qs-codec 0.2.2

A query string encoding and decoding library for Python. Ported from qs for JavaScript.

A query string encoding and decoding library for Python.

Ported from qs for JavaScript.

Usage

A simple usage example:

import qs_codec

# Encoding
assert qs_codec.encode({'a': 'b'}) == 'a=b'

# Decoding
assert qs_codec.decode('a=b') == {'a': 'b'}

Decoding

dictionaries

import qs_codec, typing as t

def decode(
    value: t.Optional[t.Union[str, t.Mapping]],
    options: qs_codec.DecodeOptions = qs_codec.DecodeOptions(),
) -> t.Dict[str, t.Any]:
    """Decodes a str or Mapping into a Dict.

    Providing custom DecodeOptions will override the default behavior."""
    pass

decode allows you to create nested dicts within your query strings, by surrounding the name of sub-keys with square brackets []. For example, the string 'foo[bar]=baz' converts to:

import qs_codec

assert qs_codec.decode('foo[bar]=baz') == {'foo': {'bar': 'baz'}}

URI encoded strings work too:

import qs_codec

assert qs_codec.decode('a%5Bb%5D=c') == {'a': {'b': 'c'}}

You can also nest your dicts, like 'foo[bar][baz]=foobarbaz':

import qs_codec

assert qs_codec.decode('foo[bar][baz]=foobarbaz') == {'foo': {'bar': {'baz': 'foobarbaz'}}}

By default, when nesting dicts qs will only decode up to 5 children deep. This means if you attempt to decode a string like 'a[b][c][d][e][f][g][h][i]=j' your resulting dict will be:

import qs_codec

assert qs_codec.decode("a[b][c][d][e][f][g][h][i]=j") == {
    "a": {"b": {"c": {"d": {"e": {"f": {"[g][h][i]": "j"}}}}}}
}

This depth can be overridden by setting the depth:

import qs_codec

assert qs_codec.decode(
    'a[b][c][d][e][f][g][h][i]=j',
    qs_codec.DecodeOptions(depth=1),
) == {'a': {'b': {'[c][d][e][f][g][h][i]': 'j'}}}

The depth limit helps mitigate abuse when decode is used to parse user input, and it is recommended to keep it a reasonably small number.

For similar reasons, by default decode will only parse up to 1000 parameters. This can be overridden by passing a parameter_limit option:

import qs_codec

assert qs_codec.decode(
    'a=b&c=d',
    qs_codec.DecodeOptions(parameter_limit=1),
) == {'a': 'b'}

To bypass the leading question mark, use ignore_query_prefix:

import qs_codec

assert qs_codec.decode(
    '?a=b&c=d',
    qs_codec.DecodeOptions(ignore_query_prefix=True),
) == {'a': 'b', 'c': 'd'}

An optional delimiter can also be passed:

import qs_codec

assert qs_codec.decode(
    'a=b;c=d',
    qs_codec.DecodeOptions(delimiter=';'),
) == {'a': 'b', 'c': 'd'}

delimiter can be a regular expression too:

import re, qs_codec

assert qs_codec.decode(
    'a=b;c=d',
    qs_codec.DecodeOptions(delimiter=re.compile(r'[;,]')),
) == {'a': 'b', 'c': 'd'}

Option allow_dots can be used to enable dot notation:

import qs_codec

assert qs_codec.decode(
    'a.b=c',
    qs_codec.DecodeOptions(allow_dots=True),
) == {'a': {'b': 'c'}}

Option decode_dot_in_keys can be used to decode dots in keys.

Note: it implies allow_dots, so decode will error if you set decode_dot_in_keys to True, and allow_dots to False.

import qs_codec

assert qs_codec.decode(
    'name%252Eobj.first=John&name%252Eobj.last=Doe',
    qs_codec.DecodeOptions(decode_dot_in_keys=True),
) == {'name.obj': {'first': 'John', 'last': 'Doe'}}

Option allow_empty_lists can be used to allowing empty list values in a dict

import qs_codec

assert qs_codec.decode(
    'foo[]&bar=baz',
    qs_codec.DecodeOptions(allow_empty_lists=True),
) == {'foo': [], 'bar': 'baz'}

Option duplicates can be used to change the behavior when duplicate keys are encountered

import qs_codec

assert qs_codec.decode('foo=bar&foo=baz') == {'foo': ['bar', 'baz']}

assert qs_codec.decode(
    'foo=bar&foo=baz',
    qs_codec.DecodeOptions(duplicates=qs_codec.Duplicates.COMBINE),
) == {'foo': ['bar', 'baz']}

assert qs_codec.decode(
    'foo=bar&foo=baz',
    qs_codec.DecodeOptions(duplicates=qs_codec.Duplicates.FIRST),
) == {'foo': 'bar'}

assert qs_codec.decode(
    'foo=bar&foo=baz',
    qs_codec.DecodeOptions(duplicates=qs_codec.Duplicates.LAST),
) == {'foo': 'baz'}

If you have to deal with legacy browsers or services, there’s also support for decoding percent-encoded octets as LATIN1:

import qs_codec

assert qs_codec.decode(
    'a=%A7',
    qs_codec.DecodeOptions(charset=qs_codec.Charset.LATIN1),
) == {'a': '§'}

Some services add an initial utf8=✓ value to forms so that old Internet Explorer versions are more likely to submit the form as utf-8. Additionally, the server can check the value against wrong encodings of the checkmark character and detect that a query string or application/x-www-form-urlencoded body was not sent as utf-8, e.g. if the form had an accept-charset parameter or the containing page had a different character set.

decode supports this mechanism via the charset_sentinel option. If specified, the utf8 parameter will be omitted from the returned dict. It will be used to switch to LATIN1 or UTF8 mode depending on how the checkmark is encoded.

Important: When you specify both the charset option and the charset_sentinel option, the charset will be overridden when the request contains a utf8 parameter from which the actual charset can be deduced. In that sense the charset will behave as the default charset rather than the authoritative charset.

import qs_codec

assert qs_codec.decode(
    'utf8=%E2%9C%93&a=%C3%B8',
    qs_codec.DecodeOptions(
        charset=qs_codec.Charset.LATIN1,
        charset_sentinel=True,
    ),
) == {'a': 'ø'}

assert qs_codec.decode(
    'utf8=%26%2310003%3B&a=%F8',
    qs_codec.DecodeOptions(
        charset=qs_codec.Charset.UTF8,
        charset_sentinel=True,
    ),
) == {'a': 'ø'}

If you want to decode the &#…; syntax to the actual character, you can specify the interpret_numeric_entities option as well:

import qs_codec

assert qs_codec.decode(
    'a=%26%239786%3B',
    qs_codec.DecodeOptions(
        charset=qs_codec.Charset.LATIN1,
        interpret_numeric_entities=True,
    ),
) == {'a': '☺'}

It also works when the charset has been detected in charset_sentinel mode.

lists

decode can also decode lists using a similar [] notation:

import qs_codec

assert qs_codec.decode('a[]=b&a[]=c') == {'a': ['b', 'c']}

You may specify an index as well:

import qs_codec

assert qs_codec.decode('a[1]=c&a[0]=b') == {'a': ['b', 'c']}

Note that the only difference between an index in a list and a key in a dict is that the value between the brackets must be a number to create a list. When creating lists with specific indices, decode will compact a sparse list to only the existing values preserving their order:

import qs_codec

assert qs_codec.decode('a[1]=b&a[15]=c') == {'a': ['b', 'c']}

Note that an empty string is also a value, and will be preserved:

import qs_codec

assert qs_codec.decode('a[]=&a[]=b') == {'a': ['', 'b']}

assert qs_codec.decode('a[0]=b&a[1]=&a[2]=c') == {'a': ['b', '', 'c']}

decode will also limit specifying indices in a list to a maximum index of 20. Any list members with an index of greater than 20 will instead be converted to a dict with the index as the key. This is needed to handle cases when someone sent, for example, a[999999999] and it will take significant time to iterate over this huge list.

import qs_codec

assert qs_codec.decode('a[100]=b') == {'a': {'100': 'b'}}

This limit can be overridden by passing an list_limit option:

import qs_codec

assert qs_codec.decode(
    'a[1]=b',
    qs_codec.DecodeOptions(list_limit=0),
) == {'a': {'1': 'b'}}

To disable list parsing entirely, set parse_lists to False.

import qs_codec

assert qs_codec.decode(
    'a[]=b',
    qs_codec.DecodeOptions(parse_lists=False),
) == {'a': {'0': 'b'}}

If you mix notations, decode will merge the two items into a dict:

import qs_codec

assert qs_codec.decode('a[0]=b&a[b]=c') == {'a': {'0': 'b', 'b': 'c'}}

You can also create lists of dicts:

import qs_codec

assert qs_codec.decode('a[][b]=c') == {'a': [{'b': 'c'}]}

(decode cannot convert nested ``dict``s, such as ``’a={b:1},{c:d}’``)

primitive values (int, bool, None, etc.)

By default, all values are parsed as strings.

import qs_codec

assert qs_codec.decode(
    'a=15&b=true&c=null',
) == {'a': '15', 'b': 'true', 'c': 'null'}

Encoding

import qs_codec, typing as t

def encode(
    value: t.Any,
    options: qs_codec.EncodeOptions = qs_codec.EncodeOptions()
) -> str:
    """Encodes an object into a query string.

    Providing custom EncodeOptions will override the default behavior."""
    pass

When encoding, encode by default URI encodes output. dicts are encoded as you would expect:

import qs_codec

assert qs_codec.encode({'a': 'b'}) == 'a=b'
assert qs_codec.encode({'a': {'b': 'c'}}) == 'a%5Bb%5D=c'

This encoding can be disabled by setting the encode option to False:

import qs_codec

assert qs_codec.encode(
    {'a': {'b': 'c'}},
    qs_codec.EncodeOptions(encode=False),
) == 'a[b]=c'

Encoding can be disabled for keys by setting the encode_values_only option to True:

import qs_codec

assert qs_codec.encode(
    {
        'a': 'b',
        'c': ['d', 'e=f'],
        'f': [
            ['g'],
            ['h']
        ]
    },
    qs_codec.EncodeOptions(encode_values_only=True)
) == 'a=b&c[0]=d&c[1]=e%3Df&f[0][0]=g&f[1][0]=h'

This encoding can also be replaced by a custom Callable in the encoder option:

import qs_codec, typing as t


def custom_encoder(
    value: str,
    charset: t.Optional[qs_codec.Charset],
    format: t.Optional[qs_codec.Format],
) -> str:
    if value == 'č':
        return 'c'
    return value


assert qs_codec.encode(
    {'a': {'b': 'č'}},
    qs_codec.EncodeOptions(encoder=custom_encoder),
) == 'a[b]=c'

(Note: the encoder option does not apply if encode is False).

Similar to encoder there is a decoder option for decode to override decoding of properties and values:

import qs_codec, typing as t

def custom_decoder(
    value: t.Any,
    charset: t.Optional[qs_codec.Charset],
) -> t.Union[int, str]:
    try:
        return int(value)
    except ValueError:
        return value

assert qs_codec.decode(
    'foo=123',
    qs_codec.DecodeOptions(decoder=custom_decoder),
) == {'foo': 123}

Examples beyond this point will be shown as though the output is not URI encoded for clarity. Please note that the return values in these cases will be URI encoded during real usage.

When lists are encoded, they follow the list_format option, which defaults to INDICES:

import qs_codec

assert qs_codec.encode(
    {'a': ['b', 'c', 'd']},
    qs_codec.EncodeOptions(encode=False)
) == 'a[0]=b&a[1]=c&a[2]=d'

You may override this by setting the indices option to False, or to be more explicit, the list_format option to REPEAT:

import qs_codec

assert qs_codec.encode(
    {'a': ['b', 'c', 'd']},
    qs_codec.EncodeOptions(
        encode=False,
        indices=False,
    ),
) == 'a=b&a=c&a=d'

You may use the list_format option to specify the format of the output list:

import qs_codec

# ListFormat.INDICES
assert qs_codec.encode(
    {'a': ['b', 'c']},
    qs_codec.EncodeOptions(
        encode=False,
        list_format=qs_codec.ListFormat.INDICES,
    ),
) == 'a[0]=b&a[1]=c'

# ListFormat.BRACKETS
assert qs_codec.encode(
    {'a': ['b', 'c']},
    qs_codec.EncodeOptions(
        encode=False,
        list_format=qs_codec.ListFormat.BRACKETS,
    ),
) == 'a[]=b&a[]=c'

# ListFormat.REPEAT
assert qs_codec.encode(
    {'a': ['b', 'c']},
    qs_codec.EncodeOptions(
        encode=False,
        list_format=qs_codec.ListFormat.REPEAT,
    ),
) == 'a=b&a=c'

# ListFormat.COMMA
assert qs_codec.encode(
    {'a': ['b', 'c']},
    qs_codec.EncodeOptions(
        encode=False,
        list_format=qs_codec.ListFormat.COMMA,
    ),
) == 'a=b,c'

Note: When using list_format set to COMMA, you can also pass the comma_round_trip option set to True or False, to append [] on single-item lists, so that they can round trip through a decoding.

BRACKETS notation is used for encoding dicts by default:

import qs_codec

assert qs_codec.encode(
    {'a': {'b': {'c': 'd', 'e': 'f'}}},
    qs_codec.EncodeOptions(encode=False),
) == 'a[b][c]=d&a[b][e]=f'

You may override this to use dot notation by setting the allow_dots option to True:

import qs_codec

assert qs_codec.encode(
    {'a': {'b': {'c': 'd', 'e': 'f'}}},
    qs_codec.EncodeOptions(encode=False, allow_dots=True),
) == 'a.b.c=d&a.b.e=f'

You may encode dots in keys of dicts by setting encode_dot_in_keys to True:

import qs_codec

assert qs_codec.encode(
    {'name.obj': {'first': 'John', 'last': 'Doe'}},
    qs_codec.EncodeOptions(
        allow_dots=True,
        encode_dot_in_keys=True,
    ),
) == 'name%252Eobj.first=John&name%252Eobj.last=Doe'

Caveat: When both encode_values_only and encode_dot_in_keys are set to True, only dots in keys and nothing else will be encoded!

You may allow empty list values by setting the allow_empty_lists option to True:

import qs_codec

assert qs_codec.encode(
    {'foo': [], 'bar': 'baz', },
    qs_codec.EncodeOptions(
        encode=False,
        allow_empty_lists=True,
    ),
) == 'foo[]&bar=baz'

Empty strings and None values will be omitted, but the equals sign (=) remains in place:

import qs_codec

assert qs_codec.encode({'a': ''}) == 'a='

Keys with no values (such as an empty dict or list) will return nothing:

import qs_codec

assert qs_codec.encode({'a': []}) == ''

assert qs_codec.encode({'a': {}}) == ''

assert qs_codec.encode({'a': [{}]}) == ''

assert qs_codec.encode({'a': {'b': []}}) == ''

assert qs_codec.encode({'a': {'b': {}}}) == ''

Undefined properties will be omitted entirely:

import qs_codec

assert qs_codec.encode({'a': None, 'b': qs_codec.Undefined()}) == 'a='

The query string may optionally be prepended with a question mark (?) by setting add_query_prefix to True:

import qs_codec

assert qs_codec.encode(
    {'a': 'b', 'c': 'd'},
    qs_codec.EncodeOptions(add_query_prefix=True),
) == '?a=b&c=d'

The delimiter may be overridden as well:

import qs_codec

assert qs_codec.encode(
    {'a': 'b', 'c': 'd', },
    qs_codec.EncodeOptions(delimiter=';')
) == 'a=b;c=d'

If you only want to override the serialization of datetime objects, you can provide a Callable in the serialize_date option:

import qs_codec, datetime, sys

# First case: encoding a datetime object to an ISO 8601 string
assert (
    qs_codec.encode(
        {
            "a": (
                datetime.datetime.fromtimestamp(7, datetime.UTC)
                if sys.version_info.major == 3 and sys.version_info.minor >= 11
                else datetime.datetime.utcfromtimestamp(7)
            )
        },
        qs_codec.EncodeOptions(encode=False),
    )
    == "a=1970-01-01T00:00:07+00:00"
    if sys.version_info.major == 3 and sys.version_info.minor >= 11
    else "a=1970-01-01T00:00:07"
)

# Second case: encoding a datetime object to a timestamp string
assert (
    qs_codec.encode(
        {
            "a": (
                datetime.datetime.fromtimestamp(7, datetime.UTC)
                if sys.version_info.major == 3 and sys.version_info.minor >= 11
                else datetime.datetime.utcfromtimestamp(7)
            )
        },
        qs_codec.EncodeOptions(encode=False, serialize_date=lambda date: str(int(date.timestamp()))),
    )
    == "a=7"
)

To affect the order of parameter keys, you can set a Callable in the sort option:

import qs_codec

assert qs_codec.encode(
    {'a': 'c', 'z': 'y', 'b': 'f'},
    qs_codec.EncodeOptions(
        encode=False,
        sort=lambda a, b: (a > b) - (a < b)
    )
) == 'a=c&b=f&z=y'

Finally, you can use the filter option to restrict which keys will be included in the encoded output. If you pass a Callable, it will be called for each key to obtain the replacement value. Otherwise, if you pass a list, it will be used to select properties and list indices to be encoded:

import qs_codec, datetime, sys

# First case: using a Callable as filter
assert (
    qs_codec.encode(
        {
            "a": "b",
            "c": "d",
            "e": {
                "f": (
                    datetime.datetime.fromtimestamp(123, datetime.UTC)
                    if sys.version_info.major == 3 and sys.version_info.minor >= 11
                    else datetime.datetime.utcfromtimestamp(123)
                ),
                "g": [2],
            },
        },
        qs_codec.EncodeOptions(
            encode=False,
            filter=lambda prefix, value: {
                "b": None,
                "e[f]": int(value.timestamp()) if isinstance(value, datetime.datetime) else value,
                "e[g][0]": value * 2 if isinstance(value, int) else value,
            }.get(prefix, value),
        ),
    )
    == "a=b&c=d&e[f]=123&e[g][0]=4"
)

# Second case: using a list as filter
assert qs_codec.encode(
    {'a': 'b', 'c': 'd', 'e': 'f'},
    qs_codec.EncodeOptions(
        encode=False,
        filter=['a', 'e']
    )
) == 'a=b&e=f'

# Third case: using a list as filter with indices
assert qs_codec.encode(
    {
        'a': ['b', 'c', 'd'],
        'e': 'f',
    },
    qs_codec.EncodeOptions(
        encode=False,
        filter=['a', 0, 2]
    )
) == 'a[0]=b&a[2]=d'

Handling None values

By default, None values are treated like empty strings:

import qs_codec

assert qs_codec.encode({'a': None, 'b': ''}) == 'a=&b='

To distinguish between None values and empty strs use the strict_null_handling flag. In the result string the None values have no = sign:

import qs_codec

assert qs_codec.encode(
    {'a': None, 'b': ''},
    qs_codec.EncodeOptions(strict_null_handling=True),
) == 'a&b='

To decode values without = back to None use the strict_null_handling flag:

import qs_codec

assert qs_codec.decode(
    'a&b=',
    qs_codec.DecodeOptions(strict_null_handling=True),
) == {'a': None, 'b': ''}

To completely skip rendering keys with None values, use the skip_nulls flag:

import qs_codec

assert qs_codec.encode(
    {'a': 'b', 'c': None},
    qs_codec.EncodeOptions(skip_nulls=True),
) == 'a=b'

If you’re communicating with legacy systems, you can switch to LATIN1 using the charset option:

import qs_codec

assert qs_codec.encode(
    {'æ': 'æ'},
    qs_codec.EncodeOptions(charset=qs_codec.Charset.LATIN1)
) == '%E6=%E6'

Characters that don’t exist in LATIN1 will be converted to numeric entities, similar to what browsers do:

import qs_codec

assert qs_codec.encode(
    {'a': '☺'},
    qs_codec.EncodeOptions(charset=qs_codec.Charset.LATIN1)
) == 'a=%26%239786%3B'

You can use the charset_sentinel option to announce the character by including an utf8=✓ parameter with the proper encoding of the checkmark, similar to what Ruby on Rails and others do when submitting forms.

import qs_codec

assert qs_codec.encode(
    {'a': '☺'},
    qs_codec.EncodeOptions(charset_sentinel=True)
) == 'utf8=%E2%9C%93&a=%E2%98%BA'

assert qs_codec.encode(
    {'a': 'æ'},
    qs_codec.EncodeOptions(charset=qs_codec.Charset.LATIN1, charset_sentinel=True)
) == 'utf8=%26%2310003%3B&a=%E6'

Dealing with special character sets

By default, the encoding and decoding of characters is done in UTF8, and LATIN1 support is also built in via the charset and charset parameter, respectively.

If you wish to encode query strings to a different character set (i.e. Shift JIS)

import qs_codec, codecs, typing as t

def custom_encoder(
    string: str,
    charset: t.Optional[qs_codec.Charset],
    format: t.Optional[qs_codec.Format],
) -> str:
    if string:
        buf: bytes = codecs.encode(string, 'shift_jis')
        result: t.List[str] = ['{:02x}'.format(b) for b in buf]
        return '%' + '%'.join(result)
    return ''

assert qs_codec.encode(
    {'a': 'こんにちは！'},
    qs_codec.EncodeOptions(encoder=custom_encoder)
) == '%61=%82%b1%82%f1%82%c9%82%bf%82%cd%81%49'

This also works for decoding of query strings:

import qs_codec, re, codecs, typing as t

def custom_decoder(
    string: str,
    charset: t.Optional[qs_codec.Charset],
) -> t.Optional[str]:
    if string:
        result: t.List[int] = []
        while string:
            match: t.Optional[t.Match[str]] = re.search(r'%([0-9A-F]{2})', string, re.IGNORECASE)
            if match:
                result.append(int(match.group(1), 16))
                string = string[match.end():]
            else:
                break
        buf: bytes = bytes(result)
        return codecs.decode(buf, 'shift_jis')
    return None

assert qs_codec.decode(
    '%61=%82%b1%82%f1%82%c9%82%bf%82%cd%81%49',
    qs_codec.DecodeOptions(decoder=custom_decoder)
) == {'a': 'こんにちは！'}

RFC 3986 and RFC 1738 space encoding

The default format is RFC3986 which encodes ' ' to %20 which is backward compatible. You can also set the format to RFC1738 which encodes ' ' to +.

import qs_codec

assert qs_codec.encode(
    {'a': 'b c'},
    qs_codec.EncodeOptions(format=qs_codec.Format.RFC3986)
) == 'a=b%20c'

assert qs_codec.encode(
    {'a': 'b c'},
    qs_codec.EncodeOptions(format=qs_codec.Format.RFC3986)
) == 'a=b%20c'

assert qs_codec.encode(
    {'a': 'b c'},
    qs_codec.EncodeOptions(format=qs_codec.Format.RFC1738)
) == 'a=b+c'

---

Special thanks to the authors of qs for JavaScript: - Jordan Harband - TJ Holowaychuk