Python regex.Regex方法代码示例

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def _encode_regex(name, value, dummy0, dummy1):
    """Encode a python regex or bson.regex.Regex."""
    flags = value.flags
    # Python 2 common case
    if flags == 0:
        return b"\x0B" + name + _make_c_string_check(value.pattern) + b"\x00"
    # Python 3 common case
    elif flags == re.UNICODE:
        return b"\x0B" + name + _make_c_string_check(value.pattern) + b"u\x00"
    else:
        sflags = b""
        if flags & re.IGNORECASE:
            sflags += b"i"
        if flags & re.LOCALE:
            sflags += b"l"
        if flags & re.MULTILINE:
            sflags += b"m"
        if flags & re.DOTALL:
            sflags += b"s"
        if flags & re.UNICODE:
            sflags += b"u"
        if flags & re.VERBOSE:
            sflags += b"x"
        sflags += b"\x00"
        return b"\x0B" + name + _make_c_string_check(value.pattern) + sflags 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def _get_regex(data, position, dummy0, opts, dummy1):
    """Decode a BSON regex to bson.regex.Regex or a python pattern object."""
    pattern, position = _get_c_string(data, position, opts)
    bson_flags, position = _get_c_string(data, position, opts)
    bson_re = Regex(pattern, bson_flags)
    return bson_re, position 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def object_hook(dct, compile_re=True):
    if "$oid" in dct:
        return ObjectId(str(dct["$oid"]))
    if "$ref" in dct:
        return DBRef(dct["$ref"], dct["$id"], dct.get("$db", None))
    if "$date" in dct:
        secs = float(dct["$date"]) / 1000.0
        return EPOCH_AWARE + datetime.timedelta(seconds=secs)
    if "$regex" in dct:
        flags = 0
        # PyMongo always adds $options but some other tools may not.
        for opt in dct.get("$options", ""):
            flags |= _RE_OPT_TABLE.get(opt, 0)

        if compile_re:
            return re.compile(dct["$regex"], flags)
        else:
            return Regex(dct["$regex"], flags)
    if "$minKey" in dct:
        return MinKey()
    if "$maxKey" in dct:
        return MaxKey()
    if "$binary" in dct:
        if isinstance(dct["$type"], int):
            dct["$type"] = "%02x" % dct["$type"]
        subtype = int(dct["$type"], 16)
        if subtype >= 0xffffff80:  # Handle mongoexport values
            subtype = int(dct["$type"][6:], 16)
        return Binary(base64.b64decode(dct["$binary"].encode()), subtype)
    if "$code" in dct:
        return Code(dct["$code"], dct.get("$scope"))
    if bson.has_uuid() and "$uuid" in dct:
        return bson.uuid.UUID(dct["$uuid"])
    return dct 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def _get_regex(data, position, as_class, tz_aware, uuid_subtype, compile_re):
    pattern, position = _get_c_string(data, position)
    bson_flags, position = _get_c_string(data, position)
    bson_re = Regex(pattern, bson_flags)
    if compile_re:
        return bson_re.try_compile(), position
    else:
        return bson_re, position 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def decode(self, as_class=dict,
               tz_aware=False, uuid_subtype=OLD_UUID_SUBTYPE, compile_re=True):
        """Decode this BSON data.

        The default type to use for the resultant document is
        :class:`dict`. Any other class that supports
        :meth:`__setitem__` can be used instead by passing it as the
        `as_class` parameter.

        If `tz_aware` is ``True`` (recommended), any
        :class:`~datetime.datetime` instances returned will be
        timezone-aware, with their timezone set to
        :attr:`bson.tz_util.utc`. Otherwise (default), all
        :class:`~datetime.datetime` instances will be naive (but
        contain UTC).

        :Parameters:
          - `as_class` (optional): the class to use for the resulting
            document
          - `tz_aware` (optional): if ``True``, return timezone-aware
            :class:`~datetime.datetime` instances
          - `compile_re` (optional): if ``False``, don't attempt to compile
            BSON regular expressions into Python regular expressions. Return
            instances of
            :class:`~bson.regex.Regex` instead. Can avoid
            :exc:`~bson.errors.InvalidBSON` errors when receiving
            Python-incompatible regular expressions, for example from
            ``currentOp``

        .. versionchanged:: 2.7
           Added ``compile_re`` option.
        .. versionadded:: 1.9
        """
        (document, _) = _bson_to_dict(
            self, as_class, tz_aware, uuid_subtype, compile_re)

        return document 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def test_command_with_regex(self, test_db):
        await test_db.test.insert_one({'r': re.compile('.*')})
        await test_db.test.insert_one({'r': Regex('.*')})

        result = await test_db.command('aggregate', 'test', pipeline=[])
        for doc in result['result']:
            assert isinstance(doc['r'], Regex) 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def test_regex(self):
        for regex_instance in (
                re.compile("a*b", re.IGNORECASE),
                Regex("a*b", re.IGNORECASE)):
            res = self.round_tripped({"r": regex_instance})["r"]

            self.assertEqual("a*b", res.pattern)
            res = self.round_tripped({"r": Regex("a*b", re.IGNORECASE)})["r"]
            self.assertEqual("a*b", res.pattern)
            self.assertEqual(re.IGNORECASE, res.flags)

        unicode_options = re.I | re.M | re.S | re.U | re.X
        regex = re.compile("a*b", unicode_options)
        res = self.round_tripped({"r": regex})["r"]
        self.assertEqual(unicode_options, res.flags)

        # Some tools may not add $options if no flags are set.
        res = bsonjs_loads('{"r": {"$regex": "a*b"}}')['r']
        self.assertEqual(0, res.flags)

        self.assertEqual(
            Regex(".*", "ilm"),
            bsonjs_loads(
                '{"r": {"$regex": ".*", "$options": "ilm"}}')['r'])

        # Order should be $regex then $options
        self.assertEqual(
            '{ "regex" : { "$regex" : ".*", "$options" : "mx" } }',
            bsonjs_dumps({"regex": Regex(".*", re.M | re.X)}))

        self.assertEqual(
            '{ "regex" : { "$regex" : ".*", "$options" : "mx" } }',
            bsonjs_dumps({"regex": re.compile(b".*", re.M | re.X)})) 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def default(obj):
    # We preserve key order when rendering SON, DBRef, etc. as JSON by
    # returning a SON for those types instead of a dict.
    if isinstance(obj, ObjectId):
        return {"$oid": str(obj)}
    if isinstance(obj, DBRef):
        return _json_convert(obj.as_doc())
    if isinstance(obj, datetime.datetime):
        # TODO share this code w/ bson.py?
        if obj.utcoffset() is not None:
            obj = obj - obj.utcoffset()
        millis = int(calendar.timegm(obj.timetuple()) * 1000 +
                     obj.microsecond / 1000)
        return {"$date": millis}
    if isinstance(obj, (RE_TYPE, Regex)):
        flags = ""
        if obj.flags & re.IGNORECASE:
            flags += "i"
        if obj.flags & re.LOCALE:
            flags += "l"
        if obj.flags & re.MULTILINE:
            flags += "m"
        if obj.flags & re.DOTALL:
            flags += "s"
        if obj.flags & re.UNICODE:
            flags += "u"
        if obj.flags & re.VERBOSE:
            flags += "x"
        if isinstance(obj.pattern, text_type):
            pattern = obj.pattern
        else:
            pattern = obj.pattern.decode('utf-8')
        return SON([("$regex", pattern), ("$options", flags)])
    if isinstance(obj, MinKey):
        return {"$minKey": 1}
    if isinstance(obj, MaxKey):
        return {"$maxKey": 1}
    if isinstance(obj, Timestamp):
        return {"$timestamp": SON([("t", obj.time), ("i", obj.inc)])}
    if isinstance(obj, Code):
        return SON([('$code', str(obj)), ('$scope', obj.scope)])
    if isinstance(obj, Binary):
        return SON([
            ('$binary', base64.b64encode(obj).decode()),
            ('$type', "%02x" % obj.subtype)])
    if PY3 and isinstance(obj, bytes):
        return SON([
            ('$binary', base64.b64encode(obj).decode()),
            ('$type', "00")])
    if isinstance(obj, uuid.UUID):
        return {"$uuid": obj.hex}
    raise TypeError("%r is not JSON serializable" % obj) 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def decode_all(data, codec_options=DEFAULT_CODEC_OPTIONS):
    """Decode BSON data to multiple documents.

    `data` must be a string of concatenated, valid, BSON-encoded
    documents.

    :Parameters:
      - `data`: BSON data
      - `codec_options` (optional): An instance of
        :class:`~bson.codec_options.CodecOptions`.

    .. versionchanged:: 3.0
       Removed `compile_re` option: PyMongo now always represents BSON regular
       expressions as :class:`~bson.regex.Regex` objects. Use
       :meth:`~bson.regex.Regex.try_compile` to attempt to convert from a
       BSON regular expression to a Python regular expression object.

       Replaced `as_class`, `tz_aware`, and `uuid_subtype` options with
       `codec_options`.

    .. versionchanged:: 2.7
       Added `compile_re` option. If set to False, PyMongo represented BSON
       regular expressions as :class:`~bson.regex.Regex` objects instead of
       attempting to compile BSON regular expressions as Python native
       regular expressions, thus preventing errors for some incompatible
       patterns, see `PYTHON-500`_.

    .. _PYTHON-500: https://jira.mongodb.org/browse/PYTHON-500
    """
    if not isinstance(codec_options, CodecOptions):
        raise _CODEC_OPTIONS_TYPE_ERROR

    docs = []
    position = 0
    end = len(data) - 1
    use_raw = _raw_document_class(codec_options.document_class)
    try:
        while position < end:
            obj_size = _UNPACK_INT(data[position:position + 4])[0]
            if len(data) - position < obj_size:
                raise InvalidBSON("invalid object size")
            obj_end = position + obj_size - 1
            if data[obj_end:position + obj_size] != b"\x00":
                raise InvalidBSON("bad eoo")
            if use_raw:
                docs.append(
                    codec_options.document_class(
                        data[position:obj_end + 1], codec_options))
            else:
                docs.append(_elements_to_dict(data,
                                              position + 4,
                                              obj_end,
                                              codec_options))
            position += obj_size
        return docs
    except InvalidBSON:
        raise
    except Exception:
        # Change exception type to InvalidBSON but preserve traceback.
        _, exc_value, exc_tb = sys.exc_info()
        reraise(InvalidBSON, exc_value, exc_tb) 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def decode(self, codec_options=DEFAULT_CODEC_OPTIONS):
        """Decode this BSON data.

        By default, returns a BSON document represented as a Python
        :class:`dict`. To use a different :class:`MutableMapping` class,
        configure a :class:`~bson.codec_options.CodecOptions`::

            >>> import collections  # From Python standard library.
            >>> import bson
            >>> from bson.codec_options import CodecOptions
            >>> data = bson.BSON.encode({'a': 1})
            >>> decoded_doc = bson.BSON.decode(data)
            <type 'dict'>
            >>> options = CodecOptions(document_class=collections.OrderedDict)
            >>> decoded_doc = bson.BSON.decode(data, codec_options=options)
            >>> type(decoded_doc)
            <class 'collections.OrderedDict'>

        :Parameters:
          - `codec_options` (optional): An instance of
            :class:`~bson.codec_options.CodecOptions`.

        .. versionchanged:: 3.0
           Removed `compile_re` option: PyMongo now always represents BSON
           regular expressions as :class:`~bson.regex.Regex` objects. Use
           :meth:`~bson.regex.Regex.try_compile` to attempt to convert from a
           BSON regular expression to a Python regular expression object.

           Replaced `as_class`, `tz_aware`, and `uuid_subtype` options with
           `codec_options`.

        .. versionchanged:: 2.7
           Added `compile_re` option. If set to False, PyMongo represented BSON
           regular expressions as :class:`~bson.regex.Regex` objects instead of
           attempting to compile BSON regular expressions as Python native
           regular expressions, thus preventing errors for some incompatible
           patterns, see `PYTHON-500`_.

        .. _PYTHON-500: https://jira.mongodb.org/browse/PYTHON-500
        """
        if not isinstance(codec_options, CodecOptions):
            raise _CODEC_OPTIONS_TYPE_ERROR

        return _bson_to_dict(self, codec_options) 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def default(obj):
    # We preserve key order when rendering SON, DBRef, etc. as JSON by
    # returning a SON for those types instead of a dict. This works with
    # the "json" standard library in Python 2.6+ and with simplejson
    # 2.1.0+ in Python 2.5+, because those libraries iterate the SON
    # using PyIter_Next. Python 2.4 must use simplejson 2.0.9 or older,
    # and those versions of simplejson use the lower-level PyDict_Next,
    # which bypasses SON's order-preserving iteration, so we lose key
    # order in Python 2.4.
    if isinstance(obj, ObjectId):
        return {"$oid": str(obj)}
    if isinstance(obj, DBRef):
        return _json_convert(obj.as_doc())
    if isinstance(obj, datetime.datetime):
        # TODO share this code w/ bson.py?
        if obj.utcoffset() is not None:
            obj = obj - obj.utcoffset()
        millis = int(calendar.timegm(obj.timetuple()) * 1000 +
                     obj.microsecond / 1000)
        return {"$date": millis}
    if isinstance(obj, (RE_TYPE, Regex)):
        flags = ""
        if obj.flags & re.IGNORECASE:
            flags += "i"
        if obj.flags & re.LOCALE:
            flags += "l"
        if obj.flags & re.MULTILINE:
            flags += "m"
        if obj.flags & re.DOTALL:
            flags += "s"
        if obj.flags & re.UNICODE:
            flags += "u"
        if obj.flags & re.VERBOSE:
            flags += "x"
        if isinstance(obj.pattern, unicode):
            pattern = obj.pattern
        else:
            pattern = obj.pattern.decode('utf-8')
        return SON([("$regex", pattern), ("$options", flags)])
    if isinstance(obj, MinKey):
        return {"$minKey": 1}
    if isinstance(obj, MaxKey):
        return {"$maxKey": 1}
    if isinstance(obj, Timestamp):
        return SON([("t", obj.time), ("i", obj.inc)])
    if isinstance(obj, Code):
        return SON([('$code', str(obj)), ('$scope', obj.scope)])
    if isinstance(obj, Binary):
        return SON([
            ('$binary', base64.b64encode(obj).decode()),
            ('$type', "%02x" % obj.subtype)])
    if PY3 and isinstance(obj, binary_type):
        return SON([
            ('$binary', base64.b64encode(obj).decode()),
            ('$type', "00")])
    if bson.has_uuid() and isinstance(obj, bson.uuid.UUID):
        return {"$uuid": obj.hex}
    raise TypeError("%r is not JSON serializable" % obj) 

# 需要导入模块: from bson import regex [as 别名]
# 或者: from bson.regex import Regex [as 别名]
def decode_all(data, as_class=dict,
               tz_aware=True, uuid_subtype=OLD_UUID_SUBTYPE, compile_re=True):
    """Decode BSON data to multiple documents.

    `data` must be a string of concatenated, valid, BSON-encoded
    documents.

    :Parameters:
      - `data`: BSON data
      - `as_class` (optional): the class to use for the resulting
        documents
      - `tz_aware` (optional): if ``True``, return timezone-aware
        :class:`~datetime.datetime` instances
      - `compile_re` (optional): if ``False``, don't attempt to compile
        BSON regular expressions into Python regular expressions. Return
        instances of :class:`~bson.regex.Regex` instead. Can avoid
        :exc:`~bson.errors.InvalidBSON` errors when receiving
        Python-incompatible regular expressions, for example from ``currentOp``

    .. versionchanged:: 2.7
       Added `compile_re` option.
    .. versionadded:: 1.9
    """
    docs = []
    position = 0
    end = len(data) - 1
    try:
        while position < end:
            obj_size = struct.unpack("<i", data[position:position + 4])[0]
            if len(data) - position < obj_size:
                raise InvalidBSON("objsize too large")
            if data[position + obj_size - 1:position + obj_size] != ZERO:
                raise InvalidBSON("bad eoo")
            elements = data[position + 4:position + obj_size - 1]
            position += obj_size
            docs.append(_elements_to_dict(elements, as_class,
                                          tz_aware, uuid_subtype, compile_re))
        return docs
    except InvalidBSON:
        raise
    except Exception:
        # Change exception type to InvalidBSON but preserve traceback.
        exc_type, exc_value, exc_tb = sys.exc_info()
        raise InvalidBSON, str(exc_value), exc_tb