New package to add a yaml parser

master
Daniel Berteaud 6 years ago
parent ad7c7d3de0
commit fadb159d30
  1. 32
      WAPT/control
  2. BIN
      WAPT/icon.png
  3. 275
      WAPT/wapt.psproj
  4. 17
      setup.py
  5. 315
      yaml/__init__.py
  6. 139
      yaml/composer.py
  7. 675
      yaml/constructor.py
  8. 85
      yaml/cyaml.py
  9. 62
      yaml/dumper.py
  10. 1140
      yaml/emitter.py
  11. 75
      yaml/error.py
  12. 86
      yaml/events.py
  13. 40
      yaml/loader.py
  14. 49
      yaml/nodes.py
  15. 589
      yaml/parser.py
  16. 190
      yaml/reader.py
  17. 486
      yaml/representer.py
  18. 227
      yaml/resolver.py
  19. 1453
      yaml/scanner.py
  20. 111
      yaml/serializer.py
  21. 104
      yaml/tokens.py

@ -0,0 +1,32 @@
package : fws-pyyaml
version : 1
architecture : all
section : base
priority : high
maintainer : Daniel Berteaud <daniel@firewall-services.com>
description : PyYAML support for WAPT Agent
depends :
conflicts :
maturity : PROD
locale :
target_os : windows
min_os_version : 5.0
max_os_version :
min_wapt_version : 1.5
sources :
installed_size :
impacted_process :
description_fr : Support de PyYAML pour l'agent WAPT
description_pl :
description_de :
description_es :
audit_schedule : 2d
editor : Firewall Services
keywords :
licence :
homepage : https://pyyaml.org/
package_uuid :
signer : Daniel Berteaud
signer_fingerprint:
signature_date :
signed_attributes :

Binary file not shown.

After

Width:  |  Height:  |  Size: 9.5 KiB

@ -0,0 +1,275 @@
[PyScripter]
Version=3.4.2.0
[Project]
ClassName=TProjectRootNode
StoreRelativePaths=TRUE
ShowFileExtensions=FALSE
[Project\ChildNodes\Node0]
ClassName=TProjectFilesNode
[Project\ChildNodes\Node0\ChildNodes\Node0]
ClassName=TProjectFolderNode
Name=wapt
[Project\ChildNodes\Node0\ChildNodes\Node0\ChildNodes\Node0]
ClassName=TProjectFileNode
FileName=C:\Program Files (x86)\wapt\common.py
[Project\ChildNodes\Node0\ChildNodes\Node0\ChildNodes\Node1]
ClassName=TProjectFileNode
FileName=C:\Program Files (x86)\wapt\setuphelpers.py
[Project\ChildNodes\Node0\ChildNodes\Node0\ChildNodes\Node2]
ClassName=TProjectFileNode
FileName=C:\Program Files (x86)\wapt\wapt-get.py
[Project\ChildNodes\Node0\ChildNodes\Node0\ChildNodes\Node3]
ClassName=TProjectFileNode
FileName=C:\Program Files (x86)\wapt\wapt-get.ini
[Project\ChildNodes\Node0\ChildNodes\Node0\ChildNodes\Node4]
ClassName=TProjectFileNode
FileName=C:\Program Files (x86)\wapt\waptpackage.py
[Project\ChildNodes\Node0\ChildNodes\Node0\ChildNodes]
Count=5
[Project\ChildNodes\Node0\ChildNodes\Node1]
ClassName=TProjectFileNode
FileName=$[Project-Path]changelog.txt
[Project\ChildNodes\Node0\ChildNodes\Node2]
ClassName=TProjectFileNode
FileName=$[Project-Path]control
[Project\ChildNodes\Node0\ChildNodes\Node3]
ClassName=TProjectFileNode
FileName=$[Project-Path]..\setup.py
[Project\ChildNodes\Node0\ChildNodes]
Count=4
[Project\ChildNodes\Node1]
ClassName=TProjectRunConfiguationsNode
[Project\ChildNodes\Node1\ChildNodes\Node0]
ClassName=TProjectRunConfiguationNode
Name=install
[Project\ChildNodes\Node1\ChildNodes\Node0\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=install "$[Project-Path].."
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node0\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes\Node1]
ClassName=TProjectRunConfiguationNode
Name=remove
[Project\ChildNodes\Node1\ChildNodes\Node1\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=remove "$[Project-Path].."
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node1\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes\Node2]
ClassName=TProjectRunConfiguationNode
Name=session-setup
[Project\ChildNodes\Node1\ChildNodes\Node2\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=session-setup "$[Project-Path].."
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node2\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes\Node3]
ClassName=TProjectRunConfiguationNode
Name=update
[Project\ChildNodes\Node1\ChildNodes\Node3\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=update
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node3\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes\Node4]
ClassName=TProjectRunConfiguationNode
Name=upgrade
[Project\ChildNodes\Node1\ChildNodes\Node4\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=-f upgrade
WorkingDir=$[ActiveScript-Dir]
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node4\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes\Node5]
ClassName=TProjectRunConfiguationNode
Name=-i build-upload
[Project\ChildNodes\Node1\ChildNodes\Node5\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=-i build-upload "$[Project-Path].."
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node5\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes\Node6]
ClassName=TProjectRunConfiguationNode
Name=svn update
[Project\ChildNodes\Node1\ChildNodes\Node6\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=sources "$[Project-Path].."
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node6\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes\Node7]
ClassName=TProjectRunConfiguationNode
Name=uninstall
[Project\ChildNodes\Node1\ChildNodes\Node7\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=uninstall "$[Project-Path].."
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node7\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[Project-Path]..
[Project\ChildNodes\Node1\ChildNodes\Node8]
ClassName=TProjectRunConfiguationNode
Name=update-package-sources
[Project\ChildNodes\Node1\ChildNodes\Node8\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=update-package-sources "$[Project-Path].."
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node8\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes\Node9]
ClassName=TProjectRunConfiguationNode
Name=audit
[Project\ChildNodes\Node1\ChildNodes\Node9\RunConfig]
ScriptName=C:\Program Files (x86)\wapt\wapt-get.py
EngineType=peRemote
ReinitializeBeforeRun=TRUE
Parameters=audit -f "$[Project-Path].."
WorkingDir=$[Project-Path]..
WriteOutputToFile=FALSE
OutputFileName=$[ActiveScript-NoExt].log
AppendToFile=FALSE
[Project\ChildNodes\Node1\ChildNodes\Node9\RunConfig\ExternalRun]
Caption=External Run
Description=Run script using an external Python Interpreter
ApplicationName=$[PythonExe-Short]
Parameters=$[ActiveScript-Short]
WorkingDirectory=$[ActiveScript-Dir]
[Project\ChildNodes\Node1\ChildNodes]
Count=10
[Project\ChildNodes]
Count=2
[Project\ExtraPythonPath]
Count=0

@ -0,0 +1,17 @@
# -*- coding: UTF-8 -*-
from setuphelpers import *
uninstallkey = []
def install():
mkdirs(makepath(programfiles32,'wapt','lib','yaml'))
copytree2("yaml",makepath(programfiles32,'wapt','lib','yaml'))
def uninstall():
remove_tree(makepath(programfiles32,'wapt','lib','yaml'))
def audit():
if not isfile(makepath(programfiles32,'wapt','lib','yaml','__init__.py')):
print('PyYAML not installed')
return "ERROR"
return "OK"

@ -0,0 +1,315 @@
from error import *
from tokens import *
from events import *
from nodes import *
from loader import *
from dumper import *
__version__ = '3.13'
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)
try:
while loader.check_token():
yield loader.get_token()
finally:
loader.dispose()
def parse(stream, Loader=Loader):
"""
Parse a YAML stream and produce parsing events.
"""
loader = Loader(stream)
try:
while loader.check_event():
yield loader.get_event()
finally:
loader.dispose()
def compose(stream, Loader=Loader):
"""
Parse the first YAML document in a stream
and produce the corresponding representation tree.
"""
loader = Loader(stream)
try:
return loader.get_single_node()
finally:
loader.dispose()
def compose_all(stream, Loader=Loader):
"""
Parse all YAML documents in a stream
and produce corresponding representation trees.
"""
loader = Loader(stream)
try:
while loader.check_node():
yield loader.get_node()
finally:
loader.dispose()
def load(stream, Loader=Loader):
"""
Parse the first YAML document in a stream
and produce the corresponding Python object.
"""
loader = Loader(stream)
try:
return loader.get_single_data()
finally:
loader.dispose()
def load_all(stream, Loader=Loader):
"""
Parse all YAML documents in a stream
and produce corresponding Python objects.
"""
loader = Loader(stream)
try:
while loader.check_data():
yield loader.get_data()
finally:
loader.dispose()
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)
try:
for event in events:
dumper.emit(event)
finally:
dumper.dispose()
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)
try:
dumper.open()
for node in nodes:
dumper.serialize(node)
dumper.close()
finally:
dumper.dispose()
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)
try:
dumper.open()
for data in documents:
dumper.represent(data)
dumper.close()
finally:
dumper.dispose()
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)

@ -0,0 +1,139 @@
__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

@ -0,0 +1,675 @@
__all__ = ['BaseConstructor', 'SafeConstructor', 'Constructor',
'ConstructorError']
from error import *
from nodes import *
import datetime
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 node in self.constructed_objects:
return self.constructed_objects[node]
if deep:
old_deep = self.deep_construct
self.deep_construct = True
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:
module_name, object_name = name.rsplit('.', 1)
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)

@ -0,0 +1,85 @@
__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)

@ -0,0 +1,62 @@
__all__ = ['BaseDumper', 'SafeDumper', 'Dumper']
from emitter import *
from serializer import *
from representer import *
from resolver import *
class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
Emitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break)
Serializer.__init__(self, encoding=encoding,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
Representer.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)
class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
Emitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break)
Serializer.__init__(self, encoding=encoding,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
SafeRepresenter.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)
class Dumper(Emitter, Serializer, Representer, Resolver):
def __init__(self, stream,
default_style=None, default_flow_style=None,
canonical=None, indent=None, width=None,
allow_unicode=None, line_break=None,
encoding=None, explicit_start=None, explicit_end=None,
version=None, tags=None):
Emitter.__init__(self, stream, canonical=canonical,
indent=indent, width=width,
allow_unicode=allow_unicode, line_break=line_break)
Serializer.__init__(self, encoding=encoding,
explicit_start=explicit_start, explicit_end=explicit_end,
version=version, tags=tags)
Representer.__init__(self, default_style=default_style,
default_flow_style=default_flow_style)
Resolver.__init__(self)

File diff suppressed because it is too large Load Diff

@ -0,0 +1,75 @@
__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)

@ -0,0 +1,86 @@
# 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

@ -0,0 +1,40 @@
__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)

@ -0,0 +1,49 @@
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'

@ -0,0 +1,589 @@
# 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 dispose(self):
# Reset the state attributes (to clear self-references)
self.states = []
self.state = None
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)

@ -0,0 +1,190 @@
# 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
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 = codecs.utf_16_le_decode
self.encoding = 'utf-16-le'
elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
self.raw_decode = codecs.utf_16_be_decode
self.encoding = 'utf-16-be'
else:
self.raw_decode = codecs.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

@ -0,0 +1,486 @@
__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer',
'RepresenterError']
from error import *
from nodes import *
import datetime
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 is None:
return True
if isinstance(data, tuple) and data == ():
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)

@ -0,0 +1,227 @@
__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__:
implicit_resolvers = {}
for key in cls.yaml_implicit_resolvers:
implicit_resolvers[key] = cls.yaml_implicit_resolvers[key][:]
cls.yaml_implicit_resolvers = implicit_resolvers
if first is None:
first = [None]
for ch in first:
cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp))
add_implicit_resolver = classmethod(add_implicit_resolver)
def add_path_resolver(cls, tag, path, kind=None):
# Note: `add_path_resolver` is experimental. The API could be changed.
# `new_path` is a pattern that is matched against the path from the
# root to the node that is being considered. `node_path` elements are
# tuples `(node_check, index_check)`. `node_check` is a node class:
# `ScalarNode`, `SequenceNode`, `MappingNode` or `None`. `None`
# matches any kind of a node. `index_check` could be `None`, a boolean
# value, a string value, or a number. `None` and `False` match against
# any _value_ of sequence and mapping nodes. `True` matches against
# any _key_ of a mapping node. A string `index_check` matches against
# a mapping value that corresponds to a scalar key which content is
# equal to the `index_check` value. An integer `index_check` matches
# against a sequence value with the index equal to `index_check`.
if not 'yaml_path_resolvers' in cls.__dict__:
cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy()
new_path = []
for element in path:
if isinstance(element, (list, tuple)):
if len(element) == 2:
node_check, index_check = element
elif len(element) == 1:
node_check = element[0]
index_check = True
else:
raise ResolverError("Invalid path element: %s" % element)
else:
node_check = None
index_check = element
if node_check is str:
node_check = ScalarNode
elif node_check is list:
node_check = SequenceNode
elif node_check is dict:
node_check = MappingNode
elif node_check not in [ScalarNode, SequenceNode, MappingNode] \
and not isinstance(node_check, basestring) \
and node_check is not None:
raise ResolverError("Invalid node checker: %s" % node_check)
if not isinstance(index_check, (basestring, int)) \
and index_check is not None:
raise ResolverError("Invalid index checker: %s" % index_check)
new_path.append((node_check, index_check))
if kind is str:
kind = ScalarNode
elif kind is list:
kind = SequenceNode
elif kind is dict:
kind = MappingNode
elif kind not in [ScalarNode, SequenceNode, MappingNode] \
and kind is not None:
raise ResolverError("Invalid node kind: %s" % kind)
cls.yaml_path_resolvers[tuple(new_path), kind] = tag
add_path_resolver = classmethod(add_path_resolver)
def descend_resolver(self, current_node, current_index):
if not self.yaml_path_resolvers:
return
exact_paths = {}
prefix_paths = []
if current_node:
depth = len(self.resolver_prefix_paths)
for path, kind in self.resolver_prefix_paths[-1]:
if self.check_resolver_prefix(depth, path, kind,
current_node, current_index):
if len(path) > depth:
prefix_paths.append((path, kind))
else:
exact_paths[kind] = self.yaml_path_resolvers[path, kind]
else:
for path, kind in self.yaml_path_resolvers:
if not path:
exact_paths[kind] = self.yaml_path_resolvers[path, kind]
else:
prefix_paths.append((path, kind))
self.resolver_exact_paths.append(exact_paths)
self.resolver_prefix_paths.append(prefix_paths)
def ascend_resolver(self):
if not self.yaml_path_resolvers:
return
self.resolver_exact_paths.pop()
self.resolver_prefix_paths.pop()
def check_resolver_prefix(self, depth, path, kind,
current_node, current_index):
node_check, index_check = path[depth-1]
if isinstance(node_check, basestring):
if current_node.tag != node_check:
return
elif node_check is not None:
if not isinstance(current_node, node_check):
return
if index_check is True and current_index is not None:
return
if (index_check is False or index_check is None) \
and current_index is None:
return
if isinstance(index_check, basestring):
if not (isinstance(current_index, ScalarNode)
and index_check == current_index.value):
return
elif isinstance(index_check, int) and not isinstance(index_check, bool):
if index_check != current_index:
return
return True
def resolve(self, kind, value, implicit):
if kind is ScalarNode and implicit[0]:
if value == u'':
resolvers = self.yaml_implicit_resolvers.get(u'', [])
else:
resolvers = self.yaml_implicit_resolvers.get(value[0], [])
resolvers += self.yaml_implicit_resolvers.get(None, [])
for tag, regexp in resolvers:
if regexp.match(value):
return tag
implicit = implicit[1]
if self.yaml_path_resolvers:
exact_paths = self.resolver_exact_paths[-1]
if kind in exact_paths:
return exact_paths[kind]
if None in exact_paths:
return exact_paths[None]
if kind is ScalarNode:
return self.DEFAULT_SCALAR_TAG
elif kind is SequenceNode:
return self.DEFAULT_SEQUENCE_TAG
elif kind is MappingNode:
return self.DEFAULT_MAPPING_TAG
class Resolver(BaseResolver):
pass
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:bool',
re.compile(ur'''^(?:yes|Yes|YES|no|No|NO
|true|True|TRUE|false|False|FALSE
|on|On|ON|off|Off|OFF)$''', re.X),
list(u'yYnNtTfFoO'))
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:float',
re.compile(ur'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)?
|\.[0-9_]+(?:[eE][-+][0-9]+)?
|[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]*
|[-+]?\.(?:inf|Inf|INF)
|\.(?:nan|NaN|NAN))$''', re.X),
list(u'-+0123456789.'))
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:int',
re.compile(ur'''^(?:[-+]?0b[0-1_]+
|[-+]?0[0-7_]+
|[-+]?(?:0|[1-9][0-9_]*)
|[-+]?0x[0-9a-fA-F_]+
|[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X),
list(u'-+0123456789'))
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:merge',
re.compile(ur'^(?:<<)$'),
[u'<'])
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:null',
re.compile(ur'''^(?: ~
|null|Null|NULL
| )$''', re.X),
[u'~', u'n', u'N', u''])
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:timestamp',
re.compile(ur'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]
|[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]?
(?:[Tt]|[ \t]+)[0-9][0-9]?
:[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)?
(?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X),
list(u'0123456789'))
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:value',
re.compile(ur'^(?:=)$'),
[u'='])
# The following resolver is only for documentation purposes. It cannot work
# because plain scalars cannot start with '!', '&', or '*'.
Resolver.add_implicit_resolver(
u'tag:yaml.org,2002:yaml',
re.compile(ur'^(?:!|&|\*)$'),
list(u'!&*'))

File diff suppressed because it is too large Load Diff

@ -0,0 +1,111 @@
__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()

@ -0,0 +1,104 @@
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
Loading…
Cancel
Save