- test_utils.py

# imports
from collections import namedtuple
from urllib.parse import parse_qs, unquote, urlencode, urlsplit, urlunsplit

import pytest  # used for our unit tests

# function to test
SENSITIVE_DATA_SUBSTITUTE = "SENSITIVE_DATA_SUBSTITUTE"

def sanitize_url(url, remove_authority=True, remove_query_values=True, split=False):
    # type: (str, bool, bool, bool) -> Union[str, Components]
    """
    Removes the authority and query parameter values from a given URL.
    """
    parsed_url = urlsplit(url)
    query_params = parse_qs(parsed_url.query, keep_blank_values=True)

    # strip username:password (netloc can be usr:[email protected])
    if remove_authority:
        netloc_parts = parsed_url.netloc.split("@")
        if len(netloc_parts) > 1:
            netloc = "%s:%s@%s" % (
                SENSITIVE_DATA_SUBSTITUTE,
                SENSITIVE_DATA_SUBSTITUTE,
                netloc_parts[-1],
            )
        else:
            netloc = parsed_url.netloc
    else:
        netloc = parsed_url.netloc

    # strip values from query string
    if remove_query_values:
        query_string = unquote(
            urlencode({key: SENSITIVE_DATA_SUBSTITUTE for key in query_params})
        )
    else:
        query_string = parsed_url.query

    components = Components(
        scheme=parsed_url.scheme,
        netloc=netloc,
        query=query_string,
        path=parsed_url.path,
        fragment=parsed_url.fragment,
    )

    if split:
        return components
    else:
        return urlunsplit(components)

Components = namedtuple("Components", ["scheme", "netloc", "path", "query", "fragment"])

ParsedUrl = namedtuple("ParsedUrl", ["url", "query", "fragment"])
from sentry_sdk.utils import parse_url

# unit tests

def test_standard_url():
    url = "http://example.com/path?query=value#fragment"
    result = parse_url(url, sanitize=False)
    assert result.url == "http://example.com/path"
    assert result.query == "query=value"
    assert result.fragment == "fragment"

def test_standard_url_with_sanitization():
    url = "http://example.com/path?query=value#fragment"
    result = parse_url(url, sanitize=True)
    assert result.url == "http://example.com/path"
    assert result.query == "query=SENSITIVE_DATA_SUBSTITUTE"
    assert result.fragment == "fragment"

def test_url_with_username_password():
    url = "http://user:[email protected]/path?query=value#fragment"
    result = parse_url(url, sanitize=False)
    assert result.url == "http://example.com/path"
    assert result.query == "query=value"
    assert result.fragment == "fragment"

def test_empty_url():
    url = ""
    result = parse_url(url, sanitize=False)
    assert result.url == ""
    assert result.query == ""
    assert result.fragment == ""

def test_url_without_scheme():
    url = "example.com/path?query=value#fragment"
    result = parse_url(url, sanitize=False)
    assert result.url == "example.com/path"
    assert result.query == "query=value"
    assert result.fragment == "fragment"

def test_url_with_unusual_scheme():
    url = "ftp://example.com/resource"
    result = parse_url(url, sanitize=False)
    assert result.url == "ftp://example.com/resource"
    assert result.query == ""
    assert result.fragment == ""

def test_url_with_special_characters_in_query():
    url = "http://example.com/path?query=value%20with%20spaces"
    result = parse_url(url, sanitize=False)
    assert result.url == "http://example.com/path"
    assert result.query == "query=value with spaces"
    assert result.fragment == ""

def test_multiple_query_parameters():
    url = "http://example.com/path?param1=value1&param2=value2&param3=value3"
    result = parse_url(url, sanitize=False)
    assert result.url == "http://example.com/path"
    assert result.query == "param1=value1&param2=value2&param3=value3"
    assert result.fragment == ""

def test_internationalized_url():
    url = "http://例子.测试/路径?查询=值#片段"
    result = parse_url(url, sanitize=False)
    assert result.url == "http://例子.测试/路径"
    assert result.query == "查询=值"
    assert result.fragment == "片段"

def test_large_number_of_query_parameters():
    url = "http://example.com/path?" + "&".join(f"param{i}=value{i}" for i in range(1000))
    result = parse_url(url, sanitize=False)
    assert result.url == "http://example.com/path"
    assert result.query == "&".join(f"param{i}=value{i}" for i in range(1000))
    assert result.fragment == ""

def test_malformed_url():
    url = "http:///example.com"
    result = parse_url(url, sanitize=False)
    assert result.url == "http:///example.com"
    assert result.query == ""
    assert result.fragment == ""

def test_url_with_only_fragment():
    url = "http://example.com/path#fragment"
    result = parse_url(url, sanitize=False)
    assert result.url == "http://example.com/path"
    assert result.query == ""
    assert result.fragment == "fragment"

def test_url_with_only_query():
    url = "http://example.com/path?query=value"
    result = parse_url(url, sanitize=False)
    assert result.url == "http://example.com/path"
    assert result.query == "query=value"
    assert result.fragment == ""

def test_url_with_empty_query_and_fragment():
    url = "http://example.com/path"
    result = parse_url(url, sanitize=False)
    assert result.url == "http://example.com/path"
    assert result.query == ""
    assert result.fragment == ""