metaflow 2.16.6__py2.py3-none-any.whl → 2.16.8__py2.py3-none-any.whl

metaflow/_vendor/yaml/reader.py

@@ -0,0 +1,185 @@
+# 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, bytes):
+            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 a unicode string,
+    # - checks if characters are in allowed range,
+    # - adds '\0' to the end.
+
+    # Reader accepts
+    #  - a `bytes` object,
+    #  - a `str` 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 = ''
+        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, str):
+            self.name = "<unicode string>"
+            self.check_printable(stream)
+            self.buffer = stream+'\0'
+        elif isinstance(stream, bytes):
+            self.name = "<byte string>"
+            self.raw_buffer = stream
+            self.determine_encoding()
+        else:
+            self.stream = stream
+            self.name = getattr(stream, 'name', "<file>")
+            self.eof = False
+            self.raw_buffer = None
+            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 '\n\x85\u2028\u2029'  \
+                    or (ch == '\r' and self.buffer[self.pointer] != '\n'):
+                self.line += 1
+                self.column = 0
+            elif ch != '\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 (self.raw_buffer is None or len(self.raw_buffer) < 2):
+            self.update_raw()
+        if isinstance(self.raw_buffer, bytes):
+            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('[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]')
+    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 as exc:
+                    character = self.raw_buffer[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 += '\0'
+                self.raw_buffer = None
+                break
+
+    def update_raw(self, size=4096):
+        data = self.stream.read(size)
+        if self.raw_buffer is None:
+            self.raw_buffer = data
+        else:
+            self.raw_buffer += data
+        self.stream_pointer += len(data)
+        if not data:
+            self.eof = True

metaflow/_vendor/yaml/representer.py

@@ -0,0 +1,389 @@
+
+__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer',
+    'RepresenterError']
+
+from .error import *
+from .nodes import *
+
+import datetime, copyreg, types, base64, collections
+
+class RepresenterError(YAMLError):
+    pass
+
+class BaseRepresenter:
+
+    yaml_representers = {}
+    yaml_multi_representers = {}
+
+    def __init__(self, default_style=None, default_flow_style=False, sort_keys=True):
+        self.default_style = default_style
+        self.sort_keys = sort_keys
+        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 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 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, str(data))
+        #if alias_key is not None:
+        #    self.represented_objects[alias_key] = node
+        return node
+
+    @classmethod
+    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
+
+    @classmethod
+    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
+
+    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 = list(mapping.items())
+            if self.sort_keys:
+                try:
+                    mapping = sorted(mapping)
+                except TypeError:
+                    pass
+        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, bytes, bool, int, float)):
+            return True
+
+    def represent_none(self, data):
+        return self.represent_scalar('tag:yaml.org,2002:null', 'null')
+
+    def represent_str(self, data):
+        return self.represent_scalar('tag:yaml.org,2002:str', data)
+
+    def represent_binary(self, data):
+        if hasattr(base64, 'encodebytes'):
+            data = base64.encodebytes(data).decode('ascii')
+        else:
+            data = base64.encodestring(data).decode('ascii')
+        return self.represent_scalar('tag:yaml.org,2002:binary', data, style='|')
+
+    def represent_bool(self, data):
+        if data:
+            value = 'true'
+        else:
+            value = 'false'
+        return self.represent_scalar('tag:yaml.org,2002:bool', value)
+
+    def represent_int(self, data):
+        return self.represent_scalar('tag:yaml.org,2002:int', str(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 = '.nan'
+        elif data == self.inf_value:
+            value = '.inf'
+        elif data == -self.inf_value:
+            value = '-.inf'
+        else:
+            value = 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 '.' not in value and 'e' in value:
+                value = value.replace('e', '.0e', 1)
+        return self.represent_scalar('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('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('tag:yaml.org,2002:map', data)
+
+    def represent_set(self, data):
+        value = {}
+        for key in data:
+            value[key] = None
+        return self.represent_mapping('tag:yaml.org,2002:set', value)
+
+    def represent_date(self, data):
+        value = data.isoformat()
+        return self.represent_scalar('tag:yaml.org,2002:timestamp', value)
+
+    def represent_datetime(self, data):
+        value = data.isoformat(' ')
+        return self.represent_scalar('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", data)
+
+SafeRepresenter.add_representer(type(None),
+        SafeRepresenter.represent_none)
+
+SafeRepresenter.add_representer(str,
+        SafeRepresenter.represent_str)
+
+SafeRepresenter.add_representer(bytes,
+        SafeRepresenter.represent_binary)
+
+SafeRepresenter.add_representer(bool,
+        SafeRepresenter.represent_bool)
+
+SafeRepresenter.add_representer(int,
+        SafeRepresenter.represent_int)
+
+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_complex(self, data):
+        if data.imag == 0.0:
+            data = '%r' % data.real
+        elif data.real == 0.0:
+            data = '%rj' % data.imag
+        elif data.imag > 0:
+            data = '%r+%rj' % (data.real, data.imag)
+        else:
+            data = '%r%rj' % (data.real, data.imag)
+        return self.represent_scalar('tag:yaml.org,2002:python/complex', data)
+
+    def represent_tuple(self, data):
+        return self.represent_sequence('tag:yaml.org,2002:python/tuple', data)
+
+    def represent_name(self, data):
+        name = '%s.%s' % (data.__module__, data.__name__)
+        return self.represent_scalar('tag:yaml.org,2002:python/name:'+name, '')
+
+    def represent_module(self, data):
+        return self.represent_scalar(
+                'tag:yaml.org,2002:python/module:'+data.__name__, '')
+
+    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 copyreg.dispatch_table:
+            reduce = copyreg.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 an object", 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 = 'tag:yaml.org,2002:python/object/new:'
+            newobj = True
+        else:
+            tag = 'tag:yaml.org,2002:python/object/apply:'
+            newobj = False
+        function_name = '%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(
+                    '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)
+
+    def represent_ordered_dict(self, data):
+        # Provide uniform representation across different Python versions.
+        data_type = type(data)
+        tag = 'tag:yaml.org,2002:python/object/apply:%s.%s' \
+                % (data_type.__module__, data_type.__name__)
+        items = [[key, value] for key, value in data.items()]
+        return self.represent_sequence(tag, [items])
+
+Representer.add_representer(complex,
+        Representer.represent_complex)
+
+Representer.add_representer(tuple,
+        Representer.represent_tuple)
+
+Representer.add_representer(type,
+        Representer.represent_name)
+
+Representer.add_representer(collections.OrderedDict,
+        Representer.represent_ordered_dict)
+
+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(object,
+        Representer.represent_object)
+