You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hawq.apache.org by rl...@apache.org on 2016/01/06 09:56:10 UTC
[09/13] incubator-hawq git commit: HAWQ-271. Remove external python
modules.
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/0672292f/tools/bin/ext/yaml/constructor.py
----------------------------------------------------------------------
diff --git a/tools/bin/ext/yaml/constructor.py b/tools/bin/ext/yaml/constructor.py
deleted file mode 100644
index e66dd2c..0000000
--- a/tools/bin/ext/yaml/constructor.py
+++ /dev/null
@@ -1,691 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied. See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-__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 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
- state_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 = int(values['fraction'][:6].ljust(6, '0'))
- 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)
-
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/0672292f/tools/bin/ext/yaml/cyaml.py
----------------------------------------------------------------------
diff --git a/tools/bin/ext/yaml/cyaml.py b/tools/bin/ext/yaml/cyaml.py
deleted file mode 100644
index c3eaf77..0000000
--- a/tools/bin/ext/yaml/cyaml.py
+++ /dev/null
@@ -1,101 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied. See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-__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,
- 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,
- 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,
- 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)
-
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/0672292f/tools/bin/ext/yaml/dumper.py
----------------------------------------------------------------------
diff --git a/tools/bin/ext/yaml/dumper.py b/tools/bin/ext/yaml/dumper.py
deleted file mode 100644
index a955200..0000000
--- a/tools/bin/ext/yaml/dumper.py
+++ /dev/null
@@ -1,78 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied. See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-__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_uncode=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)
-
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/0672292f/tools/bin/ext/yaml/emitter.py
----------------------------------------------------------------------
diff --git a/tools/bin/ext/yaml/emitter.py b/tools/bin/ext/yaml/emitter.py
deleted file mode 100644
index 23730d8..0000000
--- a/tools/bin/ext/yaml/emitter.py
+++ /dev/null
@@ -1,1179 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied. See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-# 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 *
-
-import re
-
-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
-
- # 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:
- 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:
- 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):
- 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 <= 'Z' or u'a' <= ch <= '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 <= 'Z' or u'a' <= ch <= '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
- for prefix in self.tag_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 <= 'Z' or u'a' <= ch <= '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 <= 'Z' or u'a' <= ch <= '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
-
- # Whitespaces.
- inline_spaces = False # non-space space+ non-space
- inline_breaks = False # non-space break+ non-space
- leading_spaces = False # ^ space+ (non-space | $)
- leading_breaks = False # ^ break+ (non-space | $)
- trailing_spaces = False # (^ | non-space) space+ $
- trailing_breaks = False # (^ | non-space) break+ $
- inline_breaks_spaces = False # non-space break+ space+ non-space
- mixed_breaks_spaces = False # anything else
-
- # 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_space = True
-
- # Last character or followed by a whitespace.
- followed_by_space = (len(scalar) == 1 or
- scalar[1] in u'\0 \t\r\n\x85\u2028\u2029')
-
- # The current series of whitespaces contain plain spaces.
- spaces = False
-
- # The current series of whitespaces contain line breaks.
- breaks = False
-
- # The current series of whitespaces contain a space followed by a
- # break.
- mixed = False
-
- # The current series of whitespaces start at the beginning of the
- # scalar.
- leading = 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_space:
- block_indicators = True
- if ch == u'-' and followed_by_space:
- 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_space:
- block_indicators = True
- if ch == u'#' and preceeded_by_space:
- 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
-
- # Spaces, line breaks, and how they are mixed. State machine.
-
- # Start or continue series of whitespaces.
- if ch in u' \n\x85\u2028\u2029':
- if spaces and breaks:
- if ch != u' ': # break+ (space+ break+) => mixed
- mixed = True
- elif spaces:
- if ch != u' ': # (space+ break+) => mixed
- breaks = True
- mixed = True
- elif breaks:
- if ch == u' ': # break+ space+
- spaces = True
- else:
- leading = (index == 0)
- if ch == u' ': # space+
- spaces = True
- else: # break+
- breaks = True
-
- # Series of whitespaces ended with a non-space.
- elif spaces or breaks:
- if leading:
- if spaces and breaks:
- mixed_breaks_spaces = True
- elif spaces:
- leading_spaces = True
- elif breaks:
- leading_breaks = True
- else:
- if mixed:
- mixed_breaks_spaces = True
- elif spaces and breaks:
- inline_breaks_spaces = True
- elif spaces:
- inline_spaces = True
- elif breaks:
- inline_breaks = True
- spaces = breaks = mixed = leading = False
-
- # Series of whitespaces reach the end.
- if (spaces or breaks) and (index == len(scalar)-1):
- if spaces and breaks:
- mixed_breaks_spaces = True
- elif spaces:
- trailing_spaces = True
- if leading:
- leading_spaces = True
- elif breaks:
- trailing_breaks = True
- if leading:
- leading_breaks = True
- spaces = breaks = mixed = leading = False
-
- # Prepare for the next character.
- index += 1
- preceeded_by_space = (ch in u'\0 \t\r\n\x85\u2028\u2029')
- followed_by_space = (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 whitespace are bad for plain scalars. We also
- # do not want to mess with leading whitespaces for block scalars.
- if leading_spaces or leading_breaks or trailing_spaces:
- allow_flow_plain = allow_block_plain = allow_block = False
-
- # Trailing breaks are fine for block scalars, but unacceptable for
- # plain scalars.
- if trailing_breaks:
- allow_flow_plain = allow_block_plain = False
-
- # The combination of (space+ break+) is only acceptable for block
- # scalars.
- if inline_breaks_spaces:
- allow_flow_plain = allow_block_plain = allow_single_quoted = False
-
- # Mixed spaces and breaks, as well as special character are only
- # allowed for double quoted scalars.
- if mixed_breaks_spaces or special_characters:
- allow_flow_plain = allow_block_plain = \
- allow_single_quoted = allow_block = False
-
- # We don't 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'\xFF\xFE'.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)
- 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_chomp(self, text):
- tail = text[-2:]
- while len(tail) < 2:
- tail = u' '+tail
- if tail[-1] in u'\n\x85\u2028\u2029':
- if tail[-2] in u'\n\x85\u2028\u2029':
- return u'+'
- else:
- return u''
- else:
- return u'-'
-
- def write_folded(self, text):
- chomp = self.determine_chomp(text)
- self.write_indicator(u'>'+chomp, True)
- self.write_indent()
- leading_space = False
- spaces = False
- breaks = False
- 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]
- 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):
- chomp = self.determine_chomp(text)
- self.write_indicator(u'|'+chomp, True)
- self.write_indent()
- breaks = False
- 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 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.writespace = 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.writespace = 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
-
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/0672292f/tools/bin/ext/yaml/error.py
----------------------------------------------------------------------
diff --git a/tools/bin/ext/yaml/error.py b/tools/bin/ext/yaml/error.py
deleted file mode 100644
index 89e4a6a..0000000
--- a/tools/bin/ext/yaml/error.py
+++ /dev/null
@@ -1,91 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied. See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-__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)
-
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/0672292f/tools/bin/ext/yaml/events.py
----------------------------------------------------------------------
diff --git a/tools/bin/ext/yaml/events.py b/tools/bin/ext/yaml/events.py
deleted file mode 100644
index f57b773..0000000
--- a/tools/bin/ext/yaml/events.py
+++ /dev/null
@@ -1,102 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied. See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-# 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
-