requests/tests/test_utils.py

# coding: utf-8
from io import BytesIO

import pytest
from requests import compat
from requests.structures import CaseInsensitiveDict
from requests.utils import (
    address_in_network, dotted_netmask,
    get_auth_from_url, get_encoding_from_headers,
    get_encodings_from_content, get_environ_proxies,
    guess_filename, guess_json_utf, is_ipv4_address,
    is_valid_cidr, iter_slices, parse_dict_header,
    parse_header_links, prepend_scheme_if_needed,
    requote_uri, select_proxy, should_bypass_proxies, super_len,
    to_key_val_list, to_native_string,
    unquote_header_value, unquote_unreserved,
    urldefragauth)

from .compat import StringIO, cStringIO


class TestSuperLen:

    @pytest.mark.parametrize(
        'stream, value', (
            (StringIO.StringIO, 'Test'),
            (BytesIO, b'Test'),
            pytest.mark.skipif('cStringIO is None')((cStringIO, 'Test')),
        ))
    def test_io_streams(self, stream, value):
        """Ensures that we properly deal with different kinds of IO streams."""
        assert super_len(stream()) == 0
        assert super_len(stream(value)) == 4

    def test_super_len_correctly_calculates_len_of_partially_read_file(self):
        """Ensure that we handle partially consumed file like objects."""
        s = StringIO.StringIO()
        s.write('foobarbogus')
        assert super_len(s) == 0

    @pytest.mark.parametrize('error', [IOError, OSError])
    def test_super_len_handles_files_raising_weird_errors_in_tell(self, error):
        """
        If tell() raises errors, assume the cursor is at position zero.
        """
        class BoomFile(object):
            def __len__(self):
                return 5

            def tell(self):
                raise error()

        assert super_len(BoomFile()) == 0

    def test_string(self):
        assert super_len('Test') == 4

    @pytest.mark.parametrize(
        'mode, warnings_num', (
            ('r', 1),
            ('rb', 0),
        ))
    def test_file(self, tmpdir, mode, warnings_num, recwarn):
        file_obj = tmpdir.join('test.txt')
        file_obj.write('Test')
        with file_obj.open(mode) as fd:
            assert super_len(fd) == 4
        assert len(recwarn) == warnings_num


class TestToKeyValList:

    @pytest.mark.parametrize(
        'value, expected', (
            ([('key', 'val')], [('key', 'val')]),
            ((('key', 'val'), ), [('key', 'val')]),
            ({'key': 'val'}, [('key', 'val')]),
            (None, None)
        ))
    def test_valid(self, value, expected):
        assert to_key_val_list(value) == expected

    def test_invalid(self):
        with pytest.raises(ValueError):
            to_key_val_list('string')


class TestUnquoteHeaderValue:

    @pytest.mark.parametrize(
        'value, expected', (
            (None, None),
            ('Test', 'Test'),
            ('"Test"', 'Test'),
            ('"Test\\\\"', 'Test\\'),
            ('"\\\\Comp\\Res"', '\\Comp\\Res'),
        ))
    def test_valid(self, value, expected):
        assert unquote_header_value(value) == expected

    def test_is_filename(self):
        assert unquote_header_value('"\\\\Comp\\Res"', True) == '\\\\Comp\\Res'


class TestGetEnvironProxies:
    """Ensures that IP addresses are correctly matches with ranges
    in no_proxy variable."""

    @pytest.fixture(autouse=True, params=['no_proxy', 'NO_PROXY'])
    def no_proxy(self, request, monkeypatch):
        monkeypatch.setenv(request.param, '192.168.0.0/24,127.0.0.1,localhost.localdomain,172.16.1.1')

    @pytest.mark.parametrize(
        'url', (
            'http://192.168.0.1:5000/',
            'http://192.168.0.1/',
            'http://172.16.1.1/',
            'http://172.16.1.1:5000/',
            'http://localhost.localdomain:5000/v1.0/',
        ))
    def test_bypass(self, url):
        assert get_environ_proxies(url) == {}

    @pytest.mark.parametrize(
        'url', (
            'http://192.168.1.1:5000/',
            'http://192.168.1.1/',
            'http://www.requests.com/',
        ))
    def test_not_bypass(self, url):
        assert get_environ_proxies(url) != {}


class TestIsIPv4Address:

    def test_valid(self):
        assert is_ipv4_address('8.8.8.8')

    @pytest.mark.parametrize('value', ('8.8.8.8.8', 'localhost.localdomain'))
    def test_invalid(self, value):
        assert not is_ipv4_address(value)


class TestIsValidCIDR:

    def test_valid(self):
        assert is_valid_cidr('192.168.1.0/24')

    @pytest.mark.parametrize(
        'value', (
            '8.8.8.8',
            '192.168.1.0/a',
            '192.168.1.0/128',
            '192.168.1.0/-1',
            '192.168.1.999/24',
        ))
    def test_invalid(self, value):
        assert not is_valid_cidr(value)


class TestAddressInNetwork:

    def test_valid(self):
        assert address_in_network('192.168.1.1', '192.168.1.0/24')

    def test_invalid(self):
        assert not address_in_network('172.16.0.1', '192.168.1.0/24')


class TestGuessFilename:

    @pytest.mark.parametrize(
        'value', (1, type('Fake', (object,), {'name': 1})()),
    )
    def test_guess_filename_invalid(self, value):
        assert guess_filename(value) is None

    @pytest.mark.parametrize(
        'value, expected_type', (
            (b'value', compat.bytes),
            (b'value'.decode('utf-8'), compat.str)
        ))
    def test_guess_filename_valid(self, value, expected_type):
        obj = type('Fake', (object,), {'name': value})()
        result = guess_filename(obj)
        assert result == value
        assert isinstance(result, expected_type)


class TestContentEncodingDetection:

    def test_none(self):
        encodings = get_encodings_from_content('')
        assert not len(encodings)

    @pytest.mark.parametrize(
        'content', (
            # HTML5 meta charset attribute
            '<meta charset="UTF-8">',
            # HTML4 pragma directive
            '<meta http-equiv="Content-type" content="text/html;charset=UTF-8">',
            # XHTML 1.x served with text/html MIME type
            '<meta http-equiv="Content-type" content="text/html;charset=UTF-8" />',
            # XHTML 1.x served as XML
            '<?xml version="1.0" encoding="UTF-8"?>',
        ))
    def test_pragmas(self, content):
        encodings = get_encodings_from_content(content)
        assert len(encodings) == 1
        assert encodings[0] == 'UTF-8'

    def test_precedence(self):
        content = '''
        <?xml version="1.0" encoding="XML"?>
        <meta charset="HTML5">
        <meta http-equiv="Content-type" content="text/html;charset=HTML4" />
        '''.strip()
        assert get_encodings_from_content(content) == ['HTML5', 'HTML4', 'XML']


class TestGuessJSONUTF:

    @pytest.mark.parametrize(
        'encoding', (
            'utf-32', 'utf-8-sig', 'utf-16', 'utf-8', 'utf-16-be', 'utf-16-le',
            'utf-32-be', 'utf-32-le'
        ))
    def test_encoded(self, encoding):
        data = '{}'.encode(encoding)
        assert guess_json_utf(data) == encoding

    def test_bad_utf_like_encoding(self):
        assert guess_json_utf(b'\x00\x00\x00\x00') is None


USER = PASSWORD = "%!*'();:@&=+$,/?#[] "
ENCODED_USER = compat.quote(USER, '')
ENCODED_PASSWORD = compat.quote(PASSWORD, '')


@pytest.mark.parametrize(
    'url, auth', (
        (
            'http://' + ENCODED_USER + ':' + ENCODED_PASSWORD + '@' +
            'request.com/url.html#test',
            (USER, PASSWORD)
        ),
        (
            'http://user:pass@complex.url.com/path?query=yes',
            ('user', 'pass')
        ),
        (
            'http://user:pass%20pass@complex.url.com/path?query=yes',
            ('user', 'pass pass')
        ),
        (
            'http://user:pass pass@complex.url.com/path?query=yes',
            ('user', 'pass pass')
        ),
        (
            'http://user%25user:pass@complex.url.com/path?query=yes',
            ('user%user', 'pass')
        ),
        (
            'http://user:pass%23pass@complex.url.com/path?query=yes',
            ('user', 'pass#pass')
        ),
        (
            'http://complex.url.com/path?query=yes',
            ('', '')
        ),
    ))
def test_get_auth_from_url(url, auth):
    assert get_auth_from_url(url) == auth


@pytest.mark.parametrize(
    'uri, expected', (
        (
            # Ensure requoting doesn't break expectations
            'http://example.com/fiz?buz=%25ppicture',
            'http://example.com/fiz?buz=%25ppicture',
        ),
        (
            # Ensure we handle unquoted percent signs in redirects
            'http://example.com/fiz?buz=%ppicture',
            'http://example.com/fiz?buz=%25ppicture',
        ),
    ))
def test_requote_uri_with_unquoted_percents(uri, expected):
    """See: https://github.com/kennethreitz/requests/issues/2356
    """
    assert requote_uri(uri) == expected


@pytest.mark.parametrize(
    'uri, expected', (
        (
            # Illegal bytes
            'http://example.com/?a=%--',
            'http://example.com/?a=%--',
        ),
        (
            # Reserved characters
            'http://example.com/?a=%300',
            'http://example.com/?a=00',
        )
    ))
def test_unquote_unreserved(uri, expected):
    assert unquote_unreserved(uri) == expected


@pytest.mark.parametrize(
    'mask, expected', (
        (8, '255.0.0.0'),
        (24, '255.255.255.0'),
        (25, '255.255.255.128'),
    ))
def test_dotted_netmask(mask, expected):
    assert dotted_netmask(mask) == expected


@pytest.mark.parametrize(
    'url, expected', (
        ('hTTp://u:p@Some.Host/path', 'http://some.host.proxy'),
        ('hTTp://u:p@Other.Host/path', 'http://http.proxy'),
        ('hTTps://Other.Host', None),
        ('file:///etc/motd', None),
    ))
def test_select_proxies(url, expected):
    """Make sure we can select per-host proxies correctly."""
    proxies = {'http': 'http://http.proxy',
               'http://some.host': 'http://some.host.proxy'}
    assert select_proxy(url, proxies) == expected


@pytest.mark.parametrize(
    'value, expected', (
        ('foo="is a fish", bar="as well"', {'foo': 'is a fish', 'bar': 'as well'}),
        ('key_without_value', {'key_without_value': None})
    ))
def test_parse_dict_header(value, expected):
    assert parse_dict_header(value) == expected


@pytest.mark.parametrize(
    'value, expected', (
        (
            CaseInsensitiveDict(),
            None
        ),
        (
            CaseInsensitiveDict({'content-type': 'application/json; charset=utf-8'}),
            'utf-8'
        ),
        (
            CaseInsensitiveDict({'content-type': 'text/plain'}),
            'ISO-8859-1'
        ),
    ))
def test_get_encoding_from_headers(value, expected):
    assert get_encoding_from_headers(value) == expected


@pytest.mark.parametrize(
    'value, length', (
        ('', 0),
        ('T', 1),
        ('Test', 4),
    ))
def test_iter_slices(value, length):
    assert len(list(iter_slices(value, 1))) == length


@pytest.mark.parametrize(
    'value, expected', (
        (
            '<http:/.../front.jpeg>; rel=front; type="image/jpeg"',
            [{'url': 'http:/.../front.jpeg', 'rel': 'front', 'type': 'image/jpeg'}]
        ),
        (
            '<http:/.../front.jpeg>',
            [{'url': 'http:/.../front.jpeg'}]
        ),
        (
            '<http:/.../front.jpeg>;',
            [{'url': 'http:/.../front.jpeg'}]
        ),
        (
            '<http:/.../front.jpeg>; type="image/jpeg",<http://.../back.jpeg>;',
            [
                {'url': 'http:/.../front.jpeg', 'type': 'image/jpeg'},
                {'url': 'http://.../back.jpeg'}
            ]
        ),
    ))
def test_parse_header_links(value, expected):
    assert parse_header_links(value) == expected


@pytest.mark.parametrize(
    'value, expected', (
        ('example.com/path', 'http://example.com/path'),
        ('//example.com/path', 'http://example.com/path'),
    ))
def test_prepend_scheme_if_needed(value, expected):
    assert prepend_scheme_if_needed(value, 'http') == expected


@pytest.mark.parametrize(
    'value, expected', (
        ('T', 'T'),
        (b'T', 'T'),
        (u'T', 'T'),
    ))
def test_to_native_string(value, expected):
    assert to_native_string(value) == expected


@pytest.mark.parametrize(
    'url, expected', (
        ('http://u:p@example.com/path?a=1#test', 'http://example.com/path?a=1'),
        ('http://example.com/path', 'http://example.com/path'),
        ('//u:p@example.com/path', '//example.com/path'),
        ('//example.com/path', '//example.com/path'),
        ('example.com/path', '//example.com/path'),
        ('scheme:u:p@example.com/path', 'scheme://example.com/path'),
    ))
def test_urldefragauth(url, expected):
    assert urldefragauth(url) == expected


@pytest.mark.parametrize(
    'url, expected', (
            ('http://192.168.0.1:5000/', True),
            ('http://192.168.0.1/', True),
            ('http://172.16.1.1/', True),
            ('http://172.16.1.1:5000/', True),
            ('http://localhost.localdomain:5000/v1.0/', True),
            ('http://172.16.1.12/', False),
            ('http://172.16.1.12:5000/', False),
            ('http://google.com:5000/v1.0/', False),
    ))
def test_should_bypass_proxies(url, expected, monkeypatch):
    """
    Tests for function should_bypass_proxies to check if proxy can be bypassed or not
    """
    monkeypatch.setenv('no_proxy', '192.168.0.0/24,127.0.0.1,localhost.localdomain,172.16.1.1')
    monkeypatch.setenv('NO_PROXY', '192.168.0.0/24,127.0.0.1,localhost.localdomain,172.16.1.1')
    assert should_bypass_proxies(url) == expected