Python bson.regex方法代码示例

# 需要导入模块: import bson [as 别名]
# 或者: from bson import regex [as 别名]
def _parse_legacy_regex(doc):
    pattern = doc["$regex"]
    # Check if this is the $regex query operator.
    if isinstance(pattern, Regex):
        return doc
    flags = 0
    # PyMongo always adds $options but some other tools may not.
    for opt in doc.get("$options", ""):
        flags |= _RE_OPT_TABLE.get(opt, 0)
    return Regex(pattern, flags) 

# 需要导入模块: import bson [as 别名]
# 或者: from bson import regex [as 别名]
def _parse_canonical_regex(doc):
    """Decode a JSON regex to bson.regex.Regex."""
    regex = doc['$regularExpression']
    if len(doc) != 1:
        raise TypeError('Bad $regularExpression, extra field(s): %s' % (doc,))
    if len(regex) != 2:
        raise TypeError('Bad $regularExpression must include only "pattern"'
                        'and "options" components: %s' % (doc,))
    return Regex(regex['pattern'], regex['options']) 

# 需要导入模块: import bson [as 别名]
# 或者: from bson 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: import bson [as 别名]
# 或者: from bson 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, str):
            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()),
            ('$type', "%02x" % obj.subtype)])
    if PY3 and isinstance(obj, binary_type):
        return SON([
            ('$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: import bson [as 别名]
# 或者: from bson import regex [as 别名]
def object_hook(dct, json_options=DEFAULT_JSON_OPTIONS):
    if "$oid" in dct:
        return _parse_canonical_oid(dct)
    if "$ref" in dct:
        return _parse_canonical_dbref(dct)
    if "$date" in dct:
        return _parse_canonical_datetime(dct, json_options)
    if "$regex" in dct:
        return _parse_legacy_regex(dct)
    if "$minKey" in dct:
        return _parse_canonical_minkey(dct)
    if "$maxKey" in dct:
        return _parse_canonical_maxkey(dct)
    if "$binary" in dct:
        if "$type" in dct:
            return _parse_legacy_binary(dct, json_options)
        else:
            return _parse_canonical_binary(dct, json_options)
    if "$code" in dct:
        return _parse_canonical_code(dct)
    if "$uuid" in dct:
        return _parse_legacy_uuid(dct)
    if "$undefined" in dct:
        return None
    if "$numberLong" in dct:
        return _parse_canonical_int64(dct)
    if "$timestamp" in dct:
        tsp = dct["$timestamp"]
        return Timestamp(tsp["t"], tsp["i"])
    if "$numberDecimal" in dct:
        return _parse_canonical_decimal128(dct)
    if "$dbPointer" in dct:
        return _parse_canonical_dbpointer(dct)
    if "$regularExpression" in dct:
        return _parse_canonical_regex(dct)
    if "$symbol" in dct:
        return _parse_canonical_symbol(dct)
    if "$numberInt" in dct:
        return _parse_canonical_int32(dct)
    if "$numberDouble" in dct:
        return _parse_canonical_double(dct)
    return dct