keys(self):
- # Remove entries that are no longer possible simple keys. According to
- # the YAML specification, simple keys
- # - should be limited to a single line,
- # - should be no longer than 1024 characters.
- # Disabling this procedure will allow simple keys of any length and
- # height (may cause problems if indentation is broken though).
- for level in self.possible_simple_keys.keys():
- key = self.possible_simple_keys[level]
- if key.line != self.line \
- or self.index-key.index > 1024:
- if key.required:
- raise ScannerError("while scanning a simple key", key.mark,
- "could not found expected ':'", self.get_mark())
- del self.possible_simple_keys[level]
-
- def save_possible_simple_key(self):
- # The next token may start a simple key. We check if it's possible
- # and save its position. This function is called for
- # ALIAS, ANCHOR, TAG, SCALAR(flow), '[', and '{'.
-
- # Check if a simple key is required at the current position.
- required = not self.flow_level and self.indent == self.column
-
- # A simple key is required only if it is the first token in the current
- # line. Therefore it is always allowed.
- assert self.allow_simple_key or not required
-
- # The next token might be a simple key. Let's save it's number and
- # position.
- if self.allow_simple_key:
- self.remove_possible_simple_key()
- token_number = self.tokens_taken+len(self.tokens)
- key = SimpleKey(token_number, required,
- self.index, self.line, self.column, self.get_mark())
- self.possible_simple_keys[self.flow_level] = key
-
- def remove_possible_simple_key(self):
- # Remove the saved possible key position at the current flow level.
- if self.flow_level in self.possible_simple_keys:
- key = self.possible_simple_keys[self.flow_level]
-
- if key.required:
- raise ScannerError("while scanning a simple key", key.mark,
- "could not found expected ':'", self.get_mark())
-
- del self.possible_simple_keys[self.flow_level]
-
- # Indentation functions.
-
- def unwind_indent(self, column):
-
- ## In flow context, tokens should respect indentation.
- ## Actually the condition should be `self.indent >= column` according to
- ## the spec. But this condition will prohibit intuitively correct
- ## constructions such as
- ## key : {
- ## }
- #if self.flow_level and self.indent > column:
- # raise ScannerError(None, None,
- # "invalid intendation or unclosed '[' or '{'",
- # self.get_mark())
-
- # In the flow context, indentation is ignored. We make the scanner less
- # restrictive then specification requires.
- if self.flow_level:
- return
-
- # In block context, we may need to issue the BLOCK-END tokens.
- while self.indent > column:
- mark = self.get_mark()
- self.indent = self.indents.pop()
- self.tokens.append(BlockEndToken(mark, mark))
-
- def add_indent(self, column):
- # Check if we need to increase indentation.
- if self.indent < column:
- self.indents.append(self.indent)
- self.indent = column
- return True
- return False
-
- # Fetchers.
-
- def fetch_stream_start(self):
- # We always add STREAM-START as the first token and STREAM-END as the
- # last token.
-
- # Read the token.
- mark = self.get_mark()
-
- # Add STREAM-START.
- self.tokens.append(StreamStartToken(mark, mark,
- encoding=self.encoding))
-
-
- def fetch_stream_end(self):
-
- # Set the current intendation to -1.
- self.unwind_indent(-1)
-
- # Reset simple keys.
- self.remove_possible_simple_key()
- self.allow_simple_key = False
- self.possible_simple_keys = {}
-
- # Read the token.
- mark = self.get_mark()
-
- # Add STREAM-END.
- self.tokens.append(StreamEndToken(mark, mark))
-
- # The steam is finished.
- self.done = True
-
- def fetch_directive(self):
-
- # Set the current intendation to -1.
- self.unwind_indent(-1)
-
- # Reset simple keys.
- self.remove_possible_simple_key()
- self.allow_simple_key = False
-
- # Scan and add DIRECTIVE.
- self.tokens.append(self.scan_directive())
-
- def fetch_document_start(self):
- self.fetch_document_indicator(DocumentStartToken)
-
- def fetch_document_end(self):
- self.fetch_document_indicator(DocumentEndToken)
-
- def fetch_document_indicator(self, TokenClass):
-
- # Set the current intendation to -1.
- self.unwind_indent(-1)
-
- # Reset simple keys. Note that there could not be a block collection
- # after '---'.
- self.remove_possible_simple_key()
- self.allow_simple_key = False
-
- # Add DOCUMENT-START or DOCUMENT-END.
- start_mark = self.get_mark()
- self.forward(3)
- end_mark = self.get_mark()
- self.tokens.append(TokenClass(start_mark, end_mark))
-
- def fetch_flow_sequence_start(self):
- self.fetch_flow_collection_start(FlowSequenceStartToken)
-
- def fetch_flow_mapping_start(self):
- self.fetch_flow_collection_start(FlowMappingStartToken)
-
- def fetch_flow_collection_start(self, TokenClass):
-
- # '[' and '{' may start a simple key.
- self.save_possible_simple_key()
-
- # Increase the flow level.
- self.flow_level += 1
-
- # Simple keys are allowed after '[' and '{'.
- self.allow_simple_key = True
-
- # Add FLOW-SEQUENCE-START or FLOW-MAPPING-START.
- start_mark = self.get_mark()
- self.forward()
- end_mark = self.get_mark()
- self.tokens.append(TokenClass(start_mark, end_mark))
-
- def fetch_flow_sequence_end(self):
- self.fetch_flow_collection_end(FlowSequenceEndToken)
-
- def fetch_flow_mapping_end(self):
- self.fetch_flow_collection_end(FlowMappingEndToken)
-
- def fetch_flow_collection_end(self, TokenClass):
-
- # Reset possible simple key on the current level.
- self.remove_possible_simple_key()
-
- # Decrease the flow level.
- self.flow_level -= 1
-
- # No simple keys after ']' or '}'.
- self.allow_simple_key = False
-
- # Add FLOW-SEQUENCE-END or FLOW-MAPPING-END.
- start_mark = self.get_mark()
- self.forward()
- end_mark = self.get_mark()
- self.tokens.append(TokenClass(start_mark, end_mark))
-
- def fetch_flow_entry(self):
-
- # Simple keys are allowed after ','.
- self.allow_simple_key = True
-
- # Reset possible simple key on the current level.
- self.remove_possible_simple_key()
-
- # Add FLOW-ENTRY.
- start_mark = self.get_mark()
- self.forward()
- end_mark = self.get_mark()
- self.tokens.append(FlowEntryToken(start_mark, end_mark))
-
- def fetch_block_entry(self):
-
- # Block context needs additional checks.
- if not self.flow_level:
-
- # Are we allowed to start a new entry?
- if not self.allow_simple_key:
- raise ScannerError(None, None,
- "sequence entries are not allowed here",
- self.get_mark())
-
- # We may need to add BLOCK-SEQUENCE-START.
- if self.add_indent(self.column):
- mark = self.get_mark()
- self.tokens.append(BlockSequenceStartToken(mark, mark))
-
- # It's an error for the block entry to occur in the flow context,
- # but we let the parser detect this.
- else:
- pass
-
- # Simple keys are allowed after '-'.
- self.allow_simple_key = True
-
- # Reset possible simple key on the current level.
- self.remove_possible_simple_key()
-
- # Add BLOCK-ENTRY.
- start_mark = self.get_mark()
- self.forward()
- end_mark = self.get_mark()
- self.tokens.append(BlockEntryToken(start_mark, end_mark))
-
- def fetch_key(self):
-
- # Block context needs additional checks.
- if not self.flow_level:
-
- # Are we allowed to start a key (not nessesary a simple)?
- if not self.allow_simple_key:
- raise ScannerError(None, None,
- "mapping keys are not allowed here",
- self.get_mark())
-
- # We may need to add BLOCK-MAPPING-START.
- if self.add_indent(self.column):
- mark = self.get_mark()
- self.tokens.append(BlockMappingStartToken(mark, mark))
-
- # Simple keys are allowed after '?' in the block context.
- self.allow_simple_key = not self.flow_level
-
- # Reset possible simple key on the current level.
- self.remove_possible_simple_key()
-
- # Add KEY.
- start_mark = self.get_mark()
- self.forward()
- end_mark = self.get_mark()
- self.tokens.append(KeyToken(start_mark, end_mark))
-
- def fetch_value(self):
-
- # Do we determine a simple key?
- if self.flow_level in self.possible_simple_keys:
-
- # Add KEY.
- key = self.possible_simple_keys[self.flow_level]
- del self.possible_simple_keys[self.flow_level]
- self.tokens.insert(key.token_number-self.tokens_taken,
- KeyToken(key.mark, key.mark))
-
- # If this key starts a new block mapping, we need to add
- # BLOCK-MAPPING-START.
- if not self.flow_level:
- if self.add_indent(key.column):
- self.tokens.insert(key.token_number-self.tokens_taken,
- BlockMappingStartToken(key.mark, key.mark))
-
- # There cannot be two simple keys one after another.
- self.allow_simple_key = False
-
- # It must be a part of a complex key.
- else:
-
- # Block context needs additional checks.
- # (Do we really need them? They will be catched by the parser
- # anyway.)
- if not self.flow_level:
-
- # We are allowed to start a complex value if and only if
- # we can start a simple key.
- if not self.allow_simple_key:
- raise ScannerError(None, None,
- "mapping values are not allowed here",
- self.get_mark())
-
- # If this value starts a new block mapping, we need to add
- # BLOCK-MAPPING-START. It will be detected as an error later by
- # the parser.
- if not self.flow_level:
- if self.add_indent(self.column):
- mark = self.get_mark()
- self.tokens.append(BlockMappingStartToken(mark, mark))
-
- # Simple keys are allowed after ':' in the block context.
- self.allow_simple_key = not self.flow_level
-
- # Reset possible simple key on the current level.
- self.remove_possible_simple_key()
-
- # Add VALUE.
- start_mark = self.get_mark()
- self.forward()
- end_mark = self.get_mark()
- self.tokens.append(ValueToken(start_mark, end_mark))
-
- def fetch_alias(self):
-
- # ALIAS could be a simple key.
- self.save_possible_simple_key()
-
- # No simple keys after ALIAS.
- self.allow_simple_key = False
-
- # Scan and add ALIAS.
- self.tokens.append(self.scan_anchor(AliasToken))
-
- def fetch_anchor(self):
-
- # ANCHOR could start a simple key.
- self.save_possible_simple_key()
-
- # No simple keys after ANCHOR.
- self.allow_simple_key = False
-
- # Scan and add ANCHOR.
- self.tokens.append(self.scan_anchor(AnchorToken))
-
- def fetch_tag(self):
-
- # TAG could start a simple key.
- self.save_possible_simple_key()
-
- # No simple keys after TAG.
- self.allow_simple_key = False
-
- # Scan and add TAG.
- self.tokens.append(self.scan_tag())
-
- def fetch_literal(self):
- self.fetch_block_scalar(style='|')
-
- def fetch_folded(self):
- self.fetch_block_scalar(style='>')
-
- def fetch_block_scalar(self, style):
-
- # A simple key may follow a block scalar.
- self.allow_simple_key = True
-
- # Reset possible simple key on the current level.
- self.remove_possible_simple_key()
-
- # Scan and add SCALAR.
- self.tokens.append(self.scan_block_scalar(style))
-
- def fetch_single(self):
- self.fetch_flow_scalar(style='\'')
-
- def fetch_double(self):
- self.fetch_flow_scalar(style='"')
-
- def fetch_flow_scalar(self, style):
-
- # A flow scalar could be a simple key.
- self.save_possible_simple_key()
-
- # No simple keys after flow scalars.
- self.allow_simple_key = False
-
- # Scan and add SCALAR.
- self.tokens.append(self.scan_flow_scalar(style))
-
- def fetch_plain(self):
-
- # A plain scalar could be a simple key.
- self.save_possible_simple_key()
-
- # No simple keys after plain scalars. But note that `scan_plain` will
- # change this flag if the scan is finished at the beginning of the
- # line.
- self.allow_simple_key = False
-
- # Scan and add SCALAR. May change `allow_simple_key`.
- self.tokens.append(self.scan_plain())
-
- # Checkers.
-
- def check_directive(self):
-
- # DIRECTIVE: ^ '%' ...
- # The '%' indicator is already checked.
- if self.column == 0:
- return True
-
- def check_document_start(self):
-
- # DOCUMENT-START: ^ '---' (' '|'\n')
- if self.column == 0:
- if self.prefix(3) == u'---' \
- and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029':
- return True
-
- def check_document_end(self):
-
- # DOCUMENT-END: ^ '...' (' '|'\n')
- if self.column == 0:
- if self.prefix(3) == u'...' \
- and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029':
- return True
-
- def check_block_entry(self):
-
- # BLOCK-ENTRY: '-' (' '|'\n')
- return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029'
-
- def check_key(self):
-
- # KEY(flow context): '?'
- if self.flow_level:
- return True
-
- # KEY(block context): '?' (' '|'\n')
- else:
- return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029'
-
- def check_value(self):
-
- # VALUE(flow context): ':'
- if self.flow_level:
- return True
-
- # VALUE(block context): ':' (' '|'\n')
- else:
- return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029'
-
- def check_plain(self):
-
- # A plain scalar may start with any non-space character except:
- # '-', '?', ':', ',', '[', ']', '{', '}',
- # '#', '&', '*', '!', '|', '>', '\'', '\"',
- # '%', '@', '`'.
- #
- # It may also start with
- # '-', '?', ':'
- # if it is followed by a non-space character.
- #
- # Note that we limit the last rule to the block context (except the
- # '-' character) because we want the flow context to be space
- # independent.
- ch = self.peek()
- return ch not in u'\0 \t\r\n\x85\u2028\u2029-?:,[]{}#&*!|>\'\"%@`' \
- or (self.peek(1) not in u'\0 \t\r\n\x85\u2028\u2029'
- and (ch == u'-' or (not self.flow_level and ch in u'?:')))
-
- # Scanners.
-
- def scan_to_next_token(self):
- # We ignore spaces, line breaks and comments.
- # If we find a line break in the block context, we set the flag
- # `allow_simple_key` on.
- # The byte order mark is stripped if it's the first character in the
- # stream. We do not yet support BOM inside the stream as the
- # specification requires. Any such mark will be considered as a part
- # of the document.
- #
- # TODO: We need to make tab handling rules more sane. A good rule is
- # Tabs cannot precede tokens
- # BLOCK-SEQUENCE-START, BLOCK-MAPPING-START, BLOCK-END,
- # KEY(block), VALUE(block), BLOCK-ENTRY
- # So the checking code is
- # if <TAB>:
- # self.allow_simple_keys = False
- # We also need to add the check for `allow_simple_keys == True` to
- # `unwind_indent` before issuing BLOCK-END.
- # Scanners for block, flow, and plain scalars need to be modified.
-
- if self.index == 0 and self.peek() == u'\uFEFF':
- self.forward()
- found = False
- while not found:
- while self.peek() == u' ':
- self.forward()
- if self.peek() == u'#':
- while self.peek() not in u'\0\r\n\x85\u2028\u2029':
- self.forward()
- if self.scan_line_break():
- if not self.flow_level:
- self.allow_simple_key = True
- else:
- found = True
-
- def scan_directive(self):
- # See the specification for details.
- start_mark = self.get_mark()
- self.forward()
- name = self.scan_directive_name(start_mark)
- value = None
- if name == u'YAML':
- value = self.scan_yaml_directive_value(start_mark)
- end_mark = self.get_mark()
- elif name == u'TAG':
- value = self.scan_tag_directive_value(start_mark)
- end_mark = self.get_mark()
- else:
- end_mark = self.get_mark()
- while self.peek() not in u'\0\r\n\x85\u2028\u2029':
- self.forward()
- self.scan_directive_ignored_line(start_mark)
- return DirectiveToken(name, value, start_mark, end_mark)
-
- def scan_directive_name(self, start_mark):
- # See the specification for details.
- length = 0
- ch = self.peek(length)
- while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \
- or ch in u'-_':
- length += 1
- ch = self.peek(length)
- if not length:
- raise ScannerError("while scanning a directive", start_mark,
- "expected alphabetic or numeric character, but found %r"
- % ch.encode('utf-8'), self.get_mark())
- value = self.prefix(length)
- self.forward(length)
- ch = self.peek()
- if ch not in u'\0 \r\n\x85\u2028\u2029':
- raise ScannerError("while scanning a directive", start_mark,
- "expected alphabetic or numeric character, but found %r"
- % ch.encode('utf-8'), self.get_mark())
- return value
-
- def scan_yaml_directive_value(self, start_mark):
- # See the specification for details.
- while self.peek() == u' ':
- self.forward()
- major = self.scan_yaml_directive_number(start_mark)
- if self.peek() != '.':
- raise ScannerError("while scanning a directive", start_mark,
- "expected a digit or '.', but found %r"
- % self.peek().encode('utf-8'),
- self.get_mark())
- self.forward()
- minor = self.scan_yaml_directive_number(start_mark)
- if self.peek() not in u'\0 \r\n\x85\u2028\u2029':
- raise ScannerError("while scanning a directive", start_mark,
- "expected a digit or ' ', but found %r"
- % self.peek().encode('utf-8'),
- self.get_mark())
- return (major, minor)
-
- def scan_yaml_directive_number(self, start_mark):
- # See the specification for details.
- ch = self.peek()
- if not (u'0' <= ch <= u'9'):
- raise ScannerError("while scanning a directive", start_mark,
- "expected a digit, but found %r" % ch.encode('utf-8'),
- self.get_mark())
- length = 0
- while u'0' <= self.peek(length) <= u'9':
- length += 1
- value = int(self.prefix(length))
- self.forward(length)
- return value
-
- def scan_tag_directive_value(self, start_mark):
- # See the specification for details.
- while self.peek() == u' ':
- self.forward()
- handle = self.scan_tag_directive_handle(start_mark)
- while self.peek() == u' ':
- self.forward()
- prefix = self.scan_tag_directive_prefix(start_mark)
- return (handle, prefix)
-
- def scan_tag_directive_handle(self, start_mark):
- # See the specification for details.
- value = self.scan_tag_handle('directive', start_mark)
- ch = self.peek()
- if ch != u' ':
- raise ScannerError("while scanning a directive", start_mark,
- "expected ' ', but found %r" % ch.encode('utf-8'),
- self.get_mark())
- return value
-
- def scan_tag_directive_prefix(self, start_mark):
- # See the specification for details.
- value = self.scan_tag_uri('directive', start_mark)
- ch = self.peek()
- if ch not in u'\0 \r\n\x85\u2028\u2029':
- raise ScannerError("while scanning a directive", start_mark,
- "expected ' ', but found %r" % ch.encode('utf-8'),
- self.get_mark())
- return value
-
- def scan_directive_ignored_line(self, start_mark):
- # See the specification for details.
- while self.peek() == u' ':
- self.forward()
- if self.peek() == u'#':
- while self.peek() not in u'\0\r\n\x85\u2028\u2029':
- self.forward()
- ch = self.peek()
- if ch not in u'\0\r\n\x85\u2028\u2029':
- raise ScannerError("while scanning a directive", start_mark,
- "expected a comment or a line break, but found %r"
- % ch.encode('utf-8'), self.get_mark())
- self.scan_line_break()
-
- def scan_anchor(self, TokenClass):
- # The specification does not restrict characters for anchors and
- # aliases. This may lead to problems, for instance, the document:
- # [ *alias, value ]
- # can be interpteted in two ways, as
- # [ "value" ]
- # and
- # [ *alias , "value" ]
- # Therefore we restrict aliases to numbers and ASCII letters.
- start_mark = self.get_mark()
- indicator = self.peek()
- if indicator == u'*':
- name = 'alias'
- else:
- name = 'anchor'
- self.forward()
- length = 0
- ch = self.peek(length)
- while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \
- or ch in u'-_':
- length += 1
- ch = self.peek(length)
- if not length:
- raise ScannerError("while scanning an %s" % name, start_mark,
- "expected alphabetic or numeric character, but found %r"
- % ch.encode('utf-8'), self.get_mark())
- value = self.prefix(length)
- self.forward(length)
- ch = self.peek()
- if ch not in u'\0 \t\r\n\x85\u2028\u2029?:,]}%@`':
- raise ScannerError("while scanning an %s" % name, start_mark,
- "expected alphabetic or numeric character, but found %r"
- % ch.encode('utf-8'), self.get_mark())
- end_mark = self.get_mark()
- return TokenClass(value, start_mark, end_mark)
-
- def scan_tag(self):
- # See the specification for details.
- start_mark = self.get_mark()
- ch = self.peek(1)
- if ch == u'<':
- handle = None
- self.forward(2)
- suffix = self.scan_tag_uri('tag', start_mark)
- if self.peek() != u'>':
- raise ScannerError("while parsing a tag", start_mark,
- "expected '>', but found %r" % self.peek().encode('utf-8'),
- self.get_mark())
- self.forward()
- elif ch in u'\0 \t\r\n\x85\u2028\u2029':
- handle = None
- suffix = u'!'
- self.forward()
- else:
- length = 1
- use_handle = False
- while ch not in u'\0 \r\n\x85\u2028\u2029':
- if ch == u'!':
- use_handle = True
- break
- length += 1
- ch = self.peek(length)
- handle = u'!'
- if use_handle:
- handle = self.scan_tag_handle('tag', start_mark)
- else:
- handle = u'!'
- self.forward()
- suffix = self.scan_tag_uri('tag', start_mark)
- ch = self.peek()
- if ch not in u'\0 \r\n\x85\u2028\u2029':
- raise ScannerError("while scanning a tag", start_mark,
- "expected ' ', but found %r" % ch.encode('utf-8'),
- self.get_mark())
- value = (handle, suffix)
- end_mark = self.get_mark()
- return TagToken(value, start_mark, end_mark)
-
- def scan_block_scalar(self, style):
- # See the specification for details.
-
- if style == '>':
- folded = True
- else:
- folded = False
-
- chunks = []
- start_mark = self.get_mark()
-
- # Scan the header.
- self.forward()
- chomping, increment = self.scan_block_scalar_indicators(start_mark)
- self.scan_block_scalar_ignored_line(start_mark)
-
- # Determine the indentation level and go to the first non-empty line.
- min_indent = self.indent+1
- if min_indent < 1:
- min_indent = 1
- if increment is None:
- breaks, max_indent, end_mark = self.scan_block_scalar_indentation()
- indent = max(min_indent, max_indent)
- else:
- indent = min_indent+increment-1
- breaks, end_mark = self.scan_block_scalar_breaks(indent)
- line_break = u''
-
- # Scan the inner part of the block scalar.
- while self.column == indent and self.peek() != u'\0':
- chunks.extend(breaks)
- leading_non_space = self.peek() not in u' \t'
- length = 0
- while self.peek(length) not in u'\0\r\n\x85\u2028\u2029':
- length += 1
- chunks.append(self.prefix(length))
- self.forward(length)
- line_break = self.scan_line_break()
- breaks, end_mark = self.scan_block_scalar_breaks(indent)
- if self.column == indent and self.peek() != u'\0':
-
- # Unfortunately, folding rules are ambiguous.
- #
- # This is the folding according to the specification:
-
- if folded and line_break == u'\n' \
- and leading_non_space and self.peek() not in u' \t':
- if not breaks:
- chunks.append(u' ')
- else:
- chunks.append(line_break)
-
- # This is Clark Evans's interpretation (also in the spec
- # examples):
- #
- #if folded and line_break == u'\n':
- # if not breaks:
- # if self.peek() not in ' \t':
- # chunks.append(u' ')
- # else:
- # chunks.append(line_break)
- #else:
- # chunks.append(line_break)
- else:
- break
-
- # Chomp the tail.
- if chomping is not False:
- chunks.append(line_break)
- if chomping is True:
- chunks.extend(breaks)
-
- # We are done.
- return ScalarToken(u''.join(chunks), False, start_mark, end_mark,
- style)
-
- def scan_block_scalar_indicators(self, start_mark):
- # See the specification for details.
- chomping = None
- increment = None
- ch = self.peek()
- if ch in u'+-':
- if ch == '+':
- chomping = True
- else:
- chomping = False
- self.forward()
- ch = self.peek()
- if ch in u'0123456789':
- increment = int(ch)
- if increment == 0:
- raise ScannerError("while scanning a block scalar", start_mark,
- "expected indentation indicator in the range 1-9, but found 0",
- self.get_mark())
- self.forward()
- elif ch in u'0123456789':
- increment = int(ch)
- if increment == 0:
- raise ScannerError("while scanning a block scalar", start_mark,
- "expected indentation indicator in the range 1-9, but found 0",
- self.get_mark())
- self.forward()
- ch = self.peek()
- if ch in u'+-':
- if ch == '+':
- chomping = True
- else:
- chomping = False
- self.forward()
- ch = self.peek()
- if ch not in u'\0 \r\n\x85\u2028\u2029':
- raise ScannerError("while scanning a block scalar", start_mark,
- "expected chomping or indentation indicators, but found %r"
- % ch.encode('utf-8'), self.get_mark())
- return chomping, increment
-
- def scan_block_scalar_ignored_line(self, start_mark):
- # See the specification for details.
- while self.peek() == u' ':
- self.forward()
- if self.peek() == u'#':
- while self.peek() not in u'\0\r\n\x85\u2028\u2029':
- self.forward()
- ch = self.peek()
- if ch not in u'\0\r\n\x85\u2028\u2029':
- raise ScannerError("while scanning a block scalar", start_mark,
- "expected a comment or a line break, but found %r"
- % ch.encode('utf-8'), self.get_mark())
- self.scan_line_break()
-
- def scan_block_scalar_indentation(self):
- # See the specification for details.
- chunks = []
- max_indent = 0
- end_mark = self.get_mark()
- while self.peek() in u' \r\n\x85\u2028\u2029':
- if self.peek() != u' ':
- chunks.append(self.scan_line_break())
- end_mark = self.get_mark()
- else:
- self.forward()
- if self.column > max_indent:
- max_indent = self.column
- return chunks, max_indent, end_mark
-
- def scan_block_scalar_breaks(self, indent):
- # See the specification for details.
- chunks = []
- end_mark = self.get_mark()
- while self.column < indent and self.peek() == u' ':
- self.forward()
- while self.peek() in u'\r\n\x85\u2028\u2029':
- chunks.append(self.scan_line_break())
- end_mark = self.get_mark()
- while self.column < indent and self.peek() == u' ':
- self.forward()
- return chunks, end_mark
-
- def scan_flow_scalar(self, style):
- # See the specification for details.
- # Note that we loose indentation rules for quoted scalars. Quoted
- # scalars don't need to adhere indentation because " and ' clearly
- # mark the beginning and the end of them. Therefore we are less
- # restrictive then the specification requires. We only need to check
- # that document separators are not included in scalars.
- if style == '"':
- double = True
- else:
- double = False
- chunks = []
- start_mark = self.get_mark()
- quote = self.peek()
- self.forward()
- chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark))
- while self.peek() != quote:
- chunks.extend(self.scan_flow_scalar_spaces(double, start_mark))
- chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark))
- self.forward()
- end_mark = self.get_mark()
- return ScalarToken(u''.join(chunks), False, start_mark, end_mark,
- style)
-
- ESCAPE_REPLACEMENTS = {
- u'0': u'\0',
- u'a': u'\x07',
- u'b': u'\x08',
- u't': u'\x09',
- u'\t': u'\x09',
- u'n': u'\x0A',
- u'v': u'\x0B',
- u'f': u'\x0C',
- u'r': u'\x0D',
- u'e': u'\x1B',
- u' ': u'\x20',
- u'\"': u'\"',
- u'\\': u'\\',
- u'N': u'\x85',
- u'_': u'\xA0',
- u'L': u'\u2028',
- u'P': u'\u2029',
- }
-
- ESCAPE_CODES = {
- u'x': 2,
- u'u': 4,
- u'U': 8,
- }
-
- def scan_flow_scalar_non_spaces(self, double, start_mark):
- # See the specification for details.
- chunks = []
- while True:
- length = 0
- while self.peek(length) not in u'\'\"\\\0 \t\r\n\x85\u2028\u2029':
- length += 1
- if length:
- chunks.append(self.prefix(length))
- self.forward(length)
- ch = self.peek()
- if not double and ch == u'\'' and self.peek(1) == u'\'':
- chunks.append(u'\'')
- self.forward(2)
- elif (double and ch == u'\'') or (not double and ch in u'\"\\'):
- chunks.append(ch)
- self.forward()
- elif double and ch == u'\\':
- self.forward()
- ch = self.peek()
- if ch in self.ESCAPE_REPLACEMENTS:
- chunks.append(self.ESCAPE_REPLACEMENTS[ch])
- self.forward()
- elif ch in self.ESCAPE_CODES:
- length = self.ESCAPE_CODES[ch]
- self.forward()
- for k in range(length):
- if self.peek(k) not in u'0123456789ABCDEFabcdef':
- raise ScannerError("while scanning a double-quoted scalar", start_mark,
- "expected escape sequence of %d hexdecimal numbers, but found %r" %
- (length, self.peek(k).encode('utf-8')), self.get_mark())
- code = int(self.prefix(length), 16)
- chunks.append(unichr(code))
- self.forward(length)
- elif ch in u'\r\n\x85\u2028\u2029':
- self.scan_line_break()
- chunks.extend(self.scan_flow_scalar_breaks(double, start_mark))
- else:
- raise ScannerError("while scanning a double-quoted scalar", start_mark,
- "found unknown escape character %r" % ch.encode('utf-8'), self.get_mark())
- else:
- return chunks
-
- def scan_flow_scalar_spaces(self, double, start_mark):
- # See the specification for details.
- chunks = []
- length = 0
- while self.peek(length) in u' \t':
- length += 1
- whitespaces = self.prefix(length)
- self.forward(length)
- ch = self.peek()
- if ch == u'\0':
- raise ScannerError("while scanning a quoted scalar", start_mark,
- "found unexpected end of stream", self.get_mark())
- elif ch in u'\r\n\x85\u2028\u2029':
- line_break = self.scan_line_break()
- breaks = self.scan_flow_scalar_breaks(double, start_mark)
- if line_break != u'\n':
- chunks.append(line_break)
- elif not breaks:
- chunks.append(u' ')
- chunks.extend(breaks)
- else:
- chunks.append(whitespaces)
- return chunks
-
- def scan_flow_scalar_breaks(self, double, start_mark):
- # See the specification for details.
- chunks = []
- while True:
- # Instead of checking indentation, we check for document
- # separators.
- prefix = self.prefix(3)
- if (prefix == u'---' or prefix == u'...') \
- and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029':
- raise ScannerError("while scanning a quoted scalar", start_mark,
- "found unexpected document separator", self.get_mark())
- while self.peek() in u' \t':
- self.forward()
- if self.peek() in u'\r\n\x85\u2028\u2029':
- chunks.append(self.scan_line_break())
- else:
- return chunks
-
- def scan_plain(self):
- # See the specification for details.
- # We add an additional restriction for the flow context:
- # plain scalars in the flow context cannot contain ',', ':' and '?'.
- # We also keep track of the `allow_simple_key` flag here.
- # Indentation rules are loosed for the flow context.
- chunks = []
- start_mark = self.get_mark()
- end_mark = start_mark
- indent = self.indent+1
- # We allow zero indentation for scalars, but then we need to check for
- # document separators at the beginning of the line.
- #if indent == 0:
- # indent = 1
- spaces = []
- while True:
- length = 0
- if self.peek() == u'#':
- break
- while True:
- ch = self.peek(length)
- if ch in u'\0 \t\r\n\x85\u2028\u2029' \
- or (not self.flow_level and ch == u':' and
- self.peek(length+1) in u'\0 \t\r\n\x85\u2028\u2029') \
- or (self.flow_level and ch in u',:?[]{}'):
- break
- length += 1
- # It's not clear what we should do with ':' in the flow context.
- if (self.flow_level and ch == u':'
- and self.peek(length+1) not in u'\0 \t\r\n\x85\u2028\u2029,[]{}'):
- self.forward(length)
- raise ScannerError("while scanning a plain scalar", start_mark,
- "found unexpected ':'", self.get_mark(),
- "Please check http://pyyaml.org/wiki/YAMLColonInFlowContext for details.")
- if length == 0:
- break
- self.allow_simple_key = False
- chunks.extend(spaces)
- chunks.append(self.prefix(length))
- self.forward(length)
- end_mark = self.get_mark()
- spaces = self.scan_plain_spaces(indent, start_mark)
- if not spaces or self.peek() == u'#' \
- or (not self.flow_level and self.column < indent):
- break
- return ScalarToken(u''.join(chunks), True, start_mark, end_mark)
-
- def scan_plain_spaces(self, indent, start_mark):
- # See the specification for details.
- # The specification is really confusing about tabs in plain scalars.
- # We just forbid them completely. Do not use tabs in YAML!
- chunks = []
- length = 0
- while self.peek(length) in u' ':
- length += 1
- whitespaces = self.prefix(length)
- self.forward(length)
- ch = self.peek()
- if ch in u'\r\n\x85\u2028\u2029':
- line_break = self.scan_line_break()
- self.allow_simple_key = True
- prefix = self.prefix(3)
- if (prefix == u'---' or prefix == u'...') \
- and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029':
- return
- breaks = []
- while self.peek() in u' \r\n\x85\u2028\u2029':
- if self.peek() == ' ':
- self.forward()
- else:
- breaks.append(self.scan_line_break())
- prefix = self.prefix(3)
- if (prefix == u'---' or prefix == u'...') \
- and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029':
- return
- if line_break != u'\n':
- chunks.append(line_break)
- elif not breaks:
- chunks.append(u' ')
- chunks.extend(breaks)
- elif whitespaces:
- chunks.append(whitespaces)
- return chunks
-
- def scan_tag_handle(self, name, start_mark):
- # See the specification for details.
- # For some strange reasons, the specification does not allow '_' in
- # tag handles. I have allowed it anyway.
- ch = self.peek()
- if ch != u'!':
- raise ScannerError("while scanning a %s" % name, start_mark,
- "expected '!', but found %r" % ch.encode('utf-8'),
- self.get_mark())
- length = 1
- ch = self.peek(length)
- if ch != u' ':
- while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \
- or ch in u'-_':
- length += 1
- ch = self.peek(length)
- if ch != u'!':
- self.forward(length)
- raise ScannerError("while scanning a %s" % name, start_mark,
- "expected '!', but found %r" % ch.encode('utf-8'),
- self.get_mark())
- length += 1
- value = self.prefix(length)
- self.forward(length)
- return value
-
- def scan_tag_uri(self, name, start_mark):
- # See the specification for details.
- # Note: we do not check if URI is well-formed.
- chunks = []
- length = 0
- ch = self.peek(length)
- while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \
- or ch in u'-;/?:@&=+$,_.!~*\'()[]%':
- if ch == u'%':
- chunks.append(self.prefix(length))
- self.forward(length)
- length = 0
- chunks.append(self.scan_uri_escapes(name, start_mark))
- else:
- length += 1
- ch = self.peek(length)
- if length:
- chunks.append(self.prefix(length))
- self.forward(length)
- length = 0
- if not chunks:
- raise ScannerError("while parsing a %s" % name, start_mark,
- "expected URI, but found %r" % ch.encode('utf-8'),
- self.get_mark())
- return u''.join(chunks)
-
- def scan_uri_escapes(self, name, start_mark):
- # See the specification for details.
- bytes = []
- mark = self.get_mark()
- while self.peek() == u'%':
- self.forward()
- for k in range(2):
- if self.peek(k) not in u'0123456789ABCDEFabcdef':
- raise ScannerError("while scanning a %s" % name, start_mark,
- "expected URI escape sequence of 2 hexdecimal numbers, but found %r" %
- (self.peek(k).encode('utf-8')), self.get_mark())
- bytes.append(chr(int(self.prefix(2), 16)))
- self.forward(2)
- try:
- value = unicode(''.join(bytes), 'utf-8')
- except UnicodeDecodeError, exc:
- raise ScannerError("while scanning a %s" % name, start_mark, str(exc), mark)
- return value
-
- def scan_line_break(self):
- # Transforms:
- # '\r\n' : '\n'
- # '\r' : '\n'
- # '\n' : '\n'
- # '\x85' : '\n'
- # '\u2028' : '\u2028'
- # '\u2029 : '\u2029'
- # default : ''
- ch = self.peek()
- if ch in u'\r\n\x85':
- if self.prefix(2) == u'\r\n':
- self.forward(2)
- else:
- self.forward()
- return u'\n'
- elif ch in u'\u2028\u2029':
- self.forward()
- return ch
- return u''
-
-#try:
-# import psyco
-# psyco.bind(Scanner)
-#except ImportError:
-# pass
-
diff --git a/tablib/packages/yaml/serializer.py b/tablib/packages/yaml/serializer.py
deleted file mode 100644
index 0bf1e96..0000000
--- a/tablib/packages/yaml/serializer.py
+++ /dev/null
@@ -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()
-
diff --git a/tablib/packages/yaml/tokens.py b/tablib/packages/yaml/tokens.py
deleted file mode 100644
index 4d0b48a..0000000
--- a/tablib/packages/yaml/tokens.py
+++ /dev/null
@@ -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
-